检索结果-内蒙古大学图书馆

19th IEEE International Conference on Cognitive Informatics and Cognitive Computing, ICCI*CC 2020

作者： Hu, Yifei Jing, Xiaonan Ko, Youlim Rayz, Julia Taylor Computer and Information Technology Purdue University United States

ISBN: (纸本)9781728195940

Spelling irregularities, known now as spelling mistakes, have been found for several centuries. As humans, we are able to understand most of the misspelled words based on their location in the sentence, perceived pronunciation, and context. Unlike humans, computer systems do not possess the convenient auto complete functionality of which human brains are capable. While many programs provide spelling correction functionality, many systems do not take context into account. Moreover, Artificial Intelligence systems function in the way they are trained on. With many current Natural Language Processing (NLP) systems trained on grammatically correct text data, many are vulnerable against adversarial examples, yet correctly spelled text processing is crucial for learning. In this paper, we investigate how spelling errors can be corrected in context, with a pretrained language model BERT. We present two experiments, based on B E R T and the edit distance algorithm, for ranking and selecting candidate corrections. The results of our experiments demonstrated that when combined properly, contextual word embeddings of B E R T and edit distance are capable of effectively correcting spelling errors. ©2020 IEEE

关键词： Text processing

来源：评论

学校读者我要写书评

暂无评论

Solving the Federated Edge Learning Participation Dilemma: A Truthful and Correlated Perspective

arXiv

引用

arXiv 2022年

作者： Hu, Qin Li, Feng Zou, Xukai Xiao, Yinhao Department of Computer and Information Science Indiana University-Purdue University IndianapolisIN United States Department of Computer Information and Graphics Technology Indiana University-Purdue University IndianapolisIN United States School of Information Science Guangdong University of Finance and Economics Guangzhou China

An emerging computational paradigm, named federated edge learning (FEL), enables intelligent computing at the network edge with the feature of preserving data privacy for edge devices. Given their constrained resources, it becomes a great challenge to achieve high execution performance for FEL. Most of the state-of-the-arts concentrate on enhancing FEL from the perspective of system operation procedures, taking few precautions during the composition step of the FEL system. Though a few recent studies recognize the importance of FEL formation and propose server-centric device selection schemes, the impact of data sizes is largely overlooked. In this paper, we take advantage of game theory to depict the decision dilemma among edge devices regarding whether to participate in FEL or not given their heterogeneous sizes of local datasets. For realizing both the individual and global optimization, the server is employed to solve the participation dilemma, which requires accurate information collection for devices’ local datasets. Hence, we utilize mechanism design to enable truthful information solicitation. With the help of correlated equilibrium, we derive a decision making strategy for devices from the global perspective, which can achieve the long-term stability and efficacy of FEL. For scalability consideration, we optimize the computational complexity of the basic solution to the polynomial level. Lastly, extensive experiments based on both real and synthetic data are conducted to evaluate our proposed mechanisms, with experimental results demonstrating the performance advantages. Copyright © 2022, The Authors. All rights reserved.

关键词： Decision making

来源：评论

学校读者我要写书评

暂无评论

Progressive Iterative Approximation of SOR for Non-uniform Cubic B-spline Curve and Surface Interpolation 12th

Progressive Iterative Approximation of SOR for Non-uniform C...

引用

12th EAI International Conference on Simulation Tools and Techniques, SIMUtools 2020

作者： Hu, Liangchen Shou, Huahao Fang, Shiaofen College of Science Zhejiang University of Technology Hangzhou Zhejiang China Department of Computer and Information Science Indiana University-Purdue University Indianapolis IndianapolisIN United States

ISBN: (纸本)9783030727918

Progressive iterative approximation (PIA) is an efficient data fitting technique which makes the initial curve or surface approximate the data points to be processed by successive iterations. However, since the spectral radius of iterative matrix in traditional PIA is relatively large, the iterative convergence rate is relatively slow, which results in poor efficiency of data fitting. In this paper, we develop a successive over-relaxation progressive iterative approximation (SOR-PIA) for non-uniform cubic B-splines to overcome the defect. Besides, we employ the equidistant search strategy to estimate the relaxation factor, which greatly accelerates the convergence speed of the iterative process. Experimental results show that SOR-PIA iterative interpolation can achieve a higher accuracy within the equivalent number of iterations compared with the standard PIA and weighted PIA (WPIA) iterative interpolation. © ICST Institute for computer Sciences, Social Informatics and Telecommunications Engineering 2021.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Scattering Matrix Based IMPM for Multiport Antenna Systems

引用

IEEE Antennas and Wireless Propagation Letters 2025年

作者： Zhang, Chuangfeng Liao, Shaolin Li, Min Sun Yat-sen University School of Electronics and Information Technology Guangdong Guangzhou China Illinois Institute of Technology Department of Electrical and Computer Engineering ChicagoIL 60616 United States Purdue University United States Tianjin University School of Microelectronics Tianjin China

This letter presents a comprehensive and systematic theory of the scattering-matrix-based internal multiport method (S-IMPM) for multiport antenna systems, integrating essential antenna parameters such as impedance matching, isolation, radiation pattern, efficiency, gain, envelope correlation coefficient (ECC), and more. In contrast to the conventional impedance-matrix-based IMPM (Z-IMPM), S-IMPM optimizes matrix operations, particularly the matrix inversion process, enhancing computational efficiency. This methodology is validated through an example in which the multiport antenna achieves impedance matching with $|S_{11}| \leq -10$ dB, high isolation with $|S_{21}| \leq -20$ dB, efficiency exceeding 80%, and low ECC (below 0.005) within a designated frequency range. Furthermore, S-IMPM results align with those from Z-IMPM and electromagnetic (EM) simulations, while measured results confirm its accuracy. Comparative runtime analyses reveal that S-IMPM achieves over 10% higher computational efficiency than Z-IMPM. © 2002-2011 IEEE.

关键词： Impedance matching (electric)

来源：评论

学校读者我要写书评

暂无评论

A study on the sizes of vehicle surrogates for AEB testing based on representative passenger vehicles in China

引用

International Journal of Vehicle Safety 2021年第1期12卷 49-65页

作者： Li, Wenli Zhang, Yousong Chien, Stanley Wang, Kan Key Laboratory of Advanced Manufacture Technology for Automobile Parts Ministry of Education Chongqing University of Technology Chongqing Banan400054 China Department of Electrical and Computer Engineering Indiana University-Purdue University IndianapolisIN46202 United States Automotive Active Safety Testing Technology Chongqing Key Laboratory of Industry and Information Technology Chongqing401122 China

Owing to the rapid advancement of automotive active safety technology, more and more cars with Advanced Driver Assistance Systems (ADAS) features are produced in recent years. The performance testing of ADAS in various crash scenarios often requires surrogate vehicles that represent actual vehicles. Most vehicle surrogates on the market are designed based on the vehicles in the USA and European markets. China is the world’s most massive automobile production and sales market, so it is worthwhile to study vehicle characteristics in China to develop vehicle surrogate requirements for the China New Car Assessment Program (C-NCAP). This paper describes a method for determining the representative dimension characteristics of passenger vehicles in China based on the last ten years of vehicle sales data. Copyright © 2021 Inderscience Enterprises Ltd.

关键词： Advanced driver assistance systems

来源：评论

学校读者我要写书评

暂无评论

Impact of Instructional Activities on Students' Positivity, Participation, and Perceived Value in a Systems Analysis and Design Course

Impact of Instructional Activities on Students' Positivity, ...

引用

Frontiers in Education (FIE) Conference

作者： Syeda Fizza Ali Daniel Bang Alejandra J. Magana Saira Anwar Department of Multidisciplinary Engineering Texas A&M University College Station TX USA Computer and Information Technology and Engineering Education Purdue University West Lafayette IN USA

The ICAP framework classifies learning into four levels based on students' cognitive engagement with the course materials. These levels are Interactive, Constructive, Active, and Passive. The built-in hypothesis within the framework suggests that Interactive activities may generate better learning and engagement than Constructive activities, which may generate better outcomes than Active activities, which in turn may generate better results than Passive activities. Prior literature has focused on the impact of ICAP learning modes on student engagement, motivation, and learning outcomes. Most of these studies were conducted in either lab settings or for testing a section of the hypothesis. Although ICAP provides a baseline to determine the nature of class activities, literature is scarce on studies that use the framework. Considering this gap, for this study, we specifically selected a class where the instructor conducted lectures using active learning-based instructional activities. Considering that the instructor's perspective may differ from students' perspective, we use the validated survey instrument Student Response to Instructional Practices (StRIP) to examine how students perceive the instructional activities in class. Also, this study focuses on the impact of the Interactive, Constructive, Active, and Passive components of ICAP on students' positivity, participation, and the value they derive from course materials. More specifically, the study answers two research questions: 1) How did students perceive the frequency of the different instructional activities (interactive, constructive, active, or passive) in class? and 2) How did the instructional activities relate to students' positivity, participation, and perceived value of the activities? We collected the data from a systems analysis and design course at a large Midwestern university. Eighty-eight students voluntarily participated in the end-of-semester survey. Data were collected for students' responses

关键词：

来源：评论

学校读者我要写书评

暂无评论

Artificial intelligence tools: a potential for error-free scholarly communication in Nigerian universities

引用

AI and Ethics 2025年 1-12页

作者： Okafor, Peter-Ebuka Udosen, Abasiafak Ndifreke Igboanugo, Benson Ikechukwu MOE Key Laboratory of Thermo-Fluid Science and Engineering School of Energy and Power Engineering Xi’an Jiaotong University Xi’an China Department of Computer and Information Technology Purdue University West Lafayette United States Department of Science Education Alex Ekwueme Federal University Ndufu-Alike Abakaliki Nigeria

Recently, efforts have been intensified in Nigerian universities to address errors and ethical issues in scholarly communications. However, despite significant efforts by the government and university administrators to resolve these challenges, most researchers still lack the expertise to effectively utilize advanced artificial intelligence (AI) tools that are essential for producing ethically sound and error-free scholarly articles. AI has speedily emerged as one of the most significant and transformative innovations of our time, with wide-ranging applications in almost every field of knowledge. Among these applications, research has arguably witnessed the fastest growth and adoption of AI-driven tools in developed nations. This study provides an in-depth review of the present applications of AI-driven tools in higher education in Nigeria, with a focus on universities, and explores the factors affecting innovative research output in universities in Nigeria. The findings from the articles reveal that several factors contribute to this, such as poor research sponsorship, limited access to online scholarly articles, unethical practices, unintentional errors, and brain drain. Benefits, implications, and strategies for improvement, along with a roadmap outlining the way forward, are suggested.

关键词：

来源：评论

学校读者我要写书评

暂无评论

基于侧基多通道和对称性破缺效应的分子电导调控

引用

Science China Materials 2024年第6期67卷 1994-1999页

作者：郝杰汪博宇赵璁霍雅妮王进莹贾传成郭雪峰 Center of Single-Molecule Sciences Institute of Modern OpticsFrontiers Science Center for New Organic MatterTianjin Key Laboratory of Micro-scale Optical Information Science and TechnologyCollege of Electronic Information and Optical EngineeringNankai UniversityTianjin 300350China Network for Computational Nanotechnology School of Electrical and Computer EngineeringPurdue UniversityIndiana 47907USA Beijing National Laboratory for Molecular Sciences National Biomedical Imaging CenterCollege of Chemistry and Molecular EngineeringPeking UniversityBeijing 100871China

化学取代是有效调节分子电导,产生多通道输运、量子干涉效应和其他机制的关键方法.但分子骨架和侧基之间存在复杂的相互作用,目前仍未被研究清楚.在本工作中,我们结合扫描隧道显微镜裂结实验技术和第一性原理计算方法,深入研究了具有不... 详细信息

化学取代是有效调节分子电导,产生多通道输运、量子干涉效应和其他机制的关键方法.但分子骨架和侧基之间存在复杂的相互作用,目前仍未被研究清楚.在本工作中,我们结合扫描隧道显微镜裂结实验技术和第一性原理计算方法,深入研究了具有不同σ和π侧基的分子电导.实验结果及理论分析表明,σ侧基的加入引起了分子前线轨道的对称性破缺并加剧了分子内散射,从而导致电导的降低.相反,π侧基引入了额外的电荷传输通道,实现了电荷传输的多通道效应,增加了分子的电导.这些发现为未来分子功能化和分子电子器件的设计提供了坚实的基础.

关键词： side substituent multiple-channel effect symmetry-breaking effect single-molecule junction

来源：评论

学校读者我要写书评

暂无评论

Lightweight Semantic Segmentation Model for Disaster Area Based on TransUNet

Lightweight Semantic Segmentation Model for Disaster Area Ba...

引用

International Conference on information and Communication technology Convergence (ICTC)

作者： Hyunsoo Kim Ilmo Kang Donghun Baek Haechan Jung Catherine Morales Dept. of Computer Science and Engineering Chungnam National University Daejeon Republic of Korea The Division of Computer Convergence Chungnam National University Daejeon Republic of Korea Dept. of Linguistics Chungnam National University Daejeon Republic of Korea Computer and Information Technology Purdue University West Lafayette Indiana USA

ISBN: (数字)9798350364637

ISBN: (纸本)9798350364644

In this paper, we propose a lightweight and real-time capable variant of the TransUNet model for disaster area semantic segmentation tasks, optimized for deployment on edge devices. While traditional TransUNet models have demonstrated performance in medical image segmentation, their size and complexity hinder real-time inference on resource-constrained platforms. To address this limitation, we used pre-trained R-ViT-Ti_16 model for the encoder part which maintains competitive performance despite a smaller model size. Additionally, we added an extra layer to the decoder and utilized only one skip connection to further reduce complexity. Several experiments were conducted to refine the model, including comparisons of different Vision Transformer (ViT) models, optimizers, loss functions, and activation functions. Our results demonstrated that the combination of R-ViT-Ti_16 with SGD optimizer, Log-Cosh Dice loss, and TanhExp activation function yielded a compact model with 87.5% of the performance of the baseline TransUNet while using only 13% of the model size. The final model was compressed using TensorRT; however, this step introduced significant performance degradation, indicating limitations in achieving real-time efficiency with this particular setup. This research highlights both the potential and the challenges of deploying highly efficient segmentation models on edge devices, suggesting the need for further optimization to balance performance and resource efficiency in real-time applications.

关键词： Performance evaluation Disasters Semantic segmentation Transformers Real-time systems Nanoscale devices Decoding Complexity theory information and communication technology Optimization

来源：评论

学校读者我要写书评

暂无评论

Cattle-Based Manure Management and Soil Fertilization System for Labor Efficiency

Cattle-Based Manure Management and Soil Fertilization System...

引用

Energy Efficiency and Agricultural Engineering (EE&AE), International Conference on

作者： Youjin Kim Chaerim Lim Seunghyeon Cho Hayoung Kim Olivia Anderson Duong Dinh Anthony Smith Software Convergence Kyung Hee University Yongin Republic of Korea Computer Science and Engineering Yonsei University Seoul Republic of Korea Computer Engineering Daegu Catholic University Gyeongsan Republic of Korea Medical IT Engineering Soonchunhyang University Asan Republic of Korea Computer and Information Technology Purdue University West Lafayette IN USA

ISBN: (数字)9798350369380

ISBN: (纸本)9798350369397

Improving and maintaining soil fertility is a crucial responsibility among essential farming tasks. On cattle farms, the task of collecting and distributing cow manure for soil fertility management has been one of the most substantial shares of the excessive workload for farmers. This paper introduces a novel method for labor-reduced manure management and soil fertilization process, aimed at improving labor efficiency. The proposed approach utilizes an Internet of Things solution that leverages the natural behavior and excretory activities of cattle. Dividing farmlands into smaller units, installed end nodes collect soil nutrient data from each area. Through a centralized web application, farmers can remotely oversee and manage the soil fertility of their entire farmland. Upon a farmer identifying areas with nutrient deficiencies, the proposed system utilizes feeders and bells to attract cattle to these low-fertility areas, encouraging them to deposit manure and enhance soil fertility. The LoRaWAN protocol facilitates bi-directional interaction between farmers located remotely and sensors deployed across vast agricultural landscapes, enabling efficient communication in expansive farming settings.

关键词： LoRaWAN Bidirectional control Soil Cows Nutrients Sensors Internet of Things

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：