The precision of conventional PV fault diagnostic methods faces challenges due to the nonlinear output power characteristics of photovoltaic (PV) arrays and the implementation of the maximum power point tracking (MPPT...
详细信息
The precision of conventional PV fault diagnostic methods faces challenges due to the nonlinear output power characteristics of photovoltaic (PV) arrays and the implementation of the maximum power point tracking (MPPT) algorithm. In severe cases, it may lead to power losses and even arouse safety issues. In this study, the variation characteristics of the sequence waveforms at the moment of failure are investigated and used to develop a novel PV fault diagnostic framework. Firstly, the sequence waveforms of string voltages and currents before and after the fault occurred are collected;the normalized sequence data of voltages, currents, and powers are used as analytic data. Then, the fault feature extraction is realized via a stacked autoencoder (SAE) model. After that, an improved multi-grained cascade forest (IgcForest) is proposed to diagnose faults, e.g., line-to-line (L-L) fault, open-circuit (OC) fault, partial-shading of PV arrays, etc. The advantages of the proposed method are that the SAE method to extract features with higher recognition automatically, and the IgcForest to enhance and exploit fault features. Particularly, the proposed improvements can reduce the feature vector dimension and enhance the information connectivity between forests at all levels for further improving the accuracy of diagnoses. In addition, the validity of the proposed method is verified by numerical simulations and measured data, and the corresponding accuracy of fault diagnoses for single failure reach 99.33% and 98.61%, respectively, which are superior to traditional methods, such as softmax, support vector machines, random forest, gcForest, and daForest. Furthermore, it also has a high accuracy of 98.83% for data sets with the occurrence of multiple faults.
In this paper, we propose a Deep Neural Network model based on WiFi-fingerprinting to improve the accuracy of zone location in a multi-building, multi-floor indoor environment. The proposed model is presented as a Sta...
详细信息
ISBN:
(纸本)9781538677476
In this paper, we propose a Deep Neural Network model based on WiFi-fingerprinting to improve the accuracy of zone location in a multi-building, multi-floor indoor environment. The proposed model is presented as a stacked autoencoder (SAE) to allow efficient reduction of the feature space in order to achieve robust and precise classification. The multi-label classification is used to simplify and reduce the complexity of the learning classification task during the training phase. To achieve a hierarchical classification, we applied an argmax function on the multi-label output to convert the multi-label classification into multi-class classification ones to estimate the building, the floor and the zone identifier. Experimental results show that the proposed model achieves an accuracy of 100% for building, 99.66% for floor and 83.47% for zone location with a test time that does not exceed 10.21s.
Traffic Prediction in a large-scale network has become an important topic of an intelligent transportation system (ITS). The problem is challenging due to various nonlinear temporal and difficulty for longer-step ahea...
详细信息
ISBN:
(纸本)9781538675120
Traffic Prediction in a large-scale network has become an important topic of an intelligent transportation system (ITS). The problem is challenging due to various nonlinear temporal and difficulty for longer-step ahead prediction. The recurring congestion on rush-hour and non-recurring congestion on accidents are the main patterns. While most of the previously proposed techniques focus on rush-hour, unexpected accidents that affect local traffic were not considered in these works. To improve the prediction, we propose an ensemble deep neural network to archive the recurring and non-recurring congestion together combining CNN and LSTM architectures. Furthermore, the accident information is utilized and embedded using stacked autoencoder. An experiment was conducted on two data sets: England's Highways and Thailand's Expressways. The results showed that a combination of CNN and LSTM can be improved by using an embedded vector of accident information.
The development of condition monitoring system provides large amounts of operational data. These data present typical characteristics of multiple sources, polymorphism, diversity and mass, and can reflect the service ...
详细信息
ISBN:
(纸本)9781728150451
The development of condition monitoring system provides large amounts of operational data. These data present typical characteristics of multiple sources, polymorphism, diversity and mass, and can reflect the service quality and operating state of the equipment. How to use these data becomes one of the main problems in data analysis. To address the issue, this paper presents a generalized model for complex mechanical system anomaly detection based on the data collected from distributed control system (DCS). The stacked Auto-encoder network is used to achieve the automatic extraction of the hidden features in multidimensional polymorphic data. The isolation forest (IF) method is used to achieve the anomaly detection, which only needs to use the DCS monitoring data during normal operation of the unit for network training and model fitting without fault data. And the method can realize the abnormal detection during the operation of the unit without the traditional signal processing method for feature extraction. The proposed method has been used for real compressor. The results show that the proposed approach can detect the anomalies without the need for fault data. And the proposed method is more effective than traditional methods.
Recommender systems improve browsing experience of users for large amount of items by assisting selection and classification of items utilizing item metadata. The performance of recommender system usually deteriorates...
详细信息
ISBN:
(纸本)9781728106762
Recommender systems improve browsing experience of users for large amount of items by assisting selection and classification of items utilizing item metadata. The performance of recommender system usually deteriorates when implicit data is used with limited user interaction history also regarded as cold start (CS) problem. This paper proposes a model to address cold start problem using content based technique where user or item metadata is used to break this ice barrier. The proposed method utilizes the feature extraction techniques (such as term frequency-Inverse document frequency(TF-IDF)) and word embedding technique (Word2Vec). These content features are then used to predict the ratings for CS items by constructing user profiles using stacked auto-encoder. Experiments performed on largest real world dataset provided by Movielens 20M shows that proposed model outperforms the state-of-the-art approaches in CS item scenario.
In this study, the indoor localization was performed on indoor networks. WiFi technology is located in almost every building. For this reason, WiFi technology has been selected to perform positioning, and RSSI values ...
详细信息
ISBN:
(纸本)9789811304088;9789811304071
In this study, the indoor localization was performed on indoor networks. WiFi technology is located in almost every building. For this reason, WiFi technology has been selected to perform positioning, and RSSI values from WiFi technology access points have been examined. For this purpose, RFKON_MB_WIFI dataset in RFKON database which is a sample database is used and data of 18480 signal strength are analyzed. The Fingerprinting method of Scene Analysis methods is used to perform the localization process. As a first step, the signal strengths in the data set are normalized by preprocessing. In the second step, positioning was performed using SVM, PCA, LDA, KNN, N3, BNN, Naive Bayes Classification, and Deep Learning methods. When the results obtained are compared, the most successful result is obtained from deep learning that is known to have a high accuracy on big data with an accuracy of 95.95%.
Aiming at the problem of Synthetic Aperture Radar (SAR) target recognition, a new deep learning method is proposed. The stacked Auto Encoder (SAE) network and the convolutional Neural Network (CNN) have remarkable per...
详细信息
ISBN:
(纸本)9781728117089
Aiming at the problem of Synthetic Aperture Radar (SAR) target recognition, a new deep learning method is proposed. The stacked Auto Encoder (SAE) network and the convolutional Neural Network (CNN) have remarkable performance. Through the implementation and comparison of these methods, it is shown that the proposed deep learning recognition method has strong adaptability to different situations and has robustness to attitude angle, background and noise.
The threat-alert fatigue problem, which is the inability of security operators to genuinely investigate each alert coming from network-based intrusion detection systems, causes many unexplored alerts and hence a deter...
详细信息
ISBN:
(纸本)9783030367084;9783030367077
The threat-alert fatigue problem, which is the inability of security operators to genuinely investigate each alert coming from network-based intrusion detection systems, causes many unexplored alerts and hence a deterioration of the quality of service. Motivated by this pressing need to reduce the number of threat-alerts presented to security operators for manual investigation, we propose a scheme that can triage alerts of significance from massive threat-alert logs. Thanks to the fully unsupervised nature of the adopted isolation forest method, the proposed scheme does not require any prior labeling information and thus is readily adaptable for most enterprise environments. Moreover, by taking advantage of the temporal information in the alerts, it can be used in an online mode that takes in the most recent information from past alerts and predicts the incoming ones. We evaluated the performance of our scheme using a 10-month dataset consisting of more than half a million alerts collected in a real-world enterprise environment and found that it could screen out 87.41% of the alerts without missing any single significant ones. This study demonstrates the efficacy of unsupervised learning in screening minor threat-alerts and is expected to shed light on the threat-alert fatigue problem.
In this paper, a novel stacked marginal discriminative autoencoder (SMDAE) method is proposed for hyperspectral image classification. It uses a deep neural network to learn discriminative features from hyperspectral i...
详细信息
ISBN:
(纸本)9781509049516
In this paper, a novel stacked marginal discriminative autoencoder (SMDAE) method is proposed for hyperspectral image classification. It uses a deep neural network to learn discriminative features from hyperspectral images automatically. In hyperspectral images, the collection of training samples is difficult. When the number of training samples is not enough, these training samples are difficult to estimate the statistical distribution of hyperspectral images accurately. In order to solve the small sample problem and improve the classification performance of the autoencoder, the marginal samples are selected through the distribution characteristics of samples. The marginal samples are searched based on k nearest neighbors between different classes. These samples are used to fine-tune the SMDAE network. The experimental results show that the proposed SMDAE method can achieve satisfying performance under small training set.
This paper employs a novel-deep learning method and brain frequencies to discriminate school-aged children with autism spectrum disorders (ASD) from typically developing (TD) school-aged children with functional magne...
详细信息
This paper employs a novel-deep learning method and brain frequencies to discriminate school-aged children with autism spectrum disorders (ASD) from typically developing (TD) school-aged children with functional magnetic resonance imaging (fMRI) data of 84 subjects from the ABIDE (Autism Brain Imaging Data Exchange) database. Firstly, the fMRI data were preprocessed, and then each subject's dataset was decomposed into 30 independent components (IC). Secondly, some key ICs were selected and inputted into a stacked autoencoder (SAE). The SAE was adopted for features subtraction and dimensionality reduction. Finally, a softmax classifier was used to discriminate the school-aged children with ASD from TD school-aged children. The average accuracy of the work was as high as 87.21% (average sensitivity = 92.86%, average specificity = 84.32%). The results of classification demonstrated that the proposed method may have the potential to automatically discriminate school-aged children with ASD from TD school-aged children. Attempts to use deep learning-based algorithms and brain frequencies to discriminate school-aged children with ASD from TD school-aged children should likely be a key step forward in auxiliary clinical utility.
暂无评论