Dynamic Convolutional Neural Network Research Articles

Sign Language Recognition Using Wearable Electronics: Implementing k-Nearest Neighbors with Dynamic Time Warping and Convolutional Neural Network Algorithms.

We propose a sign language recognition system based on wearable electronics and two different classification algorithms. The wearable electronics were made of a sensory glove and inertial measurement units to gather fingers, wrist, and arm/forearm movements. The classifiers were k-Nearest Neighbors with Dynamic Time Warping (that is a non-parametric method) and Convolutional Neural Networks (that is a parametric method). Ten sign-words were considered from the Italian Sign Language: cose, grazie, maestra, together with words with international meaning such as google, internet, jogging, pizza, television, twitter, and ciao. The signs were repeated one-hundred times each by seven people, five male and two females, aged 29–54 y ± 10.34 (SD). The adopted classifiers performed with an accuracy of 96.6% ± 3.4 (SD) for the k-Nearest Neighbors plus the Dynamic Time Warping and of 98.0% ± 2.0 (SD) for the Convolutional Neural Networks. Our system was made of wearable electronics among the most complete ones, and the classifiers top performed in comparison with other relevant works reported in the literature.

Jet tagging via particle clouds

How to represent a jet is at the core of machine learning on jet physics. Inspired by the notion of point clouds, we propose a new approach that considers a jet as an unordered set of its constituent particles, effectively a "particle cloud". Such a particle cloud representation of jets is efficient in incorporating raw information of jets and also explicitly respects the permutation symmetry. Based on the particle cloud representation, we propose ParticleNet, a customized neural network architecture using Dynamic Graph Convolutional Neural Network for jet tagging problems. The ParticleNet architecture achieves state-of-the-art performance on two representative jet tagging benchmarks and is improved significantly over existing methods.

Point Cloud Semantic Segmentation Using a Deep Learning Framework for Cultural Heritage

In the Digital Cultural Heritage (DCH) domain, the semantic segmentation of 3D Point Clouds with Deep Learning (DL) techniques can help to recognize historical architectural elements, at an adequate level of detail, and thus speed up the process of modeling of historical buildings for developing BIM models from survey data, referred to as HBIM (Historical Building Information Modeling). In this paper, we propose a DL framework for Point Cloud segmentation, which employs an improved DGCNN (Dynamic Graph Convolutional Neural Network) by adding meaningful features such as normal and colour. The approach has been applied to a newly collected DCH Dataset which is publicy available: ArCH (Architectural Cultural Heritage) Dataset. This dataset comprises 11 labeled points clouds, derived from the union of several single scans or from the integration of the latter with photogrammetric surveys. The involved scenes are both indoor and outdoor, with churches, chapels, cloisters, porticoes and loggias covered by a variety of vaults and beared by many different types of columns. They belong to different historical periods and different styles, in order to make the dataset the least possible uniform and homogeneous (in the repetition of the architectural elements) and the results as general as possible. The experiments yield high accuracy, demonstrating the effectiveness and suitability of the proposed approach.

Traffic Demand Prediction Based on Dynamic Transition Convolutional Neural Network

Precise traffic demand prediction could help government and enterprises make better management and operation decisions by providing them with data-driven insights. However, it is a nontrivial effort to design an effective traffic demand prediction method due to the spatial and temporal characteristics of traffic demand distributions, dynamics of human mobility, and impacts of multiple environmental factors. To handle these problems, a Dynamic Transition Convolutional Neural Network (DTCNN) is proposed for the purpose of precise traffic demand prediction. Particularly, a transition network is first constructed according to the citiwide historical departure and arrival records, where the nodes are virtual stations discovered by a density-peak based clustering algorithm and the edges of two nodes correspond to transition flows of two stations. Then, a dynamic transition convolution unit is designed to model the spatial distributions of the traffic demands, and to capture the evolution of the demand dynamics. Last, a unifying learning framework is provided to incorporate the spatiotemporal states of the traffic demands with environmental factors. Experiments have been conducted on NYC taxi and bike-sharing data, and the results validate the effectiveness of the proposed method.

Spatial temporal incidence dynamic graph neural networks for traffic flow forecasting

Accurate and real-time traffic passenger flows forecasting at transportation hubs, such as subway/bus stations, is a practical application and of great significance for urban traffic planning, control, guidance, etc. Recently deep learning based methods are promised to learn the spatial-temporal features from high non-linearity and complexity of traffic flows. However, it is still very challenging to handle so much complex factors including the urban transportation network topological structures and the laws of traffic flows with spatial and temporal dependencies. Considering both the static hybrid urban transportation network structures and dynamic spatial-temporal relationships among stations from historical traffic passenger flows, a more effective and fine-grained spatial-temporal features learning framework is necessary. In this paper, we propose a novel spatial-temporal incidence dynamic graph neural networks framework for urban traffic passenger flows prediction. We first model dynamic traffic station relationships over time as spatial-temporal incidence dynamic graph structures based on historically traffic passenger flows. Then we design a novel dynamic graph recurrent convolutional neural network, namely Dynamic-GRCNN, to learn the spatial-temporal features representation for urban transportation network topological structures and transportation hubs. To fully utilize the historical passenger flows, we sample the short-term, medium-term and long-term historical traffic data in training, which can capture the periodicity and trend of the traffic passenger flows at different stations. We conduct extensive experiments on different types of traffic passenger flows datasets including subway, taxi and bus flows in Beijing. The results show that the proposed Dynamic-GRCNN effectively captures comprehensive spatial-temporal correlations significantly and outperforms both traditional and deep learning based urban traffic passenger flows prediction methods.

DEM Extraction from ALS Point Clouds in Forest Areas via Graph Convolution Network

It is difficult to extract a digital elevation model (DEM) from an airborne laser scanning (ALS) point cloud in a forest area because of the irregular and uneven distribution of ground and vegetation points. Machine learning, especially deep learning methods, has shown powerful feature extraction in accomplishing point cloud classification. However, most of the existing deep learning frameworks, such as PointNet, dynamic graph convolutional neural network (DGCNN), and SparseConvNet, cannot consider the particularity of ALS point clouds. For large-scene laser point clouds, the current data preprocessing methods are mostly based on random sampling, which is not suitable for DEM extraction tasks. In this study, we propose a novel data sampling algorithm for the data preparation of patch-based training and classification named T-Sampling. T-Sampling uses the set of the lowest points in a certain area as basic points with other points added to supplement it, which can guarantee the integrity of the terrain in the sampling area. In the learning part, we propose a new convolution model based on terrain named Tin-EdgeConv that fully considers the spatial relationship between ground and non-ground points when constructing a directed graph. We design a new network based on Tin-EdgeConv to extract local features and use PointNet architecture to extract global context information. Finally, we combine this information effectively with a designed attention fusion module. These aspects are important in achieving high classification accuracy. We evaluate the proposed method by using large-scale data from forest areas. Results show that our method is more accurate than existing algorithms.

Dynamic Multi-Scale Convolutional Neural Network for Time Series Classification

Time series classification is an essential task in many real-world application domains. As a popular deep learning network, convolutional neural networks have achieved excellent performance in time series classification tasks. The filters of the convolutional neural networks are fixed length and shared by each sample. However, each time series usually has different time scale features. Therefore, convolutional neural networks are not capable of extracting multi-scale features for each sample flexibly. In this paper, we propose dynamic multi-scale convolutional neural network to extract multi-scale feature representations existing in each time series dynamically. Specifically, we design a variable-length filters generator to produce a set of variable-length filters conditioned on the input time series. To make model differentiable, we use the learnable soft masks to control the lengths of variable-length filters. Therefore, the feature representations of different time scales can be captured through the variable-length filters. Then, the max-over-time pooling is used to select the most discriminative local patterns. Finally, the fully connected layer with softmax output is employed to calculate the final probability distribution for each class. Experiments conducted on extensive time series datasets show that our approach can improve the performance of time series classification through the learning of variable-length filters. Furthermore, we demonstrate the effectiveness of dynamically learning variable-length filters for each sample through the visualization analysis.

A Convolutional Neural Network for Point Cloud Instance Segmentation in Cluttered Scene Trained by Synthetic Data Without Color

3D Instance segmentation is a fundamental task in computer vision. Effective segmentation plays an important role in robotic tasks, augmented reality, autonomous driving, etc. With the ascendancy of convolutional neural networks in 2D image processing, the use of deep learning methods to segment 3D point clouds receives much attention. A great convergence of training loss often requires a large amount of human-annotated data, while making such a 3D dataset is time-consuming. This paper proposes a method for training convolutional neural networks to predict instance segmentation results using synthetic data. The proposed method is based on the SGPN framework. We replaced the original feature extractor with “dynamic graph convolutional neural networks” that learned how to extract local geometric features and proposed a simple and effective loss function, making the network more focused on hard examples. We experimentally proved that the proposed method significantly outperforms the state-of-the-art method in both Stanford 3D Indoor Semantics Dataset and our datasets.

An Automatic Mapping Method of Intelligent Recorder Configuration Datasets Based on Chinese Semantic Deep Learning

Mapping the Intelligent Electronic Devices (IEDs) output interface address description datasets to the intelligent recorder is the groundwork for the recorder to accurately collect IEDs' operation information. These datasets, which are also intelligent recorder configuration datasets, are included in the Substation Configuration Description (SCD) file of an intelligent substation. The mainstream mapping method is manually mapping these datasets based on output interface Chinese description texts. When the number of IEDs is extremely large, the manual operation often takes a huge amount of time, together with the higher labor cost. And since the Chinese description texts have a certain degree of irregularity, it also poses a problem for the automatic mapping of the datasets. Aiming at this problem, this paper proposes an automatic mapping method of IEDs configuration datasets based on a deep learning framework-Dynamic Convolutional Neural Network (DCNN). Firstly, it uses the word representation model Word2vec to vectorize words in Chinese description texts as well as their semantics relationships. Then word vectors will be imported in the DCNN, which, based on its multilayer abstract learning characteristics of typical sample features, can perform semantic law mining and automatic mapping. The configuration datasets of intelligent recorder will be automatically mapped based on the Chinese descriptions mapping result. The Practical example shows that the Chinese description texts classification method based on the Dynamic Convolutional Neural Network model has strong semantic analysis ability and high classification accuracy, which effectively improves the accuracy of automatic mapping of intelligent recorder configuration data.

SLNet: Stereo face liveness detection via dynamic disparity-maps and convolutional neural network

Current state-of-the-art dual camera-based face liveness detection methods utilize either hand-crafted features, such as disparity, or deep texture features to classify a live face and face Presentation Attack (PA). However, these approaches limit the effectiveness of classifiers, particularly deep Convolutional Neural Networks (CNN) to unknown face PA in adverse scenarios. In contrast to these approaches, in this paper, we show that supervising a deep CNN classifier by learning disparity features using the existing CNN layers improves the performance and robustness of CNN to unknown types of face PA. For this purpose, we propose to supervise a CNN classifier by introducing a disparity layer within CNN to learn the dynamic disparity-maps. Subsequently, the rest of the convolutional layers, following the disparity layer, in the CNN are supervised using the learned dynamic disparity-maps for face liveness detection. We further propose a new video-based stereo face anti-spoofing database with various face PA and different imaging qualities. Experiments on the proposed stereo face anti-spoofing database are performed using various test case scenarios. The experimental results indicate that our proposed system shows promising performance and has good generalization ability.

Dynamic Spatial-Temporal Graph Convolutional Neural Networks for Traffic Forecasting

Graph convolutional neural networks (GCNN) have become an increasingly active field of research. It models the spatial dependencies of nodes in a graph with a pre-defined Laplacian matrix based on node distances. However, in many application scenarios, spatial dependencies change over time, and the use of fixed Laplacian matrix cannot capture the change. To track the spatial dependencies among traffic data, we propose a dynamic spatio-temporal GCNN for accurate traffic forecasting. The core of our deep learning framework is the finding of the change of Laplacian matrix with a dynamic Laplacian matrix estimator. To enable timely learning with a low complexity, we creatively incorporate tensor decomposition into the deep learning framework, where real-time traffic data are decomposed into a global component that is stable and depends on long-term temporal-spatial traffic relationship and a local component that captures the traffic fluctuations. We propose a novel design to estimate the dynamic Laplacian matrix of the graph with above two components based on our theoretical derivation, and introduce our design basis. The forecasting performance is evaluated with two realtime traffic datasets. Experiment results demonstrate that our network can achieve up to 25% accuracy improvement.

Deep learning-based carotid media-adventitia and lumen-intima boundary segmentation from three-dimensional ultrasound images.

PurposeQuantification of carotid plaques has been shown to be important for assessing as well as monitoring the progression and regression of carotid atherosclerosis. Various metrics have been proposed and methods of measurements ranging from manual tracing to automated segmentations have also been investigated. Of those metrics, quantification of carotid plaques by measuring vessel‐wall‐volume (VWV) using the segmented media‐adventitia (MAB) and lumen‐intima (LIB) boundaries has been shown to be sensitive to temporal changes in carotid plaque burden. Thus, semi‐automatic MAB and LIB segmentation methods are required to help generate VWV measurements with high accuracy and less user interaction.MethodsIn this paper, we propose a semiautomatic segmentation method based on deep learning to segment the MAB and LIB from carotid three‐dimensional ultrasound (3DUS) images. For the MAB segmentation, we convert the segmentation problem to a pixel‐by‐pixel classification problem. A dynamic convolutional neural network (Dynamic CNN) is proposed to classify the patches generated by sliding a window along the norm line of the initial contour where the CNN model is fine‐tuned dynamically in each test task. The LIB is segmented by applying a region‐of‐interest of carotid images to a U‐Net model, which allows the network to be trained end‐to‐end for pixel‐wise classification.ResultsA total of 144 3DUS images were used in this development, and a threefold cross‐validation technique was used for evaluation of the proposed algorithm. The proposed algorithm‐generated accuracy was significantly higher than the previous methods but with less user interactions. Comparing the algorithm segmentation results with manual segmentations by an expert showed that the average Dice similarity coefficients (DSC) were 96.46 ± 2.22% and 92.84 ± 4.46% for the MAB and LIB, respectively, while only an average of 34 s (vs 1.13, 2.8 and 4.4 min in previous methods) was required to segment a 3DUS image. The interobserver experiment indicated that the DSC was 96.14 ± 1.87% between algorithm‐generated MAB contours of two observers' initialization.ConclusionsOur results showed that the proposed carotid plaque segmentation method obtains high accuracy and repeatability with less user interactions, suggesting that the method could be used in clinical practice to measure VWV and monitor the progression and regression of carotid plaques.

Involve Convolutional-NN to Generate Item Latent Factor Consider Product Genre to Increase Robustness in Product Sparse Data for E-commerce Recommendation

Online shopping also popular named e-commerce business need a computer machine to provide product information for customer or buyer candidate. Relevant information served by ecommerce system engine famous dubbed recommender system. It will impact seriously in increasing of marketing target achievement. The character of information in ecommerce have to be specific, personalized, relevant and fit according to customer profiling. There are four kind of recommender system to provide ecommerce recommender system, however only one model that most successful to applied in real ecommerce industry that namely collaborative filtering. These approaches rely on rating as basic calculation to generate product recommendation. However, just a little number of rating that given by customer reference to several convince datasets. The problem causes of sparse product rating, it will bring the impact to product recommendation accuracy. Sometime, in extreme condition impossible to generate product recommendation. Some work efforts have been developing to tackle lack of rating, one of them is considering to involving text sentences document such as text genre, product review, abstract, product description, synopsis, etc. All of material text sentences useful as raw component to predict the product rating. Reference previous work method aims extract text sentences document such as product review to become rating value based on bag of word and word order, sometimes they have got the mis in deeper understanding of text sentences description about product. Therefore, it influenced the result of predict the rating was inaccurate. In this research, author proposed novel method enhance variant of convolutional neural network dubbed dynamic convolutional neural network to improve scalability and increase deeper understanding to increase accuracy level. Based on our experiment, our model outperforms over existing state of the art in previous work in extracting text sentences product description based on evaluation approach uses RMSE.

Deep Learning for Sensor-Based Rehabilitation Exercise Recognition and Evaluation.

In this paper, a multipath convolutional neural network (MP-CNN) is proposed for rehabilitation exercise recognition using sensor data. It consists of two novel components: a dynamic convolutional neural network (D-CNN) and a state transition probability CNN (S-CNN). In the D-CNN, Gaussian mixture models (GMMs) are exploited to capture the distribution of sensor data for the body movements of the physical rehabilitation exercises. Then, the input signals and the GMMs are screened into different segments. These form multiple paths in the CNN. The S-CNN uses a modified Lempel–Ziv–Welch (LZW) algorithm to extract the transition probabilities of hidden states as discriminate features of different movements. Then, the D-CNN and the S-CNN are combined to build the MP-CNN. To evaluate the rehabilitation exercise, a special evaluation matrix is proposed along with the deep learning classifier to learn the general feature representation for each class of rehabilitation exercise at different levels. Then, for any rehabilitation exercise, it can be classified by the deep learning model and compared to the learned best features. The distance to the best feature is used as the score for the evaluation. We demonstrate our method with our collected dataset and several activity recognition datasets. The classification results are superior when compared to those obtained using other deep learning models, and the evaluation scores are effective for practical applications.

Multi-sensor data fusion for sign language recognition based on dynamic Bayesian network and convolutional neural network

A new multi-sensor fusion framework is proposed, which is based on the Convolutional Neural Network (CNN) and the Dynamic Bayesian Network (DBN) for Sign Language Recognition (SLR). In this framework, a Microsoft Kinect, which is a low-cost RGB-D sensor, is used as tools of the Human-Computer-Interaction (HCI). In our method, at first, the color and depth videos are collected using the Kinect, the next, all image sequences features are extracted out using the CNN. The color and depth feature sequences are input into the DBN as observation data. Based on graph model fusion, the maximum recognition rate of dynamic isolated sign language is calculated. The proposed the DBN + CNN SLR framework is tested in our dataset, the highest recognition rate can up to 99.40%. The test results show that our approach is effective.

Dynamic convolutional neural network for eliminating item sparse data on recommender system

Several efforts have been conducted to handle sparse product rating in e-commerce recommender system. One of them is the inclusion of texts such as product review, abstract, product description, and synopsis. Later, it converted to become rating value. Previous researches have tried to extract these texts based on bag of word and word order. However, this approach was given misunderstanding of text description of products. This research proposes a novel Dynamic Convolutional Neural Network (DCNN) to improve meaning accuracy of product review on a collaborative filtering recommender system. DCNN was used to eliminate item sparse data on text product review while the accuracy level was measured by Root Mean Squared Error (RMSE). The result shows that DCNN has outperformed the other previous methods.

CryptoKnight: Generating and Modelling Compiled Cryptographic Primitives

Cryptovirological augmentations present an immediate, incomparable threat. Over the last decade, the substantial proliferation of crypto-ransomware has had widespread consequences for consumers and organisations alike. Established preventive measures perform well, however, the problem has not ceased. Reverse engineering potentially malicious software is a cumbersome task due to platform eccentricities and obfuscated transmutation mechanisms, hence requiring smarter, more efficient detection strategies. The following manuscript presents a novel approach for the classification of cryptographic primitives in compiled binary executables using deep learning. The model blueprint, a Dynamic Convolutional Neural Network (DCNN), is fittingly configured to learn from variable-length control flow diagnostics output from a dynamic trace. To rival the size and variability of equivalent datasets, and to adequately train our model without risking adverse exposure, a methodology for the procedural generation of synthetic cryptographic binaries is defined, using core primitives from OpenSSL with multivariate obfuscation, to draw a vastly scalable distribution. The library, CryptoKnight, rendered an algorithmic pool of AES, RC4, Blowfish, MD5 and RSA to synthesise combinable variants which automatically fed into its core model. Converging at 96% accuracy, CryptoKnight was successfully able to classify the sample pool with minimal loss and correctly identified the algorithm in a real-world crypto-ransomware application.

Multi-level wavelet packet fusion in dynamic ensemble convolutional neural network for fault diagnosis

Due to the complicated structure and varying operating conditions of machinery in various applications, intelligent identification of the health state based on the vibration data is still a great challenge in fault diagnosis. In this paper, a variant of the convolutional neural network, named dynamic ensemble convolutional neural network was proposed for fault diagnosis by intelligent fusion of the multi-level wavelet packet. First, wavelet packet transform was employed to construct multi-level wavelet coefficients matrixes for representing the nonstationary vibration signal comprehensively. Then, several paralleled convolutional neural networks with shared parameters were built, not only to learn the multi-level fault features automatically, but also to restrain the overfitting of the deep learning partially. At last, a dynamic ensemble layer was applied to fuse multi-level wavelet packet by assigning weights dynamically. The validation on two experimental datasets of the planetary gearbox under varying speed demonstrated that the developed method can fuse the fault features in multi-level wavelet packet thoroughly, and improve the effectiveness and robustness for fault diagnosis of gearbox under whether the sufficient or limited fault data conditions.

Sentiment Analysis of Movie Opinion in Twitter Using Dynamic Convolutional Neural Network Algorithm

Movie has unique characteristics. When someone writes an opinions about a movie, not only the story in the movie itself is written, but also the people involved in the movie are also written. Opinion ordinary movie written in social media primarily twitter.To get a tendency of opinion on the movie, whether opinion is likely positive, negative or neutral, it takes a sentiment analysis. This study aims to classify the sentiment is positive, negative and neutral from opinions Indonesian language movie and look for the accuracy, precission, recall and f-meausre of the method used is Dynamic Convolutional Neural Network. The test results on a system that is built to show that Dynamic Convolutional Neural Network algorithm provides accuracy results better than Naive Bayes method, the value of accuracy of 80,99%, the value of precission 81,00%, recall 81,00%, f-measure 79,00% while the value of the resulting accuracy Naive Bayes amounted to 76,21%, precission 78,00%, recall 76,00%, f-measure 75,00%.

Dynamic Convolutional Neural Network For Image Super-resolution

<p>Single image super-resolution (SISR) is a technique that reconstructs high resolution image from single low resolution image. Dynamic Convolutional Neural Network (DCNN) is used here for the reconstruction of high resolution image from single low resolution image. It takes low resolution image as input and produce high resolution image as output for dynamic up-scaling factor 2, 3, and 4. The dynamic convolutional neural network directly learns an end-to-end mapping between low resolution and high resolution images. The CNN trained simultaneously with images up-scaled by factors 2, 3, and 4 to make it dynamic. The system is then tested for the input images with up-scaling factors 2, 3 and 4. The dynamically trained CNN performs well for all three up-scaling factors. The performance of network is measured by PSNR, WPSNR, SSIM, MSSSIM, and also by perceptual.</p><p><strong>Journal of Advanced College of Engineering and Management,</strong> Vol. 3, 2017, Page: 1-10</p>