Journal of Science Engineering Technology and Management Science

With the proliferation of wireless technologies and the increasing prevalence of mobile devices, ad-hoc networks have become an integral part of modern communication systems. However, the dynamic and decentralized nature of ad-hoc networks poses significant challenges to ensuring robust and secure data transmission. Traditional cryptographic methods and routing protocols often struggle to cope with the complexities and uncertainties inherent in ad-hoc environments. This paper proposes a novel approach to address these challenges by leveraging artificial intelligence (AI) techniques for enhancing the robustness and security of data transmission in ad-hoc networks. Specifically, we explore the application of machine learning algorithms, such as reinforcement learning, neural networks, and evolutionary algorithms, to dynamically adapt to changing network conditions, mitigate malicious attacks, and optimize routing decisions. By harnessing the power of AI, our proposed framework can autonomously learn and adapt to the evolving network dynamics, thereby improving the reliability and resilience of data transmission in ad-hoc networks. Furthermore, the integration of AI-based intrusion detection and anomaly detection mechanisms enhances the security posture of the network by effectively identifying and mitigating potential threats in real-time. Through extensive simulations and experiments, we demonstrate the effectiveness and efficiency of our AI-driven approach in ensuring robust and secure data transmission in various ad-hoc network scenarios. Our results highlight the superior performance of the proposed framework compared to traditional methods, particularly in terms of packet delivery ratio, end-to-end delay, and resilience to attacks.In conclusion, this paper presents a pioneering solution that harnesses the transformative capabilities of artificial intelligence to address the inherent challenges of data transmission in ad-hoc networks. By providing adaptive, intelligent, and resilient communication mechanisms, our approach lays the foundation for the development of next-generation ad-hoc networks that can seamlessly operate in dynamic and hostile environments while ensuring the integrity and confidentiality of transmitted data.

Keywords : In recent years, the proliferation of mobile devices and wireless technologies has led to the widespread deployment of ad-hoc networks, which offer flexible communication capabilities without the need for a fixed infrastructure.

Author : M.Prem Kiran,K.Subash Chandra

Title : Robust and Secure Data Transmission Using Artificial Intelligence Techniques in Ad-Hoc Networks

Volume/Issue : 2026;03(06)

Page No : 896-903

Online payment systems have become a crucial component of modern financial services,buttheyareincreasinglyvulnerable to fraudulent activities. Detecting fraudulent transactions is a challenging task due to the high class imbalance between genuine and fraudulenttransactions.Thisprojectpresents a machine learning-based approach to accurately detect online payment fraud by leveragingbalancedalgorithmstoaddressthe skewed distribution of data. Various resampling techniques such as Synthetic Minority Over-sampling Technique (SMOTE) and Adaptive Synthetic Sampling (ADASYN) are employed to balance the dataset.Multiplemachinelearningclassifiers including Random Forest, Decision Tree, Logistic Regression, and XGBoost are trained and evaluated on the balanced data. The models are assessed using performance metrics such as accuracy, precision, recall, F1-score, and Area Under the Curve (AUCROC) to ensure robustness. Experimental results demonstrate that balancing the data significantly improves the ability of the classifierstodetectfraudulentactivities.This studyhighlightstheeffectivenessof combiningbalancedsamplingstrategieswith machinelearningalgorithmstobuildreliable fraud detection systems in online payment environments.

Keywords : With the rapid growth of e-commerce and digital transactions, online payment systems havebecome an essential aspectof everyday life.

Author : SK.AnjaneyuluBabu1 ,V.Praveen2

Title : ONLINE FRAUD PAYMENT DETECTION USING BALANCED ML ALGORITHMS

Volume/Issue : 2026;03(06)

Page No : 904-916

With the rapid growth of online video platforms, spam comments on video-sharing websites have become a major concern. Spam comments often contain advertisements, malicious links, or irrelevant content that can affect user experience and platform credibility. This project proposes a machine learning-based system to automatically classify and detect spam comments on YouTube. The system analyzes comment text using natural language processing (NLP) techniques and applies machine learning algorithms to classify comments as spam or non-spam. By training the model with labeled datasets, the system can identify patterns commonly found in spam messages. The proposed solution helps improve content quality, enhances user interaction, and reduces manual moderation efforts.

Keywords : With the rapid growth of social media platforms, YouTube has become one of the largest video-sharing platforms in the world, hosting billions of users and generating massive volumes of user-generated content daily.

Author : Sk. AnjaneyuluBabu1 , M.V.S Nagarjuna Raju 2

Title : YOUTUBE COMMENT SPAM CLASSIFICATION

Volume/Issue : 2026;03(06)

Page No : 917-923

Skin cancer is one of the most common types of cancer worldwide, and early detection plays a crucial role in improving patient survival rates. Traditional diagnosis methods rely heavily on dermatologists and manual examination of skin lesions, which can be time-consuming and subjective. This project proposes a deep learning-based system for automatic skin cancer classification using dermoscopic images. Convolutional Neural Networks (CNNs) are used to analyze and classify skin lesion images into different categories such as benign and malignant. The system processes images through preprocessing, feature extraction, and classification stages to accurately identify cancerous lesions. By using deep learning techniques, the proposed system improves diagnostic accuracy, reduces human error, and assists dermatologists in early detection and treatment planning. The proposed system processes input images, performs image preprocessing, feature extraction, and classification using deep learning techniques. By learning patterns from a large dataset of skin lesion images, the model can identify suspicious lesions with high accuracy. This approach helps in early detection of skin cancer, assists dermatologists in diagnosis, and reduces the chances of misclassification. Overall, the system provides an efficient and automated solution for skin cancer classification, improving diagnostic accuracy and supporting healthcare professionals in providing timely treatment.

Keywords : Skin cancer is one of the most common and rapidly increasing types of cancer worldwide, primarily caused by prolonged exposure to ultraviolet (UV) radiation.

Author : 1 HIMAMBASHA SHAIK, 2 .M.SIREESHA

Title : AN AUTOMATED SKIN CANCER DETECTION SYSTEM USING CONVOLUTIONAL NEURAL NETWORKS

Volume/Issue : 2026;03(06)

Page No : 924-930

Agriculture is one of the most important sectors contributing to the economy and food security of many countries. Farmers often face challenges in selecting suitable crops due to changing climatic conditions, soil fertility variations, and lack of accurate agricultural guidance. Incorrect crop selection can result in low productivity, financial losses, and inefficient utilization of resources. This project proposes a Machine Learning-Based Agricultural Crop Recommendation System that recommends suitable crops based on productivity, soil characteristics, and seasonal conditions. The system analyzes parameters such as soil type, temperature, humidity, rainfall, pH level, and historical crop productivity using machine learning algorithms like Decision Tree, Random Forest, and Support Vector Machine (SVM). Based on the analysis, the system predicts the most appropriate crop for cultivation in a particular season and location. The proposed approach improves agricultural productivity, supports datadriven farming decisions, and promotes sustainable agricultural practices.

Keywords : Agriculture plays a crucial role in the economic development of many countries and serves as the primary source of livelihood for millions of people.

Author : B. AMARNATH REDDY1 , P. MADHU KARTHIKEYA TEJA REDDY2

Title : Agricultural Crop Recommendations Based On Productivity And Season

Volume/Issue : 2026;03(06)

Page No : 931-939

Communication is one of the fundamental needs of human interaction, but individuals with hearing and speech impairments often face difficulties in communicating with others. Sign language serves as an important medium for such individuals; however, many people are unfamiliar with sign language, creating communication barriers. This project proposes a Sign Language Recognition System using Convolutional Neural Networks (CNN) that converts hand gestures into text and voice output in real time. The system captures hand gestures using a camera, preprocesses the images, and uses deep learning techniques to classify sign language gestures accurately. The recognized gestures are converted into readable text and synthesized speech, enabling effective communication between sign language users and non-sign language users. The proposed system improves accessibility, enhances communication efficiency, and demonstrates the effectiveness of CNN models in imagebased gesture recognition applications.

Keywords : Sign language is a visual means of communication used by people with hearing and speech disabilities to express their thoughts and emotions through hand gestures, facial expressions, and body movements.

Author : SK.ANJANEYULU BABU1 , B.RAVISINGH2

Title : SIGN LANGUAGE RECOGNITION TO TEXT AND VOICE USING CNN

Volume/Issue : 2026;03(06)

Page No : 940-946

There have been significant changes in the global luxury fashion industry owing to globalization, technological development, changing lifestyles of consumers, and heightened levels of societal consciousness. Today, luxury fashion consumption not only relates to its basic purpose but is also driven by its symbolic values, including prestige, self-expression, social position, and pleasure, among others. This paper analyzes the significance of symbolic value in influencing the behavior of luxury fashion consumption by bringing together relevant theoretical concepts, scholarly studies, and market trends. The review shows that luxury products are symbols of social and psychological nature through which the consumer conveys his/her identity. Based on well-known theories like conspicuous consumption, hedonic consumption, impression management, reference groups, and signaling theory, the paper highlights the multifaceted approach towards luxury consumption behavior. Nevertheless, there are also several important issues that arise from the literature review, among which include problems with measurements, market segmentation, and increasing presence of counterfeits and masstige products, which altogether make the study of symbolic luxury consumption quite problematic. The findings from the literature review reveal that future research should focus on creating culturally adaptive instruments for measuring luxury consumption behavior, further exploring virtual luxury spaces, and implementing more stringent policies.

Keywords : Luxury fashion consumption, symbolic value, consumer behaviour, prestige, social status, identity signaling, conspicuous consumption, hedonic consumption, cultural influence, digital luxury, social media.

Author : Jagadishwar Reddy REDDYGARI

Title : Understanding the Role of Symbolic Value in Shaping Luxury Fashion Consumption Patterns

Volume/Issue : 2026;03(06)

Page No : 947-954

Financial literacy plays a crucial role in shaping individuals’ financial decisions and their ability to achieve long-term financial well-being. In recent years, the growing participation of young investors in financial markets has highlighted the importance of understanding how financial knowledge influences investment behavior and wealth creation. In the Indian context, increasing access to digital financial services, online investment platforms, and diverse financial products has created both opportunities and challenges for young investors. Against this backdrop, the present study examines the relationship between financial literacy, investment behavior, and wealth creation among young investors in India. The study adopts a quantitative research approach and is based on primary data collected from 280 young investors in India through a structured questionnaire. The research evaluates key dimensions of financial literacy, including financial knowledge, financial planning, savings behavior, risk assessment, and investment awareness. Statistical tools such as descriptive analysis, correlation, and regression analysis are employed to examine the impact of financial literacy on investment behavior and wealth creation. The findings reveal that financial literacy has a significant positive influence on investment behavior and wealth creation. Young investors with higher levels of financial literacy are more likely to engage in informed investment decisions, adopt diversified investment strategies, and participate in long-term wealthgenerating financial instruments such as mutual funds, equities, and systematic investment plans. The study further indicates that sound investment behavior serves as an important pathway through which financial literacy contributes to sustainable wealth accumulation and financial security. The study contributes to the existing literature on personal finance and investor behavior by providing empirical evidence from India. The findings offer valuable insights for policymakers, educational institutions, financial service providers, and investment advisors in developing effective financial education initiatives that enhance financial literacy and promote sustainable wealth creation among young investors.

Keywords : Financial Literacy, Wealth Creation, Investment Behavior, Young Investors, Financial Decision-Making, Personal Finance, Investment Planning, India.

Author : Kiran Shivunuri, Mayank Shukla, Dr. S. Srinivas Rao

Title : FINANCIAL LITERACY AND WEALTH CREATION AMONG YOUNG INVESTORS: AN EMPIRICAL STUDY OF INVESTMENT BEHAVIOR IN INDIA

Volume/Issue : 2026;03(06)

Page No : 955-967

Neuromarketing has emerged as an innovative field that combines principles of neuroscience, psychology, and marketing to gain deeper insights into consumer behavior. As modern markets become increasingly competitive, understanding the underlying psychological and neurological factors that influence purchasing decisions has become essential for marketers. Traditional market research techniques, such as surveys, interviews, and focus groups, often rely on self-reported information and may not fully capture the subconscious processes that shape consumer preferences and decision-making. Neuromarketing addresses this limitation by examining consumers’ neural and emotional responses to marketing stimuli, providing a more comprehensive understanding of how individuals perceive, evaluate, and respond to brands, advertisements, and products. The present study explores the relationship between neuromarketing and consumer psychology, with particular emphasis on the role of emotions, attention, memory, and perception in influencing buying behavior. The research adopts a quantitative approach and is based on primary data collected from 300 consumers through a structured questionnaire. The study investigates how neuromarketing-based marketing strategies affect consumer attitudes, brand engagement, purchase intentions, and decision-making processes. Statistical tools such as descriptive analysis, correlation analysis, and regression analysis are employed to examine the relationships among the study variables. The findings indicate that emotional engagement, sensory stimulation, and attention-driven marketing strategies significantly influence consumer responses and purchase behavior. The study further reveals that consumers are more likely to develop stronger brand associations and favorable purchasing intentions when marketing messages effectively appeal to both cognitive and emotional processes. These results highlight the growing relevance of neuromarketing in designing effective advertising campaigns, enhancing customer experiences, and building long-term brand relationships. The study contributes to the emerging body of knowledge on neuromarketing and consumer psychology by providing empirical evidence on the role of brain-based marketing strategies in shaping consumer behavior. The findings offer valuable insights for marketers, business organizations, researchers, and policymakers seeking to understand and utilize advanced consumer behavior analytics in contemporary marketing environments.

Keywords : Neuromarketing, Consumer Psychology, Consumer Behavior, Emotional Marketing, Consumer Decision-Making, Brand Engagement, Purchase Intention, Marketing Strategy

Author : Dronavalli Karthika, Naga Sai Durga Varnika Mandapati, Veerla Vinay

Title : NEUROMARKETING AND CONSUMER PSYCHOLOGY: UNDERSTANDING THE HUMAN BRAIN IN MODERN MARKETING

Volume/Issue : 2026;03(06)

Page No : 968-980

Accent recognition has emerged as an important research area in speech processing due to its wide range of applications in automatic speech recognition (ASR), speaker identification, multilingual virtual assistants, language learning systems, and human-computer interaction. Variations in pronunciation, intonation, rhythm, and phonetic patterns across different geographical regions often reduce the performance of conventional speech recognition systems. Recent advances in machine learning and deep learning have significantly improved accent recognition by automatically extracting complex acoustic and linguistic features from speech signals. This paper presents a comprehensive framework for accurate accent recognition by integrating advanced feature extraction techniques with machine learning and deep learning models. The proposed framework employs Mel-Frequency Cepstral Coefficients (MFCCs), spectrogram analysis, and audio preprocessing techniques to extract discriminative speech features. Machine learning algorithms such as Support Vector Machine (SVM) and Random Forest (RF) are compared with deep learning architectures including Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and hybrid CNN-LSTM models. Experimental evaluation demonstrates that deep learning models outperform conventional machine learning methods by achieving higher classification accuracy, robustness to speaker variability, and improved generalization across multiple accents. The proposed framework contributes to the development of intelligent speech processing systems capable of recognizing diverse accents with high reliability, thereby enhancing speech-enabled applications in multilingual and global communication environments.

Keywords : Accent Recognition, Machine Learning, Deep Learning, Automatic Speech Recognition (ASR), Mel-Frequency Cepstral Coefficients (MFCC), Convolutional Neural Network (CNN), Long ShortTerm Memory (LSTM), Speech Processing, Audio Classification, Artificial Intelligence.

Author : Dr Nazimunisa, Gali Lakshmi Pras Anna, Thalla Shiva Kumar, Mohammad Saniya, Mohammad Junaid

Title : EXPLORING MACHINE AND DEEP LEARNING METHODS FOR ACCURATE ACCENT RECOGNITION

Volume/Issue : 2026;03(06)

Page No : 981-991

Lung cancer remains one of the leading causes of cancer-related mortality worldwide, primarily due to delayed diagnosis and the lack of efficient, non-invasive screening methods. Conventional diagnostic techniques such as computed tomography (CT), positron emission tomography (PET), bronchoscopy, and tissue biopsy provide high diagnostic accuracy but are often expensive, invasive, time-consuming, and unsuitable for large-scale population screening. Recent advancements in Artificial Intelligence (AI), Machine Learning (ML), and breathomics have introduced promising alternatives by analyzing volatile organic compounds (VOCs) present in exhaled breath as potential biomarkers for early lung cancer detection. This paper proposes an AI-enhanced breath analysis framework that integrates volatile organic compound profiling, intelligent feature selection, ensemble machine learning models, and predictive analytics for accurate lung cancer diagnosis. The proposed framework employs preprocessing, VOC biomarker extraction, feature selection, ensemble classification, and explainable prediction techniques to identify high-risk patients with improved accuracy and reliability. Comparative experimental analysis demonstrates that the proposed feature-selected ensemble learning model significantly outperforms conventional machine learning classifiers in terms of accuracy, precision, recall, F1-score, and prediction efficiency while minimizing false-positive and false-negative rates. Furthermore, the proposed framework provides a non-invasive, rapid, cost-effective, and clinically interpretable solution for early lung cancer screening. The integration of Artificial Intelligence with breath biomarker analysis offers a transformative approach toward precision medicine, intelligent healthcare, and personalized cancer diagnosis by supporting clinicians with reliable decision-support systems for early intervention and improved patient outcomes.

Keywords : Lung Cancer Detection, Breath Analysis, Volatile Organic Compounds, Artificial Intelligence, Machine Learning, Ensemble Learning, Feature Selection, Explainable AI, Breathomics, Precision Medicine.

Author : Mrs. P Swapna Reddy, A Manoj Kumar, Lothumalla Poojitha, Ganji Sowmya, Dr S Venkata Achuta Rao

Title : PREDICTING LUNG CANCER WITH AI-ENHANCED BREATH ANALYSIS: FEATURE-SELECTED ENSEMBLE MODELS OF VOC BIOMARKERS

Volume/Issue : 2026;03(06)

Page No : 992-1000

Electrocardiography (ECG) is one of the most widely used non-invasive diagnostic techniques for monitoring cardiac activity and detecting cardiovascular abnormalities. With the increasing adoption of wearable health devices, Holter monitors, and remote patient monitoring systems, large volumes of longterm ECG signals are continuously generated for clinical assessment. However, these recordings are often contaminated by various types of noise, including baseline wander, muscle artifacts, motion artifacts, power-line interference, and electrode contact disturbances, which significantly degrade signal quality and reduce the accuracy of automated cardiac diagnosis. Conventional ECG noise classification methods primarily rely on handcrafted signal processing techniques and traditional machine learning algorithms, which often struggle to generalize across diverse patient populations and varying recording conditions. This paper proposes an interpretable deep learning framework for long-term ECG noise classification that integrates advanced signal preprocessing, feature extraction, deep neural networks, and Explainable Artificial Intelligence (XAI) techniques. The proposed framework employs convolutional neural networks (CNNs), recurrent neural networks (RNNs), attention mechanisms, and explainability methods such as Grad-CAM and SHAP to accurately classify different ECG noise types while providing transparent visual explanations for clinical interpretation. Experimental evaluation demonstrates that the proposed framework achieves superior classification accuracy, precision, recall, F1-score, and computational efficiency compared with conventional machine learning approaches. Furthermore, the explainable prediction mechanism enhances clinician trust by identifying the signal regions responsible for classification decisions. The proposed framework contributes to intelligent healthcare by improving ECG signal quality assessment, supporting reliable cardiac diagnosis, and enabling trustworthy AI-assisted remote patient monitoring.

Keywords : Electrocardiogram, ECG Noise Classification, Deep Learning, Explainable Artificial Intelligence, Convolutional Neural Networks, Signal Processing, Wearable Healthcare, Remote Patient Monitoring, Biomedical Signal Analysis, Healthcare Analytics.

Author : Dr G. Jawaherlalnehru, Chiramani Dhamodar, Gorige Srinath, Meesa Yogendra

Title : INTERPRETABLE AI FOR HEALTHCARE: DEEP LEARNING-BASED LONG-TERM ECG NOISE CLASSIFICATION

Volume/Issue : 2026;03(06)

Page No : 1001-1009

Passenger identification has become a critical component of modern transportation systems, particularly in railway stations, bus terminals, and other terrestrial transit hubs where large passenger volumes require secure, efficient, and real-time identity verification. Conventional identification methods such as manual ticket verification, barcode scanning, RFID cards, and biometric authentication often suffer from limitations including long processing times, human errors, identity fraud, and increased operational costs. Recent advancements in Artificial Intelligence (AI), Computer Vision, Deep Learning, and Convolutional Neural Networks (CNNs) have enabled intelligent automated passenger identification systems capable of recognizing individuals from facial images and surveillance video streams with high accuracy. This paper proposes a CNN-based automated passenger identification framework that integrates image preprocessing, facial detection, feature extraction, deep learning classification, and Explainable Artificial Intelligence (XAI) to achieve reliable real-time passenger recognition in terrestrial terminals. The proposed framework employs advanced CNN architectures, transfer learning, feature optimization, and intelligent decisionsupport mechanisms to improve identification accuracy while minimizing false recognition rates. Experimental evaluation demonstrates that the proposed system significantly outperforms conventional machine learning approaches in terms of accuracy, precision, recall, F1-score, and processing efficiency. Furthermore, the integration of Explainable AI and blockchain-enabled identity management enhances transparency, security, and traceability of passenger information. The proposed framework contributes to intelligent transportation systems by improving passenger security, operational efficiency, automated access control, and smart terminal management through trustworthy AI-assisted identity verification

Keywords : Passenger Identification, Convolutional Neural Networks, Computer Vision, Deep Learning, Facial Recognition, Intelligent Transportation Systems, Explainable Artificial Intelligence, Blockchain, Smart Terminals, Automated Surveillance.

Author : Dr G. Jawaherlalnehru, Guguloth Lavanya, Oddepally Uma, S Jeevan Kumar, Mantri Aravind Kumar

Title : CONVOLUTIONAL NEURAL NETWORKS IN MOTION: AUTOMATING PASSENGER IDENTIFICATION AT TERRESTRIAL TERMINALS

Volume/Issue : 2026;03(06)

Page No : 1010-1018

Cloud computing has become the backbone of modern digital transformation by providing scalable infrastructure, flexible computing resources, and cost-effective service delivery for enterprises, governments, and individuals. However, the rapid adoption of cloud platforms has also increased the complexity of cybersecurity threats, including malware attacks, ransomware, insider threats, distributed denial-of-service (DDoS) attacks, account hijacking, data breaches, advanced persistent threats (APTs), and zero-day vulnerabilities. Conventional cloud security mechanisms primarily depend on signature-based detection systems and static security policies, which often fail to detect sophisticated and evolving cyberattacks. Recent advancements in Machine Learning (ML), Artificial Intelligence (AI), and cyber threat intelligence have enabled intelligent cloud security systems capable of automatically identifying malicious behavior, predicting emerging threats, and supporting proactive cybersecurity decision-making. This paper presents a comprehensive study on the integration of machine learning and threat intelligence in cloud security, highlighting current trends, major challenges, and future research directions. The proposed framework combines intelligent data collection, feature engineering, machine learning-based anomaly detection, threat intelligence analysis, Explainable Artificial Intelligence (XAI), and blockchain-enabled security management to improve cyber threat detection accuracy and response efficiency. Experimental evaluation demonstrates that AI-assisted threat intelligence significantly enhances attack detection, reduces false alarms, and improves incident response compared with conventional security approaches. Furthermore, Explainable AI improves transparency in security decisions, while blockchain technology ensures secure, tamper-resistant management of security logs and threat intelligence data. The proposed framework provides an intelligent, scalable, and trustworthy solution for protecting cloud computing infrastructures against continuously evolving cyber threats

Keywords : Cloud Security, Machine Learning, Threat Intelligence, Cybersecurity, Intrusion Detection, Anomaly Detection, Explainable Artificial Intelligence, Blockchain, Cloud Computing, Intelligent Security Analytics.

Author : Mr. P. Sathish, Harshit Singal, Appanala Sai Ram Arjun, Kasarla Sai Venkat Sriram, Madikonda Vinay

Title : MACHINE LEARNING AND THREAT INTELLIGENCE IN CLOUD SECURITY: TRENDS, CHALLENGES, AND FUTURE

Volume/Issue : 2026;03(06)

Page No : 1019-1027

The design and development of the electric vehicle charging station presented in this study offer a universal solution compatible with a broad spectrum of modern EVs, emphasizing that successful real-time integration depends heavily on the strategic availability and seamless accessibility of the infrastructure within urban environments. By navigating the complexities of diverse charging standards, multi-level power delivery, and advanced control strategies, the research introduces a sophisticated "e-storage" paradigm where the grid doesn't just deliver power but actively manages and optimizes battery health through intelligent oversight. The transition from a passive power outlet to an active, rule-based modeling system demonstrates how charging behavior can be synchronized with grid demands to reduce charging times and prevent system strain. Ultimately, the findings validate the technical viability and immense potential of this suggested framework, proving that an integrated, high-efficiency charging ecosystem is not only a theoretical model but a practical necessity for the sustainable evolution of global transportation.

Keywords : Charger, Charging Station, Charging systems

Author : Dr. S.Rajender Reddy1 , Mr.G.Ranga Purushotham2 Dr.P. Parthasaradhy3 Tallapally Rohith Kumar4 , Korra Srikanth5 , Shivaneni Lohitha

Title : Design and Simulation of Improved Fast Charging Technique for Modern Electric Vehicle

Volume/Issue : 2026;03(06)

Page No : 1028-1039

The increasing penetration of photovoltaic (PV) systems into modern power networks necessitates the development of advanced control strategies that ensure efficient energy management and enhanced power quality. This paper proposes an Adaptive Fuzzy Sliding Mode Control (AFSMC)-based energy management approach for a Split Source Inverter (SSI)-based PV system. The split source inverter combines the functionalities of a conventional voltage source inverter and a DC–DC boost converter, thereby reducing component count and improving conversion efficiency. However, maintaining stable operation under fluctuating solar irradiance, load variations, and grid disturbances remains a significant challenge. The proposed AFSMC strategy integrates the robustness of Sliding Mode Control (SMC) with the adaptive reasoning capability of Fuzzy Logic Control (FLC) to regulate the DC-link voltage, improve power flow management, and mitigate power quality issues. The controller dynamically adjusts the switching control law to minimize tracking errors and suppress chattering effects associated with traditional SMC methods. MATLAB/Simulink simulations demonstrate that the proposed controller achieves superior dynamic performance, reduced total harmonic distortion (THD), improved power factor, enhanced voltage regulation, and efficient utilization of PVgenerated power compared with conventional PI and standalone SMC approaches. The results validate the effectiveness of the AFSMC strategy in enabling reliable and high-quality operation of SSI-based PV systems.

Keywords : Split Source Inverter, Photovoltaic System, Energy Management, Adaptive Fuzzy Sliding Mode Control, Power Quality Improvement, Total Harmonic Distortion, Renewable Energy.

Author : 1Mr.G. GNANESHWAR KUMAR, 2Mr.K. RAJESH BABU, 3 POLOJU RACHANA ,4UPPULA POOJITHA, 5KORRA ROHITH

Title : AN ADVANCED SPLIT-SOURCE INVERTER-BASED GRIDCONNECTED PV SYSTEM WITH INTEGRATED POWER QUALITY CONDITIONING

Volume/Issue : 2026;03(06)

Page No : 1040-1048

In recent years, the demand for wireless data acquisition and real-time electrical parameter monitoring in direct current applications has increased. However, traditional setups lack realtime telemetry; one way to improve fault detection is by using Wireless Sensor Networks (WSN), which require embedded architectures. Monitoring systems are required to accurately measure the voltage and current to calculate power. In this Project, the design and implementation of a Bluetooth-enabled embedded system for electrical data acquisition is presented, obtaining a lowlatency, high connectivity, scalable, modular, and open architecture system. The tests recorded the instantaneous voltage, current, and environmental data, resulting in highly accurate real-time telemetry and reliable fault alerting mechanism. Notably, the developed embedded system exhibited a robust wireless data transmission rate.

Keywords : Embedded Systems, Data Acquisition, Bluetooth Communication, Voltage Sensor, Current Sensor, Raspberry Pi Pico, Wireless Monitoring.

Author : D.S. Veeranna1 , Mrs.Ch. Laxmi2 , Rachakonda Rajesh Kumar3 , Vankudoth Pavan4 , Padya Prudhvi5

Title : ELECTRICAL DATA MONITORING SYSTEM USING EMBEDDED SYSTEMS

Volume/Issue : 2026;03(06)

Page No : 1049-1059

The automated flood safety system for river bridges is an essential innovation aimed at protecting public safety and infrastructure in flood-prone areas. By integrating water level sensors, microcontrollers, communication modules, and cloud storage, the system enables realtime monitoring and timely alerts during high water flow conditions. This proactive approach reduces the risk of accidents, minimizes damage to bridges, and supports disaster management efforts through remote accessibility and datadriven decision making. Despite challenges such as initial costs, maintenance needs, and communication limitations in remote areas, the benefits of continuous, automated flood detection and multi-channel alerting significantly outweigh these issues. With scalable and cost-effective technology, this system contributes to safer transportation networks and smarter urban and rural flood management. Overall, the project offers a practical and impactful solution for enhancing resilience against flood hazards on river bridges, ultimately saving lives and protecting valuable infrastructure. This comprehensive system exemplifies the promising intersection of sensor technology, IoT, and automation in addressing critical environmental and public safety challenges.

Keywords : Floods are among the most destructive natural disasters worldwide, causing substantial loss of life, property damage, and infrastructure failures.

Author : 1Dr. P. PARTHASARADHY, 2Mr. G. RANGA PURUSHOTHAM, 3 PAYYAVULA TEJA SANJAY, 4R SRINU, 5 SURYAM KUNA

Title : AUTOMATED SAFETY SYSTEM ON THE RIVER BRIDGES, FOR PUBLIC DURING FLOODS AND HIGH WATERFLOW IN THE RIVER

Volume/Issue : 2026;03(06)

Page No : 1060-1066

Efficient speed planning is crucial for the safe and comfortable navigation of autonomous vehicles in dynamic environments. This Project introduces a novel energy-efficient, jerkcontrolled speed planning approach based on quintic polynomial generation. We present a systematic methodology to determine the dynamic speed of autonomous vehicles by integrating several factors, including the relative velocity with dynamic obstacles, the curvature of the base frame and optimal selected path, road adherence, and road gradient. The direct integration of road adherence and gradient into the speed profiling approach contributes to improving vehicle safety. Comparative analysis with literature methods demonstrates the significant impact of jerk smoothness on energy efficiency. Simulations are conducted in a joint simulation between Simulink and SCANeR Studio vehicle dynamics simulator, followed by validation on a real-world dataset. Our findings elucidate the significance of the proposed planning method in enhancing safety, energy economy, driving comfort, and computational efficiency, while effectively addressing a wide range of critical situations.

Keywords : Ride comfort has recently received much attention in different driving scenarios due to its influence on the public acceptance of autonomous vehicles (AVs) and the health of passengers Ride comfort is a subjective sensation of passengers associated with the motion of vehicles in different directions.

Author : Mr.M.Suryakanth1 , Mr.A.Radha Krishna2 , Ketham Keerthana3 , Ramavath Saikumar4 , Valavoju Tharun

Title : SAFE AND ENERGY-EFFICIENT JERK-CONTROLLED SPEED PROFILING FOR ON-ROAD AUTONOMOUS VEHICLES

Volume/Issue : 2026;03(06)

Page No : 1067-1075

Unmanned Aerial Vehicles (UAVs), commonly referred to as drones, are becoming increasingly significant in various sectors due to their ability to perform tasks that are dangerous, timeconsuming, or difficult for humans to handle manually. This project focuses on the design and development of a Surveillance and Light Cargo Carrier Drone that integrates real-time monitoring capabilities with small-scale payload transportation. The system is built on a quadcopter platform powered by brushless DC motors and regulated using electronic speed controllers for stable and efficient flight. A flight controller serves as the core intelligence unit, ensuring balance, stability, and responsiveness to remote control inputs. A wireless FPV/HD camera enables live video transmission, allowing the operator to observe distant or inaccessible areas for security and inspection purposes. In addition to surveillance, the drone is equipped with a servo-actuated payload carrying mechanism, capable of delivering lightweight items such as medical supplies, emergency kits, or essential goods in areas affected by disasters, conflict, or limited accessibility. The system aims to reduce human risk, lower operational cost, and improve efficiency in field operations such as border monitoring, search and rescue, agricultural observation, and disaster response. Its modular design allows customization and scalability based on specific use-case requirements. Overall, the proposed drone offers a cost-effective, flexible, and practical aerial solution that combines real-time situational awareness with reliable light- cargo delivery capability.

Keywords : In recent years, drones have evolved from simple hobbyist gadgets into highly capable and intelligent systems that serve a wide range of professional and industrial applications.

Author : K. Rajesh Babu1 , Mr. G. Gnaneshwar Kumar2 Rudavath Eshwar3 , Mohammad Toufeeq4 , Sokkam Sampath5

Title : FALCONEYE: TACTICAL SURVEILLANCE & DELIVERY DRONE

Volume/Issue : 2026;03(06)

Page No : 1076-1084

The rapid advancement of Unmanned Aerial Vehicles (UAVs) has enabled their widespread adoption in surveillance, logistics, and emergency response applications. This project presents the design and development of “SkySentinel,” an intelligent surveillance and payload delivery drone capable of performing dual functions within a single integrated platform. The system is based on a quadcopter architecture powered by brushless DC motors and controlled using electronic speed controllers and a flight controller for stable and efficient flight operations. The drone incorporates a high-definition camera module that provides real-time video transmission, enhancing situational awareness for monitoring remote or hazardous environments. In addition to surveillance, the system includes a servo-actuated payload mechanism that enables the transportation and controlled release of lightweight materials such as medical supplies, emergency kits, and essential goods. The integration of GPS and wireless communication ensures precise navigation and real-time control. The proposed system addresses limitations of conventional methods by reducing human risk, improving response time, and increasing operational efficiency. Its modular design allows flexibility and scalability for various applications including disaster management, border security, agriculture monitoring, and industrial inspection. Overall, the system provides a cost-effective, reliable, and versatile solution that combines aerial monitoring and logistics support, contributing to modern smart surveillance and delivery systems.

Keywords : UAV, Drone, Surveillance, Payload Delivery, BLDC Motor, Flight Controller, GPS, Wireless Communication

Author : 1Mr. K. RAJESH BABU, 2Dr.P. PARTHASARADHY, 3GUNDAGONI SANJAY GOUD, 4KAMBALI PRAJWAL, 5 POLOJU CHANTI

Title : SKYSENTINEL: INTELLIGENT SURVEILLANCE AND PAYLOAD DELIVERY DRONE

Volume/Issue : 2026;03(06)

Page No : 1085-1090