Tinku Singh

My name is Tinku Singh and I am currently working as a Postdoctoral Researcher at Chungbuk National University, Cheongju, South Korea. I completed the Master’s in Technology (M.Tech) in Computer Science and Engineering in 2016 from Maharshi Dayanand University, Rohtak, Haryana, India and Ph.D. from the Indian Institute of Information Technology Allahabad (IIITA), India in 2023.
The potential of machine learning and deep learning algorithms in solving problems from different areas has always intrigued me, so I follow this as a research area of interest. I have published papers in international journals, conferences and pre-print servers. My main research includes Big data analytics, Machine learning, and Deep learning in different domains. I have also gained outreach experience in delivering tutorial sessions, hands-on sessions and organizing several workshops and conferences on international platforms.

EDUCATION

PhD from Indian Institute of Information Technology, Allahabad India

RESEARCH, TEACHING, or OTHER INTERESTS

Computer Engineering, Computer Science, Artificial Intelligence

Scopus Publications

An augmented ECG data based classification for arrhythmia using optimal feature set
Mohammad Shahnawaz, Nikhil Kumawat, Tinku Singh, Satakshi, Manish Kumar
Health Information Science and Systems, 2026
FedLBW: A loss-based weighting strategy for federated learning on non-IID data in wireless networks
Majid Kundroo, Tinku Singh, Taehong Kim
Expert Systems with Applications, 2026
AI-Enhanced Energy Conservation in Context-Aware MANETs
Hemant Kumar Saini, Aditya Dev Mishra, Tinku Singh
Conference Proceedngs Wccst 2026 World Conference on Computational Science and Technology, 2026
Mobile Ad Hoc Networks, due to their dynamic topology, face severe energy challenges and routing overheads. In most of the experiments, AODV and OLSR protocols do not consider the battery levels, mobility patterns and link quality, which causes much energy drainage in disaster response, IoT swarms, and aerial networks where recharging is impossible in motion. This investigation addresses the challenges of inefficient energy utilization in context-aware Mobile Ad Hoc Networks environments to solve heterogeneous operations by intelligent and adaptive decision-making. Therefore, CAECT (Context-Aware Energy Conservation for MANETs) is proposed using Markov chain pre-classification of context vectors <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$[E_{bat}^{\prime} v^{\prime} LQ^{\prime} N_{nei}]$</tex> to predict routing states. A lightweight DRL agent dynamically selects energy-optimal next-hops and transmit powers, implemented as an NS-3 cross-layer module, achieving a 25% reduction in routing overhead. Experimentation conducted in NS3 demonstrates that the proposed approach achieves 50-node urban scenario, 10m/s mobility show upto 37% total energy savings, 92% packet delivery ratio and 28ms end-to-end delay compared to AODV 45ms, 85% PDR. Relay node drain reduced by 42% while maintaining QoS and enhanced packet delivery ratio compared to conventional energy-aware MANET protocols. This framework is particularly suitable for energy-constrained applications such as disaster-response networks, military communications, vehicular ad hoc networks, and large-scale IoTbased mobile sensing systems.
FedMeanStd: Federated Aggregation With Outliers Filtering
Tinku Singh, Majid Kundroo, Taehong Kim
IEEE Access, 2026
Federated Learning faces significant challenges due to data heterogeneity, particularly in non-independent and identically distributed (non-IID) environments. This issue hampers the accuracy and convergence of traditional aggregation methods like Federated Averaging (FedAvg). To overcome this problem, this study proposes FedMeanStd, a novel aggregation technique utilizing the mean and standard deviation of client updates to dynamically select participants. This selection ensures that only stable, relevant contributions are included in the global model, filtering out unreliable or extreme updates. FedMeanStd introduces a statistically driven filtering mechanism that improves robustness against outliers and enhances the consistency of client selection. It operates entirely at the server side, preserving client privacy and scalability. Evaluated on benchmark datasets including CIFAR-10 and FashionMNIST under extreme non-IID settings, FedMeanStd consistently achieves superior accuracy and stability compared to traditional methods such as FedAvg, FedAvgM, and FedProx. By leveraging statistical measures, the method promotes balanced and representative learning, resulting in a more robust global model.
Analysis of Image Classification Using Machine Learning
Naveen Tyagi, Ashok Kumar Rai, Tinku Singh
2025 3rd International Conference on Iot Communication and Automation Technology Icicat 2025, 2025
Enhancing Traffic Management in Smart Cities: A Federated Learning Approach for Traffic Light Violation Detection
Human Centric Computing and Information Sciences, 2025
Deep Learning Based Framework for Real-Time Detection and Classification of Driver Drowsiness States
Anuj Kumar, Aditya Gupta, Sonam Tyagi, Vishal Jayaswal, Tinku Singh
2025 2nd International Conference on Advanced Computing and Emerging Technologies Acet 2025, 2025
Road accidents remain a major public safety concern in India, with driver drowsiness identified as one of the leading contributing factors. Fatigue and sleep deprivation significantly increase the likelihood of collisions, particularly among drivers aged 18–45 years, who constitute the majority of road accident victims. Studies indicate that 10–15% of crashes are directly linked to tiredness, highlighting the urgent need for an effective detection mechanism. In this study, we propose a convolutional neural network (CNN)-based real-time driver drowsiness detection system. Initially, the system recognizes faces using the Haar Cascade classifier before using Dlib to identify the areas of the lips and eyes. Features such as the eye opening angle and the mouth's height-to-width ratio are extracted and combined with CNN predictions to classify four states: eyes open, eyes closed, yawning, and not yawning. A dataset of 2890 images was preprocessed through resizing, normalization, and augmentation before being used to train the CNN model. The trained model, consisting of four convolutional layers and two fully connected layers, achieved an accuracy of about 97.93%. Real-time implementation with webcam input demonstrated that the system can reliably recognize drowsiness and trigger timely alerts, outperforming conventional classification techniques.
Automatic Detection of Parkinson Disease Through Various Machine Learning Models
Harendra Singh Negi, Bhawnesh Kumar, Manoj Diwakar, Prabhishek Singh, Tinku Singh, Ishwari Singh Rajput
Springer Series in Reliability Engineering, 2025
User story clustering using K-means and K-medoids algorithms in Agile software development for healthcare system
Bhawnesh Kumar, Dinesh C. Dobhal, Umesh Kumar Tiwari, Manoj Diwakar, Prabhishek Singh, Tinku Singh, Ishwari Singh Rajput
Data Driven Diagnostics and Disease Prediction with AI Optimization, 2025
Lazy learning and sparsity handling in recommendation systems
Suryanshi Mishra, Tinku Singh, Manish Kumar, Satakshi
Knowledge and Information Systems, 2024
COVID-19 severity detection using chest X-ray segmentation and deep learning
Tinku Singh, Suryanshi Mishra, Riya Kalra, Satakshi, Manish Kumar, Taehong Kim
Scientific Reports, 2024
An efficient hybrid approach for forecasting real-time stock market indices
Riya Kalra, Tinku Singh, Suryanshi Mishra, Satakshi, Naveen Kumar, Taehong Kim, Manish Kumar
Journal of King Saud University Computer and Information Sciences, 2024
Sentiment analysis based distributed recommendation system
Tinku Singh, Vinarm Rajput, Nikhil Sharma, Satakshi, Manish Kumar
Multimedia Tools and Applications, 2024
Multivariate time series short term forecasting using cumulative data of coronavirus
Suryanshi Mishra, Tinku Singh, Manish Kumar, Satakshi
Evolving Systems, 2024
WSN-Driven Advances in Soil Moisture Estimation: A Machine Learning Approach
Tinku Singh, Majid Kundroo, Taehong Kim
Electronics Switzerland, 2024
Distributed hyperparameter optimization based multivariate time series forecasting
Tinku Singh, Ayush Sinha, Satakshi Singh, O. P. Vyas, Manish Kumar
Multimedia Tools and Applications, 2024
An efficient real-time stock prediction exploiting incremental learning and deep learning
Tinku Singh, Riya Kalra, Suryanshi Mishra, Satakshi, Manish Kumar
Evolving Systems, 2023
Adaptive load balancing in cluster computing environment
Tinku Singh, Shivam Gupta, Satakshi, Manish Kumar
Journal of Supercomputing, 2023
A study on machine learning-based water quality assessment and wastewater treatment
Satakshi Singh, Suryanshi Mishra, Tinku Singh, Shobha Thakur
Artificial Intelligence Applications in Water Treatment and Water Resource Management, 2023
Quality Assessment and Monitoring of River Water Using IoT Infrastructure
Manish Kumar, Tinku Singh, Manish Kumar Maurya, Anubhav Shivhare, Ashwin Raut, Pramod Kumar Singh
IEEE Internet of Things Journal, 2023
Real-time traffic light violations using distributed streaming
Tinku Singh, Vinarm Rajput, Satakshi, Umesh Prasad, Manish Kumar
Journal of Supercomputing, 2023
Improved multi-class classification approach for imbalanced big data on spark
Tinku Singh, Riya Khanna, Satakshi, Manish Kumar
Journal of Supercomputing, 2023
Analysis and forecasting of air quality index based on satellite data
Tinku Singh, Nikhil Sharma, Satakshi, Manish Kumar
Inhalation Toxicology, 2023
Stock Market Prediction Using Ensemble Learning and Sentimental Analysis
Tinku Singh, Siddhant Bhisikar, Satakshi, Manish Kumar
Lecture Notes in Electrical Engineering, 2023
A Methodological Review of Time Series Forecasting with Deep Learning Model: A Case Study on Electricity Load and Price Prediction
Ayush Sinha, Tinku Singh, Ranjana Vyas, Manish Kumar, O. P. Vyas
Lecture Notes in Electrical Engineering, 2023
Distributed Item Recommendation Using Sentiment Analysis
Tinku Singh, Vinarm Rajput, Nikhil Sharma, Satakshi, Manish Kumar
Lecture Notes in Networks and Systems, 2023
Performance Analysis and Deployment of Partitioning Strategies in Apache Spark
Tinku Singh, Shivam Gupta, Satakshi, Manish Kumar
Procedia Computer Science, 2022
Air Quality Analysis During COVID-19 Utilizing Satellite Data
Tinku Singh, Nikhil Sharma, Vinarm Rajput, Suryanshi Mishra, Satakshi, Manish Kumar
2022 2nd International Conference on Intelligent Technologies Conit 2022, 2022
Fingerprint Identification using Modified Capsule Network
Tinku Singh, Siddhant Bhisikar, Satakshi, Manish Kumar
2021 12th International Conference on Computing Communication and Networking Technologies Icccnt 2021, 2021
Multiclass Imbalanced Big Data Classification Utilizing Spark Cluster
Tinku Singh, Riya Khanna, Satakshi, Manish Kumar
2021 12th International Conference on Computing Communication and Networking Technologies Icccnt 2021, 2021
A novel approach for CPU utilization on a multicore paradigm using parallel quicksort
Tinku Singh, Durgesh Kumar Srivastava, Alok Aggarwal
3rd IEEE International Conference on, 2017

RECENT SCHOLAR PUBLICATIONS

Automatic Detection of Parkinson Disease Through Various Machine Learning Models
HS Negi, B Kumar, M Diwakar, P Singh, T Singh, IS Rajput
Machine Learning and Deep Learning Modeling and Algorithms with Applications … , 2025
2025
Citations: 3
Enhancing Traffic Management in Smart Cities: A Federated Learning Approach for Traffic Light Violation Detection
T Singh, M Kundroo, S Kim, T Kim
HUMAN-CENTRIC COMPUTING AND INFORMATION SCIENCES 15 , 2025
2025
Lazy learning and sparsity handling in recommendation systems.
S Mishra, T Singh, M Kumar
Knowledge & Information Systems 66 (12), 7775 , 2024
2024
Citations: 4
An efficient hybrid approach for forecasting real-time stock market indices
R Kalra, T Singh, S Mishra, N Kumar, T Kim, M Kumar
Journal of King Saud University-Computer and Information Sciences 36 (8), 102180 , 2024
2024
Citations: 28
COVID-19 severity detection using chest X-ray segmentation and deep learning
T Singh, S Mishra, R Kalra, Satakshi, M Kumar, T Kim
Scientific Reports 14 (1), 19846 , 2024
2024
Citations: 33
Sentiment analysis based distributed recommendation system
T Singh, V Rajput, N Sharma, Satakshi, M Kumar
Multimedia Tools and Applications 83 (25), 66539-66563 , 2024
2024
Citations: 7
Multivariate time series short term forecasting using cumulative data of coronavirus
S Mishra, T Singh, M Kumar, Satakshi
Evolving Systems 15 (3), 811-828 , 2024
2024
Citations: 16
WSN-driven advances in soil moisture estimation: A machine learning approach
T Singh, M Kundroo, T Kim
Electronics 13 (8), 1590 , 2024
2024
Citations: 29
Water Quality Monitoring on Streaming Data
B Kumar, T Singh, A Kumar, N Kumar
Computology: Journal of Applied Computer Science and Intelligent … , 2024
2024
Citations: 4
Distributed hyperparameter optimization based multivariate time series forecasting
T Singh, A Sinha, S Singh, OP Vyas, M Kumar
Multimedia Tools and Applications 83 (2), 5031-5053 , 2024
2024
Citations: 3
An efficient real-time stock prediction exploiting incremental learning and deep learning
T Singh, R Kalra, S Mishra, Satakshi, M Kumar
Evolving Systems 14 (6), 919-937 , 2023
2023
Citations: 61
Adaptive load balancing in cluster computing environment: T. Singh et al.
T Singh, S Gupta, Satakshi, M Kumar
The Journal of Supercomputing 79 (17), 20179-20207 , 2023
2023
Citations: 2
Real-time traffic light violations using distributed streaming: T. Singh et al.
T Singh, V Rajput, Satakshi, U Prasad, M Kumar
The Journal of Supercomputing 79 (7), 7533-7559 , 2023
2023
Citations: 20
Improved multi-class classification approach for imbalanced big data on spark: T. Singh et al.
T Singh, R Khanna, Satakshi, M Kumar
The Journal of Supercomputing 79 (6), 6583-6611 , 2023
2023
Citations: 19
Analysis and forecasting of air quality index based on satellite data
T Singh, N Sharma, Satakshi, M Kumar
Inhalation Toxicology 35 (1-2), 24-39 , 2023
2023
Citations: 19
Quality assessment and monitoring of river water using IoT infrastructure
M Kumar, T Singh, MK Maurya, A Shivhare, A Raut, PK Singh
IEEE Internet of Things Journal 10 (12), 10280-10290 , 2023
2023
Citations: 79
Analysis and forecasting of air quality index based on satellite data
SMK T. Singh, N. Sharma
Inhalation Toxicology 35 (1-2), 1-17 , 2023
2023
A study on machine learning-based water quality assessment and wastewater treatment
S Singh, S Mishra, T Singh, S Thakur
Artificial Intelligence Applications in Water Treatment and Water Resource … , 2023
2023
Citations: 2
A methodological review of Time Series forecasting with Deep Learning Model: a Case Study on Electricity load and price prediction
A Sinha, T Singh, R Vyas, M Kumar, OP Vyas
Machine Learning, Image Processing, Network Security and Data Sciences … , 2023
2023
Citations: 5
Stock market prediction using ensemble learning and sentimental analysis
T Singh, S Bhisikar, Satakshi, M Kumar
Machine Learning, Image Processing, Network Security and Data Sciences … , 2023
2023
Citations: 4

MOST CITED SCHOLAR PUBLICATIONS

Quality assessment and monitoring of river water using IoT infrastructure
M Kumar, T Singh, MK Maurya, A Shivhare, A Raut, PK Singh
IEEE Internet of Things Journal 10 (12), 10280-10290 , 2023
2023
Citations: 79
An efficient real-time stock prediction exploiting incremental learning and deep learning
T Singh, R Kalra, S Mishra, Satakshi, M Kumar
Evolving Systems 14 (6), 919-937 , 2023
2023
Citations: 61
A novel approach for CPU utilization on a multicore paradigm using parallel quicksort
T Singh, DK Srivastava, A Aggarwal
2017 3rd International Conference on Computational Intelligence … , 2017
2017
Citations: 39
COVID-19 severity detection using chest X-ray segmentation and deep learning
T Singh, S Mishra, R Kalra, Satakshi, M Kumar, T Kim
Scientific Reports 14 (1), 19846 , 2024
2024
Citations: 33
WSN-driven advances in soil moisture estimation: A machine learning approach
T Singh, M Kundroo, T Kim
Electronics 13 (8), 1590 , 2024
2024
Citations: 29
An efficient hybrid approach for forecasting real-time stock market indices
R Kalra, T Singh, S Mishra, N Kumar, T Kim, M Kumar
Journal of King Saud University-Computer and Information Sciences 36 (8), 102180 , 2024
2024
Citations: 28
Performance comparison of sequential quick sort and parallel quick sort algorithms
I Rajput
International Journal of Computer Applications , 2012
2012
Citations: 27
Real-time traffic light violations using distributed streaming: T. Singh et al.
T Singh, V Rajput, Satakshi, U Prasad, M Kumar
The Journal of Supercomputing 79 (7), 7533-7559 , 2023
2023
Citations: 20
Improved multi-class classification approach for imbalanced big data on spark: T. Singh et al.
T Singh, R Khanna, Satakshi, M Kumar
The Journal of Supercomputing 79 (6), 6583-6611 , 2023
2023
Citations: 19
Analysis and forecasting of air quality index based on satellite data
T Singh, N Sharma, Satakshi, M Kumar
Inhalation Toxicology 35 (1-2), 24-39 , 2023
2023
Citations: 19
Multivariate time series short term forecasting using cumulative data of coronavirus
S Mishra, T Singh, M Kumar, Satakshi
Evolving Systems 15 (3), 811-828 , 2024
2024
Citations: 16
Performance Analysis and Deployment of Partitioning Strategies in Apache Spark
T Singh, S Gupta, Satakshi, M Kumar
7th International Conference on Machine Learning and Data Engineering … , 2022
2022
Citations: 16
Fingerprint identification using modified capsule network
T Singh, S Bhisikar, M Kumar
2021 12th International conference on computing communication and networking … , 2021
2021
Citations: 11
Multiclass imbalanced big data classification utilizing spark cluster
T Singh, R Khanna, M Kumar
2021 12th International Conference on Computing Communication and Networking … , 2021
2021
Citations: 8
Sentiment analysis based distributed recommendation system
T Singh, V Rajput, N Sharma, Satakshi, M Kumar
Multimedia Tools and Applications 83 (25), 66539-66563 , 2024
2024
Citations: 7
A methodological review of Time Series forecasting with Deep Learning Model: a Case Study on Electricity load and price prediction
A Sinha, T Singh, R Vyas, M Kumar, OP Vyas
Machine Learning, Image Processing, Network Security and Data Sciences … , 2023
2023
Citations: 5
Threshold Analysis and Comparison of Sequential and Parallel Divide and Conquer Sorting Algorithms
T Singh, DK Srivastava
International Journal of Computer Applications 145 (10), 0975-8887 , 2016
2016
Citations: 5
Lazy learning and sparsity handling in recommendation systems.
S Mishra, T Singh, M Kumar
Knowledge & Information Systems 66 (12), 7775 , 2024
2024
Citations: 4
Water Quality Monitoring on Streaming Data
B Kumar, T Singh, A Kumar, N Kumar
Computology: Journal of Applied Computer Science and Intelligent … , 2024
2024
Citations: 4
Stock market prediction using ensemble learning and sentimental analysis
T Singh, S Bhisikar, Satakshi, M Kumar
Machine Learning, Image Processing, Network Security and Data Sciences … , 2023
2023
Citations: 4