Claim Missing Document
Check
Articles

Found 6 Documents
Search

DECISION SUPPORT SYSTEM IN IMPROVING THE QUALITY OF BANJARMASIN TOURISM, GET TOUR APPLICATION USING THE SAW METHOD Farisi, Imam; Kamarudin, Kamarudin
Jurnal Riset Sistem dan Teknologi Informasi Vol. 2 No. 1 (2024): Jurnal Riset Sistem dan Teknologi Informasi (RESTIA) Vol. 2 No. 1
Publisher : Universitas Aisyiyah Surakarta

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30787/restia.v2i1.1327

Abstract

Tourism is an activity that is liked by many people, even tourism is one of the important needs, especially regarding socio-economic activities which are seen as having good prospects in the future. In South Kalimantan, especially the city of Banjarmasin, there are many good tourist attractions such as the historical mosque of Sultan Suriansyah, Siring Park, Banjarmaisn City, and culinary tours of Arab villages. Of the tourist attractions that have been mentioned, tourists are still confused in determining tourist attractions because there are many places and a lack of information about tourist attractions in South Kalimantan. From this description, a Decision Support System (DSS) or Decision Support System (DSS) was created to determine tourist attractions in South Kalimantan called the Get Tour application. In addition to displaying information about tourist attractions, this application also displays information on tourist attractions in the form of a map. The results of calculations in the application are in accordance with the formula and expected results based on several criteria, namely distance, parking area, the first special criteria, the second special criteria and the third special criteria using the Simple Additive Weighting (SAW) method.
DEVELOPMENT OF A WEB-BASED POINT OF SALE APPLICATION US-ING THE LARAVEL FRAMEWORK Apriani, Rika; Haerani, Reni; Nugroho, Praditya Adi; Farisi, Imam
JURTEKSI (Jurnal Teknologi dan Sistem Informasi) Vol 11, No 3 (2025): Juni 2025
Publisher : Universitas Royal

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurteksi.v11i3.3918

Abstract

The development of information technology encourages businesses to take over digital systems in business operations, even in the sales process. The Point of Sales (POS) system is the leading solution for recording transactions, managing stock, and creating sales reports efficiently. This study aims to develop a POS application based on a website and make it easier for administrators to manage sales transactions, making them faster and more efficient. This system is made with a structured Agile method, requirements, design, development, testing, deployment, and implementation, and the framework used is the Laravel framework. The test results show that the system is on track and that the efficiency of the transaction and reporting process can be increased. A web-based basis allows users to manage their business more easily in real time because this application is flexible and can be used on various devices.            Keywords: Point of Sales; Laravel; Agile Model;Websites
Long Short-Term Memory Optimization Using Hybrid Sparrow Search Algorithm and Particle Swarm Optimization in Prediction of Water Level at Sluice Gates Farisi, Imam; Hardjianto, Mardi
ASTONJADRO Vol. 13 No. 2 (2024): ASTONJADRO
Publisher : Universitas Ibn Khaldun Bogor

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32832/astonjadro.v13i2.16251

Abstract

During the period from 2014 to 2020, approximately 24 out of 44 districts in Jakarta experienced flooding disasters. Notably, at the beginning of January 2020, the Manggarai floodgate recorded a water height of 962 cm, categorized under Alert Level 1, indicating a critical and hazardous situation that required the evacuation of residents to safe places. This circumstance prompted the local government to enhance the monitoring and prediction system for water levels across all floodgates in the DKI Jakarta region. By utilizing improved water height predictions, the government can prepare more effective mitigation measures, such as reinforcing embankments, improving water channels, and implementing preventive actions prior to the occurrence of flooding disasters. The forecasting technique employing Long Short-Term Memory (LSTM) has been widely employed in previous research to predict water heights. Unfortunately, the accuracy of LSTM heavily depends on the manual selection of hyperparameters. The optimization of hyperparameters in LSTM is essential to find the optimal combination of values that influence the performance of the LSTM network. The objective is to maximize the model's performance, such as accuracy or lower error rates on previously unseen data. This optimization process plays a crucial role in achieving good results from the LSTM model, as the right choice of hyperparameters can yield a model that better understands complex patterns in the data. This research aims to determine the optimal hyperparameters using a hybrid optimization method. The hyperparameter optimization involves a combined approach of Sparrow Search Algorithm (SSA) and Particle Swarm Optimization (PSO) known as Hybrid SSA-PSO. This hybrid method is employed to reduce the error rate in predictions. The research outcomes, utilizing the Hybrid SSA-PSO optimization, revealed the smallest Root Mean Square Error (RMSE) evaluation at the Pulo Gadung water gate, measuring 9,553.
Machine Learning Predictive Model for Analyzing the Influence of Academic Performance on Course Completion in Algorithms and Programming Arifin, Rita Wahyuni; Safitri, Nadya; Farisi, Imam
PIKSEL : Penelitian Ilmu Komputer Sistem Embedded and Logic Vol. 13 No. 2 (2025): September 2025
Publisher : LPPM Universitas Islam 45 Bekasi

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33558/piksel.v13i2.11463

Abstract

The success of students in core computer science courses such as Algorithms and Programming is a critical factor in their academic journey, as it reflects both mastery of fundamental concepts and readiness for more advanced studies. Academic performance in this course is not only shaped by grades but also by behavioral and psychological attributes that influence learning outcomes. This study investigates the influence of academic performance on graduation in Algorithms and Programming using a predictive machine learning approach. The dataset includes 106 student records encompassing academic variables (attendance, average grades, assignment scores), psychological factors (motivation, anxiety toward examinations), and behavioral indicators (discussion participation, AI tool usage, online learning activities). The research adopts the SEMMA methodology, consisting of sampling, exploration, modification, modeling, and assessment. Several classification algorithms were tested, and Random Forest was selected as the primary model due to its strong performance and interpretability. The results indicate that academic achievement variables, particularly average grades and attendance, significantly influence graduation. Additionally, non-academic factors such as motivation, discussion activity, and exam anxiety contribute to predictive outcomes. The model achieved an accuracy of around 91% and an AUC score of 0.93, confirming its reliability in distinguishing between students who passed and those who did not. These findings highlight that academic performance influences success in algorithm and programming courses.
DEVELOPMENT OF A WEB-BASED POINT OF SALE APPLICATION US-ING THE LARAVEL FRAMEWORK Apriani, Rika; Haerani, Reni; Nugroho, Praditya Adi; Farisi, Imam
JURTEKSI (jurnal Teknologi dan Sistem Informasi) Vol. 11 No. 3 (2025): Juni 2025
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat (LPPM) STMIK Royal Kisaran

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33330/jurteksi.v11i3.3918

Abstract

Abstract: The development of information technology encourages businesses to take over digital systems in business operations, even in the sales process. The Point of Sales (POS) system is the leading solution for recording transactions, managing stock, and creating sales reports efficiently. This study aims to develop a POS application based on a website and make it easier for administrators to manage sales transactions, making them faster and more efficient. This system is made with a structured Agile Development method, requirements, design, development, testing, deployment, and implementation. The framework used is the Laravel framework, with system testing conducted using BlackBox. The test results show that the system is on track and that the efficiency of the transaction and reporting process can be increased. A web-based basis allows users to manage their business more easily in real time because this application is flexible and can be used on various devices.            Keywords: agile model;laravel;point of sales; websites  Abstrak: Pengembangan teknologi informasi mendorong bisnis untuk mengambil alih sistem digital dalam operasi bisnis, bahkan dalam proses penjualan. Sistem Point of Sales (POS) adalah solusi utama untuk merekam transaksi, mengelola stok dan membuat laporan penjualan secara efisien. Tujuan dari penelitian ini adalah untuk mengembangan aplikasi POS berdasarkan situs web dan memudahkan administrator dalam mengelola transaksi penjualan, membuatnya lebih cepat dan lebih efisien. Sistem ini dibuat dengan metode Agile Development yang terstruktur, requirement, design, development, testing, deployment, dan implementation serta kerangka kerja yang digunakan yaitu framework Laravel dengan pengujian sistem menggunakan Blackbox. Hasil pengujian menunjukkan bahwa sistem berada di jalur dan bahwa efisiensi proses transaksi dan pelaporan dapat meningkat. Dengan berbasis web memungkinkan pengguna untuk lebih mudah mengelola bisnisnya secara real time, karena aplikasi ini fleksibel melalui berbagai perangkat. Kata kunci: model agile;laravel;point of sales;website
Arsitektur Hybrid Berbasis Aturan dengan Fuzzy Matching dan Klasifikasi Intent SVM untuk Chatbot Pengaduan pada Layanan Nadya Safitri; Farisi, Imam; Putro Dwi Mulyo
TEMATIK Vol. 12 No. 2 (2025): Tematik : Jurnal Teknologi Informasi Komunikasi (e-Journal) - Desember 2025
Publisher : LPPM POLITEKNIK LP3I BANDUNG

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.38204/tematik.v12i2.2669

Abstract

Abstract This study proposes a hybrid architecture for complaint-handling chatbots in the public-service domain by integrating rule-based response generation, fuzzy string matching, and Support Vector Machine (SVM)-based intent classification. Rule-based approaches ensure fast and consistent responses but fail to handle linguistic variations, while fuzzy matching provides tolerance to misspellings and synonyms but lacks measurable evaluation. Meanwhile, NLP-based classifiers such as SVM enable quantitative performance assessment but do not guarantee deterministic control over chatbot outputs in sensitive domains. To address these limitations, a fallback mechanism is designed in which deterministic rules and fuzzy similarity are prioritized, and the SVM classifier is invoked only when no match is detected. The model was trained on 500 annotated conversational entries and evaluated using standard metrics. The results indicate perfect performance with precision, recall, F1-score, and accuracy reaching 1.00 for both intent classes (FAQ/Request and Report), and all dialogue flows passed black-box functional testing. Nevertheless, this performance may be influenced by dataset homogeneity and limited size. Future work will focus on dataset expansion, cross-validation, and out-of-domain evaluation to mitigate overfitting risks. The proposed hybrid architecture demonstrates strong potential for reliable deployment of complaint chatbots in public-service contexts where deterministic control and measurable accuracy are both required. Keywords: hybrid chatbot, rule-based, fuzzy matching, SVM, public-service complaints. Abstrak Penelitian ini mengusulkan sebuah arsitektur hybrid untuk chatbot pengaduan pada layanan publik dengan mengombinasikan pendekatan rule-based, fuzzy matching, dan klasifikasi intent berbasis Support Vector Machine (SVM). Pendekatan rule-based mampu memberikan respons yang cepat dan konsisten, namun gagal menghadapi variasi input bahasa, sedangkan fuzzy matching toleran terhadap kesalahan ketik dan sinonim tetapi tidak memungkinkan pengukuran akurasi. Sementara itu, model NLP seperti SVM dapat memberikan evaluasi kinerja secara kuantitatif, namun tidak menjamin kendali deterministik atas keluaran chatbot pada domain sensitif. Untuk menjembatani keterbatasan tersebut, dirancang sebuah mekanisme fallback yang memprioritaskan aturan deterministik dan fuzzy similarity, kemudian mengaktifkan SVM saat input tidak teridentifikasi. Model dilatih menggunakan 500 entri percakapan teranotasi dan dievaluasi menggunakan metrik standar. Hasil menunjukkan nilai precision, recall, f1-score, dan akurasi sebesar 1.00 untuk dua kelas intent (FAQ/Permintaan dan Lapor), serta seluruh alur percakapan lulus uji fungsional black-box. Meskipun demikian, capaian ini berpotensi dipengaruhi oleh homogenitas korpus dan ukuran dataset yang terbatas. Penelitian lanjutan diarahkan pada perluasan dataset, penerapan validasi silang, serta pengujian pada data di luar domain untuk mengurangi risiko overfitting. Arsitektur hybrid yang diusulkan berpotensi menjadi pendekatan yang andal untuk chatbot pengaduan pada konteks layanan publik yang membutuhkan respons deterministik sekaligus akurasi terukur. Kata kunci: : chatbot hybrid, rule-based, fuzzy matching, SVM, pengaduan layanan publik