检索结果-内蒙古大学图书馆

Electrical and computer engineering Researches (ICECER), International Conference on

作者： Muteb Aljasem Mustafa Alhababi Ali Javed Zaid Aldoulah Mohammed Abouheaf Mohammad Mayyas Wasseem Al-Rousan Robotics Engineering Bowling Green State University Bowling Green OH MI USA Electrical and Computer Engineering Wayne State University Detroit MI USA Department of Software Engineering University of Engineering and Technology Taxila Pakistan Electrical and Electronics Engineering Alasala colleges Dammam Saudi Arabia Department of Engineering Technology Hamilton Miami University OH MI USA Department of Electrical Engineering Philadelphia University Amman Jordan

ISBN: (数字)9798331539733

ISBN: (纸本)9798331539740

Chronic wounds represent a significant global healthcare challenge, affecting millions of individuals and leading to substantial financial burdens. Accurate classification of chronic wounds is crucial for guiding effective treatment strategies, improving patient outcomes, and reducing healthcare costs. However, existing methods in chronic wound classification predominantly focus on binary classification, with limited success in multi-class scenarios. Consequently, there is a need for diagnostic solutions that can reliably classify multiple wound types. To overcome these challenges, we present a novel feature concatenation-based deep learning method for reliable multiclass classification of chronic wounds. Specifically, we employed the DenseNet121 and XceptionNet models for generating effective and compact feature maps that are then passed to a Multilayer perceptron Classifier to accurately identify different types of wounds. The ability of DenseNet121 to truncate redundant features and XceptionNet to handle complex features with fewer computational resources allows us to generate compact and efficient feature maps. We evaluated the performance of our method using the publicly available AZH and Medetec datasets, as well as their augmented versions. Multiple augmentation techniques were employed to increase sample size and diversity, addressing overfitting and class imbalance issues. A rigorous experimental study performed on the AZH, Medetec, and augmented collections demonstrates the effectiveness of our method for multiclass wound classification.

关键词： Deep learning Costs Accuracy Computational modeling Medical services Wounds Multilayer perceptrons Computational efficiency Reliability Overfitting

来源：评论

学校读者我要写书评

暂无评论

Exploring Natural Language Processing Model Acceleration in Molecular Dynamics Simulation Using High-Performance Computing and Machine Learning

Exploring Natural Language Processing Model Acceleration in ...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Qi Du Feng Wang Hui Huang Heng Wan Xiaoyu Wu Chengkun Wu College of Computer Science and Electronic Engineering Hunan University Changsha China Hunan Institute of Scientific and Technical Information Changsha China Laboratory of Digitizing Software for Frontier Equipment National University of Defense Technology Changsha China

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

In molecular dynamics simulations, the integral methods used to calculate molecular trajectories, such as the Verlet integral method, involve significant computational costs. On the premise of ensuring the accuracy of simulation, how to effectively reduce the amount of computation is always a challenging problem. This paper applies Natural Language Processing models to simulate molecular motion trajectories in molecular dynamics, integrating the MPI programming model and machine learning on a high-performance computing platform to achieve MPI parallelization during model training and inference. The results indicate that different types of neural network architectures have a significant impact on inference performance and accuracy. When using the deep spatio-temporal networks model, the mean absolute error is 0.0032. At an atomic scale of 3M, the parallel efficiency with 1024 computational nodes exceeds 90%, demonstrating excellent parallel performance.

关键词： Training Accuracy Computational modeling High performance computing Neural networks Machine learning computer architecture Natural language processing Trajectory Computational efficiency

来源：评论

学校读者我要写书评

暂无评论

USDRL: Unified Skeleton-Based Dense Representation Learning with Multi-Grained Feature Decorrelation

arXiv

引用

arXiv 2024年

作者： Weng, Wanjiang Wang, Hongsong Wang, Junbo He, Lei Xie, Guosen School of Computer Science and Engineering Southeast University Nanjing210096 China Key Laboratory of New Generation Artificial Intelligence Technology and Its Interdisciplinary Applications Ministry of Education China School of Software Northwestern Polytechnical University Xi’an710072 China School of Vehicle and Mobility Tsinghua University Beijing China School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

Contrastive learning has achieved great success in skeleton-based representation learning recently. However, the prevailing methods are predominantly negative-based, necessitating additional momentum encoder and memory bank to get negative samples, which increases the difficulty of model training. Furthermore, these methods primarily concentrate on learning a global representation for recognition and retrieval tasks, while overlooking the rich and detailed local representations that are crucial for dense prediction tasks. To alleviate these issues, we introduce a Unified Skeleton-based Dense Representation Learning framework based on feature decorrelation, called USDRL, which employs feature decorrelation across temporal, spatial, and instance domains in a multi-grained manner to reduce redundancy among dimensions of the representations to maximize information extraction from features. Additionally, we design a Dense Spatio-Temporal Encoder (DSTE) to capture fine-grained action representations effectively, thereby enhancing the performance of dense prediction tasks. Comprehensive experiments, conducted on the benchmarks NTU-60, NTU-120, PKU-MMD I, and PKU-MMD II, across diverse downstream tasks including action recognition, action retrieval, and action detection, conclusively demonstrate that our approach significantly outperforms the current state-of-the-art (SOTA) approaches. Our code and models are available at https://***/wengwanjiang/USDRL. © 2024, CC BY.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Roll With the Punches: Expansion and Shrinkage of Soft Label Selection for Semi-supervised Fine-Grained Learning

arXiv

引用

arXiv 2023年

作者： Duan, Yue Zhao, Zhen Qi, Lei Zhou, Luping Wang, Lei Shi, Yinghuan National Key Laboratory for Novel Software Technology Nanjing University China School of Electrical and Information Engineering The University of Sydney Sydney Australia School of Computer Science and Engineering Southeast University China School of Computing and Information Technology University of Wollongong Australia

While semi-supervised learning (SSL) has yielded promising results, the more realistic SSL scenario remains to be explored, in which the unlabeled data exhibits extremely high recognition difficulty, e.g., fine-grained visual classification in the context of SSL (SS-FGVC). The increased recognition difficulty on fine-grained unlabeled data spells disaster for pseudo-labeling accuracy, resulting in poor performance of the SSL model. To tackle this challenge, we propose Soft Label Selection with Confidence-Aware Clustering based on Class Transition Tracking (SoC) by reconstructing the pseudo-label selection process by jointly optimizing Expansion Objective and Shrinkage Objective, which is based on a soft label manner. Respectively, the former objective encourages soft labels to absorb more candidate classes to ensure the attendance of ground-truth class, while the latter encourages soft labels to reject more noisy classes, which is theoretically proved to be equivalent to entropy minimization. In comparisons with various state-of-the-art methods, our approach demonstrates its superior performance in SS-FGVC. Checkpoints and source code are available at https://***/NJUyued/SoC4SS-FGVC. Copyright © 2023, The Authors. All rights reserved.

关键词： Shrinkage

来源：评论

学校读者我要写书评

暂无评论

Advancing Blackboard Framework: Responsive Trigger Mechanisms and Dynamic Feasibility Conditions for Optimal Knowledge Source Selection

Advancing Blackboard Framework: Responsive Trigger Mechanism...

引用

International Conference on Ubiquitous Information Management and Communication (IMCOM)

作者： Hana Munira Muhd Mukhtar Husna Sarirah Husin Suriana Ismail Azizah Rahmat Roslan Ismail Software Engineering Section Malaysian Institute of Information Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia School of Computer Science Taylor's University Kuala Lumpur Malaysia Centre of Innovative Digital Education & Emerging Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia

ISBN: (数字)9798331507817

ISBN: (纸本)9798331507824

Expert systems (ES) rely heavily on effective control mechanisms to navigate complex problem-solving tasks. These mechanisms govern how ES utilizes knowledge and data to make decisions and execute actions. Optimizing these mechanisms, or addressing the “control problem,” remains a central challenge. Blackboard architectures, with their separation of knowledge and control processes, offer a promising approach. This study introduces an improved control mechanism for blackboard architectures. It focuses on a critical aspect-trigger mechanisms and feasible conditions-for optimal knowledge source selection to participate in the problem-solving process. By leveraging these features, this study aims to enhance decision-making and problem-solving capabilities within complex domains. This paper focuses on the technical details of exploring how it manages the flow of rule activation and execution throughout the problem-solving process.

关键词： Navigation Decision making Process control Information management Problem-solving Expert systems

来源：评论

学校读者我要写书评

暂无评论

Boundary-Guided Learning for Gene Expression Prediction in Spatial Transcriptomics

Boundary-Guided Learning for Gene Expression Prediction in S...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Mingcheng Qu Yuncong Wu Donglin Di Anyang Su Tonghua Su Yang Song Lei Fan Faculty of Computing Harbin Institute of Technology Harbin China School of Astronautics Harbin Institute of Technology Harbin China Space AI Li Auto Beijing China College of Software Jilin University Changchun China Computer Science and Engineering UNSW Sydney Australia

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

Spatial transcriptomics (ST) has emerged as an advanced technology that provides spatial context to gene expression. Recently, deep learning-based methods have shown the capability to predict gene expression from WSI data using ST data. Existing approaches typically extract features from images and the neighboring regions using pretrained models, and then develop methods to fuse this information to generate the final output. However, these methods often fail to account for the cellular structure similarity, cellular density and the interactions within the *** this paper, we propose a framework named BG-TRIPLEX, which leverages boundary information extracted from pathological images as guiding features to enhance gene expression prediction from WSIs. Specifically, our model consists of three branches: the spot, in-context and global branches. In the spot and in-context branches, boundary information, including edge and nuclei characteristics, is extracted using pretrained models. These boundary features guide the learning of cellular morphology and the characteristics of microenvironment through Multi-Head Cross-Attention. Finally, these features are integrated with global features to predict the final *** experiments were conducted on three public ST datasets. The results demonstrate that our BG-TRIPLEX consistently outperforms existing methods in terms of Pearson Correlation Coefficient (PCC). This method highlights the crucial role of boundary features in understanding the complex interactions between WSI and gene expression, offering a promising direction for future research. Codes are available at: https://***/WcloudC0416/BG-TRIPLEX

关键词： Learning systems Pathology Technological innovation Image edge detection Transcriptomics Morphology Predictive models Feature extraction Gene expression Data mining

来源：评论

学校读者我要写书评

暂无评论

Towards Long Video Understanding via Fine-detailed Video Story Generation

arXiv

引用

arXiv 2024年

作者： You, Zeng Wen, Zhiquan Chen, Yaofo Li, Xin Zeng, Runhao Wang, Yaowei Tan, Mingkui The School of Future Technology South China University of Technology Guangzhou China Peng Cheng Laboratory Shenzhen China The School of Software Engineering South China University of Technology Guangzhou China The Artificial Intelligence Research Institute Shenzhen MSU-BIT University China College of Mechatronics and Control Engineering Shenzhen University China The School of Computer Science and Technology Harbin Institute of Technology Shenzhen China

Long video understanding has become a critical task in computer vision, driving advancements across numerous applications from surveillance to content retrieval. Existing video understanding methods suffer from two challenges when dealing with long video understanding: intricate long-context relationship modeling and interference from redundancy. To tackle these challenges, we introduce Fine-Detailed Video Story generation (FDVS), which interprets long videos into detailed textual representations. Specifically, to achieve fine-grained modeling of long-temporal content, we propose a Bottom-up Video Interpretation Mechanism that progressively interprets video content from clips to video. To avoid interference from redundant information in videos, we introduce a Semantic Redundancy Reduction mechanism that removes redundancy at both the visual and textual levels. Our method transforms long videos into hierarchical textual representations that contain multi-granularity information of the video. With these representations, FDVS is applicable to various tasks without any fine-tuning. We evaluate the proposed method across eight datasets spanning three tasks. The performance demonstrates the effectiveness and versatility of our method. Copyright © 2024, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Top-Down Target Object Detection Through Context

Top-Down Target Object Detection Through Context

引用

International Conference on Image and Vision Computing New Zealand, IVCNZ

作者： Ibrahim M. H. Rahman Christopher Hollitt Mengjie Zhang Osama Rehman Aisha Ajmal Simon Jigwan Park Information Technology The Open Polytechnic of New Zealand Wellington New Zealand School of Engg. and Computer Science Victoria University of Wellington Wellington New Zealand Department of Software Engineering Bahria University Karachi Pakistan

ISBN: (数字)9798331518776

ISBN: (纸本)9798331518783

Visual attention is crucial for identifying the most salient regions in an image. However, when the objective involves higher-level visual tasks, such as target object detection, it becomes necessary to incorporate high-level information to guide the search for the target. This process, known as top-down saliency detection, leverages guidance sources like contextual information and target features to identify regions of interest that are more likely to contain the target object. In this paper, we propose a model that generates top-down saliency maps by adjusting the feature map weights of a universal visual attention model based on contextual information. While contextual information has traditionally been used to understand the gist of an image, it has not been integrated into the creation of saliency maps for target object detection. We demonstrate that incorporating contextual information into a visual attention model enhances target object detection performance. The proposed model, tested on six datasets, shows significant improvements in detecting target objects compared to models that do not utilize contextual information.

关键词： Weight measurement Visualization Accuracy Object detection Feature extraction Search problems Tuning Optimization Context modeling Saliency detection

来源：评论

学校读者我要写书评

暂无评论

Detection of Alzheimer's disease using deep learning models: A systematic literature review

引用

Informatics in Medicine Unlocked 2024年 50卷

作者： Mohammed, Eqtidar M. Fakhrudeen, Ahmed M. Alani, Omar Younis Department of Computer Science College of Computer Science and Information Technology University of Kirkuk Kirkuk Iraq Department of Software College of Computer Science and Information Technology University of Kirkuk Kirkuk Iraq School of Science Engineering & Environmnet University of Salford Manchester M5 4WT United Kingdom

Alzheimer's disease (AD) is a progressive neurological disease considered the most common form of late-stage dementia. Usually, AD leads to a reduction in brain volume, impacting various functions. This article comprehensively analyzes the AD context in fivefold main topics. Firstly, it reviews the main imaging techniques used in diagnosing AD disease. Secondly, it explores the most proposed deep learning (DL) algorithms for detecting the disease. Thirdly, the article investigates the commonly used datasets to develop DL techniques. Fourthly, we conducted a systematic review and selected 45 papers published in highly ranked publishers (Science Direct, IEEE, Springer, and MDPI). We analyzed them thoroughly by delving into the stages of AD diagnosis and emphasizing the role of preprocessing techniques. Lastly, the paper addresses the remaining practical implications and challenges in the AD context. Building on the analysis, this survey contributes to covering several aspects related to AD disease that have not been studied thoroughly. © 2024

关键词： AD Alzheimer's disease Challenges Datasets Deep learning Mild cognitive impairment

来源：评论

学校读者我要写书评

暂无评论

A Comprehensive Approach to Identify Stroke based on Real-time Medical Data

A Comprehensive Approach to Identify Stroke based on Real-ti...

引用

Cognitive Robotics and Intelligent Systems (ICC - ROBINS), International Conference on

作者： M. Maragatharajan Shanmugapriya S M. B. Sudhan Deeptha R. Sankar Muthu Paramasivam School of Computing Science and Engineering VIT Bhopal University Kothrikalan Madhya Pradesh India Department of Computer Science and Engineering School of Computing Kalasalingam Academy of Research and Education Srivilliputhur Tamilnadu India Department of Computer Science and Engineering SRM Institute of Science and Technology Ramapuram Chennai Tamilnadu Department of Information Technology SRM Institute of Science and Technology Ramapuram Chennai Tamilnadu India Distinguished Software Engineer Palo Alto Networks Inc Santa Clara California USA

ISBN: (数字)9798350372748

ISBN: (纸本)9798350372755

Strokes or cardiovascular disorders continue to be a major global health concern. Proactive intervention and timely detection greatly reduce the morbidity and death related to strokes. The goal of this research is to build a prediction model using machine learning techniques to assess a person’s risk of stroke based on a variety of sociodemographic and health characteristics. The dataset used in this study consists of a large collection of medical records. It contains important details including age, gender, BMI, smoking habits, heart disease, hypertension, and the type of residential property. Using this information, a Decision Tree Classifier is trained to predict the likelihood of strokes, enabling early detection and customized treatment plans. A Decision Tree Classifier with a predetermined maximum depth is used in the proposed methodology’s rigorous data preprocessing, which includes handling missing values, encoding categorical features, and developing models. Both the training and testing datasets are used to evaluate the model’s performance using evaluation measures including accuracy, precision, and recall. The model’s insights provide important characteristics that influence the prediction of stroke risk, assisting medical professionals in focused risk assessment and preventive intervention. The proposed method has the potential to improve healthcare practices by facilitating prompt interventions and personalized treatment for stroke risk individuals. The proposed model has resulted in 86.78% accuracy for this dataset by using the traditional machine learning algorithms. This work highlights the value of predictive modelling in the healthcare industry by demonstrating how it may improve early detection techniques and lessen the impact of strokes on public health.

关键词： Training Machine learning algorithms Machine learning Predictive models Stroke (medical condition) Real-time systems Risk management

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：