检索结果-内蒙古大学图书馆

39th Annual AAAI Conference on Artificial Intelligence, AAAI 2025

作者： Ding, Yifan Facciani, Matthew Joyce, Ellen Poudel, Amrit Bhattacharya, Sanmitra Veeramani, Balaji Aguinaga, Sal Weninger, Tim Department of Computer Science and Engineering University of Notre Dame Notre Dame 46556 IN United States AI Center for Excellence Deloitte & Touche LLP New York City 10112 NY United States

ISBN: (纸本)157735897X

Question answering systems are rapidly advancing, but their opaque nature may impact user trust. We explored trust through an anti-monitoring framework, where trust is predicted to be correlated with presence of citations and inversely related to checking citations. We tested this hypothesis with a live question-answering experiment that presented text responses generated using a commercial Chatbot along with varying citations (zero, one, or five), both relevant and random, and recorded if participants checked the citations and their self-reported trust in the generated responses. We found a significant increase in trust when citations were present, a result that held true even when the citations were random;we also found a significant decrease in trust when participants checked the citations. These results highlight the importance of citations in enhancing trust in AI-generated content. Copyright © 2025, Association for the Advancement of Artificial Intelligence (***). All rights reserved.

关键词：

来源：评论

学校读者我要写书评

暂无评论

High-Fidelity and High-Efficiency Talking Portrait Synthesis With Detail-Aware Neural Radiance Fields

引用

IEEE Transactions on Visualization and computer Graphics 2024年 PP卷 PP-PP页

作者： Wang, Muyu Zhao, Sanyuan Dong, Xingping Shen, Jianbing Wuhan University School of Computer Science National Engineering Research Center for Multimedia Software Institute of Artificial Intelligence Hubei Key Laboratory of Multimedia and Network Communication Engineering Wuhan430072 China Beijing Institute of Technology School of Computer Science Beijing China University of Macau State Key Laboratory of Internet of Things for Smart City Department of Computer and Information Science China

In this paper, we propose a novel rendering framework based on neural radiance fields (NeRF) named HH-NeRF that can generate high-resolution audio-driven talking portrait videos with high fidelity and fast rendering. Specifically, our framework includes a detail-aware NeRF module and an efficient conditional super-resolution module. Firstly, a detail-aware NeRF is proposed to efficiently generate a high-fidelity low-resolution talking head, by using the encoded volume density estimation and audio-eye-aware color calculation. This module can capture natural eye blinks and high-frequency details, and maintain a similar rendering time as previous fast methods. Secondly, we present an efficient conditional super-resolution module on the dynamic scene to directly generate the high-resolution portrait with our low-resolution head. Incorporated with the prior information, such as depth map and audio features, our new proposed efficient conditional super resolution module can adopt a lightweight network to efficiently generate realistic and distinct high-resolution videos. Extensive experiments demonstrate that our method can generate more distinct and fidelity talking portraits on high resolution (900 × 900) videos compared to state-of-the-art methods. Our code is available at https://***/muyuWang/HHNeRF. © 1995-2012 IEEE.

关键词： Rendering (computer graphics)

来源：评论

学校读者我要写书评

暂无评论

Direct Data Modulation via Passive RIS: Concept and Implementation of RIS-Backscatter Communications

Direct Data Modulation via Passive RIS: Concept and Implemen...

引用

IEEE Globecom Workshops

作者： Muhammad Miftahul Amri Nguyen Minh Tran Arif Abdul Aziz Je Hyeon Park Dong In Kim Kae Won Choi Department of Electrical and Computer Engineering Sungkyunkwan University Suwon South Korea University Center of Excellence for Intelligent Sensing-IoT Telkom University Bandung Indonesia

Reconfigurable intelligent surface (RIS) has recently garnered attention for its ability to intelligently manipulate the wireless environment. However, the absence of radio frequency (RF) chains has traditionally limited the RIS's ability to transmit information. This article presents a practical approach where the RIS is utilized as the primary information generator, enabling direct information transmission without the need for RF chains. Our proposed method uses the adaptive RIS-backscatter scheme to modulate incident unmodulated electromagnetic (EM) waves. Notably, our main contributions lie in the development of the algorithm itself, followed by comprehensive validations through simulations and experiments, establishing the feasibility of our approach. This work presents a step forward in the field of RIS-based symbiotic radio (SR), enhancing the applicability of conventional RIS structures in practical wireless communication scenarios.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Unsupervised Unlearning of Concept Drift with Autoencoders

Unsupervised Unlearning of Concept Drift with Autoencoders

引用

IEEE Symposium Series on Computational Intelligence (SSCI)

作者： André Artelt Kleanthis Malialis Christos G. Panayiotou Marios M. Polycarpou Barbara Hammer Faculty of Technology Bielefeld University Bielefeld Germany KIOS Research and Innovation Center of Excellence Department of Electrical and Computer Engineering University of Cyprus Nicosia Cyprus

Concept drift refers to a change in the data distribution affecting the data stream of future samples. Consequently, learning models operating on the data stream might become obsolete, and need costly and difficult adjustments such as retraining or adaptation. Existing methods usually implement a local concept drift adaptation scheme, where either incremental learning of the models is used, or the models are completely retrained when a drift detection mechanism triggers an alarm. This paper proposes an alternative approach in which an unsupervised and model-agnostic concept drift adaptation method at the global level is introduced, based on autoencoders. Specifically, the proposed method aims to “unlearn” the concept drift without having to retrain or adapt any of the learning models operating on the data. An extensive experimental evaluation is conducted in two application domains. We consider a realistic water distribution network with more than 30 models in-place, from which we create 200 simulated data sets / scenarios. We further consider an image-related task to demonstrate the effectiveness of our method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Lightweight and Robust Access Control Protocol for IoT-based e-Healthcare Network

引用

IEEE Transactions on Mobile Computing 2025年

作者： Ghaffar, Zahid Kuo, Wen-Chung Mahmood, Khalid Tariq, Tayyaba Shamshad, Salman Das, Ashok Kumar Alenazi, Mohammed J.F. National Yunlin University of Science and Technology Graduate School of Engineering Science and Technology Douliu64002 Taiwan National Yunlin University of Science and Technology Department of Computer Science and Information Engineering Douliu64002 Taiwan National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliu64002 Taiwan The University of Lahore Department of Software Engineering Lahore54590 Pakistan International Institute of Information Technology Center for Security Theory and Algorithmic Research Hyderabad500 032 India Korea University Department of Computer Science and Engineering College of Informatics 145 Anam-ro Seongbuk-gu Seoul02841 Korea Republic of King Saud University College of Computer and Information Sciences Department of Computer Engineering Riyadh Saudi Arabia

Internet of Things (IoT) devices are crucial components in e-healthcare networks. It enables remote patient health monitoring and facilitates seamless communication among medical sensors, wearable devices, and healthcare providers through public communication channels. Despite these advantages, the use of public communication among medical sensors in e-healthcare networks introduces critical challenges, such as vulnerability to impersonation, physical capture, and ephemeral secret leakage, particularly in resource-constrained environments. In recent years, various access control protocols have been developed to mitigate these risks. However, these protocols often fail to ensure robust security while incurring significant communication and computation overhead. To overcome these limitations, we propose a lightweight and robust access control protocol for IoT-based e-healthcare networks using chaotic maps. We propose a novel protocol that integrates a PUF-based mechanism to mitigate the challenges of physical tampering and cloning attacks in e-healthcare networks. It leverages the inherent uniqueness of PUF and enhances security through the high-entropy properties of chaotic maps. We analyze the proposed protocol informally, which confirms that it significantly bolsters efficiency and security. We also validate the security using the Random or Real (RoR) model. Moreover, we verify the security of the proposed protocol using Scyther. These analyses highlight that the proposed protocol offers robust resistance to numerous attacks, such as impersonation, physical capture, and ephemeral secret leakage. Moreover, we also compare it with existing and relevant protocols. The comparative analysis showcases its superior performance. Notably, the proposed authentication protocol significantly reduces 46.84% computational overhead and decreases 31.30% communication overhead, underscoring its enhanced performance and resource efficiency. © 2002-2012 IEEE.

关键词： Authentication

来源：评论

学校读者我要写书评

暂无评论

Long-Term Unit Commitment with Combined-Cycle Units

Long-Term Unit Commitment with Combined-Cycle Units

引用

Power Tech Conference

作者： Lysandros Tziovani Markos Asprou Irina Ciornei Panayiotis Kolios Lenos Hadjidemetriou Antonis Lazari Rogiros Tapakis Stelios Timotheou Department of Electrical and Computer Engineering KIOS Research and Innovation Center of Excellence University of Cyprus Nicosia Cyprus Transmission System Operator Cyprus Nicosia Cyprus

The performance of long-term power system studies are vital to evaluate the system reliability and efficiency under an increasing penetration of renewable energy sources (RES). This work develops a long-term unit commitment (UC) model considering combined-cycle (CC) units to enable the performance of annual studies in power systems. Specifically, a simplified configuration-based model of the CC units is used that decreases the number of configurations to reduce the computational complexity. The considered UC problem is formulated as a mixed-integer linear program (MILP), which is intractable when a long-term horizon is used. To make the problem tractable, a rolling horizon approach is proposed to solve the long-term MILP problem, generating high-quality approximate solutions. The proposed approach is applied to a real isolated power system and an annual study is carried out to examine the impact of an increasing RES penetration on the system operation.

关键词：

来源：评论

学校读者我要写书评

暂无评论

FixCyprus: Crowdsourcing Smartphone Imagery Data For Managing Road Safety Hazards

FixCyprus: Crowdsourcing Smartphone Imagery Data For Managin...

引用

International Conference on Mobile Data Management

作者： Georgios Christou Andreas Georgiou Christos Laoudias Aristotelis Savva Christos G. Panayiotou KIOS Center of Excellence University of Cyprus Cyprus Public Works Department Ministry of Transport Communications and Works Cyprus Department of Electrical and Computer Engineering University of Cyprus Cyprus

In this demonstration paper, we present FixCyprus, which is a cost-effective crowdsourcing service for road transportation authorities in Cyprus to gather information and manage defects and incidents on the road network and surrounding infrastructure (e.g., pavements, lighting, drinking water pipes, etc.). The production service, which includes a lightweight and user-friendly mobile application for sharing image-annotated incident reports, is already operating nationwide for six months providing significant budget savings by reducing field inspections and the use of expensive equipment. We will demonstrate FixCyprus using two modes: i) Interactive mode, where attendees will be able to create and submit their own dummy incident reports and see the end-to-end processing flow in a test environment and ii) Trace-driven mode, where attendees will be able to visualize a large number of synthetic reports, see the workload for manually managing them, and explore enhancements that are underway for automating some of the underlying tasks using machine learning.

关键词：

来源：评论

学校读者我要写书评

暂无评论

HealthEdge: A Machine Learning-Based Smart Healthcare Framework for Prediction of Type 2 Diabetes in an Integrated IoT, Edge, and Cloud Computing System 14

HealthEdge: A Machine Learning-Based Smart Healthcare Framew...

引用

14th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2023 and The 6th International Conference on Emerging Data and Industry 4.0, EDI40 2023

作者： Hennebelle, Alain Materwala, Huned Ismail, Leila Melbourne Australia Research Laboratory Department of Computer Science and Software Engineering College of Information Technology United Arab Emirates University United Arab Emirates National Water and Energy Center United Arab Emirates University United Arab Emirates Lab School of Computing and Information Systems The University of Melbourne Australia

Diabetes Mellitus has no permanent cure to date and is one of the leading causes of death globally. The alarming increase in diabetes calls for the need to take precautionary measures to avoid/predict the occurrence of diabetes. This paper proposes HealthEdge, a machine learning-based smart healthcare framework for type 2 diabetes prediction in an integrated IoT-edge-cloud computing system. Numerical experiments and comparative analysis were carried out between the two most used machine learning algorithms in the literature, Random Forest (RF) and Logistic Regression (LR), using two real-life diabetes datasets. The results show that RF predicts diabetes with 6% more accuracy on average compared to LR. © 2023 Elsevier B.V.. All rights reserved.

关键词： Edge computing

来源：评论

学校读者我要写书评

暂无评论

Comparison of Multi-Phase Power Converters and Power Delivery Networks for Next-Generation Space Architectures

Comparison of Multi-Phase Power Converters and Power Deliver...

引用

IEEE Conference on Aerospace

作者： Nicholas Franconi Thomas Cook Christopher Wilson Alan D. George NASA Goddard Space Flight Center Science Data Processing Branch Code 587 Software Engineering Division Department of Electrical and Computer Engineering NSF Center for Space High-Performance and Resilient Computing (SHREC) University of Pittsburgh

Next-generation spacecraft developers are earnestly investigating the application of artificial intelligence (AI) algorithms onboard to enable new mission concepts for space exploration and science. However, the current generation of radiation-hardened processors are inferior compared to commercial-off-the-shelf alternatives in terms of the computational performance required by modern AI applications. To address this disparity, space-system designers have started employing novel radiation-tolerant architectures combining both commercial and radiation-hardened components to mitigate radiation effects at a system level. Unfortunately, developing single-board computers with radiation-tolerant, high-performance processors is challenging because designers must balance the sparce selection of radiation-hardened power converters and high-reliability decoupling capacitors with SmallSat/CubeSat area constraints and limited thermal conduction. Consequently, the next-generation of space processors, including the AMD-Xilinx Versal Adaptive Compute Acceleration Platform require demanding power solutions capable of supplying core rails with 0.8V ± 18mV and currents up to 150 A. In this paper, we present a multifaceted analysis of the power system and decoupling network for a future Versal-based design. We developed preliminary power estimates based on expected processor and FPGA resource utilization for common AI processing applications. These estimates drive the power system requirements and a comparative analysis of single-phase integrated converters and multi-phase discrete converters for high-current FPGA supplies. We develop a tradespace between the number of phases, input voltage, load current, switching frequency, power efficiency, and printed circuit board area. Finally, we design and simulate four power delivery networks based on commercial, high-reliability, and flight-qualified capacitors to compare the efficacy of 0201 decoupling capacitors in flight missions.

关键词： Rails Program processors Capacitors Voltage Power systems Resource management Artificial intelligence

来源：评论

学校读者我要写书评

暂无评论

Depthwise Over-Parameterized CNN for Voxel Human Pose Classification

Depthwise Over-Parameterized CNN for Voxel Human Pose Classi...

引用

International Seminar on Intelligent Technology and Its Applications (ISITIA)

作者： Oddy Virgantara Putra Riandini Eko Mulyanto Yuniarno Mauridhi Hery Purnomo Department of Electrical Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia Department of Electrical Engineering Politeknik Negeri Jakarta Depok Indonesia Department of Electrical Engineering Department of Computer Engineering Institut Teknologi Sepuluh Nopember Surabaya Indonesia University Center of Excellence on Artificial Intelligence for Healthcare and Society (UCE AIHeS)

Light Detection and Ranging (LiDAR) capture objects and backgrounds using a laser sensor, producing unstructured points in 3-dimensional called point clouds (PC). However, captured human pose PC is limited partially due to the LiDAR scan. The only information in the scanned area exists. Due to the inadequacy of PC data, it is challenging to classify such data. In this paper, we proposed a solution to overcome those problems. It is a novel depthwise over-parameterized (DOConv) embedded into a simple CNN. The raw PCs are converted into a 3D voxel in the input layer. In the convolutional (Conv) layer, the regular Conv is substituted with a-three layered DOConv. Lastly, to assess the performance of our model, we commence an evaluation with multiple classifier algorithms in ModelNet40 and our human pose dataset. Accuracy, loss, recall, precision, F1-scores, and Geometric mean are engaged as performance indicators. To sum up, our model outperformed all compared classifiers in accuracy for the primary dataset by 87.06 % and ModelNet40 by 68.68%.

关键词：

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：