Towards Robust Speech Models: Mitigating Backdoor Attacks via Audio Signal Enhancement and Fine-Pruning Techniques by Heyan Sun, Qi Zhong, Minfeng Qi, Uno Fang, Guoyi Shi, Sanshuai Cui

“…Second, we apply an adaptive fine-pruning algorithm to selectively deactivate malicious neurons while preserving the model’s linguistic capabilities. …”
Get full text

A 3D acid fracturing design calibrated to describe the productivity index in several southwestern Iranian oil fields by Mohammad Mirhashemi, Kaveh Ahangari, Ali Naghi Dehghan, Kamran Goshtasbi

“…Once these parameters are stabilized, the algorithm proceeds to calculate acid concentration at each node within the fracture area. …”
Get full text

Human adaptation to adaptive machines converges to game-theoretic equilibria by Benjamin J. Chasnov, Lillian J. Ratliff, Samuel A. Burden

“…Surprisingly, one algorithm can steer the human-machine interaction to the machine’s optimum, effectively controlling the human’s actions even while the human responds optimally to their perceived cost landscape. …”
Get full text

Deep learning-based energy efficient LSFD weights prediction for user centric cell free massive MIMO system by Moustafa Mohamed, Salwa El-Ramly, Bassant Abdelhamid

“…These models are trained using dataset generated from heuristic sparse LSFD optimization algorithm, this allows the models to learn the sparsity nature of the system and apply AP-UE association based on the values of the predicted LSFD weights at the receiver side while using the large scale fading coefficients as the models’ input. …”
Get full text

Cross-layer scheduling and dynamic resource allocation for MIMO-OFDMA/SDMA systems with multi-service by ZHONG Chong-xian1, LI Chun-guo1, YANG Lv-xi1

“…Cross-layer scheduling and dynamic resource allocation problems were investigated for downlink MIMO-OFDMA/SDMA systems with multi-service.Firstly,a mathematical formulation of the optimization problem was provided with the objective of maximizing the total system throughput under various constraints.Secondly,a user group-ing scheme was proposed utilizing clustering analysis method based on the type of services and the spatial compatibility of multiple users with multiple receive antennas.Thirdly,a new cross-layer scheduling and dynamic resource allocation algorithm was developed based on the proposed user grouping scheme combined with the priorities of different service,which maximizes the total system throughput by maximizing the throughput of each subcarrier.Simulation results show that compared with the existing schemes,the proposed algorithms obtain reasonable throughput performance while provide better QoS requirement for each user of different services.…”
Get full text

Multifactor Stock Selection Strategy Based on Machine Learning: Evidence from China by Jieying Gao, Huan Guo, Xin Xu

“…The main findings are as follows: the support vector regression has the most stable successful rate for predicting, while ridge regression and linear regression have the most unstable successful rate with more extreme cases; algorithm of support vector regression fitting higher-degree polynomials in Chinese A-share market is optimized, compared with the traditional linear regression both in terms of stock return and retracement control; the results of support vector regression significantly outperforming the CSI 500 index prove further.…”
Get full text

A Correlational Study on Architectural Design and Thermal Distribution Patterns Using a Novel Multi-Terminal Approach in Cylindrical Li-Ion Cell-Integrated Battery Packs by Sagar D, Raja Ramar, Shama Ravichandran

“…This approach features a multi-terminal configuration, incorporating a modified battery pack structure along with a multi-terminal switching algorithm that identifies the optimal terminal for current flow to the load. …”
Get full text

End-to-end deep learning pipeline for real-time Bragg peak segmentation: from training to large-scale deployment by Cong Wang, Valerio Mariani, Frédéric Poitevin, Matthew Avaylon, Jana Thayer

“…We present an end-to-end deep learning pipeline with three key components: (1) a data engine that combines traditional algorithms with our peak matching algorithm to generate high-quality training data at scale, (2) a modular architecture that scales from a few million to hundreds of million parameters, enabling us to train large expert-level models offline while deploying smaller, distilled models at the edge, and (3) a decoupled producer-consumer architecture that separates specialized data source layer from model inference, enabling flexible deployment across diverse computing environments. …”
Get full text

Protein docking by the underestimation of free energy funnels in the space of encounter complexes. by Yang Shen, Ioannis Ch Paschalidis, Pirooz Vakili, Sandor Vajda

“…We describe a docking method based on stochastic global minimization of funnel-shaped energy functions in the space of rigid body motions (SE(3)) while accounting for flexibility of the interface side chains. …”
Get full text

Hierarchical energy management of distribution network with multi-microgrids based on double Stackelberg game by XIE Yuanhao, LIN Shenghong, ZHU Jianquan

“…In the external game, the distribution network as leader sets the prices, while microgrids as followers adjust their trading strategy with the distribution network. …”
Get full text

Minimum Error Integration Method for Quadrilateral Flat Plate Fitting in Steel Construction by Zhuoju Huang, Jiemin Ding

“…Current industry practices often approximate mildly curved surfaces with flat plates within tolerances, but optimizing this substitution to minimize fitting errors while reducing the quantity of curved plates remains a critical engineering challenge. …”
Get full text

Hybrid fuzzy logic approach for enhanced MPPT control in PV systems by Mustapha Melhaoui, Mohammed Rhiat, Mohammed Oukili, Ilias Atmane, Kamal Hirech, Badre Bossoufi, Mishari Metab Almalki, Thamer A. H. Alghamdi, Mohammed Alenezi

“…While conventional algorithms are widely used, their performance is limited under fluctuating conditions. …”
Get full text

FedACT: An adaptive chained training approach for federated learning in computing power networks by Min Wei, Qianying Zhao, Bo Lei, Yizhuo Cai, Yushun Zhang, Xing Zhang, Wenbo Wang

“…Second, we propose a Genetic-Algorithm-based Sorting (GAS) method to optimize the order of clients participating in training. …”
Get full text

Integrated Vehicle-to-Building and Vehicle-to-Home Services for Residential and Worksite Microgrids by Andrea Bonfiglio, Manuela Minetti, Riccardo Loggia, Lorenzo Frattale Mascioli, Andrea Golino, Cristina Moscatiello, Luigi Martirano

“…In particular, this paper describes the coordination between a battery management algorithm that optimally assigns its capacity so that at least a part is reserved for mobility and a vehicle-to-building (V2B) service algorithm that uses a share of EV battery energy to improve user participation in renewable energy exploitation at home and at work. …”
Get full text

QoS-Based Resource Allocation in Multicarrier NOMA-IBFD Cellular System With Sectorization by Ananda Kumar Karem, A. Krishna Chaitanya, Satya Kumar Vankayala, Seungil Yoon, Ganesh Chandrasekaran, Karthik Muralidhar

“…To address this, we introduce a heuristic approach aimed at optimizing subcarrier and power allocation with the goal of minimizing required downlink powers while ensuring QoS for each user. …”
Get full text

Research on a Surface Roughness Measurement Under ResNet-Based Roughness Classification and Light-Section With Seam-Driven Image Stitching (RCLS) by Huashen Guan, Qiushen Cai, Xiaobin Li, Guofu Sun

“…First, the images were classified with ResNet neural network, then stitched and enhanced by scale invariant feature transform (SIFT) and optimized random sample consensus (RANSAC) algorithm for the best visual effect. …”
Get full text

Multisegment Parallel Coregistration of Sentinel-1 SAR Time-Series Images by Combining OpenMP With MPI by Yonghui Kang, Yonghong Zhang, Hong'an Wu, Jujie Wei, Xiaoxue Sun, Yue Zuo

“…Validation with 30 Sentinel-1 SAR images from Tianjin-Tangshan (plain) and Zhejiang (mountainous) regions demonstrates significant improvements. OpenMP achieves optimal efficiency with 10-12 parallel kernels, while the combined OpenMP-MPI method performs best with 16 tasks for geometric coregistration and 24 for enhanced spectral diversity coregistration. …”
Get full text

Short video preloading via domain knowledge assisted deep reinforcement learning by Yuhong Xie, Yuan Zhang, Tao Lin, Zipeng Pan, Si-Ze Qian, Bo Jiang, Jinyao Yan

“…As such, an important challenge in short video streaming is to design a preloading algorithm that can effectively decide which videos to download, at what bitrate, and when to pause the download in order to reduce bandwidth waste while improving the Quality of Experience (QoE). …”
Get full text

A Blockchain-Based Collaborative Storage Scheme for Roadside Unit Clusters in Social Internet of Vehicles by Dai Hou, Lan Wei, Lei Zheng, Geng Wu, Jiaxing Hu, Chenxi Dong, Xinru Li, Kai Peng

“…Experimental results indicate that, compared to baseline algorithms, the proposed method achieves a 27.7% reduction in cost and a 3.5-fold decrease in execution time, thereby demonstrating the feasibility of collaborative storage optimization in blockchain-enabled SIoV.…”
Get full text

IMSBA: A Novel Integrated Sensing and Communication Beam Allocation Based on Multi-Agent Reinforcement Learning for mmWave Internet of Vehicles by Jinxiang Lai, Deqing Wang, Yifeng Zhao

“…To address these challenges, this paper proposes an integrated sensing and communication (ISAC) beam allocation algorithm, termed IMSBA, which jointly optimizes beam direction, transmission power, and spectrum resource allocation to effectively mitigate the interference between I2V and V2V while maximizing the overall network performance. …”
Get full text