Development of an IoT-Based Real-Time Patient Health Monitoring System
ABSTRACT: Accurate and timely monitoring of cardiac patients can be difficult, especially in remote or marginalised communities. This study proposes a remote real-time cardiac monitoring system that leverages Internet of Things (IoT) technologies to overcome these challenges. It combines wireless communication and IoT technologies to allow seamless transfer of vital Electrocardiographic (ECG) data, facilitating timely monitoring and intervention. The system also features a smartphone app, making it easier for clinicians to access and monitor patients' data remotely. Accurate placement of electrodes ensures precise ECG data, offering insights into the patient's heart activity. Additionally, the system's robust data storage features securely maintain and manage patient data, allowing for long-term monitoring and analysis for a holistic view of the patient's condition and informed treatment strategies. With its cutting-edge features, this remote real-time cardiac monitoring system transforms the monitoring and management of cardiac patients, offering a convenient, accurate and holistic approach to patient data management for improved healthcare
AI-Based Clinical Decision Support System for Thyroid Nodule Classification in Ultrasound Imaging with Web-Based Implementation
Abstract: Thyroid nodules are a frequent clinical phenomenon and proper classification into the normal, benign, and malignant types is required to diagnose and plan treatment at an early phase. One of the most common imaging techniques is ultrasound, which is non-invasive, economical, but its interpretation is subjective, and it requires the expertise of the radiologist. In this study, a novel intelligent artificial intelligence (AI) system of diagnostic thyroid nodules through ultrasound imaging is offered. An efficient preprocessing pipeline, comprising of image resizing, intensity normalization, CLAHE-based contrast enhancement, median filtering, and data augmentation, was used to improve image quality and the performance of the model. A variety of deep learning models were tested (a baseline convolutional neural network (CNN)) and various transfer learning architectures. The CNN baseline obtained 76% accuracy and transfer learning models greatly enhanced performance. VGG16 and MobileNetV2 were capable of 84% and 88% accuracy, respectively, but ResNet50 scored 91 %. EfficientNet achieved the highest performance of 94% accuracy, high recall, precision, and F1-score. The findings show that transfer learning was effective in classifying thyroid ultrasound and the proposed system has potential to be an effective clinical decision-support tool in enhancing diagnostic accuracy and early diagnosis of malignant cases.
TRAFFIC AND SECURITY MANAGEMENT SYSTEM: REAL-TIME VIDEO ANOMALY DETECTION USING AI MODELS
Abstract: The traffic and security management systems need effective real-time monitoring to guarantee the safety of the people, especially in the high-risk and crowded areas. Manual monitoring of CCTV video streams is time-consuming, prone to errors, and ineffective, which necessitates intelligent automated solutions. This paper introduces a real-time video anomaly detection system to monitor traffic and security with the help of LSTM-based deep learning. The suggested method uses a hybrid spatio-temporal feature extraction system that involves Convolutional Neural Networks (CNN) and Long Short-Term Memory (LSTM) networks to extract spatial features and temporal motion patterns in video sequences. The LSTM model is effective in learning sequential dependencies and thus detecting abnormal events accurately with time. The extracted features are then categorized with the help of various machine learning models, such as Histogram-Based Gradient Boosting (HGB), Gradient Boosting (GB), Extreme Gradient Boosting (XGBoost), Light Gradient Boosting Machine (LGBM), Support Vector Machine (SVM), and K-Nearest Neighbor (KNN). The UCSD Anomaly Detection Dataset is tested on the framework with performance measures of accuracy, precision, recall, F1-score, Cohen Kappa, Matthews Correlation Coefficient (MCC), and loss. Experimental results show validation accuracies of 76% (SVM), 72% (KNN), 90% (HGB), 98% (XGBoost), 95% (GB), and 98% (LGBM). Among them, XGBoost has the highest performance with 98 percent accuracy, better classification rates, and low loss, which proves the efficiency and strength of the suggested system in the context of real-time traffic and security surveillance applications.
Towards Multiple Knapsack Problem Approach for Home Energy Management in Smart Grid
Abstract: The energy demand of residential end users has been so far largely uncontrollable and inelastic with respect to the power grid conditions. In this paper, we describe a scheme to solve multiple knapsack problems (MKP) using heuristic algorithms. Keeping total energy consumption of each household appliance under certain threshold with maximum benefit is regarded as knapsack problem. Here, we design multiple knapsack problems for each hour of a day to schedule different numbers of appliance. To avoid peak hours, load is shifted in low and mid peak hours. Different algorithms are used to schedule household appliances. We use ant colony optimization (ACO) that is one of the meta-heuristic techniques to solve multiple knapsack problems which enables fast convergence rate for scheduling of appliances. Results show that propose scheme is an efficient method for home energy management to maximize user comfort and minimize electricity bills.
An Efficient Genetic Algorithm Based Demand Side Management Scheme for Smart Grid
Abstract: In this paper, we propose a novel strategy for a Demand Side Management (DSM) in a Smart Grid (SG). In this strategy, three types of loads are considered, i.e., residential load, commercial load and industrial load. The larger number of appliances of different power rating for each type of load is considered in this work. The focus of this work is to minimize the Peak to Average Ratio (PAR) to increase the efficiency of SG, by increasing the utilization of spinning reserves. On the other hand, our aim is to minimize the electricity consumption cost. Tackling the large number of appliances in an SG is a challenging task, because it increases the complexity of the problem. However, in literature the focus is on small number of appliance. In this work, the load scheduling problem is mathematically formulated and solved by using genetic algorithm. The simulation results show that the propose algorithm reduces the cost, while reducing the peak load demand of the SG.
Bio-Inspired Routing in Wireless Sensor Networks
Abstract: In order to increase network life time scalable, efficient and adaptive routing protocols are need of current time. Many energy efficient protocols have been proposed, the Clustering algorithm is also a basic technique used for energy efficiency.In this paper we propose an energy efficient routing protocol that is based on Artificial Bee Colony (ABC) algorithm of Bio Inspired.The presented protocol efficiently utilized characteristics of ABC algorithm such as foraging principle and waggle dance of honey bees. Waggle dance technique is used to find Routing Node (RN) that has maximum energy.Simulation results proves increase network life time and high throughput with minimum delay.
Interference and Bandwidth Aware Depth Based Routing Protocols in Underwater WSNs
Abstract: Many researcher has paid their to explore and monitor the under water environment. There are lot of application of Underwater WSNs like environment monitoring, exploration of under water surfaces, disaster preventions assisted navigation etc. Underwater sensors are totally different from the terrestrial sensors. Terrestrial sensor network uses the radio signal and underwater sensor network uses the acoustic signal. As the radio signal has not good strength that it can propagate in the water. The Radio signal can propagate over the large distance as compared to the acoustic signals. Therefor, acoustic signal are used. In this paper, we propose Energy Hole Repairing Depth based routing protocol (EHRDBR) and Interference-Bandwidth aware Depth based routing (IBDBR) protocol. In both protocols, nodes move toward the specific area where the other node dies and cover the energy hole. In EHRDBR, forwarder node is selected on the basis of the interference residual energy, and depth parameters. In IBDBR, interference, bandwidth, residual energy, and depth parameters are used to select the forward node. Our protocols have performed better in network lifetime, throughput and ene to end delay .