During building operation, a significant amount of energy is wasted due to equipment and human related faults. To reduce waste, today's smart buildings monitor energy usage with the aim of identifying abnormal con...
详细信息
During building operation, a significant amount of energy is wasted due to equipment and human related faults. To reduce waste, today's smart buildings monitor energy usage with the aim of identifying abnormal consumption behaviour and notifying the building manager to implement appropriate energy saving procedures. To this end, this research proposes a new pattern-based anomaly classifier, the collective contextual anomaly detection using sliding window (CCAD-SW) framework. The CCAD-SW framework identifies anomalous consumption patterns using overlapping sliding windows. To enhance the anomaly detection capacity of the CCAD-SW, this research also proposes the ensemble anomaly detection (EAD) framework. The EAD is a generic framework that combines several anomaly detection classifiers using majority voting. To ensure diversity of anomaly classifiers, the EAD is implemented by combining pattern-based (e.g., CCAD-SW) and prediction-based anomaly classifiers. The research was evaluated using real-world data provided by Powersmiths, located in Brampton, Ontario, Canada. Results show that the EAD framework improved the sensitivity of the CCAD-SW by 3.6% and reduced false alarm rate by 2.7%. (C) 2017 The Author(s). Published by Elsevier B.V.
Classifying human actions from varied views is challenging due to huge data variations in different views. The key to this problem is to learn discriminative view-invariant features robust to view variations. In this ...
详细信息
Classifying human actions from varied views is challenging due to huge data variations in different views. The key to this problem is to learn discriminative view-invariant features robust to view variations. In this paper, we address this problem by learning view-specific and view-shared features using novel deep models. View-specific features capture unique dynamics of each view while view-shared features encode common patterns across views. A novel sample-affinity matrix is introduced in learning shared features, which accurately balances information transfer within the samples from multiple views and limits the transfer across samples. This allows us to learn more discriminative shared features robust to view variations. In addition, the incoherence between the two types of features is encouraged to reduce information redundancy and exploit discriminative information in them separately. The discriminative power of the learned features is further improved by encouraging features in the same categories to be geometrically closer. Robust view-invariant features are finally learned by stacking several layers of features. Experimental results on three multi-view data sets show that our approaches outperform the state-of-the-art approaches.
Cervical cancer remains a significant cause of mortality all around the world, even if it can be prevented and cured by removing affected tissues in early stages. Providing universal and efficient access to cervical s...
详细信息
Cervical cancer remains a significant cause of mortality all around the world, even if it can be prevented and cured by removing affected tissues in early stages. Providing universal and efficient access to cervical screening programs is a challenge that requires identifying vulnerable individuals in the population, among other steps. In this work, we present a computationally automated strategy for predicting the outcome of the patient biopsy, given risk patterns from individual medical records. We propose a machine learning technique that allows a joint and fully supervised optimization of dimensionality reduction and classification models. We also build a model able to highlight relevant properties in the low dimensional space, to ease the classification of patients. We instantiated the proposed approach with deep learning architectures, and achieved accurate prediction results (top area under the curve AUC = 0.6875) which outperform previously developed methods, such as denoising autoencoders. Additionally, we explored some clinical findings from the embedding spaces, and we validated them through the medical literature, making them reliable for physicians and biomedical researchers.
Currently, deep learning has been successfully applied in many fields and achieved amazing results. Meanwhile, big data has revolutionized the transportation industry over the past several years. These two hot topics ...
详细信息
Currently, deep learning has been successfully applied in many fields and achieved amazing results. Meanwhile, big data has revolutionized the transportation industry over the past several years. These two hot topics have inspired us to reconsider the traditional issue of passenger flow prediction. As a special structure of deep neural network (DNN), an autoencoder can deeply and abstractly extract the nonlinear features embedded in the input without any labels. By exploiting its remarkable capabilities, a novel hourly passenger flow prediction model using deep learning methods is proposed in this paper. Temporal features including the day of a week, the hour of a day, and holidays, the scenario features including inbound and outbound, and tickets and cards, and the passenger flow features including the previous average passenger flow and real-time passenger flow, are defined as the input features. These features are combined and trained as different stacked autoencoders (SAE) in the first stage. Then, the pre-trained SAE are further used to initialize the supervised DNN with the real-time passenger flow as the label data in the second stage. The hybrid model (SAE-DNN) is applied and evaluated with a case study of passenger flow prediction for four bus rapid transit (BRT) stations of Xiamen in the third stage. The experimental results show that the proposed method has the capability to provide a more accurate and universal passenger flow prediction model for different BRT stations with different passenger flow profiles. (C) 2017 Elsevier Ltd. All rights reserved.
A quaternionic extension of feed forward neural network, for processing multi-dimensional signals, is proposed in this paper. This neural network is based on the three layered network with random weights, called Extre...
详细信息
A quaternionic extension of feed forward neural network, for processing multi-dimensional signals, is proposed in this paper. This neural network is based on the three layered network with random weights, called Extreme Learning Machines (ELMs), in which iterative least-mean-square algorithms are not required for training networks. All parameters and variables in the proposed network are encoded by quaternions and operations among them follow the quaternion algebra. Neurons in the proposed network are expected to operate multidimensional signals as single entities, rather than real-valued neurons deal with each element of signals independently. The performances for the proposed network are evaluated through two types of experiments: classifications and reconstructions for color images in the CIFAR-10 dataset. The experimental results show that the proposed networks are superior in terms of classification accuracies for input images than the conventional (real-valued) networks with similar degrees of freedom. The detailed investigations for operations in the proposed networks are conducted.
Previous matrix completion methods are generally based on linear and shallow models where the given incomplete matrices are of low-rank and the data are assumed to be generated by linear latent variable models. In thi...
详细信息
Previous matrix completion methods are generally based on linear and shallow models where the given incomplete matrices are of low-rank and the data are assumed to be generated by linear latent variable models. In this paper, we first propose a novel method called autoencoder based matrix completion (AEMC). The main idea of AEMC is to utilize the partially observed data to learn and construct a nonlinear latent variable model in the form of autoencoder. The hidden layer of the autoencoder has much fewer units than the visible layers do. Meanwhile, the unknown entries of the data are recovered to fit the nonlinear latent variable model. Based on AEMC, we further propose a deep learning based matrix completion (DLMC) method. In DLMC, AEMC is used as a pre-training step for both the missing entries and network parameters;the hidden layer of AEMC is then used to learn stacked autoencoders (SAES) with greedy layer-wise training;finally, fine-tuning is carried out on the deep network formed by AEMC and SAES to obtain the missing entries of the data and the parameters of the network. In addition, we also provide out-of-sample extensions for AEMC and DLMC to recover online incomplete data. AEMC and DLMC are compared with state-of-the-art methods in the tasks of synthetic matrix completion, image inpainting, and collaborative filtering. The experimental results verify the effectiveness and superiority of the proposed methods. (C) 2017 Elsevier B.V. All rights reserved.
Compression algorithm is an essential part of Telemedicine systems, to store and transmit large amount of medical signals. Most of existing compression methods utilize fixed transforms such as discrete cosine transfor...
详细信息
Compression algorithm is an essential part of Telemedicine systems, to store and transmit large amount of medical signals. Most of existing compression methods utilize fixed transforms such as discrete cosine transform (DCT) and wavelet and usually cannot efficiently extract signal redundancy especially for non-stationary signals such as electroencephalogram (EEG). In this paper, we first propose learning-based adaptive transform using combination of DCT and artificial neural network (ANN) reconstruction technique. This adaptive ANN-based transform is applied to the DCT coefficients of EEG data to reduce its dimensionality and also to estimate the original DCT coefficients of EEG in the reconstruction phase. To develop a new near lossless compression method, the difference between the original DCT coefficients and estimated ones are also quantized. The quantized error is coded using Arithmetic coding and sent along with the estimated DCT coefficients as compressed data. The proposed method was applied to various datasets and the results show higher compression rate compared to the state-of-the-art methods.
Since the proposal of a fast learning algorithm for deep belief networks in 2006, the deep learning techniques have drawn ever-increasing research interests because of their inherent capability of overcoming the drawb...
详细信息
Since the proposal of a fast learning algorithm for deep belief networks in 2006, the deep learning techniques have drawn ever-increasing research interests because of their inherent capability of overcoming the drawback of traditional algorithms dependent on hand-designed features. Deep learning approaches have also been found to be suitable for big data analysis with successful applications to computer vision, pattern recognition, speech recognition, natural language processing, and recommendation systems. In this paper, we discuss some widely used deep learning architectures and their practical applications. An up-to-date overview is provided on four deep learning architectures, namely, autoencoder, convolutional neural network, deep belief network, and restricted Boltzmann machine. Different types of deep neural networks are surveyed and recent progresses are summarized. Applications of deep learning techniques on some selected areas (speech recognition, pattern recognition and computer vision) are highlighted. A list of future research topics are finally given with clear justifications.
Different modalities have been proved to carry various information. This paper aims to study how the multiple face regions/channels and multiple models (e.g., hand-crafted and unsupervised learning methods) answer to ...
详细信息
Different modalities have been proved to carry various information. This paper aims to study how the multiple face regions/channels and multiple models (e.g., hand-crafted and unsupervised learning methods) answer to the face recognition problem. Hand crafted and deep feature learning techniques have been proposed and applied to estimate discriminative features in object recognition problems. In our Multi-Channel Multi-Model feature learning (McMmFL) system, we propose a new autoencoder (AE) optimization that integrates the alternating direction method of multipliers (ADMM). One of the advantages of our AE is dividing the energy formulation into several sub-units that can be used to paralyze/distribute the optimization tasks. Furthermore, the proposed method uses the advantage of K-means clustering and histogram of gradients (HOG) to boost the recognition rates. McMmFL outperforms the best results reported on the literature on three benchmark facial data sets that include AR, Yale, and PubFig83 with 95.04%, 98.97%, 95.85% rates, respectively. (C) 2016 Published by Elsevier B.V.
Multilayer feedforward neural networks (MFNNs) have been widely used for classification or approximation of nonlinear mappings described by a data set consisting of input and output samples. In many MFNN applications,...
详细信息
Multilayer feedforward neural networks (MFNNs) have been widely used for classification or approximation of nonlinear mappings described by a data set consisting of input and output samples. In many MFNN applications, a common compressive sensing task is to find the redundant dimensions of the input data. The aim of a regularization technique presented in this paper is to eliminate the redundant dimensions and to achieve compression of the input layer. It is achieved by introducing an L-1 or L-1/2 regularizer to the input layer weights training. As a comparison, in the existing references, a regularization method is usually applied to the hidden layer for a better representation of the dataset and sparsification of the network. Gradient-descent method is used for solving the resulting optimization problem. Numerical experiments including a simulated approximation problem and three classification problems (Monk, Sonar, and the MNIST data set) have been used to illustrate the algorithm.
暂无评论