检索结果-内蒙古大学图书馆

26th International Symposium on Symbolic and Numeric Algorithms for Scientific Computing, SYNASC 2024

作者： Ciobanu, Alexandru-Adrian Bacanin, Nebojsa Sanders, Tilman Stoean, Catalin University of Craiova Department of Computer Science Craiova Romania Singidunum University Faculty of Informatics and Computing Belgrade Serbia FH Muenster Department of Electrical Engineering and Computer Science Steinfurt Germany

ISBN: (纸本)9798331532833

Accurate forecasting of solar energy production is highly important for an adequate integration of renewable energy into the power grid. This study explores the importance of various predictors for enhancing the accuracy of solar energy forecasting using two distinct Long Short-Term Memory models: one that relies solely on historical power production data and past exogenous weather data, and another that additionally incorporates future exogenous weather data. Various settings are tried to improve the results and relatively similar parameters are used by both, yielding more accurate results for the model that also uses information from the future. The results also demonstrate that predictor importance varies significantly between the two models. These findings suggest that different models benefit from distinct predictor combinations and incorporating exogenous data can significantly enhance forecasting performance. © 2024 IEEE.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Mobile Robot Tracker for the Presence of Gas in a House Prototype Using Left Hand Rule Based on PID

Mobile Robot Tracker for the Presence of Gas in a House Prot...

引用

2023 International Conference on Modeling and E-Information Research, Artificial Learning and Digital Applications, ICMERALDA 2023

作者： Jayadi, Akhmad Adhinata, Faisal Dharma Putri, Novia Utami Setiawan, Ridho Universitas Teknokrat Indonesia Faculty of Engineering and Computer Science Lampung Indonesia Institut Teknologi Telkom Purwokerto Faculty of Informatics Jawa Tengah Indonesia

ISBN: (纸本)9798350369359

The designed mobile robot can follow the arena automatically and can detect gas automatically without human assistance. This mobile robot can run from a predetermined starting point, and will detect gas at a predetermined point. This mobile robot is built with an Arduino Uno microcontroller which uses the C programming language and is equipped with 2 ultrasonic sensors and an MQ-6 sensor. The results obtained after testing in this study are the establishment of an intelligent mobile robot system that is able to navigate walls with the help of ultrasonic sensors and is able to detect gas wells. In this study using the PID value, namely kp=40ki= 0.0001kd=2 and for gas readings the MQ-6 sensor detects the presence of gas of 800 PPM. Thus, this mobile robot is expected to be implemented so that it can be used to facilitate the role of humans in detecting gas leaks based on intelligent mobile robots. © 2023 IEEE.

关键词： Gases

来源：评论

学校读者我要写书评

暂无评论

One-Class Classification of 3D Point Clouds Using Dynamic Graph CNN 7

One-Class Classification of 3D Point Clouds Using Dynamic Gr...

引用

7th International Conference on computer Science and engineering, UBMK 2022

作者： Gencer, Zeki Sahin, Yusuf H. Unal, Gozde Istanbul Technical University Faculty of Computer and Informatics Engineering Istanbul Turkey

ISBN: (数字)9781665470100

ISBN: (纸本)9781665470100

Anomaly detection is defined as a binary classification of normal and abnormal samples in a given data. In this task, anomalous samples are considered very rare and thus they are not used in training the deep learning model. Anomaly detection is thoroughly studied in 2D images, but 3D applications are not common yet. In this work, we combine studies in the field of 3D point cloud and anomaly detection and present a one-class classification method for 3D data. This method uses a pretrained Dynamic Graph Convolutional Neural Network (DG-CNN) to extract features from 3D point cloud data, and then fits a separate multivariate Gaussian distribution for each class. In the test phase, features are extracted from the test samples, and the distances to the distribution obtained in training indicate how anomalous the sample is for that class. Our method achieves 94.2% AUROC accuracy for the given setup. This is the first attempt to handle 3D point cloud classification as an anomaly detection case, and thus our findings and methods serve as a baseline for further studies. © 2022 IEEE.

关键词： Anomaly detection

来源：评论

学校读者我要写书评

暂无评论

Indonesian Stock Prices Prediction using Bidirectional Long Short-Term Memory 7

Indonesian Stock Prices Prediction using Bidirectional Long ...

引用

7th International Conference on Sustainable Information engineering and Technology, SIET 2022

作者： Dinata, I Gede Angga Yudistira, Novanto Muflikhah, Lailil Department of Informatics Engineering Faculty of Computer Science Brawijaya University Indonesia

ISBN: (纸本)9781450397117

This paper aims to know how well Bidirectional Long Short-Term Memory (BiLSTM) is in predicting Indonesian stock prices. First, the best hyperparameter of BiLSTM is searched through hyperparameter tuning. After finding the best hyperparameter, we train the data train containing close prices from Indonesian stock. After that, we try to find optimal days to predict by measuring the error rate using Mean Absolute Error (MAE). We also compared BiLSTM with Recurrent Neural Network (RNN) and LSTM by comparing the MAE from each method. Finally, we also tried using multivariate BiLSTM using Indonesian stock. The evaluations yield the best hyperparameters setting and how many days suitable for predicting BiLSTM performance. BiLSTM performed better than RNN and LSTM. Moreover, univariate BiLSTM performs better than multivariate BiLSTM in predicting Indonesian stock prices. © 2022 ACM.

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

Leveraging Transformer-Based Topic Modeling using BERTopic for Publication Venue Recommendation 11

Leveraging Transformer-Based Topic Modeling using BERTopic f...

引用

11th International Conference on Electrical engineering, computer Science and informatics, EECSI 2024

作者： Badieah Chaerul Haviana, Sam Farisa Mulyono, Sri Salim, Channa Abdullah Adli, Muhammad Fatih Febriansah, Moh Taufik Wiktasari Sulaiman, Noor Suhana Yaqob, Azliza Universitas Islam Sultan Agung Informatics Engineering Department Semarang Indonesia Politeknik Negeri Semarang Computer Engineering Technology Semarang Indonesia University College of TATI Faculty of Computer Media and Technology Management Terengganu Malaysia

ISBN: (纸本)9798350355314

Topic modeling has become essential in a variety of text mining applications, such as document clustering and recommendation systems. This study investigates the potential of BERTopic, a transformer-based method that leverages BERT embeddings to recommend publication venues. Traditional topic modeling methods are made better by BERTopic, which uses the deep contextual embeddings that BERT (Bidirectional Encoder Representations from Transformers) offers. This investigation assesses the efficacy of BERTopic in clustering academic papers according to their content in order to suggest appropriate publication venues. We also compare the performance between different kinds of pre-trained sentence embedding models and input types (title, abstract, and title+abstract). The experimental results indicate that BERTopic performs well with the GARUDA dataset, which comprises 5272 records from three different research subjects. The results emphasize the transformative influence of the transformer-based model. The best performance of all cases was 99.17% mean average precision in the Top 3 position, using Title+Abstract as input data and all-mpnet-base-v2 as the sentence embedding model. © 2024 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

Measuring Bug Reporter's Reputation and Its Effect on Bug Resolution Time Prediction 7

Measuring Bug Reporter's Reputation and Its Effect on Bug Re...

引用

7th International Conference on computer Science and engineering, UBMK 2022

作者： Yucel, Muhammed Kadir Tosun, Ayse Istanbul Technical University Faculty of Computer and Informatics Engineering Istanbul Turkey

ISBN: (数字)9781665470100

ISBN: (纸本)9781665470100

In software projects, bug reports remain open and get updates from team members during the related bug's lifetime. It is an important task to predict when a bug would be resolved so that managers plan timeline and allocate team resources accordingly. Prior works show that reporter information is the most effective feature for predicting resolution time. Previous work only considers bug reporting activity to define reporter reputation and misses other activities. In this paper, we propose a new reputation calculation method that considers all activities of a reporter within a bug tracking system. We collected bug reports of Chromium and WebRTC projects and calculated reputations of each bug reporter within the dataset using our weighted, activity based calculation method as well as other methods from previous work in order to compare performance. We trained a Doc2Vec model to utilize textual information in bug reports to build a base model for comparing different reputation methods. Bug reports are classified into two categories as FAST and SLOW according to their resolution time. Stochastic Gradient Descent (SGD) and Extreme Gradient Boost (XGB) classifier algorithms are employed. XGB classifier resulted with 55 % - 72 % F -Scores for FAST and SLOW respectively. The results also show that data characteristics of project affects the effectiveness of the reputation calculation method on bug resolution time prediction. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Implementation of PID Control as a One Axis Balancing Control System on the Bicopter Vehicle 2

Implementation of PID Control as a One Axis Balancing Contro...

引用

2nd International Conference on Converging Technology in Electrical and Information engineering, ICCTEIE 2023

作者： Jayadi, Akhmad Adhinata, Faisal Dharma Sembiring, Jaka Persada Putri, Novia Utami Pranita, Elka Setiawan, Arif Universitas Teknokrat Indonesian Faculty of Engineering and Computer Science Lampung Indonesia Institute Technology Telkom Purwokerto Faculty of Informatics Central Java Indonesia

ISBN: (纸本)9798350370645

This Bicopter is an unmanned aircraft with two brushless motor drive systems connected to propellers in a horizontal parallel position. The problem that often occurs in bicopters is stability or flight balance. When the vehicle cannot control or maintain its balance angle, it is most likely that the bicopter vehicle will fall while flying. Thus, a research design is carried out that can develop and overcome problems in Bicopter stability through PID Control Implementation as a One Axis Balancing Control System on the Bicopter Vehicle. This study aims to find out how to apply the PID control system as a balance controller on the bicopter and to see the results of the dynamic response generated by the PID control system using testing methods using different load weights and load positions. The research results show that the prototype of the bicopter vehicle with PID controller has been successfully made and can work well in carrying out balance control. By providing a value of Kp = 2.4329, Ki = 0.000821, Kd = 603.98901, and a Throttle of 1600 rpm, it produces a dynamic response in the form of the smallest Steady State Error value of 0.16 and the largest value of 9.29, the smallest Rise Time is 0.22s and the largest is 1.92s, The biggest overshoot is 6.68 and the smallest is -0.17. The biggest settling time is 3.36s, and the smallest is 0.92s © 2023 IEEE.

关键词： Unmanned aerial vehicles (UAV)

来源：评论

学校读者我要写书评

暂无评论

Enhancing Classification Algorithm Recommendation in Automated Machine Learning: A Meta-Learning Approach Using Multivariate Sparse Group Lasso

引用

computer Modeling in engineering & Sciences 2025年第2期142卷 1611-1636页

作者： Irfan Khan Xianchao Zhang Ramesh Kumar Ayyasamy Saadat M.Alhashmi Azizur Rahim School of Software Dalian University of TechnologyDalian116620China Faculty of Information and Communication Technology Universiti Tunku Abdul RahmanKampar31900Malaysia College of Computing and Informatics University of SharjahSharjah27272United Arab Emirates Department of Computer Systems Engineering University of Engineering and Applied SciencesSwat19200Pakistan

The rapid growth of machine learning(ML)across fields has intensified the challenge of selecting the right algorithm for specific tasks,known as the Algorithm Selection Problem(ASP).Traditional trial-and-error methods have become impractical due to their resource *** Machine Learning(AutoML)systems automate this process,but often neglect the group structures and sparsity in meta-features,leading to inefficiencies in algorithm recommendations for classification *** paper proposes a meta-learning approach using Multivariate Sparse Group Lasso(MSGL)to address these *** method models both within-group and across-group sparsity among meta-features to manage high-dimensional data and reduce multicollinearity across eight meta-feature *** Fast Iterative Shrinkage-Thresholding Algorithm(FISTA)with adaptive restart efficiently solves the non-smooth optimization *** validation on 145 classification datasets with 17 classification algorithms shows that our meta-learning method outperforms four state-of-the-art approaches,achieving 77.18%classification accuracy,86.07%recommendation accuracy and 88.83%normalized discounted cumulative gain.

关键词： Meta-learning machine learning automated machine learning classification meta-features

来源：评论

学校读者我要写书评

暂无评论

Selection of a Simple 5G Handover Algorithm: Preparation for Named Data Networking 10

Selection of a Simple 5G Handover Algorithm: Preparation for...

引用

10th International Conference on Wireless and Telematics, ICWT 2024

作者： Nurhayati, Ade Ahdan, Syaiful Juhana, Tutun Syambas, Nana Rachmana Bandung Institute of Technology School of Electrical Engineering and Informatics Bandung40132 Indonesia Telkom University Faculty of Applied Science Jakarta11710 Indonesia Universitas Teknokrat Indonesia Faculty of Engineering & Computer Science 35132 Indonesia

ISBN: (纸本)9798350377057

Named Data Networking as an alternative network for 5G network traffic is required to be able to provide better performance compared to other networks such as internet protocol networks. In NDN wireless, it is known that there is producer mobility and consumer mobility, so optimal mobility management is needed, including the handover process. In this paper the author proposes a simple RSSI-based 5G handover algorithm with distance as a reference RSSI value. This algorithm is a preparation for the handover algorithm on the NDN wireless network. By using the assumed distance value MS to eNB as the basic value for calculating RSSI, handover determination is determined by comparing the RSSI value to the RSSI threshold value. With the scenario of different numbers of users and cluster sizes, from the handover process involving 8 eNB. It can be calculated how big the handover probability is for each user. From the simulation results, it can be concluded that the more users and the larger the cluster size, the greater the handover probability value. This is linear, with the wider the cluster, the probability of getting an RSSI signal from the original eNB becomes smaller, making it possible to get an RSSI signal from neighboring eNB, so that a handover occurs. © 2024 IEEE.

关键词： 5G mobile communication systems

来源：评论

学校读者我要写书评

暂无评论

Data Analytics for Volunteer-Based Educational Application 16

Data Analytics for Volunteer-Based Educational Application

引用

16th IEEE AFRICON, AFRICON 2023

作者： Sherif, Omar Zaghloul, Yasmine Sharaf, Nada Informatics and Computer Science The German International University Cairo Egypt German International University Faculty of Engineering Cairo Egypt

ISBN: (纸本)9798350336214

In the world of technology, data have been available easily and in huge amounts. Because of the large amounts of data, Educational Data Mining (EDM) is increasingly gaining more importance. Educational data mining is trending as it is the analysis method for analyzing educational data. It involves checking the relationship between the characteristics of students and which features affect their final grades the most. It can also involve predictive modeling by predicting the final grades of students in the future to help educational institutes rescue failing students before they actually fail. Predictive analysis was the main focus in past years where most researchers targeted predicting grades of students. However, not all educational institutes are able to collect the amount of data suitable for machine learning models to achieve good accuracy. That is why the main target of the work presented in this paper is to develop an interactive interface that gives the ability to educational institutes to check by themselves the relation between different factors using correlation mining. The output of the tool is visual with message boxes to make it understandable by users. That is the best way to discover hidden patterns and trends without the need for a large amount of data in addition to removing the cost of deploying machine learning models. The second goal of the work is to give teachers the ability to check the quality of the content of their slides to help them provide a better learning process. © 2023 IEEE.

关键词： Students

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：