Software-defined networking (SDN) is becoming the standard for the management of networks due to its scalability and flexibility to program the network. SDN provides many advantages but it also involves some specific security problems; for example, the controller can be taken down using cyber attacks, which can result in the whole network shutting down, creating a single point of failure. In this paper, DDoS attacks in SDN are detected using AI-enabled machine and deep learning models with some specific features for a dataset under normal DDoS traffic. In our approach, the initial dataset is collected from 84 features on Kaggle and then the 20 top features are selected using a permutation importance algorithm. The dataset is learned and tested with five AI-enabled models. Our experimental results show that the use of a machine learning-based random forest model achieves the highest accuracy rate of 99.97% in DDoS attack detection in SDN. Our contributions through this study are, firstly, that we found the top 20 features that contributed to DDoS attacks. Secondly, we reduce the time and cost of comparing various learning models and their performance in determining a learning model suitable for DDoS detection. Finally, various experimental methods to evaluate the performance of the learning model are presented so that related researchers can utilize them.

In this paper, a large-capacity white light source module using a high-power blue laser diode and a reflective spaced phosphor was designed. The reflective spacing phosphor ensured thermal stability. The proposed white light module is a reflective phosphor structure with a bi-directional optical system based on a rhombus prism lens. The rhombus prism optical system can greatly narrow the blue laser beam width and a long-wavelength band-pass filter of 500 $\mathrm{nm}$ or more is applied to change the movement path of the laser beam and transmit white light excited by the phosphor. A dichroic filter was applied to the fold mirror part and a planar convex lens was designed to focus the blue laser beam so that the phosphor was irradiated. Finally, a high-power white light source is obtained from the pre-optics unit to which the dichroic filter is applied. In order to use the proposed white light source as a searchlight, a divergence angle of 4° or less is required. For this implementation, a large-area collimating lens combining an aspheric condensing lens and an achromatic lens was applied. It was confirmed that the divergence angle of 4 degrees or less was satisfied at the focal length (FL) of 38.5 to 42.5 mm of the optical lens of the laser white light module emitter and the collimating optical system.

Software Defined Networking (SDN) is positioning the standard for the management of networks due to its scalability and flexibility to program the network. The SDN provides many advantages but it also involves some specific security problems take down the controller using cyber attack and in result the whole network will shut down which makes it a single point of failure. In this paper, the DDoS attacks in SDN were detected using AI-enabled, machine and deep learning, models with some specific features for data-set under normal and DDoS traffic. In our approach, initial data-set is collected from 84 features on kaggle and then the 20 top most features are selected using permutation importance algorithm. The data-set were learned and tested with AI-enabled 5 models. Our experimental results showed that the use of machine learning based random forest model has achieved the highest accuracy rate of 99.97%, in DDoS attack detection in SDN. Our contributions through this study are, first, we found highest 20 attacks that absolutely contributed to DDoS attacks. Secondly, it can reduce the time and cost of comparing various learning models and performance required for determining a learning model suitable for DDoS detection. Finally, various experimental methods for evaluating the performance of the learning model are presented so that related researchers can utilize them.

We present a variable-rate learned image compression (LIC) model that integrates Transformer-based quantization–reconstruction (QR) offset prediction, entropy-guided hyper-latent quantization, and perceptually informed multi-objective optimization. Unlike existing LIC frameworks that train separate networks for each bitrate, the proposed method achieves continuous rate adaptation within a single model by dynamically balancing rate, distortion and perceptual objectives. Channel-wise asymmetric quantization and a composite loss combining MSE and LPIPS further enhance reconstruction fidelity and subjective quality. Experiments on the Kodak, CLIC2020 and Tecnick datasets show gains of +1.15 dB PSNR, +0.065 MS-SSIM, and −0.32 LPIPS relative to the baselines variable-rate method, while improving bitrate-control accuracy by 62.5%. With approximately 15% computational overhead, the framework achieves competitive compression efficiency and enhanced perceptual quality, offering a practical solution for adaptive, high-quality image delivery.

Object detection has evolved from classical feature-based methods to deep-learning frameworks, with the YOLO (You Only Look Once) family becoming one of the most widely adopted paradigms for real-time detection. Despite rapid architectural change from YOLOv1 to YOLO26, the literature remains fragmented, lacking a unified synthesis that integrates structural innovations, quantitative benchmarking, and domain-specific deployment. This review provides a longitudinal analysis of the YOLO lineage—from Darknet backbones to hypergraph-enhanced correlation modeling (YOLOv13) and end-to-end, NMS-free architectures (YOLO26), and from anchor-based to anchor-free, decoupled, and end-to-end heads. We compile and harmonize source-reported metrics (mAP, FPS, FLOPs, parameters) across canonical datasets (PASCAL VOC, MS COCO, KITTI) and domain benchmarks, treating the result as a cross-source synthesis rather than hardware-normalized re-benchmarking. Recent 2025–2026 advances are highlighted: YOLOv13 reports a +3.0% mAP@[0.5:0.95] gain over YOLO11-N (38.6%→41.6%) through high-order correlation modeling, while YOLO26 reports up to 43% faster CPU inference relative to YOLO11. Through a multi-sector analysis across seven application domains, we map design choices to operational constraints, identify persistent challenges (domain generalization, small-object localization, open-set detection), and outline a research agenda emphasizing hybrid correlation-enhancement architectures, deployment-centric training, data-efficient learning, and sustainability-aware benchmarking.