Advances in Computer Science Research

Network administration has been completely transformed by Software-Defined Networking (SDN), which makes it for centralized possible control, programmability, and dynamic resource allocation. However, because it is centralized, it is vulnerable to serious security risks, including DDoS assaults that...

This research details a computer interface operated through eye tracking, replacing conventional mouse input. The system enables users to navigate and interact with a computer solely by moving their eyes. Employing an IP camera, the software utilizes OpenCV for pupil localization and DLIB for precise...

The proliferation of unstructured medical documents necessitates efficient methods for extracting and analyzing patient symptoms to enhance clinical decision-making. Now-a-days, in medical field clinical coding and symptoms identification are doing manually or they are manual process. This paper presents...

This project is concerned with real-time emotion recognition from speech using machine learning methods to interpret vocal expressions. The system records audio through a microphone, processes it to extract major prosodic features like pitch, intensity, and tone using the Librosa library, and then classifies...

Sign language is a fundamental mode of communication for the deaf and hard-of-hearing communities, yet real-time automated translation remains a significant challenge due to the complexity of hand gestures, variations in lighting, and differences in signing styles. This study introduces Hand Speak, an...

This literature review emphasizes the importance of early brain tumor detection for improving treatment outcomes and survival rates. It critiques traditional diagnostic methods, such as MRI interpretation by radiologists, which can be slow and prone to errors. The review highlights advancements in artificial...

Understanding human gait patterns is essential for medical diagnostics, rehabilitation, and prosthetic development. This study presents an advanced deep learning approach that combines Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM), and Gated Recurrent Units (GRUs) to analyze lower...

As our reliance on networked systems continues to grow, so does the risk of cybersecurity threats, which are becoming increasingly sophisticated and difficult to detect. Traditional Intrusion Detection Systems (IDS) often fall short in keeping up with these evolving threats, as they typically rely on...

Career guidance in the modern era faces significant challenges in creating accessible systems that effectively bridge education and employment. While there has been limited research on leveraging artificial intelligence (AI) in this domain, its potential to transform career guidance services in higher...

Earthquakes are a big threat. They kill people, wreck buildings, and mess up economies. We need to predict them well to lower risks and handle disasters better. This project uses deep learning methods, such as neural networks and Long Short-Term Memory (LSTM) models, to guess earthquake sizes and depths....

Plant diseases pose a significant challenge to agricultural productivity, leading to considerable reductions in both the quality and quantity of crops. In rice, a vital staple for global food security, common disorders caused by mineral deficiencies and pest infestations typically emerge during critical...

Skin cancer remains one of the most common and life-threatening diseases globally, making early and accurate detection crucial for effective treatment. This study introduces a deep learning-based solution that significantly enhances skin cancer diagnosis. The proposed system employs a Convolutional Neural...

Object detection is the very backbone of computer vision. Applications surface in autonomous vehicles, healthcare diagnostics, and surveillance systems. All the conventional methods of object detection typically require massive amounts of annotated data and use heavy computation, making it hard to use...

Almost one in six deaths worldwide is due to infection, although the speed and accuracy of conventional diagnostic techniques are limited. Medical image analysis, such as CT and MRI scans, can now be done more quickly and accurately thanks to artificial intelligence (AI), which has become a potent tool...

Cervical spine fractures are critical medical conditions that demand rapid and accurate diagnosis due to their potential to cause severe neurological impairment or death. Traditional diagnostic methods relying on manual radiographic interpretation are often limited by subjectivity and time constraints....

In today’s digital age, cyber threats like phishing and malware attacks have become increasingly sophisticated, making it essential to develop advanced solutions to protect users. Phishing websites often disguise themselves as legitimate platforms, tricking users into entering sensitive information such...

The rapid evolution of malware poses significant challenges for traditional detection methods, necessitating advanced approaches that combine deep learning with effective interpretability techniques. This work combines Long Short Term Memory (LSTM) networks and Generative Adversarial Networks (GANs)...

The Bullwhip Effect is a supply chain management phenomenon wherein slight changes in consumer-level demand result in substantial order variability in upstream supply chain processes, thus leading to the inefficient generation of excess inventory costs, stock-outs, and instability in their operations....

The evolution of cybersecurity in a landscape with observable changes calls for sturdy and inventive alternatives for the escalating threats to traditional authentication approaches such as passwords and personal identification numbers (PIN). Keystroke dynamics emerges as a behavioral biometric that...

Packaging Standards; Packaging quality is key in the modern industrial sector where defects can cost-businesses large sums and harm their brand, image. Conventional ways of inspection are time-consuming, labour intensive and error prone, unsuitable for modern production. The project explores the use...

Brain tumor detection is increasingly becoming an issue in the medical field. A brain tumor is a growth or mass of abnormal cells in your brain cells develop uncontrollably. MRI (Magnetic Resonance Imaging) plays one of the primary roles in brain tumor detection where the tumor segmentation is required...

A 2-port MIMO (Multiple input Multiple Output) antenna is analyzed in this research. The antenna configuration is designed with antenna elements positioned orthogonally. FR4 foundation, with an antenna with a dielectric constant of 4.4 and a loss tangent of 0.02 is built. Within the below-6 GHz spectrum,...

It is important to consider multiple factors, including academic fit, finances, and personal preferences, while deciding to select a university. For this, we propose a hybrid recommendation system that uses Machine Learning (ML) and Natural Language Processing (NLP). Using acceptance rates, tuition fees,...

Sign language translation systems have been studied over and over and have become really important for helping deaf people talk to those who hear every day. This paper is a broad overview of what recent critical progress has been made in the conversion of one sign language into another, conveying efforts...

High-dimensional documents play a crucial role in classification tasks, yet their size often raises challenges and signals potential issues. Dimensional reduction, while offering both advantages and disadvantages, becomes pivotal in managing these challenges. However, improper dimensional reduction can...

Rapid advancements in power electronics have enabled the evolution of multilevel inverters (MLIs) for diverse applications. Compared to traditional two- level inverters, MLIs offer several advantages such as reduced voltage stress, minimized electromagnetic interference, and smaller filter requirements....

The “Two-Stage framework for Job Title Identification System in Online recruitment” presents an approach to accurately extracting and classifying job titles from online job advertisements using a two-stage process. This system addresses the challenge of parsing and understanding job titles from diverse...

Cardiovascular diseases (CVDs) pose a significant worldwide health issue, and early prevention and detection are therefore critical to lowering mor- tality. This heart disease prediction app relies on sophisticated machine learn-ing techniques to assess an individual’s risk level against vital health...

The purpose of an intrusion detection system is to prevent damaging attacks. Additionally, the tactics and technologies used by attackers are always changing. In the last work, we proposed employing random forest and support vector machines (SVM) in military defense environments (KDD dataset).Numerous...

This Paper focuses on enhancing the detection of student attentiveness in online classes through the use of Recurrent Neural Networks (RNNs). The system leverages video data to assess student engagement by analyzing both emotions and behavioral cues over time. RNN-based models are employed to handle...

The agriculture sector has become a focal point in addressing global greenhouse gas emissions due to its substantial contribution to the carbon footprint. As population growth and resource consumption accelerate, there is an urgent need for sustainable solutions to mitigate environmental impacts without...

Cyberbullying has become a major concern in digital communication, as they are appropriate for any other device, social media is on-demand giving rise to a new form of bullying called cyberbullying and their detection is required for immediate action. In this work, we propose an automated cyberbullying...

Secure web-based voting systems improve the accessibility of elections, especially for NRIs and the disabled, through internet-enabled device-based voting from anywhere. Incorporating OTP authentication, facial recognition, and surveillance via cameras enhances security and authenticity of voters. An...

This project proposes a wearable health monitoring device aimed at supporting individuals with physical and mental disabilities through real-time monitoring and direct alert capabilities. The primary objective is to create a reliable system that enhances user safety and independence by continuously tracking...

The security of industrial supply Chains (ISCs) has progressed with the incorporation of industrial internet of things (IIoT) and Blockchain (BC) technology, presenting sturdy defense in opposition to cyber attacks and ensuring operational resilience. This work examines lightweight machine learning algorithms...

Kidney tumor segmentation and identification. This system detects tumor in digital images of kidneys by means of analysis. Precision tumorlocalisation is achieved using U-Net model, so improving the segmentation and detection flow. This method guarantees better performance in medical diagnostics as well...

The remote sensing imagery classification is a vital application of machine learning technology going beyond satellite-based platforms into aerial imagery. These techniques substitute for conventional manual categorization, allowing for auto- mated detection of particular land features in geospatial...

One of the biggest problems today is how fast misinformation spreads, affecting people, groups, and entire societies. With so many of all of the people relying on social media such as WhatsApp, Facebook, and blogs, it’s more important now than ever it was to check for whether the information that we...

Precise identification and quantification of necrotic lung lesions in CT scans are important for analyzing lesion traits and monitoring disease advancement; how- ever, conventional techniques frequently face challenges in extracting detailed features and depend significantly on manual input. An optimized...

This project focuses on the development of a low-cost, web-controlled surveillance robot using the ESP32microcontroller, which offers Wi-Fi capabilities for real-time remote access. The robot is equipped with a camera module that streams live video to a web interface, allowing users to monitor and control...

Driver fatigue-induced road accidents are one of the primary threats to traffic safety, and this has driven the need for real-time detection systems. A driver drowsiness detection system based on deep learning, machine learning, and computer vision is proposed in this study for improving road safety....

In Computers must be able to identify human emotions and gestures by examining a person’s behavior, body language, emotional state, and hand gestures in order to engage with them intelligently. In interpersonal interactions, facial expressions and hand gestures let computers and people respond intelligently...

In today’s ever-changing educational environment, students and teachers face many challenges related to effective communication, attendance management, and resource accessibility. Traditional solutions address these needs alone, often resulting in ineffectiveness and timelessness. This study presents...

Subscription-based services have made digital platforms more accessible; their rapid rise comes with mixed blessings for users looking for low- cost deals. In this paper, we introduce Sab-Share, a web-based application that enables users to share subscriptions across different services, including OTT...

Monitoring the health of plants and diagnosing diseases at early stages is an important step to boost agricultural productivity. This project proposes an IoT plant monitoring system that collects images of plants, taking into consideration secondary environmental factors such as soil moisture, temperature,...

Personalized tax optimization and fraud detection pose a challenge to financial decision-making due to the constraints of conventional methods. This research provides a composite machine learning framework combining XGBoost with SHAP for personalized tax- saving recommendations and Random Forest with...

In traffic monitoring and surveillance systems that have been improved with the empirical mode decomposition (EMD) technology, this re- search suggests an effective radar-based method for vehicle classification. A type of signal known as micro-Doppler signatures can identify minute motion patterns in...

Agriculture is one of the long-established occupations across the globe. More than half of the population predominantly rely on agriculture as the primary occupation for their livelihood. Despite the advancement of technology farmers still follow traditional methods to carry out the tasks. The development...

Human carelessness frequently affects traditional water management systems, leading to waste and runoff. To address this issue, we have created Internet of Things solutions. Plans presented by Rankin: An immediate solution for water monitoring and management in a variety of applications, including water...