arXiv subjects

Zeeshan Kaleem

Publications and source records attributed to Zeeshan Kaleem.

18 recordsLinked to original sources

arXiv2026

Rate-Aware Quantum-Inspired Trajectory Learning for Interference-Limited Multi-UAV Networks

Unmanned aerial vehicle (UAV) can provide on-demand, high-capacity connectivity in disaster and normal situation. However, it faces a challenge of curse of dimensionality in trajectory optimization, where interference-limited environments and vast search spaces make real-time coordination computationally expensive. To overcome this challenge, we propose the Rate-Aware Quantum-Annealed Graph Condensation (RA-QAGC) scheme, which combines rate-aware graph abstraction with decentralized reinforcement learning to enable scalable, interference-aware UAV coordination. By identifying high throughput locations and guiding UAV trajectory adaptation toward throughput-optimal regions, RA-QAGC effectively balances network capacity by maintaining quality-of-service (QoS) requirements. Simulation results demonstrate the proposal outperformed over existing schemes by achieving 59.4 Mbps total throughput and 23.9 Mbps priority-user throughput, representing gains of approximately 15% and 34%, respectively, over the baseline schemes.

cs.MA↗

arXiv2026

Depth-Aware Image and Video Orientation Estimation

This paper introduces a novel approach for image and video orientation estimation by leveraging depth distribution in natural images. The proposed method estimates the orientation based on the depth distribution across different quadrants of the image, providing a robust framework for orientation estimation suited for applications such as virtual reality (VR), augmented reality (AR), autonomous navigation, and interactive surveillance systems. To further enhance fine-scale perceptual alignment, we incorporate depth gradient consistency (DGC) and horizontal symmetry analysis (HSA), enabling precise orientation correction. This hybrid strategy effectively exploits depth cues to support spatial coherence and perceptual stability in immersive visual content. Qualitative and quantitative evaluations demonstrate the robustness and accuracy of the proposed approach, outperforming existing techniques across diverse scenarios.

cs.CV↗

arXiv2025

Quantum-Driven State-Reduction for Reliable UAV Trajectory Optimization in Low-Altitude Networks

This letter introduces a Graph-Condensed Quantum-Inspired Placement (GC-QAP) framework for reliability-driven trajectory optimization in Uncrewed Aerial Vehicle (UAV) assisted low-altitude wireless networks. The dense waypoint graph is condensed using probabilistic quantum-annealing to preserve interference-aware centroids while reducing the control state space and maintaining link-quality. The resulting problem is formulated as a priority-aware Markov decision process and solved using epsilon-greedy off-policy Q-learning, considering UAV kinematic and flight corridor constraints. Unlike complex continuous-action reinforcement learning approaches, GC-QAP achieves stable convergence and low outage with substantially and lower computational cost compared to baseline schemes.

eess.SY↗

arXiv2025

Reward-Augmented Reinforcement Learning for Continuous Control in Precision Autonomous Parking via Policy Optimization Methods

Autonomous parking (AP) represents a critical yet complex subset of intelligent vehicle automation, characterized by tight spatial constraints, frequent close-range obstacle interactions, and stringent safety margins. However, conventional rule-based and model-predictive methods often lack the adaptability and generalization needed to handle the nonlinear and environment-dependent complexities of AP. To address these limitations, we propose a reward-augmented learning framework for AP (RARLAP), that mitigates the inherent complexities of continuous-domain control by leveraging structured reward design to induce smooth and adaptable policy behavior, trained entirely within a high-fidelity Unity-based custom 3D simulation environment. We systematically design and assess three structured reward strategies: goal-only reward (GOR), dense proximity reward (DPR), and milestone-augmented reward (MAR), each integrated with both on-policy and off-policy optimization paradigms. Empirical evaluations demonstrate that the on-policy MAR achieves a 91\% success rate, yielding smoother trajectories and more robust behavior, while GOR and DPR fail to guide effective learning. Convergence and trajectory analyses demonstrate that the proposed framework enhances policy adaptability, accelerates training, and improves safety in continuous control. Overall, RARLAP establishes that reward augmentation effectively addresses complex autonomous parking challenges, enabling scalable and efficient policy optimization with both on- and off-policy methods. To support reproducibility, the code accompanying this paper is publicly available.

cs.RO↗

arXiv2025

Quantum Skyshield: Quantum Key Distribution and Post-Quantum Authentication for Low-Altitude Wireless Networks in Adverse Skies

Recently, low-altitude wireless networks (LAWNs) have emerged as a critical backbone for supporting the low-altitude economy, particularly with the densification of unmanned aerial vehicles (UAVs) and high-altitude platforms (HAPs). To meet growing data demands, some LAWN deployments incorporate free-space optical (FSO) links, which offer exceptional bandwidth and beam directivity. However, without strong security measures in place, both conventional radio frequency channels and FSO beams remain vulnerable to interception and spoofing and FSO in particular can suffer from turbulence, misalignment, and weather-related attenuation. To address these challenges in the quantum era, a quantum-secure architecture called Quantum Skyshield is proposed to enable reliable communication between the base transceiver station (BTS) and LAWN. The proposed design integrates BB84 quantum key distribution (QKD) with post-quantum authentication mechanisms. Simulation results confirm the reliable generation of a 128-bit symmetric key when the quantum bit error rate (QBER) remains below the threshold of 11%. Authentication is enforced using Lamport one-time signatures and hash-based message authentication codes (HMAC) to ensure message integrity. A Grover-inspired threat detection mechanism identifies anomalies with up to 89% probability in a single iteration, enabling real-time trust evaluation. Lastly, future research challenges have also been identified and discussed to guide further development in this area.

cs.CR↗

arXiv2025

SMSAT: A Multimodal Acoustic Dataset and Deep Contrastive Learning Framework for Affective and Physiological Modeling of Spiritual Meditation

Understanding how auditory stimuli influence emotional and physiological states is fundamental to advancing affective computing and mental health technologies. In this paper, we present a multimodal evaluation of the affective and physiological impacts of three auditory conditions, that is, spiritual meditation (SM), music (M), and natural silence (NS), using a comprehensive suite of biometric signal measures. To facilitate this analysis, we introduce the Spiritual, Music, Silence Acoustic Time Series (SMSAT) dataset, a novel benchmark comprising acoustic time series (ATS) signals recorded under controlled exposure protocols, with careful attention to demographic diversity and experimental consistency. To model the auditory induced states, we develop a contrastive learning based SMSAT audio encoder that extracts highly discriminative embeddings from ATS data, achieving 99.99% classification accuracy in interclass and intraclass evaluations. Furthermore, we propose the Calmness Analysis Model (CAM), a deep learning framework integrating 25 handcrafted and learned features for affective state classification across auditory conditions, attaining robust 99.99% classification accuracy. In contrast, pairwise t tests reveal significant deviations in cardiac response characteristics (CRC) between SM analysis via ANOVA inducing more significant physiological fluctuations. Compared to existing state of the art methods reporting accuracies up to 90%, the proposed model demonstrates substantial performance gains (up to 99%). This work contributes a validated multimodal dataset and a scalable deep learning framework for affective computing applications in stress monitoring, mental well-being, and therapeutic audio-based interventions.

cs.SD↗

arXiv2024

How to deal with glare for improved perception of Autonomous Vehicles

Vision sensors are versatile and can capture a wide range of visual cues, such as color, texture, shape, and depth. This versatility, along with the relatively inexpensive availability of machine vision cameras, played an important role in adopting vision-based environment perception systems in autonomous vehicles (AVs). However, vision-based perception systems can be easily affected by glare in the presence of a bright source of light, such as the sun or the headlights of the oncoming vehicle at night or simply by light reflecting off snow or ice-covered surfaces; scenarios encountered frequently during driving. In this paper, we investigate various glare reduction techniques, including the proposed saturated pixel-aware glare reduction technique for improved performance of the computer vision (CV) tasks employed by the perception layer of AVs. We evaluate these glare reduction methods based on various performance metrics of the CV algorithms used by the perception layer. Specifically, we considered object detection, object recognition, object tracking, depth estimation, and lane detection which are crucial for autonomous driving. The experimental findings validate the efficacy of the proposed glare reduction approach, showcasing enhanced performance across diverse perception tasks and remarkable resilience against varying levels of glare.

cs.CV↗

arXiv2024

Efficient UAVs Deployment and Resource Allocation in UAV-Relay Assisted Public Safety Networks for Video Transmission

Wireless communication highly depends on the cellular ground base station (GBS). A failure of the cellular GBS, fully or partially, during natural or man-made disasters creates a communication gap in the disaster-affected areas. In such situations, public safety communication (PSC) can significantly save the national infrastructure, property, and lives. Throughout emergencies, the PSC can provide mission-critical communication and video transmission services in the affected area. Unmanned aerial vehicles (UAVs) as flying base stations (UAV-BSs) are particularly suitable for PSC services as they are flexible, mobile, and easily deployable. This manuscript considers a multi-UAV-assisted PSC network with an observational UAV receiving videos from the affected area's ground users (AGUs) and transmitting them to the nearby GBS via a relay UAV. The objective of the proposed study is to maximize the average utility of the video streams generated by the AGUs upon reaching the GBS. This is achieved by optimizing the positions of the observational and relay UAVs, as well as the distribution of communication resources, such as bandwidth, and transmit power, while satisfying the system-designed constraints, such as transmission rate, rate outage probability, transmit power budget, and available bandwidth. To this end, a joint UAVs placement and resource allocation problem is mathematically formulated. The proposed problem poses a significant challenge for a solution. Considering the block coordinate descent and successive convex approximation techniques, an efficient iterative algorithm is proposed. Finally, simulation results are provided which show that our proposed approach outperforms the existing methods.

cs.NI↗

arXiv2023

Reconfigurable Intelligent Surface for Physical Layer Security in 6G-IoT: Designs, Issues, and Advances

Sixth-generation (6G) networks pose substantial security risks because confidential information is transmitted over wireless channels with a broadcast nature, and various attack vectors emerge. Physical layer security (PLS) exploits the dynamic characteristics of wireless environments to provide secure communications, while reconfigurable intelligent surfaces (RISs) can facilitate PLS by controlling wireless transmissions. With RIS-aided PLS, a lightweight security solution can be designed for low-end Internet of Things (IoT) devices, depending on the design scenario and communication objective. This article discusses RIS-aided PLS designs for 6G-IoT networks against eavesdropping and jamming attacks. The theoretical background and literature review of RIS-aided PLS are discussed, and design solutions related to resource allocation, beamforming, artificial noise, and cooperative communication are presented. We provide simulation results to show the effectiveness of RIS in terms of PLS. In addition, we examine the research issues and possible solutions for RIS modeling, channel modeling and estimation, optimization, and machine learning. Finally, we discuss recent advances, including STAR-RIS and malicious RIS.

cs.NI↗

arXiv2023

SafeSpace MFNet: Precise and Efficient MultiFeature Drone Detection Network

The increasing prevalence of unmanned aerial vehicles (UAVs), commonly known as drones, has generated a demand for reliable detection systems. The inappropriate use of drones presents potential security and privacy hazards, particularly concerning sensitive facilities. To overcome those obstacles, we proposed the concept of MultiFeatureNet (MFNet), a solution that enhances feature representation by capturing the most concentrated feature maps. Additionally, we present MultiFeatureNet-Feature Attention (MFNet-FA), a technique that adaptively weights different channels of the input feature maps. To meet the requirements of multi-scale detection, we presented the versions of MFNet and MFNet-FA, namely the small (S), medium (M), and large (L). The outcomes reveal notable performance enhancements. For optimal bird detection, MFNet-M (Ablation study 2) achieves an impressive precision of 99.8\%, while for UAV detection, MFNet-L (Ablation study 2) achieves a precision score of 97.2\%. Among the options, MFNet-FA-S (Ablation study 3) emerges as the most resource-efficient alternative, considering its small feature map size, computational demands (GFLOPs), and operational efficiency (in frame per second). This makes it particularly suitable for deployment on hardware with limited capabilities. Additionally, MFNet-FA-S (Ablation study 3) stands out for its swift real-time inference and multiple-object detection due to the incorporation of the FA module. The proposed MFNet-L with the focus module (Ablation study 2) demonstrates the most remarkable classification outcomes, boasting an average precision of 98.4\%, average recall of 96.6\%, average mean average precision (mAP) of 98.3\%, and average intersection over union (IoU) of 72.8\%. To encourage reproducible research, the dataset, and code for MFNet are freely available as an open-source project: github.com/ZeeshanKaleem/MultiFeatureNet.

cs.CV↗

arXiv2023

GAANet: Ghost Auto Anchor Network for Detecting Varying Size Drones in Dark

The usage of drones has tremendously increased in different sectors spanning from military to industrial applications. Despite all the benefits they offer, their misuse can lead to mishaps, and tackling them becomes more challenging particularly at night due to their small size and low visibility conditions. To overcome those limitations and improve the detection accuracy at night, we propose an object detector called Ghost Auto Anchor Network (GAANet) for infrared (IR) images. The detector uses a YOLOv5 core to address challenges in object detection for IR images, such as poor accuracy and a high false alarm rate caused by extended altitudes, poor lighting, and low image resolution. To improve performance, we implemented auto anchor calculation, modified the conventional convolution block to ghost-convolution, adjusted the input channel size, and used the AdamW optimizer. To enhance the precision of multiscale tiny object recognition, we also introduced an additional extra-small object feature extractor and detector. Experimental results in a custom IR dataset with multiple classes (birds, drones, planes, and helicopters) demonstrate that GAANet shows improvement compared to state-of-the-art detectors. In comparison to GhostNet-YOLOv5, GAANet has higher overall mean average precision (mAP@50), recall, and precision around 2.5\%, 2.3\%, and 1.4\%, respectively. The dataset and code for this paper are available as open source at https://github.com/ZeeshanKaleem/GhostAutoAnchorNet.

cs.CV↗

arXiv2022

Simultaneous Transmitting and Reflecting-Reconfigurable Intelligent Surface in 6G: Design Guidelines and Future Perspectives

Reconfigurable intelligent surfaces (RISs) have been considered as a promising technology for the sixth-generation (6G) wireless networks that can control wireless channels in a desirable way and significantly enhance the network performance. Simultaneous transmitting and reflecting-RISs (STAR-RISs) can overcome limitation of reflecting-only RISs by leveraging the higher design flexibility and full-space coverage. Despite the benefits, the modeling and analysis of STAR-RISs are complicated because of various control parameters for both transmission and reflection links. In this article, a general framework to facilitate the design and implementation of STAR-RISs in 6G scenarios and network topologies is presented. We provide a systematic introduction to the STAR-RIS operating protocols for different communication modes and discuss recent efforts to identify the research progress and combination solutions. Finally, we provide the design concepts, research challenges, potential solutions, and future directions related to the channel modeling, channel estimation, hardware implementations, modeling and limitations, and optimization.

cs.NI↗

arXiv2022

TF-Net: Deep Learning Empowered Tiny Feature Network for Night-time UAV Detection

Technological advancements have normalized the usage of unmanned aerial vehicles (UAVs) in every sector, spanning from military to commercial but they also pose serious security concerns due to their enhanced functionalities and easy access to private and highly secured areas. Several instances related to UAVs have raised security concerns, leading to UAV detection research studies. Visual techniques are widely adopted for UAV detection, but they perform poorly at night, in complex backgrounds, and in adverse weather conditions. Therefore, a robust night vision-based drone detection system is required to that could efficiently tackle this problem. Infrared cameras are increasingly used for nighttime surveillance due to their wide applications in night vision equipment. This paper uses a deep learning-based TinyFeatureNet (TF-Net), which is an improved version of YOLOv5s, to accurately detect UAVs during the night using infrared (IR) images. In the proposed TF-Net, we introduce architectural changes in the neck and backbone of the YOLOv5s. We also simulated four different YOLOv5 models (s,m,n,l) and proposed TF-Net for a fair comparison. The results showed better performance for the proposed TF-Net in terms of precision, IoU, GFLOPS, model size, and FPS compared to the YOLOv5s. TF-Net yielded the best results with 95.7\% precision, 84\% mAp, and 44.8\% $IoU$.

cs.CV↗

arXiv2020

A Reliable Link-adaptive Position-based Routing Protocol for Flying Ad hoc Network

Flying ad hoc network (FANET) provides portable and flexible communication for many applications and possesses several unique design challenges; a key one is the successful delivery of messages to the destination, reliably. For reliable communication, routing plays an important role, which establishes a path between source and destination on the basis of certain criteria. Conventional routing protocols of FANET generally use a minimum hop count criterion to find the best route between source and destination, which results in lower latency with the consideration that there is single source/destination network environment. However, in a network with multiple sources, the minimum hop count routing criterion along with the 1-Hop HELLO messages broadcasted by each node in the network may deteriorate the network performance in terms of high End-to-End (ETE) delay and decrease in the lifetime of the network. This research work proposes a Reliable link-adaptive position-based routing protocol (RLPR) for FANET. It uses relative speed, signal strength, and energy of the nodes along with the geographic distance towards the destination using a forwarding angle. This angle is used to determine the forwarding zone that decreases the undesirable control messages in the network in order to discover the route. RLPR enhances the network performance by selecting those relay nodes which are in the forwarding zone and whose geographic movement is towards the destination. Additionally, RLPR selects the next hop with better energy level and uses signal strength and relative speed of the nodes to achieve high connectivity-level. Based on the performance evaluation performed in the Network simulator (ns-2.35), it has been analysed that RLPR outperforms the Robust and reliable predictive based routing (RARP) and Ad hoc on-demand distance vector (AODV) protocols in different scenarios.

cs.NI↗

arXiv2020

RDSP: Rapidly Deployable Wireless Ad Hoc System for Post-Disaster Management

In post-disaster scenarios, such as after floods, earthquakes, and in war zones, the cellular communication infrastructure may be destroyed or seriously disrupted. In such emergency scenarios, it becomes very important for first aid responders to communicate with other rescue teams in order to provide feedback to both the central office and the disaster survivors. To address this issue, rapidly deployable systems are required to re-establish connectivity and assist users and first responders in the region of incident. In this work, we describe the design, implementation, and evaluation of a rapidly deployable system for first response applications in post-disaster situations, named RDSP. The proposed system helps early rescue responders and victims by sharing their location information to remotely located servers by utilizing a novel routing scheme. This novel routing scheme consists of the Dynamic ID Assignment (DIA) algorithm and the Minimum Maximum Neighbor (MMN) algorithm. The DIA algorithm is used by relay devices to dynamically select their IDs on the basis of all the available IDs of networks. Whereas, the MMN algorithm is used by the client and relay devices to dynamically select their next neighbor relays for the transmission of messages. The RDSP contains three devices; the client device sends the victim's location information to the server, the relay device relays information between client and server device, the server device receives messages from the client device to alert the rescue team. We deployed and evaluated our system in the outdoor environment of the university campus. The experimental results show that the RDSP system reduces the message delivery delay and improves the message delivery ratio with lower communication overhead.

cs.NI↗

arXiv2019

UAV-Empowered Disaster-Resilient Edge Architecture for Delay-Sensitive Communication

The fifth-generation (5G) communication systems will enable enhanced mobile broadband, ultra-reliable low latency, and massive connectivity services. The broadband and low-latency services are indispensable to public safety (PS) communication during natural or man-made disasters. Recently, the third generation partnership project long term evolution (3GPPLTE) has emerged as a promising candidate to enable broadband PS communications. In this article, first we present six major PS-LTE enabling services and the current status of PS-LTE in 3GPP releases. Then, we discuss the spectrum bands allocated for PS-LTE in major countries by international telecommunication union (ITU). Finally, we propose a disaster resilient three-layered architecture for PS-LTE (DR-PSLTE). This architecture consists of a software-defined network (SDN) layer to provide centralized control, an unmanned air vehicle (UAV) cloudlet layer to facilitate edge computing or to enable emergency communication link, and a radio access layer. The proposed architecture is flexible and combines the benefits of SDNs and edge computing to efficiently meet the delay requirements of various PS-LTE services. Numerical results verified that under the proposed DR-PSLTE architecture, delay is reduced by 20% as compared with the conventional centralized computing architecture.

cs.NI↗

arXiv2018

Block Error Rate and UE Throughput Performance Evaluation using LLS and SLS in 3GPP LTE Downlink

This paper provides a link and system level study of the downlink using OFDMA techniques based on LTE systems. At the link level, the Block Error Rate (BLER) performance curves are generated and 10 % points of BLER curves, calculated under SISO AWGN channel, are considered as reference to generate the SNR-to-CQI mapping. These mapping results are used in system level simulator (SLS) via MIESM link to system interface. Then the UE throughput is evaluated by considering proportional fair (PF), round robin (RR), and best CQI schedulers at different values of UE throughput CDF. In this paper we analyze that the PF scheduler outperforms other schedulers in fairness and average throughput, while the best CQI scheduler performs good under high SINR region. The RR is the best choice when resource allocation is to be done without considering any kind of channel condition.

cs.NI↗

arXiv2017

Amateur Drone Monitoring: State-of-the-Art Architectures, Key Enabling Technologies, and Future Research Directions

The unmanned air-vehicle (UAV) or mini-drones equipped with sensors are becoming increasingly popular for various commercial, industrial, and public-safety applications. However, drones with uncontrolled deployment poses challenges for highly security-sensitive areas such as President house, nuclear plants, and commercial areas because they can be used unlawfully. In this article, to cope with security-sensitive challenges, we propose point-to-point and flying ad-hoc network (FANET) architectures to assist the efficient deployment of monitoring drones (MDr). To capture amateur drone (ADr), MDr must have the capability to efficiently and timely detect, track, jam, and hunt the ADr. We discuss the capabilities of the existing detection, tracking, localization, and routing schemes and also present the limitations in these schemes as further research challenges. Moreover, the future challenges related to co-channel interference, channel model design, and cooperative schemes are discussed. Our findings indicate that MDr deployment is necessary for caring of ADr, and intensive research and development is required to fill the gaps in the existing technologies.

cs.NI↗