E jurnal Matematika

106-115

Authors: Ida Ayu Made Supartini, I Komang Gde Sukarsa, I Gusti Ayu Made Srinadi

Tabanan Regency is one of the eight regencies and one municipality in Bali Province. Administratively, it is divided into 10 districs and 133 villages. There are rural areas and urban areas in the regions. Discriminant analysis is a technique related to the separation of objects into different groups that have been set previously. The purpose of this research is to classify 133 villlages in Tabanan Regency into urban or rural groups with discriminant analysis. Linear discriminant analysis assumes that the covariance matrix of the two groups are equals, if the assumption of equality of covariance matrix is violated, quadratic discriminant analysis can be used for classification. This research uses k-fold crosss validation method for calculating the accuracy of quadratic discriminant function where k=2,3,4. Quadratic discriminant function is obtained by k=4 with the smallest APER value (0.09). All of classification results are stable and consistence.

124-130

Authors: Tri Alit Tresna Putra, I Komang Gde Sukarsa, I Gusti Ayu Made Srinadi

The aim of this study was to demonstrate the application of Statistics Quality Control in fierce industries. By observing Batik production process at PT XYZ as a case in this work, we applied Six Sigma Method to analyze defective product and their cause while also measure overall quality goodness. Six Sigma is a method to improve a process and reduce defects in productions into 3.4 defects per million productions. We use handprint batik productions at PT XYZ as a case in this study. The method is involving Define, Measure and Analyze (DMA) phases. By using Six Sigma, it was obtained that the quality of handprint batik are quite good with sigma of 3.105 and defect rate of 54.269 million production (DPMO). There are four defect causes of handprint batik namely: ripped fabric, shallowness, perforation, and mispattern which contribute 41,7%, 35,8%, 15%, 7,5% respectively from overall defects. The main cause of defects is the carelessness of workers in production process. Therefore we need to reduce the carelessness to improve production quality.

137-142

Authors: Jonner Nainggolan

A tuberculosis model of SEIT type which incorporates treatment of infectives is considered. The population is divided into four compartments, that is: S are individuals in the susceptible compartment, E are individuals in the exposed compartments, I are individuals in the infected compartment, and T are individuals in the treatment compartments. For this model, controls on treatment is incorporated to reduce the actively infected individual compartments, via application of the Pontryagins Maximum Principle of optimal control theory. Numerical calculations with the approach of the Runge-Kutta method of fourth order can be seen that, the influence of the control treatment to more effectively reduce the number of individuals in the infected compartment compared with no controls. The basic reproduction ratio with control less compared with no controls.

152-160

Authors: I Putu Arista Yasa, Ni Luh Putu Suciptawati, Made Susilawati

The aim of this study was to be able to determine some factors that affected customer satisfaction on the quality of the services provided by LPD Sidakarya. Samples of this study were 150 respondents. The respondents were customers of LPD Sidakarya who have been registered since at least a year ago. There were two variables in this study; i.e. perception and expectation variables in which each of the variable had 30 indicators that affected the satisfaction of the customer on service quality. In addition, this study also determined five factors that affected customer satisfaction on the service quality. The method used was confirmatory factor analysis. It was found on the results of this study that the formed factor of these 30 indicators that affected the satisfaction of the customer on service quality indeed five main factors consisted of tangibles, reliability, responsiveness, assurance and empathy. The most dominant factor obtained was reliability.

220-225

Authors: I Gede Seka Suyoga, I Putu Eka Nila Kencana, I Komang Gde Sukarsa

Tuition fee is the payment of tuition fees each semester borne by each student based on their economic capabilities. Tuition fee is divided into five groups from tuition fee group 1 to tuition fee group 5. This research aims to find the accuracy of the classification of tuition fee using Support Vector Machine (SVM). SVM is a method used for classification of the concept to find hyperplane (separator function) that can separate the data into a predetermined class. In this research, SVM is used to determine the accuracy of tuition fee classification. The variables used are income parents, father’s occupation, mother’s occupation, home ownership status, building, land area, electricity cost, water cost, phone cost, saving accounts, jewelry ownership, and a premium ownership. The results obtained are five hyperplanes to separate tuition fee with accuracy of the classification of tuition fee was 59,69%.

233-240

Authors: Komang Kokom Sucahyati Dewi P., Made Susilawati, I Wayan Sumarjaya

Spatial autoregressive (SAR) is a model of spatial regression which assumes that autoregressive process is only for the dependent variable by considering the spatial effect. The spatial effect consists of spatial dependence and spatial heterogeneity. One of problems which considers spatial effect is the case of society which do public bathing, washing, and toilets facilities (PBWTF) in the river, in Blahbatuh District. The aim of this research is to obtaine the model of society which still do PBWTF in the river, in Blahbatuh Districts in 2016 and to determine the factors that influence it. In this research, we obtained the model which is able to illustrate the case of society which do PBWTF and the factors that influence it such as the amount of householde which do not have latrine and the amount of family who lives near the river in every subvillage in Blahbatuh District.

248-252

Authors: Moh. Heri Setiawan, G. K. Gandhiadi, Luh Putu Ida Harini

This study to determine the selection of computer hardware using fuzzy database method. This is because of many series of hardware produced by the manufacture, so the public will be confused in determining the choice of a combination of computer assembly. In this study the processor, motherboard, random access memory, hard disk, vga cards, power supply studied to find best recommendation. The result obtained from this study these several results obtained in study in the form of recommendation, that is if the recommendation value 0 then the hardware is not displayed as a decision, whereas if the recommendation value is greater than 0 and less than or equal to 1 the device will be displayed as a decision according to the value of its recommendation.

176-182

Authors: Maman Ahdiyat, Lasia Agustina, Nurul Hikmah

The objective of this research is to obtain data about the model of learning that is designed specifically for children who have difficulty in studying in the State Elementary School of Inclusive Education in South Jakarta. The research is done by Research and Development method with qualitative approach with descriptive analysis Observation and documentary study). Population is State Elementary School Provider of Inclusive Education in South Jakarta with a large sample of 10 schools, with sampling technique used is random sampling. Instrument research used questionnaire. Result is: 1) There is no single school that uses a specific learning model for children with learning difficulties, 2) The learning model used still uses conventional learning model where children are treated the same as normal children (no learning difficulties).

188-195

Authors: Ni Wayan Eka Surya Artini, I Putu Eka Nila Kencana, Ketut Jayanegara

The purpose of this research is to determine the dominant factors that influence the increment of poverty in 6 villages in Bangli regency which categorized as disadvantaged village in Bali province, namely, Binyan Village, Ulian Village, Langgahan Village, Abuan Village, Mengani Village, and Tembuku Village. The total respondents in this research are 84 poor families which determined through the stratified proportional random sampling method. The research regarding the poverty in disadvantaged village involves 5 latent variables, namely, poverty rate, inability to meet basic needs, the shortage of human resource competencies, inability to meet support needs, and the shortage of access to infrastructure which are each 5 of the latent variable have the reflective indicator. This research is using the variant-based (PLS-SEM) Structural Equation Modeling (SEM) method and calculated through smart PLS software. Based on the output of structural poverty rate equation model resulting from the analysis, it can be concluded that the increment of inability to meet basic needs, the shortage of human resource competencies, and the shortage of access to infrastructure have a significant effect towards the increment of poverty rate in a disadvantage village, meanwhile inability to meet support needs rate has no effect towards poverty rate in the disadvantaged village of Bangli Regency.

205-213

Authors: Dicky Arya Bramanta, I Nyoman Widana, Luh Putu Ida Harini, I Wayan Sumarjaya

This study examines about last survivor life insurance with return of premium for married couples with independent and dependent mortality model. By using Frank copula, Clayton copula, Gumbel copula and Indonesian Mortalita Table 2011, the impact of future life dependence on single premiums and annually premium is evaluated. Based on the calculation of premium with a 10 year contract for the insured parties aged 58 years and 55 years with interest rate used 6.5%, the value of insurance premium last survivor with return of premium is more expensive than without return of premium. The greater the dependency, the more expensive the price of the premium.

133-138

Authors: Ni Putu Prema Dewanti, Made Susilawati, I Gusti Ayu Made Srinadi

Poisson regression is a nonlinear regression which is often used for count data and has equidispersion assumption (variance value equal to mean value). However in practice, equidispersion assumption is often violated. One of it violations is overdispersion (variance value greater than the mean value). One of the causes of overdipersion is excessive number of zero values on the response variable (excess zeros). There are many methods to handle overdispersion because of excess zeros. Two of them are Zero Inflated Poisson (ZIP) regression and Zero Inflated Negative Binomial (ZINB) regression. The purpose of this research is to determine which regression models is better in handling overdispersion data. The data that can be analyzed using the ZIP and ZINB regression is maternal mortality rate in the Province of Bali. Maternal mortality rate data has proportion of zeros value more than 50% on the response variable. In this research, ZINB regression better than ZIP regression for modeling maternal mortality rate. The independent variable that affects the number of maternal mortality rate in the Province of Bali is the percentage of mothers who carry a pregnancy visit, with ZINB regression models ln⁡〖(μ_i)〗=2,7729-0,0247X_1 and logit (p_i )=-3,8670-0,0381X_1.

148-155

Authors: Gede Suryawan, Ni Ketut Tari Tastrawati, Kartika Sari

Companies which engaged in production activities such as Ramadhan Bakery would want optimal profit in their every production. The aim of this study was to find optimal profit and optimal combination of bread production (original chocolate bread, extra chocolate bread, rounding chocolate bread and mattress chocolate bread) that was produced by Ramadhan Bakery by applying Branch and Bound Algorithm method. Branch and Bound Algorithm is one method to solve Integer Programming’s problems other than Cutting Plane method. Compared with Cutting Plane method, Branch and Bound Algorithm method is more effective in determining the optimal value. As the result of this study showed that to get optimal profit, Ramadhan Bakery should produce 360 pcs of original chocolate bread, 300 pcs of extra chocolate bread, 306 pcs of rounding chocolate bread and 129 pcs of mattress chocolate bread with optimal profit amounts Rp. 1.195.624,00.. The profit will increase amounts 25,2 % than before.

164-169

Authors: Luh Gede Udayani, I Wayan Sumarjaya, Made Susilawati

Dependence relationship between two or more variables is an issue that is often studied in the science of probability and statistics. Pearson correlation is often the easiest option to measure dependencies between variables. It is well known, that Pearson correlation assumes that the variable under study must be normally distributed. However, in reality this is not the case; for example, data in fields such as climatology and meteorology, insurance, and financial. Copula is a tool that can be used to model the joint distribution because it does not require the assumption of normality of the data so that it is resilient against a wide range of data. In this study, we discussed the application of copula in modeling the structure of dependencies between two variables: the production of rice and El-Nino Southern Oscillation (ENSO) indicator per period in Tabanan Regency. The best dependency model structure is given by the Frank copula of the Archimedean copula family with estimation parameter, θ = 2,817 and the loglikelihood value of 3,47.

176-182

Authors: Ami Hilda Agustin, G.K. Gandhiadi, Tjokorda Bagus Oka

Fuzzy logic is a way to map an input space into an output space. The basic of fuzzy logic is fuzzy set theory. In the fuzzy set theory, the role of membership degree is important to determine the presence of elements in a set. Membership degree is the fundamental feature of reasoning in fuzzy logic. There are several methods that are often used in solving fuzzy inference system, one of them is fuzzy Sugeno method. The aim of this research is applications of fuzzy methods is to forecast to determine the selling price of used motorcycles. In determining the selling price of used motorcycles, there are several things that need to be considered, namely : the production year of the motorcycles, the physical condition of the motorcycles, the origin of the license plates, and the purchase price of the motorcycles. The calculation can be done by using Matlab program. The result obtained were then tested using the Mean Absolute Percentage Error (MAPE) by calculating difference between the selling price of dealer minus the selling price of fuzzy Sugeno then divided by the selling price of dealer. From the test result, MAPE value obtained was 5,64% . This indicates that error rate below 10%, so we can say the result of these calculation is considerably accurate.

90-97

Authors: I Wayan Radika Apriana, Ni Ketut Tari Tastrawati, Kartika Sari

Cat Swarm Optimization (CSO) algorithm is a metaheuristic algorithm which is based on two behaviors of cat, seeking and tracing. CSO algorithm is used in solving optimization problems. One of the optimization problems which can be seen in daily life is Job Shop Scheduling Problem (JSSP). This study aimed to observe the performance of CSO algorithm in solving JSSP. This study focused on 5 job-12 machine cases. According to this study, CSO algorithm was effective in solving real case of JSSP in 5 jobs – 12 machines scheduling at CV Mitra Niaga Indonesia agriculture tools industry. In implementing CSO algorithm in JSSP, a correct parameter choosing could lead to an optimal result. On other hand, the greater the number of jobs or machines the more complex and difficult the JSSP that needed to be solved.

103-110

Authors: Palupi Purnama Sari, Made Susilawati, I Gusti Ayu Made Srinadi

This research was conducted to determine the variables that significantly influence nutritional status of children based on indicators that defined as height for age (H/A) and to classify children nutritional status into normal, short or very short categories. Height for age (H/A) is indicator used to describe the circumstances of malnutrition short. Short children (stunting) is children who fail to reach optimal growth. The secondary data was list of 116 data of children aged 24-59 months at UPT. Puskesmas Klungkung I in 2015. The method was used was ordinal logistic regression and bagging ordinal logistic regression. Based on the research results, it was obtained variables children body length at birth, birth weight, and length of mid-upper arm circumference (MUAC) in pregnant woman were significantly affects the nutritional status of children by the classification accuracy level of ordinal logistic regression 62,86% and misclassification 37,14%. Classification accuracy of ordinal logistic regression can be improved by bagging ordinal logistic regression method. Bagging works well on classification method which has unstable procedures. One of classification method which has unstable procedures is ordinal logistic regression. Bagging ordinal logistic regression method by 501 times replication capable to improve classification accuracy of ordinal logistic regression model from 62,86% to 68,57%, increased 5,71%.

117-125

Authors: I Putu Gede Dian Gerry Suwedayana, I Wayan Sumarjaya, Ni Luh Putu Suciptawati

The purpose of this research is to forecast the number of Australian tourists arrival to Bali (y_t) using Time Varying Parameter (TVP) model based on inflation of Indonesia (x_1t) and exchange rate AUD to IDR (x_2t) from January 2010 – December 2015 as explanatory variables. TVP model is specified in a state space model and estimated by Kalman filter algorithm. The result shows that the TVP model can be used to forecast the number of Australian tourists arrival to Bali because it satisfied the assumption that the residuals are distributed normally and the residuals in the measurement and transition equations are not correlated. The estimated TVP model is (y_t ) ̂=201.8253x_1t+8.903399x_2t. This model has a value of mean absolute percentage error (MAPE) is equal to 1.77% dan root mean square percentage error (RMSPE) is equal to 2.3418%. The number of Australian tourists arrival to Bali for the next five periods is predicted: 87,534; 86,708; 88,864; 90,651; and 88,077 (January - May 2016).