VOLUME 11, ISSUE 2, FEBRUARY 2022

Abstract: Diminishing of green areas (vegetation, park, forest, etc.) influences the climate change and the quality of life in an area. Indonesia has large are, hence, it is difficult to find the number of vegetation and without the computer-based calculation accurately. Also, nowadays, the remote sensing technology has been widely used to capture the large region using satellite sensor, e.g., Landsat, Sentinel, Ikonos, etc. from websites that give free access like United States Geological Survey (USGS). Many vertical applications can be used to calculate percentage of vegetation, e.g., IDRISI, Dyna-Clue, eCognition, etc., but in this study, a Matlab-based calculation was used. This programming language will convert a data into a mat-file that can be integrated in a single datastore, hence the program will execute the data efficiently. In a datastore, many regions can be calculated simultaneously using the big data facility in Matlab. The study shows the calculation using a special data format (mat-file) has good accuracy and fast although in this study multispectral data were used before conversion into normalized difference vegetation index (NDVI).

Keywords: Satellite Imagery, Multispectral, Matlab, NDVI, Near Infrared, sensors

Abstract: Now-a-days, people face various diseases due to the environmental condition and their living habits. So the prediction of disease at earlier stage becomes important task. But the accurate prediction on the basis of symptoms becomes too difficult for doctor. There is a need to study and make a system which will make it easy for end users to predict the chronic diseases without visiting physician or doctor for diagnosis. To detect the Various Diseases through the examining Symptoms of patient’s using different techniques of Machine Learning Models.

Keywords: CNN (Convolutional Neural Network), Python, Disease Prediction Machine Learning.

Abstract: Artificial intelligence (AI) has been applied widely in our daily lives in a variety of ways with numerous successful stories. AI has also contributed to dealing with the coronavirus disease (COVID-19) pandemic, which has been happening around the globe. This paper presents a survey of AI methods being used in various applications in the fight against the COVID-19 outbreak and outlines the crucial roles of AI research in this unprecedented battle. We touch on a number of areas where AI plays as an essential component, from medical image processing, data analytics, text mining and natural language processing, the Internet of Things, to computational biology and medicine. Research directions on exploring the potentials of AI and enhancing its capabilities and power in the battle are thoroughly discussed. This paper aims to comprehensively review the role of AI and ML as one significant method in the arena of screening, predicting, forecasting, contact tracing, and drug development for SARS-CoV-2 and its related epidemic.

Keywords: Artificial intelligence; AI; machine learning; coronavirus; COVID-19; SARS CoV-2; pandemic; epidemic; outbreak; survey; review; overview; future research directions.

Abstract: Object triangulation has become a vital part of many systems and applications. As different application areas develop, the need for more refined object triangulation methods has increased. This paper aims to utilize on-chip transducers that transmit and receive a signal of a small object in a precise way. These transducers are controlled by a python code and are mounted on a working surface area which can be moved to wherever it may be needed. The sensors will be able to triangulate an object’s position within a three-dimensional plane, as well as communicate with each other to calculate the object’s position more accurately. These transducers are wired to a computer system which displays the recorded data. A similar system could then be implemented in various industries to increase safety or performance.

Abstract: - Melanoma skin cancer detection at an early stage is crucial for an efficient treatment. Recently, it is well known that, the most dangerous form of skin cancer among the other types of skin cancer is melanoma because it’s much more likely to spread to other parts of the body if not diagnosed and treated early. The non-invasive medical computer vision or medical image processing plays increasingly significant role in clinical diagnosis of different diseases. Such techniques provide an automatic image analysis tool for an accurate and fast evaluation of the lesion. The steps involved in this study are collecting dermoscopy image database, preprocessing, segmentation using thresholding, statistical feature extraction using Gray Level Co-occurrence Matrix (GLCM), Asymmetry, Border, Color, Diameter, (ABCD) etc., feature selection using Principal component analysis (PCA), calculating total Dermoscopy Score and then classification using Convocation neural network(CNN). results show that the achieved classification accuracy is 92.1.

Abstract: Network scanning is the process of discovering active hosts on the network and information about the hosts, such as operating systems, active ports, services, and applications. In addition to these basic techniques, advanced network s canners can perform other techniques such as masking the origin of the scanning, enabling timing features for stealth y scans, evading perimeter defenses such as firewalls, and providing reporting options. Nmap is used to perform the above task, but Nmap is a cmd line tool and for beginners, it is daunting to use the cmd line tool. Sometimes while te sting, organizations do not allow our toolset to perform the test. They offer their environment. So we build the GUI interface which is easy to use because of the graphical user interface and also we host this as a website so the tester can access it from anywhere .

Keywords: Network Mapper, GUI, Nmap, port scanning.

Abstract: We do have a human partner. But is it possible to make a computer as your companion? This problem was solved by a research team of IBM at Almaden Research Centre. They conducted the BLUE EYES TECHNOLOGY which aims at designing computational machines that have perceptual and sensory abilities similar to those of human beings. Through this Tech the computer system understands the six basic human emotions (anger, disgust, fear, surprise, sadness and happiness) using various techniques by analysing our blood pressure, temperature, heartbeat etc. We could create machines with emotional quotient. Blue eyes tech creates a PAN (personal area network) using Bluetooth, understand human emotions and empower the computer system.

Keywords: Blue eyes technology, Techniques: Emotion mouse, MAGIC, AISR, SUITOR, DAU, CSU.

Abstract: Touch screens have become increasingly popular and widely used in most human-computer interfaces. We present a new low-cost touch display method based on handling projectors using image processing, in which we use object detection instance segmentation and key points detection to improve the efficiency of touch detection and reduce the probability of misrecognition. We are using a high-definition camera and Torch with red beam light that provides more touch accuracy which converts the camera coordinates to space coordinates. The main idea is to make it easy to handle a projector using fingertip processing using the OpenCV library. Here we handle some projector functionality like swipe left and right and virtual typing using Fingertip. We can easily convert a simple projector into an interactive projector using just a webcam through image processing.

Keywords: Image Processing, OpenCV, Camera coordinates -to- Space coordinates, Touch Detection, Infrared Touch Model.

Abstract: In recent years, yoga has become part of life for many people across the world. Due to this there is the need of scientific analysis of y postures. It has been observed that pose detection techniques can be used to identify the postures and also to assist the people to perform yoga more accurately. Recognition of posture is a challenging task due to the lack availability of dataset and also to detect posture on real-time bases. To overcome this problem a large dataset has been created which contain at least 5500 images of five different yoga poses and used logistic regression Algorithm. 80% of the dataset has been used for training purpose and 20% of the dataset has been used for testing. This dataset is tested on different Machine learning classification models and achieves an accuracy of 99.04% by using a Random Forest Classifier. Yoga is an ancient science and discipline originated in India 5000 years ago. It is used to bring harmony to both body and mind with the help of asana, meditation and various other breathing techniques it bring peace to the mind. Due to increase of stress in the modern lifestyle, yoga has become popular throughout the world. There are various ways through which one can learn yoga. Yoga can be learnt by attending classes at a yoga center or through home tutoring. It can also be self-learnt with the help of books and videos. Most people prefer self-learning but it is hard for them to find incorrect parts of their yoga poses by themselves. Using the system, the user can select the pose that he/she wishes to practice. He/she can then upload a photo of themselves doing the pose. The pose of the user is compared with the pose of the expert and difference in angles of various body joints is calculated. Based on this difference of angles feedback is provided to the user so that he/she can improve the pose.

Keywords: Yoga, Computer Vision, Machine Learning, Classification, Pose, Self-Learning, logistic regression , Pose Classification.

Abstract: an automatic bird species recognition system has been developed and methods for their identification has been investigated. Automatic identification of bird sounds without physical intervention has been a formidable and onerous endeavor for significant research on the taxonomy and various other sub fields of ornithology. In this pa- per, a two-stage identification process is employed. The first stage in- volved construction of an ideal dataset which incorporated all the sound recordings of different bird species. Subsequently, the sound clips were subjected to various sound preprocessing techniques like pre-emphasis, framing, silence removal and reconstruction. Spectrograms were gen- erated for each reconstructed sound clip. The second stage involved deploying a neural network to which the spectrograms were provided as input. Based on the input features, the Convolutional Neural Net- work (CNN) classifies the sound clip and recognizes the bird species.A Real time implementation model was also designed and executed for the above described system.

Keywords: Bird, Computer Vision, Machine Learning, Classification, Neural Network, Self-Learning, Cnn , Audio Signal Processing.

Abstract: Covid-19 is a deadly pandemic that is currently ravaging the whole world. The World Health Organization (WHO) has recommended the wearing of face masks to contain the spread of the virus. Enforcing the wearing of face masts most times requires that the security personnel will be in close proximity with the people required to have their face masks on. This requirement makes the security personnel vulnerable. There is the need to have an automated checking system in order check conformity. This will ensure complete isolation. In this work, an automated Covid-19 Entrance Door Checking System that checks if individuals wear face mask or not before securing access to the door is designed and implemented. This system was implemented using an electromagnetic solenoid lock to perform the locking mechanism and a Raspberry pi as the controller was coded in python language using Geany as the IDE after which it was executed in the raspberry pi. The controller was interfaced with a camera module and a Temperature module for providing the user input interface on which the face is detected. The system features a liquid crystal display (LCD) Monitor for indicating system status as well as the reason for denial of access. The system operates by scanning the user’s face, checks if he is putting on nose mast, upon successful verification, the electronic lock unlocks and the user will be allowed to access the door. If the user on the other hand does not wear nose mast, the electronic lock will not be unlocked and the LCD will indicate reason.

Keywords: Raspberry pi, Face masks, temperature detection, camera module.

Abstract: Smartphone have become the major part of human’s life. Nowadays mobile applications are playing major role in many areas such as banking, social networking, financial applications, and entertainment and so on. Android applications and its security threats are increasing with interest due to the mass spread of smart devices, and vulnerabilities in developed applications are being exposed while mobile malicious codes are spreading. To avoid malicious codes and attacks we are designing and developing an application which provides security for transferring the file with the help of Advanced Encryption Standard (AES), where it encrypts and decrypts the data with the secret key, here transmission is done in two ways, If the file is public then file is selected and sent to particular receiver, if the file is private it ask for security key and sent towards receiver, this way we achieve the secure transmission of information (file) between end-users. The proposed mechanism was evaluated using ASP.NET based on four performance metrics: (1) Jobs Completion Times, (2) Effective Network Usage, (3) Storage Element Usage, and (4) Computing Element Usage.

Keywords: Smartphone, Mobile application, Security, Threat, Attacks, Encryption, Decryption.

Abstract: This work presents the review on concept of image fusion method by using DNN. The CNN and DBN system has a problem with accuracy, then proposed method is used for improving the system. The fundamental test of picture de-obscuring is to devise effective and dependable calculations for recuperating however much data as could reasonably be expected from the given information. The use of DBN network in existing system works only to reduce error in system. Due to this, it requires better deep learning method for improving accuracy of system. The CNN method uses only 2 convolutional layers for feature mapping. But the proposed method uses 5 convolutional layers and 3 overlapping layers. Due to this, it will help to improve accuracy of system as compared to other existing methods.

Keywords: Image Classification, Machine Learning, Deep Learning, MATLAB etc.

Abstract: Bitcoin is an innovative payment network and a new kind of money. It is open-source; its design is public; nobody owns or controls Bitcoin and everyone can take part. Bitcoin uses peer-to-peer technology to operate with no central authority or banks; managing transactions and the issuing of bitcoins is carried out collectively by the network. Recently Bitcoin has received a lot of attention from the media and the public due to its recent price hike. As Bitcoin has been viewed as a financial asset and is traded through many cryptocurrency exchanges like a stock market, many researchers have studied various factors that affect the price of Bitcoin and the patterns behind its fluctuations using various analytical and predictive methods. In recent years, Bitcoin is the most valuable in the cryptocurrency market. However, prices of Bitcoin have highly fluctuated which make them very difficult to predict. Hence, this research aims to discover the most efficient and highest accuracy model to predict Bitcoin prices using machine learning algorithms. Using the available information through the dataset, we will predict the sign of the daily price change with highest possible accuracy.

Keywords: Bitcoin, Price Prediction, Blockchain, Cryptocurrency, Random Forest, Predictive Analysis

Abstract: RL is a model which is derived from the machine learning methods. RL doesn't require earlier information, it can independently get discretionary strategy with the information gotten by experimentation and ceaselessly associating with changing climate. Its qualities of understanding and web based Training make the Model to be smart specialist's center technology. Then, at that point, we entirely present the primary Model calculations, including Sarsa, fleeting contrast, Q-learning furthermore work estimation. At long last, we momentarily present some utilization of Model which Describes some up coming exploration headings of RL

Keywords: RL; Sarsa; distinction; Q-learning; work estimation transient

Abstract: In this current networked world, Web has become the foremost effective and advanced way of communication. During the initial evolution of the web there was no presumption that the web development is going to be a big deal in the future. In such a short period, Web 2.0 and the Web 3.0 has built an excellent impression within the face of Internet world. The gap from Web 1.0 to Web 2.0 has been covered almost in an exceeding decade. But soon after Web2.0 a replacement, Web3.0 has evolved which has not only raised the extent of interest but also many questions among developers, users and the regulators. Do we actually need Web3.0 at this stage, what are the forcing factors, how it's different from Web2.0 and Semantic Web, what are its social, moral and security implications, is it only about personalization, of these questions have made Web3.0 popular among its stakeholders. During this paper the first focus are on the link between Web 2.0, Web 3.0 and therefore the Semantic Web while the secondary is on the rising security concerns about rapid and sequential Web developments. However, the changing business models within the future Web 3.0 also will be highlighted. Semantic Web technologies are considered as a bridge for the technological evolution from Web 2.0 to Web 3.0. Efforts are made to explain the distinctions bet–ween this and therefore the future Web.

Keywords: Web 3.0, Semantic Web, New Internet, Decentralized Internet, Privacy.

Abstract: Web conferencing or online meeting tools allow remote meeting and collaborative work in any company or institute. Poor Internet service how ever makes most Web conferencing solutions unreliable for some region and developing countries in general. This paper reviews the literature on improving the user experience with low bandwidth and unstable Internet conditions for Website conferencing .we have special concentration on audio/video stream optimization, which is the most affected feature of a any conferencing system. The ongoing research in this area can be grouped into multiple domains. First thing is research on rate adaptation schemes that aims to provide the Stream high-quality content to many recipients while making the most of available bandwidth.Second thing is research on compression which attempts to reduce the bandwidth requirement with acceptable content quality. The last research studies how to weak en the influence of transmission errors andproblems over the content provided.

Abstract: Nowadays, the concept of smart parking have achieved great popularity. Since, nowadays lots of people have their own vehicles, therefore the number of vehicles are increasing day by day. While the number of vehicles are increasing, the requirement for parking lot will also be restricted. Therefore to find a free parking space has become a problem for the people. The purpose of this paper is to introduce a smart parking model to find a vacant parking space and also reduce the wastage of time. With the help of Internet of Things we can easily allocate the vacant spaces. For successful completion of the project we have integrated Arduino UNO, Ultrasonic Sensor, LED light and Android Application together.

Keywords: Smart Car Parking, IOT, Arduino Uno, Ultrasonic Sensor

Abstract: Images are usually exposed to noise. Noise is gained while capturing an image, transmission etc. Reduction of noise in image processing is an essential step. Noise removal has a strong influence on the quality of the image processing techniques. Color image processing has various noise removal techniques. Different types of noise needs different types of removal techniques. Various linear and non-linear methods of filtering are being used for noise reduction. Impulse noise reduction by linear filters are prone to blur the edges. Non linear filters have an upper hand in this case. Few other techniques will be NLM filter, Median filter and Mode filter. Salt and pepper noise, Speckle noise and Gaussian noise are to be discussed in this article. Results of various filtering techniques shall be compared and measured in Peak signal noise ratio (PSNR) and Mean square error (MSE).

Keywords: NLM filter, Mode filter, Median filter, Salt and Pepper Noise, Speckle Noise, Gaussian Noise.

Abstract: The goal of this research is to construct an accurate sign language recognition model by experimenting with several segmentation methodologies and unsupervised learning algorithms. We tested with just up to 10 different classes/letters in our self-made dataset instead of all 26 potential letters to make the problem easier to approach and produce reasonable results. Using a Microsoft Kinect, we acquired 12000 RGB photos and their related depth data. The autoencoder was used to extract features from up to half of the data, while the other half was used for testing. Using our trained model, we were able to attain a classification accuracy of 98 percent on a randomly selected set of test data. We built a live demo version of the project in addition to the work we did on static photos.Techniques for colour and depth segmentation were the most reliable.

Keywords: RGB, Kinect, sign language, accuracy, algorithm, reasonable, dataset.

Abstract: Computer vision is the sphere of computer technological know-how and software system that makes a speciality of replicating components of the complexity of the human imaginative and prescient system and enabling computers to identify and procedure gadgets in photos and movies inside the same manner that people do. Computer vision imaginative and prescient recognizes as well as understands photos, scenes and movies. Image popularity, object detection, photo technology, photograph amazing- resolution and plenty of greater those are the various aspects of computer vision. Object detection or object prediction is widely used for diverse things consisting of face detection, individual detection, vehicle detection, pedestrian counting, object detection, web images, security structures and self-riding motors and many greater. On this mission, we are the usage of rather correct object detection-algorithms and various strategies consisting of CNN, and fast yet especially correct ones like SSD. The use of these methods and algorithms, based totally on deep mastering which is likewise primarily based on gadget mastering require masses of mathematical and deep mastering frameworks knowledge by using the use of dependencies together with Tensor float, Open-CV and so on. We will stumble on very and each object in picture by the area object in highlighted square boxes and discover every object and assign its tag to the object. This additionally offers the accuracy of every technique for identifying gadgets with its name.

Keywords: CNN, RCNN, SSD-300, SSD-512, YOLO

Abstract: "E-waste" is a famous, informal name for the electronic products which are almost reached end of their beneficial life. It is considered as one of the quickest-developing waste on earth. E-waste contains very threatening chemical components along with lead, cadmium, mercury etc. that are harmful to the environment. Many of the digital products may be reused, refurbished, or recycled in an environmentally sound manner so that they may be much less dangerous to the atmosphere. This paper highlights the impact of e-waste on environment and e-waste management.

Keywords: impact of e-waste on environment, e-waste management.

Abstract: Green computing is the utilizing of computers and its resources in environment friendly manner. Green computing was introduced to reduce the environmental problems occurred during the time from developing to disposing of different computer modules and devices. The green computing makes the computer and other devices more energy-efficient.

Keywords: Green Computing, Environment, Computer, IT

Abstract: This study proposes a new universal drone design that can be used in a variety of applications. The drone system has four to twelve rotors and is equipped with movable arms. For the proposed universal drone simulations, a standard eight rotors (Octocopter) and independently controlled twelve rotors (Dodecacopter) configurations are chosen as a comparison study to benchmark the trajectory performance. Furthermore, because the arm lengths of this drone system can be altered, the effect of varied arm lengths can be seen. The lengths of this performance are also investigated. Both systems are compared in five different operating conditions, including without disturbance, with periodic disturbances, and with non-periodic disturbances. When the amplitude was increased by 100% under the periodic disturbing effect, the root mean square of the position errors of the Octocopter and Dodecacopter systems increased by 69.7% and 47.6%, respectively, in the simulations. Similarly, for non-periodic disruptions, both systems saw a 13 percent and 7 percent increase, respectively. According to the obtained results, the octocopter system is partially more stable without disturbing effect while the dodecacopter system is more stable flight than octocopter systems as the disturbance effect grows.

Keywords: Control and design of multirotor UAVs, Modeling in motion simulation

Abstract: This document describes various night vision techniques. "Night vision" is called the technology we provide. It's strange to see in total darkness or improve your eyesight in a dark environment. This technology is one A mixture of several different methods, each with its own strengths and weaknesses. The most common method this section describes Lowlight Imaging, Thermal Imaging, and Illumination. This white paper also gives a brief overview of the various things. The Night Vision Device (NVD), which allows you to generate images at light levels close to full darkness, also explains that various applications that use night vision technology to solve different problems in dark places.

Keywords: Image intensification, Active illumination, Thermal imaging, night vision technology, Night Vision device (NVD)

Abstract: This paper presents an efficient analytical approach to study the performance of interconnection networks namely, Hypercube and Perfect Difference Network. The performance measure has been defined as Link utilization. As the number of processors increases in a system, the processing speed increases. A threshold is reached after which the increase in the number of processors decrease the utilization of the processors as they spend most of their time in communicating the messages. We have compared the Link utilization and topological properties of hypercube and perfect difference network with some simplifying assumptions. The assumptions include that the links are overlap (1-2,2-1) at which a processor can communicate parallel with adjacent processor. Both hypercube and perfect difference network are regular, vertex symmetric and edge symmetric. Keywords- Interconnection Network, Multiprocessors, Hypercube, Perfect Difference Network, Link Utilization.

Abstract: A lot of individuals are applying for bank loans but the bank has its limited assets which it's to grant to limited people only, so checking out to whom the loan is granted could be able to be a safer option for the bank is a typical process. So here we attempt to reduce this risk factor behind selecting the safe person so as to save many bank efforts and assets. This is done by mining the large Data of the previous records of the people to whom the loan was granted before and on the premise of these records/experiences the machine was trained using the machine learning model which gives the foremost accurate result. The foremost objective of this paper is to predict whether assigning the loan to a particular person is safe or not. This paper is split into four sections (i)Data Collection (ii) Comparison of machine learning models on collected data (iii) Training of system on most promising model (iv) Testing.

Keywords: Loan, Prediction, Safe Person, Machine Learning.

Abstract: In interconnection and automation of different physical gadgets, vehicles, home machines and different things, the internet of things (IoT) innovation plays a critical role. These objects associate and deal information with the assistance of software, different sensors, and actuators. A human's standard of life and living are improved with this automation of gadgets, which is a forthcoming need. In this paper we talked about a similar requirement for instance, a smart car parking system which empowers a driver to discover a parking area and a free slot in that parking area inside a city. This paper focus on decreasing the time squandered on discovering parking area. This in turn diminishes the fuel utilization and way of life. With the exponential increment in the quantity of vehicles and total population, vehicle accessibility, use out, about starting late, finding a space for parking the vehicle is turning out to be increasingly more troublesome with realizing the amount of conflicts, for example, automobile overloads. This paper is connected to making a trustworthy system that accept authority over the undertaking of recognizing free slots in a parking area and keeping the record of vehicles left in an extremely methodical way. The predicted system decreases human effort at the parking area generally, for example, in case of looking of free slots by the driver and calculating the portion for each vehicle using parking area. The different advances engaged with this system are vehicle unique proof utilizing RFID labels. payment count is done based on time of parking.

Keywords: IOT, RASPBERY PI, RFID, POWER SUPPLY, LCD.

Abstract: This application is used for terminate the corruption. There are a lot of files in the computer , it is very difficult to find a file. For that, the file tracking system is an application designed to track every task in the software development lifecycle. The client can easily upload and download files and track any file without any difficulty. This application based on two modules admin and User, Admin can see the all files created by the user and Sometimes someone wants to do corruption , he does not even send the file forward, in a way the file is stopped. Admin direct can send mail or message to the user of that department and ask why this file is stuck for so long, what is the reason for keeping it for so long and the user will have to tell about file to the admin. In this way the corruption will stop because the Admin can see each and every movement of the file, so the user will not even hold the files and will approve the file and pass it on to the next receiver.

Abstract: This manifesto focused on understanding of digital marketing growth in banking and small business orientation and reports the results of study design to investigate the impact of product innovation and services. Digital marketing is cost effective having a great commercial smash in both the sectors. The paradigm of marketing activity been shifted from traditional platform to modern digital platforms. When a bank launches a mobile application for transaction at the same time other company will also invent new marketing application for trading. The sequence is based on secondary data. The outline is to examine the aspects of digital marketing inhabit to fill the space and make simplified ways of living life.

Keywords: Digital marketing, Banking, Small business, Marketing trends, Traditional Marketing.

Abstract: Development in Machine Learning algorithms has led to early detection and prediction of fatal diseases. Certain websites help patients to identify such diseases. Many pharmaceutical companies use advanced data mining techniques to extract the data from pathological reports of patients to generate statistical reports and decide their drug supply and marketing strategies. Our software bridges the needs of patients as well as pharmaceutical companies by predicting fatal diseases like brain tumour, diabetes mellitus, lung cancer and cardiovascular (heart) diseases for the patient and generating analytical reports from patient’s data which provide a bird’s eye view of prevalence of a disease within an area for the pharma sector.

Keywords: Machine Learning, Diabetes Mellitus, Lung Cancer, Cardiovascular Disease, Brain Tumour

Abstract: Digital marketing refers to any marketing campaign that uses an electronic device or the internet. Businesses utilize digital platforms such as search engines, social media, email, and other websites to communicate with current and future customers. Although an expert inbound marketer may argue that inbound and digital marketing are almost similar, there are a few minor differences. At this stage, digital marketing is crucial for your company's and brand's visibility. To make a long story short, if you want to stay competitive as a business owner, you'll need to embrace some aspects of digital marketing. Because digital marketing provides so many options and concepts, you may be creative and experiment with a variety of marketing tactics on a budget. You can also track the success and ROI of your campaigns more readily with digital marketing than you could with traditional promotional content like a billboard or print ad, thanks to technologies like analytics dashboards. The best digital marketers are able to identify how each digital marketing activity helps them achieve their overall goals. Marketers may also use the free and paid channels available to them to assist a larger campaign, depending on the goals of their marketing strategy. We'll go through these specific digital marketers in more depth in a bit. Digital marketing may assist any company in any industry. Regardless of what services your company provides, digital marketing still requires creating buyer personas to better understand your target audience's demands and creating valuable online content. That isn't to say that every business should implement a digital marketing strategy in the same way.

Keywords: Business, Digital Marketing, Business Strategy

Abstract: Library plays an important role in providing people with reliable content. Although digital technology growth rapidly in the 21st century, but the importance of library is still there for its users. The rapid growth of information technology has considerably increased our capacity to process information and exponential growth in the information sector. The effect of information technology rises from its hallmarks such as enabling technology which can be applied in a different range of circumstances, the capacity of the technology increased very fast ; and the cost of the technology falling rapidly. Ambience of libraries needs to be changed because the documents of library is moving toward a digital platform and Internet access of library documents is becoming more user friendly. The implementation of modern technology in libraries is very important now.

Keywords: Library, digital , knowledge, information technology.

Abstract: Marketing Principles lies at the heart of the field of marketing management and is vital to the practice of marketing. It is also the scenario within which many of the imperative challenges identified by the companies. In this paper, we uncover various components of marketing mix of BYJU’S learning application. BYJU’S is India’s giant ed-tech and online tutorial platform developed in 2011. During this pandemic their product has reached over 115 million registered students across the globe via distance learning, e-learning and m-learning. BYJU’S the learning app has become one of the world’s largest e-learning platform currently valued at $21 billion. How far the principles of marketing have influenced the company in securing this drastic growth will be elaborated throughout the study.

Keywords: Marketing Principles, BYJU’S, E-learning, M-learning, Online learning platform.

Abstract: In this era ICT is used in everywhere to solve the human problems and perform smooth functioning of each and every task of life. In this paper to study the impact of ICT tools in the Management research. This presents research, which identified the benefits in using ICT, the challenges when it comes to managing it, communal performance and the attitudes of executives, and the relationship that exists among these dimensions in subject of Management research. The contribution is to increase the knowledge about the dimensions of the use of this technology, as the relationship among them and the technology, and among the dimensions themselves, and to present a framework for analyzing this use. To analyze or classified the data using SPSS.

Keywords: - ICT, Impacts of ICT, SPSS, Management Research

Abstract: Computers and phones may be more common than ever, but most people still prefer the traditional way of writing with ink on paper. People in the rural parts of India are mostly comfortable with the pen and paper way of going about their work. But with rapid technology advancements, everything has gone digital from Aadhar card forms to Birth Certificates. Despite this easy availability of a vast number of technical writing tools, many people choose to take their notes traditionally in the written manner in the language they are comfortable with, which is usually Hindi. Our work is on word recognition of handwritten Hindi characters and its implementation on handwritten forms. Our paper introduces an end-to-end word spotting system for the Hindi language using Segmentation based approaches. Our proposed architecture implements an end-to-end strategy that recognizes handwritten Hindi words from printed forms and is translated into English. Hence, handwriting recognition and translation interpret the Hindi handwritten input from various handwritten sources, such as paper documents, forms, into digital form translated into English. A form recognition system handles the formatting, performs correct segmentation into characters, and detects the Hindi words, which are then translated into English and shown on the form. The computational study of people’s opinions, sentiments expressed is termed as sentiment analysis which is also known as opinion mining. For the feedback forms, sentiment analysis is performed using Random Forest algorithms and NLTK libraries like Porter stemmer and Stop words are used giving an accuracy of 88%.

Keywords: OCR , NLP , Image Processing , Sentiment analysis

Abstract: In the few recent years, common major diseases have emerged together of the foremost common causes of deaths worldwide. As the changing in lifestyle, food habits, working cultures etc, has significantly contributed to the present issues related to health across world-wide including the developed, underdeveloped and developing countries, a challenge to the medical science to overcome from this situation[1]. As per as WHO (World Health Organization) Global Health Estimates report is concerned, an estimated 74% of all deaths were noncommunicable diseases globally, 3 out of 10 major diseases are communicable. In this paper, we have taken 5 major diseases (Ischaemic Heart Disease (IHD) with Stroke, Chronic Kidney Disease (CKD), Diabetes Mellitus (DM) including BP, Chronic Liver, and Cancer) among the top 10 deadliest diseases[2]. All these major diseases can be curable with proper diagnosis and early detection. The purpose of this paper is to establish some Machine Learning supervised algorithms with some hybrid approach for better comparative analysis and predict for the particular disease at an early stage with a greater accuracy level. The outcome of this paper also justify that the hybrid algorithm model has better processing, performance with more accuracy outputs so as to help the medical and healthcare sector in the early stage disease prediction.

Keywords: Algorithm, Classifier, Machine Learning, Predictive Analysis.

Abstract: Learning Management System provides a simple interface for maintenance of different student, department, faculties, library and others information. All the colleges usually have a number of departments and educational modules such as courses, seminar hall, etc. Managing all these departments and other modules manually is a very difficult and hard, ineffective and expensive task. So here we propose an Learning Management System for college. Learning Management System has all the information about the students, teachers, events, library, departments and other respected information. The system allows the admin to manage accounts of all the users. Teacher can add stuff, schedule meeting, add attendance ,add grades, etc. Students can have access to all the stuffs provided by teacher. An online meet feature where online meetings and lectures can be conducted within the application only. An e-library, Notes section and Chat feature will be available. A discussion forum where alumni and students can interact. Technical News and T&P related materials will be available. The main purpose is to create a user-friendly environment, where students, faculty and admin can interact and the workload of each of one will be less.

Abstract: We have Aadhar card, Pan card, driving license like identity proofs for our day-to-day transactions, but we have a major missing feature that is our health card, which manages our day-to-day health history like disease, allergy etc. And the same card is used everywhere in private and public hospitals and clinics, medical stores, laboratories to track your health-related data, which the concerned entity will enter the system. We aim to gather only health related data, so we are not aiming to involve any economical transaction into the system. We are proposing an Environment where all the Medical Reports will be managed by our system and provided to the user through our portal. Managing all Reports, Prescription, Medical History arranged in Time Frame format so it can be accessed easily whenever needed. Only doctors and authorized hospital staff can insert the health reports in the system. Patients can only access the reports in read only mode. This will give Real time information to health authorities so that action can be taken at the right time and thus it can save many people from becoming victims of some viral disease. We aim to gather only health related data, so we are not aiming to involve any economical transaction into the system. The health card will store all the scans, x-rays, prescriptions and other health related documents of a patient. It will also include details of patients' long-term conditions, allergies, etc. The health records can only be edited by authorized staff of a hospital and care system involved in the patient's direct care. This health card will make it easier for doctors to operate under emergency conditions.

Keywords: Health care, data management, prescriptions , medical history.

Abstract: Reverse-engineering malware is an important task in cyber security. The thesis presents a method for malware analysis which helps to detect the possible threats and by-pass vulnerabilities using hypervisor-based method. The purpose of this study is to develop a thin hypervisor with a monitoring component to provide a data security and protection to the host system. Also, the thesis aims to provide a behavioral based malware analysis on a malware lab to hunt for various malware with evasion resistance. The thin protective hypervisor aims to analyze the threat behavior and mitigate those using innovative monitoring component with better performance, transparency, kernel integrity and scalability.

Keywords: Hypervisor, Virtual Machine, Monitoring Component, Malware, Virtualization, Cyber Security

Abstract: The spread of Covid-19 has resulted in worldwide health concerns. Social media is increasingly used to share news and opinions about it. Therefore, it is the need of the hour to implement different measures to safeguard the countries by demystifying the pertinent facts and information. This paper focused on sentiment analysis on Twitter data related to Covid-19 using RNN. Originally, the input data collected from the dataset are pre-processed and applied to the sentiment lexicon dictionary for estimating sentiment values. The output data with the sentiment values are clustered using the Probability-based K- medoid algorithm to find whether the tweet caries any sentiment or not. Then from clustered results, the important is extracted and tagged using Part of Speech (POS). Then the Optima POS words are selected by using the Uniform Distribution based Cat Swarm Optimization (UD-CSO) algorithm and are subjected to Xavior initialization and Linear Logistic based Recurrent Neural Network (XL2-RNN) for classification. The experimental results indicated the effectiveness of the proposed sentiment analysis model.

Keywords: Probability-based K- medoid algorithm, Uniform Distribution based Cat Swarm Optimization (UD-CSO), Part of Speech (POS), Xavior initialization and Linear Logistic based Recurrent Neural Network (XL2-RNN), Covid-19 tweets, Sentiment Analysis

Abstract: Data analysis is crucial for decision support in every firm, whether it is a manufacturing unit or an educational institution. Data mining techniques are used in a wide range of fields. This paper proposes the use of data mining techniques to improve the efficiency of higher education institutions. When data mining techniques such as clustering, decision trees, and association are used to higher education processes, they can aid in improving student performance, life cycle management, course selection, retention rate monitoring, and grant fund management. This is a strategy for determining how data mining tools affect higher education. Educational Data Mining (EDM) is an interdisciplinary research area focused on data mining's application in the field of education. It uses a number of tools and techniques from machine learning, statistics, data mining, and data analysis to analyses data created during teaching and learning. Educational Data Mining is the process of converting raw data from large educational databases into useful and meaningful information that can be used to better understand students and their learning environments, improve teacher assistance, and make educational system decisions. The goal of this research is to give a broad overview of educational data mining, including its uses and benefits.

Keywords: Educational data mining (EDM), learning analytics (LA), knowledge discovery in databases (KDD), data mining techniques, data mining methods. EDM tools, visualizations tools.

Abstract: The production of grains in the world can be estimated to be in millions of tones every year. This paper focuses on major staple food grains consumed globally – The wheat, The quality and standard of the grains vary significantly due to differences in the physiological, growing conditions, crop management culture, grains management and different storage techniques. The grading of grains is based on their physical appearance and chemical characteristics. Thru the visual inspection the external features such as size, texture and color can be measured by comparing with the standards which are set by quality teams of individual countries every year. The chemical properties can be moisture content and the amount of nutrients present in the grains. The moisture content can be measured by specified moisture meter. The amount of nutrients present in the grains, for example the protein content in the wheat can be determined using a near-infrared spectroscopy based instrument. It is necessary to develop a fast, accurate and automated system to monitor the grading factors. There may be a chance of the grain being infested (presence of insect inside the grain). This paper concentrates on different digital imaging techniques to evaluate the grains standards.

Keywords: Computer vision system, image processing, soft X-ray imaging, near-infrared spectroscopy, Spectral imaging, Thermal imaging.

Abstract: One of the most global challenges met by the data analyst is to analyze large amount of stored data and extract essential information. The task of extracting the data is required for future predictions in many sectors of that matter. The predictions are made using forecasting models to take necessary actions for decision policy making. J48 Decision tree algorithm is one of the best techniques to make predictions on nominal data. The paper focuses on implementing and proposes an approach to predict Student results using J48 Algorithm. The entropy of information is measured using student dataset. Based on the predictions made, the educational institutions can make decisions to improve the quality of results. The task is carried out using Data mining tool such as Weka.

Keywords: J48 Algorithm, Decision Tree, Forecasting models, Nominal data, Data mining tool, Weka.

Abstract: Phishing attack is one of the commonly known attack where the information from the internet users is stolen by the intruder. The internet users are losses their sensitive information such as Protected passwords, personal information and their transactions to the intruders. The Phishing attack is normally carried by the attackers where the legitimate frequently used websites are manipulated and masked to gather the personal information of the users. The Intruders use the personal information and can manipulate the transactions and get definite from them. From the literature there are various anti-Phishing websites by the various authors. Some of the techniques are Blacklist or Whitelist and heuristic and visual similarity-based methods. In spite of the users using these techniques most of the users are getting attacked by the intruders by means of Phishing to gather their sensitive information. A novel Machine Learning based classification algorithm has been proposed in this paper which uses heuristic features where feature selection can be extracted from the attributes such as Uniform Resource Locator, Source Code, Session, Type of security involve, Protocol used, type of website. The proposed model has been evaluated using five machine learning algorithms such as random forest, Decision Tree, Logistic regression. Out of these models, the random forest algorithm performs better with attack detection accuracy of 92%. More over the Random Forest Model uses orthogonal and oblique classifiers to select the best classifiers for accurate detection of Phishing attacks in the websites.

Keywords: Phishing attack; Personal Machine Learning; Classification Algorithms; Cyber Security.

Abstract: UNESCO has called all countries to implement AI Education to all levels of students. In India, efforts are in full swing to bring awareness to teachers to equip themselves to teach the concepts of Artificial Intelligence, use Artificial Intelligence tools for imparting education and create awareness and use Artificial Intelligence tools and applications in various fields. This study aims to analyse the implications of this effort by the various policy makers and also study the risks and related ethical issues.

Keywords: Artificial Intelligence, Education, Higher Education, NEP 2020, Digital Fluency, Beijing Consensus,

Abstract: The challenge in most of the establishments including library and information systems in developing countries like India is the collection, organization, dissemination and management of information. Information management focuses on improving the effectiveness of academic institutions by managing information as a hub, providing access to relevant information resources in a timely and most cost-effective manner. Effective information management systems enable institutions to have meaningful, reliable and accessible information when needed and providing mechanism for ensuring accountability and managing risk. There has been concern for educational institutions in a country like India to overcome this problem arising from insufficient storage, funding, infrastructure, flow and utility of information. Inadequate access to/or gaining relevant information has negative impact on the effectiveness of decision-making of knowledge stakeholders. Librarians and other information managers must identify the dynamic user community and their need of information, engaging competent professional staff to administer the information management systems, nurture the informational and knowledge professionals, automate the library and adopt proper information management strategies to improve the efficiency of information in higher educational institutions.

Keywords: Information, Information management, Information professionals, academic libraries, strategies