Garuda - Garba Rujukan Digital

Expert System Using Naive Bayes Method in Identifying Caries Disease in Human Teeth Hari, Tio Ramadan Sapto; Sumijan, S
Jurnal Sistim Informasi dan Teknologi 2021, Vol. 3, No. 4 (Accepted)
Publisher : Rektorat Universitas Putra Indonesia YPTK Padang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/jsisfotek.v3i4.180

Caries disease in human teeth is a disease that permanently destroys the inner walls of teeth and forms small holes in the teeth. The Indonesian people lack the knowledge to find information and identify tooth decay, which makes many people unaware of the consequences and dangers of this disease. Tooth decay disease is usually caused by three factors. The first factor is teeth and saliva, which are the hosts of microorganisms in the oral cavity. Bacteria and food are the second and third factors. The purpose of this research is to help the public find information about tooth decay, thus forming a branch of artificial intelligence, the expert system. Artificial intelligence is a science that allows you to build computer systems that display intelligence in different ways. An expert system is a computer program or information system that uses some knowledge of an expert. The methods used in this study are the Naive Bayes method and the model's view controller, which are implemented as a database in the PHP Codeigniter framework and MySQL. The data processed in this study is knowledge about the symptoms of dental caries obtained from experts. The test results of this method provide patients with the knowledge necessary to prevent tooth decay, with an accuracy rate of 83.61%. This expert system helps the public to recognize and obtain information about tooth decay. The Expert System can also be used to take the first step in preventing tooth decay.

Audit Web E-Government Dengan Acunetix Web Vulnerability Guna Menganalisis Dan Perbaikan Celah Keamanan Website Khairani, Maisan Dewi Puspa; Yuhandri, Y; Sumijan, S
Jurasik (Jurnal Riset Sistem Informasi dan Teknik Informatika) Vol 9, No 1 (2024): Edisi Februari
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/jurasik.v9i1.751

The use of the internet in government to encourage the realization of e-Government can provide benefits in increasing the power of society by increasing access to information, improving government services to the community, strengthening interaction between government and the private sector in related industries, and increasing the ease and openness of government management. One tool used to identify vulnerabilities in web applications is Acunetix Web Vulnerability. This tool is a security scanner that can automatically detect common vulnerabilities in web applications, including SQL injection attacks, Cross-Site Scripting (XSS), and others. The purpose of this research is to conduct an e-Government web audit, steps for e-Government security analysis and provide recommendations for improvements from the results of security analysis using Acunetix web vulnerabilities on the Padang City DPMPTSP website. Data was obtained using the Acunetix web Vulnerability tool to obtain a report from the penetration test process which contains information about security vulnerabilities found on the SINOPEN website https://nonperizinan.web.dpmptsp.padang.go.id/sinopen. The vulnerability findings of 148 data were at a high level, 107 data were at a medium level, 16 data were at a low level. Some of the attacks found were 11 attacks, namely Blind SQL injection, Cross site scripting (XSS), SQL injection, Application error message, HTML form without CSRF protection, Clickjacking: X-Frame-Option Header Missing, Cookie Without Secure Flag Set, File Upload, Login Page Password Guessing Attack, Broken Link, Password Type Input With AutoComplete Enabled. The Acunetix web vulnerability tool is used as a basis for analyzing improvements made after scanning the website. The results after an e-gov security audit was carried out to analyze and improve the level of vulnerabilities found on the SINOPEN website were at a low level, thereby increasing the level of security from attacks and the status of the website can be said to be safe from attack vulnerabilities.

Sistem Penunjang Keputusan dalam Penentuan Calon Kepala Madrasah dengan Metode Weighted Product Silvia, Ade; Sumijan, S
Jurnal Informasi dan Teknologi 2021, Vol. 3, No. 4
Publisher : SEULANGA SYSTEM PUBLISHER

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37034/jidt.v3i4.156

Madrasah is one of educational institutions integrated in the system of national education as outlined in UU Sisdiknas No. 2 Tahun 1989 and updated in the UU No. 2 Tahun 2003. The manager or the headmaster of madrasah plays the most significant role in the progress of madrasah, having a variety of functions such as managerial and supervisional ones with implication on its physical and non physical aspects. Therefore, it is very essential to choose a headmaster of certain madrasah out of the best possible candidate. In West Sumatera, election of headmaster through promotion and rotation lies upon the authortity of the provincial office of the Ministry of Religious Affairs, i.e. its Head of Office and selection committee. To this time, the basis for the election depends on simple observation, interviews and a kind of selection process for a number of teachers sent by the regency offices of the Ministry of Religious Affairs. This survey is conducted to rank all promoted candidates according to certain criteria outlined by the regulations by computerised information system. The method used in this survey is weighted product, one of the methods of the Decision Support System DSS. With this method in the system, all possible candidates will be ranked and the selection commitee will need less time and more accuration to pick the best ones. It is hoped that this product will be a contribution to be used by the provincial office of the Ministry of Religious Affairs in West Sumatra and can be adjusted to needs of the office.

Pemilihan Deteksi Tepi Terbaik Untuk Menganalisa Citra Ultrasonografi Kehamilan Rizki, Syafrika Deni; Sumijan, S; Putra, Okta Andrica
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v5i1.344

In its development, image processing is very helpful for solving problems faced by humans. Imaging processing is an image processing technique of an object to distinguish the background and the object to be analyzed. This research uses a segmentation method that can distinguish between objects and backgrounds. Analyzing objects from ultrasound images requires the expertise of an experienced doctor. In addition, there are artificial factors that make automated analysis complicated. We aim to improve natural imagery. Therefore to overcome the potential difficulties in analysis, we present four Comparison of Edge Detection, namely Gradient Image, Roberts Operator, Sobel Operator and Prewitt Operator. In image processing, data accuracy and accuracy are required as well as knowledge of statistics because image processing is related to data processing. The result of this research is to determine which edge detection is more appropriate for analyzing ultrasound images. The conclusion from this research is that from the four operators that were tried, the results of the testing process showed that the Prewit operator succeeded in detecting existing objects, even objects that function as background were successfully detected. The resulting edge detection is smoother compared to other operators.

Penerapan Metode Preference Rangking Organization Method For Enrichment Evaluation Dalam Pemilihan Perguruan Tinggi Terbaik Yani, Ahmad; Sumijan, S; Ramadhanu, Agung
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.498

Information technology is a means and object of a system method to organize, transmit, interpret, use, process, obtain, and store data in a meaningful and useful way. Higher education is the form of post-secondary education that includes diploma, bachelor, master, doctoral and vocational programmes, as well as specialized programmes organized by the College based on the culture of the Indonesian nation. The Institute of Higher Education Services (LLDIKTI) is a working unit surrounded by the Ministry of Research Technology, and the Government of higher education that helps to improve the quality of the higher education. Decision support systems combine a variety of techniques and methods aimed at collecting, analysing, and presenting relevant information to support better and more effective decision-making processes. In research using PROMETHEE (Preference Ranking Organization Method for Enrichment Evaluation) is one of the methods Multi Criteria Decision Making (MCDM) means performing determination or sequencing in a multicriteria analysis. The data used in this study are data of private colleges in LLDIKTI region X of the province of Western Sumatra with a total of 84 Colleges. Private colleges based on calculations using the PROMETHEE method, Private Colleges with the name of Colleges UNIVERSITAS PUTRA INDONESIA YPTK PADANG showed the largest value compared to other Colleges, thus obtaining the best position 1 with leaving flow value 0,58333 entering flow value 0,05556 and net flow value 0.522778. Based on the values obtained, it was concluded that the PROMETHEE method was very effective for use in mating. These results show that the method is capable of producing.

Optimalisasi Analisis Keamanan Menggunakan Acunetix Vulnerability Pada Rekam Medis Elektronik Tamin, Zulfiqar; Yuhandri, Y; Sumijan, S
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.494

The use of the internet and web applications has significantly increased across various sectors, including education, healthcare, finance, and entertainment. However, web applications are highly vulnerable to various types of cyberattacks, such as SQL Injection, Cross-Site Scripting (XSS), and code injection, which can threaten the confidentiality, availability, and integrity of data. In line with technological advancements, the 2022 Ministry of Health regulation mandates that all healthcare facilities in Indonesia implement Electronic Medical Records (EMR). Universitas Andalas Hospital (RS UNAND) has adhered to this policy by developing a web-based EMR system. This study aims to evaluate and analyze the security of the EMR application used at RS UNAND. The Vulnerability Assessment process in this study was conducted using the Acunetix Web Vulnerability Scanner tool, which is designed to identify and assess vulnerabilities in web applications. The results of the first scan revealed that the RS UNAND EMR application had significant vulnerabilities, with a threat level of 3 (high). This scan identified 573 alerts, including 1 high-level, 253 medium-level, 2 low-level, and 317 informational alerts. These issues were followed by a thorough recap and further analysis to determine optimization steps. Several major vulnerabilities identified included HTML Form Without CSRF Protection, User Credentials Sent in Clear Text, Directory Listing, Source Code Disclosure, Git Repository Found, Multiple Vulnerabilities Fixed in PHP Versions, and Slow HTTP Denial of Service Attack. Optimization measures were then taken through a comprehensive review of the source code and enhancements to the security features of the EMR application. After the optimization, the second scan showed a significant reduction in the threat level, with the RS UNAND EMR application dropping to threat level 1 (low), with 12 alerts, consisting of 0 high and medium-level alerts, 9 low-level alerts, and 3 informational alerts. This study underscores the importance of regular security assessments and the optimization of security features to protect sensitive data in electronic medical record systems.

Analisis Data Mining Menggunakan Algoritma C 4.5 Dalam Memprediksi Penerima Bantuan Sosial Yemi, Leonardo; Defit, Sarjon; Sumijan, S
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.496

Poverty is one of the highest problems most often experienced by various developing countries, there are many ways to overcome the purpose of social assistance is to overcome poverty, social assistance is usually provided by the government and non-profit organizations to groups of people who have economic limitations. The purpose of this study was to help recipients of social assistance to be right on target and can help people with limitations. One of the techniques used in data analysis is data mining. This study identifies recipients of social assistance using data mining efficiently and fairly. and testing the rapidminer application in the prediction process using the C4.5 algorithm. This research dataset uses 80 data based on data on recipients of social assistance in the Jati sub-district, Padang city. The results of the C4.5 algorithm performance test were able to present prediction analysis output with a very good level of accuracy, namely 93.75%. These results are quite evident that the C4.5 algorithm is able to present maximum prediction output in determining recipients of social assistance in the Jati sub-district, Padang city for the next period. Based on these results, it can facilitate and accelerate decision-making related to determining the receipt of social assistance by applying the C4.5 algorithm and can provide more accurate results.

Implementasi Algoritma C4.5 untuk Memprediksi Tingkat Ketepatan Kelulusan Mahasiswa Sari, Imrah; Defit, Sarjon; Sumijan, S
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 5, No 4 (2024): Edisi Oktober
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v5i4.506

Timeliness of graduation not only reflects the competence of graduates but also affects the assessment of study programme accreditation. To achieve this goal, it is important to predict and classify the timeliness of graduation to support more effective academic decision making. In this research, the Knowledge Discovery in Database (KDD) process is used, which aims to find knowledge from big data. One of the main stages in KDD is data mining, which focuses on pattern extraction with various algorithms. This research uses the C4.5 algorithm, a classification method that builds a decision tree to identify attributes that affect the timeliness of student graduation. This study uses data from students in 2017, 2018, and 2019 from the Bachelor of Nursing and Bachelor of Public Health study programmes at Syedza Saintika University, with a total sample of 46 student records. The C4.5 algorithm is applied to form a decision tree model, which produces classification rules based on attributes such as Grade Point Average (GPA), Study Programme, Gender, and Region of Origin. The results of the C4.5 algorithm implementation show a prediction accuracy of 89.13%, with GPA as the most dominant factor in influencing graduation accuracy. This research proves that the C4.5 algorithm is effective in predicting the timeliness of student graduation.

Penerapan Metode Linear Discriminant Analysis Dalam Mendeteksi Kematangan Buah Tomat Setiawan, Adil; Sumijan, S
Kesatria : Jurnal Penerapan Sistem Informasi (Komputer dan Manajemen) Vol 6, No 1 (2025): Edisi Januari
Publisher : LPPM STIKOM Tunas Bangsa

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/kesatria.v6i1.539

Tomatoes are fruits of various shapes and sizes originating from the American continent, the tree can reach a height of 2.5 meters, grows as a fruit plant in fields, yards or is found wild at an altitude of 1-1600 meters. above the sea level. Tomatoes are classified as fruits because they are the edible part of the plant and contain seeds or seeds visible through fiber which play an important role in improving digestion. Fiber facilitates bowel movements and prevents constipation, thereby improving the digestive system. Researchers examined the level of ripeness of tomatoes to obtain a classification of ripe tomato parts and unripe tomato parts by utilizing the Linear Discriminant Analysis method, one of the supervised learning algorithms used to carry out classification in machine learning. This technique is used to find the best linear combination of variables as an indicator of separating classes (classifying) in the dataset. LDA works by projecting data into a lower dimensional space that maximizes the separation between RGB, hue, saturation classes. Farmers usually sort them manually to determine the ripeness of tomatoes, so a system is needed that is capable of classifying the ripeness of tomatoes using the Linear Discriminant Analysis method. Based on the results of accuracy testing, the accuracy rate reaches 85%, this is a result that has become reference material for future researchers

Pemilihan Deteksi Tepi Terbaik Untuk Menganalisa Citra Ultrasonografi Kehamilan Rizki, Syafrika Deni; Sumijan, S; Putra, Okta Andrica
J-SAKTI (Jurnal Sains Komputer dan Informatika) Vol 5, No 1 (2021): EDISI MARET
Publisher : STIKOM Tunas Bangsa Pematangsiantar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30645/j-sakti.v5i1.344

In its development, image processing is very helpful for solving problems faced by humans. Imaging processing is an image processing technique of an object to distinguish the background and the object to be analyzed. This research uses a segmentation method that can distinguish between objects and backgrounds. Analyzing objects from ultrasound images requires the expertise of an experienced doctor. In addition, there are artificial factors that make automated analysis complicated. We aim to improve natural imagery. Therefore to overcome the potential difficulties in analysis, we present four Comparison of Edge Detection, namely Gradient Image, Roberts Operator, Sobel Operator and Prewitt Operator. In image processing, data accuracy and accuracy are required as well as knowledge of statistics because image processing is related to data processing. The result of this research is to determine which edge detection is more appropriate for analyzing ultrasound images. The conclusion from this research is that from the four operators that were tried, the results of the testing process showed that the Prewit operator succeeded in detecting existing objects, even objects that function as background were successfully detected. The resulting edge detection is smoother compared to other operators.

Title

Found 23 Documents
Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title Search

Found 23 Documents Search

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Title

Found 23 Documents
Search