VOLUME 12, ISSUE 1, JANUARY 2023

Keywords: Augmented Reality (AR), Artificial Reality (AI), Virtual Try-On (VTON), Photo-Realistic Image

Abstract: Comparative Machine Learning Analysis on Electrocardiogram (ECG) Anomaly Detection. Anomaly Detection on the ECG dataset of 4998 patients was done with each patient having 140 data points, around 7,00,00 data points. Data is divided as 4998 patients learning data. Machine Learning (ML) model is created using Algorithms like Logistic Regression, Decision Tree Classifier, Random Forest Classifier, and Support Vector Machines on which and remaining 1000 patient data is tested to get accuracy to check whether the model has learned correctly. The same is again analyzed by Deep Learning algorithms like RMSProp, Adam Optimization, and SGD.

Keywords: Anomaly detection, Electrocardiogram (ECG), Machine Learning (ML), Deep Learning (DL), Artificial Intelligence (AI), SVM (Support Vector Machines).

Abstract: Beyond the infinite lighting options, smart poles offer many Smart City technologies, including electric car/vehicle (EV) charging unit, panic button, CCTV, Audio Speakers and Mobile equipment, weather stations and photovoltaic (PV) units within internal batteries and inverter, sized as applicable. Smart poles can improve parking and traffic management through real-time data, leading to a reduction in congestion and emissions. It can also monitor air quality and detect and notify officials about street flooding. The heart of the system is the solar panel which makes the entire project self- sustained. The entire system is powered by solar panel. It is equipped with the most efficient solar panel technology to power the smart pole. The proposed work uses ESP8266 WiFi module which analyses the input data and acts according to it. Multiple environmental sensors like humidity and temperature, gas sensors for measuring, monitoring, and recording environmental parameters and for pollution deduction. Smart pole integrates SOS button that will help our citizens to communicate with the services like hospitals or police, in emergency situations like thefts, and accident. Live streaming camera to provide surveillance of the surroundings gives security. This will be monitored by the authorities for providing the responses through the control room. Display board provides information of the environmental conditions and conveys messages to the public. Loud speaker system is used to alert the public in case of emergency and dissemination of information regarding pollution level and traffic

Keywords: Smart Pole, DBOOT model, Internet of Things (IoT), Solar Power

Abstract: Suicide has been a world problem, that has no respect or regard for its victims. Suicide treat is like a moving invisible virus that can capture anybody regardless of age, sex, county and seems to have no cure because you do not know who might be the next victim. But due to a lot of data collected on death rates caused by suicide based on age, generation, gender, county and research on prevention, we have been able to see that suicide might have a cure and can be prevented through various methods mostly involving mental, emotional and financial health. This research paper shows that indeed an individual can escape the wave of this invisible virus called Suicide.

Keywords: CDC, suicide, ML, mental health.

Abstract: Windows Server is a line of operating systems developed by Microsoft that are designed to be used in a networked environment, such as a corporate network or a cloud computing environment. Windows Server is designed to provide a secure and reliable platform for business-critical applications, and it offers a range of features and technologies that can help organizations to manage their IT infrastructure efficiently and effectively. Windows Server is available in a variety of editions, including Windows Server Standard, Windows Server Datacenter, and Windows Server Essentials. Each edition is designed to meet the specific needs of different types of organizations, from small businesses to large enterprises. Windows Server includes features such as support for virtualization, active directory, and a range of security and networking capabilities. It is designed to be scalable, reliable, and secure, and can be managed through a graphical user interface or through command-line tools and scripts. Windows Server is a popular choice for businesses because it provides a stable and reliable platform for running applications and storing data. It can be easily integrated with other Microsoft products and is compatible with a wide range of hardware and software platforms. Overall, Windows Server is a powerful and flexible operating system that can help organizations to efficiently manage and secure their IT infrastructure and resources.

Keywords: VIRTUALIZATION SOFTWARE, VMWARE, HYPER-V, DHCP, DNS, ACTIVE DIRECTORY.

Abstract: Smart supply chain is a must, not a choice, in the age of Industry 4.0 to meet global demands. This paper attempts to classify how Artificial Intelligence (AI) contributes to smart supply chain organization by systematically reviewing the existing literature. The article focuses on addressing the current research gap of artificial intellect in smart source chain management. Additionally, the research paper tries to identify how AI and Microsoft 365 are used in smart supply chain management to improve their effectiveness. Thus, the paper identifies the existing and possible AI techniques and Microsoft dynamics 365 to facilitate the research and practice of supply chain management. The main areas covered in the study on how AI is used in smart supply chain management include AI in intelligent delivery management, implementation of AI in Facebook, AI in smart retailing, and AI in smart manufacturing. In addition, the research demonstrates how smart supply chain utilizes Microsoft 365 by focusing on Supply Chain Managing and Microsoft Energetic forces 365, the Benefits of Microsoft Energetic forces 365 Supply Chain Management, Why Microsoft 365 Should Be Used in Smart Supply Chain Management, and Features of Microsoft 365 in Smart Supply Chain Management. This research paper offers perceptions via orderly examination and synthesis. Moreover, the research provides recommendations on how an intelligent supply chain can be improved using artificial intelligence.

Keywords: Smart supply chain management (SCM), Machine learning, artificial intelligence (AI), Microsoft 365, Microsoft dynamics 365, manufacturing, smart delivery, and retailing

Abstract: Brain tumors are one of the most threatening types of tumors in the world. Magnetic Resonance Imaging (MRI), a popular non-invasive strategy, produces a large and diverse number of tissue contrasts in each imaging modality and has been widely used by medical specialists to diagnose brain tumors. However, the manual segmentation and analysis of structural MRI images of brain tumors is an arduous and time-consuming task which, thus far, can only be performed by a professional neurologist. Our project aims to simplify this process with the help of machine learning algorithms so as to efficiently detect brain tumors in an MRI using a computer. In this project we use two different machine learning models to compare their success and loss rates and to also identify which algorithm performs better. The two machine learning algorithms being used are LeNet-5 and a self-designed model of convolutional neural networks (CNN). The loss rates of the two models can be compared through our project. In a recent study, researchers developed a model based on deep learning to analyze data. The model used inputs from a psychological questionnaire to estimate an individual’s psychological age and so on. We believe this project will have a great significance in the coming future not only in relevance in the medical industry but in the technological industry as well.

Abstract: This paper presents and modern approach for water metering it uses a real time approach of monitoring the standard water quality parameters and store them for further analysis and reporting purposes. Considering the ever-increasing demand of water and the purity it become essential to develop the SMART System which can provide the real time data for decision making purposes at various ETP, WTP and STP plants. The proposed solution is one of the solutions which uses today’s technology IoT to resolve the above problems. This paper directs by taking initiative steps for presenting the water level and quality monitoring. The approach here is to collect the real time data from various sensors (water flow sensor, pH sensor, water control valve and water level sensor) and can further be monitored on software, website or mobile devices. After capturing the data from the various sensors, the data can be processed with microcontroller and stored in database and further with the help of wireless module it can be sent to the cloud environment from where it can be accessed 24x7 anywhere anytime via internet.

Keywords: Real time monitoring, water quality monitoring, IoT, cloud environment, Ph sensor, water flow sensor, water level sensor, Microcontroller, Software, Website, Wireless module

Abstract: This paper aims at identifying the different categories of information disclosed by the going public firms and practices adopted by them at the time of IPO issue in their IPO prospectus in India. The paper adopted the thematic analysis qualitative approach to identify the information contents for the 139 firms from their IPO prospectus for the period from January 2012 to December 2020 downloaded from SEBI website. The paper identified the 12 themes representing the information categories and described in the paper. The paper also describes the themes and sub themes, their keywords and their relative importance for the Indian firms and the investors.Even though many firms in developing economies have started reporting and managing valuable informationboth mandatory and non-mendatory, real information disclosure is still at infancy stage and is mostly restricted to intellectual capital so far as it adds value to the competitive advantage of the companies. Keeping in view such issues, present study is conducted on information disclosure in IPO prospectus of selected Indian companies going public.

Keywords: IPO, prospectus, thematic analysis, information disclosure, intellectual capital

Abstract: Education refers to the knowledge, insights, and skills inherited by students from teachers. An Outcome Based Education (OBE) system can measure the students’ capabilities and performance. The National Board of Accreditation (NBA) is the supreme accreditation body for Engineering and Management Programs in India. This paper is based on Criteria 3 of the Self Assessment Report (SAR) for NBA. Criteria 3 is focused on the attainment of Course Outcomes (COs) and Program Outcomes (POs) by a department and its courses as a part of Outcome-based Education (OBE).

Keywords: Detection, Anomaly, Normal-abnormal, Neural-Network

Abstract: In the digital age, cloud and mobile applications have emerged as crucial channels for businesses to interact with their customers and digitalize purchasing patterns. As they transition to digital transformation, convenience stores have created mobile applications to interact with and collect customer data. Mobile application user experience research is essential since it paves the way for a successful digital transformation. This study aims to examine consumer perceptions of mobile applications or online reviews used by convenience stores. In order to empirically assess online evaluations for mobile apps, this study recommended using a model of the quality of mobile apps as the theoretical groundwork. Numerous internet customer reviews provide vital strategic advantages for organization and service design. This study proposes a framework for studying online shoppers’ customer feedback and how it affects the business overall.

Keywords: Online experience, Customer Satisfaction, AI framework, Mobile app, NLP

Abstract: The demand to reach and satisfy audiences world- wide increases the number of influencers and content creators on social media, which is the primary platform to disseminate their work. Each video could potentially get thousands of comments as a content creator grows, and these comments acts as direct feedback from the viewers, also as major means of understanding viewer expectations and improving channel engagement. We have proposed approach to classify social media comments into five categories namely good, discussion, motivational, demotivating and abusive. In this paper we have elaborated comparative analysis between the available machine learning classification algorithm like Logistic Regression, SGD Classifier, and Random Forest. Index Terms: Machine Learning, Natural language Process- ing, Logistic Regression, SGD Classifier, Random Forest

Abstract: Data analytics is the process of analysing unprocessed data to derive conclusions. In this paper, we'll examine the trends in employee turnover and the factors that influence them. A model that can forecast whether a specific employee will leave the organisation or not will be developed. The objective is to develop or enhance various retention methods for selected staff. The paper presents data pre-processing, the initial step in data analytics. Techniques for data pre-processing transform unusable data into useful forms. Real-world data are frequently insufficient, inconsistent, and full of inaccuracies. Analysis and prediction are of higher quality when these factors are eliminated. Inference, or the process of drawing conclusions, is the main emphasis of data analytics. In this paper 2 out of top 3 strategies affecting employee turnover are being analysed and graphs plotted. The 3 top features include evaluation v/s exit, average monthly income v/s exit and satisfaction v/s exit.

Keywords: examination of raw or crude data and drawing conclusions- data analytics, employee turnover pattern, data pre-processing, evaluation v/s exit, average monthly income v/s exit and satisfaction v/s exit.

Abstract: Mining of data from large data sets and the process of discovering patterns using statistics, machine learning, data correlation, data plotting or data visualization and data evaluation are called data mining. Data analytics and data mining are a subset of Business Intelligence (BI). In our previous paper titled “Data Science to Analyse Employee data” the process of data pre-processing was demonstrated by writing a program in Python. Libraries like pandas, numpy, seaborn and matplotlib of Python provide platform for computing, evaluation and visualization of acquired data. [1-2] In this paper we demonstrate three analytical tools- plotting and evaluating, correlation and data prediction/ Machine learning which are involved in data mining and analytics of company’s data. The company wants to understand the factors contributing to employee turnover and to think of various retention strategies.

Keywords: Python, analytical tools- plotting and evaluating, correlation and data prediction/Machine learning.

Abstract: This project is aimed at development a Web application that depicts online shopping of plants, seeds ,fertilizers and flowers etc. products .Using this software , companies can improve the efficiency of their services. Online Shopping is one of the application to improve the marketing and sale of the company’s products. This web application involve all the basic features of online shopping. As getting the information from various research papers and other sources we analyse that many peoples want to buy a plants and they directly concerned to nursery but sometimes people doesn’t know specific information about particular plant items as well seller is not technically skilled. Customer doesn’t compare plants pricing with different shopkeeper as well as in nursery there is no facility for online payment only cash may consumed.So, in this case e-nursery is platform where customer can compare plants pricing and make online payment easily. Customer service is extremely important. We want each customer to have a pleasant shopping experience, and it is the intention of our staff to answer questions with expertise and to offer advice when we feel it is needed. Retain customers to generate repeat purchases and make referrals. Continue to expand daily sales by adding to the variety of plants we sell. Communicate with our customers through creative advertising.”

Keywords: Recommender System, E-Commerce, Product Sales, Social-media Marketing

Abstract: Our paper introduces a gesture human action recognition system to monitor the various human actions and aids in the creation of the Human Robot Interaction (HRI) interface. The depth image of the person is initially acquired using the Kinect sensor 2.0, while the colour image is initially obtained using the RGB Sensor. The Histogram of Oriented Gradient (HOG) Features is calculated by combining the data from the image and the colour image into a single image. Finally, these traits are transformed into robot-recognizable actions. This system is capable of identifying a wide range of human behaviours, including walking, waving the left and right hands, bowing, and holding the left and right hands. Neural Network (NN) classifiers are being used to recognise the different gestures. In essence, Haar cascade classifiers are used to examine if a picture matches both positively and negatively. The actions taken by the human are what determine the robot's entire movement. The person standing in front of the Kinect sensor is completely responsible for controlling the device. This can be utilised as a real-time application and put into action as a human replacement where necessary.

Keywords: Kinect sensor 2.0, Human Robot Interaction (HRI) Interface, Histogram of Oriented Gradient (HOG), Neural Network (NN), human action recognition system, RGB Sensor, real time application and Haar cascade classifiers.

Abstract: Counterfeit products have been a significant factor in the manufacturing of goods in recent years. This has an impact on a company’s brand, sales, and bottom line. Blockchain technology is used to identify genuine goods and identify counterfeit goods. The distributed, decentralized, and digital ledger that houses transactional data is called blockchain technology. Many databases store information in the form of blocks that are linked together via chains. Blockchain innovation is secure technology, therefore no block can be altered or compromised. Blockchain technology allows for Customers or users do not have to rely on other users to vouch for the security of the product. Quick Response (QR) codes, a developing trend in wireless and mobile technologies, were used in this project a strong strategy to combat the problem of product counterfeiting. A QR code scanner is used to identify fake goods because each product’s QR code is connected to a Blockchain. Therefore, this system may be utilized to store product information and its produced unique code as database blocks. It requests the user’s unique code, then checks it against entries in the Blockchain database. If the code matches, the customer will receive notification; if not, the consumer will receive notification that the product is a fake.  General Terms: Blockchain, SHA-256, QR-code.

Keywords: Blockchain, Data Flow, Challenges, Future scope.

Abstract: In recent times, drastic climate changes and lack of immunity in crops has caused substantial increase in growth of crop diseases. This causes large scale demolition of crops, decreases cultivation and eventually leads to financial loss of farmers. Due to rapid growth in variety of diseases and adequate knowledge of farmer, identification and treatment of the disease has become a major challenge. This paper proposes Artificial Intelligence (AI) system classifies and identifies the leaf diseases early using K-Means clustering algorithm and Support Vector Machine (SVM) classifier. The model serves its objective by classifying images of leaves into diseased category based on the pattern of defect.

Keywords: Leaf disease, Image processing, Artificial Intelligence, Keras.

Abstract: India is mainly an agricultural country. Agriculture is the most important Occupation for the most of the Indian families. It plays vital role in the Development of agricultural country. In India, agriculture contributes about16%of totalGDPand10% of total exports. Water is main resource for Agriculture. Irrigation is one method to supply water but, in some cases, there Will be lot of water wastage. So, in this regard to save water and time we have Proposed project titled automatic irrigation system using IoT. In this proposed System we are using various sensors like temperature, humidity, soil moisture Sensors which senses the various parameters of the soil and based on soil Moisture value land a gets automatically irrigated by ON/OFF of the motor. These sensed parameters and motors status will be displayed on user channel.

Keywords: GDB – Gross Domestic Product, Internet of Things

Abstract: Building an online voting system that satisfies the legal requirements of legislators has been a challenging task for a long time. The exciting technology with respect to the same is the Distributed Ledger technologies. Block chain is one such technology that offers an infinite range of applications. In this paper, block chain technology is used as a service to implement distributed online voting system by identifying the legal and technological limitations of using block chain as a service. A novel online voting system has been proposed that addresses all the limitations discovered. The paper evaluates the potential of distributed ledger technologies such as the process of election and implementing a block chain-based application. As a result, the security is improved and the cost of hosting a nation-wide election is drastically reduced.

Keywords: Block chain, Distributed Ledger

Abstract: Now-a-day’s technology is running with time; it completely occupied the life style of human beings. Even though there is such an importance for technology in our routine life there are even people whose life styles are very far to this well-known term technology. So, it is our responsibility to design few reliable systems which can be even efficiently used by them. Automatic Room Temperature Controlled Fan Speed Controller is one of them. The developed system provides an environment in which no user needed to control the fan speed. Automatically control the fan speed by sensing the room temperature. These fascinating efforts to create intelligent system are to provide human being a more convenient life. The circuit was designed using electronic components available in local market to keep the cost at low level. Index Terms: DHT 11, Room Temperature, Home Automation, Fan Speed, Low-cost

Abstract: Internet of Things (IoT) and Artificial intelligence (AI) are two of the fastest growing technologies in the world. As more and more people move to cities, the concept of a smart city is not foreign. The idea of a smart city is based on transforming healthcare by increasing efficiency, reducing costs, and putting the focus back on better patient care. Implementing IoT and AI for remote healthcare monitoring (RHM) systems requires a deep understanding of the various frameworks in smart cities. These frameworks come in the form of underlying technologies, devices, systems, models, designs, use cases, and applications. The IoT-based RHM system mainly uses AI and machine learning (ML) by collecting various datasets and data. On the other hand, the methods of ML are widely used to create analytical representations and integrated into clinical decision support systems and various forms of healthcare services. After careful consideration of each factor in clinical decision support systems, individualized treatment, lifestyle counselling advice, and care strategy are suggested to patients. The technology used helps support health applications and analysis of activities, body temperature, heart rate, blood glucose, etc. With this background, this paper provides an overview that focuses on identifying the most relevant health applications in the Internet of Things (H-IoT) supported.

Keywords: Design Thinking, Internet of Things (IoT) and Artificial intelligence (AI)

Abstract: Object detection has been used in many of the field now and it has become the main reason for the development of many applications of the auto driving cars, Statistics and etc. In this paper we will see how the YOLO algorithm works and how it is more efficient than other object detection algorithms using the comparison graphs with the various versions of the YOLO algorithm and other algorithms such as Convolutional Neural Networks, Fast-CNN, etc., In this algorithm, the dataset used for object detection can predefined dataset or dataset manually generated according to the use cases. The experimental data has been taken for the testing of the YOLO algorithm and the dataset is trained and tested with given dataset. Here the image is converted into bounding boxes to which a particular value is given so that it is faster in detecting the images than other object detecting algorithms.

Keywords: Object detection, Fast – Convolution Neural Network, Bounding Boxes, YOLO

Abstract: In recent years, blockchain has received increasing attention and numerous applications have emerged from this technology. A renowned Blockchain application is the cryptocurrency Bitcoin, that has not only been effectively solving the double-spending problem but also it can confirm the legitimacy of transactional records without relying on a centralized system to do so. Therefore, any application using Blockchain technology as the base architecture ensures that the contents of its data are tamper-proof. We will be using the decentralized Blockchain technology approach to ensure that consumers do not fully rely on the merchants to determine if products are genuine. We describe a decentralized Blockchain system with products anti- counterfeiting, in that way manufacturers can use this system to provide genuine products without having to manage direct- operated stores, which can significantly reduce the cost of product quality assurance.

Keywords: Blockchain, Counterfeit, QR code, security.

Abstract: IDMA (interleaved division multiple access) is one of the most developing technology in modern mobile communication. It has gained widespread international acceptance by cellular radio system operators as an upgrade that will dramatically increase both their system capacity and the service quality. The core principle of spread spectrum is the use of noise-like carrier waves, and, as the name implies, bandwidths much wider than that required for simple point-to-point communication at the same data rate. Most third generation mobile communication systems are using CDMA as their modulation technique. In CDMA interleaving is used for multiplexing of several input data over shared media. In CDMA system different type of interleaving schemes are used. In this paper we analyze the performance of these interleaving schemes in multipath fading and additive white Gaussian noise (AWGN) channels. We conclude that different interleaving schemes has different data rates and bit error rate.

Keywords: CDMA, System Model of CDMA, Interleaving, BER.

Abstract: Worldwide Interoperability for Microwave Access (WiMAX) emerged with an aim of providing voice, data, video and multimedia services on mobile phones at high speeds and cheap rates.For this we study system architecture, radio aspects of the air interface (such as frequency band, radio access modes, multiple access technologies, multiple antenna technologies and modulation), mobility and Quality of Service (QoS). For this we need to discuss various modulation schemes such as Quadrature Amplitude Modulation, Quadrature Phase Shift Keying, encoding methods such as RS, CRC, Convolution and OFDM that are vital for performance of WiMax system. Then first compare the performance of different modulation schemes such as Quadrature Amplitude Modulation and Quadrature Phase Shift Keying with these systems and get the best modulation schemes with less BER. Then with the combination of modulation schemes analyze the different encoding schemes such as Cyclic Redundancy Code and Reed – Solomon encoding with these systems. After that redesign the WIMAX system with best encoding and modulation schemes.

Keywords: WiMAX, OFDM, BER, CRC, RS.

Abstract: In wireless communication, higher data rates can be achieved by increased or more efficient use of bandwidth and transmitting power. A key technique for spectral optimization is Orthogonal Frequency Division Multiplexing (OFDM). OFDM is a technique proposed for high-speed wireless LAN by the European Telecommunication Standards Institute and IEEE which is being considered for 4G mobile. OFDM technology is described for physical layer of ETSI’s proposed HIPERLAN standard whose data rate ranges from 6 to 54 Mbit/s depending on Quality of Service (QoS). It is designed to provide Wireless Local Loop (WLL) to core networks, e.g. Asynchronous Transfer Mode, GSM/UMTS or any IP-based multimedia network. Data rate, coding rate and modulation type are determined by the link adoption scheme automatically depending on the channel conditions. There are several ways to utilize the frequency band in a flexible way so that the available bandwidth is utilized to maximal efficiency. These access techniques uses a small portion of available energy with low power spectral density, high data transmission rates, less intercarrier interference and efficient use of bandwidth. The main cause of interference in OFDM system is channel fading, and all the errors are in transmission occurred due to effects of channel. One method that can be implemented to overcome this problem is by introducing channel coding. Channel encoding is applied by adding redundant bits to the transmitted data. The redundant bits increase raw data used in the link and therefore, increase the bandwidth requirement. So, if noise or fading occurred in the channel, some data may still be recovered at the receiver. While at the receiver, channel decoding is used to detect or correct errors that are introduced to the channel. To design an HIPERLAN system with Rectangular 16 – QAM Baseband Modulator and OFDM as a multiple access technique. Then, analyze this system with different interleaving schemes to reduce the interference and improve the performance of system.

Keywords: HIPERLAN, BER, OFDM, Interleaving.

Abstract: OFDM is one of the most developing technologies in modern mobile communication. OFDM is a parallel transmission scheme, where a high – rate serial data stream is split up into a set of low – rate sub streams, each of which is modulated on a separate subcarrier. Increasing the number of parallel transmission reduces the data rate that each individual carrier must convey and that lengthens the symbol period. In present communication systems, increasing the number of users reduces the data rate that each individual carrier must convey and that lengthens the symbol period. Hence, a performance comparison of OFDM system in multipath fading and additive white Gaussian noise channels is presented. The comparison proceeds in two steps. First, design simple OFDM system. Second, a binary modulating signal is transmitted over the system and the bit error rate in multipath fading and additive white Gaussian noise channels is observed. Then first compare the performance of different modulation schemes such as Quadrature Amplitude Modulation and Quadrature Phase Shift Keying with these systems and get the best modulation schemes with less BER. Then with the combination of modulation schemes analyze the different encoding schemes such as Cyclic Redundancy Code and Reed – Solomon encoding with these systems. After that redesign the OFDM system with best encoding and modulation schemes.

Keywords: OFDM, BER, CRC, RS.

Abstract: Human-Computer Interface(HCI) is centered around the utilization of Computer innovation to give an interface between the PC and the human. There is a requirement for tracking down the reasonable innovation that makes successful correspondence between humans and Computers. Human Computer connection assumes a significant part. Consequently, there is a need to track down a technique that spreads a substitute way for making correspondence between the human and computer to the people. As computers helped to learn growing up, the meaning of human-computer communication is quickly extending. Human and PC interconnection has extended as of late. Individual and PC calculations are a need in the work area as well with respect to scholastic purposes. In the proposed framework, we have incorporated face recognition, face following, eye location, and translation of a grouping of eye flickers progressively for controlling a nonintrusive human computer interface. Ordinary strategy for connection with the computer with the mouse is supplanted with natural eye developments. This strategy will help the incapacitated individual, truly tested individuals particularly individuals without hands to figure out effectively and effortlessly purpose. A webcam is expected to secure pictures of facial developments are recorded by the webcam. The picture is preprocessed by flipping and changing over into a dim-scale picture. These developments are additionally charted to a PC screen to likewise situate a mouse cursor. The development of the mouse is naturally changed by the place of the anchor point. The camera is utilized to catch the picture of face development. The framework would take the ongoing video input from the client with the assistance of OpenCV and run behind the scenes. It can play out all mouse controls alongside some other console controls. An extra element to this framework is given by utilizing the Sound to Text (Discourse Acknowledgment) Module. A client can utilize this module to type expected text simply by directing the text to the framework.

Keywords: PWDs, disabled, facial gestures, OpenCV, feature extraction, recognition, HOG, HCI, cursor control, Speech Recognition.

Abstract: Low-power and lossy networks (LLNs) are critical components of the IoT ecosystem. These networks are distinguished by common characteristics such as low resources and a high rate of packet loss. In 2012, the Routing Protocol for Low-Power and Lossy Networks (RPL) was suggested as a routing protocol for such networks. Even though RPL is now standardized and widely acknowledged, there are still areas for improvement, such as load balancing, stability, routing, and mobility support. This review work focuses the limitations and open challenge in RPL. Many researchers are attempted to address this issue in the literature by developing various routing measures that address various aims. This review work makes assessment of the RPL works, their strengths and shortcomings, and provides future directions on the issues.

Keywords: IoT, LLNs, RPL, Routing, Challenges.

Abstract: Several studies have been made on identifying diseases in mulberry leaves, however, identifying nutrient deficiency in mulberry leaves has not been accomplished. The silkworms that feed on nutrient-deficient mulberry leaves produce low-quality silk. There is a great need for identifying nutrient-rich and healthy mulberry leaves for feeding the silkworm to get good quality silk yield. This paper is focused on segregating nutritious mulberry leaves for feeding the silkworms for cocoon formation. The process involves image acquisition, processing, segmentation, feature extraction, and classification. Auto-Encoder is used for feature extraction from mulberry leaves and for discrete them into nutritious and nutrient-deficient leaves. The real-valued feature vectors are passed to machine learning algorithms like the Naïve Bayes classifier algorithm, Support Vector Machine (SVM), and K-Nearest Neighbour (KNN) for classification. Among them KNN provides higher accuracy for segregating the leaves.

Keywords: Nutrient deficiency, Support Vector Machine (SVM), K-Nearest Neighbour (KNN), Naïve Bayes Classifier Algorithm, Auto-Encoder.

Abstract: Smart agriculture and farming is a big input field for economic development. The most population of country like India depends on agriculture and smart farming. In this paper, it is proposed to develop a smart agriculture and farming system that uses technologies such as wireless sensor network, Internet of Things (IoT) to help farmers. Sensors are used to get information about the field help farmers to take appropriate decisions on insights and recommendations based on the collected data. Internet of Things (IoT) in agriculture is designed to assist farmers monitor vital information like humidity, temperature, and quality of soil using remote sensors, and to improve yields, plan more efficient irrigation, and make harvest forecasts.

Keywords: Internet of Things (IOT), Smart Agriculture, Smart Farming, IoT based agriculture applications.

Abstract: The Purpose of “Water Refilling Management System” Design is to overcome difficulties in manual operation in refilling station. The difficulty in the manual system is one of The reasons why the efficiency in availing services of the clients is not satisfying and keeping of records is often misplaced and not secure. This system manages to display the data to be filled by the user according to the information of the customer in organize manner, such that their personal details, and the services they want to avail as well as the payment on the transaction they purchased. The system keeps the information of the customer and the details of what they purchased. The system coordinates the arrangement on the delivery of products. It consist all the records for the location of the clients, date of transaction, schedule of delivery, contact number and the person assigned to deliver and the payment of customer to the quantity of product that about to deliver.

Abstract: The new discipline of the twenty-first century is business analytics. A rising number of company operations, including business intelligence, are now managed by machine learning algorithms. The majority of BI systems offer more functionality than just data gathering and reporting. Using the capabilities of predictive analytics, they could potentially offer insights or optimization ideas. In this paper, data collecting comes first. Any gathered or provided data can be examined, and conclusions can be made as necessary. The gathered or provided data is typically in its unprocessed or raw form. Pre-processing data helps to format the data into a usable form by removing noise and redundancy, as well as missing values and non-numerical values. Data analysis and visualization are carried out to improve the statistical analysis of given data. Logistic regression is carried out on the data since it contains lot of columns with categorical values. Accuracy, precision, and f1 score of the model have been measured. Various conclusions can be drawn from this interdependent data set and can be stored as historical data for future analysis. Linear Regression is also carried out on the data set and r-squared values noted. R-squared is a statistical measure of how close the data are to the fitted regression line. For the automotive business, an ML model is created using both logistic regression and linear regression. The manufacturers and sales department can identify their product in the market of the twenty-first century thanks to the help of this business intelligence model.

Keywords: Business Analytics (BA)/ BI (Business Intelligence), Machine Learning, Data pre-processing, Logistic regression, accuracy, precision, and f1 score, linear regression, data analysis and visualization, R-squared, Business Intelligence.

Abstract: Our civilization has become much more computerised, which has greatly improved our ability to generate and gather data from a variety of sources. Almost every element of our lives has been inundated with an enormous amount of data. It is necessary to convert the enormous volume of data into knowledge and relevant information. Data mining is a promising and flourishing field of computer science as a result of this. Data mining is the automated or practical extraction of patterns that represent implicitly stored or recorded knowledge from huge information repositories, such as databases, data warehouses, the web, and other big information repositories or data streams. Any type of data can be used for data mining as long as it has value for the intended application. In this paper, we discuss in detail data warehouse and data warehouse data, which is almost basic form of data for data science applications. We also present to you a typical framework of a data warehouse and data pre-processing techniques. Additionally, we talk about OLAP (Online Analytical Processing) Data Marts, a subset of an organisational data store that is typically focused on a single objective or key data area and can be disseminated to meet business requirements.

Keywords: computerization, data science, databases, data warehouses, data pre-processing techniques, OLAP (Online Analytical Processing) Data Marts, Total Quality Management.

Abstract: Artificial Intelligence and machine learning are the emerging technologies in the world in every fields. Mainly emerging in the security fields. These technologies are promising to improve convivence and comfort of the user by securing the data and resolving the problems like cyber-attacks, communication security, big data security, cloud based, social media, finance, IOT and weapon detection. Many companies promote their product using social media and e-commerce platform. These platforms provide more opportunities for companies to attract customers. Trusting these platforms many customers started purchasing products from them. At that same instant many fake accounts have been created by replicating the organization names. By making online payments through these sites the customers are getting charged for the product they never placed. In this paper, discussion is classified into two parts. First part describes about the security using the AI-ML technologies and algorithms and also a review of AL-ML based security systems and methods, in the second part it describes about online fraud detection by training classification model using ML technology.

Keywords: Cyber-attacks, big data security, IOT, Cloud based, AI-ML