Brain tumor diagnosis through CNN and LSTM
Design and development of an optimized underwater forensic robot for enhanced detection of submerged human remains
Accurate Screen Detection in Presentation Videos Using Deep Learning
Nature Inspired Metaheuristic Effectiveness Used in Phishing Intrusion Detection Systems with Grey Wolf Algorithm Techniques
Smart Guide Visual Aid Glasses
Reimagining Manufacturing with Generative AI: A Comprehensive Review of Current Applications and Future Directions
Chemistry and Chemical Engineering: Approaches, Observations, and Outlooks
Integration of PMS Software and Decision Matrix Tool Based on Data Acquired from Latest IT Advanced Sensors and 3D CAD Models in Marine Operations Field
The Impacts of Climate Change on Water Resources in Hilly Areas of Nepal
A Series of Tool-Life Studies on Aluminium Matrix Hybrid Composites
Dynamic Changes in Mangrove Forest and Lu/Lc Variation Analysis over Indian Sundarban Delta in West Bengal (India) Using Multi-Temporal Satellite Data
An Analysis of Machining Forces On Graphite/Epoxy, Glass/Epoxy and Kevlar/Epoxy Composites Using a Neural Network Approach
Deformation Behaviour of Fe-0.8%C-1.0%Si-0.8%Cu Sintered P/M Steel during Powder Preform Forging
A Series of Tool-Life Studies on Aluminium Matrix Hybrid Composites
Achieving Manufacturing Excelence by Applying LSSF Model – A Lean Six Sigma Framework
Design and Analysis of Piezo- Driven Valve-Less Micropump
Medical diagnosis and treatment planning significantly depend on brain tumor classification processes to detect tumors early and develop appropriate therapies. The presented approach utilizes Convolutional Neural Networks (CNN) together with Long Short-Term Memory (LSTM) networks for classifying four categories of MRI brain scans which include glioma and meningioma as well as pituitary tumor and no tumor. The trained model works on a preprocessed set which includes grayscale MRI images that received resizing and normalization procedures to reach better learning outcomes. Images produce spatial features through CNN evaluation which pairs effectively with LSTM analysis that detects sequential patterns for better classification. The proposed network produces performance results matching or exceeding those of typical networks VGG16, ResNet50, and EfficientNet when evaluated with accuracy measurements along with confusion matrices and classification report metrics. The robustness is enhanced through data augmentation that includes Gaussian and salt-and-pepper noise application as well as noise reduction techniques to achieve better image quality. The model generates effective tumor classifications through high accuracy which indicates its usefulness in automated brain tumor diagnosis.
Underwater forensic robotics has emerged as a transformative tool in the detection, location, and recovery of submerged human remains, addressing the limitations of traditional forensic methods in aquatic environments. This paper provides a comprehensive review of advancements in underwater forensic robotics, focusing on three key areas, design, optimization, and enhanced detection techniques. The design of these robotic systems incorporates pressure-resistant materials, advanced sensors, and efficient power systems to ensure durability and performance in challenging underwater conditions. Remotely Operated Vehicles (ROVs), Autonomous Underwater Vehicles (AUVs), and hybrid systems are explored for their unique capabilities in forensic investigations. Optimization techniques, including sensor integration, navigation systems, and energy efficiency, are discussed to highlight improvements in operational effectiveness. Enhanced detection methods, such as 3D sonar imaging, chemical sensors, and AI-driven pattern recognition, are examined for their role in improving the accuracy and efficiency of locating human remains. Case studies demonstrate the successful application of these technologies in real-world scenarios, underscoring their practical significance. Despite these advancements, challenges such as environmental factors, technical limitations, and ethical considerations persist. Future directions include the development of swarm robotics, biomimetic designs, and interdisciplinary collaboration to further enhance the capabilities of underwater forensic robotics. This review underscores the critical role of robotics in advancing underwater forensics and highlights the need for continued innovation to address existing challenges and expand the potential applications of these technologies.
Lecture videos are important in numerous applications such as indexing, summarization, content extraction, search, and navigation. In classroom and conference environments, digital slides are frequently displayed on a screen, making screen detection vital for extracting slide areas from presentation videos. This study presents a method for identifying the position of slide areas in video frames by utilizing the You Only Look Once (YOLO) object detection framework. A tailored YOLOv7 model is trained using a labeled dataset that includes frames from presentation videos featuring projected slides. The trained model is subsequently evaluated on unfamiliar images to correctly identify projector screens. The dataset includes more than 2,000 labeled frames, which are increased to 5,000 images by using data augmentation methods. The suggested approach is assessed in comparison to other renowned object detection models. Experimental findings show that the customized YOLOv7 model attains superior accuracy and computational efficiency relative to the standard YOLOv7 and Retinanet. The results indicate that this method provides a dependable solution for detecting projector screens and can be utilized in different real-world situations.
Phishing attacks pose a severe cybersecurity threat, often bypassing traditional Intrusion Detection Systems (IDS) due to high false positives and low detection accuracy. This study enhances phishing detection by integrating nature-inspired metaheuristic algorithms with machine learning. Support Vector Machine (SVM) performance is optimized using Grey Wolf Optimizer (GWO), Firefly Algorithm, Bat Algorithm, and Whale Optimization Algorithm, mimicking natural behaviours for improved efficiency. Experimental evaluation shows that our model outperforms traditional methods, achieving over 95% detection accuracy while significantly reducing false positives, making it a more adaptive and intelligent phishing detection system
Visually impaired individuals face significant challenges in recognizing objects, people, and text in their surroundings, often limiting their autonomy and independence. This study focuses on developing smart glasses equipped with Raspberry Pi to facilitate real-time object and facial recognition, supported by audio feedback. Utilizing advanced machine learning algorithms such as YOLOv5 for object detection and Dlib for facial recognition, the system delivers auditory cues through text-to-speech technology, allowing users to navigate their environment with enhanced confidence. The prototype's evaluation demonstrates its accuracy and usability while also discussing potential improvements for future development.
In recent years, the manufacturing industry has undergone transformative changes spurred by the rapid evolution of artificial intelligence (AI), particularly Generative AI (GenAI). As a subset of AI capable of creating new data from learned patterns, GenAI is poised to reshape manufacturing processes by enhancing productivity, product customization, quality assurance, and operational efficiency. This review synthesizes key findings from scholarly articles published in the first half of 2024, with a primary focus on three GenAI models: Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), and Transformer-Based Architectures. The paper critically analyzes the roles and capabilities of GenAI technologies in improving predictive maintenance, supply chain optimization, and sustainable production. It also sheds light on the prevailing challenges and potential future advancements of GenAI integration in industrial environments.
