检索结果-内蒙古大学图书馆

Masked hybrid attention with Laplacian query fusion and tripartite sequence matching for medical image segmentation

Neural Computing and applications 2025年第8期37卷 5891-5911页

作者： Ekong, Favour Yu, Yongbin Patamia, Rutherford Agbeshi Sarpong, Kwabena Ukwuoma, Chiagoziem C. Wang, Xiangxiang Ukot, Akpanika Robert Cai, Jingye School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu611731 China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan Chengdu610059 China

Medical image segmentation is pivotal in computer-aided diagnosis systems, demanding high precision and contextual understanding. Vision Transformer-based approaches have gained much attention recently due to their excellent performance and ability to capture long-range dependencies in medical images. However, research shows they suffer from inadequate multi-scale feature integration, poor object localization, and inconsistent mask predictions, leading to sub-optimal segmentation performance. This paper addresses these challenges by redefining semantic medical image segmentation through learnable object queries within an enhanced transformer framework with a masked hybrid attention querying mechanism, optimizing multi-scale feature fusion, object localization, and instance-specific segmentation. First, this study presents a novel transformer-based masked hybrid attention mechanism using Laplacian query fusion on learnable query features and incorporating a novel tripartite sequence matching technique as part of the enhanced decoder block to improve the consistency of mask predictions and optimize decoder queries. The designed hybrid multi-head self- and cross-attention mechanisms aim to selectively integrate multi-scale features, ensuring optimal feature combinations for precise segmentation. Secondly, multiple class tokens are incorporated to improve object localization and capture class-specific characteristics within the transformer framework, leveraging the transformer decoders’ ability to learn distinct instance representations. Experimental results and extensive ablation studies demonstrate the effectiveness of the proposed approach on three publicly available datasets, obtaining better segmentation results compared to various state-of-the-art approaches using various evaluation metrics. Specifically, the proposed model achieves a Dice Score of 95.25%, 92.75%, and 85.25% on LUNA, ISIC, and DRIVE datasets, respectively. © The Author(s), under exclusive licence

关键词： Laplace transforms

来源：评论

学校读者我要写书评

暂无评论

Dual-head alternating attention-based adaptive convolutional framework for improving low-resource and imbalanced text classification

引用

Neural Computing and applications 2025年 1-21页

作者： Agbesi, Victor Kwaku Chen, Wenyu Hossin, Md Altab Ukwuoma, Chiagoziem C. School of Computer Science and Engineering University of Electronic Science and Technology of China No. 2006 Xiyuan Ave West Hi-Tech Zone Sichuan Chengdu China School of Innovation and Entrepreneurship Chengdu University No. 2025 Chengluo Avenue 610106 Sichuan Chengdu China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan Chengdu610059 China

Low-resource imbalance texts pose significant challenges due to class imbalance, adversely affecting the performance of deep learning approaches. To address this issue, we propose a dual-head alternating attention-based adaptive convolutional framework with label embedding (AltXLM-AdaCLE), a novel framework designed for imbalanced text classification in low-resourced datasets. Our framework features a new alternating attention model, which combines a dual-head attention mechanism with a bidirectional long short-term memory network, facilitating dynamic filter generation that adapts to the input data’s characteristics and enhances the capture of relevant features and long-range dependencies. A key innovation in this study is the dual-head attention mechanism, which utilizes an alternating reading sequence to extract information from multiple document segments, thereby minimizing information loss and improving the understanding of complex relationships. Furthermore, we introduce a method for embedding class labels in a shared vector space with the text, allowing the model to leverage label information throughout the classification process, which is particularly beneficial for imbalanced datasets. Our framework also incorporates an adaptive convolutional layer that processes text features and label embeddings, generating more representative features of the underlying data distribution and improving classification performance. Experimental results on six low-resourced imbalance text datasets validate the effectiveness of AltXLM-AdaCLE with an average AUC gain of 26.42%, demonstrating its superiority over existing methods. © The Author(s), under exclusive licence to Springer-Verlag London Ltd., part of Springer Nature 2025.

关键词： Vector spaces

来源：评论

学校读者我要写书评

暂无评论

Comparative analysis of data-driven models on detection and classification of electrical faults in transmission systems: Explainability, applicability and industrial implications

引用

Alexandria engineering Journal 2025年 127卷 75-91页

作者： Ukwuoma, Chibueze D. Cai, Dongsheng Ukwuoma, Chiagoziem C. Otuka, Chinedu I. Huang, Qi College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan 610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan 610059 China OBU Sino-British Collaborative Education Chengdu University of Technology Sichuan 610059 China Information Engineering Department Southwest University of Science and Technology Sichuan Mianyang China

Most data-driven fault detection methods often face challenges in accuracy, adaptability, and real-time implementation, particularly in complex transmission networks. To address these issues, this study presents an in-depth comparative analysis of data-driven models, including machine learning, neural networks, and deep learning techniques, for detecting and classifying electrical faults in transmission lines. A few key gaps were identified to persist particularly in terms of the accuracy, computational complexity, explainability, applicability, and industrial implications of these models. Hence, a Quadratic Discriminant Analysis by Projection (QDA-P) model which effectively captures non-linear relationships between electrical fault features is proposed, enhancing classification accuracy, less computationally complex and explainable for both binary and multi-class scenarios. Using a publicly available simulated dataset generated through MATLAB Simulink to represent various fault types, the QDA-P model achieved binary classification scores of 0.988, 0.980, 0.982, 0.995, and 0.987 while recording a multi-class classification score of 0.982, 0.979, 0.982, 0.982, and 0.980 for accuracy, precision, specificity, recall, and F1-score, respectively. Feature importance analysis showed that voltage at the sending or receiving end of the transmission line for phase A was the most influential while the length of the transmission line in phase A had the lowest importance. In contrast, techniques such as SHAP, LIME, and PDP reveal that the length of the transmission line in Phases A & C significantly influenced Class 1 and Class 5 predictions, with the length of the transmission line in Phase C contributing positively and the length of the transmission line in phase A showing varied effects. An industrial applicability analysis using the Mahalanobis distance plot confirmed that the QDA-P model effectively captured underlying data patterns without significant outliers. These findi

关键词： Discriminant analysis

来源：评论

学校读者我要写书评

暂无评论

A few-shot learning model for renewable energy transmission fault diagnosis in tunnels

引用

Electric Power Systems research 2025年 247卷

作者： Zhang, Zhuofan Cai, Dongsheng Ukwuoma, Chiagoziem C. Huang, Qi College of Energy Chengdu University of Technology Chengdu610059 China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Chengdu610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Chengdu610059 China

The buried high-voltage direct current (HVDC) transmission technology has been successfully applied in domestic projects, addressing challenges such as extreme cold, seismic activity, and high altitudes. However, existing fault diagnosis methods face two main issues: insufficient fault data samples and difficulty in diagnosing multiple or coupled faults. To address these, this paper proposes and optimizes a Siamese neural network-based fault diagnosis model using limited data. The study simulates six fault types, including coupled fault scenarios. Compared to other models, the proposed model achieves an accuracy of over 90 %, while CNN and deep belief network models achieve 75 % and 60 %, respectively. In coupled fault scenarios, the proposed model maintains an accuracy of 93 %, demonstrating its effectiveness. © 2025

关键词： HVDC power transmission

来源：评论

学校读者我要写书评

暂无评论

Advancing cancer diagnosis and prognostication through deep learning mastery in breast, colon, and lung histopathology with ResoMergeNet

引用

Computers in Biology and Medicine 2025年 185卷 109494-109494页

作者： Ejiyi, Chukwuebuka Joseph Qin, Zhen Agbesi, Victor K. Yi, Ding Atwereboannah, Abena A. Chikwendu, Ijeoma A. Bamisile, Oluwatoyosi F. Bakanina Kissanga, Grace-Mercure Bamisile, Olusola O. College of Nuclear Technology and Automation Engineering & Sichuan Industrial Internet Intelligent Monitoring and Application Engineering Research Center Chengdu University of Technology Sichuan Chengdu China Network and Data Security Key Laboratory of Sichuan Province University of Electronic Science and Technology of China Sichuan Chengdu China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu China School of Information and Communication Engineering University of Electronic Science and Technology of China Chengdu China School of Life Science University of Electronic Science and Technology of China Chengdu China

Cancer, a global health threat, demands effective diagnostic solutions to combat its impact on public health, particularly for breast, colon, and lung cancers. Early and accurate diagnosis is essential for successful treatment, prompting the rise of Computer-Aided Diagnosis Systems as reliable and cost-effective tools. Histopathology, renowned for its precision in cancer imaging, has become pivotal in the diagnostic landscape of breast, colon, and lung cancers. However, while deep learning models have been widely explored in this domain, they often face challenges in generalizing to diverse clinical settings and in efficiently capturing both local and global feature representations, particularly for multi-class tasks. This underscores the need for models that can reduce biases, improve diagnostic accuracy, and minimize error susceptibility in cancer classification tasks. To this end, we introduce ResoMergeNet (RMN), an advanced deep-learning model designed for both multi-class and binary cancer classification using histopathological images of breast, colon, and lung. ResoMergeNet integrates the Resboost mechanism which enhances feature representation, and the ConvmergeNet mechanism which optimizes feature extraction, leading to improved diagnostic accuracy. Comparative evaluations against state-of-the-art models show ResoMergeNet's superior performance. Validated on the LC-25000 and BreakHis (400× and 40× magnifications) datasets, ResoMergeNet demonstrates outstanding performance, achieving perfect scores of 100 % in accuracy, sensitivity, precision, and F1 score for binary classification. For multi-class classification with five classes from the LC25000 dataset, it maintains an impressive 99.96 % across all performance metrics. When applied to the BreakHis dataset, ResoMergeNet achieved 99.87 % accuracy, 99.75 % sensitivity, 99.78 % precision, and 99.77 % F1 score at 400× magnification. At 40× magnification, it still delivered robust results with 98.85 % accuracy,

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

The “Japa-Japada” construct: A theoretical framework for exploring the recent medical brain drain scourge in Sub-saharan Africa and the potential medical reverse brain drain

引用

International Journal of Intercultural Relations 2025年 107卷

作者： Thomas, Dara Li, Ying Ukwuoma, Chiagoziem C. Dossa, Joel Business School Sichuan University Sichuan 610064 China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan 610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan 610059 China OBU Sino-British Collaborative Education Chengdu University of Technology Sichuan 610059 China Global Organization of African Academic Doctors (OAAD) Langata Nairobi P.O. Box 14833-00100 Kenya

The emigration of professionals particularly doctors, colloquially known as “Japa”, has created a critical shortage in the country's healthcare workforce. This mass exodus has contributed to one of the world's lowest doctor-to-patient ratios being Nigeria, the focus of this research. In contrast, “Japada”, refers to the potential return of these emigrated professionals, offering an opportunity to mitigate the healthcare crisis. This study introduces the “Japa-Japada” construct, framed within the push-pull theory, to explore the factors driving both medical brain drain and those encouraging medical reverse migration. Leveraging Confirmatory Factor Analysis (CFA) and Structural Equation Modelling (SEM), this research investigates the dimensional drivers for Nigerian doctors' migration decisions, focusing on existential, social, growth, economic, and political factors. The statistical validation demonstrated the model fitness and ranked the critical push factors responsible for medical brain drain as social, political, existential, growth, and economic, respectively and the pull factors as political, economic, social, existential and growth respectively. Conversely, for potential medical reverse brain drain, the key push factors were ranked as growth, social, economic, political, and existential, while pull factors such as social, existential, economic, growth, and political dimensions showed a strong propensity to influence doctors' return to Nigeria. The findings emphasize the complex interplay between push-pull factors and mediating elements such as immigration policies within the broader socio-political landscape whereas validating the insignificance of the moderating elements. Thus, contributing to the global understanding of medical migration and offer actionable strategies for retaining and attracting skilled healthcare professionals in low- and middle-income countries. © 2025 Elsevier Ltd

关键词： Japa Japada Medical Brain Drain Medical Doctors Medical Reverse Brain Drain Migration Satisfaction

来源：评论

学校读者我要写书评

暂无评论

Hydrogen production prediction from Co-gasification of biomass and plastics using attention-gated MLP model

引用

Renewable Energy 2025年 249卷

作者： Ukwuoma, Chiagoziem C. Cai, Dongsheng Bamisile, Olusola Bizi, Antonio M. Amos, Toluwani Joan Delali, Fiasam Linda Thomas, Dara Huang, Qi College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan P.R. 610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan P.R. 610059 China OBU Sino-British Collaborative Education Chengdu University of Technology Sichuan P.R. 610059 China School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Sichuan P.R. 610059 China School of Life Science and Technology University of Electronic Science and Technology of China Sichuan P.R. 610059 China School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan P.R. 610059 China School of Business Administration Sichuan University Sichuan P.R. 610059 China

research explores combining plastics and biowastes to decrease carbon footprints in the cement, iron, and steel industries. Co-gasification of these materials cuts carbon and converts it into hydrogen and syngas. The escalating demand for alternative energy sources has driven significant interest in hydrogen as a clean and efficient fuel. However, accurate prediction techniques are indispensable for ensuring the viability and sustainability of hydrogen production processes. While artificial intelligence models have shown promise in various fields, including computer vision and hydrogen prediction, they often encounter limitations such as low prediction accuracy with few data samples, lack of interpretability in yield result explanations, and susceptibility to adversarial attacks. Addressing these challenges is critical for advancing the reliability and applicability of hydrogen production prediction models. This study presents an attention-gated MLP model (agMLP). This novel end-to-end approach integrates MLP and attention mechanisms to enhance the accuracy and interpretability of hydrogen production prediction from the co-gasification of biomass and plastics. Furthermore, several explainable AI models were implemented to explain the proposed agMLP prediction for human understanding while using the Williams plot to indicate the applicability of the proposed agMLP. Further analysis was carried out using the Fast Gradient Sign Method and Projected Gradient Descent adversarial attack on the proposed agMLP model based on 0.2, 0.4, 0.6, and 0.8 perturbation to establish the associated risk of artificial intelligence model prediction via adversarial attack. Lastly, to compare the result of the agMLP model, nine (9) machine learning regression models and three ensemble models were developed and evaluated. The implemented model's performance was assessed using various evaluation metrics, including Mean Absolute, Mean Squared, Root Mean Squared, Root Mean Squared Logarithmic

关键词： Iron and steel industry

来源：评论

学校读者我要写书评

暂无评论

Provably Secure Authenticated Key-Management Mechanism for e-Healthcare Environment

引用

IEEE internet of Things Journal 2025年

作者： Saleem, Muhammad Asad Li, Xiong Mahmood, Khalid Ghaffar, Zahid Xie, Yong Wang, Guijuan University of Electronic Science and Technology of China School of Computer Science and Engineering Sichuan Chengdu611731 China National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Yunlin Douliu64002 Taiwan National Yunlin University of Science and Technology Graduate School of Engineering Science and Technology Douliu64002 Taiwan Qinghai Institute of Technology School of Computer and Information Science China Qinghai Provincial Laboratory for Intelligent Computing and Application China Key Laboratory of Computing Power Network and Information Security Jinan250353 China Shandong Provincial Key Laboratory of Industrial Network and Information System Security China Shandong Fundamental Research Center for Computer Science Jinan250353 China

The internet of Things (IoT) is rapidly permeating all aspects of human life, involving a network of devices that share sensitive data. A notable application is the e-healthcare systems, which employ connected sensors, medical servers, and wearable devices. However, the public nature of communication in e-healthcare systems poses challenges such as security, privacy, and authentication of participating entities. Recently, many authentication protocols have been introduced to address these challenges. However, most of these protocols remain vulnerable to various security attacks, including device or medical server impersonation, denial of service, physical or cloning, and de-synchronization attacks. Therefore, we introduce an authenticated key-management protocol utilizing hash functions and Cipher-Block Chaining-Advanced Encryption Standard encryption (CBC-AES) encryption. The proposed protocol also employs the Physical Unclonable Function (PUF), which makes it more robust and efficient in resisting physical or cloning attacks. Additionally, the proposed scheme resists various security threats, including impersonation, session key leakage, ephemeral secret leakage, and de-synchronization attacks. We analyze the scheme’s security and reliability through formal and informal analysis. The informal analysis demonstrates that the scheme encompasses crucial security features, while the formal analysis substantiates. Moreover, performance analysis of the proposed protocol with various competing results indicates that our protocol achieves an average reduction in communication and computation overheads by 36.03.% and 41.79%, respectively. © 2014 IEEE.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

RetVes segmentation: A pseudo-labeling and feature knowledge distillation optimization technique for retinal vessel channel enhancement

引用

Computers in Biology and Medicine 2024年 182卷 109150-109150页

作者： Ekong, Favour Yu, Yongbin Patamia, Rutherford Agbeshi Sarpong, Kwabena Ukwuoma, Chiagoziem C. Ukot, Akpanika Robert Cai, Jingye School of Information and Software Engineering University of Electronic Science and Technology of China Sichuan Chengdu610054 China College of Nuclear Technology and Automation Engineering Chengdu University of Technology Sichuan Chengdu610059 China Sichuan Engineering Technology Research Center for Industrial Internet Intelligent Monitoring and Application Chengdu University of Technology Sichuan Chengdu610059 China

Recent advancements in retinal vessel segmentation, which employ transformer-based and domain-adaptive approaches, show promise in addressing the complexity of ocular diseases such as diabetic retinopathy. However, current algorithms face challenges in effectively accommodating domain-specific variations and limitations of training datasets, which fail to represent real-world conditions comprehensively. Manual inspection by specialists remains time-consuming despite technological progress in medical imaging, underscoring the pressing need for automated and robust segmentation techniques. Additionally, these methods have deficiencies in handling unlabeled target sets, requiring extra preprocessing steps and manual intervention, which hinders their scalability and practical application in clinical settings. This research introduces a novel framework that employs semi-supervised domain adaptation and contrastive pre-training to address these limitations. The proposed model effectively learns from target data by implementing a novel pseudo-labeling approach and feature-based knowledge distillation within a temporal convolutional network (TCN) and extracts robust, domain-independent features. This approach enhances cross-domain adaptation, significantly enhancing the model's versatility and performance in clinical settings. The semi-supervised domain adaptation component overcomes the challenges posed by domain shifts, while pseudo-labeling utilizes the data's inherent structure for enhanced learning, which is particularly beneficial when labeled data is scarce. Evaluated on the DRIVE and CHASE_DB1 datasets, which contain clinical fundus images, the proposed model achieves outstanding performance, with accuracy, sensitivity, specificity, and AUC values of 0.9792, 0.8640, 0.9901, and 0.9868 on DRIVE, and 0.9830, 0.9058, 0.9888, and 0.9950 on CHASE_DB1, respectively, outperforming current state-of-the-art vessel segmentation methods. The partitioning of datasets into train

关键词： Sensitivity analysis

来源：评论

学校读者我要写书评

暂无评论

Intra-Graph-Based Few-Shot Link Prediction in Knowledge Graph 6

Intra-Graph-Based Few-Shot Link Prediction in Knowledge Grap...

引用

6th IEEE Conference on Energy internet and Energy System Integration, EI2 2022

作者： Jonathan, Anto Leoba Bamisile, Olusola Cai, Dongsheng Joseph, Ejiyi Chukwuebuka Junior Nkou Nkou, Joseph Huang, Qi Chengdu University of Technology School of Nuclear and Automation Engineering Chengdu China Chengdu University of Technology Sichuan Indust. Internet Intelligent Monitoring and Applic. Engineering Technology Research Center Chengdu China University of Electronic Science and Technology of China School of Information and Software Engineering Chengdu China

ISBN: (纸本)9798350347159

Knowledge graphs (KG) that express the structure of relations between entities have become an increasingly attractive area in research into cognition and intelligence at the human level. One of the most known challenges in KG, which is the fact that a large number of training examples are required for every relation to predict a new triple, has sparked increasing interest in the few-shot link prediction method. Existing work on few-shot link prediction does not fully exploit entity information such as symmetry. In this work, we made a prediction of new triples about relations by observing only a few associative triples. In order to make new predictions of triples, we concentrated on the transfer of the most important common information and the reconciliation of the entity between the set and query set support by using Intra-Graph. Our experiment are lead on two datasets and demonstrated that our results achieved the state-of-the-art in few-shot link prediction. © 2022 IEEE.

关键词： Knowledge graph

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：