Volume 14 | Issue 7 | July-2026

 Abstract

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Adaptive Neuro-Fuzzy Inference System (ANFIS), Electric Vehicle Charging, Interleaved DC-DC Boost Converter, Pulse Width Modulation (PWM)

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

This research reviews the transformative role of Artificial Intelligence (AI) in enhancing the control, diagnostic, and estimation frameworks of Brush-less DC (BLDC) motors within electric vehicle (EV) and fuel cell electric vehicle (FCEV) environments. Traditional Proportional-Integral (PI) controllers often fail to maintain stability under the high nonlinearity, parameter variations, and load disturbances inherent in modern propulsion systems. To address these limitations, this paper examines advanced AI methodologies, including Adaptive Neuro-Fuzzy Inference Systems (ANFIS), Deep Reinforcement Learning (DRL), and Deep Transfer Learning (DTL). These tools are utilized for real-time parameter tuning, sensorless position estimation, and predictive maintenance through Remaining Useful Life (RUL) forecasting. Experimental and simulation results across the reviewed literature consistently demonstrate that AI-integrated systems significantly reduce settling time, eliminate overshoot, and minimize torque ripple. Ultimately, the integration of AI acts as a "virtual sensing" and "intelligent decision-making" layer that optimizes energy efficiency and extends the operational lifespan of EV powertrains.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

BLDC motor, ANFIS, sensorless control, Electric Vehicles.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Dynamic Wireless Power Transfer (DWPT) is proposed as a pathway toward eliminating onboard batteries in electric vehicles (EVs), thereby addressing the weight, cost, and end-of-life disposal challenges associated with conventional lithium-ion packs. A prototype EV system is presented that operates with zero onboard energy storage, receiving power continuously from 18 road-embedded transmitter coils operating at 120 kHz through a fixed 5 mm air gap. Three relay switches, sequenced by a hardware timer circuit, activate coil zones autonomously without the need for a programmable controller. A hybrid supply combining solar photovoltaic energy with a 12 V AC-DC adapter powers the transmitter infrastructure, while a separate 5 V adapter maintains the isolated control plane. Experimental validation confirms continuous battery-free vehicle motion, reliable autonomous coil sequencing, and seamless hybrid supply switchover across all test conditions.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Dynamic Wireless Power Transfer; Battery-Free Electric Vehicle; Inductive Coupling; Timer-Controlled Relay Sequencing; Hybrid Solar-AC Supply; 120 kHz Resonant Transfer; Autonomous Coil Activation.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The increasing demand for clean and sustainable transportation has accelerated the adoption of electric vehicles (EVs) worldwide. However, the dependency of EV charging systems on conventional grid power creates challenges related to carbon emissions, energy shortage, and grid instability. This paper presents the integration of solar and wind energy systems for sustainable electric vehicle charging applications. The proposed hybrid renewable energy system combines photovoltaic (PV) panels and wind turbines to provide reliable, eco-friendly, and continuous power for EV charging stations. An energy management system is employed to optimize power flow between renewable sources, battery storage, and the electric vehicle load. The hybrid approach enhances system reliability by compensating for the intermittency of individual renewable sources. Solar energy contributes during daytime conditions, while wind energy supports power generation during low sunlight or nighttime periods. The proposed system reduces dependence on fossil fuels, minimizes greenhouse gas emissions, and improves energy efficiency. Simulation and performance analysis demonstrate that the integrated solar-wind EV charging system can effectively meet charging demands with reduced operational cost and environmental impact. The study highlights the potential of renewable energy integration in developing sustainable and smart transportation infrastructure for future energy systems.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Electric Vehicle (EV), Solar Energy, Wind Energy, Hybrid System, Renewable Energy, EV Charging, Sustainable Energy, Battery Storage, Smart Grid.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Agriculture is a fundamental sector that requires continuous innovation to improve productivity and reduce manual labor. This paper presents the design and implementation of a multipurpose smart agriculture robot controlled using a smartphone. The proposed system integrates modern technologies such as wireless communication, sensors, and automation to perform multiple farming operations efficiently. The robot is capable of executing tasks such as seed sowing, irrigation, pesticide spraying, and soil monitoring with minimal human intervention. A mobile application is used to control and monitor the robot in real time, providing flexibility and ease of operation to farmers. The system utilizes components such as microcontrollers, motor drivers, and environmental sensors to ensure accurate and reliable performance. Experimental results demonstrate that the robot improves operational efficiency, reduces labor costs, and enhances precision in agricultural practices. This smart solution contributes to sustainable farming and supports the advancement of modern agriculture.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Smart agriculture, automation, smartphone control, agricultural robot, IoT, sensors.

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Bomb disposal operations involve significant risks to human life due to the possibility of accidental explosions and exposure to hazardous environments. To improve operator safety and operational efficiency, robotic systems are increasingly being adopted for remote handling applications. This paper presents the design and development of a smart AI-based human motion synchronised robotic arm using Arduino for bomb disposal applications. The proposed system captures human hand movements using flex sensors and accelerometer sensors integrated into a wearable glove. The sensed motion data is processed using Arduino and transmitted wirelessly through RF communication to a robotic arm. Artificial Intelligence techniques are incorporated for gesture recognition, motion prediction, and movement optimization to improve synchronization accuracy and response performance. Servo motors attached to the robotic arm replicate the operator's hand movements in real time, enabling safe remote handling of suspicious objects. Experimental results demonstrate reliable wireless communication, accurate gesture synchronization, reduced response delay, and stable object manipulation. The proposed system is economical, portable, and suitable for defense, hazardous material handling, and industrial automation applications.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Arduino, Bomb Disposal Robot, Flex Sensor, Human Motion Synchronization, RF Communication, Robotic Arm, Servo Motor, Wireless Control,Artificial Intelligence

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

The cardiovascular diseases (CVDs) can be listed among the significant causes of mortality in the world and this is why there is a need of a reliable and early answer to the risk. Since Electronic Health Records (EHRs) are integrated in numerous hospitals, the amount of structured patient data to analyze and predict is enormous. However, the historical machine learning techniques typically assume the existence of individual samples of patient records and ignore the already existing interrelations among individuals within the same clinical phenotype. This is a weakness because it narrows their ability to adopt complex relationships, which are present in real medical records.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Gra.ph Neural Netw.ork (GNN), Cardiov.ascular Disease Predi.ction, Elect.ronic Hea.lth Reco.rds (EHR), Gra.ph Convolu.tional Netw.ork (GCN), Gra.ph Atten.tion Netw.ork (GAT), Deep Lear.ning, Risk Asses.sment, Clin.ical Deci.sion Supp.ort Sys.tem, Machine Lear.ning, Healt.hcare Analy.tics

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Mental health problems like stress, anxiety, and depression are becoming quite widespread owing to rapidly changing lifestyles, academic stress, and social factors. In order to mitigate the risk of negative psychological outcomes, it is important to recognize such mental disorders at an early stage. However, existing assessment practices are based mainly on clinical interviews and the use of questionnaire tools, which may be insufficient or unavailable in certain situations. Therefore, the current research proposes an innovative solution in the form of an AI-based mental health assessment system.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Artif.icial Intelligence, Mental Hea.lth Asses.sment, Spe.ech Anal.ysis, Text Anal.ysis, Natu.ral Lang.uage Proce.ssing (NLP), Mach.ine Lear.ning, Emot.ion Detec.tion, MFCC, Logi.stic Regre.ssion, Ran.dom For.est

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Hospital-acquired infections remain an issue of great concern in contemporary health care systems. In addition to posing significant dangers to patients' wellbeing, HAIs result in increased mortality rates, prolonged hospitalization periods, and increased costs. The classical infection prevention and control rely on manual surveillance, laboratory tests, and retrospective analysis, which cannot detect infection warning signs promptly enough to prevent infections. With a steady increase in healthcare information becoming available through electronic health records, there is a need for intelligent, data-based techniques that would analyze vast amounts of data and predict the potential risks of infection.

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Hospital.-Acquired Infec.tions (HAIs), Mach.ine Learning, Infec.tion Risk Predi.ction, Healt.hcare Analy.tics, Clin.ical Deci.sion Supp.ort Syst.ems, Electronic Health Reco.rds (EHR), Ran.dom For.est, Data Preproc.essing, Predi.ctive Modeling, Infec.tion Cont.rol

  License

Creative Commons Attribution 4.0 and The Open Definition

 Abstract

Infertility is a complicated health issue that involves numerous complex relations between several different physiological, hormonal, and even lifestyle variables. The traditional means of diagnosing infertility include separate testing and manual image analysis that can be inconsistent and time-consuming. In order to overcome these drawbacks, this paper proposes a hybrid Artificial Intelligence (AI) model for predicting fertility status that will incorporate techniques of Machine Learning (ML) and Deep Learning (DL).

Licence: creative commons attribution 4.0

  License

Creative Commons Attribution 4.0 and The Open Definition

 Keywords

Fertility Predi.ction, Hyb.rid Mach.ine Lear.ning Mod.el, Deep Learning, Ran.dom Forest Class.ifier, Convolu.tional Neu.ral Network, Medi.cal Ima.ge Anal.ysis, Ultra.sound Imag.ing, Predictive Healt.hcare, Clin.ical Deci.sion Supp.ort Sys.tem, Artif.icial Intell.igence in Healt.hcare, Feat.ure Fus.ion, Reprod.uctive Hea.lth Analy.tics

  License

Creative Commons Attribution 4.0 and The Open Definition