VOLUME 10, ISSUE 4, APRIL 2021

Abstract: Visual feature extraction is widely used in many of computer vision algorithms such as object detection, stereo matching, image matching, and Visual SLAM. Real-time implementation of visual feature extraction suffers from long latency, and heavy computation. GPUs are commonly used to accelerate computationally intensive applications, but they are power hungry devices and, they have a fixed level of parallelism. To achieve processing optimization for such computationally intensive applications, FPGA, and ASIC are more efficient. In this work, an efficient and optimized FPGA architecture is designed to accelerate the computation of visual feature extraction. FAST and BRIEF algorithms are used in this system because they are simple and efficient when working with mobile and embedded systems. The system uses different frequency clocks for input pixels streaming and for processing to prevent stall cycles and achieve high speed. Multi pixels are processed per single clock cycle using optimized parallel and pipelined architecture. The proposed architecture is implemented on TERASIC DE2-115 FPGA board and tested with different image sizes and achieved very high throughput. The system can detect features up to 1000 frames per second for grayscale images with the size of 480 ×480 pixels.

Keywords: feature extraction, Parallel image processing, computer vision , FPGA, real-time processing.

Abstract: The creation of automatic text summaries is the result of the execution and application of text mining. Its complexity consists in finding the most relevant information, different methods or perceptions have been developed through time for this matter. Research shows a detailed analysis of the execution, presenting the most representative characteristics of the automatic extractive summaries generation, being this one, one of the methods developed in the recent years.

Keywords: Text Mining, Extractive Text Summarization, Abstractive Text Summarization, Information Retrieval.

Abstract: In recent years, a substantial growth has been experienced in the mobile phone market. A cumulative of 432.1 million mobile gadgets has delivered in the second quarter of 2013 with an increment of 6.0% year over year. As the acquisition of cellphone gadgets has become common, Short Message Service (SMS) has developed into a multi-billion-dollar business. A rush in the quantity of unwanted business notices sent to cell phones utilizing text messages has additionally expanded due to the increased popularity of mobile platforms. This rise attracted attackers, which have resulted in SMS Spam problem. This study presents model for SMS spam filtering classification using Deep Machine Learning Techniques. The system uses the deep machine learning model(MLPNM) in tensorflow and keras framework to classify SMS Message dataset containing 5574 messages. The dataset was read from directory using the pandas.read_csv function. The dataset was cleaned to make sure there are no null values present. The Deep learning model was built with a total of three dense layer with takes in 8672 inputs and 1 output, a batch size (batch size equals the total dataset thus making the iteration and epochs values equivalents) of 32 and epoch value of 50. This trained model was saved and exported into web for easy access and testing with the help of python flask, so that users make various input SMS message. Bootstrap framework (HTML and CSS) was use to design the Front End, while for the Backend, python programming language was use. The results of the test showed accuracy of 99.82% of all input message classified as either ham(legimate) or spam to verify if it’s actually a Spam SMS message or a Ham (Legitimate) SMS spam messages. Keyword: SMS, Spam, Deep Learning, Tensorflow, Keras.

Abstract: In this study, research work is done in the field of image enhancement by using the SVD technique. In my study, I took into consideration CT-scan lungs images of COVID-19 patient for carrying out my work and the SVD technique used in it. The main objective of this whole study is to obtain an improved enhanced image by applying the SVD technique and also computing image enhancement parameters such as root mean square error (RMSE), percentage fit error (PFE), mean absolute error (MAE), correlation (CORR), signal to noise ratio (SNR), peak signal to noise ratio (PSNR), mutual information (MI), and quality index (QI), a measure of structural similarity (SSIM). An algorithm is developed for image enhancement of biomedical images. On the image taken into consideration, the SVD technique is applied.

Keywords: CT-scan, SVD, Image quality, Decomposition Matrix.

Abstract: Electrocardiogram (ECG) is an intermittent sign, which mirrors the movement of the heart. From ECG a great deal data is gotten for typical and obsessive physiology of heart. The ECG signal is non-fixed in nature and extremely hard to dissect. Clinical perception takes long time and the sign is non-fixed. This paper presents a convolutional neural network algorithm for electrocardiogram signal classification. This system uses a ECG dataset which was downloaded from kaggle.com. The dataset signals were preprocessed to make sure that each segment conforms to a heartbeat. This dataset was read into the jupyter notebook by using pandas.read_csv function. The dataset was made into two, which are the training data and the testing data. After successful reading of the data signal from directory and solving of the in balance problem by means of data augmentation, the proposed model was trained using a convolutional neural network(CNN) algorithm with a total hidden layers of six, hiden size of 128, batch_size of 96, and number of epoch to be 10. After successful training, we had an accuracy of 99% at an epoch level of 10.

Keywords: Deep Learning, Electrocardiogram, ConvolutionalNeural Network, Heart Beat, Signal

Abstract: A protected information bunch sharing and contingent spread topic with multi-proprietor in distributed computing, with in which information proprietor will share non-open information with a gathering of clients through the cloud in an exceedingly secure way, and information communicator will share the information to a shiny new group of clients if the properties fulfill the entrance approaches inside the ciphertext. We tend to extra blessing a multiparty get to the executives system over the dispersed figure text, inside which the information co-proprietors will attach new access approaches to the figure text because of their security inclinations. In addition, 3 strategy total ways, along with full grant, proprietor need and greater part license, are given to explain the protection clashes drawback brought about by totally unique access arrangements. Numerous plans are as of late progressed for putting away data on different mists. Conveying information over totally unique distributed storage providers (CSPs) precisely gives clients a positive level of information run the board, for no single reason for assault will release all the information. Nonetheless, impromptu appropriation of information pieces will cause high data uncovering even though misuse numerous mists. An effective stockpiling plan age algorithmic principle upheld bunch for disseminating data lumps with least information escape over numerous mists. So to give greater security to client's information we will partition our information into different squares and transfer those squares onto numerous mists. As each square is on various clouds, if there is assault on any cloud the rest of the squares which are put away on different mists will be protected, this is the means by which we are giving greater security to client's information.

Keywords: Data Sharing, Conditional Proxy re-encryption, Attribute-based encryption, Privacy Conflict, System Attack ability, Remote Synchronization, Distribution and Optimization

Abstract: Data security in this digital age of human era is the important motivation behind this research work. As the utilization the online application becomes high, Trails of digital data’s are always available to track a human behaviour, like his/her birthday, school of study and profile pic etc. It is unavoidable to be in online maximum of time, so strong fool proof data security mechanism without a large hardware trade-off is much needed..

Abstract: Base stations (BSs) are essential in cellular networks. Lack of access to reliable electricity in mobile communication systems is a major economic and environmental concern for service delivery in Tanzania. Mobile network operators (MNOs) use diesel generators (DG) to power their BSs which are costly and high greenhouse gases (GHG) emissions. In this paper, we investigate challenges hindering the use of renewable energy (RE) by MNOs. We provide a techno-economic analysis for using a hybrid power system (HPS) comprising of DG and RE. In techno-economic analysis, we considered solar, wind, battery, and DG in different configurations. The systems were simulated in HOMER to get the optimized model suitable for the BS sites. Results show that the solar/DG/Battery and the solar/wind/DG/Battery provide optimal solution susceptible to satisfy the needs. Although HPS suffers from the high initial cost, the results are satisfactory. The analysis indicates a reduction of net present cost (NPC) by 54%, cost of energy (COE) by more than 50%, and the GHG emissions for about 88%.

Keywords: Off-grid base station, Net present cost, Greenhouse gases emissions, Mobile communication systems, Hybrid Power System, and Renewable energy

Abstract: The change detection in remote sensing images remains an important and open problem for damage assessment. A new change detection method for LANSAT-8 images based on Homogeneous Pixel Transformation (HPT) is proposed. Homogeneous Pixel Transformation transfers one image from its original feature space (e.g., gray space) to another feature space (e.g., spectral space) in pixel-level to make the pre-event images and post-event images to be represented in a common space or projection space for the convenience of change detection. A multi-value estimation method with the noise tolerance is produced to determine the mapping pixel using K-nearest neighbours technique. Once the mapping pixels of pre-event image are identified, the difference values between the mapping image and the post-event image can be directly generated. Then the similar work is done for backward transformation to combine the post-event image with the first space, and one more difference value for each pixel will be generated. Then, the two difference values are taken and combined to improve the robustness of detection with respect to the noise and heterogeneousness of images. (FRFCM) Fast and Robust Fuzzy C-means clustering algorithm is employed to divide the integrated difference values into two clusters- changed pixels and unchanged pixels. This detection results may contain few noisy regions as small error detections, and a spatial-neighbor based noise filter is developed to reduce the false alarms and missing detections. The experiments for change detection with real images of LANSAT-8 in Tamilnadu are given to validate the percentage of the changed regions in the proposedmethod.

Abstract: Underwater images often suffer from color distortion and low contrast, because light is scattered and absorbed when travelling through water. Such images with different color tones can be shot in various lighting conditions, making restoration and enhancement difficult. There are several algorithms available which is helpful in restoring the underwater images back to the actual scene. In this project we analysis three different underwater image enhancement algorithms such as DSPV, AACP, G-GIF for restoring both the underwater images as well as videos. Also, the experimental results of these three algorithms are analysed for the better understanding of the performance. The image restoration aims to recover a degraded image using a model of the degradation and of the original image formation.

Keywords: Difference Structure Preservation Value, Graphical User Interface Development Environment, Adaptive Attenuation Curve Prior, Mean Square Error, Mean Square Error, Just In Time, Remotely Operated Vehicle

Abstract: Government has been working on most of the schemes which were introduced but yet many of these are dumped by the authorities who brings up instruction that makes many of the citizens not to be eligible for the scheme, thereby for many ordinary citizens to apply the scheme, track it from time to time and to know whether he is entitled to appraise their opportunities regarding to the scheme rejected by the official, he pretends to need a secured system with transparency in it. The process for utilization of numerous schemes headed by the government regardless to many of the panchayats is compiled to form a software application named Government Scheme Management System. The supervision of the ventures of the schemes guided by the government comes under the Government Schemes Management System while its most superior supervision is to provide a lot of great effort for the proper utilization of contrasting schemes in a transparent habitat. The tracking of actual ventures that comes under process within the panchayats or higher level at any point of time by the administrators helps the system to keep a regular and clear check on the track of status of the user's application. The Management of important piece of information in a highly secured manner for the authenticating the users at numerous levels id guided by the system as well as the novice user also does not feel any operational barriers due to a great GUI introduced by the government in this system. Scheme wise details report, Panchayats wise details report, User wise report are some of the various reports mainly focused on designing by the system which are requested by the users as well as higher authority. When the user applies for a scheme, his details will be stored in the database and sent to the panchayat for verification. Panchayat people conduct a physical verification and send their remarks to the DDO who would write his comments. These details are sent to final approving authority and help him to approve or disapprove the person for the scheme. The same details can be viewed by the user so that the user would get a clear picture of what is happening from time to time.

Keywords: Web Based E-governance

Abstract: In the present scenario due to Covid-19, the need for face mask detection applications, temperature detection and hand sanitizing are now in high demand for Railway Entrance, Airport Entrance, Office Entrance, Museums and Amusement Parks, Other Public Places and enterprises to ensure safety. These steps are now done in manual way by which the personnel may get in contact with the other personnel while sanitizing and checking temperature might not be accurate. To mitigate the problem, this research work introduce an affordable IoT-based solution aiming to increase Covid-19 entrance safety, covering several relevant aspects: Contactless temperature sensing, Mask detection, Automatic hand sanitizing. Contactless temperature sensing subsystem relies on Raspberry Pi using temperature sensor, while mask detection performed by leveraging computer vision techniques on camera-equipped Raspberry Pi, then the automatic hand sanitizing is achieved by the DC motor connected with the PIR sensor and Raspberry Pi. Any person without temperature check, hand sanitizing and mask scan will not be provided entry. Only person having the conditions satisfied by the system is instantly allowed inside, else the buzzer will alert the security about the situation, if any violation of the condition is found. From the simulation results, it is clearly observed that the proposed method has high accuracy compare to the existing methods. Thus the system provides a 100% automated system to prevent the spread of Covid-19.

Keywords: Covid-19, Contactless temperature sensing, Mask detection, Automatic hand sanitizing, Raspberry Pi, DC motor, PIR sensor.

Abstract: The objective of this journal is to compare the efficiency between these two algorithms, the simple round robin and intelligent round robin algorithms. In real time algorithm, round robin plays a significant role to be use in embedded systems. Here we compare the number of context switching, average turn around time, average waiting time between the two. Intelligent round robin algorithm, is an algorithm with dynamic time quantum. The quantum is calculated and the quantums can be different between tasks. While in simple round robin algorithm, the quantum is the same for every tasks. This comparison proves that intelligent round robin algorithm is more efficient, with lower context switching and lower average turn around time and lower average waiting time. There by this increases the system throughput.

Keywords: Round Robin Algorithm, Intelligent Round Robin Algorithm, Average Turn Around Time, Average Waiting Time, Quantum

Abstract: Restaurant billing system project is a web application, which is going to manage the ordering of food items. It uses HTML as its frontend and PHP as its backend. It is going to allow the user to select the desired items to be ordered. This website then calculates the overall pricing, CGST, SGST, the grand total or total amount to be paid. And finally produce it to the user. To make this project further more interesting and attractive, CSS and JavaScript are going to be used. In a whole, this website can used by customer or administrator to place an order or to make a bill.

Keywords: Restaurant Billing website,Online Billing,online menucare, restaurant

Abstract: Cloud computing provides high performance, accessibility and low cost for data storing and sharing, provides a better consumption of resources. In cloud computing, cloud services providers compromise an abstraction of infinite storage space for clients to mass data. Electronic health record possesses the patient’s medical details and their health history. The data owner has the capability to encrypt files and limiting access to only authorized data user.Data owner could add the users and distribute key for the verification of user.Key will be generated using Random Key Generation procedure. AES is implemented to provide security parameters to encrypt the data before store on cloud. We provide Role based authentication for medical data access.

Keywords: Medical Record Sharing, Advance Encryption Standard, Role Based Access Control, Attributes Based Access Control.

Abstract: Security and safety is increasing day by day and with improvements brought in the past decade and innovations to bring comfort in our lives. In today's world technology has become a part of an integrated part of the society and therefore the security of an individual's home, office or their organization had to be considered with upmost priority. Smart Receptionist with a smart lock system is therefore mainly designed and developed for security system purpose. The smart security system is used in situation to see visitor when the main door of office or organization is closed. The purpose of this system is to control the door lock using RASPBERRY PI 3. In this system whenever person enters the office door, image of person is captured by CAMERA MODULE which is compared with database. If the persons images is matched with the database the SOLENOID LOCK opens, but when the image is unidentified it Emails the owner requesting to allow or deny the access.

Keywords: Raspberry pi 3, Camera module, Email, Solenoid lock.

Abstract: Today, social media platforms are being utilized by a gazillion of people which covers a vast variety of media. Among this, around 192 million active accounts are stated as Twitter users. This discovered an increasing number of bot accounts are problematic that spread misinformation and humor, and also promote unverified information which can adversely affect various issues. So in this paper, we will detect bots on Twitter using machine learning techniques. A web application where we can verify if the account is a bot or a genuine account. We analyze the dataset extracted from the Twitter API which consists of both human and bot accounts. We analyze the important features like tweets, likes, retweets, etc., which are required to provide us with good results. We use this data to train our model using machine learning methods Decision Trees and Random Forest. For linking our model with the web content, we used the flask server. Our result on our framework indicates that the user belongs to a human account or a bot with reasonable accuracy.

Keywords: Machine learning, Twitter, bot detection, Random forest.

Abstract: For maintenance of the grid and reliable to be prepared for the exponential growth of electrical vehicles in the future. The optimal allocation infrastructures, lack of regulations and market rules and network codes devolvement have low visibility on distribution grid. It consist of communicational and computational barriers. A small capacity bidirectional half bridge DC/DC converter is designed to function the harmonics DC to compensate the active power filter (DCAPF) suppress the harmonic current getting into the battery packs in the single stage structure. Finally, both simulation and experimental results are carried out to validate the low order harmonic current compensation effect. The simulation model developed in a MATLAB Simulink tools and verified with corresponding factors. Based on that hardware Prototype is designed.

Keywords: Batterycharger,constantcurrent(CC),constantvoltage (CV), state of charge(SOC),

Abstract: Biometrics finds a lot of application in the modern day security aspects whether it may be in industrial sector, defense sector or in domestic sectors. In this world, without biometrics, it is very difficult to incorporate the security measures in any organization. Hence, personal identification can be very important problem in any bio-metric recognition scenarios. In this proposed technique, this biometric recognition using retinal images is done. The retinal images are preprocessed and features are extracted using image processing and KNN classifier is trained with 66 recognized images and 35 unrecognized images The proposed algorithm is tested with 20 images and the output represents if the input image is a recognized one or not.ROC curve is plotted. This accuracy of the algorithm can be extended with more number of training images. This method of biometric recognition using retinal images finds more use in this Covid pandemic situation compared to the fingerprint biometric recognition system.

Keywords: Bio-metric recognition, Retinal images, KNN classifier

Abstract: Arcade Games Website is an online website where seven arcade games are brought together on a webpage, also it has a chat box feature for communication. In the high score part, one can find the global lead board of games hosted on the website. There is also a covid stats chart where 202 countries’ live covid stats are displayed.

Keywords: Online, Game, Website, Arcade Games

Abstract: Augmented reality (AR) is an interactive experience of a real-world environment where the objects that reside in the real world are enhanced by computer-generated perceptual information, sometimes across multiple sensory modalities , including visual, auditory, haptic, somatosensory and olfactory. AR can be defined as a system that fulfils three basic features: a combination of real and virtual worlds, real-time interaction, and accurate 3D registration of virtual and real objects. The overlaid sensory information can be constructive (i.e. additive to the natural environment), or destructive (i.e. masking of the natural environment).This experience is seamlessly interwoven with the physical world such that it is perceived as an immersive aspect of the real environment. In this way, augmented reality alters one's ongoing perception of a real-world environment, whereas virtual reality completely replaces the user's real-world environment with a simulated one. Augmented reality is related to two largely synonymous terms: mixed reality and computer-mediated reality. Augmented reality, the technology of overlaying graphical objects on the real world, is radiating everywhere, and all industries are trying to shine by leveraging this sophisticated real-time piece of advancement. One such niche is the automotive sector. This is one of the fastest expanding verticals whose market share falls in the category of trillion dollars.

Keywords: Augmented Reality, Real-time interaction , virtual reality.

Abstract: Gardening can be a hobby as well as an opportunity to begin agriculture at a micro level. There might be many issues one might be facing related to gardening like how to check the environment conditions, irrigation, maximizing the produce etc. Concepts like Artificial Intelligence and Internet of Things (IoT) have proved to be of much more assistance to today’s consumers. Keeping this in mind, we are proposing the following set of ideas:(1) Create an automated irrigation system suitable to small scale gardening which can scale up to traditional farms. (2)Create an array of sensors which track different gardening and weather condition like soil moisture, soil PH etc. (3) Create a web-app so that the gardener can see all the data collected by the sensors and make systemic changes to his/her gardening methods. (4)Create an image processing system for plant disease detection by taking the images of the leaves of the specific plant as input.

Keywords: Gardening, IoT, NodeMCU, Deep Learning, Image Processing

Abstract: As a means of contact for personal and professional use, emails are commonly used. Information shared that emails, such as banking information, credit reports, login details, etc., is often sensitive and confidential. This makes them useful for cyber criminals who are able to exploit the data for malicious purposes. Phishing is a technique that fraudsters use to acquire confidential data from individuals by claiming to be from proven sources. The sender will persuade you to provide personal information under bogus pretences in a phished email. Phishing website detection is an intelligent and efficient model focused on the use of data mining algorithms for classification or association. In order to identify the phishing website and the relationship that correlates them with each other, these algorithms were used to identify and characterize all rules and factors so that we detect them by their efficiency, accuracy, number of generated rules and speed. The proposed system integrates both classification and association algorithms, which optimize the system more effectively and faster than the current system. The error rate of the current system decreases by 30 percent by using these two algorithms with several protocols, so that the proposed system creates an effective way to detect the phishing website by using this approach. While there is no device that will detect the entire phishing website, it can create a more effective way to detect the phishing website using these methods. Spam emails can be only annoying but also dangerous to consumer. People using them for illegal and unethical conducts, phishing and fraud.

Keywords: Machine learning, Natural Language Processing (NLP), Feature extraction, Feature selection.

Abstract: A dozen species of locusts (Orthoptera: Acrididae) are a major threat to food security worldwide. Their outbreaks occur on every continent except Antarctica, threatening the livelihood of 10% of the world’s population. The locusts are infamous for their voracity, polyphagy, and capacity for long-distance migrations. For effective control, the insects need to be detected on the ground before they start to develop air borne swarms. Detection systems need to determine pest density and location with high speed and accuracy. Location of the swarms on the ground then enables their control by the application of pesticides and bio-pesticides. This work proposes a locust species recognition method based on Resnet50 -convolutional neural network (CNN). We experimentally compared the proposed method with other the state-of-the-art methods on the established dataset. Experimental results showed that accuracy of this method reached higher than the state-of-the-art methods. This method has a good detection effect on the fly species recognition.

Abstract: Every year, it is estimated that 1.25 million people die in road accidents around the world. Humans' failure to heed road signs and obey the law is a significant cause of accidents. To avoid this issue, a signboard detection system has been implemented. This device would be useful in identifying unique domains such as classrooms, traffic signals, colleges, hospitals, offices, and so on, as well as potentially saving many lives. The creation of a low-cost prototype of a miniature self-driving car model using easy and readily available technologies is presented in this paper. To achieve vehicle automation, the Raspberry Pi controller and H-bridge drive two DC motors in this prototype. Intelligent systems have used technologies such as sonar sensors, image processing, computer vision, and machine learning. To solve the problem, we propose implementing a self-driving vehicle that employs a pattern matching technique.

Keywords: Raspberry Pi, Lane detection, Traffic light detection.

Abstract: Extracting specific information from large volumes of text document possess a tremendous challenge. Medical records tend to have information glut problem (Masses of continuously increasing information) resulting in delay of early detection of diseases. This research concentrates on modeling a domain-based technique for knowledge acquisition and text mining in a database. The Term Frequency-Inverse Document Frequency (TF-IDF) was used to extract the entity's text features and the frequency of the terms is rescaled in TF-IDF by considering how often the words appear in all the documents. Random Forest Classifier (RFC) has been used to model the class of objects associated with symptoms’ illnesses to facilitate accurate prediction of likely diseases the knowledge -base and text mining system calculates the possibilities of diseases according to given symptoms and displays the probabilities of disease accuracy.

Keywords: Domain Based, Knowledge Acquisition, Text Mining, TF-IDF,RCF.

Abstract: This project is significant in various ways because in today's world, everyday many lives are affected because the patients are not timely and properly operated. Also, for real time parameter values are not efficiently measured in clinic as well as in hospitals. Sometimes it becomes difficult for hospitals to frequently check patient’s conditions. Also, continuous monitoring of ICU patients is very difficult. To deal with these types of situations, our system is beneficial. Our system is designed to be used in hospitals and homes also for measuring and monitoring various parameters like temperature, ECG, heart rate, pulse rate. The results can be recorded using Arduino. Also, the doctors can see those results on android app. The system will also generate an alert notification which will be sent to doctor. Our system is useful for monitoring health system of every person through easily attach the device and record it. In which we can analysis patient’s condition through their past data, we will recommend medicines if any emergency occurred through symbolic A.I.

Keywords: ECG, Heart rate, Temperature, Pulse rate.

Abstract: The aim of the paper is to focus on important aspect of the Diseases which is affecting a Huge Amount of Population today i.e Dementia and building an Android application that could ease the everyday life of a person affected by Dementia disease. It is hoped that this research will analyze that specially created apps and existing assistive software can be used to decrease the symptoms and improve cognition of adults suffering from dementia related diseases. It addresses the problem of increased dependency of Dementia patients on caregivers and helping them in a Techie way as each person on Earth owns a Mobile Phone specially if you consider India as India is ranking among top countries wherein its population is suffering from this disease.

Keywords: Dementia, Mobile Phone, Caregivers.

Abstract: This document aims to computerize the hospital reception department to develop software that is easy to use, simple, fast, and profitable. Healthcare is so fascinating for the social order. Generally, Hospital Management Information System (HMIS) is a computer-based system that has the potential to coordinate all information to enable healthcare carriers to do their works correctly and efficiently. According to the use of these systems across the globe, requires a strong need to apprehend such systems and their competencies. HMIS has the objective of eliminating the stock of improper information, erroneous reports, excess time in storage, dispensation, and recovering information handled by the prevailing hospital data system to improve the general efficiency of the medical institution. This system offers the benefits of streamlined operations, improved management and control, excellent patient care, tight cost control, and increased profitability.

Keywords: Hospital management information system (HIMS), Healthcare, Globe, Hospital, Dispensation, Patient care

Abstract: Here our research work is on scheming and conception of Hospital Management System (HMS). A medical institution requires excellent data and information administration to operate excellently and efficiently. It's an irony to mention that a lot of establishments, institutions, government associations have become significantly curved into the consumption of database systems for their accomplishments in the hospital especially. This work objective at rising an upgraded hospital information management system via a functional approach. A well-organized HMS will be liable to maintain patient data and its management is accessible in the work. The system uses JAVA as interface software, an object-oriented programming language that is linked to the management software. The HMS can be entered with a username and password. It is accessible to both an administrator and a receptionist. Only they can add data to the database. The data can be easily restored. The information is properly protected for private use and makes statistics processing very fast.

Keywords: HMS-Hospital Management System, Administrator, Medical Institution, Object-oriented programming

Abstract: Nowadays, many organizations do the business form one level to another level. They do the business through the different agents and organizations. With the increment of the business level the storage and transmission of the data via one place to other also increased so in the middle may be any user can leak the data. Our main focus is to detect the guilt agent who has leak the Sensitive data. Information leakage can be referred to as the unofficial move of arranging data from a server area to the outside world. In those papers, it describes the appropriation model for data leakage counteractive action and chooses a document allotment plan with minimal cover between the sets of records of the clients, as a result, it can detect leaked sources with high probability. Sensitive information in organizations may be company internal policies, money related data, individual charge card information, and organization-related data, this type of sensitive data can be a leak by a malicious user. Information leakage leads to a major issue for various organizations. In some Data Leakage Detection model used the ‘fake objects’ which are store in the server database. The fake objects help to identify the user who has leaked the file. Every user has a probability to leak the file which probability is called the guilt probability. Those users who have the probability to leak the file is known as the guilt probability. Many models of detection of the data leakage focus on the fake object which is including with the database to find out the leaker.

Keywords: data upload, data download, unauthorized access, data leakage, malicious user, Role base access control.

Abstract: Online Food Ordering App is an application designed primarily for use in the food delivery industry. This system will allow hotels and restaurants to increase scope of business by reducing the labor cost involved. The system also allows to quickly and easily manage an online menu which customers can browse and use to place orders with just few clicks. Admin employees then use these orders through an easy to navigate graphical interface for efficient processing. The online food ordering system provides convenience for the customers. This system increases the takeaway of foods than visitors. The online food ordering app set up menu online and the customers easily places the order with a simple click. Also, with a food menu online you can easily track the orders, maintain customer s database and improve your food delivery service. This system allows the user to select the desired food items from the displayed menu. The user orders the food items. The user’s details are maintained confidential because it maintains a separate account for each user. An id and password are provided for each user. Therefore, it provides a more secured ordering.

Keywords: online food ordering app, menu, register, online

Abstract: This study presents a method to identify articles written in Vietnamese on the internet that contain reactionary viewpoints against the Government of Vietnam and the leadership of the Communist Party of Vietnam. These articles often comprise various errors such as spelling mistakes, typos, misplaced punctuation marks, new and unfamiliar “terms” to Vietnamese people, etc. Hence, it is not appropriate to apply grammatical and vocabulary analysis methods. We propose to use the word orders in triplet form (Subject, Verb, Object) and its variables including doublet form (Subject, Predicate, null) or (Verb, Object, null), and singulet form (Subj, null, null) to screen these articles in accordance with the following principle: if one article has at least one sentence containing the elements of such word orders, the article will be considered as containing reactionary viewpoints. The original triplets are established based on the training corpus (dataset), and then extended using the synonyms in VietWordNet. The extension of triplets is able to increase the accuracy of this algorithm significantly. The Program can help professional security units to reduce human resources and enhance operational effectiveness.

Keywords: document analysis, document classification, reactionary viewpoint, triple, edge triplet, triplet finding, Spark GraphX, VietWordNet.

Abstract: Our world is turning into an e-world. A lot of data is created daily. The digital info that we share around needs to be protected by the unwanted craps, the intruders who gets into the database and make issues. Cryptography provides the methods through which one can safeguard our data. And in this paper, we are providing review on the types of modern cryptography and its various terminologies.

Keywords: cryptography, modern cryptography, safeguard, database.

Abstract: The future depends on what you do today. So today if one is not clear about how and what right path he/she needs to take to balance present and future then it's a matter of concern. Competition in today's education and career world is at peak. Importance of correct guidance for different colleges and jobs related queries are other fundamentals for better future. Nowadays students are often facing a dilemma in deciding to choose a career in their life. Students get confused about their career which is the defining point of their life. There are several factors that influence the students while choosing their career path such as their personal aptitude, educational achievements and their environment. From completing their first degree or under graduation students are always in some sort of difficulty when it comes to choose a career path which may suit their skill and potential the best. Our system helps in guiding the students for choosing the appropriate field. For that we will be taking their information which will mainly include the user’s qualifications, interest area and other academic related data. On the bases of which it will suggest a list of colleges so, it will make it a bit easier for students. Also it is important to be aware of the notified vacancies in time so that aspirants can apply within the given time frame and can prepare for the job as well. Teacher also needs a stable and easily accessible platform to search for vacancies in different schools and colleges as per the data provided. Our system helps in searching the vacancies around on the bases of one’s qualification and teaching experience. It even filters the data according to their subject and location which will make it easier to the user. In a nutshell our project focuses on helping students and teachers in finding best possible colleges, courses and jobs around as per their situations and demands.

Keywords: Career guidance: colleges, job opportunity, Client Server, Colleges, Job opportunity, Web Applications, Data Mining.

Abstract: The main aim of the mess is to provide clean and fresh food to the students/employees of the organization. In Today’s world the entire Mess Management and costing calculations are done manually till date. It is very time consuming & increases the chances of performing calculation mistakes. Thus, there arises a need to create software that will make the entire Mess Management an automated system. This software will be useful to any school/college hostel or in general to any institute maintaining a mess. The Mess Management System helps the user to access all the functionalities of the mess without having to visit the mess physically and to apply for leave. It enables the admin to view the inventory and access guest details. This application is free of cost for the users. Individuals who wish to use any functionality of the mess can simply log in to the app and have everything on their fingertips. It uses the internet to update all user queries and put it across to the admin. Using the information provided by all the users the admin can take decisions and the inventory for the mess can be managed. The aim of this android based mobile application project is to offer comprehensive information portal about hostel mess. In this system users can download the app on their Smartphone and then they can access the functions of the mess. They can apply for leave and check the menu. They can also access their account information.

Keywords: Mess Management, inventory,Information Portal.

Abstract: In this Paper we implemented and design Face recognition play a vital role in variety of applications from biometrics, surveillance, security, identification to the authentication. In this paper we design and implement a Bank locker security system where access people whose faces are available in the training database. First, we are going to detect the face by detecting the human motion. Then face recognition is performed to determine the authority of the person to enter the sensitive area. At the same time, we track the coordinate of detected motion. Failing to recognize the face finally passes the estimated coordinate to anesthetic gun for targeting the intruder automatically. Experimental results demonstrate the effectiveness of proposed Bank locker security system in order to restrict the unauthorized access and enhanced reliability by use of Liveness face recognition.

Keywords: Face Detection, Feature Extraction, Tracking, Machine Learning.

Abstract: Good Health is a secret of every human being. Since the very beginning, Health is a matter of great concern. Some have to, without a choice, maintain a healthy lifestyle by taking medicines. Many patients find it difficult to take medicines at a proper time due to various reasons such as forgetfulness, busy schedule, old age, etc. This happens most commonly with the people taking medicines daily which results in medical non-adherence. Medical Non-adherence is a very serious issue as it can lead to various health-related problems. The advancement in mobile technology has enabled various techniques to solve these types of problems by designing and developing an application which patient will find it easy to carry along. In this paper, we aim to build an Android-based application, that will cover major features such as Medicine Reminder, Medicine Restocking Alert, Searching Hospitals, Medicals, Doctors in the vicinity, BMI Calculator, Notes, Caretaker Information, First Aid/Health Tips, Alarm System, etc. This system has a rich GUI and easy navigation which can be used by people of every age. This app will have a positive impact on people as it will act as a companion that can display reminders and notify the user to take the pills on time supporting Medical adherence and improving health.

Keywords: Medicine Reminder, Android App, Medication Adherence, Alarm System.

Abstract: -Our colleges have a large number of students who pay all the college fees through cash deposits, electronic funds transfer or bank drafts to the college accounts in specific bank branches. These methods of paying fees have not been efficient enough especially during periods of tests and examinations when most of the students are paying fees to meet the requirements for entering examination rooms. The process of paying fees is characterized by long queues, too much waiting by students and congestion at banks where payments are made. This has always resulted in students missing to sit for their tests and/or examinations while they are queuing to make payments. It was upon such background that the researchers embarked on the project to develop of an alternative system that enables online fees payment by students and their sponsors. With the use of questionnaires, interviews, observation and document reviews, data was collected from project stakeholders and analysed. Data flow diagrams and Entity relationship diagrams were used to accomplish system analysis and design. The system was implemented using PHP, MySQL database server, Hypertext Pre-processor, Hypertext markup language, Cascading style sheets and JavaScript. System testing and validation was also done by allowing users of the system interact with it using test data. Findings showed that most of the students were unsatisfied with the current modes of paying fees to the university and agree that an online fees payment system can improve the process of fees payment. The result of the project was an online fees payment system for our college and researchers recommend the college to implement the system that provides relief of the long-endured problems of the current modes of payment at the colleges.

Keywords: - System Administration, Online Fees Payment, Educational Institutes, Graphical User Interface

Abstract: Cyber related crimes are increasing enormously across the world. Hacking and viruses are used to steal important personal information. Understanding cybercrime is essential to understand how criminals are using the internet to commit various crimes and what can be done to prevent these crimes from happening. The Internet is a place saturated with information and over the years, information has become more easily accessible than ever before. How much information that is chosen to be shared on the internet should be carefully considered. A simple post to any social media site could give out more personal information than originally intended. Cyber security is a priority with the growing use and ease of access of the internet. If an internet user is not careful about the information given over to cyberspace, the user’s identity could easily be stolen or their finances drained. Cyber security is important not just to the government but also to the average user. The field is of growing importance due to the increasing reliance on computer systems in most societies. Computer systems now include a very wide variety of "smart" devices, including smartphones, televisions and tiny devices as part of the Internet of Things (IoT) and networks include not only the internet and private data networks, but also Bluetooth, Wi-Fi and other wireless networks. Cybercriminals are attacking the computer networks and systems of individuals, businesses and even global organizations at a time when cyber defences might be lowered due to the shift of focus to the COVID-19 health crisis. This paper will cover different kind of cybercrimes, statistics on cybercrime, cyberattacks, COVID-19 impact on cybercrimes and information on what the average internet user can do to protect themselves from falling victim to cybercrimes.

Keywords: Cybercrimes, Cyber Security, Cyberattacks, COVID-19 impact on cybercrimes.

Abstract: Data security and privacy are rapidly becoming the predominant issue that forces small and medium business organizations to migrate their data from on-site to the cloud storage facilities. The recent apprehension regarding cloud storage arises mostly from the very fact that currently most of the cloud storage service providers are having unlimited access and therefore the opportunity to read the client’s private and sensitive data. There is also a concern that such service providers have so far been unable to convey reasonable surety and confidence that whatever data or information they store on their cloud’s infrastructure remains free from unauthorised or unwarranted access and modification in the files. Appreciably, some have managed to use either symmetric and asymmetric cryptography techniques to realize some level of security on cloud storage. This paper mainly focuses on the file securing and cloud storage security issues, giving particular attention to emerging trends and mechanisms of hybrid cryptography techniques. Keywords – File Security, Cloud Computing, Cryptography, Hybrid Cryptography, Access, Authorization, Authentication Data Security, Data Privacy, File Storage

Abstract: Today technology is growing to a bigger extent, but there's no value-effective device for visually impaired folks. God precocious sense of vision to the human being is a very important side of our life. However, there are some unfortunate those who lack the flexibility of visualizing things. Throughout their daily lives, they need to face additional challenges. For a visually impaired person, it becomes not possible to try to his/her day to day activities, after you take them into account, you may notice that without the help of others they cannot walk towards their destination one has to guide them the directions. Therefore, sensible Blind stick will facilitate visually impaired folks in moving and permitting them to perform their work simply. The smart stick will have sensors embedded with it, thereby it senses the objects/intruder, when any objects or obstacles come in range of an ultrasonic sensor then the person is alerted with a quick response time using a vibrator and buzzer that provides voice output. The stick senses the item before the individual and provides the user direction with a vibration. This stick additionally incorporates a camera for effective obstacle detection. The system is meant to supply overall measures – Artificial vision and object detection. Coming up with a price-effective and economical blind stick is that the main aim of the project.

Keywords: Arduino, inaudible sensing element, Camera, Object detection.

Abstract: In the current century, everything around us has become dependent upon technology to make our lives much easier. Day-to-Day tasks are continuously becoming computerized. Nowadays a lot people prefer to do their work electronically. To the best of knowledge we have, the process of recording attendance of the students at the university is still manual. Faculties go through attendance sheets and signed papers manually to record attendance. This is very slow, inefficient and time-consuming process. The main aim of the project is to offer system that simplify and automate the process of recording and tracking students’ attendance through facial recognition technology. It uses biometric technology to identify or verify a person from a digital image or surveillance video. Facial recognition is widely used nowadays in different areas such as universities, banks, airports, offices etc. We will use pre-processing techniques to detect, recognize and verify the captured faces like LBPH method. We aim to provide a software that will make the attendance process fast and precise. The problem is identified along with solutions and project path. Furthermore, detailed software analysis and design, user interface, methods and the estimated results are presented through our documentation.

Keywords: Face detection Face recognition Local Binary Pattern Student’s attendance system, Haar cascade classifier, LBPH algorithm.

Abstract: The direction of computing is affected and lead by several trends. First, we have the Data Overwhelm from Commercial sources (e.g., Amazon), Community sources (e.g., Twitter), and Scientific applications (e.g., Genomics). Next, we have several light‐weight clients belong to many devices spanning from smartphones, tablets to sensors. Then, clouds are getting popular due to their advantages since they are cheaper, greener, and easy to use compared to traditional systems. Finally, sensitive data stored as a plain text on a cloud system would be vulnerable to unauthorized access and the security become an important aspect. We believe that these advancements steer both research and education and will put together as we look at data security in the cloud. We introduce a password‐based encryption (PBE) approach to protect sensitive data, investigate the performance metrics of the proposed approach, and present the experimental results for the key generation and the encryption/decryption calculations.

Abstract: In a growing world, where internet has everything, literally everything which makes tedious to search each and everything over and over. Like movies, series, songs and much more. A recommendation system is a specialized system, made for a specific domain, which shows similar searches, result based on our search and query. We live in an era of OTT, which made it possible that we don’t need theaters and TV for movies and series altogether. The need of recommendation rose up quickly. To give recommendation, once a series or a movie is finished, based on what is just finished. Write a name of a series of movies in Google, scroll down, and in the right you will see “people also search for”. That shows how recommendation systems are important. In this project, an attempt is made to make a hybrid movie recommendation system, by combining two techniques, collaborative filtering and content-based filtering. Keyword: Content-based filtering, collaborative filtering, nearest neighbors, user-item interaction matrix.

Abstract: Currently, the people finds a car to rent via social network and make some call to car’s owner for a rent. To offer the benefits for both owner and rental, the hire car system was developed. This project was done to beat the matter of individuals to seek out a car to be easier and for the car’s owner they will manage booking made by rental through this technique. This technique includes three modules which are of rental, car’s owner and administrator. The title of this project is named “Online Car Rental System”. Car rental system primarily serve people who require a temporary vehicle, for example, those who do not own their own car, travellers who are out of town, or owners of damaged or destroyed vehicles who are awaiting repair or insurances compensation. Car rental agencies may also serve the self-moving industry needs, by renting vans or trucks or bikes, and in certain markets, other types of vehicles such as motorcycles or scooters may also be offered.The aim of the project is to create an automatic system for reserving Vehicles online and simply manage rental services by using the online based system. The project aims to create a web hire car system. We used five stages development life cycle including planning, analysis, design, implementation and use, which utilized programing language of PHP and MYSQL database.

Keywords: Online hire car, Luxuly hire car, car rental Online, Car Near Me

Abstract: Smart phone are necessary as oxygen is necessary for life we cannot imagine life without them. They can work without us but we cannot live without them. They are good but everything has dark side and smart phone has too. May they are more harmful then they are useful. Though we cannot imagine toady society without these technology but we can limit the harm they do to our social, physical and mental health.

Keywords: Smartphone, Cyberbullying,electromagnetic impulses,family life,Insomnia

Abstract: -A chatbot is a computer software program that conducts a conversation via auditory or textual methods. This software is used to perform tasks such as quickly responding to users, informing them helping to purchase products and providing better service to customers. Chatbot are programs that work on Machine Learning Platform. A computer program designed to simulate conversation with human users, especially over the Internet. A chatbot is an artificial intelligence computer program which performs communication using audio and video system. A person can ask any questions and chatbot will answer accordingly. A chatbot is used in many areas like order food, product suggestions, customer support, weather, personal finance assistance, scheduled a meeting, search and track flights, send money, and many more. The system was implemented using python. In this paper, we streamline machine learning algorithms for effective prediction of chronic disease outbreak in disease-frequent communities. The concepts of artificial intelligence, machine learning and natural language tool kit (NLTK) have provided substantial assistance in the field of healthcare.

Keywords: -Chatbot, Answer agent, Machine Learning, Natural Language Processing, Artificial Intelligence, Python, Natural Language Tool Kit.

Abstract: This paper proposes the development of a parental control utility for Android cell phones, with the intention of minimizing dangers and preventing threats in opposition to minors from materializing.Android dad and mom control applications are used by means of dad and mom to display and restriction their children’s cell behaviour (e.g., mobile apps usage, web browsing, calling, and texting). In order to offer this service, parental manage apps require privileged get right of entry to the device sources and get right of entry to the touchy data. This may additionally extensively limit the risks associated with kids’ online activities, however it raises necessary privacy concerns.The system uses java as front-end and Firebase as back-end.

Keywords: Parental control Utility, Parental, Java , Minor's, Internet safety, Child safety.

Abstract: There is an expectation that the blood will always be there when it is really needed. Blood donor volunteers constitute the main supply source in an effective blood supply chain management. They feed blood stocks through their donation. In an emergency situation, if the stocks are insufficient, the only source of blood supply will be the people who come to the health center and donate the blood on a voluntary basis. It is certain that time is a very important component in such situation. For this reason, the health care center should call the nearest available donor in order to ensure to get the service as quickly as possible. A smart phone application is developed to facilitate the identification of the nearest available blood donor volunteer and the communication with him/her in the emergency situations where the blood can’t be supplied through the blood banks’ stocks.

Keywords: Smart phone application, Plasma donation information system, optimization, distance calculation, java development platforms

Abstract: Recommender systems play a vital role in engaging a user on a platform by recommending similar new items based on users interest. Some of the tech giants like amazon use recommendation systems to recommend new items based on users previous search or purchases, Netflix uses recommendation systems to recommend new movies to users based on their interest. In past few years due to the availability of huge amounts of data, it is difficult to find information that is useful and relevant. Collaborative filtering, Content-based filtering, Hybrid filtering are some of the techniques used by recommendation systems. Few issues that exist in recommendation systems are data sparsity problem and cold start problem. This paper proposes a method to address the issue of sparsity in SVD based approaches. Data sparsity refers to problems in finding similar users because users only rate a few items. Cold start refers to difficulties in generating accurate recommendations for users who have rated very small items.

Keywords: Matrix Factorization (MF), Singular Value Decomposition (SVD), Sparsity, Collaborative Filtering (CF)

Abstract: Cyber-Physical-Social System (CPSS) big data which is usually stored in cloud. The local real-time data which is usually stored in the fog-edge server (FeS) of the mobile terminal devices or sensors. The social data which is usually stored in the social data server (SdS). CPSS big data to be tampered and to be leaked. A light-weighted symmetric encryption algorithm is used to achieve privacy-preserving.

Abstract: The way in which people emote, express, share, opine thoughts have drastically changed in the past few decades, thanks to the Internet. Nowadays people can relentlessly express their thoughts, opinions on a social media platform, forums, product review sections, comment sections, online survey portals, etc., and the list is endless in the world of Internet. More importantly the major chunk of sentiments comes from social media platforms like Twitter and Facebook due to having a large number of daily active users under their belt.

Keywords: Sentiment analysis, Twitter, Facebook, Naïve Bayes Classifier, Social networks, classification and opinion.

Abstract: Big data is an emerging and popular trend in information technology. Operation on data and analysis is usually a remarkable thing which was accustomed keep records and data for future purpose. the majority sectors required data collection and that they perform different operations thereon so this technology accepted by all. As data collected from any wired or wireless media so to stay safe and accurate is that the main role in concern with security. Data stored within the cloud always give flexibility to access from anywhere on any platform. Real time operation are often performed on data through cloud to create digital applications. Big data and cloud computing move to serve input furthermore as output for several applications like education, medical, government, etc. As we see dream of digital India so these two things give more contribution towards it. Maintaining security of information over cloud is required at a high level through security techniques. Maintaining integrity of information could be a key challenge to save lots of sensitive data on cloud. This paper covers all points regarding concept of massive data, analysis, operations, tools for data collections and applications of huge data. It also covers the importance of huge data concept for digital India. This paper also deals with cloud security and techniques accustomed secure data on the cloud.

Keywords: Big Data, Analytics, Cloud, Security, Digital India.

Abstract: The use of social networks is a growing phenomenon, being increasingly important in both private and academic life. Social networks are used as tools to enable users to have social interaction. The use of social networks (SNs) complements and enhances the teaching in traditional classrooms. For example, YouTube, Facebook, wikis, and blogs provide a huge amount of material on a wide range of subjects. This research aims to explore the need to change the traditional style of teaching and learning after the innovation of Web 2.0. The main objectives of this research are to discover the motives for the use of social networks by higher education students in Oman, to recognize the impact of social networking tools in learning and education generally, to analyse the problems that students might face when using social networks

Keywords: Social Media, College, Android, Application,

Abstract: Brain tumor can be classified into two types: benign and malignant. The brain tumors, are the most common and aggressive disease, leading to a very short life expectancy in their highest grade. Thus, treatment planning is a key stage to improve the quality of life of patients. Generally, various image techniques such as Computed Tomography (CT), Magnetic Resonance Imaging (MRI) and ultrasound image are used to evaluate the tumor in a brain, lung, liver, breast, prostate…etc. Especially, in this work MRI images are used to diagnose tumor in the brain. However the huge amount of data generated by MRI scan thwarts manual classification of tumor vs non-tumor in a particular time. But it having some limitation (i.e) accurate quantitative measurements is provided for limited number of images. Hence trusted and automatic classification scheme are essential to prevent the death rate of human. The automatic brain tumor classification is very challenging task in large spatial and structural variability of surrounding region of brain tumor. In this work, automatic brain tumor detection is proposed by using Convolutional Neural Networks (CNN) classification. The deeper architecture design is performed by using small kernels. The weight of the neuron is given as small. Experimental results show that the CNN archives rate of 97.5% accuracy with low complexity and compared with the all other state of arts methods. Brain tumor identification is really challenging task in early stages of life. But now it became advanced with various machine learning and deep learning algorithms. Now a day’s issue of brain tumor automatic identification is of great interest. In Order to detect the brain tumor of a patient we consider the data of patients like MRI images of a patient’s brain. Here our problem is to identify whether tumor is present in patient’s brain or not. It is very important to detect the tumors at starting level for a healthy life of a patient. There are many literatures on detecting these kinds of brain tumors and improving the detection accuracies. The segmentation, detection, and extraction of infected tumor area from magnetic resonance (MR) images are a primary concern but a tedious and time taking task performed by radiologists or clinical experts, and their accuracy depends on their experience only. So, the use of computer aided technology becomes very necessary to overcome this limitation. We estimate the brain tumor severity using Convolutional Neural Network algorithm which gives us accurate results.

Keywords: Tumor Detection, Convolutional Neural Network, Gaussian Filters, MRI Images, Brain.

Abstract: In today’s world the time which people spend on device while working is to do productive work but many people get into the trap of wasting the time in using social media, entertainment, etc and after a few hours they recognise that the time has been wasted unconsciously by doing unproductive things.Since every work is moving towards the digital solution, which will lead many of the human existence to use the computer or mobile to get there work done. Hence it is necessary to have a monitor of activities that has been performed to avoid the unproductive time spent on their device. By taking this problem into consideration, this paper proposes Python, Deep Learning, Natural Language and Cloud Computing Frameworks for automating the tasks of classifying user activities into productive and nonproductive categories which has 13 subcategories which can be shown to the user in various statistical and tabular formats which will help user able to identify its activities as productive and non productive along with the time spent on the same. The user will be able to visualize its unproductive activities and can become conscious which will help the user to stop doing unwanted activities on desktop or mobile phone and start doing what the user actually wanted to do. For automating these tasks, along with the frameworks mentioned above, we have built a Desktop Application which will act as a productivity assistant for the user on a Desktop but the same can be built on an Android Application as well.

Keywords: Machine Learning, Productivity Assistant, Cloud Computing, Natural Language Processing, Cosine Similarity Algorithm, Desktop Application, Android Application, Electron, Algorithmia, Firebase, Text Classification, Voice Assistant, Website Classification, Chart.js.

Abstract: This paper describes electoral machine which is completely automated, unbiased and online for easing the process of voting , increasing safety and decreasing the counting time The undertaking is divided on the whole into two part first one is voter registration section of voter and 2d one is of genuine vote casting phase on vote casting console. In voter registration phase the database of voter will be saved in repository which in particular includes voter’s unique identification number and finger prints information. Project consists of biometric device which will verify the identification from the database saved in repository through the verbal exchange of Wi-Fi module i.e. esp8266 and if respective voter is identified then authorization will approve to that respective voter at the equal time in other area of repository it updates the database of licensed voter to register voter is qualify to vote and to strong point ,also it will forestall the duplication and falsification of voter ;after getting authority from the repository balloting enabling sign will send from VVB via using ZigBee to balloting console for enabling vote casting for that precise voter , when voter votes then that vote will ship to repository with the assist of esp8266 and the vote casting console will be reset after the voting of every vote.

Keywords: Electronic Voting Machine (EVM), Biometric, Voting System, Voting analysis.

Abstract: In this growing age of the Technology, every hand has smartphone or another device. A study shows that number of smartphone users in India was estimated to reach over 760 million in 2021, with the number of smartphone users worldwide forecasted to exceed to 3.8 billion users in 2021. Many Development process of software also increased. Due to lot of availability of different devices there is need to develop a single source code programming language or SDK which covers all aspects of all different devices for application development. Keeping all this in mind Google have developed a software Develop Tool kit called Flutter which is a cross-platform application development toolkit. Flutter is an open-source SDK for developing high-performance and more reliable mobile applications for operating systems like iOS and Android. AOT compilation (Ahead-of-time compilation) compiles a high-level programming language such as C or C++, or an intermediary representation such as Java bytecode or .NET Framework Common Intermediate Language (CIL) code, into native system-dependent machine code so that the subsequent binary file can execute natively. During Experimenting and debugging process it provides hot reload. This feature is unique in Flutter. Hot reload works by inserting updated source code files into the running Dart Virtual Machine (VM). After the VM updates classes with the new versions of fields and functions, the Flutter framework automatically reconstructs the widget tree, permitting you to rapidly view the special effects of your changes.

Keywords: Android, iOS, Flutter, Dart, Cross-Platform Mobile application development, SDK

Abstract: In today’s world, everyone wishes for a house that suits their lifestyle and budget and provides amenities according to their needs. House prices keep on changing very frequently which proves that house prices are often exaggerated. There are many factors that have to be taken into consideration for predicting house prices such as location, number of rooms, carpet area, how old the property is? and other basic local amenities. This research aims to predict house prices based on every basic parameter that is considered while determining the price.

Keywords: Machine learning , Supervised learning , linear regression , model , Ridge regression

Abstract: Online event decoration booking is an online event decoration booking software project that serves the functionality of an event ornament manager. The system allow registered user login and new user are allowed to register on the application. The system helps in the decoration of events, users and the aspects related to them. This proposed to be a web application. The project provides most of the basic functionality required for an event type e.g. [Marriage, Engagement party, etc.], the system then allows the user to select date and time of event, place and the event equipment. All the data is logged in the database and the user is given a receipt number for his booking. The data is then sent to administrator (website owner) and they may interact with the client as per his requirement.

Keywords: User, Admin, Events, Book, Event Decoration booking, Database.

Abstract: In the early 2000’s, when data used to be of simple structure and small size, the client- server architecture handled the sharing and storage of data pretty efficiently. But as the technology progressed, the data became more and more complex and huge in size which led to load on servers for storing and sharing the data. Here, the P2P network architecture comes into picture where the peers could communicate and share the data without any centralized server. The basic idea behind the proposal of this system is the combined use of segmented file transfer on P2P network. This makes it possible to download a single file from multiple peers at the same time. Moreover, it also includes a synchronized server module for efficient storage and updating data more efficiently on the servers. This paper presents a system in which data transfer and storage system uses file downloading based on peer-to-peer network architecture. It’s the software developed for sharing/downloading huge data files and storing important data efficiently. It’s very convenient to share data using this system as the data is spread across the peer-to-peer network. The synchronized servers provide reliable data storage for any file format. All the peers present in the network communicate to other peers using the information present in the tracker. Tracker is responsible for maintaining the peers in the whole network.

Keywords: Client-Server, Peer-to-Peer, Synchronized servers, Load distribution.

Abstract: Finding of fire in forest is essential to keep away from destruction of belongings due to fire accidents. Detection of fire can prove to be very important as it could mean the difference between life and death. Fires can occur from anywhere and at any point of time; hence the presence of Fire monitoring System helps in keeping forest safe. Some people don’t see the need to have a fire alarm system. They just assume that they could smell the fire and run out in time. The average time for a forest to burn down nowadays is just 15-20 Minutes. So, by the time you smell the fire and try to run away, the fire has probably engulfed the forest. The Internet of Things (IoT) is a system of devices connected and accessible through the internet. The ‘Thing’ in IOT could refer to any physical device, varying from a toaster to an automobile. These devices can be connected through the internet and help us manipulate or collect data from them. In this paper, we will be using a wide variety of sensors to detect the presence of fire and alert its presence to the forest and fire officials. It discusses in detail about the functions of each module and its execution in an detailed manner. It also discusses the application of Iot Technology in relation to fire detection technologies.

Keywords: Fire Montoring system, Gas sensor, MCU, GSM, Temp Sensor.

Abstract: The world is experiencing severe health issue as a result of the rapid spread of coronavirus disease-2019 (COVID-19). According to the World Health Organization (WHO), the best way to prevent the spread of COVID-19 is wearing a mask and keeping a distance. But there is huge neglect of the guidelines by people which is resulting in daily increase in an infected patient. In these regions, manually monitoring the citizens is quite challenging. So, in this paper, we study ideas to monitor people using the automation process to identify the people who are wearing the mask and who are not. Many incipient trained models are being developed utilizing pre-subsisting datasets to make the algorithm as precise as possible.

Keywords: Semantic Segmentation, OpenCV, Convolutional Neural Network(CNN), YOLO, Deep Learning,

Abstract: We introduce a home automation system (HAS) that uses wireless communication to allow the user to remotely control various lights, fans and devices in their home and to save the data in the cloud. This system is inexpensive and expandable, and allows a wide variety of devices to be controlled.

Keywords: IoT, NodeMCU, Relay, IFTTT, Blynk , Google Assistant

Abstract: Medical era has developed with a terrible level of achievements in disease pattern prediction, prevention and cure with the advancements of data mining techniques. Among various mining techniques feature selection occupies an indispensable role for the sake of improving accuracy in any kind of forecasting or cure of diseases. Thus it is treated as an essential earlier work of any kind of mining techniques. Microarray data have a high dimension of variables and a small sample size. In microarray data analyses, two important issues are how to choose genes, which provide reliable and good prediction for disease status, and how to determine the final gene set that is best for classification. Associations among genetic markers mean one can exploit information redundancy to potentially reduce classification cost in terms of time and computation cost. So in this project, we can implement the framework to predict the diseases using optimization and classification algorithm such as Genetic algorithm and Semi-supervised deep learning algorithm with improved accuracy rate. This paper presents an overview of various disease classification methods and evaluates these proposed methods based on their classification accuracy, computational time and ability to reveal gene information. We have also evaluated and introduced various proposed gene selection method.

Keywords: Microarray data, Bio-markers. High Dimension data, Optimization, Deep learning algorithm

Abstract: Clinical time has created with a terrible degree of accomplishments in illness design expectation, anticipation and fix with the progressions of information mining procedures. Among different mining strategies highlight determination possesses a key part for improving precision in any sort of forecasting or fix of sicknesses. This paper presents SeQual, a versatile device to productively perform quality control of enormous genomic datasets. Our tool currently supports in excess of 30 distinct tasks (e.g., separating, managing, designing) that can be applied to DNA/RNA peruses in FASTQ/FASTA organizations to improve subsequent downstream investigations, while giving a straightforward and easy to use graphical interface for non-master clients. Hence it is treated as a fundamental before work of any sort of mining methods. Microarray information has a high element of factors and a little example size. In microarray information examinations, two significant issues are the ways to pick qualities, CNN give solid and great forecast to illness status, and how to decide the last quality set that is best for grouping. Relationship among genetic markers mean one can misuse data excess to possibly diminish order cost as far as time and calculation cost. So in this undertaking, CNN can actualize the structure to foresee the sicknesses utilizing advancement and order calculation like Genetic calculation and Semi-administered profound learning calculation with improved exactness rate. This paper presents an overview of different sickness order techniques and assesses these proposed strategies dependent on their arrangement precision, computational time and capacity to uncover quality data. We have likewise assessed and presented different proposed quality determination technique.

Keywords: next-generation sequencing (NGS), SeQual, DNA/RNA, FASTQ/FASTA, microarray, Genetic algorithm, deep learning.

Abstract: Technological advances in medicine have significantly decreased affected person's difficulties. One of the main classes of bodily disabilities that result in paralysis is motor neuron disease (MND). An affected person with MND is not able to speak, walk, express feelings, and communicate Due to the weakening of the muscles, the affected person has the best control over the blinking of the eyes, which makes it tough for the affected person, in contrast to an everyday person, to relate to the surroundings and communicate their fundamental desires and the surroundings generally tend to suppress an essential element of their emotions due to the restlessness of the broadcast. A suitable mixture of hardware and software programs should be integrated to obtain a functional solution. This document discussed a portable solution for converting blink sequences to speech. CV library for programming Raspberry Pi 3 A camera detects winking and based on the EAR calculation, the code converts the sequence. The flashes with the corresponding voice output.

Keywords: Motor Neuron Disease, emotionally detached, liaise, Raspberry Pi 3, Raspbian, Open CV, Ear Aspect Ratio, eye blinks, speech.

Abstract: Motion detection and the subsequent identification of the cause of motion plays a pivotal role in advanced surveillance systems. Cross border infiltrations are increasing rapidly and an autonomous system that identifies and classifies the cause of motion has a tremendous potential to augment the surveillance process. Deep learning methods can be used to smarten such systems to perform under any illumination setting with high accuracy. In our study we have developed a system that identifies intruders in well illuminated as well as in low or no illumination conditions. The system identifies motion in a live video feed by background subtraction and identifies the regions of interest (ROI). Subsequently, a Convolutional Neural Network (CNN) model trained using regular and thermal images classifies the regions of interest and detects if motion is caused by a human intruder. Our system detects human intruders with an accuracy of 96.13%.

Keywords: visual surveillance, background subtraction, motion detection, static background, convolutional neural networks

Abstract: Now-a-days information and communication technology support the development of human interaction with physical, computer and virtual environment such as science, commercial, banking, education, etc. A field of computer science which deals with a combining of reality with computer related data can be called as Augmented Reality. In early days if we users wanted to buy a furniture/decorative objects without visiting the shops it was possible but it was not possible to check how the object actually looks in home structure. Now in our proposed system, it is possible for user to buy the furniture objects sitting in the home without visiting the shops. The main purpose of the “Furniture Layout Application Using Augmented Reality” is to develop an android application for trying different furniture in virtual way using a mobile which supports AR camera. The application will remove or rather eliminate the human efforts by physically visiting the furniture store which is too much time-consuming activity. Besides, this it might be easier to use this technique in Online shopping as an option for user to try out the furniture items in their room they are thinking to buy and allow user to visualize the room how it will look after placing furniture in it. User can try out multiple combinations virtually, without physical movement of furniture items. Our motivation here is to increase the time efficiency and improve the accessibility of furniture try on by creating furniture augmented reality application. This system will help the customer to view the furniture object virtually in real environment before buying the object. Due to this system customer will come to know how his home structure would look after buying the furniture object. This system would let the user to try multiple combination of object virtually without physical movement of furniture objects. These will help the buyer to determine how to setup furniture in home structure.

Keywords: Augmented-reality , Markless-Detection , Rendering, Firebase, 3D model.

Abstract: The technological development and have an effect on of computers and internet on our lives that has been verified over time affected a number sectors of activity. And nearly each mission today is being run via computer systems. In this paper, a computerized platform for managing the results of all categories of students in a seamless and interactive manner is presented. The system was developed using PHP, CSS, HTML, MYSQL and was hosted locally using an Apache webserver. The present-day lookup aims at growing a web-based scholar result administration system, decreasing time, effort and improving security. The methodology adopted for the elaboration of the lookup is based on a qualitative study. Use case diagram is presented to show the different categories of the system users and the various functionalities associated with the different system users. Screenshots of various system functionalities are presented from the test run of the functional system. Firstly, ER design of the Student Result Management System is described, and numerous factors are covered in it. Secondly, a practical module design for Student Result Management System is provided, in which three kinds of users are designed in this system, that is, admin, faculties, and students.

Keywords: System Administration, Student Online Result, Educational Institute, Graphical User Interface.

Abstract: All of the life that is on the earth can survive because of the sun. Every day, the energy given from the sun’s rays sustains life. It provides us with heat, light, health benefits and various other applications, like the widely used and known solar energy. Without the sun, the earth would be just a ball of rock without any life forms. The importance of solar energy in our daily life is more significant than any other thing in your life — besides water and food. Solar energy has been growing as a renewable and alternative energy source. That’s why it’s necessary to understand the importance of the sun’s power because, if you don’t already, you could very well be reliant on the sun for your daily energy needs. So keeping that though in mind and to attribute to the Mission-ATMA Nirbhar bharat we have presented SOLAR SUNFLOWER system which is working of solar tracker and to design the same. Solar panel has been used increasingly in recent years to convert solar energy to electrical energy. The panels can be utilized either as a large solar system that is connected to the electricity grids or as a stand-alone system.We are trying to munch additional energy from the sun via solar panel. In order to maximize the conversion from solar to electrical energy, the solar panels need to be placed at right angle to the sun. Thus the tracing of the sun’s position and positioning of the solar panels is a significant task. The goal of this project is to make an automatic tracing system, which can trace location of the sun. The tracing device will move the solar panel so that it is positioned perpendicular to the sun for maximum energy conversion at all time. LDR's are used as sensors in this system. The system will consist of light sensing system, microcontroller, gear motor system, and a solar panel. Our system will output up to 30% more energy than solar panels without tracking systems.

Keywords: Solar pannel , LDR, Microcontroller, battery,Gear Box

Abstract: Pattern lock has been widely used in smartphones as a simple and effective authentication mechanism, which however is shown to be vulnerable to various attacks. In this paper, we design a novel authentication system for more secure pattern unlocking on smartphones. This project is written in J-script and click are automatically recognized by the code and no external configurations are required. Android pattern lock is still popularly used for mobile user authentication. Unfortunately, however, many concerns have been raised regarding its security and usability. User-created patterns tend to be simply structured or reduced to a small set. Complex patterns are hard to memorize. Input patterns are susceptible to various attacks, such as guessing attacks, smudge attacks, and shoulder surfing attacks. Our basic idea starts from turning the lock pattern into public knowledge rather than a secret and leveraging touch dynamics. Users do not need to create their own lock patterns or memorize them. Instead, our system shows a public pattern along with guidance on how to draw it. All the user needs to do for authentication is to draw the pattern as shown. For adversaries, the above-mentioned attacks are rendered useless by this new mechanism. Specifically, we study how to generate the public patterns and how to perform authentication. You have probably seen this on a touchscreen smartphone you have 9 dots and you have to draw a pattern. It works great: drawing a shape on a small touch screen is far easier than typing on those small keyboards AND far easier to remember too. Once you've got used to it, typing passwords in general gets pretty annoying A proof of concept project illustrating the use of the Android Pattern Lock Screen inside a HTML

Keywords: “J-script”, “Android”, “Smartphone”, “HTML”, “Pattern Lock”, “9 dots

Abstract: The Smart College Campus Portal project is aimed at developing an Online Intranet College Management System (CMS) that is of importance to either an educational institution or a college. The main idea behind this project is that due to the covid crisis all colleges were shut and many colleges were not able to carry out the daily operations that they used to perform on the floor. Also, colleges have to rely on third-party ERP systems to carry out operations which may cost the college/institutions. This project is developed by the collaboration of 4 students to help institutions carry out their activities even though college may remain shut. This project focuses on the Teachers, HOD, and students to carry out college activities just by sitting at home at ease. The system is developed by two main technology stacks 1) JDBC 2) Django. This system concludes that the system will be effective even though colleges are closed and follow an online mode of learning or even if they follow the usual way of learning. This system eradicates the use of paper and encourages students to follow digitalization.

Keywords: JDBC, ChatBot, Django, Attendance.

Abstract: Information is very important today,every time we read a piece of information or watch news on TV,we look for reliable source.Nowadays fake news is making various issues from harsh articles to made news and planning government proclamations in specific outlets.Fake news and nonattendance of trust in the media are creating issues with enormous ramifications in our overall public.Obviously,a deliberately deceptive story is "fake news" yet recently babbling online media talk is changing its definition[1].Some of them currently utilize the term to excuse the realities counter to their favored perspectives.In this today’s era we try to get an information or news from the internet and from the social media handles or YouTube,but Information quality in social media is an increasingly important issue.There are so many fake news or tampered video news spread all over the internet and social media.A large portion of the fake news identification frameworks use the semantic element of the news. Nonetheless,they experience issues in detecting profoundly equivocal fraudulent news which can be recognized solely after distinguishing its importance and most recent related data. Therefore,identifying whether the news in text as well as in video format is fake or real has become an important aspect.So,we intended to solve this problem by using different techniques and algorithms.We will be proposing a system where it will be very easy to identify whether the given NEWS on Social Media is Real or Fake,this NEWS can be in Text form[2].

Keywords: Fake,Real,Social Media,News,Algorithms,Machine Learning

Abstract: The rapid adoption of cloud computing has introduced significant security vulnerabilities, making it a prime target for cyber threats. Traditional security frameworks struggle to detect sophisticated attacks due to their high computational complexity, limited scalability, and reliance on handcrafted feature engineering. This study proposes an AI-powered network security framework leveraging the Informer model, a transformer-based architecture optimized for long-sequence time-series data. The proposed framework integrates feature selection using Mutual Information and employs ProbSparse Self-Attention to enhance anomaly detection accuracy. By efficiently processing cloud network logs, it ensures real-time threat identification and mitigation with minimal false positives. The framework also incorporates automated security enforcement mechanisms, including access control, encryption, and intrusion prevention, to enhance cloud security resilience. Performance evaluations demonstrate that the proposed Informer-based model achieves superior accuracy, precision, and recall compared to existing CNN-LSTM and Tab-Transformer models. With a high accuracy of 99.5% and low false positive and false negative rates, the proposed framework offers a scalable and efficient solution for detecting cloud-based cyber threats. This research contributes to strengthening cloud security by providing a robust, adaptive, and real-time anomaly detection mechanism.

Keywords: Cloud Security, Informer Model, Anomaly Detection, Cyber Threats, Transformer-Based Architecture.