Dilip Kumar Choubey
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Dilip Kumar Choubey has a total of 82 co-authors. Here are the top co-authors by number of shared publications:
Sanchita Paul
Computer Science and Engineering, Birla Institute of Technology Mesra, Ranchi, India
8 shared publications- Ratnesh Kumar Dubey
Indian Institute of Information Technology Bhagalpur
7 shared publications - Manish Kumar
Marwadi University
5 shared publications - Mukesh Kumar Ojha
Greater Noida Institute of Technology, Greater Noida, India
5 shared publications Vaibhav Shukla
Tech Mahindra Ltd
4 shared publications- Debabrata Singh
Siksha’O’ Anusandhan University, Bhubaneswar, India
3 shared publications
Latest Publications
- 2 June 2026
- Published by Taylor & Francis
- p. 393-432
Tomato Plant Disease Classification using Deep Learning Techniques
- 2 June 2026
- Published by Taylor & Francis
- p. 393-432
Tomato Plant Disease Classification using Deep Learning Techniques
- 1 June 2026
- Published by Springer Nature
- p. 260-271
Deep Learning-Based Brain Tumor Identification: A Lightweight CNN Approach for MRI Analysis
- 1 June 2026
- Published by Springer Nature
- p. 260-271
Deep Learning-Based Brain Tumor Identification: A Lightweight CNN Approach for MRI Analysis
- 24 November 2025
- Published by Springer Nature
- p. 45-55
Predictive Maintenance on C-MAPSS Using LSTM Variants and Attention
- 24 November 2025
- Published by Springer Nature
- p. 45-55
Predictive Maintenance on C-MAPSS Using LSTM Variants and Attention
- 1 August 2025
- Published by IGI Global Scientific Publishing
- p. 75-88
Digitally Innovative IoT-Enabled Smart Health Emergency Alert System
The mechanical approach to modern detecting devices and the Internet has produced helpful solutions for public and private sector projects, government institutes across the globe, and a variety of systems administration fields. To improve the utility and personalization of health monitoring, this manuscript proposes to integrate IoT with wellness monitoring. This study looks at various wearable health monitoring devices that people can use to monitor physiological data such as internal body temperature, pulse, and heart rate. To build a health monitoring system, data is gathered via a remote sensor. To achieve continuous observation, information pertaining to the IoT is integrated for handling, interacting, and processing. By examining each of the three people separately, the average temperature was found to be 36.5, 36.4, and 36.5 (°C), suggesting that the framework showed some degree of accurate and steady testability. According to the temperature thermometer, each of the three people has a temperature of 36.4, 36.7, and 36.5 (°C). The three individuals assessed by the framework had pulse rates of 78, 78, and 79 (times/min), respectively, which match the findings from the clinical heartbeat meter. The physiological data procured utilizing the semantic acknowledgment, matching framework, and character it is generally exact to match framework. It reasons that the human wellbeing observing framework considering the IoT can furnish individuals with day-to-day wellbeing the board, instrumental in increasing wellbeing administration quality and level.
- 1 August 2025
- Published by IGI Global Scientific Publishing
- p. 75-88
Digitally Innovative IoT-Enabled Smart Health Emergency Alert System
The mechanical approach to modern detecting devices and the Internet has produced helpful solutions for public and private sector projects, government institutes across the globe, and a variety of systems administration fields. To improve the utility and personalization of health monitoring, this manuscript proposes to integrate IoT with wellness monitoring. This study looks at various wearable health monitoring devices that people can use to monitor physiological data such as internal body temperature, pulse, and heart rate. To build a health monitoring system, data is gathered via a remote sensor. To achieve continuous observation, information pertaining to the IoT is integrated for handling, interacting, and processing. By examining each of the three people separately, the average temperature was found to be 36.5, 36.4, and 36.5 (°C), suggesting that the framework showed some degree of accurate and steady testability. According to the temperature thermometer, each of the three people has a temperature of 36.4, 36.7, and 36.5 (°C). The three individuals assessed by the framework had pulse rates of 78, 78, and 79 (times/min), respectively, which match the findings from the clinical heartbeat meter. The physiological data procured utilizing the semantic acknowledgment, matching framework, and character it is generally exact to match framework. It reasons that the human wellbeing observing framework considering the IoT can furnish individuals with day-to-day wellbeing the board, instrumental in increasing wellbeing administration quality and level.
- 21 January 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (1)
Multi-deep learning models based analysis for classification of thunderstorms on meteorological dataset over Ranchi region
Deep learning (DL) is now generally acknowledged as the benchmark and evolution in machine learning (ML) fields. Further more, it has steadily suited the most extensively in computational techniques for ML, delivering excellent outcomes in several challenging intellectual works that have equal or still outperformed human ability. DL has the advantage of learning from enormous amounts of data. Here, the DL approach has been applied to classify thunderstorms and non-thunderstorms with a meteorological dataset. Daily observational hourly data sets from 2016 to 2021 have been used to classify the incidence of thunderstorms and non-thunderstorms. Three DL approaches are used: Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM) to classify thunderstorm incidences. These DL techniques are compared with conventional ML techniques, showing that DL approaches outperformed ML. The CNN method provides the highest performance with 92.01% accuracy among all DL and ML approaches.
- 21 January 2025
- Published by IOP Publishing in Engineering Research Express
- Vol. 7 (1)
Multi-deep learning models based analysis for classification of thunderstorms on meteorological dataset over Ranchi region
Deep learning (DL) is now generally acknowledged as the benchmark and evolution in machine learning (ML) fields. Further more, it has steadily suited the most extensively in computational techniques for ML, delivering excellent outcomes in several challenging intellectual works that have equal or still outperformed human ability. DL has the advantage of learning from enormous amounts of data. Here, the DL approach has been applied to classify thunderstorms and non-thunderstorms with a meteorological dataset. Daily observational hourly data sets from 2016 to 2021 have been used to classify the incidence of thunderstorms and non-thunderstorms. Three DL approaches are used: Convolutional Neural Networks (CNN), Recurrent Neural Networks (RNN), and Long Short-Term Memory (LSTM) to classify thunderstorm incidences. These DL techniques are compared with conventional ML techniques, showing that DL approaches outperformed ML. The CNN method provides the highest performance with 92.01% accuracy among all DL and ML approaches.
- 2 October 2024
- Published by Taylor & Francis
- p. 216-238
Machine Learning, Deep Learning and IoT in Smart Healthcare for Retinal Diseases Management
The convergence of cutting-edge technologies, specifically ML and DL integrated into the IoT, is revolutionizing healthcare, particularly in the field of ophthalmology. The impact of ML and DL-based Smart IoT Healthcare Systems on retinal disease early detection and management is examined in this study. Globally, retinal diseases such as glaucoma, age-related macular degeneration, and diabetic retinopathy are among the leading causes of visual impairment. Conventional screening techniques are expensive, time-consuming, and prone to human error. The integration of IoT devices, wearable technology, and smart sensors into ophthalmic healthcare settings presents novel opportunities for early diagnosis, continuous monitoring, and personalized treatment plans. This chapter focuses on the classification of images from the "Cataract Dataset" into two classes, "normal" and "cataract," utilizing various machine learning classifiers. The proposed methodology encompasses key phases, beginning with data preparation, where images are loaded, resized, and converted into NumPy arrays. A diverse set of classifiers, including logistic regression, decision tree, random forest, SVM, KNN, and others, is employed for classification. Experimental results highlight XGBoost as the top performer with an accuracy of 0.90781, closely followed by Gradient Boosting and the Voting Classifier. The ROC AUC scores, crucial for evaluating classification models, reinforce the high performance of these classifiers. Logistic Regression, Random Forest, SVM, K-nearest neighbors, and others showcase varying degrees of effectiveness based on their ROC AUC scores. The research provides a detailed analysis of the proposed methodology's effectiveness in classifying cataract images. The comparative evaluation of diverse classifiers and the emphasis on performance metrics contribute valuable insights for selecting appropriate models based on specific application requirements.
- 2 October 2024
- Published by Taylor & Francis
- p. 216-238
Machine Learning, Deep Learning and IoT in Smart Healthcare for Retinal Diseases Management
The convergence of cutting-edge technologies, specifically ML and DL integrated into the IoT, is revolutionizing healthcare, particularly in the field of ophthalmology. The impact of ML and DL-based Smart IoT Healthcare Systems on retinal disease early detection and management is examined in this study. Globally, retinal diseases such as glaucoma, age-related macular degeneration, and diabetic retinopathy are among the leading causes of visual impairment. Conventional screening techniques are expensive, time-consuming, and prone to human error. The integration of IoT devices, wearable technology, and smart sensors into ophthalmic healthcare settings presents novel opportunities for early diagnosis, continuous monitoring, and personalized treatment plans. This chapter focuses on the classification of images from the "Cataract Dataset" into two classes, "normal" and "cataract," utilizing various machine learning classifiers. The proposed methodology encompasses key phases, beginning with data preparation, where images are loaded, resized, and converted into NumPy arrays. A diverse set of classifiers, including logistic regression, decision tree, random forest, SVM, KNN, and others, is employed for classification. Experimental results highlight XGBoost as the top performer with an accuracy of 0.90781, closely followed by Gradient Boosting and the Voting Classifier. The ROC AUC scores, crucial for evaluating classification models, reinforce the high performance of these classifiers. Logistic Regression, Random Forest, SVM, K-nearest neighbors, and others showcase varying degrees of effectiveness based on their ROC AUC scores. The research provides a detailed analysis of the proposed methodology's effectiveness in classifying cataract images. The comparative evaluation of diverse classifiers and the emphasis on performance metrics contribute valuable insights for selecting appropriate models based on specific application requirements.
- 2 October 2024
- Published by Taylor & Francis
- p. 184-215
Transfer Learning for Multiclass Classification of Bone Marrow Cells
Accurate classification of bone marrow cells for hematological disorder diagnosis faces challenges due to complex morphology and subjectivity in manual assessment. Inconsistencies among experts, time constraints, and intra-observer variability further hinder the process. To address these issues, researchers are working on standardized criteria, improved resources, and AI-based automation. This study rigorously analyzes diverse deep and machine learning techniques in bone marrow cell classification, highlighting their role in modernizing cytology. The authors present their own CNN-based model for digital cytology, achieving a notable 91.66% test accuracy. The study is structured into five main sections: introduction, motivation, related work, material and methods, experimental results, and discussions along with future directions. This research showcases the potential of AI-driven approaches to enhance accuracy and efficiency in bone marrow cell classification, revolutionizing hematological disorder diagnostics.
- 2 October 2024
- Published by Taylor & Francis
- p. 184-215
Transfer Learning for Multiclass Classification of Bone Marrow Cells
Accurate classification of bone marrow cells for hematological disorder diagnosis faces challenges due to complex morphology and subjectivity in manual assessment. Inconsistencies among experts, time constraints, and intra-observer variability further hinder the process. To address these issues, researchers are working on standardized criteria, improved resources, and AI-based automation. This study rigorously analyzes diverse deep and machine learning techniques in bone marrow cell classification, highlighting their role in modernizing cytology. The authors present their own CNN-based model for digital cytology, achieving a notable 91.66% test accuracy. The study is structured into five main sections: introduction, motivation, related work, material and methods, experimental results, and discussions along with future directions. This research showcases the potential of AI-driven approaches to enhance accuracy and efficiency in bone marrow cell classification, revolutionizing hematological disorder diagnostics.
- 5 July 2024
- Published by Springer Nature
- p. 485-501
Identification and Detection of Rice Plant Diseases by Using Neural Network
- 5 July 2024
- Published by Springer Nature
- p. 485-501
Identification and Detection of Rice Plant Diseases by Using Neural Network
- Retracted
- 23 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (33) , 80281
RETRACTED ARTICLE: Feature selection with Optimized XGBoost model-based paddy plant leaf disease classification
- 23 February 2024
- Published by Springer Nature in Multimedia Tools and Applications
- Vol. 83 (33) , 80281
RetractedRETRACTED ARTICLE: Feature selection with Optimized XGBoost model-based paddy plant leaf disease classification