检索结果-内蒙古大学图书馆

12th International Electrical engineering Congress, iEECON 2024

作者： Miangphan, Sudatip Kawdungta, Supakit Torrungrueng, Danai Akkaraekthalin, Prayoot Rajamangala University Of Technology Lanna Faculty Of Engineering Chiang Mai Thailand Research Center Of Innovation Digital And Electromagnetic Technology King Mongkut's University Of Technology North Bangkok Faculty Of Technical Education Bangkok Thailand King Mongkut's University Of Technology North Bangkok Faculty Of Engineering Department Of Electrical And Computer Engineering Bangkok Thailand

ISBN: (纸本)9798350383591

This paper proposes the design of a compact inverted C patch on-body antenna for biomedical applications. The antenna structure consists of an inverted C patch on the top of the FR4 substrate, integrated with the radiation rectangular patch at the bottom by using a shorted pin. The ground plane is also at the bottom of the FR4 substrate, separated by a gap. The proposed antenna is considered on the human skin in the environment of on-body communications. From simulated results, the antenna has | S11| less than -10 dB covered the frequency range of 2.36-2.58 GHz, uni-directional radiation pattern, and -4.5 dBi of gain at 2.45 GHz. It is found that the lossy human skin affects antenna characteristics by reducing its gain and efficiency. Moreover, the proposed antenna is appropriate for on-body communication systems. © 2024 IEEE.

关键词： Slot antennas

来源：评论

学校读者我要写书评

暂无评论

Parameter estimation of nonlinear systems: dwarf mongoose optimization algorithm with key term separation principle

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第12期14卷 16921-16931页

作者： Mehmood, Khizer Chaudhary, Naveed Ishtiaq Khan, Zeshan Aslam Cheema, Khalid Mehmood Raja, Muhammad Asif Zahoor Department of Electrical and Computer Engineering International Islamic University Islamabad44000 Pakistan Future Technology Research Center National Yunlin University of Science and Technology 123 University Road Section 3 Yunlin Douliou64002 Taiwan Department of Electronic Engineering Fatima Jinnah Women University Rawalpindi46000 Pakistan

In recent years, swarm intelligence-based metaheuristics are extensively explored for optimizing challenging and stiff nonlinear problems. This research explores the identification of the input nonlinear output error (NOE) model through a swarm intelligence-based metaheuristic called dwarf mongoose optimization algorithm (DMOA). Further, the key term separation method (KTSM) based identification model is presented to address the issue of over-parameterization. The DMOA performance is deeply examined for various generations, population sizes, and signal-to-noise ratios. The comparative analyses of the DMOA with the recent counterpart through observations of non-parametric statistical tests confirmed the effectiveness of the DMOA for NOE identification. © 2023, The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Nonlinear systems

来源：评论

学校读者我要写书评

暂无评论

Structural and functional connectivity of the whole brain and subnetworks in individuals with mild traumatic brain injury:predictors of patient prognosis

引用

Neural Regeneration Research 2024年第7期19卷 1553-1558页

作者： Sihong Huang Jungong Han Hairong Zheng Mengjun Li Chuxin Huang Xiaoyan Kui Jun Liu Department of Radiology The Second Xiangya HospitalCentral South UniversityChangshaHunan ProvinceChina Department of Computer Science Aberystwyth UniversityAberystwythCeredigionUK Shenzhen Institutes of Advanced Technology Chinese Academy of SciencesShenzhenGuangdong ProvinceChina School of Computer Science and Engineering Central South UniversityChangshaHunan ProvinceChina Department of Radiology Quality Control Center of Hunan ProvinceChangshaHunan ProvinceChina Clinical Research Center for Medical Imaging of Hunan Province ChangshaHunan ProvinceChina

Patients with mild traumatic brain injury have a diverse clinical presentation,and the underlying pathophysiology remains poorly *** resonance imaging is a non-invasive technique that has been widely utilized to investigate neuro biological markers after mild traumatic brain *** approach has emerged as a promising tool for investigating the pathogenesis of mild traumatic brain injury.G raph theory is a quantitative method of analyzing complex networks that has been widely used to study changes in brain structure and ***,most previous mild traumatic brain injury studies using graph theory have focused on specific populations,with limited exploration of simultaneous abnormalities in structural and functional *** that mild traumatic brain injury is the most common type of traumatic brain injury encounte red in clinical practice,further investigation of the patient characteristics and evolution of structural and functional connectivity is *** the present study,we explored whether abnormal structural and functional connectivity in the acute phase could serve as indicators of longitudinal changes in imaging data and cognitive function in patients with mild traumatic brain *** this longitudinal study,we enrolled 46 patients with mild traumatic brain injury who were assessed within 2 wee ks of injury,as well as 36 healthy ***-state functional magnetic resonance imaging and diffusion-weighted imaging data were acquired for graph theoretical network *** the acute phase,patients with mild traumatic brain injury demonstrated reduced structural connectivity in the dorsal attention *** than 3 months of followup data revealed signs of recovery in structural and functional connectivity,as well as cognitive function,in 22 out of the 46 ***,better cognitive function was associated with more efficient ***,our data indicated that small-worldness in the acute sta

关键词： cognitive function cross-section follow-up functional connectivity graph theory longitudinal study mild traumatic brain injury prediction small-worldness structural connectivity subnetworks whole brain network

来源：评论

学校读者我要写书评

暂无评论

Transforming Cybersecurity in the digital Era: The Power of AI 2

Transforming Cybersecurity in the Digital Era: The Power of ...

引用

2nd International Conference on Cyber Resilience, ICCR 2024

作者： Mahfuri, Mahmoud Ghwanmeh, Sameh Almajed, Rsha Alhasan, Waseem Salahat, Mohammed Lee, Jin Hie Ghazal, Taher M. International University For Science And Technology Computer And Information Technology Department Damascus Syria American University In The Emirates Department Of Computer Scienc Dubai United Arab Emirates School Of Computer Science And Informatics De Montfort University Dubai Dubai United Arab Emirates College Of Engineering And Technology University Of Science And Technology Of Fujairah Fujairah United Arab Emirates Miracle Clinic Seoul Korea Republic of Khalifa University Centre For Cyber Physical Systems Computer Science Department United Arab Emirates Center For Cyber Security Faculty Of Information Science And Technology Selangor Bangi43600 Malaysia

ISBN: (纸本)9798350394962

In the midst of the digital revolution of the 21st century, cybersecurity has come to be a primary social situation, requiring revolutionary and Innovative solution. To find the proper answer for this pressing demand, AI (AI) has developed as an innovative catalyst that has fundamentally transformed the cybersecurity landscape. The power of AI is exemplified by its ability to process and interpret large and heterogeneous cybersecurity data sets optimizing critical functions such as threat detection, asset prioritization, and vulnerability management beyond human capabilities swiftly and accurately. This transformation is redefining our cybersecurity approach. This paper presents a full exploration of AI's extreme influence on cybersecurity, delving deep into how AI tools not only enhance but often surpass human-mediated processes. By unraveling the intricacies of integrating AI into the realm of cybersecurity, we vividly illustrate AI's potential to anticipate, detect, and proactively mitigate cyber threats, empowering organizations to bolster their digital security. However, it's vital to recognize the essential difficulties of AI. We underline the critical necessity for non-stop human administration and involvement to confirm that cybersecurity processes are in proportion and powerful. Additionally, we mention the probable ethical concerns and underscore the importance of strong authority structures to accelerate accountable and transparent AI usage in cybersecurity. This paper elucidates how AI is revolutionizing cybersecurity techniques, contributing to a more secure and greater secure digital future. It additionally lays the base for current investigation and discourse on the role of AI in cybersecurity - a conversation of growing importance in our unexpectedly advancing digital age. © 2024 IEEE.

关键词： Cybersecurity

来源：评论

学校读者我要写书评

暂无评论

Artificial Neural Network-Assisted Confinement Loss Prediction of D-Shaped PCF-SPR Biosensor 7

Artificial Neural Network-Assisted Confinement Loss Predicti...

引用

7th IEEE International Humanitarian Technologies Conference, IHTC 2024

作者： Islam, Nazrul Hasan, Mia Mohammad Shoaib Hasan, Md. Nahid Shibly, Imam Hossain Yousuf, Mohammad Abu Uddin, Md Zia Jahangirnagar University Institute of Information Technology Savar Dhaka1342 Bangladesh Rajshahi University of Engineering and Technology Department of EEE Rajshahi6204 Bangladesh Khulna University Computer Science and Engineering Discipline Khulna9208 Bangladesh SINTEF Digital Sustainable Communication Technologies Oslo Norway

ISBN: (纸本)9798350354645

Machine learning (ML) has become a pivotal force in enhancing the capabilities of sensing technologies across a wide range of applications, including biosensing, agriculture, industrial automation, and more. This paper presents a photonic crystal fiber (PCF)-surface plasmon resonance (SPR) biosensor with a maximum wavelength sensitivity (WS) of 41,000 nm/RIU and attains the highest resolution of 2.44 × 10-6 within an analyte refractive index (RI) of 1.39. The sensor's highest sensitivity and resolution stem from its thoughtful design and the strategic choice of gold as a plasmonic material for the PCF, enhancing light-analyte interactions. Moreover, an artificial neural network (ANN) is used to accurately predict confinement loss with high precision and refine the biosensor's design for optimal performance. Furthermore, a pivotal part of this research is to study various ML activation functions such as rectified linear activation (ReLU), hyperbolic tangent (Tanh), and Sigmoid to understand their role in accurately predicting confinement loss. Additionally, the work detects subtle changes in the RI of analytes holding various types of human cancerous cells. This advancement in SPR sensor technology heralds exciting developments in sensitive detection platforms, offering a powerful instrument for cutting-edge research. © 2024 IEEE.

关键词： Photonic crystal fibers

来源：评论

学校读者我要写书评

暂无评论

Optimization of 3D Holographic Projection for a Medical Image System using Taguchi Method and Fuzzy Inference System

引用

Journal of Imaging science and technology 2023年第4期67卷 1-7页

作者： Chou, Ming-Chung Huang, Tian-Hsiang Tsai, Jinn-Tsong Chen, Yen-Ming J. Hwang, Kao-Shing Huang, Wei-Tai Ho, Wen-Hsien Department of Medical Imaging and Radiological Sciences Kaohsiung Medical University Kaohsiung Taiwan Center for Big Data Research Kaohsiung Medical University Kaohsiung Taiwan Department of Medical Research Kaohsiung Medical University Hospital Kaohsiung Taiwan Department of Computer Science and Information Engineering National Penghu University of Science and Technology Penghu Taiwan Department of Computer Science and Artificial Intelligence National Pingtung University Pingtung Taiwan Department of Healthcare Administration and Medical Informatics Kaohsiung Medical University Kaohsiung Taiwan Department of Information Management National Kaohsiung University of Science and Technology Kaohsiung Taiwan Department of Electrical Engineering National Sun Yat-Sen University Kaohsiung Taiwan Department of Mechanical Engineering National Pingtung University of Science and Technology Pingtung Taiwan College of Professional Studies National Pingtung University of Science and Technology Pingtung Taiwan

Two dimensional projections of three dimensional (3D) objects are used to teach anatomy. These projections are relatively unrealistic, and medical students cannot easily and accurately grasp the position and shape of each anatomical structure. As a remedy, 3D holographic projections allow for 3D anatomical structures to be projected in space without the use of worn contraptions. This study designed a method for optimizing 3D holographic projections with respect to the quality characteristics of 3D imaging definition and stereoscopic quality. The Taguchi method was used to determine the factors that most greatly influenced these quality characteristics, and the Delphi method and fuzzy theory were used to quantify image quality. Among three main factors of material of the projection panel, thickness of the projection panel, and angle made by the projection panel with the horizontal plane, thickness was the most influential. The optimal combination of factors was acrylic material, a thickness of 1 mm, and an angle of 45°. This paper's method aids medical pedagogy and can be used by the holographic projection manufacturing industry to optimize 3D imaging definition and stereoscopic quality. © 2023 Society for Imaging science and technology.

关键词： Taguchi methods

来源：评论

学校读者我要写书评

暂无评论

Perioperative Anesthesia Data: Visualization, Effects, Analysis with Artificial Intelligence 4

Perioperative Anesthesia Data: Visualization, Effects, Analy...

引用

4th IEEE International Conference on Electronic Communications, Internet of Things and Big Data, ICEIB 2024

作者： Liu, Xiaoxiao McGrath, Sean Flanagan, Colin Lei, Yiming Zeng, Liaoyuan Electronic and Computer Engineering University of Limerick Limerick Ireland School of Mathematics and Information HeBei University HeBei China Mobile Digital Hospital System School of Electronics Peking University Ministry of Education Engineering Research Center Beijing China University of Electronic Science and Technology of China Department of Information and Communication Engineering Chengdu China

ISBN: (纸本)9798350360721

A comprehensive understanding of physiological data is essential for anesthesiologists to monitor and maintain the health of surgical patients. Understanding anesthetic signals is essential to improve over the past ten decades to comprehend a variety of diseases, ensure the safety of patients, and accelerate their recovery. We identified and summarized four themes of artificial intelligence (AI) research in anesthesia: applications of AI in anesthesiology, signals monitored in different anesthesia stages, commonly monitored signs, and data standardization. The effect of various AI technologies on data analysis was studied, and the types, functions, sensors, characteristics, and intelligent analysis of physiological signals monitored during anesthesia are presented in this article. AI influences anesthesia practices in many ways, including preoperative data evaluation, anesthetic depth monitoring, and postoperative event prediction. © 2024 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Positive Sample Augmentation with Graph Mixup for DDI Prediction 1

Positive Sample Augmentation with Graph Mixup for DDI Predic...

引用

1st IEEE International Conference on Medical Artificial Intelligence, MedAI 2023

作者： Yu, Hailong Ma, Xinyu Chu, Xu Wang, Yasha Wu, Rengyu Zhou, Qiang School of Computer Science Peking University Beijing China Tsinghua University Department of Computer Science and Technology Beijing China National Engineering Research Center for Software Engineering Peking University Beijing China Shenzhen Center for Prehospital Care Shenzhen China

ISBN: (纸本)9798350358780

Unexpected drug-drug interactions (DDIs) may occur when drugs are taken at the same time. Harmful DDIs can reduce drug efficacy and even increase unintended toxicity, putting patients treated with different drugs at risk. Previous works on DDI prediction mainly rely on hand-engineered domain knowledge, which is laborious to obtain and cannot handle the problem of sparse positive samples in DDI prediction. Even though some works attempt to handle data sparsity from the perspective of data distribution to improve the generalization ability of the model, they are limited to negative samples distribution. To address these limitations, we propose a novel method, Graph Mixup for Positive Sample Augmentation (GMPSA), to effectively combine positive drug molecule graphs and extend the training distribution to alleviate the problem of sparse positive samples. To model the graph signals and graph structures jointly, we map source graphs to the fused gromov-wasserstein metric space, then minimizes the weighted sum of transportation distances between the distributions of the source graphs and the objective graph in this metric space. By doing so, interpolated positive samples improve the the generalization error of the model. Experiments results on a real-word dataset show that our method effectively improve the perfomermance in DDI prediction on a state-of-the-art architecture. Further studies also verify the robustness and generalizability of GMPSA under different GNN backbones and parameter settings. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

HERA: A Novel Heuristic Resource Allocator for Multi-SDM Multi-User Settings

HERA: A Novel Heuristic Resource Allocator for Multi-SDM Mul...

引用

2024 IEEE Conference on Standards for Communications and Networking, CSCN 2024

作者： Antoniadis, Christos Katsalis, Kostas Tyrovolas, Dimitrios Tegos, Sotiris A. Ioannidis, Sotiris Diamantoulakis, Panagiotis D. Karagiannidis, George K. Liaskos, Christos DOCOMO Euro-Labs Munich Germany Aristotle University of Thessaloniki Department of Electrical and Computer Engineering Thessaloniki54124 Greece Technical University of Crete Dept. of Electrical and Computer Engineering Chania Greece Artificial Intelligence & Cyber Systems Research Center Lebanon University of Ioannina Computer Science Engineering Department Ioannina Greece Institute of Computer Science Foundation for Research and Technology Hellas Greece

ISBN: (纸本)9798331507428

The advent of Programmable Wireless Environments (PWEs) has transformed the wireless propagation phenomenon into a software-defined resource, leveraging Software-defined metasurfaces (SDMs). These new technologies have shown that wireless waves can be routed within a space, contrary to the regular, chaotic wireless propagation, yielding considerable benefits to communication efficiency, and even completely new applications. A new topic has risen, in the context of modeling these capabilities as network resources, and allocating them to users. In this context, the present paper contributes HERA, a heuristic resource allocator that receives a setup with users and SDMs as input, and produces the necessary configuration of the latter, for efficient shared performance. Simulation results demonstrate considerable efficiency in this task, while the heuristic nature of HERA sets the basis for a flexible definition of complex user objectives in the future. © 2024 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

Exploring the Impact of Drivers’ Emotion and Multi-task Learning on Takeover Behavior Prediction in Multimodal Environment Exploring Takeover Behavior Prediction in Multimodal Environment

Exploring the Impact of Drivers’ Emotion and Multi-task Lea...

引用

2025 CHI Conference on Human Factors in Computing Systems, CHI EA 2025

作者： Feng, Xinyu Gu, Yu Lin, Yuming Cai, Yaojun Guangxi Key Laboratory of Trusted Software Guilin University of Electronic Technology Guangxi Guilin China School of Computer Science and Engineering University of Electronic Science and Technology of China Sichuan Province Chengdu China Guangxi Key Laboratory of Digital Infrastructure Guangxi Zhuang Autonomous Region Information Center Guangxi Nanning China

ISBN: (纸本)9798400713958

With the development of autonomous driving technology, drivers may be immersed in non-driving related tasks. Therefore, takeover safety has received increasing attention. Previous studies have focused on designing the empirical analysis to formulate preventive measures or constructing methods for a single-task learning strategy. However, due to the persistent gaps between modalities and ignoring the correlation between tasks, they make it difficult to capture similar information between modalities. In this paper, we propose the Multi-TBP, a general deep learning framework for takeover behavior prediction. Experiments show that our method achieves the best performance on all tasks. Through ablation studies and visualization, we find that each modality’s importance varies from each task, and there are also correlations between tasks. © 2025 Copyright held by the owner/author(s).

关键词： Multi-task learning

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：