检索结果-内蒙古大学图书馆

Airport Capacity prediction and Optimization Based on Semi-Varying Coefficient and Dynamic Programming

IEEE ACCESS 2025年 13卷 67908-67924页

作者： Xia, Huan Yao, Weirui Zheng, Yi Jiang, Chaozhe Zhang, Chenyang Southwest Jiaotong Univ Sch Transportat & Logist Chengdu 610032 Peoples R China Xihua Univ Sch Comp & Software Engn Chengdu 610097 Peoples R China Second Res Inst Civil Aviat Adm China Chengdu 610000 Peoples R China

Air traffic congestion has emerged as a critical challenge in modern air traffic management. Adverse weather conditions and other factors frequently lead to reduced airport arrival capacity, resulting in flight delays. Accurate capacity prediction and optimization are essential for maximizing airport utilization and minimizing flight delays. This study introduces a capacity prediction model based on the semi-varying coefficient approach, utilizing real-world data from Guangzhou Baiyun Airport collected over a specific time period. Through 5-fold cross-validation, the semi-varying coefficient model is compared to the varying-coefficient model, demonstrating superior out-of-sample prediction capabilities. Subsequently, we establish and solve a flight arrival and departure flow allocation optimization model using dynamic programming to enhance traffic flow coordination. Analysis of case study results demonstrates that this method can generate optimal strategies for allocating arrival and departure traffic flows within airport capacity constraints, thereby minimizing overall flight delay costs.

关键词： Airports Atmospheric modeling Delays Estimation Predictive models Resource management Meteorology prediction algorithms Optimization Fitting Air traffic flow management airport capability utilization capacity prediction flow allocation

来源：评论

学校读者我要写书评

暂无评论

Comparative Analysis of Software Reliability prediction and Optimization using Machine Learning algorithms

Comparative Analysis of Software Reliability Prediction and ...

引用

Intelligent Systems and Computational Networks (ICISCN), International Conference on

作者： Prashanth Kumar Bolisetty Midhunchakkaravarthy Faculty of AI AI Computing and Multimedia Lincoln University College Selangor Darul Eshan Malaysia Faculty of AI Computing and Multimedia Lincoln University College Selangor Darul Eshan Malaysia

ISBN: (数字)9798331529246

ISBN: (纸本)9798331529253

Software reliability plays a crucial role in assessing the overall quality of software systems. Developing highly reliable software presents challenges, including ensuring usability, maintaining consistent performance, offering reliable service, and facilitating smooth maintenance. To overcome these limitations, researchers have turned to intelligent prediction and optimization algorithms. This paper presents a comprehensive review of software reliability prediction, emphasizing the application of machine learning techniques. It also provides an analytical evaluation of existing methods to identify areas for improvement and future research opportunities in software reliability prediction.

关键词： Machine learning algorithms Reviews Software algorithms Machine learning Software systems prediction algorithms Software reliability Maintenance Usability Optimization

来源：评论

学校读者我要写书评

暂无评论

Boosting algorithms Empowering Heart Disease prediction for Enhanced Medical Accuracy

Boosting Algorithms Empowering Heart Disease Prediction for ...

引用

International Symposium on Advanced Computing and Communication (ISACC)

作者： Urvashi Sharma Kanak Saxena Computer Science & Engineering Department Samrat Ashok Technological Institute Vidisha Head Computer Science & Engineering Department Samrat Ashok Technological Institute Vidisha India

ISBN: (数字)9798331523893

ISBN: (纸本)9798331523909

Heart disease remains a leading cause of mortality worldwide, necessitating accurate and reliable predictive models to aid early diagnosis and treatment. Traditional machine learning methods like LR and DT Classifiers offer reasonable recall rates but suffer from lower precision and accuracy. To address this challenge, we employed advanced boosting algorithms, specifically GradientBoostingClassifier and XGBClassifier, to enhance predictive accuracy in heart disease detection. Our study shows that these algorithms achieve accuracy rates above 93%, with precision exceeding 52%, and a significantly low False Positive Rate below 0.5%. However, the trade-off involves lower recall rates, suggesting some true cases remain undetected. Boosting algorithms thus provide a robust approach for heart disease prediction, though attention to false negatives is essential for comprehensive application.

关键词： Heart Accuracy Machine learning algorithms Predictive models Boosting prediction algorithms Classification algorithms Reliability Medical diagnostic imaging Diseases

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis of Machine Learning and Deep Learning algorithms for Lung Disease prediction

Predictive Analysis of Machine Learning and Deep Learning Al...

引用

International Conference on Inventive Computation Technologies (ICICT)

作者： Raji Ramachandran Ashina A Jawad Amal U J Department of Computer Science and Applications Amrita School of Computing Amrita Vishwa Vidyapeetham Amritapuri India

ISBN: (数字)9798331512248

ISBN: (纸本)9798331512255

Lung cancer is a significant health issue all over the world, and thus requires effective and precise solutions. Traditionally, lung cancer detection relied on primitive methods such as radiology examination of CT scans, which most of the time leads to delayed diagnosis. These primitive methods were error-prone, inconsistent, and might result in inaccurate results, hence making them hard. This paper discusses predictive analysis of machine learning and deep learning algorithms for prediction of lung cancer. In our approach, using both CSV data and CT scan images, we assess the accuracy and efficiency of different machine learning and deep learning models. While deep learning algorithms process images, machine learning algorithms are applied in CSV data. The paper combines machine learning and deep learning models with hyperparameter tuning to achieve the systems best performance. Evaluation metrics, such as accuracy, recall, precision, and F1-score, are utilized in the evaluation of the comparison purpose. Through model tuning and performance evaluation, the system seeks to uncover the most effective and efficient prediction model.

关键词： Deep learning Machine learning algorithms Accuracy Computed tomography Computational modeling Lung cancer Predictive models prediction algorithms Predictive analytics Tuning

来源：评论

学校读者我要写书评

暂无评论

Enhancing Wireless Communication Efficiency Through Advanced Frequency Band and Path Loss prediction with Random Forest algorithms

Enhancing Wireless Communication Efficiency Through Advanced...

引用

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： V. Revathi Yagateela Pandu Rangaiah Amit Dutt Dinesh Kumar Yadav Tamam Ali Abd Ulabbas Abedi Department of Applied Sciences New Horizon College of Engineering Bangalore India Department of Electronics and Communication Enfineering Institute of Aeronautical Engineering Hyderabad India Lovely Professional University Phagwara India Lloyd Institute of Engineering & Technology Greater Noida Uttar Pradesh Radiology Techniques Department College of Medical Technology The Islamic University Najaf Iraq

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Mobile communication systems are popular in today's world, whereas estimating the frequency bands and the path loss is complicated due to the changes in environment and operations. This research introduces a new method involving the use of Random Forest algorithms in identification of the frequency bands and path loss in various wireless communication scenarios accurately. The methodology incorporates voluminous databases that consist of the environmental aspects such as type of terrain, Building density and foliage and operating parameters consisting of transmission power, antenna height & frequency band. This is made possible through the incorporation of Random Forests which has the ability to learn from the ensemble in cases of complex and non-linear input data. The investigation reveals that Random Forests are capable of improving the predictive performance far much better than the conventional path loss models such as Okumura-Hata and COST-231 models. The suggested approach not only contributes to the enhancement of the selection of frequency bands, thus increasing the spectrum resource efficiency but also offers accurate calculation of the path loss for networks, which is vital in the network design and implementation. Real-world applications and numerous simulations prove the applicability of the model demonstrating its capacity to meet the flexible needs of 5G and beyond context. This thesis benefits the progress of predictive analytics in wireless communication while providing a versatile application to improve the network and its dependability.

关键词： Wireless communication Wireless sensor networks 5G mobile communication Vehicular ad hoc networks Predictive models prediction algorithms Frequency estimation Predictive analytics Random forests Context modeling

来源：评论

学校读者我要写书评

暂无评论

Quantum Vs. Classical Machine Learning algorithms for Software Defect prediction: Challenges and Opportunities

Quantum Vs. Classical Machine Learning Algorithms for Softwa...

引用

Quantum Software Engineering (Q-SE), International Workshop on

作者： Md Nadim Mohammad Hassan Ashis Kumar Mandal Chanchal K. Roy Department of Computer Science University of Saskatchewan Saskatoon SK Canada University of Prince Edward Island Charlottetown PE Canada

ISBN: (数字)9798331526214

ISBN: (纸本)9798331526221

Software defect prediction is a critical aspect of software quality assurance, as it enables early identification and mitigation of defects, thereby reducing the cost and impact of software failures. Over the past few years, quantum computing has risen as an exciting technology capable of transforming multiple domains; Quantum Machine Learning (QML) is one of them. QML algorithms harness the power of quantum computing to solve complex problems with better efficiency and effectiveness than their classical counterparts. However, research into its application in software engineering to predict software defects still needs to be explored. In this study, we worked to fill the research gap by comparing the performance of three QML and five classical machine learning (CML) algorithms on the 20 software defect datasets. Our investigation reports the comparative scenarios of QML vs. CML algorithms and identifies the better-performing and consistent algorithms to predict software defects. We also highlight the challenges and future directions of employing QML algorithms in real software defect datasets based on the experience we faced while performing this investigation. The findings of this study can help practitioners and researchers further progress in this research domain by making software systems reliable and bug-free.

关键词： Machine learning algorithms Quantum computing Software algorithms Machine learning Software quality prediction algorithms Software systems Software Software reliability Software engineering

来源：评论

学校读者我要写书评

暂无评论

Grey-Topsis and Optimized RNN algorithms with Dynamic Weight Adjustment: Construction of a Precise prediction Model for the Global Cybercrime Situation

Grey-Topsis and Optimized RNN Algorithms with Dynamic Weight...

引用

Advanced algorithms and Control Engineering (ICAACE), International Conference on

作者： Yuyang Dai Runze Yuan Zhen Tian School of Finance Capital University of Economic and Business Beijing China School of Management Beijing Forestry University Beijing China James Watt School of Engineering University of Glasgow UK

ISBN: (数字)9798331535087

ISBN: (纸本)9798331535094

This paper proposes a hybrid model integrating Grey-Topsis and Recurrent Neural Network (RNN) for predicting the global cybercrime trend. Data from 38 countries from 2010 to 2024 were collected, and after data preprocessing and CRITIC-based weighting, an improved Grey-TOPSIS evaluation system was applied. The RNN model was optimized with dynamic weight adjustment. K-means clustering was used to analyze crime patterns, and the DID method was employed to verify the effectiveness of policy interventions. The experimental results show that the average relative error of the predictions for 2025 - 2030 is 17.72%, providing strong support for formulating targeted strategies.

关键词： Adaptation models Recurrent neural networks Sensitivity analysis Heuristic algorithms Predictive models prediction algorithms Market research Stability analysis Real-time systems Computer crime

来源：评论

学校读者我要写书评

暂无评论

Classification and prediction-based data mining algorithms to predict visitors to the museum

Classification and prediction-based data mining algorithms t...

引用

algorithms, Computing and Machine Learning (CACML), Asia Conference on

作者： Yingrui Chi Jiaran Zhang International School of Advanced Studies University of Camerino Ascoli Piceno Italy

ISBN: (数字)9798331543143

ISBN: (纸本)9798331543150

The perception that museums are often perceived as disconnected from everyday life has resulted in a notable reluctance among a substantial segment of the population to visit these institutions. To enhance visitor attendance, it is essential to conduct an analysis of social survey databases. The objective of this study is to identify potential museum visitors within a given population and to predict their likelihood of visiting through the application of a data mining model utilizing classification algorithms. The dataset employed in this research was sourced from the "2021 China General Social Survey." We implemented five classification algorithms using the opensource software WEKA to classify and predict the dataset, specifically Naive Bayes, Logistic, J48, Random Trees, and KStar. Among these algorithms, the J48 classification method yielded the highest accuracy in predicting potential visitors, achieving a success rate of 78.7012%. The findings suggest that lifestyle habits and individual preferences play a significant role in determining the frequency of museum visits. This study demonstrates the effectiveness of classification and prediction algorithms in the context of museum visitor research and proposes several promising avenues for future investigation.

关键词： Surveys Accuracy Computational modeling Software algorithms prediction algorithms Museums Data models Classification algorithms Data mining Standards

来源：评论

学校读者我要写书评

暂无评论

prediction Wireless Network Traffic Evaluation Potential Based on Ensemble algorithms

Prediction Wireless Network Traffic Evaluation Potential Bas...

引用

IEEE SSD International Multi-Conference on Systems, Signals and Devices

作者： Osama Yassin Mohammed Ibrahim Ahmed Saleh dept. of Computer Science College of Computer and Mathematics University of Mosul Nineveh Iraq dept. of Software College of Computer Science and Mathematics University of Mosul Nineveh Iraq

ISBN: (数字)9798331542726

ISBN: (纸本)9798331542733

This paper proposes intelligence methods for the prediction of wireless network traffic and the evaluation of its development. This solution analyses the changing patterns of actual business traffic data in cellular networks in the time dimension and uses ensemble learning (EL) to predict the tendency of traffic, providing guidance for operators' network optimization deployment from a short-term perspective. The paper depends on a dataset taken from the Eurecom ElasticMon 5G monitoring platform. The approach applied a multi-dimensional mapping relationship between other operational data and traffic in the network using four ensembles of learning: Extreme Gradient Boosting (XGBoost), ADA boosting, gradient boosting algorithm, and a voting regression algorithm. They applied to find the upper limit of traffic that the cellular cell can carry, optimizing the deployment of the network from a long-term perspective. The results showed that XGBoost outperforms other methods, whose best performance ensures the privacy of traffic data.

关键词： Economics Data privacy Machine learning algorithms Wireless networks Telecommunication traffic prediction algorithms Boosting Ensemble learning Optimization Monitoring

来源：评论

学校读者我要写书评

暂无评论

Bone Cancer prediction Using Regression algorithms and Machine Learning Approaches

Bone Cancer Prediction Using Regression Algorithms and Machi...

引用

Cognitive Computing in Engineering, Communications, Sciences and Biomedical Health Informatics (IC3ECSBHI), International Conference on

作者： Abhilash Kokala Kartheek Kalluri Nagaraj Parvatha Naveen Kodakandla Harinagapraveen Gundugolanu Infomatics Corp USA Navy Federal Credit Union USA National Student Clearinghouse USA REI Systems USA

ISBN: (数字)9798331518523

ISBN: (纸本)9798331518530

Bone cancer is an aggressive disease that is often difficult to diagnose and treat and can be very dangerous for the patient. Bone cancer needs to be predicted in time and accurately for successful treatment and good patient care. This study aims to introduce a bone cancer prediction model that combines regression algorithms and machine learning techniques. The model reads data from patient medical records, such as age, sex, or genetic markers, and trains on it to predict the probability of bone cancer. We have tested linear regression, logistic regression, random forest multiple regression algorithm artificially neural networks, and support vector Machine Learning. We used an extensive bone cancer cases and controls dataset from different research centers and hospitals. 6 Our preliminary results show that the new method is more accurate in predicting bone cancer than traditional methods. Regrettably, regression algorithms and machine learning techniques are good enough to model many variables at once while detecting intricate patterns in the data, so as a result, the ability to predict is enhanced. Their model can help healthcare professionals identify PD earlier and make well-informed early treatment choices to improve patient outcomes and quality of life. This is a critical goal given the progressive nature of manystage synucleinopathies. However, more studies and validation are needed before implementing the model clinically.

关键词： Support vector machines Machine learning algorithms Artificial neural networks Predictive models Bones prediction algorithms Genetics Data models Regression tree analysis Cancer

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：