Search

Deep neural networks are extensively used in text mining and Natural Language Processing is to enable computers to understand, analyze, and generate natural language data, such as text or speech, but semantic resources, such as taxonomies and ontologies, are not fully included in deep learning. In this paper, we use Deep Convolutional Neural Network (Deep CNN) to classify research papers using the Computer Science Ontology, an ontology of research areas in the field of computer science. It takes as input the abstract and keywords of a particular research paper and returns the relevant research topic. To evaluate our ontology, we used a gold standard dataset that includes research articles. To further improve text classification results, we propose to design a Deep CNN model. We then used ontology matching to reduce the classes and get better results. Experimental results show that the proposed approach outperforms the one with the highest precision, recall, and F1-score. [ABSTRACT FROM AUTHOR]

Nonconvex penalties are utilized for regularization in high-dimensional statistical learning algorithms primarily because they yield unbiased or nearly unbiased estimators for the parameters in the model. Nonconvex penalties existing in the literature such as SCAD, MCP, Laplace and arctan have a singularity at origin which makes them useful also for variable selection. However, in several high-dimensional frameworks such as deep learning, variable selection is less of a concern. In this paper, we present a nonconvex penalty which is smooth at origin. The paper includes asymptotic results for ordinary least squares estimators regularized with the new penalty function, showing asymptotic bias that vanishes exponentially fast. We also conducted simulations to better understand the finite sample properties and conducted an empirical study employing deep neural network architecture on three datasets and convolutional neural network on four datasets. The empirical study based on artificial neural networks showed better performance for the new regularization approach in five out of the seven datasets. [ABSTRACT FROM AUTHOR]

Hurricanes are tropical storms that cause immense damage to human life and property. Rapid assessment of damage caused by hurricanes is extremely important for the first responders. But this process is usually slow, expensive, labor intensive and prone to errors. The advancements in remote sensing and computer vision help in observing Earth at a different scale. In this paper, a new Convolutional Neural Network model has been designed with the help of satellite images captured from the areas affected by hurricanes. The model will be able to assess the damage by detecting damaged and undamaged buildings based upon which the relief aid can be provided to the affected people on an immediate basis. The model is composed of five convolutional layers, five pooling layers, one flattening layer, one dropout layer and two dense layers. Hurricane Harvey dataset consisting of 23,000 images of size 128 × 128 pixels has been used in this paper. The proposed model is simulated on 5750 test images at a learning rate of 0.00001 and 30 epochs with the Adam optimizer obtaining an accuracy of 0.95 and precision of 0.97. The proposed model will help the emergency responders to determine whether there has been damage or not due to the hurricane and also help those to provide relief aid to the affected people. [ABSTRACT FROM AUTHOR]

The explosive growth of geospatial data is increasing requirements for automatic and efficient data learning abilities. Many deep learning methods have been widely applied for geospatial data understanding tasks, such as road networks and geospatial object detection. However, the demands for more accurate learning of high-level features require the use of deeper neural networks. To further improve the learning efficiency of deep neural networks, in this paper, we propose an improved convolutional neural network named EDense. First, we use its dense connectivity to integrate a CNN with an extreme learning machine. Then, we expand the kernels in the convolutional layers to increase the width of the network model. Furthermore, we propose one-feature EDense (OF-EDense), which is a simplified version of EDense, to fit conditions in which the number of parameters is strictly limited. Finally, the experimental results fully demonstrate the strong learning ability and high learning efficiency of EDense. [ABSTRACT FROM AUTHOR]

Plant diseases are the major factor behind production loss in agriculture. The traditional manual methods for disease detection in plants involve expert knowledge that may be biased. The modern computing techniques and image processing can assist non-experts in plant disease management. Recently, deep learning techniques have observed remarkable success in image-based health assessment of plants. In this paper, the state-of-the-art pre-trained convolutional neural network (CNN) models are fine-tuned to detect and diagnose the diseases in apple crop using digital images. The experiments are performed on a publicly available dataset PlantVillage. The dataset consists of three classes of apple diseases including Scab, Black Rot, and Cedar Rust, and one class of Healthy leaves. The experimental results on ten well-known CNN models DenseNet201, DenseNet169, InceptionV3, InceptionResNetV2, MobileNet, MobileNetV2, ResNet50, VGG16, VGG19, and Xception showed that deep learning techniques can accurately discriminate the apple diseases. DenseNet201 outperformed the other models with an accuracy of 98.75%. The high accuracy shows that CNN-based methods could be a useful alternative to the conventional methods. [ABSTRACT FROM AUTHOR]

Diabetic Retinopathy (DR), one of the most progressive sight-threatening diseases caused by the long-term diabetic condition, can lead to vision impairment and blindness later. Early diagnosis and timely treatment help control and avert DR from its progression. However, manual grading is exceptionally challenging and arduous due to the complex anatomical features in the retina. Therefore, developing an automated diagnostic method for screening DR is obligatory. This paper proposes a deep learning-enabled optimized feature selection approach to classify the stage of DR severity in the fundus image. At first, a pre-processing phase eradicates the noise and improves the contrast in the retinal fundus image. Then, blood vessel segmentation is performed using the Coherence Enhancing Energy Based Regularized Level Set Evolution method in the green channel fundus image. Subsequently, the optic disk is segmented with Canny Anisotropic Diffusion filter and morphological transformations. Next, the candidate lesion region is detected using an Attention-based Fusion Network (AFU-Net). Then, shape and texture features are extracted, and then, the optimal subset of features is selected using the Improved Harris Hawk Optimization algorithm. Finally, a deep Convolutional Neural Network classifies the DR stages, and the model weight is updated using the same algorithm. The proposed method achieved superior performance in two benchmark public datasets compared with the existing state-of-the-art methods using F1-score, accuracy, sensitivity, and specificity measures. [ABSTRACT FROM AUTHOR]

Smart cities are shifting the presence of people from physical world to cyber world (cyberspace). Along with the facilities for societies, the troubles of physical world, such as bullying, aggression and hate speech, are also taking their presence emphatically in cyberspace. This paper aims to dig the posts of social media to identify the bullying comments containing text as well as image. In this paper, we have proposed a unified representation of text and image together to eliminate the need for separate learning modules for image and text. A single-layer Convolutional Neural Network model is used with a unified representation. The major findings of this research are that the text represented as image is a better model to encode the information. We also found that single-layer Convolutional Neural Network is giving better results with two-dimensional representation. In the current scenario, we have used three layers of text and three layers of a colour image to represent the input that gives a recall of 74% of the bullying class with one layer of Convolutional Neural Network. [ABSTRACT FROM AUTHOR]

This paper introduces a novel deep learning approach for generating fine resolution structures that preserve all the information from the topology optimization (TO). The proposed approach utilizes neural networks (NNs) that map the desired engineering properties to seed for determining optimized structure. The main novelty of this framework is the utilization of parameters such as density and nodal deflections to predict optimized topologies for a wide range of design space. In this research, a three-stage NN framework is employed, wherein the first stage is a feedforward deep neural network. The second stage uses a convolutional neural network (CNN), and the final stage is the post-processing of results obtained from CNN. The first stage maps input design variables vector to output density distribution image. The image output of the first stage and design variables vector inputted to the first network serve as inputs to the second stage, which outputs optimized structure. Finally, post-processing of this optimized structure is done to ensure volume fraction constraint and optimal solution. These structures can be tessellated per the nodal displacement of an FEA solved larger structure. Because of this framework, the proposed approach makes TO computations faster and captures essential physics while using NNs to determine the final structure. The application of the proposed model to three-dimensional problems is also demonstrated. [ABSTRACT FROM AUTHOR]

In this paper, a novel hybrid deep learning model called DeepVisDroid has been suggested for detecting android malware samples based on hybridizing image-based features with deep learning techniques. To this end, four grayscale image datasets have been constructed by converting some files from the source of the android applications into grayscale images. Then, two types of image-based features, namely local features and global features, have been extracted from the constructed image datasets and used for training the proposed model. The bag of visual words representation has been used for constructing one feature vector from multiple local feature descriptors extracted from each image. After that, 1D-convolutional layers-based neural network model has been proposed and trained using the extracted local and global image-based features. To the best of our knowledge, this is the first time that a convolutional neural network model is trained based on this type of features and used in the android malware detection domain. Furthermore, two classical 2D-convolutional layers-based neural network models have been proposed and two well-known deep learning models have been tested in order to compare the results of the proposed DeepVisDroid model with the results of the traditional convolutional neural network models and the results of the state-of-the-art deep learning models. The results of the proposed DeepVisDroid model are very promising, where its classification accuracy reached more than 98% with very efficient run-time overhead ranging between 0.11 and 2.02 s for each sample. [ABSTRACT FROM AUTHOR]

Wear particles produced by machines in the process of wear carry valuable information including wear mechanism and wear severity. Wear particle classification based on wear particle images provides predictive analysis for wear condition of machines. A novel wear particle recognition network based on feature fusion, FFWR-Net, is proposed in this research paper for wear particle images classification. In FFWR-Net, traditional feature extraction method by image processing technique (i.e. manually feature extracting) and deep learning convolutional neural network method (i.e. automatically feature extracting) is paralleled to extract the features of wear particle image. Then the features obtained by two different methods are fused together for building a wear particle classifier. In order to verify the effectiveness of the proposed classifier, it is compared with the previous convolutional neural network models on the same wear particle dataset. The comparison results show the accuracy and effectiveness of the proposed FFWR-Net classifier is better than the previous models. [ABSTRACT FROM AUTHOR]

The successful diagnosis of the faulty signal in rolling element bearings relies on the accurate evaluation of the early fault present within the components of bearings. Because of system imperfection and interference between the data acquisition devices, the fault signal is heavily masked by noise. Hence, to extract the fault information, signal processing techniques are widely used in bearing diagnosis. Although numerous research have dedicated on finding representative features to indicate the damage of the bearing elements, the correlation between defect size and acquired vibration signal has not been properly established. In the recent few years, deep learning has been widely used in bearing diagnosis. In general, the unprocessed signal is directly input into the deep learning model and the neural network extracts useful features during the optimization process. Until now, the selection of features from signals is arbitrary which does not yield much insights into the diagnosis and prognosis. In addition, the features could contain noise information, which could possibly deteriorate diagnostic or prognostic results, while the effect of using preprocessed data has not been fully explored. In this paper, we present an innovative diagnosis model using the deep convolutional network with Bayesian optimization to diagnose the defect severity of bearings. The acquired signal is initially processed using the complementary ensemble empirical mode decomposition method to extract the frequency band containing the fault signature. An experimental based defect size estimation equation is implemented to calculate the defect size based on the signal and experimental setup. After the estimated defect size is obtained, the deep convolutional neural network is implemented to categorize the defect severity. The parameters of the network are optimized by the Bayesian algorithm. The proposed algorithm can be used for diagnosis of the health condition of various rotating machinery. [ABSTRACT FROM AUTHOR]

Automatic modulation classification plays an important role in many fields to identify the modulation type of wireless signals in order to recover signals by demodulation. In this paper, we contribute to explore the suitable architecture of deep learning method in the domain of communication signal recognition. Based on architecture analysis of the convolutional neural network, we used real signal data generated by instrument as dataset, and achieved compatible recognition accuracy of modulation classification compared with several representative structure. We state that the deeper network architecture is not suitable for the signal recognition due to its different characteristic. In addition, we also discuss the difficult of training algorithm in deep learning methods and employ the transfer learning method in order to reap the benefits, which stabilize the training process and lift the performance. Finally, we adopt the denoising autoencoder to preprocess the received data and provide the ability to resist finite perturbations of the input. It contributes to a higher recognition accuracy and it also provide a new idea to design the denoising modulation recognition model. [ABSTRACT FROM AUTHOR]