检索结果-内蒙古大学图书馆

50th International Conference on Computers and Industrial engineering: Sustainable Digital Transformation, CIE 2023

作者： Alshaikh, R. Ahmed, V. Bahroun, Z. Engineering Systems and Management PhD Program College of Engineering American University of Sharjah Sharjah United Arab Emirates Department of Industrial Engineering American University of Sharjah Sharjah United Arab Emirates

ISBN: (纸本)9781713886952

Maritime shipping plays a pivotal role in the global transportation system, providing safety and cost-effectiveness. However, it encounters numerous challenges, including port congestion, delivery delays, complex paperwork, unreliable reports on hazardous materials, and difficulties in tracing containers. To address these issues and mitigate risks associated with the transportation of hazardous goods, researchers have explored the implementation of blockchain technology in the maritime sector. Blockchain offers decentralization, transparency, and auditability of transactions, as well as the ability to trace and track cargo, particularly hazardous materials. Despite its potential, there is limited research available on the practical implementation of blockchain for hazardous material traceability. This research paper aims to investigate the application of blockchain technology in enhancing hazardous material traceability in seaports, contributing to the growing body of knowledge regarding blockchain's potential in this area and providing valuable insights for future research and practical implementations. Moreover, the paper suggests a preliminary framework for an optimized blockchain algorithm for hazardous material traceability. The main findings highlight the significant potential of blockchain technology in improving traceability of hazardous materials in seaports. Real-time tracking and monitoring of hazardous materials from origin to destination can be achieved through blockchain's distributed nature, reducing the risk of data manipulation or fraud. The immutability of blockchain records ensures the integrity and accuracy of critical data related to material composition, handling procedures, and safety certifications. Furthermore, blockchain's decentralized control allows for collaborative traceability in seaports, involving stakeholders such as port authorities, shipping companies, regulatory bodies, and manufacturers. This distributed governance model promote

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

OPTIMIZING HYPERPARAMETERS OF AN ARTIFICIAL NEURAL NETWORK MODEL FOR TRAFFIC INCIDENT DETECTION 50

OPTIMIZING HYPERPARAMETERS OF AN ARTIFICIAL NEURAL NETWORK M...

引用

50th International Conference on Computers and Industrial engineering: Sustainable Digital Transformation, CIE 2023

作者： Elsahly, O. Abdelfatah, A. Engineering Systems Management PhD Program American University of Sharjah Sharjah United Arab Emirates Department of Civil Engineering American University of Sharjah Sharjah United Arab Emirates

ISBN: (纸本)9781713886952

This paper discusses the optimization of hyperparameters of the Multilayer Feedforward (MLF) Artificial Neural Network (ANN), for Automatic Incident Detection (AID) within freeway systems. The MLF model was developed and tested using simulated data generated from VISSIM traffic simulation software. The optimized hyperparameters include the number of hidden layers, the size of hidden layers, the learning rate, momentum, error epsilon, and training cycles. To reduce computational time, a stepwise approach was adopted to optimize these hyperparameters. The model's performance was evaluated based on the Fscore, which is the harmonic mean of the recall and precision metrics. This evaluation metric was used because the AID is an imbalanced binary classification problem, where normal instances are the majority class and incident instances are the minority class. The results showed that optimizing the hyperparameters of the MLF model resulted in a 0.79% improvement in the F-score of the model and a 0.32% improvement in the overall accuracy of the model. The near-optimal hyperparameters for the MLF model were determined to be 1 hidden layer with 35 neurons, a learning rate of 0.015, momentum of 0.9, an error epsilon of 1.00E-10, and 1000 training cycles. The study provides insights into optimizing the hyperparameters of ANNs for AID applications in traffic management systems, which can help improve the performance of such systems. The optimized model can be utilized by Traffic Management Centres (TMCs) to detect incidents accurately and in a timely manner, thereby reducing the negative impacts of traffic incidents and ensuring safe and efficient travel for drivers. © 2023 Computers and Industrial engineering. All rights reserved.

关键词： Multilayer neural networks

来源：评论

学校读者我要写书评

暂无评论

Optimized photonic integrated circuit components for optical coherence tomography at 1060 nm

Optimized photonic integrated circuit components for optical...

引用

CLEO: Applications and Technology in CLEO 2024, CLEO: A and T 2024 - Part of Conference on Lasers and Electro-Optics

作者： Hao, Senyue Adkins, Aaron J. Zhang, Yitian Zhou, Chao Department of Electrical & Systems Engineering Washington University Saint Louis United States Imaging Science PhD Program Washington University Saint Louis United States Department of Biomedical Engineering Washington University Saint Louis United States

To implement optical coherence tomography on photonic chips, we developed optimized and experimentally validated silicon nitride-based components for photonic integrated circuits in order to achieve high sensitivity a... 详细信息

关键词： Photonic integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Optimized photonic integrated circuit components for optical coherence tomography at 1060 nm

Optimized photonic integrated circuit components for optical...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

ISBN: (纸本)9781957171395

关键词： Photonic integrated circuits

来源：评论

学校读者我要写书评

暂无评论

OPTIMIZING HYPERPARAMETERS OF RANDOM FOREST MODEL FOR TRAFFIC INCIDENT DETECTION 50

OPTIMIZING HYPERPARAMETERS OF RANDOM FOREST MODEL FOR TRAFFI...

引用

50th International Conference on Computers and Industrial engineering: Sustainable Digital Transformation, CIE 2023

作者： Elsahly, O. Abdelfatah, A. Alshraideh, H. Engineering Systems Management PhD Program American University of Sharjah Sharjah United Arab Emirates Department of Civil Engineering American University of Sharjah Sharjah United Arab Emirates Department of Industrial Engineering American University of Sharjah Sharjah United Arab Emirates

ISBN: (纸本)9781713886952

Traffic incidents are non-recurring events that disrupt normal traffic flow and can have negative impacts on traffic operations, safety, and economy. As a result, there is a growing need for developing effective and reliable Automatic Incident Detection (AID) systems to detect incidents as early as possible to minimize their impacts. Machine Learning models, such as Neural Networks and Random Forests, have been utilized to develop AID models. However, the performance of machine learning models is significantly determined by its hyperparameters that need to be tuned to improve its performance in detecting incidents accurately and quickly. In this study, incident and normal traffic scenarios were generated using traffic simulator data, which is used to train and test a Random Forest incident detection model. The proposed methodology uses VISSIM microsimulation software to generate a diverse dataset of incident and normal conditions scenarios. Traffic parameters such as flow rate, speed, and occupancy at upstream and downstream stations were used as input variables for the model. The Random Forest model was trained and tested through RapidMiner software with 5-fold cross validation. Model performance was enhanced through the model hyperparameters tunning. An improvement of 0.35% in the F-score and 0.15% in the overall accuracy was achieved compared to the default model parameters. Findings of this study suggest that the tunning of hyperparameters of Random Forest models is crucial for developing accurate AID systems. The proposed methodology and optimized hyperparameter values provided by this study can be used as a guideline for developing Random Forest models for incident detection in transportation systems. Overall, this study contributes to the development of accurate and efficient traffic incident detection systems, which could help to mitigate the negative impacts of traffic incidents and improve transportation operations, safety, and economy. © 2023 Computers an

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

Some Comments on the Aircraft Landing Problem: How Optimal is the First Come First Serve Policy?

引用

Transportation Research Procedia 2025年 82卷 923-937页

作者： Aitichya Chandra Nipun Choubey Ashish Verma PhD Student Department of Civil Engineering Indian Institute of Science (IISc) Bangalore India PhD Student Robert Bosch Centre for Cyber-Physical Systems (RBCCPS) Indian Institute of Science (IISc) Bangalore India Professor Department of Civil Engineering Indian Institute of Science (IISc) Bangalore India

Managing aircraft landings in the Terminal Area (TMA) is a key challenge in Air Traffic Management (ATM) and has been gaining attention due to the consistent growth of air traffic congestion and delays. The Aircraft Landing Problem (ALP) deals with this issue by optimally scheduling the aircraft landings in the TMA so that the overall delay is minimized. Most modern models and solution methods addressing ALP allow aircraft re-positioning. However, majority of the airports still employ the First Come First Serve (FCFS) policy to manage landings. This study seeks to assess the optimality of the FCFS policy. Mixed Integer Programming (MIP) models are proposed to replicate FCFS, and the solutions are compared with the results from a state-of-the-art (SOA) model. Results suggest that FCFS results in 1.76 times more deviation from the target landing time than the SOA outcome on a single runway. While, in case of multiple runways, FCFS results are comparable with the SOA model outcomes. Findings also suggest that different holding times may result in different runway combinations. Implications of this study can help ATM decision-makers estimate the overall delay/deviation arising from FCFS and efficiently plan the available resource, workforce, and infrastructure augmentation decisions under FCFS policy.

关键词： Aircraft Landing Problem (ALP) First Come First Serve (FCFS) Mixed Integer Programming (MIP) Air Traffic Management (ATM)

来源：评论

学校读者我要写书评

暂无评论

The Impact of Blockchain and AI in the Healthcare 3

The Impact of Blockchain and AI in the Healthcare

引用

3rd IEEE International Conference on Electrical Power and Energy systems, ICEPES 2024

作者： Thatikonda, Ramya Kempanna, M. Tatikonda, Reshmi Bhuvanesh, A. University of the Cumberlands PhD in Information Technology Williamsburg United States Bangalore Institute of Technology Department of Artificial Intelligence and Machine Learning Karnataka Bengaluru India University of the Central Missouri Masters in Computer Information Systems Warrensburg United States PSN College of Engineering and Technology Department of Electrical and Electronics Engineering Tamil Nadu Tirunelveli India

ISBN: (纸本)9798350390728

Integrating blockchain and artificial intelligence (AI) in healthcare presents a transformative opportunity. Therefore, this can revolutionize patient care by improving data management and medical research. Decentralization and invulnerability granted by blockchain technology foster improved data consistency and interoperability. AI enhances blockchain by streamlining data examination, automatic tasks, and decision-making processes, resulting in more precise medical diagnoses and tailored therapy programs. The intersection of blockchain and AI is explored, along with their potential benefits and practical applications in healthcare. The document examines the hurdles encountered when integrating innovations, including scalability, interoperability, and regulatory adherence issues. Additionally, the study investigates moral questions surrounding data ownership and patient consent, thereby protecting confidentiality and trust. The synergy between blockchain, AI, and healthcare will lead to transformative advancements. It pledges to fortify data safety and expedite information sharing. Consequently, this will result in an improved, price-effective, and patient-focused healthcare environment. Recommendations were made for additional research and practical implementation in healthcare technology. The study should concentrate on creating scalable and compatible blockchain systems. A vital factor for extensive use is tackling regulatory and moral issues. Hybrid blockchain designs and federated learning strategies will bolster information privacy and utility. © 2024 IEEE.

关键词： Data consistency

来源：评论

学校读者我要写书评

暂无评论

Photoresponse of Thermally Evaporated Copper Oxide-Based Solar Cells 1

Photoresponse of Thermally Evaporated Copper Oxide-Based Sol...

引用

1st Middle East and North Africa Solar Conference, MENA-SC 2023

作者： Alami, Abdul Hai Ayoub, Mohamad Alashkar, Adnan Alasad, Shamma Mdallal, Ayman Khuri, Siren Aljaghoub, Haya University of Sharjah Sustainable Energy & Power Systems Research Centre Sustainable and Renewable Energy Engineering Department Sharjah United Arab Emirates American University of Sharjah Materials Science and Engineering PhD Program Sharjah United Arab Emirates American University of Sharjah Mechancial Engineering Department Sharjah United Arab Emirates University of Sharjah Sustainable Energy & Power Systems Research Centre Sharjah United Arab Emirates University of Sharjah Industrial Engineering and Engineering Management Department Sharjah United Arab Emirates

ISBN: (纸本)9781665491464

This study reports on the fabrication and characterization of a copper oxide (CuO)-based photoactive cell. Copper was thermally evaporated onto two substrates and post-treated using chemical and thermal treatments to obtain different semiconducting types of CuO. Absorption measurements were conducted to obtain the bandgaps of CuO, which were found to be 1.51 eV and 1.21 eV, for the chemically and thermally treated CuO, respectively. Finally, a chronoamperometry test was conducted to confirm the photoresponse of the cell, which showed a doubling of output current values under light conditions compared to dark conditions. © 2023 IEEE.

关键词： Copper oxides

来源：评论

学校读者我要写书评

暂无评论

Enhancing Schizophrenia Prediction Using Class Balancing and SHAP Explainability Techniques on EEG Data

Enhancing Schizophrenia Prediction Using Class Balancing and...

引用

Pattern Recognition systems (ICPRS), International Conference on

作者： Javiera T. Arias César A. Astudillo PhD in Engineering Systems University of Talca Curicó Chile Department of Computer Science Faculty of Engineering Universidad de Talca Curicó Chile

Machine learning (ML) makes predictions or supports decision making based on data, achieving high accuracy, saving time and resources, and even running real-time analysis. However, one drawback of these models is the lack of transparency in complex models, reducing confidence in sensitive fields such as health. This paper analyzes electroencephalogram (EEG) data to predict schizophrenia in patients. Three classifiers are compared, considering Support Vector Machines(SVM), Adaptive Boosting (AdaBoost), and Extreme Gradient Boosting (XGBoost). Three metrics are used to measure the classification process, including accuracy (ACC), area under the curve (AUC) and F-l score (F1). XAI is incorporated into the pipeline to identify relevant features. XGBoost is the model with the best performance in predicting schizophrenia cases, reaching an ACC = 0.93, AUC = 0.93 and F1 score = 0.92, outperforming the SVM and AdaBoost algorithms. The SHAP explainability technique was applied on the XGBoost model, identifying the sex, IQ, delta T6, and delta Pz waves as the most relevant characteristics in the prediction processes. Based on the data analysis, we found that schizophrenia causes an alteration of the delta wave in an EEG, which is different to other mental illnesses. On the other hand, the study generates a specific impact by showing that XGBoost presents better results in 3 validation metrics (ACC, AUC, and F1 Score) compared to SVM and AdaBoost. It is shown that balancing classes is essential to obtain better ML predictions.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Space Division Multiplexing Optical Coherence Tomography for Wide-field Angiographic Imaging of the Human Retina

Space Division Multiplexing Optical Coherence Tomography for...

引用

2024 Frontiers in Optics, FiO 2024

作者： Adkins, Aaron J. Hao, Senyue Ren, Chao Song, Andrew Zhou, Chao Department of Biomedical Engineering Washington University in St. Louis St. LouisMO United States Imaging Science PhD Program Washington University in St. Louis St. LouisMO United States Department of Electrical and Systems Engineering Washington University in St. Louis St. LouisMO United States

We have constructed a parallelized 4-channel multi-beam optical coherence tomography system capable of achieving high speed and wide field of view angiographic imaging of the retina. © Optica Publishing Group 202... 详细信息

关键词： Optical coherence tomography

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：