Conference Proceeding - “Recent Trends in Engineering, Science and Technology-2026”
Volume 14 | Issue 6

 Abstract

Nowadays the world is shifting towards electrified mobility to reduce the pollutant emissions caused by non-renewable fossil-fueled vehicles and to provide an alternative to pricey fuel for transportation is an Electric Vehicle. But for electric vehicles, traveling range and charging process are the two major issues affecting its adoption over conventional vehicles WPT Enabled infrastructure has to be employed to achieve a Hybrid (dynamic/ stationary) EV charging concept. The weight of the battery pack can be reduced as the required energy storage is lower if the vehicle can be powered wirelessly while driving.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

WIRELESS ELECTRIC VEHICLE CHARGING STATION

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents Electric vehicles are today's zero emission vehicular technology which are considered as the future of automotive industry. The batteries of the vehicles get charged in order to drive the vehicle. The methodology of charging the electric vehicle currently is through plug-in method where the charging station charges the battery of an electric vehicle. However, an alternative method for charging the battery of an electric vehicle is through Wireless Power Transfer where it can be as a Static or Dynamic charging systems. Static Charging System can be implemented to charge the batteries of the electric vehicles when the vehicle is parked in static mode. Dynamic Charging System can be implemented to charge when the vehicle is in motion. This method of wireless charging of electric vehicle is done through inductive power transfer where wireless transmission of power is achieved by mutual induction of magnetic field between transmitter and receiver coil. The state of the battery is monitored using Battery Management system (BMS).

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Wire less Charging Station free Energy Transfer

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Energy Generation is a big problem in developing and developed countries. Its supply and demand is an issue as Energy Consumption is always higher than Energy production. Renewable Energy sources are playing a significant role in bridging the gap between energy generation and consumption. Photovoltaic Solar panels and wind generators are now widely available that can be used in order to conserve non-renewable resources. Wind Generator with Doubly-fed induction generator (DFIG) system is quite common in which the power electronic interface controls the rotor currents to achieve the variable speed necessary for maximum energy capture in variable winds. Exhaustion of Non-renewable Energy sources also leads to environmental problems. Therefore, there is the time to use renewable energy sources from non-renewable power sources such a way, which maximizes the use of power generated by renewable resources without affecting the power system. There should be an intelligent power system that can use the electrical power from renewable resources and only needs to use non-renewable power sources if renewable power is either not available or not fulfilling the required demand, which is the primary function of Smart Grid Power Network. Therefore, a smart grid is an electrical grid, which includes a vast variety of operations and energy measures, including smart meters, smart appliances, renewable energy resources, and energy-efficient resources. In this paper, different types of energy sources both non-renewable and renewable are connected and simulation is done with the help of MatLab Simulink Tool Box.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Simulation of Smart Grid in MATLAB/Simulink

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

PulseAI: Low-Cost IoT-Based Real-Time ECG Monitoring System Using AD8232, ADS1115, and ESP32

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

PulseAI: Low-Cost IoT-Based Real-Time ECG Monitoring System Using AD8232, ADS1115, and ESP32

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The Password-Based Circuit Breaker is a smart electrical protection system designed to improve safety and prevent unauthorized use of electrical power. In traditional circuit breakers, anyone can switch the power ON or OFF manually, which may lead to misuse, accidents, or electric hazards. This project introduces a password security feature that allows only authorized users to control the electrical supply.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Password-based Circuit Breaker

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Modelling and Simulation of a 100 kW Solar Power Plant Using MATLAB/Simulink

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Modelling and Simulation of a 100 kW Solar Power Plant Using MATLAB/Simulink

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents an IoT-Based Energy Monitoring and Control System using ESP32 and PZEM-004T sensor for real-time electrical parameter monitoring. The system measures voltage, current, power, and energy consumption and displays the data on an LCD display as well as on the ThingSpeak cloud platform through Wi-Fi connectivity. A relay module is integrated for remote load control using a mobile application. The proposed system enables real-time monitoring, cloud data storage, graphical analysis, and remote access for efficient energy management. The project helps reduce electricity wastage and supports smart home and smart campus applications.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

IoT Based Energy Monitoring System

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In this proposed system, two zero crossing detectors are used for detecting zero crossing of voltage and current. The project is designed to minimize penalty for industrial units using Automatic Reactive Power Compensation unit. The PIC microcontroller used in this project.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Automatic Reactive Power Compensation System

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Inefficient waste segregation at the source remains a significant challenge for effective waste management and recycling efforts. This project presents the design and implementation of an automated, IoT-enabled smart garbage separation system capable of classifying waste into distinct categories: Dry, Wet, and Metal.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

IOT, pico w, E waste, machine Learning, Sensor, WI- FI

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The project " EV BICYCLE" focuses on studying, designing, and understanding the mechanical and electrical systems that enable bicycles to be one of the most efficient human-powered machines ever developed. This report aims to present a detailed analysis of the basic working principles, structural components, efficiency factors, and innovations in modern bicycles.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Bicycle Design, Mechanical Transmission, Gear Systems, Brake Efficiency, Energy Conservation, Sustainable Transport

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Air Quality Monitoring Using Drone: A Quadcopter-Based Real-Time Atmospheric Sensing System

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Air Quality Monitoring Using Drone: A Quadcopter-Based Real-Time Atmospheric Sensing System

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Modern agriculture requires efficient water management, especially in hilly regions where uneven terrain makes irrigation difficult. Traditional irrigation methods often result in improper water distribution, increased wastage, and reduced crop productivity. To overcome these challenges, this project presents an IoT-based smart irrigation system designed for multi-crop cultivation, specifically for Wheat and Jowar crops.The system uses NodeMCU modules as wireless sensor nodes to monitor soil moisture, temperature, and humidity in real time across different crop zones. The collected data is transmitted to the Blynk cloud platform via Wi-Fi, enabling continuous monitoring through a mobile application. A Raspberry Pi acts as the central controller, processing the data and controlling irrigation components such as a water pump and solenoid valves using a relay module.The system operates in both automatic and manual modes. In automatic mode, irrigation is controlled based on soil moisture thresholds to ensure optimal water usage. In manual mode, users can monitor data and control the system remotely through the Blynk mobile application.This system improves water efficiency, reduces manual effort, and ensures proper irrigation in hilly environments. It is cost-effective, scalable, and supports real-time agricultural applications, contributing to sustainable farming and improved crop yield.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

IoT, Smart Irrigation, Raspberry Pi, NodeMCU, Soil Moisture Sensor, Blynk, Automation

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Tampering in weighing and measuring instruments poses a significant threat to commercial accuracy, consumer protection, and fair-trade practices. With the increasing shift from mechanical to digital systems, new forms of tamperingsuch as sensor bypassing, data manipulation, magnetic interference, and microcontroller hacking have emerged. This project focuses on the development of an intelligent tamper-detection and prevention system designed to ensure the integrity and reliability of weighing instruments. The proposed system integrates multiple security mechanisms including load cell monitoring through HX711 amplifier modules, tamper switches for enclosure security, magnetic field detection, and anomaly-based detection algorithms within a microcontroller unit. Any detected irregularity triggers visual and audible alarms and can log the event for regulatory inspection. Additionally, protective circuit design, shielding techniques, and secure firmware architecture are employed to minimize vulnerabilities. The outcomes demonstrate that a multi-layered approach combining hardware, software, and mechanical safeguards significantly increases resistance to tampering and enhances accuracy and trustworthiness in measurement systems. This solution supports legal metrology standards and promotes transparency in commercial transactions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Tampering detection, Weighing instruments, Legal metrology, Load cell security, HX711 amplifier, Microcontroller-based monitoring

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

AgroPredict: Intelligent Analysis of Soil Data for Crop Suggestion

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

AgroPredict: Intelligent Analysis of Soil Data for Crop Suggestion

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The integration of automation technologies in the hospitality industry is becoming increasingly important for improving service quality and reducing operational costs. This paper presents the development of a cost-effective autonomous service robot designed for indoor hospitality environments such as hotels, restaurants, and office spaces. The system is specifically designed to be low-cost, reliable, and easy to deploy, making it suitable for small and medium-sized enterprises.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Design and Implementation of a Low-Cost Autonomous Hospitality Robot for Smart Indoor Service Application

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

India's 146 million smallholder farming households continue to rely heavily on diesel-powered tillers for soil cultivation, weeding, and trenching. These machines consume 1.2-1.5 litres of diesel per operating hour, generating roughly 3.4 kg of CO? per hour and imposing an operating fuel cost of INR108-135/hr on marginal farmers. This paper presents the fabrication, testing, and detailed energy analysis of a 48 V brushless DC (BLDC) motor-driven electric soil cultivator, developed by third-year B.Tech students of the Electrical Engineering department at R.C. Patel Institute of Technology (RCPIT), Shirpur, Maharashtra, as part of their 2025-26 departmental project.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Electric cultivator, battery-powered weeder, BLDC motor, 48 V LiFePO?, FOC controller, Indian agriculture, energy saving, rural student fabrication, RCPIT Shirpur, JAP-O design.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid adoption of electric vehicles (EVs) worldwide has created an urgent need for sophisticated monitoring systems capable of tracking vehicle performance, battery health, energy consumption, and location in real time. This review paper examines the current state of real-time EV monitoring systems, exploring their architecture, key technologies, communication protocols, and applications. We analyse the challenges facing these systems and discuss emerging trends that will shape their future development. The integration of Internet of Things (IoT), cloud computing, machine learning, and advanced sensor technologies has enabled unprecedented capabilities in EV monitoring, [1] contributing to improved safety, efficiency, and user experience.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Electric vehicles, real-time monitoring, battery management system, IoT, telematics, cloud computing, machine learning, fleet management

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This work presents an IoT-enabled hybrid renewable energy charging station designed for electric vehicle applications. The system integrates a 12V/10W polycrystalline solar photovoltaic panel and a 3V DC generator motor functioning as a small-scale Wind Energy Conversion System to address the intermittency challenges inherent in single-source renewable installations. The station employs an ESP32 DevKit V1 microcontroller with dual-core Xtensa 32-bit LX6 processor, integrated 12-bit analog-to-digital conversion capability, and built-in Wi-Fi connectivity.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Hybrid renewable energy systems, wireless power transfer, Internet of Things, electric vehicle charging, ESP32 microcontroller, Blynk cloud platform.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid global integration of Photovoltaic (PV) systems requires robust monitoring and diagnostic mechanisms to ensure high efficiency and operational safety. PV systems are highly susceptible to various anomalies, including line-to-line faults, open circuits, partial shading, and degradation, which can severely diminish power output and cause permanent damage. Traditional fault detection methods rely on predefined thresholds, which often fail under fluctuating environmental conditions. This paper proposes a Machine Learning (ML) based approach for the automatic detection and diagnosis of faults in PV systems. By extracting key electrical features (voltage, current, power) and environmental data (irradiance, temperature), several supervised ML algorithms, including Support Vector Machines (SVM), Artificial Neural Networks (ANN), and Random Forest (RF), are evaluated. The methodology involves data preprocessing, feature extraction, and model training using simulated I-V characteristic curves under healthy and faulty conditions. The proposed model demonstrates high diagnostic accuracy, offering a reliable, sensor-efficient, and computationally viable solution for real-time predictive maintenance in solar energy systems.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Photovoltaic System, Fault Diagnosis, Machine Learning, Artificial Neural Networks (ANN), Predictive Maintenance, Partial Shading.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid growth of photovoltaic (PV) solar systems has increased the need for efficient monitoring and maintenance techniques to ensure optimal performance. Faults such as hotspots, shading, cracks, and connection failures significantly degrade system efficiency. This paper presents a comprehensive performance analysis of PV systems using thermal imaging technology for anomaly detection. Infrared thermography enables non-contact, real-time monitoring of PV modules by detecting temperature variations associated with defects. The study analyzes various anomalies, evaluates their impact on system performance, and highlights the effectiveness of thermal imaging combined with image processing techniques.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Photovoltaic systems, thermal imaging, anomaly detection, hotspots, infrared thermography, fault diagnosis.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This study investigates the structural, piezoelectric, and ferroelectric properties of lead-free Barium Calcium Titanate-Cobalt Ferrite (BCT-CFO) magnetoelectric composites. The samples were synthesized using a solid-state reaction method and characterized using SEM, EDS, and X-ray diffraction techniques.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

BCT-CFO, Magnetoelectric composites, Ferroelectricity, Piezoelectricity, SEM

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Metal chalcogenide-carbon nanocomposites are gaining significant attention as advanced materials for modern energy storage and conversion technologies. Their effectiveness arises from the complementary properties of both components: metal chalcogenides provide high electrochemical activity and multiple redox states, while carbon materials enhance electrical conductivity, mechanical strength, and surface area. This review highlights recent progress in synthesis approaches, structural engineering, and applications of these nanocomposites in batteries, supercapacitors, electrocatalysis, and photocatalysis. Additionally, key limitations such as structural instability, volume expansion, and scalability challenges are critically discussed, along with future research directions for real-world applications.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Metal Chalcogenide, Carbon Nanocomposites, Energy Storage, Energy Conversion, Chemical Vapor Deposition, Electrospinning

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

In this study, the binary mixtures n-butanol with formamide were investigated, focusing on their dielectric constant, density and refractive index. The dielectric constants were measured to assess the electrostatic interactions within the mixtures, density values provided insights into the overall composition and packing of molecules. Additionally refractive index data offered information on the optical properties of the mixtures, through systematic analysis. we observed variations in these properties in n-butanol with formamide binary mixtures. These findings contribute to a deeper understanding of the physicochemical behaviour of these mixtures. From the experimental dielectric data, excess dielectric constant, Kirkwood correlation factor, Bruggeman factor are estimated and reported in the study. The results show that the dielectric constants, densities and refractive index of the binary mixtures, decreases with increasing percentage of volume of n-butanol and the study shows the presence of molecular interactions and hydrogen bonding in the binary mixtures.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Binary liquid mixtures, Dielectric constant, Kirkwood correlation factor, Hydrogen bonding, Density and refractive index, Formamide-n-butanol system, Bruggeman factor

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

HelioFusion Smart Solar Tracking Hybrid PCM Cryo-Refrigerator is an advanced and energy-efficient refrigeration system designed to operate using renewable solar energy. The system integrates a dual-axis solar tracking mechanism, which continuously aligns the solar panel with the sun to maximize energy absorption and improve overall efficiency. To ensure uninterrupted cooling, the system incorporates Phase Change Material (PCM) for thermal energy storage. PCM stores excess cooling energy and maintains the desired temperature even during power interruptions or low solar availability, thereby enhancing system reliability.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Solar Energy, Dual-Axis Solar Tracking, IoT-Based Monitoring, Phase Change Material (PCM), Thermal Energy Storage, Heat Pipe Technology, Energy Efficiency, Smart Refrigeration, Off-Grid Applications.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Traditional cam-follower test rigs rely on manual measurement techniques using tachometers, vernier scales, and protractors to analyze simple harmonic motion (SHM). These conventional methods are prone to human error, limited in precision, and unable to provide real-time data visualization. This research presents the development of an advanced digital cam-follower test rig integrating sensor-based data acquisition, automated measurement, and real-time computational analysis. The system employs a Royal Enfield Bullet cam-follower mechanism with a rotary encoder for RPM and angular position measurement, and a Linear Variable Differential Transformer (LVDT) for follower displacement measurement. An Arduino microcontroller transmits data to a custom Python software platform which implements signal processing algorithms to generate kinematic graphs: cam angle vs. follower displacement, velocity, and acceleration. The system also automatically reconstructs the complete cam profile. Experimental validation demonstrates measurement accuracy improvement of 95%, data acquisition time reduced by 80%, and the capability to analyze complex motion patterns previously undetectable with manual methods. This digital test rig serves as a modern pedagogical tool bridging theoretical concepts with Industry 4.0 measurement technologies.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Cam-follower mechanism, simple harmonic motion, LVDT sensor, rotary encoder, data acquisition, Arduino, kinematic analysis, Python software.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents the design, structural analysis, fabrication, and experimental testing of a 1-ton capacity pillar-mounted jib crane with 180-degree controlled rotation, developed to address material handling challenges in small and medium-scale industrial environments. Conventional jib cranes providing 360-degree rotation impose safety risks in confined workspaces. The proposed crane employs an ISMB 250 structural steel boom as a cantilever beam, supported by a hollow circular steel mast of 225 mm outer diameter.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Jib Crane; ISMB 250; Structural Analysis; Material Handling; Cantilever Beam; Buckling; Fabrication

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Solar desalination has emerged as a sustainable and environmentally friendly solution to address the growing global demand for potable water, particularly in arid and remote regions where conventional water treatment technologies are economically or logistically unfeasible. With increasing freshwater scarcity driven by population growth, industrialization, and climate change, solar stills offer a simple, low-cost, and renewable energy-based desalination method. However, despite their advantages, conventional solar stills suffer from inherently low productivity due to limited heat absorption, poor evaporation rates, and significant thermal losses, which restrict their large-scale applicability.To overcome these limitations, recent research has focused on enhancing the performance of solar stills through hybridization techniques, among which the integration of solar air heaters has shown promising potential. This review paper aims to systematically analyze and synthesize existing experimental studies on hybrid solar stills coupled with solar air heaters to evaluate their effectiveness in improving distillate yield and overall thermal efficiency.The review methodology involves a comprehensive literature survey of peer-reviewed articles obtained from reputed journal databases such as Scopus, Web of Science, ScienceDirect, and Springer, covering publications primarily from 2010 to 2025. Selected studies are critically examined based on experimental configurations, operating conditions, climatic influences, and performance metrics such as daily yield, efficiency, and cost analysis.Key findings from the reviewed literature indicate that the integration of solar air heaters significantly enhances basin water temperature, accelerates evaporation rates, and improves overall system productivity compared to conventional solar stills. Additional augmentation techniques such as the use of phase change materials (PCM), nanofluids, external condensers, and optimized basin geometries further contribute to performance improvement. Among these, combined systems incorporating solar air heaters with thermal energy storage and advanced materials demonstrate the highest efficiency gains and yield enhancements.In conclusion, hybrid solar stills integrated with solar air heaters present a viable and efficient solution for improving desalination performance. Future research should focus on optimizing system design, integrating advanced materials, conducting long-term field studies, and performing economic.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Efficiency Gains: Yield Improvement: Optimal Conditions: Condensation Recovery.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The present study focuses on the design, development, and performance evaluation of a hemispherical solar dryer for agricultural applications. Drying is an essential process for preserving food materials by reducing their moisture content, thereby extending shelf life and minimizing post-harvest losses. Conventional open sun drying methods are associated with several limitations such as contamination, uneven drying, and dependence on climatic conditions. To overcome these challenges, a hemispherical solar dryer was developed using a dome-shaped transparent structure that enhances heat retention through the greenhouse effect. The system consists of an absorber surface, drying chamber with trays, and a controlled airflow mechanism.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Hemispherical Solar Dryer, Solar Drying, Agricultural Drying, Greenhouse Effect, Moisture Removal, IoT Monitoring, Renewable Energy, Drying Efficiency

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The present study focuses on the hybrid solar thermal water purification system with metaheuristic optimization for improved efficiency aimed at addressing the growing demand for safe drinking water using renewable energy sources. The proposed system utilizes solar energy as the primary power input, which is stored in a battery and subsequently used to operate a heating unit. Water is heated to a controlled temperature below its boiling point to initiate the purification process. The generated vapor is then condensed to obtain distilled water, which undergoes an additional filtration stage using a suitable filtering medium to enhance water quality. A secondary condensation stage ensures that the purified water is delivered at ambient temperature for direct consumption. The development process followed a systematic product design approach, beginning with the identification of user requirements and proceeding through design, prototyping, and evaluation stages. Furthermore, an economic assessment was carried out to evaluate the feasibility of large-scale production. To improve system performance, metaheuristic optimization techniques were applied to key processes, including heating, cooling, and purification. The results indicate that the proposed system is an energy-efficient and cost-effective solution for decentralized water purification, particularly suitable for rural and remote areas. If implemented effectively, the system has significant potential to alleviate the scarcity of potable water.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Solar Energy, Water Purification, Metaheuristic Optimization, Thermal Distillation, Hybrid System, Renewable Energy, Sustainable Water Treatment

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid proliferation of high-energy-density Lithium-ion Batteries (LIBs) in electric vehicles and grid-scale storage has shifted the critical bottleneck from energy capacity to thermal stability. Conventional air and liquid cooling methods increasingly struggle to manage the localized heat flux generated during Extreme Fast Charging (XFC) and high-discharge cycles, often leading to capacity fade or catastrophic thermal runaway. This review evaluates the transition from macro-scale cooling to nanomaterial-based thermal control, focusing on the integration of nanotechnology within passive and active cooling architectures.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Lithium-ion Battery (LIB), Thermal Management System (BTMS), Nanofluids, Phase Change Materials (PCM), Graphene, Thermal Runaway, Heat Transfer Enhancement.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The convergence of Artificial Intelligence (AI) and the Internet of Things (IoT) is transforming agriculture into a data-driven, automated, and sustainable domain. By integrating intelligent analytics with sensor-rich environments, smart agriculture aims to optimize crop yields, resource utilization, and food supply chains. This review critically examines recent developments in AI-enabled IoT for agriculture, highlighting architectures, algorithms, applications, and implementation challenges. We synthesize insights from more than forty-five scholarly works (2020-2025) and provide a thematic analysis of research trends. Particular attention is given to connectivity constraints, interoperability gaps, cybersecurity risks, and socio-economic barriers that hinder adoption. Comparative evaluations of existing IoT-AI frameworks demonstrate notable improvements in precision farming, yet reveal persistent limitations in scalability, explainability, and energy efficiency. The paper identifies research opportunities in edge/fog computing, federated learning, explainable AI (XAI), and blockchain-enabled trust frameworks. By offering a comprehensive synthesis of progress and open challenges, this review positions AI-driven IoT as a cornerstone for Agriculture 5.0 and provides guidance for researchers, policymakers, and practitioners working toward resilient, inclusive, and sustainable food systems.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Smart Agriculture, Artificial Intelligence, Internet of Things, Precision Farming, Machine Learning, Cybersecurity, Agriculture 5.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Urban traffic congestion significantly impacts emergency response times and public transport efficiency. Traditional fixed-time and semi-actuated signal systems fail to adapt dynamically to such priority needs, resulting in delayed emergency services and unreliable bus schedules. This project presents a Self-decisive traffic monitoring at crossroad junction system that integrates vehicle-in-urgency and public transport first preference mechanisms using IoT, sensors and vehicle-to-infrastructure (V2I) communication. The system detects approaching vehicle-in-urgency vehicles or buses via RFID, GPS, or camera-based sensing, predicts their arrival, and temporarily overrides normal signal cycles to grant a green corridor while ensuring pedestrian and cross-traffic safety. Conditional preference is also provided to delayed public transport vehicles to enhance schedule that follows. The system is assembled using Raspberry Pi 5 and the program code is executed using Thonny.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Smart Traffic Monitor and Control, Emergency Vehicle Pre-emption, Public Transport Priority, IoT and V2I Communication, Adaptive Signal Control, Intelligent Transportation System (ITS), Crossroad junction

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Water scarcity is becoming a serious issue in many urban areas due to increasing population and excessive consumption of freshwater resources. Grey water, which includes wastewater generated from household activities such as washing, bathing, and cleaning, can be reused for non-potable purposes if properly monitored. This paper proposes an IoT-based smart grey water management system using Raspberry Pi 4 to monitor water quality parameters such as pH and turbidity. The system automatically decides whether the water is reusable or not. If the water quality meets predefined standards, a Solenoid Valve directs the water to a reusable storage tank; otherwise, it is diverted to a waste tank. Sensor data is transmitted to the cloud platform ThingSpeak, allowing users to monitor water quality through a mobile device or laptop. The proposed system improves water conservation and enables intelligent water management in residential environments.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Grey Water, IoT, Water Quality Monitoring, Raspberry Pi, Turbidity Sensor.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Groundwater accumulation in mining areas leads to operational delays, increased maintenance costs, and safety hazards. Conventional dewatering systems rely on diesel-powered pumps or grid electricity, which are costly and environmentally harmful. This paper presents the design and implementation of a solar-powered automated dewatering system using an Arduino-based control mechanism. The system utilizes an ultrasonic sensor to monitor water levels and a relay-controlled DC pump for automatic water removal. A solar panel integrated with an MPPT charge controller provides a sustainable energy source, ensuring reliable operation in remote locations. To enhance system capabilities, an IoT-based monitoring approach is proposed, enabling real-time data visualization and remote access through cloud platforms such as ThingSpeak or Blynk. The proposed system aims to reduce human intervention, improve efficiency, and promote eco-friendly mining operations. Experimental observations indicate stable operation, efficient energy utilization, and effective automation, making the system suitable for small and medium-scale mining applications.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Solar Energy, Dewatering System, Mining Operations, IoT, Automation, Ultrasonic Sensor, Renewable Energy

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Electric fences are widely used in agricultural fields, industrial premises, and restricted areas for perimeter protection. However, unauthorized use, tampering, and accidental contact with electric fences can lead to safety hazards, property damage, and misuse of electrical energy. This paper presents an IoT-based smart hardware system designed to detect and prevent unauthorized use of electric fences through real-time monitoring, control, and alert mechanisms. The proposed system integrates a microcontroller-based unit with voltage and current sensors, motion detection modules, relay control circuits, and wireless communication technology such as Wi-Fi or GSM. The hardware continuously monitors fence status, power consumption, and intrusion attempts. If unauthorized activation, wire cutting, bypassing, or abnormal current flow is detected, the system immediately disconnects the fence power supply using an automated relay mechanism and sends instant alerts to the owner or security personnel through a mobile application or SMS.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

IOT, electric fence, unauthorized

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Autism Spectrum Disorder (ASD) is a neurodevelopmental condition characterized by impairments in social interaction, communication, and behavior, making early diagnosis crucial for effective intervention. Traditional diagnostic methods rely on behavioral assessments, which are often time-consuming and subjective. In recent years, deep learning-based computer vision techniques have emerged as promising tools for automated and non-invasive autism detection using facial images. This paper presents a comprehensive review of deep learning approaches for facial image-based autism detection, focusing on convolutional neural networks, transfer learning models, and hybrid architectures. The study analyzes commonly used datasets, evaluation metrics, and performance trends, highlighting that modern approaches achieve high accuracy but remain limited by dataset size, diversity, and clinical validation. Furthermore, key challenges such as ethical concerns, generalization issues, and lack of interpretability are discussed. The paper also outlines future research directions, including multimodal learning, explainable artificial intelligence, and the adoption of advanced architectures, to enhance the reliability and applicability of automated ASD detection systems

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Autism Spectrum Disorder, Deep Learning, Facial Image Analysis, Convolutional Neural Networks, Transfer Learning, Computer Vision, Medical Image Analysis, Explainable AI.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Memristor based systems represent an innovative approach to secure communications systems, nonlinear dynamics and hardware based efficient cryptographic systems. These systems demonstrate a unique combinatorial behavior produced by their non-linearity and ability to retain memory. As a result, they can exhibit a large variety of complex chaotic behaviors. When combined with field programmable gate arrays (FPGAs), memristor based chaotic systems may have the ability to be implemented in real-time, scalable and reconfigurable manner that makes them excellent candidates for current and future engineering applications. In this article, we review the literature pertaining to the generation of memristor based chaos on FPGA platforms through three major categories of discussion including theoretical foundations of memristors, implementation techniques for memristors and performance metrics of memristors from various study's performed within the literature. Performance metrics will be evaluated using comparison metrics including: hardware utilization, power consumption rate, throughput rate and system complexity. Finally, this research paper will identify the key gaps within existing research on memristor based chaos, outline limitations and discuss possibilities for future research. The combination of FPGA reconfigurability and memristor non-linear dynamics will create a new paradigm for the generation of high-speed, efficient and secure chaotic systems that can potentially be used in the future.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

FPGA, Memristor, Chaos, Cryptography, Throughput, Reconfigurability

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project presents an IoT-based Smart Medication Management and Pill Dispenser System designed to promote medication adherence through automation, tracking, and remote supervision. The system ensures that patients receive the right dose at the right time, minimizing human errors and noncompliance. It integrates IoT technology, sensors, and cloud connectivity to automatically dispense medication, monitor intake, and alert both patients and caregivers. A companion mobile application provides real-time updates, reminders, and visualization. By bridging healthcare with smart automation, the system improves patient safety, enhances treatment outcomes, and supports the growing demand for digital healthcare management Introduction

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Internet of Things (IoT), Smart Medication System, Pill Dispenser, Medication Adherence, Automated Drug Delivery, Health Monitoring, Embedded Systems, ESP32 .

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Waste management has become a major global challenge due to rapid urbanization and increasing population. Improper segregation of waste at the source leads to environmental pollution, inefficient recycling, and health hazards. This paper proposes a Smart Waste Segregation and Recycling System using Internet of Things (IoT) technologies. The system utilizes multiple sensors such as moisture sensors, metal sensors, and IR proximity sensors to automatically classify waste into biodegradable, recyclable, and non-biodegradable categories. A motor-driven mechanism ensures proper segregation into designated compartments. Additionally, ultrasonic sensors monitor bin fill levels and send real-time alerts using IoT modules. The system also incorporates a data-driven reward mechanism to encourage public participation. The proposed solution enhances waste management efficiency, reduces manual labor, and promotes sustainable environmental practices.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

IoT, Waste Segregation, Smart Bin, Sensors, Recycling, Automation.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Proper medication intake is a major concern, particularly for elderly individuals and patients suffering from long-term illnesses. Missing doses or consuming incorrect medication can lead to severe health complications and increased medical risks. This paper proposes an Integrated Drug Dispenser system that automates the process of medicine distribution while improving patient safety and adherence.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Smart Medication System, Automated Drug Dispenser, Raspberry Pi, GSM Aler, Healthcare IoT, Elderly Assitance

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper proposes an improved Dadda multiplier architecture aimed at achieving high speed and area efficiency in digital processing systems. Since multipliers consume a significant portion of hardware resources, optimizing their performance is critical in VLSI design. The proposed approach enhances the conventional Dadda multiplier by incorporating 4:2 compressors in the partial product reduction stage, which helps reduce critical path delay. Additionally, parallel prefix adders are employed in the final summation stage to further improve computational speed.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Dadda Multiplier, 4:2 Compressor, Parallel Prefix Adders, VLSI Design, High-Speed Arithmetic, Area Efficiency, Propagation Delay, LUT Utilization, DSP Applications

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Smart parking management systems are becoming an important part of smart cities due to the increasing number of vehicles and parking problems in urban areas. Traditional parking systems waste time, fuel, and increase traffic congestion. This paper presents a comprehensive literature review of smart parking systems based on recent research work. Various technologies such as Internet of Things (IoT), wireless sensor networks, image processing, and cloud computing are discussed. These technologies help in detecting available parking spaces and guiding drivers efficiently. The review also focuses on different methods like sensor-based, camera-based, and mobile application-based parking systems. Advantages such as reduced traffic congestion, lower fuel consumption, and improved user convenience are highlighted. However, challenges like high installation cost, data privacy, and system maintenance are also identified. From the literature, it is observed that modern systems are moving towards Artificial Intelligence and machine learning for better prediction and automation. This paper also suggests innovative improvements such as integrating face recognition, dynamic pricing, and smart reservation systems. Overall, smart parking systems can significantly improve urban mobility and make parking more efficient, reliable, and user-friendly.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Smart Parking, IoT, Sensors, Machine Learning, Smart Cities, Automation

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This project presents a portable, energy-efficient, and self-sustaining IoT-based health monitoring system designed to address the limitations of conventional battery-powered devices and the growing need for continuous health tracking. The system utilizes hybrid energy harvesting by combining solar power and ambient radio frequency (RF) energy. These sources are captured through a solar panel and RF harvesting coil, then processed via rectification and voltage regulation circuits. The harvested energy is stored in a lithium-ion battery, serving as the primary power supply and eliminating dependence on external power sources.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

IoT-based Health Monitoring, Hybrid Energy Harvesting ,Solar and RF Energy, NodeMCU (ESP8266) , MAX30102 Sensor , Remote Patient Monitoring , Self-Powered System ,Real-Time Data Transmission

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Facial emotion recognition is an important research area in artificial intelligence and computer vision. Human emotions are commonly expressed through facial expressions, voice, and body language. Among these communication channels, facial expressions are considered one of the most reliable indicators of emotional states. Automatic emotion recognition systems analyse facial images and classify emotions using computational techniques.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Facial Emotion Recognition, Deep Learning, Convolutional Neural Network (CNN), Computer Vision, Real-time Systems

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The rapid spread of infectious diseases such as COVID-19 has highlighted the importance of preventive measures like wearing face masks in public spaces. This project presents an automated face mask detection system using Machine Learning and Deep Learning techniques to monitor and ensure compliance with mask-wearing guidelines. The system is designed to detect human faces in real-time and classify whether a person is wearing a mask or not. The proposed model utilizes Convolutional Neural Networks (CNN), a class of deep learning algorithms particularly effective in image processing and computer vision tasks. The system is trained on a dataset containing images of people with and without masks. Image preprocessing techniques such as resizing, normalization, and augmentation are applied to improve the model's accuracy and robustness. For face detection, algorithms such as Haar Cascade or deep learning-based detectors are used to identify facial regions in images or video streams. The detected face is then passed through the trained classification model to determine mask presence. The system can be integrated with CCTV cameras to enable real-time monitoring in public areas such as airports, hospitals, schools, and offices. Experimental results demonstrate that the model achieves high accuracy in detecting face masks under varying lighting conditions and orientations. The system is cost-effective, scalable, and can be deployed on embedded devices for widespread use. This solution contributes to public health safety by automating mask detection and reducing the need for manual supervision.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Face Mask Detection, Machine Learning, Deep Learning, Convolutional Neural Network (CNN), Computer Vision Image Processing, Real-Time Detection etc.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Agricultural productivity is a key component of the economy, but every year crops succumb to several diseases. Artificial Intelligence (AI) models for plant disease detection frequently struggle in real-world farm environments, primarily due to environmental noise and complex backgrounds that fail to capture the pristine variability of lab conditions. This study proposes an innovative, robust framework that leverages the compound scaling of EfficientNetB0 trained on raw, real-environment images to address this domain gap. The performance of EfficientNetB0 is systematically compared against DenseNet121 and MobileNetV2. To further bridge the gap between automated detection and practical agronomy, this system integrates the Gemini API to provide Explainable AI (XAI) and dynamic treatment remedies. The core objective is to develop a reliable, generalizable system that overcomes the "black-box" limitations of traditional CNNs, enhancing the accuracy (achieving 94% in field conditions) and efficiency of plant disease diagnosis in the unpredictable conditions of a real farm.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

EfficientNetB0, Large Language Models (LLMs), Plant Disease Detection, Explainable AI (XAI), Convolutional Neural Networks (CNN), Precision Agriculture.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper focuses on reviewing sorting algorithm visualizers and their role in improving the understanding of algorithms. Visualization helps in learning complex concepts in a simple and interactive way. The proposed system demonstrates sorting algorithms step-by-step using graphical representation, making learning easier and more effective..

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Sorting Algorithms, Visualization, Data Structures, Bubble Sort, Quick Sort, Learning Tool

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Smart Parking System

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Smart Parking System

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Process scheduling plays an essential role in multitasking operating systems. Some of its benefits include high CPU utilization, short waiting times, short turnaround time, and better responsiveness. Round Robin is one of the most widely used techniques today due to its simplicity and fairness. However, it suffers from certain limitations based on a fixed time quantum which is dependent on different process burst times. This leads to increased context switching, wasted resources, and poor performance for processes that have huge differences in execution time. In the view of these issues, there is a need for the ADBRR scheduling algorithm. This self- tuning approach, called ADRR, adjusts time quantum based on changes in the process's burst characteristics. It means that ADRR treats short and long processes equitably. ADRR reduces unnecessary preemptions to ensure that no process starves in CPU time. We compare the performance of the new ADRR algorithm with traditional Round Robin scheduling after running the simulation and making observations. The experimental results show that ADRR maintains fairness and boosts CPU efficiency while significantly lowering average waiting time, turnaround time, and context switching overhead. These results support using an artificial intelligence technique with adaptive scheduling and prove how modern operating systems can be improved through machine learning

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Sensitive Operating Systems, Round Robin, Dynamic Time Quantum, Machine Learning, Decision Trees, CPU scheduling, Adaptive Scheduling.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

RetinoScopeAI is an OCT retinal prediction platform that was created using AI to deliver precise and early identification of reti-nal conditions like Choroidal Ne- ovascularization (CNV), Dia-betic Macular Edema (DME), and Drusen. It is a system that involves deep learning algo- rithms to decode high-resolution Optical Coherence Tomog- raphy (OCT) images. Such images are initially optimized by performing preprocessing on the image to remove noise and enhance the clarity of the image. Once preprocessed, the im- ages go through a trained neural network and disease-spe- cific patterns in the layers on the eye are detected. The site offers secure and easy web interface to physicians and healthcare providers. Users are able to send OCT images and get real-time results of diagnosis. The system shows the pre- dicted disease as well as the visual finding of the OCT scan. It can also give confidence scores and clinical insights to make medical decisions. RetinoScopeAI will help eliminate the reliance on manual interpretation by professionals. This reduces the human error and enhances consistency in diag- nosis. The platform aids in early detection and this aids in preventing loss of vision. It also can be used in remote and tele-ophthalmology. The automatic analysis saves time on the part of the doctors and more efficient on the screen-ing. Ret- inoScopeAI is an AI-based medical imaging company that creates better patient care. In general, the platform provides an efficient, rapid, and smart way of diagnosing and man- management of retinal diseases.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

AI-driven diagnosis, retinal OCT imaging, deep learning models, automated retinal analysis, early eye disease detec- tion, clinical decision support, telemedicine ophthalmology

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Integrating multiple APIs, third-party services, and AI models into single comprehensive workflow has become more difficult in this increasing growth of modern applications. Traditional workflow automation platforms often struggle to manage such complexity, especially when working with long and inter-related tasks, real-time data processing and AI-driven operations. This platform frequently faces issues such as API timeouts, inefficient resource utilization and loss of data consistency between different stages of workflow. Challenges such as maintaining context across multiple steps and ensuring reliability between interconnected components in the system often occurs while integrating different AI models and Services. These drawbacks make current systems difficult to scale and not suited for real-world production environment.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

AI Workflow Orchestration, Type-Safe Full-Stack Systems, Multi-Model LLM Integration, Asynchronous Task Execution, Distributed Workflow Systems, Context-Aware Data Flow

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Cultural heritage sites often face challenges such as structural deterioration, environmental damage, or limited accessibility, making preservation and public engagement dif-ficult. Emerging digital technologies, particularly Augmented Reality (AR), provide innovative ways to experience and interact with such monuments. This paper presents an AR-based system designed to facilitate interactive heritage exploration through digital reconstruction, intelligent narration, and community en-gagement.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Augmented Reality, Cultural Heritage, Mon-ument Reconstruction, AI Assistant, ChatGPT API, Tourism, Education

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The freshness of fruits is critical for maintaining quality in fruit. This paper represents an automated fruit freshness detection system using YOLOv8 object detection with squeeze-and-Excitation. the freshness of fruits our method balances accuracy and real time performance while detecting the freshness level of fruits the average accuracy is 85.5% with a maximum accuracy of 94.7% for detecting accuracy of 94.7% for detecting the freshness level of single fruits category .the results confirm that the enhanced YOLOv8 - SE model effectively detects and localizes fruit freshness conditions , indicating its suitability for smart agriculture and food quality monitoring applications.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Fruit recognition, freshness detection, image classification, MobileNet2, computer vision, K means clustering, deep learning, nutrition analysis, React.js, flask.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The fingertip acts as a virtual colored marker. Using Open CV, the captured frames are converted into HSV colour space, where colour detection and segmentation techniques are applied to isolate the fingertip region. The detected fingertip coordinates are continuously tracked and mapped onto a digital canvas, allowing the system to draw strokes corresponding to the user's hand movement. With designers and performers using digital media, touch and gesture-based interfaces are increasingly widely used in the creative industry. There are issues or flaws with these touchscreens, such as ergonomic strain and accuracy. The goal of this research is to thoroughly analyse how well these interfaces facilitate accuracy, expressiveness, and intuitive interaction while taking ergonomics into account.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

computer vision, virtual drawing, human-computer interaction, gesture recognition, hand tracking, and real-time processing

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents a critical review and comparative evaluation of machine learning methods to predict the compressive strength of concrete with particular emphasis on mixes that incorporate supplementary cementitious materials. The analysis includes ensemble algorithms (e.g., Random Forest, CatBoost, XGBoost, AdaBoost, Gradient Boosting), regression algorithms (Support Vector Regression, Linear Regression), and neural networks (Artificial Neural Networks, Extreme Learning Machines) by synthesizing the results of the latest studies. CatBoost was the most effective one, with the highest R 2 values of up to 0.94 in several studies. The most significant parameters found are concrete age, water-to-binder ratio, and cement content. Other important gaps in current literature that are identified during the review are inconsistency in datasets, lack of external model validation, lack of interest in hybrid models, and real-world implementation barriers. These results provide a basis on which universal and predictable forecasting models can be developed to more sustainably build concrete constructions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

RandomForest,,CatBoost,,LinearRegression,,NeuralNetwork

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Word Sense Disambiguation (WSD) is a critical task in Natural Language Processing (NLP) that seeks to resolve lexical ambiguity by determining the appropriate meaning of a word within a specific context. While considerable progress has been made in WSD for high-resource languages, low-resource languages have received limited focus due to a lack of annotated datasets, lexical resources, and computational tools. This paper provides a thorough survey of current WSD techniques, including knowledge-based, supervised, unsupervised, and deep learning methods, and assesses their applicability in low-resource language environments. The study also addresses the challenges faced by low-resource languages, such as data scarcity, morphological complexity, the absence of standardized tools, and multilingual influences. Furthermore, it reviews WSD research in Indian languages, including Manipuri, Malayalam, Punjabi, Bengali, and Sindhi, to highlight both current advancements and limitations. Notably, Sindhi is recognized as one of the least investigated languages concerning WSD research. The findings of this survey underscore the necessity for developing resource-efficient and adaptable approaches, particularly leveraging machine learning and deep learning techniques, to enhance WSD performance in low-resource languages. The paper also outlines future research directions aimed at overcoming existing challenges and closing the research gap in this area.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Word Sense Disambiguation, Low-Resource Languages, NLP, Machine Learning, Deep Learning, Sindhi

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Driver fatigue and drowsiness are significant contributors to road traffic accidents worldwide, posing serious threats to public safety and increasing the need for reliable driver monitoring technologies. Vision-based driver drowsiness detection systems have emerged as an effective and non-intrusive solution for monitoring driver behavior using computer vision and artificial intelligence techniques. These systems analyze visual indicators such as eye closure, blink rate, yawning behavior, head pose, and gaze direction to assess the driver's level of alertness. This paper presents a PRISMA-guided systematic review of vision-based driver drowsiness detection approaches, focusing on detection algorithms, fatigue indicators, machine learning techniques and real-time monitoring architectures. The review examines widely used techniques such as facial landmark detection, Eye Aspect Ratio (EAR), PERCLOS-based fatigue estimation, yawning detection, gaze tracking, and deep learning models. Comparative analysis of existing methods indicates that deep learning and hybrid vision-based approaches significantly enhance detection accuracy, although challenges related to illumination variation, occlusion, head pose changes, and real-time deployment remain. The study highlights current research trends and outlines future directions for developing robust and efficient driver monitoring systems for intelligent transportation environments.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Driver Drowsiness Detection, Computer Vision, Eye Aspect Ratio (EAR), PERCLOS, Deep Learning, Driver Monitoring Systems, Intelligent Transportation Systems, PRISMA Systematic Review.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Deepfake technologies driven by generative adversarial networks (GANs), neural vocoders, and end-to-end speech synthesis architectures have significantly advanced the generation of highly realistic synthetic audio. Modern voice cloning systems are capable of replicating speaker identity, linguistic style, and vocal timbre with minimal training data, making synthetic speech increasingly indistinguishable from authentic human recordings. While these developments offer substantial benefits in assistive technologies, entertainment, virtual agents, and content creation, they simultaneously introduce serious security, ethical, and societal risks. Malicious applications include financial fraud, identity impersonation, political misinformation, social engineering attacks, and erosion of public trust in digital media.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

CE-14 Deepfake Detection: Assessment of Speech and Emotion-Based Forensic Analysis

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The proposed system is based on e-certificate system in India's educational framework that leverages blockchain technology to address the widespread issue of certificate forgery. The inherent qualities of blockchain, including its immutability and transparency, create a solid foundation for enhancing the security and reliability of educational certifications. The operational framework is built around creating and storing an electronic file containing essential academic information in a dedicated database. Concurrently, the system generates a unique hash value for this electronic file, which serves as an exclusive identifier. This hash is securely embedded within a blockchain block, benefiting from the technology's resistance to tampering. To enable verification processes, both an inquiry string code and a QR code are linked to each certificate, encapsulating necessary information for authenticity verification. Users can initiate validation by scanning the QR code with a mobile device or entering the inquiry string on a specific website. The hash stored in the blockchain is then checked to confirm that the certificate has not been altered. This proposed solution significantly enhances the credibility of traditional paper certificates by implementing a dependable, transparent, and tamper-resistant verification process.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Blockchain, Digital Certificate, Hashing, E-Certificate, Certificate Verification, Transparency, QR Code, Secure Storage, Credential Authentication.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Evaluating subjective answers remains a major challenge in educational assessment due to the wide variation in students' writing styles, vocabulary, and expression of concepts. Traditional grading methods, such as manual evaluation or rule-based systems, are time-consuming, inconsistent, and unable to capture the true semantic meaning of answers. This paper presents a machine learning-based framework for automated subjective answer evaluation that leverages Natural Language Processing (NLP) techniques to assess student responses more effectively. The proposed system utilizes semantic embeddings and transformer-based architectures to analyze the contextual meaning of answers, enabling it to recognize paraphrased expressions and evaluate the relevance, completeness, and coherence of responses. The model is trained and validated using the ASAP-SAS dataset and further adapted to evaluate teacher-uploaded question papers. Standard evaluation metrics such as Quadratic Weighted Kappa (QWK), F1-score, and Pearson correlation are used to measure performance. The system aims to reduce manual effort, improve grading fairness, and provide timely feedback to students. Experimental outcomes demonstrate that machine learning can offer a scalable, consistent, and intelligent alternative to traditional grading, enhancing both the efficiency and reliability of academic assessments.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Subjective Answer Evaluation, Machine Learning, Natural Language Processing (NLP), Semantic Similarity, Transformer Models, BERT, Automated Grading, Educational Assessment, Deep Learning, Text Evaluation.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Melancholy is a common mental disorder that has a significant impact on people's wellbeing and frequently results in serious emotional, cognitive, and physical deficits. More precise and scalable solutions are required since traditionaldiagnostic techniques, which rely on self-reported questionnaires and clinician interviews, are subject to subjectivity and prejudice. This work suggests a sophisticated machine learning-based method for using facial expression analysis to identify and categorize depression. By automatically evaluating and classifying depression severity, the process seeks to enhance the early detection of depressive disorders by utilizing cutting-edge deep learning algorithms. The study combines a number ofmachine learning models, such as EfficientNet, Vision Transformers, Visual Geometry Group (VGG16), and Residual Network (ResNet50). The goal of the suggested method is to automatically evaluate and categorize depression severity with more precision and dependability.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Depression detection, facial expression analysis, deep learning, emotion recognition.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper proposes a robust framework for detecting and classifying road surface defects--specifically cracks and potholes - using machine learning algorithms trained on annotated image datasets. High-resolution images of various road conditions are processed and fed into a CNN model, which learns visual features to differentiate between defect types and severities. Traditional inspection methods are labor-intensive, time-consuming, and subject to human error. With the emergence of computer vision and deep learning, particularly convolutional neural networks (CNNs), automated road surface analysis has become a practical solution. The rapid growth of urban infrastructure has made the maintenance of road surfaces a critical issue for city planners and civil engineers. Road cracks and potholes significantly contribute to traffic accidents and long-term infrastructure degradation. The system integrates pre-processing steps like image enhancement, edge detection, and data augmentation to improve detection accuracy under varied lighting and environmental conditions. The trained model achieves high precision in identifying surface anomalies, outperforming conventional techniques. Evaluation metrics such as accuracy, recall, and F1-score are used to validate performance. The proposed method offers scalable deployment options in real-time road surveillance systems through drones or vehicle-mounted cameras. Furthermore, the model supports predictive maintenance planning by pinpointing early-stage defects. This initiative reduces human effort, increases monitoring efficiency, and ultimately enhances road safety. The system's adaptability across diverse geographical terrains further highlights its practicality. With the integration of GPS and cloud storage, defect locations can be mapped and archived for future assessments. This AI-driven approach has the potential to revolutionize road maintenance and traffic safety management globally.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Computer Vision, Pavement Crack Detection, Pothole Identification and Segmentation, Deep Learning, Convolutional Neural Network (CNN), Image Classification, Surface Defect Detection, Edge Detection, Automated Inspection, Road Maintenance, , Predictive Maintenance, Real-Time Detection.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This paper presents a comprehensive review of deep learning-based approaches for real-time recognition of continuous sign language. The primary objective is to analyze and compare various techniques used in gesture recognition systems that translate sign language into text and speech, thereby enabling effective communication for deaf and hard-of-hearing individuals. The study focuses on computer vision-based models such as Convolutional Neural Networks (CNNs), Recurrent Neural Networks (RNNs), Long Short-Term Memory (LSTM), and Media Pipe-based hand tracking systems.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Sign Language Recognition, Deep Learning, CNN, LSTM, Media Pipe, Computer Vision, Real-Time Systems, Assistive Technology

  License

Creative Commons Attribution 4.0 and The Open Definition