SafeMove: monitoring seniors with mild cognitive impairments using deep learning and location prediction

Neural Computing and Applications - Due to society aging, age-related issues such as mild cognitive impairments (MCI) and dementia are attracting the attention of health professionals, scientists...     

基于深度学习的精神分裂症脑电分析

精神分裂症是最常见的精神疾病之一,目前具体病因尚未明确,准确诊断患病与否是治疗该疾病的前提。深度学习是一种构造多层神经网络的机器学习方法,具有发现数据中隐藏的分布式特征表示的能力。针对精神分裂症患者的脑电信号,提出了一种栈式自编码网络深度模型,以达到根据脑电信号自动识别受试者是否患病的效果。     

Sentiment analysis using deep learning approaches: an overview

Nowadays,with the increasing number of Web 2.0 tools,users generate huge amounts of data in an enormous and dynamic way.In this regard,the sentiment analysis ap...     

Structural health monitoring by using a sparse coding-based deep learning algorithm with wireless sensor networks

Structural health monitoring has received remarkable attention due to the arising structural safety problems. Most of these structural health problems are accumulative damages such as slight changes in structural deformations which are very hard to be detected. In addition, the complexity of real structure and environmental noises make structural health monitoring more difficult. Existing methods largely use various types of sensors to collect useful parameters and then train a machine learning model to diagnose damage level and location, in which a large amount of training data are needed for the model training, while the labeled data are rare in the real world. To overcome this problem, sparse coding is employed in this paper to achieve structural health monitoring of a bridge equipped with a wireless sensor network, so that a large amount of unlabeled examples can be used to train a feature extractor based on the sparse coding algorithm. Features learned from sparse coding are then used to train a neural network classifier to distinguish different statuses of the bridge. Experimental results show the sparse coding-based deep learning algorithm achieves higher accuracy for structural health monitoring under the same level of environmental noises, compared with some existing methods.     

Audio fingerprint analysis for speech processing using deep learning method

International Journal of Speech Technology - We are generating truly mind-boggling amounts of audio data on a daily basis simply by using the Internet. In different audio-based applications, it...     

Stock prediction using deep learning

Stock market is considered chaotic, complex, volatile and dynamic. Undoubtedly, its prediction is one of the most challenging tasks in time series forecasting. Moreover existing Artificial Neural Network (ANN) approaches fail to provide encouraging results. Meanwhile advances in machine learning have presented favourable results for speech recognition, image classification and language processing. Methods applied in digital signal processing can be applied to stock data as both are time series. Similarly, learning outcome of this paper can be applied to speech time series data. Deep learning for stock prediction has been introduced in this paper and its performance is evaluated on Google stock price multimedia data (chart) from NASDAQ. The objective of this paper is to demonstrate that deep learning can improve stock market forecasting accuracy. For this, (2D)²PCA + Deep Neural Network (DNN) method is compared with state of the art method 2-Directional 2-Dimensional Principal Component Analysis (2D)²PCA + Radial Basis Function Neural Network (RBFNN). It is found that the proposed method is performing better than the existing method RBFNN with an improved accuracy of 4.8% for Hit Rate with a window size of 20. Also the results of the proposed model are compared with the Recurrent Neural Network (RNN) and it is found that the accuracy for Hit Rate is improved by 15.6%. The correlation coefficient between the actual and predicted return for DNN is 17.1% more than RBFNN and it is 43.4% better than RNN.     

基于深度学习的智能动态防御系统

在面对日益突出的网络安全问题,现有的基于威胁特征感知的防御机制,在应对未知风险、高级持续性威胁(APT)、机器流量中,暴露其不足之处,论文提出了基于深度学习的智能动态防御系统架构,提升了互联网应用网络安全威胁应对能力。     

Machining quality monitoring (MQM) in laser-assisted micro-milling of glass using cutting force signals: an image-based deep transfer learning

Journal of Intelligent Manufacturing - This research proposes a method for machining quality monitoring (MQM) in laser-assisted micro-milling (LAMM) of glass. In tool-based mechanical processing...     

Pneumonia classification using quaternion deep learning

Pneumonia is an infection in one or both the lungs because of virus or bacteria through breathing air. It inflames air sacs in lungs which fill with fluid which further leads to problems in respiration. Pneumonia is interpreted by radiologists by observing abnormality in lungs in case of fluid in Chest X-Rays. Computer Aided Detection Diagnosis (CAD) tools can assist radiologists by improving their diagnostic accuracy. Such CAD tools use neural networks which are trained on Chest X-Ray dataset to classify a Chest X-Ray into normal or infected with Pneumonia. Convolution neural networks have shown remarkable performance in object detection in an image. Quaternion Convolution neural network (QCNN) is a generalization of conventional convolution neural networks. QCNN treats all three channels (R, G, B) of color image as a single unit and it extracts better representative features and which further improves classification. In this paper, we have trained Quaternion residual network on a publicly available large Chest X-Ray dataset on Kaggle repository and obtained classification accuracy of 93.75% and F-score of .94. We have also compared our performance with other CNN architectures. We found that classification accuracy was higher with Quaternion Residual network when we compared it with a real valued Residual network.

     

A survey on deep learning and deep reinforcement learning in robotics with a tutorial on deep reinforcement learning

This article is about deep learning (DL) and deep reinforcement learning (DRL) works applied to robotics. Both tools have been shown to be successful in delivering data-driven solutions for robotics tasks, as well as providing a natural way to develop an end-to-end pipeline from the robot’s sensing to its actuation, passing through the generation of a policy to perform the given task. These frameworks have been proven to be able to deal with real-world complications such as noise in sensing, imprecise actuation, variability in the scenarios where the robot is being deployed, among others. Following that vein, and given the growing interest in DL and DRL, the present work starts by providing a brief tutorial on deep reinforcement learning, where the goal is to understand the main concepts and approaches followed in the field. Later, the article describes the main, recent, and most promising approaches of DL and DRL in robotics, with sufficient technical detail to understand the core of the works and to motivate interested readers to initiate their own research in the area. Then, to provide a comparative analysis, we present several taxonomies in which the references can be classified, according to high-level features, the task that the work addresses, the type of system, and the learning techniques used in the work. We conclude by presenting promising research directions in both DL and DRL.

     

Intelligent fingerprint quality analysis using online sequential extreme learning machine

Because the quality of fingerprints can be degraded by diverse factors, recognizing the quality of fingerprints in advance can be beneficial for improving the performance of fingerprint authentication systems. This paper proposes an effective fingerprint quality analysis approach based on the online sequential extreme learning machine (OS-ELM). The proposed method is based not only on basic fingerprint properties, but also on the physical properties of the various sensors. Instead of splitting a fingerprint image into traditional small blocks, direction-based segmentation using the Gabor filter is used. From the segmented image, a feature set which consists of four selected independent local or global features: orientation certainty, local orientation quality, consistency, and ridge distance, is extracted. The selected feature set is robust against various factors responsible for quality degradation and can satisfy the requirements of different types of capture sensors. With the contribution of the OS-ELM classifier, the extracted feature set is used to determine whether or not a fingerprint image should be accepted as an input to the recognition system. Experimental results show that the proposed method performs better in terms of accuracy and time consumed than BPNN-based and SVM-based methods. An obvious improvement to the fingerprint recognition system is achieved by adding a quality analysis system. Other comparisons to traditional methods also show that the proposed method outperforms others.     

Promoting vicarious learning of physics using deep questions with explanations

Two experiments explored the role of vicarious “self” explanations in facilitating student learning gains during computer-presented instruction. In Exp. 1, college students with low or high knowledge on Newton's laws were tested in four conditions: (a) monologue (M), (b) questions (Q), (c) explanation (E), and (d) question + explanation (Q + E). Those with low pre-experimental knowledge levels showed marginally significant yet consistently greater gains than those with high levels and condition Q + E outperformed the other three (M, Q, E). Among those with high knowledge, the Q + E presentations actually inhibited learning. In Exp. 2, high school physics students in standard and honors classes were studied during their introduction to Newton's laws. Brief (12 min) computer videos that introduced key Newtonian concepts preceded teacher presentations in seven daily sessions. Both standard and honors students who received Q + E presentations prior to regular classroom activities learned more in daily sessions than those who received either M or Q presentations. It was concluded that when key concepts are introduced in the context of deep questions along with explanations new learning was facilitated both in vicarious environments and in subsequent standard classroom activities.     

Identification using ANFIS with intelligent hybrid stable learning algorithm approaches and stability analysis of training methods

This paper proposes a novel hybrid learning algorithm with stable learning laws for Adaptive Network based Fuzzy Inference System (ANFIS) as a system identifier and studies the stability of this algorithm. The new hybrid learning algorithm is based on particle swarm optimization (PSO) for training the antecedent part and forgetting factor recursive least square (FFRLS) for training the conclusion part. Two famous training algorithms for ANFIS are the gradient descent (GD) to update antecedent part parameters and using GD or recursive least square (RLS) to update conclusion part parameters. Lyapunov stability theory is used to study the stability of the proposed algorithms. This paper, also studies the stability of PSO as an optimizer in training the identifier. Stable learning algorithms for the antecedent and consequent parts of fuzzy rules are proposed. Some constraints are obtained and simulation results are given to validate the results. It is shown that instability will not occur for the leaning rate and PSO factors in the presence of constraints. The learning rate can be calculated on-line and will provide an adaptive learning rate for the ANFIS structure. This new learning scheme employs adaptive learning rate that is determined by input–output data. Also, stable learning algorithms for two common methods are proposed based on Lyapunov stability theory and some constraints are obtained.     

Air quality prediction using CT-LSTM

Neural Computing and Applications - With the development of industry, air pollution has become a serious problem. It is very important to create an air quality prediction model with high accuracy...     

Biped dynamic walking using reinforcement learning

This paper presents some results from a study of biped dynamic walking using reinforcement learning. During this study a hardware biped robot was built, a new reinforcement learning algorithm as well as a new learning architecture were developed. The biped learned dynamic walking without any previous knowledge about its dynamic model. The self scaling reinforcement (SSR) learning algorithm was developed in order to deal with the problem of reinforcement learning in continuous action domains. The learning architecture was developed in order to solve complex control problems. It uses different modules that consist of simple controllers and small neural networks. The architecture allows for easy incorporation of new modules that represent new knowledge, or new requirements for the desired task.     

基于深度学习的虹膜人脸多特征融合识别

传统多生物特征融合识别方法中人工设计特征提取存在盲目性和差异性,特征融合存在空间不匹配或维度过高等问题,为此提出一种基于深度学习的多生物特征融合识别方法。通过卷积神经网络(convolutional neural networks,CNN)提取人脸和虹膜特征、参数化t-SNE算法特征降维和支持向量机(support vector machine,SVM)分类组合进行融合识别。实验结果表明,该融合识别方法与单一生物特征识别以及其它融合识别方法相比,鲁棒性增强,识别性能提升明显。     

Socialized healthcare service recommendation using deep learning

Socialized recommender system recommends reliable healthcare services for users. Ratings are predicted on the healthcare services by merging recommendations given by users who has social relations with the active users. However, existing works did not consider the influence of distrust between users. They recommend items only based on the trust relations between users. We therefore propose a novel deep learning-based socialized healthcare service recommender model, which recommends healthcare services with recommendations given by recommenders with both trust relations and distrust relations with the active users. The influences of recommenders, considering both the node information and the structure information, are merged via the deep learning model. Experimental results show that the proposed model outperforms the existing works on prediction accuracy and prediction coverage simultaneously, even for cold start users or users with very sparse trust relations. It is also computational less expensive.

     

The stochastic aeroelastic response analysis of helicopter rotors using deep and shallow machine learning

Neural Computing and Applications - This paper addresses the influence of manufacturing variability of a helicopter rotor blade on its aeroelastic responses. An aeroelastic analysis using finite...