Garuda - Garba Rujukan Digital

Article Per Year (5 Year)

All

Jurnal Pilar Nusa Mandiri

pilar
Website

Published by STMIK Nusa Mandiri

ISSN : 19781946 EISSN : 25276514 DOI : -

Core Subject : Science,

Computer Science & IT

Jurnal Pilar merupakan jurnal ilmiah yang diterbitkan oleh program studi sistem informasi STMIK Nusa Mandiri. Jurnal ini berisi tentang karya ilmiah yang bertemakan: Rekayasa Perangkat Lunak, Sistem Pakar, Sistem Penunjang, Keputusan, Perancangan Sistem Informasi, Data Mining, Pengolahan Citra.

Arjuna Subject : -

Articles 418 Documents

28 29 30 31 32

CLASSIFICATION OF LOMBOK SONGKET CLOTH IMAGE USING CONVOLUTION NEURAL NETWORK METHOD (CNN) Hambali, Hambali; Mahayadi, Mahayadi; Imran, Bahtiar
Jurnal Pilar Nusa Mandiri Vol 17 No 2 (2021): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v17i2.2705

The diversity of tribes makes Indonesia rich in culture that characterizes it, one of which is traditional cloth. Through a variety of patterns and motifs that exist in traditional fabrics, reflecting the life, customs, and culture that exist in an area. Lombok is one of the areas that produces a typical songket cloth. The famous songket craft centers in Lombok are located in the Pringgasela area, Pringgasela District, Sade Village is in Pujut District, Central Lombok Regency and Sukarara is in Jonggat District, Central Lombok Regency. Each area of the center for songket craftsmen has their own characteristics both in terms of the name, motif and texture. When viewed with the naked eye, the texture of each songket will look the same, to be able to know the differences in the texture of each songket, it is necessary to do a classification using computers or technology. Today's society still does not know much information about the textures of songket cloth. The method used to classify the typical Lombok songket in this study uses the Convolution Neural Network (CNN) method. The results obtained from the use of 64 datasets, with details of 40 types of Sade songket and 24 types of Pringgasela songket, after the dataset is trained it produces 86.36% accuracy, 87% precision, 86% recall, and 86% F1-Score. Keywords: Histogram Equalization, Convolution Neural Network, Songket Cloth.

IMPLEMENTATION OF MOORA METHOD FOR DECISION SUPPORT SYSTEM SCHOLARSHIP SELECTION IN SMK MUHAMMADIYAH PRAMBANAN Perdana, Dinar Abdi; Prabowo, Donni; Sari, Bety Wulan
Jurnal Pilar Nusa Mandiri Vol 18 No 1 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i1.2261

Decision Support System for Scholarship Selection at SMK Muhammadiyah Prambanan Using the MOORA Method aims to implement the Multi-Objective Optimization method on the basis of Ration Analysis. In determining scholarship recipients based on predetermined criteria and building a system in the form of a website to help provide alternative decisions in determining the acceptance of scholarships at SMK Muhammadiyah Prambanan. Based on the source of the data obtained, using primary data including interview and observation methods supported by secondary data obtained by literature studies that are relevant to the problem. Scholarship data is calculated and then ranked based on the final value generated from the MOORA calculation. The process of scholarships selection is based on criteria including report card grades, dependents of parents, the income of parents, percentage of attendance, and the number of siblings. The results of this study are the Scholarship Selection Decision Support System Using the MOORA Method, where the final value in the form of an alternative that has the greatest preference value will be placed at the top rank. The alternative will be a recommendation to receive a scholarship.

IDENTIFICATION OF BACTERIAL SPOT DISEASES ON PAPRIKA LEAVES USING CNN AND TRANSFER LEARNING Ilhamsyah, M.; Enri, Ultach
Jurnal Pilar Nusa Mandiri Vol 18 No 1 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i1.2755

Paprika, often called bell peppers, is a plant with the Latin name Capsicum annuum var. gross. Paprika in Indonesia has a high selling value, so the opportunity for cultivating the paprika plant itself is enormous. However, the cultivation of this plant cannot be separated from the threat of disease that can affect the yield of paprika. Bacterial spot is one of them, and it is a disease that is very dangerous for paprika plants because the disease infects all parts of the plant. In this case, early detection is needed to carry out appropriate treatment to minimize the effects caused by bacterial spots. Detection of bacterial spots on paprika can be done by direct observation or conducting laboratory tests, but this requires people who have the appropriate knowledge and experience. Based on the above problems, the identification system can be an option in identifying bacterial spot disease in paprika. This research chose the Convolutional Neural Network (CNN) algorithm in the identification system. Because CNN is one of the algorithms that can receive output in the form of an image which is very suitable for the case of bacterial spots on peppers, this research dataset is divided into healthy leaves and leaves infected with bacterial spots. In this study, the implementation of CNN with transfer learning obtained results from a test accuracy of 90%, training accuracy 97% with a loss of 8.5%, validation accuracy of 97.5% with a loss of 6.9%.

INTEREST ANALYSIS OF USING FINTECH OVO WITH TAM MODEL ON MSMEs IN DENPASAR CITY Amor Waning, Diah Rachmafalen; Estiyanti, Ni Made; Putri, I Gst. Agung Pramesti Dwi
Jurnal Pilar Nusa Mandiri Vol 18 No 1 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i1.2757

The development of technology has now been felt in almost various sectors, one of which is the financial sector. Financial Technology (Fintech) is an innovation in the financial sector that can accelerate the process of financial services, one of which is digital payments. OVO is a type of digital payment with the widest acceptance in Indonesia because it has several partnerships, one of which is with MSMEs. Even so, the use of digital payments is still not massive among MSMEs. The reasons are, among others, the unsupported infrastructure and the perceived usefulness of the digital payment. This study aims to determine the factors that can affect the use of technology using a modified Technology Acceptance Model (TAM) by adding 2 external variables (system quality and culture). The method used is a quantitative method. The research data used primary data obtained directly from the respondents by distributing questionnaires. The data in this study will be analyzed using the PLS-based SEM method using the SmartPLS statistical tool. The results of this study show that as many as seven hypotheses can have a positive and significant effect on interest in using Fintech OVO, while there is one hypothesis that has a positive but not significant effect on interest in using Fintech OVO, namely the effect of perceived easy of use on perceived usefulness.

CLASSIFICATION OF BLOOD DONOR DATA USING C4.5 AND K-NEAREST NEIGHBOR METHODS (CASE STUDY: UTD PMI BALI PROVINCE) Astuti, Ni Ketut Melly; Utami, Nengah Widya; Juliharta, I Gede Putu Krisna
Jurnal Pilar Nusa Mandiri Vol 18 No 1 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i1.2790

Classification of blood donor data at UTD PMI Bali Province by applying the C4.5 and K-Nearest Neighbor algorithms. The number of blood donor data donors is 34,948, of which 90% of the data, namely 31,454 is used as training data. Meanwhile, 10% of the data, which is 3,494 data, is used as the implementation of data testing using the Orange application. C4.5 obtained an accuracy score of 92.9%, F1 of 92.2%, Precision of 93.1%, Recall of 92.9%, specificity of 68.2%. While K-nearest neighbor obtained an accuracy score of 91%, F1 of 90.1%, Precision of 90.8%, Recall of 91%, specificity of 63%. With the AUC (Area Under Curve) value for the C4.5 algorithm is 0.875 and the K-nearest neighbor is 0.813 Good Classification. The results of the evaluation using the confusion matrix C4.5 obtained an accuracy score of 92.6%, F1 of 95.7%, Precision of 99.4%, Recall of 92.4%, specificity of 96%. While k-nearest neighbor obtained an accuracy score of 90.9%, F1 of 94.6%, Precision of 98.4%, Recall of 91.2%, specificity of 88.4%. Based on the evaluation of the confusion matrix and the ROC Analysis Graph, the C4.5 algorithm obtained higher results than the K-Nearest Neighbor algorithm. Based on the data on the characteristics of blood donors at UTD PMI Bali Province, it shows that the gender is male, Badung area, Age 20 to < 30, the occupation of private employees dominates in blood donation.

DATA MINING USING RANDOM FOREST, NAÏVE BAYES, AND ADABOOST MODELS FOR PREDICTION AND CLASSIFICATION OF BENIGN AND MALIGNANT BREAST CANCER Imran, Bahtiar; Hambali, Hambali; Subki, Ahmad; Zaeniah, Zaeniah; Yani, Ahmad; Alfian, Muhammad Rijal
Jurnal Pilar Nusa Mandiri Vol 18 No 1 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i1.2912

This study predicts and classifies benign and malignant breast cancer using 3 classification models. The method used in this research is Random Forest, Naïve Bayes and AdaBoost. The prediction results get Random Forest = 100%, Naïve Bayes = 80% and AdaBoost = 80%. Results using Test and Score with Number of Folds 2, 5 and 10. Number of Folds 2 Random Forest model Accuracy = 95%, Precision = 95% and Recall = 95%, Naïve Bayes Accuracy = 93%, Precision = 93% and Recall 93%, AdaBoost Accuracy = 90%, Precision = 90% and Recall = 90%. With Number of Folds 5 with Random Forest = 96%, Precision = 96% and Recall 96%. Naïve Bayes Accuracy value = 94%, Precision = 94% and Recall = 94%, AdaBoost Accuracy value = 93%, Precision = 93% and Recall = 93%. With Number of Folds 10 Random Forest model = 96%, Precision = 96% and Recall 96%. Naïve Bayes Accuracy value = 94%, Precision = 94% and Recall = 94%, AdaBoost Accuracy value = 92%, Precision = 92% and Recall = 92%. Of the 3 models used, Random Forest got the best classification results compared to the others.

IMPLEMENTATION OF INFERENCE ENGINE WITH CERTAINTY FACTOR ON POTENTIAL DIAGNOSIS OF BRAIN TUMOR DISEASE Harjanti, Trinugi Wira
Jurnal Pilar Nusa Mandiri Vol 18 No 1 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i1.2947

An expert system is a system that has the ability of experts or experts who master a particular field to assist in solving problems. Certainty factor (CF) is one of the methods in an expert system that can define the level of certainty based on facts to show the level of confidence of the expert. This study aims to apply a certainty factor (CF) algorithm to solve the problem of diagnosing potential human brain tumors. Because the symptoms that are felt are not necessarily brain tumors, it is necessary to analyze whether the person has the potential to have a brain tumor or not, even if the potential level is. Brain tumor disease is one of several types of dangerous conditions. This disease is caused by the abnormal growth of cells around the brain. This research produces an application that can diagnose potential brain tumor diseases based on symptom input selected by the user. Then the expert system can display the diagnosis results in percentages and solutions from the results of the diagnosis. The study results indicate that the CF method can solve the problem of uncertainty by giving a degree of confidence from an expert and system user. The accuracy test results resulted in an accuracy value reaching 95%. These results indicate that the system can function and can diagnose potential brain tumor diseases properly

DECISION SUPPORT SYSTEM FOR PALM PLANTATION LAND SELECTION USING THE TOPSIS METHOD Nuraini, Rini; Liesnaningsih, Liesnaningsih; Handayani, Nurdiana; Rusdianto, Hengki
Jurnal Pilar Nusa Mandiri Vol 18 No 1 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i1.2950

Palm oil is an important export commodity in Indonesia. Quality palm oil is produced from quality oil palm plants as well. One of the factors to be able to produce quality oil palm plantations requires the right land. For this reason, land selection is an important factor. This study aims to develop a decision support system by implementing the Technique for Order of Preference by Similarity to Ideal Solution (TOPSIS) method for the selection of oil palm plantations. The TOPSIS method is a negative approach that is obtained by considering the shortest distance from the positive ideal solution and the farthest from the ideal solution. The system is built using a waterfall system development approach that starts from analysis, design, coding and testing. The developed system has the ability to manage alternatives, manage criteria, perform alternative calculations with TOPSIS, and display the best alternative results with TOPSIS. From the results of black-box testing, it proves that the developed system can work and run well. In addition, the results of manual calculations with the system show the same results.

APPLICATION OF DECISION TREE AND NAIVE BAYES ON STUDENT PERFORMANCE DATASET amalia, Hilda; Puspita, Ari; Lestari, Ade Fitria; Frieyadie, Frieyadie
Jurnal Pilar Nusa Mandiri Vol 18 No 1 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i1.2714

Student performance is the ability of students to deal with the entire academic series taken during school. Student performance produces two labels, namely successful and unsuccessful students. Successful students can graduate with excellent, excellent, and suitable performance labels. At the same time, students who have a label on average are students who get poor performance. Measurement of student performance is needed for every educational institution to take strategic steps to improve student performance. This study aimed to obtain a data mining method that worked well on student performance datasets. In this study, student performance datasets were processed, which had 11 indicators with one result label. Student performance datasets are processed using data mining methods, namely decision tree and nave Bayes, while the tool used for dataset processing is WEKA. The research results from processing student performance datasets obtained that the accuracy value for the decision tree method was 94.3132%, and the accuracy produced by the naive Bayes method was 84.8052%.

DECISION SUPPORT SYSTEM TO DETERMINE THE BEST ONLINE SHOP COLLEGE STUDENTS USING THE TOPSIS METHOD Marlina, Marlina; Sari, Retno
Jurnal Pilar Nusa Mandiri Vol 18 No 1 (2022): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Peri
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v18i1.2940

Internet users in Indonesia aged 16 to 64 years who access the internet on mobile phones as many as 195.3 million. In 2015 the number of online shops was 7.4 million people. Convenience and customer service today are key in improving an online shop. The number of online shop applications available for MSME has difficulty in determining the online shop to determine the right online shop in marketing products among students. The TOPSIS method is used as a method for decision-making because it has a simple and easy-to-understand the concept. This study has five criteria, namely product completeness, interface design, service response, delivery services, and transaction processes. And has 5 alternatives namely shopee, tokopedia, bukalapak, lazada and blibli. In this study obtained from the 5 alternatives, the online shop that is most in demand by students is shopee, this can be seen from the pretension value of 0.89.

Page 30 of 42 | Total Record : 418

28 29 30 31 32

Filter by Year

2007 2026

Filter By Issues

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name
-

Contact Email
-

Phone
-

Journal Mail Official
-

Editorial Address
-

Location
Kota adm. jakarta timur,

Dki jakarta

INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Home Page

OAI Link

Editorial Team

Contact

Reviewer

Google Scholar

Contact Name -

Contact Email -

Phone -

Journal Mail Official -

Editorial Address -

Location Kota adm. jakarta timur, Dki jakarta INDONESIA

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Abstract

Contact Name
-

Contact Email
-

Phone
-

Journal Mail Official
-

Editorial Address
-

Location
Kota adm. jakarta timur,

Dki jakarta

INDONESIA