JAMI: Jurnal Ahli Muda Indonesia

SiPuTiH: Model Convolutional Neural Network untuk Sistem Pengenalan Tulisan Tangan Hijaiyah

Saiful Nur Budiman — 2025-12-31

This research presents the development of SiPuTiH (Handwritten Hijaiyah Character Recognition System) using the Convolutional Neural Network (CNN) algorithm to address the challenges of handwriting variability in Arabic scripts. The methodology includes dataset acquisition and preprocessing, CNN architecture design, model training, and performance evaluation. The dataset consists of 1,680 handwritten images representing 30 Hijaiyah characters, divided into 80% training and 20% testing data. The proposed CNN architecture employs four convolutional and pooling layers with a total of 6.8 million trainable parameters. Experimental results show that SiPuTiH achieved a 99.7% accuracy rate in recognizing Hijaiyah characters, with only one misclassification between ‘ta’ (ت) and ‘tsa’ (ث) due to morphological similarity. The trained model was implemented in an interactive Streamlit-based application that includes learning modules, quizzes, and real-time handwriting prediction. SiPuTiH demonstrates high reliability not only as a handwriting recognition system but also as an engaging educational platform for learning Arabic letters. This study confirms the effectiveness of CNNs in handling the morphological complexity of Hijaiyah characters and contributes to the development of intelligent educational tools. Future work may explore larger datasets, transfer learning architectures, and contextual (word-level) recognition to enhance system scalability and performance.

A The Influence of TikTok's Recommendation Algorithm (the ‘FYP Destiny’ Effect) and TikTok Live Chat on Purchase Decisions with Perceived Personalization as an Intervening Variable

Dini Febriani — 2025-12-31

purchasing decisions, with perceived personalization as a mediating variable. This study explores how TikTok users' perception of personalization strengthens the relationship between Live Chat interactions, recommendation algorithms, and purchasing decisions.

Methods. This study used a quantitative survey design. The sample consisted of 200 TikTok users in Wonocolo District, Surabaya, who were selected through purposive sampling based on the following criteria: active use of TikTok, interaction with FYP and Live Chat, and making purchases through TikTok Shop. Data were collected using a questionnaire with 20 indicators to measure four latent variables on a 1–5 Likert scale. Data analysis was performed using Partial Least Squares Structural Equation Modeling (PLS-SEM) with SmartPLS 4.

Results. The findings show that both the Live Chat feature and the FYP algorithm have a positive influence on perceptions of personalization and purchasing decisions. In addition, perceived personalization proved to be a significant mediator, linking the influence of Live Chat and the FYP algorithm on purchasing decisions.

Conclusions This study confirms that perceived personalization is a key psychological mechanism that links user interactions through Live Chat and algorithmic recommendations with purchasing decisions. To increase purchasing decisions on TikTok, an effective personalization strategy integrated with platform features is required.

Evaluation of Growth Performance and Economic Efficiency of Hybrid Ducks through Herbal Probiotic Feed Supplementation

David Kurniawan — 2025-12-31

Backgrounds. This study aimed to evaluate the effects of herbal probiotic supplementation in duck feed on the production performance and economic viability of hybrid meat ducks. Methods. A total of 500 unsexed hybrid meat ducklings (DOD), obtained from a cross between Peking drakes and Khaki Campbell ducks, were randomly assigned into five treatment groups (100 ducks per replicate). The experiment was conducted over a 6-week period using a completely randomized design (CRD). All ducks were fed a basal diet formulated according to NRC (1994) standards, with herbal probiotics added to the feed as treatments. Performance indicators measured included feed intake, body weight gain, and feed conversion ratio (FCR). Economic analysis included production costs, revenue, net income, break-even point (BEP), income over feed cost (IOFC), income over feed cost and chick (IOFCC), and revenue-to-cost (R/C) ratio. Data was analyzed using descriptive quantitative methods. Results. Herbal probiotic supplementation positively influenced duck growth performance, resulting in an average FCR of approximately 2.00. Economic analysis revealed improved profitability, with an average R/C ratio of 1.26 and favorable IOFC values. These findings indicate that herbal probiotics can enhance nutrient efficiency without increasing production costs. Conclusions. Incorporating herbal probiotics into duck feed is a promising strategy to improve both biological performance and economic returns in commercial duck farming. Further research is recommended to confirm long-term benefits and broader applicability.

Pergeseran Feature Importance pada Prediksi Pasar Saham Teknologi Menggunakan Machine Learning: Studi Komparatif Pra dan Pasca Pandemi COVID-19

Dzaky Rayssa Buntoro — 2025-12-31

Tujuan: Penelitian ini bertujuan untuk menganalisis apakah model machine learning (XGBoost dan Random Forest) mengalami pergeseran dalam menentukan fitur terpenting untuk memprediksi arah pergerakan saham teknologi sebelum dan sesudah pandemi COVID-19.

Metode: Data yang digunakan adalah time-series harian dari Invesco QQQ Trust (QQQ) sebagai representasi sektor teknologi Amerika Serikat, serta variabel makroekonomi dan volatilitas. Periode penelitian dibagi menjadi dua rezim: pra-pandemi (2018–2019) dan pasca-pandemi (2021–2022). Model dilatih secara terpisah untuk masing-masing rezim, kemudian dilakukan analisis komparatif terhadap feature importance. Evaluasi model menggunakan metrik Accuracy dan F1 Score.

Hasil: Hasil menunjukkan adanya peningkatan prediktabilitas pasar pada periode pasca-pandemi, dengan F1 Score XGBoost meningkat dari 0,346 menjadi 0,556 dan Random Forest dari 0,164 menjadi 0,544. Analisis feature importance menunjukkan pergeseran dominasi faktor: pra-pandemi dipengaruhi secara merata oleh harga, teknikal, dan makroekonomi, sedangkan pasca-pandemi lebih didominasi faktor makroekonomi (FedFundsRate) dan volatilitas (ATR, VIX).

Kesimpulan: Penelitian ini menyimpulkan bahwa pandemi COVID-19 menyebabkan perubahan rezim prediktif di pasar saham teknologi, dengan meningkatnya peran faktor makroekonomi dan volatilitas. Temuan ini menegaskan pentingnya adaptasi model prediksi serta memberikan wawasan praktis bagi investor dalam memahami dinamika pasar pasca-pandemi.

Pembuatan FarmAR: Media Pembelajaran Hewan Ternak untuk Anak TK Berbasis Augmented Reality

Rafika Akhsani — 2025-12-31

Tujuan. Penelitian ini bertujuan untuk mengembangkan Smartbox FarmAR yaitu sebuah media pembelajaran interaktif berbasis Augmented Reality (AR) untuk mengenalkan hewan ternak kepada anak-anak Taman Kanak-Kanak (TK). FarmAR dikemas dalam bentuk smartbox edukatif untuk menciptakan pengalaman belajar yang imersif dan kontekstual.

Material dan Metode. Penelitian menggunakan model pengembangan Multimedia Development Life Cycle (MDLC). Sistem dikembangkan menggunakan Unity dan Vuforia Engine.

Hasil. Hasil penelitian menunjukkan bahwa prototipe Smartbox FarmAR yang dikembangkan telah lolos uji fungsionalitas (black box) dengan hasil 100% fungsi berjalan normal. Selanjutnya, uji coba terbatas kepada 42 anak TK menunjukkan skor rata-rata (X) yang diperoleh dari kuesioner Respon Langsung Anak adalah 1.07 dan dominasi respons positif diperkuat oleh data frekuensi di mana 93.39% dari total seluruh jawaban yang diberikan oleh responden adalah pilihan "positif" (Skor 1). Hal ini mengindikasikan bahwa FarmAR efektif meningkatkan minat dan pemahaman anak TK tentang hewan ternak.

Kesimpulan. Smartbox FarmAR berhasil dikembangkan sebagai media pembelajaran Augmented Reality yang sangat layak dan efektif untuk mengenalkan hewan ternak pada anak usia dini. Implementasi FarmAR disarankan untuk diterapkan sebagai alat bantu mengajar untuk meningkatkan kualitas pembelajaran di TK.