Skip to main content

Neural Processing Letters OnlineFirst articles


Finite-Time Synchronization for Delayed Inertial Neural Networks by the Approach of the Same Structural Functions

This paper is concerned about the finite-time synchronization for the delayed drive-response inertial neural networks. Without applying the previous finite-time stability theorems, integral inequality way and the maximum-valued approach, by put …

Huaying Liao, Zhen Yang, Zhengqiu Zhang, Yin Zhou


Node Similarity Preserving Graph Convolutional Network Based on Full-frequency Information for Node Classification

Recently, graph neural networks have achieved good performance in graph representation learning. However, most graph neural networks only utilize node low-frequency signals and destroy node similarity when aggregating graph structure and node …

Yuqiang Li, Jing Liao, Chun Liu, YingJie Wang, Lin Li


Active Learning by Extreme Learning Machine with Considering Exploration and Exploitation Simultaneously

As an important machine learning paradigm, active learning has been widely applied to scenarios in which it is easy to acquire a large number of instances but labeling them is expensive and/or time-consuming. In such scenario, active learning can …

Yan Gu, Hualong Yu, Xibei Yang, Shang Gao


Using Cartesian Genetic Programming Approach with New Crossover Technique to Design Convolutional Neural Networks

In image classification problems, Convolutional Neural Networks (CNNs) are deep neural networks that include a variety of different layers aimed at classifying images. Until today, the most promising and state-of-the-art method in image …

Ali Torabi, Arash Sharifi, Mohammad Teshnehlab


Moving Object Detection in Video Sequences Based on a Two-Frame Temporal Information CNN

Moving object detection methods, MOD, must solve complex situations found in video scenarios related to bootstrapping, illumination changes, bad weather, PTZ, intermittent objects, color camouflage, camera jittering, low camera frame rate, noisy …

Mario I. Chacon-Murguia, Abimael Guzman-Pando


Asymptotic Stability of Fractional-Order Incommensurate Neural Networks

The dynamics and stability of fractional-order (FO) neural networks (FONN) and FO memristive neural networks (FOMNN), have received great attention in the last years. However, most research focused merely on commensurate FONN (all neurons have the …

Liping Chen, Panpan Gu, António M. Lopes, Yi Chai, Shuiqing Xu, Suoliang Ge


A Novel Link Prediction Model in Multilayer Online Social Networks Using the Development of Katz Similarity Metric

The analysis of online social networks (OSNs) using graph theory is performed with the aim of extracting knowledge embedded in these networks. Link prediction (LP) problem is an important topic in the analysis of OSNs. LP refers to estimating the …

Zhie Gao, Amin Rezaeipanah


Finite-Horizon Robust Event-Triggered Control for Nonlinear Multi-agent Systems with State Delay

This paper investigates the finite-horizon robust event-triggered control for nonlinear multi-agent systems (NMASs) with state delay. The consensus of NMASs has been studied extensively. Robustness, as another significant topic of NMASs, has not …

Chen Liu, Lei Liu


Ultra Fast Classification and Regression of High-Dimensional Problems Projected on 2D

We propose the two-dimensional visual map classifier and regressor, which project the high-dimensional patterns on a 2D map, for human visualization and understanding of the data, and afterwards define a classification or regression map that …

Heba Alateyat, Manuel Fernández-Delgado, Eva Cernadas, Senén Barro


Pseudo S-Asymptotically -Antiperiodic Solutions for SICNNs with Mixed Delays

In this paper, we mainly investigate pseudo S-asymptotically $$\omega $$ ω -antiperiodic solutions to shunting inhibitory cellular neural networks (SICNNs) with mixed delays. After proving some auxiliary results, we first show the existence of …

Penghui Lü, Yong-Kui Chang


Scene Level Image Classification: A Literature Review

Convolutional neural networks (CNNs) have made significant contributions to natural and remote sensing imaging since the development of deep learning. Scene-level image classification is a challenge that affects both the natural and remote sensing …

Sagar Chavda, Mahesh Goyani


Deep Convolutional Neural Networks with Transfer Learning for Visual Sentiment Analysis

The objective of visual sentiment analysis is to predict the positive or negative sentiment polarity evoked by images by analysing the image contents. The task of automatically recognizing sentiments in still images is inherently more challenging …

K. Usha Kingsly Devi, V. Gomathi


Real-Time Accurate Text Detection with Adaptive Double Pyramid Network

Segmentation-based methods have been widely adopted in scene text detection recently, for they could more accurately predict the shape of various scene text at pixel-level than other methods. However, complicated feature aggregation or label …

Weina Zhou, Wanyu Song

16-11-2022 | Correction

Correction: A Lightweight Neural Learning Algorithm for Real-Time Facial Feature Tracking System via Split-Attention and Heterogeneous Convolution

Yuandong Ma, Qing Song, Mengjie Hu, Xiaotong Zhu


A Generalization of Sigmoid Loss Function Using Tsallis Statistics for Binary Classification

In this paper, we present a generalization of sigmoid loss function by applying $${\varvec{ q}}$$ q -exponential ( $${\varvec{ q}}$$ q -exp) of Tsallis statistics. With this framework, we could relax and/or tighten-up the slopes of sigmoid loss …

Hilman F. Pardede, Purwoko Adhi, Vicky Zilvan, Asri R. Yuliani, Andria Arisal


Biomedical Image Segmentation Using Fuzzy Artificial Cell Swarm Optimization (FACSO)

This article describes a novel unsupervised approach to segmenting biomedical images. The proposed approach will be known as Fuzzy Artificial Cell Swarm Optimization. Artificial cell swarm optimization is one of the newest metaheuristic …

Shouvik Chakraborty, Kalyani Mali


Positive-Unlabeled Learning for Knowledge Distillation

Convolutional neural networks (CNNs) have greatly promoted the development of artificial intelligence. In general, CNNs with high performance are over-parameterized, requiring massive calculations to process and predict the data. It leads CNNs …

Ning Jiang, Jialiang Tang, Wenxin Yu


Detection of Drug Abuse Using Rough Set and Neural Network-Based Elevated Mathematical Predictive Modelling

In the smart world scenario, the application of the Internet of Things is manifold as its utilization can be observed in health care services, home, and office automation, grid systems etc. This was evident during the current pandemic situation …

S. Selvi, M. Chandrasekaran


SRK-Augment: A self-replacement and discriminative region keeping augmentation scheme for better classification

Data augmentation has been proved to be a critical and effective way to alleviate over-fitting of deep learning model. Region-level removal is one of state-of-the-art solutions, which can not only synthesize vicinity samples, but also improve …

Hao Zhao, Jikai Wang, Zonghai Chen, Shiqi Lin, Peng Bao


Underwater Backscatter Recognition Using Deep Fuzzy Extreme Convolutional Neural Network Optimized via Hunger Games Search

Although deep learning methods are accurate in underwater backscatter detection, identification, and classification, they suffer from long processing times, especially in the training phase. Therefore, a four-phase deep learning (DL) based …

Mohammad Khishe, Mokhtar Mohammadi, Ali Ramezani Varkani