检索结果-内蒙古大学图书馆

The Impact of ChatGPT Exposure on User Interactions With a Motivational Interviewing Chatbot: Quasi-Experimental Study

引用

JMIR Formative Research 2025年 9卷 e56973页

作者： Zhu, Jiading Dong, Alec Wang, Cindy Veldhuizen, Scott Abdelwahab, Mohamed Brown, Andrew Selby, Peter Rose, Jonathan The Edward S. Rogers Sr. Department of Electrical & Computer Engineering University of Toronto Toronto ON Canada Department of Mechanical & Industrial Engineering University of Toronto Toronto ON Canada INTREPID Lab Centre for Addiction and Mental Health Toronto ON Canada Institute for Mental Health Policy Research Centre for Addiction and Mental Health Toronto ON Canada Department of Family and Community Medicine University of Toronto Toronto ON Canada Dalla Lana School of Public Health University of Toronto Toronto ON Canada

Background: The worldwide introduction of ChatGPT in November 2022 may have changed how its users perceive and interact with other chatbots. This possibility may confound the comparison of responses to pre-ChatGPT and post-ChatGPT iterations of pre-existing chatbots, in turn affecting the direction of their evolution. Before the release of ChatGPT, we created a therapeutic chatbot, MIBot, whose goal is to use motivational interviewing to guide smokers toward making the decision to quit smoking. We were concerned that measurements going forward would not be comparable to those in the past, impacting the evaluation of future changes to the chatbot. Objective: The aim of the study is to explore changes in how users interact with MIBot after the release of ChatGPT and examine the relationship between these changes and users’ familiarity with ChatGPT. Methods: We compared user interactions with MIBot prior to ChatGPT’s release and 6 months after the release. Participants (N=143) were recruited through a web-based platform in November of 2022, prior to the release of ChatGPT, to converse with MIBot, in an experiment we refer to as MIBot (version 5.2). In May 2023, a set of (n=129) different participants were recruited to interact with the same version of MIBot and asked additional questions about their familiarity with ChatGPT, in the experiment called MIBot (version 5.2A). We used the Mann-Whitney U test to compare metrics between cohorts and Spearman rank correlation to assess relationships between familiarity with ChatGPT and other metrics within the MIBot (version 5.2A) cohort. Results: In total, 83(64.3%) participants in the MIBot (version 5.2A) cohort had used ChatGPT, with 66 (51.2%) using it on a regular basis. Satisfaction with MIBot was significantly lower in the post-ChatGPT cohort (U=11,331.0;P=.001), driven by a decrease in perceived empathy as measured by the Average Consultation and Relational Empathy Measure (U=10,838.0;P=.01). Familiarity with ChatGPT was

关键词： artificial intelligence chatbot ChatGPT conversational agent digital health experimental large language models motivational interviewing natural language processing smoking cessation

来源：评论

学校读者我要写书评

暂无评论

Smart Happy Device with IoT : For those who suffer anxiety, stress, and depression

Smart Happy Device with IoT : For those who suffer anxiety, ...

引用

IEEE Region 10 Humanitarian Technology Conference (R10-HTC)

作者： Fitri Yakub Azizul Azizan Inge Dhamanti Ahmad Zahran Md. Khudzari Niranjana Govindan Muljono Muljono Electronic System Engineering Department Malaysia-Japan International Institute of Technology UTM Kuala Lumpur Malaysia Cyberphysical Research Group (Embedded AI & ML Science Lab) Faculty of Artificial Intelligence Universiti Teknologi Malaysia Kuala Lumpur Malaysia Department of Health Policy and Administration Faculty of Public Health Universitas Airlangga Surabaya Indonesia Department of Biosciences & Medical Engineering Faculty of Engineering UTM Johor Bahru Malaysia Department of Computing Technologies Faculty of Engineering & Technology SRMIST Chennai India Faculty of Computer Science Universitas Dian Nuswantoro Semarang Indonesia

ISBN: (数字)9798350340204

ISBN: (纸本)9798350340211

Due to the rising cases of Covid-19 in the world especially in Malaysia, the impact had been hit hard for many people. Due to this all people must be isolated in their home. It has affected the well-being and working life of millions of people across the world. Due to this disease, the mental health among people has increased significantly for the past 2 years. According to MoH, out of 983 Malaysian students, about 20.4%, 6.6%, and 2.8% are experienced minimal to moderate, marked to severe, and most extreme levels of anxiety, respectively. The main stressors are the remote online teaching, and uncertainty about the future regarding study and career which can affect mental health. Thus, the main objective of this project is to develop a product that may provide different medication methods to its users by helping people who suffer anxiety, stress, and depression. We used aromatherapy, positive quotes, and music therapy in order to release stress. The user can also check his or her pulse rate by only touching the fingerprint through the sensor. The microcontrollers used in this project are Arduino Uno and Arduino Mega to build the project circuit. The experimental results can improve body health, mind and spirit which enhances both physical and emotional health.

关键词： COVID-19 Uncertainty Pandemics Microcontrollers Anxiety disorders Medical treatment Mental health Fingerprint recognition Biomedical imaging IEEE Regions

来源：评论

学校读者我要写书评

暂无评论

A general survey on medical image super-resolution via deep learning

引用

computers in Biology and Medicine 2025年 193卷 110345-110345页

作者： Yu, Miao Xu, Zhenghua Lukasiewicz, Thomas Public Health Sciences and Engineering College Tianjin University of Traditional Chinese Medicine Tianjin China State Key Laboratory of Reliability and Intelligence of Electrical Equipment School of Health Sciences and Biomedical Engineering Hebei University of Technology Tianjin China Tianjin Key Laboratory of Bioelectromagnetic Technology and Intelligent Health School of Health Sciences and Biomedical Engineering Hebei University of Technology China Institute of Logic and Computation TU Wien Vienna Austria Department of Computer Science University of Oxford Oxford United Kingdom

Medical image super-resolution (SR) is a classic regression task in low-level vision. Limited by hardware limitations, acquisition time, low radiation dose, and other factors, the spatial resolution of some medical images is not sufficient. To address this problem, many different SR methods have been proposed. Especially in recent years, medical image SR networks based on deep learning have been vigorously developed. This survey provides a modular and detailed introduction to the key components of medical image SR technology based on deep learning. In this paper, we first introduce the background concepts of deep learning and medical image SR task. Subsequently, we present a comprehensive analysis of the key components from the perspectives of effective architecture, upsampling module, learning strategy, and image quality assessment of medical image SR networks. Furthermore, we focus on the urgent problems that need to be addressed in the medical image SR task based on deep learning. And finally we summarize the trends and challenges of future development. © 2025 Elsevier Ltd

关键词： Damage detection

来源：评论

学校读者我要写书评

暂无评论

Unlocking Real-Time Data Access in Diabetes Management: Toward an Interoperability Model

SSRN

引用

SSRN 2024年

作者： Randine, Pietro Wolff, Miriam Kopperstad Pocs, Matthias Connell, Ian R.O. Cafazzo, Joseph A. Årsand, Eirik Faculty of Science and Technology Department of Computer Science UiT The Arctic University of Norway Tromsø Norway Faculty of Information Technology and Electrical Engineering Department of ICT and Natural Sciences Norwegian University of Science and Technology Trondheim Norway STELAR Security Technology Law Research Hamburg Germany Centre for Digital Therapeutics Toronto General Hospital University Health Network Toronto Canada Institute of Health Policy Management and Evaluation Institute of Biomedical Engineering Department of Computer Science the Rotman School of Management University of Toronto Toronto Canada Institute of Health Policy Management and Evaluation Dalla Lana School of Public Health University of Toronto Toronto Canada UiT The Arctic University of Norway Tromsø Norway

Background: In today's data-driven era, 'Openness' promotes transparency and accessibility. This trend is particularly relevant in new initiatives like the European Health Data Space or when processing health data. This article focuses on Diabetes, which relies on real-time medical device data, such as continuous glucose monitors (CGMs), insulin pumps or hybrid closed-loop systems. These devices provide vital information for monitoring and adjusting treatment plans, making real-time access to their data critical for effective diabetes ***: We explore real-time data access for third-party applications, emphasising primary (treatment) and secondary (research) use. Our exploration includes analysing how Application Programming Interfaces (APIs) contribute to secure data retrieval. Additionally, we investigate the impact of terms of service and copyright law on patient-driven innovation within open-source ***: We evaluated current diabetes medical devices and software solutions in Norway, emphasising their real-time data provision capabilities and API functionality. The study also addresses the legal frameworks relevant to these devices and software, particularly the needs of open-source DIY communities, and proposes an interoperability ***: Our research identified seven diabetes medical devices and nine regulated software solutions, with only one offering a publicly accessible API. This finding underlines a significant lack of real-time data access options. The analysis compares vendor-specific and open-source software, highlighting substantial limitations in interoperability and data accessibility. The DIY solutions, while innovative, presented technical and legal challenges, limiting their practical ***: Diabetes management needing real-time data involves navigating challenges related to security, transparency, and accessibility. We propose a model for interoperability that necessitates regulatory decisio

关键词： Interoperability

来源：评论

学校读者我要写书评

暂无评论

Adapting a Self-Supervised Speech Representation for Noisy Speech Emotion Recognition by Using Contrastive Teacher-Student Learning

Adapting a Self-Supervised Speech Representation for Noisy S...

引用

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

作者： Seong-Gyun Leem Daniel Fulford Jukka-Pekka Onnela David Gard Carlos Busso Department of Electrical and Computer Engineering The University of Texas at Dallas Occupational Therapy and Psychological & Brain Sciences Boston University Department of Biostatistics Harvard T.H. Chan School of Public Health Harvard University Psychology Department San Francisco State University

Studies have shown high performance in the speech emotion recognition (SER) task by fine-tuning a self-supervised speech representation model. Although this model can provide emotionally discriminative embedding in clean conditions, adapting it to a noisy target environment is still required when deployed on real-world applications. For adaptation, it is essential to balance between acquiring new knowledge from noisy speech and keeping the previous knowledge acquired during the pre-training and fine-tuning of the model. Therefore, we propose a contrastive teacher-student learning framework to retrain a self-supervised speech representation model for noisy SER. To keep the knowledge of the original model, we minimize the root mean square error between the clean embeddings from the original SER model and the noisy embeddings from the retrained model. To acquire the discriminative knowledge in the target noisy condition, we also minimize the InfoNCE loss by selecting the corresponding clean embedding as a positive sample and other noisy embeddings with different emotional labels as negative samples. Our experiment with the clean and noisy version of the MSP-Podcast corpus demonstrates that the contrastive teacher-student learning framework can significantly improve the performance of the model only trained with the clean speech in the target noisy condition for all the emotional attributes.

关键词： Adaptation models Emotion recognition Transfer learning Speech recognition Recording Noise measurement Speech processing

来源：评论

学校读者我要写书评

暂无评论

Diversifying Transmission Planning of Wind-Heavy Systems by Incorporating Dynamic Line Rating

Diversifying Transmission Planning of Wind-Heavy Systems by ...

引用

Annual North-American Power Symposium

作者： Sarangan Rajendrane Amirthagunaraj Yogarathnam Tianqiao Zhao Satoshi Endo Visvakumar Aravinthan Al Tamimi Charles R. Yokley Meng Yue Interdisciplinary Science Department Brookhaven National Laboratory Upton NY USA Department of Electrical and Computer Engineering Wichita State University Wichita KS USA Environmental and Climate Sciences Department Brookhaven National Laboratory Upton NY USA Transmission Planning and Policy Sunflower Electric Power Corporation Wichita KS USA

ISBN: (数字)9798331521035

ISBN: (纸本)9798331521042

Expanding electric transmission capacity for renewable energy sources such as wind and solar is essential for decarbonization efforts and meeting increased load demand. This typically requires significant investments in new transmission lines or upgrades to existing ones. However, enhancing the efficiency of current infrastructure can also be highly beneficial. Recently, the use of Dynamic Line Ratings (DLR) has gained significant attention from utilities. DLR allows operators to use lines at their true capacities by considering weather conditions, which can be much higher than the conservative static line ratings. This paper presents a methodology for identifying and implementing DLR on selected lines to enhance capacity and reduce upgrade costs. Line identification is performed using power flow tracing algorithms, where lines carrying more wind power are chosen as candidates for DLR implementation. A criticality score, which is a function of the average wind power flow in the line and the worst-case loading level, is then defined to prioritize the lines that need DLR implementation. The proposed method is tested on a modified system based on the Western Kansas area, with estimated cost savings evaluated. The criticality of these transmission lines during $(n-1)$ contingencies is also evaluated. Additionally, alternative reinvestment strategies for these savings are explored, which show their potential benefits for system security and reliability.

关键词： Wind Renewable energy sources Power transmission lines Costs Wind power generation Low carbon economy Planning Security Reliability North America

来源：评论

学校读者我要写书评

暂无评论

Value of Information in Der Roll-Out

SSRN

引用

SSRN 2022年

作者： Khan, Hafiz Anwar Ullah Unel, Burcin Dvorkin, Yury Department of Electrical and Computer Engineering NYU Tandon School of Engineering New York University NY United States Institute for Policy Integrity NYU School of Law New York University NY United States

Integration of Distributed Energy Resources (DERs) in power systems exacerbates the existing information problems between power utilities and regulators. DER policies oblivious to the trilemma of information asymmetry between power utilities, DER aggregators, and regulators result in distorted price signals to DER investors, economically inefficient DER policies, and socially suboptimal DER roll-out. Therefore, in this paper, we propose a Stackelberg game approach for modeling and analyzing information asymmetry in distribution network information and consumer data between the DER aggregators and the power utilities. The proposed framework is based on hierarchical Single Leader Single Follower (SLSF) games, reformulated as Mathematical Programs with Equilibrium Constraints (MPECs), and solved using the Scholtes’s relaxation technique. Our results, based on the 7-bus Manhattan power network, show that unless the DER aggregators have perfect information about the distribution network characteristics, the welfare along with the realized installed capacity of DERs in the system decreases. Hence, policy interventions to alleviate the rampant information problems are imperative to ensure an optimal DER roll-out. © 2022, The Authors. All rights reserved.

关键词： Energy resources

来源：评论

学校读者我要写书评

暂无评论

Score-PA: Score-based 3D Part Assembly

arXiv

引用

arXiv 2023年

作者： Cheng, Junfeng Wu, Mingdong Zhang, Ruiyuan Zhan, Guanqi Wu, Chao Dong, Hao Department of Electrical and Electronic Engineering Imperial College London London United Kingdom School of CS Peking University Beijing China College of Computer Science and Technology Zhejiang University Hangzhou China Department of Engineering Science University of Oxford Oxford United Kingdom School of Public Affairs Zhejiang University Hangzhou China

Autonomous 3D part assembly is a challenging task in the areas of robotics and 3D computer vision. This task aims to assemble individual components into a complete shape without relying on predefined instructions. In this paper, we formulate this task from a novel generative perspective, introducing the Score-based 3D Part Assembly framework (Score-PA) for 3D part assembly. Knowing that score-based methods are typically time-consuming during the inference stage. To address this issue, we introduce a novel algorithm called the Fast Predictor-Corrector Sampler (FPC) that accelerates the sampling process within the framework. We employ various metrics to assess assembly quality and diversity, and our evaluation results demonstrate that our algorithm outperforms existing state-of-the-art approaches. We release our code at https://***/J-F-Cheng/Score-PA_Score-based-3D-Part-Assembly. Copyright © 2023, The Authors. All rights reserved.

关键词： Machine learning

来源：评论

学校读者我要写书评

暂无评论

Advancing Real-time Pandemic Forecasting Using Large Language Models: A COVID-19 Case Study

arXiv

引用

arXiv 2024年

作者： Du, Hongru Zhao, Jianan Zhao, Yang Xu, Shaochong Lin, Xihong Chen, Yiran Gardner, Lauren M. Yang, Hao Center for Systems Science and Engineering Johns Hopkins University BaltimoreMD United States Department of Civil and Systems Engineering Johns Hopkins University BaltimoreMD United States Mila - Quebec AI Institute MontréalQC Canada Department of Computer Science Universite de Montréal MontréalQC Canada Department of Biostatistics Harvard T.H. Chan School of Public Health BostonMA United States Department of Statistics Harvard University CambridgeMA United States Department of Electrical and Computer Engineering Duke University DurhamNC United States Department of Epidemiology Johns Hopkins Bloomberg School of Public Health BaltimoreMD United States

Forecasting the short-term spread of an ongoing disease outbreak is a formidable challenge due to the complexity of contributing factors, some of which can be characterized through interlinked, multi-modality variables such as epidemiological time series data, viral biology, population demographics, and the intersection of public policy and human behavior. Existing forecasting model frameworks struggle with the multifaceted nature of relevant data and robust results translation, which hinders their performances and the provision of actionable insights for public health decision-makers. Our work introduces PandemicLLM, a novel framework with multi-modal Large Language Models (LLMs) that reformulates real-time forecasting of disease spread as a text reasoning problem, with the ability to incorporate real-time, complex, non-numerical information—such as textual policies and genomic surveillance data—previously unattainable in traditional forecasting models. This approach, through a unique AI-human cooperative prompt design and time series representation learning, encodes multi-modal data for LLMs. By redefining the forecasting process as an ordinal classification task, PandemicLLM yields more robust and trustworthy predictions, facilitating public health decision-making. The model is applied to the COVID-19 pandemic, and trained to utilize textual public health policies, genomic surveillance, spatial, and epidemiological time series data, and is subsequently tested across all 50 states of the U.S. for a duration of 16 weeks. Empirically, PandemicLLM is shown to be a high-performing pandemic forecasting framework that effectively captures the impact of emerging variants and can provide timely and accurate predictions. The proposed PandemicLLM opens avenues for incorporating various pandemic-related data in heterogeneous formats and exhibits performance benefits over existing models. This study illuminates the potential of adapting LLMs and representation learning to enh

关键词： Genome

来源：评论

学校读者我要写书评

暂无评论

Energy Efficiency Optimization for RF Energy Harvesting Relay System 11th

Energy Efficiency Optimization for RF Energy Harvesting Rela...

引用

11th EAI International Conference on Broadband Communications, Networks, and Systems, BROADNETS 2020

作者： Liang, Guangjun Xin, Jianfang Wang, Qun Xia, Lingling Li, Meng Department of Computer Information and Network Security Jiangsu Police Institute Nanjing China Jiangsu Provincial Public Security Department Key Laboratory of Digital Forensics Nanjing China Electrical Engineering School Anhui Polytechnic University Wuhu China

ISBN: (纸本)9783030687366

This paper conducts research on the RF energy harvesting relay network, and proposes an improved energy harvesting relay protocol, which allows the energy harvesting source node to retransmit data to improve the system diversity gain, and constructs energy harvesting slot allocation, subcarrier pairing, and power Optimized model of distributed system energy efficiency. A resource allocation algorithm based on optimal energy efficiency is further proposed. The Dinkelbach method is used to transform the nonlinear programming problem into a linear programming problem. Then, the Hungarian algorithm and the sub-gradient method are used to obtain the iterative algorithm based on energy efficiency optimization. Simulation shows that the algorithm reduces the complexity of the algorithm and has good global convergence. © 2021, ICST Institute for computer Sciences, Social Informatics and Telecommunications engineering.

关键词： Energy harvesting

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：