Claim Missing Document
Check
Articles

Found 6 Documents
Search
Journal : Journal Information System Development

Feature Addition to the Color Harmonization Application in Two Dimensional Image Lukas, Samuel
Journal Information System Development (ISD) Vol 6, No 2 (2021): Journal Information System Development (ISD)
Publisher : UNIVERSITAS PELITA HARAPAN

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

– In the era of digital technology, the demand for good visual communication increases. It deals with how to harmonize the usage of colors on that visual communication. It is called as color harmony. Color harmony is a series of combinations of colors that are balanced and aesthetically for visual perception.  There is an application developed by Yang (2018) that can be used to design  a good visual communication based on color harmony. This paper discusses on how to add some additional features to that application so that it can be more easily used and understood for the general public. Additional features include manual harmonization operation, color palette recommendation using the K-means clustering algorithm, multithreading and GUI. This paper also measures the performance and expert judgment of the level of color harmony in the application output. The experiment data are 5 sample images with various resolution sizes of 640x480, 800x600, 960x720, 1024x768, 1280x960, 1440x1080, 1600x1200, and 1920x1440. The fastest prosses time for the best harmonic scheme is 201 seconds for 640x480 resolution and the longest time is 1350 seconds for 1600x1200 resolution. The rate of expert judgment in harmonious samples is 9.07 out of 12.00 and in non-harmonized samples is 6.02 out of 12.00.
ANALISIS PREMI DAN CADANGAN PREMI MODEL MULTIPLE STATE DISKRIT DENGAN SIMULASI MONTE CARLO Krisnadi, Dion; Felia, Felia; Lukas, Samuel; Widjaja, Petrus

Publisher :

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Terdapat lima jenis asuransi, yaitu asuransi seumur hidup, berjangka, dwiguna, dwiguna murni, dan tangguhan. Perhitungan premi serta cadangan (premi) dibutuhkan untuk memastikan penanggung dapat memberikan manfaat yang dijanjikan. Pengaruh dari empat variabel, yaitu suku bunga dan nilai deviasi, masa kontrak, serta manfaat, terhadap premi dan cadangan dianalisis menggunakan model multiple state diskrit dengan simulasi Monte Carlo. Tingginya suku bunga membuat nilai premi menurun dan cadangan semakin mendekati nol. Besarnya deviasi suku bunga mengakibatkan premi dan cadangan menjauh dari hasil perhitungan tanpa deviasi. Besarnya manfaat asuransi membuat premi meningkat dan cadangan semakin menjauhi nol. Sementara itu, perubahan masa kontrak memberi pengaruh yang berbeda sesuai dengan jenis asuransinya. Dengan analisis sensitivias, suku bunga memiliki pengaruh terbesar pada asuransi seumur hidup, sementara variabel paling berpengaruh pada dwiguna murni dan tangguhan adalah masa kontrak. Di sisi lain, variabel paling berpengaruh pada berjangka dan dwiguna adalah suku bunga atau masa kontrak, tergantung dari status tertanggung
ANALISIS PREMI DAN CADANGAN PREMI MODEL MULTIPLE STATE DISKRIT DENGAN SIMULASI MONTE CARLO Dion Krisnadi; Felia Felia; Samuel Lukas; Petrus Widjaja
Journal Information System Development (ISD) Vol 7 No 1 (2022): Journal Information System Development (ISD)
Publisher : UNIVERSITAS PELITA HARAPAN

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Terdapat lima jenis asuransi, yaitu asuransi seumur hidup, berjangka, dwiguna, dwiguna murni, dan tangguhan. Perhitungan premi serta cadangan (premi) dibutuhkan untuk memastikan penanggung dapat memberikan manfaat yang dijanjikan. Pengaruh dari empat variabel, yaitu suku bunga dan nilai deviasi, masa kontrak, serta manfaat, terhadap premi dan cadangan dianalisis menggunakan model multiple state diskrit dengan simulasi Monte Carlo. Tingginya suku bunga membuat nilai premi menurun dan cadangan semakin mendekati nol. Besarnya deviasi suku bunga mengakibatkan premi dan cadangan menjauh dari hasil perhitungan tanpa deviasi. Besarnya manfaat asuransi membuat premi meningkat dan cadangan semakin menjauhi nol. Sementara itu, perubahan masa kontrak memberi pengaruh yang berbeda sesuai dengan jenis asuransinya. Dengan analisis sensitivias, suku bunga memiliki pengaruh terbesar pada asuransi seumur hidup, sementara variabel paling berpengaruh pada dwiguna murni dan tangguhan adalah masa kontrak. Di sisi lain, variabel paling berpengaruh pada berjangka dan dwiguna adalah suku bunga atau masa kontrak, tergantung dari status tertanggung
Feature Addition to the Color Harmonization Application in Two Dimensional Image Samuel Lukas
Journal Information System Development (ISD) Vol 6 No 2 (2021): Journal Information System Development (ISD)
Publisher : UNIVERSITAS PELITA HARAPAN

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

– In the era of digital technology, the demand for good visual communication increases. It deals with how to harmonize the usage of colors on that visual communication. It is called as color harmony. Color harmony is a series of combinations of colors that are balanced and aesthetically for visual perception.  There is an application developed by Yang (2018) that can be used to design  a good visual communication based on color harmony. This paper discusses on how to add some additional features to that application so that it can be more easily used and understood for the general public. Additional features include manual harmonization operation, color palette recommendation using the K-means clustering algorithm, multithreading and GUI. This paper also measures the performance and expert judgment of the level of color harmony in the application output. The experiment data are 5 sample images with various resolution sizes of 640x480, 800x600, 960x720, 1024x768, 1280x960, 1440x1080, 1600x1200, and 1920x1440. The fastest prosses time for the best harmonic scheme is 201 seconds for 640x480 resolution and the longest time is 1350 seconds for 1600x1200 resolution. The rate of expert judgment in harmonious samples is 9.07 out of 12.00 and in non-harmonized samples is 6.02 out of 12.00.
PERBANDINGAN PERFORMA BAGGING DAN ADABOOST UNTUK KLASIFIKASI DATA MULTI-CLASS Samuel Lukas; Osvaldo Vigo; Dion Krisnadi; Petrus Widjaja
Journal Information System Development (ISD) Vol 7 No 2 (2022): Journal Information System Development (ISD)
Publisher : UNIVERSITAS PELITA HARAPAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19166/isd.v7i2.547

Abstract

One technique to improve the performance of Machine Learning algorithms is to use Ensemble Learning. The idea of ​​this technique combines several Machine Learning algorithms or commonly referred to as base learners. The purpose of this study is to compare the performance of the two Ensemble Learning algorithms, namely the Bootstrap Aggregating (Bagging) method and the Adaptive Boosting (AdaBoost) method. This study uses eleven datasets with multi-class classifications that are independent of the characteristics (data proportion, number of data, and problems) and the number of different classes of target variables. The results showed that the accuracy and F1 model formed by the Bagging method tended to show better value performance than that of the AdaBoost method on the evaluation metric with an average evaluation value of 72.21% and 61% for Bagging and 66.25% and 53, respectively. 7% for AdaBoost. However, the results of hypothesis testing show that it is not significant enough. In addition, the length of computation time to form the Bagging model and the AdaBoost model is not different
Analysis Of The Sirs Model Of The Spread Of Dengue Hemorrhagic Fever Using Runge-Kutta Method And Genetic Algorithm Melyssa Mentari Tjioenata; Samuel Lukas; Dina Stefani; Petrus Widjaja
Journal Information System Development (ISD) Vol 8 No 1 (2023): Journal Information System Development
Publisher : UNIVERSITAS PELITA HARAPAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.19166/isd.v8i1.566

Abstract

Dengue Hemorrhagic Fever is a contagious disease that often occurs in Indonesia. Dengue Hemorrhagic Fever, caused by the Dengue Virus, has four serotypes : DEN-1, DEN-2, DEN-3 and DEN-4. Someone can be infected four times, once for each serotype. After recovering from one serotype, a person gets a lifetime of immunity against that serotype. In this paper a model will be created for modeling the spread of Dengue Hemorrhagic Fever with assumption there are only two serotypes, namely DEN-1 and DEN-2. Model formed based on SIR Model (Susceptible, Infected, Recovered) and SIRS Model (Susceptible, Infected, Recovered, Susceptible). The changes in populations over time are written into a system of differential equations. The system of differential equations is then used to do an equilibrium point analysis. The numerical solution for the system of differential equations can be found using the Runge-Kutta Method. Genetic Algorithm are used to find the values of parameters in the model that are unknown. A series of simulations are performed to get the combination that produces the Genetic Algorithm system that will produce the best approximation solution. The combination includes population size, selection value, crossover value and mutation value. This best combination then will produce an approximation solution with the smallest error.