The hyperspectral anomaly detection (HAD) aims to identify potential anomalies from complex backgrounds. Most reconstruction-based autoencoders equally treat background pixels and anomalies or ignore potential spatial...
详细信息
The hyperspectral anomaly detection (HAD) aims to identify potential anomalies from complex backgrounds. Most reconstruction-based autoencoders equally treat background pixels and anomalies or ignore potential spatial information. In this letter, we propose an HAD method based on multiscale memory autoencoder and spatial filtering, abbreviated as SFM2AE. Specifically, by introducing memory modules into different hidden layers of the autoencoder, multiscale reconstruction of background and anomaly pixels is achieved in the spectral domain. In addition, morphological filtering in the spatial domain is used to extract spatial structural information from anomalies. Joint spatial-spectral anomaly detection is achieved by combining multiscale memory autoencoder and spatial filtering. Experiments demonstrate superior detection performance of the proposed method over the state-of-the-art methods.
Due to the rapid increase in User-Generated Content (UGC) data, opinion mining, also called sentiment analysis, has attracted much attention in both academia and industry. Aspect-Based Sentiment Analysis (ABSA), a sub...
详细信息
ISBN:
(数字)9783031126703
ISBN:
(纸本)9783031126703;9783031126697
Due to the rapid increase in User-Generated Content (UGC) data, opinion mining, also called sentiment analysis, has attracted much attention in both academia and industry. Aspect-Based Sentiment Analysis (ABSA), a subfield of sentiment analysis, aims to extract the aspect and the corresponding sentiment simultaneously. Previous works in ABSA may generate undesired aspects, require a large amount of training data, or produce unsatisfactory results. This paper proposes a Graph Neural Network based method to automatically generate aspect-specific sentiment words using a small number of aspect seed words and general sentiment words. It subsequently leverages the aspect-specific sentiment words to improve the Joint Aspect-Sentiment autoencoder (JASA) model. We conduct experiments on two datasets to verify the proposed model. It shows that our approach has better performance in the ABSA task when compared with previous works.
This study applies a data-driven anomaly detection frame-work based on a Long Short-Term Memory (LSTM) autoencoder network for several subsystems of a public transport bus. The proposed frame-work efficiently detects ...
详细信息
ISBN:
(数字)9783031013331
ISBN:
(纸本)9783031013331;9783031013324
This study applies a data-driven anomaly detection frame-work based on a Long Short-Term Memory (LSTM) autoencoder network for several subsystems of a public transport bus. The proposed frame-work efficiently detects abnormal data, significantly reducing the false alarm rate compared to available alternatives. Using historical repair records, we demonstrate how detection of abnormal sequences in the signals can be used for predicting equipment failures. The deviations from normal operation patterns are detected by analysing the data collected from several on-board sensors (e.g., wet tank air pressure, engine speed, engine load) installed on the bus. The performance of LSTM autoencoder (LSTM-AE) is compared against the multi-layer autoencoder (mlAE) network in the same anomaly detection framework. The experimental results show that the performance indicators of the LSTM-AE network, in terms of F1 Score, Recall, and Precision, are better than those of the mlAE network.
Novelty detection (ND) has gained attention in many applications for its effectiveness in dealing with imbalanced data. Many ND algorithms have been proposed. For example, the level set boundary description (LSBD) alg...
详细信息
ISBN:
(数字)9781728186719
ISBN:
(纸本)9781728186719
Novelty detection (ND) has gained attention in many applications for its effectiveness in dealing with imbalanced data. Many ND algorithms have been proposed. For example, the level set boundary description (LSBD) algorithm can accurately estimate a boundary around normal data which is subsequently used to detect novelties. However, the computational complexity and the convergence time of the LSBD algorithms increases substantially when data dimensionality increases. To solve those challenges, we propose an Integrated autoencoder-Level Set Method (AE-LSM) for ND in this paper. The AE structure is employed to reduce the feature space with high dimensionality to a 3-dimensional (3D) space. The LSM algorithm is trained based on the compressed 3D data to identify the boundary of normal data. The AE-LSM has advantages of boundary control and good generalization performance. Experiments on 5 benchmark UCI datasets and an Alzheimer's Disease Neuroimaging Initiative (ADNI) dataset demonstrate that the proposed AE-LSM present a 3%similar to 14% significant improvement based on the average AUC (p<0.05) over the AE and LSBD algorithms across the six datasets.
Discovering the anomalies of the steam power system in time can optimize the operating efficiency and avoid major losses. The existing single anomaly detection method is not effective outside its assumptions. Aiming a...
详细信息
Discovering the anomalies of the steam power system in time can optimize the operating efficiency and avoid major losses. The existing single anomaly detection method is not effective outside its assumptions. Aiming at this problem, a new anomaly detection method based on the coupling of thermoeconomics and autoencoder is proposed. This method uses the autoencoder to reconstruct the normal values of the thermoeconomic calculation benchmark and other parameters. Then the endogenous irreversible loss of each component is calculated according to the benchmark. Finally, it is detected together with the reconstruction error of the parameters, and the deviation exceeding the threshold is abnormal. The experimental results show that under the premise of ensuring the precision, the traditional thermoeconomic anomaly detection method, the autoencoder anomaly detection method and the proposed coupling anomaly detection method can detect 58.7 %, 88.9 % and 94 % abnormal samples, respectively. In terms of the accuracy and F1-score, the coupling method is also the highest, reaching 93.9 % and 96.8 % respectively. It is proved that the coupling method is superior to the single thermoeconomic method or the autoencoder method, which is of great significance to ensure the safe and stable operation of the steam power system.
Sensor networks are playing an increasingly important role in modern buildings. With the growing size of building sensor networks and the increasing use of low-cost sensors, the accuracy and reliability of these senso...
详细信息
Sensor networks are playing an increasingly important role in modern buildings. With the growing size of building sensor networks and the increasing use of low-cost sensors, the accuracy and reliability of these sensor networks face challenges. Therefore, in-situ calibration of sensor networks is crucial to maintain data quality. Various state-of-the-art methods typically require meeting stringent conditions, such as reference sensors or colocated sensors, accurate physical models, and a large amount of operational data, limiting their applicability in some scenarios. This paper addresses a common issue in sensor calibration: the non-differential calibration issue in uncontrolled environments. We propose an in-situ calibration method based on virtual samples and autoencoder. Virtual samples are generated through Monte Carlo sampling to ensure the completeness of sample information. autoencoder autonomously establishes relationships within the sensor network, integrating sensor fault detection and calibration into one step. Offline experiments optimize methods, and online experiments are utilized for verification and analysis. The online experiments demonstrated that the proposed method achieved a calibration accuracy above 98.9 % for single and multiple sensor faults, with a calibration error below 3 %. Compared to the SoT methods, our approach consistently delivered superior performance, confirming its outstanding efficacy.
In order to speed up the process of optimizing design of metasurface absorbers, an improved design model for metasurface absorbers based on autoencoder (AE) and BiLSTM-Attention-FCN-Net (including bidirectional long-s...
详细信息
In order to speed up the process of optimizing design of metasurface absorbers, an improved design model for metasurface absorbers based on autoencoder (AE) and BiLSTM-Attention-FCN-Net (including bidirectional long-short-term memory network, attention mechanism, and fully-connection layer network) is proposed. The metasurface structural parameters can be input into the forward prediction network to predict the corresponding absorption spectra. Meantime, the metasurface structural parameters can be obtained by inputting the absorption spectra into the inverse prediction network. Specially, in the inverse prediction network, the bidirectional long-short-term memory (BiLSTM) network can effectively capture the context relationship between absorption spectral sequence data, and the attention mechanism can enhance the BiLSTM output sequence features, which highlight the critical feature information. After the training, the mean square error (MSE) value on the validation set of the reverse prediction network converges to 0.0046, R2 reaches 0.975, and our network can accurately predict the metasurface structure parameters within 1.5 s with a maximum error of 0.03 mm. Moreover, this model can achieve the optimal design of multi-band metasurface absorbers, including the single-band, dual-band, and three-band absorptions. The proposed method can also be extended to other types of metasurface optimization design.
Unknown cyber-attack detection in network traffic streams is challenging but crucial to ensure network security. It is observed that new security threats occur on a daily basis and make cyberspace vulnerable. In the l...
详细信息
Unknown cyber-attack detection in network traffic streams is challenging but crucial to ensure network security. It is observed that new security threats occur on a daily basis and make cyberspace vulnerable. In the literature, machine learning and deep learning-based network intrusion detection systems have gained a lot of success but still face many challenges in detecting new security threats and unknown cyber-attacks in real-time. Additionally, high false alarm rates and real-time detection in constantly evolving high-dimensional network data streams are open issues for the research community. To address this issue, a DL-based solution is developed to detect real-time network anomalies in streaming data with high detection accuracy, precision, recall and low false negative and positive scenarios. The proposed novel algorithm, AE-Integrated, is developed and evaluated on the latest CICIDS-2017 dataset. The AE-Integrated is updated with the newest network traffic data stream by the human administrator after a certain period to maintain its prediction accuracy for future inference. The simulation study is conducted with the Apache Kafka and Slack API to get real-time anomaly alerts. Finally, we compared the result with recent state-of-the-art research to evaluate the significance of the proposed algorithm. It is concluded that combining multiple lightweight autoencoders into a single large architecture provides optimal results. The accuracy, recall, and AUC of AE-Integrated obtained are 99.54%, 99.53%, and 0.998, respectively.
The imminent depletion of oil resources and increasing environmental pollution have driven the use of clean energy, particularly wind energy. However, wind turbines (WTs) face significant challenges, such as critical ...
详细信息
The imminent depletion of oil resources and increasing environmental pollution have driven the use of clean energy, particularly wind energy. However, wind turbines (WTs) face significant challenges, such as critical component failures, which can cause unexpected shutdowns and affect energy production. To address this challenge, we analyzed the Supervisory Control and Data Acquisition (SCADA) data to identify significant differences between the relationship of variables based on data reconstruction errors between actual and predicted values. This study proposes a hybrid short- and long-term memory autoencoder model with multihead self-attention (LSTM-MA-AE) for WT converter fault detection. The proposed model identifies anomalies in the data by comparing the reconstruction errors of the variables involved. However, more is needed. To address this model limitation, we developed a fault prediction system that employs an adaptive threshold with an Exponentially Weighted Moving Average (EWMA) and a fixed threshold. This system analyzes the anomalies of several variables and generates fault warnings in advance time. Thus, we propose an outlier detection method through data preprocessing and unsupervised learning, using SCADA data collected from a wind farm located in complex terrain, including real faults in the converter. The LSTM-MA-AE is shown to be able to predict the converter failure 3.3 months in advance, and with an F1 greater than 90% in the tests performed. The results provide evidence of the potential of the proposed model to improve converter fault diagnosis with SCADA data in complex environments, highlighting its ability to increase the reliability and efficiency of WTs.
The establishment of a comprehensive predictive model for red meat polyunsaturated fatty acids holds profound significance for the food industry. However, challenges, such as intricate features and low chemical conten...
详细信息
The establishment of a comprehensive predictive model for red meat polyunsaturated fatty acids holds profound significance for the food industry. However, challenges, such as intricate features and low chemical content bestow complexity upon this endeavor. In the study, an autoencoder-assisted generative adversarial network (AE-GAN) was used to address the intricacies of generative models in regression operations. Following numerous iterations, the AE-GAN generated samples akin to the original data. Upon the incorporation of these generated samples into training, the test set R 2 values of Support Vector Regression, Random Forest and Fully Convolutional Network witnessed respective enhancements of 0.1589, 0.1482 and 0.2998. The outcomes underscore the efficacy of this novel approach in ameliorating the challenges faced by generative models in regression tasks, thereby augmenting the model 's generalizability.
暂无评论