检索结果-内蒙古大学图书馆

8th International Conference on Medical and Health Informatics, ICMHI 2024

作者： Huang, Yu-Ju Tseng, Yi-Shiou Chen, Tzu-Jung Chien, Ting-Ying Department of Computer Science and Engineering Yuan Ze University Taoyuan City Taiwan Department of Surgery Far Eastern Memorial Hospital Graduate Institute of Medicine Yuan Ze University Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan City Taiwan Innovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan City Taiwan

ISBN: (纸本)9798400716874

Kidney stones are primarily crystals formed from ion oversaturation in urine. Currently, the diagnosis of kidney stones involves experienced professionals manually interpreting images of urinary crystals under a microscope. In recent years, with the rapid development of artificial intelligence (AI), many researchers have proposed various methods to assist in diagnosis, hoping to improve medical quality. This study explored the application of AI in the medical field, aiming to automate the interpretation of urinary crystal images, such as red blood corpuscles (RBCs), calcium oxalate monohydrate (COM), calcium oxalate dihydrate octahedron (COD-OCT), calcium oxalate dihydrate dodecahedron (COD-DOD), debris, and others, and to use image processing techniques to classify urinary crystal types. This research is expected to assist medical personnel in quickly determining the categories of urinary crystals. Ultimately, our model achieved an F1-score of 0.93, indicating that this architecture has significant potential. © 2024 Copyright ACM.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

EM Pre-training for Multi-party Dialogue Response Generation

arXiv

引用

arXiv 2023年

作者： Li, Yiyang Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University China Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University China

Dialogue response generation requires an agent to generate a response according to the current dialogue history, in terms of which two-party dialogues have been well studied, but leaving a great gap for multi-party dialogues at the same time. Different from two-party dialogues where each response is a direct reply to its previous utterance, the addressee of a response utterance should be specified before it is generated in the multi-party scenario. Thanks to the huge amount of two-party conversational data, various pre-trained language models for two-party dialogue response generation have been proposed. However, due to the lack of annotated addressee labels in multiparty dialogue datasets, it is hard to use them to pre-train a response generation model for multi-party dialogues. To tackle this obstacle, we propose an Expectation-Maximization (EM) approach that iteratively performs the expectation steps to generate addressee labels, and the maximization steps to optimize a response generation model. Theoretical analyses and extensive experiments have justified the feasibility and effectiveness of our proposed method. The official implementation of this paper is available at https://***/EricLee8/MPDRG. © 2023, CC BY.

关键词： Iterative methods

来源：评论

学校读者我要写书评

暂无评论

Constructing an Automated Method for Interpreting Alzheimer’s Disease Based on Deep Learning Models and Image Processing 24

Constructing an Automated Method for Interpreting Alzheimer...

引用

8th International Conference on Medical and Health Informatics, ICMHI 2024

作者： Yi, Chia-Pin Ting, Hsien-Wei Yang, Tzu-Fang Chien, Ting-Ying Department of Computer Science and Engineering Yuan Ze University Taoyuan City Taiwan Department of Neurosurgery Taipei Hospital Ministry of Health and Welfare New Taipei City242 Taiwan Graduate Program in Biomedical Informatics Yuan Ze University Taoyuan City Taiwan TaiwanInnovation Center for Big Data and Digital Convergence Yuan Ze University Taoyuan City Taiwan

ISBN: (纸本)9798400716874

Alzheimer’s disease (AD) often presents only mild symptoms in its early stages, and as there is no direct diagnostic method currently available, many patients are diagnosed only after the condition has worsened. Considering that magnetic resonance imaging (MRI) can provide key information in the diagnosis of AD, but the condition may go undiagnosed under manual interpretation due to the subtleness of symptoms and the reliance on radiologists to interpret MRI images, this study aimed to develop an automated method for interpreting brain MR images, hoping to screen for potential AD patients. By combining image processing, the U-Net model, YOLOv8 model, various CNN model architectures, and ensemble data statistics, our method was able to identify features related to AD and predict whether a patient has the disease. Our method can process a complete set of MR images and automatically extract important slices for prediction, making it practical for medical applications. Furthermore, we tested the accuracy and reliability of the method with additional datasets. © 2024 Copyright ACM.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

Contract-Inspired Contest Theory for Controllable Image Generation in Mobile Edge Metaverse

引用

IEEE Transactions on Mobile Computing 2025年

作者： Liu, Guangyuan Du, Hongyang Wang, Jiacheng Niyato, Dusit Kim, Dong In Nanyang Technological University College of Computing and Data Science Energy Research Institute @ NTU Interdisciplinary Graduate Program Singapore University of Hong Kong Department of Electrical and Electronic Engineering Hong Kong Hong Kong Nanyang Technological University College of Computing and Data Science Singapore Sungkyunkwan University Department of Electrical and Computer Engineering Korea Republic of

The rapid advancement of immersive technologies has propelled the development of the Metaverse, where the convergence of virtual and physical realities necessitates the generation of high-quality, photorealistic images to enhance user experience. However, generating these images, especially through Generative Diffusion Models (GDMs), in mobile edge computing environments presents significant challenges due to the limited computing resources of edge devices and the dynamic nature of wireless networks. This paper proposes a novel framework that integrates contract-inspired contest theory, Deep Reinforcement Learning (DRL), and GDMs to optimize image generation in these resource-constrained environments. The framework addresses the critical challenges of resource allocation and semantic data transmission quality by incentivizing edge devices to efficiently transmit high-quality semantic data, which is essential for creating realistic and immersive images. The use of contest and contract theory ensures that edge devices are motivated to allocate resources effectively, while DRL dynamically adjusts to network conditions, optimizing the overall image generation process. Experimental results demonstrate that the proposed approach not only improves the quality of generated images but also achieves superior convergence speed and stability compared to traditional methods. This makes the framework particularly effective for optimizing complex resource allocation tasks in mobile edge Metaverse applications, offering enhanced performance and efficiency in creating immersive virtual environments. © 2002-2012 IEEE.

关键词： Resource allocation

来源：评论

学校读者我要写书评

暂无评论

ECG signals-based security and steganography approaches in WBANs: A comprehensive survey and taxonomy

引用

Sustainable Computing: Informatics and Systems 2024年 41卷

作者： Masdari, Mohammad Band, Shahab S. Qasem, Sultan Noman Sayed, Biju Theruvil Pai, Hao-Ting Department of Computer Engineering Urmia Branch Islamic Azad University Urmia Iran Future Technology Research Center National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Taiwan Riyadh11432 Saudi Arabia Computer Science Department Faculty of Applied Science Taiz University Taiz6803 Yemen Department of Computer Science Dhofar University PO Box 2509 SalalahPCode 211 Oman Bachelor Program of Big Data Applications in Business National Pingtung University Pingtung Taiwan

Wireless Body Area Networks (WBANs) are integral components of e-healthcare systems, responsible for monitoring patients' physiological states through intelligent implantable or wearable sensor nodes. These nodes collect medical data, which is then transmitted to remote healthcare facilities for thorough evaluation. Securing medical data within WBANs is paramount due to its central role in preserving patient privacy and confidentiality. Notably, Electrocardiogram (ECG) signals have recently gained prominence as pivotal elements within diverse security frameworks. Incorporating ECG signals strategically enhances the security and reliability of WBANs and broader e-healthcare systems, instilling greater trustworthiness. This survey article provides an in-depth exploration of contemporary ECG-based security schemes, adding to the scholarly discourse. The imperative to categorize these security paradigms revolves around their use of ECG signals. This categorization identifies three key domains: the first involves schemes that utilize ECG signals for cryptographic operations, encompassing key generation, agreement, management, and authentication. The second category employs steganography-based techniques, using ECG signals to conceal patients' sensitive medical data. The third category focuses on enhancing ECG signal security during data transmission. Each category is meticulously elaborated, detailing architectural foundations, notable contributions, and intrinsic security services. Furthermore, each section presents a comprehensive overview of the attributes characterizing ECG-based security frameworks. This includes insights into employed datasets, simulation environments, evaluation metrics, and inherent advantages and limitations. Expanding on this, a thorough analysis of distinctive attributes underpinning these security frameworks concludes by shedding light on potential directions for future research. © 2023 Elsevier Inc.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Feature Weighting Optimization: Genetic Algorithms and Random Forest for Classification of Pregnant Potential Risk

Feature Weighting Optimization: Genetic Algorithms and Rando...

引用

2022 International Conference on Information Technology Research and Innovation, ICITRI 2022

作者： Ramdhani, Yudi Maulidia, Dea Setiadi, Ahmad Alamsyah, Doni Purnama Universitas Adhirajasa Reswara Sanjaya Informatics Engineering Program Bandung Indonesia Universitas Adhirajasa Reswara Sanjaya Computer Science Program Bandung Indonesia Universitas Bina Sarana Informatika Information System Program Jakarta Indonesia Bina Nusantara University Entrepreneurship Department Jakarta Indonesia

ISBN: (数字)9781665461849

ISBN: (纸本)9781665461849

Many pregnant women still do not want to check their pregnancy to recognize the signs of high-risk pregnant women. High-risk pregnancies refer to abundant women with several risky conditions requiring special care during and after delivery. This study aims to predict pregnancy risk levels with early detection efforts. The method used in this research is the Random Forest method for classification and the Genetic Algorithm for optimization. The results obtained from the Maternal Health Risk dataset analysis using the Random Forest method get an accuracy value of 73.37%. After optimizing the features using a genetic algorithm, the accuracy value in the classification of the health risk level of pregnant women has increased significantly to 90.20%. The results of the t-Test in this study showed a value of less than 0.05, and the t-Test value obtained is 0.000218269. That is, the genetic algorithm has excellent performance to improve the performance of the classification algorithm. Based on the results of the study to get a good accuracy value, it can be used by medical personnel to detect the level of health risk in pregnant women. It can be a reference material for further research to implement this research into a program. © 2022 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

HSI: Human Saliency Imitator for Benchmarking Saliency-Based Model Explanations 10th

HSI: Human Saliency Imitator for Benchmarking Saliency-Based...

引用

10th AAAI Conference on Human Computation and Crowdsourcing, HCOMP 2022

作者： Yang, Yi Zheng, Yueyuan Deng, Didan Zhang, Jindi Huang, Yongxiang Yang, Yumeng Hsiao, Janet H. Cao, Caleb Chen Huawei Research Hong Kong Hong Kong Department of Psychology University of Hong Kong Hong Kong Department of Electronic and Computer Engineering Hong Kong University of Science and Technology Hong Kong State Key Laboratory of Brain and Cognitive Sciences University of Hong Kong Hong Kong Institute of Data Science University of Hong Kong Hong Kong

ISBN: (纸本)9781577358787

Model explanations are generated by XAI (explainable AI)methods to help people understand and interpret machine learning models. To study XAI methods from the human perspective, we propose a human-based benchmark dataset, i.e., human saliency benchmark (HSB), for evaluating saliency based XAI methods. Different from existing human saliency annotations where class-related features are manually and subjectively labeled, this benchmark collects more objective human attention on vision information with a precise eyetracking device and a novel crowdsourcing experiment. Taking the labor cost of human experiment into consideration, we further explore the potential of utilizing a prediction model trained on HSB to mimic saliency annotating by humans. Hence, a dense prediction problem is formulated, and we propose an encoder-decoder architecture which combines multimodal and multi-scale features to produce the human saliency maps. Accordingly, a pretraining-finetuning method is designed to address the model training problem. Finally, we arrive at a model trained on HSB named human saliency imitator(HSI).We show, through an extensive evaluation, that HIS can successfully predict human saliency on our HSB dataset, and the HSI-generated human saliency dataset on Image Netshow cases the ability of benchmarking XAI methods both qualitatively and quantitatively. © 2022, Association for the Advancement of Artificial Intelligence.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach to IoT- Based Water Quality Monitoring

Machine Learning Approach to IoT- Based Water Quality Monito...

引用

IEEE Eurasia Conference on Biomedical engineering, Healthcare and Sustainability (ECBIOS)

作者： Chin-Chih Chang Chi-Hung Wei Min-Tien Lin Sz-Chwun John Hwang Department of Computer Science and Information Engineering Chung Hua University Hsinchu Taiwan Program in Engineering Science Chung Hua University Hsinchu City Taiwan Department of Landscape Architecture Chung Hua University Hsinchu Taiwan

Water resources are inevitable for human survival but untreated wastewater harms the environment. Thus, ongoing monitoring of water quality is necessary to identify pollution sources and prevent further damage. For such monitoring, an IoT water quality monitoring system was developed using Arduino technology to collect and transmit data to MQTT Brokers and store it in a database. The data is presented on a monitoring webpage. Three machine learning methods (Random Forest, ANN, and LightGBM) were used for backend analysis and prediction. LightGBM was found to have the highest prediction accuracy for NH3, pH, ORP, and temperature. The research contributes to reducing the need for frequent and costly data collection by using an IoT system for real-time monitoring and employing machine learning predictions to compensate for missing data. This approach provides a more efficient and effective method for analyzing and predicting water quality.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Chinese Spelling Correction as Rephrasing Language Model

arXiv

引用

arXiv 2023年

作者： Liu, Linfeng Wu, Hongqiu Zhao, Hai Department of Computer Science and Engineering Shanghai Jiao Tong University Key Laboratory of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Shanghai Jiao Tong University Shanghai China

This paper studies Chinese Spelling Correction (CSC), which aims to detect and correct the potential spelling errors in a given sentence. Current state-of-the-art methods regard CSC as a sequence tagging task and fine-tune BERT-based models on sentence pairs. However, we note a critical flaw in the process of tagging one character to another, that the correction is excessively conditioned on the error. This is opposite from human mindset, where individuals rephrase the complete sentence based on its semantics, rather than solely on the error patterns memorized before. Such a counter-intuitive learning process results in the bottleneck of generalizability and transferability of machine spelling correction. To address this, we propose Rephrasing Language Model (ReLM), where the model is trained to rephrase the entire sentence by infilling additional slots, instead of character-to-character tagging. This novel training paradigm achieves the new state-of-the-art results across fine-tuned and zero-shot CSC benchmarks, outperforming previous counterparts by a large margin. Our method also learns transferable language representation when CSC is jointly trained with other tasks. Copyright © 2023, The Authors. All rights reserved.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

The Impact of Transient and Stable Patterns of Functional Connectivity in Emotion Recognition

The Impact of Transient and Stable Patterns of Functional Co...

引用

IEEE International Conference on Computational Intelligence and Virtual Environments for Measurement Systems and Applications

作者： Yinghao Huang Xucheng Liu Ye Li Chio-In Ieong Yong Hu Feng Wan Department of Electrical and Computer Engineering Faculty of Science and Technology University of Macau Macau China Department of Electrical and Computer Engineering Faculty of Science and Technology Centre for Cognitive and Brain Sciences Institute of Collaborative Innovation University of Macau Macau China Shenzhen Institute of Advanced Technology Chinese Academy Sciences Shenzhen China Guangdong Institute of Intelligence Science and Technology Zhuhai China Department of Orthopaedics and Traumatology The University of Hong Kong Hong Kong China

ISBN: (数字)9798350322996

ISBN: (纸本)9798350323009

The achievement of emotional functions relies on the interactions of various functional systems of the human brain. Numerous studies tried to explore the mechanism of the emotions based on the functional connectivity. However, the contribution of the transient and stable patterns of brain communication in brain emotions was still unclear. The recently proposed activation network framework assumed the activity of functional connectivity (AFC) and background of functional connectivity (BFC) to respectively represent transient and stable patterns of functional connectivity. In this paper, we employed the activation network framework to SEED-IV dataset to achieve the emotion recognition and evaluate the performance of the transient and stable patterns in emotional activities. The top 100 critical connections of each subject were extracted by a data-driven feature selection strategy. The critical connections across all subjects of both AFC and BFC suggested the importance of Gamma band in emotion recognition. Especially, the AFC and BFC showed the different communication modes during the emotions. Finally, the subject-independent classification was employed on each subject’s critical connections to achieve the emotion recognition. The BFC showed the best classification accuracy of 78.71% ± 1.73% (mean ± std). The findings demonstrated that human emotions were mostly influenced by the consistent brain communication patterns. The findings of this investigation offer a new insight on the studies of human emotion.

关键词： Emotion recognition Accuracy Virtual environments Feature extraction Electroencephalography Transient analysis Computational intelligence

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：