Pub Date : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982412
Samuel Zico Christopher, T. Siswantining, Devvi Sarwinda, Alhadi Bustaman
One of the solutions of missing value in a survey is imputation. Imputation is a method to replace the missing value with the imputed value from a particular technique, such as mean value, median value, etc. This paper specifically discusses a technique that fuses fractional imputation technique and hot-deck imputation technique. Fractional imputation is popular because this imputation tends to produce lower standard error compared to other methods. Unfortunately, fractional imputation tends to extend the number of observations. Because of the observation extension, sampling becomes a solution to produce less observation. Sampling limits the numbers of imputed values (donor) in the observations by using hot deck imputation nature. The imputation that fuses fractional imputation and hot-deck imputation is known as the fractional hot deck. This paper presents three things about fractional hot deck imputation, first, it shows that the result of fractional hot deck imputation produces fewer donor than fractional imputation, but still has a similar property to fractional imputation that presented in linear regression; Second, it presents an additional information about it's effect on modifying it's k-value in discretization step and the standard error of regression; Third, it presents the comparison of standard errors with fractional imputation, listwise deletion, mean imputation, and median imputation.
{"title":"Missing Value Analysis of Numerical Data using Fractional Hot Deck Imputation","authors":"Samuel Zico Christopher, T. Siswantining, Devvi Sarwinda, Alhadi Bustaman","doi":"10.1109/ICICoS48119.2019.8982412","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982412","url":null,"abstract":"One of the solutions of missing value in a survey is imputation. Imputation is a method to replace the missing value with the imputed value from a particular technique, such as mean value, median value, etc. This paper specifically discusses a technique that fuses fractional imputation technique and hot-deck imputation technique. Fractional imputation is popular because this imputation tends to produce lower standard error compared to other methods. Unfortunately, fractional imputation tends to extend the number of observations. Because of the observation extension, sampling becomes a solution to produce less observation. Sampling limits the numbers of imputed values (donor) in the observations by using hot deck imputation nature. The imputation that fuses fractional imputation and hot-deck imputation is known as the fractional hot deck. This paper presents three things about fractional hot deck imputation, first, it shows that the result of fractional hot deck imputation produces fewer donor than fractional imputation, but still has a similar property to fractional imputation that presented in linear regression; Second, it presents an additional information about it's effect on modifying it's k-value in discretization step and the standard error of regression; Third, it presents the comparison of standard errors with fractional imputation, listwise deletion, mean imputation, and median imputation.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125691217","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982530
Amazona Adorada, A. Wibowo
Breast cancer is one of the most common types of cancer found in women. Breast cancer mortality increases every year because it has not found an appropriate early detection method. MicroRNA can be used as a potential biomarker, because the profile of the microRNA feature in breast cancer will decrease or increase the value of expression compared to normal conditions. But because of the thousands of types of microRNA that make up breast cancer, a lot of money is needed to detect it entirely. Backpropagation Artificial Neural Network Method has good performance in generalization, so it is suitable to be used as a method for classification with many features. The classification results from the neural network model will be more accurate if the parameters used can be optimized precisely. Genetic algorithms can be used to optimize backpropagation neural network parameters as well as feature selection, because of its global search characteristics. This study aims to compare the performance of backpropagation artificial neural networks optimized parameters as well as feature selection using genetic algorithms (GABPNN_ FS) with backpropagation artificial neural networks optimized using genetic algorithms without feature selection (GABPNN). The results showed that the GABPNN had better results with an error value of 0.016115. But GABPNN_ FS has a faster average process duration of 53.2689 seconds. The best individual chromosome translation results on GABPNN_ FS for breast cancer classification based on microRNA profile are random state = 6098, learning rate = 0.7, number of neuron hidden = 6, and selected features = 707 features that produce accuracy, sensitivity, and specificity ie 97.50 %, 99.00% and 96.00%.
{"title":"Genetic Algorithm-Based Feature Selection and Optimization of Backpropagation Neural Network Parameters for Classification of Breast Cancer Using MicroRNA Profiles","authors":"Amazona Adorada, A. Wibowo","doi":"10.1109/ICICoS48119.2019.8982530","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982530","url":null,"abstract":"Breast cancer is one of the most common types of cancer found in women. Breast cancer mortality increases every year because it has not found an appropriate early detection method. MicroRNA can be used as a potential biomarker, because the profile of the microRNA feature in breast cancer will decrease or increase the value of expression compared to normal conditions. But because of the thousands of types of microRNA that make up breast cancer, a lot of money is needed to detect it entirely. Backpropagation Artificial Neural Network Method has good performance in generalization, so it is suitable to be used as a method for classification with many features. The classification results from the neural network model will be more accurate if the parameters used can be optimized precisely. Genetic algorithms can be used to optimize backpropagation neural network parameters as well as feature selection, because of its global search characteristics. This study aims to compare the performance of backpropagation artificial neural networks optimized parameters as well as feature selection using genetic algorithms (GABPNN_ FS) with backpropagation artificial neural networks optimized using genetic algorithms without feature selection (GABPNN). The results showed that the GABPNN had better results with an error value of 0.016115. But GABPNN_ FS has a faster average process duration of 53.2689 seconds. The best individual chromosome translation results on GABPNN_ FS for breast cancer classification based on microRNA profile are random state = 6098, learning rate = 0.7, number of neuron hidden = 6, and selected features = 707 features that produce accuracy, sensitivity, and specificity ie 97.50 %, 99.00% and 96.00%.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133684997","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982506
Mochamad Umar Al Hafidz, D. I. Sensuse
Abstraet-Scrum as one of a popular agile frameworks is quite flexible to changes. However, this behavior is accompanied by several shortcomings, especially the documentation section since its dependence on direct communication. Therefore, the use of knowledge management in Scrum seems to be important. Knowledge management in Scrum was influenced by several challenges such as the various locations of the team members, the changes of software developers, the methods for large-scale projects, and the needs for high-quality software. These problems need to be resolved to avoid the amount of knowledge loss. Therefore researchers want to find out more about how knowledge management system influences the development of scrum-based software and its effect on developers' performance. This study uses a quasi-experimental approach with the application in the real world to startup companies. A quasi-experimental is research method used to compare the effect before and after treatment in a group by comparing the performance conditions before and after the implementation of the knowledge management system. The data collected from experiment are scrum artefact, knowledge artefact, and developers' performance (using IWQP). The first experiment for the group lasted for two sprints using a scrum support system. Knowledge management system based scrum used for the second experiment. The findings obtained were an increase in adaptation performance of 8%, contextual performance of 12%, and improvement of knowledge circulation from the development team. The Knowledge Management System is proven to be able to improve and handle the knowledge circulation in Scrum and give impact to software developers.
{"title":"The Effect of Knowledge Management System on Software Development Process with Scrum","authors":"Mochamad Umar Al Hafidz, D. I. Sensuse","doi":"10.1109/ICICoS48119.2019.8982506","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982506","url":null,"abstract":"Abstraet-Scrum as one of a popular agile frameworks is quite flexible to changes. However, this behavior is accompanied by several shortcomings, especially the documentation section since its dependence on direct communication. Therefore, the use of knowledge management in Scrum seems to be important. Knowledge management in Scrum was influenced by several challenges such as the various locations of the team members, the changes of software developers, the methods for large-scale projects, and the needs for high-quality software. These problems need to be resolved to avoid the amount of knowledge loss. Therefore researchers want to find out more about how knowledge management system influences the development of scrum-based software and its effect on developers' performance. This study uses a quasi-experimental approach with the application in the real world to startup companies. A quasi-experimental is research method used to compare the effect before and after treatment in a group by comparing the performance conditions before and after the implementation of the knowledge management system. The data collected from experiment are scrum artefact, knowledge artefact, and developers' performance (using IWQP). The first experiment for the group lasted for two sprints using a scrum support system. Knowledge management system based scrum used for the second experiment. The findings obtained were an increase in adaptation performance of 8%, contextual performance of 12%, and improvement of knowledge circulation from the development team. The Knowledge Management System is proven to be able to improve and handle the knowledge circulation in Scrum and give impact to software developers.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"21 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130532538","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982406
Nadya Safitri, N. Pohan, D. I. Sensuse, Deki Satria, Shidiq Al Hakim
Universitas indonesia's learning system called SCeLE that it still lacks use by learners in Universitas Indonesia. Its impacts not yet give satisfaction to them. Therefore, It needs to evaluate SCeLE Universitas Indonesia. The model is a modification of the Delone and McLean's model. It examined using a survey by questionnaire and distributed to learners experience using SCeLE Universitas Indonesia. The data used and analyzed using SmartPLS 3. From 78 usable data, its found system quality, perceived usefulness, peer influence, subjective norms have a significant affect on learner satisfaction. Service quality, course quality, and lecturer quality do not have a significant affect on learner satisfaction. Research findings in the model can use a reference for the next paper using sample data from other university case studies.
印尼大学的学习系统称为SCeLE，但仍缺乏印尼大学学习者的使用。它的影响还没有让他们满意。因此，它需要评估SCeLE Universitas Indonesia。该模型是对Delone和McLean模型的修改。它通过问卷调查进行了审查，并向学习者分发了使用印度尼西亚SCeLE大学的经验。数据使用和分析使用SmartPLS 3。从78个可用数据中发现，系统质量、感知有用性、同伴影响、主观规范对学习者满意度有显著影响。服务质量、课程质量和讲师质量对学习者满意度没有显著影响。模型的研究成果可以为下一篇使用其他大学案例研究样本数据的论文提供参考。
{"title":"An Assesment of Knowledge Sharing System: SCeLE Universitas Indonesia","authors":"Nadya Safitri, N. Pohan, D. I. Sensuse, Deki Satria, Shidiq Al Hakim","doi":"10.1109/ICICoS48119.2019.8982406","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982406","url":null,"abstract":"Universitas indonesia's learning system called SCeLE that it still lacks use by learners in Universitas Indonesia. Its impacts not yet give satisfaction to them. Therefore, It needs to evaluate SCeLE Universitas Indonesia. The model is a modification of the Delone and McLean's model. It examined using a survey by questionnaire and distributed to learners experience using SCeLE Universitas Indonesia. The data used and analyzed using SmartPLS 3. From 78 usable data, its found system quality, perceived usefulness, peer influence, subjective norms have a significant affect on learner satisfaction. Service quality, course quality, and lecturer quality do not have a significant affect on learner satisfaction. Research findings in the model can use a reference for the next paper using sample data from other university case studies.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115735160","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982503
F. A. Nugroho, T. Ederveen, A. Wibowo, J. Boekhorst, M. D. de Jonge, T. Heskes
Most clinical studies are descriptive, measuring different parameters that are associated with certain treatment effects, while causal relations cannot be confirmed. Computational models aid researchers to make predictions of causality and help to focus on the most relevant part of the data. This study used a computational model to find a causal link between iron supplementation effectiveness, RTI, and systemic inflammation parameters, and gut microbiome profiles. We used a causal discovery algorithm on a randomized controlled trial dataset (n=72) of 6 month-old infants from Kenya. We also used correlation and partial correlation to determine the causal effect of any causal link. We found that (1) expression of the Transferrin Receptor (TfR) has a positive causal link with the serum TfR-Ferritin ratio, whereasserumFerritin levels have a negative causal link to TfR expression. (2) C-Reactive Protein (CRP) together with IL-8 and IL-1B have a positive causal relation with IL-6. (3) No causal link between iron supplementation and gut microbiome profile. The first and second result is in accordance with the currentbiological research findings. While the third result shows no causality model, the skeleton might give information for future studies on understanding the gut microbiome profile. Computer modeling helped to uncover causality between clinical parameters in iron deficiency anemia children with iron-micronutrient supplementation. This could lead to more focused studies to better understand the iron supplementation practice as well as the biological mechanism of RTI, gut microbiome alteration, and iron supplementation.
大多数临床研究是描述性的，测量与某些治疗效果相关的不同参数，而因果关系无法确认。计算模型帮助研究人员预测因果关系，并帮助关注数据中最相关的部分。本研究使用计算模型来寻找补铁效果、RTI、全身炎症参数和肠道微生物群特征之间的因果关系。我们对来自肯尼亚的6个月大婴儿的随机对照试验数据集(n=72)使用了因果发现算法。我们还使用相关和部分相关来确定任何因果关系的因果效应。我们发现:(1)转铁蛋白受体(TfR)的表达与血清TfR-铁蛋白比值呈正相关，而血清铁蛋白水平与TfR表达呈负相关。(2) c -反应蛋白(CRP)、IL-8、IL-1B与IL-6呈正相关。(3)补铁与肠道微生物群之间没有因果关系。第一、二项结果与目前生物学研究成果一致。虽然第三个结果没有显示因果关系模型，但骨骼可能为未来了解肠道微生物组概况的研究提供信息。计算机模型有助于揭示缺铁性贫血儿童补充微量铁元素的临床参数之间的因果关系。这可能会导致更有针对性的研究，以更好地了解铁补充实践以及RTI的生物学机制，肠道微生物组改变和铁补充。
{"title":"Application of A Causal Discovery Model to Study The Effect of Iron Supplementation in Children with Iron Deficiency Anemia","authors":"F. A. Nugroho, T. Ederveen, A. Wibowo, J. Boekhorst, M. D. de Jonge, T. Heskes","doi":"10.1109/ICICoS48119.2019.8982503","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982503","url":null,"abstract":"Most clinical studies are descriptive, measuring different parameters that are associated with certain treatment effects, while causal relations cannot be confirmed. Computational models aid researchers to make predictions of causality and help to focus on the most relevant part of the data. This study used a computational model to find a causal link between iron supplementation effectiveness, RTI, and systemic inflammation parameters, and gut microbiome profiles. We used a causal discovery algorithm on a randomized controlled trial dataset (n=72) of 6 month-old infants from Kenya. We also used correlation and partial correlation to determine the causal effect of any causal link. We found that (1) expression of the Transferrin Receptor (TfR) has a positive causal link with the serum TfR-Ferritin ratio, whereasserumFerritin levels have a negative causal link to TfR expression. (2) C-Reactive Protein (CRP) together with IL-8 and IL-1B have a positive causal relation with IL-6. (3) No causal link between iron supplementation and gut microbiome profile. The first and second result is in accordance with the currentbiological research findings. While the third result shows no causality model, the skeleton might give information for future studies on understanding the gut microbiome profile. Computer modeling helped to uncover causality between clinical parameters in iron deficiency anemia children with iron-micronutrient supplementation. This could lead to more focused studies to better understand the iron supplementation practice as well as the biological mechanism of RTI, gut microbiome alteration, and iron supplementation.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"64 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121605039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982483
S. Endah, E. Sarwoko, P. S. Sasongko, R. A. Ulfattah, S. R. Juwita
Soybean is one of Indonesia's main commodities that is widely used as a secondary food source because of its protein content. This article compares three attribute selection algorithms, namely Backward Elimination, Forward Selection, and Stepwise Regression with Learning Vector Quantization2 (LVQ2) classifier to detect soybean to avoidance the diseases and pests. Attribute selection is needed at the pre-processing phase of soybean disease data. By selecting relevant data attributes, it is expected that detection accuracy can be maximally generated with minimum computation. The selected attributes are then classified using the LVQ2 method which is a variation of the development of LVQ. LVQ2 has the ability to classify several diseases better than LVQ with the existence of two reference vectors for weight update. The experimental results show that the best parameter for feature selection are p 0.25, a-enter 0.095 and a-remove 0.095 which can reduce the attribute up to 20 attributes with LVQ2 classification accuracy reaching 91%. The results of this accuracy can be obtained through all three selection algorithms.
{"title":"Attribute Selection for Detection of Soybean Plant Disease and Pests","authors":"S. Endah, E. Sarwoko, P. S. Sasongko, R. A. Ulfattah, S. R. Juwita","doi":"10.1109/ICICoS48119.2019.8982483","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982483","url":null,"abstract":"Soybean is one of Indonesia's main commodities that is widely used as a secondary food source because of its protein content. This article compares three attribute selection algorithms, namely Backward Elimination, Forward Selection, and Stepwise Regression with Learning Vector Quantization2 (LVQ2) classifier to detect soybean to avoidance the diseases and pests. Attribute selection is needed at the pre-processing phase of soybean disease data. By selecting relevant data attributes, it is expected that detection accuracy can be maximally generated with minimum computation. The selected attributes are then classified using the LVQ2 method which is a variation of the development of LVQ. LVQ2 has the ability to classify several diseases better than LVQ with the existence of two reference vectors for weight update. The experimental results show that the best parameter for feature selection are p 0.25, a-enter 0.095 and a-remove 0.095 which can reduce the attribute up to 20 attributes with LVQ2 classification accuracy reaching 91%. The results of this accuracy can be obtained through all three selection algorithms.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"74 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117326853","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/icicos48119.2019.8982479
{"title":"Welcome Speech from General Chair of ICICoS 2019","authors":"","doi":"10.1109/icicos48119.2019.8982479","DOIUrl":"https://doi.org/10.1109/icicos48119.2019.8982479","url":null,"abstract":"","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126708040","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982464
O. Adikhresna, R. Kusumaningrum, B. Warsito
Researches on multi label classification methods generally use training data that already have multi label output as ground truth, but there are real-world problems where it is required to produce multi label prediction output but the available training data only have single label as ground truth. This study compared the performance of various multi label classification methods i.e. Ranking Support Vector Machine (Rank-SVM), Backpropagation for Multi Learning (BP-MLL), Multi Label K-Nearest Neighbor (ML-KNN), and Multi Label Radial Basis Function (ML-RBF) that were trained using multi label training data as intended and which were trained using single label training data. The dataset used in this research is an example of real-world problem, namely the personality-aptitude psychological test results is used to predict suitable majors in vocational high school. The results showed that hamming loss between the two was not far adrift so that it can be concluded that in certain problems, multi label classification methods can train single label and still produce multi label predictions with fairly good accuracy.
{"title":"Comparative Experimental Study of Multi Label Classification using Single Label Ground Truth with Application to Field Majoring Problem","authors":"O. Adikhresna, R. Kusumaningrum, B. Warsito","doi":"10.1109/ICICoS48119.2019.8982464","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982464","url":null,"abstract":"Researches on multi label classification methods generally use training data that already have multi label output as ground truth, but there are real-world problems where it is required to produce multi label prediction output but the available training data only have single label as ground truth. This study compared the performance of various multi label classification methods i.e. Ranking Support Vector Machine (Rank-SVM), Backpropagation for Multi Learning (BP-MLL), Multi Label K-Nearest Neighbor (ML-KNN), and Multi Label Radial Basis Function (ML-RBF) that were trained using multi label training data as intended and which were trained using single label training data. The dataset used in this research is an example of real-world problem, namely the personality-aptitude psychological test results is used to predict suitable majors in vocational high school. The results showed that hamming loss between the two was not far adrift so that it can be concluded that in certain problems, multi label classification methods can train single label and still produce multi label predictions with fairly good accuracy.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126302859","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982515
Sholiq Sholiq, R. Sarno, A. Tjahyanto, A. D. Wulandari
In developing software for the automation of an organization's business processes, it is important to include the complexity of business processes as one of the cost drivers when determining the estimate costs of project. In this paper, we propose a model for calculating the complexity of business processes using cyclometric complexity which was initially used as a quantitative measure of the logic complexity of a program. Furthermore, the results of measuring the complexity of the workflow are attached to one of the multiplier efforts in constructive cost model (COCOMO) II.
{"title":"Workflow Complexity in Constructive Cost Model II","authors":"Sholiq Sholiq, R. Sarno, A. Tjahyanto, A. D. Wulandari","doi":"10.1109/ICICoS48119.2019.8982515","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982515","url":null,"abstract":"In developing software for the automation of an organization's business processes, it is important to include the complexity of business processes as one of the cost drivers when determining the estimate costs of project. In this paper, we propose a model for calculating the complexity of business processes using cyclometric complexity which was initially used as a quantitative measure of the logic complexity of a program. Furthermore, the results of measuring the complexity of the workflow are attached to one of the multiplier efforts in constructive cost model (COCOMO) II.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"40 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125679535","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2019-10-01DOI: 10.1109/ICICoS48119.2019.8982473
Wulan Tri Lestari, E. Suharto, P. W. Wirawan, Kabul Kurniawan
OnlineTax was intended as an effective e-filing application. However in its implementation, the number of OnlineTax application users is still under expectation. This study was conducted to measure the acceptance of OnlineTax application in Tax Office Pratama Salatiga City in Indonesia. The model used in this study was Technology Acceptance Model (TAM) with the addition of trust and risk variables. The model was applied to 50 samples by using Partial Least Square (PLS) to test the conceptual model. Data were obtained through offline distribution of questionnaires to taxpayer in a certain time periods. Results obtained from this study indicated that perceived usefulness and trust had a significant effect on the intention to use the OnlineTax application. Meanwhile the risk did not have any significant effect on the intention to use the application. Risk variable in t-statistics had smaller than t-table (1.68), the hypothesis can not be accepted.
{"title":"Trust and Risk for Measuring OnlineTax Application Acceptance","authors":"Wulan Tri Lestari, E. Suharto, P. W. Wirawan, Kabul Kurniawan","doi":"10.1109/ICICoS48119.2019.8982473","DOIUrl":"https://doi.org/10.1109/ICICoS48119.2019.8982473","url":null,"abstract":"OnlineTax was intended as an effective e-filing application. However in its implementation, the number of OnlineTax application users is still under expectation. This study was conducted to measure the acceptance of OnlineTax application in Tax Office Pratama Salatiga City in Indonesia. The model used in this study was Technology Acceptance Model (TAM) with the addition of trust and risk variables. The model was applied to 50 samples by using Partial Least Square (PLS) to test the conceptual model. Data were obtained through offline distribution of questionnaires to taxpayer in a certain time periods. Results obtained from this study indicated that perceived usefulness and trust had a significant effect on the intention to use the OnlineTax application. Meanwhile the risk did not have any significant effect on the intention to use the application. Risk variable in t-statistics had smaller than t-table (1.68), the hypothesis can not be accepted.","PeriodicalId":105407,"journal":{"name":"2019 3rd International Conference on Informatics and Computational Sciences (ICICoS)","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131342143","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：