检索结果-内蒙古大学图书馆

An effective medical image fusion method utilizing moth-flame optimization and coupled neural P systems

Neural Computing and Applications 2025年 1-41页

作者： Dinh, Phu-Hung Le, Thi-Hong-Ha Giang, Nguyen Long Faculty of Computer Science and Engineering Thuyloi University 175 Tay Son Dong Da Hanoi Viet Nam Hong Duc University 565 Quang Trung Dong Ve Thanh Hoa Viet Nam Institute of Information Technology Vietnam Academy of Science and Technology Hanoi Viet Nam Graduate University of Science and Technology Vietnam Academy of Science and Technology Hanoi Viet Nam

Medical image fusion is crucial for various applications, yet existing fusion models often encounter issues such as low quality, information loss, and insufficient contrast. This paper presents a novel approach to medical image fusion that directly addresses these challenges by enhancing brightness and contrast, improving overall image quality, and preserving essential structural features. Our method begins by decomposing input images into a base component and two detail components using a three-component decomposition (TCD) method with a truncated Huber filter (THF). The detail components are subsequently fused using an integrated approach combining the structure tensor saliency detection operator (STSDO), distance-weighted regional energy (DWRE), fast guided filter (FGF), and coupled neural P system (CNPS). The base components are then fused through an adaptive method guided by the moth-flame optimization (MFO) algorithm. To evaluate our approach, we used a dataset of 120 pairs of medical images and assessed performance with metrics such as QMLI, QCI, QAG, QAB/F, QP, QW, QE, and QCB. Experimental results demonstrate that the proposed model significantly enhances brightness and contrast and more effectively preserves information compared to recent methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Image fusion

来源：评论

学校读者我要写书评

暂无评论

Cost-Optimized Task Offloading for Dependent Applications in Collaborative Edge and Cloud Computing

引用

IEEE Internet of Things Journal 2025年第9期12卷 12975-12988页

作者： Yuan, Haitao Hu, Qinglong Wang, Shen Bi, Jing Buyya, Rajkumar Lu, Jinhu Yang, Jinhong Zhang, Jia Zhou, MengChu Beihang University School of Automation Science and Electrical Engineering Beijing100191 China City University of Hong Kong Department of Computer Science Kowloon Tong Hong Kong Beijing University of Technology School of Software Engineering Faculty of Information Technology Beijing100124 China Laboratory School of Computing and Information Systems MelbourneVIC3010 Australia CSSC Systems Engineering Research Institute Beijing100036 China Southern Methodist University Lyle School of Engineering Department of Computer Science DallasTX75205 United States New Jersey Institute of Technology Department of Electrical and Computer Engineering NewarkNJ07102 United States

A collaborative system that includes mobile devices (MDs), edge nodes (ENs), and the cloud is needed where ENs at the network edge can run offloaded tasks of MDs with limited resources and energy for timely processing for latency-sensitive applications. Unlike existing studies, we formulate a total cost minimization problem for the system for applications, which can be divided into several interdependent subtasks. Each subtask can be executed in MDs, ENs, and the cloud. This work formulates a mixed-integer nonlinear program to minimize the total system cost. To address it, a novel meta-heuristic optimization algorithm called Genetic Simulated-annealing-based Particle swarm optimization with Auto-Encoder (GSPAE) is proposed, which innovatively combines feature extraction of deep learning and global search of meta-heuristic optimization. Genetic operations provide diverse solutions, the Metropolis acceptance of annealing offers a robust global search, and autoencoders (AEs) extract distribution characteristics of particles toward high-quality regions for fast convergence. Thus, GSPAE optimizes the associations between ENs and MDs and the scheduling of subtasks among MDs, ENs, and the cloud. Experiments with large-scale Google cluster datasets show that compared to state-of-the-art benchmark methods, GSPAE reduces the total cost by at least 17% while strictly meeting limits of application latency, available energy, computing, and communication resources of ENs and MDs. © 2014 IEEE.

关键词： Mobile edge computing

来源：评论

学校读者我要写书评

暂无评论

A Multi-Scale Deep Learning Framework Combining MobileViT-ECA and LSTM for Accurate ECG Analysis

引用

IEEE Access 2025年 13卷 85473-85492页

作者： Ba Mahel, Abduljabbar S. Al-Gaashani, Mehdhar S. A. M. Alkanhel, Reem Ibrahim Hassan, Dina S. M. Muthanna, Mohammed Saleh Ali Muthanna, Ammar Aziz, Ahmed University of Electronic Science and Technology of China School of Life Science and Technology Chengdu610054 China University of Electronic Science and Technology of China School of Resources and Environment Chengdu610056 China Princess Nourah bint Abdulrahman University College of Computer and Information Sciences Department of Information Technology P.O. Box 84428 Riyadh11671 Saudi Arabia Tashkent State University of Economics Department of International Business Management Tashkent Uzbekistan RUDN University Department of Applied Probability and Informatics Peoples’Friendship University of Russia 6 Miklukho-Maklaya St Moscow117198 Russia Faculty of Computer and Artificial Intelligence Benha University Department of Computer Science Egypt Central Asian University Engineering school Tashkent Uzbekistan

Electrocardiogram (ECG) analysis is crucial for diagnosing cardiovascular diseases (CVD), especially atrial fibrillation (AF), a prevalent cardiac rhythm abnormality. However, the variability and complexity of ECG signals make AF classification challenging, highlighting the need for more accurate and reliable methods. This paper introduces a novel deep learning (DL) architecture designed to enhance the processing, feature extraction, and analysis of ECG signals. The proposed model utilizes a hybrid framework that combines standard and dilated convolutional networks, advanced attention mechanisms, and temporal sequence learning to address the complexities of ECG data. A parallel architecture integrates a MobileViT block for efficient spatial feature extraction and an Efficient Channel Attention (ECA) module to refine feature representations. Simultaneously, a Long Short-Term Memory (LSTM) network captures temporal dependencies in the data. The concatenation of the outputs from both the MobileViT-ECA block and the LSTM network allows for the extraction of both local and global features. Fully connected layers, along with dropout regularization, ensure robust performance and effective classification. We analyzed ECG signals of three different lengths (1, 2, and 3 seconds) to investigate how segment length affects model performance. Additionally, we conducted various classification scenarios and an ablation study to simulate real-world conditions and identify key components of the architecture. Our experimental findings show that the model attains high accuracy in ECG classification and AF identification, with average metrics including accuracy of 87.80%, recall of 87.80%, F1-score of 87.45%, and specificity of 95.66%. The proposed model outperforms existing methods on the same AF dataset, demonstrating its superior performance. This method accurately classifies ECG signals and detects AF, highlighting its potential for clinical application. The results help move forwar

关键词： Electrocardiography

来源：评论

学校读者我要写书评

暂无评论

Video classification for efficient data storage using deep learning: a comparison of sequential and simultaneous feature extraction methods

引用

Multimedia Tools and Applications 2025年第6期84卷 3071-3094页

作者： Dang Thi, Phuc Nguyen Dang, Hoang Thi Doan Huu, Phuc Dau Sy, Hieu Department of Computer Science Faculty of Information Technology Industrial University of Ho Chi Minh City 12 Nguyen Van Bao Ho Chi Minh City7000 Viet Nam Department of Applied Physics Faculty of Applied Science University of Technology - Viet Nam National University HCMC To Hien Thanh Ho Chi Minh City7000 Viet Nam

Optimizing camera information storage is a critical issue due to the increasing data volume and a large number of daily surveillance videos. In this study, we propose a deep learning-based system for efficient data storage. Videos captured by cameras are classified into four categories: no action, normal action, human action, and dangerous action. Videos without action or with normal action are stored temporarily and then deleted to save storage space. Videos with human action are stored for easy retrieval, while videos with dangerous action are promptly alerted to users. In the paper, we propose two approaches using deep learning models to address the video classification problem. The first approach is a separate approach, where pretrained CNN models extract features from video frame images. These features are then passed through RNN, Transformer models to extract relationships between them. The goal of this approach is to delve into extracting features of objects in the video. The proposed models include VGG16, InceptionV3 combined with LSTM, BiLSTM, Attention, and Vision Transformer. The next approach combines CNN and LSTM layers simultaneously through models like ConvLSTM and LRCN. This approach aims to help the model simultaneously extract object features and their relationships, with the goal of reducing model size, accelerating the training process, and increasing object recognition speed when deployed in the system. In Approach 1, we construct and refine network architectures such as VGG16+LSTM, VGG16+Attention+LSTM, VGG16+BiLSTM, VGG16+ViT, InceptionV3+LSTM, InceptionV3+Attention+LSTM, InceptionV3+BiLSTM. In Approach 2, we build a new network architecture based on the ConvLSTM and LRCN model. The training dataset, collected from real surveillance cameras, comprises 3315 videos labeled into four classes: no action (1018 videos), actions involving people (832 videos), dangerous actions (751 videos), and normal actions (714 videos). Experimental results show t

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Software Reliability Assessment:An Architectural and Component Impact Analysis

引用

Tsinghua science and technology 2025年第2期30卷 908-925页

作者： Saleh Alyahyan Mohammed Naif Alatawi Mrim M.Alnfiai Shoayee Dlaim Alotaibi Abdullah Alshammari Zaid Alzaid Hathal Salamah Alwageed Applied College in Dwadmi Shaqra UniverityShaqra 11961Saudi Arabia Department of Information Technology University of TabukTabuk 47713Saudi Arabia Department of Information Technology Taif UniversityTaif 21944Saudi Arabia Department of Artificial Intelligence and Data Science University of HailHail 55431Saudi Arabia College of Computer Science and Engineering University of Hafr AlbatinHafar Albatin 31991Saudi Arabia Department of Computer Science Islamic University of MadinahMadinah 42351Saudi Arabia College of Computer and Information Sciences Jouf UniversitySakaka 42421Saudi Arabia

In the software landscape,understanding component impacts on system reliability is pivotal,especially given the unique complexities of modern software *** paper presents a model tailored for software reliability *** approach introduces the“component influence”to measure a single component’s effect on overall system ***,we adapt a state transition model to cater to the diverse architectures of software *** a discrete-time Markov chain,we predict software *** test our model on an actual software system,finding it notably accurate and superior to existing *** work offers a promising direction for those venturing into software reliability enhancement.

关键词： software reliability architectural analysis state transition model

来源：评论

学校读者我要写书评

暂无评论

Early Detection of Childhood Malnutrition Using Survey Data and Machine Learning Approaches 4

Early Detection of Childhood Malnutrition Using Survey Data ...

引用

4th International Conference on Sentiment Analysis and Deep Learning, ICSADL 2025

作者： Zumma, Thoufiq Rahaman, Anikur Islam Prova, Nuzhat Noor Haque, Tasriful Joy Bose, Julias Caeser Youki, Ravina Akter Daffodil International University Department of Computer Science and Engineering Dhaka Bangladesh Washington University Science and Technology Department of Computer Science New York United States Pace University Department of Seidenberg School of Csis New York United States Victorian Institute of Technology Master of Information Technology and Systems Australia University of Wollongong Faculty of Artificial Intelligence and Science Australia University of Technology Sydney Faculty of Engineering and It Australia

ISBN: (纸本)9798331523923

Children's physical, mental and emotional development depends heavily on sleep, with age-specific sleep needs fluctuating. Malnutrition may result from eating too little, absorbing nutrients poorly, being unwell, living in poverty or not knowing enough about nutrition. Food allergies and iron insufficiency are two examples of illnesses whose onsets might differ depending on environmental exposures and genetics. By providing proper diet, getting medical attention when necessary and encouraging healthy behaviors, parents play a crucial role in supporting their children's health. For children to grow and develop properly, they need meals high in fruits, vegetables, milk, protein, calcium, iron and fiber. Key advantages of a balanced diet include aiding bone formation, improving heart health and encouraging regular bowel motions and digestion. In general, children's general health and wellness depend on caregivers being aware of their dietary requirements and giving them the proper attention. The findings of the research imply that machine learning algorithms may be useful in understanding and predicting the prevalence of malnutrition in children. Furthermore, these algorithms could provide perceptive data that might help politicians create effective policies. In this research, we make use of five different machine learning algorithms. With a decision tree, the accuracy is 0.92%, followed by svm which provides 0.91%, KNN, which provides 0.84%, GBM classifier, which provides 0.79% and random forest, which provides 0.65%. © 2025 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Dynamic Modeling and Analysis for Electricity-Gas systems With Electric-Driven Compressors

引用

IEEE Transactions on Smart Grid 2025年第3期16卷 2144-2155页

作者： Huang, Yujia Sun, Qiuye Chen, Zhe Wenzhong Gao, David Bach Pedersen, Torben Guldstrand Larsen, Kim Li, Yushuai Shenyang University of Technology School of Electrical Engineering Shenyang110870 China Northeastern University School of Information Science and Engineering Shenyang110819 China Aalborg University Department of Energy Technology Aalborg9220 Denmark University of Denver Department of Electrical and Computer Engineering DenverCO80208 United States Aalborg University Department of Computer Science Aalborg9220 Denmark

The dynamic gas flow model with static electric driven compressor (EDC) model has been widely studied in coordinated analysis of integrated electricity-gas system (IEGS). However, as a crucial coupling unit, the boost characteristics of the EDC change dynamically with gas state, which may lead to unstable operation mode and then affect safe operating of IEGS. Meanwhile, its nonlinear model greatly increases the difficulty of analysis. This paper proposes a reduced-order transfer function model that considers EDCs for an accurate and efficient dynamic analysis of the IEGS. Firstly, a general two-port model in the Laplace-domain is derived to jointly analyze the pipeline and EDCs dynamic characteristics. The model based on transfer function, explicitly gives the relation between the pressures and flows state at ports. On this basis, to concisely analyze state variations of crucial nodes, the multiple cascaded pipelines and compressors are aggregated and to form an equivalent model. Meanwhile, to reduce the computational burden of the high-order Laplacian "s" in the aggregated process, a reduced-order method is developed based on Jordan continued-fraction expansion by preserving the main gas dynamic feature. Then the analytical expression of state fluctuation can be conveniently derived to analyze the underlying impact and interaction between power system and gas system. Finally, case studies are conducted to prove the effectiveness of proposed model and reduction method. © 2010-2012 IEEE.

关键词： Compressibility of gases

来源：评论

学校读者我要写书评

暂无评论

iWBFCxr: improved weighted box fusion for analyzing chest x ray images for enhancing thoracic abnormalities

引用

International Journal of information technology (Singapore) 2025年第2期17卷 711-720页

作者： Verma, Sonia Devarajan, Ganesh Gopal Sharma, Pankaj Kumar Department of Computer Science and Engineering Faculty of Engineering and Technology SRM Institute of Science and Technology Delhi - NCR Campus Delhi - Meerut Road Modinagar Uttar Pradesh Ghaziabad 201204 India Department of Computer Science ABES Engineering College UP Ghaziabad 201009 India

Chest x-ray studies can be automatically detected and their locations located using artificial intelligence (AI) in healthcare. To detect the location of findings, additional annotation in the form of bounding boxes is required, rather than image-level labeling. Accurate interpretation of chest radiographs is essential for diagnosing thoracic abnormalities. This paper introduces a novel method for abnormality detection in chest radiographs using the VinDr-CXR dataset. Labeled training sets are improved by incorporating data augmentation and advanced pre-processing techniques. To improve the accuracy of anomaly identification, the study makes use of ensemble object detection models, such as the modified weighted boxes fusion (iWBFCxr) technique. With an average precision (AP) of 0.2434 for class 14, experimental results on the VinDr-CXR dataset show an overall mean average precision (mAP) of 0.2791. The iWBFCxr approach, when combined with ensemble predictions, has the potential to improve abnormality localization. By integrating enhanced label merging with ensemble object detection models, our method improves abnormality localization in chest radiographs significantly, improving thoracic abnormality diagnosis accuracy and possibly leading to new medical interventions. © Bharati Vidyapeeth's Institute of computer Applications and Management 2024.

关键词： Automated classification Automated localization Chest radiographs computer vision Deep learning Machine learning Thoracic anomalies

来源：评论

学校读者我要写书评

暂无评论

Contemporary Impact of Cyberbullying on Youngsters: An Appraisal of Psychological, Emotional, Physical Health, and Academic Implications 19

Contemporary Impact of Cyberbullying on Youngsters: An Appra...

引用

19th International Conference on Ubiquitous information Management and Communication, IMCOM 2025

作者： Faith, Fatokun B. Long, Zalizah Awang Hamid, Suraya Malaysian Institute of Information Technology Universiti Kuala Lumpur Kuala Lumpur Malaysia Department of Information Systems Faculty of Computer Science IT Universiti Malaya Kuala Lumpur Malaysia

ISBN: (纸本)9798331507817

Cyberbullying is now a serious issue in contemporary times. The impact of cyberbullying on youngsters is of enormous concern in the public health sector as well as in the cybersecurity field. Several researchers have discussed the impact of cyberbullying from diverse perspectives, however, there is still a large gap in finding the paramount impact of cyberbullying in contemporary times, as well as providing solutions to eradicate this menace, especially as it deals with the negative effects of technology which is emerging daily. This study reviews via a scoping evidence approach suggesting the impact of cyberbullying on youngsters, focusing on the psychological, emotional, physical health, and academic implications. Findings from studies revealed that most youngsters face more of the psychological and emotional consequences of cyberbullying as compared to others discussed in the literature. Interestingly, there were also revelations of how cyberbullying had negative influences on the physical health and academic achievements of youngsters. These findings thus instigate the need for novel approaches that can help curb the rampancy of cyberbullying as well as ensure that decision-makers and stakeholders in the respective institutions put these impacts of cyberbullying into consideration when designing cybersecurity policies to ensure that victims of cyberbullying are assisted to recover, put in place technological solutions that can track and punish offenders and also reduce the rate of cyberbullying victimization. © 2025 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Task Consistent Prototype Learning for Incremental Few-Shot Semantic Segmentation 27th

Task Consistent Prototype Learning for Incremental Few-Shot...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Xu, Wenbo Wu, Yanan Jiang, Haoran Wang, Yang Wu, Qiang Zhang, Jian Faculty of Engineering and Information Technology University of Technology Sydney Sydney2007 Australia School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China Department of Computer Science and Software Engineering Concordia University MontrealH3G2J1 Canada

ISBN: (纸本)9783031783463

Incremental Few-Shot Semantic Segmentation (iFSS) tackles a task that requires a model to continually expand its segmentation capability on novel classes using only a few annotated examples. Typical incremental approaches encounter a challenge that the objective of the base training phase (fitting base classes with sufficient instances) does not align with the incremental learning phase (rapidly adapting to new classes with less forgetting). This disconnect can result in suboptimal performance in the incremental setting. This study introduces a meta-learning-based prototype approach that encourages the model to learn how to adapt quickly while preserving previous knowledge. Concretely, we mimic the incremental evaluation protocol during the base training session by sampling a sequence of pseudo-incremental tasks. Each task in the simulated sequence is trained using a meta-objective to enable rapid adaptation without forgetting. To enhance discrimination among class prototypes, we introduce prototype space redistribution learning, which dynamically updates class prototypes to establish optimal inter-prototype boundaries within the prototype space. Extensive experiments on iFSS datasets built upon PASCAL and COCO benchmarks show the advanced performance of the proposed approach, offering valuable insights for addressing iFSS challenges. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Semantic Segmentation

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：