检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Moore, Steven Schmucker, Robin Mitchell, Tom Stamper, John Human-Computer Interaction Carnegie Mellon University PittsburghPA United States Machine Learning Department Carnegie Mellon University PittsburghPA United States

Knowledge Components (KCs) linked to assessments enhance the measurement of student learning, enrich analytics, and facilitate adaptivity. However, generating and linking KCs to assessment items requires significant effort and domain-specific knowledge. To streamline this process for higher-education courses, we employed GPT-4 to generate KCs for multiple-choice questions (MCQs) in Chemistry and E-Learning. We analyzed discrepancies between the KCs generated by the Large Language Model (LLM) and those made by humans through evaluation from three domain experts in each subject area. This evaluation aimed to determine whether, in instances of non-matching KCs, evaluators showed a preference for the LLM-generated KCs over their human-created counterparts. We also developed an ontology induction algorithm to cluster questions that assess similar KCs based on their content. Our most effective LLM strategy accurately matched KCs for 56% of Chemistry and 35% of E-Learning MCQs, with even higher success when considering the top five KC suggestions. human evaluators favored LLM-generated KCs, choosing them over human-assigned ones approximately two-thirds of the time, a preference that was statistically significant across both domains. Our clustering algorithm successfully grouped questions by their underlying KCs without needing explicit labels or contextual information. This research advances the automation of KC generation and classification for assessment items, alleviating the need for student data or predefined KC labels. © 2024, CC BY.

关键词： E-learning

来源：评论

学校读者我要写书评

暂无评论

Automating Gaze Target Annotation in human-Robot interaction

Automating Gaze Target Annotation in Human-Robot Interaction

引用

IEEE International Workshop on Robot and human Communication (ROMAN)

作者： Linlin Cheng Koen V. Hindriks Artem V. Belopolsky Faculty of Science Computer Science Vrije Universiteit Amsterdam Department of Human Movement Sciences Vrije Universiteit Amsterdam

ISBN: (数字)9798350375022

ISBN: (纸本)9798350375039

Identifying gaze targets in videos of human-robot interaction is useful for measuring engagement. In practice, this requires manually annotating for a fixed set of objects that a participant is looking at in a video, which is very time-consuming. To address this issue, we propose an annotation pipeline for automating this effort. In this work, we focus on videos in which the objects looked at do not move. As input for the proposed pipeline, we therefore only need to annotate object bounding boxes for the first frame of each video. The benefit, moreover, of manually annotating these frames is that we can also draw bounding boxes for objects outside of it, which enables estimating gaze targets in videos where not all objects are visible. A second issue that we address is that the models used for automating the pipeline annotate individual video frames. In practice, however, manual annotation is done at the event level for video segments instead of single frames. Therefore, we also introduce and investigate several variants of algorithms for aggregating frame-level to event-level annotations, which are used in the last step in our annotation *** compare two versions of our pipeline: one that uses a state-of-the-art gaze estimation model (GEM) and a second one using a state-of-the-art target detection model (TDM). Our results show that both versions successfully automate the annotation, but the GEM pipeline performs slightly (≈10%) better for videos where not all objects are visible. Analysis of our aggregation algorithm, moreover, shows that there is no need for manual video segmentation because a fixed time interval for segmentation yields very similar results. We conclude that the proposed pipeline can be used to automate almost all of the annotation effort.

关键词： Annotations Soft sensors Pipelines human-robot interaction Manuals Object detection Time division multiplexing Particle measurements Robots Videos

来源：评论

学校读者我要写书评

暂无评论

The IoT Codex: A Book of Programmable Stickers for Authoring and Composing Embedded Computing Applications

The IoT Codex: A Book of Programmable Stickers for Authoring...

引用

IEEE Symposium on Visual Languages and human Centric Computing (VL/HCC)

作者： Kristin Williams Jessica Hammer Scott Hudson Computer Science Emory University Atlanta USA Human Computer Interaction Institute Carnegie Mellon University Pittsburgh USA Entertainment Technology Center Carnegie Mellon University Pittsburgh USA

The Internet-of-Things (IoT) promises to enhance everyday objects with computing, but rarely enables directly authoring or composing that behavior. Lightweight IoT approaches attach identifiers (e.g., RFID tags) to objects to enable networked services. Typically these tags are passive, and so, depend on activity recognition and predefined context. This limits interaction to invoking predetermined behavior. Instead, this work presents The IoT Codex: a lightweight approach to customizing everyday objects with IoT by enabling interactive attachable IDs (aIDs) to compose software-supported behavior in situ. This work contributes 1) paper engineering techniques to construct aIDs that embody state, and 2) a tangible, end user programming (EUP) language for customizing IoT within symbolic and idiosyncratic contexts. Here, we provide preliminary validation of our approach with an empirically informed design space, sample applications, and a small co-design workshop. In doing so, we offer preliminary evidence for tangible, end user programming to enable meaningful control over IoT services.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Correction: Prompt4LJP: prompt learning for legal judgment prediction

引用

The Journal of Supercomputing 2025年第5期81卷 1-2页

作者： Huang, Qiongyan Xia, Yuhan Long, Yunfei Fang, Hui Liang, Ruiwei Guan, Yin Xu, Ge College of Mechanical and Electrical Engineering Fujian Agriculture and Forestry University Fuzhou China School of Computer Science and Electronic Engineering University of Essex Colchester UK School of Computer and Big Data Minjiang University Fuzhou China Fujian Mental Health Human-Computer Interaction Technology Research Center Minjiang University Fuzhou China Fuzhou Institute of Oceanography Fuzhou China

来源：评论

学校读者我要写书评

暂无评论

Emotion Detection by Image Analysis for Painter 26

Emotion Detection by Image Analysis for Painter

引用

26th World Multi-Conference on Systemics, Cybernetics and Informatics, WMSCI 2022

作者： Wu, Yung-Gi Yang, Meng-Hua Chen, Wen-Jing Lin, Zi-Yu Wu, Ke-Shang Department of Computer Science & Information Engineering Chang Jung Christian University Tainan City711 Taiwan Department of Interaction Design Chang Jung Christian University Tainan City711 Taiwan

ISBN: (纸本)9781950492640

Painting is an expression of visual psychological intentions, which presents inner thoughts and emotions to the outside. This expression and the displayed picture works have an initial diagnostic function and can be used as one of the emotional indicators of the painter. Because traditional interviews are often limited to the use of speech, or limited by cognitive functions;in contrast, painting does not depend on language, nor is it limited by age and education level, language loss, intelligence inadequate or children can do it, and they can express their thoughts through creation. Understanding psychological emotions are the beginning of mental therapy. The goal of this research is to use artificial intelligence and deep learning technologies to develop a system that can detect the psychological state of the painter. This paper collects pictures of those with weak communication skills and through image analysis methods captures color, shape, composition, pattern, and other information, with the help of psychologists and art professional professors for deep learning and recognition. In our system, people can detect emotions through the pictures drawn. If they have been in negative emotions frequently, they can seek medical assistance. We hope to help more people to be aware of their emotional status in an easy way. Copyright 2022. © by the International Institute of Informatics and Systemics. All rights reserved.

关键词： Image analysis

来源：评论

学校读者我要写书评

暂无评论

Multi-View Body Image-Based Prediction of Body Mass Index and Various Body Part Sizes

Multi-View Body Image-Based Prediction of Body Mass Index an...

引用

2023 IEEE/CVF Conference on computer Vision and Pattern Recognition Workshops, CVPRW 2023

作者： Kim, Seunghyun Lee, Kunyoung Lee, Eui Chul Sangmyung University Graduate School Department of AI & Informatics Korea Republic of Sangmyung University Graduate School Department of Computer Science Korea Republic of Sangmyung University Department of Human-Centered Artificial Intelligence Korea Republic of

ISBN: (纸本)9798350302493

This paper proposes a novel model for predicting body mass index and various body part sizes using front, side, and back body images. The model is trained on a large dataset of labeled images. The results show that the model can accurately predict body mass index and various body part sizes such as chest, waist, hip, thigh, forearm, and shoulder width. One significant advantage of the proposed model is that it can use multiple views of the body to achieve more accurate predictions, overcoming the limitations of models that only used a single image. The model also does not require complex pre-processing or feature extraction, making it straightforward to apply in practice. We also explore the impact of different environmental factors, such as clothing and posture, on the model's performance. The findings show that the model is relatively insensitive to posture but is more sensitive to clothing, emphasizing the importance of controlling for clothing when using this model. Overall, the proposed model represents a step forward in predicting body mass index and various body part sizes from images. The model's accuracy, convenience, and ability to use multiple views of the body make it a promising tool for a wide range of applications. The proposed method is expected to be utilized as a parameter for accurate sensing of various vision-based non-contact biomarkers, in addition to body mass index inference. © 2023 IEEE.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Combined Correlational Network for Identifying Behavioral Health Cases from First Responder Report

Combined Correlational Network for Identifying Behavioral He...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Pederson, Mason Azmee, Abm Adnan Nweke, Francis Al Hafiz Khan, Md Abdullah Pei, Yong Thomas, Dominic Nandan, Monica Kennesaw State University Department of Computer Science MariettaGA United States Kennesaw State University Department of Information Systems and Security KennesawGA United States Kennesaw State University Department of Social Work and Human Services KennesawGA United States

ISBN: (纸本)9798350362480

Behavioral health is a broad term which encompasses our overall mental and physical well-being. Behavioral health issues do not just impact an individual's life, they also impact wider society. First responders are often the first point of contact for individuals facing emergency. Reports from first responders are a great resource to identify potential behavioral health cases. Manually identifying these cases are time consuming and prone to error. Automation in identifying these reports would be a huge time saver for facilities and allow for them to spend more time on addressing these problems or on more pressing matters. Natural language processing techniques are widely used by researchers for analyzing texts. However, due to the linguistic complexity of the first responder reports it is challenging for traditional natural language processing and deep learning technique to identify these reports. To address this issues in this work we proposed a novel correlational network which utilizes domain experts knowledge along with their correlational relationships to appropriately identify behavioral health cases. Our proposed framework uses the correlation between features and combines them which allows for granular and broad scope insights into a report. Moreover, we performed multi-label classification which reflects the real world scenarios where reports can contain multiple classes. We performed extensive evaluation to determine the efficiency and efficacy of our model. Furthermore, our proposed model outperformed the state-of-the-art model with an accuracy of 72%. © 2024 IEEE.

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Approach for Evaluating Industry-Based Employer Ranking and Financial Stability 5

Machine Learning Approach for Evaluating Industry-Based Empl...

引用

5th IEEE International Conference on Recent Trends in computer science and Technology, ICRTCST 2024

作者： Swain, Prakash Chandra Balan, Seema Lakshmi, S.R. Choudhary, Ankur Patjoshi, Pramod Kumar Raja, J. School of Social Financial & Human Sciences Odisha Bhubaneswar India Rajalakshmi Engineering College Department of Management Studies Chennai India Christ University Department of Business & Management Karnataka Bangalore560073 India Graphic Era Deemed to be University Department of Computer Science & Engineering Uttarakhand Dehradun248002 India Centurion University of Technology and Management BBSR Campus School of Management India St. Martins Engineering College Department of Computer Science and Engineering Telangana Secunderabad India

ISBN: (纸本)9798350351378

Using the computational prowess of machine learning, this study presents a fresh method for assessing the relative standing and fiscal health of employers across different sectors. The research makes use of a wide variety of data, including financial reports, statistics on the labor market, employee evaluations, and indicators unique to the business, to arrive at in-depth judgements. The financial stability assessment applies a linear regression model, whereas employer ranking is predicted using a logistic regression model. Financial data, employment market dynamics, and sentiment research are used as foundational characteristics for these models. Company A is more financially stable than Company B, yet it is anticipated to be ranked lower as an employer. This highlights the difficulty of judging businesses. The implications of these results for job-seekers, investors, and businesses are varied. The study also highlights the significance of ethics, openness, and addressing biases in assessment. This study paves the way for future advancements in this crucial subject and provides a basis for data-driven, well-informed decision-making in the ever-changing landscapes of contemporary industrial evaluations. © 2024 IEEE.

关键词： Commerce

来源：评论

学校读者我要写书评

暂无评论

Instruction-Driven Game Engine: A Poker Case Study

Instruction-Driven Game Engine: A Poker Case Study

引用

2024 Conference on Empirical Methods in Natural Language Processing: System Demonstrations, EMNLP 2024

作者： Wu, Hongqiu Liu, Xingyuan Wang, Yan 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 Shanghai Key Laboratory of Trusted Data Circulation and Governance in Web3 China Tencent China

ISBN: (纸本)9798891761674

The Instruction-Driven Game Engine (IDGE) project aims to democratize game development by enabling a large language model (LLM) to follow free-form game descriptions and generate game-play processes. The IDGE allows users to create games simply by natural language instructions, which significantly lowers the barrier for game development. We approach the learning process for IDGEs as a Next State Prediction task, wherein the model autoregressively predicts the game states given player actions. The computation of game states must be precise;otherwise, slight errors could corrupt the game-play experience. This is challenging because of the gap between stability and diversity. To address this, we train the IDGE in a curriculum manner that progressively increases its exposure to complex scenarios. Our initial progress lies in developing an IDGE for Poker, which not only supports a wide range of poker variants but also allows for highly individualized new poker games through natural language inputs. This work lays the groundwork for future advancements in transforming how games are created and played. © 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

Explainable Multi-Label Classification Framework for Behavioral Health Based on Domain Concepts

Explainable Multi-Label Classification Framework for Behavio...

引用

2024 IEEE International Conference on Big Data, BigData 2024

作者： Nweke, Francis Azmee, Abm Adnan Al Hafiz Khan, Md Abdullah Pei, Yong Thomas, Dominic Nandan, Monica Kennesaw State University Department of Computer Science MariettaGA United States Kennesaw State University Department of Information Systems and Security KennesawGA United States Kennesaw State University Department of Social Work and Human Services KennesawGA United States

ISBN: (纸本)9798350362480

Behavioral health, which covers mental health, lifestyle choices, addictions, and crises, poses serious issues in the community. Thus, appropriately analyzing and classifying behavioral health data is crucial for making informed health-care decisions. Traditional deep learning and natural language processing approaches struggle to effectively identify behavioral health issues because the data is unstructured, complex, and lacks sufficient context. Furthermore, subject matter experts must be consulted to ensure effective identification. In this work, we proposed a deep learning-based framework consisting of several modules: A) domain concept encoder converts the keywords and their evidence types to vectors, which were predefined by a subject matter expert;B) the semantic representation encoder (SRE) is trained on the vectors to learn the relationship between them;C) transformed-based feature learner is an advanced learner that extracts feature embeddings from documents and generates attention weights since it has more context given the incorporated relationship weights;D) The behavioral health multilabel classifier utilizes feature embeddings to classify a document into one or more behavioral health classes;and E) The LLM-enabled explainer provides explanations based on attention weights and classifications. Our proposed framework outperformed state-of-the-art models in multilabel behavioral health case classification while also providing explanations for each classification. Which is crucial in behavioral health analysis. © 2024 IEEE.

关键词： Electronic health record

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：