Article Per Year (5 Year)
p-Index From 2021 - 2026
2.195
P-Index
This Author published in this journals
All Journal Al-Hayat: Journal of Islamic Education Jurnal Teknologi Terpadu Dedication : Jurnal Pengabdian Masyarakat Didaktik : Jurnal Ilmiah PGSD STKIP Subang JAMI: Jurnal Ahli Muda Indonesia PELS (Procedia of Engineering and Life Science) Dedication : Jurnal Pengabdian Masyarakat JOSAR (Journal of Students Academic Research) Jurnal Komputer, Informasi dan Teknologi Jurnal Ekonomi, Manajemen, Akuntansi dan Keuangan
Lestanti, Sri
Program Studi Teknik Informatika S1, Fakultas Teknologi Informasi, Universitas Islam Balitar
Agriculture, Biological Sciences & Forestry Humanities Computer Science & IT Control & Systems Engineering Economics, Econometrics & Finance Education Electrical & Electronics Engineering Engineering Languange, Linguistic, Communication & Media Social Sciences Other

Published : 15 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 15 Documents
Search

 1   2 
Implementasi Algoritma Fuzzy Membership Function dan Naive Bayes untuk Diagnosis Penyakit Ayam Petelur Moch. Rahmadijaya; Sri Lestanti; Saiful Budiman
Jurnal Komputer, Informasi dan Teknologi Vol. 5 No. 2 (2025): Desember
Publisher : Penerbit Jurnal Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53697/jkomitek.v5i2.3361

Abstract

Penyakit pada ayam petelur dapat menyebar cepat dalam satu kandang dan berisiko menyebabkan kematian massal. Keterbatasan akses dokter hewan yang hanya berkunjung setiap satu hingga dua bulan sekali memperlambat penanganan ketika ayam sakit. Penelitian ini bertujuan mengimplementasikan algoritma Fuzzy Membership Function dan Naive Bayes untuk membantu peternak dalam mengidentifikasi penyakit ayam petelur secara dini. Fuzzy Membership Function digunakan untuk mengubah data suhu, misalnya 37,2°C menjadi nilai fuzzy 0,483, yang kemudian diintegrasikan dengan dataset gejala penyakit pada Naive Bayes untuk menghitung probabilitas penyakit tertinggi. Pengukuran akurasi dilakukan dengan metode Accuracy Rate menunjukkan tingkat akurasi 93% dari 100 data uji, dengan 93 diagnosis tepat dan 7 tidak sesuai. Walaupun akurasinya cukup tinggi, hasil algoritma ini masih mengalami kesulitan dalam mendiagnosis penyakit dengan gejala ringan atau mirip antar penyakit.
Analisis Sentimen Terhadap Produk Kecantikan Emina Daily Matte Loose Powder di Emina Official Shop Menggunakan Metode Support Vector Machine Alvena Destria Wirahadi; Sri Lestanti; Abdi Pandu Kusuma
Jurnal Ekonomi, Manajemen, Akuntansi dan Keuangan Vol. 7 No. 1 (2026): January
Publisher : Penerbit Jurnal Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.53697/emak.v7i1.3624

Abstract

Pertumbuhan e-commerce meningkatkan jumlah ulasan konsumen yang dapat menjadi sumber informasi penting bagi produsen. Namun, ulasan tersebut sering ditulis dengan bahasa tidak baku sehingga sulit dianalisis secara manual. Penelitian ini bertujuan untuk mengetahui sentimen konsumen terhadap Emina Daily Matte Loose Powder di Emina Official Shop serta menilai efektivitas metode Support Vector Machine (SVM) dalam klasifikasi sentimen. Sebanyak 1.000 ulasan konsumen dikumpulkan dari Shopee dengan teknik web scraping. Data diproses melalui tahapan pembersihan teks, casefolding, penghapusan stopwords, stemming, dan tokenisasi. Representasi data dilakukan menggunakan TF-IDF, kemudian diklasifikasikan dengan SVM kernel Radial Basis Function (RBF). Hasil penelitian menunjukkan distribusi ulasan didominasi oleh sentimen positif, sedangkan model SVM menghasilkan akurasi 70%. Metode SVM dengan kernel RBF terbukti efektif dalam mengklasifikasikan sentimen produk kecantikan.
Sentiment Analysis Of Mie Gacoan Reviews In Blitar City On The Grab Application Using The Support Vector Machine Method Bayu Samudra; Sri Lestanti; Rizky Dwi Romadhona
JOSAR (Journal of Students Academic Research) Vol 10 No 2 (2025): September
Publisher : Universitas Islam Balitar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35457/jwf5eb71

Abstract

This study aims to analyze customer review sentiments for Mie Gacoan restaurant in Blitar City through the Grab application using the Support Vector Machine (SVM) algorithm. Customer reviews are categorized into three sentiment classes: positive, negative, and neutral. And the total amount of data used is 991 data. The research process includes manual data collection, text preprocessing, weighting using the TF-IDF method, and classification with the SVM algorithm. Model performance is evaluated using a confusion matrix with precision, recall, and F1-score metrics. And for the testing of the algorithm method using Grid Search and Cross Validation. The results show that the linear kernel achieves the best performance with an F1-score of 0.4649. Positive sentiment dominates the reviews, while negative and neutral sentiments are less prevalent. This study demonstrates that SVM is effective for classifying sentiments in customer reviews and can assist restaurant managers in identifying areas for service improvement.
SiPuTiH: Model Convolutional Neural Network untuk Sistem Pengenalan Tulisan Tangan Hijaiyah Saiful Nur Budiman; Sri Lestanti; Sandi Widya Permana
JAMI: Jurnal Ahli Muda Indonesia Vol. 6 No. 2 (2025): Desember 2025
Publisher : Akademi Komunitas Negeri Putra Sang Fajar Blitar

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46510/jami.v6i2.390

Abstract

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.
Implementasi Algoritma FP-Growth untuk Optimalisasi Strategi Pemasaran di Toko Pakaian: Studi Kasus Toko Trend Batara Mahardika Aryoko; Saiful Nur Budiman; Sri Lestanti
Jurnal Teknologi Terpadu Vol 12 No 1 (2026): Juli, 2026
Publisher : LPPM STT Terpadu Nurul Fikri

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54914/jtt.v12i1.2592

Abstract

TREND store is a retail outlet that sells various types of clothing and accessories. As market competition intensifies, the store needs to develop more efficient marketing strategies to remain competitive. One approach is to utilise sales data to analyse consumer purchasing patterns, given that such data has not been optimally used previously. This study aims to identify purchasing patterns and generate association rules as a basis for marketing strategies using the FP-Growth algorithm. The algorithm was chosen because it can identify frequent itemsets without candidate generation, making it more efficient than other methods in market basket analysis. The research data consist of 64 sales transactions from March 2025. In addition to pattern discovery, lift ratios were calculated to measure the strength of relationships between items. The results show that FP-Growth successfully identified significant purchasing patterns and generated relevant association rules. Several rules have lift ratios above 1, such as 1.2472 and 1.1463 for the combination K7, K1, C5, indicating positive relationships. These findings can be used to develop more data-driven and efficient marketing strategies, such as placing related items together to encourage impulsive purchases, supporting product recommendations, promoting planning, and informing other marketing decisions.
Co-Authors Abdi Pandu Kusuma Afirin Alvena Destria Wirahadi Batara Mahardika Aryoko Bayu Samudra Fauzi Asrofi Kirom, Sabitul Moch. Rahmadijaya Ni'ma Kholila Riska Dhenabayu Rizky Dwi Romadhona Saiful Budiman Saiful Nur Budiman Sandi Widya Permana Sendi Dwi Jayanti Yusniarsi Primasari