检索结果-内蒙古大学图书馆

Forecast the electricity price of US using a wavelet transform-based hybrid model

ENERGY 2020年第0期193卷 511-530页

作者： Qiao, Weibiao Yang, Zhe North China Univ Water Resources & Elect Power Sch Environm & Municipal Engn 136 Jinshui East Rd Zhengzhou 450046 Henan Peoples R China Sinopec Petr Engn Zhongyuan Co Ltd Zhengzhou 450046 Peoples R China Univ Manchester Sch Comp Sci Manchester M13 9PL Lancs England

Wavelet transform (WT), as a data preprocessing algorithm, has been widely applied in electricity price forecasting. However, this deterministic-based algorithm does not present stable performance owing to the experiential selection of its orders and layers. For determining the selection of WTs orders and layers in U.S. electricity prices forecasting, this paper designs a crossover experiment with 240 schemes of WT parameter selection and forecasts each scheme with stacked autoencoder (SAE) and long short-term memory (LSTM), generating a novel hybrid model WT-SAE-LSTM. The results show that the proposed model outperforms other AI models, such as back propagation neural network et al., in forecasting accuracy. The best performance of WT-SAE-LSTM in residential, commercial, and industrial electricity price cases obtained by five order four layers, five order four layers, and four order seven layers, where the MAPE is 0.8606%, 0.4719%, and 0.4956%, respectively. Additionally, the difference between the proposed forecasting model and the forecasting result of Energy Information Administration (U.S.) is small. This paper determines the optimal orders and layers of WT in U.S. electricity prices forecasting, which provides an effective reference for the application of WT in other forecasting scenarios and for electricity market participants. (C) 2019 Elsevier Ltd. All rights reserved.

关键词： Electricity price Wavelet transform stacked autoencoder Long short-term memory Forecasting Energy information administration

来源：评论

学校读者我要写书评

暂无评论

Threat Alert Prioritization Using Isolation Forest and stacked Auto Encoder With Day-Forward-Chaining Analysis

引用

IEEE ACCESS 2020年 8卷 217977-217986页

作者： Aminanto, Muhamad Erza Ban, Tao Isawa, Ryoichi Takahashi, Takeshi Inoue, Daisuke Natl Inst Informat & Commun Technol Tokyo 1848795 Japan Univ Indonesia Grad Sch Strateg & Global Studies Jakarta 16424 Indonesia

Security Incident and Event Manager (SIEM) is a security management approach designed to identify possible threats within a real-time enterprise environment. The main challenge for SIEM is to find critical security incidents among a huge number of less critical alerts coming from separate security products. The continuously growing number of internet-connected devices has led to the alert fatigue problem, which is defined as the inability of security operators to investigate each incoming alert from intrusion detection systems. This fatigue can lead to human errors and leave many alerts being not investigated. Aiming at reducing the number of less important threat alerts presented to security operators, this paper presents a new method for highlighting critical alerts with a minimal number of false negatives. The proposed method employs isolation forest to ensure unsupervised performance and adaptability to different types of networks. Furthermore, it takes the advantage of day-forward-chaining analysis to ensure the detection of highly important alerts in real time. The number of false positive cases is reduced by employing an autoencoder. The proposed method achieved a recall score of 95.89% and a false positive rate of 5.86% on a dataset comprising more than half a million alerts collected in a real-world enterprise environment over ten months. This study highlights the importance of addressing the alert fatigue problem and validates the effectiveness of unsupervised learning in filtering out less important threat alerts.

关键词： Security Fatigue Forestry Real-time systems Task analysis Monitoring Intrusion detection Threat alert fatigue stacked autoencoder isolation forest intrusion detection system

来源：评论

学校读者我要写书评

暂无评论

Spatial-Adaptive Siamese Residual Network for Multi-/Hyperspectral Classification

引用

REMOTE SENSING 2020年第10期12卷 1640-1640页

作者： He, Zhi He, Dan Sun Yat Sen Univ Sch Geog & Planning Southern Marine Sci & Engn Guangdong Lab Zhuhai Guangdong Prov Key Lab Urbanizat & GeoSimulatCtr Guangzhou 510275 Guangdong Peoples R China Dongguan Univ Technol City Coll Dongguan 511700 Peoples R China

Deep learning methods have been successfully applied for multispectral and hyperspectral images classification due to their ability to extract hierarchical abstract features. However, the performance of these methods relies heavily on large-scale training samples. In this paper, we propose a three-dimensional spatial-adaptive Siamese residual network (3D-SaSiResNet) that requires fewer samples and still enhances the performance. The proposed method consists of two main steps: construction of 3D spatial-adaptive patches and Siamese residual network for multiband images classification. In the first step, the spectral dimension of the original multiband images is reduced by a stacked autoencoder and superpixels of each band are obtained by the simple linear iterative clustering (SLIC) method. Superpixels of the original multiband image can be finally generated by majority voting. Subsequently, the 3D spatial-adaptive patch of each pixel is extracted from the original multiband image by reference to the previously generated superpixels. In the second step, a Siamese network composed of two 3D residual networks is designed to extract discriminative features for classification and we train the 3D-SaSiResNet by pairwise inputting the training samples into the networks. The testing samples are then fed into the trained 3D-SaSiResNet and the learned features of the testing samples are classified by the nearest neighbor classifier. Experimental results on three multiband image datasets show the feasibility of the proposed method in enhancing classification performance even with limited training samples.

关键词： remote sensing classification stacked autoencoder superpixel Siamese network

来源：评论

学校读者我要写书评

暂无评论

Deep learning-based retrieval of cyanobacteria pigment in inland water for in-situ and airborne hyperspectral data

引用

ECOLOGICAL INDICATORS 2020年第0期110卷 105879-000页

作者： Yim, Inhyeok Shin, Jihoon Lee, Hyuk Park, Sanghyun Nam, Gibeom Kang, Taegu Cho, Kyung Hwa Cha, YoonKyung Univ Seoul Sch Environm Engn Seoul 130743 South Korea Natl Inst Environm Res Water Qual Assessment Res Div Environm Res Complex Incheon South Korea Ulsan Natl Inst Sci & Technol Sch Urban & Environm Engn Ulsan 689798 South Korea

Worldwide proliferation of cyanobacteria blooms in inland waters not only affects the intended use of water but potentially threatens human and animal health. In this study, a stacked autoencoder-deep neural network (SAE-DNN) was developed to estimate phycocyanin (PC) concentration by using in situ reflectance spectra in productive inland water. The estimated PC using the SAE-DNN was in close agreement with the measured PC, with an R-2 of 0.87, root mean square error (RMSE) of 14.45 mu g/L, and relative RMSE of 86.42%. The performance of the SAE-DNN was superior to that of the DNN and band-ratio algorithms. An analysis on the deep spectral features extracted using the SAE yielded the most useful spectral bands, namely 538, 596, and 735 nm, for the retrieval of PC. The estimation accuracy of the SAE-DNNPeaks, using only the aforementioned spectral bands as input variables, was comparable to that of the SAE-DNN, demonstrating that the high-level of abstraction using the SAE facilitated the improvement in feature learning. The application of the SAE-DNNPeak to airborne hyperspectral image data resulted in an acceptable estimation accuracy, despite a bias toward underestimation, potentially arising from uncertainty associated with atmospheric correction, at high PC concentrations. Our results suggest that simple, empirical-based approaches, such as the SAE-DNNPeak have the potential to serve as a rapid assessment tool for the abundance and spatial distribution of cyanobacteria.

关键词： Cyanobacteria Phycocyanin Hyperspectral imaging Deep learning Deep neural networks stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Novel PV Fault Diagnoses via SAE and Improved Multi-Grained Cascade Forest With String Voltage and Currents Measures

引用

IEEE ACCESS 2020年 8卷 133144-133160页

作者： Gao, Wei Wai, Rong-Jong Chen, Shi-Qun Natl Taiwan Univ Sci & Technol Dept Elect & Comp Engn Taipei 106 Taiwan Fuzhou Univ Coll Elect Engn & Automat Fuzhou 350108 Peoples R China

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.

关键词： Feature extraction Circuit faults Fault diagnosis Maximum power point trackers Forestry Arrays Current measurement Photovoltaic fault diagnosis stacked autoencoder improved multi-grained cascade forest

来源：评论

学校读者我要写书评

暂无评论

stacked Auto-Encoder for Scalable Indoor Localization in Wireless Sensor Networks 15

Stacked Auto-Encoder for Scalable Indoor Localization in Wir...

引用

15th IEEE International Wireless Communications and Mobile Computing Conference (IEEE IWCMC)

作者： BelMannoubi, Souad Touati, Haifa Snoussi, Hichem Univ Gabes Fac Sci Gabes Hatem Bettaher IResCoMath Res Unit Gabes Tunisia Univ Technol Troyes CNRS FRE 2848 ICD Troyes France

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.

关键词： Zoning Localization WiFi-Fingerprint Deep Neural Network stacked autoencoder Multi-Class Multi-Label

来源：评论

学校读者我要写书评

暂无评论

Improve Traffic Prediction Using Accident Embedding on Ensemble Deep Neural Networks 11

Improve Traffic Prediction Using Accident Embedding on Ensem...

引用

11th Annual International Conference on Knowledge and Smart Technology (KST)

作者： Liyong, Wanida Vateekul, Peerapon Chulalongkorn Univ Fac Engn Dept Comp Engn Big Data Analyt & IoT Ctr CUBIC Bangkok Thailand

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.

关键词： Traffic Prediction Convolutional Neural Networks Long Short-Term Memory stacked autoencoder Ensemble

来源：评论

学校读者我要写书评

暂无评论

An unsupervised anomaly detection approach based on industrial big data 2

An unsupervised anomaly detection approach based on industri...

引用

2nd World Conference on Mechanical Engineering and Intelligent Manufacturing (WCMEIM)

作者： Zhang, Cong Zhu, Yongsheng Ren, Zhijun Chen, Kaida Xi An Jiao Tong Univ Key Lab Educ Minist Modern Design & RotorBearing Xian Peoples R China

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.

关键词： Anomaly detection DCS data stacked autoencoder Isolation Forest

来源：评论

学校读者我要写书评

暂无评论

A Deep Learning Framework to Predict Rating for Cold Start Item Using Item Metadata 28

A Deep Learning Framework to Predict Rating for Cold Start I...

引用

28th IEEE International Conference on Enabling Technologies - Infrastructure for Collaborative Enterprises (WETICE)

作者： Anwaar, Fahad Iltaf, Naima Afzal, Hammad Abbas, Haider Natl Univ Sci & Technol NUST Mil Coll Signals Islamabad Pakistan

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.

关键词： Collaborative Filtering Neural Network Word2vec Cold Start profile Learner stacked autoencoder

来源：评论

学校读者我要写书评

暂无评论

Deep Learning in Indoor Localization Using WiFi 1st

Deep Learning in Indoor Localization Using WiFi

引用

1st International Telecommunications Conference (ITelCon)

作者： Turgut, Zeynep Ustebay, Serpil Aydin, Gulsum Zeynep Gurkas Sertbas, Ahmet Halic Univ Istanbul Turkey Istanbul Univ Istanbul Turkey

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%.

关键词： Indoor Localization Deep learning stacked autoencoder Fingerprinting

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：