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

Global air quality index prediction using integrated spatial observation data and geographics machine learning by Tania Septi Anggraini, Hitoshi Irie, Anjar Dimara Sakti, Ketut Wikantika

“…The GML considers geographical characteristics in the analysis by calculating the optimal bandwidth area in its algorithm. The study employs nine scenarios to identify which parameters significantly contribute to the model and determine the best parameter combinations. …”
Get full text

A Novel Graph Reinforcement Learning-Based Approach for Dynamic Reconfiguration of Active Distribution Networks with Integrated Renewable Energy by Hua Zhan, Changxu Jiang, Zhen Lin

“…The dynamic reconfiguration of active distribution networks (ADNDR) essentially belongs to a complex high-dimensional mixed-integer nonlinear stochastic optimization problem. Traditional mathematical optimization algorithms tend to encounter issues like slow computational speed and difficulties in solving large-scale models, while heuristic algorithms are prone to fall into local optima. …”
Get full text

Research on SeaTreasure Target Detection Technology Based on Improved YOLOv7-Tiny by Xiang Shi, Yunli Zhao, Jinrong Guo, Yan Liu, Yongqi Zhang

“…Experimental results demonstrate that our optimized algorithm achieves a mAP0.5 of 79.5%, representing a 2.0 percentage point improvement over the baseline YOLOv7-tiny model (77.5%) while maintaining computational efficiency at 45.2 GFLOPs. …”
Get full text

Minimization of Resource Consumption with URLLC Constraints for Relay-Assisted IIoT by Yujie Zhao, Tao Peng, Yichen Guo, Yijing Niu, Wenbo Wang

“…In this work, the packet error probability (PEP) and blocklength allocation across two-hop links are jointly optimized to minimize total blocklength (resource consumption) while satisfying reliability, latency, and throughput requirements. …”
Get full text

Denoising of acoustic emission signals from rock failure processes through ICEEMDAN combined with multiple criteria and wavelet transform by Tao Wang, Weiwei Ye, Liyuan Liu, Zhihui Zhao, Wei Huang

“…The peak frequency range is unaffected before and after optimization, while the main amplitude reduction is concentrated in the high-frequency range. …”
Get full text

A Model‐Independent Strategy for the Targeted Observation Analysis and Its Application in ENSO Prediction by Weixun Rao, Youmin Tang, Yanling Wu, Xiaojing Li

“…Sensitive experiments show that while number of data sets reaches 12, a robust optimal observational array is obtained. …”
Get full text

Computational design exploration of rocket nozzle using deep reinforcement learning by Aagashram Neelakandan, Arockia Selvakumar Arockia Doss, Natrayan Lakshmaiya

“…Additionally, the use of the Single-Step Proximal Policy Optimization (SSPPO) algorithm enhances the exploration of nozzle geometries by maximizing aerodynamic performance while balancing computational efficiency. …”
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 introduce a strategy that uses separate independent variables for side-chain optimization, center-to-center distance of the two proteins, and five angular descriptors of the relative orientations of the molecules. …”
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

Assessing ornamental tree maturity and spray requirements using depth sensing and LiDAR technologies by Aleena Rayamajhi, Guoyu Lu, Ernest William Tollner, Jean Williams-Woodward, Md Sultan Mahmud

“…Effective assessment of tree maturity and agrochemical application requirements is important for optimizing resource use and sustainability in woody ornamental nurseries. …”
Get full text

Scalable Hyperspectral Enhancement via Patch-Wise Sparse Residual Learning: Insights from Super-Resolved EnMAP Data by Parth Naik, Rupsa Chakraborty, Sam Thiele, Richard Gloaguen

“…The spectral and spatial characteristics of the scene encoded in the dictionary enable reconstruction through a first-order optimization algorithm to ensure an efficient sparse representation. …”
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

A population spatialization method based on the integration of feature selection and an improved random forest model. by Zhen Zhao, Hongmei Guo, Xueli Jiang, Ying Zhang, Changjiang Lu, Can Zhang, Zonghang He

“…Additionally, considering the imbalanced in population spatial distribution, we used the K-means ++ clustering algorithm to cluster the optimal feature subset, and we used the bootstrap sampling method to extract the same amount of data from each cluster and fuse it with the training subset to build an improved random forest model. …”
Get full text

Meta surface Assisted Open radio access networks by 7haneenabdulrahman7 ajeel, Ismail Hburi

“…In specific, a channel-gain-based selection of UEs/O-RU-RIS pairs joint with duality theory (DT) and transform of quadratic function (TQF) algorithm (namely DT_TQF) is proposed. Firstly, the non-convex optimization problem is relaxed via duality and transform of quadratic functions, and then an iterative approach is carried out for the active and passive beamformers via a simple alternating optimization approach. …”
Get full text

A Full-Life-Cycle Modeling Framework for Cropland Abandonment Detection Based on Dense Time Series of Landsat-Derived Vegetation and Soil Fractions by Qiangqiang Sun, Zhijun You, Ping Zhang, Hao Wu, Zhonghai Yu, Lu Wang

“…The parameters of the optimization model (fitting type, change magnitude, start timing, and change duration) are subsequently integrated to develop a rule-based hierarchical identification scheme for cropland abandonment based on these complex scenarios. …”
Get full text

Mapping the air temperature in China from time-normalized MODIS land surface temperature data via zone-based stacking ensemble models by Yan Xin, Yongming Xu, Xudong Tong, Yaping Mo, Yonghong Liu, Shanyou Zhu

“…Finally, the Ta estimation results from the base models were integrated using five ensemble methods to develop an optimal integration strategy for mapping Ta. The results showed that temporal normalization effectively reduced the time difference in LST. …”
Get full text

A new internal clustering validation index for categorical data based on concentration of attribute values by FU Li-wei, WU Sen

“…For data with a clustering structure, different results obtained under different algorithms and parameters also need to be further optimized by clustering validation. …”
Get full text