Computer Science and Information Systems最新文献_第6页

Analyzing feature importance for a predictive undergraduate student dropout model 预测大学生辍学模型的特征重要性分析

IF 1.4 4区计算机科学

Computer Science and Information Systems Pub Date : 2023-01-01 DOI: 10.2298/csis211110050j

Alberto Jiménez-Macías, Pedro Manuel Moreno-Marcos, P. Muñoz-Merino, Margarita Ortiz-Rojas, C. D. Kloos

{"title":"Analyzing feature importance for a predictive undergraduate student dropout model","authors":"Alberto Jiménez-Macías, Pedro Manuel Moreno-Marcos, P. Muñoz-Merino, Margarita Ortiz-Rojas, C. D. Kloos","doi":"10.2298/csis211110050j","DOIUrl":"https://doi.org/10.2298/csis211110050j","url":null,"abstract":"Worldwide, one of the main concerns of universities is to reduce the dropout rate. Several initiatives have been taken to avoid this problem; however, it is essential to recognize at-risk students as early as possible. This article is an extension of a previous study that proposed a predictive model to identify students at risk of dropout from the beginning of their university degree. The new contribution is the analysis of the feature importance for dropout segmented by faculty, degree program, and semester in the different predictive models. In addition, we propose a dropout model based on faculty characteristics to try to infer the dropout based on faculty features. We used data of 30,576 students enrolled in a Higher Education Institution ranging from years 2000 to 2020. The findings indicate that the variables related to Grade Point Average(GPA), socioeconomic factor, and a pass rate of courses taken have a more significant impact on the model, regardless of the semester, faculty, or program. Additionally, we found a significant difference in the predictive power between Science, Technology, Engineering, and Mathematics (STEM) and humanistic programs.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80524241","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Personalization exercise recommendation framework based on knowledge concept graph 基于知识概念图的个性化习题推荐框架

IF 1.4 4区计算机科学

Computer Science and Information Systems Pub Date : 2023-01-01 DOI: 10.2298/csis220706024y

Zhang Yan, Hongle Du, Zhang Lin, Jianhua Zhao

{"title":"Personalization exercise recommendation framework based on knowledge concept graph","authors":"Zhang Yan, Hongle Du, Zhang Lin, Jianhua Zhao","doi":"10.2298/csis220706024y","DOIUrl":"https://doi.org/10.2298/csis220706024y","url":null,"abstract":"With the explosive increase of online learning resources, how to provide students with personalized learning resources and achieve the goal of precise teaching has become a research hotspot in the field of computer-assisted teaching. In personalized learning resource recommendation, exercise recommendation is the most commonly used and most representative research direction, which has attracted the attention of a large number of scholars. Aiming at this, a personalized exercise recommendation framework is proposed in this paper. First, it automatically constructs the relationship matrix between questions and concepts based on students' answering records (abbreviated as Q-matrix). Then based on the Q-matrix and answer records, deep knowledge tracing is used to automatically build the course knowledge graph. Then, based on each student's answer records, Q-matrix and the course knowledge graph, a recommendation algorithm is designed to obtain the knowledge structure diagram of every student. Combined the knowledge structure diagram and constructivist learning theory, get candidate recommended exercises from the exercise bank. Finally, based on their diversity, difficulty, novelty and other characteristics, exercises are filtered and obtain the exercises recommended to students. In the experimental part, the proposed framework is compared with other algorithms on the real data set. The experimental results of the proposed algorithm are close to the current mainstream algorithms without the Q-matrix and curriculum knowledge graph, and the experimental results of some indicators are better than Algorithms exist.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81625080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Multi-perspective approach for curating and exploring the history of climate change in Latin America within digital newspapers 在数字报纸中策划和探索拉丁美洲气候变化历史的多视角方法

IF 1.4 4区计算机科学

Computer Science and Information Systems Pub Date : 2023-01-01 DOI: 10.2298/csis220110008v

Genoveva Vargas-Solar, J. Zechinelli-Martini, Javier-Alfonso Espinosa-Oviedo, Luis Manuel Vilches Blázquez

{"title":"Multi-perspective approach for curating and exploring the history of climate change in Latin America within digital newspapers","authors":"Genoveva Vargas-Solar, J. Zechinelli-Martini, Javier-Alfonso Espinosa-Oviedo, Luis Manuel Vilches Blázquez","doi":"10.2298/csis220110008v","DOIUrl":"https://doi.org/10.2298/csis220110008v","url":null,"abstract":"This paper introduces a multi-perspective approach to deal with curation and exploration issues in historical newspapers. It has been implemented in the platform LACLICHEV (Latin American Climate Change Evolution platform). Exploring the history of climate change through digitalized newspapers published around two centuries ago introduces four challenges: (1) curating content for tracking entries describing meteorological events; (2) processing (digging into) colloquial language (and its geographic variations5) for extracting meteorological events; (3) analyzing newspapers to discover meteorological patterns possibly associated with climate change; (4) designing tools for exploring the extracted content. LACLICHEV provides tools for curating, exploring, and analyzing historical news paper articles, their description and location, and the vocabularies used for referring to meteorological events. This platform makes it possible to understand and identify possible patterns and models that can build an empirical and social view of the history of climate change in the Latin American region.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81007825","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

DG_summ: A schema-driven approach for personalized summarizing heterogeneous data graphs dg_sum:用于个性化汇总异构数据图的模式驱动方法

4区计算机科学

Computer Science and Information Systems Pub Date : 2023-01-01 DOI: 10.2298/csis230331062b

Amal Beldi, Salma Sassi, Richard Chbeir, Abderrazek Jemai

{"title":"DG_summ: A schema-driven approach for personalized summarizing heterogeneous data graphs","authors":"Amal Beldi, Salma Sassi, Richard Chbeir, Abderrazek Jemai","doi":"10.2298/csis230331062b","DOIUrl":"https://doi.org/10.2298/csis230331062b","url":null,"abstract":"Advances in computing resources have enabled the processing of vast amounts\u0000 of data. However, identifying trends in such data remains challenging for\u0000 humans, especially in fields like medicine and social networks. These\u0000 challenges make it difficult to process, analyze, and visualize the data. In\u0000 this context, graph summarization has emerged as an effective framework\u0000 aiming to facilitate the identification of structure and meaning in data.\u0000 The problem of graph summarization has been studied in the literature and\u0000 many approaches for static contexts are proposed to summarize the graph.\u0000 These approaches provide a compressed version of the graph that removes many\u0000 details while retaining its essential structure. However, they are\u0000 computationally prohibitive and do not scale to large graphs in terms of\u0000 both structure and content. Additionally, there is no framework providing\u0000 summarization of mixed sources with the goal of creating a dynamic,\u0000 syntactic, and semantic data summary. In this paper, our key contribution is\u0000 focused on modeling data graphs, summarizing data from multiple sources\u0000 using a schema-driven approach, and visualizing the graph summary version\u0000 according to the needs of each user. We demonstrate this approach through a\u0000 case study on the use of the E-health domain.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135400715","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

SRDF_QDAG: An efficient end-to-end RDF data management when graph exploration meets spatial processing SRDF_QDAG:当图探索遇到空间处理时，有效的端到端RDF数据管理

4区计算机科学

Computer Science and Information Systems Pub Date : 2023-01-01 DOI: 10.2298/csis230225046y

Houssameddine Yousfi, Amin Mesmoudi, Allel Hadjali, Houcine Matallah, Seif-Eddine Benkabou

{"title":"SRDF_QDAG: An efficient end-to-end RDF data management when graph exploration meets spatial processing","authors":"Houssameddine Yousfi, Amin Mesmoudi, Allel Hadjali, Houcine Matallah, Seif-Eddine Benkabou","doi":"10.2298/csis230225046y","DOIUrl":"https://doi.org/10.2298/csis230225046y","url":null,"abstract":"The popularity of RDF has led to the creation of several datasets (e.g., Yago, DBPedia) with different natures (graph, temporal, spatial). Different extensions have also been proposed for SPARQL language to provide appropriate processing. The best known is GeoSparql, that allows the integration of a set of spatial operators. In this paper, we propose new strategies to support such operators within a particular TripleStore, named RDF QDAG, that relies on graph fragmentation and exploration and guarantees a good compromise between scalability and performance. Our proposal covers the different TripleStore components (Storage, evaluation, optimization). We evaluated our proposal using spatial queries with real RDF data, and we also compared performance with the latest version of a popular commercial TripleStore. The first results demonstrate the relevance of our proposal and how to achieve an average gain of performance of 28% by choosing the right evaluation strategies to use. Based on these results, we proposed to extend the RDF QDAG optimizer to dynamically select the evaluation strategy to use depending on the query. Then, we show also that our proposal yields the best strategy for most queries.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"136208668","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Knowledge transfer in multi-objective multi-agent reinforcement learning via generalized policy improvement 基于广义策略改进的多目标多智能体强化学习中的知识转移

4区计算机科学

Computer Science and Information Systems Pub Date : 2023-01-01 DOI: 10.2298/csis221210071a

Almeida de, Lucas Alegre, Ana Bazzan

{"title":"Knowledge transfer in multi-objective multi-agent reinforcement learning via generalized policy improvement","authors":"Almeida de, Lucas Alegre, Ana Bazzan","doi":"10.2298/csis221210071a","DOIUrl":"https://doi.org/10.2298/csis221210071a","url":null,"abstract":"Even though many real-world problems are inherently distributed and multi-objective, most of the reinforcement learning (RL) literature deals with single agents and single objectives. While some of these problems can be solved using a single-agent single-objective RL solution (e.g., by specifying preferences over objectives), there are robustness issues, as well the fact that preferences may change over time, or it might not even be possible to set such preferences. Therefore, a need arises for a way to train multiple agents for any given preference distribution over the objectives. This work thus proposes a multi-objective multi-agent reinforcement learning (MOMARL) method in which agents build a shared set of policies during training, in a decentralized way, and then combine these policies using a generalization of policy improvement and policy evaluation (fundamental operations of RL algorithms) to generate effective behaviors for any possible preference distribution, without requiring any additional training. This method is applied to two different application scenarios: a multi-agent extension of a domain commonly used in the related literature, and traffic signal control, which is more complex, inherently distributed and multi-objective (the flow of both vehicles and pedestrians are considered). Results show that the approach is able to effectively and efficiently generate behaviors for the agents, given any preference over the objectives.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135446685","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Robust compensation with adaptive fuzzy Hermite neural networks in synchronous reluctance motors 同步磁阻电动机的自适应模糊Hermite神经网络鲁棒补偿

4区计算机科学

Computer Science and Information Systems Pub Date : 2023-01-01 DOI: 10.2298/csis230803076c

Chao-Ting Chu, Hao-Shang Ma

{"title":"Robust compensation with adaptive fuzzy Hermite neural networks in synchronous reluctance motors","authors":"Chao-Ting Chu, Hao-Shang Ma","doi":"10.2298/csis230803076c","DOIUrl":"https://doi.org/10.2298/csis230803076c","url":null,"abstract":"In this paper, a robust compensation scheme using adaptive fuzzy Hermite neural networks (RCAFHNN), for use in synchronous reluctancemotors (SRMs), is proposed. SRMs have a simple underlying mathematical model and mechanical structure, but are affected by problems related to parameter variations, external interference, and nonlinear dynamics. In many fields, precise control of motors is required. Although the use of neural network and fuzzy are widespread, such controllers are affected by unbound nonlinear system model. In this study, RCAFHNN, based on an adaptive neural fuzzy interface system (ANFIS), was used to bound motor system model controller algorithm. RCAFHNN can be characterized in three parts. First, RCAFHNN offers fuzzy expert knowledge, a neural network for online estimation, and recursive weight estimation. Second, the replacement of the Gaussian function by the Hermite polynomial in RCAFHNN enables reduced member ship function training times. Third, the system convergence and robustness compensation of RCAFHNN were confirmed using Lyapunov stability. RCAFHNN amelio rates the problems of external load and system lump uncertainty. The experimental results, in which the output responses of RCAFHNN and ANFIS (adaptive neural fuzzy interface systems) were compared, demonstrated that RCAFHNN exhibited superior performance.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"135446871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Selective ensemble learning algorithm for imbalanced dataset 不平衡数据集的选择性集成学习算法

IF 1.4 4区计算机科学

Computer Science and Information Systems Pub Date : 2023-01-01 DOI: 10.2298/csis220817023d

Hongle Du, Yan Zhang, Lin Zhang, Yeh-Cheng Chen

{"title":"Selective ensemble learning algorithm for imbalanced dataset","authors":"Hongle Du, Yan Zhang, Lin Zhang, Yeh-Cheng Chen","doi":"10.2298/csis220817023d","DOIUrl":"https://doi.org/10.2298/csis220817023d","url":null,"abstract":"Under the imbalanced dataset, the performance of the base-classifier, the computing method of weight of base-classifier and the selection method of the base-classifier have a great impact on the performance of the ensemble classifier. In order to solve above problem to improve the generalization performance of ensemble classifier, a selective ensemble learning algorithm based on under-sampling for imbalanced dataset is proposed. First, the proposed algorithm calculates the number K of under-sampling samples according to the relationship between class sample density. Then, we use the improved K-means clustering algorithm to under-sample the majority class samples and obtain K cluster centers. Then, all cluster centers (or the sample of the nearest cluster center) are regarded as new majority samples to construct a new balanced training subset combine with the minority class?s samples. Repeat those processes to generate multiple training subsets and get multiple base-classifiers. However, with the increasing of iterations, the number of base-classifiers increase, and the similarity among the base-classifiers will also increase. Therefore, it is necessary to select some base-classifier with good classification performance and large difference for ensemble. In the stage of selecting base-classifiers, according to the difference and performance of base-classifiers, we use the idea of maximum correlation and minimum redundancy to select base-classifiers. In the ensemble stage, G-mean or F-mean is selected to evaluate the classification performance of base-classifier for imbalanced dataset. That is to say, it is selected to compute the weight of each base-classifier. And then the weighted voting method is used for ensemble. Finally, the simulation results on the artificial dataset, UCI dataset and KDDCUP dataset show that the algorithm has good generalization performance on imbalanced dataset, especially on the dataset with high imbalance degree.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81956810","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Guest editorial - Management of digital ecosystems 客座社论-数字生态系统的管理

IF 1.4 4区计算机科学

Computer Science and Information Systems Pub Date : 2023-01-01 DOI: 10.2298/csis230100viib

D. Benslimane, Z. Maamar, Ladjel Bellatreche

引用次数: 0

A novel multi-objective learning-to-rank method for software defect prediction 一种新的软件缺陷预测的多目标学习排序方法

IF 1.4 4区计算机科学

Computer Science and Information Systems Pub Date : 2023-01-01 DOI: 10.2298/csis220830036c

Yiji Chen, Lianglin Cao, Li Song

{"title":"A novel multi-objective learning-to-rank method for software defect prediction","authors":"Yiji Chen, Lianglin Cao, Li Song","doi":"10.2298/csis220830036c","DOIUrl":"https://doi.org/10.2298/csis220830036c","url":null,"abstract":"Search-Based Software Engineering (SBSE) is one of the techniques used for software defect prediction (SDP), in which search-based optimization algorithms are used to identify the optimal solution to construct a prediction model. As we know, the ranking methods of SBSE are used to solve insufficient sample problems, and the feature selection approaches of SBSE are employed to enhance the prediction model?s performance with curse-of-dimensionality or class imbalance problems. However, it is ignored that there may be a complex problem in the process of building prediction models consisting of the above problems. To address the complex problem, two multi-objective learning-to-rank methods are proposed, which are used to search for the optimal linear classifier model and reduce redundant and irrelevant features. To evaluate the performance of the proposed methods, excessive experiments have been conducted on 11 software programs selected from the NASA repository and AEEEM repository. Friedman?s rank test results show that the proposed method using NSGA-II outperforms other state-of-the-art single objective methods for software defect prediction.","PeriodicalId":50636,"journal":{"name":"Computer Science and Information Systems","volume":null,"pages":null},"PeriodicalIF":1.4,"publicationDate":"2023-01-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85144642","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0