Volume - 12 Issue - 7

Area of research: Information Technology

Machine Learning Has Revolutionized Churn Prediction, Enabling Organizations To Anticipate And Mitigate Risks Effectively. By Leveraging Historical Data And Advanced Algorithms, Businesses Can Identify At-risk Customers Or Employees And Take Proactive Measures To Retain Them As Markets Become Increasingly Competitive, Retaining Existing Customers Has Proven To Be More Cost-effective Than Acquiring New Ones. In This Context, Machine Learning (ML) Has Emerged As A Powerful Tool For Analyzing Customer Behavior And Predicting Churn With High Accuracy. By Leveraging Vast Datasets And Sophisticated Algorithms, Businesses Can Proactively Identify At-risk Customers And Take Targeted Actions To Retain Them. The Success Of Churn Prediction Largely Depends On The Quality And Relevance Of Input Features. Important Features Include Customer Demographics, Transaction Frequency, Service Usage Patterns, Complaint Records, And Engagement Metrics. Feature Engineering, Which Involves Creating New Features Or Transforming Existing Ones, Is A Critical Step In Improving Model Performance This Paper Presents A Comprehensive Survey Of Statistical Models For Forecasting Churn Rates Along With Associated Challenges That The Sector Faces.

Author: Ritu Yadav | Prof. Pradeep Sharma

Area of research: Information Technology

With Increasing Number Of Cellular Network Users, Large Data Being Generated And Limited Bandwidth Available For Systems, Efficient Multiplexing Techniques Are Needed That Use The Available Bandwidth Efficiently For IoT And Web 3.0 Systems. It Is Widely Used In Cellular And Internet Of Things (IoT) Based Applications. One Of The Major Challenges That IoT Suffers From Is High Value Of Peak To Average Power Ratio (PAPR), Which Reduces Its Security. High PAPR Causes High Level Of Perceptibility And Low Security. Hence It Is Necessary To Reduce The PAPR Of The OFDM Systems. Several Techniques Have Been Employed So Far For The Reduction Of PAPR In IoT Systems. This Paper Presents A Review On The Most Common PAPR Reduction Techniques For OFDM Systems.

Author: Deepshikha Anijwal | Dr. Ruchika Pachori

Area of research: Management Studies

Credit Card Companies Must Be Able To Identify Fraudulent Credit Card Transactions So That Clients Are Not Charged For Items They Did Not Purchase. Previously, Many Machine Learning Approaches And Classifiers Were Used To Detect Fraudulent Transactions. However, Because Fraud Patterns Are Always Changing, It Is Becoming Increasingly Vital To Investigate New Frauds And Develop The Model Based On The New Patterns. The Purpose Of This Research Is To Create A Machine Learning Classifier That Not Only Detects Fraud But Also Detects Legitimate Transactions. As A Result, The Model Should Have Excellent Accuracy, Precision, Recall, And F1-score. As A Result, We Began With A Large Dataset In This Study And Used Four Machine Learning Classifiers: Support Vector Machine (SVM), Decision Tree, Naïve Bayes, And Random Forest. The Random Forest Classifier Scored 99.96% Overall Accuracy With The Best Precision, Recall, F1- Score, And Matthew’s Correlation Coefficient In The Experiments.

Author: Kabir S M

Area of research: Computer Science

Chronic Health Risks Have Risen Among Young Individuals Due To Several Factors Such As Sedentary Lifestyle, Poor Eating Habits, Sleep Irregularities, Environmental Pollution, Workplace Stress Etc. The Problem Seems To Be More Menacing In The Near Future. One Possible Solution Is Thus To Design Health Risk Prediction Systems Which Can Evaluated Some Critical Features Of Parameters Of The Individual And Then Be Able To Predict Possible Health Risks. As The Data Shows Large Divergences In Nature With Non-correlated Patterns, Hence Choice Of Machine Learning Based Methods Becomes Inevitable To Design Systems Which Can Analyze The Critical Factors Or Features Of The Data And Predict Possible Risks. This Paper Presents An Ensemble Approach For Health Risk Prediction Based On The Steepest Descent Algorithm And Decision Trees. It Is Observed That The Proposed Work Attains A Classification Accuracy Of 93.72% Which Is Comparatively Higher Than Baseline Techniques.

Author: Saroj Tekam | Prof. Pawan Panchole

Area of research: Computer Science

Data Science And Machine Learning Are Being Used Extensively For Business Analytics. One Of The Major Applications Happens To Be Estimating Churn And Attrition Rates. In Today’s Competitive Market Landscape, Retaining Customers Is As Crucial As Acquiring New Ones. Churn Rate, Which Measures The Proportion Of Customers Who Discontinue Their Relationship With A Business Over A Specific Period, Is A Critical Metric For Companies Across Industries. Forecasting Churn Enables Businesses To Proactively Address Customer Dissatisfaction And Refine Their Strategies To Retain Valuable Clients. By Understanding The Likelihood Of Churn, Companies Can Make Informed Decisions To Sustain Growth And Profitability. The Proposed Approach Combines Swarm Intelligence And Neural Networks To Forecast Churn Rates. The Results Clearly Indicate That The Proposed Approach Outperforms Existing Baseline Approaches In Terms Of Forecasting Accuracy.

Author: Mahak Mansuri | Prof. Pawan Panchole

Area of research: Computer Science

Proactive Physical Layer Security Has Evolved With The Emergence Of Web 3.0 Which 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. One Of The Most Pressing Challenges Is To Implement Proactive Security Through Peak To Average Power Ration (PAPR) Reduction. 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 PAPR Which Make Data Transmission Perceptible. The Proposed Work Uses A Neural Selective Mapping (N-SLM) Technique And Attains Lower PAPR Compared To Previously Existing Work, Thereby Increasing The Security Of Distributed Wireless Networks.

Author: Nikita Paliwal | Dr. Neha Jain

Area of research: Computer Science

Machine Learning And Deep Learning Models Are Being Extensively Used At The Backend Of Forecasting Crypto Prices. Many Factors, Including Changes In Regulation, Public Opinion On Social Media, Investor Actions, And Overall Global Economic Trends, Contribute To The High Degree Of Volatility In The Cryptocurrency Market. Predicting The Future Value Of Cryptocurrencies With Any Degree Of Accuracy Has Emerged As A Top Concern For Academics, Traders, And Investors Due To The Inherent Uncertainty Of The Market. Machine Learning (ML) Provides Excellent Methods For Evaluating Large Volumes Of Real-time And Historical Data To Forecast Price Changes In The Future. ML Models Range From Simple Statistical Methods To Intricate Deep Learning Architectures. The Proposed Work Employs An Optimized Second Order Regularization Based Back Propagation Algorithm Along With The Data Pre-processing Using The Discrete Wavelet Transform (DWT) For Crypto Price Prediction. It Has Been Shown That The Proposed System Attains Lesser Mean Square Percentage Error Compared To Previously Existing Technique.

Author: Ayush Pal | Dr. Neha Jain

Area of research: Computer Science

Of Late, Big Data And Big Data Analytics Has Fund Applications In Diverse Fields. Social Media And Allied Applications Is One Such Domain For Research, Where Artificial Intelligence Has Shown Unprecedented Impact. In This Paper A Mechanism Has Been Proposed Which Can Classify Text Data Into Classes Of Different Sentiments. Data In The Form Of Tweets Has Been Used In This Case. Pre-processing Of Raw Data Has Been Done Prior To Using It To Train A Neural Network. A Neural Network Is Then Trained Using The Categories Of The Data Which Are Tweets That Correspond To Happy, Neutral And Sad Moods Of The Twitter Users. The Bayesian Deep Learning Model With Regularization Algorithm Has Been Used For Training The Artificial Neural Network. It Has Been Observed That This Proposed Technique Achieves A Significantly Higher Accuracy Compared To Existing Work In The Domain.

Author: Vikas Balhon | Dr. Neha Jain

Area of research: Computer Science

The Transition Towards Intelligent Traffic Systems (ITS) Is Inevitable In Future. Accurate Travel Time Estimation Is Vital For The Effectiveness Of Modern Public Transportation Systems. It Plays A Central Role In Applications Such As Real-time Passenger Information, Transit Planning, And Traffic Management. With Increasing Urbanization And Demand For Efficient Mobility, Transit Agencies Are Turning To Data-driven Models To Improve Service Reliability. One Valuable Data Source Is The General Transit Feed Specification (GTFS), Which Standardizes Public Transportation Schedules And Associated Geographic Information. When Integrated With Statistical Modeling Techniques, GTFS Features Can Significantly Enhance The Precision Of Street-level Travel Time Estimations. This Paper Presents A Comprehensive Review Of Statistical Models For Forecasting Street Level Travel Time Employing GTFS Features, Along With Associated Challenges That The Sector Faces.

Author: Vaishnavi Sambare | Prof. Pradeep Pal

Area of research: Computer Science

Machine Learning Is Transforming Stock Market Prediction By Leveraging Vast Datasets, Advanced Algorithms, And Computational Power To Provide More Accurate Forecasts. While Challenges Remain, Continuous Advancements In Artificial Intelligence And Deep Learning Are Improving Predictive Models, Making Them An Essential Tool For Traders And Investors. Stock Market Prediction Extremely Challenging Due To The Dependence Of Stock Prices On Several Financial, Socio-economic And Political Parameters Etc. For Real Life Applications Utilizing Stock Market Data, It Is Necessary To Predict Stock Market Data With Low Errors And High Accuracy. This Needs Design Of Appropriate Artificial Intelligence (AI) And Machine Learning (ML) Based Techniques Which Can Analyze Large And Complex Data Sets Pertaining To Stock Markets And Forecast Future Prices And Trends In Stock Prices With Relatively High Accuracy. This Paper Presents A Comprehensive Review On The Various Techniques Used In Recent Contemporary Papers For Stock Market Forecasting.

Author: Srishti Mongre | Dr. Dayashankar Pandey

Area of research: Cyber Security, Digital Forensic,deepfake ,Chatbot

The Rapid Expansion Of Generative AI (GenAI) Technologies Has Enabled Unprecedented Synthesised Media And Sophisticated Automated Systems. The Existence Of Advanced Deepfake Technology, Generative Large Language Models (LLMs) That Can Produce Toxic Content, And Automated AI Botnets Has Created Substantial New Obstacles In Digital Forensics. The Present Review Consolidates Recent Work (2024–2025) Concerning The Forensics Of Three Colliding AI Threats: Audio-visual Deepfakes, Toxic Or Weaponised Chatbots, And The Automated Facilitation Of Harm. The Review Reconstructs The Shift From Artefact Detection Systems Toward The Use Of Behavioural, Semantic, And Multimodal Forensics. The Emerging Methodologies, Such As Biological Signal Processing, Audiovisual Correlation, LLM Systematisation Fingerprinting, And Traffic Encryption Biometrics, As Well As The Comprehensive Integration Of These Methodologies, Reveal Vital Yet Unrefined Methodologies That Focus On The Challenges Of Adversarial Attacks, Laundering Via Paraphrasing, And Performance Drops On Real-world Data. The Review Articulates The Necessity Of Well-founded, Transparent, And Standardizable Forensic Systems That Are Meant To Work In Adversarial Conditions.

Author: Dr.Kiranbhai R Dodiya, Miss Ankita Kumari, Sudha Shetty,Dr. Parvesh Sharma,Dr. Kapil Kumar

Area of research: Civil Engineering

The Rapid Expansion Of Global Infrastructure Has Led To An Unprecedented Demand For Natural Construction Materials, Necessitating The Exploration Of Sustainable Alternatives. This Research Investigates The Feasibility Of Replacing Natural Coarse Aggregates With Manually Crushed Recycled Concrete Aggregates (RCA) In High-strength M50 Grade Concrete. A Primary Challenge Addressed In This Study Is The Presence Of Adhered Mortar On The Surface Of Recycled Aggregates, Which Significantly Influences Concrete Performance. The Experimental Program Involved Characterizing The Physical Properties Of Recycled Aggregates, Specifically Quantifying The Average Adhered Mortar Content. A Comprehensive Mix Design For M50 Grade Concrete Was Developed, And An Optimum Replacement Ratio Was Determined. The Mechanical Performance Was Evaluated Through Compressive Strength Testing Of Both Natural And Recycled Aggregate Concrete Under Normal Water Curing Conditions. Furthermore, The Study Explores The Effect Of Recycled Aggregate Utilization On Durability By Assessing The Concrete's Resistance To Sulphate Attack. The Findings Provide Critical Insights Into The Viability Of Incorporating Recycled Aggregates Into High-performance Concrete, Offering A Pathway Toward More Sustainable Construction Practices By Mitigating The Reliance On Virgin Natural Resources.

Author: K SURYAKALA | P D SASIKALA

Area of research: Civil Engineering

The Construction Industry’s Rapid Expansion Is Driving An Unsustainable Increase In Global Cement Production, Currently Exceeding 1.6 Billion Tons Annually. This Demand Not Only Depletes Natural Resources But Also Results In Significant Environmental Degradation Due To The Emission Of Greenhouse Gases, Including CO2, SO2, And NOX. To Address These Concerns, This Study Explores The Utilization Of Industrial Byproducts Specifically Cenospheres And Dolomite Powder As Sustainable Additives In Concrete Manufacturing. Cenospheres, Lightweight Hollow Spheres Derived From Coal Combustion, Were Utilized To Reduce The Unit Weight Of The Concrete, While Dolomite Powder Was Introduced As A Mineral-rich Cementitious Material To Enhance Mechanical Performance. This Research Investigates The Mechanical And Physical Properties Of M-30 Grade Concrete Through A Series Of Partial Replacements. The Experimental Program Evaluates Varying Proportions Of Dolomite Powder (0, 10, 20 And 30% By Weight Of Cement) In Combination With Cenospheres (0, 2, 4, And 6% By Weight). The Study Provides A Detailed Experimental Analysis Of Compressive, Flexural, And Split Tensile Strength At 7, 14, And 28 Days Of Curing. Preliminary Results Aim To Determine The Optimal Synergy Between These Materials To Produce A Structural-grade Lightweight Concrete That Minimizes Environmental Impact Without Compromising Mechanical Integrity. This Research Contributes To The Development Of Circular-economy-based Construction Materials, Offering A Viable Pathway For Reducing The Carbon Footprint Of Structural Infrastructure.

Author: D SRI SIVA KIRAN VARMA | K URMILA DEVI

Area of research: Computer Science And Engineering (CSE)

This Project Builds A System That Checks Student Attention In Real Time. It Uses A Camera Feed To Detect Faces, Track Eyes, And Read Basic Emotions. The System Works With A Single Student Or Many Students At The Same Time. It Also Supports Different Platforms Like Webcam, Video Files, Zoom, Google Meet, And Microsoft Teams. Each Frame Is Processed To Find Faces, Detect Eyes, And Estimate Emotions. These Results Are Used To Calculate Attention Levels And Engagement Scores. The System Can Show Alerts, Track Trends, And Create Simple Reports. All Processing Happens On The User’s Machine, So No Data Is Sent Outside. The Goal Is To Help Teachers Understand When Students Are Focused And When They Are Not.

Author: Dhanyaa J | Karthika.K | Dr.Balasubramanie P | Shanmugapriya P | Ramya T E

Area of research: Computer Science

Author: Jagmohan | Dr. Neha Jain

Area of research: Civil Engineering

Marine Soil Refers To The Deposits Formed Beneath The Seabed And Is Also Commonly Found Along Coastal Areas. The Engineering Behavior Of Fully Saturated Marine Soil Is Considerably Different From That Of Partially Moist Or Dry Soil. It Generally Contains A High Percentage Of Organic Matter And Exhibits Expansive Characteristics, Undergoing Swelling And Shrinkage As Its Moisture Content Changes. These Volume Variations Can Adversely Affect The Stability Of Foundations And Other Civil Engineering Structures, Resulting In Increased Construction And Maintenance Costs In Coastal Regions. To Overcome These Challenges, Ground Improvement Techniques Are Widely Adopted To Enhance The Engineering Properties Of Marine Soil So That It Satisfies Foundation And Infrastructure Requirements. Maintaining A Consistent Moisture Condition Around And Beneath Foundations Is Considered One Of The Most Effective Methods For Minimizing The Harmful Effects Associated With Expansive Soils. For The Present Investigation, Marine Clay Samples Were Collected From The Coastal Region Of UPPADA Village In Kakinada District, Andhra Pradesh. The Primary Reason For Selecting Marine Clay From This Location Is The Recent Announcement By The Government Of Andhra Pradesh Regarding The Construction Of A Fishing Harbour In The Area. Therefore, A Preliminary Investigation Has Been Carried Out To Assess The Engineering And Strength Characteristics Of The Locally Available Marine Clay. At The Same Time, The Disposal Of Industrial Waste Materials Has Become A Significant Environmental Concern. Fly Ash, A By-product Generated From Coal-fired Thermal Power Plants, Is One Such Material With Considerable Potential For Reuse. Although Fly Ash Possesses Limited Cementitious Properties On Its Own, It Reacts With Moisture To Produce Cementitious Compounds That Improve The Strength And Compressibility Behavior Of Soils. Accordingly, This Experimental Study Aims To Enhance The Properties Of Marine Clay While Promoting The Beneficial Utilization Of Industrial Waste. The Research Focuses On Evaluating The Influence Of Fly Ash And Lime On The Strength Characteristics Of Marine Clay.

Author: P.Prudhvi Teja | P.D. Sasikala

Area of research: Civil Engineering

Expansive Soils, Commonly Referred To As Black Cotton Soils In India, Present Significant Geotechnical Challenges Because They Undergo Swelling When They Absorb Moisture And Shrink Upon Drying. This Repeated Cycle Of Expansion And Contraction Can Lead To Considerable Damage To The Foundations Of Structures Constructed On Such Soils. Therefore, Understanding The Engineering Behaviour Of Expansive Soils And Implementing Suitable Stabilization Techniques Has Become An Important Area Of Study For Geotechnical Engineers. Considerable Research Has Been Undertaken To Identify Effective Methods For Minimizing The Expansive Characteristics Of These Soils. Among The Various Ground Improvement Techniques, The Use Of Electrolytes Has Emerged As A Promising Approach For Enhancing The Engineering Properties Of Expansive Soils. In The Present Study, A Systematic Laboratory Investigation Was Carried Out To Evaluate The Effects Of An Electrolyte And An Industrial Waste By-product, Namely Shredded Rubber Mulch, Together With Calcium Chloride, On The Engineering Properties Of Expansive Soil. The Experimental Program Was Conducted Under Carefully Controlled Laboratory Conditions Following A Structured Testing Methodology To Assess The Effectiveness Of These Stabilizing Materials.

Author: Visai Ganapathi Sai | P.D. Sasikala

Area of research: Artificial Intelligence

Author: Ravi Ramesh Mishra