Showing papers in "Neurocomputing in 2018"

TL;DR: Deep domain adaptation has emerged as a new learning technique to address the lack of massive amounts of labeled data as discussed by the authors, which leverages deep networks to learn more transferable representations by embedding domain adaptation in the pipeline of deep learning.

TL;DR: It is shown that generated medical images can be used for synthetic data augmentation, and improve the performance of CNN for medical image classification, and generalize to other medical classification applications and thus support radiologists’ efforts to improve diagnosis.

TL;DR: This study discusses several frequently-used evaluation measures for feature selection, and surveys supervised, unsupervised, and semi-supervised feature selection methods, which are widely applied in machine learning problems, such as classification and clustering.

TL;DR: An overview of recent advances on security control and attack detection of industrial CPSs is presented, and robustness, security and resilience as well as stability are discussed to govern the capability of weakening various attacks.

TL;DR: The Python package tsfresh (Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests) accelerates this process by combining 63 time series characterization methods, which by default compute a total of 794 time series features, with feature selection on basis automatically configured hypothesis tests.

TL;DR: This paper aims to propose utilizing vanilla LSTM neural networks to get good RUL prediction accuracy which makes the most of long short-term memory ability, in the cases of complicated operations, working conditions, model degradations and strong noises.

TL;DR: This work improves the state-of-the-art Faster RCNN framework by combining a number of strategies, including feature concatenation, hard negative mining, multi-scale training, model pre-training, and proper calibration of key parameters.

TL;DR: This paper shows how to modify the backpropagation algorithm to compute the partial derivatives of the network output with respect to the space variables which is needed to approximate the differential operator.

TL;DR: A novel framework for facial expression recognition to automatically distinguish the expressions with high accuracy is presented and a high recognition accuracy is achieved, which successfully demonstrates the feasibility and effectiveness of the approach.

TL;DR: The results indicate that the learned features of NSAE are meaningful and dissimilar, and LCN helps to produce shift-invariant features and recognizes mechanical health conditions effectively, and the superiority of the proposed NSAE-LCN is verified.

TL;DR: The proposed framework generalizes adversarial training, as well as previous approaches for increasing local stability of ANNs, and increases the robustness of the network to existing adversarial examples, while making it harder to generate new ones.

TL;DR: This paper objectively reviews the advantages and disadvantages of N NRW model, tries to reveal the essence of NNRW, and provides some useful guidelines for users to choose a mechanism to train a feed-forward neural network.

TL;DR: In this survey paper, vision-based pedestrian detection systems are analysed based on their field of application, acquisition technology, computer vision techniques and classification strategies, and the reported results highlight the importance of testing pedestrians detection systems on different datasets to evaluate the robustness of the computed groups of features used as input to classifiers.

TL;DR: Experimental results show that the proposed fault classification algorithm achieves high diagnosis accuracy for different working conditions of rolling bearing and outperforms some traditional methods both mentioned in this paper and published in other literature.

TL;DR: This paper presents an enhanced CNN-based approach that requires only two measurement sets regardless of the size of the structure and successfully estimated the actual amount of damage for the nine damage scenarios of the benchmark study.

TL;DR: A novel approach that is based on Long Short-Term Memory (LSTM) is proposed that obtains higher accuracy in traffic flow prediction compared with other approaches.

TL;DR: A survey on recent advances in distributed cooperative control under a sampled-data setting, with special emphasis on the published results since 2011, and several challenging issues for future research are proposed.

TL;DR: This work analyzes the key properties of eight popular incremental methods representing different algorithm classes and evaluates them with regards to their on-line classification error as well as to their behavior in the limit, facilitating the choice of the best method for a given application.

TL;DR: The experimental results show that the developed SDAE-GAN method for planetary gearbox has good anti-noise ability and achieve better fault diagnosis performance in the case of small samples.

TL;DR: A novel retinal vessel segmentation method of the fundus images based on convolutional neural network (CNN) and fully connected conditional random fields (CRFs) which allows for detection of more tiny blood vessels and more precise locating of the edges.

TL;DR: A new neural network model (SR-LSTM) with two hidden layers that outperform the state-of-the-art models on three publicly available document-level review datasets and an approach to improve it which first clean datasets and remove sentences with less emotional polarity in datasets to have a better input for the model.

TL;DR: A framework is proposed for the diagnosis of AD, which consists of MRI images preprocessing, feature extraction, principal component analysis, and the support vector machine (SVM) model, and a new switching delayed particle swarm optimization (SDPSO) algorithm is proposed to optimize the SVM parameters.

TL;DR: A comprehensive survey of facial feature point detection with the assistance of abundant manually labeled images is presented in this article, where the authors categorize existing methods into two primary categories according to whether there is the need of a parametric shape model: Parametric Shape Model-based methods and Nonparametric Shape Models-Based methods.

TL;DR: FP-BNN, a binarized neural network (BNN) for FPGAs, is presented, which drastically cuts down the hardware consumption while maintaining acceptable accuracy, and an inference performance of Tera opartions per second with acceptable accuracy loss is obtained.

TL;DR: The problem foundation of manipulator control and the theoretical ideas on using neural network to solve this problem are analyzed and then the latest progresses on this topic in recent years are described and reviewed in detail.

TL;DR: An overview of recent developments in each step of the Lyapunov–Krasovskii functional method to derive a global asymptotic stability criterion is provided to guide the future research.

TL;DR: The experimental results of this study suggest the proposed deep distance metric learning method offers a new and promising tool for intelligent fault diagnosis of rolling bearings.

TL;DR: A convolutional neural network based HI construction method considering trend burr is proposed, which aims to automatically construct HIs and achieves better results in terms of trendability, monotonicity and scale similarity.

TL;DR: A feature selection method based on correlation analysis and Fisher is proposed, which can remove the redundant features that have close correlations with each other, which would make it possible to realize the interaction between speaker-independent and computer/robot in the future.

TL;DR: A hybrid structure which includes Convolutional Neural Network and Extreme Learning Machine, and integrates the synergy of two classifiers to deal with age and gender classification is introduced.