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 b...
详细信息
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.
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 perf...
详细信息
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.
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 commun...
详细信息
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).
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...
详细信息
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.
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...
详细信息
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.
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 dou...
详细信息
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.
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 achie...
详细信息
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.
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 ...
详细信息
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
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 deviation...
详细信息
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.
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. node...
详细信息
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.
暂无评论