检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Pushp, Durgakant Xu, Junhong Chen, Zheng Liu, Lantao The Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN47408 United States

Bounded rational agents often make decisions by evaluating a finite selection of choices, typically derived from a reference point termed the ‘default policy,’ based on previous experience. However, the inherent rigidity of the static default policy presents significant challenges for agents when operating in unknown environment, that are not included in agent’s prior knowledge. In this work, we introduce a context-generative default policy that leverages the region observed by the robot to predict unobserved part of the environment, thereby enabling the robot to adaptively adjust its default policy based on both the actual observed map and the imagined unobserved map. Furthermore, the adaptive nature of the bounded rationality framework enables the robot to manage unreliable or incorrect imaginations by selectively sampling a few trajectories in the vicinity of the default policy. Our approach utilizes a diffusion model for map prediction and a sampling-based planning with B-spline trajectory optimization to generate the default policy. Extensive evaluations reveal that the context-generative policy outperforms the baseline methods in identifying and avoiding unseen obstacles. Additionally, real-world experiments conducted with the Crazyflie drones demonstrate the adaptability of our proposed method, even when acting in environments outside the domain of the training distribution. © 2024, CC BY-NC-SA.

关键词：

来源：评论

学校读者我要写书评

暂无评论

C2DA: Contrastive and Context-aware Domain Adaptive Semantic Segmentation

arXiv

引用

arXiv 2024年

作者： Khan, Md Al-Masrur Chen, Zheng Liu, Lantao Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN47408 United States

Unsupervised domain adaptive semantic segmentation (UDA-SS) aims to train a model on the source domain data (e.g., synthetic) and adapt the model to predict target domain data (e.g. real-world) without accessing target annotation data. Most existing UDA-SS methods only focus on inter-domain knowledge to mitigate the data-shift problem. However, learning the inherent structure of the images and exploring the intrinsic pixel distribution of both domains are ignored;which prevents the UDA-SS methods from producing satisfactory performance like the supervised learning. Moreover, incorporating contextual knowledge is also often overlooked. Considering these issues, in this work, we propose a UDA-SS framework that learns both intra-domain and context-aware knowledge. To learn the intra-domain knowledge, we incorporate contrastive loss in both domains, which pulls pixels of similar classes together and pushes the rest away, facilitating intra-imagepixel-wise correlations. To learn context-aware knowledge, we modify the mixing technique by leveraging contextual dependency among the classes to learn context-aware knowledge. Moreover, we adapt the Mask Image Modeling (MIM) technique to properly use context clues for robust visual recognition, using limited information about the masked images. Comprehensive experiments validate that our proposed method improves the state-of-the-art UDA-SS methods by a margin of 0.51% mIoU and 0.54% mIoU in the adaptation of GTA-V→Cityscapes and Synthia→Cityscapes, respectively. We open-source our C2DA code. Code link: ***/Masrur02/C-Squared-DA © 2024, CC BY.

关键词： Semantic Segmentation

来源：评论

学校读者我要写书评

暂无评论

Visual-Geometry GP-based Navigable Space for Autonomous Navigation

arXiv

引用

arXiv 2024年

作者： Ali, Mahmoud Pushp, Durgkant Chen, Zheng Liu, Lantao The Luddy School of Informatics Computing and Engineering Indiana University BloomingtonIN47408 United States

Autonomous navigation in unknown environments is challenging and demands the consideration of both geometric and semantic information in order to parse the navigability of the environment. In this work, we propose a novel space modeling framework, Visual-Geometry Sparse Gaussian Process (VG-SGP), that simultaneously considers semantics and geometry of the scene. Our proposed approach can overcome the limitation of visual planners that fail to recognize geometry associated with the semantic and the geometric planners that completely overlook the semantic information which is very critical in realworld navigation. The proposed method leverages dual Sparse Gaussian Processes in an integrated manner;the first is trained to forecast geometrically navigable spaces while the second predicts the semantically navigable areas. This integrated model is able to pinpoint the overlapping (geometric and semantic) navigable space. The simulation and real-world experiments demonstrate that the ability of the proposed VG-SGP model, coupled with our innovative navigation strategy, outperforms models solely reliant on visual or geometric navigation algorithms, highlighting a superior adaptive behavior. We provided a demonstration video1 and open-sourced our code 2 © 2024, CC BY.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Exploring Design Recommendations for Promoting Brain Health, ADRD Health Literacy, and Participation in clinical ADRD trials in Older African American/Black Adults

引用

Proceedings of the ACM on Human-Computer Interaction 2025年第2期9卷 1-26页

作者： Theisz, Alec Andrew Bosco, Cristina Torres, John Osorio Shojaei, Fereshtehossadat Lin, Jenny Cureton, Bianca Himes, Anna K. Jessup, Nenette M. Barnes, Priscilla A. Lu, Yvonne Hendrie, Hugh C. Hill, Carl V. Shih, Patrick C. Luddy School of Informatics Computing and Engineering Indiana University United States School of Nursing Indiana University United States Alzheimer’s Association United States

Alzheimer’s Disease and related dementia (ADRD) is prevalent in one in nine individuals age 65 or above, and it has a 65% higher risk of incidence for African American/Black adults. With an aging population in the United States and persisting healthcare inequities for African American/Black adults, our research aims to explore design requirements of a digital health platform for delivering culturally relevant content that informs African Americans/Black adults (45 years and older) about brain health and participation in clinical ADRD studies. We conducted seven focus groups (n = 44) to collect information on facilitators and barriers to brain health literacy and participation in clinical ADRD research, followed by seven participatory design workshops (n = 44) to collaboratively develop solutions for improving brain health literacy and participation in clinical ADRD research. Our findings provide insights into incorporating community into accessible, technological design for reducing brain health disparities for African American/Black adults. © 2025 Copyright held by the owner/author(s).

关键词： mHealth

来源：评论

学校读者我要写书评

暂无评论

Generating Descriptive Explanations of Machine Learning Models Using LLM

Generating Descriptive Explanations of Machine Learning Mode...

引用

IEEE International Conference on Big Data

作者： Andrew Pang Hyeju Jang Shiaofen Fang Horace Greeley High School NY Luddy School of Informatics Computing and Engineering Indiana University Indianapolis

ISBN: (数字)9798350362480

ISBN: (纸本)9798350362497

Machine learning algorithms play a pivotal role in a wide range of Artificial Intelligence (AI) applications. Explaining the results and behavior of a machine learning model, however, remains a challenge. In this paper, we present a new approach to the explanation of machine learning models using a large language model (LLM). In this work, we seek natural language descriptions of the behavioral patterns of a machine learning model by a combination of prompting and model sampling. A subspace sampling technique is developed to generate ML model outputs using partial features in a user defined space. A projective visualization method is employed to guide the sampling process, including user-directed interactive sampling and feature-based sampling, so that an optimal amount of information can be provided to the LLM to ensure accurate and concise natural language explanations. Two public datasets, a student performance dataset and a weather dataset, were used to test our approach under various conditions.

关键词： Visualization Systematics Machine learning algorithms Large language models Natural languages Machine learning Big Data Data models Human in the loop Meteorology

来源：评论

学校读者我要写书评

暂无评论

QR-Code Pixelated Antenna with Multi-Factor Authentication for Wireless and Security Applications 1

QR-Code Pixelated Antenna with Multi-Factor Authentication f...

引用

1st International Conference on Microwave, Antenna and Communication, MAC 2023

作者： Basherlou, Haleh Jahanbakhsh Ullah, Atta Parchin, Naser Ojaroudi See, Chan Hwang Abd-Alhameed, Raed A. School of Computing Engineering and the Built Environment Edinburgh Napier University Edinburgh United Kingdom University of Bradford Faculty of Engineering and Informatics BradfordBD7 1DP United Kingdom

ISBN: (纸本)9798350303001

Quick response (QR) codes can be used for antenna applications, in addition to being used as information-sharing and security devices. QR-Code pixelated antennas present a game-changing solution for wireless communication and security applications. Their ability to facilitate efficient data transfer, compact form factor, compatibility with existing infrastructure, and enhanced security measures make them highly desirable for a wide range of applications, ranging from consumer electronics to industrial systems. The aim of this paper is to demonstrate the feasibility and success of QR code structures as antennas in wireless communication applications. It is designed on a low-cost FR4 substrate board. The suggested antenna configuration contains a modified coaxial-fed patch resonator with a QR pixelated configuration and a full ground plane providing a broad bandwidth of 8 to 9.6 GHz. The critical characteristics have been examined in simulations and sufficient return loss, radiation gain, levels are all achievable with the planned compact QR antenna design. © 2023 IEEE.

关键词： Data transfer

来源：评论

学校读者我要写书评

暂无评论

Multi/Broad-Band Phased Array Enabling Capacity and Physical-Layer Security in Cyberspace Mobile Communications for 5G and beyond 1

Multi/Broad-Band Phased Array Enabling Capacity and Physical...

引用

1st International Conference on Microwave, Antenna and Communication, MAC 2023

作者： Ullah, Atta Basherlou, Haleh Jahanbakhsh Parchin, Naser Ojaroudi See, Chan Hwang Abd-Alhameed, Raed A. University of Bradford Faculty of Engineering and Informatics BradfordBD7 1DP United Kingdom School of Computing Engineering and the Built Environment Edinburgh Napier University Edinburgh United Kingdom

ISBN: (纸本)9798350303001

Broadband/multiband phased array antennas with wide-scan and smart beam-steering are desirable to meet the capacity and security requirements of 5G and beyond. This paper discusses the characteristics of a new beam-steerable phased array design having broadband/multiband function for 5G and beyond communications. The discussion is focused on smartphones, due to their small size and complexity. The design procedure is straightforward and accomplished on a mainboard of future smart handheld devices. The introduced phased array design involves eight Yagi-dipole resonators with a 1× 8 linear form. The resonators have small sizes with discrete feedings. For -10 dB, the design represents dual broad bands including 22-33 GHz and 38-65 GHz covering multiple bands in the 5G and beyond spectrums. © 2023 IEEE.

关键词： Resonators

来源：评论

学校读者我要写书评

暂无评论

Knowledge Enhanced Digital Objects: a Data Lake Approach

Knowledge Enhanced Digital Objects: a Data Lake Approach

引用

Cluster, Cloud and Internet computing Workshops (CCGridW), IEEE/ACM International Symposium on

作者： Yu Luo Beth Plale School of Informatics Computing and Engineering Indiana University Bloomington IN USA

Open science is gaining traction as a means to bring greater value to the products of research beyond the published manuscript - that is, to make data and software more accessible and usable. The FAIR principles [1] are a significant step forward in defining the characteristics needed of data for it to be shared, used, and reused.

关键词：

来源：评论

学校读者我要写书评

暂无评论

CryptoQFL: Quantum Federated Learning on Encrypted Data

CryptoQFL: Quantum Federated Learning on Encrypted Data

引用

Quantum computing and engineering (QCE), IEEE International Conference on

作者： Cheng Chu Lei Jiang Fan Chen Luddy School of Informatics Computing and Engineering Indiana University Bloomington IN

Recent advancements in Quantum Neural Networks (QNNs) have demonstrated theoretical and experimental performance superior to their classical counterparts in a wide range of applications. However, existing centralized QNNs cannot solve many real-world problems because collecting large amounts of training data to a common public site is time-consuming and, more importantly, violates data privacy. Federated Learning (FL) is an emerging distributed machine learning framework that allows collaborative model training on decentralized data residing on multiple devices without breaching data privacy. Some initial attempts at Quantum Federated Learning (QFL) either only focus on improving the QFL performance or rely on a trusted quantum server that fails to preserve data privacy. In this work, we propose CryptoQFL, a QFL framework that allows distributed QNN training on encrypted data. CryptoQFL is (1) secure, because it allows each edge to train a QNN with local private data, and encrypt its updates using quantum homomorphic encryption before sending them to the central quantum server; (2) communication-efficient, as CryptoQFL quantize local gradient updates to ternary values, and only communicate non-zero values to the server for aggregation; and (3) computation-efficient, as CryptoQFL presents an efficient quantum aggregation circuit with significantly reduced latency compared to state-of-the-art approaches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Towards Highly Compressed CNN Models for Human Activity Recognition in Wearable Devices 26

Towards Highly Compressed CNN Models for Human Activity Reco...

引用

26th IEEE Signal Processing: Algorithms, Architectures, Arrangements, and Applications, SPA 2023

作者： Gkountelos, Dimitrios Kokhazadeh, Milad Bournas, Charalampos Keramidas, Georgios Kelefouras, Vasilios Aristotle University of Thessaloniki School of Informatics Thessaloniki Greece An Applied Materials Company Think Silicon S.A. Patras Greece University of Plymouth School of Engineering Computing and Mathematics Plymouth United Kingdom

ISBN: (纸本)9798350304985

The widespread usage of wearables set the foundations for many new applications that process the wearable sensor data. Human Activity Recognition (HAR) is a well-studied application that targets to classify the data captured by multiple wearable sensors into one of a predefined set of activity classes. Earlier approaches in the area relied on Machine Learning (ML) classifiers, while many researchers proposed solutions based on Deep Neural Networks (DNNs), e.g., using Long Short-Term Memory (LSTMs) or Convolution Neural Network (CNNs). Even though the usage of DNNs for HAR is a widely explored field, the problem of compressing (thus reducing the computational requirements) the resulting DNN models has been disregarded by the research community. This is of paramount importance if we consider that wearables are characterized by scarce memory and computational resources. In this work, we first analyze the impact of the size of the various CNN components (focusing on the convolution and dense layers) to the model validation performance. As a second step, we focus on two CNN models with diverse memory characteristics (the lean and the fat model) and we employ three different compression techniques (Filter-Based Pruning -FBP,- Low Rank Factorization -LRF,- and dynamic range quantization) assuming various compressibility scenarios. © 2023 Division of Signal Processing and Electronic Systems, Poznan University of Technology (DSPES PUT).

关键词： Neural network models

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：