Estimating Stochastic Linear Combination of Non-linear Regressions Efficiently and Scalably
Publication date: Available online 26 February 2020Source: NeurocomputingAuthor(s): Di Wang, Xiangyu Guo, Chaowen Guan, Shi Li, Jinhui Xu (Source: Neurocomputing)
Source: Neurocomputing - February 28, 2020 Category: Neuroscience Source Type: research

Precise Iterative Closest Point Algorithm for RGB-D Data Registration with Noise and Outliers
Publication date: Available online 26 February 2020Source: NeurocomputingAuthor(s): LeXian Liang (Source: Neurocomputing)
Source: Neurocomputing - February 28, 2020 Category: Neuroscience Source Type: research

Spatial-Spectral Weighted Nuclear Norm Minimization for Hyperspectral Image Denoising
Publication date: Available online 26 February 2020Source: NeurocomputingAuthor(s): Xinjian Huang, Bo Du, Dapeng Tao, Liangpei Zhang (Source: Neurocomputing)
Source: Neurocomputing - February 28, 2020 Category: Neuroscience Source Type: research

Editorial Board
Publication date: 14 April 2020Source: Neurocomputing, Volume 385Author(s): (Source: Neurocomputing)
Source: Neurocomputing - February 28, 2020 Category: Neuroscience Source Type: research

On a granular functional link network for classification
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): Francesco Colace, Vincenzo Loia, Witold Pedrycz, Stefania Tomasiello (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Summarizing Egocentric Videos using Deep Features and Optimal Clustering
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): Abhimanyu Sahu, Ananda S. Chowdhury (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Robust IoT Time Series Classification with Data Compression and Deep Learning
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): Joseph Azar, Abdallah Makhoul, Raphaël Couturier, Jacques Demerjian (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Multilayer Deep Features with Multiple Kernel Learning for Action Recognition
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): Biyun Sheng, Jun Li, Fu Xiao, W.ou Yang (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Multi-task Learning for Aspect Term Extraction and Aspect Sentiment Classification
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): Md Shad Akhtar, Tarun Garg, Asif Ekbal (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Adaptive finite-time fuzzy control of full-state constrained high-order nonlinear systems without feasibility conditions and its application
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): You Wu, Ruiming Xie, Xue-Jun Xie (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Robust Adaptive Neuronal Controller for Exoskeletons with Sliding-Mode
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): A. Jebri, T. Madani, K. Djouani, A. Benallegue (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Structural Correlation Filters Combined with A Gaussian Particle Filter for Hierarchical Visual Tracking
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): Manna Dai, Gao Xiao, Shuying Cheng, Dadong Wang, Xiangjian He (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Adaptive Blind Deconvolution Using Generalized Cross-Validation with Generalized lp/lq Norm Regularization
Publication date: Available online 26 February 2020Source: NeurocomputingAuthor(s): Lei Chen, Quansen Sun, Fanhai Wang (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Robust Ellipse Fitting Based on Lagrange Programming Neural Network and Locally Competitive Algorithm
Publication date: Available online 26 February 2020Source: NeurocomputingAuthor(s): Zhanglei Shi, Hao Wang, Chi-Sing Leung, Hing Cheung So, Junli Liang, Kim-Fung Tsang, Anthony G. Constantinides (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Semi-supervised sparse representation classifier (S3RC) with deep features on small sample sized hyperspectral images
Publication date: Available online 26 February 2020Source: NeurocomputingAuthor(s): M. Said Aydemir, Gokhan Bilgin (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Local Preserving Logistic I-Relief for Semi-supervised Feature Selection
Publication date: Available online 26 February 2020Source: NeurocomputingAuthor(s): Baige Tang, Li Zhang (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Using a Low Correlation High Orthogonality Feature Set and Machine Learning Methods to Identify Plant Pentatricopeptide Repeat Coding Gene/Protein
Publication date: Available online 24 February 2020Source: NeurocomputingAuthor(s): Changli Feng, Quan Zou, Donghua Wang (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Global exponential stability analysis of neural networks with a time-varying delay via some state-dependent zero equations
Publication date: Available online 24 February 2020Source: NeurocomputingAuthor(s): Xiaojie Peng, Yong He, Fei Long, Min Wu (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

A new result on L2 - L∞ performance state estimation of neural networks with time-varying delay
Publication date: Available online 24 February 2020Source: NeurocomputingAuthor(s): Guoqiang Tan, Jidong Wang, Zhanshan Wang (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

LDGRNMF: LncRNA-Disease Associations Prediction based on Graph Regularized Non-Negative Matrix Factorization
Publication date: Available online 24 February 2020Source: NeurocomputingAuthor(s): Mei-Neng Wang, Zhu-Hong You, Lei Wang, Li-Ping Li, Kai Zheng (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Texture Feed Based Convolutional Neural Network for Pansharpening
Publication date: Available online 24 February 2020Source: NeurocomputingAuthor(s): Maryam Imani (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Siamese Deformable Cross-Correlation Network for Real-Time Visual Tracking
Publication date: Available online 24 February 2020Source: NeurocomputingAuthor(s): Linyu Zheng, Ming Tang, Yingying Chen, Jinqiao Wang, Hanqing Lu (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Weakly Supervised Easy-to-hard Learning for Object Detection in Image Sequences
Publication date: Available online 24 February 2020Source: NeurocomputingAuthor(s): Hongkai Yu, Dazhou Guo, Zhipeng Yan, Lan Fu, Jeff Simmons, Craig P. Przybyla, Song Wang (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

The NN-Stacking: Feature weighted linear stacking through neural networks
Publication date: Available online 24 February 2020Source: NeurocomputingAuthor(s): Victor Coscrato, Marco Henrique de Almeida Inácio, Rafael Izbicki (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Joint Discriminative Attributes and Similarity Embeddings Modeling for Zero-Shot Recognition
Publication date: Available online 24 February 2020Source: NeurocomputingAuthor(s): Min Meng, Xiaoyu Zhan, Jigang Wu (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Unified Non-uniform Scale Adaptive Sampling Model for Quality Assessment of Natural and Screen Images
Publication date: Available online 24 February 2020Source: NeurocomputingAuthor(s): Tianli Tao, Li Ding, Hua Huang (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Wavelet packet analysis for speaker-independent emotion recognition
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): Kunxia Wang, Guoxin Su, Li Liu, Shu Wang (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Fast adaptive neighbors clustering via embedded clustering
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): Yijun Liu, Yongda Cai, Xiaojun Yang, Feiping Nie, Wujian Ye (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Neural-network-based decentralized output-feedback control for nonlinear large-scale delayed systems with unknown dead-zones and virtual control coefficients
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): Honghong Wang, Bing Chen, Chong Lin, Yumei Sun (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

An Oversampling Framework for Imbalanced Classification Based on Laplacian Eigenmaps
Publication date: Available online 25 February 2020Source: NeurocomputingAuthor(s): Xiucai Ye, Hongmin Li, Akira Imakura, Tetsuya Sakurai (Source: Neurocomputing)
Source: Neurocomputing - February 26, 2020 Category: Neuroscience Source Type: research

Mix-zero-sum differential games for linear systems with unknown dynamics based on off-policy IRL
Publication date: Available online 24 February 2020Source: NeurocomputingAuthor(s): Ruizhuo Song, Kanghao DuAbstractThis paper discusses a multi-player mixed-zero-sum (MZS) differerntial games with completely unknown dynamics. Based on off-policy integral reinforcement learning (IRL), a novel algorithm is proposed to obtain the optimal control. First, a policy iteration algorithm is put forward to obtain the optimal solution for deterministic system. Next, the case that the system dynamics is completely unknown is considered. And an IRL-based off-policy algorithm is presented. Meanwhile, the convergence of the presented al...
Source: Neurocomputing - February 24, 2020 Category: Neuroscience Source Type: research

Auto-weighted Multi-view Clustering via Spectral Embedding
Publication date: Available online 22 February 2020Source: NeurocomputingAuthor(s): Shaojun Shi, Feiping Nie, Rong Wang, Xuelong LiAbstractAs is well-known, multi-view clustering has attracted considerable attention since many benchmark data sets exist heterogeneous features. Previous multi-view spectral clustering methods mainly contain two steps: 1) constructing multiple similarity graphs; 2) performing K-means (KM) clustering. The two-step strategy cannot acquire optimal results since the clustering performance highly relies on the constructed similarity graphs. To address this drawback, a unified framework named a...
Source: Neurocomputing - February 23, 2020 Category: Neuroscience Source Type: research

Neural-network-based adaptive backstepping control for a class of unknown nonlinear time-delay systems with unknown input saturation
Publication date: Available online 22 February 2020Source: NeurocomputingAuthor(s): HOSSEIN DASTRES, BEHROOZ REZAIE, BARMAK BAIGZADEHNOEAbstractIn this paper, a neural-network-based adaptive backstepping control scheme is developed for a class of unknown nonlinear systems with unknown time-varying delayed states and unknown saturated delayed input. In the proposed method, radial basis function neural network is adopted to approximate the unknown nonlinear functions. An adaptive backstepping design is employed to compensate for the unknown time-varying delays in states. In addition, to overcome the effects of input delay, a...
Source: Neurocomputing - February 23, 2020 Category: Neuroscience Source Type: research

Fixed-time stochastic outer synchronization in double-layered multi-weighted coupling networks with adaptive chattering-free control
Publication date: Available online 22 February 2020Source: NeurocomputingAuthor(s): Fei Tan, Lili Zhou, Yuming Chu, Yongmin LiAbstractThe problem for fixed-time outer synchronization of double-layered multi-weighted coupled complex networks with stochastic effects is considered in this paper. To suppress chattering in synchronization, an adaptive chattering-free control algorithm is designed. Based upon the Lyapunov stability theory, some sufficient criteria for the adaptive stochastic outer synchronization are proposed. The designed adaptive chattering-free controller and the sufficient conditions can be applicable to not...
Source: Neurocomputing - February 23, 2020 Category: Neuroscience Source Type: research

An Online and Generalized Non-negativity Constrained Model for Large-scale Sparse Tensor Estimation on Multi-GPU
Publication date: Available online 22 February 2020Source: NeurocomputingAuthor(s): Linlin Zhuo, Kenli Li, Hao Li, Jiwu Peng, Keqin LiAbstractNon-negative Tensor Factorization (NTF) models are effective and efficient in extracting useful knowledge from various types of probabilistic distribution with multi-way information. Current NTF models are mostly designed for problems in computer vision which involve the whole Matricized Tensor Times Khatri−Rao Product (MTTKRP). Meanwhile, a Sparse NTF (SNTF) proposed to solve the problem of sparse Tensor Factorization (TF) can result in large-scale intermediate data. A Single-...
Source: Neurocomputing - February 23, 2020 Category: Neuroscience Source Type: research

An improved discrete backtracking searching algorithm for fuzzy multiproduct multistage scheduling problem
In this study, we address the fuzzy multiproduct multistage scheduling problem (FMMSP). The FMMSP with the objective of minimizing makespan is close to practical manufacturing circumstances in terms of the uncertainty in processing time. Backtracking searching algorithm (BSA) is a new proposed meta-algorithm for continuous optimization problems. To solve the FMMSP, an improved discrete BSA, called discrete BSA with local search (DBSA-LS), is developed. The information of the global best solution is incorporated into the mutation process to improve the convergence speed of discrete BSA. A local search related to the FMMSP e...
Source: Neurocomputing - February 23, 2020 Category: Neuroscience Source Type: research

Artificial Intelligence Using Hyper-Algebraic Networks
Publication date: Available online 22 February 2020Source: NeurocomputingAuthor(s): Sudharsan Thiruvengadam, Jei Shian Tan, Karol MillerAbstractThis work presents a novel paradigmatic revision of traditional neural networks, using network theoretic methods and Conformal Geometric Algebra. A unique theoretical framework called the ‘hyperfield cognition framework’ expands upon the mathematical foundations of neural networks in five-dimensional Conformal Geometric Algebraic space. This framework allows one to construct a novel theoretical computational engine, which is similar to a standard artificial neural netwo...
Source: Neurocomputing - February 23, 2020 Category: Neuroscience Source Type: research

Image Deblurring Using Tri-Segment Intensity Prior
Publication date: Available online 23 February 2020Source: NeurocomputingAuthor(s): Hong Zhang, Yujie Wu, Lei Zhang, Zeyu Zhang, Yawei LiAbstractCamera shake during exposure often introduces annoying blur of objects and deteriorates image quality. Existing image deblurring algorithms usually use intensity and gradient priors to alleviate the degree of blurring. However, these methods only consider the changes caused by the blur process in the low intensity range, omitting the changes caused by the blur process in the high and middle part of the intensity range. In this paper, we propose an effective blind image deblurring ...
Source: Neurocomputing - February 23, 2020 Category: Neuroscience Source Type: research

Extending Information Maximization from a Rate-Distortion Perspective
Publication date: Available online 21 February 2020Source: NeurocomputingAuthor(s): Yan Zhang, Junjie Hu, Takayuki OkataniAbstractIn this paper, we propose a new interpretation of the information maximization method (InfoMax) from a perspective of the rate distortion theory. We show that under specific conditions, InfoMax is equivalent to the minimization of a compression rate under the constraint of zero distortion. Zero distortion, or equivalently, zero reconstruction error between the input and its reconstruction, does not provide meaningful solutions in many cases. Based on the new interpretation, we extend InfoMax to ...
Source: Neurocomputing - February 23, 2020 Category: Neuroscience Source Type: research

Left Ventricle Landmark Localization and Identification in Cardiac MRI by Deep Metric Learning-Assisted CNN Regression
Publication date: Available online 21 February 2020Source: NeurocomputingAuthor(s): Xuchu Wang, Suiqiang Zhai, Yanmin NiuAbstractAccurate left ventricle landmark localization in cardiac MRI plays a vital role in computer-aided diagnosis of heart disease. Typical classification models hardly deal with artifacts and low discrimination of landmark regions by using only local image information, while regression models suffer from ambiguity between random samples and label, also the imbalance of samples. To overcome this limitation, this paper proposes a left ventricle landmark localization and identification method in cardiac ...
Source: Neurocomputing - February 23, 2020 Category: Neuroscience Source Type: research

Understanding Dropout as an Optimization Trick
Publication date: Available online 22 February 2020Source: NeurocomputingAuthor(s): Sangchul Hahn, Heeyoul ChoiAbstractAs one of standard approaches to train deep neural networks, dropout has been applied to regularize large models to avoid overfitting, and the improvement in performance by dropout has been explained as avoiding co-adaptation between nodes. However, when correlations between nodes are compared after training the networks with or without dropout, one question arises if co-adaptation avoidance explains the dropout effect completely. In this paper, we propose an additional explanation of why dropout works and...
Source: Neurocomputing - February 23, 2020 Category: Neuroscience Source Type: research

Triple Loss for Hard Face Detection
Publication date: Available online 21 February 2020Source: NeurocomputingAuthor(s): Zhenyu Fang, Jinchang Ren, Stephen Marshall, Huimin Zhao, Zheng Wang, Kaizhu Huang, Bing XiaoAbstractAlthough face detection has been well addressed in the last decades, despite the achievements in recent years, effective detection of small, blurred and partially occluded faces in the wild remains a challenging task. Meanwhile, the trade-off between computational cost and accuracy is also an open research problem in this context. To tackle these challenges, in this paper, a novel context enhanced approach is proposed with structural optimiz...
Source: Neurocomputing - February 21, 2020 Category: Neuroscience Source Type: research

Dreaming machine learning: Lipschitz extensions for reinforcement learning on financial markets
Publication date: Available online 21 February 2020Source: NeurocomputingAuthor(s): J.M. Calabuig, H. Falciani, E.A. Sánchez-PérezAbstractWe consider a quasi-metric topological structure for the construction of a new reinforcement learning model in the framework of financial markets. It is based on a Lipschitz type extension of reward functions defined in metric spaces. Specifically, the McShane and Whitney extensions are considered for a reward function which is defined by the total evaluation of the benefits produced by the investment decision at a given time. We define the metric as a linear combination of...
Source: Neurocomputing - February 21, 2020 Category: Neuroscience Source Type: research

RNN-GWR: A Geographically Weighted Regression Approach For Frequently Updated Data
In this study, to handle frequently updated data on given locations, a computationally efficient GWR approach, RNN-GWR, which utilizes reverse nearest neighbor (RNN) strategy, is proposed. The performance of the proposed RNN-GWR approach is compared with the performances of a Naïve-GWR and FastGWR approaches. Experimental evaluations show that the proposed approach is computationally efficient than the other approaches on handling frequently updated data. (Source: Neurocomputing)
Source: Neurocomputing - February 20, 2020 Category: Neuroscience Source Type: research

Consensus of Multi-Agent Systems with Intermittent Communications via Sampling Time Unit Approach
Publication date: Available online 19 February 2020Source: NeurocomputingAuthor(s): Jian Sun, Zhanshan WangAbstractThis paper investigates the consensus problem of multi-agent systems with intermittent communications under sampled-data control. A novel approach called sampling time unit (STU) approach is proposed to study such system. In such approach, the work time is described by finite number of sampling time units and the rest time is describe by several average time units. The lengths of work time and rest time depend on the convergence or divergence property of each time unit. Based on the STU approach, the stabiliza...
Source: Neurocomputing - February 20, 2020 Category: Neuroscience Source Type: research

Learning 3D Spatiotemporal Gait Feature by Convolutional Network for Person Identification
Publication date: Available online 19 February 2020Source: NeurocomputingAuthor(s): Thien Huynh-The, Cam-Hao Hua, Nguyen Anh Tu, Dong-Seong KimAbstractFor person identification in non-interaction biometric systems, gait recognition has been recently encouraged in literature and industrial applications instead of face recognition. Although numerous advanced methods that learn object appearance by conventional machine learning models have been discussed in the last decade, most of them are strongly sensitive to scene background motion. In this research, we address the drawbacks of existing works by comprehensively studying g...
Source: Neurocomputing - February 20, 2020 Category: Neuroscience Source Type: research

Exploiting Geographical-Temporal Awareness Attention for Next Point-of-Interest Recommendation
Publication date: Available online 20 February 2020Source: NeurocomputingAuthor(s): Tongcun Liu, Jianxin Liao, Zhigen Wu, Yulong Wang, Jingyu WangAbstractWith the prosperity of the location-based social networks, next point-of-interest (POI) recommendation has become an increasingly significant requirement since it can benefit both users and business. Obtaining insight into user mobility for the next POI recommendations is a vital yet challenging task. Existing approaches to understanding user mobility mainly gloss over the check-in sequence, making it fail to explicitly capture the subtle POI–POI interactions across...
Source: Neurocomputing - February 20, 2020 Category: Neuroscience Source Type: research

Social Relationship Prediction across Networks Using Tri-training BP Neural Networks
Publication date: Available online 20 February 2020Source: NeurocomputingAuthor(s): Qun Liu, Shuxin Liu, Guoyin Wang, Shuyin XiaABSTRACTIt is well known that the number of users is increasing rapidly in online social networks. People are linked through various types of social relationships. Detecting the type of social relationships is fundamental to improve performance on many applications in social networks. Existing studies mainly focus on predicting social relationships in the same network based on its own abundant information. However, there are few works on predicting social relationships across different networks. I...
Source: Neurocomputing - February 20, 2020 Category: Neuroscience Source Type: research

Efficient Continual Learning in Neural Networks with Embedding Regularization
Publication date: Available online 20 February 2020Source: NeurocomputingAuthor(s): Jary Pomponi, Simone Scardapane, Vincenzo Lomonaco, Aurelio UnciniAbstractContinual learning of deep neural networks is a key requirement for scaling them up to more complex applicative scenarios and for achieving real lifelong learning of these architectures. Previous approaches to the problem have considered either the progressive increase in the size of the networks, or have tried to regularize the network behavior to equalize it with respect to previously observed tasks. In the latter case, it is essential to understand what type of inf...
Source: Neurocomputing - February 20, 2020 Category: Neuroscience Source Type: research

ℓ1/2-Based Penalized Clustering with Half Thresholding Algorithm
Publication date: Available online 20 February 2020Source: NeurocomputingAuthor(s): Xingwei Wang, Hongjuan ZhangAbstractClustering is a widely applied method in data analysis. As a novel framework of clustering analysis, penalized clustering bases itself on the sparsity of solution, which contributes to its ability of determining the best number of clusters automatically rather than specified in advance. Moreover, ℓ1/2 regularization has been recognized extensively in recent studies. Compared with other ℓp (0 
Source: Neurocomputing - February 20, 2020 Category: Neuroscience Source Type: research