Sri Ramakrishna Institute of Technology

The growing adoption of electric vehicles (EVs) necessitates an extensive and efficient charging infrastructure, which must be reliably integrated into the smart grid. However, uncoordinated deployment of Electric Vehicle Charging Stations (EVCS) can compromise grid reliability, increase power losses, and contribute to environmental burdens. This research presents a novel hybrid methodology combining the Crayfish Optimization Algorithm (COA) with Finite Basis Physics-Informed Neural Networks (FBPINN) to strategically allocate EVCS for enhanced smart grid performance. The Proposed methodology is named COA-FBPINN. COA performs global optimization of EVCS locations, while FBPINN provides intelligent modeling of grid behaviour to ensure effective integration. The Simulation results obtained using MATLAB show that the COA-FBPINN approach significantly outperforms benchmark algorithms like Particle Swarm Optimization (PSO), Salp Swarm Algorithm (SSA), and Honey Badger Optimization (HBO). Specifically, the proposed technique attains a daily operational cost of $0.50, computation time of 5.1 s, power loss of just 0.01 MW, and emission levels of 2.5 × 10⁵ g. Furthermore, it delivers high predictive performance with 95% accuracy and 98% precision in placement decisions. These results demonstrate that COA-FBPINN is highly effective in reducing operational costs, minimizing energy losses and emissions, and improving the entire reliability of the smart grid. The proposed approach is recommended as a robust solution for next-generation EVCS planning and smart grid resilience.

The integration of Internet of Things (IoT) technologies into plant care systems has gained significant traction due to its potential to automate and optimize maintenance processes. This study presents an IoT-based automated plant watering system comprising key components such as a NodeMCU (ESP8266) microcontroller, various environmental sensors, and a relay module. Central to the system is a soil moisture sensor, calibrated via the Blynk application, which facilitates real-time monitoring and remote control from any location. Users can actively manage irrigation by controlling the water pump through the app, ensuring efficient and timely watering based on actual soil conditions. The system has been designed for quick setup, requiring only a few hours and has undergone comprehensive testing to validate its reliability and performance. Its adaptability makes it suitable for both domestic and agricultural environments, offering an effective solution for conserving water and enhancing plant protection across a range of cultivation scenarios.

MIMO–OFDM systems are essential for high-capacity wireless networks, offering improved data throughput and spectral efficiency necessary for dense user environments. Effective power and interference management are pivotal for maintaining signal quality and enhancing resource utilization. Existing techniques for resource allocation and interference control in massive MIMO–OFDM networks face challenges related to scalability, adaptability, and energy efficiency. To address these limitations, this work proposes a novel bio-inspired Termite Colony Optimization-based Multi-Agent System (TCO-MAS) integrated with an LSTM model for predictive adaptability. The deep learning LSTM model aids agents in forecasting future network conditions, enabling dynamic adjustment of pheromone levels for optimized power allocation and interference management. By simulating termite behavior, agents utilize pheromone-based feedback to achieve localized optimization decisions with minimal communication overhead. Experimental analyses evaluated the proposed TCO-MAS across key metrics such as Sum Rate, Energy Efficiency, Spectral Efficiency, Latency, and Fairness Index. Results demonstrate that TCO-MAS outperformed conventional algorithms, achieving a 20% higher sum rate and 15% better energy efficiency under high-load conditions. Limitations include dependency on specific pheromone adjustment parameters, which may require fine-tuning for diverse scenarios. Practical implications highlight its potential for scalable and adaptive deployment in ultra-dense wireless networks, though additional field testing is recommended to ensure robustness in varied real-world environments.

Augmented Reality (AR) and Virtual Reality (VR) technologies rapidly transform the healthcare landscape, offering innovative solutions to enhance patient care, medical education, and therapeutic interventions. This chapter delves into the current state of AR and VR in healthcare, exploring their diverse applications and their profound impact on reshaping various aspects of the industry. The chapter examines the multifaceted applications of AR in healthcare settings, including patient education and engagement through interactive visualizations, enhancing diagnostic procedures through real-time guidance, gamified rehabilitation programs, and empowering patients with chronic conditions through real-time feedback and monitoring. Additionally, it explores the transformative potential of VR in exposure therapy for anxiety and phobias, pain management and distraction, surgical training and simulation, and mental health assessments and interventions. While highlighting the numerous benefits and applications, the chapter also addresses the challenges and considerations associated with implementing AR and VR in healthcare, such as accessibility and cost, data privacy and security concerns, and user experience and design considerations. This chapter paves the way for discussions on the future of these immersive technologies in healthcare by providing a comprehensive overview of the current landscape and exploring the opportunities and challenges. It underscores the immense potential of AR and VR to lead to a more patient-centered, efficient, and accessible healthcare system that prioritizes personalized care and improved outcomes.

Virtual Reality (VR) therapy emerges as a groundbreaking solution in mental healthcare, providing a safe, controlled, and highly personalized environment for treating various mental health conditions. This chapter delves into the transformative potential of VR therapy, tracing its historical development and unique capabilities in creating realistic, multisensory virtual environments tailored to individual patient needs. The chapter explores VR therapy’s applications across a spectrum of mental disorders, including anxiety disorders, posttraumatic stress disorder (PTSD), chronic pain management, and depression. It examines how established therapeutic techniques, such as exposure therapy, cognitive-behavioral interventions, and mindfulness practices, are enhanced through VR’s capacity for immersion, presence, and embodied experiences. While highlighting VR’s potential benefits, including increased accessibility, personalization, and patient engagement, the chapter also addresses challenges. These encompass technological barriers, the need for standardized protocols, ethical considerations surrounding data privacy and informed consent, and the importance of responsible implementation guided by evidence-based practices. In conclusion, the chapter positions VR therapy as a pioneering approach poised to reshape mental healthcare delivery, underscoring the necessity for continued research, interdisciplinary collaboration, and the development of comprehensive guidelines to harness VR’s full therapeutic potential ethically and effectively.

The major prevalent primary bone cancer is osteosarcoma. Preoperative chemotherapy is accompanied by resection as part of the normal course of treatment. The diagnosis and treatment of patients are based on the chemotherapy reaction. Contrarily, chemotherapy without operation results in persistent cancer and an osteosarcoma regrowth. Thus, osteosarcoma patients should receive comprehensive therapy, which includes tumor-free surgery and global chemotherapy, to improve their survival. Hence, early diagnosis and individualized care of osteosarcoma are essential since they may lead to more effective therapies and higher survival rates. Here, the main goal of the recommended research is to use a unique deep learning approach to predict the osteosarcoma on histology images. Initially, the data is collected from the navigation confluence mobile osteosarcoma data of UT Southwestern/UT Dallas dataset. Next, the pre-processing of the collected images is accomplished by the Weiner filter technique. Further, the segmentation for the pre-processed images is done by the 2D Otsu’s method. From the segmented images, the features are extracted by the linear discriminant analysis (LDA) approach. These extracted features undergo the final prediction phase that is accomplished by the novel improved recurrent gated recurrent unit (IGRU), in which the parameter tuning of GRU is accomplished by the osprey optimization algorithm (OOA) with the consideration of error minimization as the major objective function. On contrast with various conventional methods, the simulation findings demonstrate the effectiveness of the developed model in terms of numerous analysis.

Recently monkeypox outbreak has raised concerns due to its increasing number of cases and diverse dermatological symptoms in 2024, which can complicate early diagnosis due to similarities with other viral infections such as measles and chickenpox. To enhance diagnostic accuracy, transfer learning models and artificial intelligence (AI) have been explored as effective tools. Pre-trained models such as VGG16, VGG19, ResNet50V2, and MobileNetV2 have been employed for monkeypox detection, each with distinct trade-offs in terms of computational efficiency and diagnostic precision. MobileNetV2 offers superior efficiency, but this comes at the cost of reduced accuracy. VGG models provide higher accuracy but require much more computational power.Among these models, DenseNet121 stands out by achieving 99% accuracy while requiring 37% less computational power, making it the model optimized choice for efficient and accurate monkeypox classification.

Micro/meso fabrication techniques have gained significant recognition globally for their advanced manufacturing capabilities. Among these, microforming stands out as a leading process in micromanufacturing. Despite growing interest in microextrusion for industrial applications, the technology remains underdeveloped compared to conventional forming methods, with limited expertise available. To address this gap, it is essential to develop a comprehensive understanding of the microextrusion process, which can guide the production of metallic microcomponents. This research focuses on the numerical simulation of microextrusion to study the influence of die entry angles on the deformation behavior of AA6063 aluminum alloy. Simulations were conducted using die angles of 15°, 30°, 45°, and 60° under varying frictional conditions. Results show a direct relationship between die angle and forming load, while punch displacement decreases as the die angle increases. The role of friction was also found to be crucial in the extrusion process. Numerical results for the 30° die angle were compared with experimental data, highlighting the effectiveness of finite element analysis in predicting microforming outcomes. This study demonstrates the potential of numerical simulation as a powerful tool for optimizing microforming processes in industrial applications. Keywords: Microextrusion; FE simulation; AA6063; Die-angle; friction

The rapid spread of COVID-19 has resulted in significant harm and impacted tens of millions of people globally. In order to prevent the transmission of the virus, individuals often wear masks as a protective measure for themselves and others. Coronavirus protection guidelines have been published by the World Health Organization (WHO). According to WHO standards, COVID-19 can be prevented by wearing a mask in public places and congested regions. In these places, it is very difficult to personally check to see if people are wearing face masks or not. The objective of this research work is to build a powerful, efficient, and real-time approach for detecting people not wearing masks. Three cutting-edge object identification models, namely YOLOv4, Tiny-YOLOv4, and YOLOv5, are employed in this study for the identification of masked faces. The proposed YOLOv5 model is evaluated using real-time images captured using a smartphone or tablet. The test images include both single and multiple people with and without masks. The YOLOv5 model achieved recognition accuracy of 88.90% with an average detection speed of 0.0316 s per image, whereas the YOLOv4 and Tiny-YOLOv4 produced recognition accuracy of 82.24% and 74.80% with an average detection speed of 0.0530 s and 0.0541 s per image, respectively. The comparative performance suggests that the YOLOv5 model has a maximum recognition accuracy of 88.90% in face mask identification tasks compared to other models such as the YOLOv4 and Tiny-YOLOv4.

The global spread of COVID-19, particularly through cough symptoms, necessitates efficient diagnostic tools. COVID-19 patients exhibit unique cough sound patterns distinguishable from other respiratory conditions. This study proposes an advanced framework to detect and predict COVID-19 using deep learning from cough audio signals. Audio data from the COUGHVID dataset undergo preprocessing through fuzzy gray level difference histogram equalization, followed by segmentation with a U-Net model. Key features are extracted via Zernike Moments (ZM) and Gray Level Co-occurrence Matrix (GLCM). The Enhanced Deep Neural Network (EDNN), tuned by the Coronavirus Herd Immunity Optimizer (CHIO), performs final prediction by minimizing error metrics. Comparative simulation results reveal that the proposed EDNN–CHIO model improves MSE by 25.35% and SMAPE by 42.06% over conventional models like PSO, WOA, and LSTM. The proposed approach demonstrates superior error reduction, highlighting its potential for effective COVID-19 detection.

In order to lower death risks, provide the mosteffective course of treatment, and improve communityhealthcare, the majority of recent research has concentrated onexamining prevalent illnesses in the population. One of theprevalent ailments that has impacted our society is kidneydisease. Around the world, kidney tumors (KT) rank tenth interms of frequency in both men and women. The organizationof cancer is a problem that is attracting increasing attention inthe domains of bioinformatics and computational biology. Thisstudy presents a comparative analysis of the latest developmentsin deep learning (DL) and machine learning (ML). While severalmethods have been proposed to tackle the cancer classificationchallenge, new research indicates that supervised and deeplearning-based methods are the most effective. Healthcare hasadvanced as a result of the creation of numerous machinelearning techniques for awareness evaluation in cancercategorization. It seems that there is a high requirement for theongoing development of efficient categorization algorithms inorder to handle the growth in healthcare applications. Thecomparative analysis of the proposed classification shows theaccuracy as 0.92%