Claim Missing Document
Check
Articles

Found 23 Documents
Search

An Efficient Journal Articles Searching using Vector Space Model Algorithm Azis Alvriyanto; Muhammad Taufiq Nuruzzaman; Maria Ulfah Siregar; Rahmat Hidayat
IJID (International Journal on Informatics for Development) Vol. 9 No. 1 (2020): IJID June
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2020.09104

Abstract

One of the main feature of digital library is a search engine which depends on keywords submitted by a user. However, in the traditional algorithm, the computation performance, searching speed, significantly relies on the number of journal articles stored in the databases. Some irrelevant search results also increase the speed of article searching process. To solve the problem, in this paper we propose vector space model (VSM) algorithm to search for relevant journal articles. The VSM algorithm considers a term frequency - inversed document frequency (TF-IDF). The VSM algorithm will be compared to the baseline algorithm namely traditional algorithm. Both algorithms will be evaluated using combination of keywords which can be a synonym, phrase, error typography, or suffix and prefix. By using the data consist of 635 journal articles, both algorithms are compared in terms of 11 evaluation criteria. The results show that VSM algorithm is able to obtain the intended journal at 5th rank on average as compared to the traditional algorithm which can obtain the intended journal at rank of 171st on average. Therefore, our proposed algorithm can improve the performance to accurately sort the journal articles based on the submitted keywords as compared to traditional algorithm.   
Price Forecasting of Chili Variant Commodities Using Radial Basis Function Neural Network Ade Umar Ramadhan; Maria Ulfah Siregar; Syifaun Nafisah; Muhammad Anshari; Rebeccah Ndungi; Rizki Mulyawan; Nurochman Nurochman; Eko Hadi Gunawan
IJID (International Journal on Informatics for Development) Vol. 12 No. 1 (2023): IJID June
Publisher : Faculty of Science and Technology, Universitas Islam Negeri (UIN) Sunan Kalijaga Yogyakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14421/ijid.2023.5129

Abstract

This study addresses the challenge of price instability in chili markets, which can lead to economic losses and inflation. To mitigate this issue, we propose a machine learning model using Radial Basis Function Neural Networks (RBFNN) to predict prices of various chili variants. Our quantitative approach involves a comprehensive data preparation process, including preprocessing and normalization of time series data collected from 2018 to 2022. The RBFNN model is constructed with K-Means clustering for optimal hidden layer configurations and evaluated using Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE). The results demonstrate promising accuracy, with MAPE error rates below 20% and relatively low RMSE values for large red chili (10.37%, 4484) and curly red chili (14.77%, 5590). Our findings indicate the potential for creating a reliable forecast model for predicting chili prices over 7 days, enabling better supply and demand management. The study's results also suggest that increased training data enhances forecasting accuracy. This research contributes to the development of effective price forecasting models, providing valuable insights for policymakers and stakeholders in the chili industry.
PENINGKATAN KOMPETENSI MAHASISWA TINGKAT AKHIR DALAM PENULISAN SKRIPSI MELALUI WORKSHOP MICROSOFT WORD DAN MENDELEY Fiki Sanora; Arya Indrawan; Maria Ulfah Siregar; Fitri Wulandari
Community Development Journal : Jurnal Pengabdian Masyarakat Vol. 7 No. 4 (2026): Vol. 7 No. 4 (2026)
Publisher : Universitas Pahlawan Tuanku Tambusai

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31004/cdj.v7i4.62203

Abstract

Skripsi merupakan karya ilmiah tertulis yang wajib disusun oleh mahasiswa program sarjana untuk memperoleh gelar akademik. Kendala utama yang dialami oleh mahasiswa dalam menyusun skripsi tidak hanya terletak pada substansi materi, tetapi seringkali terdapat pada penguasaan alat bantu penulisan yang mengakibatkan format naskah yang disusun tidak rapi dan referensi yang berantakan. Kegiatan Pengabdian Kepada Masyarakat (PKM) ini bertujuan untuk meningkatkan kapasitas mahasiswa dalam penulisan skripsi melalui workshop Microsoft Word dan Mendeley. Workshop ini dilakukan di kampus Institut Sains Al Qur’an Syekh Ibrahim Pasir Pengaraian yang ditujukan kepada mahasiswa tingkat akhir. Materi yang diberikan berupa pengaturan fitur-fitur di Microsoft Word (penomoran otomatis, penomoran beda halaman, heading dan daftar isi otomatis) serta manajemen referensi menggunakan aplikasi Mendeley. Metode yang interaktif dengan pemaparan materi, diskusi dan pelatihan sudah menunjukkan keberhasilan dari program. Penilaian melalui metode pre-test dan post-test sudah menunjukkan adanya peningkatan pemahaman mahasiswa terhadap penggunaan fitur-fitur yang ada di microsoft word dan mendeley dalam mengerjakan skripsi. Workshop ini memberikan kontribusi nyata untuk mempersiapkan mahasiswa dalam menghadapi proses penulisan skripsi dengan lebih sistematis dan efisien.