The emergence of mobile health (mHealth) systems has risen the challenges and concerns due to the sensitivity of the data involved in such systems. It is essential to ensure that these data are well delivered to the h...
详细信息
ISBN:
(纸本)9781509043729
The emergence of mobile health (mHealth) systems has risen the challenges and concerns due to the sensitivity of the data involved in such systems. It is essential to ensure that these data are well delivered to the health monitoring center for accurate and perfect diagnosis and follow-up. Due to the wireless network constraints, these requirements become more challenging. In this paper, we propose a deep learning approach for EEG data compression in mHealth system. We show that the stacked autoencoder neural network architecture is efficient for EEG data compression. We conduct a comprehensive comparative study that demonstrates the effectiveness of our system for EEG compression in addition to preserving the total energy consumption.
anomaly detection of gateway electrical energy metering device is important for maintenance and operations in the power systems. Traditionally, anomaly detection was typically performed manually through the analysis o...
详细信息
anomaly detection of gateway electrical energy metering device is important for maintenance and operations in the power systems. Traditionally, anomaly detection was typically performed manually through the analysis of the collected energy information. However, the manual process is time-consuming and labor-intensive. In this condition, this paper proposes a hybrid deep-learning model, which integrates stacked intelligently detecting the abnormal events of gateway electrical energy metering device. The proposed model named SAE-LSTM model, first uses SAE to extract deep latent features of threephase voltage data collected from the gateway electrical energy metering device, and then adopts LSTM for separating the abnormal events based on the extracted deep latent features. The SAE-LSTM model, can effectively highlight the temporal information of the electrical data, thereby enhancing the accuracy of anomaly detection. The simulation experiments verify the advantages of the SAE-LSTM model in anomaly detection under different signal-to-noise ratios. The experimental results of real datasets demonstrate that it is suitable for anomaly detection of gateway electrical energy metering devices in practical scenarios.
Advanced Persistent Threat (APT) attack is one of the most common and costly destructive attacks on the target system. This attack has become a challenge for companies, governments, and organizations’ information sec...
详细信息
ISBN:
(纸本)9781450387347
Advanced Persistent Threat (APT) attack is one of the most common and costly destructive attacks on the target system. This attack has become a challenge for companies, governments, and organizations’ information security systems. In recent years, methods for detecting and preventing APT attacks that use machine learning or deep learning algorithms to analyze indications and anomalous behaviors in network traffic have become popular. However, due to a lack of typical data from attack campaigns, the APT attack detection approach that uses behavior analysis and evaluation approaches encounter many issues. Network traffic analysis to detect a common APT attack is one of the solutions for dealing with this situation. This paper develops efficient and flexible deep learning models. To analyze huge network traffic, a hybrid deep learning approach that builds two models is used: stacked autoencoder with Long Short-Term Memory (SAE-LSTM) and Convolutional Neural Networks with Long Short-Term Memory Network (CNN-LSTM) to detect indications of APT attacks. A reliable dataset ’DAPT2020’ that covers all APT stages is used to evaluate the proposed approach. The experimental results demonstrate that the hybrid deep learning approach proved to give higher performance than the individual deep learning model in detecting malicious behavior in each APT stage.
In modern industrial processes, timely detection and diagnosis of process abnormalities are critical for monitoring process *** fault detection and diagnosis(FDD) methods have been proposed and implemented, the perfor...
详细信息
In modern industrial processes, timely detection and diagnosis of process abnormalities are critical for monitoring process *** fault detection and diagnosis(FDD) methods have been proposed and implemented, the performance of which,however, could be drastically influenced by the common presence of incomplete or missing data in real industrial *** paper presents a new FDD approach based on an incomplete data imputation technique for process fault *** employs the modified stacked autoencoder, a deep learning structure, in the phase of incomplete data treatment, and classifies data representations rather than the imputed complete data in the phase of fault identification.A benchmark process, the Tennessee Eastman process, is employed to illustrate the effectiveness and applicability of the proposed method.
Computational protein structure prediction is very important for many applications in bioinformatics. In the process of predicting protein structures, it is essential to accurately assess the quality of generated mode...
详细信息
ISBN:
(纸本)9781479914821
Computational protein structure prediction is very important for many applications in bioinformatics. In the process of predicting protein structures, it is essential to accurately assess the quality of generated models. Although many single-model quality assessment (QA) methods have been developed, their accuracy is not high enough for most real applications. In this paper, a new approach based on C-a atoms distance matrix and machine learning methods is proposed for single-model QA and the identification of native-like models. Different from existing energy/scoring functions and consensus approaches, this new approach is purely geometry based. Furthermore, a novel algorithm based on deep learning techniques, called DL-Pro, is proposed. For a protein model, DL-Pro uses its distance matrix that contains pairwise distances between two residues' C-α atoms in the model, which sometimes is also called contact map, as an orientation-independent representation. From training examples of distance matrices corresponding to good and bad models, DL-Pro learns a stacked autoencoder network as a classifier. In experiments on selected targets from the Critical Assessment of Structure Prediction (CASP) competition, DL-Pro obtained promising results, outperforming state-of-the-art energy/scoring functions, including OPUS-CA, DOPE, DFIRE, and RW.
Since industrial process data often presents complexity and nonlinearity,this study proposes a deep learning model based on semi-supervised Inter-Relational Mahalanobis stacked autoencoder(IRM-SAE) to learn deep fault...
详细信息
Since industrial process data often presents complexity and nonlinearity,this study proposes a deep learning model based on semi-supervised Inter-Relational Mahalanobis stacked autoencoder(IRM-SAE) to learn deep fault-relevant features of process data for fault ***,the Inter-Relational Mahalanobis loss function is introduced to learn meaningful inter-relational distribution features within the ***,active time-frame preprocessing is utilized to capture dynamic features of ***,to fully utilize both labeled and unlabeled data in industrial processes,the semi-supervised strategy is introduced to learn fault-related features for better fault ***,the Tennessee Eastman process is utilized to validate the effectiveness of the proposed *** experimental results show that IRM-SAE outperforms other deep learning models with an average fault classification accuracy of 96.59%.
Modern industrial process data often exhibit nonlinear and dynamic *** deep learning methods,such as stacked autoencoder(SAE),have excellent nonlinear feature learning capabilities,but they ignore the dynamic correlat...
详细信息
Modern industrial process data often exhibit nonlinear and dynamic *** deep learning methods,such as stacked autoencoder(SAE),have excellent nonlinear feature learning capabilities,but they ignore the dynamic correlation between process *** learning based on manifold learning using neighborhood structure preserving has been widely used in industrial dynamic process ***,most of them extract linear features and the complex nonlinearities in process data are largely ***,a spatial temporal neighborhood preserving stack autoencoder(STNP-SAE) is proposed to learn static neighborhood features and dynamic neighborhood features of process data simultaneously in this ***,STNP-SAE is utilized to construct a soft sensor framework for quality *** effectiveness and prediction performance of the proposed method are validated on a practical hydrocracking process.
暂无评论