☆ 4.6 Article

A maximum-entropy-attention-based convolutional neural network for image perception

NEURAL COMPUTING & APPLICATIONS (2023)

相关参考文献

注意：仅列出部分参考文献，下载原文获取全部文献信息。

Article Computer Science, Artificial Intelligence

A structure-self-organizing DBN for image recognition

Qili Chen et al.

Summary: The S-DBN proposed in this paper improves feature learning ability in unsupervised training through strategies such as dropout and regularization-reinforced transfer function. Experimental results show that S-DBN has better generation capability and faster convergence rate compared to traditional methods.

NEURAL COMPUTING & APPLICATIONS (2021)

添加到收藏夹

Article Engineering, Electrical & Electronic

A Novel Explainable Deep Belief Network Framework and Its Application for Feature Importance Analysis

Qili Chen et al.

Summary: Feature analysis and selection in deep learning applications are important, but current methods lack deep insights into training mechanisms due to the perceived "black box" nature of deep learning. This paper introduces novel visualization techniques and feature importance criteria to understand the inner workings of deep belief networks (DBNs) in both unsupervised and supervised training stages, leading to improved model accuracy and performance in car collision prediction.

IEEE SENSORS JOURNAL (2021)

添加到收藏夹

Article Automation & Control Systems

Ensemble Meta-Learning for Few-Shot Soot Density Recognition

Ke Gu et al.

Summary: This study proposes an image-based flare soot density recognition network (FSDR-Net) using meta-learning technology to improve the accuracy of identifying flare gas soot in petrochemical plants.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

CA-Net: Comprehensive Attention Convolutional Neural Networks for Explainable Medical Image Segmentation

Ran Gu et al.

Summary: The study presented a comprehensive attention-based CNN (CA-Net) for medical image segmentation, which significantly improved accuracy and explainability. The CA-Net achieved better segmentation results for skin lesions, placenta, and fetal brain compared to the U-Net model, while reducing the model size by approximately 15 times.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2021)

添加到收藏夹

Article Physics, Multidisciplinary

Entropy as an Objective Function of Optimization Multimodal Transportations

Oleg Bazaluk et al.

Summary: This study explores the optimization and forecasting of multimodal transport under conditions of deterministic, stochastic, and fuzzy risks using the entropy method. A mathematical model is developed to make real-time optimal choices for alternative routes, predict load redistribution at transport nodes, and estimate dynamic changes in turnover through intermediate nodes while considering long-term risks. Analyses and forecasts of cargo turnover through Ukrainian seaports are presented to validate the proposed mathematical model.

ENTROPY (2021)

添加到收藏夹

Article Physics, Multidisciplinary

Rolling Bearing Fault Diagnosis Based on VMD-MPE and PSO-SVM

Maoyou Ye et al.

Summary: The paper presents a solution to improve the fault detection accuracy of rolling bearings using VMD, MPE, and PSO-SVM, achieving higher identification accuracy compared to other methods. Experimentation validates the effectiveness of the proposed method in two cases.

ENTROPY (2021)

添加到收藏夹

Article Automation & Control Systems

Cooperative Fuzzy-Neural Control for Wastewater Treatment Process

Honggui Han et al.

Summary: In this article, a cooperative fuzzy-neural controller is proposed for wastewater treatment process, which improves operation performance by coordinating structure and parameters. The controller demonstrates superior control precision and low computational burden through a balanced redundant structure and optimized global and local parameters coordination.

IEEE TRANSACTIONS ON INDUSTRIAL INFORMATICS (2021)

添加到收藏夹

Article Computer Science, Information Systems

An Improved Bearing Fault Diagnosis Scheme Based on Hierarchical Fuzzy Entropy and Alexnet Network

Xiaoyu Shi et al.

Summary: This article proposes a new method based on VMD algorithm and Alexnet neural network for bearing fault diagnosis and fault detection. By adaptively decomposing non-stationary signals and extracting fault features using hierarchical fuzzy entropy method, as well as utilizing Alexnet to learn the relationship between fault features and bearing health conditions, a higher fault diagnosis accuracy rate is achieved compared to traditional convolutional neural networks.

IEEE ACCESS (2021)

添加到收藏夹

Article Computer Science, Information Systems

Semi-Reference Sonar Image Quality Assessment Based on Task and Visual Perception

Weiling Chen et al.

Summary: Researchers proposed a task- and perception-oriented sonar image quality assessment method, utilizing a semi-reference approach to adapt to the limited bandwidth of underwater communication channels. The final quality indicator is obtained through ensemble learning, achieving high accuracy and generalization ability. Experimental results demonstrate competitive performance, high efficiency, and strong robustness compared to the latest available image quality metrics.

IEEE TRANSACTIONS ON MULTIMEDIA (2021)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Attend and Guide (AG-Net): A Keypoints-Driven Attention-Based Deep Network for Image Recognition

Asish Bera et al.

Summary: The article introduces a novel keypoints-based attention mechanism for visual recognition in still images, improving the ability to discriminate fine-grained changes by capturing spatial structures and semantic regions. The proposed model surpasses state-of-the-art approaches on various benchmark datasets, showcasing its effectiveness in image recognition tasks.

IEEE TRANSACTIONS ON IMAGE PROCESSING (2021)

添加到收藏夹

Article Computer Science, Information Systems

Scene Semantic Recognition Based on Modified Fuzzy C-Mean and Maximum Entropy Using Object-to-Object Relations

Ahmad Jalal et al.

Summary: The study introduces a novel scene semantic recognition framework, which intelligently segments object locations, generates a novel Bag of Features, and utilizes Maximum Entropy for scene recognition. During experiments, the system demonstrated high accuracy rates on various datasets and shows promising applications in different fields.

IEEE ACCESS (2021)

添加到收藏夹

Article Physics, Multidisciplinary

Multi-Level Image Thresholding Based on Modified Spherical Search Optimizer and Fuzzy Entropy

Husein S. Naji Alwerfali et al.

ENTROPY (2020)

添加到收藏夹

Article Chemistry, Multidisciplinary

An Unsupervised Regularization and Dropout based Deep Neural Network and Its Application for Thermal Error Prediction

Yang Tian et al.

APPLIED SCIENCES-BASEL (2020)

添加到收藏夹

Article Automation & Control Systems

Road safety performance function analysis with visual feature importance of deep neural nets

Guangyuan Pan et al.

IEEE-CAA JOURNAL OF AUTOMATICA SINICA (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Automatic Fuzzy Clustering Framework for Image Segmentation

Tao Lei et al.

IEEE TRANSACTIONS ON FUZZY SYSTEMS (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Vision-Based Monitoring of Flare Soot

Ke Gu et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2020)

添加到收藏夹

Proceedings Paper Computer Science, Artificial Intelligence

Discriminative Feature Pyramid Network For Object Detection In Remote Sensing Images

Xiaoqian Zhu et al.

2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN) (2020)

添加到收藏夹

Article Engineering, Electrical & Electronic

Random Forest Ensemble for River Turbidity Measurement From Space Remote Sensing Data

Ke Gu et al.

IEEE TRANSACTIONS ON INSTRUMENTATION AND MEASUREMENT (2020)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Entropy-based Sampling Approaches for Multi-Class Imbalanced Problems

Lusi Li et al.

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING (2020)

添加到收藏夹

Article Computer Science, Information Systems

Automatic Segmentation Algorithm of Ultrasound Heart Image Based on Convolutional Neural Network and Image Saliency

Hui Liu et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Information Systems

Unsupervised EA-Based Fuzzy Clustering for Image Segmentation

Mengxuan Zhang et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Computer Science, Information Systems

Deep Guidance Network for Biomedical Image Segmentation

Pengshuai Yin et al.

IEEE ACCESS (2020)

添加到收藏夹

Article Automation & Control Systems

3-D Fully Convolutional Networks for Multimodal Isointense Infant Brain Image Segmentation

Dong Nie et al.

IEEE TRANSACTIONS ON CYBERNETICS (2019)

添加到收藏夹

Article Computer Science, Information Systems

Analyzing the Dynamics of Lung Cancer Imaging Data Using Refined Fuzzy Entropy Methods by Extracting Different Features

Lal Hussain et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Computer Science, Information Systems

A Biological Mechanism Based Structure Self-Adaptive Algorithm for Fee forward Network and Its Engineering Applications

Guang Han et al.

IEEE ACCESS (2019)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Neighborhood Rough Filter and Intuitionistic Entropy in Unsupervised Tracking

Debarati Bhunia Chakraborty et al.

IEEE TRANSACTIONS ON FUZZY SYSTEMS (2018)

添加到收藏夹

Article Computer Science, Interdisciplinary Applications

Anatomically Constrained Neural Networks (ACNNs): Application to Cardiac Image Enhancement and Segmentation

Ozan Oktay et al.

IEEE TRANSACTIONS ON MEDICAL IMAGING (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Learning a No-Reference Quality Assessment Model of Enhanced Images With Big Data

Ke Gu et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2018)

添加到收藏夹

Article Computer Science, Artificial Intelligence

Evaluating the Visualization of What a Deep Neural Network Has Learned

Wojciech Samek et al.

IEEE TRANSACTIONS ON NEURAL NETWORKS AND LEARNING SYSTEMS (2017)

添加到收藏夹

© Peeref 2019-2024. All rights reserved.