Eigen Mathematics Journal
Not a member yet
116 research outputs found
Sort by
Determination of The Best Koperasi Using SAW (Simple Additive Weighting)
Get PDFOffice of Koperasi, UKM, and Trade of Tanah Laut Regency, South Kalimantan conducts the health of Koperasi by manually checking the financial report data of each Koperasi. This study aims to determine the best Koperasi performance using a decision-making system with the Simple Additive Weighting (SAW) method. Performance evaluation is based on the criteria in the Technical Instructions for the Deputy for Koperasi Number 15 of 2021 concerning Guidelines for Working Papers on Cooperative Health Examination. The criteria to determine the best Koperasi performance were based on the attributes of the governance, risk profile, financial performance, and capital of Koperasi. The SAW method was used to select the best Koperasi by adding up each attribute, then multiplying by the weight of the related attributes. Based on the calculations using the SAW method, Koperasi 33 was selected, with the highest Vector value (V(i)) of 0.944719. Koperasi 33 can be categorized as the best of 100 Koperasi in Tanah Laut Regency, South Kalimantan.Dinas Koperasi, UKM, dan Perdagangan Tanah Laut conducts the health of Koperasi by manually checking the financial report data of each Koperasi. It takes precision and a long time to carry out Koperasi health checks with manual calculations. This study aims to determine the best Koperasi performance using a decision-making system with the Simple Additive Weighting (SAW) method. The criteria to determine the best Koperasi performance were based on the attributes of the governance, risk profile, financial performance, and capital of Koperasi. The SAW method was used to select the best Koperasi by adding up each attribute, then multiplying by the weight of the related attributes. Based on the calculations using the SAW method, Koperasi 33 was selected as the best Koperasi with the highest vector value (V(i ))= 0.944719. This means that Koperasi 33 can be categorized as the best Koperas
Negative Binomial and Generalized Poisson Regression Model for Death Due to Dengue Hemorrhagic Fever Data
Get PDFData on the number of deaths due to Dengue Fever in statistics is count data often approximated by a Poisson distribution. However, if overdispersion occurs, Poisson regression is no longer sufficient, so the Negative Binomial and Generalized Poisson Regression approaches are used. From the two models, the best model was chosen based on the smallest AIC value, 66.50, namely the Negative Binomial Regression model. From this model, factors that have a significant effect are determined based on the p-value, and the factor ratio of health facilities per 100,000 population is obtained
Modifikasi Algoritma Edmonds Karp untuk Menentukan Aliran Maksimum Pada Jaringan Distribusi Air PDAM (Studi Kasus Jaringan Telaga Sari PDAM Giri Menang Mataram)
Get PDFClean water is the main and basic need for humans which is of concern to the government. Distribution network system is a very important part to delivering water to all consumers. The lack of water discharge distribution in several areas, especially at the end of the pipeline service, is cause by not optimal water distribution, the flow rate of sorce and leak in pipeline effect. This research has to analyze the optimal network model and determine the maximum flow rate from the PDAM pipeline using modified Edmonds Karp algorithm. Modified Edmonds Karp algorithm is a method for calculating maximum flow of a network. Based on analysis of modified Edmonds Karp algorithm there is a less efficient us of pipe in PDAM network and result of maximum flow from the network is 202,30 liter/second. This means it can be adding flow discharge to the water distribution pipe by PDAM for expedite the flow to consumer with the addition of flow should not exceed 202,30 liter/second.Clean water is the main and basic need for humans which is of concern to the government. Distribution network system is a very important part to delivering water to all consumers. The lack of water discharge distribution in several areas, especially at the end of the pipeline service, is cause by not optimal water distribution, the flow rate of sorce and leak in pipeline effect. This research has to analyze the optimal network model and determine the maximum flow rate from the PDAM pipeline using modified Edmonds Karp algorithm. Modified Edmonds Karp algorithm is a method for calculating maximum flow of a network. Based on analysis of modified Edmonds Karp algorithm there is a less efficient us of pipe in PDAM network and result of maximum flow from the network is 202,30 liter/second. This means it can be adding flow discharge to the water distribution pipe by PDAM for expedite the flow to consumer with the addition of flow should not exceed 202,30 liter/second
Some Properties of Rough Ideals on Rough Rings
Get PDFThe concept of rough set was first introduced by Pawlak in 1982. The basic concepts in set theory such as intersections, unions, differences, and complements still apply to rough sets. Furthermore, researchers in the field of mathematics and informatics who study rough sets can relate the concept of rough sets to algebraic structures so that a concept called rough algebraic structures is obtained. Some concepts on rough algebraic structures are rough groups, rough rings, and rough modules. In this paper, the properties related to the ideal of roughness will be given to the rough ring.Konsep himpunan kasar pertama kali diperkenalkan oleh Pawlak pada tahun 1982. Konsep dasar pada teori himpunan seperti irisan, gabungan, selisih, dan komplemen masih berlaku pada himpunan kasar. Selanjutnya, para peneliti bidang matematika dan informatika yang mendalami himpunan kasar dapat mengaitkan konsep himpunan kasar dengan struktur aljabar sehingga diperoleh konsep yang dinamakan struktur aljabar kasar. Beberapa konsep pada struktur aljabar kasar adalah grup kasar, ring kasar, dan modul kasar. Pada paper ini, akan diberikan sifat-sifat terkait ideal kasar pada dari ring kasar
Modelling the Recovery of Malaria Patients in West Lombok District Using Cox Regression
Get PDFMalaria is one of the health problems in West Lombok Regency. There are 413 positive malaria cases, so it is necessary to research the models and factors affecting malaria sufferers' recovery. The analysis used is survival analysis using the Cox Proportional Hazard Regression method. The data used in this study is in the form of secondary data obtained from medical record data from all patients with malaria disease in West Lombok Regency from 2019 to 2020, with dependent variables in the form of recovery time of malaria patients and nine independent variables that are suspected of affecting the recovery of malaria sufferers. This study aims
to determine a recovery model for malaria sufferers based on Cox regression and determine the factors that influence the recovery of malaria sufferers in West Lombok Regency.
Based on the survival analysis results with the Cox Proportional hazard Regression method, the best model was obtained with two significant variables affecting the recovery time of malaria patients: the parasite type variable and the incidence of pregnancy or not getting pregnant. The model can be interpreted based on hazard ratio values that the variable type of parasite category Plasmodium vivax has a probability of being able to recover within one month of treatment by 2,542 times faster than Plasmodium falciparum. In comparison, the type of parasite in the Plasmodium mix category has a probability of being able to recover within one month of treatment 1.108 times faster than Plasmodium vivax, and for the pregnant or non-pregnant variables for the category of pregnant patients had a 2,307 times faster probability of recovery within one month of treatment compared to non-pregnant patients
Model Regresi Cox Untuk Data Masa Studi (Studi Kasus: Data Masa Studi Mahasiswa Fakultas Teknik Universitas Bangka Belitung)
No full textStudent study time is the time needed by students to complete their education, which starts from the time they enter college until they are declared graduated or have completed their study period. In the study period data, survival time observations were only carried out partially or not until the failure event. In other words, termination occurs until the observation deadline. This termination occurred due to several factors that allegedly influenced the student's study period. This study intends to determine what variables influence the study period of students of the Faculty of Engineering, University of Bangka Belitung through survival analysis. Using study period data for students of the Faculty of Engineering, University of Bangka Belitung, class of 2015/2016, this study used the Kaplan Meier Estimation to see the survival function of each factor causing the length of the study period graphically and the Log Rank Test statistically. Meanwhile, to look at the factors that determine the length of a student's study period, researchers used the Cox Regression and Maximum Likelihood Estimation (MLE) models to find the best model. The results of the data analysis show that there are differences in the survival function in each category for all variables graphically, while the statistical comparison of the results of the estimation of the survival function curve based on gender and organizational status is not significantly different. The results of the analysis also show that the proportional hazard assumption is fulfilled through the cumulative hazard log so that categorical variables can be used in the Cox Regression model. Based on the results of the likelihood estimation, the variables that have a significant effect on the study period of Engineering Faculty students are majors and GPA variables. Furthermore, from the interpretation of the model parameters, it is obtained that the Hazard Ratio (HR) value for the study period of Mechanical, Mining and Electrical Engineering students is faster than that of Civil Engineering students, while students with GPA ≥ 3.00 have a shorter study period than students with GPA < 3.00.Student study time is the time needed by students to complete their education, which starts from the time they enter college until they are declared graduated or have completed their study period. In the study period data, survival time observations were only carried out partially or not until the failure event. In other words, termination occurs until the observation deadline. This termination occurred due to several factors that allegedly influenced the student's study period. Using study period data for students of the Faculty of Engineering, University of Bangka Belitung, class of 2015/2016, this study used the Kaplan Meier Estimation to see the survival function of each factor causing the length of study period graphically and the Log Rank Test statistically. Meanwhile, to look at the factors that determine the length of a student's study period, researchers used the Cox Regression and Maximum Likelihood Estimation (MLE) models to find the best model. The results of the data analysis show that there are differences in the survival function in each category for all variables graphically, while the statistical comparison of the results of the estimation of the survival function curve based on gender and organizational status is not significantly different. The results of the analysis also show that the proportional hazard assumption is fulfilled through the cumulative hazard log so that categorical variables can be used in the Cox Regression model. Based on the results of the likelihood estimation, the variables that have a significant effect on the study period of Engineering Faculty students are majors and GPA variables. Furthermore, from the interpretation of the model parameters, it is obtained that the Hazard Ratio (HR) value for the study period of Mechanical, Mining and Electrical Engineering students is faster than that of Civil Engineering students, while students with GPA ≥ 3.00 have a shorter study period than students with GPA < 3.00
Comparison Analysis of Clustering Methods for Clustering of Indonesian’s Gender Empowerment Conditions in 2022
Get PDFGender empowerment is one of the components of gender development achievement measures that is an important agenda at the global level in realizing the Sustainable Development Goals. The Gender Empowerment Index (GEI) of Indonesia has been continuously improving since 2010, indicating an increasing involvement of women in various areas of life. However, behind this upward trend in GEI, there is still inequality at the provincial level. Therefore, there is a need to formulate development strategies, one of which is gender-based. One possible step is to categorize regions in Indonesia based on their gender empowerment characteristics so that government interventions can be targeted effectively. This research utilizes two clustering approaches, namely Hierarchical Methods and Partitioning Methods, with data consisting of three variables representing the components of GEI for 34 provinces in Indonesia in 2022. The selection of the best method and number of clusters is based on internal and stability validity, followed by the determination of the smallest within and between standard deviation ratios. From the cluster analysis results, the best method is found to be K-means with a total of 5 clusters.Gender empowerment is one of the components of gender development achievement measures that is an important agenda at the global level in realizing the Sustainable Development Goals. The Gender Empowerment Index (GEI) of Indonesia has been continuously improving since 2010, indicating an increasing involvement of women in various areas of life. However, behind this upward trend in GEI, there is still inequality at the provincial level. Therefore, there is a need to formulate development strategies, one of which is gender-based. One possible step is to categorize regions in Indonesia based on their gender empowerment characteristics, so that government interventions can be targeted effectively. This research utilizes two clustering approaches, namely Hierarchical Methods and Partitioning Methods, with data consisting of three variables representing the components of GEI for 34 provinces in Indonesia in 2022. The selection of the best method and number of clusters is based on internal validity and stability validity, followed by the determination of the smallest within and between standard deviation ratios. From the cluster analysis results, the best method is found to be K-means with a total of 5 clusters
ANALISIS LULUSAN MATEMATIKA FMIPA UNIVERSITAS MATARAM MENGGUNAKAN DIAGRAM KONTROL MULTIVARIATE EXPONENTIALLY WEIGHTED MOVING AVERAGE (MEWMA
No full textQuality control of Mathematics graduates of FMIPA UNRAM in 2012-2018 with a control chart of the Multivariate Exponentially Weighted Moving Average (MEWMA), is carried out to determine the quality of graduates of the Mathematics Study Program FMIPA UNRAM and to compare the quality of Mathematics graduates FMIPA UNRAM in 2012-2018 using MEWMA and T2 Hotelling control charts. In this test, control was carried out using three control variables, namely the Grade Point Average , length of study , and the number of Semester Credit Units . This study used the weighting value with the Upper Control Limit (UCL) of 10,685. The results obtained that the control chart formed to show that 42 data are outside the control limits (out of control), which causes the quality of graduates to be out of control. Using the EWMA univariate control chart, it is known that the length of study variable causes the data to be out of control. Therefore, a revision was made to the MEWMA control chart so that the quality control process for Mathematics FMIPA Mataram University graduates was within the control limits after the second revision. This is indicated by the absence of observation points outside the control limits so that the quality of mathematics graduates can be said to be good. Furthermore, a comparison of the results of observations with the quality of Mathematics graduates of Mataram University using the T2 Hotelling control chart in the previous study was carried out with the results that there was one data subgroup that was outside the control limit with = 14.5249 which led to the need for one revision of the T2 Hotelling control chart to obtain statistically controlled diagram. Thus, it can be said that the MEWMA control chart is more sensitive than the Hotelling T2 control chart.Pengendalian kualitas lulusan Matematika FMIPA UNRAM tahun 2012-2018 dengan diagram kontrol Multivariate Exponentially Weighted Moving Average (MEWMA), merupakan bentuk uji yang digunakan untuk mengontrol kualitas lulusan dan mengetahui penyebab kurangnya kualitas lulusan mahasiswa Matematika. Dalam uji ini, dilakukan pengontrolan dengan menggunakan tiga variabel kontrol yaitu Indeks Prestasi Kumulatif , lama studi , dan jumlah Satuan Kredit Semester . Pada penelitian ini digunakan nilai pembobot dengan Batas Kontrol Atas (BKA) senilai 10,685. Diperoleh hasil bahwa diagram kontrol yang terbentuk menunjukkan terdapat 42 data yang berada diluar batas kontrol (out of control), hal ini menyebabkan kualitas lulusan menjadi tidak terkontrol. Dengan menggunakan diagram kontrol univariat EWMA, diketahui bahwa variabel lama studi menjadi penyebab data out of control. Oleh karena itu, dilakukan revisi pada diagram kontrol MEWMA sehingga proses pengendalian kualitas lulusan Matematika FMIPA Universitas Mataram berada dalam batas kontrol setelah revisi kedua. Hal tersebut ditunjukkan dengan tidak adanya titik pengamatan yang berada di luar batas kontrol sehingga kualitas lulusan matematika dapat dikatakan baik. Selanjutnya, dilakukan perbandingan hasil pengamatan dengan kualitas lulusan Matematika Universitas Mataram menggunakan diagram kontrol T2 Hotelling pada penelitian sebelumnya dengan hasil terdapat satu subgrup data yang keluar batas kontrol dengan = 14,5249 yang menyebabkan perlunya revisi diagram kontrol T2 Hotelling sebanyak satu kali revisi sehingga mendapatkan diagram yang terkontrol secara statistik. Dengan demikian, dapat dikatakan bahwa diagram kontrol MEWMA lebih sensitif dibandingkan dengan diagram kontrol T2 Hotelling
Perbandingan Metode Data Mining dalam Pengklasifikasian Status Desa Kabupaten Purwakarta dan Bandung Barat (Podes 2021)
No full textEach village has different characteristics and is constantly changing along with the level of development in a village. These changes in conditions are used as indicators to classify villages into urban or rural village status. In this study, researchers will compare or evaluate of several data mining methods, namely decision trees, support vector machines, naïve bayes, and random forests to find the best algorithm in classifying urban villages and rural villages in Purwakarta and West Bandung Regencies. The data used in this study were 357 records and 8 attributes sourced from village potential data (Podes 2021). Furthermore, it was obtained that the best method in classifying urban villages and rural villages is to use random forests with accuracy value and F- score of 0,9.Setiap desa memiliki karakteristik yang berbeda-beda dan terus berubah seiring dengan tingkat pembangunan di suatu desa. Perubahan kondisi tersebut dijadikan sebagai indikator untuk mengklasifikasikan desa ke dalam status desa perkotaan atau perdesaan. Pada penelitian ini, peneliti akan membandingkan atau mengevaluasi dari beberapa metode data mining, yaitu decision tree, support vector machine, naïve bayes, dan random forest untuk menemukan algoritma terbaik dalam mengklasifikasikan desa perkotaan dan desa perdesaan di Kabupaten Purwakarta dan Bandung Barat. Data yang digunakan dalam penelitian ini adalah sebanyak 357 record dan 8 atribut yang bersumber dari data potensi desa (Podes 2021). Selanjutnya diperoleh bahwa metode terbaik dalam mengklasifikasikan desa perkotaan dan desa perdesaan adalah menggunakan random forest dengan nilai akurasi dan F1-score sebesar 0,9
Optimization of water flow on Regency Municipality Waterworks-network of Jonggat Central Lombok Regency using Ford Fulkerson Algorithm and Dinic Algorithm
Get PDFClean water is essential for humans which must be fulfilled for humans survival. The population in Jonggat, Central Lombok, increases from year to year which causes the using of clean water get an increase too. The necessity of rising clean water is not in line with the availability of water in nature, therefore the PDAM (Regency Municipality Waterworks) manages existing water resource. Then, it will be distributed to consumers. The purpose of this research is to determine the optimal solution in the distribution of clean water in Jonggat using Ford Fulkerson algorithm and Dinic algorithm. Both Ford Fulkerson algorithm and Dinic algorithm are methods used to calculate the maximum flow in a network. Based on the results of research using Python software on the Ford Fulkerson algorithm, the maximum current is 133 liters/second, while using the Dinic algorithm, the maximum current is 133.49 liters/second. Meanwhile, the average water flow is delivered by PDAM is 95 liters/second. It means, it can be added the amount of flow in the clean water distribution pipe by the PDAM. It’s for facilitating the flow of water that reaches consumers with the addition of a flow that cannot exceed 133.49 liters/second.
Keywords: Network flow, Maximum flow, Ford Fulkerson algorithm, Dinic algorith