检索结果-内蒙古大学图书馆

IEEJ Transactions on Electronics, Information and Systems 2025年第1期145卷 16-24页

作者： Shouno, Kazuhiro Sato, Lina Fukagawa, Kanta Tanimoto, Hiroshi Muto, Cosy Division of Information Engineering University of Tsukuba 1-1-1 Tennoudai Ibaraki Tsukuba305-8573 Japan Graduate School of Science and Technology Degree Programs in Systems and Information Engineering Master’s Program in Computer Science University of Tsukuba Japan Kitami Institute of Technology 165 Koen-cho Hokkaido Kitami090-8507 Japan Faculty of Education Nagasaki University 1-14 Bunkyo-machi Nagasaki852-8521 Japan

This paper proposes a measurement technique for an integrated complex filter. The proposed method is based on two measurement methods with integrated circuitry for calibration. It is accomplished by applying square waves to an FUT (Filter Under Test) instead of sinusoidal waves or by superposing transfer characteristics obtained by applying a single sinusoidal wave to an FUT. In both of the above methods, the output signal connected to the external measurement equipment via a 50 Ω coaxial cable and so on. In this case, the output signal of the FUT should be amplified by internal or external amplifiers, which degrades the response. However, it is cancelled out by the proposed calibration circuitry with some analog switches. In addition to the above, for the RC polyphase filter, the source resistance and the load capacitance degrade the measurement results and their effect is discussed. The validity of the proposal is confirmed through computer simulation for a third-order RCPF whose passband is 8–40 MHz fabricated by Phenitec 0.6 µm CMOS process. It is shown that the measurement error is −1.10 dB for the square-wave method and −1.00 dB and −0.43 degrees for the superposition method at 40 MHz. © 2025 The Institute of Electrical Engineers of Japan.

关键词： Capacitance

来源：评论

学校读者我要写书评

暂无评论

Human Activity Classification: A LSTM and MediaPipe Approach for Intelligent Systems Application 6

Human Activity Classification: A LSTM and MediaPipe Approach...

引用

6th International Conference on Control and Robotics, ICCR 2024

作者： Chen, Yi-An Yang, Pei-Ching Chang Jung Christian University Master Degree Program in Information and Design Tainan Taiwan Chang Jung Christian University Department of Computer Science and Information Engineering Tainan Taiwan Chang Jung Christian University Artificial Intelligence Research Center Tainan Taiwan

ISBN: (纸本)9798331518158

With advancements in artificial intelligence, computer vision technologies have seen significant progress, enabling applications like facial recognition, autonomous driving, and medical imaging. This study leverages the Multi-Camera Action Dataset (MCAD) and MediaPipe Pose to create a skeletal dataset for training a Long Short-Term Memory (LSTM) model to recognize 18 types of daily actions. Evaluation using confusion matrix and F1 score reveals that Action 16 (Object Carry) is often misclassified as Action 7 (Walk) due to similar leg movements, and Action 9 (Cell to Ear) as Action 1 (Wave) due to similar hand movements. Future work aims to enhance model accuracy and explore broader applications in physical activity and exercise analysis. © 2024 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Using SYCLomatic to Migrate CUDA Code to oneAPI Adapting NVIDIA GPU

Using SYCLomatic to Migrate CUDA Code to oneAPI Adapting NVI...

引用

IEEE International Conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS)

作者： Wentao Liang Norihisa Fujita Ryohei Kobayashi Taisuke Boku Master's Program in Computer Science Degree Program in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Center for Computational Sciences University of Tsukuba

ISBN: (数字)9798350383454

ISBN: (纸本)9798350383461

Nowadays, the use of accelerators in high performance computing has become more common than ever before. The most used accelerators must be the Graphics Processing Unit (GPU). It has emerged as an important component in most of the parallel computing scenarios, surpassing the capabilities of the traditional Central Processing Unit (CPU) in perspective of both performance and energy efficiency.

关键词： Codes Conferences High performance computing Graphics processing units Cluster computing Parallel processing Energy efficiency Central Processing Unit

来源：评论

学校读者我要写书评

暂无评论

A UNIFIED MODEL FOR ZERO-SHOT SINGING VOICE CONVERSION AND SYNTHESIS 23

A UNIFIED MODEL FOR ZERO-SHOT SINGING VOICE CONVERSION AND S...

引用

23rd International Society for Music Information Retrieval Conference, ISMIR 2022

作者： Wu, Jui-Te Wang, Jun-You Jang, Jyh-Shing Roger Su, Li NTU-AS Data Science Degree Program National Taiwan University Taiwan Department of Computer Science and Information Engineering National Taiwan University Taiwan Institute of Information Science Academia Sinica Taiwan

ISBN: (纸本)9781732729926

Recent advances in deep learning not only facilitate the implementation of zero-shot singing voice synthesis (SVS) and singing voice conversion (SVC) tasks but also provide the opportunity to unify these two tasks into one generalized model. In this paper, we propose such a model that generate the singing voice of any target singer from any source singing content in either text or audio format. The model incorporates self-supervised joint training of the phonetic encoder and the acoustic encoder, with an audio-to-phoneme alignment process in each training step, such that these encoders map the audio and text data respectively into a shared, temporally aligned, and singer-agnostic latent space. The target singer’s latent representations encoded at different granularity levels are all trained to match the source latent representations sequentially with the attention mechanisms in the decoding stage. This enables the model to generate unseen target singer’s voice with fine-grained resolution from either text or audio sources. Both objective and subjective experiments confirmed that the proposed model is competitive with the state-of-the-art SVC and SVS methods. © J.-T. Wu, J.-Y. Wang, J.-S. R. Jang and L. Su.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic weight-based connectivity recovery in wireless sensor and actor networks

引用

Journal of Supercomputing 2024年第1期80卷 734-760页

作者： Chiang, Mao-Lun Hsieh, Hui-Ching Lin, Tzu-Ling Chang, Tsui-Ping Chen, Hong-Wei Bachelor Degree Program of Artificial Intelligence National Taichung University of Science and Technology Taichung City Taiwan Department of New Media Communication Hsing Wu University New Taipei City Taiwan Department of Business Management National Taichung University of Science and Technology Taichung City Taiwan Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung City Taiwan Department of Information and Communication Engineering Chaoyang University of Technology Taichung City Taiwan

Wireless sensors and actor networks (WSANs) have been widely used in various fields, from basic data collection to precise real-time control and monitoring, including battlefield monitoring, rescue, and exploration. The actor nodes in a WSAN play a key role in processing and transmitting data, and because of the harsh environmental conditions encountered, network node failures are prone to occur. The failure of an actor causes a loss of connectivity with its neighbor nodes, resulting in network splits and failure to deliver messages between nodes. Therefore, determining how to quickly and autonomously recover network connectivity while minimizing the moving distance of backup nodes and the number of relocated nodes is crucial. In this paper, we propose a dynamic weight-based connectivity recovery (DWCR) method to minimize the total moving distance of actor nodes, the number of relocated nodes, the total messages sent, and the coverage loss rate. The proposed DWCR method involves selecting a backup node for each critical node by dynamically adjusting the weight. If a critical node fails, the backup node starts to move to restore the connectivity of the failed node. The simulation results indicate that the proposed DWCR method outperforms the recovery through inward motion (RIM) method and other methods in terms of minimizing the total moving distance, the number of relocated nodes, and the total messages sent. However, because the RIM algorithm requires the relocation of more nodes during the network process, the DWCR algorithm is slightly inferior to the RIM algorithm in terms of coverage loss rate. Nevertheless, the DWCR algorithm still outperforms the distributed actor recovery algorithm and the distributed autonomous connectivity restoration method based on finite state machine algorithm. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Recovery

来源：评论

学校读者我要写书评

暂无评论

Mental Status Identification for Infertile Patients Using Artificial Intelligence Models 14th

Mental Status Identification for Infertile Patients Using Ar...

引用

14th International Conference on Frontier Computing, FC 2024

作者： Hsu, Hao-Siang Wang, Jong-Yi Chiou, Hai-Chi Wu, Fu-Hsing Lin, Chuen-Horng Chan, Yung‑Kuan Department of Computer Science and Information Engineering National Taichung University of Science and Technology Taichung404336 Taiwan Department of Health Services Administration China Medical University Taichung406040 Taiwan Bachelor Degree Program of Artificial Intelligence National Taichung University of Science and Technology Taichung404336 Taiwan Department of Management Information Systems National Chung-Hsing University Taichung402202 Taiwan

ISBN: (纸本)9789819623945

Infertile patients may be a high-risk group of mental disorder. The precise identification of the mental status of infertile patients can provide decision support to healthcare professionals and may be helpful in providing preventive measures accordingly. Rare studies focused on the mental status identification using artificial intelligence (AI) models for infertile people. This study aimed to precisely identify the mental status (anxiety and depression) of infertile patients using three AI models, the XGBoost, decision tree, and stacking models. The dataset, retrieved from a structured questionnaire survey in 2011, which included 400 infertility outpatients seeking reproductive treatments at three teaching hospitals in Taiwan was adopted for training and testing AI models. Aforementioned AI models were designed and reached identification performances of accuracy, precision, recall and area under ROC curve (AUC) equaling 0.75–0.82, 0.70–0.80, 0.64–0.72, and 0.64–0.72, respectively. The XGBoost model (accuracy = 0.82, precision = 0.80, recall = 0.72, and AUC = 0.72) outperformed or equaled the decision tree and stacking models in terms of accuracy, precision, recall, and AUC values. Designed AI models for mental status identification can be integrated into the clinical decision support system (CDSS) to provide the anxiety and depression group automatically. Accordingly, the worsening of infertility-related anxiety and depression can be prevented. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： artificial intelligence infertile patients Mental status identification stacking model XGBoost

来源：评论

学校读者我要写书评

暂无评论

CAMRI Loss: Improving the Recall of a Specific Class without Sacrificing Accuracy

CAMRI Loss: Improving the Recall of a Specific Class without...

引用

作者： Nishiyama, Daiki Fukuchi, Kazuto Akimoto, Youhei Sakuma, Jun Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Tsukuba-shi305-8577 Japan RIKEN Center for Advanced Intelligence Project Tokyo103-0027 Japan Department of Computer Science Faculty of Engineering Information and Systems University of Tsukuba Tsukuba-shi305-8577 Japan

In real world applications of multiclass classification models, misclassification in an important class (e.g., stop sign) can be significantly more harmful than in other classes (e.g., no parking). Thus, it is crucial to improve the recall of an important class while maintaining overall accuracy. For this problem, we found that improving the separation of important classes relative to other classes in the feature space is effective. Existing methods that give a class-sensitive penalty for cross-entropy loss do not improve the separation. Moreover, the methods designed to improve separations between all classes are unsuitable for our purpose because they do not consider the important classes. To achieve the separation, we propose a loss function that explicitly gives loss for the feature space, called class-sensitive additive angular margin (CAMRI) loss. CAMRI loss is expected to reduce the variance of an important class due to the addition of a penalty to the angle between the important class features and the corresponding weight vectors in the feature space. In addition, concentrating the penalty on only the important class hardly sacrifices separating the other classes. Experiments on CIFAR-10, GTSRB, and AwA2 showed that CAMRI loss could improve the recall of a specific class without sacrificing accuracy. In particular, compared with GTSRB's second-worst class recall when trained with cross-entropy loss, CAMRI loss improved recall by 9%. © 2023 The Institute of Electronics, Information and Communication Engineers.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Preliminary Evaluation of Kyokko for Inter-FPGA Communication Framework CIRCUS

Preliminary Evaluation of Kyokko for Inter-FPGA Communicatio...

引用

IEEE International Conference on Cluster Computing Workshops and Posters (CLUSTER WORKSHOPS)

作者： Kaito Kitazume Norihisa Fujita Ryohei Kobayashi Taisuke Boku Master's Program in Computer Science Degree Programs in Systems and Information Engineering Graduate School of Science and Technology University of Tsukuba Center for Computational Sciences University of Tsukuba

In recent years, Field-programmable Gate Arrays (FPGAs) are gaining attention as computational acceleration devices in the field of high-performance computing. By implementing specialized circuits that can be customiz... 详细信息

ISBN: (数字)9798350383454

ISBN: (纸本)9798350383461

关键词： Conferences High performance computing Circuits Cluster computing Low latency communication Field programmable gate arrays

来源：评论

学校读者我要写书评

暂无评论

The design of the cse-ucla evaluation model using topsis and ahp methods for optimizing digital library services in badung regency 3

The design of the cse-ucla evaluation model using topsis and...

引用

3rd International Conference on Vocational Education and Technology, IConVET 2020

作者： Atmaja, I.M.D.S. Divayana, D.G.H. Setemen, K. Master Degree Program in Computer Science Universitas Pendidikan Ganesha Indonesia Universitas Pendidikan Ganesha Indonesia

The Regional Archives and Library Office of Badung Regency must optimize the services provided in order to achieve excellent service quality. In its implementation, the office encountered difficulties in prioritizing aspects of services that require optimization. The purpose of this study was to design a Center for the Study of Evaluation-University of California in Los Angeles (CSE-UCLA) evaluation model using Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) and Analytical Hierarchy Process (AHP) to provide recommendations on which aspects of services need to be optimized. The research method used stages that included problem identification, problem formulation, literature review, data collection, data analysis, design, and conclusions. The TOPSIS and AHP methods had the ability to rank a variety of aspects in the CSE-UCLA model. Aspect with the lowest ranking was considered as the aspect that is prioritized for optimization. That aspects used five service criteria: Tangible, reliability, assurance, responsiveness, and empathy, all of which were classified in the "benefit"category. Each criterion had a value of 0.200, 0.200, 0.200, 0.200, 0.200 for the weight values for system assessment, program planning, program implementation, and program improvement, while for program certification: 0.556, 0.111, 0.111, 0.111, 0.111, respectively. © Published under licence by IOP Publishing Ltd.

关键词： Digital libraries

来源：评论

学校读者我要写书评

暂无评论

Predicting Microsatellite Instability from Histology Images with Dilated Neighborhood Attention Transformer in Colorectal Cancer 24

Predicting Microsatellite Instability from Histology Images ...

引用

24th IEEE International Conference on Bioinformatics and Bioengineering, BIBE 2024

作者： Chen, Yun-Chi Chao, Tung Phandita, Wimaya Nitya Sun, Tzu-Yu Wang, Huai-Zhi Hsieh, Yi-Hsien Hsu, Le-Yin Lin, Che Taipei Taiwan College of Bioresources and Agriculture NTU Taipei Taiwan National Taiwan University of Science and Technology Department of Computer Science and Information Engineering Taipei Taiwan Graduate Institute of Communication Engineering NTU Taipei Taiwan NTU Data Science Degree Program Taipei Taiwan NTU Department of Electrical Engineering Taipei Taiwan Center for Advanced Computing and Imaging in Biomedicine NTU Taipei Taiwan NTU Smart Medicine and Health Informatics Program Taipei Taiwan

ISBN: (纸本)9798331518622

Microsatellite instability (MSI) is a pivotal genetic marker influencing the efficacy of immunotherapy in colorectal cancer. Traditional MSI examination often requires additional genetic or immunohistochemical tests, whereas histology images, widely available in colorectal cancer diagnosis, offer a valuable alternative for MSI prediction. Although Transformer-based models have demonstrated promising outcomes in predicting MSI from histology images, they are hampered by traditional local attention mechanisms that struggle to capture long-range interdependencies and establish a comprehensive global receptive field. In this study, we introduce DiNAT-MSI, a novel framework for histology-based MSI prediction that incorporates the Dilated Neighborhood Attention Transformer (DiNAT). This model enhances global context recognition and substantially expands receptive fields, all without additional computational burden. Our results demonstrate that DiNAT-MSI achieves a superior patientwise AUROC compared to ResNet18 and Swin Transformer, along with commendable explainability. Our work not only illustrates a more accessible diagnostic tool for leveraging histological data but also underscores the potential of Transformerbased models with sophisticated attention designs in advancing precision medicine for colorectal cancer patients. © 2024 IEEE.

关键词： Diseases

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：