检索结果-内蒙古大学图书馆

20th International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2023

作者： Yinqi, Luo Jianping, Li Jiaheng, Luo Graduate School University of Electronic Science and Technology of China Chengdu611731 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu611731 China

ISBN: (纸本)9798350318982

In order to achieve analysis and prediction of journal impact factors, we take Nature magazine as an example in this paper. Firstly, we analyze the rationality of model selection by constructing a Generic Extreme Value model. Next, we calculate the return levels under different return periods and compare them with the data from the test years, to analyze the predictive effect of the Generic Extreme Value model on impact factors. Finally, we analyze the stability of the Generic Extreme Value model in different starting years. The results are shown that: (1) The Generic Extreme Value model and the Gumbel Distribution model are feasible to impact factors. The Generic Extreme Value model does not restrict on the shape parameters and has good flexibility. (2) The return levels and the confidence interval of the return levels can predict the impact factors, and as the return periods increase, the accuracy of the prediction gradually decreases. (3) The Generic Extreme Value model is not sensitive to the starting years, and has good stability. © 2023 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Automatic Multiple Choice Question Generation: A Systematic Literature Review 9

Automatic Multiple Choice Question Generation: A Systematic ...

引用

9th International Conference on Information technology and Digital Applications, ICITDA 2024

作者： Henry, Matthew Martianus Heryanto, Nur Adhianti Isnan, Mahmud Nugroho, Kuncahyo Setyo Pardamean, Bens Bina Nusantara University Bioinformatics and Data Science Research Center Jakarta11480 Indonesia School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Department Jakarta11480 Indonesia

ISBN: (纸本)9798331510732

Despite their drawbacks, multiple-choice questions (MCQ) have been widely used to assess the students' understanding of lectures through examinations. The development of automatic MCQ generation is beneficial, especially for educators. As a starting point for further development, a Systematic Literature Review (SLR) is conducted to uncover current trends, future challenges, and opportunities in automatic MCQ generation. Previously, an SLR was conducted, but it lacks coverage of the utilization of transformer-based models. This SLR covers the development of automatic MCQ generation using either traditional or advanced approaches such as Transformers. The Preferred Reporting Items for Systematic Reviews and Meta-Analyses framework was used to gather the data from Scopus, IEEE Xplore, SpringerLink, arXiv, and Semantic Scholar. The included articles must be open-access computer science conference papers or journal articles and written in English less than five years ago. Four independent reviewers analyzed the research workflow, evaluation metric, and dataset used in each study. There are 18 included studies, where 17% (n = 3) studies are from 2024, 33% (n = 6) studies are from 2023, 22% (n = 4) studies are from 2022, 11% (n = 2) studies are from 2021, and 17% (n = 3) studies are from 2020. There are 33% (n = 6) of the studies used the traditional feature-based engineering approach, 39% (n = 7) of the studies used the Transformer-based model fine-tuning approach, and the remaining used novel approaches. The study found that BERT variants are the most utilized Transformer-based model in automatic MCQ. The research notes some challenges, but also open various opportunities for further research, including Large Language Model (LLM) utilization for automatic MCQ generation, the utilization BERT-based models for standardized machine-learned evaluation metrics, and the initiative for the creation of an MCQ dataset benchmark. © 2024 IEEE.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Analysis of Extreme Diurnal Temperature Range: Based on Generalized Extreme Value Model 21

Analysis of Extreme Diurnal Temperature Range: Based on Gene...

引用

21st International computer Conference on Wavelet Active Media technology and Information Processing, ICCWAMTIP 2024

作者： Yinqi, Luo Liyin, Liu Guoyi, Xie Sui, Luo Suhang, Li Graduate School University of Electronic Science and Technology of China Chengdu611731 China University of Electronic Science and Technology of China Logistics Support Department Chengdu611731 China School of Computer Science and Engineering University of Electronic Science and Technology of China Chengdu Sichuan611731 China

ISBN: (纸本)9798331519254

Cengong County is a traditional agricultural county in Guizhou province. Extreme temperature difference between day and night has a significant impact on the development of local agriculture. In order to analyze the distribution characteristics of extreme day-night temperature difference in the local area, a Generalized Extreme Value(GEV) model was constructed. Firstly, according to the relevant theory of GEV modeling, this paper extracts the daily temperature difference between day and night in Cengong County from 1960 to 2022, takes one year as the grouping unit, and calculates the maximum value in each group, so as to obtain the sample data needed for modeling. Then, the Maximum Likelihood Estimation(MLE) and Profile Likelihood Estimation(PLE) are used to solve the model parameter estimates. Secondly, the grouping length has a significant impact on the accuracy of the model, so the stability of the model under different grouping intervals is analyzed. The last, the return level is calculated under the different return period. The results showed that the maximum temperature difference between day and night in Cengong County obeyed Weibull distribution with an upper limit, and the theoretical upper limit was 26.819C°. The model had good extrapolation ability. © 2024 IEEE.

关键词： Weibull distribution

来源：评论

学校读者我要写书评

暂无评论

Barrier Function-Based Backstepping Fractional-Order Sliding Mode Control for Quad-Rotor Unmanned Aerial Vehicle under External Disturbances

引用

IEEE Transactions on Aerospace and Electronic Systems 2024年第1期60卷 716-728页

作者： Liu, Bowen Wang, Yingxun Mofid, Omid Mobayen, Saleh Khooban, Mohammad Hassan Beihang University School of Automation Science and Electrical Engineering Beijing100191 China University of Zanjan Department of Electrical Engineering Zanjan45371-38791 Iran National Yunlin University of Science and Technology Graduate School of Intelligent Data Science Douliou64002 Taiwan Aarhus University Department of Electrical and Computer Engineering Aarhus8200 Denmark

The main control objective for the quad-rotor system is the attitude and position tracking control which is accomplished in this article using the backstepping fractional-order sliding mode control approach combined with the adaptive tuning based barrier function theory. The quad-rotor's dynamical model is obtained at the appearance of the disturbance that is entered to the quad-rotor system by an exterior force. Hence, the attitude and position tracking errors between the quad-rotor's actual states and their desired trajectory are defined. Afterward, the fractional-order sliding surfaces are defined to guarantee finite-time reachability of the defined tracking error. The designed fractional-order surface eases the control process due to the removal of the high-derivative of virtual controllers. Then, the extended adaptive barrier function laws named fractional-order-based adaptive barrier function laws are employed to eliminate the knowledge of the upper bounds of external disturbances. The Lyapunov theory concept mixed with the backstepping control strategy is used to demonstrate that the fractional-order sliding surface reaches the neighborhood of origin in the finite time. Finally, simulation results in various scenarios on the MATLAB/ Simulink environment are provided to show that the designed control procedure in this article is an efficient control technique to assure that attitude and position's trajectories of the quad-rotor system track desired trajectories properly in the existence of the external disturbances. Moreover, the designed method is compared to the existing method to validate the efficiency of the proposed method. Lastly, experimental results using the Speedgoat real-time target machine is implemented to assure validity of the recommended method. © 1965-2011 IEEE.

关键词： Backstepping

来源：评论

学校读者我要写书评

暂无评论

Question Classification of University Admission using Named-Entity Recognition (NER) 10

Question Classification of University Admission using Named-...

引用

10th International Conference on Information technology, computer, and Electrical Engineering, ICITACEE 2023

作者： Yossy, Emny Harna Suhartono, Derwin Trisetyarso, Agung Budiharto, Widodo Bina Nusantara University Computer Science Department BINUS Graduate Program Computer Science Jakarta11480 Indonesia Bina Nusantara University Computer Science Department School of Computer Science Jakarta11480 Indonesia Bina Nusantara University Mathematics Department School of Computer Science Jakarta11480 Indonesia

ISBN: (纸本)9798350322729

The university admission process can be overwhelming for applicants and admission officers, with many questions being asked and answered every year. The manual classification of these questions can be time-consuming and may lead to errors, making exploring automated solutions to this problem essential. In recent years, advances in natural language processing (NLP), including question classification. The research proposes an architecture for a question classification system using the Indonesian Language in closed-domain question answering. The purpose of this research is to find out the classification of questions. We created a system with the Named-Entity Recognition method to recognize the next word that will be used as a candidate type of question and candidate answer. The type of question used is a factoid question. Research makes patterns and rules for extracting important words as features to determine the taxonomy of question classification. Datasets are collected from one private university in Indonesia. Data sources from Binus Online Learning websites and data on questions frequently asked by users, especially prospective students. The results of the question classification are presented using descriptive statistics. The results show that the question classification with users' most frequent question type is 'What' by 63.3%, and the answer category is 'tuition fees' by 22.4%. It can be concluded that the most frequent question type asked by users is 'What', and the most frequent topic of interest is 'tuition fees'. Organizations can use this information to improve customer service by providing more relevant information and resources about tuition fees. © 2023 IEEE.

关键词： Natural language processing systems

来源：评论

学校读者我要写书评

暂无评论

How Useful Is Image-Based Active Learning for Plant Organ Segmentation?

引用

Plant Phenomics 2022年第1期4卷 384-394页

作者： Shivangana Rawat Akshay L.Chandra Sai Vikas Desai Vineeth N.Balasubramanian Seishi Ninomiya Wei Guo Department of Computer Science and Engineering Indian Institute of TechnologyHyderabadIndia Department of Computer Science University of FreiburgGermany Graduate School of Agricultural and Life Sciences The University of TokyoJapan

Training deep learning models typically requires a huge amount of labeled data which is expensive to acquire,especially in dense prediction tasks such as semantic ***,plant phenotyping datasets pose additional challenges of heavy occlusion and varied lighting conditions which makes annotations more time-consuming to *** learning helps in reducing the annotation cost by selecting samples for labeling which are most informative to the model,thus improving model performance with fewer *** learning for semantic segmentation has been well studied on datasets such as PASCAL VOC and ***,its effectiveness on plant datasets has not received much *** bridge this gap,we empirically study and benchmark the effectiveness of four uncertainty-based active learning strategies on three natural plant organ segmentation *** also study their behaviour in response to variations in training configurations in terms of augmentations used,the scale of training images,active learning batch sizes,and train-validation set splits.

关键词： consuming lighting sizes

来源：评论

学校读者我要写书评

暂无评论

Measuring Student Satisfaction Based on Analysis of Physical Parameters in Smart Classroom 12

Measuring Student Satisfaction Based on Analysis of Physical...

引用

12th International Conference on Information and Education technology, ICIET 2024

作者： Shiri, Farhad Mortezapour Perumal, Thinagaran Mustapha, Norwati Mohamed, Raihani Ahmadon, Mohd Anuaruddin Bin Yamaguchi, Shingo University Putra Malaysia Faculty Of Computer Science And Information Technology Malaysia Graduate School Of Sciences And Technology For Innovation Yamaguchi University Japan

ISBN: (纸本)9798350371772

Several factors related to the physical environment, including temperature, environmental noise, CO2 levels, air pressure, humidity, and the lecturer's vocal delivery, significantly impact student satisfaction. Evaluating, quantifying, and enhancing these factors can significantly contribute to enhancing students' satisfaction with lecture quality. The objective of this study is to assess students' satisfaction regarding the quality of lectures through an analysis of data obtained from a variety of smart devices that record physical environmental parameters. In this study, the machine learning techniques employed encompass Decision Tree (DT), Support Vector Machine (SVM), Random Forest (RF), Adaptive Boosting (AdaBoost), K-nearest neighbors (KNN), and Stochastic Gradient Descent (SGD). Additionally, the deep learning models utilized comprise Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), Gated Recurrent Unit (GRU), Bidirectional Gated Recurrent Unit (Bi-GRU), Long Short-Term Memory (LSTM), and Bidirectional Long Short-Term Memory (Bi-LSTM). The findings of this study suggest that, on the whole, deep learning models demonstrate superior performance when it comes to classifying data about this particular problem, as compared to traditional machine learning models. Notably, the CNN model emerges as the top performer among all the models assessed, achieving an impressive accuracy rate of 74.62%. it is worth mentioning that the decision tree exhibits the highest accuracy among classical machine learning models. © 2024 IEEE.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Improving the Learning Efficiency of Hierarchical Reinforcement Learning SUHRL Using Transition Information Between Subgoals 13

Improving the Learning Efficiency of Hierarchical Reinforcem...

引用

Joint 13th International Conference on Soft Computing and Intelligent Systems and 25th International Symposium on Advanced Intelligent Systems, SCIS and ISIS 2024

作者： Kurodo, Yuya Manabe, Yusuke Graduate School of Information and Computer Science Chiba Institute of Technology Japan Chiba Institute of Technology Department of Cognitive and Information Sciences Japan

ISBN: (纸本)9798350373332

The hierarchical reinforcement learning approach incorporates intrinsic motivation into reinforcement learning. In this approach, the agents are hierarchically organized into a higher-level strategy that learns the application order (plan) of sub goals and a lower-level strategy that learns the sequence of actions up to the subgoals. This incorporation has been shown to facilitate problem-solving even in environments with sparse rewards. Stepwise Unified Hierarchical Reinforcement Learning (SUHRL) has been proposed as a hierarchical reinforcement learning algorithm. SUHRL enables autonomous learning without the need for prior knowledge or predefined subgoals. However, learning efficiency is low, and, in some cases, problem solving is not possible. Therefore, we propose the enhancement of SUHRL by constraining the exploration of sub goals based on the number of steps required to transition between them. This improvement is based on Hierarchical Reinforcement Learning with a k-step Adjacency Constraint, a method that can achieve efficient learning when sub goals are predefined. Experimental results using the Frozen Lake environment show that the proposed method exhibits a better learning efficiency than SUHRL. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

Server Cloud Based Security Surveillance Systems: a Design science Research 11

Server Cloud Based Security Surveillance Systems: a Design S...

引用

11th International Conference on Cyber and IT Service Management, CITSM 2023

作者： Nurenie, Alexander Ramadhan, Arief Abdurachman, Edi Trisetyarso, Agung Zarlis, Muhammad Bina Nusantara University Binus Graduate Program - Computer Science Computer Science Department Jakarta11480 Indonesia Telkom University School of Computing Bandung Indonesia

ISBN: (纸本)9798350305968

In this research, the author addresses the prevalent issues faced by users of cloud services, especially those using Peer-to-Peer (P2P) technology, such as connection losses, security concerns, and poor video quality. The study does not delve into the complex problems at the data center level but instead proposes a novel Design science Research approach. This new method, tested with five clients in varied locations, utilizes port forwarding to establish a direct server-client connection, bypassing traditional P2P frameworks. The results show that this approach significantly improves quality over the P2P system. Feedback from clients before and after the experiment indicates a positive response to this new method. This research offers insights into overcoming P2P-related issues in cloud services and contributes to the development of cloud-based server science, presenting a cost-effective, independent alternative to data center-dependent P2P services, with plans for ongoing research in this area. © 2023 IEEE.

关键词： Cost effectiveness

来源：评论

学校读者我要写书评

暂无评论

Random Forest Based QSAR Model Analysis for Predicting Drug Effectiveness Against Mycobacterium Tuberculosis Bacteria 11

Random Forest Based QSAR Model Analysis for Predicting Drug ...

引用

11th International Conference on ICT for Smart Society, ICISS 2024

作者： Ekosputri, Alicia Josephine Ardianti, Amanda Anggreainy, Maria Susan Artanto, Brychan Fitriawati, Nora Valentina, Fanny Angelia Santoso, Vincent Kartamulya School of Computer Science Bina Nusantara University Computer Science Department Jakarta11480 Indonesia Bina Nusantara University Binus Graduate Program Computer Science Computer Science Department Jakarta11530 Indonesia Bina Nusantara University Binus Online Learning Information Systems Department Jakarta11530 Indonesia

ISBN: (纸本)9798350389654

This research focuses on the use of machine learning methods, especially Random Forest, in designing tuberculosis drugs more effectively and efficiently. The research process begins with the creation of a QSAR (Quantitative Structure-Activity Relationship) model using a dataset from ChEMBL that includes compounds with activity against Mycobacterium tuberculosis. This model aims to predict the pIC50 value, which is an indicator of a compound's biological activity as a tuberculosis drug. The results of the Random Forest model showed high accuracy, which is 92%. This accuracy indicates that the model has a good ability in predicting the effectiveness of compounds against Mycobacterium tuberculosis. With this result, the developed model can be used as an auxiliary tool in the discovery of tuberculosis drugs and can be further developed to increase the effectiveness in drug research. © 2024 IEEE.

关键词： Prediction 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：