Claim Missing Document
Check
Articles

Found 5 Documents
Search
Journal : JURNAL SISTEM INFORMASI BISNIS

Penerapan Machine Learning Untuk Prediksi Bencana Banjir Sulis Sandiwarno
Jurnal Sistem Informasi Bisnis Vol 14, No 1 (2024): Volume 14 Nomor 1 Tahun 2024
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21456/vol14iss1pp62-76

Abstract

Indonesia beriklim tropis karena terletak pada garis katulistiwa, oleh karena itu Indonesia juga hanya memiliki dua musim, yaitu musim kemarau dan musim hujan. Apabila musim hujan tiba dan curah hujan intensitasnya tinggi, maka hal tersebut berpotensi menyebabkan bencana banjir. Kerugian yang ditimbulkan akibat bencana banjir cukup besar. Untuk mengurangi risiko bencana dan kerugian akibat banjir, diperlukan inovasi dalam mitigasi bencana. Beberapa penelitan sebelumnya telah melakukan analisa dan prediksi mengenai bencana banjir dengan menggunakan metode berbasis machine learning seperti Support Vector Machine (SVM), K-Nearest Neighbor (KNN), dan Naive Bayes. Akan tetapi metode yang digunakan dalam penelitian tersebut memiliki permasalahan seperti tingkat akurasi yang rendah dan membutuhkan waktu yang lama untuk melakukan perhitungan data. Dalam penelitian ini kami mengusulkan sebuah model baru yang dinamakan Deep Neural Investigation Network (DNIN) algorithm, yang dikombinasikan dari Convolutional Neural Network (CNN) dan Bidirectional Long Short Term Memory (BiLSTM). Proses dari usulan metode dalam penelitiaan terdiri dari tiga bagian, yang pertama Convolutional Neural Network (CNN) digunakan untuk melakukan ekstraksi fitur spasial dari data banjir, selanjutnya Bidirectional Long Short Term Memory (BiLSTM) digunakan untuk menangkap pola temporal dari fitur-fitur tersebut. Kemudian tahap terakhir adalah menggabungkan hasil dari kedua metode tersebut. Hasil dari penelitian yang dilakukan terhadap data curah hujan, didapatkan informasi bahwa model yang kami usulkan lebih unggul dibandingkan dengan model sebelumnya dalam melakukan prediksi bencana banjir.
Penerapan Metode Service Quality (SERVQUAL) dan Simple Additive Weighting (SAW) untuk Menentukan Pengambilan Keputusan terhadap Kepuasan Pelanggan (Studi Kasus: Restoran Ayam Geprek) Sulis Sandiwarno
Jurnal Sistem Informasi Bisnis Vol 14, No 1 (2024): Volume 14 Nomor 1 Tahun 2024
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.21456/vol14iss1pp88-99

Abstract

Perkembangan usaha kuliner di Jakarta bisa dibilang mengalami perkembangan yang cukup pesat. Setiap bulannya selalu ada resto baru maupun tempat makan baru seperti pedagang kaki lima maupun kafe. Untuk menghadapi persaingan tersebut, perlu adanya suatu ulasan kepada para pelaku Usaha Mikro Kecil dan Menengah (UMKM) agar dapat melakukan peningkatan dan perbaikan dalam pelayanannya. Pada penelitian terdahulu, telah dilakukan analisis terhadap kepuasan pelanggan menggunakan metode Simple Additive Weighting (SAW). SAW merupakan suatu metode penjumlahan terbobot yang dikenal secara luas untuk pengambilan keputusan. Akan tetapi, metode tersebut memiliki masalah seperti kurangnya akurasi data. Untuk mengatasi permasalahan tersebut dalam penelitian ini kami ingin menggunakan metode Servqual secara bersama di metode SAW. Tahapan dari usulan penelitian yang kami lakukan adalah melakukan pengumpulan data menggunakan kuesioner yang disebar lalu dianalisis menggunakan metode Servqual dan SAW. Berdasarkan uji coba sistem yang dilakukan pada 5 cabang restoran ayam geprek Sultan, didapatkan hasil bahwa pemilik harus memperbaiki dimensi Responsiveness dengan nilai gap sebesar 0.105, nilai ini lebih rendah dibandingkan dimensi yang lain. Sedangkan cabang Semper ini memiliki prioritas terbesar untuk dilakukan perbaikan dibandingkan dengan 4 cabang lainnya dengan nilai akhir 0.6237. Dengan hasil yang didapatkan tersebut, diharapkan pemilik restoran dapat memberikan perbaikan pelayanannya.
Penentuan Prioritas Persediaan Barang dengan Menggunakan Hybrid Method Aldino, Muhammad Satria; Sandiwarno, Sulis
Jurnal Sistem Informasi Bisnis Vol 15, No 1 (2025): Volume 15 Number 1 Year 2025
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/vol15iss1pp1-10

Abstract

Warehouse is a facility that serves as storage of goods or products. Inventory of goods has an impact on the continuity of the construction project, because if the material runs out, the contractor cannot carry out the work, as a result the project may be delayed from the predetermined schedule. The purpose of the warehouse is to monitor and control the incoming or outgoing materials in a project. In previous studies, an analysis of the AHP and TOPSIS methods has been carried out, but AHP has problems when used in cases with a large number of criteria and alternatives. While TOPSIS has problems in determining the value of the criteria because it is too subjective. Therefore, in this study we propose a hybrid method for calculating DSS which is called “Analytical Hierarchy – Similarity to Ideal Process” (AH-SIP). This proposed method has goals, namely in determining the value of the criteria with a comparison matrix using AHP, and performing alternative rankings using TOPSIS. The results of this study in determining the best material recommendations for procurement are D 25 Threaded Iron with a preference of 0.777, Chicken Wire with a preference of 0.677, and Pilox with a preference of 0.669.
Prediction Analysis of Sleep Disorders Using Machine Learning-Based Techniques Setiawati, Mega; Aldianto, Denise; Sandiwarno, Sulis
Jurnal Sistem Informasi Bisnis Vol 15, No 1 (2025): Volume 15 Number 1 Year 2025
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/vol15iss1pp89-101

Abstract

Sleep is crucial indicator for an individual. Poor sleep quality has serious implication for health. This condition is often triggered by high work pressure and imbalance between work and rest time. While previous research with similar topic has been conducted, it has not comprehensively elucidated the key factors influencing sleep disorders. Therefore, this study conducts more in-depth analysis of factors contributing to sleep disorders including; gender, age, occupation, sleep duration, quality of sleep, physical activity level, stress level, BMI, heart rate, and daily steps. Subsequently, we employ Machine Learning (ML) techniques to investigate further sleep disorders. The ML models include: Naïve Bayes (NB), Support Vector Machine (SVM), K-Nearest Neighbor (KNN), Logistic Regression (LR), Convolutional Neural Network (CNN), dan Long Short-Term Memory Network (LSTM). The objective is to assess the effectiveness of ML model implementation based on information from data and the significance of specific factors in predicting sleep disturbances. The results of this study indicate that the combination of the LR model with Chi-Square achieved the highest average F1 score, which was 84.75%, in sleep disorder classification. The research comprises several stages: (1) Data collection, (2) Pre-processing of the collected data, and (3) Training models capable of processing data for evaluation to understand the contribution of indicators to sleep disorder predictions. The findings of this study provide insights into the effectiveness of the constructed models in predicting sleep disorders
Comparison of Sentiment Analysis Models Using Machine Learning Methods for Customer Response Evaluation (Case Study: Bosca Living) Pangestu, Ryan; Priantama, Tio Alwi; Agustian, Virman; Sandiwarno, Sulis
Jurnal Sistem Informasi Bisnis Vol 15, No 3 (2025): Volume 15 Number 3 Year 2025
Publisher : Diponegoro University

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.14710/vol15iss3pp359-366

Abstract

Bosca Living, a star seller on Shopee and Tokopedia, is facing the challenge of customer sentiment analysis. This research evaluates models and methods to strengthen the response to customer feedback. In previous studies, feature extraction techniques such as Term Frequency-Inverse Document Frequency (TF-IDF), Word2Vec, FastText, and Global Vectors for Word Representation (GloVe) have been tested. Machine learning models such as K-Nearest Neighbors (KNN), Random Forest, Support Vector Classifier (SVC), XGBoost, Logistic Regression, and Decision Tree have been employed, but a more in-depth comparison is needed according to Bosca Living's assessment. This research proposes a model comparison through preprocessing, feature extraction, and parameter determination stages using GridSearchCV. Machine learning models like KNN, Random Forest, SVC, XGBoost, Logistic Regression, and Decision Tree are evaluated with StratifiedKFold to reduce the risk of overfitting. The research results provide deep insights, guiding Bosca Living in improving responses to customer feedback. This approach is expected to optimize business strategies, support continuous improvement, and be responsive to market dynamics and evolving customer needs