Article Per Year (5 Year)
p-Index From 2020 - 2025
0.778
P-Index
This Author published in this journals
All Journal J-Icon : Jurnal Komputer dan Informatika
Derwin R Sina
Universitas Nusa Cendana
Computer Science & IT

Published : 5 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 5 Documents
Search

 1 
CASE BASED REASONING UNTUK MENDIAGNOSA PENYAKIT GIGI DAN MULUT MENGGUNAKAN METODE BLOCK CITY Emanuel Fahik; Derwin R Sina; Arfan Y Mauko
J-Icon : Jurnal Komputer dan Informatika Vol 5 No 2 (2017): Oktober 2017
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v5i2.362

Abstract

Case Based Reasoning (CBR) method is one method to build a system with new case decision based on solution from previous cases by calculating similarity level. In this study, the authors apply CBR to diagnose dental and mouth disease in humans. Sources of system knowledge are obtained by collecting cases that have occurred before. The calculation of similarity values ​​using the Block City Gower method with threshold 60%. This system can diagnose 5 diseases based on 26 existing symptoms. The output of the system in the form of the illness experienced by the patient based on the symptoms entered by non-physician medical personnel, as well as the treatment solution which accompanied the presentation of similarities with the previous case to show the truth level of possible diagnosis. Based on the results of the test case obtained the results: the system can take back the old case is appropriate and has used the formulation of Block City method correctly indicated with 100% accuracy, and use 122 cases is optimal enough to diagnose 5 diseases indicated by the average similarity to 20 cases for milk teeth growth phase of 80% and 30 cases for adult tooth growth phase of 90%.
CASE BASED REASONING UNTUK MENDIAGNOSA PENYAKIT ANAK MENGGUNAKAN METODE BLOCK CITY Marnon C. Y Mage; Derwin R Sina; Tiwuk Widiastuti
J-Icon : Jurnal Komputer dan Informatika Vol 5 No 2 (2017): Oktober 2017
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v5i2.364

Abstract

The Case Based Reasoning (CBR) method is one of the methods to build a system that works by diagnosing new cases based on old cases that have occurred and providing solutions to new cases based on old cases with the highest similarity values. In this study, the authors apply CBR to diagnose diseases of children aged 1-12 years. Sources of system knowledge were obtained by collecting patient medical record files in 2014 and 2015. The calculation of similarity values using the Block City Gower method with a fairness value is 70%. This system can diagnose 10 illnesses based on 48 existing symptoms. The output of the system in the form of the illness experienced by the patient based on symptoms implanted by non-physician medical personnel, handling solution and presentation similarities with the previous case to show the truth level of the diagnosis. Based on the test of 83 new cases obtained system accuracy of 75,90%.
DIAGNOSA HAMA DAN PENYAKIT PADA TANAMAN CABAI MENGGUNAKAN METODE VARIABLE CENTERED INTELLIGENT RULE SYSTEM (VCIRS) Daud Meko; Derwin R Sina; Kornelis Letelay
J-Icon : Jurnal Komputer dan Informatika Vol 6 No 2 (2018): Oktober 2018
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v6i2.510

Abstract

This research led to an expert system application that was built by applying the method variable centered intelligent rule system and the certainty factor. Variable Centered Intelligent Rule System (VCIRS) is an intelligent rule-based system that focuses on the variables. VCIRS procedures are able to take over the construction of knowledge, update knowledge as well as advice or inference process. Procedure own certainty factor on the symptoms of pests or diseases taking into account the weighting process used to provide from the weighting process result in the form of pests or diseases to the value of the trust of the system. The location of this research is located in Rote Ndao Regency. Data used in this application testing of 28 case data sourced from an expert or agricultural expert. Accuracy in this study was 100 %. The results showed that the method variable centered intelligent rule system and certainty factor can be applied in the application of expert system for the diagnosis of plant pests and diseases chili.
DIAGNOSA HAMA DAN PENYAKIT PADA TANAMAN PADI MENGGUNAKAN METODE NAIVE BAYES DAN K-NEAREST NEIGHBOR Restanti M Bianome; Yelly Y Nabuasa; Derwin R Sina
J-Icon : Jurnal Komputer dan Informatika Vol 8 No 2 (2020): Oktober 2020
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v8i2.2906

Abstract

This study builds systems Case Based Reasoning (CBR) to diagnose pests and diseases in rice plants using Naïve Bayes algorithm and K-Nearest Neighbor. CBR is one method of solving the problem with new cases of decision making based on the solution of previous cases by calculating the degree of similarity (similarity), The case consists of 13 species and 10 types of disease pests of rice plants. The degree of similarity can be determined by indexing and nonindexing. Indexing is the process of grouping the cases by classes that have been determined, while nonindexing a process without grouping cases. Based on cross validation testing using average values obtained accuracy of 92.88% to 153 test data on testing using the indexing and the average value of 89.63% accuracy of the test data in the test 153 using nonindexing.
APLIKASI KEAMANAN PESAN (.TXT) MENGGUNAKAN METODE TRIPLE DES DAN METODE KOMBINASI LSB DAN BLUM-BLUM-SHUB Derwin R Sina; Guido A Kiu; Bertha S Djahi; Emerensye S Y Pandie
J-ICON : Jurnal Komputer dan Informatika Vol 10 No 2 (2022): Oktober 2022
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v10i2.8465

Abstract

Security is one of the important aspects of the process of exchanging information (messages). To prevent misuse or attacks by unauthorized parties (attackers) on private messages, the message must be secured. Several methods can be used to secure messages, one of which is by combining the Triple Data Encryption Standard (DES) cryptography method, Blum-Blum Shub (BBS) random number generator, and Least Significant Bit (LSB) steganography. In this study, the Triple DES cryptographic method is used to encrypt messages (embedded-message) with the extension .txt and the BBS random number generator method is used to determine the position of a random pixel to be inserted in the cover-image message. The LSB steganography method is used to perform the embedding process of the encrypted embedded-message at the pixel position resulting from the BBS random number generation process. The test results show that the system can extract embedded messages hidden in a stego-image with 100% accuracy. The maximum number of embedded-message characters that can be used in the test is 150 characters. The test also produces a stego-image that has an average Peak Signal to Noise Ratio (PSNR) value of 88.61, which means that the resulting stego-image has high quality (no significant quality degradation) and the presence of messages in the stego-image is getting harder to detect (imperceptibility).
Co-Authors Arfan Y Mauko Arfan Y Mauko Bertha S Djahi Daud Meko Emanuel Fahik Emerensye S Y Pandie Guido A Kiu Kornelis Letelay Marnon C. Y Mage Restanti M Bianome Tiwuk Widiastuti Yelly Y Nabuasa