Article Per Year (5 Year)
p-Index From 2021 - 2026
4.309
P-Index
This Author published in this journals
All Journal Jurnal Transformatika Jurnal Informatika dan Teknik Elektro Terapan Sistemasi: Jurnal Sistem Informasi Sinkron : Jurnal dan Penelitian Teknik Informatika JTT (Jurnal Teknologi Terpadu) JIKO (Jurnal Informatika dan Komputer) J-SAKTI (Jurnal Sains Komputer dan Informatika) Jurnal Riset Informatika Jurnal Teknologi Terpadu Jusikom: Jurnal Sistem Informasi Ilmu Komputer JURNAL Al-AZHAR INDONESIA SERI SAINS DAN TEKNOLOGI Idealis : Indonesia Journal Information System Jurnal Teknik Informatika (JUTIF) Jurnal FASILKOM (teknologi inFormASi dan ILmu KOMputer) J-SAKTI (Jurnal Sains Komputer dan Informatika) Jurnal Riset dan Aplikasi Mahasiswa Informatika (JRAMI) SmartComp
Hermanto, Teguh Iman
Unknown Affiliation
Biochemistry, Genetics & Molecular Biology Civil Engineering, Building, Construction & Architecture Computer Science & IT Control & Systems Engineering Decision Sciences, Operations Research & Management Electrical & Electronics Engineering Energy Engineering Industrial & Manufacturing Engineering Materials Science & Nanotechnology Mechanical Engineering Public Health

Published : 27 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 27 Documents
Search

 1   2   3 
Perancangan UI/UX Aplikasi Ngaji Ummi Berbasis Mobile Menggunakan Metode Design Thinking Khasanah, Afifa Nur; Resmi, Mochzen Gito; Hermanto, Teguh Iman
JURNAL Al-AZHAR INDONESIA SERI SAINS DAN TEKNOLOGI Vol 9, No 1 (2024): January 2024
Publisher : Universitas Al Azhar Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36722/sst.v9i1.2129

Abstract

Muslims occupy first place in Indonesia. There are 223 million Indonesian Muslims spread throughout the archipelago, among them there are 153.8 million or around 65% of the Indonesian Muslim population who cannot read the Qur'an, this is a matter of concern for the Indonesian Muslim population in learning the Qur'an. Many factors that affect people are difficult to learn the reading of the Qur'an, and from various observations, the Ummi method is applied as a method that is easy to apply and is a method that is starting to be widely used today. The current technological developments certainly support the ease of learning the Ummi method anywhere, anytime, and by anyone. An important factor of mobile applications is the user interface to provide convenience and comfort for application users. The design thinking method is used in this research, this method solves problems by approaching users, there are 5 stages in this method: The mobile application prototype produced in this study is called "Ngaji Ummi", and testing is carried out using the system usability scale method. The average SUS value obtained is 81.071, it can be concluded that the "Ngaji Ummi" application meets the acceptable category or can be accepted by users. With the "Ngaji Ummi" mobile application, it is hoped that it will help the community to learn the Qur'an easily and pleasantly.Keywords – Al-Qur’an, Ummi Method, Ngaji Ummi, Design Thinking, System Usability Scale.
OPTIMIZATION OF HYPERPARAMETERS FOR LSTM-BASED SENTIMENT ANALYSIS ON FACIAL SERUM DATASETS Saputri, Merly; Hermanto, Teguh Iman; Nugroho, Imam Ma'ruf
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 1 (2024): JUTIF Volume 5, Number 1, February 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.1.1192

Abstract

Air pollution and environmental pollutants directly exposed to the skin can damage the skin by accelerating premature aging, increasing the risk of acne, and causing hyperpigmentation. Skincare products such as facial serums containing vitamin C, niacinamide, and vitamin E can effectively address these issues. Awareness of the importance of using facial serums is increasing, so information about product quality through user reviews is essential before placing an order. Sentiment analysis used to classify product reviews into positive or negative, thus providing an overview of the product quality sought before placing an order. This research uses the Long Short-Term Memory (LSTM) method for the sentiment classification process. In this process, the text is converted into a number vector through feature extraction using Word2Vec. In addition, several hyperparameters such as the number of epochs, batch size, and activation function are tested to obtain optimal accuracy results. Testing the number of epochs was conducted with variations of 10, 15, and 20 to determine the performance of the resulting model as the number of epochs increased. Testing the batch size is done to evaluate the batch size in influencing the performance of the model. The batch sizes tested were 16, 32, and 64. In addition, choosing the best activation function can help the LSTM model learn more complex patterns and improve performance in sentiment analysis. The activation functions tested were Softmax, Sigmoid, and Softplus. The results of this study show that the optimal combination of the number of epochs 20, batch size 16, and Softmax activation function can provide optimal accuracy of 96.45%.
Implementasi Algoritma Support Vector Machine dan Randoom Forest Terhadap Analisis Sentimen Masyarakat Dalam Penggunaan Aplikasi Tiket.com, Traveloka, dan Agoda Pada Google Playstore Prabowo, Calleb Bhaskoro; Hermanto, Teguh Iman; Ma'ruf, Imam
Smart Comp :Jurnalnya Orang Pintar Komputer Vol 13, No 1 (2024): Smart Comp: Jurnalnya Orang Pintar Komputer
Publisher : Politeknik Harapan Bersama

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30591/smartcomp.v13i1.5378

Abstract

Internet hadir sebagai elemen penting dalam menyokong perkembangan teknologi dan informasi dalam segala sektor aktifitas manusia. Pada sektor perdagangan dan pariwisata contohnya, aplikasi Tiket.com, Traveloka, dan Agoda menjadi aplikasi yang paling diminati masyrakat Indonesia saat ini. Ulasan atau review yang disematkan oleh para pengguna merupakan hal penting bagi pihak perusahaan untuk mengetahui kepuasan pelanggan yang nantinya digunakan untuk meningkatkan kualitas dalam segi pelayanan. Proses menganalisis ulasan komentar memiliki beberapa tahapan karena memiliki data yang jumlahnya tidak sedikit. Penggunaan suatu metode membantu dalam melakukan proses klasifikasi komentar yang bersifat positif atau negatif. Ulasan pengguna aplikasi yang diproses diambil dari platform layanan penyedia aplikasi Google Playstore, lalu menarik data yang diinginkan dengan mamasukan library Google Scraper pada Python. Data yang sudah ditarik selanjutnya diberi label untuk memisahkan ulasan yang bersifat positif dan negatif hal ini bertujuan untuk mepermudah proses klasifikasi dengan menggunakan metode Support Vector Machine (SVM) dan Random Forest. Hasil yang didapatkan nantinya merupakan tingkat akurasi dari dua metode yang digunakan berdasarkan pengolahan data yang sudah dilakukan pada masing-masing ulasan yang menjadi data set pada setiap aplikasi. Support Vector Machine memiliki akurasi yang lebih baik dibandingkan dengan Random Forest dengan rincian 85,5%, 87%, dan 88,7% pada urutan aplikasi Tiket.com, Traveloka, dan Agoda. Sedangkan Random Forest memiliki akurasi 84.7%, 84.7%, dan 88.2% dengan urutan aplikasi yang sama.
ANALISIS SEGMENTASI PELANGGAN BERBASIS MODEL RECENCY FREQUENCY DAN MONETARY (RFM) MENGGUNAKAN ALGORITMA K-MEANS Pangestu, Panji Indra; Hermanto, Teguh Iman; Irmayanti, Dede
Jurnal Informatika dan Teknik Elektro Terapan Vol. 11 No. 3s1 (2023)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v11i3s1.3396

Abstract

Business development is currently growing very rapidly, with the development of internet technology that can facilitate all business activities. Increasing business development has an impact on presenting new business competitors, so companies need strategies that are able to maintain customer quality. This study aims to segment customers from the company's sales transaction data, with a large number of transactions, technology is needed to group a data so that the method used in this study is a data mining method  and uses  the K-Means algorithm. With the K-Means Algorithm, it  can help in grouping customers to make it easier for companies to strategize each customer group. This customer grouping uses an initial model of Recency, Frequency and Monetary (RFM) to help calculate customer groups. Data mining evaluation  was carried out  using Silhouette Coefficient with test results using Visual Studio Code software python programming language, The results of this study selected 3 clusters consisting of Low Loyalty totaling 137 customers, Medium Loyalty totaling  1636 customers and Highest Loyalty totaling 2395 customers.
KLASIFIKASI JENIS PENYAKIT PADA DAUN TUMBUHAN STROBERI MENGGUNAKAN METODE CONVOLUTIONAL NEURAL NETWORK ARSITEKTUR INCEPTIONV3 Sitohang, Andrian Herbert Parsaoran; Hermanto, Teguh Iman; Lestari, Candra Dewi
Jurnal Informatika dan Teknik Elektro Terapan Vol. 12 No. 3S1 (2024)
Publisher : Universitas Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.23960/jitet.v12i3S1.5274

Abstract

Stroberi adalah salah satu komoditas tanaman dengan nilai ekonomi yang cukup tinggi di Indonesia. Namun, terdapat upaya yang dapat mengurangi kualitas dan kuantitas hasil panen stroberi, yaitu penyakit-penyakit daun stroberi, termasuk leaf scorch. Oleh karena itu, deteksi dini dan klasifikasi penyakit mengenai daun stroberi ini sangat penting untuk melakukan tindakan yang diperlukan agar kerugian dapat diminimalkan. Tujuan dari penelitian ini adalah untuk mengembangkan model klasifikasi penyakit pada daun stroberi dengan metode Convolutional Neural Network menggunakan arsitektur InceptionV3. Proses penelitian yang dibutuhkan dalam pengembangan model melibatkan pengumpulan dataset gambar daun stroberi yang terdiri dari kategori sehat dan penyakit leaf scorch. Model CNN dilatih dan diuji dengan menggunakan dataset gambar daun tersebut untuk mengidentifikasi dan mengklasifikasikan jenis penyakit dengan tingkat akurasi yang tinggi. Hasil dari penelitian ini menunjukkan bahwa model CNN dengan arsitektur InceptionV3 berhasil mencapai akurasi klasifikasi sebesar 99%, menandakan keandalan model dalam mendeteksi penyakit pada daun stroberi. Selain itu, Implementasi model ini dalam aplikasi berbasis Android diharapkan dapat memberikan alat bantu yang praktis dan efisien bagi petani dalam memantau dan mengendalikan penyakit tanaman secara real-time, sehingga dapat meningkatkan kualitas dan kuantitas hasil panen stroberi. Dengan demikian, penelitian ini tidak hanya berkontribusi pada pengembangan teknologi deteksi penyakit tanaman tetapi juga pada peningkatan produktivitas pertanian.
Development of Hybrid K-Means DBSCAN Algorithm for Optimization of Landslide-Prone Area Clusters based on Web-GIS Irmayanti, Dede; Hermanto, Teguh Iman
SISTEMASI Vol 15, No 1 (2026): Sistemasi: Jurnal Sistem Informasi
Publisher : Program Studi Sistem Informasi Fakultas Teknik dan Ilmu Komputer

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32520/stmsi.v15i1.5671

Abstract

Landslides represent one of the major geological hazards in West Java Province, posing serious impacts on social life, economic activities, and public infrastructure. A key challenge in landslide mitigation lies in the inaccuracy of spatial and temporal classification of landslide-prone areas, as well as the limitations of single-method approaches in disaster data analysis. This study aims to develop a data-driven classification model for landslide-prone areas using a hybrid clustering approach that combines the K-Means and DBSCAN algorithms. The dataset consists of landslide incident records from 2020 to 2024 and administrative spatial data at the regency/city level. The analysis stages include data integration and normalization, statistical exploration, the application of K-Means clustering as a global segmentation framework, and DBSCAN for identifying local patterns and outliers. Model validation was conducted using internal evaluation metrics, yielding a Silhouette Coefficient of 0.448 and a Davies–Bouldin Index of 0.602, indicating that the hybrid method provides superior performance in terms of cluster compactness and separation. The classification results are visualized through an interactive Web-GIS platform developed using Streamlit and Folium, enabling users to select specific years and classification methods while displaying mitigation strategies based on risk categories. This study concludes that the hybrid clustering approach enhances the accuracy of landslide-prone area classification and makes a significant contribution to the provision of more adaptive and practical spatial information to support mitigation policy decision-making in landslide-vulnerable regions.
SENTIMENT ANALYSIS OF INTERNET SERVICE PROVIDERS USING NAÏVE BAYES BASED ON PARTICLE SWARM OPTIMIZATION Anugrah, Anugrah; Hermanto, Teguh Iman; Kaniawulan, Ismi
Jurnal Riset Informatika Vol. 4 No. 4 (2022): September 2022
Publisher : Kresnamedia Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.34288/jri.v4i4.117

Abstract

Twitter is a social media application that is widely used. Where as many as 18.45 million users in Indonesia, Twitter users can send and read messages with a maximum of 280 characters displayed. Many opinions and reviews uploaded by users via tweets on social media are experienced in everyday life. Lately, comments about internet service providers in the covid-19 pandemic have been widely reviewed by Twitter users. Problems about internet providers through words often uploaded include internet provider complaints related to network quality, package prices, user satisfaction, and others. This study aims to classify Twitter users' tweets against internet service providers in Indonesia by analyzing the sentiments of 3 internet service providers, namely with the keywords Biznet, first media, and Indihome, using the Naïve Bayes algorithm and optimization with Particle Swarm Optimization. This research is also helpful in helping to become a measure where prospective new users will see the quality of an internet service provider in Indonesia through tweets and then divide the opinion into positive and negative. The results of Biznet's research using Naïve Bayes produce an accuracy of 77.94%, and after optimization, it becomes 81.62%. First media using Naïve Bayes produces 91.39% accuracy, and after optimization, it becomes 92.88%. Indihome using Naïve Bayes produces an accuracy of 85.78%, and after optimization, it becomes 87.48%. It can be concluded that the Naïve Bayes algorithm is a good algorithm for classification, and optimization using Particle Swarm Optimization has an effect on increasing accuracy results.
Co-Authors Anggraeni, Annisa Mustika Anugrah, Anugrah Azhar, Sarah Afifah Dede Irmayanti Defriani, Meriska Fauzi, Ibnu Fiki Febrianti, Nisa Ghozali, Miftah Al Ismi Kaniawulan, Ismi Khasanah, Afifa Nur Krishnavarty, Ayumas Aura Kusuma, Bagus Lestari, Candra Dewi Lestari, Chandra Dewi Ma'ruf, Imam Mahbubi, Firhan Abdillah Melati, Winda Ayu Muhyidin, Yusuf Ningsih, Tiara Sari Nugraha, Rivan Adi Nugroho, Imam Ma ruf Nugroho, Imam Ma'ruf Nugroho, Imam Maruf Nugroho, Imam Ma’ruf Pangestu, Panji Indra Prabowo, Calleb Bhaskoro Ramadhan, Yudhi Raymond Rengganis, Mega Dwi Resmi, Mochzen Gito Saputri, Merly Sari, Anita Wulan Sitohang, Andrian Herbert Parsaoran Sunandar, Muhamad Agus Syakir, Yusuf Totohendarto, Mochamad Hafid Undamayanti, Erina