检索结果-内蒙古大学图书馆

IEEE International Conference on Healthcare informatics (ICHI)

作者： Xuguang Ai Ramakanth Kavuluru Department of Computer Science University of Kentucky Lexington USA Dept. of Internal Medicine Division of Biomedical Informatics University of Kentucky Lexington USA

End-to-end relation extraction (E2ERE) is an important task in information extraction, more so for biomedicine as scientific literature continues to grow exponentially. E2ERE typically involves identifying entities (or named entity recognition (NER)) and associated relations, while most RE tasks simply assume that the entities are provided upfront and end up performing relation classification. E2ERE is inherently more difficult than RE alone given the potential snowball effect of errors from NER leading to more errors in RE. A complex dataset in biomedical E2ERE is the ChemProt dataset (BioCreative VI, 2017) that identifies relations between chemical compounds and genes/proteins in scientific literature. ChemProt is included in all recent biomedical natural language processing benchmarks including BLUE, BLURB, and BigBio. However, its treatment in these benchmarks and in other separate efforts is typically not end-to-end, with few exceptions. In this effort, we employ a span-based pipeline approach to produce a new state-of-the-art E2ERE performance on the ChemProt dataset, resulting in >4% improvement in F1-score over the prior best effort. Our results indicate that a straightforward fine-grained tokenization scheme helps span-based approaches excel in E2ERE, especially with regards to handling complex named entities. Our error analysis also identifies a few key failure modes in E2ERE for ChemProt.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Comparison of pipeline, sequence-to-sequence, and GPT models for end-to-end relation extraction: experiments with the rare disease use-case

arXiv

引用

arXiv 2023年

作者： Gupta, Shashank Ai, Xuguang Kavuluru, Ramakanth Division of Biomedical Informatics Dept. of Internal Medicine University of Kentucky United States Computer Science Department University of Kentucky United States

Objective: End-to-end relation extraction (E2ERE) is an important and realistic application of natural language processing (NLP) in biomedicine. In this paper, we aim to compare three prevailing paradigms for E2ERE using a complex dataset focused on rare diseases involving discontinuous and nested entities. Methods: We use the RareDis information extraction dataset to evaluate three competing approaches (for E2ERE): NER → RE pipelines, joint sequence to sequence models, and generative pre-trained transformer (GPT) models. We use comparable state-of-the-art models and best practices for each of these approaches and conduct error analyses to assess their failure modes. Results: Our findings reveal that pipeline models are still the best, while sequence-to-sequence models are not far behind;GPT models with eight times as many parameters are worse than even sequence-to-sequence models and lose to pipeline models by over 10 F1 points. Partial matches and discontinuous entities caused many NER errors contributing to lower overall E2E performances. We also verify these findings on a second E2ERE dataset for chemical-protein interactions. Although generative LM-based methods are more suitable for zero-shot settings, when training data is available, our results show that it is better to work with more conventional models trained and tailored for E2ERE. Conclusion: More innovative methods are needed to marry the best of the both worlds from smaller encoder-decoder pipeline models and the larger GPT models to improve E2ERE. As of now, we see that well designed pipeline models offer substantial performance gains at a lower cost and carbon footprint for E2ERE. Our contribution is also the first to conduct E2ERE for the RareDis dataset. The dataset and code for all our experiments are publicly available: https://***/shashank140195/Raredis © 2023, CC BY.

关键词： Carbon footprint

来源：评论

学校读者我要写书评

暂无评论

Co-Operative CNN for Visual Saliency Prediction on WCE Images

Co-Operative CNN for Visual Saliency Prediction on WCE Image...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： George Dimas Anastasios Koulaouzidis Dimitris K. Iakovidis Dept. of Computer Science and Biomedical Informatics University of Thessaly Greece Dept. of Surgery Odense University Hospital and Svendborg Hospital Denmark Dept. of Clinical Research University of Southern Denmark Denmark

The physician’s experience is highly correlated with the content interpretation of medical images. Over time, physicians develop their ability to examine the images, and this is usually reflected on gaze patterns they follow to observe visual cues that lead them to diagnostic decisions. In the context of gaze prediction, graph and machine learning methods have been proposed for the visual saliency estimation on generic images. In this work we preset a novel and robust gaze estimation methodology based on physicians’ eye fixations, using convolutional neural networks (CNNs) trained according to a novel co-operative scheme, on medical images acquired during Wireless Capsule Endoscopy (WCE). The proposed training approach considers both the reconstruction accuracy of the estimated saliency maps, and their contribution to the classification process of normal and abnormal findings. The model that was trained with the proposed co-operative procedure was able to achieve an average score of 0.76 Judd’s Area Under the receiver operating Characteristic (AUC-J).

关键词： Wireless communication Training Visualization Wireless sensor networks Estimation Receivers Signal processing

来源：评论

学校读者我要写书评

暂无评论

Multi-view Learning for the Identification of Risky Users in Dynamic Social Networks

arXiv

引用

arXiv 2025年

作者： Benedetti, Francesco Pellicani, Antonio Pio, Gianvito Ceci, Michelangelo Dept. of Computer Science University of Bari Bari Italy Dept. of Computer Science University of Pisa Pisa Italy Data Science Lab National Interuniversity Consortium for Informatics Rome Italy Dept. of Knowledge Technologies Jožef Stefan Institute Ljubljana Slovenia

Technological progress in the last few decades has granted an increasing number of people access to social media platforms such as Facebook, X (formerly Twitter), and Instagram. Consequently, the potential risks associated with these services have also risen due to users exploiting these services for malicious purposes. The platforms have tools capable of detecting and blocking dangerous users, but they primarily focus on the content posted by users and usually overlook additional factors, such as the relationships among users. Another key aspect to consider is that users’ beliefs and interests evolve over time. Therefore, a user who can be considered safe at one moment might later become malicious, and vice versa. This work describes a novel approach to node classification in temporal graphs, aimed at classifying users in social networks. The method was evaluated on a real-world scenario and was compared to a state-of-the-art system that treats the network as a static entity. Experiments showed that taking into account the temporal evolution of the network, in terms of node features and connections, is beneficial. © 2025, CC BY.

关键词： Federated learning

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of 2-DOF Arm Manipulator Robot as Robotic Kinematic Learning Platform 6

Design and Implementation of 2-DOF Arm Manipulator Robot as ...

引用

6th International Conference on Vocational Education and Electrical Engineering, ICVEE 2023

作者： Widayaka, Parama Diptya Puspitaningayu, Pradini Alamsyah, Sayyidul Aulia Muktiadji, Rifqi Firmansyah Widodo, Arif Abdillah, Rifqi Universitas Negeri Surabaya Dept. of Electrical Engineering Surabaya Indonesia King Abdulaziz University Dept. of Electrical and Computer Engineering Jeddah Saudi Arabia Okayama University Graduate School of Interdisciplinary Science and Engineering in Health Systems Okayamas Japan Institut Teknologi Sepuluh Nopember Surabaya Dept. of Informatics Surabaya Indonesia

ISBN: (纸本)9798350326642

Technological developments have impacts and challenges in human life. Technological advances have made human life easier. The impact of technological developments is the industrial manufacturing process getting faster with the help of robotics technology. Robots can shorten manufacturing process time and efficient. On the other hand, challenges with technological developments force us to keep learning and adaptive to every changes around us, especially in the education sector. In education sector, formal educational institutions or campuses must be able to facilitate students to be able to learn comprehensively in the field of technology, especially robotics, where we can make an innovative learning platform based on robotics technology. In this study, we discussed a 2-DOF arm manipulator robot as kinematics learning platform of industrial robot to increase student competencies in preparation for facing the industrial environment in century. Inverse kinematics equation has been applied in the robot by providing input coordinates on the x-Axis and y-Axis where the accuracy value on the x-Axis is 77% and the accuracy on the y-Axis is 83.1%. © 2023 IEEE.

关键词： Machine design

来源：评论

学校读者我要写书评

暂无评论

Machine Learning-based sEMG Signal Classification for Hand Gesture Recognition

Machine Learning-based sEMG Signal Classification for Hand G...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Parshuram N. Aarotale Ajita Rattani Dept. of Biomedical Engineering Wichita State University USA Dept. of Computer Science and Engineering Uni. of North Texas USA

ISBN: (数字)9798350386226

ISBN: (纸本)9798350386233

EMG-based hand gesture recognition uses electromyographic (EMG) signals to interpret and classify hand movements by analyzing electrical activity generated by muscle contractions. It has wide applications in prosthesis control, rehabilitation training, and human-computer interaction. Using electrodes placed on the skin, the EMG sensor captures muscle signals, which are processed and filtered to reduce noise. Numerous feature extraction and machine learning algorithms have been proposed to extract and classify muscle signals to distinguish between various hand *** paper aims to benchmark the performance of EMG-based hand gesture recognition using novel feature extraction methods, namely, fused time-domain descriptors, temporal-spatial descriptors, and wavelet transform-based features, combined with the state-of-the-art machine and deep learning models. Experimental investigations on the Grabmyo dataset demonstrate that the 1D Dilated CNN performed the best with an accuracy of 97% using fused time-domain descriptors such as power spectral moments, sparsity, irregularity factor and waveform length ratio. Similarly, on the FORS-EMG dataset, random forest performed the best with an accuracy of 94.95% using temporal-spatial descriptors (which include time domain features along with additional features such as coefficient of variation (COV), and Teager-Kaiser energy operator (TKEO)).

关键词： Hands Deep learning Wavelet transforms Accuracy Biological system modeling Gesture recognition Muscles Feature extraction Electromyography Time-domain analysis

来源：评论

学校读者我要写书评

暂无评论

Object criticality for safer navigation

arXiv

引用

arXiv 2024年

作者： Ceccarelli, Andrea Montecchi, Leonardo Dept. of Mathematics and Informatics University of Florence Florence Italy Department of Computer Science NTNU Trondheim Norway

Object detection in autonomous driving consists in perceiving and locating instances of objects in multi-dimensional data, such as images or lidar scans. Very recently, multiple works are proposing to evaluate object detectors by measuring their ability to detect the objects that are most likely to interfere with the driving task. Detectors are then ranked according to their ability to detect the most relevant objects, rather than the highest number of objects. However there is little evidence so far that the relevance of predicted object may contribute to the safety and reliability improvement of the driving task. This position paper elaborates on a strategy, together with partial results, to i) configure and deploy object detectors that successfully extract knowledge on object relevance, and ii) use such knowledge to improve the trajectory planning task. We show that, given an object detector, filtering objects based on their relevance, in combination with the traditional confidence threshold, reduces the risk of missing relevant objects, decreases the likelihood of dangerous trajectories, and improves the quality of trajectories in general. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Key Factors Influencing Mobile Banking Adoption in Saudi Arabia

Key Factors Influencing Mobile Banking Adoption in Saudi Ara...

引用

Federated Conference on computer science and Information Systems (FedCSIS)

作者： Amal Alzahrani Natalia Beloff Martin White Dept. of Computer Science & Information Systems Baha University Baha Saudi Arabia Dept. of Informatics University of Sussex Brighton United Kingdom

ISBN: (数字)9788396960160

ISBN: (纸本)9798350359718

The introduction of mobile banking has revolutionized traditional financial practices, enhancing efficiency, customer experiences, and business models globally. Despite the global advancements in mobile banking, adoption rates remain low in Saudi Arabia. This paper seeks to identify key factors affecting adoption, using a mixed-methods approach. We propose a novel model integrating factors from the DeLone and McLean (D&M) model and the Unified Theory of Acceptance and Use of Technology (UTAUT2) model, complemented by additional factors. Data was gathered through online surveys and customer interviews. Findings revealed that net benefits, compatibility, facilitating conditions, and trust positively influence adoption, while literacy levels and digital skills pose barriers. Our study offers a significant theoretical contribution by synthesizing multiple models and enriches understanding of mobile banking adoption, aiding future research and industry decisions.

关键词： Surveys Industries computer science Computational modeling Banking Interviews Business

来源：评论

学校读者我要写书评

暂无评论

WebRTC-based Resource Offloading in Smart Home Environments

WebRTC-based Resource Offloading in Smart Home Environments

引用

2022 IEEE International Conference on Consumer Electronics, ICCE 2022

作者： Jeong, Hunseop Lee, Taehyung Eom, Young Ik Sungkyunkwan University Dept. of Digital Media and Communications Engineering Suwon Korea Republic of Sungkyunkwan University Dept. of Computer Science and Engineering Suwon Korea Republic of College of Computing and Informatics Sungkyunkwan University Dept. of Electrical and Computer Engineering Suwon Korea Republic of

ISBN: (纸本)9781665441544

Web platforms face new demands for emerging applications, which use machine learning models such as pose recognition or object detection. These models require significant computing powers in processing enormous inputs such as images or audios for machine learning computation. These demands are also being generated in smart home appliances based on web platforms. Unfortunately, smart home appliances do not generally have built-in input devices, such as cameras or microphones, due to privacy issues and have limited performance compared to mobile devices. This paper proposes a WebRTC-based resource offloading system for web applications, which allows smart home appliances to use resources of nearby mobile devices as if the resources are their own. We implemented the proposed system, performed experiments on the resource offloading framework, and evaluated the performance using five computation-intensive web applications, which use a machine learning model. Our system was able to run machine learning models, through resource offloading to mobile devices, on smart home appliances without an attached camera, and achieved up to 1.5x speedup, compared to local execution with a camera. © 2022 IEEE.

关键词： Domestic appliances

来源：评论

学校读者我要写书评

暂无评论

Next Sentence Prediction: The Impact of Preprocessing Techniques in Deep Learning 10

Next Sentence Prediction: The Impact of Preprocessing Techni...

引用

10th International Conference on computer, Control, informatics and its Applications, IC3INA 2023

作者： Yuyun Latief, Andi Djalal Sampurno, Tri Hazriani Arisha, Andriansyah Oktafiandi Mushaf National Research and Innovation Agency Research Center for Data and Information Science Bandung Indonesia National Research and Innovation Agency Research Center for Data and Information Science Jakarta Indonesia Handayani University Dept. of Computer System Makassar Indonesia Dipa Makassar University Dept. of Informatics Management Makassar Indonesia

ISBN: (纸本)9798350394870

Text preprocessing in the field of Natural Language Processing (NLP) plays a crucial role in enhancing the model's ability to understand given tasks. This process helps in avoiding potential errors that could interfere with data processing. This study aims to investigate the effectiveness of four preprocessing techniques (tokenization, case-folding, stopword removal, and stemming) in predicting the next word in a sentence. The case focuses on Indonesian language text documents preprocessing using word2vec embedding and the long short-term memory networks (LSTM) classification model. The evaluation was conducted by incorporating human perception approach and evaluation matrix which focused on the suitability of word sequences and pairs on the prediction results. The result reveals that the combination of tokenizing and casefolding can enrich the meaning of the sentences. Meanwhile the combination of tokenizing, casefolding, stopword removal, and stemming can cause lose and overlap meaning in the sentences. The prediction model performs best on one-word n-grams, with precision 0.1, recall 1.0, and F-score 0.1. © 2023 IEEE.

关键词： Forecasting

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：