检索结果-内蒙古大学图书馆

autoencoder-Based Feature Extraction for Identifying Hate Speech Spreaders in Social Media

IEEE TRANSACTIONS ON COMPUTATIONAL SOCIAL SYSTEMS 2024年第4期11卷 4819-4827页

作者： Kumar, Gunjan Singh, Jyoti Prakash Singh, Amit Kumar Natl Inst Technol Patna Dept Comp Sci & Engn Patna 800005 India

Hate speech on social media has become a big problem, making regular users very upset and giving victims depression and suicidal thoughts. Early identification of the user spreading this type of hate speech may be a better solution, allowing hate speech to be stopped at source. In this article, we attempt to identify these hate speech spreaders by finding a representation for each user. Each user's comments are aggregated and fed to an auto-encoder to train it. The encoder part of the auto-encoder is used to get an encoded vector for each user. The encoded vector is used with different machine learning (ML) classifiers to determine if a user is spreading hate speech. The proposed model was tested using the dataset released by PAN 2021 (https://***/***) hate speech spreader profiling competition in English and Spanish. The experimental results show that support vector machine (SVM) with encoded vectors as features outperforms existing models with an accuracy of 92% for both English and Spanish dataset. The proposed features extraction technique is found to be equally effective at identifying fake news spreaders on fake news datasets provided by PAN 2020 yielding accuracy values of 95% and 83% for English and Spanish, respectively.

关键词： autoencoder hate speech hate speech spreader long short-term memory (LSTM)

来源：评论

学校读者我要写书评

暂无评论

autoencoder-based nonlinear Bayesian locally weighted regression for soft sensor development

引用

ISA TRANSACTIONS 2020年 103卷 143-155页

作者： Liu, Kang Shao, Weiming Chen, Guoming China Univ Petr Ctr Offshore Engn & Safety Technol Qingdao 266580 Peoples R China China Univ Petr Coll New Energy Qingdao 266580 Peoples R China

The framework of locally weighted learning (LWL) has established itself as a popular tool for developing nonlinear soft sensors in process industries. For LWL-based soft sensors, the key factor for achieving high performance is to construct accurate localized models. To this end, in this paper a nonlinear local model training algorithm called nonlinear Bayesian weighted regression (NBWR) is proposed. In the NBWR, the nonlinear features of process data are first extracted by the autoencoder;then, given a query sample a local dataset is selected on the feature space and a fully Bayesian regression model with differentiated sample weights is developed. The benefits of this approach, which include better consistency of correlation, stronger abilities to deal with process nonlinearities and uncertainties, overfitting and numerical issues, lead to superior performance. The NBWR is used for developing a soft sensor under the LWL framework, and a real-world industrial process is used to evaluate the performance of the NBWR-based soft sensor. The experimental results demonstrate that the proposed method outperforms several benchmarking soft sensing approaches. (C) 2020 ISA. Published by Elsevier Ltd. All rights reserved.

关键词： Soft sensor Locally weighted learning Bayesian weighted regression autoencoder Nonlinear feature extraction

来源：评论

学校读者我要写书评

暂无评论

autoencoder Neural Network Based Intelligent Hybrid Beamforming Design for mmWave Massive MIMO Systems

引用

IEEE TRANSACTIONS ON COGNITIVE COMMUNICATIONS AND NETWORKING 2020年第3期6卷 1019-1030页

作者： Tao, Jiyun Chen, Jienan Xing, Jing Fu, Shengli Xie, Junfei Univ Elect Sci & Technol China Natl Key Lab Sci & Technol Commun Chengdu 611731 Peoples R China Univ North Texas Dept Elect Engn Denton TX 76201 USA San Diego State Univ Dept Elect & Comp Engn San Diego CA 92182 USA

Hybrid beamforming (HB) is a promising technology for the millimeter-wave (mmWave) massive multiple-input-multiple-output (MIMO) system, which supplies high data capacity with low complexity for next-generation communication systems. However, the joint design of digital and analog beamformer is a non-convex optimization problem due to the hardware constraints of analog shifter arrays. To address this issue, we proposed an intelligent HB design method based on the autoencoder (AE) neural network in this paper. By mapping the HB system to an AE neural network, the solving of the original non-convex optimization problem is converted to the neural network training process. The beamformer and combiner can be automatically formulated by the training process of the neural network. We also discuss the chosen of hyper-parameter and provide a guideline for the AE neural network HB design. With the strong representation ability of the deep neural network, the proposed intelligent HB exhibits superior performance in terms of bit error rate (BER).

关键词： Millimeter-wave massive MIMO hybrid beamforming autoencoder deep neural networks

来源：评论

学校读者我要写书评

暂无评论

autoencoder node saliency: Selecting relevant latent representations

引用

PATTERN RECOGNITION 2019年 88卷 643-653页

作者： Fan, Ya Ju Lawrence Livermore Natl Lab Ctr Appl Sci Comp Livermore CA 94551 USA

The autoencoder is an artificial neural network that performs nonlinear dimension reduction and learns hidden representations of unlabeled data. With a linear transfer function it is similar to the principal component analysis (PCA). While both methods use weight vectors for linear transformations, the autoencoder does not come with any indication similar to the eigenvalues in PCA that are paired with eigenvectors. We propose a novel autoencoder node saliency method that examines whether the features constructed by autoencoders exhibit properties related to known class labels. The supervised node saliency ranks the nodes based on their capability of performing a learning task. It is coupled with the normalized entropy difference (NED). We establish a property for NED values to verify classifying behaviors among the top ranked nodes. By applying our methods to real datasets, we demonstrate their ability to provide indications on the performing nodes and explain the learned tasks in autoencoders. (C) 2018 Elsevier Ltd. All rights reserved.

关键词： autoencoder Latent representations Unsupervised learning Neural networks Node selection Model interpretation

来源：评论

学校读者我要写书评

暂无评论

autoencoder with Fitting Network for Terahertz Wireless Communications:A Deep Learning Approach

引用

China Communications 2022年第3期19卷 172-180页

作者： Zhaohui Huang Dongxuan He Jiaxuan Chen Zhaocheng Wang Sheng Chen Beijing National Research Center for Information Science and Technology Department of Electronic EngineeringTsinghua UniversityBeijing 100084China Shenzhen International Graduate School Tsinghua UniveristyShenzhen 518055China School of Electronics and Computer Science University of SouthamptonSouthampton SO171BJU.K.

Terahertz wireless communication has been regarded as an emerging technology to satisfy the ever-increasing demand of ultra-high-speed wireless ***,affected by the imperfections of cheap and energy-efficient Terahertz devices,Terahertz signals suffer from serve hybrid distortions,including in-phase/quadrature imbalance,phase noise and nonlinearity,which degrade the demodulation performance *** improve the robustness against these hybrid distortions,an improved autoencoder is proposed,which includes coding the transmitted symbols at the transmitter and decoding the corresponding signals at the ***,due to the lack of information of Terahertz channel during the training of the autoencoder,a fitting network is proposed to approximate the characteristics of Terahertz channel,which provides an approximation of the gradients of *** results show that our proposed autoencoder with fitting network can recover the transmitted symbols under serious hybrid distortions,and improves the demodulation performance significantly.

关键词： Terahertz wireless communication hybrid distortion signal demodulation autoencoder

来源：评论

学校读者我要写书评

暂无评论

autoencoder-Based End-to-End OTFS System Design With Hardware Impairments

引用

IEEE WIRELESS COMMUNICATIONS LETTERS 2024年第8期13卷 2285-2289页

作者： Singh, Amit Sharma, Sanjeev Sharma, Mohit Deka, Kuntal da Costa, Daniel B. Indian Inst Technol BHU Varanasi Varanasi 221005 India Technol Innovat Inst AI & Telecom Dept Abu Dhabi U Arab Emirates Indian Inst Technol Guwahati EEE Dept Gauhati 781039 India King Fahd Univ Petr & Minerals Dept Elect Engn Dhahran 31261 Saudi Arabia

Orthogonal time-frequency space (OTFS) modulation is an innovative waveform which effectively multiplexes information symbols across a delay-Doppler (DD) plane, resulting in a superior performance, particularly in doubly dispersive channels. At higher carrier frequencies, the hardware impairments (HIs) at transceivers significantly degrade the performance of OTFS wireless systems. To mitigate the impact of HIs, conventionally an HI-aware channel equalization is performed, which is difficult to achieve in practice. In contrast to this, an autoencoder-based end-to-end design for OTFS (AE-OTFS) system is proposed, which does not require HI-aware channel equalization. Due to its end-to-end design approach, the proposed AE-OTFS significantly enhances the error performance of the OTFS system in the presence of HIs. In particular, it is found that the proposed HI-aware AE-OTFS achieves approximately 3 dB higher performance compared to existing autoencoder based OTFS design, which does not consider the impact of HIs. In addition, comparisons are performed against the conventional OTFS system with state-of-the-art signal detectors for HI-compensation, based on convolutional neural network (CNN), and it is found that due to its end-to-end design the proposed AE-OTFS results in signal-to-noise ratio improvement of up to 8 dB.

关键词： Symbols Vectors Receivers Channel estimation Wireless communication Time-domain analysis autoencoder deep learning HIs mapper and demapper OTFS signal detection signal detection

来源：评论

学校读者我要写书评

暂无评论

autoencoder-Based Enhanced Orthogonal Time Frequency Space Modulation

引用

IEEE COMMUNICATIONS LETTERS 2023年第10期27卷 2628-2632页

作者： Tek, Yusuf Islam Dogukan, Ali Tugberk Basar, Ertugrul Koc Univ Dept Elect & Elect Engn Commun Res & Innovat Lab CoreLab TR-34450 Istanbul Turkiye

Orthogonal time frequency space (OTFS) is a novel waveform that provides a superior performance in doubly-dispersive channels. Since it spreads information symbols across the entire delay-Doppler plane, OTFS can achieve full diversity. However, reliability still needs to be improved in OTFS systems to meet the stringent demands of future communication systems. To address this issue, we propose an autoencoder (AE)-based enhanced OTFS (AEE-OTFS) modulation scheme. By training an AE under an additive white Gaussian noise (AWGN) channel, a feasible mapper and demapper are learned to improve the error performance and decrease the detection complexity of the OTFS system. The learned mapper is used to map incoming bits into high-dimensional symbols while the learned demapper recovers the information bits in the delay-Doppler domain. Additionally, we derive a theoretical upper bound for the frame error rate (FER). Simulation results confirm that AEE-OTFS outperforms conventional OTFS in terms of FER under perfect and imperfect channel conditions. AEE-OTFS also enjoys low decoding complexity in addition to its superior error performance.

关键词： Orthogonal time frequency space (OTFS) time-varying channel autoencoder minimum Euclidian distance AWGN diversity

来源：评论

学校读者我要写书评

暂无评论

autoencoder as a New Method for Maintaining Data Privacy While Analyzing Videos of Patients With Motor Dysfunction: Proof-of-Concept Study

引用

JOURNAL OF MEDICAL INTERNET RESEARCH 2020年第5期22卷 e16669页

作者： D'Souza, Marcus Van Munster, Caspar E. P. Dorn, Jonas F. Dorier, Alexis Kamm, Christian P. Steinheimer, Saskia Dahlke, Frank Uitdehaag, Bernard M. J. Kappos, Ludwig Johnson, Matthew Univ Hosp Basel Dept Med Neurol Clin & Policlin Petersgraben 4 Basel 4031 Switzerland Univ Hosp Basel Dept Biomed Neurol Clin & Policlin Petersgraben 4 Basel 4031 Switzerland Univ Hosp Basel Dept Clin Res Neurol Clin & Policlin Petersgraben 4 Basel 4031 Switzerland Univ Basel Petersgraben 4 Basel 4031 Switzerland Univ Amsterdam Multiple Sclerosis Ctr Amsterdam Dept Neurol Med Ctr Amsterdam Netherlands Novartis Pharma AG Basel Switzerland Luzerner Kantonsspital Neuroctr Luzern Switzerland Univ Bern Dept Neurol Inselspital Bern Switzerland Microsoft Res Cambridge England

Background: In chronic neurological diseases, especially in multiple sclerosis (MS), clinical assessment of motor dysfunction is crucial to monitor the disease in patients. Traditional scales are not sensitive enough to detect slight changes. Video recordings of patient performance are more accurate and increase the reliability of severity ratings. When these recordings are automated, quantitative disability assessments by machine learning algorithms can be created. Creation of these algorithms involves non-health care professionals, which is a challenge for maintaining data privacy. However, autoencoders can address this issue. Objective: The aim of this proof-of-concept study was to test whether coded frame vectors of autoencoders contain relevant information for analyzing videos of the motor performance of patients with MS. Methods: In this study, 20 pre-rated videos of patients performing the finger-to-nose test were recorded. An autoencoder created encoded frame vectors from the original videos and decoded the videos again. The original and decoded videos were shown to 10 neurologists at an academic MS center in Basel, Switzerland. The neurologists tested whether the 200 videos were human-readable after decoding and rated the severity grade of each original and decoded video according to the Neurostatus-Expanded Disability Status Scale definitions of limb ataxia. Furthermore, the neurologists tested whether ratings were equivalent between the original and decoded videos. Results: In total, 172 of 200 (86.0%) videos were of sufficient quality to be ratable. The intrarater agreement between the original and decoded videos was 0.317 (Cohen weighted kappa). The average difference in the ratings between the original and decoded videos was 0.26, in which the original videos were rated as more severe. The interrater agreement between the original videos was 0.459 and that between the decoded videos was 0.302. The agreement was higher when no deficits or very severe de

关键词： autoencoder video-rating machine learning algorithms deep neuronal network Neurostatus-EDSS

来源：评论

学校读者我要写书评

暂无评论

autoencoder-based anomaly root cause analysis for wind turbines

引用

Energy and AI 2021年第2期4卷 57-65页

作者： Cyriana M.A.Roelofs Marc-Alexander Lutz Stefan Faulstich Stephan Vogt Fraunhofer IEE Konigstor 59Kassel 34119Germany Intelligent Embedded Systems Universitat KasselWilhelmshoher Allee 67Kassel 34121Germany

A popular method to detect anomalous behaviour or specific failures in wind turbine sensor data uses a specific type of neural network called an *** models have proven to be very successful in detecting such deviations,yet cannot show the underlying cause or failure *** information is necessary for the implementation of these models in the planning of maintenance *** this paper we introduce a novel method:*** use ARCANA to identify the possible root causes of anomalies detected by an *** describes the process of reconstruction as an optimisation problem that aims to remove anomalous properties from an anomaly *** reconstruction must be similar to the anomaly and thus identify only a few,but highly explanatory anomalous features,in the sense of Ockham’s *** proposed method is applied on an open data set of wind turbine sensor data,where an artificial error was added onto the wind speed sensor measurements to acquire a controlled test *** results are compared with the reconstruction errors of the autoencoder *** ARCANA method points out the wind speed sensor correctly with a significantly higher feature importance than the other features,whereas using the non-optimised reconstruction error does *** though the deviation in one specific input feature is very large,the reconstruction error of many other features is large as well,complicating the interpretation of the detected ***,we apply ARCANA to a set of offshore wind turbine *** case studies are discussed,demonstrating the technical relevance of ARCANA.

关键词： Anomaly detection autoencoder Root cause analysis Predictive maintenance Wind turbine Explainable artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

autoencoder Model Using Edge Enhancement to Detect Communities in Complex Networks

引用

ARABIAN JOURNAL FOR SCIENCE AND ENGINEERING 2023年第2期48卷 1303-1314页

作者： Chaudhary, Laxmi Singh, Buddha Jawaharlal Nehru Univ New Delhi 110067 India

Community structure is the utmost significant characteristics in complex networks. Numerous algorithms of community detection have been developed so far. Some methods consider only the lower-order framework, i.e. nodes and edges, and neglect the higher-order framework, whereas other recent methods capture higher-order framework, i.e. motifs (a small dense subgraph), yet they mainly put emphasis on the connected motif hypergraph. These methods help to encounter only fragmentation issue. Moreover, the other major issue in complex network is to reduce the dimension and extract the significant characteristics. In addition to this, the existing methods have sparsity and computational issues as well. Hence, we have developed an autoencoder model using edge enhancement (AMEE) to tackle these issues and uncover the hidden communities in complex networks. It begins by emphasizing edge enhancement to redesign the network connectivity of input network and creates a rewired graph. Embedding of a rewired network is obtained by applying the autoencoder model. Finally, a community detection technique is applied to reveal the communities. Hence, the proposed method (AMEE) deals with the above-mentioned issues efficiently. Furthermore, a comprehensive analysis of the proposed method is carried out on eight different real-world network datasets, i.e. Polbooks, Email, Polblogs, Cora, Facebook, Com-Orkut, Com-Amazon and Com-Youtube. The Modularity score, F-score and normalized mutual information are used as evaluation parameters to measure the performance of the proposed method. The higher value of these measures clearly indicates the efficacy and quality of the communities achieved using the proposed approach. It shows a significant improvement in comparison with other existing community detection techniques.

关键词： Communities Community detection Social networks Complex networks autoencoder Deep 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：