Muhammad Burhan Khan
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Muhammad Burhan Khan has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Humaira Nisar
Department of Electronic Engineering, Universiti Tunku Abdul Rahman, Kampar, Malaysia
3 shared publications Choon Aun Ng
Department of Environmental Engineering, Universiti Tunku Abdul Rahman, Jalan Universiti, Bandar Barat 31900, Kampar, Malaysia
2 shared publications- Aqsa Aslam
Department of Computer Science, National University of Computer and Emerging Sciences, Karachi 75030, Pakistan
1 shared publication - Attaullah Y. Memon
Department of Electronics & Power Engineering, PN Engineering College, National University of Science and Technology, Karachi 75350, Pakistan
1 shared publication Chuanbo Li
1 shared publicationDileep Kumar
1 shared publication
Latest Publications
- Open Access
CIRS: A Multi-Agent Machine Learning Framework for Real-Time Accident Detection and Emergency Response
Road traffic accidents remain a leading cause of fatalities worldwide, and the consequences are considerably worsened by delayed detection and emergency response. Although several machine learning-based approaches have been proposed, accident detection systems are not widely deployed, and most existing solutions fail to handle the growing complexity of modern traffic environments. This study introduces Collaborative Intelligence for Road Safety (CIRS), a novel, multi-agent, machine-learning-based framework designed for real-time accident detection, semantic scene understanding, and coordinated emergency response. Each agent in CIRS is designed for a distinct role perception, classification, description, localization, and decision-making, working collaboratively to enhance situational awareness and response efficiency. These agents integrate advanced models: YOLOv11 for high-accuracy accident detection and VideoLLaMA3 for contextual-rich scene description. CIRS bridges the gap between low-level visual analysis and high-level situational awareness. Extensive evaluation on a custom dataset comprising (5200 accident, 4800 nonaccident) frames demonstrates the effectiveness of the proposed approach. YOLOv11 achieves a top-1 accuracy of 86.5% and a perfect top-5 accuracy of 100%, ensuring reliable real-time detection. VideoLLaMA3 outperforms other vision-language models with superior factual accuracy and fewer hallucinations, generating strong results in the metrics of BLEU (0.0755), METEOR (0.2258), and ROUGE-L (0.3625). The decentralized multi-agent architecture of CIRS enables scalability, reduced latency, and the timely dispatch of emergency services while minimizing false positives.
Open AccessCIRS: A Multi-Agent Machine Learning Framework for Real-Time Accident Detection and Emergency Response
Road traffic accidents remain a leading cause of fatalities worldwide, and the consequences are considerably worsened by delayed detection and emergency response. Although several machine learning-based approaches have been proposed, accident detection systems are not widely deployed, and most existing solutions fail to handle the growing complexity of modern traffic environments. This study introduces Collaborative Intelligence for Road Safety (CIRS), a novel, multi-agent, machine-learning-based framework designed for real-time accident detection, semantic scene understanding, and coordinated emergency response. Each agent in CIRS is designed for a distinct role perception, classification, description, localization, and decision-making, working collaboratively to enhance situational awareness and response efficiency. These agents integrate advanced models: YOLOv11 for high-accuracy accident detection and VideoLLaMA3 for contextual-rich scene description. CIRS bridges the gap between low-level visual analysis and high-level situational awareness. Extensive evaluation on a custom dataset comprising (5200 accident, 4800 nonaccident) frames demonstrates the effectiveness of the proposed approach. YOLOv11 achieves a top-1 accuracy of 86.5% and a perfect top-5 accuracy of 100%, ensuring reliable real-time detection. VideoLLaMA3 outperforms other vision-language models with superior factual accuracy and fewer hallucinations, generating strong results in the metrics of BLEU (0.0755), METEOR (0.2258), and ROUGE-L (0.3625). The decentralized multi-agent architecture of CIRS enables scalability, reduced latency, and the timely dispatch of emergency services while minimizing false positives.
- Open Access
Robust Output Feedback Stabilization and Tracking for an Uncertain Nonholonomic Systems with Application to a Mobile Robot
This paper presents a novel robust output feedback control that simultaneously performs both stabilization and trajectory tracking for a class of underactuated nonholonomic systems despite model uncertainties, external disturbance, and the absence of velocity measurement. To solve this challenging problem, a generalized normal form has been successfully created by employing an input–output feedback linearization approach and a change in coordinates (diffeomorphism). This research mainly focuses on the stabilization problem of nonholonomic systems that can be transformed to a normal form and pose several challenges, including (i) a nontriangular normal form, (ii) the internal dynamics of the system are non-affine in control, and (iii) the zero dynamics of the system are not in minimum phase. The proposed scheme utilizes combined backstepping and sliding mode control (SMC) techniques. Furthermore, the full-order high gain observer (HGO) has been developed to estimate the derivative of output functions and internal dynamics. Then, full-order HGO and the backstepping SMC have been integrated to synthesize a robust output feedback controller. A differential-drive type (2,0) the wheeled mobile robot has been considered as an example to support the theoretical results. The simulation results demonstrate that the backstepping SMC exhibits robustness against bounded uncertainties.
Open AccessRobust Output Feedback Stabilization and Tracking for an Uncertain Nonholonomic Systems with Application to a Mobile Robot
This paper presents a novel robust output feedback control that simultaneously performs both stabilization and trajectory tracking for a class of underactuated nonholonomic systems despite model uncertainties, external disturbance, and the absence of velocity measurement. To solve this challenging problem, a generalized normal form has been successfully created by employing an input–output feedback linearization approach and a change in coordinates (diffeomorphism). This research mainly focuses on the stabilization problem of nonholonomic systems that can be transformed to a normal form and pose several challenges, including (i) a nontriangular normal form, (ii) the internal dynamics of the system are non-affine in control, and (iii) the zero dynamics of the system are not in minimum phase. The proposed scheme utilizes combined backstepping and sliding mode control (SMC) techniques. Furthermore, the full-order high gain observer (HGO) has been developed to estimate the derivative of output functions and internal dynamics. Then, full-order HGO and the backstepping SMC have been integrated to synthesize a robust output feedback controller. A differential-drive type (2,0) the wheeled mobile robot has been considered as an example to support the theoretical results. The simulation results demonstrate that the backstepping SMC exhibits robustness against bounded uncertainties.
- 31 May 2022
- Published by Elsevier in Materials Science in Semiconductor Processing
- Vol. 148
Recent progress in Ti3C2Tx-based materials: From fundamentals to emerging applications
- 31 May 2022
- Published by Elsevier in Materials Science in Semiconductor Processing
- Vol. 148
Recent progress in Ti3C2Tx-based materials: From fundamentals to emerging applications
- 18 September 2019
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2157 (1) , 020004
Image stitching of microscopic wastewater images
In this paper, image stitching strategy is proposed to prepare a virtual slide image of the sample of activated sludge obtained from the wastewater treatment plant. The bright-field microscopic images have inherent problem of vignetting and less contrast, which result into failed image registration by conventional methods. Our method involves illumination correction, image segmentation, image registration and finally, image stitching. First, flat-field correction method is applied to all the acquired field of views (FOVs) to balance the illumination on each FOV. In the second step, adaptive thresholding method is employed to segment all the acquired FOVs to convert into binary images. This step is meant to increase the accuracy of finding the overlapping region during image registration. Then, phase correlation is used to find the overlapping region between images in horizontal direction during image stitching for each row of the microscopy slide, and in vertical direction subsequently for image stitching between the rows. The proposed method has been compared with the state-of-the-art algorithms using subjective inspection, and no reference evaluation indices of entropy and clarity. From the evaluation, we had observed that the proposed method performs better.
- 18 September 2019
- Published by AIP Publishing in AIP Conference Proceedings
- Vol. 2157 (1) , 020004
Image stitching of microscopic wastewater images
In this paper, image stitching strategy is proposed to prepare a virtual slide image of the sample of activated sludge obtained from the wastewater treatment plant. The bright-field microscopic images have inherent problem of vignetting and less contrast, which result into failed image registration by conventional methods. Our method involves illumination correction, image segmentation, image registration and finally, image stitching. First, flat-field correction method is applied to all the acquired field of views (FOVs) to balance the illumination on each FOV. In the second step, adaptive thresholding method is employed to segment all the acquired FOVs to convert into binary images. This step is meant to increase the accuracy of finding the overlapping region during image registration. Then, phase correlation is used to find the overlapping region between images in horizontal direction during image stitching for each row of the microscopy slide, and in vertical direction subsequently for image stitching between the rows. The proposed method has been compared with the state-of-the-art algorithms using subjective inspection, and no reference evaluation indices of entropy and clarity. From the evaluation, we had observed that the proposed method performs better.
- Open Access
- 18 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 1778-1791
Image Processing and Analysis of Phase-Contrast Microscopic Images of Activated Sludge to Monitor the Wastewater Treatment Plants
Image processing and analysis is useful to monitor the activated sludge (AS) wastewater treatment plants based on the morphology of microbial aggregates (flocs) and filamentous bacteria. Phase-contrast microscopy is used to observe filamentous bacteria in the AS samples at lower objective magnification with improved visibility of details. However, segmentation of the phase-contrast images faces inherent difficulties caused by the artifacts associated with the microscopy, such as halos and shade-off. This work mainly comprises of three tasks: robust segmentation of phase-contrast images for filamentous bacteria, identification of novel image analysis parameters for morphology of the bacteria, and use of the proposed parameters to model sludge volume index (SVI). SVI is the most important physical measurement employed to monitor the operation of an AS plant. In this paper, a robust phase congruency based method, augmented by top-hat and bottom-hat filtering, is proposed for segmentation of filamentous bacteria. Different metrics like accuracy, recall, variation of information, F-measure and Rand index are used for the segmentation assessment. We propose an exact procedure to determine the total length of branched and unbranched filamentous bacteria. Moreover, a novel rotation invariant feature is proposed to determine the extent of the curvature of a filament. Finally, we investigated regression models for SVI of multiple AS wastewater treatment plants, based on the proposed image analysis parameters of the filaments. The modelling of SVI proves the significance of the proposed image analysis parameters for monitoring AS plants.
- 18 December 2017
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 6, 1778-1791
Open AccessImage Processing and Analysis of Phase-Contrast Microscopic Images of Activated Sludge to Monitor the Wastewater Treatment Plants
Image processing and analysis is useful to monitor the activated sludge (AS) wastewater treatment plants based on the morphology of microbial aggregates (flocs) and filamentous bacteria. Phase-contrast microscopy is used to observe filamentous bacteria in the AS samples at lower objective magnification with improved visibility of details. However, segmentation of the phase-contrast images faces inherent difficulties caused by the artifacts associated with the microscopy, such as halos and shade-off. This work mainly comprises of three tasks: robust segmentation of phase-contrast images for filamentous bacteria, identification of novel image analysis parameters for morphology of the bacteria, and use of the proposed parameters to model sludge volume index (SVI). SVI is the most important physical measurement employed to monitor the operation of an AS plant. In this paper, a robust phase congruency based method, augmented by top-hat and bottom-hat filtering, is proposed for segmentation of filamentous bacteria. Different metrics like accuracy, recall, variation of information, F-measure and Rand index are used for the segmentation assessment. We propose an exact procedure to determine the total length of branched and unbranched filamentous bacteria. Moreover, a novel rotation invariant feature is proposed to determine the extent of the curvature of a filament. Finally, we investigated regression models for SVI of multiple AS wastewater treatment plants, based on the proposed image analysis parameters of the filaments. The modelling of SVI proves the significance of the proposed image analysis parameters for monitoring AS plants.
- 24 February 2017
- Published by Taylor & Francis in Environmental Technology
- Vol. 39 (1) , 24-34
Generalized classification modeling of activated sludge process based on microscopic image analysis
The state of activated sludge wastewater treatment process (AS WWTP) is conventionally identified by physico-chemical measurements which are costly, time-consuming and have associated environmental hazards. Image processing and analysis-based linear regression modeling has been used to monitor the AS WWTP. But it is plant- and state-specific in the sense that it cannot be generalized to multiple plants and states. Generalized classification modeling for state identification is the main objective of this work. By generalized classification, we mean that the identification model does not require any prior information about the state of the plant, and the resultant identification is valid for any plant in any state. In this paper, the generalized classification model for the AS process is proposed based on features extracted using morphological parameters of flocs. The images of the AS samples, collected from aeration tanks of nine plants, are acquired through bright-field microscopy. Feature-selection is performed in context of classification using sequential feature selection and least absolute shrinkage and selection operator. A support vector machine (SVM)-based state identification strategy was proposed with a new agreement solver module for imbalanced data of the states of AS plants. The classification results were compared with state-of-the-art multiclass SVMs (one-vs.-one and one-vs.-all), and ensemble classifiers using the performance metrics: accuracy, recall, specificity, precision, F measure and kappa coefficient (κ). The proposed strategy exhibits better results by identification of different states of different plants with accuracy 0.9423, and κ 0.6681 for the minority class data of bulking.
- 24 February 2017
- Published by Taylor & Francis in Environmental Technology
- Vol. 39 (1) , 24-34
Generalized classification modeling of activated sludge process based on microscopic image analysis
The state of activated sludge wastewater treatment process (AS WWTP) is conventionally identified by physico-chemical measurements which are costly, time-consuming and have associated environmental hazards. Image processing and analysis-based linear regression modeling has been used to monitor the AS WWTP. But it is plant- and state-specific in the sense that it cannot be generalized to multiple plants and states. Generalized classification modeling for state identification is the main objective of this work. By generalized classification, we mean that the identification model does not require any prior information about the state of the plant, and the resultant identification is valid for any plant in any state. In this paper, the generalized classification model for the AS process is proposed based on features extracted using morphological parameters of flocs. The images of the AS samples, collected from aeration tanks of nine plants, are acquired through bright-field microscopy. Feature-selection is performed in context of classification using sequential feature selection and least absolute shrinkage and selection operator. A support vector machine (SVM)-based state identification strategy was proposed with a new agreement solver module for imbalanced data of the states of AS plants. The classification results were compared with state-of-the-art multiclass SVMs (one-vs.-one and one-vs.-all), and ensemble classifiers using the performance metrics: accuracy, recall, specificity, precision, F measure and kappa coefficient (κ). The proposed strategy exhibits better results by identification of different states of different plants with accuracy 0.9423, and κ 0.6681 for the minority class data of bulking.