检索结果-内蒙古大学图书馆

Open Innovations for Tourism Logistics Design: A Case Study of a Smart Bus Route Design for the Medical Tourist in the City of Greater Mekong Subregion

引用

Journal of Open Innovation: technology, Market, and Complexity 2022年第4期8卷

作者： Ngeoywijit, Sumalee Kruasom, Tawamin Ugsornwongand, KiengKwan Pitakaso, Rapeepan Sirirak, Worapot Nanthasamroeng, Natthapong Kotmongkol, Thachada Srichok, Thanatkij Khonjun, Surajet Kaewta, Chutchai Department of International Business Management Faculty of Management Science Ubon Ratchathani University 85 Sathonlamark Muang SriKai Warin Chamrap Ubon Ratchathani 34190 Thailand Department of Financial and Investment Faculty of Management Science Ubon Ratchathani University 85 Sathonlamark Muang SriKai Warin Chamrap Ubon Ratchathani 34190 Thailand Artificial Intelligence Optimization SMART Laboratory Department of Industrial Engineering Faculty of Engineering Ubon Ratchathani University 85 Sathonlamark Muang SriKai Warin Chamrap Ubon Ratchathani 34190 Thailand Department of Industrial Engineering Faculty of Engineering Rajamangala University of Technology Lanna Chiang Rai 50300 Thailand Artificial Intelligence Optimization SMART Laboratory Department of Engineering Technology Faculty of Industrial Technology Ubon Ratchathani Rajabhat University 2 Ratchathani Nai Muang Ubon Ratchathani 34000 Thailand Department of Logistics Management Faculty of Industrial Technology Ubon Ratchathani Rajabhat University 2 Ratchathani Nai Muang Ubon Ratchathani 34000 Thailand Artificial Intelligence Optimization SMART Laboratory Department of Computer Science Faculty of Computer Science Ubon Ratchathani Rajabhat University 2 Ratchathani Nai Muang Ubon Ratchathani 34000 Thailand

One of the industries with the fastest growth rates worldwide, and notably in Thailand, is medical tourism. With connections to Cambodia and Laos, Ubon Ratchathani is located in lower northeastern Thailand, close to Vietnam and Myanmar. Therefore, there is a significant chance that this region will welcome medical travelers. High-quality medical facilities are available in Ubon Ratchathani to fulfill the needs of medical tourists. A visitor’s decision to travel to Ubon Ratchathani for medical treatment is influenced by factors other than the high-level medical facilities, such as lodging, accessibility to public transportation, and tourist attractions. The public transportation services in Ubon Ratchathani, especially the public bus system, are poorly designed and may let down visitors. The purpose of this study is to develop a smart public bus route design that will meet tourists’ demands. The concept of open innovation will be utilized to develop the model. We surveyed 400 visitors to Ubon Ratchathani. The tourists’ opinions and views of public transportation will be made public and used as an input parameter when designing bus routes. The bus route can then be constructed using the differential evolution algorithm (DE). A web-based smart public transportation system was built. In order to construct an efficient smart public bus system (SPBS), open innovation was used in the development phase. According to the computational results, the new routes using DE lead to a 5.97% reduction in travel distance when compared to the output of the more well-known genetic method. More than 98.5% of visitors are satisfied with the new routes, and once they start running, 99.5% of all respondents plan to use public transit. © 2022 by the authors.

关键词： differential evolution algorithm environmentally friendly GPS monitoring public transportation system SMART bus system

来源：评论

学校读者我要写书评

暂无评论

A parameter adaptive de algorithm on real-parameter optimization

A parameter adaptive de algorithm on real-parameter optimiza...

引用

作者： Pan, Jeng-Shyang Yang, Cheng Meng, Fanjia Chen, Yuxin Meng, Zhenyu College of Computer Science and Engineering Shandong University of Science and Technology Qingdao China Institute of Artificial Intelligence Fujian University of Technology Fuzhou China Guanzhuang Central Primary School of Zhangqiu District Jinan China Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou China

Differential Evolution (DE) algorithm generates a population of individuals by encoding with a floating point vector, and it is a simple and effective population-based stochastic optimization algorithm for global optimization of continuous space. Because of its excellent performance, DE variants can be applied in a wide range of applications in science and engineering. However, the performance of DE is sensitive to the choice of trial vector generation strategy and the associated control parameters. Therefore, it is necessary to choose appropriate mutation strategy and control parameters when tackling optimization applications. In this paper, an adaptive update mechanism is proposed to update control parameters F and Cr. The experimental results are verified on the CEC 2013 test suite which contains 28 benchmark functions for the evaluation of single objective real parameter optimization. The proposed algorithm is compared with jDE, iwPSO and ccPSO, and experiment results show its good performance. © 2020 - IOS Press and the authors. All rights reserved.

关键词： Global optimization

来源：评论

学校读者我要写书评

暂无评论

PyMIC: A deep learning toolkit for annotation-efficient medical image segmentation

arXiv

引用

arXiv 2022年

作者： Wang, Guotai Luo, Xiangde Gu, Ran Yang, Shuojue Qu, Yijie Zhai, Shuwei Zhao, Qianfei Li, Kang Zhang, Shaoting School of Mechanical and Electrical Engineering University of Electronic Science and Technology of China Chengdu China Shanghai Artificial Intelligence Laboratory Shanghai China Laboratory for Computational Sensing and Robotics Johns Hopkins University Baltimore United States West China Biomedical Big Data Center West China Hospital Sichuan University Chengdu China

Background and Objective: Open-source deep learning toolkits are one of the driving forces for developing medical image segmentation models. Existing toolkits mainly focus on fully supervised segmentation and require full and accurate pixel-level annotations that are time-consuming and difficult to acquire for segmentation tasks, which makes learning from imperfect labels highly desired for reducing the annotation cost. We aim to develop a new deep learning toolkit to support annotation-efficient learning for medical image segmentation. Methods: Our proposed toolkit named PyMIC is a modular deep learning library for medical image segmentation tasks. In addition to basic components that support development of high-performance models for fully supervised segmentation, it contains several advanced components tailored for learning from imperfect annotations, such as loading annotated and unannounced images, loss functions for unannotated, partially or inaccurately annotated images, and training procedures for co-learning between multiple networks, etc. PyMIC supports development of semi-supervised, weakly supervised and noise-robust learning methods for medical image segmentation. Results: We present several illustrative medical image segmentation tasks based on PyMIC: (1) Achieving competitive performance on fully supervised learning;(2) Semi-supervised cardiac structure segmentation with only 10% training images annotated;(3) Weakly supervised segmentation using scribble annotations;and (4) Learning from noisy labels for chest radiograph segmentation. Conclusions: The PyMIC toolkit is easy to use and facilitates efficient development of medical image segmentation models with imperfect annotations. It is modular and flexible, which enables researchers to develop high-performance models with low annotation cost. The source code is available at:https://***/HiLab-git/PyMIC. © 2022, CC BY.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Bi directional sparse attention recurrent autoencoder based intrusion detection for VANET security with tuna swarm optimization

引用

Scientific reports 2025年第1期15卷 18406页

作者： R Gopi V Thiruppathy Kesavan Md Jakir Hossen Nor Hidayati Binti Abdul Aziz Faculty of Computer Science & Engineering Dhanalakshmi Srinivasan Engineering College Perambalur Tamil Nadu India. Post Doctoral Fellow Department of Engineering and Technology Multimedia University Malaysia Melaka Malaysia. Faculty of Information Technology Dhanalakshmi Srinivasan Engineering College Perambalur India. Faculty of Engineering and Technology (FET) Center for Advanced Analytics (CAA) COE for Artificial Intelligence Multimedia University Melaka Malaysia. jakir.hossen@mmu.edu.my. Faculty of Engineering and Technology (FET) Center for Advanced Analytics (CAA) COE for Artificial Intelligence Multimedia University Melaka Malaysia.

Vehicular Ad-hoc Networks (VANETs) have garnered a lot of consideration and research in last decades. By enhancing safety and comfort, VANETs are essential to the development of self-driving and semi-self-driving cars. Security risks that are specific to VANET or that are observed in ad hoc networks, however, pose significant difficulties. External communication with the situation through data control and Cooperative Awareness Messages (CAMs) exchanges is crucial for these vehicles. Numerous assaults could possibly target VANETs. VANETs may be vulnerable to several types of assaults. The lack of intrusion detection systems, inadequate encryption methods, insecure communication routes, and inadequate authentication processes are some of the technological flaws in VANETs that make smart vehicles vulnerable to attacks. The security and effectiveness of smart vehicle operations suffer because these flaws allow attackers to intercept, change, or interrupt communication between vehicles. Owing to these security concerns, this study introduces a Bi-directional sparse Attention-recurrent Auto Encoder (BSAR-AE) based Intrusion Detection System (IDS) in VANET. The system uses the Tuna Swarm optimizer (TSO) with the enhancement through the implementation of Deep Neural Network (DNN) based feature selection in VANET. It is a useful technique for resolving issues with deep layer neural networks, like low velocity and overfitting issues in learning. The evolutionary based optimization effectively tuned the hyper parameters of the DL model which will improve the detection accuracy. The system use of the CICIDS2017 dataset, which is associated with actual data and the experimented analysis shows that the proposed model is effectual for detecting the malicious attacks in VANET with improved accuracy of 98.7%.

关键词： Anomaly detection Auto encoder Bidirectional long short term memory networks Intrusion detection system Tuna swarm optimization Vehicular Ad-hoc networks

来源：评论

学校读者我要写书评

暂无评论

Image reconstruction from photoacoustic projections

引用

Photonics Insights 2024年第3期3卷 145-209页

作者： Chao Tian Kang Shen Wende Dong Fei Gao Kun Wang Jiao Li Songde Liu Ting Feng Chengbo Liu Changhui Li Meng Yang Sheng Wang Jie Tian Institute of Artificial Intelligence Hefei Comprehensive National Science CenterHefeiChina School of Engineering Science University of Science and Technology of ChinaHefeiChina Department of Anesthesiology the First Affiliated Hospital of USTCDivision of Life Sciences and MedicineUniversity of Science and Technology of ChinaHefeiChina Anhui Province Key Laboratory of Biomedical Imaging and Intelligent Processing HefeiChina College of Automation Engineering Nanjing University of Aeronautics and AstronauticsNanjingChina School of Information Science and Technology ShanghaiTech UniversityShanghaiChina Shanghai Clinical Research and Trial Center ShanghaiChina CAS Key Laboratory of Molecular Imaging Institute of AutomationChinese Academy of SciencesBeijingChina School of Precision Instruments and Optoelectronics Engineering Tianjin UniversityTianjinChina Academy for Engineering and Technology Fudan UniversityShanghaiChina Shenzhen Institute of Advanced Technology Chinese Academy of SciencesShenzhenChina Department of Biomedical Engineering College of Future TechnologyPeking UniversityBeijingChina National Biomedical Imaging Center Peking UniversityBeijingChina Departments of Ultrasound State Key Laboratory of Complex Severe and Rare DiseasesPeking Union Medical College HospitalChinese Academy of Medical Sciences and Peking Union Medical CollegeBeijingChina School of Engineering Medicine Beihang UniversityBeijingChina Key Laboratory of Big Data-Based Precision Medicine Beihang UniversityMinistry of Industry and Information TechnologyBeijingChina

Photoacoustic computed tomography(PACT)is a rapidly developing biomedical imaging modality and has attracted substantial attention in recent *** reconstruction from photoacoustic projections plays a critical role in image formation in *** we review six major classes of image reconstruction approaches developed in the past three decades,including delay and sum,filtered back projection,series expansion,time reversal,iterative reconstruction,and deep-learning-based *** principal ideas and implementations of the algorithms are summarized,and their reconstruction performances under different imaging scenarios are *** challenges,future directions,and perspectives for the development of image reconstruction algorithms in PACT are also *** review provides a self-contained reference guide for beginners and specialists in the photoacoustic community,to facilitate the development and application of novel photoacoustic image reconstruction algorithms.

关键词： optical imaging photoacoustic tomography image reconstruction deep learning

来源：评论

学校读者我要写书评

暂无评论

Effective Class-Imbalance learning based on SMOTE and Convolutional Neural Networks

arXiv

引用

arXiv 2022年

作者： Joloudari, Javad Hasannataj Marefat, Abdolreza Nematollahi, Mohammad Ali Oyelere, Solomon Sunday Hussain, Sadiq Department of Computer Engineering Faculty of Engineering University of Birjand Birjand*** Iran Department of Artificial Intelligence Technical and Engineering Faculty South Tehran Branch Islamic Azad University Tehran Iran Department of Computer Sciences Fasa University Fasa Iran Department of Computer Science Electrical and Space Engineering Luleå University of Technology SkellefteåSE-931 87 Sweden Examination Branch Dibrugarh University Assam Dibrugarh786004 India

Imbalanced data (ID) is a problem that deters Machine Learning (ML) models for achieving satisfactory results. ID is the occurrence of a situation where the quantity of the samples belonging to one class outnumbers that of the other by a wide margin, making such models' learning process biased towards the majority class. In recent years, to address this issue, several solutions have been put forward, which opt for either synthetically generating new data for the minority class or reducing the number of majority classes for balancing the data. Hence, in this paper, we investigate the effectiveness of methods based on Deep Neural Networks (DNNs) and Convolutional Neural Networks (CNNs), mixed with a variety of well-known imbalanced data solutions meaning oversampling and undersampling. To evaluate our methods, we have used KEEL, breast cancer, and Z-Alizadeh Sani datasets. In order to achieve reliable results, we conducted our experiments 100 times with randomly shuffled data distributions. The classification results demonstrate that the mixed Synthetic Minority Oversampling Technique (SMOTE)-Normalization-CNN outperforms different methodologies achieving 99.08% accuracy on the 24 imbalanced datasets. Therefore, the proposed mixed model can be applied to imbalanced binary classification problems on other real datasets. © 2022, CC BY.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

GSMorph: Gradient Surgery for cine-MRI Cardiac Deformable Registration

arXiv

引用

arXiv 2023年

作者： Dou, Haoran Bi, Ning Han, Luyi Huang, Yuhao Mann, Ritse Yang, Xin Ni, Dong Ravikumar, Nishant Frangi, Alejandro F. Huang, Yunzhi University of Leeds Leeds United Kingdom Department of Radiology and Nuclear Medicine Radboud University Medical Centre Nijmegen Netherlands Department of Radiology Netherlands Cancer Institute Amsterdam Netherlands National-Regional Key Technology Engineering Laboratory for Medical Ultrasound School of Biomedical Engineering Health Science Center Shenzhen University China Lab Shenzhen University China Marshall Laboratory of Biomedical Engineering Shenzhen University China Shenzhen RayShape Medical Technology Co. Ltd China Division of Informatics Imaging and Data Science Schools of Computer Science and Health Sciences University of Manchester Manchester United Kingdom Electrical Engineering and Cardiovascular Sciences Departments KU Leuven Leuven Belgium Alan Turing Institute London United Kingdom Institute for AI in Medicine School of Artificial Intelligence Nanjing University of Information Science and Technology Nanjing China

Deep learning-based deformable registration methods have been widely investigated in diverse medical applications. Learning-based deformable registration relies on weighted objective functions trading off registration accuracy and smoothness of the deformation field. Therefore, they inevitably require tuning the hyperparameter for optimal registration performance. Tuning the hyperparameters is highly computationally expensive and introduces undesired dependencies on domain knowledge. In this study, we construct a registration model based on the gradient surgery mechanism, named GSMorph, to achieve a hyperparameter-free balance on multiple losses. In GSMorph, we reformulate the optimization procedure by projecting the gradient of similarity loss orthogonally to the plane associated with the smoothness constraint, rather than additionally introducing a hyperparameter to balance these two competing terms. Furthermore, our method is model-agnostic and can be merged into any deep registration network without introducing extra parameters or slowing down inference. In this study, We compared our method with state-of-the-art (SOTA) deformable registration approaches over two publicly available cardiac MRI datasets. GSMorph proves superior to five SOTA learning-based registration models and two conventional registration techniques, SyN and Demons, on both registration accuracy and smoothness. © 2023, CC BY.

关键词： Medical applications

来源：评论

学校读者我要写书评

暂无评论

Anhydrous sol-gel synthesis of TiO₂ nanoparticles: Evaluating their impact on protein interactions in biological systems

Journal of Trace Elements and Minerals

引用

Journal of Trace Elements and Minerals 2024年 7卷

作者： Marycleopha, Manka Yaou Balarabe, Bachir Adjama, Irédon Moussa, Hassimi Anandaram, Harishchander Abdoul Razak, Moumouni Wagé School of Forensic Sciences National Forensic Sciences University Sector-09 Gandhinagar 382007 India School of Engineering and Technology National Forensic Sciences University Sector-09 Gandhinagar 382007 India School of Pharmacy National Forensic Sciences University Sector-09 Gandhinagar 382007 India Environmental Science Department Faculty of Agronomic Sciences Boubakar Bâ University of Tillaberi BP: 175 Tillaberi Niger Amrita School of Artificial Intelligence Coimbatore Amrita Vishwa Vidyapeetham India University Andre Salifou Faculty of Science and Technology Department of Exact Sciences BP: 656 Zinder Niger

This study focused on the synthesis of anhydrous sol-gel synthesis of TiO2 nanoparticles using a hydrothermal route. The chemical properties of the synthesized TiO2 nanoparticles were confirmed through Fourier Transfo... 详细信息

This study focused on the synthesis of anhydrous sol-gel synthesis of TiO₂ nanoparticles using a hydrothermal route. The chemical properties of the synthesized TiO₂ nanoparticles were confirmed through Fourier Transform Infrared Spectroscopy (FT-IR) and UV–Vis spectroscopy, highlighting their optical features. Additionally, Energy Dispersive X-ray Spectrometer (EDX) analysis revealed the high purity of the nanomaterial, while the Transmission Electron Microscope (TEM) displayed spherical particles ranging in size from ≥ 80 nm. Furthermore, X-ray diffraction analysis (XRD), Raman and HRTEM analyses indicated that the nanomaterial exhibits an anatase and rutile structure. When, Hen Egg-White Lysozyme (HEWL) incubated with TiO₂ led to notable changes: reduced fluorescence indicating protein unfolding, increased light scattering showing protein aggregation, the presence of amyloid fibrils and hydrophobic regions, and reduced enzyme activity. FTIR spectroscopy revealed amyloid structure formation, while Dynamic Light Scattering confirmed the presence of larger protein oligomers. These findings highlight TiO₂'s adverse impact on HEWL structure and function, emphasizing the need for further research on nanoparticle toxicity in biological systems, particularly in biomedical applications. © 2023 The Author(s)

关键词： Hen egg-white lysozyme (HEWL) Influence Interaction Nanoparticles

来源：评论

学校读者我要写书评

暂无评论

STAR-RIS Enabled ISAC Systems With RSMA: Joint Rate Splitting and Beamforming Optimization

引用

IEEE Transactions on Cognitive Communications and Networking 2025年

作者： Liu, Yuan Zhang, Ruichen Jiang, Ruihong Zhu, Yongdong Hu, Huimin Ni, Qiang Fei, Zesong Niyato, Dusit Zhejiang Laboratory Research Center for Space Computing System Hangzhou311100 China Nanyang Technological University College of Computing and Data Science Singapore 639798 Singapore Beijing University of Posts and Telecommunications State Key Laboratory of Networking and Switching Technology Beijing100876 China Cambridge Mechatronics Ltd CambridgeCB1 2PH United Kingdom Xi’an University of Posts and Telecommunications School of Communications and Information Engineering School of Artificial Intelligence Xi’an710121 China Lancaster University School of Computing and Communications LancasterLA1 4WA United Kingdom Beijing Institute of Technology School of Information and Electronics Beijing100081 China

This paper delves into an integrated sensing and communication (ISAC) system bolstered by a simultaneously transmitting and reflecting reconfigurable intelligent surface (STAR-RIS). Within this system, a base station (BS) is equipped with communication and radar capabilities, enabling it to communicate with ground terminals (GTs) and concurrently probe for echo signals from a target of interest. Moreover, to manage interference and improve communication quality, the rate splitting multiple access (RSMA) scheme is incorporated into the system. The signal-to-interference-plus-noise ratio (SINR) of the received sensing echo signals is a measure of sensing performance. We formulate a joint optimization problem of common rates, transmit beamforming at the BS, and passive beamforming vectors of the STAR-RIS. The objective is to maximize sensing SINR while guaranteeing the communication rate requirements for each GT. We present an iterative algorithm to address the non-convex problem by invoking Dinkelbach’s transform, semidefinite relaxation (SDR), majorization-minimization, and sequential rank-one constraint relaxation (SROCR) theories. Simulation results manifest that the performance of the studied ISAC network enhanced by the STAR-RIS and RSMA surpasses other benchmarks considerably. The results evidently indicate the superior performance improvement of the ISAC system with the proposed RSMA-based transmission strategy design and the dynamic optimization of both transmission and reflection beamforming at STAR-RIS. © 2015 IEEE.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

GenFace: A Large-Scale Fine-Grained Face Forgery Benchmark and Cross Appearance-Edge Learning

arXiv

引用

arXiv 2024年

作者： Zhang, Yaning Yu, Zitong Wang, Tianyi Huang, Xiaobin Shen, Linlin Gao, Zan Ren, Jianfeng Computer Vision Institute College of Computer Science and Software Engineering Shenzhen University Shenzhen518060 China School of Computing and Information Technology Great Bay University Dongguan523000 China National Engineering Laboratory for Big Data System Computing Technology Shenzhen University Shenzhen518060 China Nanyang Technological University 50 Nanyang Ave Block N 4 639798 Singapore Shenzhen Institute of Artificial Intelligence and Robotics for Society Shenzhen518129 China Guangdong Key Laboratory of Intelligent Information Processing Shenzhen University China Jinan250014 China Key Laboratory of Computer Vision and System Ministry of Education Tianjin University of Technology Tianjin300384 China School of Computer Science University of Nottingham Ningbo China

The rapid advancement of photorealistic generators has reached a critical juncture where the discrepancy between authentic and manipulated images is increasingly indistinguishable. Thus, benchmarking and advancing techniques detecting digital manipulation become an urgent issue. Although there have been a number of publicly available face forgery datasets, the forgery faces are mostly generated using GAN-based synthesis technology, which does not involve the most recent technologies like diffusion. The diversity and quality of images generated by diffusion models have been significantly improved and thus a much more challenging face forgery dataset shall be used to evaluate SOTA forgery detection literature. In this paper, we propose a large-scale, diverse, and fine-grained high-fidelity dataset, namely GenFace, to facilitate the advancement of deepfake detection, which contains a large number of forgery faces generated by advanced generators such as the diffusion-based model and more detailed labels about the manipulation approaches and adopted generators. In addition to evaluating SOTA approaches on our benchmark, we design an innovative Cross Appearance-Edge Learning (CAEL) detector to capture multi-grained appearance and edge global representations, and detect discriminative and general forgery traces. Moreover, we devise an Appearance-Edge Cross-Attention (AECA) module to explore the various integrations across two domains. Extensive experiment results and visualizations show that our detection model outperforms the state of the arts on different settings like cross-generator, cross-forgery, and cross-dataset evaluations. Code and datasets will be available at https://***/Jenine-321/GenFace. Copyright © 2024, The Authors. All rights reserved.

关键词： Image enhancement

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：