Impact Factor
7.883
Call For Paper
Volume: 12 Issue 03 March 2026
Download Paper Format
Copyright Form
LICENSE
Under License of
Creative Commons Attribution-NonCommercial 4.0 International LicensVolume - 12 Issue - 2
Unveiling The Therapeutic Potential Of Couroupita Guianensis: An Overview Of Its Phytochemistry And Pharmacological Activities.
Area of research: Herbal Pharmaceutical Research
Couroupita Guianensis Aubl., Commonly Known As The Cannonball Tree, Is A Large Deciduous Tree From The Family Lecythidaceae, Celebrated For Its Rich Medicinal And Cultural Significance. In India, It Is Known As Nagalingam In Tamil And Kailashpati In Hindi. Originally Native To The Tropical Rainforests Of Central And South America, The Cannonball Tree Is Now Widely Cultivated Across India, Sri Lanka, And Southeast Asia. Almost Every Part Of The Plant Including Its Flowers, Leaves, Bark, And Fruit Is Used In Traditional Medicine To Treat Conditions Such As Wounds, Inflammation, Skin Disorders, Malaria, Toothaches, And Microbial Infections. Scientific Studies Have Shown That The Plant Contains A Rich Variety Of Bioactive Compounds, Including Terpenoids, Flavonoids, Alkaloids, Glycosides, Tannins, Phenolic Compounds, And Quinones. These Constituents Are Responsible For Several Pharmacological Effects, Such As Antioxidant, Anti-inflammatory, Antimicrobial, Wound-healing, Anticancer, And Hepatoprotective Activities. Some Key Compounds Such As α-amyrin, β-amyrin, Isatin, Quercetin And Couroupitine Play A Crucial Role In These Effects By Reducing Oxidative Stress, Suppressing Inflammation, And Triggering Apoptosis In Abnormal Cells. Despite Its Long History Of Traditional Use And Promising Pharmacological Profile, Couroupita Guianensis Remains Underexplored Scientifically. This Review Aims To Bring Together Existing Research On Its Phytochemical Composition, Ethnomedicinal Uses, And Therapeutic Potential, Highlighting Its Promise As A Valuable Source For Modern Drug Discovery And Phytopharmaceutical Development.
Author: Anju KR | Dr. Shrutika D Patil | Vedant S Kasle | Soumitra D Pethe | Mohd. Raza I Shikalgar
Read MoreAN ANALYSIS OF THE PSYCHOLOGICAL BARRIERS THAT PREVENTS EMPLOYEES FROM USING FORMAL GRIEVANCE REDRESSAL MECHANISMS AT TCS COIMBATORE
Area of research: COMMERCE
Formal Grievance Redressal Mechanisms Are Designed To Promote Fairness And Employee Well-being In Organizations. However, Many Employees Hesitate To Use These Systems Due To Psychological Barriers. This Study Examines Factors Such As Fear Of Retaliation, Lack Of Trust In Confidentiality, Emotional Stress, Low Self-confidence, Cultural Influences, And Negative Perceptions About Grievance Outcomes. Using A Descriptive Research Design And Survey Method, Primary Data Was Collected Through A Structured Questionnaire, Supported By Secondary Sources.
Author: Dr. K. Mahendran | Hema. P
Read MoreECHOSAFE SMART VOICE – DRIVEN PERSONAL SAFETY DEVICE
Area of research: Electrical And Electronics Engineering
Women’s Safety Remains A Major Issue In Today’s Society, Requiring Effective And Immediate Response Systems During Emergencies. This Project Presents A SmartPortable SOS Safety Keychain Designed To Provide Rapid Assistance When A User Is In Danger. The System Is Developed Using The ESP8266 SoC Microcontroller, Which Enables Wireless Communication And Real-time Alert Transmission.When The SOS Push Button Is Pressed, The Device Sends An Emergency Notification Along With The User’s Live Geographical Location Obtained Through The NEO-6M GPSmodule To Pre-configured Contacts. To Further Strengthen Security And Provide Evidence, The System Integrates A MAX9814 Microphone Module For Audio Recording And Includes A Buzzer For Alert Indication. The Recorded Data Can Be Stored In Memory And Accessed Remotely When Required.The Device Operates On A Rechargeable 7V Lithium-ion Battery, Ensuring Portability, Compact Design, And Low Power Consumption. Additionally, A 7-segment Display Is Incorporated For Status Indication. A Survey Conducted Within The Campus Indicated That Nearly Half Of The Students Were Unaware Of Existing SOS Safety Devices, Emphasizing The Necessity Of Implementing Such Smart Safety Solutions. The Proposed System Offers A Reliable, Portable And Efficient Approach To Enhance Women’s Personal Security Through Instant Alerting, Live Tracking, And Evidence Collection.
Author: Mrs.R. Deebika | V. Kokila | S. Maheshwari | P. Vinothini
Read MoreCollege Event Management System
Area of research: Computer Engineering
The College Event Management System Is A Web-based Application Developed Using The Flask Framework In Python To Simplify And Automate The Management Of Academic And Non-academic Events Within A College Campus. Conventional Event Management Methods Often Depend On Manual Registration Processes And Scattered Communication Channels, Which May Result In Scheduling Overlaps, Duplicate Records, And Inefficient Documentation. The Proposed System Offers A Unified Digital Platform Where Administrators Can Create And Manage Events, Students Can Complete Registrations Online, And Organizers Can Monitor Participation In Real Time. The Application Follows A Client–server Architecture And Utilizes A Relational Database To Ensure Organized And Secure Data Storage. Role-based Authentication Is Implemented To Maintain Data Security And Restrict Access According To User Responsibilities. Testing And Evaluation Indicate That The System Improves Operational Efficiency, Minimizes Paperwork, Enhances Data Accuracy, And Promotes Better Coordination Among Stakeholders. Future Enhancements May Include Integration Of Online Payment Systems And Mobile Compatibility To Further Improve Usability And Accessibility.
Author: Utkarsh Didore | Dilip Jadhav | Omkar Waghmare | Akash Bajad | Prof. Anil C. Naik | Prof. Mayur G. Unhale
Read MoreA Study On Unemployment Among Educated Youth And It's Impacts On Growing Economy In India
Area of research: Economics
Unemployment Among Educated Youth Is A Serious Problem In India Today. Even Though Many Young People Complete Higher Education Such As Graduation And Post-graduation, They Are Lunable To Find Suitable Jobs. This Situation Creates Disappointment And Stress Among Youth And Also Affects The Overall Development Of The Country. One Of The Main Reasons For This Problem Is The Mismatch Between The Skills Taught In Educational Institutions And The Skills Required By Employers. Lack Of Practical Training, Limited Job Opportunities, Slow Growth Of Industries, And Preference For Experienced Workers Also Increase Unemployment Among Educated Youth. In Addition, Population Growth And Competition For Government And Private Jobs Make The Situation Worse. Educated Unemployment Leads To Problems Such As Poverty, Frustration, Migration, And Waste Of Human Resources. This Research Highlights The Causes, Effects, And Challenges Of Unemployment Among Educated Youth In India. It Also Suggests That Improving The Quality Of Education, Providing Skill-based And Vocational Training, Promoting Entrepreneurship, And Creating More Job Opportunities Can Help Reduce This Problem. Proper Planning And Coordination Between Education And Employment Sectors Are Necessary To Use The Potential Of Educated Youth Effectively.
Author: A.Amsaveni | Dr . M. D. Chinnu
Read MoreA Study Of Mathematical Modeling Of Cancer Cell Growth Using Generalized Logistic Model
Area of research: Mathematical Modelling
Mathematical Modelling Provides An Effective Framework For Understanding The Growth Dynamics Of Cancer Cells. In This Study, Generalized Logistic Models (GLM) Is Used To Analyse Cancer Cell Growth And To Unify Several Classical Growth Models. The Exponential, Logistic, VonBertalanffy And Richards’s Models Are Discussed And Shown To Arise From Generalized Growth Assumptions Under Suitable Parameter Choices. The Formulation Of Each Model Is Presented Along With The Procedure For Obtaining Their Analytical Solutions. Using The Derived Solutions, Growth Values Are Computed At Selected Time Intervals By Solving Numerical Problems. To Ensure A Fair Comparison, The Same Initial Data Is Used For All Models. Furthermore, Pythonprogramming Is Employed To Perform Numerical Evaluations Of The Analytical Solutions, Allowing Efficient Computation And Comparison Of Growth Behaviour Across Different Models. The Results Reveal That The Exponential Growth Model Exhibits The Maximum Spreading Nature Due To The Absence Of Growth Restrictions, Making It Suitable Only For Early-stage Cancer Growth Analysis. In Contrast, GLM And Richards Models Incorporate Growth-limiting Factors And Provide More Realistic And Controlled Descriptions Of Long-term Cancer Cell Growth. This Study Highlights The Importance Of Combining Mathematical Theory With Computational Tools For Realistic Modelling And Analysis Of Cancer Cell Growth.
Author: Sivasangaran S
Read MoreA Comprehensive Survey Of Explainable Artificial Intelligence And Machine Learning Techniques For Heart Disease Diagnosis And Prediction
Area of research: Artificial Intelligence And Data Science
Cardiovascular Disorders Are Still Causing Morbidity And Mortality, Including Coronary Heart Disease, Structural Heart Disease With Congenital Heart Defects As Well As Atrial fibrillation. Such Measures Would Be Critical For Effective Early Diagnosis And Risk Stratification That Could Impact On Mortality And long-term Complications. Traditional Diagnosis Methodologies, Including Electrocardiography (ECG), Echocardiography And Clinical Risk Scoring Systems, Are Subject To The Experience Of Clinicians With The Underpinning Knowledge That Human Expert May Not Be Sufficient To Model Complex Nonlinear Interactions As They Exist Between Many of The Aforementioned Variables. In Recent Years, Artificial Intelligence (AI), And in Specific Machine Learning (ML), Deep Learning (DL) And Explainable AI (XAI) Have Shown Promising Results In Providing Diagnosis And Prognosis Of The Pathologies Of Cardiovascular Diseases. Ensemble Learning And Hybrid Optimization Methods, as Well As ECG-based Deep Learning Models Provided High-predictive Performance. In Addition, Explainable Systems Based On SHAP and LIME Increase Interpretability And Clinical Trust. Nevertheless, Several challenges Must Be Addressed Such As Data Imbalance, Poor Generalization Ability, Little Multi-center Validation And Non-transparency. This Review Offers An Extensive Overview Of Existing AI Approaches For Predicting Heartdisease Covering Their Techniques, datasets, Performance Metrics, Comparative Studies, Challenges And Future Work Needed For Enabling Clinically Commercialized AI Models.
Author: M. Dhinesh Kumar | S.Malolan | R.Sarveshwaran | J.Barwesh | A.Sivaramakrishnan
Read MoreMalware Behavioural Hash (MBH): An Entropy-Driven Digital Forensic Framework For Large-Scale Malware Attribution
Area of research: Biochemistry And Forensic Science
The Increasing Sophistication Of Polymorphic And Obfuscated Malware Has Significantly Weakened Traditional Static Hash-based Attribution Mechanisms In Digital Forensic Investigations. Minor Code Mutations, Packing Techniques, And Structural Transformations Render Cryptographic And Fuzzy Hashes Ineffective For Evidentiary Correlation. This Paper Proposes A Novel Entropy-driven Malware Behavioural Hash (MBH) Framework Designed Specifically For Digital Forensic Investigation And Large-scale Attribution. The Proposed Model Integrates Forensic Evidence Acquisition, Behavioral Artifact Extraction, Capability Vectorisation, Entropy Profiling, Dimensionality Reduction, And Locality-sensitive Hashing To Produce A Mutation-resilient Behavioural Fingerprint. Unlike Conventional Binary Hashes, MBH Preserves Semantic Behavioural Similarity While Enabling Scalable Cross-case Correlation, Campaign Attribution, And Courtroom Defensibility. Experimental Modelling Demonstrates That The Entropy-guided Behavioural Compression Significantly Enhances Attribution Confidence While Reducing Storage And Computational Overhead. The Framework Contributes A Standardised Forensic Methodology For Behavioural Malware Compression And Evidentiary Linkage In Large-scale Investigations.
Author: Dr. Kiran Dodiya | Dr. Parvesh Sharma | Dr. Kapil Kumar
Read MoreImmersive Augmented Reality Automotive Showroom With Real-Time Consumer Behavioral Analytics
Area of research: Artificial Intelligence And Data Science
The Automobile Retail Industry Is In A Critical Phase Re- Garding The “usability Gap” In Its Digital Transformation. Mo- Bile Applications—while Essential For Modern Business—suffer Significantly From “Information Architecture” Flaws, Where The User Is Faced With An Overwhelming Array Of Complex Text-based Specifications. This “content Overload” Inhibits The Process Of Decision-making For High-involvement Purchases Like Vehicles. In Addition, Although Digital Platforms Excel At Transactions, They Tend To Fail In Replicating The Personal Engagement Of A Physical Showroom. To Overcome These Limitations, This Project Proposes The Concept Of An “Immersive Augmented Reality Automotive Showroom.” The Idea Centers On Utilizing Augmented Reality (AR) To Replace Static 2D Catalogs With Interactive 3D Digital Twins, Offering Users The Ability To Personally View And Cus- Tomize Vehicles In Their Physical Environment. Most Impor- Tantly, It Includes A Real-Time Behavioral Analytics Module. Recognizing “Perceived Personalization” As A Strong Predictor Of Customer Retention, The Module Measures User Interaction Metrics—such As Dwell Time And Color Preference—to Ini- Tiate Intelligent, Rule-based Recommendations. Furthermore, Advancements In Vision-based Tracking Confirm The Technical Viability Of Markerless AR For Stable Product Visualization. The Project Aligns With Future Research Directions, Combining Immersive Visualization With Data-driven Business Intelligence To Create A Next-generation Retail Ecosystem.
Author: S.Yogeshwaran | R.Sarathi | P.Sabivarman | V.Yashwant | N.Thamizhmozhi
Read MoreCyber Intrusion Detection Using Machine Learning Techniques
Area of research: Detecting Network Anomalies
Cyber Intrusions Are Becoming Increasingly Complex And Sophisticated, Making Them Difficult To Detect Using Conventional Rule-based And Signature-driven Security Mechanisms. The Rapid Growth Of Network Traffic And Evolving Attack Patterns Demand Intelligent, Adaptive, And Real-time Intrusion Detection Solutions. This Project Proposes A Real-time Intrusion Detection System Based On An Ensemble Learning Framework That Integrates Random Forest, XGBoost, And Deep Neural Network Models To Enhance Detection Accuracy And Robustness. Live Network Traffic Is Continuously Captured And Analyzed At Fixed Intervals To Enable Timely Identification Of Malicious Activities. Meaningful Network Features Are Extracted From The Traffic Data And Processed In Parallel By All Three Learning Models, Allowing The System To Leverage The Strengths Of Both Machine Learning And Deep Learning Approaches. A Stacking-based Meta-classifier Is Employed To Intelligently Combine The Individual Model Predictions, Thereby Reducing False Positives And Improving Overall Classification Performance. The Proposed System Effectively Classifies Network Traffic As Either Normal Or Intrusive And Further Identifies The Specific Category Of Cyber-attacks. In Addition, Real-time Alerts And Detailed Log Reports Are Generated To Facilitate Rapid Response And Incident Analysis. Experimental Evaluation Demonstrates That Theproposed Ensemble-based Intrusion Detection System Achieves Improved Accuracy, Reliability, And Practical Applicability, Making It Suitable For Deployment In Real-world Network Security Environments.
Author: Ramya. M | Sasikala.R
Read MoreA Survey On Machine Learning And Deep Learning Approaches For Credit Card Fraud Detection
Area of research: Artificial Intelligence And Data Science
Digital Payment Systems Have Become A Vital Part Of Daily Life, With Credit Cards Being Widely Used For Both Online And Offline Transctions.Banks, Retailers, And Clients Have All Experienced Large Financial Losses Because Of The Sharp Increase In Credit Card Fraud Brought On By The Growing Use Of Credit Cards. The Highly Unbalanced Nature Of Transaction Data, Where Fraudulent Activities Are Rare And Frequently Concealed Among Legitimate Transactions, Makes It Difficult To Identify Fraudulent Transactions. Furthermore, Fraud Patterns Are Always Changing, Requiring Quick And Accurate Detection Techniques.Recent Developments In Deep Learning And Machine Learning Have Shown Tremendous Potential In Detecting Complex And Hidden Trends In Transaction Data. This Survey Examines Popular Methods For Detecting Credit Card Fraud, Such As Machine Learning, Deep Learning, And Hybrid Approaches. It Focuses On Techniques Like Multi-layer Perceptrons, Autoencoders, Convolutional Neural Networks, Attention Mechanisms, And Ensemble Learning Models.
Author: A.Keerthi | P. Devalekka | M.Sahana | Dr R.Punithavathi
Read MoreAI Powered Content Moderation And Alert System
Area of research: Artificial Intelligence And Data Science
Social Media Platforms Such As Twitter (now X) Have Become Primary Channels For Real-time Information Exchange, En- Abling Rapid Dissemination Of News, Opinions, And Public Discourse. However, This Rapid Growth Has Also Led To A Significant Rise In Spam, Misinformation, Abusive Language, And Malicious Content, Which Negatively Impact User Experience And Platform Credibility. Manual Moderation Methods Are No Longer Effective Due To The Massive Volume And Velocity Of Incoming Tweets, Making Automated Content Moderation Systems Essential. This Survey Examines Existing Machine Learning, Deep Learning, And Transformer-based Techniques For De- Tecting Spam And Harmful Content On Twitter. It Begins With Tradi- Tional Text Classification Approaches And Progresses Toward Advanced Transformer Models That Provide Improved Semantic Understanding, Such As Sentence-BERT (SBERT). Particular Emphasis Is Placed On Hybrid Deep Learning Architectures That Combine SBERT-based Semantic Embeddings With Convolutional Neural Networks (CNN) And Long Short-Term Memory (LSTM) Networks. These Hybrid Models Aim To Capture Both Local Textual Patterns And Long-range Contextual Dependencies Present In Tweet Streams. The Survey Also Highlights The Importance Of Severity-based Content Classification, Where Detected Content Is Categorized According To Risk Levels To Support Real- Time Alerts And Administrative Monitoring. A Comparative Analysis Of Existing Approaches Reveals Performance Limitations Related To Scalability, Generalization, And Real-time Applicability. While Hybrid Deep Learning Models Demonstrate Promising Results In Multi-class Classification Tasks, Several Research Challenges Remain Unresolved. The Study Concludes By Identifying Future Directions Toward Developing Scalable, Accurate, And Practical Twitter Content Moderation Systems Capable Of Adapting To Evolving Online Behaviors.
Author: Arunthathi R | Avanthika D | Kailash Nagappan S | Surya P | Mrs. B. Priyanka | Mrs. C. Sangeetha
Read MoreArtificial Intelligence–Driven Approaches For Liver Disease Diagnosis And Prediction: A Comprehensive Survey
Area of research: Artificial Intelligence And Data Science
Liver Diseases, Including Liver Cirrhosis And Cholangiocarcinoma, Are The Composites Formed In The Binding Process Of Buried Solidic aggregates Into Light And Porous Preforms. Epidemiology Analyses Suggest Increasing Disease Burden And long-term Trends In Progression Internationally. Early Diagnosis Is Essential, But The Current Diagnostic Methods, Such As Biopsy And Imaging Interpretation, Are Invasive, Expensive, And Subjective To Inter-observer Variability. Recent Developments In Artificial Intelligence (AI) And Specifically The Subfield Of Machine Learning (ML), Including Deep Learning (DL), Have Led To Automated Data-driven Systems For Better Diagnostic Accuracy And Prognosis Prediction Of Diseases. The Genomic Modeling Based On LightGBM Has A Good Performance To Diagnose cholangiocarcinoma, And Ensemble Learning Methods Can Stabilize Prediction For Structured Clinical Datasets. Very Recently, Methods Based On Deep Learning Networks That Utilize EfficientNet-B7 And Dual Attention Mechanisms Have Attained High Performance For Fibrosis Staging. Additionally, Explainable AI (XAI) Frameworks Like XAIHO Advance Interpretability And Clinical Trust, Which Is Consistent With General Healthcare AI Transparency Principles. However, The Data Imbalance, Overfitting, and Lack Of Interpretability Problems Remain. In This Review, A Comprehensive Collection And Synthesis Of The State-of-the-art AI-based Approaches Is Summarized, And Methodological Trends Are reviewed Alongside Future Research Topics Such As Multimodal Fusion Or The Development Of Explainable, Clinically Validated AI Systems.
Author: M.S.Mahavarshini | S.Abarna | S.Rithika Sri | M.Tamilselvi | A.Sivaramakrishnan
Read MoreAdvanced Materials For Environmental Remediation: Metal-Organic Frameworks (MOFs) And Emerging PFAS Destruction Technologies
Area of research: Pharmaceutical Chemistry
Per- And Polyfluoroalkyl Substances (PFAS) Constitute A Large And Chemically Diverse Group Of Anthropogenic Contaminants That Have Attracted Global Concern Due To Their Extreme Environmental Persistence, Bioaccumulative Behavior, And Adverse Health Effects. The Remarkable Stability Of The Carbon–fluorine Bond Renders PFAS Highly Resistant To Conventional Biological, Chemical, And Physical Treatment Processes, Necessitating The Development Of Advanced Remediation Technologies Capable Of Both Effective Removal And Complete Destruction. In Recent Years, Metal–organic Frameworks (MOFs) Have Emerged As A Highly Promising Class Of Advanced Materials For Environmental Remediation Owing To Their Exceptional Porosity, Tunable Surface Chemistry, Modular Structural Design, And Multifunctional Capabilities. This Review Critically Examines The Role Of MOFs In PFAS Remediation, With A Particular Emphasis On Adsorption Mechanisms, Material Design Strategies, And Catalytic And Photocatalytic Degradation Pathways. In Parallel, Emerging PFAS Destruction Technologies—including Electrochemical Oxidation, Advanced Oxidation Processes, Thermal Treatment, And Hybrid Material Systems—are Comprehensively Evaluated. Key Structure, Property, Performance Relationships Governing PFAS Interactions With MOFs Are Discussed, Alongside The Challenges Associated With Material Stability, Regeneration, Scalability, And Real-world Deployment. Finally, Future Research Directions Are Proposed, Highlighting The Integration Of MOFs With Advanced Oxidation Technologies, Computational Materials Design, And Systems-level Engineering Approaches Aimed At Achieving Sustainable, Cost-effective, And Complete PFAS Mineralization.
Author: Dr. Prachi Kanawade | Rohini Bairagi
Read MoreIoT-Enabled Smart Library Control System With Concurrent NFC Tag Monitoring
Area of research: Internet Of Things (IoT) / Artificial Intelligence And Data Science
The NFC Library Management System Is An Innovative And Efficient Solution Designed To Streamline Library Operations By Leveraging NFC (Near Field Communication) Technology. The System Focuses On Two Primary Functionalities: Attendance Tracking And Book Borrowing Management, Making Library Interactions Seamless And Automated. When Students Scan Their NFC Tags, Their Attendance Is Automatically Recorded In The System, Ensuring Accurate Tracking By Avoiding Duplicate Entries For The Same Day. Additionally, The System Maintains A Count Of Unique Attendance Days For Each Student. For Book Management, Students Can Borrow Or Return Books By Scanning NFC Tags Associated With Both Their Account And The Book. The System Records Borrow Dates, Calculates Due Dates, And Dynamically Manages Fines For Overdue Returns. The Backend Is Developed Using Node.js And Express.js, With MongoDB Serving As The Database. The Frontend, Built Using React.js, Provides A User- Friendly Interface To Monitor Attendance And Manage Library Records. Integration With Arduino Uno R4 WiFi Enables Real- Time NFC Data Transmission To The Backend. Furthermore, An SMS Notification Feature Is Implemented Using Twilio API To Alert Students About Overdue Books, Accumulated Fines, And Upcoming Due Dates. This Project Aims To Replace Traditional, Manual Library Management Processes With An Automated System That Reduces Errors, Enhances Efficiency, And Improves The Overall User Experience.
Author: Dr.S.Vijayaragavan | Dharun Prakash J A | Vetrikanth G | Thiruselvan G
Read MoreA Comprehensive Survey On AI-Powered Public Scheme Eligibility Engines And Guidance Assistance Systems
Area of research: Computer Science And Engineering
The Government Welfare Programs Are Intended To Ensure Inclusive Growth, Social Security, And Economic Stability. However, Despite The Existence Of Many Welfare Programs, A Large Number Of Eligible Beneficiaries Are Not Able To Avail Themselves Of These Benefits Due To A Lack Of Awareness And Complex Eligibility Criteria. The Recent Advancements In Artificial Intelligence (AI) And Deep Learning (DL) Technologies Have Made Intelligent Automation Possible In The Governance And Delivery Of Public Services. This Survey Work Provides A Comprehensive Review Of AI- Based Public Scheme Eligibility Engines And Guidance Assistance Systems. This Paper Examines The Existing Rule- Based, Machine Learning, Deep Learning, And Natural Language Processing (NLP) Techniques Used For The Identification And Recommendation Of Welfare Schemes. The Paper Also Points Out The Research Gaps In Terms Of Personalization, Scalability, Inclusivity, And Privacy. The Survey Work Provides A Strong Motivation For The Development Of Integrated Platforms Like SchemeSense, Which Are Intended To Enhance Welfare Accessibility Through Intelligent Eligibility Prediction And User-centric Guidance.
Author: Dheenadayalan S | Kavin P | Kishore M | Pragadeeshwaran C | Santhiya D
Read MoreA Deep Learning Based Privacy Preservation Mechanism For IoT And IoMT Applications
Area of research: Information Technology
Batch Processing In Deep Learning Has Been Explored Extensively To Secure IoMT Networks. Devices Such As Multimedia Sensor Nodes (MSNs) In The IoMT Are Able To Produce Both Multimedia And Non-multimedia Data. The Generated Data Are Sent From A Base Station (BS) To A Cloud Server. However, It's Conceivable That The BS And Cloud Server's Internet Connection Will Be Temporarily Unavailable. The MSNs Are Unable To Store The Acquired Data For A Prolonged Period Of Time Due To The Restricted Computational Capacity. In This Case, MSN Data Can Be Collected By Mobile Devices And Uploaded To A Cloud Server. However, This Data Collection Could Raise Privacy Concerns, Such As Disclosing The Identity And Whereabouts Of MSN Users. Thus, When Collecting And Analyzing Such Sporadic Data From MSNs, It Becomes Vital To Address The Issue Of Data Privacy. The Article Reviews Earlier Research In The Field Of Privacy-preserving Architecture For Certain IoMT Applications. This Paper Presents A Data Collection Mechanism And Neural Batch Processing Approach For Security Of IoMT Applications. It Has Been Shown That The Proposed Work Attains Better Performance Compared To Existing Baseline Techniques.
Author: Neelima Singh
Read MoreDesigning Proactive Security For Web 3.0 And IoT Networks Using Window Based SLM Algorithm
Area of research: Information Technology
Web 3.0 Shifts Control From Centralized Cloud Servers Toward Distributed Edge Nodes, Blockchain Miners/validators, And Peer-to-peer Communication. Many Of These Nodes Rely On Low-power Radios And Operate In Highly Dynamic Environments. High PAPR Stresses Their Power Amplifiers, Causing Energy Waste, Reduced Hardware Lifespan, And Degraded Signal Integrity. PAPR Reduction Techniques Such As Clipping, Selective Mapping, And Tone Reservation Ensure That Edge Devices Handle OFDM Waveforms Efficiently, Allowing Decentralized Nodes To Participate Reliably In Consensus Protocols And Data Exchange Without Frequent Downtime Or Excessive Energy Consumption. One Of The Major Challenges That Multiplexed Data Suffers From Is High Value Of Peak To Average Power Ratio (PAPR). This Causes High Bit Error Rates And Reduced Quality Of Service. The Proposed Work Uses A Modified Selective Mapping Technique And Attains Lower PAPR Compared To Previously Existing Work, Thereby Increasing The Security Of IoT Networks
Author: Anil Kumar Yadav | Prof. Pawan Panchole
Read MoreTHE RELATIONSHIP BETWEEN BODY IMAGE DISSATISFACTION AND SELF ESTEEM AMONG YOUNG FEMALE ADULTS
Area of research: PSYCHOLOGY
Body Image Dissatisfaction And Self-esteem Are Critical Psychological Factors Affecting Young Women, Particularly In Societies Preoccupied With Weight And Body Shape. While Previous Research Has Extensively Documented These Relationships In Adolescents And Children, Understanding Their Association Among Young Female Adults Remains Important. This Study Examined The Relationship Between Body Image Dissatisfaction And Self-esteem Among Young Female Adults Aged 18-35 Years. A Correlational Research Design Was Employed With 100 Young Female Adults From Tamil Nadu, India, Selected Through Snowball Sampling. Data Were Collected Via Online Survey Using The Body Shape Questionnaire (BSQ-16B) To Assess Body Image Dissatisfaction And The Rosenberg Self-Esteem Scale To Measure Self-esteem. Pearson's Product-moment Correlation Was Used For Statistical Analysis.The Analysis Revealed No Significant Relationship Between Body Image Dissatisfaction And Self-esteem Among Young Female Adults (r = -0.141,p> .05). The Correlation Coefficient Indicated That Body Image Concerns Were Not Significantly Associated With Self-esteem Levels In This Population.Contrary To Findings In Adolescent Populations, This Study Found That Body Image Dissatisfaction And Self-esteem Are Not Significantly Related Among Young Female Adults. These Findings Suggest That The Relationship Between These Variables May Differ Across Developmental Stages, With Self-esteem In Young Adulthood Potentially Influenced By Factors Beyond Body Image Concerns.
Author: Athiya Fathima
Read MoreLUNG TUMOUR SEGMENTATION USING CONVOLUTIONAL NEURAL NETWORKS IN MRI IMAGES
Area of research: CONVOLUTIONAL NEURAL NETWORK
Lung Cancer Is A Serious Disease Occurring In Human Being. Medical Treatment Process Mainly Depends On Cancer Types And Its Location. It Is Possible To Save Many Precious Human Lives By Detecting Cancer Cells As Early As Possible. Developing An Automated Tool Is Essential To Detecting Malignant States At The Earliest Possible Stage Lung-Retina Net. The Accuracy Of Prediction Has Always Been A Challenge, Despite The Many Algorithms Proposed In The Past By Many Researchers. Using CNN Neural Networks, This Study Proposes A Methodology To Detect Abnormal Lung Tissue Growth A Multi-scale Feature Fusion-based Module. In Order To Achieve Great Accuracy, A Tool With A Higher Probability Of Detection Is Taken Into Account.. In Order To Overcome This Problem, CNN And RCNN Deep Learning Algorithms Have Been Proposed To Detect Classifications. Both The Region Proposal Network And The Classifier Network Use The Fused Lung-Retina Net’s Architecture As Their Base Layer. The Algorithm Achieves A Precision Of 98% In Detection And Classification. Based On Confusion Matrix Computation And Classification Accuracy Results, A Quantitative Analysis Of The Proposed Network Has Been Conducted.
Author: Sneha M | Ragavi K | Kalaiyarasan K
Read MoreA NOVEL APPROACH TO DETECT AND PROTECT THE FARM AND SUITABLE FRAMEWORK USING IOT BASED
Area of research: Computer Science And Engineering
Human – Wildlife Conflicts Arising From Habitat Encroachment And Deforestation Have Led To An Alarming Increase In Crop Raiding, Causing Substantial Losses To Farmers And Posing Risks To Human Safety. Conventional Methods, Ranging From Lethal Measures To Non-lethal Deterrents, Have Proven Insufficient, Often Leading To Environmental, High Costs, And Limited Effectiveness. In Response To These Challenges, This Project Proposes Novel Integrated Wildlife Management System That Combines Computer Vision, Leveraging Temporal Convolutional Networks (TCN), For Precise Animal Species Detection And Recognition, With A Targeted Ultrasound Emission Technique For Species -specific Repelling. The System, Driven By Edge Computing, Ensures Real-time Responsiveness To Mitigate Crop Raiding. The Workflow Commences With The Activation Of The Camera By The Edge Computing Device, Triggering The Deployment Of An Advanced Animal Intrusion Detection Model. By Leveraging Cutting-edge Technology, The Proposed Solution Seeks To Strike A Balance Between Protecting Crops And Minimizing Environmental Impact. This Project Contributes To The Ongoing Discourse On Human-wildlife Conflict Resolution And Highlights The Potential Of Technology-driven Solutions In Fostering Coexistence Between Agriculture And Biodiversity.
Author: S. Thirisha | G. Narmatha | K. Kalaiyarasan
Read MoreDesign, Synthesis, And In Vitro Cytotoxic Investigations Of Several New Arylidene-Hydrazinyl-Thiazoles As Anticancer And Apoptosis-Inducing Substances
Area of research: Pharmacy
One Of The Biggest Challenges Facing Modern Healthcare Is Cancer, A Complex And Pervasive Group Of Diseases Characterised By Unchecked Cell Proliferation And The Potential For Metastasis. Cancer Is The Second Most Common Cause Of Death Worldwide, With A Wide Range Of Malignancies Displaying Distinct Biological Characteristics And A Significant Impact On People, Families, And Societies.1, 2 Even Though Traditional Therapies Like Radiation, Chemotherapy, And Surgery Have Frequently Increased Survival And Brought About Remission, Their Effectiveness Is Frequently Undermined By Serious Side Effects, Requiring A Careful Balancing Act Between The Advantages Of Treatment And The Welfare Of The Patient. With The Advent Of Precision Medicine, Immunotherapies, And Targeted Medicines, The Field Of Cancer Treatment Has Changed Dramatically In Recent Years.
Author: Sweta Raosaheb Katore | Dr Prachi Kanawade
Read MoreEXPERIMENTAL STUDY ON ENGINEERING PROPERTIES OF SUBGRADE SOIL STABILIZED BY RBI 81 ALONG WITH COIR FIBER
Area of research: Civil Engineering
Subgrade Soil Failure Due To Insufficient Strength, Weak Bearing Capacity, Excessive Deformation And Desiccation Cracking Of Problematic Soils Is Commonly Observed On The Road Network, And This Leads To Huge Expenditure In The Maintenance And Repair Of Highway Projects Every Year. It Is Necessary To Reduce These Engineering Problems And Economic Losses Through Environmentally And Economically Friendly Methods. Previous Studies Have Shown That Randomly Distributed Fibers Can Significantly Improve Various Soil Properties. However, There Is A Lack Of Comprehensive Study On The Engineering Properties Of Fiber Reinforced High Plastic Clay. Also, Limited Mechanical Models Have Been Proposed For Predicting The Shear Strength Behaviour Of Fiber Reinforced Clay. In Order To Investigate These Problems, A Series Of Laboratory Investigations Including Compaction, Bearing Capacity, One-dimensional Consolidation, Linear Shrinkage, Desiccation Cracking, Direct Tensile Strength, Compression Tests Should Be Conducted On Unreinforced And Coir Fiber Reinforced Clay. For This Study, The Soil Samples Were Prepared With Different Proportions Of RBI Grade-81 I.e. (2%, 4%, 6% And 8% Of Soil) Respectively. After That The Coir Fibers In Different Ratio I.e. 0.5%, 1%, 1.5% And 2% Respectively Will Be Added To The Sample Containing Suitable Content Of RBI Grade-81. Then OMC, MDD And CBR Values Evaluated For These Sample.
Author: Deepnarayan Tiwari | Prof. Deepak Garg
Read MorePerformance Evaluation Of Hybrid Machine Learning Models For Credit Card Fraud Detection
Area of research: Machine Learning
Credit Card Fraud Cares With The Illegal Use Of Master Card Information For Purchases. Credit Card Transactions Are Often Accomplished Either Physically Or Digitally. In The Manual Transactions, The Credit Card Is Included During The Transactions. In Digital Transactions, This Will Happen Over The Phone Or The Web. Cardholders Might Be Providing Their Card Number, Expiry Date, And The Verification Of The Card Number Through Telephone Or Website. Billions Of Dollars Are Lost Thanks To Master Card Fraud Per Annum. Machine Learning Techniques Are Wont To Detect Master Card Fraud. Standard Models Are First Used. Then, Hybrid Methods Which Use Random Forest And Xgboost Segmentation And Popular Voting Method Are Applied. Then, A Real-world Master Card Data Set From A Financial Organization Is Analysed. In Addition, Noise Is Added To The Info Samples To Further Assess The Robustness Of The Algorithms. Here Random Forest Segmentation And Xgboost Algorithm Will Give The 94% Percent Accuracy.