Nowadays, there is an ever-increasing deployment of intelligent edge devices, such as smartphones, wearable devices, and autonomous vehicles. It is enabled by the integration of advanced sensors with higher computing capabilities and widespread internet availability. These edge devices generate a vast amount of data that can be utilized for better inference. However, due to privacy concerns, communication overhead, processing delay, and security issues, traditional machine learning (ML) algorithms face challenges that work in a centralized fashion where all the available data is accumulated beforehand. Federated learning (FL) is a new distributed on-device learning method that generates a global model through the collaboration of edge devices without compromising data privacy. In this paper, we propose a federated transfer learning (FTL) model considering clients’ heterogeneity in terms of their available computing resources and model architecture. We simulate the training performance of heterogeneous clients and observe that clients with sufficient resources require significantly lower computational time. In turn, the resource-constrained clients take notably higher computational time to accomplish a given task. Inspired by that, we design an FL model that constructs multiple global models based on the available resources of the clients and carries out a separate training process for each of the global models. We demonstrate the effectiveness of our proposed strategy by evaluating our FL model on CFAR100 dataset. Our findings show that training time differs significantly among the heterogeneous clients and assigning multiple global models can notably improve convergence time.

Small-object detection plays a critical role in real-time aerial, Unmanned Aerial Vehicle (UAV), and satellite vision systems, as well as many other domains, where hardware constraints and deployment environments demand high accuracy, low latency, and energy efficiency. Although numerous lightweight object detectors have been proposed, there exists a lack of rigorous, cross-platform benchmarks that evaluate these models under consistent conditions for small-object-focused applications. This paper presents a comprehensive comparative evaluation of eight recent lightweight You Look Only Once (YOLO)-based models, including YOLOX-Nano and YOLOv6–v12 variants. Models are trained using a unified pipeline and evaluated on three representative datasets: VisDrone2019, DOTA-v1.5, and xView. Performance is assessed on both cloud GPUs (NVIDIA A100) and an edge AI platform (Jetson Orin Nano), using PyTorch and TensorRT (FP16) runtimes. The evaluation metrics include mAP@0.5, mAP@0.5:0.95, F1-score, latency, FPS, memory footprint, and energy consumption (via VDD_IN telemetry). Experimental results demonstrate that YOLOv8-Nano and YOLOv9-Tiny achieve leading accuracy across datasets, while YOLOv6-Nano and YOLOv10-Nano offer favorable trade-offs in speed and memory. TensorRT optimization yields 3×–5× speedup over PyTorch. Energy draw ranges from 7.6 W to 10.4 W, depending on the model and configuration. Pareto frontiers reveal that no single model dominates across all objectives. The study highlights the importance of multi-objective benchmarking in edge AI and provides practical guidance for selecting detectors based on deployment-specific constraints. The findings support theory-driven and application-oriented advancement of efficient detection architectures for real-time, resource-aware computer vision systems.

This study evaluates the adoption of DevSecOps among small and medium-sized enterprises (SMEs), identifying key challenges, best practices, and future trends. Through a mixed methods approach backed by the Technology Acceptance Model (TAM) and Diffusion of Innovations (DOI) theory, we analyzed survey data from 405 SME professionals, revealing that while 68% have implemented DevSecOps, adoption is hindered by technical complexity (41 %), resource constraints (35 %), and cultural resistance (38 %). Despite strong leadership prioritization of security (73 %), automation gaps persist, with only 12 % of organizations conducting security scans per commit. Our findings highlight a growing integration of security tools, particularly API security (63 %) and software composition analysis (62 %), although container security adoption remains low (34 %). Looking ahead, SMEs anticipate artificial intelligence and machine learning to significantly influence DevSecOps, under-scoring the need for proactive adoption of AI -driven security enhancements. Based on our findings, this research proposes strategic best practices to enhance CI/CD) pipeline security including automation, leadership-driven security culture, and cross-team collaboration.

The novel Coronavirus Disease 2019 (COVID-19) is a global pandemic that has infected millions of people causing millions of deaths around the world. Reverse Transcription Polymerase Chain Reaction (RT-PCR) is the standard screening method for COVID-19 detection but it requires specific molecular-biology training. Moreover, the general workflow is difficult e.g. sample collection, processing time, and analysis expertise, etc. Chest radiographic image analysis can be a good alternative screening method that is faster, more efficient, and requires minimal clinical or molecular biology trained laboratory personnel. Early studies have shown that abnormalities on the chest radiographic images are likely to be the consequence of COVID-19 infection. In this study, we propose DeepCOVIDNet, a deep learning based COVID-19 detection model. Our proposed deep-learning model is a multiclass classifier that can distinguish COVID-19, viral pneumonia, bacterial pneumonia, and healthy chest X-ray images. Our proposed model classifies radiographic images into four distinct classes and achieves the accuracy of 89.47% along with a high degree of precision, recall and F1 score. On a different dataset setting (COVID-19, bacterial pneumonia, viral pneumonia) our model achieves the maximum accuracy of 98.25%. We demonstrate generalizability of our proposed method using 5-fold cross validation for COVID-19 vs pneumonia and COVID-19 vs healthy classification that also manifests promising results.