检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Kaya, Mehmet Onurcan Oktem, Figen S. Dept. of Applied Mathematics and Computer Science DTU Lyngby2800 Denmark Dept. of Electrical and Electronics Eng. METU Ankara06800 Turkey

Diffusion models have demonstrated their utility as learned priors for solving various inverse problems. However, most existing approaches are limited to linear inverse problems. This paper exploits the efficient and unsupervised posterior sampling framework of Denoising Diffusion Restoration Models (DDRM) for the solution of nonlinear phase retrieval problem, which requires reconstructing an image from its noisy intensity-only measurements such as Fourier intensity. The approach combines the model-based alternating-projection methods with the DDRM to utilize pretrained unconditional diffusion priors for phase retrieval. The performance is demonstrated through both simulations and experimental data. Results demonstrate the potential of this approach for improving the alternating-projection methods as well as its limitations. Copyright © 2025, The Authors. All rights reserved.

关键词： Inverse problems

来源：评论

学校读者我要写书评

暂无评论

Mentorship and Legitimate Peripheral Participation in the Research Laboratory

Mentorship and Legitimate Peripheral Participation in the Re...

引用

Frontiers in Education (FIE) Conference

作者： Glen Hordemann Francis Quek Dept. of Electrical Eng. and Computer Science Texas A&M University College Station TX USA

ISBN: (数字)9798350351507

ISBN: (纸本)9798350363067

This research-to-practice paper investigates how undergraduates organically transition into researchers through the lens of Legitimate Peripheral Participation, Legitimate Peripheral Participation is a contextual learning phenomenon through which new members become core members of a community. These peripheral members begin with the execution of peripheral low-risk and simple activities, gradually accruing knowledge and experience as they take on more complex and essential activities. They gain legitimacy and access to more complex involvement through interaction with, and mentorship by, senior members of the community. Our research examines how seven undergraduate students, who are involved with a research lab, transition from peripheral roles to core membership through observation and peripheral eng.gement, skill development, community integration, increasing responsibility, and collaborative projects. These undergraduates interact with and are mentored by both graduate students and faculty members in an organic fashion, with no assigned mentorship roles existing between the undergraduate students and graduate students or faculty. The focus of our research is not on how one recruits undergraduates to work in a research lab, but on how the identity of an undergraduate as a researcher, both in their own mind and in those of their coworkers, is nurtured and developed. Through the process of surveys and interviews we extract the core elements of the undergraduates' experience and explore factors that might contribute to or hinder their transition into being more active researchers. The degree of involvement and identification as a researcher varied significantly between the undergraduate students. The key elements we discover at social eng.gement, physical presence, and near-peer interaction.

关键词： Surveys Publishing IEEE Senior Members Collaboration Logic gates Interviews Lenses

来源：评论

学校读者我要写书评

暂无评论

Crime-Intent Sentiment Detection on Twitter Data Using Machine Learning 8

Crime-Intent Sentiment Detection on Twitter Data Using Machi...

引用

8th International Conference on Automation, Control and Robotics eng.neering, CACRE 2023

作者： Bokolo, Biodoumoye George Ogegbene-Ise, Ebikela Chen, Lei Liu, Qingzhong Sam Houston State University Dept. of Computer Science HuntsvilleTX United States Kennesaw State University Dept. of Comp. and Software Eng. KennesawGA United States Georgia Southern University Dept. of Info. Tech. Statesboro Georgia

ISBN: (纸本)9798350302776

This research examines sentiment analysis in the context of crime intent using machine learning algorithms. A comparison is made between a crime intent dataset generated from a Twitter developer account and Kaggle's sentiment140 dataset for Twitter sentiment analysis. The algorithms employed include Support Vector Machine (SVM), Naïve Bayes, and Long Short-Term Memory (LSTM). The findings indicate that LSTM outperforms the other algorithms, achieving high accuracy (97%) and precision (99%) in detecting crime tweets. Thus, it is concluded that the crime tweets were accurately identified. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Facial Expression Recognition in the Wild with Application in Robotics 6

Facial Expression Recognition in the Wild with Application i...

引用

6th International Conference on computer science and eng.neering, UBMK 2021

作者： Han, Hasan Karadeniz, Oğuzcan Sönmez, Elena Battini Dalyan, Tuğba Sanoğlu, Baykal Dept. of Elec. and Electr. Eng Istanbul Bilgi University Istanbul Turkey Dept of Computer Eng Istanbul Bilgi University Istanbul Turkey

ISBN: (纸本)9781665429085

One of the major problems with robot companions is their lack of credibility. Since emotions play a key role in human behaviour their implementation in virtual agents is a conditio sine-qua-non for realistic models. That is, correct classification of facial expressions in the wild is a necessary preprocessing step for implementing artificial empathy. The aim of this work is to implement a robust Facial Expression Recognition (FER) module into a robot. Considering the results of an empirical comparison among the most successful deep learning algorithms used for FER, this study fixes the state-ofthe-art performance of 75% on the FER2013 database with the ensemble method. With a single model, the best performance of 70.8% has been reached using the VGG16 architecture. Finally, the VGG16-based FER module has been been implemented into a robot and reached a performance of 70% when tested with wild expressive faces. © 2021 IEEE

关键词： Robots

来源：评论

学校读者我要写书评

暂无评论

On the Design of Simultaneous Motion Controller for the Four-axis SCARA System

On the Design of Simultaneous Motion Controller for the Four...

引用

International Conference on Power elec.ronics and Drive Systems (PEDS)

作者： Yen-Fang Li Zhong-Wei Xu Yi-Jun Zhang Yong-Bin Wu Lilan Chuang Dept. of Elec. Eng. Ming-Hsin University of Science and Technology Hsin-Chu Taiwan Dept. of Nursing Chang Gung University of Science and Technology Taoyuan Taiwan

This paper conducted the design and implementation of a four-axis Selec.ive Compliance Assembly Robot Arm (SCARA) motion controller. Combining the SoC and FPGA circuits, a SoC/FPGA based four-axis simultaneous motion controller is proposed. The SoC-based controller operates the real-time forward and inverse kinematics computing, while the FPGA-based controller paralleled modulates the position and speed control of each axis. The SoC communicates with the PC-based host controller through TCP/Modbus so that the latter no longer requires the forward and inverse kinematics computing, in which the distributed control between SoC and PC can be achieved. The PC-based host controller only instructs the motion path order in the space, accurate path planning on each axis of the SCARA would be completed through proper movement segment calculation by the SoC-based controller, such design architect is able to accomplish a high speed, high accuracy motion control of the SCARA system.

关键词：

来源：评论

学校读者我要写书评

暂无评论

GRACE: Generating Socially Appropriate Robot Actions Leveraging LLMs and Human Explanations

arXiv

引用

arXiv 2024年

作者： Doğan, Fethiye Irmak Ozyurt, Umut Cinar, Gizem Gunes, Hatice Dept. of Computer Science and Technology University of Cambridge United Kingdom Dept. of Computer Eng. Middle East Technical University Turkey Department of Psychology Bilkent University Turkey

When operating in human environments, robots need to handle complex tasks while both adhering to social norms and accommodating individual preferences. For instance, based on common sense knowledge, a household robot can predict that it should avoid vacuuming during a social gathering, but it may still be uncertain whether it should vacuum before or after having guests. In such cases, integrating common-sense knowledge with human preferences, often conveyed through human explanations, is fundamental yet a challeng. for existing systems. In this paper, we introduce GRACE, a novel approach addressing this while generating socially appropriate robot actions. GRACE leverages common sense knowledge from LLMs, and it integrates this knowledge with human explanations through a generative network. The bidirectional structure of GRACE enables robots to refine and enhance LLM predictions by utilizing human explanations and makes robots capable of generating such explanations for human-specified actions. Our evaluations show that integrating human explanations boosts GRACE’s performance, where it outperforms several baselines and provides sensible explanations. © 2024, CC BY.

关键词： Human eng.neering

来源：评论

学校读者我要写书评

暂无评论

Development of Synthetic Data Benchmarks for Evaluating Feature Selec.ion Algorithms 2

Development of Synthetic Data Benchmarks for Evaluating Feat...

引用

2nd International Seminar on Machine Learning, Optimization, and Data science, ISMODE 2022

作者： Mitra, Rohan Varam, Dara Ali, Eyad Sulieman, Hana Kamalov, Firuz American University of Sharjah Dept. of Computer Science & Eng. Sharjah United Arab Emirates American University of Sharjah Dept. of Mathematics & Statistics Sharjah United Arab Emirates Canadian University Dubai Dept. of Electrical Eng. Dubai United Arab Emirates

ISBN: (纸本)9781665455640

The primary objective of this paper is to present a set of synthetically generated datasets as a benchmark for evaluating feature selec.ion algorithms (FSAs). The use of synthetic datasets is encouraged because of their utility in controlling data parameters, including the exact number of relevant, redundant, and irrelevant features. This paper proposes four numeric datasets with several sources of inspiration, namely based on geometric objects, trigonometric equations and multi-cut linear combinations. These synthetically generated datasets come with a fixed number of relevant, redundant and irrelevant features, which are then evaluated using feature selec.ion algorithms currently popular within industry and academia. This highlights the function of these datasets as benchmarks for future researchers in the field of feature selec.ion. Accordingly, the datasets will also be made available through GitHub for use as evaluation metrics, whilst the code is made available to be modified according to the application for the researcher. This may include research into the performance of FSAs, the development of new synthetic data, and beyond. © 2022 IEEE.

关键词： Feature Selec.ion

来源：评论

学校读者我要写书评

暂无评论

Replicability Study: Corpora For Understanding Simulink Models & Projects

Replicability Study: Corpora For Understanding Simulink Mode...

引用

International Symposium on Empirical Software eng.neering and Measurement, ESEM

作者： Sohil Lal Shrestha Shafiul Azam Chowdhury Christoph Csallner Computer Science & Eng. Dept. University of Texas at Arlington Arlington TX USA

Background: Empirical studies on widely used model-based development tools such as MATLAB/Simulink are limited despite the tools' importance in various industries. Aims: The aim of this paper is to investigate the reproducibility of previous empirical studies that used Simulink model corpora and to evaluate the generalizability of their results to a newer and larger corpus, including a comparison with proprietary models. Method: The study reviews methodologies and data sources employed in prior Simulink model studies and replicates the previous analysis using SLNET. In addition, we propose a heuristic for determining code-generating Simulink models and assess the open-source models' similarity to proprietary models. Results: Our analysis of SLNET confirms and contradicts earlier findings and highlights its potential as a valuable resource for model-based development research. We found that open-source Simulink models follow good modeling practices and contain models comparable in size and properties to proprietary models. We also collected and distribute 208 git repositories with over 9k commits, facilitating studies on model evolution. Conclusions: The replication study offers actionable insights and lessons learned from the reproduction process, including valuable information on the generalizability of research findings based on earlier open-source corpora to the newer and larger SLNET corpus. The study sheds light on noteworthy attributes of SLNET, which is self-contained and redistributable.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expanding Remote Student Learning-Internet of Things Applications and Exercises 53

Expanding Remote Student Learning-Internet of Things Applica...

引用

53rd IEEE ASEE Frontiers in Education International Conference, FIE 2023

作者： Hicks, David McLauchlan, Lifford Mehrubeoglu, Mehrube Bhimavarpu, Hemanth K. R. Texas A&m University-Kingsville Dept. of Electrical Eng. and Computer Science KingsvilleTX United States Texas A&m University-Corpus Christi Dept of Engineering Corpus ChristiTX United States

ISBN: (纸本)9798350336429

The availability of inexpensive sensor, communication, and computing devices continue to drive a rapid proliferation of Internet of Things (IoT) applications. This has resulted in an increase in the importance of the inclusion of IoT related content in education programs. A project underway at Texas A&M University-Kingsville seeks to support teaching IoT concepts to remote learners through the design and deployment of IoT learning toolkits. A series of exercises have been developed to assist remote learners in becoming familiar with the toolkits and to introduce basic IoT concepts. The learning kits are to be deployed in two senior level capstone project courses to teach IoT related concepts and encourage students to consider how IoT technology might be beneficial for and integrated into their project designs. © 2023 IEEE.

关键词： Internet of Things Remote student learning

来源：评论

学校读者我要写书评

暂无评论

Automated Power Point Generation using Natural Language Processing Techniques

Automated Power Point Generation using Natural Language Proc...

引用

International Conference on Smart Computing & Communications (ICSCC)

作者： Sebin Thomas V G John Josin Chacko Mariyam Shajahan Sharon Sunny Dept. of Computer Science & Eng. Amal Jyothi College of Engineering Kottayam India

Presentations have become an important part of the work life whether it is a student or an employee or a businessman. But creating a presentation is a time consuming process. The proposed method aims to reduce the amount of work put into creating a presentation by automatically generating an outline or a framework of the presentation based on text input. The system is a website that will be able to convert a text file or a pdf document into a presentation. If it is a text document, segments of text are created by analyzing the text and grouping sentences that belong to the same topic. Then, each of these segments will be summarized and key points will be generated. These points will be distributed over several slides. Appropriate titles will be generated for each slide based on the contents. If it is a pdf document, the titles are extracted from the document itself. The segments are already present as pdf documents and have a structure. The presentation can be exported as *** file which lets the user to edit the file easily and make any changes if necessary. The system uses Google App Script to generate a file ***, and uses API’s to summarize text, generate key points and to generate titles.

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：