检索结果-内蒙古大学图书馆

27th International Conference on Pattern Recognition, ICPR 2024

作者： Siddhad, Gourav Dey, Sayantan Roy, Partha Pratim Iwamura, Masakazu Department of Computer Science and Engineering Indian Institute of Technology Roorkee Uttarakhand Roorkee247667 India Department of Core Informatics Graduate School of Informatics Osaka Metropolitan University Osaka Sakai599-8531 Japan

ISBN: (纸本)9783031781940

Driver fatigue detection is increasingly recognized as critical for enhancing road safety. This study introduces a method for detecting driver fatigue using the SEED-VIG dataset, a well-established benchmark in EEG-based vigilance analysis. By employing advanced pattern recognition technologies, including machine learning and deep neural networks, EEG signals are meticulously analyzed to discern patterns indicative of fatigue. This methodology combines feature extraction with a classification framework to improve the accuracy of fatigue detection. The proposed NLMDA-Net reached an impressive accuracy of 83.71% in detecting fatigue from EEG signals by incorporating two novel attention modules designed specifically for EEG signals, the channel and depth attention modules. NLMDA-Net effectively integrate features from multiple dimensions, resulting in improved classification performance. This success stems from integrating temporal convolutions and attention mechanisms, which effectively interpret EEG data. Designed to capture both temporal and spatial characteristics of EEG signals, deep learning classifiers have proven superior to traditional methods. The results of this study reveal a substantial enhancement in detection rates over existing models, highlighting the efficacy of the proposed approach for practical applications. The implications of this research are profound, extending beyond academic realms to inform the development of more sophisticated driver assistance systems. Incorporating this fatigue detection algorithm into these systems could significantly reduce fatigue-related incidents on the road, thus fostering safer driving conditions. This paper provides an exhaustive analysis of the dataset, methods employed, results obtained, and the potential real-world applications of the findings, aiming to contribute significantly to advancements in automotive safety. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

Disentangling Prosody Representations With Unsupervised Speech Reconstruction

引用

IEEE/ACM Transactions on Audio Speech and Language Processing 2024年 32卷 39-54页

作者： Qu, Leyuan Li, Taihao Weber, Cornelius Pekarek-Rosin, Theresa Ren, Fuji Wermter, Stefan Institute of Artificial Intelligence Zhejiang Lab Hangzhou311121 China Department of Informatics University of Hamburg Hamburg20148 Germany School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

Human speech can be characterized by different components, including semantic content, speaker identity and prosodic information. Significant progress has been made in disentangling representations for semantic content and speaker identity in speech recognition and speaker verification tasks respectively. However, it is still an open challenging question to extract prosodic information because of the intrinsic association of different attributes, such as timbre and rhythm, and because of the need for supervised training schemes to achieve robust speech recognition. The aim of this article is to address the disentanglement of emotional prosody based on unsupervised reconstruction. Specifically, we identify, design, implement and integrate three crucial components in our proposed model Prosody2Vec: (1) a unit encoder that transforms speech signals into discrete units for semantic content, (2) a pretrained speaker verification model to generate speaker identity embeddings, and (3) a trainable prosody encoder to learn prosody representations. We first pretrain Prosody2Vec on unlabelled emotional speech corpora, then fine-tune the model on specific datasets to perform Speech Emotion Recognition (SER) and Emotional Voice Conversion (EVC) tasks. Both objective and subjective evaluations on the EVC task suggest that Prosody2Vec effectively captures general prosodic features that can be smoothly transferred to other emotional speech. In addition, our SER experiments on the IEMOCAP dataset reveal that the prosody features learned by Prosody2Vec are complementary and beneficial for the performance of widely used speech pretraining models and surpass the state-of-the-art methods when combining Prosody2Vec with HuBERT representations. Audio samples can be found on our demo website. © 2023 The Authors. This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 License.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Bad channel detection in EEG recordings

引用

Current Directions in Biomedical engineering 2022年第2期8卷 257-260页

作者： Komosar, Milana Fiedler, Patrique Haueisen, Jens Institute of Biomedical Engineering and Informatics Faculty of Computer Sciences and Automation Technische Universität Ilmenau Ilmenau Germany

Electroencephalography (EEG) is widely used in clinical applications and basic research. Dry EEG opened the application area to new fields like self-application during gaming and neurofeedback. While recording, the signals are always affected by artefacts. Manual detection of bad channels is the gold standard in both gel-based and dry EEG but is time-consuming. We propose a simple and robust method for automatic bad channel detection in EEG. Our method is based on the iterative calculation of standard deviations for each channel. Statistical measures of these standard deviations serve as indications for bad channel detection. We compare the new method to the results obtained from the manually identified bad channels for EEG recordings. We analysed EEG signals during resting state with eyes closed and datasets with head movement. The results showed an accuracy of 99.69 % for both gel-based and dry EEG for resting state EEG. The accuracy of our new method is 99.38 % for datasets with the head movement for both setups. There was no significant difference between the manual gold standard of bad channel identification and our iterative standard deviation method. Therefore, the proposed iterative standard deviation method can be used for bad channel detection in resting state and movement EEG recordings. © 2022 The Author(s), published by De Gruyter.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Bottleneck-Minimal Indexing for Generative Document Retrieval 41

Bottleneck-Minimal Indexing for Generative Document Retrieva...

引用

41st International Conference on Machine Learning, ICML 2024

作者： Du, Xin Xiu, Lixin Tanaka-Ishii, Kumiko Waseda Research Institute for Science and Engineering Waseda University Japan Department of Mathematical Informatics The University of Tokyo Japan Department of Computer Science and Engineering Waseda University Japan

We apply an information-theoretic perspective to reconsider generative document retrieval (GDR), in which a document x ∈ X is indexed by t ∈ T, and a neural autoregressive model is trained to map queries Q to T. GDR can be considered to involve information transmission from documents X to queries Q, with the requirement to transmit more bits via the indexes T. By applying Shannon's rate-distortion theory, the optimality of indexing can be analyzed in terms of the mutual information, and the design of the indexes T can then be regarded as a bottleneck in GDR. After reformulating GDR from this perspective, we empirically quantify the bottleneck underlying GDR. Finally, using the NQ320K and MARCO datasets, we evaluate our proposed bottleneck-minimal indexing method in comparison with various previous indexing methods, and we show that it outperforms those methods. Copyright 2024 by the author(s)

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Novel replaceable EEG electrode system

引用

Current Directions in Biomedical engineering 2022年第2期8卷 249-252页

作者： Warsito, Indhika Fauzhan Fiedler, Patrique Komosar, Milana Haueisen, Jens Institute of Biomedical Engineering and Informatics Faculty of Computer Science and Automation Technische Universität Ilmenau Ilmenau Germany

Due to the direct contact between electrode and scalp, dry EEG electrodes are exposed to increased mechanical wear compared to conventional gel-based electrodes. However, state-of-the-art commercial cap systems commonly use permanently fixated electrodes which can lead to downtime of the EEG cap during professional repair and replacement as well as reduced overall lifetime. An easily replaceable EEG electrode would furthermore improve hygiene, especially for newborn and infant applications. We propose a novel replaceable electrode system, consisting of an electrode holder, a snap top, a contact ring fixated inside the electrode holder, and a replaceable electrode. The production process consists of 3D printing, silicone molding, resin casting, and electroless plating. The replaceable electrode system is integrated into a multichannel EEG cap system. A verification study is conducted with 30 volunteers. The operators experienced that the new electrode holder eases adjustment of the electrode to have proper contact with the scalp. During the study, defective electrodes can be replaced without a soldering process. Furthermore, all electrodes stayed in the holder and did not fall off the cap for the whole session. In conclusion, the novel replaceable electrode system is suitable for EEG measurements. © 2022 The Author(s), published by De Gruyter.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

EEG emotion recognition framework based on invariant wavelet scattering convolution network

引用

Journal of Ambient Intelligence and Humanized Computing 2024年第4期15卷 2181-2199页

作者： Elrefaiy, Ahmed Tawfik, Nahed Zayed, Nourhan Elhenawy, Ibrahim Department of Computer Science Faculty of Computers and Informatics Zagazig University Zagazig44519 Egypt Computers and Systems Department Electronics Research Institute Cairo Egypt Mechanical Engineering Department The British University in Egypt Cairo Egypt

EEG signals for real-time emotion identification are crucial for affective computing and human-computer interaction. The current emotion recognition models, which rely on a small number of emotion classes and stimuli like music and images in controlled lab conditions, have poor ecological validity. Furthermore, identifying relevant EEG signal features is crucial for efficient emotion identification. According to the complexity, non-stationarity, and variation nature of EEG signals, which make it challenging to identify relevant features to categorize and identify emotions, a novel approach for feature extraction and classification concerning EEG signals is suggested based on invariant wavelet scattering transform (WST) and support vector machine algorithm (SVM). The WST is a new time-frequency domain equivalent to a deep convolutional network. It produces scattering feature matrix representations that are stable against time-warping deformations, noise-resistant, and time-shift invariant existing in EEG signals. So, small, difficult-to-measure variations in the amplitude and duration of EEG signals can be captured. As a result, it addresses the limitations of the previous feature extraction approaches, which are unstable and sensitive to time-shift variations. In this paper, the zero, first, and second order features from DEAP datasets are obtained by performing the WST with two deep layers. Then, the PCA method is used for dimensionality reduction. Finally, the extracted features are fed as inputs for different classifiers. In the classification step, the SVM classifier is utilized with different classification algorithms such as k-nearest neighbours (KNN), random forest (RF), and AdaBoost classifier. This research employs a principal component analysis (PCA) approach to reduce the high dimensionality of scattering characteristics and increase the computational efficiency of our classifiers. The proposed method is performed across four different emotional classific

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

引用

3rd IEEE International Conference on Software engineering and Artificial Intelligence, SEAI 2023

作者： Senthilvelan, Prasanth Li, Jialong Tei, Kenji Waseda University Department of Computer Science and Communication Engineering Tokyo Japan National Institute of Informatics Tokyo Japan

ISBN: (纸本)9798350337952

In this paper, we present an efficient design of a shield called Parameterized Shield which allows for easy modification of its requirement parameters in response to the changes in the environment instead of manually making many shields during the development time and changing the whole shield during runtime. We propose to generate one proper shield that has many requirement parameters where even when there is any complex situation, there is not any need for extra effort from engineers to develop additional requirements and prepare the shield but only the parameters need to be changed when there is a change in the environment which avoids choosing a whole new shield every time an environment change occurs during runtime. And similarity-based adaptation will be used to choose the right parameters for the shield according to the environment with the help of the MAPE-K loop framework and reinforcement learning and to give the appropriate policy for the agent to act according to that environment. We will demonstrate using a cleaning robot as an example. © 2023 IEEE.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Friends, Not Foes: Enhancing Attack Surface Metrics of Web Applications with Large Language Models 17

Friends, Not Foes: Enhancing Attack Surface Metrics of Web A...

引用

17th International Conference on Information Security and Cryptology, ISCTurkiye 2024

作者： Tortumlu, Ahmet Bicakci, Kemal Department of Defence Technologies Istanbul Technical University Istanbul Turkey Informatics Institute and Department of Computer Engineering Istanbul Technical University Istanbul Turkey

ISBN: (纸本)9798331533649

The attack surface refers to all potential points of entry in a system that an attacker could exploit. In this work, we present an advanced metric for calculating the attack surface of web applications by leveraging the capabilities of large language models (LLMs) and introducing new features based on recent evaluations of the OWASP Top 10 security risks. Incorporating 28 parameters across 9 main categories and drawing on past studies to address previously identified limitations, this metric provides a comprehensive assessment of the attack surface. The Euclidean norm of the metric allows for quantitative comparisons, enabling precise evaluation and monitoring of security risks. Additionally, we develop a tool to facilitate the calculation of attack surface parameters, with the source code available as open source. The tool features an interface that visualizes the attack surface vector, presenting the metrics of web applications in graphical form. Among its many uses, web security analysts can employ our metric and tool to monitor changes in an application's attack surface across different versions. We also provide recommendations for further improving attack surface metric calculations using LLMs. © 2024 IEEE.

关键词： Open systems

来源：评论

学校读者我要写书评

暂无评论

Learning Analytics Support in Higher-Education: Towards a Multi-Level Shared Learning Analytics Framework 16

Learning Analytics Support in Higher-Education: Towards a Mu...

引用

16th International Conference on computer Supported Education, CSEDU 2024

作者： Vierhauser, Michael Groher, Iris Sauerwein, Clemens Antensteiner, Tobias Hatmanstorfer, Sebastian University of Innsbruck Department of Computer Science Innsbruck Austria Johannes Kepler University Linz Institute of Business Informatics Software Engineering Linz Austria

ISBN: (纸本)9789897586972

Assurance of Learning and Competency-Based Education are increasingly important in higher education, not only for accreditation or transfer of credit points. Learning Analytics is crucial for making educational goals measurable and actionable, which is beneficial for program managers, course instructors, and students. While universities typically have an established tool landscape where relevant data is managed, information is typically scattered across various systems with different responsibilities and often only limited capabilities for sharing data. This diversity, however, significantly hampers the ability to analyze data, both on the course and curriculum level. To address these shortcomings and to provide program managers, course instructions, and students with valuable insights, we devised an initial concept for a Multi-Level Shared Learning Analytics Framework to provide consistent definition and measurement of learning objectives, as well as tailored information, visualization, and analysis for different stakeholders. In this paper, we present the results of initial interviews with stakeholders, devising core features. In addition, we assess potential risks and concerns that may arise from the implementation of such a framework and data analytics system. As a result, we identified six essential features and six main risks to guide further requirements elicitation and development of our proposed framework. Copyright © 2024 by SCITEPRESS – Science and Technology Publications, Lda.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

A Survey on Privacy-Enhancing Techniques in the Era of Artificial Intelligence 4th

A Survey on Privacy-Enhancing Techniques in the Era of A...

引用

4th International Conference on Novel and Intelligent Digital Systems, NiDS 2024

作者： Dritsas, Elias Trigka, Maria Mylonas, Phivos Athena Research and Innovation Center Industrial Systems Institute Patras Greece Department of Informatics and Computer Engineering University of West Attica Athens Greece

ISBN: (纸本)9783031733437

In the era of Big Data and Artificial Intelligence (AI), the unprecedented scale and complexity of data collection, processing, and analysis pose significant privacy challenges. This paper presents a survey, providing a comprehensive and focused overview of privacy-enhancing technologies (PETs) designed to mitigate these challenges and ensure the protection of sensitive information. We explore cryptographic and non-cryptographic techniques including differential privacy (DP), homomorphic encryption (HE), secure multi-party computation (SMPC), and federated learning (FL). Each of these techniques is examined in terms of its basic principles and advantages. Also, some key challenges and ethical issues for implementing PETs are briefly discussed. Finally, we conclude the survey by denoting our future research directions in the field. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Federated learning

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：