Text classification is a popular research topic in data mining. Many classification methods have been proposed. Feature selection is an important technique for text classification since it is effective in reducing dimensionality, removing irrelevant data, increasing learning accuracy, and improving result comprehensibility. In recent years, data have become increasingly larger in both the number of instances and the number of features in many applications. As a result, classical feature selection methods do not work well in processing large-scale dataset due to the expensive computational cost. To address this issue, in this paper, a parallel feature selection method based on MapReduce is proposed. Specifically, mutual information based on Renyi entropy is used to measure the relationship between feature variables and class variables. Maximum mutual information theory is then employed to choose the most informative combination of feature variables. We implemented the selection process based on MapReduce, which is efficient and scalable for large-scale problems. At last, a practical example well demonstrates the efficiency of the proposed method.
相似文献The prediction of stock price movement direction is significant in financial circles and academic. Stock price contains complex, incomplete, and fuzzy information which makes it an extremely difficult task to predict its development trend. Predicting and analysing financial data is a nonlinear, time-dependent problem. With rapid development in machine learning and deep learning, this task can be performed more effectively by a purposely designed network. This paper aims to improve prediction accuracy and minimizing forecasting error loss through deep learning architecture by using Generative Adversarial Networks. It was proposed a generic model consisting of Phase-space Reconstruction (PSR) method for reconstructing price series and Generative Adversarial Network (GAN) which is a combination of two neural networks which are Long Short-Term Memory (LSTM) as Generative model and Convolutional Neural Network (CNN) as Discriminative model for adversarial training to forecast the stock market. LSTM will generate new instances based on historical basic indicators information and then CNN will estimate whether the data is predicted by LSTM or is real. It was found that the Generative Adversarial Network (GAN) has performed well on the enhanced root mean square error to LSTM, as it was 4.35% more accurate in predicting the direction and reduced processing time and RMSE by 78 s and 0.029, respectively. This study provides a better result in the accuracy of the stock index. It seems that the proposed system concentrates on minimizing the root mean square error and processing time and improving the direction prediction accuracy, and provides a better result in the accuracy of the stock index.
相似文献As a highlighting research topic in the multimedia area, cross-media retrieval aims to capture the complex correlations among multiple media types. Learning better shared representation and distance metric for multimedia data is important to boost the cross-media retrieval. Motivated by the strong ability of deep neural network in feature representation and comparison functions learning, we propose the Unified Network for Cross-media Similarity Metric (UNCSM) to associate cross-media shared representation learning with distance metric in a unified framework. First, we design a two-pathway deep network pretrained with contrastive loss, and employ double triplet similarity loss for fine-tuning to learn the shared representation for each media type by modeling the relative semantic similarity. Second, the metric network is designed for effectively calculating the cross-media similarity of the shared representation, by modeling the pairwise similar and dissimilar constraints. Compared to the existing methods which mostly ignore the dissimilar constraints and only use sample distance metric as Euclidean distance separately, our UNCSM approach unifies the representation learning and distance metric to preserve the relative similarity as well as embrace more complex similarity functions for further improving the cross-media retrieval accuracy. The experimental results show that our UNCSM approach outperforms 8 state-of-the-art methods on 4 widely-used cross-media datasets.
相似文献Multi-atlas segmentation is widely accepted as an essential image segmentation approach. Through leveraging on the information from the atlases instead of utilizing the model-based segmentation techniques, the multi-atlas segmentation could significantly enhance the accuracy of segmentation. However, label fusion, which plays an important role for multi-atlas segmentation still remains the primary challenge. Bearing this in mind, a deep learning-based approach is presented through integrating feature extraction and label fusion. The proposed deep learning architecture consists of two independent channels composing of continuous convolutional layers. To evaluate the performance our approach, we conducted comparison experiments between state-of-the-art techniques and the proposed approach on publicly available datasets. Experimental results demonstrate that the accuracy of the proposed approach outperforms state-of-the-art techniques both in efficiency and effectiveness.
相似文献With the exponential growth of user-generated content, policies and guidelines are not always enforced in social media, resulting in the prevalence of deviant content violating policies and guidelines. The adverse effects of deviant content are devastating and far-reaching. However, the detection of deviant content from sparse and imbalanced textual data is challenging, as a large number of stakeholders are involved with different stands and the subtle linguistic cues are highly dependent on complex context. To address this problem, we propose a multi-view attention-based deep learning system, which combines random subspace and binary particle swarm optimization (RS-BPSO) to distill content of interest (candidates) from imbalanced data, and applies the context and view attention mechanisms in convolutional neural network (dubbed as SSCNN) for the extraction of structural and semantic features. We evaluate the proposed approach on a large-scale dataset collected from Facebook, and find that RS-BPSO is able to detect whether the content is associated with marijuana with an accuracy of 87.55%, and SSCNN outperforms baselines with an accuracy of 94.50%.
相似文献Fault diagnosis plays an important role in actual production activities. As large amounts of data can be collected efficiently and economically, data-driven methods based on deep learning have achieved remarkable results of fault diagnosis of complex systems due to their superiority in feature extraction. However, existing techniques rarely consider time delay of occurrence of faults, which affects the performance of fault diagnosis. In this paper, by synthetically considering feature extraction and time delay of occurrence of faults, we propose a novel fault diagnosis method that consists of two parts, namely, sliding window processing and CNN-LSTM model based on a combination of Convolutional Neural Network (CNN) and Long Short-Term Memory Network (LSTM). Firstly, samples obtained from multivariate time series by the sliding window processing integrates feature information and time delay information. Then, the obtained samples are fed into the proposed CNN-LSTM model including CNN layers and LSTM layers. The CNN layers perform feature learning without relying on prior knowledge. Time delay information is captured with the use of the LSTM layers. The fault diagnosis of the Tennessee Eastman chemical process is addressed, and it is verified that the predictive accuracy and noise sensitivity of fault diagnosis can be greatly improved when the proposed method is applied. Comparisons with five existing fault diagnosis methods show the superiority of the proposed method.
相似文献Semantic segmentation has a wide array of applications such as scene understanding, autonomous driving, and robot manipulation tasks. While existing segmentation models have achieved good performance using bottom-up deep neural processing, this paper describes a novel deep learning architecture that integrates top-down and bottom-up processing. The resulting model achieves higher accuracy at a relatively low computational cost. In the proposed model, higher-level top-down information is transmitted to the lower layers through recurrent connections in an encoder and a decoder, and the recurrent connection weights are trained using backpropagation. Experiments on several benchmark datasets demonstrate that this use of top-down information improves the mean intersection over union by more than 3% compared with a state-of-the-art bottom-up only network using the CamVid, SUN-RGBD and PASCAL VOC 2012 benchmark datasets. Additionally, the proposed model is successfully applied to a dataset designed for robotic grasping tasks.
相似文献The concerns on visual privacy have been increasingly raised along with the dramatic growth in image and video capture and sharing. Meanwhile, with the recent breakthrough in deep learning technologies, visual data can now be easily gathered and processed to infer sensitive information. Therefore, visual privacy in the context of deep learning is now an important and challenging topic. However, there has been no systematic study on this topic to date. In this survey, we discuss algorithms of visual privacy attacks and the corresponding defense mechanisms in deep learning. We analyze the privacy issues in both visual data and visual deep learning systems. We show that deep learning can be used as a powerful privacy attack tool as well as preservation techniques with great potential. We also point out the possible direction and suggestions for future work. By thoroughly investigating the relationship of visual privacy and deep learning, this article sheds insights on incorporating privacy requirements in the deep learning era.
相似文献Large-scale high-resolution three-dimensional (3D) maps play a vital role in the development of smart cities. In this work, a novel deep learning-based multi-view-stereo method is proposed for reconstructing the 3D maps in large-scale urban environments by exploiting a monocular camera. Compared with other existing works, the proposed method can perform 3D depth estimation more efficiently in terms of computational complexity and graphics processing unit memory usage. As a result, the proposed method can practically perform depth estimation for each pixel before generating 3D maps for even large-scale scenes. Extensive experiments on the well-known DTU dataset and real-life data collected on our campus confirm the good performance of the proposed method.
相似文献Robust road detection is a key challenge in safe autonomous driving. Recently, with the rapid development of 3D sensors, more and more researchers are trying to fuse information across different sensors to improve the performance of road detection. Although many successful works have been achieved in this field, methods for data fusion under deep learning framework is still an open problem. In this paper, we propose a Siamese deep neural network based on FCN-8s to detect road region. Our method uses data collected from a monocular color camera and a Velodyne-64 LiDAR sensor. We project the LiDAR point clouds onto the image plane to generate LiDAR images and feed them into one of the branches of the network. The RGB images are fed into another branch of our proposed network. The feature maps that these two branches extract in multiple scales are fused before each pooling layer, via padding additional fusion layers. Extensive experimental results on public dataset KITTI ROAD demonstrate the effectiveness of our proposed approach.
相似文献