检索结果-内蒙古大学图书馆

IEEE International Conference on Robotic Computing (IRC)

作者： Hayeon Ju Hyeji Jang Jiho Eum Minji Kang Sujeong Yim Xavier Lopez Anthony Smith Information and Statistics Yonsei University Wonju Republic of Korea IT Engineering Sookmyung Women's University Seoul Republic of Korea Software Sangmyung University Cheonan Republic of Korea Al Computer Science and Engineering Kyonggi University Suwon Republic of Korea Computer and Information Technology Purdue University West Lafayette United States

ISBN: (数字)9798331521554

ISBN: (纸本)9798331521561

Smart city applications require efficient, reliable, and cost-effective communication networks due to the rapid advancement of IoT technology. This study compares the real-world performance of LoRaWAN and 802.11ah for IoT-based environmental monitoring in smart cities. Through practical experiments, key performance metrics such as Received Signal Strength Indicator (RSSI), Signal-to-Noise Ratio (SNR), and data throughput were measured while connecting various sensors to the end devices, taking into account factors like distance, Line of Sight (LoS), and Fresnel zone obstructions. The results were analyzed using machine learning library-based statistical analysis and regression analysis to uncover deeper relationships and insights. This comprehensive analysis led to the conclusion that 802.11ah outperforms in terms of signal strength and data throughput over short distances, while LoRa Wanexcels in long-range communication but exhibits performance variability in obstructed environments. To achieve coverage equivalent to LoRaWAN, 802.11ah would require 157.83 times more access points, thereby increasing costs. These insights provide guidelines for deploying LPWAN technologies in smart city applications, balancing performance, range, and cost-effectiveness. Further-more, this paper discusses the implementation of the network-based IoT system on the web, enabling monitoring within a smart city environment.

关键词： Sensitivity Smart cities LoRaWAN Throughput Stability analysis Internet of Things Received signal strength indicator Numerical stability Signal to noise ratio Low-power wide area networks

来源：评论

学校读者我要写书评

暂无评论

It's Time to Confront Fake News and Rumors on Social Media: A Bibliometric Study Based on VOSviewer 4

It's Time to Confront Fake News and Rumors on Social Media: ...

引用

4th IEEE International Conference on computer and Communication Engineering technology, CCET 2021

作者： Ding, Yi Wang, Yajun Wang, Yaqin Anhui Polytechnic University School of Economics and Management Wuhu China Purdue University Department of Computer and Information Technology West LafayetteIN United States

ISBN: (纸本)9781665438902

This paper is aimed to use a quantitative and visual method to evaluate the history, current and future of publications regarding fake news and rumors on social media. VOSviewer was used to identify and summarize the publications from Scopus and WoS from 2010 to 2020. Publication source, publication organization, authors, country, citation of articles, citation of country and organization were recorded and analyzed. Bibliometric maps of authorship, citation, co-citation and network of co-occurrence of keywords were drawn. 6354 articles and 33503 cited references were analyzed. The United States dominates the publications (1615, 25.4%) and citations (5867). university of Chinese Academic of Sciences (85) is the most productive organization. Loftus (26) is the most productive author. Memory Cognition published the most papers about fake news and rumors. The latest keyword 'machine learning' appeared in 2018 in 182 papers. Other relatively new keywords include 'deep learning' 'natural language processing' 'social media platform' 'fake news detection' 'rumors detection' which appeared in 2018 in 98, 66, 63, 58, and 52 papers respectively. As for researchers and practitioners, this paper suggests an analysis of integrated visualization in terms of knowledge and innovation based on the area of fake news and rumors. © 2021 IEEE.

关键词： Social networking (online)

来源：评论

学校读者我要写书评

暂无评论

Comparison of goTenna and ClusterDuck Protocol: Evaluation of the Performance under Various Conditions

Comparison of goTenna and ClusterDuck Protocol: Evaluation o...

引用

International Conference on information and Communication technology Convergence (ICTC)

作者： Jinmyeong Lee Seonghyeon Bae Geonu Lim Ryan Melenchuk Sihyeong Lee Anthony Smith Environmental Engineering Chungnam National University Daejeon Republic of Korea Computer Science & Engineering Chungnam National University Daejeon Republic of Korea Computer and Information Technology Purdue University West Lafayette IN USA

Natural catastrophes cause widespread damage, including the destruction of communication infrastructure; When communication infrastructure goes down, people can no longer send SOS signals or messages for help. Furthermore, with previous problems, the frequency of natural disasters and the necessity for communication systems in emergencies is rising every year. For these reasons, companies and organizations have developed innumerable technologies focused on disaster relief. However, there is a lack of comparative research on the practical application of communication technology in this emergency environment. Therefore, two technologies (goTenna and ClusterDuck Protocol) had changes in their Received Signal Strength Indicator (RSSI) and Message Delivery Ratio (MDR) compared over a variety of environments and differing ranges. This study aims to compare the transmission range of two technologies under various conditions and provide guidance for selecting the appropriate technology based on specific use cases. By analyzing the results, this study seeks to identify the strengths and weaknesses of each technology and provide insights into their optimal use cases.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Real-Time Crowd Density Estimation and Stampede Risk Assessment System Using Thermal Camera

Real-Time Crowd Density Estimation and Stampede Risk Assessm...

引用

IEEE International Conference on Robotic Computing (IRC)

作者： GyeongYeon Kim EunSeo Ko DongRyeong Kim JuEun Kim Dane Hindsley Eric T. Matson Computer Engineering Daegu Catholic University Daegu Republic of Korea IT Engineering SookMyung Womens's University Seoul Republic of Korea Computer Science A-jou University Suwon Republic of Korea Computer Science Kyonggi University Suwon Republic of Korea Computer and Information Technology Purdue University West Lafayette Indiana United States

ISBN: (数字)9798331521554

ISBN: (纸本)9798331521561

Stampede accidents frequently occur in situations where large crowds gather. Although education on how to protect oneself and prevent accidents in dense crowds has been provided, these measures mainly focus on post-accident responses. In contrast, this study proposes a proactive approach to prevent stampede accidents by utilizing thermal cameras to detect the number of people in a space in real-time and calculate the risk of a stampede. The system collects object detection and density estimation results using thermal cameras, considering population density in a specific area, and transmits the estimated results to other devices via serial communication. Thermal imaging technology excels at detecting people with high accuracy even in challenging daytime conditions or low-light environments at night. The data collected from the thermal cameras is continuously updated through machine learning and pattern analysis to assess stampede risk, and the results are provided in real-time via a web interface. This allows safety personnel and managers to effectively monitor high-density areas and take immediate action if necessary. Additionally, the system's web interface provides users with real-time information related to stampede risk. The validity of the proposed system has been demonstrated through field applicability and performance evaluation in real-world environments, contributing to enhanced public safety by preventing stampede accidents in advance.

关键词： Performance evaluation Accuracy Lighting Estimation Object detection Cameras Real-time systems Public security Monitoring Accidents

来源：评论

学校读者我要写书评

暂无评论

Deploying a Sustainable Deep Learning Pipeline for Poison Ivy Image Classification

Deploying a Sustainable Deep Learning Pipeline for Poison Iv...

引用

Artificial Intelligence for Medicine, Health and Care (AIMHC), IEEE International Conference on

作者： Wonjun Park Sumin Cho Subin Kim Jiyeon Lee Jack Mahedy Nebey Gebresalssie Minji Lee Computer Science and Engineering Konkuk University Seoul Republic of Korea Human Centered Artificial Intelligence Sangmyung University Seoul Republic of Korea Computer Software Engineering Soonchunhyang University Asan Republic of Korea Computer Science and Engineering Kyonggi University Suwon Republic of Korea Computer and Information Technology Purdue University West Lafayette IN USA

Poison ivy, causing irritated skin in humans due to the urushiol oil it contains, is a well-known plant mainly distinguishable by the traits of its leaves. Nevertheless, according to the statistical data, a significant number of people are still affected by the plant. This research postulates that this notorious result stemmed from the scarce analysis about the plant. The paper proposes an automated pipeline, functioning Continuous Integration, Deployment, and Training on Kubeflow so that the harmful impact of the plant decreases, leading the public health outcomes to enhance. The pipeline contains a dataset composed of both a set of leaves and a stem images which are manually collected from a local farm and a devised model which considers both features to classify Western poison ivy. With the pipeline, the research contributes to decrease the number of suffering people from the plant as promptly reacting to seasonal changes.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Detection of Day-Based Health Evidence with Pretrained Large Language Models: A Case of COVID-19 Symptoms in Social Media Posts

Detection of Day-Based Health Evidence with Pretrained Large...

引用

IEEE International Conference on Bioinformatics and Biomedicine (BIBM)

作者： Keyuan Jiang Valli Devendra Soniya Chavan Gordon R. Bernard Computer Information Technology & Graphics Purdue University Northwest Hammond IN U.S.A. Department of Medicine Vanderbilt University Nashville TN U.S.A.

Gathering the information pertaining to health evidence occurring on particular days can help understand the progression of a disease over time, and such evidence as symptoms was widely shared by the social media users during the COVID-19 pandemic. Identifying this type of evidence is challenging. In this work, we investigated pretrained large language models on their ability to identify the day-based COVID-19 symptom mentions in Twitter posts. Our results on a corpus of 635 tweets show that without any supervision and optimization both GPT-3.5 and GPT 4 models achieved impressive performance, much better than Web-based ChatGPT and Google Bard. In addition, we explored and utilized GPT-4’s ability to determine the number of matches between a list of predicted symptom expressions and a list of annotated symptom expressions, reducing the effort of designing a sophisticated algorithm for finding the matches.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Adaptive Low-Rank Gradient Descent

Adaptive Low-Rank Gradient Descent

引用

IEEE Conference on Decision and Control

作者： Ali Jadbabaie Anuran Makur Amirhossein Reisizadeh Laboratory for Information & Decision Systems Massachusetts Institute of Technology Cambridge MA USA Department of Computer Science School of Electrical & Computer Engineering Purdue University West Lafayette IN USA

Low-rank structures have been observed in several recent empirical studies in many machine and deep learning problems, where the loss function demonstrates significant variation only in a lower dimensional subspace. While traditional gradient-based optimization algorithms are computationally costly for high-dimensional parameter spaces, such low-rank structures provide an opportunity to mitigate this cost. In this paper, we aim to leverage low-rank structures to alleviate the computational cost of first-order methods and study Adaptive Low-Rank Gradient Descent (AdaLRGD). The main idea of this method is to begin the optimization procedure in a very small subspace and gradually and adaptively augment it by including more directions. We show that for smooth and strongly convex objectives and any target accuracy $\epsilon$ , AdaLRGD's complexity is $\mathcal{O}(r\ln(r/\epsilon))$ for some rank $r$ no more than dimension $d$ . This significantly improves upon gradient descent's complexity of $\mathcal{O}(d\ln(1/\epsilon))$ when $r\ll d$ . We also propose a practical implementation of AdaLRGD and demonstrate its ability to leverage existing low-rank structures in data.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Robust Iterative Permittivity Inversion Method Based on Reduced Order Models

Robust Iterative Permittivity Inversion Method Based on Redu...

引用

Antennas and Propagation & USNC/URSI National Radio Science Meeting

作者： Tianchen Shao Zekui Jia Maokun Li Fan Yang Shengheng Xu Department of Electronic Engineering Beijing National Research Center for Information Science and Technology Tsinghua University Beijing China Elmore Family School of Electrical and Computer Engineering Purdue University West Lafayette IN USA

ISBN: (数字)9798350369908

ISBN: (纸本)9798350369915

To mitigate the nonlinearity and cycle-skipping effects inherent in inverse scattering problems (ISPs), we propose a robust permittivity inversion method using the iterative data to Born (DtB) process. The DtB process is based on reduced order models (ROMs) obtained by the Galerkin approximation of wave operators. We incorporate the layer-peeling (LP) strategy to ensure efficient and stable convergence. Furthermore, two regularization techniques are implemented to improve the robustness of the inversion algorithm in noisy environments. The inversion algorithm is validated through a 2D example.

关键词： Scattering Approximation algorithms Robustness Reduced order systems Iterative methods Noise measurement Permittivity

来源：评论

学校读者我要写书评

暂无评论

Studying Battery Range and Range Anxiety for Electric Vehicles based on Real Travel Demands 65th

Studying Battery Range and Range Anxiety for Electric Vehicl...

引用

65th Human Factors and Ergonomics Society Annual Meeting, HFES 2021

作者： Zhang, Zhengming Tian, Renran School of Industrial Engineering Purdue University West LafayetteIN United States Department of Computer Information Technology IUPUI IndianapolisIN United States

ISBN: (纸本)9781713844129

Determination of appropriate battery ranges is critical for developing and utilizing electric cars, which remains an active research topic. In particular, the issues of range anxiety have not been well studied concerning the battery design. Towards these research gaps, this study firstly investigates the baseline battery ranges based on the actual travel data collected from a large-scale longitudinal naturalistic driving study in the Midwestern USA. The occurrences and severity levels of range anxiety are then studied given the baseline, which leads to an augmented optimization model to eliminate such issues. Results show that in the baseline model, 60% of drivers can replace their gas cars entirely with 400-mile battery ranges, and less than 40% can do so with 200-mile battery ranges. Even when all the travel needs are satisfied, the optimal battery ranges can still cause range anxiety issues for all the drivers. An additional 25 miles of battery range can help solve the problem based on the improved optimization results. © 2021 by Human Factors and Ergonoics Society. All rights reserved.

关键词： Secondary batteries

来源：评论

学校读者我要写书评

暂无评论

CANVAS: END-TO-END KERNEL ARCHITECTURE SEARCH IN NEURAL NETWORKS

arXiv

引用

arXiv 2023年

作者： Zhao, Chenggang Zhang, Genghan Shen, Ao Gao, Mingyu Institute for Interdisciplinary Information Sciences Tsinghua University Beijing China Department of Electrical Engineering Tsinghua University Beijing China Department of Computer and Information Technology Purdue University West LafayetteIN47907 United States

The demands for higher performance and accuracy in neural networks (NNs) never end. Existing tensor compilation and Neural Architecture Search (NAS) techniques orthogonally optimize the two goals but actually share many similarities in their concrete strategies. We exploit such opportunities by combining the two into one and make a case for Kernel Architecture Search (KAS). KAS reviews NAS from a system perspective and zooms into a more fine-grained level to generate neural kernels with both high performance and good accuracy. To demonstrate the potential of KAS, we build an end-to-end framework, Canvas, to find high-quality kernels as convolution replacements. Canvas samples from a rich set of fine-grained primitives to stochastically and iteratively construct new kernels and evaluate them according to user-specified constraints. Canvas supports freely adjustable tensor dimension sizes inside the kernel and uses two levels of solvers to satisfy structural legality and fully utilize model budgets. The evaluation shows that by replacing standard convolutions with generated new kernels in common NNs, Canvas achieves average 1.5× speedups compared to the previous state-of-the-art with acceptable accuracy loss and search efficiency. Canvas verifies the practicability of KAS by rediscovering many manually designed kernels in the past and producing new structures that may inspire future machine learning innovations. For source code and implementation, we open-sourced Canvas at https://***/tsinghua-ideal/Canvas. Copyright © 2023, The Authors. All rights reserved.

关键词： Tensors

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：