VOLUME 13, ISSUE 6, JUNE 2024

Abstract: Medical image segmentation is a critical step in various healthcare applications, aiding in diagnosis, treatment planning, and disease monitoring. In this study, we investigate the efficacy of a segmentation approach based on the 2D wavelet transform. Leveraging a dataset comprising 10 diverse medical images, we evaluate the performance of our segmentation method using three key metrics: accuracy, precision, and recall. Our findings demonstrate that the proposed approach enhances segmentation accuracy, offering promising results compared to existing methods. By harnessing the multi-resolution feature extraction capabilities of the 2D wavelet transform, our method achieves improved delineation of medical image structures, paving the way for more accurate and efficient healthcare interventions.

Keywords: Image Segmentation, Medical Image Analysis, 2D Wavelet Transform, Healthcare Applications.

Abstract: In recent years, there has been a frequent and intense occurrence of both Natural Calamities and Military disasters due to National Crisis. The matter of guiding and directing individuals to locations that offer necessary provisions is a significant one. However, map applications are unable to update information consistently and promptly regarding alterations in infrastructure, and roadways caused by natural catastrophes or modifications in humanitarian corridors during times of war. Various technological solutions have been implemented, including the utilization of communication channels. Hence, to find a more prominent solution for making an efficient route from the user’s present location to the emergency relief Centre destination, a novel approach using ASTAR algorithm along with the satellite maps has been implemented to solve the problem in hand. Further in this paper, strategies for determining the shortest path, utilizing the ASTAR algorithm for pathfinding, outlining the necessary data preparation process, and evaluating the performance of algorithm in specific scenarios were experimented.

Keywords: Heuristic algorithms, A STAR algorithm, Premature Convergence, Computational intelligence.

Abstract: In the ever-evolving landscape of mobile communication, the reliability of signal strength is paramount for seamless connectivity. This project delves into the realm of signal enhancement by employing the principles of signal amplification. The mobile phone signal strength reduces due to many reasons like various obstacles and distance. The proposed method utilizes the integration of a UAV and a signal booster to improve the signal strength and enhance the cellular connectivity. The proposed system provides an enhanced mobile signal to a limited area of coverage. The main component of a signal booster is a bi-directional amplifier. It amplifies signal in both the uplink and downlink directions. This allows cell phones served by the rebroadcast antennas to both send and receive data from nearby cell towers. This system can be effectively used in situations of emergency and disasters. To verify the working principle of the proposed method we utilize MATLAB as the platform for implementation. The MATLAB environment serves as a robust platform for algorithm implementation, providing a user-friendly interface for signal processing and visualization. The project encompasses the development of a MATLAB script incorporating the signal amplification Algorithm, allowing to visualize mobile signal strength enhancement. The project aims to contribute to the improvement of mobile communication experiences by providing a tool for signal optimization. The outcomes are expected to demonstrate the efficacy of UAV based signal boosting system.

Abstract: This research paper explores the applica- tion of Arduino-based systems in dam automation to enhance operational efficiency and safety. Dams are critical infrastructures that require constant monitoring and control to ensure proper functioning and mitigate potential risks. Traditional dam opera- tion methods often rely on manual intervention, which can be time-consuming, error-prone, and risky. By leveraging Arduino microcontrollers and associated sensors and actuators, dam automation systems can provide real-time monitoring, data analysis, and automated control, leading to im- proved efficiency, reduced operational costs, and enhanced safety measures. This paper discusses the design considerations, components, implementation challenges, and potential benefits of Arduino-based dam automation systems, along with case studies and future research directions.

Keywords: Arduino, Dam Automation, Water Level, IOT

Abstract: Greenhouse agriculture is pivotal for enhancing crop yield and quality, but existing systems often grapple with precision and control limitations. This paper introduces a revolutionary ESP32-based greenhouse monitoring and control system, featuring remote capabilities. Utilizing advanced sensors and actuators, the system ensures real-time data acquisition and automated environment modulation. It aims to overcome conventional drawbacks with seamless connectivity and a user-friendly interface. The ESP32 microcontroller serves as the system's core, enabling robust processing and Wi-Fi connectivity. Strategic sensor placement allows continuous monitoring, while actuators automate adjustments for optimal growth conditions. Integration of IoT technology enables remote monitoring and control, offering real-time access globally. This innovation promises enhanced efficiency, resource optimization, and improved crop yield through automated, IoT-based remote monitoring, marking a significant stride in greenhouse agriculture, and addressing the complexities of contemporary farming practices.

Keywords: Greenhouse Automation, ESP32 Microcontroller, IoT-enabled Agriculture, Remote Environmental Monitoring, Precision Crop Control.

Abstract: In the current scenario, people are more attracted to buy groceries from Supermarket/Hypermarket. In such a case, finding the essential need of any customer in supermarket consumes more time and after all findings the customer need to wait in the billing queue to complete billing process of the selected product. Currently, due to the covid-19 pandemic, the customers are strictly instructed to maintain social distance but practically it is not possible especially in the billing process. To overcome this significant challenge, this research work proposes a smart trolley based on Internet of Things [IoT] with an advanced billing system that makes shopping easier and secured and also avoids standing in long queue. The proposed system consists of a smart trolley attached with LCD display, barcode scanner and a raspberry-pi. This exploratory model is intended to completely eradicate the tedious shopping interaction and administration-related issues. The proposed framework can be undoubtedly implemented at a business scale under the genuine situation.

Keywords: Raspberry-pi, LCD, Barcode

Abstract: A centralized logging system for collection, aggregation, monitoring and analysis of log data from various data points leveraging open-source Elasticsearch (ELK) stack. ELK is comprised of three different tools Elasticsearch, Logstash, and Kibana.  We are developing easily deployable automation script to remotely install required monitoring tools on endpoints. Tool offers Host Intrusion Detection System (HIDS) with threat hunting capabilities using Wazuh and Network Intrusion Detection System (NIDS) capabilities using Suricata, Zeek, and Snort. We are using machine learning models for threat detection. It comes with various deployment options (on-prem/cloud). Offering functionality to develop custom monitoring rules based on various signature heuristics. Because of the capabilities we are offering and the fact that storage is the only charge, it is a more cost-effective replacement for current systems.

Keywords: Elasticsearch stack (ELK stack), Network Intrusion Detection System (NIDS), Network Intrusion Detection System (NIDS), Firewall

Abstract: Disease detection using deep learning networks and Residual Networks (ResNets) has revolutionized medical imaging and diagnostics, providing unprecedented accuracy and efficiency in analyzing medical images such as X-rays, MRIs, and CT scans.Deep learning, with their unique architecture comprising convolutional, pooling, and fully connected layers, excel in feature extraction, making them highly effective in detecting various diseases including pneumonia, breast cancer, diabetic retinopathy, and skin cancer. These networks apply filters to input images to detect features like edges, textures, and shapes, while pooling layers reduce the spatial dimensions, retaining essential features and reducing computational load. ResNets, an advanced form , address the vanishing gradient problem by introducing residual blocks that allow gradients to flow through the network more easily, enabling the training of much deeper networks. This capability is crucial for accurate disease detection, particularly in complex tasks like tumor identification and classification of intricate diseases. The residual blocks include identity mappings that bypass one or more layers, thus facilitating the development of very deep networks that perform better than their shallower counterparts.

Abstract: The integration of artificial intelligence (AI) in clinical trial management represents a transformative approach in medical research. This study examines the impact of AI on clinical trials, highlighting its ability to automate routine tasks, enhance data accuracy, and improve patient recruitment and monitoring. AI's predictive analytics, natural language processing, and real-time monitoring capabilities significantly increase efficiency, reduce costs, and improve data quality. Despite these advancements, challenges such as standardization and integration with existing systems remain. Overall, AI holds substantial promise for enhancing the effectiveness and patient-centricity of clinical trials. Key words: artificial intelligence (AI), clinical trials, stakeholder engagement, medical interventions

Abstract: Machine Learning means computers learning from data using algorithms to perform a task without being explicitly programmed. Deep Learning uses a complex structure of algorithms modeled on the human brain. This enables the processing of unstructured data such as documents, images, and text. Machine Learning and Deep Learning are the two main concepts of Data Science and the subsets of Artificial Intelligence. Most of the people think the machine learning, deep learning, and as well as artificial intelligence as the same buzzwords. But in actuality, all these terms are different but related to each other.

Abstract: Blockchain, the foundation of Bitcoin, has received extensive attentions recently. Blockchain serves as an immutable ledger which allows transactions take place in a decentralized manner. Blockchain-based applications are springing up, covering numerous fields including financial services, reputation system and Internet of Things (IoT), and so on. However, there are still many challenges of blockchain technology such as scalability and security problems waiting to be overcome. This paper presents a comprehensive overview on blockchain technology. We provide an overview of blockchain architecture firstly and compare some typical consensus algorithms used in different blockchains. Furthermore, technical challenges and recent advances are briefly listed. We also lay out possible future trends for blockchain.

Keywords: Blockchain, Ledger, Decentralize, IoT

Abstract: Vedic Mathematics is an ancient Indian mathematical system known for its unique and efficient methods of computation. This paper presents the design of an 8-bit multiplier that makes use of the Nikhilam Sutra (NS) to create a fast constant coefficient (with 0xFF) and the Yavadunam Sutra (YS) to create a fast squarer which accepts inputs between 0xF0 and 0xFF. The top module decides which module to use based on the input values and makes use of IP Core for standard multiplication. The designs are implemented in Verilog and implemented in Xilinx Vivado, making use of the Atrix-7 FPGA board. The results show improvement in the NS and YS module, in terms of utilization, power consumption, and path delay. The top module, however, suffers from overheads due to multiplexing and comparisons, which offset the performance gains observed.

Keywords: Vedic, Multipliers, Yavadunam, Nikhilam, Verilog, DSP

Abstract: Computer vision is a field of computer science that focuses on enabling computers to identify and understand objects and people in images and videos. Like other types of AI, computer vision seeks to perform and automate tasks that replicate human capabilities. In this case, computer vision seeks to replicate both the way humans see, and the way humans make sense of what they see. The range of practical applications for computer vision technology makes it a central component of many modern innovations and solutions. Computer vision can be run in the cloud or on premises. Computer vision applications use input from sensing devices, artificial intelligence, machine learning, and deep learning to replicate the way the human vision system works. Computer vision applications run on algorithms that are trained on massive amounts of visual data or images in the cloud. They recognize patterns in this visual data and use those patterns to determine the content of other images.

Keywords: Object Detection, Image Segmentation, Feature Extraction, Deep Learning

Abstract: The Internet of Things (IoT) describes the network of physical objects—“things”—that are embedded with sensors, software, and other technologies for the purpose of connecting and exchanging data with other devices and systems over the internet. These devices range from ordinary household objects to sophisticated industrial tools. With more than 7 billion connected IoT devices today, experts are expecting this number to grow to 10 billion by 2020 and 22 billion by 2025. Over the past few years, IoT has become one of the most important technologies of the 21st century. Now that we can connect everyday objects—kitchen appliances, cars, thermostats, baby monitors—to the internet via embedded devices, seamless communication is possible between people, processes, and things. By means of low-cost computing, the cloud, big data, analytics, and mobile technologies, physical things can share and collect data with minimal human intervention. In this hyperconnected world, digital systems can record, monitor, and adjust each interaction between connected things. The physical world meets the digital world—and they cooperate.

Keywords: Sensor, software, things, data

Abstract: Global agriculture is greatly impacted by plant diseases, since different infections cause 20% to 40% of agricultural production to be lost each year. These losses are caused by bacteria, viruses, fungi, and other microorganisms that affect both economic stability and food security. For example, in the United States alone, the fungal infection Fusarium oxysporum causes losses of up to $1 billion yearly. Furthermore, academics and farmers alike are also concerned about the development of diseases like citrus greening and wheat rust. To mitigate these consequences and ensure long-lasting crop production, integrated approaches to disease control, like resistance breeding, cultural practices, and the prudent use of fungicide are crucial. Convolutional Neural Networks (CNNs), particularly those pre-trained on large datasets like ImageNet, have revolutionized identification of plant diseases by providing excellent accuracy and effectiveness in diagnosing various plant illnesses from images. This approach, which includes optimizing already trained models on plant disease datasets, reduces the requirement for big annotated datasets and computational resources, making it highly applicable for agricultural use. Google's Inception v3 model, known for its efficient architecture and use of inception modules, is widely used in plant disease diagnosis. It can precisely identify plant diseases through transfer learning by being pre-trained on ImageNet and fine-tuned on specific plant disease datasets. The Inception-ResNet v2 model, combining Inception architecture with residual networks, also excels in identification of plant diseases. Its deep structure captures detailed features from plant images, enabling accurate disease diagnosis. Like Inception v3, it uses transfer learning to generalize across various plant species and disease types, aiding in precision agriculture by facilitating early illness detection and timely intervention. This project aims to deploy and Compare the results of three models—Xception, Inception v3, and Inception-ResNet v2—in detecting fungal diseases in fruit plant

Keywords: Plant disease detection, CNN, Xception model, Inception V3 model, Inception ResNet V2 model

Keywords: Bibliometric analysis, Publication trends, Research clusters, Artificial Intelligence (AI)

Abstract: As the proliferation of deep fake content continues to pose a growing threat to the integrity of multimedia, this paper introduces a robust approach for deepfake detection leveraging a hybrid architecture. The proposed framework seamlessly integrates the power of Residual Networks (ResNet) for spatial feature extraction and Long Short-Term Memory (LSTM) with Convolutional Neural Networks (CNN) for modeling temporal dependencies. The ResNet component adeptly captures intricate patterns in facial and contextual information, while the LSTM-CNN module focuses on discerning dynamic facial expressions and movements over sequential frames. Transfer learning strategies are employed to bolster model generalization, combining pre-training on a large-scale dataset with fine-tuning on deepfake-specific data. Experimental evaluations on diverse deepfake datasets demonstrate superior performance in accuracy, precision, and recall, establishing the efficacy of the hybrid architecture in addressing the evolving challenges posed by increasingly sophisticated deepfake generation techniques.

Keywords: Resnet, LSTM(Long Short Term Memory), CNN(Convolutional Neural Network), Deep learning, Tensor flow.

Abstract: Although there has never been more technological connectivity on a worldwide scale because to the quick development of electronic devices, worries about environmental sustainability still exist.This study discusses material selection, manufacturing processes, energy efficiency, and disposal procedures in order to provide a detailed analysis of the most recent developments in environmentally friendly electronics. Unprecedented levels of worldwide technical interconnection have resulted from the quick development of electronic gadgets, yet questions have also been raised regarding the sustainability of the environment. In order to reduce the environmental impact of electronic equipment over their lifetime, the idea of "green electronics" has become essential in the research and development industry. The state-of-the-art in green electronics is thoroughly examined in this study, which also addresses a variety of related topics, including material selection, production methods, energy economy, and end-of-life management. By carefully examining the corpus of prior research and case studies, this study identifies opportunities for more investigation and creativity in the field of green electronics.. Ultimately, the development of environmentally benign technology is essential to building a more robust and sustainable future for both the planet and human society.

Keywords: Renewable energy, eco-design, sustainability, and green electronics Selection of materials, Production procedures, Efficiency in energy, circular economy, managing end-of-life issues, Environmental effect, recycling, additive manufacturing, artificial intelligence, Internet of Things, and eco-certification.

Abstract: A vast fraction of the population of India considers agriculture as its primary occupation. The production of crops plays an important role in our country. Bad quality crop production is often due to either excessive use of fertilizer or using not enough fertilizer. The proposed system of IoT and ML is enabled for soil testing using the sensors, is based on measuring and observing soil parameters. This system lowers the probability of soil degradation and helps to maintain crop health. Different sensors such as soil temperature, soil moisture, pH, NPK, are used in this system for monitoring temperature, humidity, soil moisture, and soil pH along with NPK nutrients of the soil respectively. The data sensed by these sensors is stored on the microcontroller and analyzed using machine learning algorithms like random forest based on which suggestions for the growth of the suitable crop are made. This project also has a methodology that focuses on using a convolution neural network as a primary way of identifying if the plant is at risk of a disease or not.

Keywords: Soil nutrient identification, Crop suggestion, Plant pathology, Nitrogen-Phosphorus-Potassium.

Abstract: Precision agriculture has become increasingly important in modern farming practices, aiming to optimize crop yields while minimizing resource use and environmental impact. In this study, we propose an IoT-based crop recommendation system utilizing the Random Forest algorithm to assist farmers in making informed decisions about crop selection based on real-time environmental data. The system leverages IoT sensors to continuously monitor key factors such as pH, temperature, nitrogen, phosphorus, and rainfall in the field. These data are preprocessed and used to train the Random Forest model, which learns the complex relationships between environmental conditions and optimal crop choices. The trained model provides timely recommendations to farmers, helping them adapt to changing conditions and maximize productivity. Through continuous feedback and retraining, the system aims to improve recommendation accuracy over time. This approach holds promise for enhancing agricultural sustainability and efficiency in modern farming practices.

Keywords: IoT, Machine learning, Predictive Analysis, Resource Optimization, Smart Farming

Abstract: Explainable Artificial Intelligence (XAI) encompasses a suite of methodologies and processes designed to make the decision-making mechanisms of AI systems transparent and comprehensible to human users. The aim is to foster trust and confidence in AI outputs by elucidating how machine learning models arrive at their predictions. This transparency is critical for ensuring accountability, detecting and mitigating biases, and enhancing the overall fairness of AI systems. XAI methods provide clear, interpretable insights into the model's behavior, which is particularly important in sectors like healthcare, finance, and law where AI-driven decisions can have significant impacts on individuals. By enabling stakeholders, including data scientists, developers, domain experts, and business managers, to understand the rationale behind AI predictions, XAI supports informed decision-making and facilitates compliance with regulatory requirements. The integration of XAI into AI workflows promotes ethical AI development and deployment, ensuring that AI technologies are not only effective but also transparent and trustworthy. This paper delves into the importance of XAI in modern AI governance, exploring its role in overcoming barriers to AI adoption and ensuring responsible AI usage. Through detailed case studies and methodological discussions, we highlight how XAI can transform the landscape of AI applications by enhancing interpretability, fostering stakeholder trust, and ensuring regulatory compliance. The paper also addresses the challenges associated with implementing XAI, such as balancing model interpretability with performance and the complexity of interpreting deep learning models. Ultimately, XAI emerges as a crucial component in the pursuit of ethical and accountable AI, paving the way for more robust and equitable AI systems that can be confidently integrated into various critical domains.

Keywords: Transparency, Accountability, Bias Mitigation, Model Interpretability

Abstract: Crime analysis and prediction is a systematic approach for identifying the crime. This system can predict region which have high probability for crime occurrences and visualize crime prone area. Using the concept of data mining we can extract previously unknown, useful information from an unstructured data. The extraction of new information is predicted using the existing datasets. Crimes are treacherous and common social problem faced worldwide. Crimes affect the quality of life, economic growth and reputation of nation. With the aim of securing the society from crimes, there is a need for advanced systems and new approaches for improving the crime analytics for protecting their communities. We propose a system which can analysis, detect, and predict various crime probability in given region. This paper explains various types of criminal analysis and crime prediction using several data mining techniques.

Keywords: Machine learning,Supervised learning, Unsupervised learning, Prediction, Classification, Model evaluation, Data Preprocessing, Future Engineering.

Abstract: An important place in the problems of digital image analysis is occupied by the task of enlarging the resolution of an image by scaling it. Such tasks include, in particular: obtaining more detailed information from a fragment of an image because of its enlargement; image magnification for object identification; obtaining a high-resolution image from a low-resolution image to facilitate its further detailed analysis, etc. Each of the existing technics is characterized by both the positive and negative sides. In particular, the negative side is the distortion of the geometric shape of small parts and damage to the texture of the image. Interpolation algorithms are used to reduce these disadvantages. One approach to solve this problem is to use interpolation techniques. The presented article attempts to use the generalized interpolation formulae (Piranashvili’s formulae) with a high-speed convergence for the task of enlarging image size. The results of using Whittaker-Kotelnikov-Shannon and Piranashvili interpolation formulae for enlarging digital images are shown. To estimate the accuracy and quality of approximation of images obtained after interpolation, the remainder terms and signal-to-noise ratio (SNR) values are calculated and compared.

Keywords: Image interpolation, Digital image enlarging, Whittaker-Kotelnikov-Shannon interpolation, Generalized interpolation formulae, Remainder term, Signal-to-noise ratio.

Abstract: Cloud computing is a method of delivering computing resources over the internet, providing on-demand access to a shared pool of computing resources such as servers, storage, databases, software, and applications. This model allows users to access and manage their data and applications remotely, reducing the need for local infrastructure and improving scalability and flexibility. Cloud computing has significant implications in various areas of computing, particularly in big data, and has become a major research theme in computer science. Its applications are diverse, ranging from data storage and processing to software development and analytics. The technology is rapidly advancing, with major companies like Alibaba and Lenovo establishing significant cloud research and development centers, further solidifying its importance in the field.

Keywords: Data, Flexibility, Technology, Computing.

Abstract: The paper presents an automated person counting system for video surveillance leveraging advanced deep learning techniques and computer vision. The system utilizes the YOLO (You Only Look Once) v3 model for efficient and accurate detection of persons in video frames. The YOLO model, pre-trained using COCO dataset, is employed to identify and locate persons within each frame by generating bounding boxes around detected individuals. To further refine the detection process, non-maximum suppression (NMS) is applied to eliminate redundant bounding boxes, ensuring each person is uniquely identified. Following detection, the VGG16 Convolutional Neural Network, trained using the famous ImageNet, is employed to extract deeper semantic features from respective detected person's region of interest (ROI). Identified features are essential for differentiating between unique individuals. The system processes video frames at specified intervals to balance computational efficiency and detection accuracy. To identify distinct individuals across the video, KMeans clustering is applied to the extracted features. The optimal number of clusters is determined empirically, representing the estimated number of unique individuals in the video. This clustering approach allows the system to compute the total number of distinct persons effectively. The implementation demonstrates a robust and scalable solution for automated person counting in surveillance videos, providing critical insights for security and monitoring applications. The system's ability to accurately detect and distinguish between individuals can enhance the effectiveness of surveillance operations, contributing to improved safety and situational awareness.

Keywords: YOLO v3, VGG16, KMeans, COCO dataset

Abstract: IBM WebSphere Application Server (WAS) is a widely used enterprise platform for deploying and managing web applications. Ensuring the security and proper maintenance of WebSphere environments is critical for organizations to protect sensitive data, maintain system stability, and meet compliance requirements. This research paper provides an in-depth analysis of key security considerations and best practices for maintaining WebSphere deployments. It covers authentication and authorization mechanisms, secure configuration guidelines, patch management strategies, performance monitoring, and troubleshooting common issues. The paper also discusses the importance of staying current with WebSphere updates and leveraging tools for simplifying administration tasks. By following the recommendations outlined in this paper, organizations can strengthen the security posture of their WebSphere infrastructure and ensure its smooth operation. Proper security and maintenance practices help mitigate risks, improve system reliability, and support the successful delivery of web applications in enterprise environments.

Keywords: WebSphere Application Server, security, maintenance, authentication, authorization, configuration, patch management, performance monitoring, troubleshooting Cite: Kishore Kandepu,"Enterprise WebSphere Server Security and Maintenance", IJARCCE International Journal of Advanced Research in Computer and Communication Engineering, vol. 13, no. 6, 2024, Crossref https://doi.org/10.17148/IJARCCE.2024.13627.

Abstract: In this paper we are designing LBP Based machine learning Convolution Neural Network called LBPNET to detect fake face images. Here first we will extract LBP from images and then train LBP descriptor images with Convolution Neural Network to generate training model. Whenever we upload new test image then that test image will be applied on training model to detect whether test image contains fake image or non-fake image. Below we can see some details on LBP. Local binary patterns (LBP) are a type of visual descriptor used for classification in computer vision andare a simple yet very efficient texture operator which labels the pixels of an image by thresholding the neighborhood of each pixel and considers the result as a binary number. Due to its discriminative power and computational simplicity, LBP texture operator has become a popular approach in various applications. It can be seen as a unifying approach to the traditionally divergent statistical and structural models of texture analysis. Perhaps the most important property of the LBP operator in real-world applications is its robustness to monotonic gray-scale changes caused, for example, by illumination variations. Another important property is its computational simplicity, which makes it possible to analyze images in challenging real-time settings. The LBP feature vector, in its simplest form, is created in the following manner: Divide the examined window into cells (e.g., 16x16 pixels for each cell). For each pixel in a cell, compare the pixel to each ofits 8 neighbors (on its left-top, left-middle, left-bottom, right-top, etc.). Follow the pixels along a circle, i.e., clockwise or counter-clockwise. Where the center pixel's value is greater than the neighbor's value, write "0". Otherwise, write "1". This gives an 8-digit binary number (which is usually converted to decimal for convenience). Compute the histogram, over the cell, of the frequency of each "number" occurring (i.e., each combination of which pixels are smaller and which are greater than the center). This histogram can be seen as a 256-dimensional feature vector.

Abstract: Traditional methods of diagnosing plant diseases are mainly based on expert diagnosis which easily causes delay in crop disease control and crop management. Due to the problems of many target areas and similar target types in the process of plant disease detection, the identification accuracy and speed are required to be high. Therefore, it is necessary to optimize and improve the existing methods (CNN, RCNN, Fast RCNN, Faster RCNN, and SSD) to meet the detection needs. So, we came up with a deep learning-based approach to identify the plant leaf diseases and classify the diseases using object detection model called YOLO. There are different versions of YOLO, proposed in the recent times, in that YOLOv5 model is considered one of the best models and the other is the recent version, YOLOv8 which was proposed in 2022. So, in this paper we compared the two models of YOLO, YOLOv5 and YOLOv8 on the same dataset, and found that for the dataset used the YOLOv5 model was found to be the better model with a mAP of 0.63, while the YOLOv8 model has mAP of 0.52. This study proposes that YOLOv5 model is suitable for plant disease identification tasks by comparing it with the latest version of YOLOv8 model which was proposed in 2022. To make the YOLO model to be better it can be optimised and the transfer learning ability of the model can be used to expand the application scope in the future.

Keywords: Deep Learning, Convolution Neural Networks, Transfer Learning, Disease Classification, Object Detection.

Keywords: Cardiovascular Diseases, Support Vector Machines, Naïve Bayes, Decision Tree, Random Forest

Abstract: In a weakly-supervised scenario, object detectors need to be trained using image level annotation only. Since bounding-box-level ground truth is not available, most of the solutions proposed so far are based on an iterative approach in which the classifier, obtained in the previous iteration, is used to predict the objects’ positions which are used for training in the current iteration. However, the errors in these predictions can make the process drift. In this paper we propose a self-paced learning protocol to alleviate this problem. The main idea is to iteratively select a subset of samples that are most likely correct, which are used for training. While similar strategies have been recently adopted for SVMs and other classifiers, as far as we know, we are the first showing that a self-paced approach can be used with deep-net-based classifiers. We show results on Pascal VOC and ImageNet, outperforming the previous state of the art on both datasets and specifically obtaining more than 100% relative improvement on ImageNet.

Keywords: Deep Learning, Supervised Learning, Detection, Algorithm.

Abstract: DDoS assaults, which interrupt the availability of services across the board, are one of the most dangerous forms of cyberattacks now in existence. The complexity of DDoS detection stems from the fact that it must analyse a large amount of real-time traffic as well as a wide variety of attack methods. In this work, we introduce LUCID, a lightweight deep learning distributed denial-of-service (DDoS) detection system that uses Convolutional Neural Networks' (CNNs) inherent features to distinguish between malicious and benign traffic flows. Specifically, we add four things to the literature: (1) a novel application of a convolutional neural network (CNN) to detect DDoS traffic with low processing overhead; (2) a dataset-agnostic pre-processing mechanism to produce traffic observations for online attack detection; (3) an activation analysis to explain LUCID's DDoS classification; and (4) an empirical validation of the solution on a resource-constrained hardware platform. When tested on the most recent data available, LUCID's detection accuracy is on par with that of the state-of-the-art methods, but its processing time is cut in half. Through our evaluations, we show that the suggested method can effectively identify DDoS attacks even in contexts where resources are few.

Keywords: Distributed Denial of Service, Deep Learning, Convolutional Neural Networks, Edge Computing.

Abstract: Intrusion Detection Systems (IDSs) have been crucial in protecting computer networks from malicious activities. However, with the rapid evolution of cyber threats and the increasing complexity of network architectures, traditional IDSs are insufficient for effectively detecting and preventing modern attacks. Next Generation Intrusion Detection Systems (NG-IDSs) have emerged in response to these challenges, incorporating advanced technologies to enhance detection capabilities and improve overall security. This survey provides an overview highlighting the key features, applications in diverse networks, and discussing current challenges. It uniquely examines the integration of Generative AI (Gen AI) within IDS frameworks, focusing on Generative Adversarial Networks (GANs) to create synthetic data and emulate complex attack patterns, significantly enhancing the detection of previously unseen threats. Additionally, the survey explores the use of ChatGPT for real-time threat alerts and Large Language Models (LLMs) like GPT-4 in protecting critical infrastructures such as energy grids. This survey aims to offer valuable insights by identifying the challenges and limitations faced by NG-IDSs and proposing areas for future research and development. Keywords: AI, ChatGPT, IDS, intrusion detection system, Generative Adversarial Networks, Generative AI, models, datasets, IoT, security, social engineering, LLM

Abstract: Intelligent systems leveraging artificial intelligence (AI) capabilities frequently depend on machine learning (ML). Machine learning refers to the ability of these systems to learn from specific training data, enabling the automation of analytical model building and the resolution of associated tasks. Unlike traditional programming, where explicit instructions for every possible scenario are coded, machine learning systems identify patterns and make decisions based on data. This capability allows them to improve their performance over time as they are exposed to more data. Machine learning can be divided into several types, including supervised learning, where the system is trained on labelled data; unsupervised learning, which involves finding hidden patterns in unlabelled data; and reinforcement learning, where systems learn by receiving feedback from their actions within an environment. These methodologies empower AI systems to perform a wide range of tasks, from recognizing speech and images to predicting future trends and automating complex processes. The adaptive nature of machine learning makes it a cornerstone of modern AI applications, enabling intelligent systems to handle tasks with a level of efficiency and accuracy that surpasses traditional programming methods. As data continues to grow in volume and complexity, machine learning's role in AI systems becomes increasingly vital.

Keywords: Feature Engineering, Computer Vision, Database, Supervised Learning

Abstract: Artificial intelligence (AI) can explore and sort through available data, recognize and learn patterns from the input unstructured/structured data to extract gainful insights from the input data. The integration of Artificial Intelligence (AI) in drug discovery has significantly revolutionized the pharmaceutical industry by expediting the development process and enhancing the precision of drug efficacy predictions. This paper explores key AI-driven innovations in drug discovery, including platforms like Atomwise, Insilico Medicine, and Exscientia, which utilize deep learning and machine learning for drug design, target identification, and clinical trial predictions. However, the adoption of AI also presents challenges such as data quality, regulatory compliance, and ethical considerations. By addressing these challenges, AI can further optimize the drug discovery process, leading to more effective and safer therapeutic solutions. Keywords: Drug discovery, clinical trial predictions, drug efficacy predictions

Abstract: Cloud computing is the on-demand availability of computing resources (such as storage and infrastructure), as services over the internet. It eliminates the need for individuals and businesses to self-manage physical resources themselves, and only pay for what they use. Cloud computing service models are based on the concept of sharing ondemand computing resources, software, and information over the internet. Companies or individuals pay to access a virtual pool of shared resources, including compute, storage, and networking services, which are located on remote servers that are owned and managed by service providers.

Keywords: Scalability, Virtualization, Multi-tenancy, Elasticity

Abstract: The rapid and straightforward association with wireless access points (APs) provides users with quick and temporary access to the Internet. This convenience requires only a few seconds for users to bring their devices to a hotspot and perform minimal configuration to gain Internet connectivity. Biometrics is a technique used in intrusion detection systems to uniquely identify and profile individual users based on various characteristics such as browser settings, behavior patterns, or network activities. This method allows for the detection of unauthorized access and malicious activities within a system. This approach enables the detection of unauthorized access and malicious activities within a system by creating distinct user profiles. By leveraging Biometrics, organizations can not only enhance security against targeted attacks but also personalize services and detect online fraud with greater accuracy. This paper examines the methodologies behind biometrics, its integration into IDS, and the resultant improvements in security measures. We discuss the practical benefits, such as reduced false positives and enhanced detection capabilities, alongside challenges like privacy concerns and computational demands. Our analysis demonstrates that biometrics is a vital tool in modern cybersecurity strategies, offering robust protection against increasingly sophisticated cyber threats.

Keywords: Intrusion detection, Biometrics, keystrokes, Authentication

Abstract: Artificial intelligence (AI) encompasses various technologies for creating intelligent systems, but ethical challenges like algorithmic bias and privacy concerns persist. Addressing these requires interdisciplinary collaboration and robust regulatory frameworks. While AI shows promise in revolutionizing industries and improving efficiency, its integration into society demands attention to ethical, legal, and societal implications. This includes ensuring transparency, fairness, and accountability, alongside managing the impact on employment dynamics.

Keywords: Automation, Machine learning, Neural networks, Data analysis

Abstract: Cyber security stands as an imperative bastion in the digital age, where the proliferation of interconnected systems exposes individuals, organizations, and nations to an array of evolving threats. This abstract delves into the multifaceted realm of cyber security, exploring its significance, challenges, and emerging trends. At its core, cyber security encompasses the proactive measures and defensive strategies employed to protect digital assets, ranging from sensitive data to critical infrastructure, against malicious actors and cyber threats. Key themes within cyber security include threat intelligence, risk management, and incident response, all aimed at fortifying defenses and mitigating vulnerabilities. Threat intelligence entails the continuous monitoring and analysis of cyber threats, enabling proactive identification and response to emerging risks. Risk management strategies involve the assessment, prioritization, and mitigation of vulnerabilities within systems and networks, ensuring resilience against potential cyber attacks. Meanwhile, incident response protocols outline procedures for effectively detecting, containing, and recovering from cyber security breaches, minimizing the impact on operations and stakeholders.

Keywords: Threat Detection, Data Encryption, Access Control, Incident Response

Abstract: Deep learning, a subset of artificial intelligence, has revolutionized numerous fields by enabling machines to learn from large amounts of data. At its core, deep learning mimics the way the human brain processes information through artificial neural networks. These networks, composed of interconnected layers of nodes, extract intricate patterns and features from data, allowing machines to make predictions, classify information, and even generate content autonomously. From image and speech recognition to natural language processing and autonomous driving, deep learning has brought about groundbreaking advancements, pushing the boundaries of what machines can achieve. Moreover, the versatility of deep learning extends beyond traditional domains, permeating into interdisciplinary fields such as healthcare, finance, and environmental science. In healthcare, deep learning models analyze medical images to detect anomalies, aid in diagnosis, and even predict patient outcomes. Financial institutions utilize deep learning algorithms to analyze market trends, assess risks, and optimize investment strategies. Additionally, environmental scientists leverage deep learning techniques to analyze satellite imagery, monitor deforestation, and track climate change indicators, facilitating informed decision-making for sustainable development. As deep learning continues to evolve, its applications will likely expand, shaping the future of technology and driving innovation across various sectors.

Keywords: Neural Networks,Convolution Neural Networks (CNNs),Recurrent Neural Networks (RNNs),Generative Adversarial Networks (GANs)

Abstract: This paper looks at the big improvements in classifying images using deep Convolutional Neural Networks (CNNs) from 2020 to 2023. We review how CNN designs have evolved, including EfficientNet and Vision Transformers (ViTs), and the rise of hybrid models that combine both convolutional and transformer techniques. We also examine new training methods like self-supervised learning and clever ways to enhance data, which have greatly boosted model performance. Additionally, we discuss optimization strategies like neural architecture search (NAS) and the use of advanced optimizers, as well as how hardware accelerators and distributed training have improved computational efficiency. By summarizing recent research, this paper gives a clear overview of the current state of CNN-based ImageNet classification, emphasizing key innovations and their importance for future research and applications in computer vision.

Keywords: Artificial Intelligence- Convolutional Neural Networks

Abstract: Artificial intelligence (AI) is rapidly transforming diabetes care by improving diagnosis and treatment. Machine learning creates algorithms that predict diabetes risk and complications. Digital therapeutics support lifestyle changes and help patients  manage the disease. AI enables continuous, frictionless, remote monitoring of symptoms and biomarkers, improving decision-making for patients and healthcare providers. Social media and online communities drive patient engagement. These advances optimize resource utilization, lower blood glucose levels, reduce blood glucose variability, and improve glycemic control. AI is moving diabetes care towards data-driven precision medicine and is becoming a fundamental tool in managing this chronic disease.

Keywords: Artificial Intelligence, Diabetes, diabetes management, Machine Learning, AI applications, multiple daily injections, Automated decision support.

Abstract: The use of drones in agriculture has gained attention in recent years as it has the potential to significantly improve traditional farming practices. Drones, also known as unmanned aerial vehicles (UAVs), offer several benefits that can improve crop productivity and quality while reducing labor costs and environmental impact. Modern management in sustainable agriculture requires rapid information on crop status and rapid response to undesirable events.  Indian agriculture faces numerous challenges Productivity decline, climate change, global warming and loss of natural resources, labor shortages, pandemic situations. Drones contribute to agricultural sustainability from social, economic and ecological perspectives. Drones can be used for soil analysis, crop growth and establishment, accurate application of agricultural inputs, plant disease identification, irrigation monitoring, plant health assessment, livestock care and disaster monitoring,  plant biomass for agriculture and damage assessment and material transportation. Studies around the world have shown that drones save time, labor, water and reduce chemical costs.

Keywords: Drone, Modern Agriculture, Environmental Impact, Farming.

Keywords: Blockchain, Systematic review, Music, Industry.

Abstract:  In Indian government schools, the teaching system predominantly relies on traditional methods such as chalkboard instruction, rote memorization, and teacher cantered lectures. These conventional approaches often fail to engage students effectively and do not cater to the diverse learning needs of a large student population. Large classroom sizes further exacerbate the issue, making individualized attention challenging. Additionally, limited access to technology and resources restricts opportunities for interactive and experiential learning, which are essential for comprehensive education. Despite various government initiatives aimed at improving the quality of education, significant dis- parities in infrastructure and resources persist, particularly in rural and economically disadvantaged areas. These disparities impact the effectiveness of education delivery, leaving many students without the necessary skills and knowledge to succeed academically and professionally. To address these challenges, the Pankh India Foundation has developed Pankh-Path-Shala, an innovative e-learning platform specifically de- signed for government school students. This plat- form aims to enhance the quality of English education and improve communication skills, which are critical for students’ academic and career success. Pankh-Path-Shala integrates modern technology with educational content to provide a dynamic, interactive, and engaging learning experience. The platform incorporates several key features to ensure effective learning outcomes. Interactive Learning modules and fun-based videos keep students engaged, while downloadable assignments allow for flexible study schedules and continuous learning.

Keywords: E-learning, government schools, English education, interactive learning, educational technology, communication skills.

Abstract: Convolutional Neural Networks (CNNs) have revolutionized computer vision, achieving state-of-the-art results in facial recognition tasks. However, the performance of CNN models heavily depends on the quality and diversity of their training datasets. Existing datasets often lack sufficient representation of various ethnicities, leading to potential biases and limitations in real-world applications. This research explores the impact of using datasets specific to Indian ethnicity on the performance of CNN modules for facial recognition. By curating a diverse dataset that captures the unique facial features and variations within the Indian population, we aim to enhance the robustness and generalization capabilities of CNN models. Our proposed methodology involves collecting a comprehensive dataset, preprocessing the data, and training CNN architectures specifically tailored for Indian facial characteristics. Through extensive experiments and evaluations, we demonstrate the effectiveness of our approach in improving the accuracy and fairness of facial recognition systems for individuals of Indian ethnicity. This research underscores the importance of considering demographic diversity in dataset curation and model development, paving the way for more inclusive and unbiased computer vision applications.

Keywords: facial recognition, Indian ethnicity, training datasets.

Abstract: There are numerous challenges facing a nation, and security concerns are among the most important ones.  Although face detection and recognition technology has many applications, its main uses are in the fields of banking, document security, smart home security, autonomous face detection, automotive security, face detection for surveillance applications, multi-face recognition, etc. These technologies are critical given the state of the nation today. Facial recognition is thought to be the most accurate and dependable technology available for identifying individuals for security purposes. One of the main problems we are currently dealing with is protecting thieves, despite the fact that we have numerous methods for apprehending the offenders, we are unable to manage the risk of escaping thieves. Here, we provide a solution to these issues by putting forth the notion of facial recognition using machine learning-related Python software. Here, we may use facial recognition to identify the robbers and apply face detection algorithms to secure the lockers. The door will be unlocked if the person at the door is identified. Automatic email notice to unauthorized users has been accomplished by sending an SMS and a security alert email to the authorized user's email address. This method can be used to enhance security systems without causing any issues because it is more dependable, efficient, and uses very little data.

Keywords: Face detection, face recognition, security, Open CV, Python, Home security system, Door lock access.

Abstract: Social media has become an influential tool in the health care system, offering various benefits and opportunities both health care providers and patients. It facilitates communication and information dissemination, allowing healthcare professionals to share medical information, communicate with patients and collaborate with peers. Patients use social networks to seek medical care, share their experiences, and access supportive communities. Social media also participate in public health campaigns, help spread awareness about health problems and preventive measures. Additionally, it serves as a platform for telemedicine and remote monitoring, improving accessibility and convenience for patients. Despite the benefits, the use of social media in health care also raises concerns about privacy, data security, and the accuracy of medical information shared online. Therefore, it is important to navigate these challenges carefully to maximize the positive impact of social media on the healthcare system[1]. Social media has become an influential tool in the healthcare system, providing a variety of benefits and opportunities for both healthcare providers and patients. It facilitates communication and information dissemination, allowing healthcare professionals to share medical information, communicate with patients and collaborate with others. Patients use social networks to seek medical advice, share their experiences and find communities of support. Social media also plays a role in public health campaigns, helping to spread awareness of health issues and preventive measures. Additionally, it serves as a platform for telemedicine and remote monitoring, improving accessibility and patient comfort. Despite the benefits, the use of social media in healthcare also raises concerns about privacy, data security, and the accuracy of medical information shared online. Therefore, it is important that these challenges are carefully addressed to maximize the positive impact of social media on the healthcare system.

Abstract: The increasing use of mobile devices in people's daily lives facilitates the completion of several useful tasks. Mobile cloud computing enhances its benefits and gets over its limitations, such as memory, CPU power, and battery life constraints, by fusing mobile and cloud computing. Big data analytics tools allow value to be extracted from data that has four Vs: volume, variety, velocity, and veracity. This article discusses mobile cloud computing and big data analytics as they relate to networked healthcare. Together with the motivations underlying the development of networked healthcare systems and applications, the usage of cloud computing in healthcare is discussed. The paper discusses a mobile cloud computing infrastructure designed specifically for handling big data applications in the healthcare sector. This infrastructure is built on the concept of cloudlets, which are small-scale cloud data centers located closer to the end-users to enhance performance and reduce latency. The paper reviews various big data analytics methods, the necessary resources, and their applications within healthcare. Additionally, it draws conclusions about how to effectively design networked healthcare systems that leverage big data and mobile cloud computing technologies to improve healthcare services.

Keywords: Healthcare systems, Bigdata analytics, Mobile Cloud Computing, Bigdata, Cloudlet infrastructure, Healthcare applications

Abstract: This paper examines the impact of artificial intelligence (AI) on the labor market and explores how the rapid development of AI technology is changing workforce dynamics around the world. It examines the impact of AI on job creation, migration and the economy as a whole through a literature review, research methods and empirical evidence. The study emphasizes that while AI has the potential to create new jobs, it also presents the challenge of replacing existing roles in a variety of industries, from manufacturing to customer service. Increased efficiency with the introduction of AI can lead to job losses, requiring strategies such as upskilling, retraining and support measures to adapt to such changes and promote job creation in new sectors.

Keywords: Artificial Intelligence, Job Creation , Job Displacement, Job Market.

Keywords: Software Asset management, license compliance, automation, AI

Abstract: As machine learning continues its rapid expansion across diverse domains, the demand for efficient optimization techniques becomes increasingly pressing. In the context of modern machine learning, characterized by exponential growth in data volume and model complexity, traditional optimization methods face new challenges. Addressing these challenges requires a systematic review and summary of optimization methods tailored to the unique demands of machine learning. This paper presents an overview of optimization problems in the realm of machine learning, focusing on the specific context of Hessian-Free Optimization. We delve into the principles and advancements of commonly employed optimization techniques, highlighting their applicability and limitations within the Hessian-Free framework. Furthermore, we examine the applications and developments of optimization methods in prominent machine learning fields, illustrating the versatility and impact of Hessian-Free Optimization across various domains. Finally, we discuss the challenges and open problems that lie ahead in the optimization landscape of machine learning, offering insights into future research directions and opportunities for innovation in the context of Hessian-Free Optimization. Through this comprehensive exploration, we aim to provide valuable guidance for both the advancement of optimization methodologies and the evolution of machine learning research.

Keywords: Adaptive Hessian-Free Optimization, Machine Learning Optimization, Large-scale optimization problems, Hessian matrix

Abstract: DevOps, you know, this area that's getting pretty popular in the tech world. It's all about security with DevOps to make things run smoother. There are tools and methods out there for doing DevOps. We're on a mission here to dig up those top-notch techniques that cover every nook and cranny of DevOps. We've sifted through research papers, analysed their findings, and read tons of reviews to get the lowdown on this topic. Taking all that info into account, we've crafted a detailed review of literature that highlights the effects and most common practices used in DevOps. Our goal is to provide a variety of options for beefing up system security while implementing DevOps. But it's not all rainbows and sunshine – there will be challenges along the way. This paper is your guide to navigating those hurdles and making sure your system is locked down tight against any threats looming out there in cyberspace.

Keywords: DevOps, DevOps Security, Systematic review

Abstract: The paper presents three prospects that social media can offer to medical and health care practices, namely, enhancement in participatory medicine, quality of care, and emergency management and preparedness. Several challenges and risks of social media use in medical and health care are also put forth, including defamation, privacy, accuracy of information, and blurring of professional boundaries .increase in social media adoption to improve the delivery of medical and health care[1]

Abstract: In our study, we recommend upgrading the functionality of our multilingual chatbot by the implementation of sentiment analysis mechanisms using advanced Natural Language Processing (NLP) methods. This ability is a fantastic step up for giving chatbots the knowledge of someone’s mental state and emotions around food, and it has a major effect on our nutrition-related behaviours. The chatbot will then utilize this further integration to provide you with personalized dietary advice tailored to your emotions and tastes. We utilize advanced NLP algorithms to improve the chatbot's empathetic support and steering of dietary recommendations which we believe makes a greater impact on Nutritional Counselling Services offering. The ultimate goal of this research is to provide novel technological interventions that can help the users in adopting healthy eating habits and a healthier lifestyle.

Keywords: NLP, AI, CHATBOT, Natural language Processing, Sentiment analysis.

Abstract: Cataract is one of the foremost common eye maladies that cause visual impedance. Exact and opportune discovery of cataract is perfect way" the most perfect way to oversee the hazard and anticipate visual disability. As of late, cataract discovery frameworks based on counterfeit information have pulled in inquire about consideration. In this paper, we propose a novel profound neural framework, Cataract Net, for programmed discovery of cataract in fundus pictures. The misfortune and actuation capacities are tuned to plan the framework with less components, less preparing parameters and layers. Robotized conclusion of eye diseases using machine and profound learning models is getting to be increasingly common. Glaucoma, cataracts, diabetic retinopathy, astigmatism and age-related macular degeneration are common eye diseases that can cause genuine hurt. It is vital to capture eye contaminations early to maintain a strategic distance from genuine results. Early conclusion of eye maladies is fundamental for successful treatment.

Keywords: Cataract detection, eye disease, machine learning, glaucoma, deep learning.

Abstract: Melanoma skin cancer, which is fatal, is a result of formation of a malignant tumor originating in melanocytes. Leukoderma is a non-cancerous disease and carcinoma is cancerous disease out of which melanoma is the most dangerous one which occurs due to pigment making cells, melanocytes. While there are many types of skin cancer, melanoma is particularly dangerous and accounts for approximately 75 percent of skin cancer deaths. Looking at the survival rate of patients with data derived from the analysis of the patients in the preceding five years, the results reveal that only 15% of the patients’ survival has received chronic treatment. It is actually in a manual system. With regards to the mole, it has roughly about six of the maximum colours so the issue is the image, it has several shades and the human eyes cannot easily recognize it. For early diagnosis of melanoma cancer and to prescribe treatment at an early stage, required machine intelligence algorithms can be utilized. It assists in decreasing the work load on specialists, improving the rate of diagnosis, enhancing the time and reducing the clinical expenses. The purpose of this paper is to identify and eliminate skin cancer before it is too late and so reduce the mortality rate

Keywords: Melonoma, Tumors, Dermoscopy, Machine Learning, CNN

Abstract: The expansion and regularly expanding capacities of mobile phones, for example, advanced smart phones offer ascent to an assortment of mobile detecting applications. This paper studies over how an untrusted aggregator in mobile sensing can intermittently acquire fancied insights over the information contributed by numerous portable clients, without compromising the security of every client. Albeit there are some current works around there, they either require bidirectional communication between the aggregator and versatile clients in every collection period, or have computational overhead and can't bolster vast plaintext spaces. Additionally, they don't consider the Min total, which is truly valuable in portable detecting. To address these issues, we propose an effective protocol to acquire the Sum aggregate, which utilizes an added substance homomorphic encryption and a novel key administration strategy to bolster substantial plaintext space. We additionally broaden the total convention to get the Min total of time-arrangement information. To manage element joins and leaves of versatile clients, we propose a plan that uses the excess in security to lessen the correspondence cost for every join and leave. Assessments demonstrate that our conventions arerequests of size quicker than existing arrangements, and it has much lower correspondence overhead.

Keywords: Mobile sensing, privacy, data aggregation, homomorphic encryption

Abstract: Human Beings have always tried to simplify the way of storing data maintaining both security and speed of access. This decade (2011-2020) is focusing on improving data storage devices. New technologies like SSDs (Solid State Drives), technical upgrades in SATA or IDE HDDs (Hard Disk Drives), etc with Terra Bytes of storage capabilities have come to light in recent past. However, DNA Data Storage technology is the next generation of storage technique, which has a lots of storage capability. DNA Data Storage will reinvent the way of storing data. This paper discusses about this storage mechanism and emphasizes on the on-going re-search in this field.

Keywords: Data Storage, DNA, SDDs, HDDs, Genes.

Abstract: This paper is based on ticketing and identification of the passenger in the public transport. In the urban city we have a severe malfunction of public transport and various security problems. Firstly, there is a lot of confusion between the passengers regarding fares which lead to corruption. Secondly, it is used to authorize the passenger travelling in bus. Thirdly passengers do not have to carry money with them. All the record of transaction will be updated automatically. Moreover, the doors of bus will be opened only when passengers had generated their ticket. This paper deals with identification, bus ticket generation and bus ticket checking.

Keywords: IOT, RFID, ARDUINO, WIFI MODULO, SERVOMOTOR.

Abstract: Sentiment analysis, also known as opinion mining, is an important part of natural language processing (NLP) that automatically detects the polarity of a text and classifies it as positive, negative or neutral. With the rise of user-generated content on the Internet, opinion polls have become extremely popular in recent years. Consumers increasingly rely on user reviews and online chats to make purchasing decisions, making sentiment analysis an important tool for businesses and marketers. This paper provides a comprehensive overview of sentiment analysis techniques, methods and challenges. By exploring techniques such as sentiment classification, feature-based classification, and addressing negative processing, the paper provides an overview of the current state of sentiment analysis research. The study highlights the importance of sentiment analysis in various fields, including marketing, forecasting customer preferences and financial research, facilitating the extraction and interpretation of subjective information from raw data sources.

Keywords: Sentiment analysis, opinion mining, natural language processing (NLP), user-generated content, sentiment classification, marketing.

Abstract: This study looks at how artificial intelligence (AI) is affecting the labour market and how the global workforce is changing as a result of the technology's quick development. It looks at how AI affects migration, employment growth, and the economy overall using research techniques, empirical data, and a review of the literature. The report highlights that although AI has the potential to generate new employment opportunities, it also poses the risk of displacing current positions in a range of sectors, including customer service and manufacturing. AI's increased efficiency may result in job losses, hence upskilling, retraining, and other support measures are necessary to adjust to these changes and encourage the creation of jobs in other industries.

Keywords: Artificial Intelligence, Job Creation , Job Displacement, Job Market.

Abstract: Unprecedented work in the field of smart cities has been done recently. Improving the quality of life for residents in smart cities is the goal of their development. Cloud computing and Internet of Things technologies have been used to accomplish that goal. One of the most exciting new technologies that can provide its customers with a plethora of beneficial services is blockchain technology. It is an immutable, programmable digital register designed mainly for digital currencies such as Bitcoin, that is used to record virtual assets with some kind of value. The features of blockchain technology, as well as its essential requirements and research problems, must be discovered in order to properly employ its services inside smart cities. Therefore, an effort has been made in this piece to[1] IndexTerms: Blockchain, smart city security, decentralization, immutability, transparency, data integrity, IoT integration, cloud computing, interoperability, scalability, energy efficiency.

Abstract: To evaluate the usefulness of virtual monochromatic images (VMIs) obtained using dual-layer dual-energy CT (DL-DECT) for evaluating brain tumors. Materials and Methods: This retrospective study included 32 patients with brain tumors who had undergone non-contrast head CT using DL-DECT. Among them, 15 had glioblastoma (GBM), 7 had malignant lymphoma, 5 had high-grade glioma other than GBM, 3 had low-grade glioma, and 2 had metastatic tumors. Conventional polychromatic images and VMIs (40–200 keV at 10 keV intervals) were generated. We compared CT attenuation, image noise, contrast, and contrast-to-noise ratio (CNR) between tumor and white matter (WM) or grey matter (GM) between VMIs showing the highest CNR (optimized VMI) and conventional CT images using the paired t test. Two radiologists subjectively assessed the contrast, margin, noise, artifact, and diagnostic confidence of optimized VMIs and conventional images on a 4-point scale. Results: The image noise of VMIs at all energy levels tested was significantly lower than that of conventional CT images (p < 0.05). The 40-keV VMIs yielded the best CNR. Furthermore, both contrast and CNR between the tumor and WM were significantly higher in the 40 keV images than in the conventional CT images (p < 0.001); however, the contrast and CNR between tumor and GM were not significantly different (p = 0.47 and p = 0.31, respectively). The subjective scores assigned to contrast, margin, and diagnostic confidence were significantly higher for 40 keV images than for conventional CT images (p < 0.01). Conclusion: In head CT for patients with brain tumors, compared with conventional CT images, 40 keV VMIs from DL-DECT yielded superior tumor contrast and diagnostic confidence, especially for brain tumors located in the WM.

Keywords: Brain neoplasms; Tomography, X-ray computed; Radiography, Dual-energy scanned projection; Image enhancement

Abstract: Clinical applications of speech technology face two challenges. The first is data sparsity. There is little data available to un- derpin techniques which are based on machine learning and, because it is difficult to collect disordered speech corpora, the only way to address this problem is by pooling what is produced from systems which are already in use. The second is person- alisation. This field demands individual solutions, technology which adapts to its user rather than demanding that the user adapt to it. Here we introduce a project, CloudCAST, which addresses these two problems by making remote, adaptive tech- nology available to professionals who work with speech: thera- pists, educators and clinicians.

Keywords: assistive technology, clinical applications of speech technology

Abstract: Automated segmentation of kidneys and kidney tumors is an important step in quantifying the tumor’s morphometrical details to monitor the progression of the disease and accurately compare decisions regarding the kidney tumor treatment. Manual delineation techniques are often tedious, error-prone and require expert knowledge for creating unambiguous representation of kidneys and kidney tumors segmentation. In this work, we propose an end-to-end boundary aware fully Convolu- tional Neural Networks (CNNs) for reliable kidney and kidney tumor semantic segmentation from arterial phase abdominal 3D CT scans. We propose a segmentation network consisting of an encoder-decoder archi- tecture that specifically accounts for organ and tumor edge information by devising a dedicated boundary branch supervised by edge-aware loss terms. We have evaluated our model on 2019 MICCAI KiTS Kidney Tu- mor Segmentation Challenge dataset and our method has achieved dice scores of 0.9742 and 0.8103 for kidney and tumor repetitively and an overall composite dice score of 0.8923.

Keywords: Abdominal CT · Kidneys · Tumor · Segmentation Deep Learning · Convolutional Neural Networks

Abstract: Image steganography is a sophisticated method of hiding information within digital images to prevent unauthorized access and protect sensitive data. This abstract explores the use of the Least Significant Bit (LSB) technique in image steganography as a means to combat cybercrime by ensuring data confidentiality and security. Cybercrime presents a significant threat to information security, with increasing instances of data breaches, identity theft, and unauthorized access to sensitive information. Image steganography offers a promising solution by embedding hidden messages within digital images, thereby obscuring the presence of the information from potential attackers. The LSB technique is one of the most effective and widely used methods for this purpose.

Keywords: LSB, Terror, al-Qaida, HTML, CSS.

Abstract: Communication is a fundamental human need, and for deaf individuals, the barriers posed by auditory impairments can be particularly isolating. Smart glasses, equipped with cutting-edge technology, have emerged as a promising solution to bridge the communication gap for the deaf community. This abstract explores the concept and implications of smart glasses designed to display spoken words in real-time during conversations, enabling deaf individuals to engage seamlessly in verbal interactions. Smart glasses for real-time speech display leverage advanced speech recognition algorithms, microphones, and augmented reality (AR) technology to transcribe spoken words into text and project them onto the glasses' heads-up display. This innovation notonly empowers deaf individuals by providing access to conversations that were previously inaccessible but also enhances their social integration, autonomy, and overall quality of life. Additionally, it discusses the potential impact on education, employment, and social interactions, emphasizing the transformative nature of this technology in empowering the deaf community. Furthermore, the abstract touches upon the ethical considerations surrounding privacy, consent, and the need for inclusive design principles in the development of such devices. It also acknowledges ongoing research and development efforts aimed at improving accuracy, accessibility, and affordability. In conclusion, smart glasses that display words spoken by others in real-time hold immense promise in breaking down communication barriers for the deaf. This abstract highlights the potential of this technology to revolutionize the lives of deaf individuals, foster inclusive societies, and promote a more accessible and equitable future. Index Terms: Smart glasses, Augmented Reality, Dynamic spectrograms

Abstract: The proliferation of digital technologies has ushered in a new era of efficiency and transparency in various sectors, including governance and electoral processes. Traditional paper-based voting systems often face challenges such as logistical complexities, security vulnerabilities, and low voter turnout. In contrast, this work proposes a Blockchain-Based E-Voting System with OTP Validation tailored for campus elections. Leveraging blockchain technology ensures transparency, immutability, and security in the voting process, while OTP validation adds an extra layer of authentication to ensure the integrity of each vote. The system aims to streamline campus election procedures, enhance voter confidence, and prevent tampering or fraud, thereby promoting fair and efficient democratic processes within educational institutions. Through the utilization of smart contracts, voters can securely cast their votes remotely, eliminating the need for physical presence and streamlining the voting process.

Keywords: Blockchain; cryptography; e-voting; smart contracts.

Abstract: We present a customized speech-activated email system that is the product of efforts focused on a single target user with high speech recognition error rates. The system, which includes off- the-shelf and custom hardware and software, allows the user to use speech to send emails with recorded audio attachments. Over the past 16 months, our target user has sent and received hundreds of emails and has integrated the system into his daily life. Key factors contributing to the long-term adoption of the device include our extended efforts to understand the target user over multiple years, iterative design, and the collaboration of our multidisciplinary team of assistive technology (AT) designers, clinicians, software developers, and researchers. Overall, we ask: if we set our sights on developing and supporting a technology that someone will actually use daily, what can we learn? We share our approach, system design, user observation and findings, with implications for speech- based AT research and development.

Keywords: speech interfaces, usability, assistive technology

Abstract: The process of creating natural resources for human survival and economic gain is known as agriculture. Agriculture, on the other hand, promotes economic fairness and helps people all around the world succeed. The COVID-19 outbreak has severely affected the Indian agriculture system. According to survey results, the pandemic has impacted production and sales due to workforce and logistical restrictions. The epidemic caused significant physical, social, economic, and emotional damage to all players in the Indian agriculture sector. The IoT has had a noteworthy effect since its introduction into the agricultural industry. This survey elaborates on cutting-edge smart farming technologies, including the IoT, cloud-fog computing, machine learning, and artificial intelligence, and thoroughly review their applicability in agriculture. This paper advances knowledge in the field by reiterating the issues with smart technology in agriculture emphasizing the worries found in the current smart agriculture framework and proposes a resource allocation algorithm that presents an optimal scheduling solution using the prediction method to inform the system about the incoming task request, considering the task priorities and assigning those requests to optimal resources for improved results in the context of delay, response time, and execution cost, and for processing the data set we supposed to use machine learning model.

Keywords: Smart Farming, Cloud Computing, Fog Computing, Image Processing, Machine Learning.

Abstract: We are living in the era where social media plays a vital role. Online social networking sites like Facebook, YouTube, and Twitter have gained popularity as the number of social media technologies has expanded because they enable people to discuss and express their ideas about numerous life events. The bulk of people spend most of their time on social media sites every day. Using a dataset of 27481 records from Kaggle, we trained our deep learning model. We predict the sentiment into 3 classes with positive, negative or neutral polarity for the opinions expressed in the form of either text or audio. Additionally, our proposed technique has various practical applications and improves the accuracy of sentiment prediction.

Keywords: Sentiment Analysis, Neural Network, Natural Language Toolkit (NLTK), Twitter sentiment analysis, Natural Language Processing (NLP), Text based Sentiment Analysis

Abstract: This paper presents INTRUSISHIELD, an intelligent, multi-layered Intrusion Detection System (IDS) and Intrusion Prevention System (IPS) designed to navigate the evolving landscape of cyber threats. By integrating traditional rule-based methods with advanced machine learning algorithms, INTRUSISHIELD provides real-time monitoring and automated response capabilities to detect and mitigate both known and unknown threats. The system continuously updates its knowledge base to adapt to new attack patterns, ensuring robust network security. Additionally, INTRUSISHIELD incorporates a user-friendly Streamlit web application for easy monitoring and management of IDS functionalities. Extending this approach, a separate Streamlit app allows users to upload files for real-time detection of malicious content, enhancing the system’s preventive capabilities. This comprehensive solution demonstrates significant improvements in threat detection, mitigation, and user accessibility, thereby strengthening overall cybersecurity defenses.

Keywords: Intrusion Detection System, Intrusion Prevention System, Machine Learning, Cybersecurity, Real-time Monitoring, Streamlit

Abstract: The Diabetes Prediction App is a vital healthcare tool developed using Django, designed to predict the likelihood of an individual developing diabetes based on various health parameters and risk factors. This project aims to provide users with an accessible and user friendly platform to assess their risk of diabetes and take preventive measures accordingly. Leveraging Django's capabilities, the application utilizes machine learning algorithms to analyse user input data and generate personalized risk assessments, empowering individuals to make informed decisions about their health. Diabetes is a chronic disease with the potential to cause a worldwide health care crisis. According to International Diabetes Federation 382 million people are living with diabetes across the whole world. By 2035, this will be doubled as 592 million. Diabetes is a disease caused due to the increase level of blood glucose. This high blood glucose produces the symptoms of frequent urination, increased thirst, and increased hunger. Diabetes is a one of the leading cause of blindness, kidney failure, amputations, heart failure and stroke. When we eat, our body turns food into sugars, or glucose. At that point, our pancreas is supposed to release insulin. Insulin serves as a key to open our cells, to allow the glucose to enter and allow us to use the glucose for energy.

Keywords:  Early Diagnosis, Health metrics, Clinical Practice, Public Health

Abstract: Information and Communication Technology (ICT) has become integral to our daily lives. From the way we communicate to how businesses operate. It refers to all communication technologies that enable users to access, retrieve, store, transmit, and manipulate information. It plays a huge role in driving innovation and transforming the society. This research explored the utilization of Information and Communication Technology (ICT) and Learning Management Systems (LMS) in educational sector, providing insight on the prevalent systems, their benefits, challenges, and strategies for effective implementation. Through a descriptive survey design, the research captured insights from both students and teachers, with a sample size of 89 respondents, consisting of 62 students and 27 teachers. Questionnaire was used for data collection. Four research questions guided the study. Mean, standard deviation, frequency, and percentage were used to analyse the research questions. It revealed popular LMS platforms like Canvas, Google Classroom, and Moodle. Additionally, this study sheds light on the transformative impact of ICT and LMS on traditional teaching methods, highlighting their role in facilitating flexible and accessible learning experiences. By identifying barriers and proposing strategies for effective integration, the study offers valuable insights for educators and administrators seeking to harness the full potential of technology in education in order to achieve their goals and objectives and enhance learning outcomes.

Keywords: Information and communication technology, Learning management system, Education

Abstract: In the realm of digital music consumption, navigating through extensive libraries poses a significant challenge for users. To address this, our project introduces an Emotion-Based Music Recommendation System, integrating Convolutional Neural Networks (CNN) and Haar Cascading algorithms. Our objective is to provide users with tailored music recommendations based on their emotional state and preferences. By harnessing CNN, we delve into the intricate nuances of facial expressions, enabling accurate emotion detection. This deep learning approach allows our system to discern subtle emotional cues, enhancing the precision of music recommendations. Additionally, the integration of Haar Cascading algorithms facilitates efficient face detection, ensuring seamless user interaction. Through the fusion of CNN and Haar Cascading, our system offers a holistic solution to the challenges of music selection, alleviating decision-making stress and enhancing the user experience. With the ability to capture and interpret users' emotional states, our system empowers users to effortlessly discover music that resonates with their mood. Moreover, by incorporating feedback mechanisms, we continuously refine and optimize our recommendation algorithm, further enhancing its accuracy and effectiveness. In summary, our Emotion-Based Music Recommendation System represents a convergence of cutting-edge technologies, aimed at revolutionizing the way users interact with their music libraries. Through the synergy of CNN and Haar Cascading, we present a user-centric solution poised to elevate music listening experiences and redefine personalized music recommendation.

Abstract: The Internet links thousands of millions of computers which are running various software and hardware platforms to provide communication as well as commercial services. But since computers are connected, bad people can abuse resources and launch cyberattacks. Creating adaptable security-focused methods is becoming increasingly difficult due to an increasing number of cyberattacks. One of the most crucial tools for spotting online threats is the intrusion detection system (IDS). Several methods from several fields have been applied in literature to create effective IDS. AIbased techniques are widely used in intrusion detection systems (IDS) development and provide several advantages over alternative methods. To investigate and comprehend the current state of these approaches to address intrusion detection issues, there is not, however, a thorough analysis of AI-based strategies. This work has studied several AI-based methodologies, with a focus on IDS generation.

Keywords: Intrusion Detection System (IDS), Machine Learning, AI Powered, Datasets, Computer Security

Abstract: Data science integrates mathematics and statistics, specialized programming, advanced analytics, artificial intelligence (AI), and machine learning with domain-specific expertise to uncover actionable insights from an organization’s data. These insights are pivotal for guiding decision-making and strategic planning. The increasing volume of data sources and the subsequent growth of data have positioned data science as one of the fastest-growing fields across various industries. Organizations are becoming increasingly reliant on data scientists to interpret data and provide actionable recommendations to enhance business outcomes.

Keywords: Data Science, Descriptive Analytics, Deep Learning, Artificial Intelligence, Machine Learning