检索结果-内蒙古大学图书馆

2023 IEEE International Conference on Data and Software engineering, ICoDSE 2023

作者： Herimanto Dharma, Arie Satia Manurung, Hotmangasi Nababan, Agnes Bertua Del Institute of Technology Faculty of Informatics and Electrical Engineering Sitoluama Indonesia

ISBN: (纸本)9798350381382

The candidate of students have difficulty in determining which college to choose. This difficulty is due to the lack of information about the college to be addressed. One of the actions that can be taken to introduce the campus is bypromoting to high schools. To find out schools that need an in-depth introduction to the X campus, it is necessary to make a prediction system that can show the possibility of the number of registrants from these schools that are still small. In this study, a comparison between the SVR and ANN methods was carried out to determine the best model in predicting the number of prospective applicants from each school. In the process of model formation, the optimal hyperparameter is found in the model using gridsearch. To determine the best model, researchers used the smallest RMSE value obtained from both models. Based on the RMSE results obtained, the ANN model RMSE value is smaller with a value of 0.04929599755078 so this model is the best model. However, after calculating MAAPE, the ANN model has not been able to predict well. copy;2023 IEEE. © 2023 IEEE.

关键词： Neural networks

来源：评论

学校读者我要写书评

暂无评论

Predicting Students Performance Using Data Mining Approach (Case Study: IT del)

Predicting Students Performance Using Data Mining Approach (...

引用

2023 IEEE International Conference on Data and Software engineering, ICoDSE 2023

作者： Bonar Sirait, Jaime Christ Togatorop, Parmonangan R. Tambunan, Paulus M.L.P Yanti Marpaung, Yemima Febe Situmeang, Samuel I.G Simanjuntak, Humasak T.A Faculty of Informatics and Electrical Engineering Institute of Del Technology Department of Information Systems Indonesia Faculty of Informatics and Electrical Engineering Institute of Del Technology Lecturer in Department of Information Systems Indonesia

ISBN: (纸本)9798350381382

Predicting student performance stands as a critical task to comprehensively assess their academic achievements, whether they classified as the category of good, sufficient, or bad. The outcome of a student's final exam can be influenced by a multitude of factors, among which the quality of the learning process and teaching methodology hold considerable significance. Recognizing the intricate interplay of these factors, it becomes evident that the integration of a satisfaction survey becomes imperative. In the realm of this research, we harness the potential embedded within both student satisfaction survey data and their ultimate academic grades. Overcoming existing challenges by an imbalanced dataset, we employ a holistic approach by utilizing the Support Vector Machine - Synthetic Minority Oversampling Technique (SVM-SMOTE) to rectify the skewed distribution of data. To further enhance prediction capabilities, we introduced an innovative technique known as Deep Feature Synthesis. This advanced approach generating 36 novel features. The culmination of our research underscores the superiority of the random forest algorithm, especially when enriched by the harmonious merging of Deep Feature Synthesis and SVM-SMOTE through the strategic implementation of Random Search. Notably, our model achieves an impressive accuracy rate of 69%, complemented by 47% precision, 52% recall, and 47% F1-score. copy;2023 IEEE. © 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

Design and Implementation of the Ulospedia DiTenun Backend Application 29

Design and Implementation of the Ulospedia DiTenun Backend A...

引用

29th International Conference on Telecommunications, ICT 2023

作者： Barus, Arlinta Christy Argo Simanjuntak, Humasak Tommy Silalahi, Alfrendo Stenley Siregar, Gunado Del Institute of Technology Faculty of Informatics and Electrical Engineering Toba Regency Indonesia

ISBN: (纸本)9798350361100

DiTenun, also known as Digital Tenun Nusantara, is a smart device that utilizes machine learning technology to create Ulos motifs. DiTenun generates new Ulos motifs by using pre-existing motifs, ensuring that the new motifs still embody the values inherent in Ulos. Currently, DiTenun lacks a feature that can offer detailed explanations about Ulos and weavers. This includes information on types of Ulos, Ulos history, Ulos functions, products related to Ulos, and other details about Ulos and weavers. Additionally, the mechanism for storing new motifs in the process of generating motifs is currently conducted separately. As a result, users face challenges in managing data related to Ulos motifs generated through this process. Consequently, this research aims to develop a new feature, namely Ulospedia DiTenun, which is to serve as an information source about Ulos and weavers. It is also to function as a platform for managing Ulos motifs generated during the motif generation process. In this research, the development of the Ulospedia DiTenun feature is to be focused on backend applications. This includes the creation of a database using MySQL and the development of an Application Programming Interface (API) using Java Spring Boot. The results of this implementation are to be integrated into the frontend side, and API tests are to be conducted. Additionally, a web test is to be performed as a result of integrating Ulospedia DiTenun. From this study, the author has successfully built 83 (eighty-three) API endpoints, which are categorized into 14 (fourteen) resources. These endpoints have passed the second iteration test. © 2023 IEEE.

关键词： Application programming interfaces (API)

来源：评论

学校读者我要写书评

暂无评论

Addressing Scalability Issues of Blockchains with Hypergraph Payment Networks

引用

IEEE Transactions on Network and Service Management 2025年第3期22卷 2427-2440页

作者： Kotzer, Arad Ladoczki, Bence Tapolcai, Janos Rottenstreich, Ori Technion -Israel Institute of Technology Haifa Israel Budapest University of Technology and Economics Department of Telecommunications and Artificial Intelligence Faculty of Electrical Engineering and Informatics Hungary

Payment channels are auspicious candidates in layer-2 solutions to reduce the number of on-chain transactions on traditional blockchains and increase transaction throughput. To construct payment channels, peers lock funds on 2-of-2 multisig addresses and open channels between one another to transact via instant peer-to-peer transactions. Transactions between peers without a direct channel are made possible by routing the payment over a series of adjacent channels. In certain cases, this can lead to relatively low transaction success rates and high transaction fees. In this work, we introduce pliability to constructing payment channels and graft edges with more than two endpoints into the payment graph. We refer to these constructions as hyperedges. We present hyperedge-based topologies to form hypergraphs and compare them to Bitcoin's Lightning network and other state-of-the-art solutions. The results demonstrate that hyperedge-based implementations can both increase transaction success rate, in addition to decreasing the network cost by more than 50% compared to that of the Lightning Network. © 2004-2012 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Website Functionality Testing Using the Automation Tool

Website Functionality Testing Using the Automation Tool

引用

2023 IEEE International Conference on Data and Software engineering, ICoDSE 2023

作者： Barus, Arlinta Christy Sembiring, Aprialdy Faculty of Informatics and Electrical Engineering Del. Institute of Technology Laguboti Informatics Department North Sumatera Indonesia

ISBN: (纸本)9798350381382

The DiTenun website is a web-based software developed to create new motifs or new weaving patterns. The motifs are made using variations of motifs from existing traditional weaving and new motifs produced by the DiTenun application. The DiTenun website itself researches to classify Nusantara weaving, generate new motifs quickly and automatically, preserve Indonesian culture and make it practically universally accessible. The DiTenun website also still has weaknesses. The weaknesses analyzed are the functional aspects of the DiTenun website. The weakness that is analyzed is to test every function contained on the DiTenun website. This test perform with blackbox test method using Specification Based Test Technique. To see how much influence the use of Specification Based Test has in testing the functionality of a website, a comparison is also made with the Random Test technique as a baseline for comparison. After the test results with the two techniques are obtained, then a comparison is made to the number of types of errors obtained by the two techniques. copy;2023 IEEE. © 2023 IEEE.

关键词： Websites

来源：评论

学校读者我要写书评

暂无评论

Dispositions as an Important Component in Computing Curriculum in IT del

Dispositions as an Important Component in Computing Curricul...

引用

2023 IEEE International Conference on Data and Software engineering, ICoDSE 2023

作者： Barus, Arlinta Liem, Inggriani Sihombing, Tahan Sinaga, Arnaldo Sinambela, Eka Silalahi, Sari Del Institute of Technology Faculty of Informatics and Electrical Engineering North Sumatera Laguboti22381 Indonesia Del Institute of Technology Faculty of Vocational North Sumatera Laguboti22381 Indonesia

ISBN: (纸本)9798350381382

Insitut Teknologi del (IT del), formerly recognized as Politeknik Informatika del (PI del), has consistently maintained its emphasis on the computing curriculum, establishing it as the institution's primary domain of expertise since its founding. Being recognized as a campus with its high employability rate, this paper aims to describe how IT del develops its computing curriculum in connection to its involvement in the Decart project. This paper first presents the Indonesia curriculum guideline. This is followed by the discussion of the development process of computing curriculum emphasizing three components: knowledge, skills, and dispositions. The last component is believed to be one of the important components aimed to prepare graduates to have 21st century skills. Then we relate them to the involvement of IT del in the DECART project, funded by Erasmus Mundus. The purpose of this paper is to demonstrate that our existing curriculum development approach has been successful to build expected graduates' competence. This is expected to give an insight to define an agile curriculum framework to face the VUCA world as one of the objectives for the DECART project. copy;2023 IEEE. © 2023 IEEE.

关键词： 21st century skills Computing Curriculum Disposition Graduate Competence

来源：评论

学校读者我要写书评

暂无评论

Design and Evaluation of AKP Application 14

Design and Evaluation of AKP Application

引用

14th International Conference on Advanced Computer Science and Information Systems, ICACSIS 2022

作者： Simbolon, Iustisia Natalia Silitonga, Devi Wahyuni Bakara, Putri Era Waty Del Institute of Technology Faculty of Informatics and Electrical Engineering Laguboti Indonesia

ISBN: (数字)9781665489362

ISBN: (纸本)9781665489362

The Akuntabilitas Kinerja Pemerintah (AKP) Application is a website-based application that functions to collect, manage, measure, report, and store all reports of work in Kemenko Marves. The purpose of developing the AKP application is to centralize the mechanism for reporting work results with the same reporting standards. The AKP application interface to be built uses the User Centered Design (UCD) method. The AKP application interface will then carry out testing to find usability problems in the initial AKP application prototype. The AKP application testing in this study was carried out in two iterations. The first iteration test was carried out using the Cognitive Walkthrough and Heuristic Evaluation methods from the expert's point of view and the Think Aloud method from the end user side. While the second iteration test, only uses the Think Aloud method. After conducting usability testing, a final high-fidelity prototype of the AKP application will be built. Based on the results of the final prototype, usability testing was carried out using the SUS questionnaire to re-measure the usability level of the AKP application prototype. The target score for the usability value that is expected from this research is 80 (Grade Scale B). Before making improvements to the initial design of the AKP application, the SUS score was 79.5 (Grade Scale = C). However, after improvements were made to the AKP application design, the SUS score became 84 (Grade Scale = B). Based on the test results, the usability score increased by 4.5 and has reached the research target. © 2022 IEEE.

关键词： User interfaces

来源：评论

学校读者我要写书评

暂无评论

Influence of Relief Feature Selection on Random Forest and Support Vector Machine Classification Algorithm 7

Influence of Relief Feature Selection on Random Forest and S...

引用

7th International Workshop on Big Data and Information Security, IWBIS 2022

作者： Simbolon, Iustisia Natalia Naibaho, Romual Del Institute of Technology Faculty of Informatics and Electrical Engineering Laguboti Indonesia

ISBN: (数字)9781665489508

ISBN: (纸本)9781665489508

The classification technique is one of the popular techniques used in helping humans decide the target class of a data based on machine learning principles. Unfortunately the construction of a classification model has no limits and will always evolve over time. There is no surefire way to make a perfect classification model, but there are ways that at least make the classification model better. This study applies the feature selection method to produce a more optimal classification model accuracy value. Of the many feature selection algorithms, this research chooses Relief which is combined with a classification algorithm, namely Random Forest and Support Vector Machine. This research also applies the Grid Search Optimization method in selecting the most influential features. In addition, it is also used to select the best hyperparameters to build the classification model. For splitting the data set, the K Fold Cross Validation technique is used in order to get the most optimal proportion of data splitting. Compared to the accuracy values before and after feature selection, both classification algorithms after feature selection significantly outperform the classification model before feature selection. It was also found that the model's capabilities in the real world, through validation with new data, performed quite well. © 2022 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

A MLP-Mixer and mixture of expert model for remaining useful life prediction of lithium-ion batteries

引用

Frontiers of Computer Science 2024年第5期18卷 1-10页

作者： Lingling ZHAO Shitao SONG Pengyan WANG Chunyu WANG Junjie WANG Maozu GUO Faculty of Computing Harbin Institute of TechnologyHarbin 150001China School of Electrical Engineering Liaoning University of TechnologyJinzhou 121004China School of Computer Science Northeast Electric Power UniversityJilin 132000China Department of Medical Informatics School of Biomedical Engineering and InformaticsNanjing Medical UniversityNanjing 211166China School of Electrical and Information Engineering Beijing University of Civil Engineering and ArchitectureBeijing 100044China

Accurately predicting the Remaining Useful Life(RUL)of lithium-ion batteries is crucial for battery management *** learning-based methods have been shown to be effective in predicting RUL by leveraging battery capacity time series ***,the representation learning of features such as long-distance sequence dependencies and mutations in capacity time series still needs to be *** address this challenge,this paper proposes a novel deep learning model,the MLP-Mixer and Mixture of Expert(MMMe)model,for RUL *** MMMe model leverages the Gated Recurrent Unit and Multi-Head Attention mechanism to encode the sequential data of battery capacity to capture the temporal features and a re-zero MLP-Mixer model to capture the high-level ***,we devise an ensemble predictor based on a Mixture-of-Experts(MoE)architecture to generate reliable RUL *** experimental results on public datasets demonstrate that our proposed model significantly outperforms other existing methods,providing more reliable and precise RUL predictions while also accurately tracking the capacity degradation *** code and dataset are available at the website of github.

关键词： lithium-ion battery remaining useful life deep learning MLP-Mixer mixture-of-experts

来源：评论

学校读者我要写书评

暂无评论

Enhancing Urban Waste Management: An IoT and LoRa-Integrated Smart Bin System for Volume Monitoring and Analysis 4

Enhancing Urban Waste Management: An IoT and LoRa-Integrated...

引用

4th International Conference on Intelligent Cybernetics technology and Applications, ICICyTA 2024

作者： Imanudin, Muhammad Farhan Kinanda, Rezky Falih, Noor Arman, Arry Akhmad Sembiring, Emenda Supangkat, Suhono Harso School of Electrical and Informatics Engineering Bandung Institute of Technology Bandung Indonesia Bandung Institute of Technology Faculty of Civil and Environmental Engineering Bandung Indonesia

ISBN: (纸本)9798331506490

Waste management in urban areas has become an increasingly pressing challenge in Indonesia, given the population of 270.20 million people. Rapid urbanization and population growth have led to rising waste generation, creating significant environmental and logistical issues. This study proposes the development of a smart waste bin system utilizing Internet of Things (IoT) and LoRa technology, designed to monitor waste volume in real-time and optimize waste management processes. The system is structured around three main components: Sensor Nodes, a Gateway, and a Data Platform & Analytics. The Sensor Nodes, equipped with ultrasonic level sensors, measure the fill level of waste bins, and identify different types of waste. This data is then transmitted via LoRa technology to the Gateway, which serves as the communication bridge to a centralized platform. The Data Platform & Analytics processes the incoming information, providing valuable insights to optimize waste collection routes and schedules. By implementing an IoT-based approach, waste management authorities can make informed decisions, reduce operational costs, and minimize the carbon footprint associated with waste collection. Additionally, this system addresses waste accumulation issues in major cities and supports long-term sustainability strategies by promoting more efficient resource management. The research also aims to increase public awareness of the importance of responsible waste disposal and to encourage the adoption of a circular economy that transforms waste into valuable resources. Overall, this innovation holds the potential to revolutionize urban waste management and contribute significantly to Indonesia's environmental and sustainability goals. © 2024 IEEE.

关键词： Circular economy

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：