检索结果-内蒙古大学图书馆

14th IIAI International Congress on Advanced Applied Informatics, IIAI-AAI 2023

作者： Yamakawa, Hiroto Yamashita, Yumiko Niida, Hibiki Komatsugawa, Hiroshi Chitose Institute of Science and Technology Department of Information Systems Engineering Hokkaido Chitose Japan Teikyo University Center of Teaching and Learning Hachiouji Tokyo Japan Chitose Institute of Science and Technology Graduate School of Science and Technology Hokkaido Chitose Japan

ISBN: (纸本)9798350324228

In this study, we describe developing a learning support system for academic writing. The proposed system attempts to detect colloquial words based on subjective or objective sentences in student reports. To achieve this, we implemented a prototype machine learning model to realize effective detection. We then proposed the system design to incorporate this model into the previous colloquial words detection system. © 2023 IEEE.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Investigation of the significance of the plaque morphology evolution in plaque rupture events using computational biomechanics 46

Investigation of the significance of the plaque morphology e...

引用

46th Annual International Conference of the IEEE engineering in Medicine and Biology Society, EMBC 2024

作者： Pleouras, Dimitrios S. Siogkas, Panagiotis K. Potsika, Vassiliki T. Tsakanikas, Vasilis D. Dimos, Sokratis S. Mantzaris, Michalis D. Koncar, Igor Fotiadis, Dimitrios I. University of Ioannina Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering IoanninaGR45110 Greece University of Belgrade Faculty of Medicine Department of Vascular and Endovascular Surgery Belgrade Serbia University of Ioannina Unit of Medical Technology and Intelligent Information Systems Biomedical Research Institute Forth Dept. of Materials Science and Engineering IoanninaGR45110 Greece

ISBN: (纸本)9798350371499

Forwarded by the technological urge of this era, several computational methods are implemented to give further insights into possible outcomes of diseases. In this context, atherosclerosis, which is one of the most fatal diseases nowadays, is treated alike, where several computational models are proposed annually allowing for the evaluation of several outcomes for patient specific cases. Among them, one of the most significant models is able to predict the atherosclerotic evolution over time. In this proof-of-concept study, we aim to investigate the effect of plaque morphology on plaque rupture in a two-case scenario - a longitudinal and a bulk plaque evolution in 3D-reconstructed patient-specific carotids arteries. Our approach is based on a three-step process: i) the implementation of a state-of-the-art plaque growth model that predicts evolving and new plaques in real patient specific carotid arteries, ii) the selection of 2 patient cases, one with longitudinal plaque evolution and one with bulk plaque evolution and, finally, iii) the evaluation the maximum principal stress over the plaques and the endothelium layers to assess the plaque rupture risk. The results indicate that the evolving plaques towards the lumen, not only cause stenoses but also are more prone to rupture. Clinical relevance- This proof-of-concept work establishes that the plaques that grow towards the luminal border present with a higher risk of potential rupture compared to plaques that grow longitudinally, thus giving valuable insights to clinicians for important decision making regarding potential endarterectomy procedures. © 2024 IEEE.

关键词： 3D reconstruction

来源：评论

学校读者我要写书评

暂无评论

Remote response modes on the paced excitable C. elegans network

引用

Physical Review Research 2024年第3期6卷 033014-033014页

作者： Yu Qian Zhili Chen Runru Yang Hongyan Gao Zhao Lei Zhigang Zheng College of Physics and Optoelectronic Technology Institute of Systems Science College of Information Science and Engineering School of Mathematical Sciences

In paced excitable systems, a traditional viewpoint on signal transmission is that an excitable pacing signal should propagate from the source to its excited neighbors in a sequential rule, which is known as the normal sequential response mode (SRM). However, in our present paper, by extensively exploring the response modes emerged on the paced excitable C. elegans network, we found that, besides the normal SRM, a response mode that breaks the sequence rule and contains isolated excited clusters or even isolated excited nodes on the propagation path of the response structure can be detected. Such remote response nodes and clusters are excited discontinuously from the source node, forming the phenomenon of the remote response mode (RRM). An effective-driving analysis approach (EDAA) is proposed to theoretically study the mechanism of the RRM, based on which key role played by the excited nodes possessing nonexcited upstream driving neighbors is confirmed in the formation of the RRM. We further verify the applicability and the universality of the EDAA in identifying the RRM on general paced excitable networks. These contributions are expected to shed light on the study of complex response modes in paced excitable systems and to have great impact in related topics.

关键词： Complex systems Patterns in complex systems

来源：评论

学校读者我要写书评

暂无评论

ASSESSING THE ACCURACY AND ETHICAL IMPLICATIONS OF AUTOMATED CRIMINAL DETECTION USING A DEEP LEARNING APPROACH

ASSESSING THE ACCURACY AND ETHICAL IMPLICATIONS OF AUTOMATED...

引用

2023 IEEE International Conference on Research Methodologies in Knowledge Management, Artificial Intelligence and Telecommunication engineering, RMKMATE 2023

作者： Jagadeesan, S. Sujigarasharma, K. Manjula, R. Vetriselvi, T. School of Computer Science Engineering and Information Systems Vellore Institute of Technology Tamil Nadu Vellore India Department of Computing Technologies School of Computing Faculty of Engineering and Technology SRM Institute of Science and Technology Kattankulathur Chennai India Department of IOT School of Computer Science and Engineering Vellore Institute of Technology Tamil Nadu Vellore India

ISBN: (纸本)9798350305708

This study examines the accuracy and ethical implications of using convolutional neural networks (CNN) for automated crime detection. A CNN model was trained on a dataset of criminal mugshots to identify potential criminal behaviour based on facial features. This study analyzed the performance of the model and achieved a high accuracy rate in identifying criminals. However, the ethical implications of automated criminal detection are also explored, including bias, privacy and human rights violations. The findings of this study highlight the need for caution and ethical considerations when implementing automated crime detection technologies. It is important to ensure that such technologies are not used to violate the rights of individuals or perpetuate societal biases. © 2023 IEEE.

关键词： CNN Criminal detection Face detection Machine learning

来源：评论

学校读者我要写书评

暂无评论

Real-Time Myanmar Hand Gestures Recognition Using Deep Learning Models 8th

Real-Time Myanmar Hand Gestures Recognition Using Deep Learn...

引用

8th International Conference on Intelligent Technologies, ICIT 2023

作者： Kyaw, Nwe Ni Mitra, Pabitra Sinha, G.R. Department of Computer Science and Engineering Indian Institute of Technology Kharagpur West Bengal721302 India Indian Knowledge System Lab International Institute of Information Technology Bangalore Karnataka Bengaluru560100 India

ISBN: (纸本)9789819738588

The proposed system for recognizing Myanmar sign language between individuals who are deaf. The aim of this study is to develop deep learning models for the purpose of accurately identifying dynamic hand gesture images depicting 14 classes of Myanmar words and numbers. The present system utilizes a new dataset comprising 7834 images for 14 classes obtained through Webcam. The objective of this study is to enhance the robustness of the new model. Next, we proceed to evaluate the proposed model by comparing them to those of existing convolutional neural network models. These models are generally recognized as effective deep-learning approaches for recognition tasks. The proposed model exhibits a performance level of 96% for both validation and testing accuracies. Furthermore, the experimental finding demonstrates that the model, convolutional layers, achieved an accuracy of 100% in recognizing Myanmar Sign Language (MSL). © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

A Low Profile and Broadband Pattern Reconfigurable Dielectric Resonator Antenna

A Low Profile and Broadband Pattern Reconfigurable Dielectri...

引用

2023 International Applied Computational Electromagnetics Society Symposium, ACES-China 2023

作者： Fang, Hai Ting Yang, Wen Wen Guo, Lei Dalian University of Technology Information and Communication Engineering Dalian China Nantong University Information Science and Technology Nantong China Sun Yat-Sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou China

ISBN: (纸本)9781733509657

In this paper, a low profile and broadband pattern reconfigurable dielectric resonator antenna (DRA) is proposed. Four different radiation patterns, including one conical pattern, two tilted patterns and one broadside pattern, are realized by changing the phase difference of the two excitation ports. The antenna has a broad impedance bandwidth of 15.1% (3.37-3.9 GHz) with a low profile of $\sim 0.1\lambda 0$. The simulated antenna gains of 5.42 dBi, 8 dBi and 8.48 dBi are achieved over the impedance bandwidth for conical, tilted, and broadside patterns, respectively. The antenna is a good candidate for 5G complex communication applications. © 2023 Applied Computational Electromagnetics Society (ACES).

关键词： Microwave antennas

来源：评论

学校读者我要写书评

暂无评论

Analysis of Temperature Distribution in Microwave Heating Based on Finite Difference Method

Analysis of Temperature Distribution in Microwave Heating Ba...

引用

2024 International Conference on Energy and Electrical engineering, EEE 2024

作者： Yang, Biao Liu, Bingyan Yang, Ying Kunming University of Science and Technology Faculty of Information Engineering and Automation Key Laboratory of Unconventional Metallurgy of Ministry of Education Kunming China Kunming University of Science and Technology The Higher Educational Key Laboratory for Industrial Intelligence and Systems of Yunnan Province Kunming China

ISBN: (纸本)9798350341768

Microwave heating entails the interaction of multiple, interconnected physical fields. Traditional numerical methods cannot directly compute the temperature distribution of materials during microwave heating. This paper analyzes two calculation methods: the explicit Euler difference method and the Crank-Nicolson difference method. The performance of these two methods in simulating the temperature distribution of deionized water under microwave heating is compared. Through simulation experiments, it is demonstrated that both methods yield results within a high accuracy range. The explicit Euler difference method has slightly lower computational accuracy but is simple and fast, while the Crank-Nicolson difference method offers higher precision at the expense of greater computational complexity. Depending on specific requirements, the suitable method can be selected to simulate the microwave heating process, thereby supporting the application of this technology. © 2024 IEEE.

关键词： Deionized water

来源：评论

学校读者我要写书评

暂无评论

An Ensembled Real-Time Hand-Gesture Recognition using CNN 15

An Ensembled Real-Time Hand-Gesture Recognition using CNN

引用

15th International Conference on Computing Communication and Networking Technologies, ICCCNT 2024

作者： Kavitha, M.N. Saranya, S.S. Prasad, M. Kaviyarasu, S. Ragunath, N. Rahul, P. Kongu Engineering College Department of Computer Science and Design Tamilnadu Erode India PSG Institute of Technology and Applied Research Department of Computer Science and Engineering Tamilnadu Coimbatore India Controller of Examinations Tamilnadu Namakkal India Kongu Engineering College Bachelor of Science - Information Systems Tamilnadu Erode India

ISBN: (纸本)9798350370249

Hand sign recognition is a vital technology in the human-computer interaction, enabling individuals to communicate with machines naturally and effectively. An innovative approach for real-time hand sign identification with the help of CNN and OpenCV is introduced with the fusion of computer vision and deep learning that can accurately interpret and classify an extensive range of hand signs and gestures. This research contributes significantly to the fields of computer vision and human-computer interaction, offering a practical and efficient solution for hand sign recognition. The combination of CNN and OpenCV presents a promising avenue for enhancing accessibility and communication, especially in environments where verbal communication is limited or non-existent. The model is trained with multiple data so that the system can recognize the hand gestures more precisely. Pre-trained architectures like ResNet and MobileNet are combined with the CNN model using ensemble learning and the performance is improved when compared to all the three CNN architectures individually. The ensemble model provides better accuracy of 96 %. The potential applications of this technology are vast, from assisting the hearing-impaired in understanding sign language to more immersive and intuitive interactions. Overall, the approach holds the promise of bridging the gap between human gestures and machine understanding, opening new doors for meaningful interactions between individuals and intelligent systems. © 2024 IEEE.

关键词： Intelligent systems

来源：评论

学校读者我要写书评

暂无评论

Regulation of Radial Higher-Order Orbital Angular Momentum Mode Based on Helically-Twisted Elliptic Fiber

Regulation of Radial Higher-Order Orbital Angular Momentum M...

引用

2023 Asia Communications and Photonics Conference/2023 International Photonics and Optoelectronics Meetings, ACP/POEM 2023

作者： Huang, Chuangrong Tu, Jiajing Gao, Shecheng Liu, Weiping Li, Zhaohui College of Information Science and Technology Jinan University Department of Electronic Engineering Guangzhou China School of Electronics and Information Technology Sun Yat-sen University Guangdong Provincial Key Laboratory of Optoelectronic Information Processing Chips and Systems Guangzhou China

ISBN: (纸本)9798350312614

Based on mode coupling theory and angular momentum matching principle, the generation process and mechanism of radial higher-order orbital angular momentum (OAM) based on helically-twisted elliptic fiber (HTEF) is analyzed. High-precision HTEFs are successfully fabricated using the arc discharge technology of a fusion splicer. By changing the twisted rate of the HTEF, OAM -2n with radial order n of 2, 3, 4 and 5 are successfully generated at 1550 nm. Subsequently, we compare the differences in twisted rates between simulations and experiments. © 2023 IEEE.

关键词： arc discharge technology helically twisted elliptical optical fiber radial higher-order orbital angular momentum

来源：评论

学校读者我要写书评

暂无评论

Robust Multiresolution and Multistain Background Segmentation in Whole Slide Images 23rd

Robust Multiresolution and Multistain Background Segmentatio...

引用

Proceedings of the 23rd Polish Conference on Biocybernetics and Biomedical engineering, PCBEE 2023

作者： Jurgas, Artur Wodzinski, Marek Atzori, Manfredo Müller, Henning Information Systems Institute Sierre Switzerland Faculty of Electrical Engineering Automatics Computer Science and Biomedical Engineering AGH University of Science and Technology Krakow Poland Department of Neuroscience University of Padova Padova Italy Medical Faculty University of Geneva Geneva Switzerland

ISBN: (纸本)9783031384295

Background segmentation is an important step in analysis of histopathological images. It allows one to remove irrelevant regions and focus on the tissue of interest. However, background segmentation is challenging due to the variability of stain colors and intensity levels across different images, modalities, and magnification levels. In this paper, we present a learning-based model for histopathology background segmentation based on convolutional neural networks. We compare two multiresolution approaches to deal with the variability of magnification in histopathology images: (i) model that uses upscaling of smaller patches of the image, and (ii) model simultaneously trained on multiple resolution levels. Our model is characterized by solid performance both in multiresolution and multistain dyes (H &E and IHC), achieving good performance on publicly available dataset. The quantitative scores are, in terms of the Dice score, close to 94.71. The qualitative analysis presents strong performance on previously unseen cases from different distributions and various dyes. We freely release the model, weights, and ground-truth annotations to promote the open science and reproducible research. © 2024, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Pathology

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：