Muhammad Naeem
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
Research Subjects
Muhammad Naeem has a total of 21 co-authors. Here are the top co-authors by number of shared publications:
- Brian Nielsen
Aalborg University
3 shared publications - Cristina Seceleanu
Mälardalen University
3 shared publications - Kim Guldstrand Larsen
Aalborg University
3 shared publications - Michele Albano
Aalborg University
3 shared publications - Alf J. Isaksson
Corporate Research
1 shared publication Anders Høedholt
MONTEM A/S, Aarhus, Denmark
1 shared publication
Latest Publications
- Open Access
Spatial–Temporal Feature Fusion with Multi-Head Attention for Supervised Anomaly Localization
Localizing anomalous activities in surveillance video requires spatial appearance to be interpreted within its temporal context. This study presents a supervised dual-branch architecture that combines YOLOv8n features from a key frame with R3D-18 features from a 16-frame RGB clip. Channel projection and spatial alignment enable convolutional fusion of the two representations. Residual multi-head self-attention then models relationships among spatial positions in the fused feature map. Dense prediction heads estimate activity classes, objectness scores, and bounding boxes on the key frame. On the six categories of UCF-Crime2Local, the reference run without nonmaximum suppression (NMS) achieves 54.21% precision, 57.85% recall, and 53.44% . Across three training seeds, mean no-NMS is %. The finalized pipeline with class-aware NMS at IoU 0.5 achieves % across the same seeds. Values following ± denote sample standard deviations. The complete model exceeds the fusion-without-attention variant by 4.44 mAP percentage points under the common experimental protocol. Class-wise analysis, controlled component comparisons, repeated runs, and video-level uncertainty analysis characterize the model within the specified key-frame localization task. The accompanying implementation documents temporal sampling, annotation validation, optimization, checkpoint selection, and prediction export. Continuous-video evaluation derives event intervals from category-specific frame scores, achieving 57.78% event at temporal IoU 0.3 and a median onset delay of 0.80 s among matched events. These intervals are obtained through temporal postprocessing rather than a learned boundary-prediction head. Cross-dataset generalization and live-stream deployment remain to be evaluated.Open AccessSpatial–Temporal Feature Fusion with Multi-Head Attention for Supervised Anomaly Localization
Localizing anomalous activities in surveillance video requires spatial appearance to be interpreted within its temporal context. This study presents a supervised dual-branch architecture that combines YOLOv8n features from a key frame with R3D-18 features from a 16-frame RGB clip. Channel projection and spatial alignment enable convolutional fusion of the two representations. Residual multi-head self-attention then models relationships among spatial positions in the fused feature map. Dense prediction heads estimate activity classes, objectness scores, and bounding boxes on the key frame. On the six categories of UCF-Crime2Local, the reference run without nonmaximum suppression (NMS) achieves 54.21% precision, 57.85% recall, and 53.44% . Across three training seeds, mean no-NMS is %. The finalized pipeline with class-aware NMS at IoU 0.5 achieves % across the same seeds. Values following ± denote sample standard deviations. The complete model exceeds the fusion-without-attention variant by 4.44 mAP percentage points under the common experimental protocol. Class-wise analysis, controlled component comparisons, repeated runs, and video-level uncertainty analysis characterize the model within the specified key-frame localization task. The accompanying implementation documents temporal sampling, annotation validation, optimization, checkpoint selection, and prediction export. Continuous-video evaluation derives event intervals from category-specific frame scores, achieving 57.78% event at temporal IoU 0.3 and a median onset delay of 0.80 s among matched events. These intervals are obtained through temporal postprocessing rather than a learned boundary-prediction head. Cross-dataset generalization and live-stream deployment remain to be evaluated. - Open Access
- 18 May 2026
- Published by Springer Nature
- p. 711-729
Efficient Multi-level Mine Dewatering Using Uppaal Stratego
Effective water management in underground mining requires maintaining safe reservoir levels while minimizing the high energy costs of continuous pumping. Although flexible electricity pricing enables cost-aware operation, traditional threshold-based controllers cannot exploit this flexibility efficiently. This paper presents an industrial case study on efficient mine dewatering using reinforcement-learning-based control synthesized with the Uppaal Stratego framework. A baseline threshold controller is first implemented, followed by a reinforcement-learning controller trained on forecast inflows and day-ahead electricity prices to minimize pumping costs while limiting pump switching. To ensure safety during learning without distorting the optimization objective, we introduce a pre-shield that blocks unsafe transitions. We formally show that this pre-shield is maximally permissive with respect to a monotonicity safety objective. Simulation results demonstrate that the learning-based strategy reduces total energy consumption by up to 40% compared to threshold-based control, while maintaining safe operation in all scenarios.
- 18 May 2026
- Published by Springer Nature
- p. 711-729
Open AccessEfficient Multi-level Mine Dewatering Using Uppaal Stratego
Effective water management in underground mining requires maintaining safe reservoir levels while minimizing the high energy costs of continuous pumping. Although flexible electricity pricing enables cost-aware operation, traditional threshold-based controllers cannot exploit this flexibility efficiently. This paper presents an industrial case study on efficient mine dewatering using reinforcement-learning-based control synthesized with the Uppaal Stratego framework. A baseline threshold controller is first implemented, followed by a reinforcement-learning controller trained on forecast inflows and day-ahead electricity prices to minimize pumping costs while limiting pump switching. To ensure safety during learning without distorting the optimization objective, we introduce a pre-shield that blocks unsafe transitions. We formally show that this pre-shield is maximally permissive with respect to a monotonicity safety objective. Simulation results demonstrate that the learning-based strategy reduces total energy consumption by up to 40% compared to threshold-based control, while maintaining safe operation in all scenarios.
- 22 August 2025
- Published by Springer Nature
- p. 73-87
Safety-Aware Strategy Synthesis for Autonomous System of Systems with UPPAAL
- 22 August 2025
- Published by Springer Nature
- p. 73-87
Safety-Aware Strategy Synthesis for Autonomous System of Systems with UPPAAL
- 14 July 2024
- Published by Springer Nature
- p. 356-373
Energy-Efficient Motion Planning for Autonomous Vehicles Using Uppaal Stratego
- 14 July 2024
- Published by Springer Nature
- p. 356-373
Energy-Efficient Motion Planning for Autonomous Vehicles Using Uppaal Stratego
- Open Access
- 16 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 56334-56343
Modeling and Analysis of Cooperative Packet Recovery Protocol
Real-time audio/video transmission through Internet media is an important part of communication. Due to bandwidth limitations and a noisy environment, delivery of multimedia content to a remote location is not 100% guaranteed. These limitations are the basic cause of missing packets which affect the Quality of Service (QoS). A protocol for the recovery of lost packets is described in [Maxemchuk, Nicholas F., K. Padmanabhan, and S. Lo. “A cooperative packet recovery protocol for multicast video.” Network Protocols, 1997. Proc. of 1997 International Conference on. IEEE]. This protocol claims significant improvement in QoS. We formally specify the protocol in a network of timed automata. By model-checking (A mathematical technique), we find that packet recovery is not always there. In this article, We report such scenarios of malfunctioning in the protocol when the size of multimedia contents is known (e.g., live video/audio broadcasting) and middle-level servers have different rates of data sending and receiving. We formulate the effect of inter-packet delay and transmission speed difference on a buffer.
- 16 April 2024
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Access
- Vol. 12, 56334-56343
Open AccessModeling and Analysis of Cooperative Packet Recovery Protocol
Real-time audio/video transmission through Internet media is an important part of communication. Due to bandwidth limitations and a noisy environment, delivery of multimedia content to a remote location is not 100% guaranteed. These limitations are the basic cause of missing packets which affect the Quality of Service (QoS). A protocol for the recovery of lost packets is described in [Maxemchuk, Nicholas F., K. Padmanabhan, and S. Lo. “A cooperative packet recovery protocol for multicast video.” Network Protocols, 1997. Proc. of 1997 International Conference on. IEEE]. This protocol claims significant improvement in QoS. We formally specify the protocol in a network of timed automata. By model-checking (A mathematical technique), we find that packet recovery is not always there. In this article, We report such scenarios of malfunctioning in the protocol when the size of multimedia contents is known (e.g., live video/audio broadcasting) and middle-level servers have different rates of data sending and receiving. We formulate the effect of inter-packet delay and transmission speed difference on a buffer.
- 29 November 2023
- Published by Springer Nature
- p. 153-169
Comparative Analysis of Uppaal SMC, ns-3 and MATLAB/Simulink
- 29 November 2023
- Published by Springer Nature
- p. 153-169
Comparative Analysis of Uppaal SMC, ns-3 and MATLAB/Simulink
- 28 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (10) , 10577-10587
Modelling and Analysis of a Sigfox-Based IoT Network Using uppaalsmc
Wireless sensor nodes are usually powered by batteries that have limited energy capacity. In many applications, the nodes are installed in inaccessible locations where they are problematic to replace or recharge. Therefore, energy optimisation is crucial for increasing the node’s lifetime. This study presents a method for the analysis and prediction of the energy consumption of Sigfox-based Wireless Sensor Nodes. The method is illustrated in a use case where the nodes monitor the water level in drainage lines in cities to improve surface and wastewater management. We propose a formal model-based technique using the UPPAAL Statistical model checker tool to model and analyse the node’s lifetime. Statistical model checking provides a highly scalable technique for performance analysis of complex cyber-physical systems. The model captures the energy-related behaviour of the node, the Sigfox radio specification, and the sensor, each parameterised with values from the device’s datasheets. Furthermore, we calibrate the model using measurements obtained from real-world hardware. Finally, we evaluate a collection of strategies to optimise the battery lifetime of the node. We simulate the model with a 10,000 mAh battery, and the results indicate that we can extend the node’s lifetime from 202 days to 2.71 years using our most optimised transmission strategy.
- 28 March 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23 (10) , 10577-10587
Modelling and Analysis of a Sigfox-Based IoT Network Using uppaalsmc
Wireless sensor nodes are usually powered by batteries that have limited energy capacity. In many applications, the nodes are installed in inaccessible locations where they are problematic to replace or recharge. Therefore, energy optimisation is crucial for increasing the node’s lifetime. This study presents a method for the analysis and prediction of the energy consumption of Sigfox-based Wireless Sensor Nodes. The method is illustrated in a use case where the nodes monitor the water level in drainage lines in cities to improve surface and wastewater management. We propose a formal model-based technique using the UPPAAL Statistical model checker tool to model and analyse the node’s lifetime. Statistical model checking provides a highly scalable technique for performance analysis of complex cyber-physical systems. The model captures the energy-related behaviour of the node, the Sigfox radio specification, and the sensor, each parameterised with values from the device’s datasheets. Furthermore, we calibrate the model using measurements obtained from real-world hardware. Finally, we evaluate a collection of strategies to optimise the battery lifetime of the node. We simulate the model with a 10,000 mAh battery, and the results indicate that we can extend the node’s lifetime from 202 days to 2.71 years using our most optimised transmission strategy.