检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Li, Zhen Zhang, Ruqian Zou, Deqing Wang, Ning Li, Yating Xu, Shouhuai Chen, Chen Jin, Hai National Engineering Research Center for Big Data Technology and System Services Computing Technology and System Lab Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security Cluster and Grid Computing Lab China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China Department of Computer Science University of Colorado Colorado Springs United States Center for Research in Computer Vision University of Central Florida United States School of Computer Science and Technology Huazhong University of Science and Technology Wuhan430074 China

Deep learning has been widely used in source code classification tasks, such as code classification according to their functionalities, code authorship attribution, and vulnerability detection. Unfortunately, the black-box nature of deep learning makes it hard to interpret and understand why a classifier (i.e., classification model) makes a particular prediction on a given example. This lack of interpretability (or explainability) might have hindered their adoption by practitioners because it is not clear when they should or should not trust a classifier's prediction. The lack of interpretability has motivated a number of studies in recent years. However, existing methods are neither robust nor able to cope with out-of-distribution examples. In this paper, we propose a novel method to produce Robust interpreters for a given deep learning-based code classifier;the method is dubbed Robin. The key idea behind Robin is a novel hybrid structure combining an interpreter and two approximators, while leveraging the ideas of adversarial training and data augmentation. Experimental results show that on average the interpreter produced by Robin achieves a 6.11% higher fidelity (evaluated on the classifier), 67.22% higher fidelity (evaluated on the approximator), and 15.87x higher robustness than that of the three existing interpreters we evaluated. Moreover, the interpreter is 47.31% less affected by out-of-distribution examples than that of LEMNA. Copyright © 2023, The Authors. All rights reserved.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Enhanced Framework for MRI Brain Tumor Recognition with Residual Learning and Intuitive Heatmap Visualization

Enhanced Framework for MRI Brain Tumor Recognition with Resi...

引用

Innovative Computing, Intelligent Communication and Smart Electrical Systems (ICSES), International Conference on

作者： L. Velmurugan R. K Maheswari K. Janani K. Agalya M. Poornima K.C. Gayathri School of Computing Science and Engineering (SCOPE VIT Bhopal University Sehore Madhya Pradesh India Artificial Intelligence and Data Science M.A.M College of Enginnering and Technology Trichy Tamilnadu India Department of Data science and computer applications Manipal institute of Technology Manipal Academy of Higher Education Manipal India Department of Computer Science Engineering Sri Eshwar College of Engineering Coimbatore India Department of Information Technology OASYS Institute of Technology Trichy Tamil Nadu India Chettinad School of physiotherapy (CSP Chettinad Hospital and Research Institute (CHRI) Chettinad Academy of Research and Education (CARE) Chennai India

ISBN: (数字)9798331543624

ISBN: (纸本)9798331543631

Early detection of brain tumors is crucial for effective treatment, yet it poses a significant challenge due to the rapid nature of the disease's progression. This study explores the application of ResNet, aimed at improving the accuracy of brain tumor diagnosis in magnetic resonance imaging (MRI) scans. Our model was trained on a dataset comprising 253 MRI images, which included 155 confirmed cases of tumors. The residual learning framework of ResNet effectively captures intricate features and mitigates issues such as vanishing gradients. The results indicate that the ResNet model achieved an impressive accuracy rate of 97%, surpassing traditional detection methods. We evaluated the model's performance using metrics like accuracy and F1-score, demonstrating its robustness. To improve the interpretability of our model's predictions, we utilized Grad-CAM (Gradient-weighted Class Activation Mapping), which highlighted critical areas in the MRI scans that influenced the model's decisions. Our findings confirm ResNet’ s effectiveness in medical imaging and stress the importance of model interpretability in healthcare, allowing radiologists to make informed diagnostic choices.

关键词： Deep learning Accuracy Magnetic resonance imaging Brain tumors Medical services Predictive models Brain modeling Robustness Stress Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Disentangling Voice and Content with Self-Supervision for Speaker Recognition

arXiv

引用

arXiv 2023年

作者： Liu, Tianchi Lee, Kong Aik Wang, Qiongqiong Li, Haizhou Singapore Dept. of Electrical and Computer Engineering National University of Singapore Singapore Dept. of Electrical and Electronic Engineering Hong Kong Polytechnic University Hong Kong School of Data Science The Chinese University of Hong Kong Shenzhen China

For speaker recognition, it is difficult to extract an accurate speaker representation from speech because of its mixture of speaker traits and content. This paper proposes a disentanglement framework that simultaneously models speaker traits and content variability in speech. It is realized with the use of three Gaussian inference layers, each consisting of a learnable transition model that extracts distinct speech components. Notably, a strengthened transition model is specifically designed to model complex speech dynamics. We also propose a self-supervision method to dynamically disentangle content without the use of labels other than speaker identities. The efficacy of the proposed framework is validated via experiments conducted on the VoxCeleb and SITW datasets with 9.56% and 8.24% average reductions in EER and minDCF, respectively. Since neither additional model training nor data is specifically needed, it is easily applicable in practical use. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Geometric Distortion Guided Transformer for Omnidirectional Image Super-Resolution

arXiv

引用

arXiv 2024年

作者： Yang, Cuixin Dong, Rongkang Xiao, Jun Zhang, Cong Lam, Kin-Man Zhou, Fei Qiu, Guoping Department of Electrical and Electronic Engineering The Hong Kong Polytechnic University Hong Kong College of Electronic and Information Engineering Shenzhen University Shenzhen518060 China Guangdong-Hong Kong Joint Laboratory for Big Data Imaging and Communication Shenzhen518060 China School of Computer Science University of Nottingham NottinghamNG8 1BB United Kingdom School of Computer Science University of Nottingham Ningbo315100 China

As virtual and augmented reality applications gain popularity, omnidirectional image (ODI) super-resolution has become increasingly important. Unlike 2D plain images that are formed on a plane, ODIs are projected onto spherical surfaces. Applying established image super-resolution methods to ODIs, therefore, requires performing equirectangular projection (ERP) to map the ODIs onto a plane. ODI super-resolution needs to take into account geometric distortion resulting from ERP. However, without considering such geometric distortion of ERP images, previous methods only utilize a limited range of pixels and may easily miss self-similar textures for reconstruction. In this paper, we introduce a novel Geometric Distortion Guided Transformer for Omnidirectional image Super-Resolution (GDGT-OSR). Specifically, a distortion modulated rectangle-window self-attention mechanism, integrated with deformable self-attention, is proposed to better perceive the distortion and thus involve more self-similar textures. Distortion modulation is achieved through a newly devised distortion guidance generator that produces guidance for the rectangular windows by exploiting the variability of distortion across latitudes. Furthermore, we propose a dynamic feature aggregation scheme to adaptively fuse the features from different self-attention modules. We present extensive experimental results on public datasets and show that the new GDGT-OSR outperforms methods in existing literature. Copyright © 2024, The Authors. All rights reserved.

关键词： Image resolution

来源：评论

学校读者我要写书评

暂无评论

Unified graph augmentations for generalized contrastive learning on graphs 24

Unified graph augmentations for generalized contrastive lear...

引用

Proceedings of the 38th International Conference on Neural Information Processing Systems

作者： Jiaming Zhuo Yintong Lu Hui Ning Kun Fu Bingxin Niu Dongxiao He Chuan Wang Yuanfang Guo Zhen Wang Xiaochun Cao Liang Yang Hebei Province Key Laboratory of Big Data Calculation School of Artificial Intelligence Hebei University of Technology Tianjin China College of Intelligence and Computing Tianjin University Tianjin China School of Computer Science and Technology Beijing JiaoTong University Beijing China School of Computer Science and Engineering Beihang University Beijing China School of Artificial Intelligence OPtics and ElectroNics (iOPEN) School of Cybersecurity Northwestern Polytechnical University Xi'an China School of Cyber Science and Technology Shenzhen Campus of Sun Yat-sen University Shenzhen China

ISBN: (纸本)9798331314385

In real-world scenarios, networks (graphs) and their tasks possess unique characteristics, requiring the development of a versatile graph augmentation (GA) to meet the varied demands of network analysis. Unfortunately, most Graph Contrastive Learning (GCL) frameworks are hampered by the specificity, complexity, and incompleteness of their GA techniques. Firstly, GAs designed for specific scenarios may compromise the universality of models if mishandled. Secondly, the process of identifying and generating optimal augmentations generally involves substantial computational overhead. Thirdly, the effectiveness of the GCL, even the learnable ones, is constrained by the finite selection of GAs available. To overcome the above limitations, this paper introduces a novel unified GA module dubbed UGA after reinterpreting the mechanism of GAs in GCLs from a message-passing perspective. Theoretically, this module is capable of unifying any explicit GAs, including node, edge, attribute, and subgraph augmentations. Based on the proposed UGA, a novel generalized GCL framework dubbed Graph cOntrastive UnifieD Augmentations (GOUDA) is proposed. It seamlessly integrates widely adopted contrastive losses and an introduced independence loss to fulfill the common requirements of consistency and diversity of augmentation across diverse scenarios. Evaluations across various datasets and tasks demonstrate the generality and efficiency of the proposed GOUDA over existing state-of-the-art GCLs.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Heterogeneous Software Effort Estimation via Cascaded Adversarial Auto-Encoder 1

引用

21st International Conference on Parallel and Distributed Computing, Applications, and Technologies, PDCAT 2020

作者： Qi, Fumin Jing, Xiao-Yuan Zhu, Xiaoke Jia, Xiaodong Cheng, Li Dong, Yichuan Fang, Ziseng Ma, Fei Feng, Shengzhong College of Computer Science and Software Engineering Shenzhen University Shenzhen China School of Computer Wuhan University Wuhan China Henan Key Laboratory of Big Data Analysis and Processing Henan University Kaifeng China National Supercomputing Center in Shenzhen Guangzhou Guangdong China School of Computer Science Qufu Normal University Rizhao China

ISBN: (数字)9783030692445

ISBN: (纸本)9783030692438

In Software Effort Estimation (SEE) practice, the data drought problem has been plaguing researchers and practitioners. Leveraging heterogeneous SEE data collected by other companies is a feasible solution to relieve the data drought problem. However, how to make full use of the heterogeneous effort data to conduct SEE, which is called as Heterogeneous Software Effort Estimation (HSEE), has not been well studied. In this paper, we propose a HSEE model, called Dynamic Heterogeneous Software Effort Estimation (i.e., DHSEE), which leverages the adversarial auto-encoder and convolutional neural network techniques. Meanwhile, we have investigated the scenario of conducting HSEE with dynamically increasing effort data. Experiments on ten public datasets indicate that our approach can significantly outperform the state-of-the-art HSEE method and other competing methods on both static and dynamic SEE scenarios. © 2021, Springer Nature Switzerland AG.

关键词： Drought

来源：评论

学校读者我要写书评

暂无评论

Chaotic Particle Swarm Optimization Based Shortest Path Routing in VANET

Chaotic Particle Swarm Optimization Based Shortest Path Rout...

引用

International Conference on Circuit, Power and Computing Technologies (ICCPCT)

作者： R. Ramya A. Yazhini T. Geetha R. Sahila Devi Kavin K. S. S. Dhanalakshmi Department of Nano Electronics Materials and Sensors ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai India Department of Computer Science & Engineering College of Engineering Anna University Chennai India Department of Artificial Intelligence and Data Science Agni College of Engineering and Technology Chennai India Department of Computer Science and Engineering Rohini College of Engineering and Technology Palkulam India Department of Electrical and Electronics Engineering Government College of Engineering Tirunelveli Tamilnadu India Department of Electronics and Communication Engineering Bannari Amman Institute of Technology Sathyamangalam Erode India

ISBN: (数字)9798350372816

ISBN: (纸本)9798350372823

The present study examines the Vehicle Ad hoc Networks (VANETs) exhibit unexpected behavior due to their high mobility and random network structure. Including ad hoc networks, a variety of problems, including repeated connected breakdowns, flexibility, multi-hop transmission of information, and information loss, impact Transmission Control Protocols (TCP). To overcome this problem, this paper suggests employing zone-based routing in VANETs while taking mobility into account. The routing technique is implemented with a hybrid optimization strategy. The most significant swarm intelligence (SI) algorithm for solving optimization issues is the chaotic particle swarm optimization (CPSO) algorithm. Due to its simplicity, which involves just a few parameters, CPSO has grown to be considered one of the most frequently used optimization techniques. When resolving challenging optimization problems, the routing algorithms experience high overhead or incompatibilities. A CPSO based shortest path routing method is presented for VANET that offers a high-quality path for connection among nodes, improving the distribution of packets percentage and preventing end-to-end delay, in order to enhanced routing effectiveness and throughput in prevailing approaches. These achievements show that CPSO performs adequately and is experiencing significant progress.

关键词： TCP Protocols Vehicular ad hoc networks Spread spectrum communication Routing Throughput Search problems

来源：评论

学校读者我要写书评

暂无评论

Structured Multi-Track Accompaniment Arrangement via Style Prior Modelling

arXiv

引用

arXiv 2023年

作者： Zhao, Jingwei Xia, Gus Wang, Ziyu Wang, Ye Institute of Data Science NUS Singapore School of Computing NUS Singapore Integrative Sciences and Engineering Programme NUS Graduate School Singapore Machine Learning Department MBZUAI United Arab Emirates Computer Science Department NYU Shanghai China

In the realm of music AI, arranging rich and structured multi-track accompaniments from a simple lead sheet presents significant challenges. Such challenges include maintaining track cohesion, ensuring long-term coherence, and optimizing computational efficiency. In this paper, we introduce a novel system that leverages prior modelling over disentangled style factors to address these challenges. Our method presents a two-stage process: initially, a piano arrangement is derived from the lead sheet by retrieving piano texture styles;subsequently, a multi-track orchestration is generated by infusing orchestral function styles into the piano arrangement. Our key design is the use of vector quantization and a unique multi-stream Transformer to model the long-term flow of the orchestration style, which enables flexible, controllable, and structured music generation. Experiments show that by factorizing the arrangement task into interpretable sub-stages, our approach enhances generative capacity while improving efficiency. Additionally, our system supports a variety of music genres and provides style control at different composition hierarchies. We further show that our system achieves superior coherence, structure, and overall arrangement quality compared to existing baselines. © 2023, CC BY.

关键词： Vector quantization

来源：评论

学校读者我要写书评

暂无评论

Identification of Cardiovascular Disease using ECG Images based on Deep Learning Procedure

Identification of Cardiovascular Disease using ECG Images ba...

引用

Advances in Computing, Communication and Applied Informatics (ACCAI), International Conference on

作者： Hannah Rose Esther T P. N. Periyasamy Rajesh Kumar. K P. GururamaSenthilvel N. Duraimutharasan Department of Artificial Intelligence and Data Science Velammal Engineering College Department of Computer Science and Engineering Hindusthan Institute of Technology Coimbatore Tamil Nadu Department of Electronics and Communication Engineering Chendu College of Engineering Madurantakam Tamil Nadu Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences (SIMATS) Chennai Department of Information Technology AMET University Kanathur Tamil Nadu

When it comes to finding out what's wrong with your heart, cardiac imaging is crucial (CVD). Its previous purpose was restricted to qualitative and quantitative evaluations of the heart. The advent of big data and machine learning, however, has opened up new possibilities for developing AI tools that can aid the physician in the diagnosis of CVDs. Our study offers a unique approach to ECG illness prediction by combining cardiology, signal processing techniques, and a deep learning model. Then, using wavelet transformation and cardiology, we convert the ECG data into a time-frequency representation. Next, a deep convolutional network is used to categories the results of the time-frequency analysis. We find that by combining the benefits of signal processing with those of deep learning, we can significantly enhance the precision of categorization using our approach. The suggested methodology has the potential to enhance performance and reduces staffing costs for major general hospitals, all while lowering the rates at which primary care facilities make diagnostic errors.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Hybrid Parallel Inference for Large Model on Heterogeneous Clusters for High Throughput

Hybrid Parallel Inference for Large Model on Heterogeneous C...

引用

International Conference on Parallel and Distributed Systems (ICPADS)

作者： Chaonong Xu Weiming Kong Min Liu Mingming Zhang Chao Li Luqi Gong Beijing Key Lab of Petroleum Data Mining China University of Petroleum (Beijing) Beijing China Institute of Intelligent Computing Zhejiang Lab Hangzhou China School of Computer Science (National Pilot Software Engineering School) BUPT Beijing China

In high-throughput intelligent computing scenarios, multi-device parallelism strategies based on data parallelism or pipeline parallelism have been extensively utilized to accelerate large deep neural network model inference. data parallelism offers nearly linear improvement in inference speed, but it is limited by the memory capacity of a single device which constrains the model size. On the other hand, pipeline parallelism can support larger models, but the total communication of the activations among devices is high, which limits the improvement of the inference speed. To address the demand for efficient model inference in high-throughput heterogeneous scenarios, we proposes a hybrid parallelism strategy that combines data parallelism and pipeline parallelism. The strategy involves grouping heterogeneous device clusters and then employing inter-group data parallelism along with intra-group pipeline parallelism. Moreover, we propose an algorithm to find an optimal hybrid parallel inference strategy with maximum throughput. The control variables of the strategy includes the number of groups, group-device assignments and model partition ratios. Our experimental evaluation demonstrates that compared to PipeEdge, a pipeline parallel inference framework for heterogeneous cluster, our strategy can achieve 1.7× −3.4× acceleration in an 8-device heterogeneous cluster without loss of accuracy.

关键词：

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：