检索结果-内蒙古大学图书馆

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Huang, Zikang Lin, Jingru Ge, Meng Jiang, Yu Wang, Xiaobao Wang, Longbiao Dang, Jianwu Tianjin Key Laboratory of Cognitive Computing and Application College of Intelligence and Computing Tianjin University Tianjin China Shenzhen China Department of Electrical and Computer and Engineering National University of Singapore Singapore Co. Ltd. Tianjin China Shenzhen Institute of Advanced Technology Chinese Academy of Sciences Shenzhen China

ISBN: (纸本)9798350368741

A high-quality enrollment speech is crucial to target speaker extraction (TSE), since it provides essential cues for identifying the target speaker in the mixture. However, real applications usually only permit a short enrollment speech, e.g. a wakeup word for a mobile device, that provides limited cues. To address this issue, we propose an enrollment augmentation strategy that allows us to enrich the limited enrollment speech with massive text data through speech synthesis. By doing so, the extended enrollment speech contains enhanced speaker timbre and phonetic content which leads to better extraction quality. Furthermore, we propose a training data augmentation strategy to improve the model's robustness and generalization in short enrollment speech scenarios. Experiments on Libri2Mix demonstrate that our proposed strategies bring a significant improvement in extreme scenarios where only 0.5s and 1-word enrollment speech is provided. We also release our code at https://***/HuangZikang-TJU/Aug4TSE. © 2025 IEEE.

关键词： continue speaking data augmentation short enrollment speech synthesis Target speaker extraction

来源：评论

学校读者我要写书评

暂无评论

Mitigating Over-Unlearning in Machine Unlearning with Synthetic Data Augmentation 24th

Mitigating Over-Unlearning in Machine Unlearning with Synt...

引用

24th International Conference on Algorithms and architectures for Parallel Processing, ICA3PP 2024

作者： Wang, Baohai Qu, Youyang Gao, Longxiang Li, Conggai Li, Lin Smith, David Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Data61 Commonwealth Science and Industry Research Organization CanberraVIC Australia College of Business and Law Royal Melbourne Institute of Technology MelbourneVIC Australia

ISBN: (纸本)9789819615445

In machine learning, data privacy and security has become an increasingly growing concern. The introduction of machine unlearning offers the ability to address this issue through the removal of personal and sensitive data from trained models to comply with laws, regulations, and user privacy requirements. However, despite the significant benefits of this technique, performing unlearning operations is only sometimes smooth in practice. When we attempt to remove specific data, the model may over-adjust, resulting in its performance on unlearned data. This phenomenon not only reduces the accuracy of the model on known data but also affects its ability to generalize new data, thus weakening the model’s overall performance. Therefore, in this paper, we analyze the phenomenon of over-unlearning;firstly, we explore how to mitigate the effects of over-unlearning by generating synthetic data to fill in the forgotten parts, using data synthesis-based techniques. Secondly, we combine the data synthesis-based compensation strategy with model fine-tuning to further improve the model’s adaptability and generalization capability by further training the model to accommodate synthetic data. Through comprehensive experimentation, we verify the effectiveness of the proposed data synthesis-based compensation strategy. The experimental results show that the data synthesis-based compensation strategy can effectively mitigate the effects of the over-unlearning phenomenon, as well as maintaining the stability and accuracy of the model after removing specific data. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Data assimilation

来源：评论

学校读者我要写书评

暂无评论

Multi-routine-data driven spatio-temporal short-term predictions for surface ozone in China

引用

Air Quality, Atmosphere and Health 2025年 1-10页

作者： Zheng, Canju Shen, Hengqing Sun, Jianan Liu, Guangliang Cao, Haowei Zhang, Jie Gong, Xiang Xu, Da Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center Qilu University of Technology (Shandong Academy of Sciences) Jinan China Environment Research Institute Shandong University Shandong Qingdao 266237 China Ningbo Yonghuanyuan Environmental Engineering and Technology Co. LTD Zhejiang Ningbo 315012 China School of Mathematics and Physics Qingdao University of Science and Technology Qingdao 266061 China Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Qingdao Innovation Center of Artificial Intelligence Ocean Technology Qingdao 266061 China

Ozone (O3) is a major atmospheric pollutant, and accurate prediction of its concentrations remains challenging due to its complex nonlinear relationships with precursor compounds. Existing machine learning methods hav... 详细信息

Ozone (O₃) is a major atmospheric pollutant, and accurate prediction of its concentrations remains challenging due to its complex nonlinear relationships with precursor compounds. Existing machine learning methods have mainly focused on single-site or spatial predictions, lacking research on spatio-temporal short-term predictions based on simple factors. To address this gap, the MRD-O₃former, a deep learning model driven by multi-routine data, was developed to predict short-term hourly spatio–temporal surface ozone concentrations over China. The model exhibits strong spatio–temporal consistency, achieving a high correlation coefficient (r2=0.85∼0.90) and low normalized mean biases (NMBs) between -15% and 15% at the national scale compared to reanalysis ozone data. Both ablation experiments and permutation importance analysis reveal that historical ozone levels play a primary role in next-day ozone prediction, while meteorological factors such as wind speed and temperature also make significant contributions. Regional validation confirms the model’s effectiveness in the Beijing-Tianjin-Hebei region. Moreover, the study investigates the differential impact of crucial factors in urban and rural areas, revealing that historical ozone levels and meteorological factors significantly influence rural areas. However, the influence of historical ozone levels on urban ozone prediction is relatively small, especially during the summer. This suggests that urban ozone undergoes rapid formation and removal processes. These findings highlight the promising potential of deep learning techniques in accurately predicting spatiotemporal short-term ozone concentrations and interpreting the mechanism and source for ozone pollution. © The Author(s), under exclusive licence to Springer Nature B.V. 2025.

关键词： Data-driven Multi-factor Ozone concentration Spatio-temporal prediction

来源：评论

学校读者我要写书评

暂无评论

Time-aware Medication Recommendation via Intervention of Dynamic Treatment Regimes 34

Time-aware Medication Recommendation via Intervention of Dyn...

引用

34th ACM Web Conference, WWW 2025

作者： Li, Yishuo Zhang, Qi Lu, Wenpeng Peng, Xueping Zhang, Weiyu Si, Jiasheng Gong, Yongshun Hu, Liang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Computing Power Internet and Service Computing Shandong Fundamental Research Center for Computer Science Jinan China Department of Computer Science and Technology Tongji University Shanghai China Australian Artificial Intelligence Institute University of Technology Sydney Sydney Australia School of Software Shandong University Jinan China

ISBN: (纸本)9798400712746

Medication recommendation aims to suggest personalized drug combinations to patients based on their longitudinal medical histories stored in electronic health record (EHR) datasets. Patients’ Dynamic Treatment Regimes (DTRs) determine how patients’ drug combinations change along with the evolution of disease treatment. DTRs are effective for comprehending disease-treatment dynamics and for recommending a timely and personalized combination of medications for patients. However, existing medication recommender systems (MRSs) overlook the multiple treatment pathways generated by the intervention of DTRs and can only recommend a single treatment paradigm, ignoring the fact that patients may be at different treatment stages and thus require different treatment regime. Such disregard leads to a significant limitation in recommending personalized medication combinations tailored to different treatment stages, yielding greatly compromised accuracy and applicability of MRSs. Moreover, existing methods often overlook the time interval information over patients’ successive visits, which is critical to indicate patients’ treatment evolution. To address these significant gaps, we propose a Time-aware Medication Recommendation Framework via Intervention of Dynamic Treatment Regimes, called MR-DTR. To explicitly illustrate the intervention processes of DTRs on similar patients, we employ a co-guided graph to connect various patient sequences. In addition, to fully utilize the time interval information, we design a time-aware guidance mechanism dedicated to the co-guided graph to efficiently learn medication representation using the patient’s guidance information. We also introduce relative time intervals in the encoder to act as positional information. Extensive experiments on two real-world datasets demonstrate that MR-DTR surpasses state-of-the-art models in terms of recommendation performance. © 2025 Copyright held by the owner/author(s).

关键词： Dynamic Treatment Regimes Electronic Health Record Medication Recommendation Recommender Systems

来源：评论

学校读者我要写书评

暂无评论

FuHsi: Shifting Base-Calling Closer to Sequencer via In-Cache Acceleration

引用

Journal of computer Science and technology 2025年第2期40卷 482-499页

作者： Li, Ye-Wen Tan, Guang-Ming Li, Xue-Qi State Key Laboratory of Processors Institute of Computing Technology Chinese Academy of Sciences Beijing 100190 China School of Computer Science and Technology University of Chinese Academy of Sciences Beijing 100049 China

Base-calling is an essential step in the analysis of third-generation genome data. Many previous hardware efforts aimed at enhancing processing in the workflow. However, an order of magnitude throughput gap still exists. In this paper, we propose FuHsi to improve the end-to-end throughput of the base-calling process. FuHsi is an in-cache accelerator that only introduces three components to the traditional CPUs in the sequencer. We propose FuHsi Cache, which offloads the bottleneck operations to cache arithmetic. Specifically, we accelerate beam search, string conversion, and MAC (multiply-accumulate) using algorithm/hardware co-design. We also introduce FuHsi APIs and FuHsi Controller to provide coarse-grained control for FuHsi Cache. Experimental results show that FuHsi can achieve 45.7x, 113.1x, and 100x throughput per watt speedup compared with an NVIDIA Jetson baseline, an NVIDIA A100 GPU baseline, and the Helix accelerator, respectively. FuHsi can provide base-calling requests for up to 15 ONT sequencers simultaneously. © institute of computing technology, Chinese Academy of Sciences 2025.

关键词： domain-specific architecture genome analysis genome base-calling in-cache accelerator Nanopore sequencing

来源：评论

学校读者我要写书评

暂无评论

VFLMonitor: Defending One-Party Hijacking Attacks in Vertical Federated Learning

引用

IEEE Transactions on Information Forensics and Security 2025年 20卷 4828-4843页

作者： Xu, Xiangrui Zhao, Yiwen Han, Yufei Zhu, Yongsheng Han, Zhen Xu, Guangquan Wang, Bin Ji, Shouling Wang, Wei Qingdao University of Science and Technology School of Information Science and Technology Qingdao266061 China University of Southern California Thomas Lord Department of Computer Science Los AngelesCA90007 United States INRIA Brittany Rennes35042 France Institute of Computing Technologies China Academy of Railway Sciences Corporation Ltd. Beijing100081 China Beijing Jiaotong University Beijing Key Laboratory of Security and Privacy in Intelligent Transportation Beijing100044 China College of Intelligence and Computing Tianjin300072 China Network and Data Security Hangzhou310053 China Zhejiang University College of Computer Science and Technology Zhejiang 310058 China Xi’an Jiaotong University Ministry of Education Key Laboratory for Intelligent Networks and Network Security Xi’an710049 China

Vertical Federated Learning (VFL) is susceptible to various one-party hijacking attacks, such as Replay and Generation attacks, where a single malicious client can manipulate the model to produce attacker-specified results, thereby compromising its reliability in real-world deployments. In this paper, we first uncover the underlying mechanisms of these attacks and observe that successful attacks induce significant discrepancies in the embedding-label associations across different clients. We establish a theoretical framework demonstrating how these discrepancies can serve as reliable indicators for detecting hijacking attempts. Building upon this insight, we propose VFLMonitor, a robust defense mechanism that leverages these embedding-label discrepancies to detect and mitigate hijacking attacks. Specifically, VFLMonitor identifies suspicious queries by analyzing differences in label estimations from multiple clients and applies a majority voting rule to correct or filter out these malicious queries. Moreover, VFLMonitor introduces a novel regularization strategy during training to reduce intra-class variance in embeddings, thereby enhancing their discriminative power and improving defense effectiveness. Extensive experiments were conducted on 5 real-world datasets against 2 different attack types under 3 attack scenarios. The results demonstrate that VFLMonitor can effectively identify and exclude potential hijacked requests in all types of one-party hijacking attacks, while maintaining a meager false positive rate for legitimate queries. © 2005-2012 IEEE.

关键词： Training Servers Electronic mail Artificial intelligence Reliability theory Predictive models Federated learning Data models Computational modeling Collaboration

来源：评论

学校读者我要写书评

暂无评论

Multi-Grained Feature Pruning for Video-Based Human Pose Estimation

Multi-Grained Feature Pruning for Video-Based Human Pose Est...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Wang, Zhigang Fan, Shaojing Liu, Zhenguang Wu, Zheqi Wu, Sifan Jiao, Yingying College of Computer Science and Technology Zhejiang Gongshang University Hangzhou China School of Computing National University of Singapore Singapore The State Key Laboratory of Blockchain and Data Security Zhejiang University Hangzhou China Institute of Blockchain and Data Security Hangzhou China College of Computer Science and Technology Jilin University Changchun China College of Computer Science and Technology Zhejiang University of Technology Hangzhou China

Human pose estimation, with its broad applications in action recognition and motion capture, has experienced significant advancements. However, current Transformer-based methods for video pose estimation often face challenges in managing redundant temporal information and achieving fine-grained perception because they only focus on processing low-resolution features. To address these challenges, we propose a novel multi-scale resolution framework that encodes spatio-temporal representations at varying granularities and executes fine-grained perception compensation. Furthermore, we employ a density peaks clustering method to dynamically identify and prioritize tokens that offer important semantic information. This strategy effectively prunes redundant feature tokens, especially those arising from multi-frame features, thereby optimizing computational efficiency without sacrificing semantic richness. Empirically, it sets new benchmarks for both performance and efficiency on three large-scale datasets. Our method achieves a 93.8% improvement in inference speed compared to the baseline, while also enhancing pose estimation accuracy, reaching 87.4 mAP on the PoseTrack2017 dataset. © 2025 IEEE.

关键词： Large datasets

来源：评论

学校读者我要写书评

暂无评论

Joint Automatic Speech Recognition And Structure Learning For Better Speech Understanding

Joint Automatic Speech Recognition And Structure Learning Fo...

引用

2025 IEEE International Conference on Acoustics, Speech, and Signal Processing, ICASSP 2025

作者： Hu, Jiliang Li, Zuchao Shen, Mengjia Ai, Haojun Li, Sheng Zhang, Jun Key Laboratory of Aerospace Information Security and Trusted Computing Ministry of Education School of Cyber Science and Engineering Wuhan University Wuhan China School of Computer Science Wuhan University Wuhan China Wuhan Second Ship Design and Research Institute Wuhan China National Institute of Information and Communications Technology Japan

ISBN: (纸本)9798350368741

Spoken language understanding (SLU) is a structure prediction task in the field of speech. Recently, many works on SLU that treat it as a sequence-to-sequence task have achieved great success. However, This method is not suitable for simultaneous speech recognition and understanding. In this paper, we propose a joint speech recognition and structure learning framework (JSRSL), an end-to-end SLU model based on span, which can accurately transcribe speech and extract structured content simultaneously. We conduct experiments on name entity recognition and intent classification using the Chinese dataset AISHELL-NER and the English dataset SLURP. The results show that our proposed method not only outperforms the traditional sequence-to-sequence method in both transcription and extraction capabilities but also achieves state-of-the-art performance on the two datasets. © 2025 IEEE.

关键词： Information Extraction Speech Recognition Spoken Language Understanding

来源：评论

学校读者我要写书评

暂无评论

MCDS: An Effective Multi-UAV Collaborative Decision-Making System in Mobile Edge computing Networks

引用

IEEE Internet of Things Journal 2025年

作者： Xiong, Naixue Zhong, Weiyu Chen, Yuxiang He, Dacheng Li, Yuhui Chen, Linshu Liang, Wei Sanya Research Institute of Hunan University of Science and Technology School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology China Sanya Research Institute of Hunan University of Science and Technology Hunan University School of Computer Science and Engineering Hunan University of Science and Technology Hunan Key Laboratory for Service Computing and Novel Software Technology School of Information Science and Engineering China The Hong Kong Polytechnic University Department of Computing Hong Kong

Mobile Edge computing (MEC) pushes computing resources from the network center to the network edge to provide efficient and reliable computing services. However, due to the mobility and diversity of mobile users (MUs), edge servers (ESs) are likely to be overloaded, which leads to a rapid decline in the quality of service provided by the MEC system. This paper introduces unmanned aerial vehicles (UAVs) to solve the problem of ES overload. This paper presents an effective Multi-UAV Collaborative Decision-Making System (MCDS) tailored to optimize task offloading and resource allocation in MEC networks. The proposed system seeks to reduce task computing delays and energy consumption while guaranteeing timely task completion and compliance with resource constraints. We design a distributed two-stage optimization algorithm to jointly optimize the task offloading decision and resource allocation of the collaborative computing system (UAVs, ESs, and MUs). To address the flight cooperation problem of multi-UAVs, we also proposed a task-aware scheduling algorithm for multi-UAVs. In addition, we conducted a large number of simulation experiments. Experimental results show that our two-stage optimization scheme is lower than other benchmark algorithms in terms of task completion delay, energy consumption and total cost of objective function. Specifically, compared with seven baseline algorithms under three different system setting scenarios, our algorithm reduces the total cost by an average of 38.79%, the energy consumption by an average of 40.70%, and the delay by an average of 15.67%. © 2014 IEEE.

关键词： Drones

来源：评论

学校读者我要写书评

暂无评论

RBLJAN: Robust Byte-Label Joint Attention Network for Network Traffic Classification

引用

IEEE Transactions on Dependable and Secure computing 2025年第3期22卷 2161-2178页

作者： Xiao, Xi Wang, Shuo Hu, Guangwu Li, Qing Mao, Kelong Luo, Xiapu Zhang, Bin Xia, Shutao Tsinghua Shenzhen International Graduate School Tsinghua University Shenzhen Guangdong518055 China Peng Cheng Laboratory Shenzhen Guangdong518038 China Key Laboratory of Cyberspace Security Ministry of Education of China Zhengzhou Henan450001 China School of Computer Science Shenzhen Institute of Information Technology Shenzhen Guangdong518172 China Gaoling School of Artificial Intelligence Renmin University Beijing100086 China Department of Computing Hong Kong Polytechnic University Hong Kong

Network traffic classification plays a crucial role in network management and cyberspace security. As the Internet evolves with new applications and protocols, traditional machine learning-based methods relying on feature mining have become obsolete. Instead, deep learning-based methods are becoming more popular in the field of traffic classification due to their end-to-end processing approach. However, the vulnerability of neural networks to adversarial examples significantly compromises their performance. In this paper, we propose Robust Byte-Label Joint Attention Network (RBLJAN), an efficient and robust deep learning-based framework for encrypted network traffic classification at both the packet-level and the flow-level. RBLJAN comprises a classifier and an adversarial traffic generator. The classifier utilizes mechanisms such as header-payload parallel processing and byte-label joint attention learning to capture implicit correlations between bytes and labels, enabling the construction of powerful packet representations. The generator produces adversarial examples that are fed to the classifier to enhance its robustness. Experimental results demonstrate that RBLJAN achieves over 99% average F1-score on real-world legitimate traffic datasets and achieves 97.86% average F1-score on malware identification. Moreover, RBLJAN exhibits superior performance in terms of detection speed and robustness compared to state-of-the-art methods in real-world scenarios. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：