检索结果-内蒙古大学图书馆

22nd IEEE International Symposium on Biomedical Imaging, ISBI 2025

作者： Nouman, Muhammad Khoriba, Ghada Rashed, Essam A. School of Information Technology and Computer Science Nile University Giza12677 Egypt Graduate School of Information Science University of Hyogo Kobe650-0047 Japan Advanced Medical Engineering Research Institute University of Hyogo Himeji670-0836 Japan

ISBN: (纸本)9798331520526

Segment Anything Model (SAM) shows robustness in prompt-based segmentation of natural images. However, adapting SAM to the medical domain as a foundation model, MedSAM, presents unique challenges arising from clinical settings. This study evaluates MedSAM's performance across five medical imaging modalities (MRI, CT, ultrasound, endoscopy, and fundus IR) using four different prompting strategies: standard bounding boxes (SBB), rotated bounding boxes (RBB), contour points (CP), and simulated human annotations (SHA). MedSAM's performance is assessed under precise and perturbed conditions for each prompt type to evaluate its segmentation capabilities comprehensively. We empirically evaluate MedSAM's abilities and adaptability by experimenting with zero-shot learning and fine-tuning approaches. The results indicate that performance varies markedly with prompt type, accuracy, and imaging modality. The study concludes that MedSAM is sensitive to prompt precision and anatomical complexity. Fine-tuning improves performance, but further refinements are necessary to make it robust in various clinical settings. This work highlights the need for prompt engineering and provides practical insights to enhance segmentation accuracy in SAM-like foundation models. © 2025 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

The Effects of the Badminton Teaching-Assisted System Using Electromyography and Gyroscope on Learners' Badminton Skills

引用

IEEE Transactions on Learning Technologies 2023年第5期16卷 780-789页

作者： Lin, Kuo-Chin Cheng, I-Ling Huang, Yin-Cheng Wei, Chun-Wang Chang, Wei-Lun Huang, Chenhsuan Chen, Nian-Shing National Sun Yat-sen University Center for Physical and Health Education Kaohsiung80424 Taiwan National Chung Hsing University Graduate Institute of Library and Information Science Taichung40227 Taiwan National Sun Yat-sen University Department of Information Management Kaohsiung80424 Taiwan Kaohsiung Medical University Hospital Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Department of Medical Research Kaohsiung80708 Taiwan National Taiwan Normal University Department of Graduate Institute of Information and Computer Education Taipei106209 Taiwan National Yunlin University of Science and Technology Department of Applied Foreign Languages Yunlin64002 Taiwan

Swing movements and muscle strength are essential for mastering badminton techniques. Traditionally, students learn badminton through their instructor's physical demonstration, verbal instructions, and small group activities. To enhance students' learning experience and assist badminton instructors more effectively, this study proposes an alternative teaching approach that utilizes a Badminton Teaching-Assisted System (BTAS) to teach swing movements. The system uses a gesture control armband to collect electromyography and gyroscope signals from professional players, which are then used to build a machine learning model based on the back propagation neural network. The model can be used as a scoring tool to assess the correctness of the student's swing movements and muscle strength. A total of 87 students participated in an eleven-week experiment focusing on two fundamental badminton skills: The backhand push and backhand lift. The results demonstrated a significant improvement in the correctness of the muscle strength during swing movements for the experimental group, compared to the control group. The BTAS can help to enhance the effectiveness of badminton instruction, thereby improving students' swing techniques. Future research could expand upon this study to develop more precise artificial intelligence-based sports assistance systems, which would facilitate personalized teaching and learning in physical education. © 2008-2011 IEEE.

关键词： Muscle

来源：评论

学校读者我要写书评

暂无评论

IoT botnet detection from software defined network using American zebra optimization algorithm with SSRNN-ELM

引用

International Journal of information Technology (Singapore) 2025年第2期17卷 959-967页

作者： Bindu, Nalluri Venkata Madhu Nassa, Vinay Kumar Vasuki, P. Manikandan, G. Jeena, R. Mahaveerakannan, R. Department of CSE-AIML Malla Reddy Engineering College (Autonomous) Medchal Secunderabad Malkajgiri (Dist) India Ellenki College of Engineering and Technology (ECET) Patelguda (v) Ameenpur (m) Sangareddy (D) Hyderabad Telangana India Department of Information Technology Sri Sivasubramaniya Nadar College of Engineering Chennai India Department of Electronics and Communication Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India Department of Computer Science and Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India

Software-defined networking (SDN) offers centralized control over large-scale networks, enhancing flexibility and enabling tailored network applications. However, SDN introduces new security vulnerabilities, including the risk of botnet attacks, which can compromise systems and steal data. This paper proposes a novel approach for detecting botnet attacks in SDN environments by leveraging a hybrid model that integrates recurrent neural networks (RNNs) and extreme learning machines (ELMs). The proposed method utilizes RNNs for feature learning and ELMs for classification, with the American zebra optimization algorithm (AZOA) optimizing ELM weights. This hybrid SSRNN-ELM (supervised subset recurrent neural network—extreme learning machine) approach is evaluated using N-BaIoT dataset and performance metrics, demonstrating effective detection of complex botnet attacks with high accuracy. The results demonstrate that the hybrid model effectively identifies complex botnet attacks, achieving a detection accuracy of 96.60%. The integration of recurrent neural networks (RNNs) for feature learning and extreme learning machines (ELMs) for classification, along with optimization by the American zebra optimization algorithm (AZOA), significantly improves detection performance as compared to the recent existing studies. © Bharati Vidyapeeth's institute of computer Applications and Management 2025.

关键词： American zebra optimization algorithm (AZOA) BotNet attack detection Extreme learning machine (ELM) Recurrent neural network (RNN) Software-defined network (SDN)

来源：评论

学校读者我要写书评

暂无评论

Research on the quantum photonic convolutional neural network for artificial intelligence-based healthcare system security

引用

Optical and Quantum Electronics 2024年第2期56卷 1-18页

作者： Sita Kumari, K. Shivaprakash, G. Arslan, Farrukh Alsafarini, Maram Y. Ziyadullayevich, Avlokulov Anvar Haleem, Sulaima Lebbe Abdul Arumugam, Mahendran Velagapudi Ramakrishna Siddhartha Engineering College Andhra Pradesh Vijayawada India Department of Electronics and Instrumentation Engineering Ramaiah Institute of Technology Bengaluru India School of Electrical and Computer Engineering Purdue University West Lafayette United States Department of Electrical Engineering University of Engineering and Technology Lahore Lahore Pakistan Computer Science Department Zarqa University Zarqa Jordan The Department of Audit Tashkent Institute of Finance Tashkent Uzbekistan Department of Information and Communication Technology Faculty of Technology South Eastern University of Sri Lanka Oluvil Sri Lanka Center for Transdisciplinary Research Saveetha Dental College Saveetha Institute of Medical and Technical Science Chennai India

Artificial intelligence (AI) has quickly integrated into contemporary healthcare organizations, providing a variety of purposes, including identifying diseases, individualized therapy suggestions, and healthcare picture analytics. However, substantial security concerns are raised by the extensive use of AI in Healthcare, particularly regarding the reliability and confidentiality of private patient information. In this paper, we offer quantum photonic convolutional neural network (QP-CNN) to strengthen AI-based healthcare systems' security to overcome this crucial issue. To create an innovative convolutional neural network (CNN) architecture capable of handling the quantum computations that can endanger the safety of patient data, we analyze the special aspects of quantum photonics in this study. We explore the basic ideas behind quantum photonic computation and show how they can be used to develop strong cryptography methods for securing healthcare information during transport and preservation. Initially, we gather the dataset and preprocess the collected data using min–max normalization to remove duplicates and guarantee homogeneity. The subsequent stage involves utilizing principal component analysis (PCA) to extract pertinent features from the preprocessed data. We simulate trials with Python 3.11 software to assess the efficiency of the suggested algorithm. In terms of accuracy (82.67%), precision (82%), recall (75.84%), and F1-score (85%), specificity (95.67%), AUC (93.15%). Our results show that the QP-CNN technique outperforms other methods in effectiveness. Our suggested QP-CNN technique provides exciting outcomes for the security of an artificial intelligence-based healthcare system. © 2023, The Author(s), under exclusive licence to Springer science+Business Media, LLC, part of Springer Nature.

关键词： Healthcare Patient evaluation Prediction Quantum photonic convolutional neural network (QP-CNN) Security

来源：评论

学校读者我要写书评

暂无评论

RAPIDEST: A Framework for Obstructive Sleep Apnea Detection

引用

IEEE Transactions on Neural Systems and Rehabilitation engineering 2023年 31卷 387-397页

作者： Lin, Xin-Xue Lin, Phone Yeh, En-Hau Liu, Gi-Ren Lien, Wan-Ching Fang, Yuguang National Taiwan University Department of Computer Science and Information Engineering Taipei10617 Taiwan Graduate Institute of Networking and Multimedia Institute of Medical Device and Imaging National Taiwan University Internet of Things Research Center Department of Computer Science and Information Engineering Taipei10617 Taiwan National Cheng Kung University Department of Mathematics Tainan City701 Taiwan National Taiwan University Hospital Department of Emergency Medicine Taipei100229 Taiwan College of Medicine National Taiwan University Department of Emergency Medicine Taipei10617 Taiwan City University of HongKong Department of Computer Science HongKong Hong Kong

The traditional polysomnography (PSG) examination for Obstructive Sleep Apnea (OSA) diagnosis needs to measure several signals, such as EEG, ECG, EMG, EOG and the oxygen level in blood, of a patient who may have to wear many sensors during sleep. After the PSG examination, the Apnea-Hypopnea Index (AHI) is calculated based on the measured data to evaluate the severity of apnea and hypopnea for the patient. This process is obviously complicated and inconvenient. In this paper, we propose an AI-based framework, called RAre Pattern Identification and DEtection for Sleep-stage Transitions (RAPIDEST), to detect OSA based on the sequence of sleep stages from which a novel rarity score is defined to capture the unusualness of the sequence of sleep stages. More importantly, under this framework, we only need EEG signals, thus significantly simplifying the signal collection process and reducing the complexity of the severity determination of apnea and hypopnea. We have conducted extensive experiments to verify the relationship between the rarity score and AHI and demonstrate the effectiveness of our proposed approach. © 2001-2011 IEEE.

关键词： Electrocardiograms

来源：评论

学校读者我要写书评

暂无评论

CoDescribe: An Intelligent Code Analyst for Enhancing Productivity and Software Quality 10th

CoDescribe: An Intelligent Code Analyst for Enhancing Produ...

引用

10th International Symposium on Applied Computing for Software and Smart systems, ACSS 2023

作者： Das, Souvick Deb, Novarun Cortesi, Agostino Chaki, Nabendu Department of Environmental Science Informatics and Statistics Ca’ Foscari University Venezia30172 Italy Indian Institute of Information Technology Vadodara Gujrat Gandhinagar382028 India Department of Computer Science and Engineering University of Calcutta 67 Sukanta Park Kolkata700101 India

ISBN: (纸本)9789819977826

Automating the documentation, explanation, and modification of source code has been an area of intense research interest for several decades. This paper proposes a novel framework for analyzing source codes to generate natural language summaries, answer complex user queries by reasoning, and even support syntactic error checking and code conversion to other languages. The framework incorporates transformer-based models and knowledge graphs to understand the context of the code and the user’s queries. The contributions of this proposed approach represent a significant leap forward by overcoming the limitations of the most advanced ChatGPT model. The framework ensures the accuracy and reliability of the responses while handling multiple source code files efficiently, making it a valuable asset for software developers and stakeholders. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

PAI-1 Derived from Alveolar Type 2 Cells Drives Aging-Associated Pulmonary Fibrosis

引用

engineering 2024年第11期42卷 74-87页

作者： Rui Quan Chenhong Shi Yanan Sun Chengying Zhang Ran Bi Yiran Zhang Xin Bi Bin Liu Ziheng Dong Dekui Jin Yixuan Li Key Laboratory of Functional Dairy Co-Constructed by the Ministry of Education and Beijing MunicipalityBeijing 100083China Department of General Practice The Third Medical Center of the Chinese PLA General HospitalBeijing 100039China Department of Thoracic Surgery The Third Medical Center of the Chinese PLA General HospitalBeijing 100039China Center for Nanomedicine and Department of Anesthesiology Brigham and Women’s HospitalHarvard Medical SchoolBostonMA 02115USA School of Computer and Information Engineering Luoyang Institute of Science and TechnologyLuoyang 471023China

Pulmonary fibrosis(PF)is a lethal lung disease that predominantly affects older adults;however,whether and how aging triggers fibrosis remains *** pinpoint the predominant initiating factors of PF,we first analyzed single-cell RNA sequencing(scRNA-seq)data from the lung tissues of 45 normal donors and 51 PF patients and found that aging might serve as the primary catalyst for PF *** further investigate the influence of aging on PF formation,we conducted a comprehensive and thorough study employing a natural aging mouse *** found that dynamic alterations in the quantity and types of collagen fibers during aging-induced PF progression,especially in collagenous(Col)I,emerged as the predominant driver of *** then investigated the regulation of Col I synthesis during aging using primary alveolar type 2(AT2)cells and A549 cells line through conditioned media and Transwell cocul-ture,and found that secretions—particularly plasminogen activator inhibitor(PAI)-1—from aged AT2 cells promoted fibrosis and enhanced collagen type I alpha 1(Col1al)production via the transforming growth factor(TGF)-b/small mother against decapentaplegic(Smad)2/3 ***,scRNA-seq and a histological analysis of human lung tissue demonstrated a significant upregulation of SERPINE1(the gene encoding PAI-1)and PAI-1 expression in both aging lung tissue and AT2 cells,which was consistent with our findings from animal experiments,providing additional evidence for the pivotal role of PAI-1 during aging and the development of *** research demonstrates that PAI-1,a crucial factor secreted by aging AT2 cells,exerts a pivotal role in promoting the synthesis of Col1a1 in fibroblasts,subsequently leading to Col I deposition,and in driving the progression of PF by mediating the TGF-b/Smad2/3 *** find-ings offer critical evidence for the involvement of epithelial dysfunction in age-related PF and provides potential novel therapeutic targets for clinical interventio

关键词： Aging Pulmonary fibrosis Alveolar type 2 cells PAI-1

来源：评论

学校读者我要写书评

暂无评论

Calculating and Comparing the Weighted and Unweighted Water Quality Indices for Cauvery River Banks based on Accuracy 4

Calculating and Comparing the Weighted and Unweighted Water ...

引用

4th International Conference on Cybernetics, Cognition and Machine Learning Applications, ICCCMLA 2022

作者： Karpagam, V. Christy, S. Evangelin, S.N. Sheela Saveetha Institute of Medical and Technical Scinces Department of Computer Science and Engineering Thandalam Chennai India Saveetha Institute of Medical and Technical Scinces Saveetha School of Engineering Department of Information Technology Thandalam Chennai India Anna University Sri Kriahna Engineering College Department of Computer Science and Engineering Chennai India

ISBN: (数字)9781665462464

ISBN: (纸本)9781665462464

Appraising the quality of water has been an important issue in recent decades. Common causes of Water pollution are affecting human activities and its consequences. Some of the sources that pollute the water bodies are Industrial Wastage, Global Warming, Fuel Spilling, Sewage Water etc. Water pollution affects dispersion of Biodiversity, contamination of Food Chain, Diseases, Infant Mortality etc,. Some of the solutions for water pollution are improved sanitation, sewage treatment and reuse for irrigation. Hence the accurate classification of water pollution is a very important activity to solve the water contamination. This paper demonstrated the accurate calculation of the Water Quality Indices (WQI) by using Weighted Mean and Unweighted Mean methods to predict the water quality. Water Quality Index is determined by evaluating arithmetic, Geometric mean for weighted index calculation and Harmonic Mean for Unweighted Index, The Sub-Indices (SI) of selected parameters for Weighted Arithmetic Mean Water Quality Index (WAMWQI) and Weighted Geometric Mean Water Quality Index (WGMWQI) are evaluated by proportional constant (K) with the standard values and ideal values of each parameters approved by World Health organization (WHO). The Sub-Indices (SI) of selected parameters for Unweighted Harmonic Mean Water Quality Index (UHMWQI) are evaluated by Oregon Unweighted Harmonic WQI (OWQI) method. Water samples are collected from the Tamil Nadu Pollution Control Board (TNPCB). WQI are calculated for the water samples for the different areas from the Cauvery River Basin of Tamil Nadu. The performances are compared by using the SPSS Tool by anova test and the results are represented as graphically by bar chart. The performance of WAMWQI is slightly higher than the other two methods. And also the WQI for the stations Thirumanimuthar and Sarabanga shows major differences between weighted mean method and unweighted mean method. But other stations do not show the major differences

关键词： Biodiversity

来源：评论

学校读者我要写书评

暂无评论

Cloud-Enabled Patient Acuity Prediction Utilizing Decision Trees in Smart ICU Nurse Assignment Systems 4

Cloud-Enabled Patient Acuity Prediction Utilizing Decision T...

引用

4th International Conference on Sustainable Expert Systems, ICSES 2024

作者： Arul Prasath, A. Saravanan, S. Monikapreethi, S.K. Brindha, G. Maheshwari, S. Srinivasan, C. Vel Tech Rangarajan Dr.Sagunthala R&d Institute of Science and Technology Department of Computer Science and Engineering Tamil Nadu Chennai India Muthayammal Engineering College Department of Electrical and Electronics Engineering Tamil Nadu Namakkal India Rajalakshmi Institute of Technology Department of Electronics and Communication Engineering Tamil Nadu Chennai India Meenakshi College of Engineering Department of Electronics and Instrumentation Engineering Tamil Nadu Chennai India Sri Sai Ranganathan Engineering College Department of Information Technology Tamil Nadu Coimbatore India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Department of Computer Science and Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798331540364

This research introduces a new method for improving Intensive Care Units (ICUs) nurse assignment using cloud computing and Decision Trees (DTs )-based patient acuity prediction models. Effective and timely care delivery is dependent on the efficient allocation of nursing resources, which is becoming more important due to the growing complexity of patients' situations in ICUs. To integrate patient data from many sources seamlessly the proposed system uses cloud infrastructure to process and analyze data in real-time. To proactively identify high-risk situations, use DTs algorithms to forecast patient acuity levels using a variety of clinical indicators. Optimizing staffing levels and improving patient outcomes which incorporates these predictions into the nurse assignment process. Through a case study performed in a real-world ICUs improves nurse efficiency and the quality of patient care. The findings of this study highlight the promise of decision support systems hosted in the cloud for improving the delivery of healthcare in ICUs. © 2024 IEEE.

关键词： Nursing

来源：评论

学校读者我要写书评

暂无评论

Smart Diagnostic System for Early Detection and Prediction of Polycystic Ovary Syndrome

Smart Diagnostic System for Early Detection and Prediction o...

引用

2023 International Conference on computer Communication and informatics, ICCCI 2023

作者： Harish, K.P. Dhivyanchali, M.N. Devi, K.Nirmala Krishnamoorthy, N. Dhana Sree, R. Dharanidharan, R. Kongu Engineering College Department of Computer Science & Engineering Erode India Swamy Vivekanandha Medical College Hospital and Research Institute Elayampalayam Tamilnadu Tiruchengode637 205 India Vellore Institute of Technology Vellore Campus School of Information Technology and Engineering Department of Software Systems and Engineering Tamilnadu 632014 India

ISBN: (纸本)9798350348217

PCOS are the serious condition which affects female ovaries during their reproductive age of 15 to 45. This disease affects 5 to 10% of reproductive-age females. Although it is difficult to fully resolve this issue,the PCOS affected women can be mitigated through proper exercise, by taking proper nutritious diet and maintaining the healthy BMI. Until they take a pregnancy test, the majority of women are unaware of the disease. The clinical dataset has the 541 instances and 45 attributes of unbalanced classes of 0 and 1 (no and yes) which has 364 instances of 0 (no) class and 177 instances of 1 (yes) class. Preprocessing is done for the unbalanced dataset by filling the null values and changing the datatype of all attributes to numeric datatypes. The unbalanced dataset is balanced by the balancing techniques of SMOTE and Random Over Sampling. Comparing the both balanced techniques through the accuracy the random oversampling gives the *** supervised learning algorithms are Decision tree, KNN,Random Forest,AdaBoost, Logistic regression,Gradient boosting, cat boosting, XGBoosting, Linear SVM, Radial SVM, Linear discriminant analysis and Quadratic discriminant analysis are *** supervised learning algorithms are trained and tested by splitting the dataset to 70% for training and 30% for testing. The ensemble stacking techniques are used by implementing the all models at the cross validation of *** xgboost gives the accuracy of 96% for the balanced dataset. © 2023 IEEE.

关键词： Adaptive boosting

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：