检索结果-内蒙古大学图书馆

25th International Electronics Symposium, IES 2023

作者： Asyrofi, Rakha Dewi, Mutia Rahmi Lutfhi, Muhammad Irfan Wibowo, Prasetyo Faculty of Marine Science and Engineering Universitas Hangtuah Surabaya Indonesia Department of Computer Science and Information Engineering National Central University Taiwan Department of Information Technology Politeknik Negeri Padang Padang Indonesia Faculty of Engineering Universitas Negeri Yogyakarta Indonesia Graduate Institute of Network Learning Technology National Central University Taiwan Department of Informatics and Computer Engineering Politeknik Elektronika Negeri Surabaya Surabaya Indonesia

ISBN: (纸本)9798350314731

While systematic literature reviews are frequently carried out within software engineering research, performing them in a rigorous and reproducible manner can be difficult. This paper proposes some new methods for evaluating and validating systematic literature reviews. Our approach consists of several steps, such as: Selecting a set of relevant scientific papers to analyze, Developing a list of questions and criteria to evaluate each literature review, and Determining what types of functionality and performance should be evaluated. We tested our method by having multiple experts evaluate the literature reviews based on our questions and criteria. We measured the similarity in scores between each expert to determine the reliability of the evaluations. The average similarity index between experts was 0.58 to 0.83, indicating a reasonable level of agreement in their assessments. This shows our evaluation method can produce fairly consistent results, even when different experts are involved. The relatively high level of agreement is notable considering each expert brings their perspectives and opinions in analyzing literature reviews. By providing concrete questions, criteria, and evaluation methods, we aimed to guide the experts toward more uniform evaluations. In summary, we developed and tested a new approach for evaluating and validating systematic literature reviews in software engineering. By assessing reliability via interrater agreement, we showed that consistent and reproducible results are possible using our evaluation framework and methodology. Our methods could help researchers gain more insight into what makes for an effective and high-quality literature review. © 2023 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Privacy Preserving Blockchain with Optimal Deep Learning Model for Smart Cities

引用

computers, Materials & Continua 2022年第12期73卷 5299-5314页

作者： K.Pradeep Mohan Kumar Jenifer Mahilraj D.Swathi R.Rajavarman Subhi R.M.Zeebaree Rizgar RZebari Zryan Najat Rashid Ahmed Alkhayyat Department of Computing Technologies SRM Institute of Science and TechnologyKattankulathurChennai603203India Department of Computer Science and Information Technology School of Engineering and TechnologyKebridehar UniversityKebridehar250Ethiopia Department of Computer Science and Engineering K.Ramakrishnan College of EngineeringTiruchirappalli621112India Department of Computer Science and Engineering K.Ramakrishnan College of TechnologyTiruchirappalli621112India Energy Department Technical College of EngineeringDuhok Polytechnic UniversityDuhokIraq Computer Science Department College of ScienceNawroz UniversityDuhokIraq Computer Network Department Technical College of InformaticsSulaimani Polytechnic UniversitySulaimaniIraq College of Technical Engineering The Islamic UniversityNajafIraq

Recently,smart cities have emerged as an effective approach to deliver high-quality services to the people through adaptive optimization of the available *** the advantages of smart cities,security remains a huge challenge to be ***,Intrusion Detection System(IDS)is the most proficient tool to accomplish security in this ***,blockchain exhibits significance in promoting smart city designing,due to its effective characteristics like immutability,transparency,and *** order to address the security problems in smart cities,the current study designs a Privacy Preserving Secure Framework using Blockchain with Optimal Deep Learning(PPSF-BODL)*** proposed PPSFBODL model includes the collection of primary data using sensing ***,z-score normalization is also utilized to transform the actual data into useful ***,Chameleon Swarm Optimization(CSO)with Attention Based Bidirectional Long Short TermMemory(ABiLSTM)model is employed for detection and classification of *** is employed for optimal hyperparameter tuning of ABiLSTM *** the same time,Blockchain(BC)is utilized for secure transmission of the data to cloud *** cloud server is a decentralized,distributed,and open digital ledger that is employed to store the transactions in different methods.A detailed experimentation of the proposed PPSF-BODL model was conducted on benchmark dataset and the outcomes established the supremacy of the proposed PPSFBODL model over recent approaches with a maximum accuracy of 97.46%.

关键词： Blockchain smart city security intrusion detection system chameleon swarm optimization deep learning parameter tuning

来源：评论

学校读者我要写书评

暂无评论

Interdependency patterns of potential seaport risk factors in relation to supply chain disruption in Indonesia

引用

Journal of Shipping and Trade 2023年第1期8卷 6页

作者： Do. Bagus, Muhammad Reza Hanaoka, Shinya Department of Transdisciplinary Science and Engineering Tokyo Institute of Technology 2-12-1 O-okayama Meguro-ku Tokyo 152-8550 Japan Department of Information System College of Informatics and Computer Management Tidore Mandiri (STMIK Tidore Mandiri) Tidore Indonesia

As an integral part of the global supply chain network, Indonesian supply chain entities should understand conditional seaport risk factors that could lead to seaport threats that affect supply chain continuity. This study aims to provide a procedure for evaluating the interdependencies, implications, and correlations among various seaport risk factors for supply chain threats, specifically by investigating current practices in the developed economic region of Indonesian seaport operations. The study uses a rough set method to solve feature selection problems and multivariate analysis of variance to assess the correlation between dependent and independent variables. We find 39 conditional seaport risk factors that are potentially influenced by about 21 dependent factors related to seaport-fulcrum supply chain entities. Furthermore, threats from the planning process, infrastructure, seaport service process, distribution process, financial costs of nuclear enterprises and security existed and affluent highest potential risk in Indonesia. © 2023, The Author(s).

关键词： Association rule mining Genetic algorithm Interdependency risk analysis Rule rough set theory Seaport risk factors

来源：评论

学校读者我要写书评

暂无评论

Predictive Analytics for Breast Cancer Survival Rates Using Random Forest 10

Predictive Analytics for Breast Cancer Survival Rates Using ...

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Kumar, Rakesh Bordoloi, Dibyhash Michaelson, Jacob Laxminarayanamma, K. Kalra, Ravi Kumar, Anil Gla University Department of Computer Engineering & Applications Mathura India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Institute of Aeronautical Engineering Department of Information Technology Telangana Hyderabad India Lloyd Institute of Engineering & Technology Greater Noida India Lloyd Law College Greater Noida India

ISBN: (纸本)9798350382471

The Random Forest algorithm was used in this study to build a prediction model for breast cancer survival rates. The study used a deductive methodology, a descriptive design, including secondary data collecting in accordance with the interpretivism philosophy. The dataset was painstakingly preprocessed, and numerous metrics were used to gauge the model's effectiveness. The significance of the model's features was investigated as well to offer insight into the factors affecting survival forecasts. The study emphasizes how the model's practical applications might improve patient care by guiding treatment choices. It assesses the model's resilience under various circumstances, admits its shortcomings, and suggests future study trajectories. The study demonstrates the way predictive models have the ability to greatly affect patient outcomes and breast cancer care. © 2023 IEEE.

关键词： Breast cancer clinical implications data preprocessing model robustness predictive modelling Random Forest algorithm

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based Characterization of COPD Progression from Spirometry Data 10

Machine Learning-based Characterization of COPD Progression ...

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Varshney, Neeraj Bordoloi, Dibyhash Michaelson, Jacob Laxminarayanamma, K. Yadav, Vijay Kumar Srivastava, Amit Gla University Department of Computer Engineering and Applications Mathura India Computer Science & Engineering Graphic Era Deemed to Be University Uttarakhand Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Institute of Aeronautical Engineering Department of Information Technology Telangana Hyderabad India Lloyd Institute of Engineering & Technology Greater Noida India Lloyd Law College Greater Noida India

ISBN: (纸本)9798350382471

This study represents a substantial advance in regard to the application of machine learning to the treatment of chronic obstructive pulmonary disease (COPD). Recurrent neural networks (RNNs) incorporating Long Short-Term Memory (LSTM) units were used in the study, which was centered on the interpretivism concept, to mimic the time-dependent aspect of COPD development. During training, the model's prediction of COPD development was optimized, significantly outperforming current diagnostic techniques. Although encouraging, the study recommends increased data gathering, and multidisciplinary cooperation, including a diversification of data sources, particularly unstructured data. To fully utilize machine learning in the management of COPD, future efforts should look into real-time patient data integration, and telemedicine applications, including user-friendly technologies. © 2023 IEEE.

关键词： Chronic Obstructive Pulmonary Disease (COPD) data integration Long Short-Term Memory (LSTM) machine learning recurrent neural networks telemedicine

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Algorithms for Early Detection of Diabetes: An Indian Perspective 1

引用

8th International Conference on information System Design and Intelligent Applications, ISDIA 2024

作者： Fatima, Shaheen Sehgal, Laveena Sharma, Mahendra Sehrawat, Meenu Alam, Naushad Khanna, Ashish Ahamed, Jameel Department of Computer Science and Information Technology Maulana Azad National Urdu University Hyderabad India IIMT College of Engineering Greater Noida India Maharaja Agrasen Institute of Technology New Delhi India Center for Global Health Research Saveetha Institute of Medical and Technical Sciences Chennai India

ISBN: (数字)9789819765812

ISBN: (纸本)9789819765805

Worldwide, Diabetes is a chronic disorder that affects millions of people and with early diagnosis and treatment, serious diabetes-related effects like heart disease, stroke, and blindness can be avoided. This study compares the performance of machine learning algorithms for the early identification of diabetes with the perspective of India. These techniques include Gradient Boosting (GB), Extreme Gradient Boosting (EGB), Convolutional Neural Network (CNN), and Extra Decision Tree (EDT), Gaussian Nave Bayes (GNB), Support Vector Machine (SVM), Logistic Regression (LR), Decision Tree (DT), K-Nearest Neighbor (KNN), Random Forest (RF), and SVM. The algorithms were evaluated using the Pima Indians Diabetes dataset, a publicly available dataset of diabetes disease. The experimental findings demonstrate that the CNN algorithm obtains the best level accuracy of 99% for early diagnosis of diabetes. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Using Bayesian Networks For Predicting Hypertension Risk Factors 10

Using Bayesian Networks For Predicting Hypertension Risk Fac...

引用

10th IEEE Uttar Pradesh Section International Conference on Electrical, Electronics and computer engineering, UPCON 2023

作者： Varshney, Neeraj Madan, Parul Michaelson, Jacob Laxminarayanamma, K. Yadav, Vijay Kumar Kumar, Navneet Gla University Department of Computer Engineering and Applications Mathura India Graphic Era Deemed to Be University Department of Computer Science & Engineering Uttarakhand Dehradun India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Chennai India Institute of Aeronautical Engineering Department of Information Technology Telangana Hyderabad India Lloyd Institute of Engineering & Technology Greater Noida India Lloyd Law College Greater Noida India

ISBN: (纸本)9798350382471

Hypertension, a primary cause of mortality as well as morbidity in the cardiovascular system, demands accurate prediction models to ensure effective treatment and preventative measures. This study predicts hypertension associated risk factors using Bayesian Systems, an interpretative mindset, a deductive approach, and an exploratory approach. Using secondary data including genetic, lifestyle, as well as environmental characteristics, the study provides a comparison to established statistical methodologies. The Bayesian neural network model performs admirably in terms of prediction, with an accuracy of more than 85%. Both sensitivity and specificity show values above 80% and 90%, respectively, suggesting proficiency in diagnosing hypertensive people. Furthermore, sensitivity analysis shows that the model is resistant to changes in input parameters. Key contributions to hypertension risk are found, with biological factors, lifestyle choices, as well as exposure to environmental stressors all playing a substantial role. These factors' complicated relationships are explored, revealing their combined impact on antihypertensive susceptibility. Bayesian networks were able to beat traditional statistical methods in terms of accuracy and selectivity in predicting the incidence of hypertension variables. This demonstrates how Bayesian techniques have a potential to transform risk assessment as well as prevention tactics in cardiovascular health. Finally, this study demonstrates the effectiveness of Bayesian models in predicting risk for hypertension using multiple variables, giving a solid framework for focused interventions and preventative measures. The findings hold great promise for furthering public health measures aimed at controlling hypertensive and its effects. © 2023 IEEE.

关键词： Bayesian Networks global health problem Hypertension lifestyle factors using probabilities

来源：评论

学校读者我要写书评

暂无评论

Leveraging Machine Learning for Real-time Anomaly Detection and Self-Repair in IoT Devices 2

Leveraging Machine Learning for Real-time Anomaly Detection ...

引用

2nd IEEE International Conference on Communication, Security and Artificial Intelligence, ICCSAI 2023

作者： Ali, S. Ahamed Sujatha, D. Michael, Raj.T.F. Ramesh, G. Agoramoorthy, Moorthy Computer Science and Engineering Easwari Engineering College Ramapuram India St. Peters College of Engineering and Technology Department of Computer Science and Engineering Chennai India Simats Department of Computer Applications Sclas TN Chennai India K.L.N. College of Engineering Department of Information Technology Sivagangai Tamilnadu Pottapalayam India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350369960

The Internet of Things (IoT) gadgets have completely transformed a number of different businesses by producing enormous amounts of data. A machine learning framework for real-time Internet of Things anomaly detection and self-repair is presented in this research for the first time. Incorporating data preparation, anomaly detection, and selfrepair are all components of the framework. Through the use of data preparation module normalization and dimensionality reduction, Internet of Things data analysis can be improved. Through the utilization of deep neural networks, support vector machines, and several other machine learning models that have been trained on previous data, abnormal behavior can be identified. The reliability of ensemble approaches is increased. The self-repair module is responsible for automatically repairing abnormalities by resetting the settings of the device, upgrading the firmware, and applying patches. Device disruptions are reduced to a minimum by validation. Within the context of smart home and industrial automation tests, events were identified with a high degree of precision and a low percentage of false positives. Because it automatically fixes problems, the self-repair module makes the Internet of Things ecosystem better. © 2023 IEEE.

关键词： Anomaly Detection Internet of Things (IoT) Machine Learning Self-Repair

来源：评论

学校读者我要写书评

暂无评论

Incremental Learning with Pseudo Labels for Enhanced Glomeruli Segmentation Using SAM

Incremental Learning with Pseudo Labels for Enhanced Glomeru...

引用

2024 IEEE International Conference on E-Health Networking, Application and Services, HealthCom 2024

作者： Liu, Xinkai Peng, Boyuan Zhu, Xin Iwasaki, Tsuyoshi Sato, Atsuya Kazama, Junichiro James Huang, Jie Graduate Department of Computer Science and Engineering The University of Aizu Fukushima Aizu-Wakamatsu Japan Department of AI Technology Development M&D Data Science Center Institute of Science Tokyo Tokyo Japan Department of Nephrology and Hypertension Fukushima Medical University Fukushima Japan Graduate Department of Computer Science and Engineering Division of Information Systems The University of Aizu Fukushima Aizu-Wakamatsu Japan

ISBN: (纸本)9798350350548

The advent of the Segment Anything Model (SAM) marks a significant milestone in deep learning semantic segmentation tasks. In this study, an incremental learning model based on pseudo labels is proposed. The model generates bounding box prompts for SAM, enhancing the accuracy of glomeruli segmentation in renal pathology images. The model uses DenseNet-121 along with contrastive learning to enable self-supervised pre-training using mouse glomeruli images. Transfer learning is then conducted using labeled human renal pathology images to develop a binary classification model for glomeruli. Unlabeled images of human renal pathology are subsequently introduced for incremental learning. Class activation maps (CAMs) generated by the incremental learning model are post-processed to extract bounding rectangles for connected regions. These rectangles are then used as prompts for SAM segmentation. The proposed approach resulted in an average Dice similarity coefficient (DSC) of 0.825 in the glomeruli segmentation task. This result demonstrates the effectiveness of the incremental learning model and post-processing algorithms in improving SAM’s segmentation accuracy for renal pathology. © 2024 IEEE.

关键词： Contrastive Learning

来源：评论

学校读者我要写书评

暂无评论

Amazing Power of DINOv2 for Automatic Diagnosis of 12-Lead ECG

Amazing Power of DINOv2 for Automatic Diagnosis of 12-Lead E...

引用

2023 International Conference on Computational science and Computational Intelligence, CSCI 2023

作者： Singh, Kushal Pal Chandra, B. Kalra, Prem Kumar Narang, Rajiv Ansk School of Information Technology Indian Institute of Technology New Delhi Delhi India Indian Institute of Technology Dept. of Computer Science and Engineering New Delhi Delhi India All India Institute of Medical Sciences Dept. of Cardiology New Delhi India

ISBN: (纸本)9798350361513

The Electrocardiogram (ECG) is a reliable and fast diagnostic test for detecting several heart anomalies to enable timely intervention. However, accurate interpretation is crucial and requires skilled professionals. Automatic diagnosis of heart disease from ECG can solve the problem. The proposed method in this paper uses a Visual transformer, DINOv2, for ECG diagnosis. DINOv2 is trained on many real-world object images. The model has been finetuned with ECG images. This finetuned model is used for extracting relevant features required by the classification method for anomaly detection. The main aim of this paper is to classify the widely known CODE-15 dataset with increased accuracy. This dataset is 15% of data from a larger CODE dataset. This 12-lead ECG dataset has samples for six heart conditions: 1dAVb, RBBB, LBBB, SB, AF, and ST. The model was finetuned for 10 epochs and achieved a test accuracy of 96.30%. This accuracy has been achieved with a short duration (2 seconds) of ECG data only. Ribeiro et al. (2020) have tried to classify the entire CODE data and have been able to achieve an average precision of 92.37%. In this paper, we have achieved an increase in accuracy to the tune of 3.3% with a smaller subset dataset. © 2023 IEEE.

关键词： Electrocardiograms

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：