Claim Missing Document
Check
Articles

Found 30 Documents
Search

ELITISME ALGORITMA GENETIKA PADA FUNGSI NONLINEAR DUA PEUBAH Adriana Fanggidae; Emerensye S Y Pandie
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.v8i2.2894

Abstract

The evolutionary operator in the genetic algorithm (GA) does not guarantee that the quality of individuals from generation to generation is always good. Elitism maintains the preservation of the best individual traits from generation to generation by multiplying the best set of individuals. In this paper, it is determined the number of copies that need to be done on the best individual. Tests were carried out on five nonlinear functions with two variables and the result was that the best individual multiplication was able to provide the best solution.
NAZIEF-ADRIANI STEMMER DENGAN IMBUHAN TAK BAKU PADA NORMALISASI BAHASA PERCAKAPAN DI MEDIA SOSIAL Katarina N. Lakonawa; Sebastianus A. S. Mola; Adriana Fanggidae
J-Icon : Jurnal Komputer dan Informatika Vol 9 No 1 (2021): Maret 2021
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v9i1.3749

Abstract

The use of non-standard language is increasingly prevalent in communication on social media. The use of indefinite language is not limited to sentences, clauses, or phrases but also word usage. In this study, the nonstandard word (NSW) will be normalized to the Indonesian standard word (SW). The Nazief-Adriani stemmer (NAS) method was developed into a nonstandard stemmer (NSS) by increasing its ability to detect non-standard additives. The Needleman-Wunsch similarity algorithm is used to weight the matches. The test results with the Mean Reciprocal Rank (MRR) of 3,438 NSW found that the use of NSS with the number of queries = 9 (Q = 9) had the highest of 79.26% with an average of 50.48%. Meanwhile, MRR testing using NAS with Q = 9 got the highest result of 72.87% and an average of 47.23%. Of the two MRR tests carried out, there were 3 letters that had the highest stemming results, both in tests using NAS and using NSS, namely the initial letters r, f and j. The most significant increase in MRR value occurs in the initial letters 'd', 'n' and 't' which are the initial letters of some non-standard affixes.
IDENTIFIKASI TELAPAK TANGAN MENGGUNAKAN METODE EKSTRAKSI CIRI PRINCIPAL COMPONENT ANALYSIS (PCA) DAN IDENTIFIKASI CIRI RESILIENT PROPAGATION Mellanie Lette; Adriana Fanggidae; Nelci D Rumlaklak
J-ICON : Jurnal Komputer dan Informatika Vol 4 No 1 (2016): Maret 2016
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v4i1.5199

Abstract

The palmprint recognation in this research was being held through several stages, which are image acquisition, preprocessing using histogram equalization,edge detection using sobel operation, feature extraction using Principal Componnent Analysis and face identification using Resilient Propagation. This research use Principal Componnent Analysis as its feature extraction method and Resilient Propagation as its recognition method. This research use 40 training data and 20 testing data wich are gained from PolyU. The final result of the research shows that accuration performance of system using Principal Componnent Analysis and Resilient Propagation by using error tolerance as 1,E-06 and neuron hidden output as 10 are giving best performation that is 65% can be recognized as compared with using the othe error tolerance , neuron output and neuron hidden .
APLIKASI PERHITUNGAN HARTA WARISAN BERDASARKAN HUKUM ISLAM Rahmadanilah Rahmadanilah; Yulianto T Polly; Adriana Fanggidae
J-ICON : Jurnal Komputer dan Informatika Vol 4 No 1 (2016): Maret 2016
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v4i1.5200

Abstract

Heritage is something that is inherited, such as property, reputation, etcetera. In the daily lives, legacy issues often trigger conflicts and raises a family relationship. The main cause is human greed, and beyond this the lack of knowledge of the relevant parties regarding the calculation of inheritance law. Many Muslims do not know the law and how the calculation is based on the Islamic law of inheritance. To overcome these problems then built an application to assist in the calculation of the legacy based on Islamic Law following that Islamic Law rules. This application produces the percentage and nomina which received by each heirs.
DETEKSI KEBERADAAN RAMBU PERINTAH DI JALAN MENGGUNAKAN EUCLIDEAN COLOR FILTERING Rizal Pebianto; Adriana Fanggidae; Yulianto Triwahyuadi Polly
J-ICON : Jurnal Komputer dan Informatika Vol 9 No 2 (2021): Oktober 2021
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v9i2.5217

Abstract

Command signs are one of the types of traffic signs that we often encounter when driving on the road and are used to express some commands while driving. A distinctive feature of command signs is that they have a blue background color. Driver negligence in paying attention to the presence of command signs on the road can result in accidents. There needs to be a system that can detect command signs on the road as a solution. The command sign detection process uses the Euclidean Color Filtering method to filter colors and BLOB to look for interconnected pixels. The RGB color center values ​​(10,110,200) and the radius range [90, 150] are used in the color filter stage with Euclidean Color Filtering. The system was tested on 150 images of primary data and 25 images of secondary data. Primary data collection was carried out in the morning, afternoon, and evening with a distance of 5–10 meters and 10–15 meters. The system's average accuracy of command sign detection in testing primary data is 90.67%, and secondary data is 76%, so the average accuracy of the whole system is 88.5%. System failure in detecting the presence of command signs on the road is due to insufficient or excessive lighting conditions, signs blocked by other objects, angles that are too tilted, and signs adjoining other things with the same color or close to the background color.
Pengamanan Portable Document Format (PDF) Menggunakan Algoritma Kriptografi Kurva Eliptik Gever Imanuel Taopan; Meiton Boru; Adriana Fanggidae
J-ICON : Jurnal Komputer dan Informatika Vol 10 No 1 (2022): Maret 2022
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v10i1.5296

Abstract

The use of digital documents has been widely used in various groups, organizations or agencies. One of the digital documents that often used is the Portable Document Format (PDF). An algorithm needed to implemented in the software, so that it can secure these documents from parties who can harm. One of the algorithms that can be used is Elliptic Curve Cryptography (ECC). ECC has an advantage on the level of data security with a key not too long. Encryption carried out on a 16 Bytes PDF header using 7 ECC parameters, prime number, coefficient A, coefficient B, base point, secret key, public key and K. The prime numbers used are 67, 71, 151, 199, 229, and 239. Other parameters chosen randomly. Each prime number involved for encryption of 4 types of file size, 1KB-2MB, 2MB-4MB, 4MB-6MB, and more than 5MB, where each type of file size has 5 different files. There were 3 trials for each file, so there were 360 trials. The 360 trials, there were ±55.33% in the very low correlation class, ±34.72% in the low class, ±10% in the medium class and ±1.94% in the strong class. Overall the average correlation generated is 0.212282779. Therefore, the use of the ECC algorithm for encryption the header of PDF is quite good. In the encryption process there is also an increase in file size by 64 Bytes, but when decrypting the file size returns to its original size.
Case Based Reasoning untuk Mendiagnosa Jenis Gangguan Jiwa Menggunakan Metode Dempster Shafer Viani Anika Afeanpah; Sebastianus Adi Santoso Mola; Adriana Fanggidae
J-ICON : Jurnal Komputer dan Informatika Vol 10 No 1 (2022): Maret 2022
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v10i1.6326

Abstract

Mental disorders are disorders of behavior, moods and thoughts that can change a person's behavior differently than usual. Cases of mental disorders obtained from medical record data at the Naimata Mental Hospital (RSJ) in 2019 were 6,157 patients with 2 mental specialists. The lack of a number of mental specialists has caused some mental health programs not to run properly, resulting in a longer recovery rate for mental disorders. In this study, a case-based reasoning system was created to overcome the problem of the lack of mental health workers at Naimata Hospital. The system uses the dempster shafer method for the indexing process and cosine similarity to calculate the similarity value. This system diagnoses 9 types of mental disorders based on 125 symptoms. The output of the system is a diagnosis of the type of mental disorder suffered by the patient. Based on the test results on 90 data on a case basis by dividing the data into 10 folds, the system accuracy for similarity is 49.83% and indexing is 81.01%. The test was carried out another way, by dividing the data randomly into 3 groups, namely 9:1, 8:2 and 7:3 20 times. The first group got an average indexing of 85.21% and similarity 49.22%, the second group got an average indexing of 82.01% and similarity 48.84%, the third group got an average indexing of 78.82% and similarity 48.09%. The average accuracy is low due to the unbalanced case data for each type of disturbance.
Klasifikasi Penentuan Status Zona di Kota Kupang Menggunakan Aalgoritma Naive Bayes Classifier Nelci Dessy Rumlaklak; Adriana Fanggidae; Yulianto Triwahyuadi Polly
J-ICON : Jurnal Komputer dan Informatika Vol 10 No 1 (2022): Maret 2022
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v10i1.6458

Abstract

The World Health Organization (WHO) made the corona virus a pandemic in 2020. This virus has hit the whole world, including Indonesia. East Nusa Tenggara (NTT) as of June 2021 recorded 18,741 positive cases of Covid-19 and the City of Kupang was the area that contributed the most positive cases. The daily increase in Covid-19 cases in Kupang City shows a fairly high increase. The purpose of this study is to build a classification system to determine the status of the Covid-19 zone in the city of Kupang. The system design using the waterfall model is used to design and build the system while the Naïve Bayes Classifier algorithm is used for classification. The criteria as input in the system for the classification process are positive confirmed data, recovered patient data and death data. The results of the classification process consist of 2 classes, namely the Green Zone and Red Zone. Kupang City's daily Covid-19 case data for January-June 2021 with a total of 181 as training data. 31 test data entered into the system were analysed using the Naïve Bayes Classifier method and succeeded in obtaining classification results as system output. Tests in the study were carried out on systems built using Blackbox testing to test the functionality of the system with the expected results. The confusion matrix is ​​used to test the performance of the classification method and the results have an accuracy rate of 77.91% and a precision value of 73.91%.
ANALISIS ELITISME PADA ALGORITMA GENETIKA MENGGUNAKAN PENGKODEAN ORDINAL REPRESENTATION DALAM TRAVELLING SALESMAN PROBLEM Arfan Yehezkiel Mauko; Adriana Fanggidae; Yulianto Triwahyuadi Polly
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.v10i2.8473

Abstract

Traveling salesman problem (TSP) is one of the optimization problems to find the shortest route, where each city is only allowed to visit exactly once. The search for the shortest route can be completed by several algorithms, one of which is the genetic algorithm. Genetic algorithm is an optimization algorithm that works by imitating the evolutionary process in nature. During the evolution process, individuals with the best fitness may undergo changes that result in a decrease in fitness. Therefore, in order to keep individuals with the best fitness from becoming extinct during the evolutionary process, it is necessary to make copies of these individuals which is called elitism. There are three models of elitism, namely, Model 1: the best individuals are copied as many as m replacing the worst m individuals, Model 2: the best m individuals replace the worst m individuals, and Model 3: the best m individuals replace the worst m individuals selected randomly from 100%-m worst individual. The values ​​of the m parameters are 10%, 20%, 30%, and 40%. The tests were carried out with elitism and without elitism on different populations and cities. The test results show that Model 2 with m = 10% and population = 20 is the ideal parameter in solving TSP.
SISTEM PENDETEKSI KERUSAKAN JALAN ASPAL MENGGUNAKAN CANNY EDGE DETECTION Farhan Aditya Rafi; Adriana Fanggidae; Yulianto Triwahyuadi Polly
J-ICON : Jurnal Komputer dan Informatika Vol 11 No 1 (2023): Maret 2023
Publisher : Universitas Nusa Cendana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35508/jicon.v11i1.10100

Abstract

Road is a means of access for humans to move from one place to another, connecting one place to another, and serving as transportation infrastructure. At all times, asphalt roads are passed by road users, including small, medium, and large vehicles. However, road conditions are not always smooth and often there are damages in certain parts of the road. Factors such as water, weather, temperature changes, unstable soil conditions, air temperature, poor compaction process on the base layer, and the weight or overload of heavy vehicles that exceed capacity, as well as the increasing volume of vehicles, can cause road damage. Road damage can reduce economic revenue and increase accident rates. Some types of asphalt road damage include undulating, potholes, cracking, and asphalt puddles on the road surface. Potholes are the most common type of damage that cause accidents for road users. This study uses the Canny edge detection method to detect asphalt road damage. The minimum object size that can be detected as road damage is 15x15 pixels and the maximum is 290x540 pixels. Testing was conducted on 65 primary data and 35 secondary data, and the average accuracy obtained were 90.5% and 88%, respectively.