Multitask Learning-Based Pipeline-Parallel Computation Offloading Architecture for Deep Face Analysis by Faris S. Alghareb, Balqees Talal Hasan

“…Nevertheless, the superior accuracy of a DNN is achieved at the expense of intensive computations and storage complexity, requiring custom expandable hardware, i.e., graphics processing units (GPUs). Interestingly, leveraging the synergy of parallelism and edge computing can significantly improve CPU-based hardware platforms. …”
Get full text

Optimal Computation Offloading Decisions Based on System Utility and Cost Balance by Bingxue Zhang, Xisheng Li, Jia You

“…Edge computing provides terminal users with computing resources and data processing capabilities by deploying edge nodes near Internet of Things (IoT) devices to meet the processing demands of terminal applications. …”
Get full text

D2D computation task offloading for efficient federated learning by Xiaoran CAI, Xiaopeng MO, Jie XU

“…Federated learning is a kind of distributed machine learning technique.The factor of communication and computation resource constraints at the edge node is becoming the performance bottleneck.In particular,when different edge node has distinct computation and communication capabilities,the model training performance may degrade severely,thus necessitating the joint communication and computation optimization.To tackle this challenge,a computational task offloading scheme enabled by device-to-device (D2D) communications was proposed,in which different edge node exchanged data samples via D2D communication links to balance the processing capability and task load,in order to minimize the total time delay for machine learning model training.Simulation results show that compared to the benchmark scheme without such D2D task offloading the training speed and efficiency of federated learning has be improved significantly.…”
Get full text

ELD-YOLO: A Lightweight Framework for Detecting Occluded Mandarin Fruits in Plant Research by Xianyao Wang, Yutong Huang, Siyu Wei, Weize Xu, Xiangsen Zhu, Jiong Mu, Xiaoyan Chen

“…Our method incorporates edge-aware processing to strengthen feature representation, introduces a streamlined detection head that balances accuracy with computational cost, and employs an adaptive upsampling strategy to minimize information loss during feature scaling. …”
Get full text

Efficient attention vision transformers for monocular depth estimation on resource-limited hardware by Claudio Schiavella, Lorenzo Cirillo, Lorenzo Papa, Paolo Russo, Irene Amerini

Get full text

An Automated Method for Detection and Enumeration of Olive Trees Through Remote Sensing by Muhammad Waleed, Tai-Won Um, Aftab Khan, Zubair Ahmad

“…The proposed technique comprises of multi-step image processing techniques applied over a single band of imagery. …”
Get full text

Spike-RISC: Algorithm/ISA Co-Optimization for Efficient SNNs on RISC-V by Ipek Akdeniz, Sandy A. Wasif, Paul R. Genssler, Hussam Amrouch

“…The sparsity-aware vector unit processes the fully connected layers avoiding unnecessary computations. …”
Get full text

Toward Energy Efficiency and Fairness in UAV-Based Task Offloading by Mohamed El-Emary, Ali Ranjha, Diala Naboulsi, Razvan Stanica

“…The rising demand for compute-intensive mobile applications challenges the limited energy and processing power of user equipment (UE). While Mobile Edge Computing (MEC) enables task offloading to nearby servers, deploying fixed MEC infrastructure is often impractical in settings like disaster zones or temporary high-density events. …”
Get full text

DSC-Net: Enhancing Blind Road Semantic Segmentation with Visual Sensor Using a Dual-Branch Swin-CNN Architecture by Ying Yuan, Yu Du, Yan Ma, Hejun Lv

“…The hybrid attention module (HAM), embedded within the Inverted Residual Module (IRM), sharpens the detection of blind road boundaries, while the IRM improves the speed of network processing. In tests on a specialized dataset designed for blind road semantic segmentation in real-world scenarios, our method achieved an impressive mIoU of 97.72%. …”
Get full text

A Comprehensive Review on ISAC for 6G: Enabling Technologies, Security, and AI/ML Perspectives by Sultan Aldirmaz-Colak, Mustafa Namdar, Arif Basgumus, Serdar Ozyurt, Selman Kulac, Nurullah Calik, Mehmet Akif Yazici, Ahmet Serbes, Lutfiye Durak-Ata

“…We explore the roles of innovative functions in enabling ISAC, including joint waveform design, edge computing, vehicular sensing and communications, and their practical applications. …”
Get full text

Mangrove Extraction Algorithm Based on Orthogonal Matching Filter-Weighted Least Squares by Yongze Li, Jin Ma, Dongyang Fu, Jiajun Yuan, Dazhao Liu

“…WLS filtering precisely processes high-frequency noise and edge details in images using an adaptive weighting matrix, significantly improving the edge clarity and overall quality of mangrove images. …”
Get full text

YOLO-SW: A Real-Time Weed Detection Model for Soybean Fields Using Swin Transformer and RT-DETR by Yizhou Shuai, Jingsha Shi, Yi Li, Shaohao Zhou, Lihua Zhang, Jiong Mu

Get full text

Power balance and divertor asymmetries in the Super-X divertors of MAST-U using SOLPS-ITER by I. Paradela Pérez, B. Lomanowski, J.D. Lore, J. Lovell, D. Moulton, MAST Upgrade team

Get full text

Parallel CUDA-Based Optimization of the Intersection Calculation Process in the Greiner–Hormann Algorithm by Jiwei Zuo, Junfu Fan, Kuan Li, Qingyun Liu, Yuke Zhou, Yi Zhang

“…To address the time-consuming intersection calculation process in the Greiner–Hormann algorithm, this paper presents two kernel functions that implement a GPU parallel improvement algorithm based on CUDA multi-threading. …”
Get full text

Bora Bora, the “pearl of the Pacific”: heritage processes, tourist image and power relationships by Frédérique Jossinet

“…It will show how the juxtaposition of these processes produces relations of power which unbalances the socio-ecological system. …”
Get full text

Deformation mechanism under essential work of fracture process in polycyclo-olefin materials

“…The fracture toughness of a glassy polycyclo-olefin (PCO) was investigated by the essential work of fracture (EWF) method using a double-edge notched specimens. It was shown that the PCO follows the EWF concept in the temperature range between room temperature and glass transition temperature Tg where the ligament yielding appear at a maximum point on the stress-displacement curves and subsequently the necking and tearing processes take place in the post yielding region. …”
Get full text

Image processing with Optical matrix vector multipliers implemented for encoding and decoding tasks by Minjoo Kim, Yelim Kim, Won Il Park

“…Our results demonstrate that ONN-based systems have the potential to surpass the energy efficiency of traditional electronic systems, enabling real-time, low-power image processing in applications such as medical imaging, autonomous vehicles, and edge computing.…”
Get full text

A molecular dynamics study of the sputtering processes of beryllium species by hydrogenic plasma by Alexander Liptak, Kerry D. Lawson, Mohammad I. Hasan

“…Abstract The plasma-facing components of nuclear fusion reactors are continuously subjected to high thermal loads and bombardment by hydrogenic ions, resulting in erosion of the first-wall material and sputtering of atomic and molecular species into the edge plasma. The management of reactor component lifetimes and control of sputtered plasma impurities remain open problems in fusion research, where quantifying the sputtering yields and understanding the sputtering processes of each impurity species is pivotal for planning an effective maintenance schedule and ensuring optimal plasma performance. …”
Get full text

PRIORITISATION OF FERRY COMMUTERS’ NEEDS IN LAGOS METROPOLIS: AN ANALYTICAL HIERARCHICAL PROCESS APPROACH by Eke Christy HART, Sulaimon Olanrewaju ADEBIYI, Olamilekan Gbenga OYENUGA

“…Thus, this study employs the analytical hierarchy process (AHP) to prioritise the ferry services needs of commuters to make effective managerial decisions that will aid efficiency in their operations, thereby, increasing the market penetration, competitive edge and commuter satisfaction. …”
Get full text

Parallelizing analog in-sensor visual processing with arrays of gate-tunable silicon photodetectors by Zheshun Xiong, Wen Liang, Meiyue Zhang, Dacheng Mao, Qiangfei Xia, Guangyu Xu

“…Here we present two scalable in-sensor visual processing arrays based on dual-gate silicon photodiodes, enabling parallelized event sensing and edge detection, respectively. …”
Get full text