Current Issue

Vol 12, Issue 9 (September 2026) Electronics And Communication Engineering

Real-Time Speech Emotion Recognition Using Lightweight Convolutional Neural Network

Speech Emotion Recognition (SER) Allows Machines To Understand Human Emotional States From Their Speech, Enabling Applications In Human-computer Interaction, Call Center Analytics, And Mental Health Monitoring. Traditional Deep CNNs Achieve High Accu... Speech Emotion Recognition (SER) Allows Machines To Understand Human Emotional States From Their Speech, Enabling Applications In Human-computer Interaction, Call Center Analytics, And Mental Health Monitoring. Traditional Deep CNNs Achieve High Accuracy; However, They Are Costly When It Comes To Computation, Which Means They Cannot Be Used In Real Time On Edge Devices With Limited Computational Power. This Paper Proposes A Lightweight CNN-based Architecture For Real-time SER Using Log-Mel Spectrograms As Input Representations. The Proposed Model Incorporates Conv2D Layers, Batch Normalization, Max Pooling, And Global Average Pooling To Learn Discriminative Time-frequency Features While Reducing Model Complexity And Inference Overhead. Unlike The Existing Artificial Neural Network (ANN) Baseline, Which Was Trained Using Only The RAVDESS Dataset, The Proposed CNN Is Trained Using A Combined RAVDESS And TESS Dataset Covering Eight Emotion Classes: Neutral, Calm, Happy, Sad, Angry, Fearful, Disgust, And Surprised. Experimental Evaluation Shows That TheproposedLightweightCNNattained75.70%testaccuracywithaweightedF1-scoreof0.78, Compared To The ANN Baseline Model’s 54.86% Accuracyand0.55F1-score. Additionally, Compared To The ANN Baseline, The Proposed Lightweight CNN Architecture Demonstrated Faster Real-time Performance Using Microphone Input While Providing Confidences Cores For Each Emotion Detected. Overall, The Proposed Lightweight CNN Model Provides Faster Inference With Good Accuracy For SER Applications. Read more Read less

Authors: Natchathiram K | Prof. Dr. G. Kulanthaivel | Prof. Dr. P. Sivasankar

Vol 12, Issue 9 (September 2026) Electrical And Electronics Engineering

Dual-Loop PI–Hysteresis Control Of A Single-Phase Bridgeless AFE Rectifier For Power-Factor-Corrected CC–CV Battery Charging

Conventional Diode- And Thyristor-based Rectifiers Draw Non-sinusoidal Current, Producing Poor Power Factor And Harmonic Distortion Exceeding IEEE-519 Limits. This Paper Presents The Design, Modelling, And Closed-loop Simulation Of A Single-phase Tot... Conventional Diode- And Thyristor-based Rectifiers Draw Non-sinusoidal Current, Producing Poor Power Factor And Harmonic Distortion Exceeding IEEE-519 Limits. This Paper Presents The Design, Modelling, And Closed-loop Simulation Of A Single-phase Totem-pole Bridgeless Active Front-End (AFE) AC–DC Converter That Performs Power-factor Correction While Charging A Battery Through A Constant Current–Constant Voltage (CC–CV) Profile, Automatically Selected From Battery State Of Charge (SOC). A Proportional–Integral (PI) Outer Loop Regulates Current Below 80% SOC And Voltage Above It, While An Inner Hysteresis Current Controller Shapes The Source Current To A Synchronised Sinusoidal Reference. Simulated In MATLAB/Simulink For A 100 W, Single-phase Charger For 22.2 V, 5 Ah Lithium-ion Battery, The Converter Achieves A Power Factor Above 0.9 And A Source-current THD Below 5%, Confirming An Effective, Low-complexity Means Of Combining Power-factor Correction With Regulated CC–CV Battery Charging. Read more Read less

Authors: Jeyakrishnan V | Dr.G.A.Rathy

Vol 12, Issue 9 (September 2026) Engineering

Experimental Investigation On The Strength And Durability Properties Of M30 Concrete By Partially Replacing Cement With Eggshell Powder

This Study Investigates Egg Shell Powder (ESP) As A Partial Replacement For Ordinary Portland Cement In M30 Grade Concrete, With Emphasis On Fresh Behaviour, Mechanical Strength And Durability. Concrete Mixes Were Prepared With 0%, 5%, 10%, 15%, 20%,... This Study Investigates Egg Shell Powder (ESP) As A Partial Replacement For Ordinary Portland Cement In M30 Grade Concrete, With Emphasis On Fresh Behaviour, Mechanical Strength And Durability. Concrete Mixes Were Prepared With 0%, 5%, 10%, 15%, 20%, 25% And 30% ESP Replacement By Mass Of Cement. The Control Mix Was Proportioned In Accordance With IS 10262:2019 Using OPC 53 Grade Cement, A Water-cement Ratio Of 0.42, 158 Kg/m³ Of Water, 648.9 Kg/m³ Of Fine Aggregate And 1275.6 Kg/m³ Of Coarse Aggregate. Workability Was Evaluated By The Slump Test; Compressive And Flexural Strengths Were Measured At 3, 7 And 28 Days; And 28-day Durability Was Assessed By Water Absorption And Rapid Chloride Permeability Test (RCPT). The 5% ESP Mixture Showed The Best Overall Performance. Its 28-day Compressive Strength Was 36.40 N/mm², Approximately 12% Above The Control Value Of 32.50 N/mm², While Its Flexural Strength Reached 5.10 N/mm², A 13.3% Increase Over The Control. Water Absorption Decreased From 2.85% To 2.45%, And RCPT Charge Decreased From 3850 To 3420 Coulombs. At 10% ESP, Strength Remained Above The Control, Whereas Replacement Beyond 10% Caused Progressive Losses In Strength And Durability. The Results Identify 5% ESP As The Optimum Replacement Level For The Investigated M30 Concrete And Demonstrate The Potential Of Controlled Eggshell-waste Utilization In Sustainable Concrete Production. Read more Read less

Authors: Akshay Laxman Kamthe | Prof. Abhijeet Undre | Dr. Atul Pujari

Vol 12, Issue 9 (September 2026) POWER ELECTRONICS AND DRIVES

MPPT Solar Street Light With IoT-Enabled Vision-Assisted Adaptive Luminous Control

Conventional Solar Street Lighting Systems Generally Operate With Fixed Illumination Levels And Non-optimal Power Extraction, Resulting In Inefficient Utilization Of Harvested Solar Energy. This Paper Presents The Modelling, Simulation And Analysis O... Conventional Solar Street Lighting Systems Generally Operate With Fixed Illumination Levels And Non-optimal Power Extraction, Resulting In Inefficient Utilization Of Harvested Solar Energy. This Paper Presents The Modelling, Simulation And Analysis Of A Maximum Power Point Tracking (MPPT) Based Solar Street Lighting System Integrated With An Internet Of Things (IoT)-enabled, Vision-assisted Adaptive Luminous Control Strategy. A Perturb And Observe (P&O) MPPT Algorithm, Implemented On A DsPIC30F2010 Digital Signal Controller, Regulates The Duty Cycle Of A SEPIC DC–DC Converter To Extract Maximum Power From A 50 W Monocrystalline Photovoltaic (PV) Module During The Day. At Night, The Same Converter Is Reconfigured Through A Relay-based Changeover To Drive The LED Load With A Duty Cycle Jointly Determined By The Day's Harvested Energy, Expressed As An Energy Sufficiency Ratio, And Real-time Road Activity Sensed By An ESP32-CAM Vision Module, Ensuring That Continuous 12-hour Illumination Is Guaranteed Irrespective Of Solar Variability While Never Compromising Visibility For Detected Pedestrians Or Vehicles. The Complete System, Including The Single-diode PV Model, The Fourth-order SEPIC Converter, The P&O Control Law And The Two-layer Adaptive-brightness Controller, Is Modelled And Simulated In MATLAB/Simulink. Simulation Results Show Stable Maximum-power-point Operation With An MPPT Tracking Efficiency Of 99.83%, A Cold-start Convergence Time Of Approximately 50 Ms, An Estimated Converter Efficiency Of Approximately 90%, And An Average Night-time Energy Saving Of 58–61% Relative To Fixed Full-brightness Operation. A Day-level Energy Balance Under A 5 Peak-sun-hour Irradiance Profile And A 12 V/18 Ah Battery Confirms A Positive Surplus Of +49.1 Wh Under Full-brightness, Full-night (12 H) Operation And +121.1 Wh Under Adaptive Dimming, Providing Resilience Against Consecutive Overcast Days. The Results Confirm That The Proposed Architecture Provides An Efficient, Low-cost, Scalable And Intelligent Solution For Adaptive Solar Street Lighting Suitable For Rural And Semi-urban Deployment, And Establish A Validated Simulation Baseline For Subsequent Hardware Realization. Read more Read less

Authors: VIJAY A J | G. A. Rathy

Vol 12, Issue 9 (September 2026) Electronics And Communication Engineering

IoT Based Smart Public Transport Framework For Location Tracking And Seat Availability Monitoring

Public Transportation Systems Face Significant Challenges In Providing Real-time Information About Bus Location And Seat Availability To Passengers, Resulting In Long Waiting Times, Overcrowding, And Inefficient Utilization Of Transport Resources. Th... Public Transportation Systems Face Significant Challenges In Providing Real-time Information About Bus Location And Seat Availability To Passengers, Resulting In Long Waiting Times, Overcrowding, And Inefficient Utilization Of Transport Resources. This Paper Presents An IoT-Based Smart Public Transport Framework That Integrates Embedded Systems, Wireless Communication, GPS Technology, And Cloud-based Monitoring To Address These Challenges. The Proposed System Consists Of Two Main Units: The Bus Unit And The Bus Stop Unit. The Bus Unit Employs An ESP32 Microcontroller As The Central Controller, Utilizing Ultrasonic Sensors For Passenger Counting At Entry And Exit Points, Infrared (IR) Sensors For Seat Occupancy Detection, And Servo Motors For Automatic Door Control. A 433 MHz RF Communication System With HT12E/HT12D Encoder-decoder Modules Enables Wireless Transmission Of Passenger And Seat Information From The Bus Unit To The Bus Stop Unit. The System Incorporates GPS-based Location Tracking And Wi-Fi Connectivity For Transmitting Real-time Data To An IoT Cloud Platform, Enabling Remote Monitoring Through A Web-based Dashboard. The Design Was Implemented Using The ESP32 Development Board With Sensors And RF Modules. Experimental Results Demonstrate Accurate Passenger Counting, Reliable Seat Occupancy Detection, Stable RF Communication, And Effective IoT-based Remote Monitoring. Total System Power Consumption Was Measured At Different Sparsity Conditions Representing Passenger Occupancy Levels. The Proposed Framework Provides A Cost-effective, Scalable Solution For Improving Passenger Convenience, Reducing Waiting Uncertainty, And Supporting Smart City Transportation Initiatives. Read more Read less

Authors: Kalaivanan K | Dr. P. Sivasankar | Dr. G. Kulanthaivel