Design of an Exercise Monitoring System for Early Warning Heart Rate Risk Alarm with Confidence Intervals and Correlation Index Analysis
IoMT-Based Seizure Detection System using Optimizing Algorithm
Embedded Sensor Belt for Cattle Stomach Measurement Monitoring with Automated Alert Functionality
Design and Development of a Device for Skin Disease Prediction using Various Parameters
Innovative Solutions for Varicose Veins using Arduino-Powered Prediction and Therapy
Verilog Based UART System Design
Intel ® Processor Architectural and Integrated Development Environment Exploration
IoT based Smart Agriculture Monitoring Framework with Automation
An Integrated Model of Digital Fuel Indicator and GPS Tracking System for Vehicles
Designing of an Embedded system for Wireless Sensor Network for Hazardous Gas leakage control for industrial Application
Hardware Implementation of Artificial Neural Networks
Fault Analysis on Grid Connected MPPT BasedPhotovoltaic System
High Efficiency Hybrid Intelligent Street Lighting Using A Zigbee Network And Sensors
Design of Dual-Band Bandpass Filter Using Interdigital Embedded Open Loop Triangular Resonator Loaded with Stubs
License Plate Localization Using Novel Recursive Algorithm And Pixel Count Method
Exercise has become a vital component of modern lifestyle to streamline the daily schedule. A heart monitoring device is essential for maintaining good health. Current solutions may delay notification if heart rate rises abruptly above the threshold level. These problems have been addressed by developing a real-time heart rate monitoring system. The methodology used in the proposed method is to predict near conditions for heart rate that lead to failure during exercise, notably in people between the ages of 21 and 40. The proposed work methodology empirically assesses the relationship between heart rate, relative risk, and confidence intervals. The relative risk and confidence intervals are calculated as (observed heart rate/6) and (96% of heart rate). The innovative aspect of the suggested method is that it offers a virtually flawless early warning during workout sessions. This analysis allows for the establishment of an appropriate limit, enabling safe monitoring of exercise activity. The least common marginal values for the incidence of heart failure were determined based on these factors and gender classification. Men between the ages of 21 and 30 have a secure zone limit of 120 and a maximum CI of 50%; men between the ages of 31 and 40 have a safe zone limit of 113 and a maximum CI of 55%; and men among the ages of 41 and 60 have a safe zone limit of 102 and a maximum CI of 50%.
The rapidly growing field of electroencephalography (EEG)-driven Seizure Detection Systems (SDSs) has attracted significant attention in the healthcare industry, focusing mainly on creating innovative methods for the early detection of epileptic seizures. Epilepsy, a neurological disorder marked by recurrent seizures, results from sudden changes in brain electrical activity. A traditional electroencephalogram (EEG) records the synchronized electrical impulses produced by the brain. Building on this principle, a new IoT-enabled EEG system is proposed to monitor and analyze multichannel EEG data. The system includes two key components: the multichannel EEG recording module and the seizure detection module. The main goal of this research is to design and develop an optimized seizure detection module that employs the Flower Pollination Algorithm (FPA) along with a CNN classifier within an IoT-supported EEG monitoring system to detect seizures. This proposed system offers improved performance compared to previous algorithms, with significant gains in accuracy using the CNN classifier. The effectiveness of this approach is expected to enhance the analysis of seizure data, especially in wearable medical devices.
Monitoring the stomach size of cattle is crucial for the early detection of health problems like bloat, malnutrition, or digestive disorders, allowing for appropriate intervention. It also helps track pregnancy progress and ensures optimal nutritional intake, directly impacting milk production in dairy cattle and growth in beef cattle. This practice enhances overall health, improves productivity, and helps prevent serious health complications. This paper introduces a smart wearable belt designed for comprehensive cattle health monitoring. The belt features measurement markings and sensors to gauge the stomach size of cattle accurately, providing essential data for effective livestock management. It is used for various purposes, including monitoring nutritional intake, detecting digestive issues early, tracking pregnancy, identifying illness, assessing stress and behavior, managing breeding, and improving milk production and beef cattle's meat quality. The belt incorporates an Arduino-controlled system with a GSM module that sends automatic alerts when certain thresholds are met, facilitating timely interventions. This tool enhances cattle welfare and farm efficiency by enabling real-time monitoring and automated notifications.
Skin diseases are a serious public health issue that are frequently impacted by physiological and environmental variables such as skin hydration, temperature, and UV radiation exposure. Potential skin disorders can be predicted, and their advancement can be stopped with early diagnosis and monitoring of these factors. The goal of this study is to create a device that can identify skin conditions by combining a moisture, UV light, and temperature sensor. An Arduino Uno and an ESP12 Wi-Fi module are interfaced with these sensors to provide effective data collection and processing. The gathered sensor data is examined to find associations with particular skin disorders, such as elevated UV levels that might point to a melanoma risk. Variations in temperature and moisture content also reveal information about other dermatological conditions. A simple website, developed with HTML, CSS, and JavaScript, presents the processed data. The website enables proactive skin health monitoring by allowing individuals to input sensor readings and view real-time forecasts of potential skin disorders. This system presents an innovative approach to addressing skin health issues by integrating advanced sensor technology with web-based analysis. Accurate sensors, reliable technology, and an intuitive interface work together to offer early forecasts, promoting preventative care and reducing the prevalence of skin conditions. This study highlights how biomedical engineering and IT can be combined to develop effective healthcare tools.
The propensity for idleness is more prevalent in contemporary society. In our modern age, individuals are growing indolent. It results in physical inactivity and diminished blood circulation within the body. Consequently, the vascular epithelial cells undergo inflammation, leading to the development of varicose veins. Primarily, it impacts the lower extremities; however, it can occur throughout the body. When varicose veins become thrombosed, the condition is termed superficial thrombophlebitis, which is typically associated with significant pain. The data collected from the survey is utilized to create a predetermined dataset. The preset dataset functions as a threshold value. The location data of an individual is analyzed utilizing several sensors. The data to be analyzed include standing, knee bending, and movement over time. The obtained positional data is processed on a Raspberry Pi utilizing artificial intelligence (AI). It is a non-invasive diagnostic and treatment approach for varicose veins that utilizes heat and vibrational therapy.
