Muzammil Khan is a researcher at the Faculty of EEMCS, University of Twente. His current research is focused on implementing simultaneous localization and mapping (SLAM) algorithms for improving laparoscopic liver resection. Prior to this, he was a Ph.D. scholar in the Department of Mathematics, Bioinformatics, and Computer Applications at the National Institute of Technology Bhopal, India. His broad research area encompasses modern computer vision and machine learning applications in the field of healthcare. He explored the topic of Optical Flow in his thesis titled “Novel Algorithms for Optical Flow Estimation and Its Application”. In his work, he developed mathematical models for accurate optical flow estimation and further utilized them with deep learning techniques to perform anomaly detection in image sequences. During his Ph.D., he wrote 12 journal articles, 15 international conferences, and 5 book chapter. He presented his research at 10 international conferences.
EDUCATION
Postdoc: Since Oct 2023 as a Computer Vision and Artificial Intelligence researcher in the Robotics and Mechatronics Group of University of Twente
Awarded on April 2024 and Submitted on Sep 2023 from Maulana Azad National Institute of Technology
CSIR-NET exam: Qualified on Aug 2019 in Mathematical Sciences
GATE (Graduate Aptitude Test in Engineering- 2019) exam: Qaulified on Mar 2019 in Mathematics
Master of Science: Awarded on Sep 2018 from Bundelkhand University Jhansi
Bachelor of Science: Awarded on May 2016 from Bundelkhand University Jhansi
RESEARCH, TEACHING, or OTHER INTERESTS
Computer Vision and Pattern Recognition, Medical Laboratory Technology, Applied Mathematics, Arts and Humanities
A Nonlinear Fractional Order Optical Flow and CNN Based Framework for Fire Prediction Using Smoke Features Nitish Kumar Mahala, Muzammil Khan, Pushpendra Kumar 2024 Opju International Technology Conference on Smart Computing for Innovation and Advancement in Industry 4 0 Otcon 2024, 2024 Thousands of fires break out daily worldwide, leading to numerous casualties and posing a significant threat to property safety and forest vegetation. Thus, detecting a fire in its early stages is crucial, since it can quickly escalate into a catastrophic and uncontrollable situation. The early detection of fire could be assisted with the help of smoke, which seems small at the beginning and exhibits various colors, shapes, and textures. This can be easily observed by security cameras placed in numerous public areas. The paper introduced a convolutional neural network (CNN) framework for predicting fires by analyzing the dynamic characteristics of smoke. The dynamic characteristics are analyzed using an optical flow color map. The aim of this work is to utilize fractional order optical flow instead of images to accurately determine the position and growth rate. Optical flow estimation is performed using a nonlinear Charbonnier norm-based fractional order variational model, which effectively preserves dynamic discontinuities in the optical flow. Optical flow assists in identifying the dynamic areas inside images (video). The color map is divided into its RGB channels, and the channel most sensitive to smoke motion is isolated using a binary mask. Finally, the segmented optical flow color maps along with the corresponding image sequences are classified using a novel CNN architecture. Various accuracy metrics are used to evaluate the performance and compare with other techniques. Experiments are conducted using a diverse set of datasets comprising 16 smoke and 19 non-smoke videos, respectively.
Unifying Scale-Aware Depth Prediction and Perceptual Priors for Monocular Endoscope Pose Estimation and Tissue Reconstruction M Khan, E Kerkhof, M Fusaglia, K Kuhlmann, T Ruers, FJ Siepel IEEE Access , 2026 2026 Citations: 1
Explainable and likelihood aware AI framework for MRI-based pixel-level bladder tumour prediction M Khan, AG de Groot, EB Cornel, AG van der Heijden, FJ Siepel Scientific Reports 15 (1), 40760 , 2025 2025
Reliable Smoke Detection via Optical Flow-Guided Feature Fusion and Transformer-Based Uncertainty Modeling NK Mahala, M Khan, P Kumar arXiv preprint arXiv:2508.14597 , 2025 2025
Unifying Scale-Aware Depth Prediction and Perceptual Priors for Monocular Endoscope Pose Estimation and Tissue Reconstruction M Khan, E Kerkhof, M Fusaglia, K Kuhlmann, T Ruers, F J. Siepel arXiv , 2025 2025
Identification of Potential Biomarkers for Diabetes Mellitus Using Gene Expression Datasets, Machine Learning, and R Packages to Predict the Risk of Diabetes S Jena, P Kumar, D Mishra, M Khan Artificial Intelligence in Healthcare, 47-76 , 2024 2024
Early Detection of Diabetic Foot Ulcers Using Optical Flow–Based Ensemble Learning CNN Framework B Singh, P Kumar, M Khan Artificial Intelligence in Healthcare, 26-46 , 2024 2024 Citations: 1
A Nonlinear Fractional Order Optical Flow and CNN Based Framework for Fire Prediction Using Smoke Features NK Mahala, M Khan, P Kumar 2024 OPJU International Technology Conference (OTCON) on Smart Computing for … , 2024 2024 Citations: 1
A nonlinear fractional order variational model for the robust estimation of optical flow A Kumar, B Singh, M Khan, P Kumar 2024 OPJU International Technology Conference (OTCON) on Smart Computing for … , 2024 2024
Integration of Visual SLAM in Robot-Assisted Minimally Invasive Surgery: Advances, Challenges, and Solutions M Khan, F Siepel, T Ruers European Robotics Forum, 399-404 , 2024 2024 Citations: 1
Caputo derivative based nonlinear fractional order variational model for motion estimation in various application oriented spectrum M Khan, NK Mahala, P Kumar Sādhanā 49 (1), 1-28 , 2024 2024 Citations: 12
A Relative Analysis of Different CNN Based Models for COVID-19 Detection using CXR and CT Images P Kumar, D Jayaswal, M Khan, B Singh Procedia Computer Science 235, 3163-3173 , 2024 2024 Citations: 2
Ensemble learning and skip connection-based CNN framework for COVID-19 identification using CXR and CT images PK Muzammil Khan, Bhavana Singh International Journal of Computational Vision and Robotics , 2024 2024
CNN-Based Fire Prediction Using Fractional Order Optical Flow and Smoke Features M Khan, P Kumar, NK Mahala Applications of Optimization and Machine Learning in Image Processing and IoT , 2023 2023 Citations: 6
A Non-Local Weighted Fractional Order Variational Model for Smoke Detection Using Deep Learning Models NK Mahala, M Khan, P Kumar TENCON 2023-2023 IEEE Region 10 Conference (TENCON), 146-151 , 2023 2023 Citations: 2
Fire Detection Using Level Set Segmentation Based Fractional Order Optical Flow and 4D Fire Features with Mixed Data CNN-LSTM Model M Khan, P Kumar TENCON 2023-2023 IEEE Region 10 Conference (TENCON), 152-157 , 2023 2023 Citations: 1
Smoke Detection Using its Static and Dynamic Features Based on Fractional Order Optical Flow and Deep Learning Models for Fire Prediction M Khan, NK Mahala, P Kumar 2023 14th International Conference on Computing Communication and Networking … , 2023 2023 Citations: 1
Study of Various Deep Learning Models for COVID-19 Detection Based on Fractional Order Optical Flow B Singh, M Khan, P Kumar 2023 14th International Conference on Computing Communication and Networking … , 2023 2023 Citations: 1
Prediction of Fire Signatures Based on Fractional Order Optical Flow and Convolution Neural Network S Gupta, M Khan, P Kumar Computer Vision and Image Processing: 7th International Conference, CVIP … , 2023 2023 Citations: 3
A Segmentation Based Robust Fractional Variational Model for Motion Estimation P Kumar, M Khan, NK Mahala Computer Vision and Image Processing: 7th International Conference, CVIP … , 2023 2023 Citations: 2
A level set based fractional order variational model for motion estimation in application oriented spectrum M Khan, P Kumar Expert Systems with Applications, 119628 , 2023 2023 Citations: 16
MOST CITED SCHOLAR PUBLICATIONS
A nonlinear modeling of fractional order based variational model in optical flow estimation M Khan, P Kumar Optik 261, 169136 , 2022 2022.0 Citations: 27
A level set based fractional order variational model for motion estimation in application oriented spectrum M Khan, P Kumar Expert Systems with Applications, 119628 , 2023 2023.0 Citations: 16
Caputo derivative based nonlinear fractional order variational model for motion estimation in various application oriented spectrum M Khan, NK Mahala, P Kumar Sādhanā 49 (1), 1-28 , 2024 2024.0 Citations: 12
Development of an IR Video Surveillance System Based on Fractional Order TV-Model P Kumar, M Khan, S Gupta 2021 International Conference on Control, Automation, Power and Signal … , 2021 2021.0 Citations: 9
CNN-Based Fire Prediction Using Fractional Order Optical Flow and Smoke Features M Khan, P Kumar, NK Mahala Applications of Optimization and Machine Learning in Image Processing and IoT , 2023 2023.0 Citations: 6
Charbonnier-Marchaud Based Fractional Variational Model for Motion Estimation in Multispectral Vision System P Kumar, M Khan Journal of Physics: Conference Series 2327 (1), 012031 , 2022 2022.0 Citations: 6
Early Prediction of COVID-19 Suspects Based on Fractional Order Optical Flow P Kumar, M Khan 2021 5th International Conference on Information Systems and Computer … , 2021 2021.0 Citations: 5
Prediction of Fire Signatures Based on Fractional Order Optical Flow and Convolution Neural Network S Gupta, M Khan, P Kumar Computer Vision and Image Processing: 7th International Conference, CVIP … , 2023 2023.0 Citations: 3
A Relative Analysis of Different CNN Based Models for COVID-19 Detection using CXR and CT Images P Kumar, D Jayaswal, M Khan, B Singh Procedia Computer Science 235, 3163-3173 , 2024 2024.0 Citations: 2
A Non-Local Weighted Fractional Order Variational Model for Smoke Detection Using Deep Learning Models NK Mahala, M Khan, P Kumar TENCON 2023-2023 IEEE Region 10 Conference (TENCON), 146-151 , 2023 2023.0 Citations: 2
A Segmentation Based Robust Fractional Variational Model for Motion Estimation P Kumar, M Khan, NK Mahala Computer Vision and Image Processing: 7th International Conference, CVIP … , 2023 2023.0 Citations: 2
A Vision Based Fractional Order TV-Model for Underwater Motion Estimation M Khan, P Kumar 2021 IEEE Bombay Section Signature Conference (IBSSC), 1-6 , 2021 2021.0 Citations: 2
Unifying Scale-Aware Depth Prediction and Perceptual Priors for Monocular Endoscope Pose Estimation and Tissue Reconstruction M Khan, E Kerkhof, M Fusaglia, K Kuhlmann, T Ruers, FJ Siepel IEEE Access , 2026 2026.0 Citations: 1
Early Detection of Diabetic Foot Ulcers Using Optical Flow–Based Ensemble Learning CNN Framework B Singh, P Kumar, M Khan Artificial Intelligence in Healthcare, 26-46 , 2024 2024.0 Citations: 1
A Nonlinear Fractional Order Optical Flow and CNN Based Framework for Fire Prediction Using Smoke Features NK Mahala, M Khan, P Kumar 2024 OPJU International Technology Conference (OTCON) on Smart Computing for … , 2024 2024.0 Citations: 1
Integration of Visual SLAM in Robot-Assisted Minimally Invasive Surgery: Advances, Challenges, and Solutions M Khan, F Siepel, T Ruers European Robotics Forum, 399-404 , 2024 2024.0 Citations: 1
Fire Detection Using Level Set Segmentation Based Fractional Order Optical Flow and 4D Fire Features with Mixed Data CNN-LSTM Model M Khan, P Kumar TENCON 2023-2023 IEEE Region 10 Conference (TENCON), 152-157 , 2023 2023.0 Citations: 1
Smoke Detection Using its Static and Dynamic Features Based on Fractional Order Optical Flow and Deep Learning Models for Fire Prediction M Khan, NK Mahala, P Kumar 2023 14th International Conference on Computing Communication and Networking … , 2023 2023.0 Citations: 1
Study of Various Deep Learning Models for COVID-19 Detection Based on Fractional Order Optical Flow B Singh, M Khan, P Kumar 2023 14th International Conference on Computing Communication and Networking … , 2023 2023.0 Citations: 1
Leveraging Mixed Data Cnn-Lstm with Fractional Order Optical Flow for Early Fire Detection and Xai-Guided Segmentation M Khan, NK Mahala, P Kumar Available at SSRN 5372325 , 0 Citations: 1