Application of Object Contrast for Forming Images Used in Technical Vision Systems for Navigation of Mobile Robots by Tymochko O., Boichenko О., Zakirov S., Holovniak D., Dmitriiev O., Padalka I.

Get full text

Neural architecture codesign for fast physics applications by Jason Weitz, Dmitri Demler, Luke McDermott, Nhan Tran, Javier Duarte

“…Our method employs neural architecture search and network compression in a two-stage approach to discover hardware efficient models. This approach consists of a global search stage that explores a wide range of architectures while considering hardware constraints, followed by a local search stage that fine-tunes and compresses the most promising candidates. …”
Get full text

Energy-aware federated learning for secure edge computing in 5G-enabled IoT networks by Milad Rahmati

“…To address these challenges, we propose an energy-aware federated learning (EAFL) framework, integrating adaptive client selection, quantization-aware model updates, and blockchain-enhanced security mechanisms to improve both energy efficiency and resistance to model poisoning attacks and adversarial gradient manipulations. …”
Get full text

Cooperative Detection for Cell-Free Massive MIMO With Multiple Central Processing Units Under Backhaul Capacity Limitation by Faurdoir Ndimumahoro, Koji Ishibashi

Get full text

An Intelligent Smart Dynamic Feature Analysis Based Approach by Utilizing Deep Learning to Improve the Breast Cancer Detection by Seong-O Shim, Lal Hussain, Eesa Alsolami, Monagi H. Alkinani

“…The model was also trained using Quantization aware training (QAT) to enable efficient deployment on low-resource devices without significant performance degradation. …”
Get full text

A survey of model compression techniques: past, present, and future by Defu Liu, Yixiao Zhu, Zhe Liu, Yi Liu, Changlin Han, Jinkai Tian, Ruihao Li, Wei Yi

“…To meet the urgent demand for efficient deployment, we delve into several compression methods—such as quantization, pruning, low-rank decomposition, and knowledge distillation—emphasizing their fundamental principles, recent advancements, and innovative strategies. …”
Get full text

Effective thermal conductivity and inner transfer surface of porous and fibrous materials on the example of foodstuffs by Yu. V. Svetlov, Yu. B. Nikiforov

Get full text

Optimized Ensemble Deep Learning for Real-Time Intrusion Detection on Resource-Constrained Raspberry Pi Devices by Muhammad Bisri Musthafa, Samsul Huda, Tuy Tan Nguyen, Yuta Kodera, Yasuyuki Nogami

“…The proposed system maintains high detection performance with accuracy of 97.3% across all test scenarios, while efficiently leveraging multi-core processing with peak CPU usage reaching 111.8%. …”
Get full text

Collaborative Learning for Task-Oriented Semantic Communications: Overcoming Data Mismatch Between Transceivers by Yanhu Wang, Ruidong Li, Changhong Wang, Jia Ye, Chenyuan Feng, Shuaishuai Guo

“…Task-oriented semantic communication (ToSC) enhances efficiency and performance by leveraging task-specific data representations and end-to-end learning, which are more compact and effective than traditional reconstruction-oriented methods. …”
Get full text

An all integer-based spiking neural network with dynamic threshold adaptation by Chenglong Zou, Chenglong Zou, Xiaoxin Cui, Shuo Feng, Guang Chen, Yi Zhong, Zhenhui Dai, Yuan Wang

“…Due to this all integer-based quantization process, the required computational operations are significantly reduced, potentially providing a substantial energy efficiency advantage for numerous edge computing applications.…”
Get full text

Sports activity in functional systems theory by N. A. Fudin, Yu. E. Vagin

“…The article demonstrates the efficiency of the systemic approach to analyze athletes' reserve capacity increase resulting from fatigue and physical performance decrease resulting from overfatigue.…”
Get full text

Deep Learning Model Compression and Hardware Acceleration for High-Performance Foreign Material Detection on Poultry Meat Using NIR Hyperspectral Imaging by Zirak Khan, Seung-Chul Yoon, Suchendra M. Bhandarkar

“…Ensuring the safety and quality of poultry products requires efficient detection and removal of foreign materials during processing. …”
Get full text

Low-Power Branch CNN Hardware Accelerator with Early Exit for UAV Disaster Detection Using 16 nm CMOS Technology by Yu-Pei Liang, Wen-Chin Chao, Ching-Che Chung

“…This paper presents a disaster detection framework based on aerial imagery, utilizing a Branch Convolutional Neural Network (B-CNN) to enhance feature learning efficiency. The B-CNN architecture incorporates branch training, enabling effective training and inference with reduced model parameters. …”
Get full text

Low-Memory-Footprint CNN-Based Biomedical Signal Processing for Wearable Devices by Zahra Kokhazad, Dimitrios Gkountelos, Milad Kokhazadeh, Charalampos Bournas, Georgios Keramidas, Vasilios Kelefouras

“…On the other hand, various DNN compression techniques have been proposed, but exploiting the combination of various compression techniques with the aim of achieving memory efficient DNN models for HAR and CDC tasks remains under-investigated. …”
Get full text

Omni directional video coding rate distortion optimization method based on weighted-to-spherically-uniform structural similarity by Yufeng ZHOU, Mei YU, Baozhen DU, Yang SONG, Gangyi JIANG

“…Aiming at the shortcomings of the coding rate distortion model in traditional video coding,considering the characteristics of equal rectangular omnidirectional video,a method of omnidirectional video coding rate distortion optimization based on spherical weighted structural similarity (WS-SSIM) was proposed.By considering the distortion of the internal structural similarity of the projection plane and the relationship between the spherical distortion and the projection plane distortion,the “spherical weighted structural similarity” was proposed to describe the degree of distortion of the planar omnidirectional image local block relative to the viewing sphere,which was applied to the rate-distortion optimization process of omnidirectional video coding and adaptive selection of quantization parameters to improve vision-based coding efficiency.The experimental results show that compared with the HEVC video coding standard HM16.9 test platform,the proposed method can save an average of 24.48% code rate under the same visual quality,which indicates that the method has significant performance for improving the omnidirectional video coding rate distortion performance.…”
Get full text

Continual Learning With Neuromorphic Computing: Foundations, Methods, and Emerging Applications by Mishal Fatima Minhas, Rachmad Vidya Wicaksana Putra, Falah Awwad, Osman Hasan, Muhammad Shafique

“…The challenging deployment of compute- and memory-intensive methods from Deep Neural Network (DNN)-based Continual Learning (CL), underscores the critical need for a paradigm shift towards more efficient approaches. Neuromorphic Continual Learning (NCL) appears as an emerging solution, by leveraging the principles of Spiking Neural Networks (SNNs) and their inherent advantages (e.g., sparse spike-driven operations and bio-plausible learning rules) for improving energy efficiency and performance, thereby enabling efficient CL algorithms (e.g., unsupervised learning approach) executed in dynamically-changed environments with resource-constrained computing systems. …”
Get full text

Perception-Based H.264/AVC Video Coding for Resource-Constrained and Low-Bit-Rate Applications by Lih-Jen Kau, Chin-Kun Tseng, Ming-Xian Lee

“…With the rapid expansion of Internet of Things (IoT) and edge computing applications, efficient video transmission under constrained bandwidth and limited computational resources has become increasingly critical. …”
Get full text

Construction of a Scientific Literature AI Data System for the Thematic Scenario: Technical Framework Research and Practice by Zhijun CHANG, Li QIAN, Yaoting WU, Yunpeng QU, Yue GONG, Zhixiong ZHANG

Get full text

Robust Model Predictive Control for AFE-Inverter Drives With Common Mode Voltage Elimination by S.M. Muslem Uddin, Galina Mirzaeva, Graham C. Goodwin

“…The main feature of the proposed MPC is elimination of Common Mode Voltage (CMV) without imposing a penalty on the corresponding term in the cost function, but rather by a smart utilisation of the restricted set of switching states in a computationally efficient algorithm. Furthermore, the paper proposes to split the conventional MPC scheme into separate Control and Modulation stages, and to enhance the Control stage by integral action, and the Modulation stage - by a Feedback Quantizer. …”
Get full text

A Dynamic Adaptive Framework for Remote Sensing Imagery Superpixel Segmentation and Classification via Dual-Branch Feature Learning by Wangtun Yang, Yang Zhang, Heng Zhang, Liangzhi Li

“…Ablation studies further confirm the efficiency and necessity of various components in the model design. …”
Get full text