检索结果-内蒙古大学图书馆

IEEE Symposium on Bioinformatics and Bioengineering (BIBE)

作者： Efterpi Karapintzou Vassilios Tsakanikas Dimitrios Kikidis Christos Nikitas Brooke Nairn Marousa Pavlou Doris-Eva Bamiou Themis Exarchos Dimitrios I. Fotiadis Unit of Medical Technology and Intelligent Information Systems Dept. of Materials Science and Engineering University of Ioannina Ioannina Greece Dept. of Otorhinolaryngology Head and Neck Surgery National and Kapodistrian University of Athens Hippocrateion General Hospital Athens Greece Faculty of Brain Sciences University College London (UCL) Ear Institute University College London London United Kingdom Dept. of Neuro-Otology University College London Hospitals London UK Faculty of Life Sciences and Medicine Centre for Human and Applied Physiological Sciences School of Basic and Medical Biosciences King's College London London United Kingdom Dept. of Informatics Ionian University Corfu Greece Biomedical Research Institute Foundation for Research and Technology Hellas FORTH Ioannina Greece

ISBN: (数字)9798331518622

ISBN: (纸本)9798331518639

This study focuses on the development of artificial intelligence models to enhance telerehabilitation practices. We utilized diverse datasets to create clinically relevant models for predicting two critical outcomes: fall risk and treatment effectiveness. By applying various machine learning techniques, including K-Nearest Neighbors, Random Forest, Decision Tree, Support Vector Machine, and XGBoost, our models demonstrated high accuracy, sensitivity, and specificity. Notably, the Random Forest model achieved an accuracy of 0.97 in predicting fall risk and 0.96 in assessing treatment effectiveness. These models equip clinicians with powerful tools for data-driven decision-making, ultimately improving patient outcomes in rehabilitation settings.

关键词： Support vector machines Accuracy Biological system modeling Decision making Patient rehabilitation Predictive models Sensitivity and specificity Feature extraction Robustness Random forests

来源：评论

学校读者我要写书评

暂无评论

The Effect of Normalization for Bi-directional Amharic-English Neural Machine Translation

arXiv

引用

arXiv 2022年

作者： Belay, Tadesse Destaw Tonja, Atnafu Lambebo Kolesnikova, Olga Yimam, Seid Muhie Ayele, Abinew Ali Haile, Silesh Bogale Sidorov, Grigori Gelbukh, Alexander College of Informatics Wollo University Kombolcha Ethiopia Centro de Investigación en Computación Instituto Politécnico Nacional Mexico City Mexico Dept. of Informatics Universität Hamburg Hamburg Germany ICT4D Research Center Bahir Dar University Bahir Dar Ethiopia Dept. of Computer Science Assosa University Assosa Ethiopia

Machine translation (MT) is one of the prominent tasks in natural language processing whose objective is to translate texts automatically from one natural language to another. Nowadays, using deep neural networks for MT task has received a great deal of attention. These networks require lots of data to learn abstract representations of the input and store it in continuous vectors. This paper presents the first relatively large-scale Amharic-English parallel sentence dataset. Using these compiled data, we build bi-directional Amharic-English translation models by fine-tuning the existing Facebook M2M100 pre-trained model achieving a BLEU score of 37.79 in Amharic-English translation and 32.74 in English-Amharic translation. Additionally, we explore the effects of Amharic homophone normalization on the machine translation task. The results show that normalization of Amharic homophone characters increases the performance of Amharic-English machine translation in both directions. © 2022, CC BY.

关键词： Neural machine translation

来源：评论

学校读者我要写书评

暂无评论

Constructing A Creative Service Software with Semantic Web 8

Constructing A Creative Service Software with Semantic Web

引用

8th International Conference on Dependable Systems and Their Applications, DSA 2021

作者： Huang, Pei-Shu Fahmi, Faisal Wang, Feng-Jian Yang, Hongji Dept. of Computer Science National Yang-Ming Chiao-Tung University Hsinchu City Taiwan EECS Int’l Graduate Program National Yang-Ming Chiao-Tung University Hsinchu City Taiwan Information and Library Science Airlangga University Surabaya City Indonesia Department of Informatics University of Leicester Leicester United Kingdom

ISBN: (纸本)9781665443913

In software development, Service Oriented Architecture (SOA) and creative computing can be adopted to utilize multiple-domain knowledges to construct service software possessing creative properties, i.e., novel, useful, and surprising. In the past, several theoretical evaluation metrics have been proposed to measure creativity of a software system. However, a systematic practical method to construct creative service software is rarely considered in current researches. In this paper, we propose a model for creative service software development based on semantic web, which is applied in two phases: domain-creative requirement specification and semantic-based service design. The model can reduce communication work between domain experts and software engineers, improve traceability of the specifications, and improve machine readability during the generation of creativity. After the model of service design is validated for completeness and consistency, the creative service software is well-designed and can be implemented and reused effectively without losing of creativity. © 2021 IEEE.

关键词： Semantic Web

来源：评论

学校读者我要写书评

暂无评论

Sharp bounds on the spectral radius of nonnegative matrices and comparison to the frobenius’ bounds

引用

International Journal of Circuits, Systems and Signal Processing 2020年 14卷 423-434页

作者： Adam, Maria Assimakis, Nicholas Babouklis, Fotis Dept. of Computer Science & Biomedical Informatics University of Thessaly Lamia Greece General Department National and Kapodistrian University of Athens Athens Greece

In this paper, a new upper bound and a new lower bound for the spectral radius of a nοnnegative matrix are proved by using similarity transformations. These bounds depend only on the elements of the nonnegative matrix and its row sums and are compared to the well-established upper and lower Frobenius’ bounds. The proposed bounds are always sharper or equal to the Frobenius’ bounds. The conditions under which the new bounds are sharper than the Frobenius' ones are determined. Illustrative examples are also provided in order to highlight the sharpness of the proposed bounds in comparison with the Frobenius’ bounds. An application to linear invariant discrete-time nonnegative systems is given and the stability of the systems is investigated. The proposed bounds are computed with complexity O(n2). © 2020, North Atlantic University Union. All rights reserved.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Accelerating deep neural networks for efficient scene understanding in automotive cyber-physical systems

arXiv

引用

arXiv 2021年

作者： Nousias, Stavros Pikoulis, Erion Vasilis Mavrokefalidis, Christos Lalos, Aris S. Industrial Systems Institute Athena Research Center Patras Science Park Greece Computer Engineering Informatics Dept. University of Patras Greece

Automotive Cyber-Physical Systems (ACPS) have attracted a significant amount of interest in the past few decades, while one of the most critical operations in these systems is the perception of the environment. Deep learning and, especially, the use of Deep Neural Networks (DNNs) provides impressive results in analyzing and understanding complex and dynamic scenes from visual data. The prediction horizons for those perception systems are very short and inference must often be performed in real time, stressing the need of transforming the original large pre-trained networks into new smaller models, by utilizing Model Compression and Acceleration (MCA) techniques. Our goal in this work is to investigate best practices for appropriately applying novel weight sharing techniques, optimizing the available variables and the training procedures towards the significant acceleration of widely adopted DNNs. Extensive evaluation studies carried out using various state-of-the-art DNN models in object detection and tracking experiments, provide details about the type of errors that manifest after the application of weight sharing techniques, resulting in significant acceleration gains with negligible accuracy losses. © 2021, 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

F-EvoRecSys: Fuzzy Inference meets Evolutionary Approach for Personalized Well-being Recommendations

F-EvoRecSys: Fuzzy Inference meets Evolutionary Approach for...

引用

2021 International Conference on Fuzzy Theory and Its Applications, iFUZZY 2021

作者： Palomares, Ivan Alcaraz-Herrera, Hugo Shen, Kao-Yi Syed-Abdul, Shabbir Malwade, Shwetambara Tainan Taiwan University of Granada Spain School of Computer Science Bristol University United Kingdom Dept. Banking and Finance Chinese Culture University Taipei Taiwan Graduate Institute of Biomedical Informatics College of Medical Science and Technology Taipei Medical University Taipei Taiwan International Center for Health Information Technology College of Medical Science and Technology Taipei Medical University Taipei Taiwan School of Gerontology Health Management College of Nursing Taipei Medical University Taipei Taiwan

ISBN: (纸本)9781665433587

Many citizens nowadays cope with busy and dynamic lifestyles. Adopting or maintaining a healthy lifestyle to prevent chronic diseases or mental disorders is a core societal challenge. The current global pandemic has evidenced more than ever before the critical importance of engaging citizens with healthy and tailored activities that they like, as a key driver for safeguarding good health from a preventive vantage point, aligned with the pursuance of SDG 3: "good health and well-being". This is why Recommender Systems for personalized health and well-being have lately become a research trend, particularly for food and physical activity recommendation. This paper presents F-EvoRecSys: an extension of an evolutionary algorithm-driven approach for "healthy bundle"well-being recommendations that incorporates a fuzzy inference engine aimed at improving physical activity recommendations based on users' exercising habits. An experimental study demonstrates how this can lead to more diversified recommendations. The paper also discusses challenges and future directions for personalized well-being recommender systems under different perspectives. © 2021 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

A Hybrid Approach to Parallel Pattern Discovery in C++ 28

A Hybrid Approach to Parallel Pattern Discovery in C++

引用

28th Euromicro International Conference on Parallel, Distributed and Network-Based Processing, PDP 2020

作者： Brown, C. Janjic, V. Barwell, A. Thomson, J. Castaneda Lozano, R. Cole, M. Franke, B. Garcia-Sanchez, J.D. Del Rio Astorga, D. MacKenzie, K. University of St Andrews School of Computer Science StAndrews United Kingdom University of Edinburgh School of Informatics Edinburgh United Kingdom Universidad Carlos III de Madrid Computer Science and Engineering Dept. Madrid Spain IOHK

ISBN: (纸本)9781728165820

Parallel pattern libraries offer a strong combination of abstraction and performance. However, discovering places in sequential code where parallel patterns should be introduced is still highly non-trivial, often requiring expert manual analysis and profiling. We present a hybrid discovery technique to detect instances of parallel patterns in sequential code. This employs both static and dynamic trace-based analysis, together with hotspot detection. We evaluate our pattern discovery mechanism on a number of representative benchmarks. We evaluate the performance of the resulting parallelised benchmarks on a 24core parallel machine. © 2020 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Development of a Calibration-Free Brain-computer Interface Utilizing Common Spatial Patterns and Artificial Neural Networks for EEG Signal Analysis

Development of a Calibration-Free Brain-Computer Interface U...

引用

Human-computer Interaction, Optimization and Robotic Applications (HORA), International Congress on

作者： Korhan Cengiz Shreyas J Udayaprasad P K Gururaj H L Dilip Kumar S M College of Information Technology University of Fujairah UAE Faculty of Organization and Informatics University of Zagreb Croatia Department of Information Technology Manipal Institute of Technology Bengaluru Manipal Academy of Higher Education Manipal Karnataka India Department of Artificial Intelligence & Machine Learning Global Academy of Technology Bengaluru India Dept. of Computer Science and Engineering University Visvesvaraya College of Engineering Bangalore India

ISBN: (数字)9798350394634

ISBN: (纸本)9798350394641

A brain computer interface (BCI) system uses a technique known calibration, that takes 20 to 30 minutes to accomplish. For the objective of creating a reliable decoder, the calibration process is challenging and expensive. In order to address the drawbacks of the current system, a spectral-spatial technique has been suggested. The motor imagery (MI) data set, comprising 15 electroencephalography (EEG) signals and fourteen test subjects, is taken into consideration. The two modules are designed to extract characteristics and process data. An artificial neural network (ANN) is used to independently train and test the suggested spectral-spatial algorithm. Based on it, a variety of machine learning techniques, including random forest (RF), neural networks (NN), and XGboost, are used to classify the data, that is then sent to the hidden layer (Lth layer). The obtained results indicates 2% of improvement in comparison with existing methodology.

关键词： Training Machine learning algorithms Artificial neural networks Electroencephalography Brain-computer interfaces Calibration Reliability

来源：评论

学校读者我要写书评

暂无评论

The doctor will polygraph you now: ethical concerns with AI for fact-checking patients

arXiv

引用

arXiv 2024年

作者： Anibal, James T. Gunkel, Jasmine Huth, Hannah Nguyen, Hang Awan, Shaheen Bensoussan, Yael Wood, Bradford J. BethesdaMD United States Computational Health Informatics Lab Institute of Biomedical Engineering Department of Engineering Science University of Oxford Oxford United Kingdom BethesdaMD United States Ho Chi Minh City Viet Nam Dept. of Communication Sciences & Disorders University of Central Florida United States Morsani College of Medicine University of South Florida Tampa Bay FL United States

Clinical artificial intelligence (AI) methods have been proposed for predicting social behaviors which could be reasonably understood from patient-reported data. This raises ethical concerns about respect, privacy, and patient awareness/control over how their health data is used. Ethical concerns surrounding clinical AI systems for social behavior verification were divided into three main categories: (1) the use of patient data retrospectively without informed consent for the specific task of verification, (2) the potential for inaccuracies or biases within such systems, and (3) the impact on trust in patient-provider relationships with the introduction of automated AI systems for "fact-checking". Additionally, this report showed the simulated misuse of a verification system and identified a potential LLM bias against patient-reported information in favor of multimodal data, published literature, and the outputs of other AI methods (i.e., "AI selftrust"). Finally, recommendations were presented for mitigating the risk that AI verification systems will cause harm to patients or undermine the purpose of the healthcare system. © 2024, CC BY.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

Context-aware Rate Adaptation for Predictive Flying Networks using Contextual Bandits

arXiv

引用

arXiv 2025年

作者： Queiros, Ruben Kaneko, Megumi Fontes, Helder Campos, Rui INESC TEC Faculty of Engineering University of Porto Porto Portugal National Institute of Informatics Dept. of Computer Science The University of Tokyo Tokyo Japan

The increasing complexity of wireless technologies, such as Wi-Fi, presents significant challenges for Rate Adaptation (RA) due to the large configuration space of transmission parameters. While extensive research has been conducted on RA for low-mobility networks, existing solutions fail to adapt in flying networks, where high mobility and dynamic wireless conditions introduce additional uncertainty. We propose Linear Upper Confidence Bound for RA (LinRA), a novel Contextual Bandit-based approach that leverages real-time link context to optimize transmission rates. Designed for predictive flying networks, where future trajectories are known, LinRA proactively adapts to obstacles affecting channel quality. Simulation results demonstrate that LinRA converges 5.2× faster than state-of-the-art benchmarks and improves throughput by 80% in Non Line-of-Sight (NLoS) conditions, matching the performance of ideal algorithms. With low time complexity, LinRA is a scalable and efficient RA solution for predictive flying networks. © 2025, CC BY.

关键词：

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：