Articles published in IJEER


PRc-PID with Teaching Learning Based Optimization Algorithm (TLBO) Based UPQC to Improve Power Quality in Standalone Microgrid

Isolated microgrids (MG) have become increasingly popular due to their enhanced adaptability in addressing customer needs, but pollution has also increased as a result. When integrating renewable energy sources with different loads, the MG will experience increased power quality (PQ) issues. Reducing MG's PQ problems is the main objective of this paper. PQ problems can be resolved with the help of the system's Unified PQ Conditioner (UPQC) device. UPQC performance is improved by integrating PRc-PID with a Teaching Learning Optimization Algorithm-based controller in series with a shunt active power filter to lessen current and voltage PQ issues. Solar cells and wind turbines are all proposed for a separate MG.

Read more

SAM-CLIP Search: Faster Region-Based Image Similarity Matching Using Lightweight Segmentation & Contrastive Learning

Imagine a designer browsing through an enormous image database for photos that contain both "a chair and a table" or a wildlife scientist attempting to find all photos of "brown bears near water." Locating such specific combinations manually is too time-consuming and cumbersome. To address this issue. This system SAM-CLIP Search is an area-based vision-language image search platform that incorporates CLIP and vision-language embeddings into the Segment Anything Model (SAM) to offer flexible prompt-based segmentation. Our approach makes precise picture search with point, box, or text prompts feasible compared to typical CBIR approaches, which often struggle with multi-object queries as well as cross-modal alignment.

Read more

Minimization of Transmission Congestion Cost using P-OPF based LSF, PSO, and ANN Techniques

The inclusion of renewable energy sources (RES) into a stabilized network has opened gates to numerous optimization problems. Optimization of RES generation might not imply merely the myth of high availability, but it is furthermore fenced by parameters such as transmission line power flow patterns, having the optimized location, bus nodal pricing (LMP), congestion scenario, congestion cost and reliability margins of the system (ATC, TRM). Integration of RES also drags towards the congestion episode within the transmission system. The uncertain behavior of renewable energy initiates uncertainty into the system from generation perspective. These uncertainties lead to congestion which alters the linear sensitivity factors (LSF), LMP and reliability margins of the network.

Read more

Design and Simulation of a Quaternary Logic Gate Using a Universal Spatial Wavefunction Switched Field-Effect Transistor NOR Gate

In Very Large-Scale Integration (VLSI) design, minimizing area and optimizing device performance have become paramount as traditional MOSFET scaling approaches fundamental limits. Energy efficiency is now a primary goal due to MOSFET scaling challenges. Multi-valued logic (MVL), such as quaternary (2-bit) logic, offers a potential solution by increasing information density and reducing interconnect complexity. However, implementing four discrete voltage levels in quaternary logic requires novel device technologies. This work explores Spatial Wavefunction Switched FET (SWS-FET) devices – quantum well transistors enabling multi-state carrier transport – as a size- and power-efficient platform for quaternary logic. We present the development of complementary n-channel and p-channel SWS-FETs to encode the four logic states (00, 01, 10, 11)

Read more

Voltage Profile Enhancement of Radial Distribution System by Genetic Algorithm in ETAP

Compensation for reactive power is provided, and the use of capacitor banks reduces both active and reactive power losses in distribution systems. In the power system, the capacitor also helps control the voltage and power factor. The genetic algorithm (GA) to the stage finds appropriate OPC. The voltage profiles of the system have improved as a result. The number of capacitors at minimum load has been determined for the candidate buses for optimal capacitor bank placements. To assess the sensitivity of compensating power losses, the calculation of optimal capacitor placement is done at peak load.

Read more

A Cross Layer Aware Hybrid Routing Algorithm Using Federated Q-Learning and Ant Colony Optimization for Wireless Sensor Networks

Efficient routing in Wireless Sensor Networks (WSNs) remains challenging due to energy constraints, link instability, and dynamic topologies. While machine learning and bio-inspired methods offer improvements, many existing protocols struggle with scalability, computational demands, and limited consideration of critical QoS metrics like delay, PDR, and network lifetime. To overcome these limitations, this paper introduces Fed-QL-ACO-X, a hybrid routing protocol combining Federated Q-Learning (FQL) for decentralized learning, Ant Colony Optimization (ACO) for adaptive path selection, and cross-layer awareness using MAC and PHY layer metrics.

Read more

Design, Stage-Wise Power Loss Evaluation and Real-Time Validation of Totem-Pole Bridgeless Boost Converter Against DBR–Boost PFC Topology

Conventional AC–DC power factor correction (PFC) systems typically employ a diode bridge rectifier (DBR) followed by a boost converter, resulting in significant conduction losses due to multiple semiconductor paths. This paper presents a comprehensive design, modeling, and comparative loss analysis of a Totem-Pole Bridgeless Boost Converter (TPBBC) as an efficient alternative to the DBR–Boost configuration. The proposed topology eliminates the front-end diode bridge, reducing conduction and switching losses while improving efficiency and power quality.

Read more

Approximate Computing Using Voltage Over Scaling Technique for Image Compression

Approximate computing has extensively been adopted as a fault-tolerant method to achieve energy-efficient designs in image processing. This paper introduces a novel, integrated approximate approach for implementing runtime-based voltage over scaling (VOS) at both the circuit and algorithmic levels, specifically for approximate discrete cosine transform (ADCT) and zigzag low-complexity approximate DCT (ZLCADCT) in image compression. In the proposed VOS scheme, the supply voltage of exact and approximate adder cells is reduced below the nominal level, causing the output delay to surpass the worst-case delay and generating errors in addition, while lowering energy consumption.

Read more

Low-Power 12T SRAM Design Using 18 nm FinFET Technology

This paper presents a low-power and high-stability 12T SRAM cell designed using 18nm FinFET technologies and compared with conventional 6T, 8T, and 10T architectures. The proposed design employs read-path isolation, stacked transistors, and a leakage-controlled sleep mechanism to minimize dynamic and static power while improving read/write stability. Simulations were carried out in Cadence Virtuoso using PTM BSIM-CMG models under varied PVT conditions (0.8–1.0 V, –25 °C to 50 °C). The results show significant enhancements in performance metrics, achieving read SNM of 205 mV, hold SNM of 245 mV, and read/write delays of 52ps and 61ps, respectively.

Read more

Hybrid CNN-BiLSTM Autoencoder for Anomaly Detection in Remote Photoplethysmography(rPPG) Signals

Remote photoplethysmography (rPPG) is becoming increasingly popular as a non-contact method for tracking physiological parameters like heart rate and respiration rate. However, the accuracy of rPPG signals is often compromised by various factors, including movement, lighting variations, and sensor noise. These challenges can severely impact signal quality, leading to unreliable measurements and hindering the practical application of rPPG-based systems. In this research, we introduced and assessed the effectiveness of a hybrid Convolutional Neural Network (CNN) and Bidirectional Long Short-Term Memory (BiLSTM) Autoencoder model specifically designed for reliable anomaly detection in rPPG time-series data.

Read more

Comparative Deep Learning for RGB-Based PV Surface Fault Classification Using ResNet50 and EfficientNetB0 with Real-Time Deployment

Photovoltaic (PV) systems are increasingly vital to global energy transitions but remain vulnerable to surface anomalies such as dust, snow, bird droppings, and physical or electrical damage—that significantly reduce power yield and long-term reliability. Manual inspection is inefficient for large-scale solar farms, motivating the development of intelligent and automated fault detection systems. This study introduces a reproducible comparative deep-learning framework that systematically benchmarks four convolutional neural network (CNN) architectures ResNet50, EfficientNetB0, MobileNetV3Small, and DenseNet121 under identical preprocessing, training, and validation settings.

Read more

Design and Simulation of a Standalone Solar Photovoltaic System for Water Pumping Using Induction Motor Drive

The rising demand for sustainable energy in off-grid regions has propelled the use of solar photovoltaic (PV) systems for water pumping, particularly for irrigation. This study investigates the design and simulation of a standalone PV-powered water pumping system employing a three-phase induction motor (IM) for remote applications. The research aims to optimize energy extraction and ensure system stability under varying solar irradiance. The methodology utilizes MATLAB/Simulink to model the system, integrating a Perturb and Observe (P&O) Maximum Power Point Tracking (MPPT) algorithm, a DC-DC boost converter, and a Voltage Source Inverter (VSI) to drive the IM.

Read more

Fundamental Frequency Extraction by Utilizing the Combination of Spectrum in Noisy Speech

Speech is the audible acoustic signal generated by the articulatory system (lungs, vocal folds, vocal tract, tongue, lips) to communicate language. The fundamental frequency (F_0) is the lowest frequency component of a speech waveform and corresponds to the vibration rate of the vocal folds during voiced speech. It also determines the pitch of the speaker’s voice. In speech signal processing, this acoustic waveform is captured and analyzed to extract information about what is being said, how it is being said and who is saying it. In various speech processing applications such as voice synthesis, speaker recognition and emotion analysis accurate extraction of the fundamental frequency (F_0) is a vital task.

Read more

Cascaded Segmentation-Classification Framework Optimized for Sports Action Recognition Using Still Images: A Comparative Analysis of PSO and Grid Search

The conventional method of evaluating human actions and activities requires integrating complex hardware and interpretation systems. This article proposes using a hybrid segmentation-classification system to recognize human sports action automatically based on still frames. This study tested the proposed framework on a public dataset containing images of humans performing three athletic actions: dancing, performing martial arts, and playing net sports. This framework combined a two-stage U-Net and EfficientNet-B0, and GoogleNet, and is optimized using particle swarm optimization (PSO) and grid search for cascaded segmentation and classification problems. Results indicated that PSO improves segmentation and classification accuracies by 5 % and 60 %, respectively, compared to the conventional grid search.

Read more

Compact Dual-Band E-Shape Patch Antenna with Defected Ground Structure for 5G Millimeter-Wave Applications

The continuous demand of sending/receiving various multimedia leads to develop 5G communications services. The 5G services requires wide bandwidth, higher speed with less time delay and all that need to use higher frequency waves that are millimeter waves. To achieve these requirements investigated a dual-band E-shape patch antenna designed on the defected ground structure (DGS) layer for 28.4/36 GHz frequency bands that are available to 5G applications. The resulted response of this antenna gives reflection factor (return loss S11) in depth of -20/-25.3dB for lower and upper frequency bands respectively.

Read more

Beluga Whale Optimization (BWO) Algorithm for Maximum Power Point Tracking from PV System for an Open-End Winding Induction Motor Drive with MPC-SVM Modulation

This paper presents a novel control framework integrating the Beluga Whale Optimization (BWO) algorithm for Maximum Power Point Tracking (MPPT) in photovoltaic (PV) systems driving an Open-End Winding Induction Motor (OEWIM) using a Model Predictive Control–Space Vector Modulation (MPC–SVM) strategy. The BWO algorithm, inspired by the intelligent hunting behaviour of beluga whales, is employed to dynamically extract the global maximum power point under varying irradiance and temperature conditions, enhancing PV efficiency.

Read more

An Effective Dual-Band Wireless Power Transfer (WPT) System using Transmission Line Equivalents for Medical Implants

There has been a pressing need for wireless power transfer due to its numerous applications, including integrated or embedded systems used in various fields, such as sensors and mobile devices, as well as medical devices implanted inside the human body. Traditional transmission methods have drawbacks in terms of protection and safety when used directly on the human body, as well as the requirement for continuous operation within the body. Therefore, wireless power transfer methods have emerged as a safe and reliable alternative, especially for medical implants. Several methods and techniques have been developed, initially operating on a single frequency.

Read more

GA-Optimized FACT-SMES Coordination and APF Selection for Enhanced AGC Stability in Deregulated Hybrid Power Systems

This research investigates the enhancement of frequency stability in a hybrid power system operating under deregulated conditions. The study integrates Flexible AC Transmission System (FACT) devices including SSSC, UPFC, TCPS, and TCSC with Superconducting Magnetic Energy Storage (SMES) units, optimized using Genetic Algorithms (GA). PID and PIDF controllers are employed for frequency regulation, and their performance is evaluated through various case studies. Results demonstrate that the combination of FACT devices with SMES, tuned via GA, significantly improves dynamic response, reducing settling time and peak overshoot.

Read more

Evaluating Reservoir Spiking Neural Network Configurations for Accurate Battery State-of-Health Prediction

Accurate prediction of battery State-of-Health (SoH) is crucial for ensuring safety, reliability, and longevity in energy storage systems. This study evaluates the utilization of Reservoir Spiking Neural Networks (RSNN) for battery SoH prediction, focusing on how network configuration affects prediction performance. Various RSNN architectures are analyzed by varying reservoir neuron number, connection density, inhibitory ratio, time step window, and readout network configuration. The findings show that a simple RSNN structure is sufficient to achieve high prediction accuracy, provided that the network is carefully configured to produce diversity in the spike count patterns within the reservoir layer.

Read more

Multi-Model Deep Feature Fusion for Robust Detection of Neuro-Oncological Abnormalities

Accurate and early diagnosis of brain tumors can significantly reduce both the invasiveness and cost of therapeutic interventions while preserving neurological function. Current limitations in manual MRI analysis, including human error, variability in expertise, and interpretive inconsistencies, have created a pressing need for advanced diagnostic systems based on artificial intelligence and deep learning techniques. This study presents a hybrid transfer learning approach designed to enhance the detection of neuro-oncological abnormalities. Our methodology employs parallel processing of MRI images through pre-trained DenseNet121 and VGG16 architectures to extract discriminative numerical features.

Read more

Improving Monocular Distance Estimation in Complex Traffic Scenarios

With the rapid development of autonomous driving technology, real-time ranging of preceding vehicles has become a critical component to ensure driving safety. Although monocular vision-based ranging methods offer advantages of low cost and easy deployment, they still suffer from limited accuracy in long-distance targets, small objects, and complex traffic scenarios. To address these challenges, this paper improves the classic Smoke monocular 3D detection model by introducing a multi-scale feature enhancement module and a dynamic Gaussian heatmap generation mechanism, which effectively strengthen feature representation and stabilize depth estimation.

Read more

Handling Class Imbalance in Video-Based Pain Intensity Estimation Using ResNetBiLSTM: A Study on Loss Functions and Optimizers

Accurate pain intensity recognition is vital for improving clinical care, especially in scenarios where patients cannot self-report. However, although existing datasets are often imbalanced, the main challenge is that current optimization and loss functions lack sensitivity to minority classes, adapt poorly to intra-class variability, and are less robust under imbalance, leading to biased recognition performance. To address these challenges, this study proposes a hybrid deep learning model based on ResNet-50 and BiLSTM to capture both spatial and temporal features from facial expression videos while incorporating strategies to mitigate the imbalance issue.

Read more

Reactive Power Compensation and DC link Voltage Control using Fuzzy-PI with DSOGI-PLL on Grid-connected PV based D-STATCOM

The large-scale integration of photovoltaic (PV) generation introduces critical challenges for power systems, including voltage stability issues and increasing requirements for reactive power compensation. To address these challenges, PV inverters can be operated as Distribution Static Synchronous Compensators (D-STATCOM) to simultaneously supply active power and provide ancillary reactive power support. This paper proposes a control strategy for grid-connected PV-based D-STATCOM systems that incorporates a Fuzzy-PI controller for DC-link voltage regulation and a Dual Second-Order Generalized Integrator Phase-Locked Loop (DSOGI-PLL) for accurate phase angle detection.

Read more

A Deep Learning-Based Approach for Heart Rate Monitoring through Combined Convolutional and Generative Networks Using Facial Videos

This research presents a deep learning-based architecture that uses facial video-extracted remote Photoplethysmography (rPPG) to non-invasively estimate heart rates. The proposed system addresses limitations in signal fidelity and scalability by integrating a Conditional Generative Adversarial Network (CGAN) to enhance the quality of raw rPPG waveforms and a 1D Convolutional Neural Network (CNN) for regression-based prediction of heart rate in beats per minute (BPM). Unlike traditional single-stream models, our framework supports concurrent processing of facial video streams, improving computational efficiency and applicability in real-time, multi-subject environments.

Read more

Multi-Objective Optimal Planning of DG and FACTS in Radial Distribution Systems via Arithmetic Optimization Algorithm

Optimal planning of Distributed Generation (DG) units and Flexible AC Transmission System (FACTS) devices is crucial for improving the efficiency, reliability, and sustainability of radial distribution networks. With increasing renewable integration and rising power system complexity, advanced optimization methods are necessary to reduce power losses, enhance voltage profiles, and ensure operational resilience. This study presents a Multi-Objective DG-FACTS Planning (MODF) approach using the Arithmetic Optimization Algorithm (AOA), which leverages basic arithmetic operators for effective global search and rapid convergence.

Read more

Energy-Efficient Sub-Millisecond DWDM Backhaul for 6G Open RAN

Wavelength-aware and constraint-driven framework is presented for dense WDM optical backhaul in 6G Open RAN. The design jointly minimizes energy while enforcing explicit sub-millisecond delay bounds under non-stationary traffic and integrates cleanly with near-RT RIC control. A three-stage controller computes a feasible allocation through projected primal–dual updates then perform energy-aware wavelength pruning and finally executes latency-responsive reconfiguration on incipient violations. Evaluation across diverse topologies and bursty as well as diurnal loads shows up to 32% lower optical power than static provisioning with delays concentrated in 0.7–0.8ms and low control overhead.

Read more

Nanophotonic-Enhanced Photoacoustic Fusion with Transformers for Brain Tumor Classification/a>

This research presents a novel diagnostic framework that integrates nanophotonic-enhanced photoacoustic imaging (PAI) with multimodal magnetic resonance imaging (MRI), computed tomography (CT), and positron emission tomography (PET). A lightweight convolutional encoder extracts low-level features, which are fused via a transformer-based architecture employing 3D patch embeddings and multi-head self-attention. Intermediate fusion balances modality-specific and joint representations, achieving an overall accuracy of 97.8%, sensitivity of 96.5%, and specificity of 98.1% on a cohort of 550 complete MRI–CT–PET cases augmented with 100 simulated PAI volumes.

Read more

Design and Analysis of P&O and Fuzzy Logic MPPT Techniques with Boost Converter for PV Optimization

This paper presents a comparative analysis of the Perturb and Observe (P&O) and Fuzzy Logic Control (FLC) methods for Maximum Power Point Tracking (MPPT) in photovoltaic (PV) systems with a boost converter. Both methods were simulated with MATLAB/Simulink, and the performance was compared on the basis of parameters such as response time, overshoot, steady-state error, and Power Extracting Efficiency for different conditions standard, Variable radiation, Partial shading, variable temperature and variable load.

Read more

Performance Analysis of High Torque Density in Switched Reluctance Motor for Electric Transportation

In this paper, the detailed comparative study of high torque density switched reluctance motor (SRM) used in the electric transport is provided. By means of sophisticated simulation packages Motor Solve and Magnet Solve. The delivered outputs of the study models of SRM that have 3KW rating of output power, 2700 RPM rates of speed,10A rated currents and a rated torque of 10 Nm. Torque density, efficiency, and power to weight ratio are essential performance parameters that are comprehensively explored in simulation approaches. The comparison between the SRM structural design is established on the basis of performance in the challenging transportation applications.

Read more

Improving Frequency Response in a Microgrid Integrated with PV-HESS Using an FOPI Controller Optimized by the Grey Wolf Optimizer Algorithm

The application of modern controllers for frequency regulation in standalone microgrids has been increasingly proven feasible. Among these, the Fractional Order Proportional-Integral (FOPI) controller with adjustable parameters has attracted considerable attention. The effectiveness of the FOPI controller is highly dependent on the proper tuning of its parameters. This paper proposes the use of the Grey Wolf Optimizer (GWO) algorithm to determine the optimal tuning parameters, with the objective of minimizing frequency oscillations. The simulation and performance evaluation are conducted using the MATLAB/Simulink platform.

Read more

A Multi-Agent Deep Reinforcement Learning Framework for MEC Resource Allocation in 5G Networks

This paper introduces a multi-agent Deep Reinforcement Learning (DRL)-based model of allocating resources in 5G MEC networks based on the Soft Actor-Critic (SAC) algorithm and the hierarchical MATD3/TD2PG-based actor-critic network. The model distributes sub-channels, power of transmission and MEC computing resources with taking into account user mobility and isolation of the slices. The Python simulation is provided with a Manhattan 5G environment comprising of four interconnected gNodeBs, 5 densities of users (327, 499, 596, 930 and 1088 users), and two MEC classes of service (security and entertainment) with predefined bandwidth, memory, and processing requirements.

Read more

Deep Learning-Driven Expiry Date Recognition on Medicine Bottles via YOLOv8 Segmentation and Multi-Stage Image Denoising

Automated expiry date recognition (EDR) on pharmaceutical packaging is essential for ensuring medicine safety and minimizing waste, but it poses challenges due to text unpredictability, environmental interference, and intricate label geometries. This study presents a comprehensive deep learning system that integrates sophisticated picture pre-processing with YOLOv8-based instance segmentation to overcome these restrictions. A curated dataset including 1,000 high-resolution photos of pharmaceutical bottles, encompassing various lighting situations, camera angles, and date formats, was assembled. The pre-processing pipeline incorporates wavelet denoising, BM3D filtering, and contrast-limited adaptive histogram equalization (CLAHE) to alleviate glare and enhance low-contrast text artefacts.

Read more

Fixed Frequency SVPWM+PI Controlled LCL Shunt Active Power Filter in dq Frame for Microgrids

This paper presents the design of simple, robust, and efficient shunt active power filter (SAPF) using a loop in loop (cascaded) PI controller and Space vector pulse width modulated synchronous reference frame (dq) controller to mitigate harmonics from a three-phase diode rectifier (nonlinear load) catering to variety of loads (R, and R-L), supplied by a microgrid (week grid) having plethora of distributed generator, exhibiting heuristic nature. The intermittent nature of DGs leads to variation in voltage and frequency, and load variation aggravates this situation further.

Read more

Coordinated Control of Grid-Connected Solar and Wind Power for Electric Vehicle Charging and Power Quality Enhancement Using DPFC

Numerous converters enhance the flexibility and manageability of the Grid-Connected Converter (GCC) within a DC/AC microgrid, facilitating the smooth incorporation of renewable energy sources. To capitalize on the power generation from photovoltaic (PV) modules and the wind turbines MPPT technique is employed. A DC voltage regulator is used in the layer of primary control to sustain a stable voltage profile. A coordinated control strategy integrates a grid-connected solar and wind power generation system with electric vehicle (EV) charging stations, balancing AC-DC loads with the support of a battery storage system. The solar PV system incorporates a boost converter with a Circle Search MPPT algorithm to optimize power extraction.

Read more

A Robust and Efficient Model Predictive Control for IPMSM Drive in Electric Vehicle Applications

The transition to Electric Vehicles (EVs) demands new motor control systems for enhanced efficiency and performance. Interior Permanent Magnet Synchronous Motors (IPMSMs) are frequently employed in EVs due to their high-power density and operational reliability. Traditional Proportional-Integral (PI) controllers generally struggle with system nonlinearities and dynamic changes. To solve these issues, Finite Control Set Model Predictive Control (FCS-MPC) offers a superior alternative by directly optimizing inverter switching states, eliminating torque ripple, and boosting system robustness.

Read more

Compact Folded T-Stub Microstrip Antenna with PIN Diode-Based Switching for Quad-Band Sub-6 GHz Wireless Systems

The article describes a miniaturized design of a microstrip patch antenna for wireless systems operating at frequencies below 6GHz. It consists of one PIN diode that can dynamically switch between two different operation modes without the need for any mechanical alterations to the radiator. The prototype was built on a Rogers RT/Duroid 5880 substrate (ε_r = 2.2, tan δ = 0.0009). The design has a small footprint of 17 x 17 x 0.55 mm3.

Read more

An Integrated Wavelet–Matched Filter–Adaptive Neural Network Framework for Enhanced Pulse Compression and Noise Reduction in Communication Systems

In modern communication systems, it is of great challenge to protect signal from being corrupted by heavy noise. We propose a four-stage overall integrated framework with wavelet-based denoising, matched filtering, adaptive compensation and DNN enhancement for pulse compression and de-noising in this paper. The applicability of the proposed method shows 18.5±2.1% reduction in MSE at 10 dB SNR, across both synthetic rectangular pulses and radar chirp signals as well as biomedical ECG waveforms. The statistical significance was verified with paired t-test (p < 0.001, n=100 trials). Extensive ablation analysis is carried out, showing that each step of the proposed method can lead to 3-8% performance improvement and the gain contributed by employing neural networks (i.e. processing) is most significant (7.2% MSE reduction).

Read more