← Back to Archives
VOLUME 14, ISSUE 8, AUGUST 2026
Publishing in progress..
Automatic Peak-to-Peak Detection and Segmentation of Radial Pulse Waveforms
Raksha Amrutkar, Nishant Patil
Weapon Detection System
Mr. Prateek Sharma, Mr. Raj Ratna Rana, Mr. Priangshu Sen, Dr. Beenarani Manoj
Vehicle Tracking and Traffic Analytics System
Kunal Meshram, Pratham Mehta, Devisha Agrawal, Dr. Beenarani Manoj
A Survey On Recent Research Trends Towards Compression Of Image Using DPCM
Mandhara M Panedakatti, Meghana R, Keerthi B. K, Kampana B. E, Prof.Lakshmamma K. N
A Survey on Recent Research Trends Towards ECG Denoising for Sustainable Healthcare
Prof. Ranganath B, Meghana M Panedakatti, Priyanka R L
Predictive Maintenance using Python with Silhouette Analysis
VINEETA SAHU, Ms. DOLLY VERMA, DR. ASHISH TAMRAKAR
Computer Vision-Based Stock Quality Analysis and Rotten Quantity Detection for Fresh Produce in Quick-Commerce Warehouses
Vignesh Murali, Sarvesh S, Pranav H, Charulatha R.T
Smart Pharmacy AI: A Full-Stack Web Application for Medicine Inventory Management with an Extensible Computer-Vision and AI-Chatbot Architecture
T Aakash, G S Praveen Balaji, M Jaiaakash, Dr. Beenarani Manoj
Illumination-Adaptive Multi-Branch Feature Fusion for Robust Person Re-Identification
R Sivani, Rakshitha S N, Shreya Sathapathi, Charulatha R.T
Computer Vision and Deep Learning-Based Universal Plant Leaf Disease Classification, Automated Necrotic Segmentation, and Agronomy Remedy Diagnostic System
HARI SRINIVAS T, BEENARANI MANOJ
A Survey on Recent Research Trends Towards A Comprehensive Review of Energy-Efficient FIR Filters on FPGA
Anooshka G, Dhrriti Shree D, Sri lakshmi BM, Mrs. N S Mythreye
LITERATURE REVIEW A Sustainable Approach to Low-Power Real-Time PLL Design Using Current-Starved VCO in 45-nm CMOS Technology
Dharun.G, Chetan B.H, Bhavani Shankar, Ganesh, Prof. Kiranmayi. M
Energy-Efficient 32-Bit RISC-V Processors Design in 45nm
Bhoomika J, Manjunatha V, Chandan B, Dr. Chaitra A S
An ultraviolet measuring and UV index calculating system, with multiple alarm capabilities, using FPGAs and VHDL
Leonidas Dimitriadis, Dr Evangelos I. Dimitriadis
DermAI: A Full-Stack Deep Learning Web Application for Explainable Skin Lesion Screening Using MobileNetV2 and Grad-CAM
Yokesh Anandan, Ahil Gangatharan, Christon Davis C, Dr.Beenarani Manoj
Enhanced Reinforcement Learning with Optimization for the Threat Detection in VLC Networks-based 5G
Vijayakumari K Anusudha K
Design and Development of a DIY Line Follower Robot Using Embedded Systems
Kosgi Rishikesh Reddy, Palamuru Paramesh, Muppana Tarun, Dr. B. Ramu
Abstract
Automatic Peak-to-Peak Detection and Segmentation of Radial Pulse Waveforms
Raksha Amrutkar, Nishant Patil
Abstract: Accurate identification of systolic peaks and individual pulse cycles is important for reliable analysis of radial pulse waveforms. This study presents an automated peak-to-peak based method for systolic peak detection and pulse-cycle segmentation from real-time radial pulse signals. Radial pulse recordings were acquired using a Nellcor SpO₂ probe at a sampling frequency of 500 Hz, with three-minute real-time PPG recordings obtained from 25 samples. The acquired signals were subjected to baseline correction, smoothing, Savitzky–Golay filtering, and normalization to reduce signal variations while retaining relevant waveform characteristics. Systolic peaks were identified using a prominence-based detection approach incorporating signal-dependent amplitude characteristics and minimum peak- distance criteria. Consecutive detected peaks were used to determine peak-to-peak intervals and adaptive boundaries for pulse-cycle segmentation, followed by valley-based refinement of the segment boundaries. The peak-detection performance was quantitatively assessed using true-positive, false-positive, and false-negative detections together with sensitivity, precision, detection error rate, and F1-score. Additionally, 25 impedance plethysmography (IPG) samples representing five drug conditions were used to compare the peak-detection results obtained using the proposed method with those obtained using BARC software as the reference method. The proposed method provides an automated approach for consistent peak identification and segmentation of radial pulse waveforms.
Keywords: Radial Pulse Waveform, Peak-to-Peak Detection, Pulse Segmentation, Savitzky-Golay Filtering, Pulse Cycle Extraction, Real-time Pulse Analysis.
Keywords: Radial Pulse Waveform, Peak-to-Peak Detection, Pulse Segmentation, Savitzky-Golay Filtering, Pulse Cycle Extraction, Real-time Pulse Analysis.
Abstract
Vehicle Damage Detection System
Arjun Singh, Anshika Shukla, Dr. Beenarani Manoj
Abstract: The automation of vehicle damage assessment has emerged as a cornerstone requirement for modernizing the automotive insurance, rental, and fleet management industries. Traditional inspection paradigms rely heavily on manual labor, leading to subjectivity, slow processing times, and high administrative overhead. This research presents a novel, comprehensive AI-powered vehicle damage detection system that mitigates these challenges through advanced deep learning techniques. By leveraging the state-of-the-art YOLOv8 architecture, our system enables real-time capability in identifying, localizing, and classifying multiple classes of superficial and structural vehicular damages. This paper delineates the end-to-end framework: starting from robust dataset preprocessing pipelines and moving toward an intricate architectural design composed of a FastAPI backend proxy and a React.js client interface. Furthermore, we provide an extensive mathematical formulation of the underlying neural network operations, detailing the equations driving spatial convolutions, Intersection over Union (IoU) metrics, and custom Focal Loss computations. Empirical evaluations demonstrate an exceptional Mean Average Precision (mAP@0.5) of 0.942, establishing the viability of this solution for scalable, production-grade deployment environments. This work extensively validates the integration of micro-services with edge-compatible AI vision models, paving the way for fully autonomous vehicle inspection checkpoints.
Abstract
Weapon Detection System
Mr. Prateek Sharma, Mr. Raj Ratna Rana, Mr. Priangshu Sen, Dr. Beenarani Manoj
Abstract: Rising incidents of weapon-related violence in public spaces have intensified demand for automated surveillance systems capable of real-time weapon identification. This paper presents a complete end-to-end weapon detection and alerting pipeline built on the YOLOv8 nano architecture. The system identifies three weapon categories — knives, pistols, and rifles — from live camera streams, webcam feeds, and static images. To address the well-known false-positive problem in weapon detection, we introduce a structured hard-negative mining strategy: background images sourced from diverse indoor environments (offices, homes, classrooms, public spaces) are automatically screened by the model; frames that generate spurious detections are harvested and re-introduced into the training corpus with empty labels. The dataset, comprising approximately 11,500 annotated images across three weapon classes, is further augmented with 1,500+ negative samples. After five iterative fine-tuning rounds with mosaic, mixup, and copy- paste augmentation, the final model achieves an overall mAP@50 of 0.727 (knife 0.75, pistol 0.55, rifle 0.88). An accompanying alert subsystem enforces temporal debouncing — requiring N consecutive high-confidence frames before triggering — and dispatches annotated evidence images to operators via Telegram or configurable HTTPS webhooks. A Flask-based local dashboard provides a browser interface for image analysis, video processing, and live webcam monitoring. Evaluation results, qualitative analyses, known limitations (notably a pistol precision of approximately 0.41), and recommendations for production deployment are discussed in detail.
Abstract
Vehicle Tracking and Traffic Analytics System
Kunal Meshram, Pratham Mehta, Devisha Agrawal, Dr. Beenarani Manoj
DOI: 10.17148/IJIREEICE.2026.14802
Abstract: Traffic monitoring plays a vital role in improving road safety and transportation management. This paper presents a Vehicle Tracking and Traffic Analytics System that utilizes YOLOv11 for real-time vehicle detection and ByteTrack for multi-object tracking. The system estimates vehicle speed, detects overspeeding vehicles, analyzes traffic movement through predefined regions of interest, and generates traffic density heatmaps. It processes highway surveillance videos to provide accurate vehicle tracking and real-time traffic insights. The proposed system offers an efficient and scalable solution for intelligent transportation systems, traffic surveillance, and highway monitoring.
Keywords: Vehicle Tracking, Traffic Analytics, YOLOv11, ByteTrack, Speed Estimation, Computer Vision
Keywords: Vehicle Tracking, Traffic Analytics, YOLOv11, ByteTrack, Speed Estimation, Computer Vision
Abstract
A Survey On Recent Research Trends Towards Compression Of Image Using DPCM
Mandhara M Panedakatti, Meghana R, Keerthi B. K, Kampana B. E, Prof.Lakshmamma K. N
DOI: 10.17148/IJIREEICE.2026.14803
Abstract: Efficient image compression is essential for minimizing storage requirements and reducing transmission bandwidth while preserving the visual quality of reconstructed images. Among the various compression techniques there is a Differential Pulse Code Modulation (DPCM) represents an effective predictive compression approach has gained considerable attention so because of its predictive coding mechanism, which utilizes the spatial dependency among the adjacent pixels by encoding prediction errors rather than absolute pixel values. This approach effectively reduces data redundancy by maintaining low computational complexity, making it well suited for real-time image computing applications.
This paper presents a detailed review of DPCM-based image compression methods, including their operating principles, prediction techniques, hardware architectures, and performance evaluation. It also discusses recent improvements in adaptive and hybrid DPCM approaches that enhance compression efficiency and reconstructed image quality. Furthermore, the study compares existing research based on compression performance, hardware resource utilization, implementation complexity, and processing speed. Finally, current research challenges, emerging trends, and future opportunities involving intelligent prediction methods, machine learning, and next-generation image coding techniques are highlighted. The review concludes that DPCM continues to be a practical, efficient, and hardware-friendly approach for real-time image compression applications.
Keywords: Differential Pulse Code Modulation (DPCM), comparative analysis, Image compression, Wavelet Transform, Biomedical Signal Processing, Real-Time Signal Processing, Sustainable Healthcare, Wearable Healthcare.
This paper presents a detailed review of DPCM-based image compression methods, including their operating principles, prediction techniques, hardware architectures, and performance evaluation. It also discusses recent improvements in adaptive and hybrid DPCM approaches that enhance compression efficiency and reconstructed image quality. Furthermore, the study compares existing research based on compression performance, hardware resource utilization, implementation complexity, and processing speed. Finally, current research challenges, emerging trends, and future opportunities involving intelligent prediction methods, machine learning, and next-generation image coding techniques are highlighted. The review concludes that DPCM continues to be a practical, efficient, and hardware-friendly approach for real-time image compression applications.
Keywords: Differential Pulse Code Modulation (DPCM), comparative analysis, Image compression, Wavelet Transform, Biomedical Signal Processing, Real-Time Signal Processing, Sustainable Healthcare, Wearable Healthcare.
Abstract
A Survey on Recent Research Trends Towards ECG Denoising for Sustainable Healthcare
Prof. Ranganath B, Meghana M Panedakatti, Priyanka R L
DOI: 10.17148/IJIREEICE.2026.14804
Abstract: Cardiovascular diseases are a major cause of death and illness worldwide. This is why accurate Electrocardiogram (ECG) monitoring is so important for finding and treating these conditions early. Unfortunately, ECG signals can be unclear because of things like baseline drift, power line noise, movement, electrode issues, and electrical signals from muscles. This makes it harder to get a reliable diagnosis. To fix this, many methods have been developed to clean up ECG signals. These include digital filters, wavelet transforms, adaptive filters, deep learning, and empirical mode decomposition. When it comes to hardware, Field Programmable Gate Arrays (FPGAs) are a good choice for cleaning ECG signals in real time. They can process data in parallel, have low delay, can be reprogrammed, and use energy efficiently. This paper looks at recent methods for cleaning ECG signals using FPGAs. We compare their algorithms, how they are optimized for hardware, how complex they are to implement, what resources they use, and how well they remove noise. We also discuss how FPGAs are being used with Artificial Intelligence (AI), Edge Computing, the Internet of Things (IoT), and wearable health devices. Finally, we talk about the current research challenges and what needs to be done in the future to create ECG denoising systems that are scalable, use little power, and perform well.
Keywords: Electrocardiogram (ECG), FPGA, ECG Denoising, Wavelet Transform, Biomedical Signal Processing, Real- Time Signal Processing, Sustainable Healthcare, Wearable Healthcare.
Keywords: Electrocardiogram (ECG), FPGA, ECG Denoising, Wavelet Transform, Biomedical Signal Processing, Real- Time Signal Processing, Sustainable Healthcare, Wearable Healthcare.
Abstract
Predictive Maintenance using Python with Silhouette Analysis
VINEETA SAHU, Ms. DOLLY VERMA, DR. ASHISH TAMRAKAR
DOI: 10.17148/IJIREEICE.2026.14805
Abstract: Predictive maintenance (PdM) has emerged as a key application of artificial intelligence, machine learning, and data analytics in modern industry. Unlike preventive maintenance, predictive maintenance utilizes historical and real-time sensor data to identify equipment degradation and estimate potential failures before they occur. Python has become one of the most widely adopted programming languages for predictive maintenance due to its extensive ecosystem of scientific and machine learning libraries such as NumPy, Pandas, Scikit-learn, Matplotlib, and Seaborn. Among clustering validation techniques, silhouette analysis plays a significant role in determining the optimal number of clusters and evaluating the quality of clustering results. This review paper presents a comprehensive overview of predictive maintenance using Python with silhouette analysis. It discusses maintenance strategies, machine learning approaches, clustering techniques, silhouette coefficient interpretation, Python-based implementation frameworks, publicly available datasets, and recent research contributions. The paper also highlights advantages, limitations, and future research directions in predictive maintenance systems employing unsupervised learning and silhouette-based cluster validation.
Keywords: Predictive Maintenance, Python, Silhouette Analysis, Machine Learning, K-Means Clustering, Unsupervised Learning, Industrial Analytics, Condition Monitoring.
Keywords: Predictive Maintenance, Python, Silhouette Analysis, Machine Learning, K-Means Clustering, Unsupervised Learning, Industrial Analytics, Condition Monitoring.
Abstract
Computer Vision-Based Stock Quality Analysis and Rotten Quantity Detection for Fresh Produce in Quick-Commerce Warehouses
Vignesh Murali, Sarvesh S, Pranav H, Charulatha R.T
DOI: 10.17148/IJIREEICE.2026.14806
Abstract: Quick-commerce fulfillment centers (dark stores) operate under strict order-to-delivery timelines, making manual quality assessment of perishable fruits and vegetables highly inefficient and error-prone. This research paper presents a robust, universal Computer Vision (CV) system integrated with a non-linear regression model for automated freshness classification, rot segmentation, and quantitative stock loss estimation. The system utilizes HSV color space analysis and edge gradient filters to segment the produce body, eliminate complex backdrops (including wooden tables and studio backgrounds), and isolate localized rot spots. Furthermore, we introduce a quantitative stock estimation model that maps pixel density ratios to physical weight, allowing operators to automatically determine the exact quantity (in kilograms) of rotten produce within a bulk batch. Tested across tomato, banana, capsicum, and spinach images, the system successfully eliminates false positives from healthy features like green stems and natural yellow/red skin variations, achieving a classification accuracy of 96.8%.
Keywords: Computer Vision, Freshness Detection, Stock Quality Analysis, Rot Spot Masking, Image Segmentation, Quantity Estimation, Quick Commerce.
Keywords: Computer Vision, Freshness Detection, Stock Quality Analysis, Rot Spot Masking, Image Segmentation, Quantity Estimation, Quick Commerce.
Abstract
Smart Pharmacy AI: A Full-Stack Web Application for Medicine Inventory Management with an Extensible Computer-Vision and AI-Chatbot Architecture
T Aakash, G S Praveen Balaji, M Jaiaakash, Dr. Beenarani Manoj
DOI: 10.17148/IJIREEICE.2026.14807
Abstract: Community pharmacies and small dispensaries in India largely continue to track stock, batch numbers, and expiry dates on paper registers or in disconnected spreadsheets, a practice that leaves them exposed to stock-outs, undetected expired inventory, and slow reconciliation. This paper presents Smart Pharmacy AI, a full-stack web application that digitizes medicine inventory management through a Flask and SQLAlchemy REST API backed by a five-table relational data model, and a React (Vite, Tailwind CSS) single-page front end. The system exposes CRUD endpoints for medicine records and a dashboard endpoint that aggregates total stock, low-stock counts, and expired-item counts directly from the database using SQL aggregate functions. Beyond the operational CRUD and analytics layer, the system is architected with dedicated data models and route modules (Scan History, OCR Record, Inventory History, Chat History) that are designed to host a computer-vision medicine-package detector, an OCR-based batch/expiry-date extractor, and a conversational assistant as they are progressively integrated. We describe the system architecture, the relational schema, the implemented REST endpoints, the front-end design, the testing procedure followed, security and data-integrity considerations, a comparison against manual and generic point-of-sale alternatives, and the current implementation status of every module, before outlining the machine-learning components planned for the computer- vision and OCR subsystems and the corresponding development roadmap.
Keywords: Pharmacy Inventory Management, Flask REST API, SQLAlchemy ORM, React.js, Single-Page Application, Computer Vision, Optical Character Recognition, Expiry Tracking, AI Chatbot, Full-Stack Web Development.
Keywords: Pharmacy Inventory Management, Flask REST API, SQLAlchemy ORM, React.js, Single-Page Application, Computer Vision, Optical Character Recognition, Expiry Tracking, AI Chatbot, Full-Stack Web Development.
Abstract
Illumination-Adaptive Multi-Branch Feature Fusion for Robust Person Re-Identification
R Sivani, Rakshitha S N, Shreya Sathapathi, Charulatha R.T
DOI: 10.17148/IJIREEICE.2026.14810
Abstract: Person re-identification (Re-ID) across camera networks remains sensitive to illumination variation, since a single global appearance encoding is rarely robust to both bright and poorly lit capture conditions. This paper presents an adaptive illumination-robust Re-ID pipeline that estimates a continuous per-crop illumination score, generates four parallel enhanced views of each detected person (raw, CLAHE, gamma-corrected, and multi-scale Retinex), extracts an OSNet embedding for each view, and fuses the four embeddings using illumination-conditioned weights before performing cosine-similarity gallery retrieval via FAISS. The system is evaluated on Market-1501 under a stratified protocol comparing a Normal split against a synthetically generated Lowlight split, and comparing the proposed adaptive fusion against a static/average-fusion ablation baseline. Results show Rank-1 accuracy saturated at 98-99.6% across all four conditions, while mean Average Precision (mAP) is more discriminative, falling from approximately 71% on the Normal split to 44-46% on the Lowlight split. Contrary to the design hypothesis, the heuristic adaptive fusion does not outperform static average fusion in this evaluation, and static fusion is marginally better under Lowlight conditions. These findings are presented transparently as evidence that the current rule-based fusion weighting requires learning-based replacement, motivating a concrete direction for future work rather than an unqualified robustness claim.
Keywords: person re-identification, illumination robustness, adaptive feature fusion, OSNet, YOLOv8, Retinex, CLAHE, FAISS, Market-1501
Keywords: person re-identification, illumination robustness, adaptive feature fusion, OSNet, YOLOv8, Retinex, CLAHE, FAISS, Market-1501
Abstract
Computer Vision and Deep Learning-Based Universal Plant Leaf Disease Classification, Automated Necrotic Segmentation, and Agronomy Remedy Diagnostic System
HARI SRINIVAS T, BEENARANI MANOJ
DOI: 10.17148/IJIREEICE.2026.14811
Abstract: Plant pathogens are responsible for an estimated 20 to 40 percent loss of global crop yield every year, and smallholder farmers rarely have affordable access to expert agronomists at the critical early-onset stage of infection. This paper presents AgroVision AI, a universal computer-vision and deep-learning diagnostic pipeline that unifies classical image processing with a lightweight convolutional neural network to detect, localize, and classify foliar disease across multiple crop species from a single uploaded leaf photograph, regardless of the background clutter, illumination, or camera angle under which it was captured. The system first performs foreground leaf segmentation and shadow-artifact suppression, then extracts a bank of vitality and pathology descriptors — including the Excess Green Index, Chlorophyll Vitality Fraction, Localized Spot Ratio, Rust Pustule Ratio, and Desiccated Dead-Tissue Fraction — before passing the normalized leaf crop through a fine-tuned MobileNetV2 backbone for eleven-class disease classification. A hybrid decision-rule engine reconciles the classical descriptors with the network's softmax confidence to reject false positives arising from natural leaf-tip browning, vein shadows, and specular glare, and an integrated agronomy remedy knowledge base then returns organic and chemical treatment plans, dosage guidance, and preventive-care instructions tailored to the diagnosed condition. Evaluated on a held-out set of 2,500 field and greenhouse images spanning tomato, potato, maize, banana, and citrus leaves, AgroVision AI achieved 97.4% overall classification accuracy, 97.1% precision, 96.8% recall, and a mean end-to-end inference latency of 117 milliseconds on commodity hardware, outperforming standalone VGG- 16 and ResNet-50 baselines while requiring a fraction of their memory footprint. The results demonstrate that a hybrid classical-plus-deep-learning pipeline can deliver agronomist-grade diagnostic reliability in a form factor light enough to run on a farmer's smartphone.
Keywords: Computer Vision, Deep Learning, Plant Disease Classification, MobileNetV2, Leaf Segmentation, Precision Agriculture, Agronomy Diagnostics, Convolutional Neural Networks.
Keywords: Computer Vision, Deep Learning, Plant Disease Classification, MobileNetV2, Leaf Segmentation, Precision Agriculture, Agronomy Diagnostics, Convolutional Neural Networks.
Abstract
A Survey on Recent Research Trends Towards A Comprehensive Review of Energy-Efficient FIR Filters on FPGA
Anooshka G, Dhrriti Shree D, Sri lakshmi BM, Mrs. N S Mythreye
DOI: 10.17148/IJIREEICE.2026.14812
Abstract: Digital Signal Processing (DSP) is an important technology in modern communications, biomedical, audio, and image processing systems. The Finite Impulse Response (FIR) filter is widely used in digital signal processing due to its inherent stability, linear-phase characteristics, and efficient hardware implementation. FPGA-based implementations of FIR filters offer advantages such as high-speed operation and design flexibility; however, they often encounter challenges related to increased power consumption and hardware complexity. The paper provides a comprehensive review of recent low-power FPGA implementations of low-pass FIR filters, focusing on advanced optimization methods, including DA, CSD encoding, multiplier-less architectures, pipelining, coefficient optimization, and clock gating. It also compares the performance of these techniques in terms of power efficiency, latency, and hardware complexity, and discusses emerging challenges, research gaps, and future research opportunities.
Keywords: Digital Signal Processing, Energy Efficiency, Low-Pass Filter, FPGA, Finite Impulse Response, Hardware Optimization, Low-Power Design, Verilog HDL
Keywords: Digital Signal Processing, Energy Efficiency, Low-Pass Filter, FPGA, Finite Impulse Response, Hardware Optimization, Low-Power Design, Verilog HDL
Abstract
LITERATURE REVIEW A Sustainable Approach to Low-Power Real-Time PLL Design Using Current-Starved VCO in 45-nm CMOS Technology
Dharun.G, Chetan B.H, Bhavani Shankar, Ganesh, Prof. Kiranmayi. M
DOI: 10.17148/IJIREEICE.2026.14813
Abstract: Phase-Locked Loops (PLLs) are essential mixed-signal circuits for clock generation, frequency synthesis, synchronization, timing recovery, wireless communication, and energy-constrained embedded systems. As semiconductor technology scales, PLL designers must simultaneously address power consumption, phase noise, jitter, lock time, tuning range, supply sensitivity, process-voltage-temperature (PVT) variations, and implementation area. The voltage-controlled oscillator (VCO) is particularly important because its delay, current, gain, and noise directly influence the closed-loop behavior of the PLL. Current-starved voltage-controlled oscillators (CSVCOs) are attractive for low- power operation because the bias current of the delay stages can be controlled through the tuning voltage. This literature review examines 15 representative publications covering low-power PLLs, current-starved VCOs, 45-nm CMOS implementations, PVT-tolerant oscillator techniques, charge-pump design, ring-VCO PLLs, and recent supply-noise- insensitive PLL research. Particular attention is given to IEEE publications and recent work from 2024–2025. The review identifies a gap in the joint optimization of a complete 45-nm CSVCO-based PLL for low power, real-time locking, wide tuning, low phase noise, and robustness. The findings provide the technical basis for the proposed sustainable PLL design using Cadence Virtuoso.
Keywords: Phase-Locked Loop (PLL), Current-Starved VCO (CSVCO), ring oscillator, 45-nm CMOS, low power, real-time locking, phase noise, jitter, charge pump, PVT variation, supply-noise immunity.
Keywords: Phase-Locked Loop (PLL), Current-Starved VCO (CSVCO), ring oscillator, 45-nm CMOS, low power, real-time locking, phase noise, jitter, charge pump, PVT variation, supply-noise immunity.
Abstract
Energy-Efficient 32-Bit RISC-V Processors Design in 45nm
Bhoomika J, Manjunatha V, Chandan B, Dr. Chaitra A S
DOI: 10.17148/IJIREEICE.2026.14814
Abstract: Energy efficiency represents a foundational design metric for modern embedded microcontrollers, edge artificial intelligence accelerators, biomedical wearables, and autonomous Internet-of-Things (IoT) sensor nodes. In these constrained deployments, stringent thermal limits, sub-milliwatt power budgets, and silicon area restrictions dictate processor microarchitecture. The open-standard RISC-V Instruction Set Architecture (ISA), particularly the unprivileged 32-bit integer base profile (RV32I) and its modular extensions (RV32IMC), has emerged as the premier open ecosystem for researching energy-optimal compute engines without the impediments of proprietary licensing. While modern industrial trends emphasize sub-10-nm FinFET nodes or FPGA-based prototyping, a standard 45-nm bulk CMOS ASIC design flow remains an indispensable, highly reproducible academic and industrial benchmark for characterizing fundamental switching dynamics, standard-cell leakage, dynamic interconnect capacitance, and clock-network parasitics. This paper provides an extensive, comprehensive literature review of contemporary IEEE advancements spanning 2020 through 2026. Furthermore, it details an end-to-end, multi-stage reference implementation methodology—spanning synthesis-friendly SystemVerilog/Verilog RTL modeling, architectural hazard mitigation, datapath operand isolation, multi-level integrated clock gating (ICG), logic synthesis, static timing analysis (STA), clock tree synthesis (CTS), and post-layout parasitic extraction (SPEF). Systematic comparative metrics across critical path delay, total equivalent gate count, leakage power, switching energy per instruction, and Energy-Delay Product (EDP) are formulated to establish a definitive reference framework for academic VLSI engineering.
Keywords: RISC-V, RV32I, RV32IMC, Low-Power VLSI, Energy Efficiency, 45-nm CMOS, Standard-Cell ASIC, Clock Tree Synthesis (CTS), Operand Isolation, Clock Gating, Energy-Delay Product (EDP), Static Timing Analysis.
Keywords: RISC-V, RV32I, RV32IMC, Low-Power VLSI, Energy Efficiency, 45-nm CMOS, Standard-Cell ASIC, Clock Tree Synthesis (CTS), Operand Isolation, Clock Gating, Energy-Delay Product (EDP), Static Timing Analysis.
Abstract
An ultraviolet measuring and UV index calculating system, with multiple alarm capabilities, using FPGAs and VHDL
Leonidas Dimitriadis, Dr Evangelos I. Dimitriadis
DOI: 10.17148/IJIREEICE.2026.14815
Abstract: A novel ultraviolet measuring system, which uses FPGAs and VHDL, is presented here. The system moni- tors UV radiation of a light source or sun using GUVA-S12SD sensor connected to DE10-Lite FPGA board and after A/D conversion presents input voltage values in seven-segment displays. Calculated UV index values are also dis- played. Five external LEDs, green, blue, white, yellow and red light up depending on UV index values range, with green one corresponding to 0-2 value and red one to values equal or greater than 10.5. The above LEDs unit acts both as indicating and also alarm system presenting UV index ranging and is in parallel operation with 10 board LEDs from which left half lights up for UV index values lower than 5.5 and right half in case that UV index exceeds value of 5.5. Time process starts operating in case that UV index is above zero and switch SW0 is ON. Depending on specific UV index a critical UV exposure time value, different for respective UV index ranges, is set by programmer. The above exposure time value must not be exceeded because there is a danger of skin damage, thus our system incorporates an- other alarm unit consisting of a buzzer and second red LED. Both of them transition to operating mode, in case that one of different five time set limits is exceeded. Our system is cheap to manufacture, easy to use and due to FPGA incorpo- ration can be combined with IoT and AI systems. It can also be used in healthcare systems, industrial UV systems and various application systems where ultraviolet radiation is needed.
Keywords: UV, UV index, UV sensor, FPGA, VHDL, LEDs, exposure time.
Keywords: UV, UV index, UV sensor, FPGA, VHDL, LEDs, exposure time.
Abstract
DermAI: A Full-Stack Deep Learning Web Application for Explainable Skin Lesion Screening Using MobileNetV2 and Grad-CAM
Yokesh Anandan, Ahil Gangatharan, Christon Davis C, Dr.Beenarani Manoj
DOI: 10.17148/IJIREEICE.2026.14816
Abstract: Skin cancer, including melanoma and basal cell carcinoma, is among the most common cancers worldwide, and early visual screening is a key factor in prognosis, yet dermatologist access is limited in many regions and unaided visual assessment of pigmented lesions is known to be unreliable without specialist training. This paper presents DermAI, a full-stack web application for automated skin lesion screening built around a FastAPI backend, a Python/SQLite-free, stateless PyTorch inference pipeline, and a vanilla HTML/CSS/JavaScript front end. The system exposes REST endpoints for health checking, disease taxonomy lookup, sample-image retrieval, and image-based prediction, the last of which runs a MobileNetV2 convolutional neural network with a custom classification head designed for the seven-class HAM10000 dermatoscopic taxonomy and returns a Gradient-weighted Class Activation Mapping (Grad-CAM) visual explanation alongside every prediction. Beyond the classification and explanation pipeline, the system is architected with a dedicated clinical taxonomy module — mapping each of the seven diagnostic classes to a plain-language description, risk level, typical dermoscopic features and recommended next steps — that enriches every prediction response rather than returning a bare label. We describe the system architecture, the model and training pipeline, the disease taxonomy and REST API, the front-end design, implementation details, the testing procedure followed, safety and data considerations, a comparison against manual self-examination and generic alternatives, and the current implementation status of every module, before outlining the roadmap for completing model training, quantitative evaluation, and fairness analysis.
Keywords: Skin Lesion Classification, Convolutional Neural Network, MobileNetV2, Transfer Learning, Explainable AI, Grad-CAM, HAM10000, Computer-Aided Diagnosis, FastAPI, Teledermatology, Full-Stack Web Development.
Keywords: Skin Lesion Classification, Convolutional Neural Network, MobileNetV2, Transfer Learning, Explainable AI, Grad-CAM, HAM10000, Computer-Aided Diagnosis, FastAPI, Teledermatology, Full-Stack Web Development.
Abstract
Enhanced Reinforcement Learning with Optimization for the Threat Detection in VLC Networks-based 5G
Vijayakumari K Anusudha K
DOI: 10.17148/IJIREEICE.2026.14817
Abstract: Visible Light Communication (VLC) offers significant bandwidth, energy efficiency, and resistance to electromagnetic interference, making it a promising addition to 5G technology. However, due to its broadcast nature and dependence on Line-of-Sight (LoS), it is vulnerable to threats such as eavesdropping, spoofing, and jamming. The unique characteristics of optical signals, background noise, and the need for real-time, low-latency communication make threat detection in VLC-based 5G networks challenging. Therefore, this research identifies threats in VLC-based 5G networks using a novel intelligent, machine-learning-based optimization approach. Threat data are collected from the benchmark VLCdata dataset and preprocessed using the Discrete Wavelet Transform (DWT) denoising technique. Feature extraction is then performed using the Hough Transform (HT). Finally, threats are detected using the proposed Enhanced Reinforcement Learning (ERL) model, in which the Builder Optimization Algorithm (BOA) is employed to optimize the reinforcement learning parameters. The optimization process aims to maximize detection accuracy. Experimental results demonstrate that the proposed ERL-BOA model outperforms existing approaches across multiple performance measures. Specifically, it achieves 8.76% higher accuracy and 4.17% higher F1-score than existing methods, demonstrating its effectiveness for intelligent threat detection in VLC-based 5G networks.
Keywords: Visible Light Communication Networks; 5G; Discrete Wavelet Transform (DWT) Denoising; Hough Transform; Enhanced Reinforcement Learning; Builder Optimization Algorithm.
Keywords: Visible Light Communication Networks; 5G; Discrete Wavelet Transform (DWT) Denoising; Hough Transform; Enhanced Reinforcement Learning; Builder Optimization Algorithm.
Abstract
Design and Development of a DIY Line Follower Robot Using Embedded Systems
Kosgi Rishikesh Reddy, Palamuru Paramesh, Muppana Tarun, Dr. B. Ramu
DOI: 10.17148/IJIREEICE.2026.14818
Abstract: This paper presents the design and implementation of a D.I.Y line follower robot based on embedded systems and real-time control principles. The proposed system is capable of autonomously navigating a predefined path by utilizing infrared (IR) sensors to detect variations in surface reflectivity between a black line and a white background. The robot is built using an Arduino UNO microcontroller, which acts as the central processing unit, along with an L298N motor driver module and DC motors to achieve controlled movement. The system operates on a closed- loop feedback mechanism, where continuous sensor input is processed to dynamically adjust the robot’s trajectory, ensuring accurate path tracking and minimal deviation. The design emphasizes simplicity, low cost, and ease of implementation while maintaining reliable performance. Experimental evaluation of the system demonstrates stable operation, quick response to directional changes, and effective navigation under controlled environmental conditions. However, factors such as ambient lighting, sensor calibration, and surface irregularities influence the overall performance. The developed robot serves as a foundational model for autonomous guided vehicles and can be further enhanced by integrating advanced control algorithms such as PID control, obstacle detection systems, and wireless communication technologies. This work highlights the practical application of embedded systems in robotics and provides a saleable approach for future automation solutions.
Keywords: Line Follower Robot, Embedded Systems, Arduino UNO, Infrared Sensors (IR Sensors), Autonomous Navigation, Closed-Loop Control System, Motor Driver (L298N), Real-Time Processing, Robotics, Automation
Keywords: Line Follower Robot, Embedded Systems, Arduino UNO, Infrared Sensors (IR Sensors), Autonomous Navigation, Closed-Loop Control System, Motor Driver (L298N), Real-Time Processing, Robotics, Automation