检索结果-内蒙古大学图书馆

Fine-tuned deep transfer learning: an effective strategy for the accurate chronic kidney disease classification

PeerJ computer Science 2025年 11卷 e2800-e2800页

作者： Khan, Zeshan Aslam Waqar, Muhammad Khan, Hashir Ullah Chaudhary, Naveed Ishtiaq Khan, Abeer T.M.A. Ishtiaq, Iqra Khan, Farrukh Aslam Raja, Muhammad Asif Zahoor Electrical and Computer Engineering International Islamic University Islamabad Pakistan International Graduate Institute of Artificial Intelligence National Yunlin University of Science and Technology Yunlin Taiwan Future Technology Research Center National Yunlin University of Science and Technology Yunlin Taiwan Rawal Institute of Health Sciences Rawalpindi Pakistan Technological University Dublin Dublin Ireland Center of Excellence in Information Assurance King Saud University Riyadh Saudi Arabia

Kidney diseases are becoming an alarming concern around the globe. Premature diagnosis of kidney disease can save precious human lives by taking preventive measures. Deep learning demonstrates a substantial performance in various medical disciplines. Numerous deep learning approaches are suggested in the literature for accurate chronic kidney disease classification by compromising on architectural complexity, classification speed, and resource constraints. In this study, deep transfer learning is exploited by incorporating unexplored yet effective variants of ConvNeXt and EfficientNetV2 for accurate and efficient classification of chronic kidney diseases. The benchmark computed tomography (CT)-based kidney database containing 12,446 CT scans of kidney tumor, stone cysts, and normal patients is utilized to train the designed fine-tuned networks. However, due to the highly imbalanced distribution of images among classes, the operation of data trimming is exploited for balancing the number of CT scans in each class, which is essential for designing an unbiased predictive network. By utilizing fine-tuned pre-trained models for our specific task, the training time is reduced leading to a computationally inexpensive solution. After the comprehensive hyperparameters tuning with respect to changes in learning rates, batch sizes, and optimizers, it is depicted that the designed fine-tuned EfficientNetV2B0 network of 23.8 MB in size with only 6.2 million architectural parameters shows substantial diagnostic performance by achieving a generalized test accuracy of 99.75% on balanced CT kidney database. Furthermore, the designed fine-tuned EfficientNetV2B0 attains high precision, recall, and F1-score of 99.75%, 99.63%, and 99.75%, respectively. Moreover, the final fine-tuned EfficientNetV2B0 ensures its scalability by achieving an impressive diagnostic accuracy of 99.73% on the test set of the original CT kidney dataset as well. Through the extensive evaluation of the proposed t

关键词： computerized tomography

来源：评论

学校读者我要写书评

暂无评论

A Triangular Stable Node Network based on Self-supervised Learning for personalized prediction

A Triangular Stable Node Network based on Self-supervised Le...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Qing Liu Qian Gao Jun Fan Zhiqiang Zhang Key Laboratory of Computing Power Network and Information Security Ministry of Education Shandong Computer Science Center (National Supercomputer Center in Jinan) Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Engineering Research Center of Big Data Applied Technology Faculty of Computer Science and Technology Qilu University of Technology (Shandong Academy of Sciences) Jinan China Shandong Provincial Key Laboratory of Industrial Network and Information System Security Shandong Fundamental Research Center for Computer Science Jinan China China Telecom Digital Intelligence Techonology Co Ltd Jinan China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In recent years, research has illuminated the potency of implicit data processing in enhancing user preferences. Nevertheless, barriers remain in breaking through the constraints of implicit information. This study aims to bridge this gap by firstly constructing a triangular stable node network model, tailored to manage implicit information with precision. Recognizing the challenge of pinpointing novel structures within large-scale graphs, we propose SLTSNN— a triangular stable node network based on self-supervised learning for personalized prediction. SLTSNN innovates by maximizing mutual information between graph-level and patch-level representations, while augmenting graph representations through extended enhanced representations. Additionally, it incorporates triangular data associations and introduces a triangular allocation attention network, which emphasizes strongly correlated preference features among similar users. Furthermore, SLTSNN employs contrastive learning to maximize mutual information between graph vectors and hidden representations, distinguishing between high-order global and local representations. The model’s effectiveness in enhancing user preferences and capturing new graph structures is evidenced by its performance on hit rate and normalized discounted cumulative gain metrics across three datasets.

关键词： Measurement Bridges Contrastive learning Signal processing Data processing Vectors Space exploration Resource management Speech processing Mutual information

来源：评论

学校读者我要写书评

暂无评论

Exploring Seasonal Coastal Water Quality Parameter Interactions Through the Self-Organizing Map Neural Network in Eastern Mediterranean: Lebanon as a Case Study

SSRN

引用

SSRN 2025年

作者： Hadjisolomou, Ekaterini El Rahman Hassoun, Abed Fakhri, Milad Ghanem, Abeer Mina, Roula Herodotou, Herodotos Michaelides, Michalis Department of Electrical Engineering Computer Engineering and Informatics Cyprus University of Technology Limassol3036 Cyprus National Center for Marine Sciences P.O. Box 189 Jounieh Lebanon GEOMAR Helmholtz Centre for Ocean Research Kiel Kiel Germany

Coastal water pollution poses significant environmental challenges, leading to severe ecological and public health consequences. Thus, new assessment tools should be developed and refined to manage water quality more efficiently. In this paper, we present the results of Self-Organizing Map (SOM) neural network models utilized to simulate several water quality parameter interactions monitored from several coastal stations in the South-Eastern Mediterranean Sea, namely in Lebanon. Four seasonal SOM models were developed and calibrated based on the available dataset. The SOM’s visualization of the Component Planes (CPs) enabled the examination of water quality parameter interactions and associations on a seasonal basis. Additionally, Pearson correlation analysis between the SOM’s Best Matching Units was calculated for each monitored parameter to augment the CPs analysis. SOM’s clustering of the data samples and assessment of anthropogenic activities nearby the associated monitoring stations, enabled the evaluation of the potential effects from the existing human activities in nearby areas for each monitoring station. Specifically, the seasonal models revealed that specific land uses nearby the monitoring stations like the ANT-2 (near river mouth), SEL-2 (near a chemical plant), BEY- 6 (public beach) are responsible for the coastal water quality degradation in Lebanon. Overall, this paper demonstrates that the SOM model is not only capable of revealing the parameters’ interactions, but also to identify sources of anthropogenic pollution. Therefore, the SOM models might be used as valuable tools in coastal water quality management. © 2025, The Authors. All rights reserved.

关键词： Eutrophication

来源：评论

学校读者我要写书评

暂无评论

OTMEA : Multi-modal Entity Alignment via Optimal Transport

OTMEA : Multi-modal Entity Alignment via Optimal Transport

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Cunda Wang Weihua Wang Xinyu Li Qiuyu Liang Feilong Bao College of Computer Science Inner Mongolia University Hohhot China National and Local Joint Engineering Research Center of Intelligent Information Processing Technology for Mongolian Hohhot China Inner Mongolia Key Laboratory of Multilingual Artificial Intelligence Technology Hohhot China

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

Multi-modal Entity Alignment (MMEA) aims to identify the same entities exhibited in different knowledge graphs (KGs), where the entities are enriched by structure and visual information. Existing MMEA methods learn multi-modal joint entity embeddings by encompassing both modality interaction and modality alignment. However, these approaches predominantly emphasize modality interaction and fail to adequately address the issue of modality heterogeneity. In this paper, we propose a novel approach OTMEA, which leverages optimal transport to mitigate modality heterogeneity from the perspective of modality distributions. Specifically, we view the modality alignment problem as a Wasserstein minimum distance problem involving multimodal distributions. Furthermore, our experiments indicate that employing entity-level attention weights significantly enhances modality alignment through optimal transport. The effectiveness of our method is validated through extensive experiments conducted on five public datasets. The source code is available at https://***/wonderCS1213/OTMEA.

关键词： Visualization Source coding Knowledge graphs Signal processing Acoustics Speech processing

来源：评论

学校读者我要写书评

暂无评论

Outage Analysis of UAV-Assisted Cooperative Cognitive NOMA in IoT-Enabled Air-Ground Networks with Imperfect SIC and CSI

引用

IEEE Internet of Things Journal 2025年

作者： Hao, Yawen Li, Meiling Xue, Peng Bouanani, Faissal El Chen, Wei Han, Zhu Taiyuan University of Science and Technology School of Electronics Information Engineering Taiyuan030024 China Mohammed V University in Rabat ENSIAS Rabat10000 Morocco Tsinghua University Beijing National Research Center for Information Science and Technology Department of Electronic Engineering Beijing100084 China University of Houston Department of Electrical and Computer Engineering HoustonTX77004 United States Kyung Hee University Department of Computer Science and Engineering Seoul446-701 Korea Republic of

This paper addresses the challenges faced by air-ground vehicle networks (AGVN), with a focus on the rapid mobility of both unmanned ground vehicle (UGV) and unmanned aerial vehicles (UAVs) clusters. UAVs employ the non-orthogonal multiple access (NOMA) transmission technique to efficiently transfer data to UGV, aiming to enhance network performance by increasing spectral efficiency and supporting simultaneous transmissions. The system integrates UAV into the network perception environment, enabling cognitive activities and convenient transmission for UGV beyond base station coverage. We provide closed-form outage probability (OP) expressions for UAVs and UGV in two assist modes, i.e., amplify-and-forward UAV (A-UAV) and decode-and-forward UAV (D-UAV), using real-world situations with double Rayleigh fading (DRF) and outdated and imperfect channel state information (ipCSI). Additionally, in both relaying modes, the asymptotic expression for the OP is provided in the high SNR regime for UAV and UGV links. In addition, the system’s diversity order is derived, and the asymptotic analysis shows an intricate interplay of relative speed, channel outdatedness, and OP. Our research results show that when the relative speed decreases or the power increases, the OP decreases. Under the same conditions, the performance of A-UAV is more stable than that of D-UAV. Additionally, the study underscores the importance of assist mode and the number of UAVs in achieving optimal outage performance. Simulation results confirm our analytical results, emphasizing the trade-offs and performance indicators for AGVN system design. The study demonstrates potential avenues for maximizing system performance even within stringent constraints through strategic parameter adjustments. © 2014 IEEE.

关键词： Trucks

来源：评论

学校读者我要写书评

暂无评论

Conditional Diffusion Model for Electrical Impedance Tomography

arXiv

引用

arXiv 2025年

作者： Shi, Duanpeng Zheng, Wendong Guo, Di Liu, Huaping School of Artificial Intelligence Beijing University of Posts and Telecommunications Beijing China School of Electrical Engineering and Automation Tianjin University of Technology Tianjin China Department of Computer Science and Technology Tsinghua University Beijing China Beijing National Research Center for Information Science and Technology China

Electrical impedance tomography (EIT) is a noninvasive imaging technique, which has been widely used in the fields of industrial inspection, medical monitoring and tactile sensing. However, due to the inherent non-linearity and ill-conditioned nature of the EIT inverse problem, the reconstructed image is highly sensitive to the measured data, and random noise artifacts often appear in the reconstructed image, which greatly limits the application of EIT. To address this issue, a conditional diffusion model with voltage consistency (CDMVC) is proposed in this study. The method consists of a pre-imaging module, a conditional diffusion model for reconstruction, a forward voltage constraint network and a scheme of voltage consistency constraint during sampling process. The pre-imaging module is employed to generate the initial reconstruction. This serves as a condition for training the conditional diffusion model. Finally, based on the forward voltage constraint network, a voltage consistency constraint is implemented in the sampling phase to incorporate forward information of EIT, thereby enhancing imaging quality. A more complete dataset, including both common and complex concave shapes, is generated. The proposed method is validated using both simulation and physical experiments. Experimental results demonstrate that our method can significantly improves the quality of reconstructed images. In addition, experimental results also demonstrate that our method has good robustness and generalization performance. Copyright © 2025, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Amorphous boron nitride: synthesis, properties and device application

引用

Nano Convergence 2025年第1期12卷 1-22页

作者： Sattari-Esfahlan, Seyed Mehdi Mirzaei, Saeed Josline, Mukkath Joseph Moon, Ji-Yun Hyun, Sang-Hwa Jang, Houk Lee, Jae-Hyun Institute for Microelectronics TU Vienna 1040 Austria CEITEC BUT Brno University of Technology Purkynova 123 Brno 61200 Czech Republic Fraunhofer Institute for Material and Beam Technology WinterbergstraBe 28 Dresden E01277 Germany Department of Energy Systems Research Ajou University Suwon 16499 South Korea Department of Mechanical Engineering and Materials Science Washington University in St. Louis St. Louis 63130 MO United States Department of Electrical and Computer Engineering Sungkyunkwan University Suwon 16419 South Korea Center for Functional Nanomaterials Brookhaven National Laboratory Upton New York 11973 United States Institute for Functional Intelligent Materials National University of Singapore Singapore 117575 Singapore

Amorphous boron nitride (a-BN) exhibits remarkable electrical, optical, and chemical properties, alongside robust mechanical stability, making it a compelling material for advanced applications in nanoelectronics and photonics. This review comprehensively examines the unique characteristics of a-BN, emphasizing its electrical and optical attributes, state-of-the-art synthesis techniques, and device applications. Key advancements in low-temperature growth methods for a-BN are highlighted, offering insights into their potential for integration into scalable, CMOS-compatible platforms. Additionally, the review discusses the emerging role of a-BN as a dielectric material in electronic and photonic devices, serving as substrates, encapsulation layers, and gate insulators. Finally, perspectives on future challenges, including defect control, interface engineering, and scalability, are presented, providing a roadmap for realizing the full potential of a-BN in next-generation device technologies. © The Author(s) 2025.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Novel design of fractional cholesterol dynamics and drug concentrations model with analysis on machine predictive networks

引用

computers in Biology and Medicine 2025年 184卷 109423-109423页

作者： Raja, Muhammad Junaid Ali Asif Hassan, Shahzaib Ahmed Chang, Chuan-Yu Raza, Hassan Mubeen, Rikza Masood, Zaheer Raja, Muhammad Asif Zahoor Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Yunlin Douliu64002 Taiwan Federal Medical and Dental College Shaheed Zulfiqar Ali Bhutto Medical University Islamabad44000 Pakistan Foundation University Medical College Foundation University Islamabad Pakistan Department of Electrical Engineering Capital University of Science and Technology Islamabad Pakistan Future Technology Research Center National Yunlin University of Science and Technology Yunlin Douliu64002 Taiwan

Within the intricate fabric of human physiology, cholesterol, a lipid present in cell membranes exerts a discernible effect on the concentration of the drug in human body that influence the aspects of drug pharmacokinetics. The objective of this work is to design a case study based fractional order cholesterol drug interaction model that encapsulates the nuanced dynamics inherent in the multifaceted human physiology with identification of essential variables including drug concentration Ksb and cholesterol level γ. The strength of nonlinear autoregressive with exogenous inputs (NARX) neural networks are exploited to predict the temporal dynamics that reveal the hidden intricacies and subtle patterns within the fractional model. Grünwald–Letnikov (GL) based fractional solver is used to generate the synthetic data, serving as a robust foundation for training, testing and validation of the NARX neural networks for different use cases of cholesterol drug interaction control strategies. A thorough comparative analysis based on exhaustive simulation unveiled a marginal distinction between the results obtained from NARX and the outcomes of fractal technique showing remarkably low MSE in the range of 10−12. The strength of the designed methodology is further verified by using other performance metrics such as MSE, regression index, autocorrelation and cross correlation. The integration of genetic and genomic information tailor the model to address the unique characteristics of individual patient facilitating advancement in precision medicines. © 2024 Elsevier Ltd

关键词： Cholesterol Pharmacokinetics Drug interaction Fractional models Neural networks Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Tumor Cellularity Assessment Using Artificial Intelligence Trained on Immunohistochemistry-Restained Slides Improves Selection of Lung Adenocarcinoma Samples for Molecular Testing

引用

American Journal of Pathology 2025年第5期195卷 907-922页

作者： Gertych, Arkadiusz Zurek, Natalia Piaseczna, Natalia Szkaradnik, Kamil Cui, Yujie Zhang, Yi Nurzynska, Karolina Pyciński, Bartłomiej Paul, Piotr Bartczak, Artur Chmielik, Ewa Walts, Ann E. Faculty of Biomedical Engineering Silesian University of Technology Zabrze Poland Department of Pathology and Laboratory Medicine Cedars-Sinai Medical Center Los Angeles California United States Department of Surgery Cedars-Sinai Medical Center Los Angeles California United States F. Widjaja Inflammatory Bowel Disease Institute Cedars-Sinai Medical Center Los Angeles California United States Biostatistics Shared Resource Cedars-Sinai Medical Center Los Angeles California United States Biobank and Research Pathology Resource Cedars-Sinai Medical Center Los Angeles California United States Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Tumor Pathology Department Maria Sklodowska-Curie National Research Institute of Oncology Gliwice Branch Gliwice Poland Hospital for Lung Diseases “Rebirth ” Zakopane Poland

Tumor cellularity (TC) in lung adenocarcinoma slides submitted for molecular testing is important in identifying actionable mutations, but lack of best practice guidelines results in high interobserver variability in TC assessments. An artificial intelligence (AI)–based pipeline developed to assess TC in hematoxylin and eosin (H&E) whole slide images (WSIs) and in tumor areas (TAs) within WSIs includes a new model (CaBeSt-Net) trained to mask cancer cells, benign epithelial cells, stroma in H&E WSIs using immunohistochemistry-restained slides, and a model to detect all cell nuclei. High masking accuracy (>91%) by CaBeSt-Net computed using 1024 H&E regions of interest and intraclass correlation coefficient >0.97 assessing TC assessments reliability by one pathologist and AI in 20 test regions of interest supported the pipeline's applicability to TC assessment in 50 study H&E WSIs. Using the pipeline, TCs assessed in TAs and WSIs were compared with those by three pathologists. Reliabilities of these ratings by the pathologists supported by the pipeline were good (intraclass correlation coefficient >0.82, P < 0.0001). The consistency of sample categorizations as inadequate or adequate (TC ≤ 20% cut point) for molecular testing among the pathologists assessing TCs without AI support was moderate in TAs (κ = 0.410, P < 0.0001) and slight in WSIs (κ = 0.132, nonsignificant). With AI support, the consistency was substantial in both WSIs (κ = 0.602, P < 0.0001) and TAs (κ = 0.704, P < 0.0001). By visualizing cancer and measuring TC in the sample, this novel AI-based pipeline assists pathologists in selecting samples for molecular testing. © 2025 American Society for Investigative Pathology

关键词： artificial intelligence computational pathology immunohistochemical staining lung adenocarcinoma restained slides tumor burden tumor cellularity assessment

来源：评论

学校读者我要写书评

暂无评论

Multi-Objective Discrete Extremal Optimization of Variable-Length Blocks-Based CNN by Joint NAS and HPO for Intrusion Detection in IIoT

引用

IEEE Transactions on Dependable and Secure Computing 2025年

作者： Lu, Kang-Di Huang, Jia-Cheng Zeng, Guo-Qiang Chen, Min-Rong Geng, Guang-Gang Weng, Jian Donghua University College of Information Science and Technology Shanghai201620 China Jinan University College of Cyber Security The National Joint Engineering Research Center of Network Security Detection and Protection Technology Guangzhou510632 China South China Normal University School of Computer Science Guangzhou510631 China

Industrial Internet of Things (IIoT) is an important part of industrial infrastructure but facing serious and evolving security threats in recent years. Deep learning has been widely considered as a promising solution for enhancing the security of IIoT. However, these existing deep learning models utilized in the intrusion detection of IIoT are manually developed that not only greatly rely on the experience of the designers but also is lack of utility due to the high model complexity. By taking into account the trade-off between the model performance and model complexity, this paper makes the first attempt to propose a multi-objective joint optimization method of neural architecture search (NAS) and hyper-parameter optimization (HPO) based on multi-objective discrete extremal optimization (MODEO) to automatically design a lightweight convolutional neural network (CNN) for the intrusion detection task of IIoT, abbreviated as MODEO-CNN. A novel hybrid variable-length encoding strategy is developed by combing binary and integer encoding to characterize both the neural architectures including the number of blocks, the blocks-based network topology and the corresponding architecture parameters in CNN block, and some important hyper-parameters including batch size, learning rate, weight optimizer and regularization. The individual-based discrete multi-objective evolutionary process of MODEO is designed to obtain the Pareto-optimal CNN models. Three widely-used IIoT intrusion detection datasets, including the Gas Pipeline, BoT-IoT, and Power System Attack datasets, have been used to illustrate the superiority of the proposed MODEO-CNN over the state-of-the-art hand-craft models and two single-objective fixed-length blocks-based NAS models in terms of accuracy, precision, recall, F1-Score, and model's million floating point operations. © 2004-2012 IEEE.

关键词： Encoding (symbols)

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：