-
mlscorecheck: Testing the consistency of reported performance scores and experiments in machine learning Neurocomputing (IF 6.0) Pub Date : 2024-03-18 György Kovács, Attila Fazekas
-
Integration of short and long-term interests: A preference aware session-based recommender Neurocomputing (IF 6.0) Pub Date : 2024-03-16 Sanjay K., Nargis Pervin
Session-based recommenders have gathered tremendous e-commerce and media streaming applications where the task is to predict the next item user would consume based on the session history. In this arena, advancements have been accomplished using deep learning techniques to model users’ long-term and short-term preferences in a session. The long-term module focuses on the entire item set in a session
-
Multimodal Knowledge-enhanced Interactive Network with Mixed Contrastive Learning for Emotion Recognition in Conversation Neurocomputing (IF 6.0) Pub Date : 2024-03-16 Xudong Shen, Xianying Huang, Shihao Zou, Xinyi Gan
Emotion Recognition in Conversations (ERC) aims to accurately identify the emotional labels of each utterance in a conversation, holding significant application value in human–computer interaction. Existing research suggests introducing commonsense knowledge (CSK) and multimodal information enhances model performance in ERC tasks. However, several challenges persist: (1) the neglect of complex psychological
-
Guided evolutionary Neural Architecture Search with efficient performance estimation Neurocomputing (IF 6.0) Pub Date : 2024-03-16 Vasco Lopes, Miguel Santos, Bruno Degardin, Luís A. Alexandre
Neural Architecture Search (NAS) methods have been successfully applied to image tasks with excellent results. However, NAS methods are often complex and tend to converge to local minima as soon as generated architectures yield good results. This paper proposes GEA, a novel approach for guided NAS. GEA guides the evolution by exploring the search space by generating and evaluating several architectures
-
BEV-CFKT: A LiDAR-camera cross-modality-interaction fusion and knowledge transfer framework with transformer for BEV 3D object detection Neurocomputing (IF 6.0) Pub Date : 2024-03-16 Ming Wei, Jiachen Li, Hongyi Kang, Yijie Huang, Jun-Guo Lu
The BEV-CFKT proposed in this paper leverages knowledge transfer through transformers for LiDAR-Camera fusion in the Bird’s-Eye-View (BEV) space, aiming to achieve accurate and robust 3D object detection. BEV-CFKT comprises three main components, which include the generation of BEV features from images and point clouds, cross-modality interaction, and hybrid object queries using a monocular detection
-
Multi-view 3D reconstruction based on deep learning: A survey and comparison of methods Neurocomputing (IF 6.0) Pub Date : 2024-03-14 Juhao Wu, Omar Wyman, Yadong Tang, Damiano Pasini, Wenlong Wang
An important objective in computer vision is to analyze multiple images and subsequently reconstruct the shape and structure in 3D. Traditional multi-view 3D reconstruction techniques extract and match key features from images with known camera parameters. However, this approach is inefficient and fails to fully exploit the advantages of multi-view information. Advancements in deep learning have revolutionized
-
Brain magnetic resonance images segmentation via improved mixtures of factor analyzers based on dynamic co-clustering Neurocomputing (IF 6.0) Pub Date : 2024-03-14 Rahman Farnoosh, Fatemeh Aghagoli
The main goal of this paper is to attain accurate and automatic detection of brain tumors in gray magnetic resonance images using reducing the local dimensions. We propose a novel model called Improved Mixtures of Factor Analyzers based on Dynamic Co-Clustering (IMFADCC) for the detection and localization of brain tumors. After image preprocessing and enhancement, the optimal numbers of row clusters
-
Enhancing class-incremental object detection in remote sensing through instance-aware distillation Neurocomputing (IF 6.0) Pub Date : 2024-03-13 Hangtao Feng, Lu Zhang, Xu Yang, Zhiyong Liu
Object detection plays a important role within the field of remote sensing, boasting significant applications including intelligent monitoring and urban planning. However, traditional models are constrained by predefined classes and encounter a challenge known as catastrophic forgetting when attempting to learn new classes post-deployment. To address this problem, we propose a novel Instance-aware
-
SSRI-Net: Subthreads Stance-Rumor Interaction Network for rumor verification Neurocomputing (IF 6.0) Pub Date : 2024-03-13 Zhendong Chen, Siu Cheung Hui, Lejian Liao, Heyan Huang
As online rumors have the potential to greatly affect areas such as social order, stock prices, and presidential elections, there is an emerging necessity for the automation of rumor verification. Although the current methods have achieved satisfactory performance, they still suffer from the following problems. First, the current methods simply concatenate the representations of different subthreads
-
Fully distributed synchronization on directed graphs via self-triggered control with positive minimum inter-event times Neurocomputing (IF 6.0) Pub Date : 2024-03-13 Lina Xia, Qing Li, Ruizhuo Song, Lu Liu
The fully distributed synchronization problem is studied for heterogeneous linear multi-agent systems (MASs) on a directed graph by observer-based adaptive self-triggered control schemes guaranteed positive minimum inter-event times (MIETs). An improved adaptive observer used to estimate the leader state under composite triggering mechanisms is proposed to achieve the combination of event-triggered
-
Joint contrastive learning of structural and semantic for graph collaborative filtering Neurocomputing (IF 6.0) Pub Date : 2024-03-13 Jie Dai, Qingshan Li, Tianyi Nong, Qipeng Bi, Hua Chu
Recently, graph collaborative filtering has been proposed as a superior recommendation technique, due to its outstanding capability of capturing high-order correlations from user-item interactions. Despite effectiveness, it still suffers from two limitations on representation learning: (1) User/item nodes with high-degree usually interfere with the representation learning process of low-degree nodes
-
FDNet: Imperceptible backdoor attacks via frequency domain steganography and negative sampling Neurocomputing (IF 6.0) Pub Date : 2024-03-13 Liang Dong, Zhongwang Fu, Leiyang Chen, Hongwei Ding, Chengliang Zheng, Xiaohui Cui, Zhidong Shen
Backdoor attacks against Deep Neural Networks (DNNs) have surfaced as a substantial and concerning security challenge. These backdoor vulnerabilities in DNNs can be introduced by third-party sources through maliciously manipulated training data. Existing backdoor attacks are primarily built on perturbation trigger patterns in the spatial domain, which makes practical deployment arduous due to the ease
-
Practical consensus tracking control for networked Euler–Lagrange systems based on UDE integrated with RBF neural network Neurocomputing (IF 6.0) Pub Date : 2024-03-13 Runlong Peng, Rongwei Guo, Lixia Liu, Jinchen Ji, Zhonghua Miao, Jin Zhou
This paper solves the practical consensus tracking control problem for networked Euler–Lagrange (EL) systems using the uncertainty and disturbance estimator (UDE) in combination with the radial basis function (RBF) neural network. An integrated consensus algorithm is proposed for the networked EL systems, where the RBF neural network is first utilized to generate online estimation of the uncertain
-
DAP: A dataset-agnostic predictor of neural network performance Neurocomputing (IF 6.0) Pub Date : 2024-03-13 Sui Paul Ang, Soan T.M. Duong, Son Lam Phung, Abdesselam Bouzerdoum
Training a deep neural network on a large dataset to convergence is a time-demanding task. This task often must be repeated many times, especially when developing a new deep learning algorithm or performing a neural architecture search. This problem can be mitigated if a deep neural network’s performance can be estimated without actually training it. In this work, we investigate the feasibility of
-
Structure-guided feature and cluster contrastive learning for multi-view clustering Neurocomputing (IF 6.0) Pub Date : 2024-03-13 Zhenqiu Shu, Bin Li, Cunli Mao, Shengxiang Gao, Zhengtao Yu
Multi-view clustering (MVC) technology performs unsupervised clustering on data collected from multiple sources, and has received intense attention in recent years. However, most existing MVC methods fail to consider retaining view-specific information when learning multi-view consistent representations. Besides, the feature and cluster structures of multi-view data cannot be fully leveraged in clustering
-
Survey of continuous deep learning methods and techniques used for incremental learning Neurocomputing (IF 6.0) Pub Date : 2024-03-13 Justin Leo, Jugal Kalita
Neural networks and deep learning algorithms are designed to function similarly to biological synaptic structures. However, classical deep learning algorithms fail to fully capture the need for continuous learning; this has led to the advent of incremental learning. Incremental learning adds new challenges that are handled differently by modern state-of-the-art approaches. Some of these include: utilization
-
MSFFT: Multi-Scale Feature Fusion Transformer for cross platform vehicle re-identification Neurocomputing (IF 6.0) Pub Date : 2024-03-12 Ashutosh Holla B., Manohara Pai M.M., Ujjwal Verma, Radhika M. Pai
A vital component of Intelligent Transportation Systems (ITS) is vehicle re-identification, which allows vehicles to be identified across surveillance devices. Re-identification of vehicles is usually done using information collected from standalone surveillance devices such as fixed surveillance cameras (CCTVs) or aerial devices (UAVs). Re-identifying vehicles across standalone surveillance systems
-
Sparsity in transformers: A systematic literature review Neurocomputing (IF 6.0) Pub Date : 2024-03-12 Mirko Farina, Usman Ahmad, Ahmad Taha, Hussein Younes, Yusuf Mesbah, Xiao Yu, Witold Pedrycz
Transformers have become the state-of-the-art architectures for various tasks in Natural Language Processing (NLP) and Computer Vision (CV); however, their space and computational complexity present significant challenges for real-world applications. A promising approach to address these issues is the introduction of sparsity, which involves the deliberate removal of certain parameters or activations
-
Temporal pattern-aware QoS prediction by Biased Non-negative Tucker Factorization of tensors Neurocomputing (IF 6.0) Pub Date : 2024-03-11 Peng Tang, Tao Ruan, Hao Wu, Xin Luo
Dynamic quality of service (QoS) data contain rich temporal patterns of user-service interactions, which are vital for better understanding user behaviors and service conditions. Canonical polyadic (CP)-based latent factorization model has proven to be capable of capturing such patterns. However, it models the relations among latent features of user, service and time in a rigid and unnatural way, causing
-
Multi-target feature selection with subspace learning and manifold regularization Neurocomputing (IF 6.0) Pub Date : 2024-03-11 Dubo He, Shengxiang Sun, Li Xie
Existing supervised Multi-Target Feature Selection (MTFS) methods seldom consider the nearest-neighbor relationship and statistical correlation of samples underlying the output space, which leads the result of feature selection to be easily interfered by the output noise, thus making it difficult to achieve satisfactory performance. This paper proposes a novel MTFS method to preserve both the global
-
Bayesian graph convolutional network for traffic prediction Neurocomputing (IF 6.0) Pub Date : 2024-03-11 Jun Fu, Wei Zhou, Zhibo Chen
Recently, adaptive graph convolutional network based traffic prediction methods, learning a latent graph structure from traffic data via various attention-based mechanisms, have achieved impressive performance. However, they are still limited to finding a better description of spatial relationships between traffic conditions due to: (1) ignoring the prior of the observed road network topology; (2)
-
Area-keywords cross-modal alignment for referring image segmentation Neurocomputing (IF 6.0) Pub Date : 2024-03-11 Huiyong Zhang, Lichun Wang, Shuang Li, Kai Xu, Baocai Yin
Referring image segmentation aims to segment the instance corresponding to the given language description, which requires aligning information from two modalities. Existing approaches usually align the cross-modal information based on different forms of feature units, such as pixel-sentence, pixel-word and patch-word. The problem is that the semantic information embodied by these feature units may
-
A new prognostic model for accurate assessment of hepatocellular carcinoma risk using RNA editing data and unsupervised machine learning Neurocomputing (IF 6.0) Pub Date : 2024-03-08 Huimin Zhu, Hui Zhang, Yuanyan Xiong, Hui Li
A-to-I RNA editing is a long-known driving factor to the progression of hepatocellular carcinoma (HCC); however, its importance is often neglected in HCC subtyping and the modeling of prognosis, partially due to the high dimensional nature of the editing data. In this paper, we first obtain a comprehensive A-to-I RNA editing profile for HCC, among which two editing sites, I387M (chr4:57110120) and
-
Layered isolation forest: A multi-level subspace algorithm for improving isolation forest Neurocomputing (IF 6.0) Pub Date : 2024-03-07 Tao Liu, Zhen Zhou, Lijun Yang
Anomaly detection is an important field in data science that has been widely researched and applied, generating many methods. Among these methods, the isolation forest algorithm is outstanding because of its efficiency and effectiveness, especially in regard to large-scale data. Unfortunately, this algorithm has some drawbacks, such as being unable to effectively handle local outliers, possibly leading
-
Being aware of localization accuracy by generating predicted-IoU-guided quality scores Neurocomputing (IF 6.0) Pub Date : 2024-03-07 Pengfei Liu, Changguang Song, Yuhan Guo, Guixin Tang, Weibo Wang, Jiubin Tan
Localization quality estimation (LQE) methods benefit the post-process by additionally considering the prediction box’s localization accuracy. In this paper, we propose a more compatible detector called Classification-Localization-Quality (CLQ), which is not only applicable to general-distribution-based detection heads but also to delta-distribution-based heads. In this method, A lightweight and learnable
-
Synchronization for neural networks over event-triggered multi-channel: Relay channels under cyber-attacks Neurocomputing (IF 6.0) Pub Date : 2024-03-07 Yumei Zhou, Xiantao Luo, Zijing Xiao, Jian Huang, Hongxia Rao, Yao Zhao
This work addresses synchronization for master–slave neural networks (MSNNs) with remote transmission. To reduce the communication frequency, an event-triggered strategy combined with a dynamically adjusted threshold is employed. For the sake of enhancing the information transmission quality, a relay channels protocol that considers cyber-attacks is established, acknowledging that occurrence rates
-
Neural networks-based data hiding in digital images: Overview Neurocomputing (IF 6.0) Pub Date : 2024-03-07 Kristina Dzhanashia, Oleg Evsutin
Nowadays, neural networks are actively used for data hiding; however, there is currently no systematic knowledge regarding their utilization in this field. This is a significant gap, considering that neural network-based data hiding has already formed a large and quite independent area of research. This review aims to provide such systematization. It also provides a general framework of neural network
-
Fully automated diagnosis of thyroid nodule ultrasound using brain-inspired inference Neurocomputing (IF 6.0) Pub Date : 2024-03-07 Guanghui Li, Qinghua Huang, Chunying Liu, Guanying Wang, Lingli Guo, Ruonan Liu, Longzhong Liu
The interpretability of artificial intelligence (AI) based medical diagnostic systems is crucial to make the diagnosis adequately convincible. Deep learning has been extensively investigated and utilized in the area of medical assistance diagnosis in recent decades due to its outstanding performance and objective prediction. However, a huge semantic chasm dividing clinicians and unexplainable deep
-
Deep learning in fringe projection: A review Neurocomputing (IF 6.0) Pub Date : 2024-03-07 Haoyue Liu, Ning Yan, Bofan Shao, Shuaipeng Yuan, Xiaodong Zhang
Fringe projection is widely recognized as a prominent technique for 3D measurement, owing to its non-contact nature, high precision, and exceptional spatial resolution. However, it faces challenges in achieving a delicate equilibrium between speed and accuracy, conducting measurements on intricate optical surfaces, and capturing objects requiring a high dynamic range. Deep learning, with its robust
-
Adaptive operator selection with dueling deep Q-network for evolutionary multi-objective optimization Neurocomputing (IF 6.0) Pub Date : 2024-03-07 Shihong Yin, Zhengrong Xiang
Adaptive operator selection is an online method that automatically adjusts the application rate of different operators based on their actual performance. This paper proposes an adaptive operator selection paradigm based on dueling deep Q-network (DDQN), aiming to improve the training efficiency of the Q-network for solving multi-objective optimization problems. The Q-network is decomposed into state
-
A new feature selection method based on importance measures for crude oil return forecasting Neurocomputing (IF 6.0) Pub Date : 2024-03-07 Yuan Zhao, Yaohui Huang, Zhijin Wang, Xiufeng Liu
This paper introduces a novel feature selection method, called Feature Selection based on Importance Measures (FS-IM), to enhance the forecasting of crude oil returns. FS-IM innovatively combines active learning with the application of Gaussian noise to input features and selects the most relevant features using an optimal threshold value. The paper applies a ridge regression (RR) model based on FS-IM
-
Special Issue on Hybrid Artificial Intelligence Systems from HAIS 2022 Conference Neurocomputing (IF 6.0) Pub Date : 2024-03-07 Héctor Quintián, Emilio Corchado
-
Progressive expansion: Cost-efficient medical image analysis model with reversed once-for-all network training paradigm Neurocomputing (IF 6.0) Pub Date : 2024-03-07 Shin Wei Lim, Chee Seng Chan, Erma Rahayu Mohd Faizal, Kok Howg Ewe
Low computational cost artificial intelligence (AI) models are vital in promoting the accessibility of real-time medical services in underdeveloped areas. The recent (OFA) network (without retraining) can directly produce a set of sub-network designs with algorithm; however, the training resource and time inefficiency downfalls are apparent in this method. In this paper, we propose a new OFA training
-
Learnable product quantization for anomaly detection Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Shi Zhang, Weilin Chen, Binlong Lu, Huixia Lai
In many anomaly detection applications, anomaly samples are difficult to obtain. We propose a novel product quantization (PQ)-based anomaly detection scheme: Learnable Product Quantization (LPQ), which only requires very few abnormal samples to train the model. The scheme extracts feature from high-dimensional data using the deep learning network, decomposes the feature space into a Cartesian product
-
Cross-modal concept learning and inference for Vision-Language Models Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Yi Zhang, Ce Zhang, Yushun Tang, Zhihai He
Large-scale pre-trained Vision-Language Models (VLMs), such as CLIP, establish the correlation between texts and images, achieving remarkable success on various downstream tasks with fine-tuning. In existing fine-tuning methods, the class-specific text description is matched against the whole image. We recognize that this image-scale matching is not effective since images from the same class often
-
Comparing multi-class classifier performance by multi-class ROC analysis: A nonparametric approach Neurocomputing (IF 6.0) Pub Date : 2024-03-06 J, i, n, g, y, a, n, , X, u
The area under the Receiver Operating Characteristic (ROC) curve (AUC) is a standard metric for quantifying and comparing binary classifiers. Real world applications often require classification into multiple (more than two) classes. For multi-class classifiers that produce class membership scores, a popular multi-class AUC (MAUC) variant is to average the pairwise AUC values (Hand and Till, 2001)
-
Normalized penalty gradient flow: A continuous-time approach for solving constrained nonconvex nonsmooth optimization problems Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Sijian Wang, Xin Yu, Haihua Qin
To avoid calculating penalty parameters, this paper introduces a continuous-time approach that combines the normalized gradient flow with the penalty method to solve the nonconvex nonsmooth optimization problem with a convex constraint set. Subsequently, this approach is extended to solve nonconvex nonsmooth optimization with a box constraint set and affine equality constraints. Compared with the current
-
Simulation of an individual with motor disabilities by a deep reinforcement learning model Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Karla K. Sánchez-Torres, Suemi Rodríguez-Romo
We have developed a new neural network model that simulates how the central nervous system (CNS) governs neural motor sensors. Our model uses reinforcement learning and transfer entropy to compare healthy individuals’ learning with those who have motor impairments. Our aim is to study effective connectivity and identify differences in information transmission between the two groups. By analyzing effective
-
Co-evolutionary dynamics in optimal multi-agent game with environment feedback Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Weiwei Han, Zhipeng Zhang, Yuying Zhu, Chengyi Xia
At present, game-based analysis and control problems with environmental feedback significantly contribute to the study of collective cooperation, and pose great challenges for the analysis of multi-agent game systems in complex real world. We consider co-evolutionary dynamics based on an extended multi-agent game with environmental feedback, which is modeled by optional public goods games (OPGGs).
-
Synergistic registration of CT-MRI brain images and retinal images: A novel approach leveraging reinforcement learning and modified artificial rabbit optimization Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Xiaolei Luo, Hua Zou, Yi Hu, Peng Gui, Yang Xu, Dengyi Zhang, Wei Hu, Min Hu
Medical image registration is a pivotal application within the field of medical imaging. It entails the fusion of commonalities among data of disparate modalities into a unified coordinate system, thereby achieving complementary imaging information. This process plays a crucial role in scenarios such as accurate disease diagnosis, surgical guidance, patient monitoring, and radiological therapy. Due
-
A novel device placement approach based on position-aware subgraph neural networks Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Meng Han, Yan Zeng, Jilin Zhang, Yongjian Ren, Meiting Xue, Mingyao Zhou
Coping with the growing demand for data and parameters in complex neural network (NN) models of contemporary times typically involves distributing them across multiple devices, giving rise to the device placement problem. Several widely adopted solutions to this challenge leverage graph embedding schemes. However, the current graph embedding models employed for device placement suffer from several
-
Independent Dual Graph Attention Convolutional Network for skeleton-based action recognition Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Jinze Huo, Haibin Cai, Qinggang Meng
Graph convolutional networks (GCNs) have been widely adopted in skeleton-based action recognition, achieving impressive outcomes. However, the convolution operations in GCNs fail to make full use of the original input data, which restricts its ability to accurately capture the correlation within the skeleton. To solve this issue, this study introduces an independent dual graph attention convolutional
-
Representation modeling learning with multi-domain decoupling for unsupervised skeleton-based action recognition Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Zhiquan He, Jiantu Lv, Shizhang Fang
Skeleton-based action recognition is one of the basic researches in computer vision. In recent years, the unsupervised contrastive learning paradigm has achieved great success in skeleton-based action recognition. However, previous work often treated input skeleton sequences as a whole when performing comparisons, lacking fine-grained representation contrast learning. Therefore, we propose a contrastive
-
Hierarchical synchronization with structured multi-granularity interaction for video question answering Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Shanshan Qi, Luxi Yang, Chunguo Li
Video Question Answering (VideoQA) requires a thorough comprehension of linguistic and visual modalities. However, recent methods confront two problems: (1) Synchronous modeling of object action and frame scene instead of a step-by-step manner, which can better mine potential semantic attributes of videos, lacks research; (2) The relationship between cross-modal alignments at different granularity
-
Audio-visual representation learning for anomaly events detection in crowds Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Junyu Gao, Hao Yang, Maoguo Gong, Xuelong Li
In recent years, anomaly events detection in crowd scenes attracts many researchers’ attentions, because of its importance to public safety. Existing methods usually exploit visual information to analyze whether any abnormal events have occurred due to only visual sensors are generally equipped in public places. However, when an abnormal event in crowds occurs, sound information may be discriminative
-
Coordinate-Aware Mask R-CNN with Group Normalization: A underwater marine animal instance segmentation framework Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Dewei Yi, Hasan Bayarov Ahmedov, Shouyong Jiang, Yiren Li, Sean Joseph Flinn, Paul G. Fernandes
Unsustainable fishing, driven by bycatch and discards, harms marine ecosystems. Addressing this, we propose a Coordinate-Aware Mask R-CNN (CAM-RCNN) method to enhance fish detection in commercial trawls. Leveraging CoordConv and Group Normalization, our approach improves generalization and stability. To tackle class imbalance, a compound Dice and cross-entropy loss is employed, and image data are enhanced
-
Degradation regression with uncertainty for blind super-resolution Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Shang Li, Guixuan Zhang, Zhengxiong Luo, Jie Liu, Zhi Zeng, Shuwu Zhang
Some recent blind super-resolution (SR) efforts focus on designing complex degradation models to better simulate real-world degradations. The paired high-resolution (HR) & low-resolution (LR) samples synthesized by these models can cover a large degradation space, which helps train a robust SR model in real scenarios. However, these diverse synthetic samples may render the SR model and prevent it from
-
Domain adaptive remote sensing image semantic segmentation with prototype guidance Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Wankang Zeng, Ming Cheng, Zhimin Yuan, Wei Dai, Youming Wu, Weiquan Liu, Cheng Wang
Current unsupervised domain adaptation (UDA) techniques in semantic segmentation effectively decrease the domain discrepancy between the labeled source domain and unlabeled target domain, thereby enhancing the model’s pixel-wise discriminative capability for target domain data. However, in remote sensing images (RSIs), our study uncovers that these approaches perform poorly in the presence of class
-
A signer-independent sign language recognition method for the single-frequency dataset Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Tianyu Liu, Tangfei Tao, Yizhe Zhao, Min Li, Jieli Zhu
Currently, there are over 70 million people worldwide using more than 300 sign languages for communication, resulting in a vast number of sign language categories. Sign language recognition faces two main challenges. Firstly, in real-world applications, sign language users may not be represented in the dataset, leading to weak recognition capabilities of the models. Secondly, constructing large-scale
-
BEV feature exchange pyramid networks-based 3D object detection in small and distant situations: A decentralized federated learning framework Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Rukai Lan, Yong Zhang, Linbo Xie, Zhaolong Wu, Yifan Liu
3D object detection, whose task is to perceive the surrounding environment, plays a significant role in autonomous driving. In this study, we propose a new BEV-FePNet 3D detection model, which can effectively fuse multi-modal information in deeply abstract features. The BEV-FePNet has been validated experimentally on the nuScenes dataset, and the findings demonstrate that the proposed approach enhances
-
Noise aware content-noise complementary GAN with local and global discrimination for low-dose CT denoising Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Kousik Sarkar, Soumen Bag, Prasun Chandra Tripathi
In response to rising concerns over radiation exposure in computed tomography (CT) imaging, effective denoising methods for low-dose CT (LDCT) images are crucial. In recent years, the use of deep learning techniques especially generative adversarial networks (GANs) significantly enhanced the efficiency of LDCT denoising methods, surpassing traditional methods. However, GAN-based denoising methods often
-
An improved asynchronous batch gradient method for ridge polynomial neural network Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Yan Xiong, Shumei He
The ridge polynomial neural network composed of pi-sigma modules is a typical higher-order feedforward network, which has good non-linear mapping capabilities. Due to the strong coupling of the network structure, the synchronous gradient method can easily result in significant fluctuations in updated weights. This will reduce the generalization ability of the ridge polynomial neural network for solving
-
Deep learning for steganalysis of diverse data types: A review of methods, taxonomy, challenges and future directions Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Hamza Kheddar, Mustapha Hemis, Yassine Himeur, David Megías, Abbes Amira
Steganography and steganalysis are two interrelated aspects of the field of information security. Steganography seeks to conceal communications, whereas steganalysis aims to discover or, if possible, recover the data they contain. These two areas have garnered significant interest, especially among law enforcement agencies. Cybercriminals and even terrorists often employ steganography to avoid detection
-
Deep contrastive representation learning for multi-modal clustering Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Yang Lu, Qin Li, Xiangdong Zhang, Quanxue Gao
Benefiting from the informative expression capability of contrastive representation learning (CRL), recent multi-modal learning studies have achieved promising clustering performance. However, it should be pointed out that the existing multi-modal clustering methods based on CRL fail to simultaneously take the similarity information embedded in inter- and intra-modal levels. In this study, we mainly
-
Local dual-graph discriminant classifier for binary classification Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Xiaohan Zheng, Li Zhang, Leilei Yan
Graph-based methods mine the potential structural information of data by constructing various graphs that positively affect the classifiers when dealing with classification problems. However, traditional graph-based classifiers are the most common single-graph classifiers and minimize only intra-class compactness, where inter-class separability is replaced by other factors. To consider real inter-class
-
Proactive cooperative consensus control for a class of human-in-the-loop multi-agent systems with human time-delays Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Zhen Qin, Huai-Ning Wu, Jin-Liang Wang
In this study, we consider a class of human-in-the-loop (HiTL) multi-agent systems that divide agents into two parts: the nonautonomous agents controlled by human operators, and the autonomous agents. First, the human operators’ models are incorporated into the multi-agent system for constructing an HiTL multi-agent system model. Next, the cooperative consensus control problem is explored for the HiTL
-
GRAformer: A gated residual attention transformer for multivariate time series forecasting Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Chengcao Yang, Yutian Wang, Bing Yang, Jun Chen
Recurrent Neural Networks (RNNs), particularly when equipped with output windows – a standard practice in contemporary time series forecasting – have shown proficiency in handling short-term dependencies. Nonetheless, RNNs can encounter challenges in maintaining hidden states over extended forecasting periods, particularly in longer-term predictions where increased hidden state sizes and extended look-back
-
Hierarchical vector transformer vehicle trajectories prediction with diffusion convolutional neural networks Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Yingjuan Tang, Hongwen He, Yong Wang
In dynamic and interactive autonomous driving scenarios, accurately predicting the future movements of vehicle agents is crucial. However, current methods often fail to capture trajectory uncertainty, leading to limitations in trajectory prediction performance. To address these limitations, this paper introduces the hierarchical vector transformer diffusion model, a novel trajectory prediction method
-
Recurrent context layered radial basis function neural network for the identification of nonlinear dynamical systems Neurocomputing (IF 6.0) Pub Date : 2024-03-06 R, a, j, e, s, h, , K, u, m, a, r
This paper proposes a novel recurrent context layered radial basis function neural network (RCLRBFNN) for the identification of nonlinear dynamical systems. The proposed model consists of an additional context layer in which the nodes represent the unit-delayed outputs of the hidden layer radial centers. These delayed outputs undergo a nonlinear transformation by applying a tangent hyperbolic function
-
DARTS-PT-CORE: Collaborative and Regularized Perturbation-based Architecture Selection for differentiable NAS Neurocomputing (IF 6.0) Pub Date : 2024-03-06 Weisheng Xie, Hui Li, Xuwei Fang, Shaoyuan Li
DARTS-PT is a well-known differentiable NAS method that measures the operation strength through its contribution to the supernet performance, extracting architecture from the underlying supernet. However, persistent issues of degraded architecture in DARTS-PT have been identified in recent studies. In response, we undertake a comprehensive analysis of this performance degradation issue and identify