scholarly journals Multiscale Bidirectional Input Convolutional and Deep Neural Network for Human Activity Recognition

2021 ◽  
Vol 2021 ◽  
pp. 1-9
Author(s):  
Yishu Qiu ◽  
Lanliang Lin ◽  
Lvqing Yang ◽  
Dingzhao Li ◽  
Runhan Song ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Original Data ◽  
Learning Ability ◽  
Activity Data ◽  
Input Module ◽  
Single Input ◽  
Input Model ◽  
Forward Sequence ◽  
Better Than

In this paper, we proposed a multiscale and bidirectional input model based on convolutional neural network and deep neural network, named MBCDNN. In order to solve the problem of inconsistent activity segments, a multiscale input module is constructed to make up for the noise caused by filling. In order to solve the problem that single input is not enough to extract features from original data, we propose to manually design aggregation features combined with forward sequence and reverse sequence and use five cross-validation and stratified sampling to enhance the generalization ability of the model. According to the particularity of the task, we design an evaluation index combined with scene and action weight, which enriches the learning ability of the model to a great extent. In the 19 kinds of activity data based on scene+action, the accuracy and robustness are significantly improved, which is better than other mainstream traditional methods.

Computed Torque Control of a Caterpillar Robot Manipulator Using Neural Network

2016 ◽  
Vol 15 ◽  
pp. 106-118 ◽  
Author(s):  
Mehran Rahmani ◽  
Ahmad Ghanbari
Keyword(s):  
Neural Network ◽  
Trajectory Tracking ◽  
Control Method ◽  
Robot Manipulator ◽  
Setting Time ◽  
Torque Control ◽  
Learning Ability ◽  
Control Effort ◽  
Better Than ◽  
Computed Torque

This paper presents a neural computed torque controller, which employs to a Caterpillar robot manipulator. A description to exert a control method application neural network for nonlinear PD computed torque controller to a two sub-mechanisms Caterpillar robot manipulator. A nonlinear PD computed torque controller is obtained via utilizing a popular computed torque controller and using neural networks. The proposed controller has some advantages such as low control effort, high trajectory tracking and learning ability. The joint angles of two sub-mechanisms have been obtained by using the numerical simulations. The discovered figures show that the performance of the neural computed torque controller is better than a conventional computed torque controller in trajectory tracking and reduction of setting time. Finally, snapshots of gain sequences are demonstrated.

scholarly journals Tensorflow vs R: A Comparative Study of Usability

2017 ◽  
Author(s):  
Luís Dias ◽  
Rosalvo Neto
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Comparative Study ◽  
Scientific Community ◽  
Deep Neural Network ◽  
Network Algorithms ◽  
Learning Framework ◽  
Usability Tests ◽  
Usability Analysis ◽  
Better Than

Google released on November of 2015 Tensorflow, an open source machine learning framework that can be used to implement Deep Neural Network algorithms, a class of algorithms that shows great potential in solving complex problems. Considering the importance of usability in software success, this research aims to perform a usability analysis on Tensorflow and to compare it with another widely used framework, R. The evaluation was performed through usability tests with university students. The study led do indications that Tensorflow usability is equal or better than the usability of traditional frameworks used by the scientific community.

scholarly journals Image Classification: A Survey

2020 ◽  
Vol 1 (2) ◽  
pp. 1-9
Author(s):  
Ankita Singh ◽  
◽  
Pawan Singh
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Deep Learning ◽  
Image Classification ◽  
Convolutional Neural Networks ◽  
Language Processing ◽  
Classification Accuracy ◽  
Deep Neural Network ◽  
Learning Ability ◽  
Final Decision

The Classification of images is a paramount topic in artificial vision systems which have drawn a notable amount of interest over the past years. This field aims to classify an image, which is an input, based on its visual content. Currently, most people relied on hand-crafted features to describe an image in a particular way. Then, using classifiers that are learnable, such as random forest, and decision tree was applied to the extract features to come to a final decision. The problem arises when large numbers of photos are concerned. It becomes a too difficult problem to find features from them. This is one of the reasons that the deep neural network model has been introduced. Owing to the existence of Deep learning, it can become feasible to represent the hierarchical nature of features using a various number of layers and corresponding weight with them. The existing image classification methods have been gradually applied in real-world problems, but then there are various problems in its application processes, such as unsatisfactory effect and extremely low classification accuracy or then and weak adaptive ability. Models using deep learning concepts have robust learning ability, which combines the feature extraction and the process of classification into a whole which then completes an image classification task, which can improve the image classification accuracy effectively. Convolutional Neural Networks are a powerful deep neural network technique. These networks preserve the spatial structure of a problem and were built for object recognition tasks such as classifying an image into respective classes. Neural networks are much known because people are getting a state-of-the-art outcome on complex computer vision and natural language processing tasks. Convolutional neural networks have been extensively used.

scholarly journals Interactive Entertainment Image Restoration Method Based on Hopfield Neural Network

2018 ◽  
Vol 232 ◽  
pp. 01008
Author(s):  
Shuangqing lv
Keyword(s):  
Neural Network ◽  
Image Restoration ◽  
Hopfield Neural Network ◽  
Original Data ◽  
Small Scale ◽  
Interactive Entertainment ◽  
Degraded Image ◽  
Restoration Method ◽  
Traditional Image ◽  
Better Than

The traditional image restoration methods of interactive entertainment are based on the original data. This paper proposes an interactive entertainment image restoration method based on Hopfield neural network. Firstly, the nonlinear mapping relationship between the degraded image and the real image is preliminarily established through the network, and then optimized by the algorithm. Finally, the image restoration can be achieved through the network. The experiments show that it has higher feasibility and the recovery effect on small-scale blur is better than the existing method.

scholarly journals Spectral Embedded Deep Clustering

Entropy ◽  
2019 ◽  
Vol 21 (8) ◽  
pp. 795 ◽  
Author(s):  
Yuichiro Wada ◽  
Shugo Miyamoto ◽  
Takumi Nakagama ◽  
Léo Andéol ◽  
Wataru Kumagai ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Unlabeled Data ◽  
Clustering Methods ◽  
Density Region ◽  
Number Of Clusters ◽  
Data Points ◽  
High Density Region ◽  
The Given ◽  
Better Than

We propose a new clustering method based on a deep neural network. Given an unlabeled dataset and the number of clusters, our method directly groups the dataset into the given number of clusters in the original space. We use a conditional discrete probability distribution defined by a deep neural network as a statistical model. Our strategy is first to estimate the cluster labels of unlabeled data points selected from a high-density region, and then to conduct semi-supervised learning to train the model by using the estimated cluster labels and the remaining unlabeled data points. Lastly, by using the trained model, we obtain the estimated cluster labels of all given unlabeled data points. The advantage of our method is that it does not require key conditions. Existing clustering methods with deep neural networks assume that the cluster balance of a given dataset is uniform. Moreover, it also can be applied to various data domains as long as the data is expressed by a feature vector. In addition, it is observed that our method is robust against outliers. Therefore, the proposed method is expected to perform, on average, better than previous methods. We conducted numerical experiments on five commonly used datasets to confirm the effectiveness of the proposed method.

scholarly journals Stochastic Batch Augmentation with An Effective Distilled Dynamic Soft Label Regularizer

2020 ◽  
Author(s):  
Qian Li ◽  
Qingyuan Hu ◽  
Yong Qi ◽  
Saiyu Qi ◽  
Jie Ma ◽  
...  
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Data Augmentation ◽  
Original Data ◽  
Learning System ◽  
Representation Space ◽  
Original Sample ◽  
Network Training ◽  
Speed Up ◽  
The Neural Networks

Data augmentation have been intensively used in training deep neural network to improve the generalization, whether in original space (e.g., image space) or representation space. Although being successful, the connection between the synthesized data and the original data is largely ignored in training, without considering the distribution information that the synthesized samples are surrounding the original sample in training. Hence, the behavior of the network is not optimized for this. However, that behavior is crucially important for generalization, even in the adversarial setting, for the safety of the deep learning system. In this work, we propose a framework called Stochastic Batch Augmentation (SBA) to address these problems. SBA stochastically decides whether to augment at iterations controlled by the batch scheduler and in which a ''distilled'' dynamic soft label regularization is introduced by incorporating the similarity in the vicinity distribution respect to raw samples. The proposed regularization provides direct supervision by the KL-Divergence between the output soft-max distributions of original and virtual data. Our experiments on CIFAR-10, CIFAR-100, and ImageNet show that SBA can improve the generalization of the neural networks and speed up the convergence of network training.

scholarly journals Internal Crack Prediction of Continuous Casting Billet Based on Principal Component Analysis and Deep Neural Network

Metals ◽  
2021 ◽  
Vol 11 (12) ◽  
pp. 1976
Author(s):  
Leilei Zou ◽  
Jiangshan Zhang ◽  
Yanshen Han ◽  
Fanzheng Zeng ◽  
Quanhui Li ◽  
...  
Keyword(s):  
Neural Network ◽  
Principal Component Analysis ◽  
Continuous Casting ◽  
Deep Neural Network ◽  
Principal Component ◽  
Component Analysis ◽  
Learning Ability ◽  
Internal Crack ◽  
Strong Nonlinearity ◽  
Neural Network Models

The accurate prediction of internal cracks in steel billets is of great importance for the stable production of continuous casting. However, it is challenging, owing to the strong nonlinearity, and coupling among continuous casting process parameters. In this study, an internal crack prediction model based on the principal component analysis (PCA) and deep neural network (DNN) was proposed by collecting sufficient industrial data. PCA was used to reduce the dimensionality of the factors influencing the internal cracks, and the obtained principal components were used as DNN input variables. The 5-fold cross-validation results demonstrate that the prediction accuracy of the DNN model is 92.2%, which is higher than those of the decision tree (DT), extreme learning machine (ELM), and backpropagation (BP) neural network models. Moreover, the variance analysis showed that the prediction results of the DNN model were more stable. The PCA-DNN model can provide a useful reference for real production, owing to its strong learning ability and fault-tolerant ability.

scholarly journals ResPRE: high-accuracy protein contact prediction by coupling precision matrix with deep residual neural networks

2019 ◽  
Vol 35 (22) ◽  
pp. 4647-4655 ◽  
Author(s):  
Yang Li ◽  
Jun Hu ◽  
Chengxin Zhang ◽  
Dong-Jun Yu ◽  
Yang Zhang
Keyword(s):  
Neural Network ◽  
Covariance Matrix ◽  
Deep Neural Network ◽  
Learning Ability ◽  
Supplementary Information ◽  
Neural Network Training ◽  
Contact Map ◽  
Precision Matrix ◽  
Contact Prediction ◽  
Network Training

Abstract Motivation Contact-map of a protein sequence dictates the global topology of structural fold. Accurate prediction of the contact-map is thus essential to protein 3D structure prediction, which is particularly useful for the protein sequences that do not have close homology templates in the Protein Data Bank. Results We developed a new method, ResPRE, to predict residue-level protein contacts using inverse covariance matrix (or precision matrix) of multiple sequence alignments (MSAs) through deep residual convolutional neural network training. The approach was tested on a set of 158 non-homologous proteins collected from the CASP experiments and achieved an average accuracy of 50.6% in the top-L long-range contact prediction with L being the sequence length, which is 11.7% higher than the best of other state-of-the-art approaches ranging from coevolution coupling analysis to deep neural network training. Detailed data analyses show that the major advantage of ResPRE lies at the utilization of precision matrix that helps rule out transitional noises of contact-maps compared with the previously used covariance matrix. Meanwhile, the residual network with parallel shortcut layer connections increases the learning ability of deep neural network training. It was also found that appropriate collection of MSAs can further improve the accuracy of final contact-map predictions. The standalone package and online server of ResPRE are made freely available, which should bring important impact on protein structure and function modeling studies in particular for the distant- and non-homology protein targets. Availability and implementation https://zhanglab.ccmb.med.umich.edu/ResPRE and https://github.com/leeyang/ResPRE. Supplementary information Supplementary data are available at Bioinformatics online.

scholarly journals Speech enhancement methods based on binaural cue coding

2019 ◽  
Vol 2019 (1) ◽  
Author(s):  
Xianyun Wang ◽  
Changchun Bao
Keyword(s):  
Neural Network ◽  
Speech Enhancement ◽  
Speech Signal ◽  
Deep Neural Network ◽  
Experimental Results ◽  
Channel Correlation ◽  
Noisy Speech ◽  
Time Frequency ◽  
Improve Accuracy ◽  
Better Than

AbstractAccording to the encoding and decoding mechanism of binaural cue coding (BCC), in this paper, the speech and noise are considered as left channel signal and right channel signal of the BCC framework, respectively. Subsequently, the speech signal is estimated from noisy speech when the inter-channel level difference (ICLD) and inter-channel correlation (ICC) between speech and noise are given. In this paper, exact inter-channel cues and the pre-enhanced inter-channel cues are used for speech restoration. The exact inter-channel cues are extracted from clean speech and noise, and the pre-enhanced inter-channel cues are extracted from the pre-enhanced speech and estimated noise. After that, they are combined one by one to form a codebook. Once the pre-enhanced cues are extracted from noisy speech, the exact cues are estimated by a mapping between the pre-enhanced cues and a prior codebook. Next, the estimated exact cues are used to obtain a time-frequency (T-F) mask for enhancing noisy speech based on the decoding of BCC. In addition, in order to further improve accuracy of the T-F mask based on the inter-channel cues, the deep neural network (DNN)-based method is proposed to learn the mapping relationship between input features of noisy speech and the T-F masks. Experimental results show that the codebook-driven method can achieve better performance than conventional methods, and the DNN-based method performs better than the codebook-driven method.

Sign in / Sign up

Export Citation Format

Share Document