Journal of Advanced Research in Electronics Engineering and Technology

Advancements in ADAS and Integration with Legacy systems

Dr. Fauzia Siddiqui — 2026-05-15

Advanced Driver Assistance Systems (ADAS) have significantly evolved, leveraging artificial intelligence (AI), machine learning (ML), and sensor fusion technologies to enhance vehicle automation, safety, and performance. This paper critically analyses ADAS advancements, challenges in retrofitting legacy systems, and safety-performance outcomes of ADAS integration. The study identifies key technological improvements, including the integration of LiDAR, radar, and real-time V2X communication, which enhance situational awareness and decision-making. However, retrofitting new ADAS into legacy vehicles presents challenges such as compatibility constraints, cybersecurity risks, and high implementation costs. Furthermore, while ADAS integration has demonstrated substantial improvements in accident prevention, driver assistance, and traffic efficiency, usability concerns related to automation reliance and human-machine interaction remain. The findings underscore the need for standardised protocols, adaptive software solutions, and robust testing frameworks to ensure seamless integration. Future research should explore adaptive AI-driven ADAS frameworks, real-world validation of cloud-edge architectures, and policy frameworks for global ADAS standardisation. Addressing these gaps will accelerate the adoption of next-generation autonomous driving technologies while ensuring safety, efficiency, and regulatory compliance.

DOI: https://doi.org/10.24321/2456.1428.202601

Assessment of Milk Adulteration Using Sensor Based Spectrophotometer

Avinash Kaushal — 2026-05-15

A serious issue that compromises consumer health, safety, and quality is milk adulteration. This paper introduces a spectroscopic system based on photodiodes that uses light intensity measurements to identify milk adulteration. The system proposes a spectrophotometer sensor-based method to analyse the transmitted light, converting it into Analogue-to-Digital Converter (ADC) values to relate to adulteration levels ranging between 10% and 100%. It requires a 10 ml milk sample to show the results in a 10-second response time and sensitivity of 10%. For this system, a total of 20 random samples were tested. For ensuring the accuracy of the detection of impurities like water, a careful calibration process was followed to match ADC values with adulteration percentages. The suggested approach offers a quick, practical, and economical way to assess the purity of milk.

DOI: https://doi.org/10.24321/2456.1428.202602

TinyML on Microcontrollers: A Review

Ugyen Jigme Rangdrel — 2026-05-15

Tiny Machine Learning (TinyML) has emerged as a potential paradigm for deploying and training machine learning models on resource-constrained systems like microcontroller units (MCUs) to enable real-time and low-power intelligent systems at the edge. This paper presents a comprehensive review on the current landscape of TinyML, focusing on architectural considerations of MCUs and machine learning models, model optimisation techniques, deployment techniques, and potential application-specific implementations of TinyML. Among the proposed models and frameworks are MCUNet, EfficientNet, TinyFL, TinyOL, TinyOPs and many more, which explore approaches to enhancing the efficacy, model training, and optimisation techniques for deploying deep neural networks on MCUs. We explore the different trade-offs in training and compression methodologies, techniques used for optimising inference for efficient execution of models and focus on exploring the feasibility of on-device training on MCUs so that the model can adapt to real-time sensing and collation of data. Furthermore, we examine the possibilities of real-world applications spanning healthcare, industrial automation and smart environments while focusing on the potential and limitations of TinyML in different domains. By reviewing the current situation of the various aforementioned factors in TinyML, this paper aims to provide a foundational insight into the future directions of study in this field.

DOI: https://doi.org/10.24321/2456.1428.202603