检索结果-内蒙古大学图书馆

International Conference on Technologies and Applications of Artificial Intelligence (TAAI)

作者： Jen-Wei Wang Kai-Hsiang Chen Jen-Wei Huang National Cheng Kung University Tainan Taiwan Graduate Program for Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan

ISBN: (纸本)9781665408264

With the development of E-commerce, an Automated Question-Answering system takes a crucial part in customer service. Question classification, which assigns labels to questions according to the answer types, is one of the tasks in question answering. Previous methods usually used handcraft features like named entity recognition, but it needs the predefined dictionary or tools. The machine learning approaches are recently applied to this task and achieve high accuracy. In this paper, we proposed HAEE, a Hierarchical intra-Attention Enhancement Encoder which composed of bidirectional GRUs and intra-attentions. In addition, we adopt the character input to address the issue of the OOV (Out-Of-Vocabulary) problem and create multiple intra-attentions to simulate the certain relationships between characters (Chinese) or words (English) to enhance the influence of tokens on the sentence. We evaluate the HAEE model in an actual corporate setting and several datasets. As shown in the experimental results, our HAEE model outperforms the existing state-of-the-art models on question classification tasks, especially for the Chinese corpus.

关键词： Dictionaries Customer services Machine learning Predictive models Electronic commerce Task analysis

来源：评论

学校读者我要写书评

暂无评论

AV-Lip-Sync+: Leveraging AV-HuBERT to Exploit Multimodal Inconsistency for Video Deepfake Detection

arXiv

引用

arXiv 2023年

作者： Shahzad, Sahibzada Adil Hashmi, Ammarah Peng, Yan-Tsung Tsao, Yu Wang, Hsin-Min The Social Networks and Human-Centered Computing Program Taiwan International Graduate Program Academia Sinica Taipei11529 Taiwan The Department of Computer Science National Chengchi University Taipei11605 Taiwan The Institute of Information Systems and Applications National Tsing Hua University Hsinchu30013 Taiwan The Research Center for Information Technology Innovation Academia Sinica Taipei11529 Taiwan The Institute of Information Science Academia Sinica Taipei11529 Taiwan

Multimodal manipulations (also known as audiovisual deepfakes) make it difficult for unimodal deepfake detectors to detect forgeries in multimedia content. To avoid the spread of false propaganda and fake news, timely detection is crucial. The damage to either modality (i.e., visual or audio) can only be discovered through multi-modal models that can exploit both pieces of information simultaneously. Previous methods mainly adopt uni-modal video forensics and use supervised pre-training for forgery detection. This study proposes a new method based on a multi-modal self-supervised-learning (SSL) feature extractor to exploit inconsistency between audio and visual modalities for multi-modal video forgery detection. We use the transformer-based SSL pre-trained Audio-Visual HuBERT (AV-HuBERT) model as a visual and acoustic feature extractor and a multi-scale temporal convolutional neural network to capture the temporal correlation between the audio and visual modalities. Since AV-HuBERT only extracts visual features from the lip region, we also adopt another transformer-based video model to exploit facial features and capture spatial and temporal artifacts caused during the deepfake generation process. Experimental results show that our model outperforms all existing models and achieves new state-of-the-art performance on the FakeAVCeleb and DeepfakeTIMIT datasets. © 2023, CC BY.

关键词： Audio acoustics

来源：评论

学校读者我要写书评

暂无评论

Effects of Spatial Uniformity of Continuous and Pulse Laser Irradiation on the Microstructure and Mechanical Properties of Ti-6Al-4V in Powder Bed Fusion

SSRN

引用

SSRN 2025年

作者： Moon, Seunghwan Ji, Seungmuk Ko, Yoonseok Lee, Min-Su Jun, Tea-Sung Kim, Dong-Ik Yeo, Jong-Souk School of Integrated Technology College of Computing Yonsei University Seoul03722 Korea Republic of BK21 Graduate Program in Intelligent Semiconductor Technology Yonsei University Seoul03722 Korea Republic of Seoul02792 Korea Republic of Department of Mechanical Engineering Incheon National University Incheon22012 Korea Republic of Hankook Precision Works 45 Munpyeongseo-ro Daedeok-gu Daejeon34303 Korea Republic of

Laser beam powder bed fusion (PBF-LB/M) with Ti-6Al-4V (Ti64) powder is a promising method for fabricating medical implants owing to its ability to fabricate precise structures and the biocompatibility of the fabricated material. The use of a pulsed laser source in a PBF-LB/M system has been proposed for stable irradiation with an appropriate amount of energy. In this study, the pulse width modulation (PWM) method was adapted into a PBF-LB/M machine with a laser that operates in both continuous wave (CW) and pulsed wave modes. The effects of CW and PWM lasers on the microstructure and mechanical properties of the fabricated material based on the volumetric energy density (VED) calculated using the average power were compared. Results revealed that the uniform distribution of energy irradiation across the entire region ensured the similarity in the porosities and Vickers hardness tendencies conferred by CW and PWM lasers in the specimens according to the VED. In contrast, the spatially nonuniform distribution of the laser irradiation resulted in a significantly higher porosity in the specimen fabricated using the PWM laser than that produced using the CW laser at the same VED, resulting in reduced compressive yield strength. Additionally, the electron backscattered diffraction analysis of the grain structures in the fabricated specimens revealed that there were no significant differences in the average grain size, phase distribution, and misorientation angle of the samples produced using CW and PWM lasers at the same VED. However, sharper grains with a grain shape aspect ratio of less than 0.3 were 7% higher in specimens produced using the PWM laser. This study highlights the possibility of fabricating medical implants with desired patient bone-specific microstructure and mechanical properties. © 2025, The Authors. All rights reserved.

关键词： Vickers hardness

来源：评论

学校读者我要写书评

暂无评论

Mobile application to track people in covid19 monitoring and patients under covid19 supervision 2

Mobile application to track people in covid19 monitoring and...

引用

2nd International Conference on Biospheric Harmony Advanced Research, ICOBAR 2020

作者： Chrysler, A. Warnars, H.L.H.S. Utomo, W.H. Computer Science Department School of Computer Science Bina Nusantara University Jakarta11480 Indonesia Computer Science Department BINUS Graduate Program-Doctor of Computer Science Bina Nusantara University Jakarta11480 Indonesia Department of Magister Science of Information Technology Faculty of Computing President University Bekasi17550 Indonesia

It is crucial for the community including the government and health workers to collaborate to halt the spread of Covid-19. The idea of developing the mobile application surfaced from the previous findings. Previous researches have implemented and developed different features to better the application. The development of a mobile application to provide a platform that will assist people with information regarding patients that are around the perimeter of users to help notify them. With the help of the notification, users will be able to avoid the chances of them being in contact with the people (ODP), patients that are under surveillance (PDP) confirmed patients. All patients including ODP and PDP are required to have the application therefore, the Minister of Health will be able to track the geolocation of patients. Moreover, people will be able to be aware of patients that are around their perimeter. Therefore, with the help of the application, it will be able to help assist the community for them to be aware of and to be able to avoid being in contact with the infected patients. © Published under licence by IOP Publishing Ltd.

关键词： Mobile computing

来源：评论

学校读者我要写书评

暂无评论

Predicting Neurological Outcomes of Comatose Cardiac Arrest Patients Using Transformer Neural Networks with EEG Data

Predicting Neurological Outcomes of Comatose Cardiac Arrest ...

引用

Computers in Cardiology (CinC)

作者： Jefferson Dionisio Che Lin Lian-Yu Lin Wen-Chau Wu Smart Medicine and Health Informatics Program National Taiwan University (NTU) Taipei Taiwan Department of Electrical Engineering NTU Graduate Institute of Communication Engineering NTU School of Medicine NTU Center for Advanced Computing and Imaging in Biomedicine NTU Center for Biotechnology NTU Department of Internal Medicine NTU Hospital Taipei Taiwan Institute of Medical Device and Imaging NTU Department of Radiology College of Medicine NTU Graduate Institute of Clinical Medicine NTU

As part of the 2023 PhysioNet Challenge, our team FINDING_MEMO utilized Transformer to predict outcomes using patient EEG data since it excels at dealing with sequential data like EEG. We mainly used the Transformer encoder block's multi-head self-attention to generate representations from the input and leverage several hidden layers to form the final prediction. Using the latest EEG from every patient, our team achieved the challenge score of 0.42 with the hidden validation set (ranked 36th out of 73 invited teams) and obtained a result of 0.37 (ranked 29th out of 36 qualified teams). Our results show a consistent performance across varying EEG recording durations in both the validation and test set. Our team also had the second-best score when evaluated, with only 12 hours of available recordings in the test set. Such promising results showcase the models' generalizability and clinical potential in predicting outcomes for comatose patients, especially for limited available EEG recordings.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A linguistic approach to short sentences keywords identification for a question answering system

引用

International Journal of Web Engineering and Technology 2019年第4期14卷 367-382页

作者： Araujo, Denis Rigo, Sandro José Schmitt, Bruna Koch Hentges, Alencar Applied Computing Graduate Program Universidade do Vale do Rio dos Sinos - UNISINOS São Leopoldo Brazil

One of the aims of question answering systems is to identify which words are more relevant to understand the users' needs. Known approaches involve the identification of the users' intentions through a set of previously built related sentences. Some limitations of these approaches are the lack of flexibility and limited selection options. In this paper, we present an approach based on computational linguistics to identify the keywords in short sentences for question answering systems. The main contribution of our approach is related to the new way we use the information generated by the natural language processing tools to identify the keywords of the sentences, by profoundly exploring the linguistic information to select the keywords of the questions. Besides, we emphasise the generalisation and the simplicity of our algorithm. The efficiency of our method was proved by the performance of 0.9776 in precision, recall value of 0.9962, resulting in an F1 score of 0.9868 reached in the validation experiment using QALD-7 as a gold standard. Copyright © 2020 Inderscience Enterprises Ltd.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

Improvement of Spatial Ambiguity in Multi-Channel Speech Separation Using Channel Attention

Improvement of Spatial Ambiguity in Multi-Channel Speech Sep...

引用

Asia-Pacific Signal and Information Processing Association Annual Summit and Conference (APSIPA)

作者： Qian-Bei Hong Chung-Hsien Wu Thanh Binh Nguyen Hsin-Min Wang Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Tainan Taiwan National Cheng Kung University Tainan Taiwan

ISBN: (纸本)9781665441629

Multi-channel speech separation has been successfully applied in a complex real-world environment such as the far-field condition. The common solution to deal with the far-field condition is using a multi-channel signal captured by a structured microphone array and leveraging the inner difference between channels to enhance the speech separation performance. The spatial feature has been widely used in recent speech separation research. This feature appears to be insufficient when the location information becomes ambiguous. This is known as the spatial ambiguity problem. In order to deal with the spatial ambiguity problem, this study proposes an attention mechanism for the Temporal-Spatial Neural Filter (TSNF), in which the channel attention on merged features and the feature map of 1D convolution block in the temporal convolution network is proposed. The proposed method is evaluated on the multi-channel reverberant dataset which is built based on the WSJ0-2mix dataset. The dataset is simulated in the real-environment room by using the Room Impulse Response generator. In the experimental results, the proposed methods produced the SI -SNR improvement of about 1.2dB in close speakers' case, while a small decrease of 0.1dB in other cases.

关键词： Convolution Information processing Speech enhancement Information filters Microphone arrays Generators Reliability

来源：评论

学校读者我要写书评

暂无评论

Exploring NLMS and IPNLMS Adaptive Filtering VLSI Hardware Architectures for Robust EEG Signal Artifacts Elimination

Exploring NLMS and IPNLMS Adaptive Filtering VLSI Hardware A...

引用

IEEE International Conference on Electronics, Circuits and Systems (ICECS)

作者： Andrei La Rosa Patrícia Ucker Guilherme Paim Eduardo da Costa Sérgio Almeida Sergio Bampi Graduate Program on Computing Federal University of Pelotas (UFPel) Brazil Graduate Program on Electronic Engineering and Computing Catholic University of Pelotas (UCPel) Brazil Graduate Program on Microelectronics (PGMicro) Federal University of Rio Grande do Sul (UFRGS) Brazil

ISBN: (数字)9781728160443

ISBN: (纸本)9781728160450

The elimination of artifacts is a crucial procedure to extract the full potential of the information into the EEG processing. Embedded systems require low circuit area (cost) and efficient hardware architectures. Adaptive filtering plays a vital role as a single method and hybrid approaches for robustly eliminating the noise of the real-world EEG measures. In this paper, we propose and implement hardware architectures for both NLMS and IPNLMS adaptive filters. We investigate the filtering performance and circuit area, timing, and power dissipation of the hardware architecture proposals. To leverage the power-efficiency, we improve our hardware architectures employing the data-gating circuit design technique, which provided up to 20% power savings. Also, applying an HDL-Simulink co-simulation, we perform the hardware architectures tradeoff comparing the synthesis results and filtering performance. Our investigation demonstrates that IPNLMS reduces the time domain error in 11%, increasing less than 1% of circuit area and about the double of the energy per operation, compared to the NLMS.

关键词： Electroencephalography Hardware Computer architecture Convergence Measurement Clocks Proposals

来源：评论

学校读者我要写书评

暂无评论

Speaker-Specific Articulatory Feature Extraction Based on Knowledge Distillation for Speaker Recognition

引用

APSIPA Transactions on Signal and Information Processing 2023年第2期12卷

作者： Qian-Bei Hong Hsin-Min Wang Chung-Hsien Wu Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica Taiwan Graduate Program of Multimedia Systems and Intelligent Computing National Cheng Kung University and Academia Sinica and Department of Computer Science and Information Engineering National Cheng Kung University Taiwan

This paper proposes a novel speaker-specific articulatory feature (AF) extraction model based on knowledge distillation (KD) for speaker recognition. First, an AF extractor is trained as a teacher model for extracting the AF profiles of the input speaker dataset. Next, a KD-based speaker embedding extraction method is proposed to distill the speaker-specific information from the AF profiles in the teacher model to a student model based on multi-task learning, in which the lower layers not only capture the speaker characteristics from acoustic features, but also learn the speaker-specific features from the AF profiles for robust speaker representation. Finally, speaker embeddings are extracted from the high-level layer, and the obtained speaker embeddings are further used to train a probabilistic linear discriminant analysis (PLDA) model for speaker recognition. In the experiments, speaker embedding models were trained using the VoxCeleb2 dataset and the AF extractor was trained based on the LibriSpeech dataset, and the performance was evaluated using the VoxCeleb1 dataset. The experiments showed that the proposed KD-based models outperformed the baseline models without KD. Furthermore, feature concatenation of multimodal results can further improve the performance.

关键词： Speaker recognition articulatory feature knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

Learning from failure - Development of a Culture of Failure Scale for Higher Education

Learning from failure - Development of a Culture of Failure ...

引用

World Engineering Education Forum - Global Engineering Deans Council (WEEF-GEDC)

作者： Michael M. Malschützky Ph.D. Jamie R. Gurganus Centre for Teaching Development and Innovation (ZIEL) & Department of Management Sciences Hochschule Bonn-Rhein-Sieg University of Applied Sciences Sankt Augustin Germany Engineering & Computing Education Program Mechanical Engineering & Graduate School University of Maryland Baltimore County Baltimore USA

ISBN: (数字)9781665475280

ISBN: (纸本)9781665475297

Benefits of a failure friendly culture, e.g., learning from failure, are widely known in occupational settings. Validated scales have been developed to measure organizational failure culture and individuals' mind-sets on failure. While research on learning from failure exists in secondary education, scales for higher education are lacking. To support both higher education engineering instructors and students, this contribution aims to develop a Culture of Failure Scale to assess students' and lecturers' handling of failures in engineering higher education settings. This data-driven approach helps inform instructors about aspects of educational settings that are safe and conducive to learning and supports their students to develop a mind-set where failures are seen as a source for improvements and learning. Exemplary application of the developed scale is shown by assessing the failure culture in different groupings, e.g., gender, between two participating German and US institutions.

关键词： Correlation Education Psychology Reliability History Engineering students Principal component analysis

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：