Muhammad Adam

Muhammad Adam

Computer and Information Sciences, Towson University, Towson, Maryland, USA
orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
21 September 2025 in Future Internet
Verified
Journal Article
Open access
PDF file
Muhammad AdamMuhammad Adam
Muhammad Adam
JSJianchao Song
Jianchao Song
Wei YuWei Yu
Wei Yu
QLqingqing li
qingqing li
Accurate livestock monitoring is critical for precision agriculture, supporting effective farm management, disease prevention, and sustainable resource allocation. Deep learning and remote sensing are recent technological advancements that have created auspicious opportunities for the development of livestock monitoring systems. This paper presents a comprehensive survey of deep learning approaches for automatic livestock detection in unmanned aerial vehicles (UAVs), highlighting key deep learning techniques, livestock detection challenges, and emerging trends. We analyze the innovations of popular deep learning models in the area of object detection, including You Look Only Once (YOLO) versions, Region-based Convolutional Neural Networks (RCNN), Anchor-based networks, and transformer models, to discuss their suitability for scalable and cost-efficient UAV-based livestock detection scenarios. To complement the survey, a case study is conducted on a custom UAV cattle dataset to benchmark representation detection models. Evaluation results demonstrate a trade-off between Precision, Recall, F1 score, IoU, mAP@50, mAP@50-95, inference speed, and model size. The case study results provide a clear understanding of selection and adapting deep learning models for UAV-based livestock monitoring and outline future directions for lightweight, domain-adapted frameworks in precision farming applications.

1 May 2026
Verified
Conference Paper
Closed access
Muhammad AdamMuhammad Adam
Muhammad Adam
VIVivian Ihekoronye
Vivian Ihekoronye
QLQingqing Li
Qingqing Li

25 April 2025 in AI & Cyber Forum: An International Journal
Verified
Journal Article
Closed access
AGAbdullahi Adam Galadima
Abdullahi Adam Galadima
UIUsman Idris Ismail
Usman Idris Ismail
EHEzeh Ikechukwu Harrison
Ezeh Ikechukwu Harrison
ECEwunonu Toochi Chima
Ewunonu Toochi Chima
Muhammad AdamMuhammad Adam
Muhammad Adam
MVMbamala Chinyere Vivian
Mbamala Chinyere Vivian
The static nature of conventional network configurations creates predictable attack surfaces that enable adversaries to perform efficient reconnaissance using automated scanning tools. This limitation is particularly critical at the early stage of cyber-attacks, where accurate network enumeration facilitates subsequent exploitation. To address this challenge, this paper proposes a lightweight Moving Target Defense (MTD) framework based on synchronized IP and port hopping to obscure network visibility and disrupt attacker reconnaissance activities. The proposed approach employs coordinated interface-level IP reconfiguration and Network Address Translation (NAT)-based port remapping to introduce continuous and unpredictable identifier mutation without relying on Software-Defined Networking (SDN) infrastructure or complex topology manipulation. The framework is implemented and evaluated in a controlled Mininet environment using an Nmap-driven attacker model. Experimental results show that the proposed system reduces reconnaissance success from 85% to 20%, significantly increases scan time, and generates high entropy in port distribution while maintaining service stability. These findings demonstrate that lightweight, host-level mutation strategies can effectively degrade attacker visibility and impose operational uncertainty. This work contributes a practical, low-overhead MTD solution suitable for deployment in resource-constrained environments, offering a viable alternative to more complex SDN-based defense mechanisms.