检索结果-内蒙古大学图书馆

2024 ACM International Conference on Intelligent User Interfaces Workshops, IUI-WS 2024

作者： van Bree, Lotte Graus, Mark Ferwerda, Bruce Department of Computer Science and Informatics School of Engineering Jönköping University Jönköping Sweden Human-Centric SARL Paris France

To improve decision-making and prevent information overload, music streaming services try to offer users personalized content. Vocabulary can be an important component in achieving personalization, in addition to recommender systems that ensure users are given access to their musical preferences. One way to apply personalization through vocabulary is to use personal pronouns. However, it is still unclear how the use of vocabulary personalization affects users’ decisions and expectations when it comes to music streaming services. This study aims to explore how vocabulary framing in playlist titles influences decision-making and the content expectations of the music playlist. Despite challenges in making informed vocabulary choices, our results show a substantial impact of personalized vocabulary in playlist titles on user choice and overall expectations. Users distinctly favor playlists with personalized vocabulary, emphasizing their crucial role in enhancing the music streaming experience. © 2024 Copyright for this paper by its authors.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Zero-shot Persuasive Chatbots with LLM-Generated Strategies and Information Retrieval

Zero-shot Persuasive Chatbots with LLM-Generated Strategies ...

引用

2024 Conference on Empirical Methods in Natural Language Processing, EMNLP 2024

作者： Furumai, Kazuaki Legaspi, Roberto Vizcarra, Julio Yamazaki, Yudai Nishimura, Yasutaka Semnani, Sina J. Ikeda, Kazushi Shi, Weiyan Lam, Monica S. Human-Centered AI Laboratories KDDI Research Inc. Saitama Japan Computer Science Department Stanford University StanfordCA United States

ISBN: (纸本)9798891761681

Persuasion plays a pivotal role in a wide range of applications from health intervention to the promotion of social good. Persuasive chatbots employed responsibly for social good can be an enabler of positive individual and social change. Existing methods rely on fine-tuning persuasive chatbots with task-specific training data which is costly, if not infeasible, to collect. Furthermore, they employ only a handful of pre-defined persuasion strategies. We propose PersuaBot, a zero-shot chatbot based on Large Language Models (LLMs) that is factual and more persuasive by leveraging many more nuanced strategies. PersuaBot uses an LLM to first generate natural responses, from which the strategies used are extracted. To combat hallucination of LLMs, Persuabot replace any unsubstantiated claims in the response with retrieved facts supporting the extracted strategies. We applied our chatbot, PersuaBot, to three significantly different domains needing persuasion skills: donation solicitation, recommendations, and health intervention. Our experiments on simulated and human conversations show that our zero-shot approach is more persuasive than prior work, while achieving factual accuracy surpassing state-of-the-art knowledge-oriented chatbots. © 2024 Association for Computational Linguistics.

关键词： Zero-shot learning

来源：评论

学校读者我要写书评

暂无评论

A DV-Hop dynamic weight positioning model with genetic algorithm

引用

International Journal of Wireless and Mobile Computing 2021年第2期20卷 139-145页

作者： Wang, Penghong Fan, Tian Cai, Xingjuan Li, Wuchao School of Computer Science and Technology Taiyuan University of Science and Technology Taiyuan Shanxi003024 China Research Centre of Intelligent Interface and Human Computer Interaction Department of Computer Science and Technology Harbin Institute of Technology Harbin Heilongjiang150006 China Jiaxing Vocational Technical College Jiaxing Zhejiang China

Wireless Sensor Networks (WSNs), as an important part of the Internet of Things (IoT), are widely deployed to the location estimation in WSNs. However, at present, the study of DV-Hop algorithm is still limited to the improvement of the sensor nodes in the ordinary region. In this paper, aiming at the complex areas under different application backgrounds, based on the analysis of the localisation principle of the traditional DV-Hop model based on optimisation algorithm, a dynamic weight positioning model based on genetic algorithm (DWMGA-DV-Hop) is proposed. The algorithm performs simulation experiments on three different types of test by adopting dynamic weight calculation model. And experimental results demonstrate that, under different test sets, compared with the standard DV-Hop algorithm, TW-PSODV-Hop and OCS-DV-Hop algorithm, this algorithm has the highest positioning accuracy and stability. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Enhancing Cancer Gene Prediction through Aligned Fusion of Multiple PPI Networks Using Graph Transformer Models

Enhancing Cancer Gene Prediction through Aligned Fusion of M...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Han, Zebei Yu, Gufeng Yang, Yang Shanghai Jiao Tong University Key Lab. of Shanghai Education Commission for Intelligent Interaction and Cognitive Engineering Department of Computer Science and Engineering Shanghai200240 China

ISBN: (纸本)9798350337488

Despite the considerable progress that has been made in cancer research, identifying cancer genes remains a significant challenge due to the intricate nature of the disease. Given the importance of incorporating gene interaction relationships in identifying potential cancer genes, Graph Neural Networks (GNNs) have garnered increasing attention for their ability to model gene associations effectively. Particularly, recent studies have demonstrated the superiority of GNNs in deciphering the knowledge embedded in Protein-Protein interaction (PPI) networks for cancer gene prediction. However, these studies primarily focused on a single PPI network, overlooking the valuable insights encapsulated within other PPI networks. Additionally, previous endeavors often centered around pan-cancer datasets, neglecting the importance of predicting specific cancer genes. To address these limitations, we present a novel method called MPIT, which employs Graph Transformer Networks (GTNs) to identify specific cancer driver genes. MPIT effectively integrates data from diverse PPI and multi-omics data via the alignment and fusion of gene representations learned from different PPI networks. We collect three distinct cancer cell line datasets to assess the model performance. Our experimental findings demonstrate the superiority of MPIT over the existing methods, achieving the state-of-the-art performance across all three datasets. © 2023 IEEE.

关键词： Cancer genes feature alignment feature fusion Graph Transformer Network specific cancer genes

来源：评论

学校读者我要写书评

暂无评论

Auto-PIP: Real-time Identification of Critical Performance Inflection Points in Software Stress Testing 35

Auto-PIP: Real-time Identification of Critical Performance I...

引用

35th IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2024

作者： Zhang, Shenglin Xiong, Xiao Li, Mengyao Sun, Yongqian Zhao, Yongxin Chen, Xia Deng, Bowen Pei, Dan Nankai University China Haihe Laboratory of Information Technology Application Innovation China Tianjin Key Laboratory of Software Experience and Human Computer Interaction China Huawei Cloud Tsinghua University Beijing National Research Center for Information Science and Technology China

ISBN: (纸本)9798350367041

Conducting stress testing is essential to ensure the stability and performance of software systems post-launch. Among its various aspects, the real-time identification of the "Smooth Load Area"(SLA) is crucial for establishing performance benchmarks, identifying bottlenecks, guiding optimization strategies, and strategically allocating resources. However, existing methods are incapable of real-time inflection point detection or require manual intervention. This paper proposes Auto-PIP, an automated identification framework for performance inflection points based on key performance indicators (KPIs) during performance stress tests. Auto-PIP integrates trend testing algorithms with unsupervised anomaly detection algorithms to identify optimal operating points and estimate maximum capacity. Auto-PIP has been deployed in Huawei Cloud, and the evaluation results show that Auto-PIP demonstrated 100% accuracy in optimal inflection point detection, a 41.7% leap over baselines, and 83.9% accuracy in maximum point identification, a 10.7% gain. Additionally, we have released the dataset to the public to promote ongoing research. © 2024 IEEE.

关键词： Software testing

来源：评论

学校读者我要写书评

暂无评论

AI-Driven Relocation Tracking in Dynamic Kitchen Environments

arXiv

引用

arXiv 2025年

作者： Esfahani, Arash Nasr Hosseini, Hamed Masouleh, Mehdi Tale Kalhor, Ahmad Sajedi, Hedieh Human and Robot Interaction Lab School of Electrical and Computer Engineering University of Tehran Tehran Iran School of Mathematics Statistics and Computer Science University of Tehran Tehran Iran

As smart homes become more prevalent in daily life, the ability to understand dynamic environments is essential which is increasingly dependent on AI systems. This study focuses on developing an intelligent algorithm which can navigate a robot through a kitchen, recognizing objects, and tracking their relocation. The kitchen was chosen as the testing ground due to its dynamic nature as objects are frequently moved, rearranged and replaced. Various techniques, such as SLAM feature-based tracking and deep learning-based object detection (e.g., Faster R-CNN), are commonly used for object tracking. Additionally, methods such as optical flow analysis and 3D reconstruction have also been used to track the relocation of objects. These approaches often face challenges when it comes to problems such as lighting variations and partial occlusions, where parts of the object are hidden in some frames but visible in others. The proposed method in this study leverages the YOLOv5 architecture, initialized with pre-trained weights and subsequently fine-tuned on a custom dataset. A novel method was developed, introducing a frame-scoring algorithm which calculates a score for each object based on its location and features within all frames. This scoring approach helps to identify changes by determining the best-associated frame for each object and comparing the results in each scene, overcoming limitations seen in other methods while maintaining simplicity in design. The experimental results demonstrate an accuracy of 97.72%, a precision of 95.83% and a recall of 96.84% for this algorithm, which highlights the efficacy of the model in detecting spatial changes. © 2025, CC BY.

关键词： Optical flows

来源：评论

学校读者我要写书评

暂无评论

Multivariate Time Series Anomaly Detection based on Pre-trained Models with Dual-Attention Mechanism 35

Multivariate Time Series Anomaly Detection based on Pre-trai...

引用

35th IEEE International Symposium on Software Reliability Engineering Workshops, ISSREW 2024

作者： Sun, Yongqian Guo, Yang Liang, Minghan Wen, Xidao Kuang, Junhua Zhang, Shenglin Li, Hongbo Xia, Kaixu Pei, Dan Nankai University China Tianjin Key Laboratory of Software Experience and Human Computer Interaction China BizSeer Haihe Laboratory of Information Technology Application Innovation China Tencent Tsinghua University Beijing National Research Center for Information Science and Technology China

ISBN: (纸本)9798350367041

In major tech companies, monitoring server performance data with anomaly detection algorithms is crucial for assessing operational status. Existing models often require separate training or fine-tuning for each server due to generalization limitations, leading to increased storage, memory, and training costs. As the number of servers grows, this approach becomes impractical. To address this, we propose using pretrained language models for time series anomaly detection, leveraging their strong generalization capabilities. Specifically, we employ two pre-trained GPT-2 models as backbones and implement a two-stage fine-tuning strategy to retain learned knowledge while adapting to specific business data characteristics. Our experiments on multiple anomaly detection datasets demonstrate that our method achieves the best average F1-Score, outperforming the leading baseline by 7%. © 2024 IEEE.

关键词： Time series

来源：评论

学校读者我要写书评

暂无评论

Conversational Agents on Your Behalf: Opportunities and Challenges of Shared Autonomy in Voice Communication for Multitasking 25

Conversational Agents on Your Behalf: Opportunities and Chal...

引用

Proceedings of the 2025 CHI Conference on human Factors in Computing Systems

作者： Yi Fei Cheng Hirokazu Shirado Shunichi Kasahara Sony Computer Science Laboratories Inc. Tokyo Japan Okinawa Institute of Science and Technology Graduate University Okinawa Japan and Human-Computer Interaction Institute Carnegie Mellon University Pittsburgh Pennsylvania USA Human-Computer Interaction Institute Carnegie Mellon University Pittsburgh Pennsylvania USA Sony Computer Science Laboratories Inc. Tokyo Japan and Okinawa Institute of Science and Technology Graduate University Okinawa Japan

ISBN: (纸本)9798400713941

Advancements in computational agents will enable them to act as surrogates for users in online communication, promising enhanced productivity by supporting multitasking. This capability may be especially powerful when combined with human control, allowing users to retain agency while achieving better performance than either human or agent alone. However, it remains unclear how people might leverage this technology to multitask effectively. We present a study with 18 dyads exploring how users employ automated responses to support an arithmetic task while staying engaged in a voice call. Participants multitasked with a conversational agent under three levels of autonomy: none, shared, and full. Our findings indicate that fully automated systems can maintain conversational engagement, enabling users to multitask effectively. Surprisingly, shared autonomy hindered this ability. Based on our results, we discuss implications for designing shared autonomy in conversations, highlighting new considerations and challenges. © 2025 Copyright held by the owner/author(s).

关键词： computer-mediated communication

来源：评论

学校读者我要写书评

暂无评论

Usability Assessment of OpenEMR: Enhancing Healthcare interactions 68th

Usability Assessment of OpenEMR: Enhancing Healthcare Intera...

引用

68th International Annual Meeting of the human Factors and Ergonomics Society, HFES 2024

作者： Mahmoud, Abdelrahman Saleem, Jason J. University of Louisville LouisvilleKY United States Department of Computer Science and Engineering Alamein International University Matrouh New Alamein City Egypt Department of Computer Science and Engineering University of Louisville KY United States Center for Human Systems Engineering University of Louisville KY United States

Electronic medical record (EMR) systems are pivotal in modern healthcare for digitizing patient records and improving clinical workflows. However, persistent usability challenges hinder their effective adoption and user satisfaction. This study employs a comprehensive user-centered design approach to identify and address usability issues in one such EHR, an open-source system named openEMR. Our main objective was to assess openEMR’s usability through several usability metrics. In addition to a summative usability test with 10 participants, we employed usability inspection (i.e., a heuristic evaluation) to generate additional findings using multiple methods. The results from the summative usability test provide a comprehensive perspective on openEMR’s performance. In addition to task-specific observations, participants offered insights into openEMR’s overall usability through a debrief interview. Through quantitative surveys, usability testing, qualitative interviews, and a heuristic evaluation, this study identified critical usability issues, proposes targeted solutions, and discusses implications for enhancing EMR systems in healthcare settings. © 2024 human Factors and Ergonomics Society.

关键词： Electronic health record

来源：评论

学校读者我要写书评

暂无评论

WIP: Integrating Green Computing Competencies Into Southern African Curricula 54

WIP: Integrating Green Computing Competencies Into Southern ...

引用

54th IEEE Frontiers in Education Conference, FIE 2024

作者： Ruwodo, Vuyelwa David Mufungulwa, George Moyo, Sibonile Uwu-Khaeb, Lannie Angula, Nikodemus Sutinen, Erkki University of Turku Department of Computing Turku Finland The Copperbelt University Department of Computer Science Kitwe Zambia National University of Science and Technology Department of Information and Analytics Buluwayo Zimbabwe Namibia University of Science and Technology Department of Commerce Human Science and Education Windhoek Namibia

ISBN: (纸本)9798350351507

This is work-in-progress research-to-practice. computer-based solutions are viewed as key to many technological problems, especially in reducing the impact of technology on the environment. At the same time, these computing solutions have their negative impacts. Such negative impacts are not understood by many computing specialists, as computing graduates have not been made aware of these undesirable impacts of their solutions. Based on frameworks such as CC2020, most computing curricula in Southern Africa, do not incorporate sustainability concepts. This means computing graduates of these African institutions will continue to view the quality of their computing solutions as defined by curricula that lack emphasis on sustainability. However, Africa's contribution to engineering education with a green twist can address this predicament. By integrating sustainability principles into computing and engineering curricula, African higher education institutions (HEI) can pioneer a new generation of professionals equipped with knowledge and skills to develop sustainable green technological solutions. Such an approach will not only address local challenges but will also position Africa as a major contributor to green computing and sustainable engineering practices, which are increasingly crucial in the global effort to mitigate environmental degradation. Using Design science Research (DSR), incorporating Action Research, this paper discusses the process of formulating a green-friendly computing curriculum for use by five African universities, participating in a European Union-funded project, Grow Green Africa (Gr2A). This hybrid approach to curriculum development ensures the viability of the resulting curriculum and its adaptability and sustainability over time. The designed curriculum incorporates sustainability principles aimed at fostering sustainable practices in the computing sector. The competency-based learning model encompasses knowledge, skills, and dispositions req

关键词： Green development

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：