检索结果-内蒙古大学图书馆

1st Workshop on Large Foundation Models for Educational Assessment

作者： Gao, Rujun Guo, Xiaosu Li, Xiaodi Narayanan, Arun Balajiee Lekshmi Thomas, Naveen Srinivasa, Arun R. J. Mike Walker’66 Department of Mechanical Engineering Texas A&M University United States Computer Science Department University of Texas Dallas United States Intelligent Systems Program University of Pittsburgh United States Department of Artificial Intelligence and Informatics Mayo Clinic United States

This study explores the feasibility of using large language models (LLMs), specifically GPT-4o (ChatGPT), for automated grading of conceptual questions in an undergraduate Mechanical engineering course. We compared the grading performance of GPT-4o with that of human teaching assistants (TAs) on ten quiz problems from the MEEN 361 course at Texas A&M University, each answered by approximately 225 students. Both the LLM and TAs followed the same instructor-provided rubric to ensure grading consistency. We evaluated performance using Spearman’s rank correlation coefficient and Root Mean Square Error (RMSE) to assess the alignment between rankings and the accuracy of scores assigned by GPT-4o and TAs under zero- and few-shot grading settings. In the zero-shot setting, GPT-4o demonstrated a strong correlation with TA grading, with Spearman’s rank correlation coefficient exceeding 0.6 in seven out of ten datasets and reaching a high of 0.9387. Our analysis reveals that GPT-4o performs well when grading criteria are straightforward but struggles with nuanced answers, particularly those involving synonyms not present in the rubric. The model also tends to grade more stringently in ambiguous cases compared to human TAs. Overall, ChatGPT shows promise as a tool for grading conceptual questions, offering scalability and consistency. © 2024 R. Gao1, X. Guo2, X. Li4, A.B.L. Narayanan3, N. Thomas1 & A.R. Srinivasa1.

关键词： Mean square error

来源：评论

学校读者我要写书评

暂无评论

Optimization Model of Housing Construction Project Scheduling Based on Optimized Ant Colony Algorithm 2

Optimization Model of Housing Construction Project Schedulin...

引用

2nd International Conference on Smart Technologies for Smart Nation, SmartTechCon 2023

作者： Srinivasa, Gowda G.K. Krishna, G.R. Sanjay Rex, J. Kumar, K. Sambath Kumar, Madhan Mohan Manikandan, N. Department of Computer Science and Engineering ACS College of Engineering Tamilnadu Bangalore India Department: Mechanical Engineering Koneru Lakshmaiah Education foundation Green fields Andhra Pradesh Vaddeswaram India Department of Civil Engineering Malla Reddy Engineering College Tamilnadu Hyderabad India Department of Electronics and Communication Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India Department of Robotics and Automation Easwari Engineering College Bharathi salai Ramapuram Tamilnadu Chennai India Dept of Mechanical Engineering School of Engineering Mohan Babu University Andhra Pradesh Tirupati India

ISBN: (纸本)9798350305418

Construction management is a standardized means of project management. The construction project takes a long time and has many links, and the construction workers involved are complicated. Poor quality buildings will not only affect the construction enterprises’ brand, but also threaten the safety of people's lives and property. In this paper, an optimization model of housing construction project scheduling based on ant colony algorithm (ACA) is put forward. By studying the relationship among various sub-projects in the construction system of building projects, the management of building projects can be better realized. The results show that compared with the other two algorithms, the optimized ACA has certain advantages in recall and accuracy. There are many contents involved in the building construction process, and there are many uncontrollable factors in the building process, which greatly impact the project's construction quality. The construction industry can use this technology to strengthen the building construction management, solve the problems existing in the construction management, and improve the construction quality. © 2023 IEEE.

关键词： ant colony algorithm Building engineering Construction supervision Optimization Model Project scheduling

来源：评论

学校读者我要写书评

暂无评论

Multi-scale pulmonary nodule classification with deep feature fusion via residual network

引用

Journal of Ambient Intelligence and Humanized Computing 2023年第11期14卷 14829-14840页

作者： Zhang, Guokai Zhu, Dandan Liu, Xiao Chen, Mingle Itti, Laurent Luo, Ye Lu, Jianwei School of Software Engineering Tongji University Shanghai China High School Affiliated to Fudan University Shanghai China Department of Computer Science and Neuroscience Program University of Southern California Los Angeles United States Institute of Translational Medicine Tongji University Shanghai China

The early stage detection of benign and malignant pulmonary nodules plays an important role in clinical diagnosis. The malignancy risk assessment is usually used to guide the doctor in identifying the cancer stage and making follow-up prognosis plan. However, due to the variance of nodules on size, shape, and location, it has been a big challenge to classify the nodules in computer aided diagnosis system. In this paper, we design a novel model based on convolution neural network to achieve automatic pulmonary nodule malignancy classification. By using our model, the multi-scale features are extracted through the multi-convolution process, and the structure of residual blocks allows the network to capture more high-level and semantic information. Moreover, a strategy is proposed to fuse the features from the last avg-pooling layer and the ones from the last residual block to further enhance the performance of our model. Experimental results on the public Lung Image Database Consortium dataset demonstrate that our model can achieve a lung nodule classification accuracy of 87.5 % which outperforms state-of-the-art methods. © 2018, Springer-Verlag GmbH Germany, part of Springer Nature.

关键词： Classification (of information)

来源：评论

学校读者我要写书评

暂无评论

Detection of Parkinson's Disease from EEG Signals with EEMD Using Machine Learning and Deep Learning Techniques

Detection of Parkinson's Disease from EEG Signals with EEMD ...

引用

Sustainable Computing and Smart Systems (ICSCSS), International Conference on

作者： Nagothu Bala Srikanth S Jeba Priya Subathra M.S.P Department of Computer Science and Engineering Karunya Institute of Technology and Sciences Coimbatore Tamil Nadu India Department of Robotics and Engineering Karunya Institute of Technology and Sciences Coimbatore Tamil Nadu India

ISBN: (数字)9798350379990

ISBN: (纸本)9798350391558

Parkinson's Disease (PD) is a progressive neurodegenerative disorder characterized by tremors, stiffness, and difficulty with movement, impacting mil-lions worldwide. Electroencephalography (EEG) signals can help detect Parkinson's disease by revealing abnormal brain wave patterns associated with motor dysfunction. This abstract examines the use of EEG data for PD classification, giving attention to the analysis of frequency bands using machine learning (ML) and deep learning (DL) methods. This research suggests a novel ML and DL models based on Extended Empirical Mode Decomposition (EEMD) signal processing method to classify PD in its early stages. The aim of the proposed method is to divide patients into two groups: PD positive and negative. The developed model uses a Machine learning algorithms including Random Forest, Gradient Boost, SVM and deep learning algorithms including CNN, DNN developed for the detection of PD among patients. Random Forest and Gradient Boost excelin ensemble learning. Enriching the performance of the modela decomposition method - Extended Empirical Mode Decomposition (EEMD), is employed to analyze complex EEG signals. EEMD's application enhances feature extraction for ML and DL algorithms, facilitating accurate PD detection. The diagnostic accuracy is further improved using CNN and DNN models, which identify complex patterns in EEG data. This integrated approach showcases promise for early classification and continuous monitoring, contributing to advancements in understanding and managing PD. The proposed CNN model achieved a greater of 0.98 accuracy metric.

关键词： Deep learning Support vector machines Accuracy Machine learning algorithms Empirical mode decomposition Parkinson's disease Signal processing algorithms

来源：评论

学校读者我要写书评

暂无评论

Jigsaw-Based Benchmarking for Learning Robotic Manipulation 8

Jigsaw-Based Benchmarking for Learning Robotic Manipulation

引用

8th IEEE International Conference on Advanced robotics and Mechatronics, ICARM 2023

作者： Liu, Xiaobo Wan, Fang Ge, Sheng Wang, Haokun Sun, Haoran Song, Chaoyang Southern University of Science and Technology Department of Mechanical and Energy Engineering Guangdong Shenzhen518055 China School of Design Southern University of Science and Technology Guangdong Shenzhen518055 China Hong Kong University of Science and Technology Robotics & Autonomous Systems Thrust System Hub Hong Kong Hong Kong The University of Hong Kong Department of Computer Science Hong Kong Hong Kong

ISBN: (纸本)9798350300178

Benchmarking provides experimental evidence of the scientific baseline to enhance the progression of fundamental research, which is also applicable to robotics. In this paper, we propose a method to benchmark metrics of robotic manipulation, which addresses the spatial-temporal reasoning skills for robot learning with the jigsaw game. In particular, our approach exploits a simple set of jigsaw pieces by designing a structured protocol, which can be highly customizable according to a wide range of task specifications. Researchers can selectively adopt the proposed protocol to benchmark their research outputs, on a comparable scale in the functional, task, and system-level of details. The purpose is to provide a potential look-up table for learning-based robot manipulation, commonly available in other engineering disciplines, to facilitate the adoption of robotics through calculated, empirical, and systematic experimental evidence. © 2023 IEEE.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Enhanced Plant Health Recognition via Humanoid Robot Advanced Sensing and AI

Enhanced Plant Health Recognition via Humanoid Robot Advance...

引用

Mobile, Intelligent, and Ubiquitous Computing Conference (MIUCC), International

作者： Manar A. Ibrahim Haneen I. Fayez Salma M. Abdo Toqa E. Ghaly Ingy A. Ghanem Ibrahim Attiya Aya M. Ai-Zoghby Khaled M. Foad Faculty of Computer Science and Engineering Artificial Intelligence Science New Mansoura University Dakhlia Egypt Computer Science Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt Faculty of Engineering Computer and Communication program Faculty of Computer Science and Engineering Mansoura University New Mansoura University Dakhlia Egypt Department of Mathematics Faculty of Science Zagazig University Zagazig Egypt Faculty of Computer Science and Engineering New Mansoura University Dakhlia Egypt Computer Science Department Faculty of Computers and Artificial lntelegence Damietta University Damietta Egypt

ISBN: (数字)9798350367775

ISBN: (纸本)9798350367782

Accurate and timely detection of plant diseases is crucial for protecting crop yields and promoting sustainable agriculture. This study introduces a deep learning-based approach for plant health detection by integrating a Convolutional Neural Network (CNN) with a Humanoid robot for real-time monitoring. The approach leverages advanced tools such as TensorFlow for model development, OpenCV for image processing, and YOLOv5 for object detection. A dataset comprising 1,530 images, labeled as “Healthy,” “Powdery,” and “Rust,” was used to train, validate, and test the model. Through pre-processing techniques like rescaling, data augmentation, and feature extraction, the model achieved impressive results, with a training accuracy of 98.4%, validation accuracy of 98.2%, and testing accuracy of 99.3%. This approach marks a significant improvement in precision agriculture, offering a scalable and highly accurate solution for early plant health detection.

关键词： YOLO Training Accuracy Humanoid robots Robot sensing systems Ubiquitous computing Real-time systems Sensors Convolutional neural networks Testing

来源：评论

学校读者我要写书评

暂无评论

Summer School on Circular Economy for Sustainable Manufacturing: A Case Study and Lessons Learned 31

Summer School on Circular Economy for Sustainable Manufactur...

引用

31st CIRP Conference on Life Cycle engineering, LCE 2024

作者： Rejeb, Helmi Ben Muxika, Eñaut Ghadimi, Pezhman Univ. Grenoble Alpes CNRS Grenoble INP G-SCOP Grenoble France Mondragon University Electronics & Computer Science Department - Signal Theory & Communications Arrasate Spain Laboratory for Advanced Manufacturing Simulation and Robotics School of Mechanical & Materials Engineering University College Dublin Belfield Dublin Ireland

The Circular Economy Action Plan is the main building block of the European Green Deal, Europe's new agenda for sustainable growth. Businesses need new technologies, new methods and new industrial organization either to create new businesses or to transform their products, processes and business models. They also need new talents to innovate, create businesses and new jobs, and transform society into a more sustainable one. Circular economy has grown significantly in recent years as a topic taught in engineering curricula. The purpose of this paper is to present the design, implementation and evaluation of a summer school program dedicated to the development, transformation and implementation of circular economy systems and new business models in manufacturing. The program was designed in collaboration with three university partners during a European project and relied on contributions from industrial companies, including start-ups and innovative companies. At the end, some lessons are drawn in order to show the main added value based on the evaluation of this summer school and to identify recommendations for the design and implementation of similar summer schools. © 2024 The Author(s).

关键词： engineering education

来源：评论

学校读者我要写书评

暂无评论

Interference cancellation in RIS-assisted FD relay transmission

Interference cancellation in RIS-assisted FD relay transmiss...

引用

International Conference on Ubiquitous and Future Networks, ICUFN

作者： Donghyeon Kim Wooyeol Choi Chanjun Chun Yohan Kim Yonggang Kim AI & Robotics Tech Lab (ART Lab) Department of Computer Engineering Chosun University Department of Software Dongseo University Division of Computer Science and Engineering Kongju National University

Reconfigurable intelligent surface (RIS) is one of the promising technology for the next-generation wireless networks. The RIS reflects the received signal with phase shift introduced by reflecting elements without analog to digital conversion. In relay transmission scenario, RIS could be exploited to enhance the network coverage and improve transmission performance. In this paper, we consider RIS-assisted full-duplex (FD) relay transmission scenario. In the considered scenario, RIS and FD relay node performs relay transmission. Although the beamformed signal could be generated by phase shift of RIS, the interference from RIS to FD relay node may degrade the throughput performance. The proposed method cancels both of interference from RIS and self-interference at the FD relay node by estimating interference channels in the preparation phase before data transmission.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of IoT Enabled Smart Assistive Systems for Healthcare Applications 2

Design and Implementation of IoT Enabled Smart Assistive Sys...

引用

2nd IEEE Global Conference on Communications and Information Technologies, GCCIT 2024

作者： Dankan Gowda, V. Srinivas, D. Srinivas, Rachakonda Ingole, Balaji Shesharao Jadhav, Priya Dongare Prasad, K.D.V. Bms Institute of Technology and Management Department of Electronics and Communication Engineering Karnataka Bangalore India Sr University School of Business Telangana Warangal506371 India Aditya Institute of Technology and Management Department of Computer Science & Engineering Tekkali Andhra Pradesh Srikakulam India GA United States Department of Robotics and Automation Maharashtra Pune412115 India Symbiosis Institute of Business Management Hyderabad India Pune India

ISBN: (纸本)9798350388916

The use of IoT technology in healthcare systems has been adopted in patient monitoring because IoT technology has been adopted rapidly in the systems. This paper discusses on design and implementation of an IoT integrated smart assistive health care system to enhance the precision and speed of patient health assessment. In the proposed system, wearable sensors are used to capture respiratory rate, pulse rate, blood pressure, oxygen saturation, and body temperature with data to be sent to the cloud server as and when it is received. Some of the features are, however, small data transmission delays, high accuracy in the physiological signals and long durations of monitoring due to the low power consumption. The simulations showed that the response time falls below 500ms, and physicians retain up to a 2 % variance to clinical grade devices, which actualized robust and effective patient care. The incorporation of predicting capacities, thus providing ways of early identification of health complications, makes the system applicable in chronic disease treatments and telemedicine. © 2024 IEEE.

关键词： Blood pressure

来源：评论

学校读者我要写书评

暂无评论

Suitability of Sacrum Motion in Computing Dynamic Gait Stability Indices

Suitability of Sacrum Motion in Computing Dynamic Gait Stabi...

引用

IEEE Global Conference on Consumer Electronics (GCCE)

作者： Ziqi Liu Tomohito Kuroda Shogo Okamoto Yasuhiro Akiyama Department of Computer Science Tokyo Metropolitan University Hino Japan Department of Mechanical Engineering and Robotics Shinshu University Ueda Japan

Gait stability indices are expected to preemptively detect people at high risk of falling. Among these, the margin of stability (MoS) is known as a valid index. Usually, the computation of MoS requires the motion-related information of multiple feature points of the body; however, we have been pursuing the use of only one feature point. We estimated the anterior and mediolateral MoS values from the velocity time series of the sacrum, knee, or toe using principal motion analysis. Based on open gait data for 60 people over 60 years of age, the sacrum was best suited for computing MoS in the anterior and mediolateral directions. The correlation coefficients between the estimated and observed values were 0.77 and 0.73, respectively. Our findings will help establish an easy-to-access and accurate measurement of MoS values using an inertial measurement unit attached to a body feature.

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：