检索结果-内蒙古大学图书馆

On the robustness of EEG tensor completion methods

Science China(Technological Sciences) 2021年第9期64卷 1828-1842页

作者： DUAN Feng JIA Hao ZHANG ZhiWen FENG Fan TAN Ying DAI YangYang CICHOCKI Andrzej YANG ZhengLu CAIAFA Cesar F. SUN Zhe SOLE-CASALS Jordi College of Artificial Intelligence Nankai UniversityTianjin 300350China Skolkowo Institute of Science and Technology Moscow 121205Russia College of Computer Science Hangzhou Dianzi UniversityHangzhou 310018China Department of Informatics Nicolaus Copernicus UniversityTorun 87-100Poland Systems Research Institute Polish Academy of SciencesWarsaw 01-447Poland College of Computer Science Nankai UniversityTianjin 300350China Instituto Argentino de Radioastronom´ıa IAR-CCT La Plata CONICET/CIC-PBA/UNLPVilla Elisa 1894Argentina Computational Engineering Applications Unit Head Office for Information Systems and CybersecurityRIKENWako-Shi 351-0106Japan Department of Psychiatry University of CambridgeCambridge CB28AHUK Data and Signal Processing Research Group University of Vic-Central University of CataloniaCatalonia 08500Spain

During the acquisition of electroencephalographic(EEG) signals, data may be missing or corrupted by noise and artifacts. To reconstruct the incomplete data, EEG signals are firstly converted into a three-order tensor(multi-dimensional data) of shape time × channel × trial. Then, the missing data can be efficiently recovered by applying a tensor completion method(TCM).However, there is not a unique way to organize channels and trials in a tensor, and different numbers of channels are available depending on the EEG setting used, which may affect the quality of the tensor completion results. The main goal of this paper is to evaluate the robustness of EEG completion methods with several designed parameters such as the ordering of channels and trials, the number of channels, and the amount of missing data. In this work, the results of completing missing data by several TCMs were compared. To emulate different scenarios of missing data, three different patterns of missing data were ***, the amount of missing data on completion effects was analyzed, including the time lengths of missing data and the number of channels or trials affected by missing data. Secondly, the numerical stability of the completion methods was analyzed by shuffling the indices along channels or trials in the EEG data tensor. Finally, the way that the number of electrodes of EEG tensors influences completion effects was assessed by changing the number of channels. Among all the applied TCMs, the simultaneous tensor decomposition and completion(STDC) method achieves the best performance in providing stable results when the amount of missing data or the electrode number of EEG tensors is changed. In other words, STDC proves to be an excellent choice of TCM, since permutations of trials or channels have almost no influence on the complete results. The STDC method can efficiently complete the missing EEG signals. The designed simulations can be regarded as a procedure to validate whether or

关键词： electroencephalogram corrupted data missing data tensor completion tensor decomposition

来源：评论

学校读者我要写书评

暂无评论

Application for Airport Tenant Selection Using Weighted Product-based Decision Support system

Application for Airport Tenant Selection Using Weighted Prod...

引用

Electrical and Information Technology (IEIT), International Conference on

作者： Arwin Datumaya Wahyudi Sumari Muhamad Andika Saputra Astika Ayuningtyas Catur Sudarmadi Aerospace Intelligent System and Data Engineering Research Group Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Cognitive Artificial Intelligence Research Group Politeknik Negeri Malang Malang Indonesia Informatics Study Program Faculty of Industrial Technology Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia Aerospace Health Informatics Research Group Faculty of Industrial Technology Adisutjipto Institute of Aerospace Technology Yogyakarta Indonesia

This research aims to develop an application for selecting the best new tenant at PT Angkasa Pura II Sultan Thaha Jambi Airport Branch by utilizing Weighted Product (WP) method as the decision support system. Our approach is descriptive research with data analysis technique using four prospective tenants coded A_1 to A_4. The data was collected through observation, interviews, documentation, and literature study. The steps for selecting the best new tenant using the WP method include determining the criteria, sorting the suitability of alternatives and criteria, determining the weight of each criterion and its normalization, calculating the score, S value as an alternative preference, and calculating the ranking, V value as the final alternative preference. Based on the final calculation results, the new tenant coded A_4 is the best alternative based on the data collected from the Financial Management (FHFM) Unit and the Commercial Unit, with a value of V_4 is 0.294.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Behaviour Analysis of News Consumption in Turkish Media

arXiv

引用

arXiv 2022年

作者： Makaroğlu, Didem Cakir, Altan Töreyin, Behçet Uğur Demirören Teknoloji A.S. İstanbul Turkey Signal Processing for Computational Intelligence Group Informatics Institute Istanbul Technical University Istanbul Turkey Physics Engineering Faculty of Science and Letters Istanbul Technical University Istanbul Turkey Istanbul Technical University Artificial Intelligence Data Science Research and Application Center Istanbul Turkey

Clickstream data, which come with a massive volume generated by human activities on websites, have become a prominent feature for identifying readers’ characteristics by newsrooms after the digitization of news outlets. It is essential to have elastic architectures to process the streaming data, particularly for unprecedented traffic, enabling conducting more comprehensive analyses, such as recommending mostly related articles to readers. Although the nature of clickstream data has a similar logic within websites, it has inherent limitations to recognize human behaviours when looking from a broad perspective, which brings the need to limit the problem in niche areas. This study investigates the anonymized readers’ click activities on the organizations’ websites to identify news consumption patterns following referrals from Twitter, who incidentally reach but propensity is mainly routed news content. The investigation is widened to a broad perspective by linking the log data with news content to enrich the insights rather than sticking into the web journey. Methodologies for ensemble cluster analysis with mixed-type embedding strategies are applied and compared to find similar reader groups and interests independent of time. Various internal validation perspectives are used to determine the optimality of the quality of clusters, where the Calinski Harabasz Index (CHI) is found to give a generalizable result. Our findings demonstrate that clustering a mixed-type dataset approaches the optimal internal validation scores, which we define to discriminate the clusters and algorithms considering applied strategies, when embedded by Uniform Manifold Approximation and Projection (UMAP) and using a consensus function as a key to access the most applicable hyper parameter configurations in the given ensemble rather than using consensus function results directly. Evaluation of the resulting clusters highlights specific clusters repeatedly present in the separated monthly sample

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Learning 22

Depth-Aware Multi-Modal Fusion for Generalized Zero-Shot Lea...

引用

22nd IEEE International Conference on Industrial Informatics, INDIN 2024

作者： Cao, Weipeng Yao, Xuyang Xu, Zhiwu Pan, Yinghui Sun, Yixuan Li, Dachuan Qiu, Bohua Wei, Muheng Shenzhen China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen China College of Computer Science and Software Engineering Shenzhen University Shenzhen China Stony Brook University New York United States Research Institute of Trustworthy Autonomous Systems Southern University of Science and Technology Shenzhen China Department of Computer Science and Engineering Southern University of Science and Technology Shenzhen China ZhenDui Industry Artificial Intelligence Co. Ltd Shenzhen China Department of Automation Shanghai Jiao Tong University Shanghai China Key Laboratory of System Control and Information Processing Ministry of Education of China Shanghai China

ISBN: (纸本)9798331527471

Realizing Generalized Zero-Shot Learning (GZSL) based on large models is emerging as a prevailing trend. However, most existing methods merely regard large models as black boxes, solely leveraging the features output by the final layer while disregarding potential performance enhancements from other layers. Indeed, numerous researchers have visually depicted variations in the features learned across different layers of neural networks. Motivated by this observation, we propose a Vision Transformer (ViT)-based GZSL method named Depth-Aware Multi-Modal ViT (DAM2ViT), which exploits multi-level features of ViT. DAM2ViT incorporates a multi-modal interaction block to align semantic information of categories across multiple layers, thereby augmenting the model’s capacity to learn associations between visual and semantic spaces. Extensive experiments conducted on three benchmark datasets (i.e., CUB, SUN, AWA2) have showcased that DAM2ViT achieves competitive results compared to state-of-the-art methods. © 2024 IEEE.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

Neural gen feature selection for supervised learning classifier

引用

research Journal of Applied Sciences, Engineering and Technology 2014年第15期7卷 3181-3187页

作者： Abdulameer, Mohammed Hasan Sheikh Abdullah, Siti Norul Huda Othman, Zulaiha Ali Pattern Recognition Research Group Centre for Artificial Intelligence Technology Faculty of Information Science and Technology 43600 Bandar Baru Bangi Malaysia Data Mining and Optimization Group Faculty of Information System and Technology Universiti Kebangsaan Malaysia 43600 Bandar Baru Bangi Malaysia

Face recognition has recently received significant attention, especially during the past few years. Many face recognition techniques were developed such as PSO-SVM and LDA-SVM However, inefficient features in the face recognition may lead to inadequate in the recognition results. Hence, a new face recognition system based on Genetic Algorithm and FFBNN technique is proposed. Our proposed face recognition system initially performs the feature extraction and these optimal features are promoted to the recognition process. In the feature extraction, the optimal features are extracted from the face image database by Genetic Algorithm (GA) with FFBNN and the computed optimal features are given to the FFBNN technique to carry out the training and testing process. The optimal features from the feature database are fed to the FFBNN for accomplishing the training process. The well trained FFBNN with the optimal features provide the recognition result. The optimal features in FFBNN by GA efficiently perform the face recognition process. The human face dataset called YALE is utilized to analyze the performance of our proposed GA-FFNN technique and also this GA-FFBNN is compared with standard SVM and PSO-SVM techniques. © Maxwell Scientific Organization, 2014.

关键词： Face recognition FFBNN GA PCA SVM

来源：评论

学校读者我要写书评

暂无评论

Complexity-based link assignment for NASA’s deep space network for follow-the-sun operations 15th

Complexity-based link assignment for NASA’s deep space netw...

引用

15th International Conference on Space Operations, SpaceOps 2018

作者： Lad, Jigna Johnston, Mark D. Tran, Daniel Brown, David Roffo, Kenneth Lee, Carlyn Jet Propulsion Laboratory Data Services Group Planning and Execution Systems Section California Institute of Technology 4800 Oak Grove Road PasadenaCA91109 United States Jet Propulsion Laboratory Artificial Intelligence Group Planning and Execution System Section California Institute of Technology 4800 Oak Grove Road PasadenaCA91109 United States Jet Propulsion Laboratory California Institute of Technology Modeling & Verification Group Planning & Execution Systems Section 4800 Oak Grove Road PasadenaCA91109 United States Jet Propulsion Laboratory California Institute of Technology Telecom Architectures Group Communication Arch. and Research Section 4800 Oak Grove Road PasadenaCA91109 United States

ISBN: (数字)9781624105623

ISBN: (纸本)9781624105623

NASA’s Deep Space Network (DSN) recently underwent a paradigm shift in its operations approach called Follow the Sun Operations (FtSO) in an effort to increase efficiency for forthcoming expansion of the network. This change requires each Deep Space Communications Complex (DSCC) to remotely control the other two complexes during their local day shift, in contrast to locally controlling only their own antennas 24x7. Remote operations increases the workload of each complex during their day shift, specifically that of the Link Control Operators (LCOs), and presents a new challenge for planning and managing the distribution of responsibility for each link. A new DSN software assembly, the Link Complexity and Maintenance (LCM) software, was developed to support workload management for LCOs, as well as for planning site-local maintenance activities. The LCM deployment was a vital part of the transition to FtSO in November 2017. This paper discusses the architecture of LCM, its feature set, and lessons learned during its development and rollout. © 2018, American Institute of Aeronautics and Astronautics Inc, AIAA. All rights reserved.

关键词： NASA

来源：评论

学校读者我要写书评

暂无评论

AEGIS DISPLAY system MAP data-BASE

引用

NAVAL ENGINEERS JOURNAL 1990年第3期102卷 138-145页

作者： PANTAZOPOULOS, MV BARKER, RG SLIMMER, RL Michael V. Pantazopoulos:has been a physicist at the Naval Surface Warfare Center in Dahlgren Va. since August 1985. He received his B.S. and M.S. in physics from Emory University. He has been a member of the Aegis Display System Group in the Aegis Combat Direction Systems Branch since 1985. This group maintains the Aegis coastline map data base and most of his work has been in the developing analyzing and testing of the digital map data bases. R. Gordon Barker:has been a mathematician at the Naval Surface Warfare Center in Dahlgren Va. since 1964. He received a B.S. from the University of Virginia and did his graduate study at Princeton University. He has been a member of the Aegis Display System Group since 1982. During the development of the Mark 1 Aegis Display System Map Data Base Mr. Barker wrote the program to perform the “data thinning” of the map data. In order to support the system upgrades in progress Mr. Barker developed a tool to polygonize the map data. Rebecca L. Slimmer:has been a computer scientist at the Naval Surface Warfare Center in Dahlgren Va. since 1984. She received her B.S. from Sam Houston State University. She has been a member of the Aegis Display System Group since 1984. Her work has included maintaining and upgrading the Aegis Display System Map Data Base Generation Computer Program participation in Defense Mapping Agency data base evaluations and development of a map data base for the Naval Intelligence Processing System in a joint effort with M. Pantazopoulos. She currently serves as the point of contact for the Aegis Display System Map Data Base.

The Aegis Combat system is an advanced integrated combat system engineered specifically for Ticonderoga class cruisers. An essential component of this system is the Aegis Display system (ADS), which displays real-time ownship and fleet tactical information. Integral to the ADS is the display of coastline map data to provide geographic perspective to the tactical picture. The purpose of this paper is to describe the design and implementation of the map data base into the ADS. The original ADS equipment limited the number of coastline points which could be displayed at one time, thus leading to the development of several data thinning techniques. The requirements for real-time maps also motivated the introduction of some novel features into the data base architecture. The data base was required to support nine range scales and yet maintain the same approximate density of points throughout the entire world. To accomplish this, the data were partitioned into “windows,” with a uniform size based on distance rather than an angular measurement. This resulted in windows approximately the same size in area, but with a longitudinal width which increases as polar latitudes are approached. The number of data points was then reduced by applying several thinning algorithms so that the desired point densities were reached. The windows were organized into four separate data subbases, each with a different window size but a similar point density. This scheme allows coverage of an entire display area with at most four windows at any range scale. The display speed was optimized by exploiting the Aegis Combat system's use of orthographic projection from the earth's surface to the display plane. This type of projection permits integer arithmetic in the transformation projection equations when the data points are stored as X,Y,Z earth-centered coordinates instead of as latitude and longitude. This results in substantially faster map processing and display times, thereby allowing the ADS

关键词： Display Devices

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Spatio-Temporal State Estimation for Fine-grained Adaptive Anomaly Diagnosis of Industrial Cyber-physical systems

arXiv

引用

arXiv 2024年

作者： Sun, Haili Huang, Yan Han, Lansheng Fu, Cai Zhou, Chunjie Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China National Key Laboratory of Science and Technology on Multispectral Information Processing School of Artificial Intelligence and Automation Huazhong University of Science and Technology Wuhan430074 China

Accurate detection and diagnosis of abnormal behaviors such as network attacks from multivariate time series (MTS) are crucial for ensuring the stable and effective operation of industrial cyber-physical systems (CPS). However, existing researches pay little attention to the logical dependencies among system working states, and have difficulties in explaining the evolution mechanisms of abnormal signals. To reveal the spatio-temporal association relationships and evolution mechanisms of the working states of industrial CPS, this paper proposes a fine-grained adaptive anomaly diagnosis method (i.e. MAD-Transformer) to identify and diagnose anomalies in MTS. MAD-Transformer first constructs a temporal state matrix to characterize and estimate the change patterns of the system states in the temporal dimension. Then, to better locate the anomalies, a spatial state matrix is also constructed to capture the inter-sensor state correlation relationships within the system. Subsequently, based on these two types of state matrices, a three-branch structure of series-temporal-spatial attention module is designed to simultaneously capture the series, temporal, and space dependencies among MTS. Afterwards, three associated alignment loss functions and a reconstruction loss are constructed to jointly optimize the model. Finally, anomalies are determined and diagnosed by comparing the residual matrices with the original matrices. We conducted comparative experiments on five publicly datasets spanning three application domains (service monitoring, spatial and earth exploration, and water treatment), along with a petroleum refining simulation dataset collected by ourselves. The results demonstrate that MAD-Transformer can adaptively detect fine-grained anomalies with short duration, and outperforms the state-of-the-art baselines in terms of noise robustness and localization performance. © 2024, CC BY.

关键词： Cyber Physical system

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Spatio-Temporal State Estimation for Fine-Grained Adaptive Anomaly Diagnosis of Industrial Cyber-Physical systems

SSRN

引用

SSRN 2024年

Accurate detection and diagnosis of abnormal behaviors such as network attacks from multivariate time series (MTS) are crucial for ensuring the stable and effective operation of industrial cyber-physical systems (CPS). However, existing researches pay little attention to the logical dependencies among system working states, and have difficulties in explaining the evolution mechanisms of abnormal signals. To reveal the spatio-temporal association relationships and evolution mechanisms of the working states of industrial CPS, this paper proposes a fine-grained adaptive anomaly diagnosis method (i.e. MAD-Transformer) to identify and assess anomalies in MTS. A temporal and spatial state matrix are constructed to characterize state changes and inter-sensor correlations for precise anomaly localization. Subsequently, a three-branch structure of series-temporal-spatial attention module is designed to simultaneously capture the series, temporal, and spatial dependencies among MTS. Three associated alignment loss and a reconstruction loss are constructed to jointly optimize the model. Finally, anomalies are determined and diagnosed by comparing the residual matrices with the original matrices. Comparative experiments on five publicly datasets along with a petroleum refining simulation dataset demonstrate that MAD-Transformer can adaptively detect fine-grained anomalies with short duration, and outperforms the state-of-the-art baselines in terms of noise robustness and localization performance. © 2024, The Authors. All rights reserved.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

research and application of artificial intelligence based webshell detection model: A literature review

arXiv

引用

arXiv 2024年

作者： Ma, Mingrui Han, Lansheng Zhou, Chunjie Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan430074 China The Key Laboratory of Ministry of Education for Image Processing and Intelligent Control School of Artificial Intelligence and Automation Huazhong University of Science and Technology Hubei Wuhan430074 China

Webshell, as the"culprit" behind numerous network attacks, is one of the research hotspots in the field of cybersecurity. However, the complexity, stealthiness, and confusing nature of webshells pose significant challenges to the corresponding detection schemes. With the rise of Artificial intelligence (AI) technology, researchers have started to apply different intelligent algorithms and neural network architectures to the task of webshell detection. However, the related research still lacks a systematic and standardized methodological process, which is confusing and redundant. Therefore, following the development timeline, we carefully summarize the progress of relevant research in this field, dividing it into three stages: Start Stage, Initial Development Stage, and In-depth Development Stage. We further elaborate on the main characteristics and core algorithms of each stage. In addition, we analyze the pain points and challenges that still exist in this field and predict the future development trend of this field from our point of view. To the best of our knowledge, this is the first review that details the research related to AI-based webshell detection. It is also hoped that this paper can provide detailed technical information for more researchers interested in AI-based webshell detection tasks. Copyright © 2024, The Authors. All rights reserved.

关键词： Machine 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：