检索结果-内蒙古大学图书馆

2nd Workshop on Generalisation (Benchmarking) in NLP, GenBench 2024

作者： Phatthiyaphaibun, Wannaphong Nonesung, Surapon Limkonchotiwat, Peerat Udomcharoenchaikit, Can Sawatphol, Jitkapat Chuangsuwanich, Ekapol Nutanong, Sarana School of Information Science and Technology VISTEC Thailand Department of Computer Engineering Faculty of Engineering Chulalongkorn University Thailand

ISBN: (纸本)9798891761827

The evaluation of generative models in Machine Reading Comprehension (MRC) presents distinct difficulties, as traditional metrics like BLEU, ROUGE, METEOR, Exact Match, and F1 score often struggle to capture the nuanced and diverse responses. While embedding-based metrics such as BERTScore and BARTScore focus on semantic similarity, they still fail to fully address aspects such as recognizing additional helpful information and rewarding contextual faithfulness. Recent advances in large language model (LLM) based metrics offer more fine-grained evaluations, but challenges such as score clustering remain. This paper introduces a multi-aspect evaluation framework, CHIE, incorporating aspects of Correctness, Helpfulness, Irrelevance, and Extraneousness. Our approach, which uses binary categorical values rather than continuous rating scales, aligns well with human judgments, indicating its potential as a comprehensive and effective evaluation method. © 2024 Association for Computational Linguistics.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A gecko-inspired adhesive robotic end effector for critical-contact manipulation

引用

Science China(Information Sciences) 2022年第8期65卷 120-133页

作者： Zhongyi CHU Jie DENG Lin SU Jing CUI Fuchun SUN School of Instrumentation and Optoelectronic Engineering Beihang University School of Mechanical Engineering and Applied Electronics Beijing University of Technology Department of Computer Science and Technology Tsinghua University

It is an emerging challenge for robots to achieve non-destructive pick-and-place manipulation for delicate objects under low normal preload, i.e., critical-contact manipulation. The prominent on-off controllable property of the gecko-inspired microwedge adhesive makes critical-contact manipulation possible for robotic end effectors. However, it is difficult for end effectors to actuate the micron-scale microwedge adhesive and detect the adhesion state. In this paper, a gecko-inspired adhesive robotic end effector for critical-contact manipulation is proposed, which consists of a half-scissor variable-scale actuator, a 3-axis high-sensitivity isotropic flexible capacitive tactile sensor, and the microwedge adhesive. The half-scissor variable-scale actuator is designed to provide pure large shear loading for the microwedge adhesive at micronscale displacement by merely controlling the normal macro-scale displacement of the actuator. Besides, the3-axis high-sensitivity isotropic flexible capacitive tactile sensor is designed for accurate detection of multiaxis contact forces and the adhesion state between the adhesive and objects to ensure the success of the critical-contact manipulation. The sensor can sense the shear and normal forces by detecting variations of the overlap and distance between electrodes, while the design of the finger-like electrodes improves the sensitivity. In addition, a set of experiments on manipulating objects are implemented and the results show that the proposed robotic end effector can provide pure large shear loading for the microwedge adhesive at micron-scale displacement and can detect the adhesion state between the microwedge adhesive and objects accurately to stably grasp delicate objects in critical-contact condition.

关键词： critical-contact manipulation gecko-inspired microwedge adhesive robotic end effector half-scissor variable-scale actuator tactile sensor

来源：评论

学校读者我要写书评

暂无评论

Human-Robot Interaction on Elderly Companion Robot Development Using Dual Intent Entity Transformer 7

Human-Robot Interaction on Elderly Companion Robot Developme...

引用

7th International Conference on Information Technology, Information Systems and Electrical engineering, ICITISEE 2023

作者： Rauf, Naufal Haidar Santoso, Heru Agus Universitas Dian Nuswantoro Faculty of Computer Science Department of Informatics Engineering Semarang Indonesia

ISBN: (纸本)9798350382266

The growing elderly population and the increasing demand for nursing home care have led to a need to improve the quality of life for residents. A popular solution is developing a companion robot to assist residents with various tasks and provide human-like interaction. In this paper, we present the prototype of a companion robot currently website-based, equipped with a Dual Intent Entity Transformer to understand what the user wants. The results of the study show the prototype is capable of classifying user messages according to their appropriate intent with precision, recall, F-score, and accuracy on average 91 %, 91 %, 90%, and 87% respectively using privately owned dataset. Future works such as expanding the robot's insight and tuning the model would improve the service provided by the companion robot. © 2023 IEEE.

关键词： Human robot interaction

来源：评论

学校读者我要写书评

暂无评论

Enhancing Panoramic Competency Through Link Prediction in Question Knowledge Graphs using a Language Representation Model 7

Enhancing Panoramic Competency Through Link Prediction in Qu...

引用

7th IEEE International Conference on computer and Communication engineering Technology, CCET 2024

作者： Okuhara, Fumika Egami, Shusaku Sei, Yuichi Tahara, Yasuyuki Ohsuga, Akihiko Graduate School of Informatics and Engineering The University of Electro-Communications Department of Informatics Tokyo Japan Artificial Intelligence Research Center Tokyo Japan

ISBN: (纸本)9798350355673

Recently, panoramic knowledge has been required. On the other hand, multiple choice questions are suitable for efficient self-learning. Therefore, the purpose of this study is to create multiple choice questions that can reinforce learners' panoramic knowledge. Specifically, we proposed a method for automatically generating multiple choice questions that use Linked Data to present relevant information to give respondents an overall picture of relevant knowledge. There is some research on the methods that generated questions by extracting small subgraphs from the knowledge graphs consisting of entities(words) and relations(links) between the entities and hiding target words (correct answer words). In this study, our goal is to enhance the panoramic of the subgraphs of a specified size by using the link prediction method to complement edges and represent relationships not present in the knowledge graph when generating questions targeted at specific fields. The method of complementing edges involves first inputting two words as subject and object in Knowledge Graph to calculate the cosine similarity using a pretrained language model based on Wikipedia and Wikidata, then predicting the links as a predicate that should be complemented, and finally generating subgraphs by using the Graph Database added the complemented edges. For this study, we generated questions in the field of history, and since history requires temporal and spatial panoramic knowledge, words related to these aspects were focused on and complemented the relationships between them. As a result, 2,746 relationships were complemented by the proposed method in the subgraphs, and the subgraphs contained more words to learn (words found in textbooks that need to be learned) in a specific field compared to those generated using existing methods. © 2024 IEEE.

关键词： Knowledge graph

来源：评论

学校读者我要写书评

暂无评论

Analyze the impact of feature selection techniques in the early prediction of CKD

引用

International Journal of Cognitive Computing in engineering 2024年第1期5卷 66-77页

作者： Hema, K. Meena, K. Pandian, Ramaraj Department of Computer Science and Engineering GITAM School of Technology GITAM University Bangalore India Netapp San JoseCA United States

Background: Chronic renal disease, often known as Chronic Kidney Disease (CKD), is an illness that causes a steady decline in kidney function. As per the World Health Organization survey, the incidence of CKD may increase from 10% to 13% by 2030. Because of the lack of symptoms in the initial phase, diagnosing CKD early on may be difficult. The key objective of this study is to develop a forecasting model for the early detection of chronic renal disease. Methods: In medical science, Machine Learning (ML) Techniques play a significant role in disease prediction despite numerous studies conducted to categorize CKD in patients using machine learning tools. Most researchers need to analyze the impact of feature selection techniques, yielding high-quality and reliable results. The efficiency of any Techniques/Algorithms depends on feature selection, feature extraction, and classifiers. In this work, the impact of feature selection is experimented with using the Exhaustive Feature Selection (EFS) method. For the early prediction of CKD, a comparative examination of machine learning classifiers, including Gradient Boost (GB), XGBoost, Decision Tree (DT), Random Forest (RF), and KNN (k-nearest neighbors), are utilized. Results: Two types of datasets, standard (New Model) & real-time data sets collected from the dialysis unit of a reputed hospital in Chennai, are used to carry out extensive experiment analysis. Various metrics, including Accuracy, Precision, Recall, and F1-score, are used to tabulate the results of experiments conducted to measure the performance of the proposed approach for various combinations of test and training data. Conclusion: CKD is an irreversible and silent disease;it might have a high impact on many people and begin to manifest themselves at an early age in life. This research paper analyses the effect of feature selection techniques on early CKD prediction. © 2023 The Authors

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Integrated Coherent Photonic Crossbar Arrays for Efficient Optical Computing

Integrated Coherent Photonic Crossbar Arrays for Efficient O...

引用

2024 Conference on Lasers and Electro-Optics, CLEO 2024

作者： Kari, Sadra Rahimi Hastings, Allison Nobile, Nicholas A. Pantin, Dominique Shah, Vivswan Youngblood, Nathan Department of Electrical and Computer Engineering Swanson School of Engineering University of Pittsburgh PittsburghPA15213 United States

ISBN: (纸本)9781957171395

We present a scalable approach to optical computing using coherent crossbar arrays for processing temporally multiplexed signals. Our design enables scalable matrix-matrix operations, and correlation detection, enabling efficient on-chip optical computing for diverse AI applications. © Optica Publishing Group 2024 © 2024 The Author(s)

关键词： Photonic integrated circuits

来源：评论

学校读者我要写书评

暂无评论

Poetry Form Identification - A Comparative Analysis of Embedding Models and Classifiers 2

Poetry Form Identification - A Comparative Analysis of Embed...

引用

2nd International Conference on Self Sustainable Artificial Intelligence Systems, ICSSAS 2024

作者： Rohan, Gamidi Manideep, Thotapalli Sri Surya Saragadam, Sneha Pati, Peeta Basa Sail, Smita Amrita School of Computing Department of Computer Science and Engineering Bengaluru India Amrita Vishwa Vidyapeetham Amrita School of Engineering Department of English Bengaluru India

ISBN: (纸本)9798350368413

In recent years, automated text classification has advanced significantly, yet poetry classification remains a relatively under-explored domain. By employing Machine Learning and pre-trained language models, the proposed paper aims to automate poetry classification and provide a comparative analysis for utilizing GPT2 (Generative Pre-Trained Transformer), BERT (Bidirectional Encoder Representations from Transformers), and RoBERTa (Robustly Optimized BERT Pre-Training Approach). We have employed tokenization, sequence padding, and fine-tuning on a diverse dataset of poetry forms, including Sonnet, Haiku, Limerick, Acrostic, Ballad, Epigram, Sestina, and Villanelle. The proposed model is trained and evaluated on a dedicated data set using the application of AdamW Optimizer, and strives for robust classification performance. This research study yields promising results, with the Support Vector Machine (SVM) classifier achieving the highest accuracy of 93.25 percent using the top 20 percent ranked features. This study contributes to the field of automated poetry analysis by integrating various embedding models and classifiers, presenting notable advancements in the categorization of poetry. © 2024 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Predicting the Power Spectrum of Amplified OFDM Signals Using Higher-Order Intercept Points

引用

Chinese Journal of Electronics 2022年第2期31卷 213-219页

作者： YAN Siyuan YANG Xianzhen WANG Xiaoru LI Fu Department of Electrical and Computer Engineering Portland State University School of Computer Science and Technology Beijing University of Posts and Telecommunications

Orthogonal frequency-division multiplexing(OFDM) has been developed into a popular modulation scheme for wireless communication systems, used in applications such as LTE and 5 G. In wireless communication systems, nonlinearity caused by radio frequency(RF)amplifiers will generate distortions to both passband and adjacent channels such that the transmission quality is degraded. The study of this article aims to predict the power spectrum for OFDM based signals at the output of an RF amplifier due to the nonlinearity. In this article,based on Taylor polynomial coefficients, a power spectrum expression for amplified OFDM signals in terms of intercept points(up to nth-order) is derived. This model is useful to RF engineers in choosing and testing RF amplifiers with appropriate specifications, such as intercept points and gain, to meet the requirements of wireless standards. Measurements are carried out to confirm the results of the proposed model.

关键词： adjacent channels modulation scheme radio frequency amplifiers power spectrum expression Taylor polynomial coefficients RF amplifier higher-order intercept points passband channels amplified OFDM signals OFDM modulation wireless communication systems radiofrequency amplifiers wireless standards radio networks polynomials orthogonal frequency-division multiplexing OFDM based signals

来源：评论

学校读者我要写书评

暂无评论

Development of Weather Forecast Application Using API 1

Development of Weather Forecast Application Using API

引用

1st International Conference on Computing, Sciences and Communications, ICCSC 2024

作者： Chadha, Shikha Ahmad, Salman Khursheed Sharma, Dolly Singh, Manu Srivastavaline, Anubhava Sharda University Department of Computer Science Greater Noida India School Of Computer Science & Engineering Galgotias University Department Of Computer Science Engineering Greater Noida India Graphic Era Hill University School of Computing Department Haldwani India ABES Engineering College Department of Computer Science UP Ghaziabad India

ISBN: (纸本)9798350353648

This research paper presents the development of a weather forecasting model that incorporates real-time data through Application Programming Interfaces. This model utilises simple algorithms to analyse meteorological parameters from diverse API data sources, aiming to improve forecast accuracy compared to traditional methods. Extensive datasets are used for training and validation, demonstrating the model's effectiveness in providing more precise predictions. The study highlights the significance of API integration in advancing weather forecasting methodologies and fostering innovation in the field. The model created has yielded highly reliable results with minimal error. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

How international conflicts and global crises can intertwine and affect the sources and levels of air pollution in urban areas

引用

Environmental Science and Pollution Research 2024年第39期31卷 51619-51632页

作者： Ghaffarpasand, Omid Blake, Rhiannon Shalamzari, Zahra Davari School of Geography Earth and Environmental Sciences University of Birmingham Birmingham United Kingdom Department of Computer Engineering University of Isfahan Isfahan Iran

This paper analyses the intertwined impacts of the 2018 US sanctions on Iran and the COVID-19 pandemic (as examples of unplanned international conflicts and global crises) on the source and extent of air pollution in Tehran, the capital of Iran. The impacts are parametrized using the levels of criteria air pollutants (CAP) for 5 years (2015–2020), which were previously deweathered using the promising machine learning technique of Random Forest (RF). The absolute principal component scores-multiple linear regression (APCS-MLR) method and the bivariate polar plot (BPP) technique are used here to analyze the source apportionment profile of the city for the business as usual (BAU;2015 to 2018), sanctions (2019), and COVID-19 and sanctions (2020) intervals. The results show the severe impact of the 2018 US sanctions on Tehran’s air quality (AQ);O3, NO2, CO, PM2.5, and PM10 levels increased by 117%, 55%, 20%, 35%, and 10%, respectively, while SO2 levels decreased by 30%. The sanctions also triggered a number of events, such as the disruption of the high-grade fuel supply chain and the Mazut crisis, which directly or indirectly accelerated the photochemical production of local tropospheric ozone to some extent. Sanctions also disrupted Tehran’s AQ response to the pandemic, with CAP levels decreasing by only 2–7% during the pandemic. The ozone and PM10 BPPs show that the source apportionment profile of the city is dominated by local anthropogenic emission sources, especially urban transport, after the sanctions and the pandemic. Results also show that the impact of soft wars, such as the US sanctions against Iran, on urban air quality degradation is much stronger than that of hard wars, such as the Russia-Ukraine war. © The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, part of Springer Nature 2024.

关键词： Air quality

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：