Search

Automatic age and gender classification has been widely used in a large amount of applications, particularly in human-computer interaction, biometrics, visual surveillance, electronic customer, and commercial applications. In this paper, we introduce a hybrid structure which includes Convolutional Neural Network (CNN) and Extreme Learning Machine (ELM), and integrates the synergy of two classifiers to deal with age and gender classification. The hybrid architecture makes the most of their advantages: CNN is used to extract the features from the input images while ELM classifies the intermediate results. We not only give the detailed deployment of our structure including design of parameters and layers, analysis of the hybrid architecture, and the derivation of back-propagation in this system during the iterations, but also adopt several measures to limit the risk of overfitting. After that, two popular datasets, such as, MORPH-II and Adience Benchmark, are used to verify our hybrid structure. Experimental results show that our hybrid architecture outperforms other studies on the same datasets by exhibiting significant performance improvement in terms of accuracy and efficiency. [ABSTRACT FROM AUTHOR]

Different words in discourse arguments usually have varying contributions on the recognition of implicit discourse relations. Following this intuition, we propose two attention-based neural networks, namely inner attention model and outer attention model , to learn better discourse representation by automatically estimating the degrees of relevance of words to discourse relations. The former model only utilizes the information inside discourse arguments, while the latter model builds upon an outside semantic memory to exploit general world knowledge. Both models are capable of assigning more weights to relation-relevant words, and operate in an end-to-end manner. Upon these two models, we further propose a full attention model that combines their strengths into a unified framework. Extensive experiments on the PDTB data set show that our model significantly benefits from highlighting relation-relevant words and yields competitive and even better results against several state-of-the-art systems. [ABSTRACT FROM AUTHOR]

Rolling bearing tips are often the most susceptible to electro-mechanical system failure due to high-speed and complex working conditions, and recent studies on diagnosing bearing health using vibration data have developed an assortment of feature extraction and fault classification methods. Due to the strong non-linear and non-stationary characteristics, an effective and reliable deep learning method based on a convolutional neural network (CNN) is investigated in this paper making use of cognitive computing theory, which introduces the advantages of image recognition and visual perception to bearing fault diagnosis by simulating the cognition process of the cerebral cortex. The novel feature representation method for bearing data is first discussed using supervised deep learning with the goal of identifying more robust and salient feature representations to reduce information loss. Next, the deep hierarchical structure is trained in a robust manner that is established using a transmitting rule of greedy training layer by layer. Convolution computation, rectified linear units, and sub-sampling are applied for weight replication and reducing the number of parameters that need to be learned to improve the general feed-forward back propagation training. The CNN model could thus reduce learning computation requirements in the temporal dimension, and an invariance level of working condition fluctuation and ambient noise is provided by identifying the elementary features of bearings. A top classifier followed by a back propagation process is used for fault classification. Contrast experiments and analyses have been undertaken to delineate the effectiveness of the CNN model for fault classification of rolling bearings. [ABSTRACT FROM AUTHOR]

In recent years, more than 300 sets of Trouble of Running Freight Train Detection Systems (TFDSs) have been installed on railway to monitor the safety of running freight trains in China. However, TFDS is simply responsible for capturing, transmitting, and storing images, and fails to recognize faults automatically. Motivated by the success of convolutional neural networks (CNNs) in the tasks of image recognition, this paper makes essential use of CNN models and proposes an automatic fault recognition system (AFRS) for recognizing four typical faults in TFDS simultaneously. AFRS is a two-stage system: In the first stage, a coarse-to-fine scheme based on CNN model is adopted to detect the target regions of side frame keys (SFKs) and shaft bolts (SBs) simultaneously. In the second stage, we establish another CNN model for multi-fault determination to recognize four typical faults emerged in the target regions of SFKs and SBs. The experimental results show that this system has an excellent performance of multi-fault recognition in TFDS. High recognition accuracy rates, low false ratios and low omission ratios are obtained for all the four typical faults, demonstrating the high recognition ability and robustness against various low quality imaging situations. [ABSTRACT FROM AUTHOR]

Estimating the number of people present in an image has many practical applications including visual surveillance and public resource management. Recently, regression-based methods for people counting have gained considerable importance, principally due to the capability of these methods to handle crowded scenes. However, the principal drawback of regression-based methods is to find an optimal set of features and a model, which is usually dependent on the crowd density. Encouraged by the recent success of sparse representation, here, we develop a robust and scalable people counting method. Sparse representation allows us to capture the hidden structure and semantic information in visual data and leads to faster processing algorithms. In order to reduce the complexity of solving l 1 - minimization problem, which resides at the heart of the sparse representation, a dimensionality reduction method based on random projection is employed. The sparse representation framework provides new insight that if sparsity in the classification problem is properly harnessed, feature extraction is no longer critical. So, in addition to several hand-crafted features, we exploit the features obtained from pre-trained deep Convolutional neural network and show these features perform competitively. Further, to render the proposed method user friendly, we employ a semi-supervised elastic net to automatically annotate unlabelled data with only a handful of user-labelled image frames. Our semi-supervised method exploits temporal continuity in videos. We use extensive evaluations on the crowd analysis benchmark datasets to demonstrate the effectiveness of our approach as well as its superiority over the state-of-the-art regression-based people counting methods, in terms of accuracy and time. [ABSTRACT FROM AUTHOR]