VOLUME 12, ISSUE 7, JULY 2023

Abstract: Hepatitis is one of the most common diseases in the world and any early diagnosis can save the lives of many people suffering from this disease. The purpose of this research is to diagnose hepatitis disease using the combined model of the decision tree algorithm and Harris Hawks Optimization. In this research, the diagnosis of hepatitis disease was made using the decision tree and evolutionary algorithm of Harris Hawks Optimization .  HHO algorithm is a population-based and gradient-independent optimization technique. The main idea of the HHO algorithm is the cooperative behavior and chasing style of Harris's falcon in nature, which is known as surprise attack. The effectiveness of the proposed HHO optimizer method, compared to other nature-inspired techniques, was tested on 29 functions and several real-world engineering problems were investigated. The statistical results and comparisons show that the HHO algorithm has very promising and sometimes competitive results compared to other well-known meta-heuristic techniques [6].

Keywords: Decision Tree, Evolutionary Algorithms, Data Mining, Harris Hawks Optimization (HHO) Works Cited:

Mohammad Ordouei, Mastooreh oeini "Identification of hepatitis disease by combining decision tree algorithm and Harris Hawks Optimization (HHO)", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 12, no. 7, pp. 1-6, 2023. Crossref https://doi.org/10.17148/IJARCCE.2023.12701

Abstract: Food insecurity is a major issue the world over as it is one of the problems bedeviling the human race. The Food and Agricultural Organization, (FAO) predicts that by 2050, there will be 9.6 billion people on the planet and this will require an increase in food production to about 70%. The use of application software resulting to e-agriculture can contribute to solving these problems to a large extent since technology has tremendous impact on the agricultural sector. But the concept and knowledge about the use of these software to enhance agricultural activities remain relatively poor among farmers, especially the smallholder farmers which produces more than 80% of the food consumed. This has resulted to many problems like poverty, health issues, insurgency, and many others.  This work reviews some existing software applications that can be applied to enhance agricultural processes for improved food production.  Key words: Agriculture, Enhancement, Farmer, Software Applications, Productivity, Smallholder Farmer and Crop Yield. Works Cited: Kile, A. Samuel, Agu, N. Monica, Tumenayu, O. Ofut " Agricultural Productivity and Processes Enhancement through the use of Software  Applications: A Review of Agriculture Based Software", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 12, no. 7, pp. 7-11, 2023. Crossref https://doi.org/10.17148/IJARCCE.2023.12702

Abstract: In this paper, the characteristics of Gate-All-Around Field Effect Transistor (GAA FET) with stack high-k are studied by using the Silvaco Atlas simulations. By using of high dielectric constant material in the place of gate oxide reduces the leakage current and improve the Short Channels Effects (SCEs) like Drain Induced Barrier Lowering (DIBL) and Subthreshold Swing (SS). Gate dielectric material of HfO₂ along with SiO2 are used to analyze various electrical characteristics at 22nm GAA FET. The analysis included the ON current, threshold voltage, DIBL, SS, leakage current at 22nm gate length.  Keywords: Dielectric material, subthreshold slope, DIBL

Abstract: Chronic Kidney Syndrome (CKD) is a persistent medical condition characterized by the gradual deterioration of renal function over time. It is a significant global health concern, impacting a substantial number of individuals. With advancements in technology, particularly in the field of machine learning (ML), there is an opportunity to utilize these tools for improving the detection, prediction and supervision of CKD. The objective of this scheme is to develop a extrapolative prototype for CKD and facilitate its management through the application of ML algorithms and techniques. By analyzing extensive datasets comprising patient medical records, demographic statistics, test site outcomes, and other relevant factors, this initiative aims to identify patterns, trends, and threat aspects accompanying with CKD. These insights can assist healthcare professionals in making more accurate assessments regarding CKD progression and devising personalized treatment plans. We propose the consumption of the Support Vector Machine (SVM) machine learning model to forecast CKD based on relevant clinical features. Our findings validate the effectiveness of the SVM model in accurately predicting CKD, achieving an impressive accuracy rate of 94%.  

Keywords: chronic kidney infection; CKD stage identification; machine learning, support vector machine

Abstract: Thyroid disorders exhibit a substantial worldwide occurrence and exert a profound influence on the health and holistic welfare of individuals. Timely identification and anticipation of thyroiditis are of paramount importance, facilitating prompt intervention and well-considered therapeutic approaches. Recent investigations have illuminated the ramifications of thyroid dysfunction on an estimated 42 million individuals in India. Imbalances in thyroid hormones give rise to hypothyroidism and hyperthyroidism, adding to the complexity of these disorders. Essential thyroid tests, such as TSH, T3, T4, and FTI, play a pivotal role in diagnosis, but the manual analysis of extensive databases poses significant challenges and demands considerable effort. In light of these obstacles, this study introduces a Machine Learning approach that utilizes the capabilities of a Decision Tree Classifier. By leveraging data patterns and relationships, the model developed demonstrates high accuracy in predicting thyroid abnormalities. The knowledge offered by the model are valuable, enhancing the understanding of thyroid diseases and aiding in the precise forecasting of these conditions. Incorporating Machine Learning methods to predict thyroiditis represents a significant advancement, Paving the way for early diagnosis and proactive management of thyroid disorders, thus positively impacting public health.

Keywords: Thyroid disorders, Machine Learning, Thyroid hormones, Decision Tree Classifier.

Abstract: A window-based Sign in System prototype for computer lab management system is successfully designed and implements to complement the conventional lab management. In order to monitor user information, and workstation status, admin application system is installed on the admin’s computer. Admin need to approve the user application in this system before they can login and unlock the workstation windows. The admin front panel interface shown is design for friendly monitoring system.

Keywords: management, console, student, lab

Abstract: In recent years, significant progress has been made in developing more accurate and efficient machine learning algorithms for detection of medical images. This study highlights the imperative role of machine learning & deep learning algorithms in enabling efficient and accurate detection in the field of medical imaging. It focuses on several key studies pertaining to the application of machine learning methods to the Parkinson’s disease. PD is a neurodegenerative disorder that affects voluntary movements. The movement difficulty is due to lack of a chemical called dopamine produced by doparninergic neurons in brain. Henceforth the study is based on the classical machine learning algorithms such as supervised, unsupervised and reinforcement algorithms. In addition, several problems and research objectives which is related to the Parkinson’s disease are probed.

Keywords: Parkinson’s disease, Machine learning, Deep learning.

Abstract: The Online Blood Donation Website is a transformative platform designed to address the critical challenges faced in maintaining a consistent and reliable blood supply. The platform serves as a vital link between blood donors and patients in urgent need, facilitating swift and efficient blood donation processes. In today's fast-paced world, traditional methods of blood donation face limitations in reaching potential donors and coordinating donations effectively. The Online Blood Donation Website aims to revolutionize the blood donation landscape by providing an intuitive and user-friendly interface that connects donors with patients seamlessly. In conclusion, the blood donation web page stands as a testament to the power of technology in uniting humanity for a common purpose—to provide the gift of life through blood donation. Its impact is not limited by geographical boundaries, transcending borders to bring hope and healing to individuals in dire need. Together, we can build a world where blood donation is not merely a responsibility but an act of compassion that transforms lives and forges a brighter, healthier future for all. Key Words: React JS, Node JS, CSS, HTML, MongoDB, Mongoose, Redux, Nodemon, VsCode, Netlify.

Abstract: In this research article, we address the critical need for effective Application Performance Management (APM) tools in the face of increasing complexity in modern software systems. As the digital landscape evolves rapidly, driven by technological advancements and ever-changing user expectations, traditional monitoring approaches have become insufficient. We present a comprehensive analysis of the challenges faced by contemporary software, emphasizing the pivotal role that APM tools play in overcoming these obstacles. Our research highlights the critical role that APM tools play in ensuring the seamless operation of modern software systems. By providing real-time insights into application performance, these tools enable developers and operations teams to identify and remediate issues before they escalate into critical incidents. In conclusion, our findings underscore the vital importance of adopting robust APM strategies to address the challenges posed by modern software. As the digital landscape continues to evolve, the demand for sophisticated APM tools will only increase, and we anticipate a growing need for innovative solutions that can adapt to the ever-changing performance management landscape. This research serves the academic and industrial communities to collaborate in developing cutting-edge APM tools that will empower organizations to navigate the complexities of contemporary software with confidence and success.

Abstract: Computer networking is broadly considered including hardware, software, procedures and people. Networking encompasses many activities, such as, creation of network products, distribution processes, user activities, and supporting services like marketing, documentation, information services and maintenance. Network management covers both the establishment of networking operations and actual operation of the network facilities. It includes all management functions performed at such network nodes as computing centres, documentation facilities, and service distribution centres. In the present-day complex networks, network monitoring and measurement has grown in significance. In past decades, administrators could have simply monitored a small number of PCs or network devices.

Keywords: Network Managing System, Synchronized Network, Network Analysis, Nagios.

Abstract: Twitter is a well-known social media platform that has stood a test of time. a large majority of people chose Twitter as their social media channel of choice for trustworthy scientific news and information in many global communities. However, the constraints of The development of affordable data science is hindered by the Twitter app software interface (API). solutions for academic institutions. To fully utilise the data analytics offered by Researchers must pay considerable expenses in order to use Twitter with a free API account. We introduce our big data analytics tool This piece, it was created at Lakehead the University's DaTALab in Canada and lets users to quickly access vast amounts of Twitter data while focus on their search criteria on Twitter. The platform makes it easy to gather net data, which is subsequently cleared up using A series of filters before artificial intellect (AI) is used and ML systems. (AI). Our main area of concentration has been healthcare-related research, demonstrating the platform's potency. The platform itself, however, is adaptable to any intriguing subject. The data. was gathered and processed can be used for additional AI/ML analysis. To highlight the effectiveness of our system for upcoming healthcare research projects, we demonstrate our platform utilising a specific search topic. Index Terms— Big data, social intelligence, analytics, web-based, robotic intelligence (AI), and data mining.

Abstract: The SGPA Calculator project aims to streamline the process of entering and managing semester marks for university students. Currently, students have to individually enter their marks in an Excel sheet in a computer lab, leading to time consuming delays and inconvenience. Additionally, if a student is absent, the process further gets delayed until they come and enter their marks. In cases where a student is unable to attend college, the attendance personnel have to enter their marks separately. To address these challenges, a website has been developed using the MERN stack. The website allows students to conveniently enter their marks through their web browsers after each semester's results are declared. The system automatically calculates the SGPA, percentage, and result based on the entered marks, which are then securely stored in a database. The stored data can be accessed through a dashboard and can even be downloaded in Excel format. This eliminates the need for students to wait or visit the lab, providing a more efficient and user-friendly solution for managing and maintaining academic records.

Keywords: SGPA Calculator, MERN Stack, Web Application, Mark Management, Automation

Abstract: Any organization's success depends on efficient project management. However, it often runs into problems brought on by poor teamwork and communication, which produces subpar outcomes and inefficiency. Web-based project tracking applications have appeared to address these issues, providing user-friendly interfaces and a wealth of capabilities to increase productivity, organization, and efficiency. This study explores the possible benefits of using online project tracking technologies to enhance project management procedures. It examines the main features and advantages of these technologies, including responsive design, work delegation, real-time updates, and progress tracking. The research also looks at how these technologies affect user involvement, project results, and decision-making. The results show that using web-based project tracking tools may better decision-making, increase user involvement, and improve project outcomes, particularly for remote teams. By adding to the project management literature, this study helps firms looking to use technology to improve their project management processes by offering insightful information.

Keywords: project management, collaboration, efficiency, Real- time updates, Task, allocation, Progress, tracking, Responsive design, Project Outcomes, User-engagement, Decision-making, Remote teams.

Abstract: Organ donation and transplantation systems now face a variety of requirements and obstacles in terms of registration, donor-recipient matching, organ removal, organ delivery, and transplantation, all of which are hampered by legal, clinical, ethical, and technical restrictions. As a result, a comprehensive organ donation and transplantation system is essential to provide a fair and efficient procedure that improves patient experience and confidence. In this work, we present a private Ethereum blockchain-based system for managing organ donation and transplantation in a completely decentralised, secure, traceable, auditable, private, and trustworthy manner. We create smart contracts and offer six algorithms, along with information on their implementation, testing, and validation. We assess the performance of the suggested solution by conducting privacy, security, and confidentiality assessments and comparing it to current solutions.

Keywords: Privacy, organ donation, transplantation, blockchain.

Abstract: Our project focuses on developing an Android-based ride-pooling app using Android Studio, Java, Firebase, and Google Maps API. The app allows users to create and join pools for convenient and efficient transportation within the BMSCE college community. The backend is implemented using a Golang server we built, Firebase Firestore, and Firebase Authentication. The app features user authentication, map-based selection of start and destination locations, pool creation with customizable options, real-time ride status updates, payment integration, feedback system, and various API endpoints for pool management.

Keywords: ridesharing, geohashing, golang, firebase, android

Abstract: People with physical disabilities are prevalent in society. People who are deaf or have speech impairments have contact problems. They use sign language to interact with the outside world. Every time they engage with civilization, they are afraid. The mobile application (VOIZE) is made up of a number of modules that help people who have trouble speaking engage with others and express themselves boldly. Each section has a unique attribute. The user can learn sign language and assess their degree of confidence using the app's e-learning module. The sections accessible through the app are, Training, Confidence Level, Virtual Boards, Text-to-sign, Sign-to-text, ASL keyboard.

Keywords: Speech Impaired, Voize, communication, mobile app.

Abstract: During the COVID-19 pandemic, it is particularly challenging to monitor and treat people who are infected with the virus. The indications of COVID-19 are going to be measured with the help of this wearable monitoring device. To provide the effective approaches for helping the covid-19 patients by the proposed model, the model consists of sensors such as temperature, oxygen (Sp0₂), heart rate, GPS for location access, emergency switch provided and camera is attached to view only a covid patient wore it. The Raspberry pi is employed to collect the information from the sensors, the sensor data is displayed on the LCD screen, if the threshold is exceed the information is passed to the nearby hospitals with location of the patient. If the patient is in emergency situation, the switch is provided to inform to the doctors. Another feature is provided, camera is provided to detect the face of the patient using Viola jones which provides the information about the patient is wearing or not. The system is developed using the Python coding and imposed on the raspberry pi to obtain the input from patient. In real time patient’s temperature location can be tracked. If the patient leaves the home the notification is sent to the concerned person.

Keywords: COVID-19, wearable sensor, real time tracking, face recognition, location tracking.

Abstract: A lot of information systems are protected by and have damage minimized by intrusion detection systems. It defends computer networks, both virtual and physical, from dangers and weaknesses. Machine learning methods are currently being widely expanded to create efficient intrusion detection systems. Machine learning techniques for intrusion detection include rule learning, ensemble approaches, statistical models, and neural networks. Machine learning ensemble approaches stand out among them for their effectiveness in the learning process. This study aims to increase detection rate accuracy for all attack kinds and individual attack types, which will aid in the identification of attacks and specific categories of attacks. K-fold cross validation is used to assess the suggested approach, and the experimental outcomes of all three classifiers are examined. UNSW-NB15 dataset is used to measure the performance of the proposed approach in order to guarantee its efficiency.

Keywords: Ensemble Learning, Network Intrusion Detection, , Multi-classification, Random Forest.

Abstract: The automatic face recognition-based attendance system is a technological solution that utilizes advanced algorithms and artificial intelligence to streamline attendance management processes. By analyzing facial features and patterns, the system automatically identifies and verifies individuals, eliminating the need for manual recording and verification. This efficient and secure system accurately captures attendance data in real-time, reducing administrative efforts and increasing accuracy. With its ability to handle large volumes of data and adapt to various environments, the face recognition-based attendance system offers a user-friendly and reliable solution for modern attendance tracking.

Keywords: Face Recognition, Attendance System, Image Processing, Enrollment Process..

Abstract: Legal document Summarization is one of the major applications of Artificial Intelligence for Law. This paper presents a survey of various types of approaches. Legal document summarization approaches are mainly categorized as: Extractive vs. Abstractive, Supervised vs. Unsupervised. Recently, Legal domain specific vs. General Domain Large Language Models for legal document summarization are developed. This paper also presents an overview of state-of-the-art technology using LLMs for Legal document summarization. An innovative approach of Knowledge Representation using Ripple-Down-Rules for document summarization is also presented. The paper also presents evaluation of methods.

Keywords: Include at least 4 keywords or phrases.

Abstract: Trust on a product is the consumer's confidence and belief in the quality, reliability, and performance of a particular item. In today's digital landscape, establishing and maintaining customer trust is paramount for the success of online businesses, making e-commerce trust an essential factor. As we delve into the realm of e-commerce, it becomes evident that understanding this area requires a comprehensive grasp of the dynamics of trust. However, there is a need to look deeper into the factors that influence customer trust in e-commerce platforms. This paper aims to investigate and analyse the various factors that contribute to customer trust in e-commerce.

Keywords: E-Commerce, dataset, Recommendation System

Abstract: This paper discusses about wireless charging of electric vehicles on the road. Wireless power transmission is a method used to transmit electricity through the air medium. Wireless charging has been in development for a quite long time, and companies like ElectReon from Israel, have taken these standards to the next level with an innovation that sounds like it came right out of a science fiction film and this innovation is none other than wireless charging roads. This picks up electricity provided by a coil, which is beneath the road. Electric vehicles are normal, fitted with batteries, but the beneficiary is that people can transport as long as possible with this technology, as continuous electricity is provided through the coil. There is no time wasted in charging the vehicle, in the station. Even the existing electric vehicles can be slightly modified to attain this technology. And even the best part is that, for no battery electric vehicle, this will be the best option, as battery weight will be reduced, and with ease electric vehicle can transport.

Keywords: CPT, WPT, Magnetic Coupling Effect, SMFIR, Recharging road, Power pickup unit, plug in electric vehicle, OLEV, IPT.

Abstract: This paper explores the potential of blockchain technology in the education sector, aiming to address its traditional challenges and inefficiencies. While technological advancements have proliferated, the higher education system in developing countries has remained largely unchanged. The study presents a bibliometric and qualitative analysis of blockchain in education, emphasizing its temporal development, emerging themes, and practical case studies. Notably, blockchain's prominence in education surfaced around five years ago, with a focus on verifying academic certificates and transcripts. However, limited efforts have been directed towards comprehensive academic records reporting and connectivity, hindering interoperability. To overcome these obstacles, the paper proposes an education blockchain based on learning outcomes and graduation requirements, facilitating continuous curriculum improvement and post-job competence evaluation. The study highlights blockchain's potential in revolutionizing education by enhancing security, accessibility, and transparency, demanding further research and experimentation for its successful integration.

Keywords: Blockchain, Education, Challenges, Applications, Transparency.

Abstract: DevOps, an extension of certain agile practices, combines various patterns to enhance collaboration between development and operations teams. The primary objective of this research is to investigate the impact of DevOps implementation on software quality, while also exploring effective strategies to improve quality efficiently. Through an extensive literature survey, current DevOps practices in the industry were explored, leading to the development of a conceptual research model with five derived hypotheses. The research objectives were achieved by conducting hypothesis testing using Pearson correlation and deriving a linear model based on linear regression analysis. To gather quantitative data, an online questionnaire was employed, supplemented by interviews with DevOps and Quality Assurance experts to identify how DevOps can enhance software quality. The feedback from interviews, along with hypotheses testing using regression analysis, served as the basis for recommendations. The findings from the quantitative study reveal that software quality experiences significant improvement through the adoption of DevOps, particularly when following the CAMS (Culture, Automation, Measurement, Sharing) framework. Among the factors, automation emerged as the most critical element for enhancing software quality. The results of multiple regression analysis further emphasize the importance of culture, automation, measurement, and sharing in the pursuit of improved software quality. In conclusion, this study strongly advocates for the implementation of DevOps to attain high-quality software. By incorporating the CAMS Framework and adhering to principles such as automation, organizations can effectively elevate the overall quality of their software products.

Keywords: DevOps, CAMS Framework, Quality, ISO 9126, Automation"

Abstract: The majority of Internet traffic today and in the future is related to media. To support the storing and distribution of Internet-enabled material, numerous storage services, media apps, and devices have evolved. The adoption of distributed storage technology by the edge servers in Content Delivery Networks (CDN) based on cloud storage enables effective resource utubilisation and efficient data storage and retrieval systems. Although each edge server has a full copy of the content files to be provided, existing CDNs based on cloud storage do not use distributed storage on edge servers. We suggest implementing a cooperative content outsourcing approach in CDN in this article. This method will distribute the cloud's media content (such as static/dynamic websites) across various edges.

Keywords: Origin, Endpoint, Page Speed Insights, Azure Cloud.

Abstract: Crowd analysis plays a crucial role in various domains, including security, transportation, and social behavior understanding. Deep learning techniques have emerged as a powerful tool for handling the complexities and challenges associated with crowd analysis tasks. This survey report delves into the recent advancements in deep learning techniques for crowd analysis, highlighting their applications, strengths, and limitations. We explore various approaches used in crowd counting, crowd behavior understanding, and crowd anomaly detection. Additionally, we discuss the datasets commonly employed for evaluating these techniques. By shedding light on the current state-of-the-art, this survey aims to provide insights into the future prospects of deep learning in crowd analysis.

Keywords: Crowd Analysis, Deep Learning, Crowd Detection, Challenges, Convolutional Neural Network.

Abstract: Organizations can now access computing resources, software, and services through the internet on a pay- as-you-go basis thanks to the revolutionary technology known as cloud computing. Even though cloud computing has many benefits, such as cost savings, scalability, and flexibility, it also presents particular security challenges. In- depth analysis and exploration of the vulnerabilities that arise due to the virtualized nature of cloud environments, data breaches, insider threats, and regulatory compliance concerns are provided in this technical seminar report, which delves into the various security issues faced by cloud computing providers and users. The study also covers a number of best practices and mitigation measures to guarantee a secure and reliable cloud computing environment. Keywords: Security issue, Cloud security, Cloud Architecture, Challenges, Automation of IT industry.

Abstract: The This chapter is focused on predicting cardiovascular diseases, and machine learning and neural network models are instrumental in this process, reducing human effort and providing accurate results. However, the challenge lies in interpreting the predictions made by these complex algorithms. To address this, the authors introduced Explainable Artificial Intelligence (XAI) to understand the reasoning behind the cardiovascular disease predictions. The authors used an explainable artificial neural network (ANN) with a multi-level model, achieving an impressive accuracy of 87%, outperforming other models. On a different note, the ongoing SARS-CoV-2 (n- Coronavirus) pandemic has resulted in the loss of millions of lives worldwide. This virus can lead to severe respiratory illnesses such as pneumonia and severe acute respiratory syndrome (SARS), sometimes resulting in death. The asymptomatic nature of this sickness has made life and work more challenging for people. In this research, the authors focused on forecasting the global situation and impacts of the COVID-19 pandemic, utilizing the FbProphet model to predict new cases and deaths for the month of August. The goal of this study is to provide valuable insights to scientists, researchers, and the general public to aid in predicting and analyzing the effects of the epidemic. The study concludes that the virus's second wave was approximately four times stronger than the first. Additionally, the trajectory analysis of COVID-19 instances (monthly and weekly) revealed that the number of cases increased more during weekdays, possibly due to weekend lockdown measures. The application of the FbProphet model and other algorithms facilitated accurate predictions and improved the understanding of the COVID-19 situation.  Keywords: Artificial intelligence, Digital transformation, Healthcare, Implementation, Healthcare leaders, Organizational change, Qualitative methods.

Keywords: Deep Learning, Neural Network, RNN, CNN, LSTMs

Abstract: For the foreseeable future, Covid-19 is likely to be a crucial differential diagnosis for anyone who visits the hospital with symptoms of flu, shortness of breath, conjunctival congestion, fatigue, body ache, lymphopenia on a complete blood count, and/or a change in their typical sense of smell (anosmia) or taste. However, chest radiography of patients who are critically ill and report to the hospital with respiratory symptoms can aid to identify individuals with covid-19 pneumonia. The majority of persons with covid-19 infection do not develop pneumonia and D-dimer was negative. As fast assessment and reporting from an onsite or remote radiologist is not always possible, in this article we provide guidance to non-radiologists on how to look for abnormalities on chest radiographs that may be suggestive of covid-19 pneumonia .Neural Networks (NN) are a subset of Machine Learning that is increasingly being employed in pre-processed image analysis. The CNN (Convolutional Neural Network) algorithm is a common NN technique that outperforms ANN in this project. The existing CNN models are Inception V3, ResNet50, MobileNet, and Xception [1], although they have been proven to be less accurate and time expensive. The H5 model is a new CNN model developed in our Project. A model that was originally created for facial detection and differentiation is currently being utilised to detect all objects with greater accuracy, focusing on five zones with variable pixel intensity scheme. The encouragingly high classification accuracy of our proposal implies that it can efficiently automate Pneumonia Detection in COVID-19 patients from radiograph images to provide a fast and reliable evidence of Pneumonia related COVID-19 infection in the lung that can complement existing COVID-19 diagnostics modalities.

Keywords: H5 Convolutional Neural Network model, Convolution Neural Network (CNN) architecture, COVID-19, Severe Acute Respiratory Syndrome corona virus 2 (SARS cov-2), deep learning based chest radiograph classification (DL-CRC), Tensorflow, Haar Cascade Classifiers, different pixel Intensity scheme, facial detection and distinction.

Abstract: Consensus mechanisms are a critical element of blockchain technology, enabling decentralized networks to achieve agreement at the validity and ordering of transactions across more than one nodes without counting on a central authority. Blockchain's consensus protocols ensure that each one participants in the network reach a common, immutable state of the disbursed ledger, fostering accept as true with and safety in an otherwise trustless environment. various consensus algorithms have been developed, each with its unique characteristics and trade-offs. The most well-known and widely used consensus mechanisms include Proof of Work (PoW), Proof of Stake (PoS), Delegated Proof of Stake (DPoS), and Practical Byzantine Fault Tolerance (PBFT), among others.In PoW-based blockchains, participants (miners) compete to solve complex cryptographic puzzles to validate transactions and add blocks to the chain. PoS, however, selects validators based totally on the number of tokens they hold and their willingness to "stake" the ones tokens as collateral. DPoS extends PoS by way of introducing a small group of elected delegates who validate transactions on behalf of the larger network, improving scalability. Consensus in blockchain is a crucial thing, directly impacting the network's safety, scalability, and decentralization. choosing the right consensus mechanism relies upon at the particular use case, the goals of the blockchain project, and the desired level of trust amongst members.  

Keywords: Blockchain, Permissioned Consensus, and Permissionless Blockchain, Bitcoin, PoW, PoS, PoB, Cryptocurrency.

Abstract: The advent of recommender systems has revolutionized the digital landscape, enabling users to effortlessly access personalized web content tailored to their preferences. These systems have become instrumental in streamlining e-commerce experiences, providing users with curated recommendations that align with their tastes. This paper delves into the realm of recommendation systems, with a specific focus on the domain of online book shopping. As the e-commerce landscape evolves, the significance of accurate and efficient recommendations cannot be overstated. Traditional methodologies often fall short, accumulating irrelevant data and impeding the user experience. In response, this paper introduces a novel approach to book recommendations, aimed at enhancing the reader's journey by suggesting the ideal book for their next reading endeavour. The proposed method centres on User-Based Collaborative Filtering (UBCF), a powerful technique that harnesses the collective preferences of users with similar reading patterns. By leveraging a well-defined set of similarity measures, the system effectively identifies like-minded readers, paving the way for insightful book recommendations. The architecture of the proposed system is meticulously outlined, showcasing its seamless integration into the online book shopping platform. In addition to UBCF, the paper underscores the importance of training, feedback, and data management in bolstering the recommendation process. The model's implementation is intricately detailed, highlighting its practicality and potential impact. As a user interacts with the system, a symphony of training, analysis, and configuration culminates in the delivery of tailored book recommendations. In conclusion, this paper not only presents a comprehensive overview of recommendation systems in the context of online book shopping but also introduces an innovative approach rooted in User-Based Collaborative Filtering. By bridging the gap between user preferences and available content, the proposed system redefines the book selection process, providing readers with a roadmap to literary exploration that aligns seamlessly with their interests. Through the convergence of cutting-edge technology and intuitive design, the paper offers a promising glimpse into the future of personalized digital experience In an era of information abundance, our approach refines content curation.  

Keywords: Recommender system, Collaborative filtering, User-based Book recommendation, Similarity measures, User preferences, Content curation, Data analysis, Information retrieval, Decision-making, Model design, User interaction, Feedback loop, Data management, User engagement.

Abstract: Driver fatigue and reckless driving are major contributors to road accidents, resulting in the loss of precious lives and compromising road traffic safety. Effective and precise solutions to detect driver drowsiness are crucial in preventing accidents and enhancing road safety. Numerous driver drowsiness detection systems have been developed using diverse technologies, each focused on detecting specific parameters related to the driver's tiredness.This research proposes a novel multi-level distribution model for detecting driver drowsiness, employing Convolutional Neural Networks (CNN) technology. The model utilizes a 2D Convolutional Neural Network to analyze the driver's facial patterns, capturing their behavior and emotions accurately. OpenCV is employed to build the suggested model, and the experimental results demonstrate its superior efficiency in recognizing the driver's emotions and level of tiredness compared to existing technologies.  

Keywords: ReLu, Voila Jones Algorithm, Support Vector Machine, Convolution Neural Network, Haar Cascade, OpenCV, Keras, TensorFlow

Keywords: DevOps, software development, culture, challenges, programs

Abstract: Pest control in agriculture is the deterrence or extermination of species threatening agricultural productivity. Farms are often businesses and depend on output so that the workers can earn money and fund their lives. Therefore, any factors affecting produce must be acted on swiftly and in a cost effective & chemical freeway mainly in India. IoT in agriculture uses remote sensors, and computer imaging combined with continuously progressing machine learning and analytical tools for monitoring crops, surveying, and mapping the fields, and providing data to farmers for rational farm management plans to save both time and money. Our technology, krshi suraksa, controls pests and keeps an eye on farms by monitoring soil & weather parameters and agricultural fields to ensure that farming is done safely and effectively, even over vast tracts of land with minimal expense. This is a low-cost IOT-based pest management and agriculture tool that aids farmers in many ways, including safe & effective irrigation. The farmer may monitor his field from his home using a mobile device.

Keywords: IOT based control, Pest control, effective, low cost, chemical free, for large area.

Abstract: Traditional Karn's techniques, along with other techniques, could render the system unreliable because they provide a feedback mechanism to identify and correct errors. Increased error rates and decreased data integrity could come from this approach. Traditional Karn's method and other algorithms aren't likely to be able to manage an enormous number of users or adapt to shifting network circumstances, which could limit their potential to scale. This may reduce their utility in extensive networks. Inadequate security measures in the traditional Karn's algorithm, along with additional algorithms, could render them vulnerable to unauthorized access and data breaches. Since traditional Karn's method and other algorithms employ a constant retransmission rate, these techniques may not be ideal for changing network circumstances and have limited efficiency. As a consequence of this, it could result in greater delay, slower data transfer, and higher latency. The Dynamic Adaptive ARQ (DA-ARQ) method, which is more effective than the traditional Karn's method because it employs a dynamic approach to change the retransmission rate based on the network conditions, is the primary focus of this proposed survey paper. Overall, the DA-ARQ algorithm is more efficient, dependable, and secure than conventional Karn's method and other algorithms because of its dynamic and adaptive nature.

Keywords: Traditional Karn’s Approach, Dynamic Adaptive ARQ (DA-ARQ), Retransmission Rate, Increased Error Rates

Abstract: Agriculture is one of the life factors for Indian farmers. In accordance with the climate and other resources accessible to them, farmers grow multiple crops in their field. The monitoring of plant detection is required now way days because of increase in plant disease in field crops. Farmers find difficulty in identification of plant disease naked eye observation is one of the oldest method to identify which may fail in proper identification of field crop diseases plant disease in plant effect the economic as well as production losses both in quantity and quality, so to achieve high quality and excellent quantity some technical as well as technological assistance is required. To maintain the food crop without plant diseases the crop surveillance is needed. The proposed system is built around Arduino Uno Microcontroller board. The robot is interfaced with ESP32 Camera which captures the image of leaf and sends to the user. Detection of leaf status is carried out through Convolution Neural network(CNN) of image processing techniques. The user will be drawn to e-commerce website which provides possible solution to the detected disease. The rover is also equipped with inbuilt fertilizer sprayer communicated through Bluetooth module. The commands are controlled by the user using Bluetooth Electronics Application. Soil moisture sensor is interfaced which notifies the moisture content of soil. Implementation of this method saves time, health and improves productivity.

Keywords: CNN, Arduino Uno, Robot, ESP32.

Abstract: This study investigates the economic empowerment of rural women entrepreneurs by exploring the role of digital platforms, with a particular focus on social media platforms. The research aims to investigate how the utilization of these digital tools can positively impact the economic growth and empowerment of women entrepreneurs in rural areas. Data was collected from women entrepreneurs in Siaya County, Kenya, using a survey research design. The study analyzed the frequency and extent of social media platform usage for various business functions, such as sales, marketing, customer relationship services, and online banking. Additionally, the research examined the relationship between social media platform usage and women's economic empowerment using statistical models, including correlation and regression analyses. The findings demonstrate that social media platforms, especially WhatsApp and Facebook, play a significant role in advancing women's economic empowerment. However, the usage of these platforms by rural women entrepreneurs remains below average, indicating a need for increased awareness and support. The study highlights that digital platforms enhance productivity, reduce costs, and improve business efficiency, leading to improved health outcomes and environmental benefits. Online sales, facilitated by social media, enable entrepreneurs to expand their markets beyond geographical boundaries, reaching a broader customer base and achieving higher profit margins. These higher profits contribute to business expansion, job creation, and improved living standards, while also offering opportunities for investment in environmental development initiatives. Overall, this research underscores the transformative potential of digital platforms, particularly social media, in fostering economic growth and gender empowerment among rural women entrepreneurs. Policymakers and stakeholders can leverage these insights to develop targeted initiatives and support mechanisms that encourage more women to embrace digital tools for business growth, ultimately contributing to economic development and gender equity in rural communities.

Keywords: Digital Platforms, Social Media Platforms, Women Empowerment, Entrepreneurship, Women Entrepreneurs, Facebook, WhatsApp, Twitter, Instagram, YouTube, LinkedIn Works Cited: Roselida Maroko Ongare "Exploring the Economic Empowerment of Rural Women Entrepreneurs through Digital Platforms: An Investigation into the Utilization of Social Media Platforms", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 12, no. 7, pp. 308-316, 2023. Crossref https://doi.org/10.17148/IJARCCE.2023.12741

Abstract: Agriculture is undoubtedly the largest livelihood provider in India and contributes a significant figure to the economy of our Country. The technological factors affecting the crop production includes practices used and also managerial decisions. So, predicting the crop yield prior to its harvest would help farmers to take appropriate steps. We attempt to resolve the issue by building a user-friendly prediction system. The results of the prediction are suggested to the farmer such that suitable changes can be made to improve the produce. There are different techniques or algorithms which help to predict crop yield. By analyzing all the parameters like location, soil nutrients, pH value, rainfall, moisture a potential solution can be obtained to overcome the situation faced by farmers. This paper focuses on the analysis of the agriculture data and finding optimal yield to provide an insight before the actual crop production using data mining techniques and Machine Learning algorithms.

Keywords: Data mining, Random forest regression, Decision Tree regression, GDP.

Abstract: Consumers and families are challenged by the Post-COVID-19 to maintain a healthy lifestyle, as unhealthful behaviors raise the mortality risk. In this investigation, we look at how the prevalent Corona virus has affected a wide range of consumer attitudes, convictions, and behavior. A variety of client data has been gathered using sentiment analysis. Additionally, utilizing a variety of quick mining methods, current breakthroughs in machine learning algorithms have enhanced sentiment analysis estimates on lifestyles. While machine learning automates the creation of logical models, a perspective's semantic orientation determines whether it is positive, negative, or neutral. This research focuses on the sentiment analysis of lifestyles utilizing quick mining approaches, classifying their polarity as good, negative, or neutral. To estimate attitudes, machine learning employs methods such as Support Vector Regression and K-means clustering.

Keywords: Machine Learning, Big Data, Sentiment Analysis, Support vector Regression (SVR), K-means

Abstract: Predicting customer churn in telecommunication industries becomes a most important topic for research in recent years. Because its helps in detecting which customer are likely to change or cancel their subscription to a service. Now a days the mobile telecom market has growing market rapidly and all the telecommunication industries focused on building a large customer base into keeping customers in house. So it is very important to find which customers are wants to switch to a other competitor by cancel their subscription in the near future. Analysis of data which is extracted from telecom companies can helps to find the reasons of customer churn and also uses the information to retain the customers.  In order to retain existing customers, Telecom providers need to know the reasons of churn, which can be realized through the knowledge extracted from Telecom data. In this we can focuses on machine learning techniques for predicting customer churn through which we can build the classification models such as logistic Regression, Random Forest and Gradient Boosting Algorithm and also compare the performance of these models.  Keywords: Churn prediction, data mining, telecom system , Customer retention, classification system.

Abstract: Cloud computing has developed into the finest answer to space-related concerns for consumers as well as numerous IT Enterprises in today's modern world. Cloud computing has evolved as the ideal option. It's possible that the user may give some thought to the data's true privacy and its integrity. Utilising the many cryptographic approaches that are now available is one way to improve the data security provided by cloud computing. This study presented a hybrid cryptography strategy for security in cloud data storage based on Hash function and visual cryptography approach. In hash function, the user computes the hash value/hash digest of file and then uploads the file for storage to the cloud. The paper also offered a hybrid cryptography technique for security in cloud data storage based on visual cryptography approach. The data that is saved and encrypted on the cloud side of things. If the two hash values are identical to one another, this demonstrates that the data has not been tampered with in any way. MATLAB 8.3 is the programme that is used in order to carry out the simulation.

Keywords: Hash, VCS, Hybrid, Data, Cryptogrsphy, Security, Cloud, IOT, Server.

Abstract: A key large data activity, feature selection (FS), reduces the "curse of dimensionality" by choosing a meaningful feature subset to improve classification performance. Search algorithms may be constrained by FS techniques as the number of attributes grows. To achieve equivalent or better classification performance and increase computing efficiency, a subset of pertinent characteristics are chosen from a large number of original features using the feature selection process. Particle swarm optimization (PSO) is a global search metaheuristic that can swiftly and with few presumptions search a space with many dimensions. An FSPSO method known as particle swarm optimization (PSO) has recently attracted a lot of attention from experts in the field. Following a basic explanation of feature selection and PSO, a review of recent PSO for feature selection work is given.

Keywords: Particle Swarm Optimization, Feature Selection, Classification, Mutation Operator.

Abstract: In this paper, we are monitoring and estimating the pollutant typically on the spectral response or scattering of water reflections. In this present study we proposed a new method that to detect pollutants and we determine water quality parameters based on the theory of texture analysis. Here the GLCM(Gray Level of Co-occurrence Matrix)is used to estimate several texture Parameter-Contract, Correlation, Energy, Homogeneity there parameters are used for estimate a regression model with WQPs(Water Quality Parameters standard) the KNN & BPNN are used to generalize the water quality estimates of all segmented image. By using situ measurements & IKOMOS data, the results can be shows that texture parameters & remote sensing can monitor & predict the distribution of WQP in large rivers.

Keywords: Water parameters, KNN, BPNN, Texture

Abstract: Manual filing activities are carried out every day and sometimes it is difficult to find back documents that have been archived so that it requires a Letter archive application. The application makes it easy to collect data, archive, and search for archived letter documents. This research focuses on developing a letter archive application by implementing the AES-256 algorithm in securing letter archive files. Advanced Encryption Standard (AES) is a cryptographic algorithm that can be used to secure data. The AES algorithm is a symmetric blockchipertext that can encrypt and decrypt information. The AES algorithm uses cryptographic keys of 128, 192, and 256 bits to encrypt and decrypt data in blocks of 128 bits. So that the AES-256 algorithm can be implemented on the current system, the help of native libraries from the go programming language is used, namely crypto/cipher and crypto/aes so that the encryption and decryption process can be applied to the letter archive file that will be archived into the application. By doing system development on the letter archive application that is currently running, it can provide a sense of trust and security to users and produce a safer archiving system than before.

Keywords: Intrution Detection System; Intrusion Prevention System; Secure Shell. Works Cited: Sugiyatno "Digital Archival Security Design with AES Algorithm on Mail Archives", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 12, no. 7, pp. 380-385, 2023. Crossref https://doi.org/10.17148/IJARCCE.2023.12750