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

Probing the Pitfalls: Understanding SVD’s Shortcomings in Language Model Compression by Сергей Александрович Плетенев

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

Speed up integer-arithmetic-only inference via bit-shifting by Mingjun Song, Yiming Zhou, Mengmeng Song, Sujie Liu, Shungen Xiao, Youshun Zheng

“…Integer-arithmetic-only quantization is an important approach in quantization and holds great significance for hardware deployment with limited resources. …”
Get full text

Enhanced Vehicle Tracking With Discretization Error Control for OFDM-Based Radar System by Seong-Hwan Hyun, Jiho Song, Keunwoo Kim, Jong-Ho Lee, Seong-Cheol Kim

“…However, the discrete sample acquisition process inherent in OFDM radar introduces quantization errors in the measured distance and relative velocity. …”
Get full text

Design Optimization of Feedforward Equalization for Mobile Fronthaul Based on Delta-Sigma Modulation With High-Order QAM Signals by Jianghao Li, Yangsheng Yuan, Yangjian Cai

“…Delta-sigma modulation can be used as a high spectral efficiency interface in place of conventional common public radio interface (CPRI) in mobile fronthaul (MFH) networks. …”
Get full text

A multi-chroma format cascaded coding method for full-chroma image in AVS2 by Liping ZHAO, Tao LIN, Kailun ZHOU, Keli HU, Chunmei LIN

“…In the second generation of audio video coding standard (AVS2),a multi-chroma format cascaded coding method (MCFCC) for full-chroma (4:4:4 sampling format) images coding was proposed.The MCFCC algorithm firstly converts the 4:4:4 sampling format image into 4:2:0 sampling format image,then the 4:2:0 sampling format image was processed by 4:2:0 sampling format intra prediction,transform,quantization,inverse quantization,inverse transform,entropy coding and a weighted 4:4:4 sampling format distortion calculation method in the rate-distortion optimization process,finally 4:4:4 sampling format in-loop filtering and offset algorithms were applied to the 4:4:4 sampling format image after up sampling.The experimental results show that,for full-chroma natural images,the MCFCC algorithm achieves higher coding efficiency at very low additional encoding complexity and very low additional design and implementation cost.…”
Get full text

Nuclei segmentation and classification from histopathology images using federated learning for end-edge platform. by Anjir Ahmed Chowdhury, S M Hasan Mahmud, Md Palash Uddin, Seifedine Kadry, Jung-Yeon Kim, Yunyoung Nam

“…To protect data privacy, the framework employs a FedAvg-based federated learning scheme, enabling decentralized training without exposing sensitive data. For efficient deployment on edge devices, full integer quantization is applied to reduce computational overhead while maintaining accuracy. …”
Get full text

GHMSA-Net: Gated Hierarchical Multi-Scale Self-Attention for Perceptually-Guided AV1 Post-Processing by Bopu Zhao, Woowoen Gwun, Kiho Choi

“…The AOMedia Video 1 (AV1) codec achieves excellent compression efficiency but often introduces visually distracting artifacts at high quantization parameters (QPs), impairing perceptual quality. …”
Get full text

BinaryViT: Binary Vision Transformer for Hyperspectral Image Classification by Xiang Hu, Taolin Liu, Zhe Guo, Yuxiang Tang, Yuanxi Peng, Tong Zhou

“…However, binary quantization in transformers faces challenges such as degradation of feature representation capability after binarizing self-attention mechanisms and decline in fusion efficiency of multiscale spectral–spatial information, leading to relatively lagging progress in this field. …”
Get full text

Optimizing Semantic-Aware Video Compression Using Particle Swarm Optimization Technique for Automotive Applications by Vadivel Shanmugam, B. Uma Maheswari

“…This paper proposes a framework for semantic-aware video compression with reduced functional complexity and a proper flow for quantization parameter optimization. The optimized quantization factors used for encoding the region of interest and the region out of interest of the input video frame. …”
Get full text

Fast Backpropagation Neural Network for VQ-Image Compression by Basil Mahmood, Omaima AL-Allaf

“…<br />In this work, a three layered backpropagation neural network (BPNN) is designed to compress images using vector quantization technique (VQ).The results coming out from the hidden layer represent the codebook used in vector quantization, therefore this is a new method to generate VQ-codebook. …”
Get full text

Long-context inference optimization for large language models: a survey by TAO Wei, WANG Jianzong, ZHANG Xulong, QU Xiaoyang

“…However, long-text inference faces challenges such as high memory consumption and latency. To improve the efficiency of LLMs in long-text inference, a comprehensive review and analysis of existing optimization techniques were conducted. …”
Get full text

Long-context inference optimization for large language models: a survey by TAO Wei, WANG Jianzong, ZHANG Xulong, QU Xiaoyang

“…However, long-text inference faces challenges such as high memory consumption and latency. To improve the efficiency of LLMs in long-text inference, a comprehensive review and analysis of existing optimization techniques were conducted. …”
Get full text

Discrete Phase Shift IRS-Assisted Energy Harvesting in Cognitive Radio Networks With Spectrum Sensing by Lilian Chiru Kawala, Guoquan Li, Mihertie Habtamu Demeke, Junzhou Xiong, Hao Xiong, Hang Hu

“…These results highlight the transformative potential of IRS with discrete phase shifts in enhancing EH-CRN efficiency, particularly in improving energy harvesting and SU throughput under practical constraints.…”
Get full text

Vector signal processing techniques for all-optical networks by Zhen XING, Hongxiang WANG, Yuefeng JI

“…The all-optical vector signal processing technology is of great significance in the evolution of optical network due to its low delay and high efficiency.Therefore,a comprehensive introduction to the technical background and application scheme of the current all-optical signal processing was given.The all-optical signal modulation format was firstly introduced,and the basic characteristics and receiving modes of each modulation format were described.Furthermore,the nonlinear optical effects,which were the basis of all-optical signal processing,were classified and introduced.The occurrence conditions,occurrence process,optical phenomena and common nonlinear media were also illustrated.The advantages of all-optical signal processing technology were briefly introduced and three typical research fields of all-optical signal regeneration,all-optical format conversion and all-optical phase quantization were introduced in detail.Finally,the application prospect of future all-optical vector signal processing technology was prospected.…”
Get full text

Center Symmetric Local Multilevel Pattern Based Descriptor and Its Application in Image Matching by Hui Zeng, Xiuqing Wang, Yu Gu

“…The CS-LMP operator has no exponential computations, so the CS-LMP descriptor can encode the differences of the local intensity values using multiply quantization levels without increasing the dimension of the descriptor. …”
Get full text

Learned distributed image compression with decoder side information by Yankai Yin, Zhe Sun, Peiying Ruan, Ruidong Li, Feng Duan

“…Multi-view image compression aims to improve compression efficiency by leveraging correlations between images. …”
Get full text

Performance of massive MIMO‐NOMA systems with low complexity group SIC receivers and low‐resolution ADCs by Changliang Zheng, Kang Yang, Tielian Fu, Tianle Liu, Mengqi Yang

“…Employing the additive quantization noise model, we derive asymptotic approximate expressions of the spectrum efficiency for the system with group successive interference cancellation (GSIC) receivers over Rician fading channels. …”
Get full text

Federated Learning for Brain Tumor Diagnosis: Methods, Challenges and Future Prospects by Ma Yuhan

“…Techniques like knowledge distillation, model quantization, and pruning are proposed to enhance computational efficiency and minimize communication costs. …”
Get full text