检索结果-内蒙古大学图书馆

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： Fanchang Tang YaLing Amit Yadav Abhishek Pratap Sah Asif Khan Department of Software Engineering Chengdu Neusoft University Chengdu China College of Engineering IT and Environment Charles Darwin University NT Australia School of Management Science and Engineering University of Electronic Science and Technology of China Chengdu China Department of Computer Application Integral University Lucknow India

ISBN: (数字)9798331522667

ISBN: (纸本)9798331522674

Existing research on speaker and emotional voice conversion often focuses on separate tasks, neglecting their joint exploration. Furthermore, the limited availability of emotional corpora for target speakers poses a significant challenge for training robustness and generalized models. This paper proposes an improved scheme for speaker-emotion voice conversion with limited target speaker's emotional corpus, integrating a large language model and a pre-trained emotional speech synthesis model. It introduces several enhancements to enhance the quality of converted speech in terms of speaker similarity and emotional expressiveness. First, emotionally tagged text is generated using a large language model and emotional speech is synthesized from this text using a fine-tuned pre-trained emotional speech synthesis model. Then, a speaker-emotion voice conversion model is co-trained with both synthesized and real target emotional speech. Finally, the model is fine-tuned with the real target emotional speech to further boost the speaker and emotional similarity.

关键词： Training Large language models Computational modeling Speech enhancement Robustness Libraries Speech synthesis Informatics Optimization Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Fairness and Sparsity within Rashomon sets: Enumeration-Free Exploration and Characterization

arXiv

引用

arXiv 2025年

作者： Langlade, Lucas Ferry, Julien Laberge, Gabriel Vidal, Thibaut Ecole nationale des ponts et chaussées Paris France CIRRELT & SCALE-AI Chair in Data-Driven Supply Chains Department of Mathematics and Industrial Engineering Polytechnique Montréal Canada Department of Computer Engineering and Software Engineering Polytechnique Montréal Canada

We introduce an enumeration-free method based on mathematical programming to precisely characterize various properties such as fairness or sparsity within the set of "good models", known as Rashomon set. This approach is generically applicable to any hypothesis class, provided that a mathematical formulation of the model learning task exists. It offers a structured framework to define the notion of business necessity and evaluate how fairness can be improved or degraded towards a specific protected group, while remaining within the Rashomon set and maintaining any desired sparsity level. We apply our approach to two hypothesis classes: scoring systems and decision diagrams, leveraging recent mathematical programming formulations for training such models. As seen in our experiments, the method comprehensively and certifiably quantifies trade-offs between predictive performance, sparsity, and fairness. We observe that a wide range of fairness values are attainable, ranging from highly favorable to significantly unfavorable for a protected group, while staying within less than 1% of the best possible training accuracy for the hypothesis class. Additionally, we observe that sparsity constraints limit these trade-offs and may disproportionately harm specific subgroups. As we evidenced, thoroughly characterizing the tensions between these key aspects is critical for an informed and accountable selection of models. Copyright © 2025, The Authors. All rights reserved.

关键词： Self-supervised learning

来源：评论

学校读者我要写书评

暂无评论

Fully Distributed Multi-Agent RL Framework for QoS Routing

Fully Distributed Multi-Agent RL Framework for QoS Routing

引用

IEEE Future Networks World Forum (FNWF)

作者： Quang Huy Duong Emil Janulewicz Brigitte Jaumard Abdelhak Bentaleb Sergio Slobodrian Department of Computer Science & Software Engineering Concordia University Montréal QC Canada Ciena Ottawa ON Canada

Classical routing heuristics, e.g., Open Shortest Path First, have several significant issues, such as they are not able to generalize or adapt to heterogeneous environments including dynamics of topology, traffic patterns, and Quality of Service (QoS) requirements. To generalize solutions, network operators recently utilized machine learning algorithms at centralized controllers. However, centralized machine learning solutions are not scalable due to many reasons, such as slow data transfer to the central controller in a large network. Distributed multi-agent systems do not require a tedious and complex central controller while reducing data storage and computation burden as tasks are divided and handled at local servers/computers. In this paper, we present a fully distributed multi-agent system named MADQN, addressing the request provisioning problem, i.e., provisioning a request on a dedicated path satisfying latency and bandwidth requirements. MADQN applies a Deep Q-Network reinforcement learning algorithm to train the agents. Although each agent has its data and policy locally, they can still cooperate with other agents to finish a common routing task that maximizes the total reward. We evaluate the effectiveness of the MADQN with a benchmark network that consists of 100 nodes and 432 directed links, and a dynamic set of thousands of requests. The results show that the agents in MADQN can learn to cooperate and provision 99% of the requests, which is about a 9% improvement against the centralized single agent scheme.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A review on computer vision and machine learning techniques for automated road surface defect and distress detection

引用

Journal of Smart Cities and Society 2023年第PRE-PRESS期Pre-press卷 1-17页

作者： Chen, Xuejing Yongchareon, Sira Knoche, Martin Computer Science and Software Engineering Department Auckland University of Technology Auckland New Zealand N3T Limited Whangarei New Zealand

As the pace grows in the development of image processing techniques and the current applications rise in machine learning and deep learning techniques for visual inspections and physical assessment, this article reviews the existing literature. It provides a detailed synthesis of the overview of surface pavement conditions, computer-vision-based technologies for road damage detection, various datasets and data collection methods. We analyse and compare different machine-learning methods and models proposed in the literature and identify challenges that need to be addressed in the future in road surface defect detection.

关键词： Road condition assessment distress detection road defects analysis

来源：评论

学校读者我要写书评

暂无评论

Slice-Fusion: Reducing False Positives in Liver Tumor Detection for Mask R-CNN

引用

IEEE/ACM Transactions on Computational Biology and Bioinformatics 2023年第5期20卷 3267-3277页

作者： Tu, Deng-Yao Lin, Peng-Chan Chou, Hsin-Hung Shen, Meng-Ru Hsieh, Sun-Yuan National Cheng Kung University Master Degree Program on Artificial Intelligence Tainan City70101 Taiwan National Cheng Kung University Institute of Medical Informatics Department of Oncology Department of Genomic Medicine National Cheng Kung University Hospital College of Medicine Department of Computer Science and Information Engineering Tainan City70101 Taiwan National Chi Nan University Department of Computer Science and Information Engineering Nantou County54561 Taiwan National Cheng Kung University Graduate Institute of Clinical Medicine Department of Obstetrics and Gynecology Department of Pharmacology National Cheng Kung University Hospital College of Medicine Tainan City70101 Taiwan National Cheng Kung University Institute of Medical Information Institute of Manufacturing Information and Systems Center for Innovative FinTech Business Models International Center for the Scientific Development of Shrimp Aquaculture Department of Computer Science and Information Engineering Tainan City70101 Taiwan

Automatic liver tumor detection from computed tomography (CT) makes clinical examinations more accurate. However, deep learning-based detection algorithms are characterized by high sensitivity and low precision, which hinders diagnosis given that false-positive tumors must first be identified and excluded. These false positives arise because detection models incorrectly identify partial volume artifacts as lesions, which in turn stems from the inability to learn the perihepatic structure from a global perspective. To overcome this limitation, we propose a novel slice-fusion method in which mining the global structural relationship between the tissues in the target CT slices and fusing the features of adjacent slices according to the importance of the tissues. Furthermore, we design a new network based on our slice-fusion method and Mask R-CNN detection model, called Pinpoint-Net. We evaluated proposed model on the Liver Tumor Segmentation Challenge (LiTS) dataset and our liver metastases dataset. Experiments demonstrated that our slice-fusion method not only enhance tumor detection ability via reducing the number of false-positive tumors smaller than 10mm, but also improve segmentation performance. Without bells and whistles, a single Pinpoint-Net showed outstanding performance in liver tumor detection and segmentation on LiTS test dataset compared with other state-of-the-art models. © 2004-2012 IEEE.

关键词： Tumors

来源：评论

学校读者我要写书评

暂无评论

Improving Electrically Evoked Compound Action Potential Based on Electrical Field Imaging and Electrode Interfaces

Improving Electrically Evoked Compound Action Potential Base...

引用

IEEE Conference on Electromagnetic Field Computation

作者： Charles T.M. Choi Chun Ting Ke Jelani Lawrence Alexander C. C. Wang Department of Electronics and Electrical Engineering College of Electrical & Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Electrical and Control Engineering College of Electrical & Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Institute of Biomedical Engineering College of Electrical & Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Electrical Engineering & Computer Science International Graduate Program College of Electrical & Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan

ISBN: (数字)9798350348958

ISBN: (纸本)9798350348965

The electrically evoked compound action potential (ECAP) has been used in various clinical studies and has become a key physiological signal for cochlear implants (CI). This study used four sensing electrodes to record ECAP signals based on the alternating polarity approach. An electrical field imaging (EFI) result based on the finite element method was used to obtain the interface impedance, then ECAP simulation results were computed and compared with a patient's clinical ECAP measurements. Preliminary modeling results show that the interface impedance obtained by this EFI-based technique can improve the simulation accuracy of the ECAP model. The ECAP modeling result will be compared with clinical ECAP measurements to validate the model in the full paper.

关键词： Electrodes Action potentials Impedance measurement Computational modeling Simulation Imaging Finite element analysis

来源：评论

学校读者我要写书评

暂无评论

Streamlining Attendance with Voice Recognition via Gaussian Mixture Model

Streamlining Attendance with Voice Recognition via Gaussian ...

引用

IT and Industrial Technologies (ICIT), International Conference on

作者： Noor Ali Khadija Ali Fatimah Ali Aaminah Ali Nisar Ali Raja Hashim Ali A-Levels Lahore Pakistan Department of Software Engineering NUST College of Electrical and Mechanical Engineering Islamabad Pakistan Faculty of Engineering and Applied Science University of Regina Regina Canada Department of Artificial Intelligence Faculty of Computer Science & Engineering GIK Institute of Engineering Sciences & Technology Topi Pakistan Department of Business University of Europe for Applied Sciences Potsdam Germany

ISBN: (数字)9798331504465

ISBN: (纸本)9798331504472

Voice recognition systems are crucial because they allow seamless human-computer interaction and improve accessibility for users of all abilities. The use of these technologies in hands-free control, language translation, virtual assistants, transcription services, and hands-free control is revolutionising how we engage with technology and enhancing convenience and productivity in general. Several attendance systems based on voice recognition exist, but we wanted to deploy an attendance system with a good graphical user interface specifically for students of GIK Institute. For this purpose, we wanted to make a user-friendly and accurate voice recognition system based and trained on self-provided data of ten students. This study introduces an AI-driven attendance system, which demonstrates high efficiency and accuracy in identifying students’ daily class attendance. To achieve this, the Gaussian Mixture Model approach was employed. The paper also delves into the utilization of libraries and methods, encompassing the training and validation of well-known machine learning models. Additionally, the system’s performance, its strengths, weaknesses and potential areas for improvement are also discussed in the study.

关键词： Biometrics Training Accuracy Translation Virtual assistants Speech recognition Transforms Security Gaussian mixture model Graphical user interfaces

来源：评论

学校读者我要写书评

暂无评论

Computing Salient Feature Points of 3D Model Based on Geodesic Distance and Decision Graph Clustering

引用

Recent Advances in computer Science and Communications 2021年第8期14卷 2489-2494页

作者： Sun, Dechao Chen, Nenglun Wang, Renfang Liu, Bangquan Liang, Feng College of Big Data and Software Engineering Zhejiang Wanli University Ningbo China Department of Computer Science Hong Kong University Hong Kong College of Digital Technology and Engineering Ningbo University of Finance & Economics Ningbo China

Introduction: Computing Salient Feature Points (SFP) of 3D models has important application value in the field of computer graphics. In order to extract the SFP more effectively, a novel SFP computing algorithm based on geodesic distance and decision graph clustering is proposed. Methods: Firstly, the geodesic distance of model vertices is calculated based on the heat conduction equation, and then the average geodesic distance and importance weight of vertices are calculated. Finally, the decision graph clustering method is used to calculate the decision graph of model vertices. Results and Discussion: 3D models in SHREC 2011 dataset are selected to test the proposed algorithm. Compared with the existing algorithms, this method calculates the SFP of the 3D model from a global perspective. Results show that it is not affected by model posture and noise. Conclusion: Our method maps the SFP of the 3D model to the 2D decision-making diagram, which simplifies the calculation process of SFP, improves the calculation accuracy and possesses strong robustness. © 2021 Bentham Science Publishers.

关键词： Clustering algorithms

来源：评论

学校读者我要写书评

暂无评论

An improved kNN method based on Spearman's rank correlation for handling medical missing values

An improved kNN method based on Spearman's rank correlation ...

引用

2022 International Conference on Machine Learning and Knowledge engineering, MLKE 2022

作者： Liang, Chuchao Zhang, Lei Wan, Zhi Li, Dongze Li, Dong Li, Wentao Sichuan University School of Computer Science School of Software Engineering Chengdu610065 China Sichuan University West China Hospital Department of Emergency Medicine Chengdu610041 China

ISBN: (纸本)9781665495677

Acute chest pain is a common symptom of cardiovascular disease, and its data have important research value. However, the presence of missing value in medical datasets is almost inevitable, which may adversely affect the results of medical data mining. The imputation method plays an important role in the missing value processing method and it can avoid the loss of information due to sample deletion. In this paper, we proposed a new weighted kNN method based on Spearman correlation, named Spearman-Weights kNN(SW-kNN). It is used for missing value imputation in medical datasets that contain a large proportion of samples with missing values. We conducted experiments on the acute chest pain dataset from West China Hospital and compared SW-kNN with seven other methods (Zero, Median, Mean, Random Forest, kNN, NS-kNN, DNNI). The results show that our proposed method has the best performance among all imputation methods in the experiments, which indicates that SW-kNN can successfully handle missing values in medical data. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

DisCOV: Distributed COVID-19 Detection on X-Ray Images with Edge-Cloud Collaboration

DisCOV: Distributed COVID-19 Detection on X-Ray Images with ...

引用

2022 IEEE World Congress on Services, SERVICES 2022

作者： Xu, Xiaolong Tian, Hao Zhang, Xuyun Qi, Lianyong He, Qiang Dou, Wanchun Nanjing University of Information Science and Technology School of Computer and Software Nanjing China Macquarie University Department of Computing Sydney Australia Qufu Normal University School of Information Science and Engineering Rizhao China Swinburne University of Technology School of Software and Electrical Engineering Melbourne Australia Nanjing University State Key Laboratory for Novel Software Technology Nanjing China

[J1C2 Presentation Abstract at IEEE SERVICES 2022 for IEEE Transactions on Services Computing DOI 10.1109/TSC.2022.3142265]

ISBN: (数字)9781665481311

ISBN: (纸本)9781665481311

[J1C2 Presentation Abstract at IEEE SERVICES 2022 for IEEE Transactions on Services Computing DOI 10.1109/TSC.2022.3142265]

关键词： COVID-19 Image edge detection Collaboration X-ray imaging

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：