检索结果-内蒙古大学图书馆

International Conference on Computer Engineering and Applications (ICCEA)

作者： Yantao Lou Jibin Wang Shoupeng Feng Xian Yu 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) Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China Department of Public Security of Shandong Province Shandong Intelligent Public Security Technology Innovation Center Jinan China

ISBN: (数字)9798350386776

ISBN: (纸本)9798350386783

Energy consumption prediction is a crucial approach to enhance the operational efficiency of HPC (High Performance computing) clusters. Existing predicting methods for the energy consumption mainly rely on time series mode, focusing on the instantaneous power during job execution. However, in practical applications, due to the large scale of HPC clusters, the prediction models need to process a vast amount of data, often resulting in poor performance. Moreover, it's challenging to provide effective predictions for jobs with significant power fluctuations. Thus we propose a more efficient energy consumption prediction framework for HPC cluster jobs, achieving two main objectives: On one hand, it uses a data encoding module to pre-encode the sampled data of energy consumption related indicators, simplifying the data that the time series prediction model needs to process and improving prediction efficiency. On the other hand, the prediction target is set to the power distribution range in a future period of time, rather than the instantaneous power at some specific time points, which improves the usability of the prediction results. Test results show that the proposed prediction framework can achieve more markable performance improvement while ensuring the effectiveness of the predictions.

关键词： Energy consumption Computational modeling High performance computing Time series analysis power distribution Predictive models Feature extraction

来源：评论

学校读者我要写书评

暂无评论

YOLO-RDD: A road defect detection algorithm based on YOLO

YOLO-RDD: A road defect detection algorithm based on YOLO

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Jiabin Pei Xiaoming Wu Xiangzhi Liu 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 Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Road maintenance is an indispensable part of the transportation system, ensuring road safety and maximizing road efficiency. The rapid and accurate acquisition of road surface information is crucial for effective road maintenance management. With the development of artificial intelligence, computer vision-based road defect detection methods are becoming popular. In this study, we propose a universal road defect detection model named YOLO-RDD, using You Only Look Once version 8 as the basic framework. Firstly, we introduce a new feature extraction and fusion approach to enhance the interaction between shallow and deep feature information, enabling multi-scale defect detection. Secondly, inspired by dynamic snake convolution, as cracks are the major road defects, we propose a new feature extraction module called DSC-C2f to adapt to the elongated and continuous morphology of cracks. Finally, we establish cross-layer connections between the backbone, neck, and prediction stages and integrate a coordinate attention module that considers inter-channel relationships and long-range positional dependencies. This allows the model to selectively focus on relevant parts of shallow and deep semantic information. We evaluate our model using the dataset provided by the crowdsensing-based road damage detection challenge (CRDDC2022) and further assess its performance on a publicly available crack and sealed crack dataset. The experiments demonstrated that our model achieved the best performance compared to the state-of-the-art (SOTA) models. Compared to the baseline model YOLOv8, our model achieved improvements of 1.2% in Precision, 1.9% in Recall, 1.9% in mAP@0.5, 0.8% in mAP@0.5:0.95, and 1.6% in F1-Score.

关键词： YOLO Cross layer design Roads Semantics Transportation Surface morphology Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Efficient CNN-Transformer Aggregation network for Remote Sensing Image Change Detection

Efficient CNN-Transformer Aggregation Network for Remote Sen...

引用

IEEE International Conference on Systems, Man and Cybernetics

作者： Bingjie Kong Qinglong Meng Fengqi Hao Jinqiang Bai 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 Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9781665410205

ISBN: (纸本)9781665410212

Change detection is a crucial task in the field of remote sensing, focusing on identifying areas where significant changes occur between two remote sensing images captured at different time points. However, existing change detection methods based on CNNs or Transformers face two main challenges. Firstly, CNNs often lack the ability to effectively model long-range dependencies, resulting in diminished recognition performance for targets sharing the same semantics but having different features. Secondly, Transformers leverage self-attention mechanisms to capture long-range dependencies adeptly but struggle to capture local details and multi-scale features effectively. In response to these challenges, we propose a CNN and Transformer Aggregation network (CTA-Net) for change detection in remote sensing images. Specifically, we devise two encoders based on Transformers and CNNs, respectively, facilitating the generation of complementary global and local features during the encoding phase. In the decoding phase, we design a pyramid-structured complementary decoder to aggregate multi-level complementary features from the CNN and Transformer branches. Furthermore, we propose a novel skip connection strategy to exploit the relationship between decoded features and multi-level complementary features, thereby enhancing the model's multi-scale invariance. Extensive experiments conducted on multiple benchmark datasets validate the effectiveness of our proposed CTA-Net model.

关键词： Target recognition Face recognition Semantics Focusing Transformers Feature extraction Encoding Decoding Remote sensing Cybernetics

来源：评论

学校读者我要写书评

暂无评论

Collaborative Prediction of Drug-target Interaction using Sequence-based CNN and Transformer

Collaborative Prediction of Drug-target Interaction using Se...

引用

International Conference on Computer Supported Cooperative Work in Design

作者： Huiting Li Weiyu Zhang Yong Shang Wenpeng Lu 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 Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350349184

ISBN: (纸本)9798350349191

Drug-target interaction (DTI) prediction is a critical step in drug discovery. Deep learning has shown great potential in DTI prediction. In recent years, many sequence-based DTI prediction methods have been proposed. However, the current methods do not fully represent drugs and proteins and ignore the local and global features of these molecules. In response to these challenges, we propose a sequence-based CNN and Transformer collaborative prediction method (SCTDTI) for drug-target interaction. We train and evaluate our proposed approach on two public drug-target datasets, and experimental results show that SCTDTI improves DTI prediction performance compared to state-of-the-art baselines.

关键词： Proteins Drugs Deep learning Federated learning Computational modeling Neural networks Collaboration

来源：评论

学校读者我要写书评

暂无评论

A Secure keyword Spotting Scheme Based on Complex Residual network

A Secure Keyword Spotting Scheme Based on Complex Residual N...

引用

Image Processing, Computer Vision and Machine Learning (ICICML), International Conference on

作者： Jingyi Chen Xiangyu Gao Peijia Zheng Huiyu Zhou Jian Li Dong Wei Jianbin Zou School of Computer Science and Engineering Sun Yat-sen University Guangzhou China Guangxi Key Laboratory of Digital Infrastructure Guangxi Zhuang Autonomous Region Information Center Nanning China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) Jinan China Yunnan Key Laboratory of Service Computing Yunnan University of Finance and Economics Kunming China Amazon Web Services Beijing China

ISBN: (数字)9798350355413

ISBN: (纸本)9798350355420

To address the privacy risks associated with intelligent voice assistants, this paper proposes a non-interactive, end-to-end keyword spotting scheme in the encrypted domain. The scheme introduces an innovative complex-valued residual neural network (CR-NN) and leverages low-degree polynomial approximations to enable encrypted computation of complex activation functions. By supporting single instruction multiple data (SIMD) operations, the scheme significantly enhances computational efficiency while reducing ciphertext size. Experimental results demonstrate that the proposed method outperforms existing approaches across multiple performance metrics, balancing efficient keyword spotting with robust privacy protection and offering new insights for the application of deep learning in the encrypted domain.

关键词： Deep learning Measurement Privacy Single instruction multiple data Image processing Personal voice assistants Polynomials Cryptography Protection Residual neural networks

来源：评论

学校读者我要写书评

暂无评论

EventTrojan: Manipulating Non-Intrusive Speech Quality Assessment via Imperceptible Events

EventTrojan: Manipulating Non-Intrusive Speech Quality Asses...

引用

IEEE International Conference on Multimedia and Expo (ICME)

作者： Ying Ren Kailai Shen Zhe Ye Diqun Yan Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Juphoon System Software Co. Ltd Ningbo China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) China

ISBN: (数字)9798350390155

ISBN: (纸本)9798350390162

Non-Intrusive speech quality assessment (NISQA) has gained significant attention for predicting speech’s mean opinion score (MOS) without requiring the reference speech. Researchers have gradually started to apply NISQA to various practical scenarios. However, little attention has been paid to the security of NISQA models. Backdoor attacks represent the most serious threat to deep neural networks (DNNs) due to the fact that backdoors possess a very high attack success rate once embedded. However, existing backdoor attacks assume that the attacker actively feeds samples containing triggers into the model during the inference phase. This is not adapted to the specific scenario of NISQA. And current backdoor attacks on regression tasks lack an objective metric to measure the attack performance. To address these issues, we propose a novel backdoor triggering approach (EventTrojan) that utilizes an event during the usage of the NISQA model as a trigger. Moreover, we innovatively provide an objective metric for backdoor attacks on regression tasks. Extensive experiments on four benchmark datasets demonstrate the effectiveness of the EventTrojan attack. Besides, it also has good resistance to several defense methods.

关键词： Measurement Resistance Adaptation models Multimedia systems Current measurement Artificial neural networks Benchmark testing

来源：评论

学校读者我要写书评

暂无评论

SML: A Backdoor Defense for Non-Intrusive Speech Quality Assessment via Semi-Supervised and Multi-Task Learning

SML: A Backdoor Defense for Non-Intrusive Speech Quality Ass...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Ying Ren Wenjie Zhang Jiahong Ye Jie Li Diqun Yan Bin Ma Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China College of Digital Technology and Engineering Ningbo University of Finance and Economics Ningbo China Key Laboratory of Computing Power Network and Information Security Ministry of Education Qilu University of Technology (Shandong Academy of Sciences) China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Non-intrusive speech quality assessment (NISQA) is widely used in speech downstream tasks due to its ability to predict the quality of speech without a reference speech. However, few researchers have focused on the backdoor security of NISQA. Despite the backdoor defenses have been extensively studied to mitigate the threat of maliciously modifications in deep neural networks. In particular, semi-supervised based backdoor defenses have excellent defensive performance by depriving backdoor attacks of their most essential need. But these defense methods rely on data-augmentation consistency and thus cannot be applied to NISQA. In this work, we propose a backdoor defense based on semi-supervised and multi-task learning (SML). Semi-supervised learning is based on the simple assumption that the same input should be as consistent as possible in two similar models. Multi-task learning further improves the prediction performance of mean opinion score (MOS) by learning the tasks of perceptual evaluation of speech quality (PESQ), short-time objective intelligibility (STOI) and speech distortion index (SDI). Extensive experiments involving five backdoor defenses against five backdoor attacks on two benchmark datasets demonstrate the superiority of our SML approach.

关键词： Acoustic distortion Artificial neural networks Semisupervised learning Benchmark testing Multitasking Acoustics Quality assessment security Indexes Speech processing

来源：评论

学校读者我要写书评

暂无评论

Unleashing the Potential of Decentralized Federated Learning in Healthcare: A Comprehensive Survey on Insights and Challenges

Unleashing the Potential of Decentralized Federated Learning...

引用

IEEE International Conference on Data Science in Cyberspace (DSC)

作者： Haibo Cheng Wenjian Liu Youyang Qu Kexue Fu Qinyuan Wang Faculty of Data Science City University of Macau Macau China 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

ISBN: (数字)9798350391367

ISBN: (纸本)9798350391374

Federated learning (FL) is a distributed learning method that reduces data transmission and privacy risks. However, the existence of a central server may become a target of attackers, resulting in an increased risk of user privacy leakage. The emergence of Decentralized Federated Learning (DFL) is posited to enhance data privacy and system reliability by reducing reliance on central servers and enhancing local data control, especially in the medical field, where personal health data is protected. This research investigates the application of (DFL) in the medical domain, focusing on its limitations. This study employs a systematic literature review, adhering to PRISMA guidelines, to comprehensively understand DFL’s current landscape and challenges in healthcare. The key findings highlight four principal obstacles faced by DFL: security and privacy, communication efficiency, data and model heterogeneity, and incentive mechanisms. It also explores the potential for DFL to facilitate personalized healthcare treatments by large datasets distributed across various medical institutions. This research fills a significant void by systematically reviewing DFL technologies in healthcare. It provides insights into applications, challenges, and future directions for participants seeking secure and efficient healthcare data handling.

关键词： Surveys Data privacy Systematics Federated learning Medical services Data models Servers security Reliability Systematic literature review

来源：评论

学校读者我要写书评

暂无评论

Improved YOLOv5 Object Detection Method for Cervical Fluid Cell Pathological Image Detection

Improved YOLOv5 Object Detection Method for Cervical Fluid C...

引用

International Joint Conference on Neural networks (IJCNN)

作者： Qingyan Ding Xuecheng Dong Na Li Yu Pan Wan Zheng Dept. 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 Computer Networks Shandong Fundamental Research Center for Computer Science Jinan China

ISBN: (数字)9798350359312

ISBN: (纸本)9798350359329

Cervical liquid-based cell pathology image detection and recognition is a key task in gynecological pathology aimed at early detection of cervical precancerous lesions. In this study, a deep learning based method is proposed for the detection and recognition of cervical liquid-based cell images. This paper is based on the YOLOv5 network model for improvement. Firstly, in the data preprocessing stage: for the characteristics of the dataset, this paper proposes two data enhancement methods to augment the training dataset; secondly, the Transformer module for local information enhancement is improved by introducing a local attention mechanism, which restricts each position to only pay attention to positions within a certain range around it; then, the spatial pyramid pooling module (DSPPCSPC) is improved, and the spatial Pyramid Pooling Module (DSPPC-SPC), introducing deformable mask of deformable convolution (ODConv); then, this paper proposes a new Attention Module (XCAttention), improving S2Attention to focus on the local information of the image, and introducing its Channel Attention Module into the third branch, which performs the Dot with the first and the second branches that have gone through Spatial-shift to obtain the final output. Product operation to get the final output. Through experiments, this paper’s algorithm improves in Precision, Recall, mAP50, and mAP50-95 metrics by 1.9%, 1.9%, 2%, and 1.2%, respectively. The experimental results show that this paper’s algorithm can effectively improve the detection performance of the model.

关键词： YOLO Training Deep learning Pathology Technological innovation Image recognition Convolution

来源：评论

学校读者我要写书评

暂无评论

Automatic recognition of depression based on audio and video:A review

引用

World Journal of Psychiatry 2024年第2期14卷 225-233页

作者： Meng-Meng Han Xing-Yun Li Xin-Yu Yi Yun-Shao Zheng Wei-Li Xia Ya-Fei Liu Qing-Xiang Wang Shandong Mental Health Center Shandong UniversityJinan 250014Shandong ProvinceChina Key Laboratory of Computing Power Network and Information Security Ministry of EducationShandong Computer Science Center(National Supercomputer Center in Jinan)Qilu University of Technology(Shandong Academy of Sciences)Jinan 250353Shandong ProvinceChina Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and TechnologyQilu University of Technology(Shandong Academy of Sciences)Jinan 250353Shandong ProvinceChina Shandong Provincial Key Laboratory of Computer Networks Shandong Fundamental Research Center for Computer ScienceJinan 250353Shandong ProvinceChina Department of Ward Two Shandong Mental Health CenterShandong UniversityJinan 250014Shandong ProvinceChina

Depression is a common mental health *** current depression detection methods,specialized physicians often engage in conversations and physiological examinations based on standardized scales as auxiliary measures for depression ***-biological markers-typically classified as verbal or non-verbal and deemed crucial evaluation criteria for depression-have not been effectively *** physicians usually require extensive training and experience to capture changes in these *** in deep learning technology have provided technical support for capturing non-biological *** researchers have proposed automatic depression estimation(ADE)systems based on sounds and videos to assist physicians in capturing these features and conducting depression *** article summarizes commonly used public datasets and recent research on audio-and video-based ADE based on three perspectives:Datasets,deficiencies in existing research,and future development directions.

关键词： Depression recognition Deep learning Automatic depression estimation System Audio processing Image processing Feature fusion Future development

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：