检索结果-内蒙古大学图书馆

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Jesika Debnath Arafath Bin Mohiuddin Al Shahriar Uddin Khondakar Pranta Anamul Sakib Amira Hossain Md. Moniruzzaman Shanto Shamim Forhad Md. Redwan Ahmed Rezaul Haque Shafiur Rahman Dept. of Computer Science Westcliff University Irvine CA USA Department of Collage of Engineering and Technology Westcliff University CA USA Dept. of Computer Science Wright State University Dayton USA Department of Business Administration International American University CA USA Dept. of Computer Science and Engineering East West University Dhaka Bangladesh Dept. of Electrical and Electronics Engineering American International University Bangladesh Dept. of Software Engineering Daffodil International University Dhaka Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Prostate cancer is a widespread disease in men worldwide, posing challenges in early detection due to its diverse nature and the limitations of current diagnostic techniques. In this study, we have developed a new method that combines CNNs with Vision Transformers (ViTs) to improve the classification of prostate cancer using MRI images. To address data imbalance and enhance model robustness, we used dual synthetic oversampling techniques and data augmentation methods. Our preprocessing pipeline reduced noise, preserved edges, and improved local contrast without amplifying noise. For feature extraction, we utilized the GrayLevel Co-occurrence Matrix (GLCM) and shape-based features to represent complex MRI data better. Among the evaluated architectures, ConvNeXt showed the best performance. Using SMOTE, it achieved an F1-score of 97.21% and a MCC of 95.32%. With ADASYN, performance improved further, reaching an F1-score of 98.82% and an MCC of 97.86%. Additionally, we created a web-based application for realtime analysis of prostate MRI scans, which can aid in clinical decision-making. These results demonstrate the potential of our approach to improve the accuracy of prostate cancer diagnosis and provide an interpretable model for clinical use.

关键词： computer vision Accuracy Magnetic resonance imaging Noise Pipelines Transformers Feature extraction Robustness Prostate cancer Resilience

来源：评论

学校读者我要写书评

暂无评论

Rare and Common Types of Retinal Disease Recognition Using Ensemble Deep Learning

Rare and Common Types of Retinal Disease Recognition Using E...

引用

International Conference on Electrical, computer and Communication engineering (ECCE)

作者： Jesika Debnath Al Shahriar Uddin Khondakar Pranta Arafath Bin Mohiuddin Amira Hossain Anamul Sakib Md. Moniruzzaman Shanto Shamim Forhad Abdullah Al-Sakib Rezaul Haque Shafiur Rahman Dept. of Computer Science Westcliff University Irvine CA USA Dept. of Computer Science Wright State University Dayton USA Department of Collage of Engineering and Technology Westcliff University CA USA Department of Business Administration International American University CA USA Dept. of Computer Science and Engineering East West University Dhaka Bangladesh Dept. of Electrical and Electronics Engineering American International University Bangladesh Dept. of Information Technology Westcliff University CA USA Dept. of Software Engineering Daffodil International University Dhaka Bangladesh

ISBN: (数字)9798350357509

ISBN: (纸本)9798350357516

Detecting retinal diseases is crucial for preventing vision loss, but it comes with challenges, such as data imbalance and accurately classifying rare conditions. This study introduces a new ensemble transfer learning model that combines EfficientNetB7, SE-ResNet, DenseNet-169, and NASNet to improve the classification of common and rare retinal diseases. The ensemble uses a probability averaging approach to maximise each architecture’s strengths. Essential preprocessing techniques such as Global Contrast Normalization (GCN) and Total Variation Denoising (TVD) were used to enhance image quality. The model was trained and evaluated on the Retinal Fundus Multi-Disease Image Dataset (RFMiD) 2.0, achieving 98.65% accuracy and an F1-score of 0.96% for common diseases and 99.10% accuracy with an F1-score of 0.97 for rare diseases, outperforming individual models significantly. The ensemble has been integrated into a web-based application that allows clinicians to upload retinal images for instant diagnostic feedback, enabling real-time analysis and visual insights. Despite its strengths, challenges such as high computational demands and reliance on high-resolution photos remain. Future work will improve computational efficiency through model compression techniques and extend the model to other imaging modalities, such as Optical Coherence Tomography (OCT). In conclusion, this study presents a robust and scalable solution for retinal disease classification, potentially improving early detection and providing real-time support in clinical settings, particularly in resource-limited environments.

关键词： Deep learning Visualization Accuracy Computational modeling Optical coherence tomography Transfer learning Imaging Retina Real-time systems Diseases

来源：评论

学校读者我要写书评

暂无评论

Efficient adaptive test case selection for DNNs robustness enhancement

引用

Journal of Systems and software 2025年 229卷

作者： Zhang, Zhiyi Meng, Huanze Ding, Yuchen Chen, Shuxian Yao, Yongming Collage of Computer Science and Technology Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing China Collaborative Innovation Center of Novel Software Technology and Industrialization Jiangsu Nanjing China School of Mathematical Science Yangzhou University Jiangsu Yangzhou China Ministry Key Laboratory for Safety-Critical Software Development and Verification Nanjing University of Aeronautics and Astronautics Jiangsu Nanjing China Army Engineering of PLA Jiangsu Nanjing China

Deep neural networks (DNNs) have been widely used in various fields, and testing for DNN-based software has become increasingly important. To discover potential faults in DNNs, a large number of test cases and their corresponding labels are required. However, labeling so many test cases consumes enormous costs. Although there have been many test case selection techniques for DNN models, these techniques still have problems such as high overhead, low efficiency, and poor diversity. To address this problem, this paper proposes an efficient adaptive test case selection method based on the principle of uniform distribution of test cases called EATS. Based on the idea of adaptive testing, EATS combines the uncertainty of the model and the diversity of faults to calculate the distance of test cases and sort them, then gives priority to test cases with a higher probability of causing faults. We conduct experiments on four popular datasets and four representative DNN models. Experiment results show that, compared with the existing eight methods, EATS performs better in uniformity of test case distribution, diversity of errors found, model optimization, and optimization efficiency. © 2025 Elsevier Inc.

关键词： software testing

来源：评论

学校读者我要写书评

暂无评论

Forecasting Mental Stress Using Machine Learning Algorithms

引用

computers, Materials & Continua 2022年第9期72卷 4945-4966页

作者： Elias Hossain Abdulwahab Alazeb Naif Almudawi Sultan Almakdi Mohammed Alshehri M.Gazi Golam Faruque Wahidur Rahman Department of Software Engineering Daffodil UniversityDhakaBangladesh Collage of Computer Science and Information System University of NajranNajranSaudi Arabia Department of Computer Science and Engineering Khwaja Yunus Ali UniversitySirajganj 6751Bangladesh

Depression is a crippling affliction and affects millions of individuals around the *** general,the physicians screen patients for mental health disorders on a regular basis and treat patients in collaboration with psychologists and other mental health experts,which results in lower costs and improved patient ***,this strategy can necessitate a lot of buy-in from a large number of people,as well as additional training and logistical ***,utilizing the machine learning algorithms,patients with depression based on information generally present in a medical file were analyzed and *** methodology of this proposed study is divided into six parts:Proposed Research Architecture(PRA),Data Pre-processing Approach(DPA),Research Hypothesis Testing(RHT),Concentrated Algorithm Pipeline(CAP),Loss Optimization Stratagem(LOS),and Model Deployment Architecture(MDA).The Null Hypothesis and Alternative Hypothesis are applied to test the *** addition,Ensemble Learning Approach(ELA)and Frequent Model Retraining(FMR)have been utilized for optimizing the loss ***,the Features Importance Interpretation is also delineated in this *** forecasts could help individuals connect with expert mental health specialists more quickly and *** to the findings,71%of people with depression and 80%of those who do not have depression can be appropriately *** study obtained 91%and 92%accuracy through the Random Forest(RF)and Extra Tree *** after applying the Receiver operating characteristic(ROC)curve,79%accuracy was found on top of RF,81%found on Extra Tree,and 82%recorded for the eXtreme Gradient Boosting(XGBoost)***,several factors are identified in terms of predicting depression through statistical data *** the additional effort is needed to develop a more accurate model,this model can be adjustable in the healthcare sector for diagnosing depression.

关键词： Depression analysis mental health machine learning model deployment XGBoost ROC-AUC

来源：评论

学校读者我要写书评

暂无评论

A cost-effective approach using generative AI and gamification to enhance biomedical treatment and real-time biosensor monitoring

引用

Scientific Reports 2025年第1期15卷 1-16页

作者： Khan, Abdullah Ayub Laghari, Asif Ali Alsafyani, Majed Baqasah, Abdullah M. Kryvinska, Natalia Almadhor, Ahmad Alroobaea, Roobaea Gregus, Michal Department of Computer Science Bahria University Karachi Campus Karachi 75260 Pakistan Software Collage Shenyang Normal University Shenyang China Department of Computer Science College of Computers and Information Technology Taif University P. O. Box 11099 Taif 21944 Saudi Arabia Department of Information Technology College of Computers and Information Technology Taif University Taif 21974 Saudi Arabia Department of Information Management and Business Systems Faculty of Management Comenius University Bratislava Odbojárov 10 Bratislava 25 82005 Slovakia Department of Computer Engineering and Networks College of Computer and Information Sciences Jouf University Sakaka 72388 Saudi Arabia

Biosensors are crucial to the diagnosis process since they are designed to detect a specific biological analyte by changing from a biological entity into electrical signals that can be processed for further inspection and analysis. The method provides stability while evaluating cancer cell imaging and real-time angiogenesis monitoring, together with a robust, accurate, and successful identification. Nevertheless, there are several advantages to using nanomaterials in biological therapies like cancer therapy. In support of this strategy, gamification creates a new framework for therapeutic training that provides patients and first aid responders with immunological, photothermal, photodynamic, and chemo-like therapy. Multimedia systems, gamification, and generative artificial intelligence enable us to set up virtual training sessions. In these sessions, game-based training is being developed to help with skin cancer early detection and treatment. The study offers a new, cost-effective solution called GAI, which combines gamification and general awareness training in a virtual environment, to give employees and patients a hierarchy of first aid instruction. The goal of GAI is to evaluate a patient’s performance at each stage. Nonetheless, the following is how the scaling conditions are defined: learners can be divided into three categories: passive, moderate, and active. Through the use of simulations, we argue that the proposed work’s outcome is unique in that it provides learners with therapeutic training that is reliable, effective, efficient, and deliverable. The examination shows good changes in training feasibility, up to 22%, with chemo-like therapy being offered as learning opportunities. © The Author(s) 2025.

关键词： Biomedical treatment Biosensors Cancer diagnosis Gamification Generative artificial intelligence (GenAI) Machine learning (ML)

来源：评论

学校读者我要写书评

暂无评论

Interactive engagment capabilities as an indicator of E-learning systems' usability 7

Interactive engagment capabilities as an indicator of E-lear...

引用

7th International Conference on Advances in computer-Human Interactions, ACHI 2014

作者： Al-Muaythir, Aljawharah Alnafjan, Khalid Al-Kwai, Lamia Software Engineering Department Collage of Computer Science King Saud University Riyadh Saudi Arabia

ISBN: (纸本)9781612083254

Interactive engagement is easier to achieve in traditional learning environments (where face-to-face interaction is assured) than in e-learning environments. Therefore, a set of functionalities should be supported in elearning systems to allow an acceptable level of interactive engagement, such as whiteboards, chartrooms, discussion boards, etc. In this study, some analysis and evaluation was conducted for a number of open source e-learning systems regarding their support for functionalities that aids in creating an interactively engaging learning environment. The evaluation included ATutor, Claroline, Dokeos, Integrated Learning, Information and Work Cooperation System (ILIAS), Modular Object-Oriented Dynamic Learning Environment (Moodle), Online Learning and Training (OLAT), and Sakai. The evaluation result showed that Moodle and Dokeos achieved the best coverage of all possible interactive engagement-supporting capabilities available, thus proving its superiority over other e-learning systems included in this study in providing an interactively engaging learning environment. Copyright © IARIA, 2014.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Behavior-oriented software requirements model and logical properties

Behavior-oriented software requirements model and logical pr...

引用

2nd International Workshop on Intelligent Systems and Applications, ISA2010

作者： Wu, Huai-Guang Wan, Li Wu, Guo-Qing Ling, Xiang Liang, Zheng-Ping School of Computer Science Wuhan University Wuhan China Collage of Software and Engineering Shenzhen University Shenzhen China

ISBN: (纸本)9781424458745

Requirements modeling is a key procedure in requirements engineering and has a important effect on the quality and cost of software. In this paper, we introduce a software behavior oriented requirements model based on our research and give syntax and semantics of the model in detail. In order to affirm correctness and reliability of the requirements model, we descript some properties, such as consistency and safety of system, behavioral trust and behavioral non-termination by means of μ-calculus, and apply to a case. ©2010 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Liquid Neural Networks - Classification and Time Series Forecasting Use Case 8

Liquid Neural Networks - Classification and Time Series Fore...

引用

8th International Artificial Intelligence and Data Processing Symposium, IDAP 2024

作者： Kavakli, Mehmet Ucar, Ferhat Gazi Vocational and Technical Collage Computer Science Department Elazig Turkey Firat University Department of Software Engineering Elazig Turkey

ISBN: (纸本)9798331531492

This study aims to comprehensively examine the potential of Liquid Neural Networks (LNNs) in machine learning field and various application areas. LNNs offer significant advantages over traditional neural networks due to their adaptive learning capacity and dynamic structures. The study involves visual classification using the MNIST dataset and time series analysis on the Yahoo Finance dataset. The performance of the LNN model on these two different datasets has been thoroughly evaluated through the training and testing processes, with results rigorously analyzed. This comprehensive analysis aims to provide an important discussion of the potential uses and advantages of the LNN model. © 2024 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Depth information aided constrained correlation filter for visual tracking 6

Depth information aided constrained correlation filter for v...

引用

6th Annual 2018 International Conference on Geo-Spatial Knowledge and Intelligence, GSKI 2018

作者： Li, Guanqun Huang, Lei Zhang, Peichang Li, Qiang Huo, Yongkai Collage of Information Engineering Shenzhen University NanHai Ave.3688 NanShan Dist Shenzhen China Collage of Computer Science and Software Engineering Shenzhen University NanHai Ave.3688 NanShan Dist Shenzhen China

In this paper, we proposed a novel visual tracking system by constructing the Constrained Correlation Filter (CCF) with Depth Information. More specifically, in our proposed system, to avoid the boundary effects and the fixed shape assumption of conventional Discriminative Correlation Filter (DCF), the shape of target is extracted from depth image provided by RGB-D sensor to construct the CCF, which may prevent the filter from being disturbed by the background noise at the learning stage and enlarge the search region. Moreover, in order to avoid the drifting problem, the update of the model is stopped once part of the target is occluded. The feature weighting coefficients, which reflect the discriminability of the feature channels, are used at the location stage to improve the discriminability. The experimental results show that our method is capable of achieving state-of-the-art performance on Princeton RGB-D tracking benchmark among all public tracking algorithms. © Published under licence by IOP Publishing Ltd.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

A Systematic Survey of Human Ear Biometrics Recognition by using 2D images 3

A Systematic Survey of Human Ear Biometrics Recognition by u...

引用

3rd IEEE International Maghreb Meeting of the Conference on sciences and Techniques of Automatic Control and computer engineering, MI-STA 2023

作者： Elmarzaki, Howayda Abedallah Gargoum, Bothaina F. Abdo, Amina A University of Benghazi Department of Software Engineering Benghazi Libya University of Benghazi Department of Computer Science Benghazi Libya Collage of Computer Technology Department of Artificial Intelligence Benghazi Libya

ISBN: (纸本)9798350319897

Nowadays, one of the most serious issues is secure verification, especially with the advent of artificial intelligence and machine learning and deep learning algorithms. As a result, the research field of recognizing human biometrics has grown significantly, and various types of algorithms have been proposed to help with security. From the available literature, we noticed that researchers were focusing on various systematic surveys for the recognition of human biometrics, including faces, eyes, finger prints, palms, and etc. Despite the popularity of machine and deep learning methods in the field of human hearing prediction, surveys of such methods are rare. In this work, we present an up-to-date survey of the ear recognition field by using 2D images and display the most relevant papers from the most popular databases by applying different techniques based on several criteria. This review presents an overview of the similarities and differences between different works and provides a statistical analysis view of common techniques commonly used in ear recognition literature. The results presented in this report provide insight on the patterns of this field's research. © 2023 IEEE.

关键词： Biometrics

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：