Claim Missing Document
Check
Articles

Found 5 Documents
Search

Komparasi Metode Machine Learning dan Metode Non Machine Learning untuk Estimasi Usaha Perangkat Lunak Adhitya, Ega Kartika; Wahono, Romi Satria; Subagyo, Hendro
Journal of Software Engineering Vol 1, No 2 (2015)
Publisher : IlmuKomputer.Com

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (302.519 KB)

Abstract

Estimasi usaha adalah proses yang sangat penting dalam kesuksesan pelaksanaan suatu proyek perangkat lunak. Memilih metode estimasi yang sesuai dengan proyek yang akan dikerjakan diperlukan pemahaman yang jelas tentang metode-metode estimasi usaha yang salah satunya mengetahui kelemahan dan kelebihan dari masing - masing metode tersebut. Dalam penelitian ini dikaji dua kelompok besar metode estimasi biaya perangkat lunak yakni metode machine learning dan metode non machine learning untuk mengetahui metode mana yang paling baik. Pada penelitian pertama mengunakan metode machine learning  dapat kita ketahui bahwa K-NN(k-nearnest neigbhors) mempunyai nilai RSME yang paling baik.  Pada penelitian Kedua mengunakan metode non machine learning  Dari hasil tersebut dapat kita ketahui bahwa FP (fungsion point ) mempunyai nilai RSME yang paling baik. Pada Penelitian Ketiga diantara metode machine learning dan non machine learning didapatkan K-NN yang mempunyai nilai RSME yang paling baik. Pada penelitian Keempat penambahan seleksi atribut  forward selection mendapatkan hasil yang paling baik untuk digunakan pada estimasi usaha perangkat lunak.
NATIONAL PLATFORM OF LIFE CYCLE INVENTORY DATABASE IN INDONESIA Ariyanto, Novy; Sasongko, Nugroho Adi; Eka Putri, Virny Zasyana; Subagyo, Hendro; Siswanto, Siswanto; Wardani, Maya Larasati Donna; Laili, Nurus Sahari; Pratiwi, Annisa Indah; Yanuar, Ahmad Ismed; Septiani, Marini; Hakim, Arif Rahman; Erlambang, Yaumil Putri; Sari, Chintya Komala; Supono, Ihsan; Widiyaningrum, Retno Ayu
ASEAN Journal of Systems Engineering Vol 9, No 1 (2025): ASEAN Journal of Systems Engineering
Publisher : Master in Systems Engineering

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/ajse.v9i1.101472

Abstract

The national Life Cycle Inventory (LCI) database needs to be built, collaborated and integrated to harmonize LCI data, research and information systems across all stakeholders nationally.  The goals of national LCI data harmonization are to: advance national data, research, and information systems by leveraging multi-agency resources and expertise; improve consistency in Life Cycle Assessment (LCA) methods developed by each institution to develop LCA results for decision-making and public disclosure; and enhance public and national institutions to access harmonized data in a standardized searchable format from a common repository. However, the low number of LCI datasets originating from Indonesia results in using other countries' LCI databases that have the potential for high errors and uncertainties and do not represent supply chain data for specific geographical locations in conducting LCA for Indonesian products. The Research Center for Sustainable Production Systems and Life Cycle Assessment (PR SPB PDH) at the National Research and Innovation Agency (BRIN), an institution tasked with establishing a national database for LCI in Indonesia, is currently entering the stage of collecting LCI datasets. This paper proposes recommendations for developing a national platform for the LCI database in Indonesia. The method used is descriptive qualitative analysis from a comparative review of national databases of various countries. The study reveals that the development that has started fulfilled several criteria. However, some requirements must still be met to become a comprehensive LCI national database.
ANALYZING THE IMPACT OF RESAMPLING METHOD FOR IMBALANCED DATA TEXT IN INDONESIAN SCIENTIFIC ARTICLES CATEGORIZATION Indrawati, Ariani; Subagyo, Hendro; Sihombing, Andre; Wagiyah, Wagiyah; Afandi, Sjaeful
BACA: Jurnal Dokumentasi dan Informasi Vol. 41 No. 2 (2020): BACA: Jurnal Dokumentasi dan Informasi (Desember)
Publisher : Direktorat Repositori, Multimedia, dan Penerbitan Ilmiah - Badan Riset dan Inovasi Nasional (BRIN Publishing)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/j.baca.v41i2.702

Abstract

The extremely skewed data in artificial intelligence, machine learning, and data mining cases are often given misleading results. It is caused because machine learning algorithms are designated to work best with balanced data. However, we often meet with imbalanced data in the real situation. To handling imbalanced data issues, the most popular technique is resampling the dataset to modify the number of instances in the majority and minority classes into a standard balanced data. Many resampling techniques, oversampling, undersampling, or combined both of them, have been proposed and continue until now. Resampling techniques may increase or decrease the classifier performance. Comparative research on resampling methods in structured data has been widely carried out, but studies that compare resampling methods with unstructured data are very rarely conducted. That raises many questions, one of which is whether this method is applied to unstructured data such as text that has large dimensions and very diverse characters. To understand how different resampling techniques will affect the learning of classifiers for imbalanced data text, we perform an experimental analysis using various resampling methods with several classification algorithms to classify articles at the Indonesian Scientific Journal Database (ISJD). From this experiment, it is known resampling techniques on imbalanced data text generally to improve the classifier performance but they are doesn’t give significant result because data text has very diverse and large dimensions.
METODE PENILAIAN KUALITAS DATA SEBAGAI REKOMENDASI SISTEM REPOSITORI ILMIAH NASIONAL Riyanto, Slamet; Marlina, Ekawati; Subagyo, Hendro; Triasih, Hermin; Yaman, Aris
BACA: Jurnal Dokumentasi dan Informasi Vol. 41 No. 1 (2020): BACA: Jurnal Dokumentasi dan Informasi (Juni)
Publisher : Direktorat Repositori, Multimedia, dan Penerbitan Ilmiah - Badan Riset dan Inovasi Nasional (BRIN Publishing)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/j.baca.v41i1.544

Abstract

High quality data and data quality assessment which efficiently needed to data standardization in theresearch data repository. Three attributes most used i.e: completeness, accuracy, and timeliness aredimensions to data quality assessment. The purposes of the research are to increase knowledge anddiscuss in depth of research done. To support the research, we are using traditional review method on theScopus database to identify relevant research. The literature review is limited for the type of documentsi.e: articles, books, proceedings, and reviews. The result of document searching is filtered using somekeywords i.e: data quality, data quality assessment, data quality dimensions, quality assessment, dataaccuracy, dan data completeness. The document that found be analyzed based on relevant research. Then,these documents compare to find out different of concept and method which used in the data qualitymetric. The result of analysis could be used as a recommendation to implement in the data qualityassessment in the National Scientific Repository.
BAGAIMANA MENGHUBUNGKAN PUBLIKASI ILMIAH DENGAN DATA PENELITIAN? Riyanto, Slamet; Subagyo, Hendro; Marlina, Ekawati; Yaniasih; Triasih, Hermin
BACA: Jurnal Dokumentasi dan Informasi Vol. 40 No. 1 (2019): BACA: Jurnal Dokumentasi dan Informasi (Juni)
Publisher : Direktorat Repositori, Multimedia, dan Penerbitan Ilmiah - Badan Riset dan Inovasi Nasional (BRIN Publishing)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14203/j.baca.v40i1.485

Abstract

Scientific data repository has a main role in science because data can be reused, reproduced, and preserved in a long time. In Indonesia there is no institution that manage scientific data repository, generally they only manage publication such as books, journals and proceedings. This is because, most of research data is still managed by a researcher or research group. By using literature study and survey to the journal publisher, authors want to get an information on how to manage research data by publications. Furthermore, the result of literature study is compared to the survey result that produces an important point i.e journal publisher strongly agree to make a policy to the author to attach research data in every paper submitted. Most of journal publisher use Open Journal System (OJS) in managing journal articles, start from paper acceptance until paper publishing. Through this way, research data that attached will be automatically stored to the scientific data repository system based on Application Programming Interface (API).