Claim Missing Document
Check
Articles

CLaGAtt: A Hybrid CNN-LSTM-GRU-Attention Model for Stunting Classification Based on Anthropometric Sequences Sofiansyah Fadli; Ahmad Tantoni; Novia Arista; M. Khairul Anam; Muhammad Bambang Firdaus
Journal of Applied Data Sciences Vol 7, No 3: September 2026
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v7i3.1454

Abstract

Stunting is a chronic nutritional problem that requires accurate early identification because it affects child growth, cognitive development, and long-term human capital. This study adapts the CLaGAtt model, a hybrid CNN–LSTM–GRU–Attention architecture, for stunting classification using anthropometric sequence data. Rather than proposing a new deep learning architecture, the main contribution of this study lies in adapting the existing CLaGAtt framework through an integrated preprocessing pipeline, sequence construction strategy, class balancing using SMOTE, and an evaluation protocol specifically designed for stunting prediction. The preprocessing pipeline included irrelevant-column removal, data transformation, label encoding, standard scaling, class balancing using SMOTE, and sequence generation with a time step of five and a step of one. Three train–test split scenarios were evaluated, namely 90:10, 80:20, and 70:30. Experimental results showed that the 90:10 split produced the best performance, with 91.42% accuracy, 91.50% precision, 91.50% recall, and 91.43% F1-score. The 80:20 and 70:30 scenarios achieved 87.14% and 85.71% accuracy, respectively, indicating that larger training proportions improved model generalization in the available dataset. These findings suggest that the adapted CLaGAtt framework can effectively integrate convolutional feature extraction, sequential learning, and temporal attention for stunting classification from structured anthropometric data. Future work should validate the model on external datasets and integrate regional visualization to support priority intervention mapping.
User Acceptance of E-Kinerja for Employee Additional Income Policy: A TAM Study in Central Lombok Baiq Amelia Suroyani; Sofiansyah Fadli; Baiq Yulia Fitriyani
Journal of Information System and Informatics Vol 8 No 4 (2026): August
Publisher : Asosiasi Doktor Sistem Informasi Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.63158/journalisi.v8i4.1725

Abstract

The increasing emphasis on professionalism, accountability, and performance management among State Civil Apparatus (ASN) has encouraged government institutions to adopt digital performance systems. This study examines user acceptance of the e-Kinerja application supporting the Employee Additional Income (TPP) policy at the Environmental Agency of Central Lombok Regency using the Technology Acceptance Model (TAM). A quantitative approach using Partial Least Squares Structural Equation Modeling (PLS-SEM) with SmartPLS 4.0.9.9 was applied to questionnaire data from 41 ASN employees. The model included Perceived Ease of Use (PEOU), Perceived Usefulness (PU), Attitude Toward Using (ATU), Behavioral Intention (BI), and Actual Use (AU), with AU measured through self-reported indicators rather than system-generated logs. The measurement model demonstrated satisfactory reliability and convergent validity, although several HTMT values exceeded the recommended threshold. Structurally, PEOU significantly affected PU (β = 0.826; p < 0.001), PU affected ATU (β = 1.070; p < 0.001), ATU affected BI (β = 0.842; p < 0.001), and BI affected AU (β = 0.823; p < 0.001), whereas PEOU did not significantly affect ATU (β = −0.346; p = 0.212). The model explained 68.2% of PU, 65.3% of ATU, 70.9% of BI, and 67.7% of AU. The findings indicate that e-Kinerja acceptance is primarily driven by perceived usefulness, attitudes, and behavioral intention. Practical improvements should emphasize TPP transparency, real-time feedback, data accuracy, simplified reporting, user training, and technical assistance to support adoption.
APLIKASI PENENTUAN HARGA SONGKET MENGGUNAKAN METODE EXTREME PROGRAMMING Anti Susilawati; Khairul Imtihan; Sofiansyah Fadli
Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol. 2 No. 3 (2022): November : Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/teknik.v2i3.710

Abstract

Sukarara Village is one of the largest traditional weaving centers in Central Lombok which has several songket motifs or ornaments that have their own motifs, so that many Lombok people and people from outside the city and abroad come to see how to make songket weaving. and sizes that are sold in the market of course with prices also vary. Such as prices (3 million, 2 million 500, 1 million and 500 hundred), as well as motifs such as motifs (keker, stork, kerit, orchid, subahanale and others), as is the case with thread types such as (silk, marcis, gold, etc.) , cotton and rayon) as well as sizes such as (2 m long – 110 cm wide, 110 cm long – 190 cm wide and 60 cm long – 2 m wide). With the problem of determining the price of songket, one alternative solution that can be used is to design a songket pricing application system that can help provide solutions to buyers. The Extreme Programming method itself is the most widely used approach to software development. So in this study it is very suitable to use Xp because the nature of the application made is done quickly through the existing stages such as: planning, designing, coding, and testing. thread.
PENERAPAN METODE WATERFALL DALAM PENGEMBANGAN SISTEM INFORMASI PELAYANAN PENDUDUKAN BERBASIS WEB (STUDI KASUS: DESA MUNCAN) Yeni Rahmayati; Sofiansyah Fadli; Saikin
Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol. 2 No. 3 (2022): November : Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/teknik.v2i3.728

Abstract

The Village Government and related officials have the task of managing and handling the interests of the local society especially in muncan village area. In the service system, residents expect services that are fast, precise and accurate. Muncan village has an area of 625,000 ha with a population of 8,035 in habitants and a geographical distance between hamlets that are very far from the place of service of villagers, to overcome this, it is necessery to design a web-based information on villages services in muncan village. It is based on the result of this study, it is expected that it could provide fast, precise and accurate services in muncan villages. The research method used is the method of data collection. The type of data used is perimer data and secondary data. Perimer data in question is interview data, while secondary data is information about village history, service information system. The data analysis method used is the PIECES method. The parts of PIECES are performance, information, economy, context and on time. The results of this study are population service information systems that have replaced several activities that were previously carried out manually so as to reduce the obstacles of data recording errors, data search, population data management, and fast and accurate information. It can also increase the effectiveness and efficiency of the functions of costs, time and labor.
IMPLEMENTASI METODE TOPSIS PADA SISTEM PENDUKUNG KEPUTUSAN SELEKSI PEMBERIAN PINJAMAN BADAN USAHA MILIK DESA (STUDI KASUS : DESA BATU NAMPAR INDUK) Rika Nurhaliza; Maulana Ashari; Wafiah Murniati; Sofiansyah Fadli
Jurnal Teknik Mesin, Elektro dan Ilmu Komputer Vol. 2 No. 3 (2022): November : Jurnal Teknik Mesin, Elektro dan Ilmu Komputer
Publisher : Lembaga Pengembangan Kinerja Dosen

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.55606/teknik.v2i3.739

Abstract

The selection process for granting loans to BUMDes Sinar Linus is done conventionally, in this case it makes researchers feel interested in designing a WEB-based Decision Support System as a decision support tool for members of BUMDes Sinar Linus. The methodology used in the development of this system is a method of collecting data in the form of observation, interviews and literature study. While the analytical method used is the TOPSIS (Technique For Others Reference by Similarity to Ideal Solution) method as a decision-making method for the design method using Extreme Programming (XP) which includes planning, design, coding and testing stages. And for the testing method using Blackbox Testing includes home display, login, loan application, applicant, criteria, alternative and TOPSIS. This research resulted in a web-based decision support system that can facilitate members of the BUMDes Sinar Linus in Batunampar Village in deciding or determining prospective recipients of loan funds at BUMDes Sinar Linus.