Journal of Electronics and Telecommunication System Engineering

Smart Vehicle Accident and Alcohol Sensing Alert with Engine Locking System

Shruthi V. — 2026-01-30

The vehicle accident and alcohol sensing alert with engine locking system is a smart vehicle safety solution designed to reduce road accidents caused by drunk driving and delayed emergency response. This system integrates alcohol detection, accident detection, automatic engine control, and alert mechanisms to enhance overall road safety for drivers and pedestrians. An MQ-3 alcohol sensor is used to continuously monitor the alcohol concentration in the driver’s breath. If the detected alcohol level exceeds a predefined safe threshold, the system immediately restricts engine ignition or disables the running engine, thereby preventing the vehicle from being operated under unsafe conditions. This feature plays a crucial role in minimizing accidents due to alcohol consumption. To detect collisions or sudden obstacles, IR sensors are employed. These sensors help identify accident events in real time by detecting abrupt changes or impacts. The entire system is controlled by a microcontroller, which continuously processes sensor inputs and makes decisions based on programmed safety logic. In the event of alcohol detection or an accident, the system activates a buzzer alert to warn the driver and triggers a communication module to send notifications to emergency contacts or authorities. This ensures quick response and timely medical assistance during emergencies. By combining monitoring, control, and alert functionalities into a single embedded platform, the proposed system significantly enhances vehicle safety, reduces drunk-driving incidents, and ensures rapid accident reporting, contributing to safer roads and improved traffic management.

IoT-based Solar-powered Air Purification with Air Quality Monitoring System

Sushant Patole — 2026-03-07

The IoT-based air purification system is an advanced and intelligent solution designed to monitor and improve indoor air quality in real-time. Air pollution has become a major concern due to increasing industrialization, urbanization, and vehicular emissions, which lead to harmful health effects such as respiratory problems and allergies. This system uses various air quality sensors to detect pollutants such as carbon dioxide (CO₂), carbon monoxide (CO), smoke, dust particles, and other harmful gases present in the environment. The collected data is processed using a microcontroller like Node MCU or Arduino, which continuously analyzes air quality levels. When pollution levels exceed the safe threshold, the system automatically activates the air purification unit. The purifier may include components such as a High Efficiency Particulate Air (HEPA) filter, an activated carbon filter, and an exhaust fan to remove dust, odor, and toxic gases effectively. Through internet of things (IoT) technology, the system sends real-time air quality data to a cloud platform or mobile application, allowing users to monitor and control the purifier remotely. Additionally, the system can be powered by renewable energy sources such as solar panels to enhance sustainability and reduce electricity consumption. This smart and automated approach ensures energy efficiency, user convenience, and improved health conditions. The IoT-based air purification system is suitable for homes, offices, hospitals, and industrial environments, providing a cost-effective and reliable solution for maintaining clean and healthy air.

Microgrid Challenges on Control, Operation, Modelling, Application and Future Perspectives: A Review

L. Bangar Raju — 2026-03-18

Power electronics play a crucial role in modern microgrids, enabling efficient grid integration, energy conversion, and control of distributed energy resources. This article presents a comprehensive study on the modelling and control strategies of power electronics in microgrids. The main theme is on inverter-based resources, voltage/frequency regulation, droop control, and advanced model predictive control. The challenges of system stability, harmonics, and real-time operation of Microgrids are examined. The interplay between digital controllers, hardware limitations, and emerging wide-bandgap devices is discussed, along with recent advancements in AI-based control. The study aims to bridge the gap between theoretical modelling and practical control implementations to foster robust and resilient microgrid operation. The conventional power grids are now obsolete, as it is difficult to protect and operate numerous interconnected distributed generators. A proper investigation of microgrid architectures is presented in this article to address the issues. This research also explores deep investigations for the improvement of concerns and challenges in various power converter topologies with the aid of control strategies and communication techniques. This in-depth research is aimed at upgrading the appropriate power converter configuration to enhance sustainable growth in power quality, stability, and control over power sharing.

Fractional-Order PID-based MPPT Controller TLBO-Optimized for Isolated PV System under Dynamic Atmospheric Conditions

Raj Sahu — 2026-04-04

This study introduces a maximum power point tracking (MPPT) approach for a standalone photovoltaic (PV) system that utilizes a fractional order proportional-integral-derivative (FOPID) controller. Its performance is evaluated against traditional perturb and observe (P&O) and classical PID-based MPPT techniques. The main aim of the proposed method is to maximize the power output of the PV system by continuously regulating the duty ratio of a DC-DC boost converter. To accomplish this, several MPPT control strategies, including PID and FOPID controllers, are designed and implemented. As the effectiveness of these controllers largely depends on the appropriate selection of their parameters, the teaching-learning-based optimization (TLBO) algorithm is applied to determine optimal gain values. This optimization process leads to improved system performance in terms of output voltage, current, and overall power generation. The proposed TLBO-tuned FOPID MPPT scheme is assessed through a comparative analysis with conventional P&O and PID-based methods. Performance indicators such as steady-state oscillations, settling duration, response delay, peak overshoot, and the achievable maximum voltage, current, and power are examined to highlight the advantages of the developed approach.

Hybrid CNN-LSTM Architecture: Early Heart Disease Prediction from Electronic Health Records

Dipti S. Lopes — 2026-04-06

Cardiovascular diseases (CVDs) remain the leading cause of mortality in India, accounting for 20% of global heart attack deaths and contributing to over 32,000 fatalities annually. Early prediction of heart disease is crucial for timely intervention and reducing premature mortality. This study proposes a novel hybrid deep learning architecture combining convolutional neural networks (CNN) and long short-term memory (LSTM) networks with a multi-visit attention mechanism to predict heart disease from electronic health records (EHR). Unlike existing models that process single-visit data, this architecture analyzes sequential patient visits (up to 5 temporal sequences) to capture disease progression patterns. The proposed model extracts spatial features using CNN layers, processes temporal dependencies through LSTM networks, and employs a self-attention mechanism to prioritize critical clinical features across multiple patient visits. By validating this approach on the UCI heart disease dataset (303 patients) and a pilot subset of 50 Indian patient records, 91.2% accuracy in preliminary trials was achieved. Full validation on 500 patients is planned for extended work, incorporating region-specific risk factors, including diabetes prevalence, hypertension, lifestyle patterns, and healthcare accessibility.