检索结果-内蒙古大学图书馆

Continual Learning through Human-Robot Interaction: Human Perceptions of a Continual Learning Robot in Repeated Interactions

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Ayub, Ali De Francesco, Zachary Holthaus, Patrick Nehaniv, Chrystopher L. Dautenhahn, Kerstin Concordia University MontrealQCH3G 1M8 Canada Department of Systems Design Engineering University of Waterloo WaterlooONN2L 3G1 Canada Department of Electrical and Computer Engineering University of Waterloo WaterlooONN2L 3G1 Canada School of Physics Engineering and Computer Science University of Hertfordshire HertfordshireAL10 9AB United Kingdom

For long-term deployment in dynamic real-world environments, assistive robots must continue to learn and adapt to their environments. Researchers have developed various computational models for continual learning (CL) that can allow robots to continually learn from limited training data, and avoid forgetting previous knowledge. While these CL models can mitigate forgetting on static, systematically collected datasets, it is unclear how human users might perceive a robot that continually learns over multiple interactions with them. In this paper, © 2023, CC BY.

关键词： Adversarial machine learning

Mixture of Experts for Network Optimization: A Large Language Model-enabled Approach

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Du, Hongyang Liu, Guangyuan Lin, Yijing Niyato, Dusit Kang, Jiawen Xiong, Zehui Kim, Dong In The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore The State Key Laboratory of Networking and Switching Technology Beijing University of Posts and Telecommunications Beijing100876 China The School of Automation Guangdong University of Technology Key Laboratory of Intelligent Information Processing and System Integration of IoT Ministry of Education Guangzhou510006 China Guangdong-HongKong-Macao Joint Laboratory for Smart Discrete Manufacturing Guangzhou510006 China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore487372 Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Optimizing various wireless user tasks poses a significant challenge for networking systems because of the expanding range of user requirements. Despite advancements in Deep Reinforcement Learning (DRL), the need for customized optimization tasks for individual users complicates developing and applying numerous DRL models, leading to substantial computation resource and energy consumption and can lead to inconsistent outcomes. To address this issue, we propose a novel approach utilizing a Mixture of Experts (MoE) framework, augmented with Large Language Models (LLMs), to analyze user objectives and constraints effectively, select specialized DRL experts, and weigh each decision from the participating experts. Specifically, we develop a gate network to oversee the expert models, allowing a collective of experts to tackle a wide array of new tasks. Furthermore, we innovatively substitute the traditional gate network with an LLM, leveraging its advanced reasoning capabilities to manage expert model selection for joint decisions. Our proposed method reduces the need to train new DRL models for each unique optimization problem, decreasing energy consumption and AI model implementation costs. The LLM-enabled MoE approach is validated through a general maze navigation task and a specific network service provider utility maximization task, demonstrating its effectiveness and practical applicability in optimizing complex networking systems. © 2024, CC BY.

关键词： Reinforcement learning

Rethinking Wireless Communication Security in Semantic Internet of Things

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Du, Hongyang Wang, Jiacheng Niyato, Dusit Kang, Jiawen Xiong, Zehui Guizani, Mohsen Kim, Dong In The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Automation Guangdong University of Technology China The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore Machine Learning Department Mohamed Bin Zayed University of Artificial Intelligence Abu Dhabi United Arab Emirates The Department of Electrical and Computer Engineering Sungkyunkwan University Korea Republic of

Semantic communication is an important participant in the next generation of wireless communications. Enabled by this novel paradigm, the conventional Internet-of-Things (IoT) is evolving toward the semantic IoT (SIoT) to achieve significant system performance improvements. However, traditional wireless communication security techniques for bit transmission cannot be applied directly to the SIoT that focuses on semantic information transmission. One key reason is the lack of new security performance indicators. Thus, we have to rethink the wireless communication security in the SIoT. As such, in the paper, we analyze and compare classical security techniques, i.e., physical layer security, covert communications, and encryption, from the perspective of semantic information security. We highlight the differences among these security techniques when applied to the SIoT. Novel performance indicators such as semantic secrecy outage probability (for physical layer security techniques) and detection error expectation (for covert communication techniques) are proposed. Considering that semantic communications can raise new security issues, we then review attack and defense methods at the semantic level. Finally, we present several promising directions for future secure SIoT research. © 2022, CC BY.

关键词： Semantics

Economics of Semantic Communication System: An Auction Approach

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Liew, Zi Qin Du, Hongyang Yang, Wei Lim, Bryan Xiong, Zehui Niyato, Dusit Miao, Chunyan Kim, Dong In Alibaba-NTU Singapore Joint Research Institute Nanyang Technological Univerity Singapore The School of Computer Science and Engineering The Energy Research Institute NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore The Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore The School of Computer Science and Engineering Nanyang Technological University Singapore639798 Singapore Nanyang Technological University Singapore639798 Singapore The Department of Electrical and Computer Engineering Sungkyunkwan University Suwon16419 Korea Republic of

Semantic communication technologies enable wireless edge devices to communicate effectively by transmitting semantic meaning of data. Edge components, such as vehicles in next-generation intelligent transport systems, use well-trained semantic models to encode and decode semantic information extracted from raw and sensor data. However, the limitation in computing resources makes it difficult to support the training process of accurate semantic models on edge devices. As such, edge devices can buy the pretrained semantic models from semantic model providers, which is called "semantic model trading". Upon collecting semantic information with the semantic models, the edge devices can then sell the extracted semantic information, e.g., information about urban road conditions or traffic signs, to the interested buyers for profit, which is called "semantic information trading". To facilitate both types of the trades, effective incentive mechanisms should be designed. Thus, in this paper, we propose a hierarchical trading system to support both semantic model trading and semantic information trading jointly. The proposed incentive mechanism helps to maximize the revenue of semantic model providers in the semantic model trading, and effectively incentivizes model providers to participate in the development of semantic communication systems. For semantic information trading, our designed auction approach can support the trading between multiple semantic information sellers and buyers, while ensuring individual rationality, incentive compatibility, and budget balance, and moreover, allowing them achieve higher utilities than the baseline method. Copyright © 2022, The Authors. All rights reserved.

关键词： Commerce

"It Feels Like Being Locked in A Cage": Understanding Blind or Low Vision Streamers' Perceptions of Content Curation Algorithms

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Rong, Ethan Z. Zhou, Mo Morgana Lu, Zhicong Fan, Mingming Computational Media and Arts Thrust The Hong Kong University of Science and Technology Guangzhou China Department of Electrical Engineering City University of Hong Kong China Department of Computer Science City University of Hong Kong China Division of Integrative Systems and Design Department of Computer Science and Engineering The Hong Kong University of Science and Technology China

Blind or low vision (BLV) people were recently reported to be live streamers on the online platforms that employed content curation algorithms. Recent research uncovered algorithm biases suppressing the content created by marginalized populations. However, little is known about the effects of the algorithms adopted by live streaming platforms on BLV streamers and how they, as a marginalized population, perceive the effects of the algorithms. We interviewed BLV streamers (N=19) of Douyin - a popular live stream platform in China - to understand their perceptions of algorithms, perceived challenges, and mitigation strategies. Our findings show the perceived factors contributing to disadvantages under algorithmic evaluation of BLV streamers' content (e.g., issues with filming and timely interaction with viewers) and perceived algorithmic suppression (e.g., content not amplified to sighted users but suppressed within the BLV community). Their mitigation strategies (e.g., not watching other BLV streamers' shows) tended to be passive. We discuss design considerations to design a more inclusive and fair live streaming platform. © 2022, CC BY-NC-ND.

关键词： Social networking (online)

District-scale surface temperatures generated from high-resolution longitudinal thermal infrared images

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Lin, Subin Ramani, Vasantha Martin, Miguel Arjunan, Pandarasamy Chong, Adrian Biljecki, Filip Ignatius, Marcel Poolla, Kameshwar Miller, Clayton Berkeley Education Alliance for Research in Singapore CREATE Tower 1 Create 6 Way 138602 Singapore Robert Bosch Centre for Cyber-physical Systems Indian Institute of Science Karnataka Bengaluru560012 India Department of the Built Environment College of Design and Engineering National University of Singapore 4 Architecture Drive 117566 Singapore Department of Electrical Engineering and Computer Sciences University of California BerkeleyCA United States Department of Architecture College of Design and Engineering National University of Singapore 4 Architecture Drive 117566 Singapore

This paper describes a dataset collected by infrared thermography, a non-contact, non-intrusive technique to acquire data and analyze the built environment in various aspects. While most studies focus on the city and building scales, an observatory installed on a rooftop provides high temporal and spatial resolution observations with dynamic interactions on the district scale. The rooftop infrared thermography observatory with a multi-modal platform capable of assessing a wide range of dynamic processes in urban systems was deployed in Singapore. It was placed on the top of two buildings that overlook the outdoor context of the National University of Singapore campus. The platform collects remote sensing data from tropical areas on a temporal scale, allowing users to determine the temperature trend of individual features such as buildings, roads, and vegetation. The dataset includes 1,365,921 thermal images collected on average at approximately 10-second intervals from two locations during ten months. © 2023, CC BY-SA.

关键词： Observatories

Establish and validate the reliability of predictive models in bone mineral density by deep learning as examination tool for women

学校读者我要写书评

暂无评论

Osteoporosis International 2024年第1期35卷 129-141页

作者： Hung, Wei- Chieh Lin, Yih-Lon Cheng, Tien-Tsai Chin, Wei-Leng Tu, Li-Te Chen, Chih-Kui Yang, Chih-Hui Wu, Chih-Hsing Department of Family Medicine and Community Medicine E-Da Hospital I-Shou University Kaohsiung Taiwan School of Medicine for International Students College of Medicine I-Shou University School Kaohsiung Taiwan Institute of Biotechnology and Chemical Engineering I-Shou University Kaohsiung Taiwan Department of Computer Science and Information Engineering National Yunlin University of Science and Technology Douliu Taiwan Department of Internal Medicine Division of Rheumatology Allergy and Immunology Kaohsiung Chang Gung Memorial Hospital and School of Medicine College of Medicine Chang Gung University Taoyuan Taiwan Enterprise Resource Planning Technical Support and Research and Design Department InfoChamp Systems Corporation Kaohsiung Taiwan Departments of Biological Science and Technology I-Shou University Kaohsiung Taiwan Institute of Gerontology College of Medicine National Cheng Kung University Tainan Taiwan Department of Family Medicine National Cheng Kung University Hospital College of Medicine National Cheng Kung University Tainan Taiwan

Summary: While FRAX with BMD could be more precise in estimating the fracture risk, DL-based models were validated to slightly reduce the number of under- and over-treated patients when no BMD measurements were available. The validated models could be used to screen for patients at a high risk of fracture and osteoporosis. Purpose: Fracture risk assessment tool (FRAX) is useful in classifying the fracture risk level, and precise prediction can be achieved by estimating both clinical risk factors and bone mineral density (BMD) using dual X-ray absorptiometry (DXA). However, DXA is not frequently feasible because of its cost and accessibility. This study aimed to establish the reliability of deep learning (DL)-based alternative tools for screening patients at a high risk of fracture and osteoporosis. Methods: Participants were enrolled from the National Bone Health Screening Project of Taiwan in this cross-sectional study. First, DL-based models were built to predict the lowest T-score value in either the lumbar spine, total hip, or femoral neck and their respective BMD values. The Bland–Altman analysis was used to compare the agreement between the models and DXA. Second, the predictive model to classify patients with a high fracture risk was built according to the estimated BMD from the first step and the FRAX score without BMD. The performance of the model was compared with the classification based on FRAX with BMD. Results: Approximately 10,827 women (mean age, 65.4 ± 9.4 years) were enrolled. In the prediction of the lumbar spine BMD, total hip BMD, femoral neck BMD, and lowest T-score, the root-mean-square error (RMSE) was 0.099, 0.089, 0.076, and 0.68, respectively. The Bland–Altman analysis revealed a nonsignificant difference between the predictive models and DXA. The FRAX score with femoral neck BMD for major osteoporotic fracture risk was 9.7% ± 6.7%, whereas the risk for hip fracture was 3.3% ± 4.6%. Comparison between the classification of FRAX with and wi

关键词： Bone health Bone mineral density Classification model FRAX Model validation Prediction model

AI Enabled Ensemble Deep Learning Method for Automated Sensing and Quantification of DNA Damage in Comet Assay

学校读者我要写书评

暂无评论

ECS Sensors Plus 2023年第1期2卷 011401-011401页

作者： Mehta, Prateek Namuduri, Srikanth Barbe, Lise Lam, Stephanie Faghihmonzavi, Zohreh Kamat, Vivek Finkbeiner, Steven Bhansali, Shekhar Electrical Computer Engineering Florida International University Miami 33174 FL United States Center for Systems and Therapeutics Gladstone Institutes San Francisco 94158 CA United States Departments of Neurology University of California San Francisco San Francisco 94158 CA United States

Comet assay is a widely used technique to assess and quantify DNA damage in individual cells. Recently, researchers have applied various deep learning techniques to automate the analysis of comet assay. Image analysis using deep learning allows combining multiple parameters of images and performing computation at a pixel level to provide quantifiable information about the comets. The current deep learning analysis algorithms use a single neural network as a standard method, which relies on many comet images and prone to high variance in predictions. Here, we propose a new ensemble model consisting of a collection of deep learning networks with different configurations and different initial random weights trained on the same dataset to calculate one weighted prediction for DNA damage quantification. To develop this model, we curated a trainable comet assay image dataset consisting of1309 images with 9204 extracted features of cell head and tail length, area, etc With the proposed method we could achieve significantly higher accuracy (R2 = 89.3%, compared to 74% with the standard single neural network as reported in data published by M. D. Zeiler and R Fergus (European conference on computer vision, pp. 818-833 2014). Furthermore, deep regression with the proposed architecture produced much more reliable and accurate results than conventional method. © 2023 The Author(s). Published on behalf of The Electrochemical Society by IOP Publishing Limited

关键词：

A LEARNING AND CONTROL PERSPECTIVE FOR MICROFINANCE

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Kurniawan, Christian Deng, Xiyu Chakraborty, Adhiraj Gueye, Assane Chen, Niangjun Nakahira, Yorie Department of Electrical and Computer Engineering Carnegie Mellon University PittsburghPA United States Carnegie Mellon University Silicon Valley CA United States Carnegie Mellon University Africa Kigali Rwanda Information Systems Technology and Design Singapore University of Technology and Design Singapore

Microfinance, despite its significant potential for poverty reduction, is facing sustainability hardships due to high default rates. Although many methods in regular finance can estimate credit scores and default probabilities, these methods are not directly applicable to microfinance due to the following unique characteristics: a) under-explored (developing) areas such as rural Africa do not have sufficient prior loan data for microfinance institutions (MFIs) to establish a credit scoring system;b) microfinance applicants may have difficulty providing sufficient information for MFIs to accurately predict default probabilities;and c) many MFIs use group liability (instead of collateral) to secure repayment. Here, we present a novel control-theoretic model of microfinance that accounts for these characteristics. We construct an algorithm to learn microfinance decision policies that achieve financial inclusion, fairness, social welfare, and sustainability. We characterize the convergence conditions to Pareto-optimum and the convergence speeds. We demonstrate, in numerous real and synthetic datasets, that the proposed method accounts for the complexities induced by group liability to produce robust decisions before sufficient loans are given to establish credit scoring systems and for applicants whose default probability cannot be accurately estimated due to missing information. To the best of our knowledge, this paper is the first to connect microfinance and control theory. We envision that the connection will enable safe learning and control techniques to help modernize microfinance and alleviate poverty. Copyright © 2022, The Authors. All rights reserved.

关键词： Finance