检索结果-内蒙古大学图书馆

Dynamic Ensemble Transfer Learning with Multi-View Ultrasonography for Improving Thyroid Cancer Diagnostic Reliability

学校读者我要写书评

暂无评论

SSRN 2024年

作者： Zhang, Xinyu Liu, Feng Lee, Vincent Cheng Siong Jassal, Karishma Muzio, Bruno Di Lee, James C. Northwestern Polytechnical University School of Electronics and Information Shaanxi Xi’an710072 China Sichuan University West China Hospital Sichuan Chengdu610041 China Monash University Faculty of IT Department of Data Science & AI MelbourneVIC3800 Australia Southeast University Monash Suzhou Campus Jiangsu Suzhou215123 China Alfred Hospital Monash University Endocrine Surgery Unit MelbourneVIC3004 Australia Monash University School of Translational Medicine Department of Surgery MelbourneVIC3004 Australia Alfred Hospital Department of Radiology MelbourneVIC3004 Australia Monash University Australia School of Computing & Information Technology Alfred Health Australia

Diagnostic decision-making requires the integration of relevant facts and clinician experience. Incorporating the clinical experience from diverse backgrounds is beneficial in multi-disciplinary model to mitigate uncertainties aroused by incomplete mastery of knowledge. However, current computer-aided diagnostic systems are generally designed using unitary datasets and are challenging to adapt to diverse institutions, leading to the limited reliability of the generated decisions. Accordingly, this study proposes a dynamic ensemble transfer learning-based system that simulates such diversity in its training and structure by integrating knowledge and data. The approach consists of a self-directed model selection scheme, a dynamic weighting mechanism, and a unified weighted ensemble averaging model, tailored for reliable diagnostic decision-making. This study adopts the most rapidly rising malignancy worldwide, thyroid cancer, for evaluation. Two multi-view thyroid ultrasonography datasets with matching tissue diagnosis from over 700 cross-national patients are used to pre-train the individual networks. The learnt knowledge is then transferred to the weighted ensemble averaging model through the dynamic weighting mechanism. The fine-tuned ensemble model is evaluated using an external set of thyroid nodules with radiological risk of malignancy based on the Thyroid Imaging Reporting and data System. Further, we alter the datasets through up-sampling and down-sampling to evaluate the ensemble model's generalisation. Extensive experiments demonstrate the proposed ensemble model yields promising performance with an area under curve value between 0.87 and 0.93 under diversified strategies. Benchmarking results show the proposed approach surpasses existing studies and improves diagnostic reliability in thyroid cancer care while guiding subsequent management options. © 2024, The Authors. All rights reserved.

关键词： Diseases

A novel deep learning-based spider wasp optimization approach for enhancing brain tumor detection and physical therapy prediction

学校读者我要写书评

暂无评论

Computer Methods and Programs in Biomedicine Update

Computer Methods and Programs in Biomedicine Update 2025年 7卷

作者： Suleiman Daoud Ahmad Nasayreh Khalid M.O. Nahar Wlla k. Abedalaziz Salem M. Alayasreh Hasan Gharaibeh Ayah Bashkami Amer Jaradat Sultan Jarrar Hammam Al-Hawamdeh Absalom E. Ezugwu Raed Abu Zitar Aseel Smerat Vaclav Snasel Laith Abualigah Neurosurgery Department Faculty of Medicine Jordan University of Science and Technology Irbid 22110 Jordan Artificial Intelligence and Data Innovation Office King Hussein Cancer Center Amman Jordan Department of Information Technology and Computer Sciences Yarmouk University Irbid 211633 Jordan Department of Rehabilitation science Faculty of applied medical science Jordan University of Science and Technology King Abdullah University Hospital Irbid Jordan Department of Medical Laboratory Sciences Al Balqa Applied University Salt Jordan Unit for Data Science and Computing North-West University 11 Hofman Street Potchefstroom 2520 South Africa College of Engineering and Computing Liwa University Abu Dhabi United Arab Emirates Faculty of Educational Sciences Al-Ahliyya Amman University Amman 19328 Jordan Computer Technologies Engineering Mazaya University College Nasiriyah Iraq Faculty of Electrical Engineering and Computer Science VŠB-Technical University of Ostrava 70800 Poruba-Ostrava Czech Republic Computer Science Department Al al-Bayt University Mafraq 25113 Jordan

A brain tumor, one of the deadliest disorders, is characterized by the abnormal growth of synapses in the brain. Early detection can improve brain tumor diagnosis, and accurate diagnosis is essential for effective treatment. Researchers have developed several deep-learning classification methods to diagnose brain tumors. Moreover, these types of tumorscan significantly impair physical activity, presenting a broad spectrum of symptoms. As a result, each patient requires an individualized physical therapy treatment plan tailored to their specific needs. However, some challenges remain, including the need for a competent expert in classifying brain tumors using deep learning models, as well as the challenge of creating the most accurate deep learning model for brain tumor classification. To address these challenges, we present a highly accurate and efficient methodology based on advanced metaheuristic algorithms and deep learning. To identify different types of pediatric brain tumors, we specifically develop an optimal residual learning architecture. We also present the Spider Wasp Optimization (SWO) algorithm, which aims to improve performance by feature selection. The algorithm enhances the effectiveness of optimization by balancing the speed of convergence and diversity of solutions. We first convert the algorithm from continuous to binary, combine it with the K-Nearest Neighbor (KNN) algorithm for classification, and evaluate it on a dataset of brain MRI images collected from King Abdullah Hospital. Our analysis revealed that in terms of metrics such as accuracy, sensitivity, specificity, and f1-score, it outperformed other conventional algorithms. We demonstrate the overall effectiveness of the proposed model by using it to select the optimal features extracted from the Resnet50V2 model for pediatric brain tumor detection. We compared the proposed SWO+KNN model with other deep learning architectures such as MobileNetV2, Resnet50V2, and machine learning algorithms

关键词： Brain tumor Pediatric Machine learning Rehabilitation Physical therapy Deep learning Metaheuristic optimization Feature selection

An Enhanced Vision Transformer with Autoencoder for Noise Reduction in Knee X-Rays

学校读者我要写书评

暂无评论

SSRN 2025年

作者： Mahmood, Jabar Hamza Abdulnabi, Mohamed Shabbir Pasha, Malaika Azeem, Muhammad Ali, Aitizaz Department of Computer Science International Institute of Science Art and Technology Punjab Gujranwala Pakistan Faculty of Computing and Information Technology University of Sialkot Daska Road Punjab Sialkot51040 Pakistan State Key Laboratory of Blockchain and Data Security School of Cyber Science and Technology College of Computer Science and Technology Zhejiang University Zhejiang Hangzhou310007 China Asia Pacific University of Technology and Innovation Kuala Lumpur57000 Malaysia

Traditional methods for medical image denoising, such as Filtering and Convolutional NeuralNetworks, have shown limitations, particularly in preserving image integrity. Recent developmentsin Vision Transformers (ViTs) demonstrate encouraging denoising capabilities but come at the cost ofhigh resource consumption. To solve this, we present an efficient model, the Denoising AutoencoderVision Transformer (DAE-VIT). It is designed specifically for knee X-ray denoising. Unlike the largeSwin Transformer UNet (SUNET), which utilizes 99M parameters, DAE-VIT significantly reducesthe computational burden with only 5.8M parameters while maintaining superior performance. Weevaluated the model on a supervised dataset of knee images. The model gave promising results, withMean Squared Error (MSE) of 0.0036, Mean Absolute Error (MAE) of 0.022, Root Mean Square Error(RMSE) of 0.060, Normalized Cross-Correlation (NCC) of 0.962, Peak Signal-to-Noise Ratio (PSNR)of 32.177, and Structural Similarity Index (SSIM) of 0.872. These scores show the effectiveness ofDAE-VIT in noise reduction while preserving critical image details and make it a favorable alternativefor resource-efficient medical image denoising tasks. © 2025, The Authors. All rights reserved.

关键词： Salt and pepper noise

UseGeo - A UAV-based multi-sensor dataset for geospatial research

学校读者我要写书评

暂无评论

ISPRS Open Journal of Photogrammetry and Remote Sensing 2024年 13卷

作者： Nex, F. Stathopoulou, E.K. Remondino, F. Yang, M.Y. Madhuanand, L. Yogender, Y. Alsadik, B. Weinmann, M. Jutzi, B. Qin, R. ITC Department of Earth Observation Science Faculty ITC University of Twente Enschede Netherlands 3D Optical Metrology (3DOM) Unit Bruno Kessler Foundation (FBK) Trento Italy Visual Computing Group University of Bath Bath United Kingdom Department of Physical Geography Faculty of Geosciences University of Utrecht Utrecht Netherlands Inter-university Department of Regional & Urban Studies and Planning (DIST) Politecnico di Torino Italy Institute of Photogrammetry and Remote Sensing Karlsruhe Institute of Technology Karlsruhe Germany Geospatial Data Analytics Laboratory The Ohio State University Columbus United States Department of Civil Environmental and Geodetic Engineering The Ohio State University Columbus United States Department of Electrical and Computer Engineering The Ohio State University Columbus United States Translational Data Analytics Institute The Ohio State University Columbus United States

3D reconstruction is a long-standing research topic in the photogrammetric and computer vision communities;although a plethora of open-source and commercial solutions for 3D reconstruction have been released in the last few years, several open challenges and limitations still exist. Undoubtedly, deep learning algorithms have demonstrated great potential in several remote sensing tasks, including image-based 3D reconstruction. State-of-the-art monocular and stereo algorithms leverage deep learning techniques and achieve increased performance in depth estimation and 3D reconstruction. However, one of the limitations of such methods is that they highly rely on large training sets that are often tedious to obtain;even when available, they typically refer to indoor, close-range scenarios and low-resolution images. Especially while considering UAV (Unmanned Aerial Vehicle) scenarios, such data are not available and domain adaptation is not a trivial challenge. To fill this gap, the UAV-based multi-sensor dataset for geospatial research (UseGeo - https://***/home) is introduced in this paper. It contains both image and LiDAR data and aims to support relevant research in photogrammetry and computer vision with a useful training set for both stereo and monocular 3D reconstruction algorithms. In this regard, the dataset provides ground truth data for both point clouds and depth maps. In addition, UseGeo can be also a valuable dataset for other tasks such as feature extraction and matching, aerial triangulation, or image and LiDAR co-registration. The paper introduces the UseGeo dataset and validates some state-of-the-art algorithms to assess their usability for both monocular and multi-view 3D reconstruction. © 2024 The Authors

关键词： 3D reconstruction Deep learning LiDAR Monocular depth estimation Multi-view stereo Stereo matching UAV

2828 The influence of ethnicity and social disadvantage on frailty in a United Kingdom (UK) populationGet access

学校读者我要写书评

暂无评论

Age and Ageing 2025年第SUPPLEMENT_1期54卷

作者： Heald, AH Lu, W Williams, R McCay, K Stedman, M O’Neill, TW The School of Medicine and Manchester Academic Health Sciences Centre University of Manchester Department of Endocrinology and Diabetes Salford Royal Hospital Salford Department of Computing & Mathematics Faculty of Science and Engineering Manchester Metropolitan University Division of Informatics Imaging and Data Science University of Manchester RES Consortium Andover Centre for Epidemiology Versus Arthritis University of Manchester Department of Rheumatology Salford UK

How generative Artificial Intelligence can transform drug discovery?

学校读者我要写书评

暂无评论

European journal of medicinal chemistry 2025年 295卷 117825页

作者： Ainin Sofia Jusoh Muhammad Akmal Remli Mohd Saberi Mohamad Tristan Cazenave Chin Siok Fong Institute for Artificial Intelligence and Big Data Universiti Malaysia Kelantan Kota Bharu 16100 Kelantan Malaysia Faculty of Data Science and Computing Universiti Malaysia Kelantan Kota Bharu 16100 Kelantan Malaysia. Electronic address: tgaininsofia98@***. Faculty of Data Science and Computing Universiti Malaysia Kelantan Kota Bharu 16100 Kelantan Malaysia. Electronic address: akmal@umk.edu.my. Health Data Science Lab Department of Genetics and Genomics College of Medical and Health Sciences United Arab Emirates University Al Ain 15551 United Arab Emirates Faculty of Engineering and Technology Multimedia University 75450 Melaka Malaysia Department of Biosystems Engineering Faculty of Agricultural Technology Universitas Brawijaya 65145 Malang East Java Indonesia. Electronic address: saberi@uaeu.ac.ae. LAMSADE Université Paris Dauphine - PSL Paris France. Electronic address: cazenave@lamsade.dauphine.fr. UKM Medical Molecular Biology Institute (UMBI) 56000 Kuala Lumpur Malaysia. Electronic address: chinsiokfong@ppukm.ukm.edu.my.

Generative Artificial Intelligence (Generative AI) is transforming drug discovery by enabling advanced analysis of complex biological and chemical data. This review explores key Generative AI models, including Generative Adversarial Networks (GANs), Variational Autoencoders (VAEs), flow-based models and Transformer-based models, with Transformers gaining prominence due to the abundance of text-based biological data and the success of language models like ChatGPT. The paper discusses molecular representations, performance evaluation metrics, and current trends in Generative AI-driven drug discovery, such as protein-protein interactions (PPIs), drug-target interactions (DTIs) and de-novo drug design. However, these approaches face significant challenges, including applicability domain issues, lack of interpretability, data scarcity, novelty, scalability, computational resource limitations, and the absence of standardized evaluation metrics. These challenges hinder model performance, complicate decision-making, and limit the generation of novel and viable drug candidates. To address these issues, strategies such as hybrid models, integration of multiomics datasets, explainable AI (XAI) techniques, data augmentation, transfer learning, and cloud-based solutions are proposed. Additionally, a curated list of databases supporting drug discovery research is provided. The review concludes by emphasizing the need for optimized AI models, robust validation methods, interdisciplinary collaboration, and future academic efforts to fully realize the potential of Generative AI in advancing drug discovery.

关键词： database Drug discovery Drug-target interactions Generative artificial Intelligence Molecules representations Performance metrics Protein-protein interactions

Ed-Tgan: A Methodology on Temporal Generative Gan for Imbalanced data for Predicting Academic Performance of Students

学校读者我要写书评

暂无评论

SSRN 2022年

作者： Waheed, Hajra Zhou, Jia Aljohani, Naif R. Tuarob, Suppawong Nawaz, Raheel Herrera, Francisco Hassan, Saeed-Ul Information Technology University 346-B Ferozepur Road Lahore Pakistan Key Laboratory of Intelligent Education Technology and Application of Zhejiang Province Zhejiang Normal University Zhejiang Jinhua321004 China Faculty of Computing and Information Technology King Abdulaziz University Jeddah Saudi Arabia Faculty of Information and Communication Technology Mahidol University Thailand Staffordshire University Stoke-on-Trent United Kingdom Andalusian Research Institute in Data Science and Computational Intelligence University of Granada Granada Spain Manchester Metropolitan University Manchester United Kingdom

With the increase in the self-paced learning phenomenon, class imbalance in the learning analytics community has become more prevalent, with lesser students dropping out than students who intend to pursue. Similarly, an imbalance in the behavioral performances of students is also observed. This imbalance problem becomes more complicated for temporal data, where each time sequence represents a particular student, and several sequences formulate the overall engagement of students throughout a course. The conventional methods for generating synthetic data do not account for this association of sequences, where each synthetically generated student is associated with its previous sequence. Generative Adversarial Networks (GANs) have been rapidly adopted in the machine learning discipline for synthetic data generation to reduce the class imbalance. In this study, we propose a deep learning-powered methodology called Educational Temporal Generative Adversarial Networks (Ed-TGANs) methodology comprising the following steps: a) Smart data Processing for Actionable data, b) GANs for Temporal data Generation, and c) Learning Approach. Furthermore, the Open University Learning Analytics dataset was deployed as a case study comprising 69% pass and 31% fail students to validate the effectiveness of our proposed methodology, encompassing discrete and continuous features. The results are compared with GAN-based and non-GAN upsampling approaches to demonstrate the proposed methodology's effectiveness, which shows an increase in accuracy of up to 5.33% compared to classic GANs, resulting in improved understating of student behavior. We believe that the presented methodology can be used as a starting point for various areas for upsampling jobs with temporal longitudinal data. © 2022, The Authors. All rights reserved.

关键词： Students

Investigation of the hyperchaos and control in the fractional order financial system with profit margin

学校读者我要写书评

暂无评论

Partial Differential Equations in Applied Mathematics 2024年 9卷

作者： Johansyah, Muhamad Deni Sambas, Aceng Qureshi, Sania Zheng, Song Abed-Elhameed, Tarek M. Vaidyanathan, Sundarapandian Sulaiman, Ibrahim Mohammed Department of Mathematics Faculty of Informatics and Computing Universiti Sultan Zainal Abidin Campus Besut Terengganu 22200 Malaysia Department of Mechanical Engineering Universitas Muhammadiyah Tasikmalaya Tamansari Gobras Tasikmalaya 46196 Indonesia Department of Computer Science and Mathematics Lebanese American University Beirut 13-5053 Lebanon Department of Mathematics Near East University Mersin 99138 Turkey Department of Basic Sciences and Related Studies Mehran University of Engineering and Technology Jamshoro 72060 Pakistan School of Data Science Zhejiang University of Finance and Economics Hangzhou 310018 China Institute of Mathematics and Interdisciplinary Sciences Zhejiang University of Finance and Economics 310018 China Department of Mathematics Faculty of Science Assiut University Assiut 71516 Egypt Centre for Control Systems Vel Tech University Avadi Tamil Nadu Chennai 600062 India Institute of Strategic Industrial Decision Modelling School of Quantitative Sciences Universiti Utara Malaysia Sintok Bukit Kayu Hitam Kedah 06010 Malaysia Faculty of Education and Arts Sohar University Sohar 311 Oman

This research study proposes a novel hyperchaotic finance system with profit margin and then utilizes the Adomian Decomposition Method (ADM) to tackle the solution of the associated Caputo-derivative based fractional-order hyperchaotic finance system with profit margin. Numerical simulations and analyses, such as the evaluation of Lyapunov exponents (LE), the creation of bifurcation diagrams (BD), the complexity analysis (CA), and the 0-1 test, are used to get a full picture of the system. The results of our study demonstrate the occurrence of periodic, chaotic, and hyperchaotic dynamics in the system. Furthermore, the overall criteria for the existence and the uniqueness of the exact solutions for Caputo fractional-order models are presented. In addition, we present a control methodology for the fractional-order hyperchaotic financial system utilizing the Laplace transform and linear feedback control. Significantly, our research showcases a noteworthy correlation between the analytical results and numerical simulations, emphasizing the soundness and effectiveness of our methodology. © 2024 The Author(s)

关键词： Chaotic system Financial system Fractional order Hyperchaos

Machine-Learning Methods for Detecting Tuberculosis in Ziehl-Neelsen Stained Slides: A Systematic Literature Review

学校读者我要写书评

暂无评论

SSRN 2023年

作者： Tamura, Gabriel Llano, Gonzalo Aristizábal, Andrés Valencia, Juan Sua, Luz Fernanda Fernandez, Liliana Department of Computing and Intelligent Systems Universidad Icesi Valle del Cauca Cali Colombia Center of Artificial Intelligence and Data Science Universidad Icesi Valle del Cauca Cali Colombia Universidad Icesi Valle del Cauca Cali Colombia Faculty of Health Sciences Universidad Icesi Valle del Cauca Cali Colombia Department of Pathology and Laboratory Medicine Fundación Valle del Lili Valle del Cauca Cali Colombia Department of Internal Medicine Pulmonology Service Fundación Valle del Lili Valle del Cauca Cali Colombia

In recent years, different Machine Learning (ML) methods applied to medical image analysis have been increasingly used for the detection of Mycobacterium Tuberculosis (MT) in Ziehl-Neelsen stained human samples, since manual detection and counting of bacteria is a tedious, costly, error-prone and slow task. This paper presents the results of a Systematic Literature Review (SLR) that comprehensively surveyed and analyzed the current stateof-the-art ML methods and approaches that have been used for TB detection in the period of 2017-2022, as well as their achieved metrics and the characteristics of the datasets on which they were applied. The primary goal of this⋆ This work was supported by Tecnoquímicas Corp. in partnertship with Fundación Valle del Lili and Universidad Icesi with the aim to strenghten the research and development of technology in health in the Valle del Cauca region. © 2023, The Authors. All rights reserved.

关键词： Computer vision