Claim Missing Document
Check
Articles

Found 40 Documents
Search

Pengembangan Sistem Keamanan Jaringan Komputer Melalui Perumusan Aturan (Rule) Snort untuk Mencegah Serangan Synflood Sahrun, Nori; Roestam, Rusdianto; Defit, Sarjon
SATIN - Sains dan Teknologi Informasi Vol 1, No 2 (2015)
Publisher : STMIK Amik Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (843.257 KB)

Abstract

Rule  snort  merupakan  database  yang  berisi  polapola  serangan  signature  jenis  serangan  yang  disusun sesuai dengan perintah-perintah snort. Rule snort ini, harus di update secara rutin supaya ketika ada sesuatu teknik  serangan  yang  baru  maka  serangan  tersebut dapat  terdeteksi,  dan  program  dalam  penelitian  ini yang  akan  mengupdate  rule  snort  tersebut  dalam mencegah serangan SYNflood. Dalam penulisan rule snort terdapat aturan-aturan yang harus di ikuti yaitu pertama  rule  snort  harus  ditulis  dalam  satu  baris  ( single line), dan yang  kedua snort terbagi menjadi dua bagian yaitu rule header dan rule option. Rule header berisi  tentang  rule  action,  protocol,  source  dan destination IP address,netmask,  source dan destination port.  Rule  option  berisi  alert  message  dan  berbagai dan  berbagai  informasi  dimana  seharusnya  paket tersebut  diletakkan.  Dalam  pengembangan  keamanan jaringan sangat penting untuk di rumuskan  seranganserangan  yang  akan  mengakibatkan  system  down dapat diatasi oleh rule terbaru
Perbandingan Algoritma K-Means Clustering dengan Fuzzy C-Means Dalam Mengukur Tingkat Kepuasan Terhadap Televisi Dakwah Surau TV Malik, Rio Andika; Defit, Sarjon; Yuhandri, Yuhandri
RABIT Vol 3 No 1 (2018): Januari
Publisher : RABIT

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (573.499 KB)

Abstract

Dawah Television Surau TV is a broadcasting media that presents broadcasts around Islam. This media will quickly develop as it presents broadcasting material in meeting the spiritual needs of its viewers. To Increased media development is highly dependent on the satisfaction of the audience in all aspects of broadcast supporting. It is therefore, to measure the level of audience satisfaction as an effort to generate continuous broadcast quality improvement.This research is performing of algorithm clustering comparation with K-Means Clustering modeling and Fuzzy C-Means modeling to classify and mapping the most appropriate dataset so that it can assist analysing or measuring the level of audience satisfaction toward the dawah television Surau TV. Comparison of clustering algorithm performance with K-Means Clustering modeling and Fuzzy C-Means modeling is based on processing speed and trace value of each RMSE parameter of clustering algorithm. The RMSE result of clustering research using algorithm with K-Means Clustering is 2.09879 and by using algorithm with Fuzzy C-Means model is 2.07911. Fuzzy C-Means modeling speed is faster in conducting the clustering process compared with K-Means Clustering modeling. It can be concluded that clustering with Fuzzy C-Means modeling is able to produce more accurate cluster compared to clustering with K-Means Clustering modeling accuracy   Keywords: Clustering; K-Means; Fuzzy C-Means; Satisfaction rate survey; RMSE
Classification of Pineapple Fruit Comosus Merr (Nanas) Quality Using Learning Vector Quantization Method Efendi, Muhamad; Defit, Sarjon; Nurcahyo, Gunadi Widi
Indonesian Journal of Artificial Intelligence and Data Mining Vol 4, No 1 (2021): March 2021
Publisher : Universitas Islam Negeri Sultan Syarif Kasim Riau

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24014/ijaidm.v2i2.4621

Abstract

The demands of publics for these fruits Ananas Comosus Merr (Pineapple) became higher years to years because of the fruit has so many virtues for human healthy and the taste of this fruit is sweet and fresh. Therefore the pineapple farmers have to protect the quality and quantity of this plant in order to get high produce. This research help the pineapple farmers to classify to quality of pineapple fruits by using neural network with Learning Vector Quantization method which has 2 classes, such as: First quality (1st) and Second quality (2nd) quality. This method has 2 process they are : training process and testing process. To input data in the training and testing process are using uniformity, characteristic of varieties, the rate of aging, hardness, size, stem, crown, manure, destroyer, spoilage, rotten and the total solid content of the least was taken by observed the crop of pineapple farmers in the Teluk Batil village Sungai Apit district Siak Riau province. Learning Vector Quantization method automatically will classify the pineapple into their class. The result of the testing classification has gotten the accuracy 65.56% for the first (1st) quality and 34.44% for the second (2nd) quality. At the second testing has gotten 66.67% the accuracy for the first (1st) quality and 33.33% for the second (2nd) quality. At the third (3rd) testing has gotten 64.44% the accuracy for first (1st) quality and 35.56% for the second (2nd) quality.
Penentuan Mutu Kelapa Sawit Menggunakan Metode K-Means Clustering Am, Andri Nofiar; Defit, Sarjon; Sumijan, Sumijan
Jurnal KomtekInfo Vol 5 No 3 (2018): KOMTEKINFO
Publisher : Lembaga Penelitian Dan Pengabdian Masyarakat UPI-YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29165/komtekinfo.v5i3.159

Abstract

The classification of the quality of palm oil in PT Tasma Puja is still done by laboratory testing and then the data is saved manually in Excel. The method of grouping takes time and allows data to be lost. With the development of knowledge, it can be replaced by a data mining approach that can be used to classify the quality of palm oil based on its standards. The k-Means clustering method can be applied to classify the quality of palm oil based on water, dirt and free fatty acids. The data used is the quality data of palm oil in December 2017 as many as 31 data with criteria of good, very good and not good. The test results contained 3 clusters, namely cluster 0 for good categories amounted to 12 data, cluster 1 for very good category amounted to 13 data and cluster 2 for less good categories amounted to 6 data. The k-Means clustering method can be used for data processing using the concept of data mining in grouping data according to criteria.
Algoritma K-Means untuk Klasterisasi Tugas Akhir Mahasiswa Berdasarkan Keahlian Sirait, Weri; Defit, Sarjon; Nurcahyo, Gunadi Widi
Jurnal Sistim Informasi dan Teknologi 2019, Vol. 1, No. 3
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (516.307 KB) | DOI: 10.35134/jsisfotek.v1i3.6

Abstract

School of Information and Computer Management (STMIK) Indonesia Padang is a private university under the auspices of the Higher Education Service Institution (LLDIKTI) Region X, producing graduates who are competent in the field of system analysts and database administrators. Requirements to meet undergraduate graduates (S1) final year students need to complete a final project or thesis.Final year students at STMIK Indonesia Padang often experience confusion in taking the final assignment topic. This is due to the fact that the final year students have not been able to direct their potential in determining the final assignment topic. In this case, researchers conducted the process of grouping final level students using the Data Mining K-means Clustering technique. The process of grouping final-level students is done by utilizing the data of course values from the field mapping system analysts and database administrators. In this grouping two clusters will be produced, namely students taking the final assignment of system analysts and database administrator. So by using this K-means Clustering method, students have direction in taking the final assignment topic. The results obtained from 40 data samples used were students who took the topic of the final project system analysts as many as 20 students and students who took the final assignment of database administrators were 20 students
Implementasi Algoritma K-Means untuk Klasterisasi Peserta Olimpiade Sains Nasional Tingkat SMA Hasanah, Miftahul; Defit, Sarjon; Nurcahyo, Gunadi Widi
Jurnal Sistim Informasi dan Teknologi 2019, Vol. 1, No. 3
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1934.43 KB) | DOI: 10.35134/jsisfotek.v1i3.7

Abstract

The abundance of students causes student data in the system to also be abundant. Schools often find it difficult to manage large amounts of data manually, especially in selecting National Science Olympiad participants and decisions made are less effective. So this research was conducted with the aim of helping the school in selecting OSN participants appropriately and effectively. The method used is Clustering with K-Means algorithm on the report card grades of students majoring in Natural Sciences at SMA Negeri 5 Sijunjung. The results in this study get 3 clusters of students on the selection of OSN participants, namely students who are Very Competent, Competent and Less Competent. This research can be used as a benchmark used by schools in making decisions on the selection of OSN participants.
Penentuan Tingkat Kerusakan Peralatan Labor Komputer Menggunakan Data Mining Rough Set Salam, Riyan Ikhbal; Defit, Sarjon
Jurnal Sistim Informasi dan Teknologi 2019, Vol. 1, No. 4
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (298.923 KB) | DOI: 10.35134/jsisfotek.v1i4.13

Abstract

Equitments of computer laboratory have a function as an important tools in supporting pratical lecturing. These facilitiesshould always be on a condition like ready are proper to use both computers and others. To avoid equipment detriment, it is necessary to do early identification in which prevent the worse condition of equitments. The method use in this study is roughset method wich consists several stages such as Decision System, Equivalence Class, Discernibility Matrix, DiscernibilityMatrix Modulo D, Reduction, and Generate Rules. From this study, it was found that 14 rules in making decisions for equipments treatment of computer laboratory such as use, repair and replace. Thus, this mrthod is very capable indetermining the detriment level of laboratory equipment
Penerapan Artificial Intelligent Rough Set dalam Pengawasan Kinerja Notaris Putri, Adek; Defit, Sarjon; Sumijan, Sumijan
Jurnal Sistim Informasi dan Teknologi 2019, Vol. 1, No. 4
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1578.794 KB) | DOI: 10.35134/jsisfotek.v1i4.15

Abstract

The Regional Supervisory Council (MPD) has the authority to conduct periodic checks on notaries. In carrying out supervision there is no clear legal or regulatory basis on how the notary performance assessment is categorized as very good, good or bad so there is no common perception from MPD members. The purpose of this study is to help MPD find the assessment category in monitoring the performance of the notary public in West Sumatra. To get the assessment category, the Rough Set method can be used to analyze the performance of a notary public. The data used in this study is the data notary examination at the Regional Office of the Ministry of Law and Human Rights in West Sumatra. This study produced 18 rules to get a decision whether the results of the notary performance check are very good, good or not good. So this research is very appropriate to be applied to get the results of the examination of notary performance
Data Mining Menggunakan Rough Set dalam Menganalisa Modal Upah Produksi pada Industri Seragam Sekolah Putra, Rahman Arief; Defit, Sarjon
Jurnal Sistim Informasi dan Teknologi 2019, Vol. 1, No. 4
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (344.133 KB) | DOI: 10.35134/jsisfotek.v1i4.18

Abstract

In a fund industry is a very important factor, mismanagement or unavailability of funds can have a negative impact on the industry, the successful shop still uses internal capital that is capital from the sale of the store itself, the sales results are not always sufficient to pay the production wage money cause late payments which adversely affect the performance of workers and the industry itself, production wage data on successful stores can be utilized by using the rough set method to find solutions to predict future production wages, The results found 57 rules of 8 reducts from 11 Equivalence Classes that provide new information that is the cause factor of not achieving capital production wages, the main factor is income followed by sewing wages, cut wages
Analisis Tingkat Kejahatan Pada Anak Dibawah Umur Menggunakan Metode FP-Growth Juledi, Angga Putra; Defit, Sarjon; Yunus, Yuhandri
Jurnal Sistim Informasi dan Teknologi 2020, Vol. 2, No. 1
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/jsisfotek.v2i1.21

Abstract

Crimes in minors are a series of negligence by parents who endanger or pose a dangerous threat to the child. The purpose of this study is to implement Data Mining, Association rule, and the FP-Growth Algorithm in cases of juvenile crime so that it can extract knowledge and important and interesting information from the database. The data source used is raw data that has not been processed and is a crime data on minors which are summarized in the form of reports from the West Sumatra Regional Police. The results of this study are in the form of software by analyzing data collected using the FP-Growth Algorithm and using the concept of FP-Tree development in searching for Frequent Itemset, for testing the results carried out with applications that have been designed namely the Php programming language. The results of testing are obtained from associations of crime cases that often occur in minors. So it can be seen that data mining using the FP-Growth Algorithm can be used to analyze cases of crime in minors as a material consideration for the police in order to know the ins and outs of crime in children so that it can assist the investigation process.