检索结果-内蒙古大学图书馆

Information Technology (ACIT)

作者： Ala’ Alyabrodi Shrouq Al-Daja MohammadNoor Injadat Abdallah Moubayed Ali Elrashidi Cyber Security Department Zarqa University Zarqa Jordan Data Science & AI Department Zarqa University Zarqa Jordan Computer Engineering Department and Interdisciplinary Research Center for Intelligent Secure Systems King Fahd University of Petroleum & Minerals Dhahran Saudi Arabia Department of Electrical Engineering University of Business and Technology Jeddah Saudi Arabia

ISBN: (数字)9798331540012

ISBN: (纸本)9798331540029

Machine learning-based improvements in anomaly detection, visualization, and segmentation are made possible by the growing digitization of medical imaging, which reduces the workload for medical specialists. Nevertheless, trustworthy labeled data is necessary for supervised machine learning and is sometimes expensive, time-consuming, or impossible to get. Consequently, techniques that need either little labeling (unsupervised methods) or partial labeling (semi-supervised methods) have been used increasingly been used. One approach that can be used to tackle medical imaging tasks like segmentation and classification is anomaly detection, which makes use of both unsupervised and semi-supervised methods. This study investigates the anomaly detection capabilities of deep learning and machine learning models trained on chest CT scans. To adopt this approach, firstly, by evaluating several feature extraction techniques (Principal Component Analysis (PCA), Autoencoder, and variance threshold), PCA achieves the best results on the selected dataset. After that, different machine learning and deep learning models (Isolation Forest, K-means, feed-forward neural networks, and convolutional neural networks) are assessed to detect anomalies using PCA for dimensionality reduction. The experiments show that the NN-Feedforward model with PCA outperformed the other models, also attains remarkably low false alarm rate, demonstrating its effectiveness in reducing false positives and precisely detecting anomalies.

关键词： Deep learning Image segmentation Forestry Feature extraction Feedforward neural networks Labeling Information technology Anomaly detection Principal component analysis Biomedical imaging

来源：评论

学校读者我要写书评

暂无评论

Estimation of Wrist Chattering Angle Based on Disturbance Observer 16

Estimation of Wrist Chattering Angle Based on Disturbance Ob...

引用

16th International Congress on Image and Signal Processing, BioMedical engineering and Informatics, CISP-BMEI 2023

作者： Zhang, Xinyu Sun, Zhenyu Shu, Bairui Yokoi, Hiroshi Yong, Xu Li, Guanglin Jing, Xiaobei The Siat Branch Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518055 China The University of Electro-Communications Joint Doctoral Program for Sustainability Research Tokyo182-8585 Japan The University of Electro-Communications Department of Mechanical Engineering and Intelligent Systems Tokyo182-8585 Japan

ISBN: (纸本)9798350330755

Due to the physiological constraints and daily habits of hand movements, the wrist chattering effect (WCE) will inadvertently cause disturbance to the accuracy of fingers' pattern recognition, when healthy subjects or amputees undergoing mirror training control their fingers according to instructions. This paper proposes a method for estimating WCE angles using a disturbance observer. Based on the Denavit-Hartenberg (D-H) convention and inverse kinematics, the intervals of the WCE during finger flexion and extension are determined. The research objective is to eliminate disturbance terms containing redundant information referring to sliding mode anti-jittering methods, making subsequent machine learning models less susceptible to disturbances. © 2023 IEEE.

关键词： Inverse kinematics

来源：评论

学校读者我要写书评

暂无评论

DAFA: DISTANCE-AWARE FAIR ADVERSARIAL TRAINING

arXiv

引用

arXiv 2024年

作者： Lee, Hyungyu Lee, Saehyung Jang, Hyemi Park, Junsung Bae, Ho Yoon, Sungroh Electrical and Computer Engineering Seoul National University Korea Republic of Department of Cyber Security Ewha Womans University Korea Republic of Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of

The disparity in accuracy between classes in standard training is amplified during adversarial training, a phenomenon termed the robust fairness problem. Existing methodologies aimed to enhance robust fairness by sacrificing the model's performance on easier classes in order to improve its performance on harder ones. However, we observe that under adversarial attacks, the majority of the model's predictions for samples from the worst class are biased towards classes similar to the worst class, rather than towards the easy classes. Through theoretical and empirical analysis, we demonstrate that robust fairness deteriorates as the distance between classes decreases. Motivated by these insights, we introduce the Distance-Aware Fair Adversarial training (DAFA) methodology, which addresses robust fairness by taking into account the similarities between classes. Specifically, our method assigns distinct loss weights and adversarial margins to each class and adjusts them to encourage a trade-off in robustness among similar classes. Experimental results across various datasets demonstrate that our method not only maintains average robust accuracy but also significantly improves the worst robust accuracy, indicating a marked improvement in robust fairness compared to existing methods. Copyright © 2024, The Authors. All rights reserved.

关键词： Economic and social effects

来源：评论

学校读者我要写书评

暂无评论

Path Following of a Tractor-Trailer System via Dynamic Extension in Forward and Backward Motion

Path Following of a Tractor-Trailer System via Dynamic Exten...

引用

RSI/ISM International Conference on Robotics and Mechatronics (ICROM)

作者： Mohammad Olyai Khalil Alipour Bahram Tarvirdizadeh Majid Sorouri Mohammad Ghamari Department of Mechatronics Eng. Advanced Service Robots (ASR) Laboratory School of Intelligent Systems Engineering College of Interdisciplinary Science and Technology University of Tehran Tehran Iran Department of Electronic Engineering Maynooth University Maynooth Co. Kildare Ireland Department of Computer and Mechatronics Engineering Science and Research Branch Islamic Azad University Tehran Iran Electrical Engineering Department California Polytechnic State University San Luis Obispo CA USA

ISBN: (数字)9798331529734

ISBN: (纸本)9798331529741

Tractor-trailer wheeled robots (TTWRs) have gained significant attention across various industries and control studies due to their complex dynamics and non-minimum phase behavior, which pose substantial control challenges. This study investigates the control of a differentially-driven tractor to follow a specified path under pure rolling conditions in both forward and backward motion. Notably, it has been established that using static feedback linearization (SFL) leads to instability during backward motion. In contrast, this research uses dynamic feedback linearization (DFL), also known as dynamic extension, for controlling the tractor-trailer system in both directions for the first time. Our findings demonstrate that the internal dynamics of the system remain stable in both forward and backward motions, enabling successful adherence to the desired path.

关键词： Industries Mechatronics Service robots Dynamics Wheels Optimal control Reinforcement learning Agricultural machinery Feedback linearization Mobile robots

来源：评论

学校读者我要写书评

暂无评论

Gradient Alignment with Prototype Feature for Fully Test-time Adaptation

arXiv

引用

arXiv 2024年

作者： Shin, Juhyeon Lee, Jonghyun Lee, Saehyung Park, Minjun Lee, Dongjun Hwang, Uiwon Yoon, Sungroh Interdisciplinary Program in Artificial Intelligence Seoul National University Korea Republic of Department of Electrical and Computer Engineering Seoul National University Korea Republic of Division of Digital Healthcare Yonsei University Korea Republic of

In context of Test-time Adaptation(TTA), we propose a regularizer, dubbed Gradient Alignment with Prototype feature (GAP), which alleviates the inappropriate guidance from entropy minimization loss from misclassified pseudo label. We developed a gradient alignment loss to precisely manage the adaptation process, ensuring that changes made for some data don’t negatively impact the model’s performance on other data. We introduce a prototype feature of a class as a proxy measure of the negative impact. To make GAP regularizer feasible under the TTA constraints, where model can only access test data without labels, we tailored its formula in two ways: approximating prototype features with weight vectors of the classifier, calculating gradient without back-propagation. We demonstrate GAP significantly improves TTA methods across various datasets, which proves its versatility and effectiveness. Copyright © 2024, The Authors. All rights reserved.

关键词： Alignment

来源：评论

学校读者我要写书评

暂无评论

Digital Transformation of Identity: A Crisis Mechanism

Digital Transformation of Identity: A Crisis Mechanism

引用

2022 Portland International Conference on Management of engineering and Technology, PICMET 2022

作者： Barella, Jonathan Langford, Whitney M. Langford, Gary O. Burns, Daniel P. Portland State University Etm Department. Systems Engineering Program PortlandOR United States Institute of Neuroscience University of Oregon EugeneOR United States Home Port Solutions SavannahGA United States

ISBN: (数字)9781890843410

ISBN: (纸本)9781890843410

The inability to perform identity management in an organization results in extreme harm to information and operational security - both individual and organization are harmed. We apply a highly-structured ontological systems approach to explore the implications of identity as it is embedded and used in operational and support infrastructures. The symptoms of a deep-seated insufficiency of identity (access denial, long-waits for adjudication, lost files) have fostered a naïve appreciation for managing a person's individuality, distinguishable attributes, validity metrics, trustworthiness, privacy concerns, intentionality, character, and roles. A multidisciplinary definition of identity was developed and evaluated through a stimulus-response / response-stimulus (SR-RS) model. The model results suggest why interactions of one's identity within different contexts present the single, most reliable opportunity for managing identity within a mereological paradigm. Specifically, enacting mechanisms of assertion and ascertainment through processes and directives illustrates why both extensional and intensional logics are necessary for a proper mix of digital and analog mechanisms. Certain digital transformations within the SR-RS model clarify how identity interactions can be used to enable new security structures by applying intensional logic. Whereas complete reliance on extensional logic - user name, fingerprint, passwords, and tokens - results in a demonstrably less secure environment. Identity and trust are essential factors for communicating identity. © 2022 PICMET.

关键词： Network security

来源：评论

学校读者我要写书评

暂无评论

Multi-channel Convolutional Neural Network for Hate Speech Detection in Social Media 9th

Multi-channel Convolutional Neural Network for Hate Speech D...

引用

9th EAI International Conference on Advancement of Science and Technology, ICAST 2021

作者： Abebaw, Zeleke Rauber, Andreas Atnafu, Solomon IT Doctoral Program Addis Ababa University Addis Ababa Ethiopia Institute of Information Systems Engineering Technical University of Vienna Vienna Austria Department of Computer Science Addis Ababa University Addis Ababa Ethiopia

ISBN: (纸本)9783030937089

As online social media content continues to grow, so does the spread of hate speech. Hate speech has devastating consequences unless it is detected and monitored early. Recently, deep neural network-based hate speech detection models, particularly conventional single-channel Convolutional Neural Network (CNN), have achieved remarkable performance. However, the effectiveness of the models depends on the type of language they are trained on and the training data size. We argue that the effectiveness of the models could further be enhanced if we use multi-channel CNN models even for under-resourced languages that have limited training data size. This is because the single-channel CNN might fail to consider the potential effect of multiple channels to generate better features, which is not well investigated for hate speech detection. Therefore, in this work, we explore the use of multi-channel CNN to extract better features from different channels in an end-to-end manner on top of a word2vec embedding layer. Tested on a new small-scale Amharic hate speech dataset containing 2000 annotated social media comments, the experimental results show that the proposed multi-channel CNN model outperforms the single-channel CNN models but underperform from the baseline Support Vector Machine (SVM) with an average F-score of 81.3%, 78.2%, and 92.5% respectively. The finding of the study implies that the proposed MC-CNN model can be used as an alternative solution for hate speech detection using a deep learning approach when dataset scarcity is an issue. © 2022, ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Embeddings

来源：评论

学校读者我要写书评

暂无评论

Improving Out-of-Distribution Generalization in Graphs via Hierarchical Semantic Environments

Improving Out-of-Distribution Generalization in Graphs via H...

引用

Conference on Computer Vision and Pattern Recognition (CVPR)

作者： Yinhua Piao Sangseon Lee Yijingxiu Lu Sun Kim Department of Computer Science and Engineering Seoul National University Institute of Computer Technology Seoul National University AIGENDRUG Co. Ltd. Interdisciplinary Program in Artificial Intelligence Seoul National University

ISBN: (数字)9798350353006

ISBN: (纸本)9798350353013

Out-of-distribution (OOD) generalization in the graph domain is challenging due to complex distribution shifts and a lack of environmental contexts. Recent methods attempt to enhance graph OOD generalization by generating flat environments. However, such flat environments come with inherent limitations to capture more complex data distributions. Considering the DrugOOD dataset, which contains diverse training environments (e.g., scaffold, size, etc.), flat contexts cannot sufficiently address its high heterogeneity. Thus, a new challenge is posed to generate more seman-tically enriched environments to enhance graph invariant learning for handling distribution shifts. In this paper, we propose a novel approach to generate hierarchical seman-tic environments for each graph. Firstly, given an input graph, we explicitly extract variant subgraphs from the in-put graph to generate proxy predictions on local environ-ments. Then, stochastic attention mechanisms are employed to re-extract the subgraphs for regenerating global environ-ments in a hierarchical manner. In addition, we introduce a new learning objective that guides our model to learn the diversity of environments within the same hierarchy while maintaining consistency across different hierarchies. This approach enables our model to consider the relationships between environments and facilitates robust graph invariant learning. Extensive experiments on real-world graph data have demonstrated the effectiveness of our framework. Par-ticularly, in the challenging dataset DrugOOD, our method achieves up to 1.29% and 2.83% improvement over the best baselines on IC50 and EC50 prediction tasks, respectively.

关键词： Training Computer vision Attention mechanisms Computational modeling Semantics Stochastic processes Pattern recognition

来源：评论

学校读者我要写书评

暂无评论

Application of Acinetobacter indicus to promote cigarette smoke particulate matter phytoremediation: removal efficiency and plant–microbe interactions

引用

Environmental Science and Pollution Research 2024年第39期31卷 52352-52370页

作者： Nookongbut, Phitthaya Thiravetyan, Paitip Salsabila, Salma Widiana, Ana Krobthong, Sucheewin Yingchutrakul, Yodying Treesubsuntorn, Chairat School of Bioresources and Technology King Mongkut’s University of Technology Thonburi Bangkok10150 Thailand Department of Biology Faculty of Science and Technology State Islamic University Sunan Gunung Djati Bandung West Java Bandung City40614 Indonesia Interdisciplinary Graduate Program in Genetic Engineering Kasetsart University Bangkok10900 Thailand Proteomics Research Team National Omics Center NSTDA Khlong Luang Pathum Thani12120 Thailand Pilot Plant Development and Training Institute King Mongkut’s University of Technology Thonburi Bangkok10150 Thailand

Particulate matter (PM) is one of the most hazardous atmospheric pollutants. Several plant species show high potential to reduce air pollutants and are widely used as green belts to provide clean outdoor spaces for human well-being. However, high PM concentrations cause physiological changes and stress in plants. In this study, 11 species of Thai native perennial plants were exposed to PM generated from tobacco smoke. Wrightia religiosa (Teijsm. & Binn.) Benth. ex Kurz, Bauhinia purpurea DC. ex Walp. and Tectona grandis L.f. reduced PM effectively (which is in the typical range of 43.95 to 52.97%) compared to other plant species. In addition, the responses of perennial plants under PM stress at the proteomic level were also evaluated. Proteomic analysis of these three plant species showed that plants respond negatively to high PM concentrations, such as reducing several photosynthetic-related proteins and increasing plant stress response proteins. To improve PM phytoremediation efficiency and reduce plant stress from PM, perennial plant–microbe interactions were investigated. W. religiosa was inoculated with Acinetobacter indicus PS1, and high biosurfactant-producing strains clearly showed a higher PM removal efficiency than non-inoculated plants (9.48, 9.5 and 12.6% for PM1.0, PM2.5 and PM10, respectively). Inoculating W. religiosa with A. indicus PS1 maintained chlorophyll a and b concentrations. Moreover, the malondialdehyde (MDA) concentration of W. religiosa inoculated with A. indicus PS1 was lower than that of non-inoculated W. religiosa. The leaf wax content (µg/cm2) and biosurfactant (µg/cm2) of W. religiosa inoculated with A. indicus PS1 were also higher than those of non-inoculated W. religiosa. This study clearly showed that inoculating plants with A. indicus PS1 can help plants remediate PM and improve their PM stress response. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Air pollution

来源：评论

学校读者我要写书评

暂无评论

Virtual Wearable Sensor Data Generation with Generative Adversarial Networks

Virtual Wearable Sensor Data Generation with Generative Adve...

引用

Simulation Winter Conference

作者： Yining Huang Hong Wan Xi Chen Operations Research Graduate Program North Carolina State University Raleigh NC USA Department of Industrial and Systems Engineering North Carolina State University Raleigh NC USA Grado Department of Industrial and Systems Engineering Virginia Tech Blacksburg VA USA

This study delves into the utilization of Generative Adversarial Networks (GANs) for generating subject-specific time series sensor data, offeringaninnovativealternativetotraditionalmetamodel-basedsimulations. We undertake an in-depth analysis of DoppelGANger, a prominent GAN variant for time series data and metadata generation, evaluating its efficiency and efficacy. The sensor data for this investigation was sourced from the National Health and Nutrition Examination Survey, which served as the foundational training set. We scrutinized the synthesized sensor data corresponding to various physical attributes, focusing on the temporal and multi-dimensional statistical properties. Our empirical findings underscore the potential of GANs to adeptly capture the time-dependent correlations and the intricate statistical characteristics inherent in multi-dimensional data. This insight into GANs’ capabilities is a crucial step towards more sophisticated synthetic data generation, with significant implications for future applications in wearable technology and personalized health monitoring systems.

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：