Journal of Advanced Research in Embedded System

Electric Vehicle Warning Sound System

K. Santha kumari, R. Karpaga Priya — Thu, 14 May 2026 00:00:00 +0000

The Electric Vehicle Warning Sound System (EVWSS) is designed to generate minimal yet effective sound levels to aid pedestrians, visually impaired individuals, and cyclists in identifying the presence and direction of electric vehicles. This system produces a sequence of alert sounds tailored to ensure awareness in the vicinity of electric vehicles. The proposed solution dynamically adjusts the frequency and volume of pre-stored WAV files based on the vehicle's speed, transmitting the audio signals to an audio power amplifier. The application modulates the frequency of the WAV files in accordance with the vehicle's speed, akin to the engine stroke. WAV files are stored in flash memory and customized as per the end user's requirements. Based on the Potentiometer input, the system selects WAV file from flash memory, modifies its frequency and pitch, and sends the processed signal to the audio power amplifier.

DOI: https://doi.org/10.24321/2395.3802.202612

Design and Implementation of a Vision‑Assisted Lift‑Based Automated Parking System with License Plate OCR and Real‑Time Slot Management

Thu, 18 Jun 2026 00:00:00 +0000

This work presents a vision-assisted, lift-based smart parking and retrieval system that integrates real-time embedded control, multi-sensor validation, and centralized event logging for improved occupancy reliability and accountability. The proposed architecture employs an STM32F446ZET6 (NUCLEO-144) as the deterministic controller for slot allocation, safety supervision, and multi-axis motion sequencing, while an ESP32-CAM performs entry-side image capture and communicates with a local OCR server to extract the vehicle license plate. Vehicle entry is verified using a dual-sensor strategy (IR sensing + metal detection) to reduce false triggers and unauthorized access, and the recognized plate text is transmitted to the STM32 via UART to enable identity-linked slot assignment and traceable retrieval. Access control is implemented using a servo-actuated barrier, and automated storage/retrieval is executed using a lift mechanism driven by NEMA17 stepper motors with DRV8825/A4988 drivers, supported by limit-switch homing and emergency stop handling. User interaction is provided through I2C LCD displays, an exit-side keypad interface, and audio prompts, while operational data (vehicle identifier, timestamps, and occupancy status) is stored in a MySQL database for real-time monitoring through a web dashboard.

DOI: https://doi.org/10.24321/2395.3802.202613

How to cite this article:

Pawar S B, Pandhare S H, Shingane A S, Rajankar S O. Design and Implementation of a Vision‑Assisted Lift‑Based Automated Parking System with License Plate OCR and Real‑Time Slot Management. J Adv Res Embed Sys 2026; 13(3&4): 10-‑14.

Home Energy Use Optimizer: A Review of IoT, AI, and Fault-Aware Residential Energy Management

Tue, 29 Sep 2026 00:00:00 +0000

Residential electrification, connected appliances, and variable tariffs have increased the need for practical home energy management systems (HEMS). Existing research demonstrates the value of optimization, Internet of Things (IoT) monitoring, artificial intelligence (AI), machine learning (ML), and model predictive control for reducing electricity cost and peak demand. However, many solutions emphasize scheduling and forecasting while treating appliance-level fault detection and automatic safety isolation as secondary functions. This paper presents a structured narrative review of 13 studies published between 2020 and 2026 and synthesizes their objectives, methods, strengths, and implementation gaps. Based on the synthesis, a low-cost Home Energy Use Optimizer is proposed using an ESP32/Arduino-class controller, voltage and current sensing, relay-based load isolation, local display, Wi-Fi connectivity, bill estimation, and user alerts. The architecture combines real-time monitoring, threshold-based protection, remote supervision, and extensibility toward predictive analytics. The paper identifies hardware validation, interoperable device integration, cybersecurity, explainable control, and field evaluation as priorities for future work.

IoT-Based Smart Attendance and Access Control System Using RFID and Face Verification: A Review

Paresh Patil, Nikhil Patil, Rohan Patil, Nishikant Patil, Tushar Patil — Tue, 29 Sep 2026 00:00:00 +0000

Attendance management and access control are important requirements in educational institutions, offices, laboratories, and other restricted areas. Traditional attendance systems mainly depend on manual records, while RFID-based systems provide faster identification but cannot always confirm whether the person using the RFID card is the actual registered user. This can result in problems such as proxy attendance and unauthorized access. The integration of Internet of Things (IoT), Radio Frequency Identification (RFID), and face verification provides an opportunity to develop a more secure and automated solution. RFID can be used to identify a registered user, while face verification provides an additional check of the user's identity. In the proposed system, an RFID reader is connected with an ESP32 controller and an ESP32-CAM is used to capture the user's face. Attendance is recorded and access is provided only when the RFID information and face identity are successfully matched. The system also uses IoT connectivity to store attendance information digitally and support remote monitoring. An electronic lock controlled through a relay can be used to manage access to a restricted area. This review discusses recent developments in RFID-based attendance systems, face-recognition-based attendance systems, IoT-enabled monitoring, and combined authentication approaches. It also identifies the research gap in integrating attendance management, face verification, electronic access control, and IoT monitoring into a single low-cost system. The proposed approach aims to improve attendance reliability, reduce manual work, decrease the possibility of proxy attendance, and provide better control over restricted access.

Ultrasound-Based Smart Blind Cap for Safe Navigation

Kanchana K, Vibin K, Suriya A — Thu, 14 May 2026 00:00:00 +0000

This smart blind cap is one of the most innovative concepts wherein safety and independence for individuals with visual impairments are maximized. The device scans its surroundings continuously and instantly identifies obstacles with the aid of cutting-edge ultrasound technology. As soon as the object enters within certain proximity, the cap alerts the wearer in terms of sound or even haptic signals that ensure safe navigation. The user will find themselves moving confidently and even alone with this technology and greatly reduced accidents, which is further complemented by the comfortable light headpiece fit that lasts longer and gives a person maximum liberty in the course of his or her daily activities. Other improvements, such as GPS guidance and smartphone connectivity in conjunction with more complex algorithms, put this far ahead of assistive technologies. This innovative gadget helps the partially sighted people to communicate better with the environment, hence widening the possibility for a more inclusive and accessible society.

DOI: https://doi.org/10.24321/2395.3802.202611

Water Level Monitoring System Using Dual Camera

Fri, 19 Jun 2026 00:00:00 +0000

Monitoring water levels is essential for the proper operation of water resources and safety. Most existing systems use sensors like ultrasonic or float devices, but these methods often face problems like corrosion, regular maintenance, and reduced reliability in harsh conditions. In our work, we developed a camera-based water level monitoring system using Raspberry Pi 5. The camera continuously captures images of the water surface and processes them using image processing techniques such as greyscale conversion, filtering, and edge detection to identify the water level accurately. This method does not require direct contact with water, which helps improve durability. which improves durability and reduces maintenance costs. The processed data is used to monitor water levels and control the system accordingly. The proposed system provides an efficient, cost-effective, and reliable solution for modern water level monitoring applications.

DOI: https://doi.org/10.24321/2395.3802.202614

How to cite this article:
Kawitkar R S, Balan M S, Rajagopalan A, Bhosale S, Daware S, Shinde S. Water Level Monitoring System Using Dual Camera. J Adv Res Embed Sys 2026; 13(3&4): 15-18.

Embedded-Based Battery Management System using TinyML and IoT: A Review

Disha Bhaskar Chaudhari, Sumit Nana Mahajan, Shraddha Anil Patil, Tushar Patil — Tue, 29 Sep 2026 00:00:00 +0000

Lithium-ion batteries require management systems that combine dependable protection with increasingly accurate state estimation and predictive maintenance. This review critically examines embedded battery management systems that integrate Tiny Machine Learning (TinyML) and Internet of Things (IoT) connectivity. Nineteen unique studies published from 2022 to 2026 were synthesized across four dimensions: monitored variables and predicted states, learning approach, embedded deployment evidence, and communication architecture. The literature shows strong progress in data-driven estimation of state of charge, state of health, remaining useful life, temperature, and abnormal cell behavior. However, the evidence is fragmented: many studies validate algorithms offline, a smaller group reports true microcontroller deployment, and only a limited subset closes the loop from prediction to safety action while maintaining secure remote monitoring. The review therefore proposes a layered reference architecture in which deterministic protection remains local, TinyML performs low-latency inference at the edge, and IoT services support supervisory visualization, fleet analytics, and controlled model updates. Key research priorities are cross-chemistry validation, standardized edge benchmarks, uncertainty-aware inference, cybersecurity, drift monitoring, and hardware-in-the-loop evaluation. The synthesis provides a practical roadmap for low-cost, energy-efficient, and trustworthy intelligent BMS development.

A LoRa and GSM-Integrated Smart Emergency Watch System with Real-Time Tracking

Minal chandrakant patil, Dhanshri Sanjay Chaudhari, Mahesh Manohar Bhat — Tue, 29 Sep 2026 00:00:00 +0000

Ensuring the safety of vulnerable groups such as women, children, elderly individuals, tourists, and hikers has become increasingly critical in today’s rapidly evolving world. Safety concerns are exacerbated in environments where access to reliable communication networks is limited or unavailable. This paper presents Safe Connect, a versatile, wearable emergency alert device that integrates LoRa (Long-Range communication), GSM (Global System for Mobile Communication), and GPS (Global Positioning System) technologies to provide real-time emergency alerts and accurate location tracking [1]. Unlike conventional safety systems that rely solely on cellular networks, Safe Connect employs LoRa as the primary communication method for long-range alerts, making it highly suitable for rural or remote areas with poor cellular coverage. GSM acts as a backup, ensuring SMS alerts can be sent when LoRa is unavailable [2]. Additionally, the system features a camera module (ESP32-CAM) that captures real-time video footage and stores it locally on an SD card, which can later be retrieved as evidence. The system is designed to cater to a wide range of users, including women, tourists, children, elderly individuals, and hikers, offering a comprehensive and reliable solution that operates in both urban and rural environments. Testing demonstrates the device's ability to provide reliable alerts, real-time tracking, and robust performance in diverse conditions, making it an essential tool for enhancing personal safety across multiple demographic groups

TinyML-Based IoT Wearable for Seizure-Like Event Detection and Emergency Alerting

Ms. Riya Bhangale, Sneha Sarode, Pramod Kumar Gupta — Tue, 29 Sep 2026 00:00:00 +0000

Epilepsy affects a large population worldwide, and a considerable share of seizure-related injuries occur when an episode is unwitnessed. This paper presents the proposed architecture of a low-cost, wrist/limb-worn wearable device intended to flag seizure-like physical movement and alert a designated caregiver. The system combines a six-axis inertial measurement unit (IMU) for motion sensing with a photoplethysmography (PPG) sensor as a supplementary physiological input, processed on an ESP32 microcontroller. Two detection paths are proposed: a TinyML classifier trained on motion-pattern features, and a deterministic threshold-based fallback rule that can operate independently if the learned model is unavailable or under-trained at the time of deployment. On flagging a probable event, the device is designed to acquire a GPS location fix and transmit an SMS alert through a GSM module to a caregiver. The device does not diagnose epilepsy and does not claim clinical-grade seizure detection; it is designed strictly as a supportive alerting aid that flags seizure-like movement patterns for human verification. This paper describes the system architecture, sensor roles, decision logic, and the validation plan intended for the working-prototype stage of the project.

RFID-Based Autonomous Campus Delivery Trolley

Tue, 29 Sep 2026 00:00:00 +0000

Autonomous mobile robots are increasingly being considered for repetitive transport tasks in environments where routes and operating areas can be controlled. This paper presents a low-cost RFID-based autonomous campus delivery trolley intended for controlled indoor routes. The system integrates an ESP32 controller, four geared encoder motors, encoder feedback, MPU6050 heading correction, RFID checkpoint confirmation, three-direction ultrasonic obstacle sensing, secure servo locking and application-assisted delivery coordination. The delivery compartment remains locked during movement and is released only after recipient authentication through RFID, with OTP provided as a backup. A simple request workflow allows the requester to specify the item, quantity, pickup location and destination, while the pickup-side user confirms loading. The design deliberately avoids LiDAR-based mapping, camera-based SLAM and ROS for the initial prototype, reducing hardware and integration complexity while retaining the functions required for repeatable point-to-point campus delivery. Since the prototype is under development, final performance values are reserved for the hardware-integration and testing stage.

Index Terms—Autonomous delivery trolley, ESP32, RFID, MPU6050, encoder odometry, ultrasonic obstacle detection, secure delivery, campus robotics.

Smart Home Automation

Mayuri Patil, Damini More, Devyani Patil, Akanksha Jadhav — Tue, 29 Sep 2026 00:00:00 +0000

— Smart home automation is an important application of the Internet of Things (IoT) that improves convenience, accessibility, security, and energy management. This paper presents a Smart Home Automation System integrated with web technologies and IoT. A web-based dashboard allows users to monitor and control household appliances remotely. The frontend can be developed using HTML, CSS, and JavaScript, while an ESP32 or similar Wi-Fi-enabled controller communicates with physical devices. User commands are transmitted through a network to the controller, which operates appliances through relay modules. Sensors such as temperature, motion, and light sensors can also support monitoring and automatic operation. The proposed architecture is simple, scalable, and affordable for academic prototype development.

IoT-Based Smart Agriculture System with Automatic Irrigation: A Review

Harshal Patil, Pravin Tamboli, Sanket Jagtap, Dipak Sonwane, Dipak Khadse — Tue, 29 Sep 2026 00:00:00 +0000

Agriculture requires efficient and reliable water management because conventional irrigation can supply water without considering actual soil moisture or changing environmental conditions. This project presents an IoT-based smart agriculture system with automatic irrigation using an ESP32 microcontroller. The system monitors soil moisture and environmental conditions and controls a relay-driven water pump according to measured soil condition. IoT connectivity enables remote observation and manual control through a cloud platform. The proposed system is designed as a low-cost embedded solution for improving water-use efficiency, reducing unnecessary irrigation, minimizing human intervention and supporting sustainable agricultural practices. The proposed work further considers weather information before irrigation so that watering can be avoided when rainfall is expected.