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

32 33 34 35 36

PROCUREMENT BUSINESS PROCESS REENGINEERING IN MANUFACTURING COMPANIES USING BUSINESS PROCESS ANALYSIS METHODS Fitria, Fitria; Feta, Neneng Rachmalia; Satria, Deki
Jurnal Pilar Nusa Mandiri Vol 18 No 2 (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.v18i2.3481

The high Increas business competition makes many organizations in any field to be able to run their business more quickly and effectively to achieve business goals. Business processes are a series of activities carried out by organizations to achieve organizational goals, in manufacturing companies the procurement business process is one of the main business processes of the organization. Therefore, in this study, an analysis of the procurement business process was carried out and then designed a more optimal targeting business process engineering for the organization. Business process engineering is carried out by analyzing business processes using the valued added analysis, flow analysis and simulation methods. The results of business process engineering show that targeting business processes that are prepared are better in terms of time and costs compared to existing business processes.

LOMBOK PEARL QUALITY CLASSIFICATION USING A COMBINATION OF FEATURE EXTRACTION AND ARTIFICIAL NEURAL NETWORKS BASED ON SHAPE Imran, Bahtiar; Yani, Ahmad; Muslim, Rudi; Zaeniah, Zaeniah
Jurnal Pilar Nusa Mandiri Vol 18 No 2 (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.v18i2.3507

Lombok is attracted to the Moto GP event, which is held annually. Various tourism brands are owned by the island of Lombok, one of which is Mutiara. The ideal Pearl is perfectly round and smooth, but there are a variety of other shapes as well. One method that can be used to process Pearl's image is Computer Vision. For that, it is necessary to have a way to classify the quality of a Pearl based on its shape. The purpose of this study is to propose a system for pearl image classification by combining feature extraction with artificial neural networks. The method used in this study is GLCM feature extraction and Neural Networks. The proposed system can provide good classification results by combining the GLCM method and the Neural Network. This study uses Epochs 5, 10, 15, 30, 50, 100, 200, 300, and 500 with a learning rate of 0.5. The results of this study indicate that Epoch 100 gives the highest accuracy, 91.66%.

DECISION SUPPORT SYSTEM OF REWARDING ON LECTURER PERFORMANCE USING FUZZY TSUKAMOTO METHOD CASE STUDY AT MATARAM UNIVERSITY OF TECHNOLOGY Yani, Ahmad; Zenuddin, Z; Hambali, H; Muslim, Rudi; Imran, Bahtiar
Jurnal Pilar Nusa Mandiri Vol 18 No 2 (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.v18i2.3548

To prepare quality and character human resources, Mataram Technological University strives to provide the best in carrying out the tridharma activities of higher education, one of which is by giving rewards in the hope that morale and loyalty can continue to be improved. However, the gift-giving system that the Mataram Technological University has implemented has not been able to bring about change because the gift-giving system is incorrect. This is because the applied reward-giving assessment system only refers to the assessment without paying attention to other criteria in the tridharma of higher education. Such as the implementation of learning, Research, and community service. Therefore, to overcome this problem, a decision support information system for awarding lecturer performance is needed, which is built using the fuzzy Tsukamoto method by considering several criteria such as Presence, Research Results, and Community Service Results. Lecturer Performance Index in carrying out the learning process. With this decision support system, the implementation of the Tridharma carried out by lecturers can continue to monitor the system and improve the quality and accreditation of study programs and universities.

EARLY WARNING SYSTEM FOR FLOOD IN GUNUNGSARI DISTRICT BASED ON IOT WITH TELEGRAM BOT AS A WARNING MESSAGE SENDER Hambali, Hambali; Akbar, Ardiyallah; Yani, Ahmad
Jurnal Pilar Nusa Mandiri Vol 18 No 2 (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.v18i2.3711

Entering the rainy season with a high level of rainfall will have an impact on vulnerability to floods that will hit a number of areas in various parts of Indonesia. As is often the case in the Gunungsari Sub-district, West Lombok Regency, heavy rains that come early with high intensity for several days often occur, which causes flood disasters and the absence of an automatic system or tool that can detect flooding in the area so that people around the difficulty of detecting floods that come early and cause many people to lose their homes and property due to the flood disaster. The purpose of this study is to provide information related to signs before a flood disaster using the Raspberry Pi 4 as the main tool and the Hc-SR04 ultrasonic sensor as a tool for measuring the distance of an object, where this system can monitor the water level of the river, then disseminate information. related to the water level periodically via Telegram. The test results of the detection sensor system show that the level of accuracy in reading the water level with an average error of 0.48%, indicates that this IoT system has good accuracy.

SENTIMENT ANALYSIS OF INDONESIAN COMMUNITY ON COVID-19 VACCINATION ON TWITTER SOCIAL MEDIA Nurmalasari, Nurmalasari; Astuti, Widi; Gata, Windu; Zuniarti, Ida
Jurnal Pilar Nusa Mandiri Vol 18 No 2 (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.v18i2.3820

In the process, data mining will extract valuable information by analyzing the existence of specific patterns or relationships from extensive data. One of the concerns of the new disease outbreak caused by the coronavirus (2019-nCoV) or commonly referred to as Covid-19, was officially designated as a global pandemic by the World Health Organization (WFO) on March 11, 2020. To break the transmission of Covid-19, the government carried out vaccinations for the Indonesian population. In the first period, the vaccination target will be for health workers with a total of 1.3 million people, public officers with 17.4 million people, and 21.5 million people. 19. The Data processed is only text data from Twitter application reviews that use Indonesian. Using the polarity of the Sentiment class Textblob, the sentiment class is positive, negative, and neutral. The data mining used is SVM, Naive Bayes, and Logistic Regression. As for this research in the form of knowledge of sentiment in the community towards vaccination activities, the results of this study get 43% positive sentiment, 40.8% negative, and 16.2% negative by testing the classification algorithm, Logistic Regression accuracy of 87%, SVM 86, 4%, and Naive Bayes, 40% of these results, can be seen that the Indonesian people have a positive sentiment towards the covid-19 vaccine.

IMPLEMENTATION OF HASHLIPS ART ENGINE TO EARN IMAGE VARIATIONS ON NON-FUNGIBLE TOKEN (NFT) Arda, Muhammad Adhli; Setiaji, Bayu
Jurnal Pilar Nusa Mandiri Vol 18 No 2 (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.v18i2.3898

Non-Fungible Token (NFT) is a blockchain-based token that securely maps copyright ownership to digital assets, these digital assets exist on the blockchain network which have identification codes and metadata that are unique and different from each other (one-of-the-kind). . It can also be interpreted as a digital asset that represents a variety of assets that are considered unique. NFTs can be traded for digital assets (images, music, videos, virtual creations) where ownership is recorded in a smart contract on the blockchain. One of the difficulties faced is that it takes a very long time for NFT creators to create a large number of works of art in a short time. To make it easier for creators to create NFT images, Daniel Eugene Botha, or better known as Hashlips, created a Hashlips Art Engine algorithm that can be used to create many different NFT images based on the layers provided using the canvas API and node.js. The hashlips algorithm also generates metadata as an important role in the mechanism for searching and exchanging NFT data and measuring the percentage of rarity in the resulting image. In addition, this study also shows the time required to create NFT images.

BALI TOURIST VISITS CLUSTERED VIA TRIPADVISOR REVIEWS USING K-MEANS ALGORITHM Wamulkan A.S, Ufik Alngatiq Hidayat; Utami, Nengah Widya; Anggara, I Nyoman Yudi
Jurnal Pilar Nusa Mandiri Vol 19 No 2 (2023): 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.v19i2.4571

Bali is one of the provinces with the most popular destinations for tourists. However, there are obstacles in developing tourist destinations in the province of Bali in terms of absorbing more tourist visits. Tripadvisor, the world's largest tourism information platform. In order to improve its service to users, Tripadvisor conducts online reviews to obtain ratings based on travel experience. The purpose of this study is to determine clustering and accuracy in tourist visits to tourist destinations in the province of Bali. Clustering is done using 3 clusters using the KDD method. The first process is data selection, then data processing which consists of several stages, first deleting rows of empty data, then cleaning duplicate data and the final result is 5261 clean data then data transformation, so that data can be read by python, The next process is data mining, this process uses the K-Means clustering algorithm which produces 3 clusters with cluster 1 being medium with 1495 data, high cluster 2 with 2315 data, and low cluster 3 with 1451 data. The Davies Boldin Index is used to evaluate the K-Algorithm means clustering, the result is 0.3 where the value is very good because it is not minus and the value is close to zero.

TREND ANALYSIS AND CORRELATION OF TOURIST, RESTAURANT AND HOTEL VISITS IN KUNINGAN REGENCY Hesananda, Rizki; Trihandoyo, Agus; Wiliani, Ninuk; Rahmawati, Nidya Sari
Jurnal Pilar Nusa Mandiri Vol. 20 No. 2 (2024): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Pe
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v20i2.4618

This study conducts an in-depth analysis of the tourism sector in Kuningan Regency, focusing specifically on hotel stays, tourist arrivals, and restaurant visits. Utilizing forecasting models and correlation analyses, the research aims to uncover trends and interdependencies within the sector. The primary objective is to identify actionable insights that can inform data-driven decision-making. The study employs the FBProphet algorithm for forecasting future trends and conducts Kendall correlation analysis to examine relationships among key variables. Data collected spans a time series of 84 months, from January 2016 to December 2022. FBProphet accurately predicts trends in hotel stays, while variations exist in predictions for tourist arrivals and restaurant visits. Mean values for hotel stays, tourist arrivals, and restaurant visits are 21,098.67, 135,647.33, and 130,660.83, respectively. Kendall correlation analysis reveals a moderate positive correlation (0.214, p-value = 0.004) between tourist arrivals and restaurant visits, a strong positive correlation (0.324, p-value = 1.291e-05) between tourist arrivals and hotel stays, and a weaker positive correlation (0.176, p-value = 0.019) between restaurant visits and hotel stays. These findings underscore the intricate dynamics of Kuningan Regency's tourism sector, providing stakeholders with critical insights for strategic planning. The research contributes significantly to sustainable growth initiatives by guiding stakeholders in leveraging the interconnected elements of tourism and making well-informed decisions.

ANALYSIS OF WHISPER AUTOMATIC SPEECH RECOGNITION PERFORMANCE ON LOW RESOURCE LANGUAGE Pratama, Riefkyanov Surya Adia; Amrullah, Agit
Jurnal Pilar Nusa Mandiri Vol. 20 No. 1 (2024): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Pe
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v20i1.4633

Implementing Automatic Speech Recognition Technology in daily life could give convenience to its users. However, speeches that can be recognized accurately by the ASR model right now are in languages considered high resources, like English. In previous research, a few regional languages like Javanese, Sundanese, Balinese and Btaknese are used in automatic speech recognition. This research aim is to improve speech recognition using the ASR model on low-resource language. The dataset used in this research is the Javanese dataset specifically because there is a high-quality Javanese speech dataset provided by previous research. The method used is fine-tuning the Whisper model which has been trained on 680,000 hours of multilingual voice data using a Javanese speech dataset. To reduce computation requirements, parameter efficient fine-tuning (PEFT) implemented in the fine-tuning process. The trainable parameter is reduced to <1% because the implementation of PEFT reduces the computation required by the model for fine-tuning. The best WER evaluation result is 13.77%, achieved by the fine-tuned Whisper large-v2 model compared to the base model of Whisper large-v2, which achieves 89.40% in WER evaluation. Performance improvement in WER evaluation showed that fine-tuning effectively improves the performance of the Whisper automatic speech recognition model on recognizing speeches in low-resource languages like the Javanese language compared to the Original Whisper model performance with minimal computational cost needed for fine-tuning large model.

OPTIMIZATION OF POTATO LEAF DISEASE IDENTIFICATION WITH TRANSFER LEARNING APPROACH USING MOBILENETV1 ARCHITECTURE Brawijaya, Herlambang; Rahmawati, Eva; Haryanto, Toto
Jurnal Pilar Nusa Mandiri Vol. 20 No. 1 (2024): Pilar Nusa Mandiri : Journal of Computing and Information System Publishing Pe
Publisher : LPPM Universitas Nusa Mandiri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33480/pilar.v20i1.4718

Diseases affecting potato leaves frequently lead to significant setbacks for farmers, reducing the overall harvest and the quality of the potatoes. Given the critical need for prompt disease detection, this research introduces the use of the MobileNet framework grounded in the Convolutional Neural Network (CNN) for adept detection of potato leaf ailments. During the research, potato leaf images undergo processing, and their distinct features are gleaned using CNN. Then, harnessing the MobileNet framework, these images undergo classification to ascertain the existence of diseases. The aspiration is that the formulated model can pinpoint diseases with notable precision, rapid feedback, and enhanced computational adeptness. Initial findings underscore the potential of this methodology in discerning potato leaf diseases, providing renewed optimism for farmers grappling with plant health issues. Experiments using the Transfer Learning approach showed good performance in classification and displayed a high accuracy rate of 99.2%.

Page 34 of 42 | Total Record : 418

32 33 34 35 36

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