Claim Missing Document
Check
Articles

SENTIMENT ANALYSIS OF THE SAMBARA APPLICATION USING THE SUPPORT VECTOR MACHINE ALGORITHM Firdaus, Thoriq Janati; Indra, Jamaludin; Lestari, Santi Arum Puspita; Hikmayanti, Hanny
Jurnal Teknik Informatika (Jutif) Vol. 5 No. 4 (2024): JUTIF Volume 5, Number 4, August 2024
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2024.5.4.2673

Abstract

Rapid technological developments have opened up new opportunities for public services by utilizing digital application innovations. One example is the West Java Samsat Mobile (SAMBARA) designed by the West Java Provincial Revenue Agency (BAPENDA). The SAMBARA application is expected to accelerate annual vehicle tax payment obligations, but several reviews on the Playstore show user dissatisfaction with SAMBARA's performance. This study aims to conduct a sentiment analysis of SAMBARA application reviews using the Support Vector Machine algorithm. SAMBARA user review data on Google Playstore was collected using the python programming language google play scraper library on google colabolatory resulting in 1620 data on January 2, 2024. The data pre-processing stage involves various steps such as data cleaning, lowercase conversion, tokenization, stemming, stop words removal, normalization, and the use of the TF-IDF method. The data is then labeled positive and negative, positive for reviews with scores of 4 and 5 and negative labels for reviews with scores of 1 to 3. The Support Vector Machine (SVM) algorithm is used for classification, a well-known method for accurate classification. Model evaluation was conducted using a confusion matrix to calculate the precision, recall, and F1-Score values. The evaluation results provide an overview of the performance of the classification algorithm in grouping user reviews into positive and negative categories. The evaluation results show that the SVM algorithm provides quite good performance with an accuracy value of 88.75%, precision 87.51%, recall 81.25%, and F1-Score 83.71% which can be the basis for improving the quality of service of the SAMBARA application. Because the Sambara application has a negative sentiment of 73.4%, it can be concluded that it still gets a bad rating in terms of use.
DETECTION OF THE SIZE OF PLASTIC MINERAL WATER BOTTLE WASTE USING THE YOLOV5 METHOD Karyanto, Dony Dwi; Indra, Jamaludin; Pratama, Adi Rizky; Rohana, Tatang
JIKO (Jurnal Informatika dan Komputer) Vol 7, No 2 (2024)
Publisher : Universitas Khairun

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.33387/jiko.v7i2.8535

Abstract

The use of plastic bottles for various needs is increasingly massive, especially in consumption needs such as mineral water bottles. The use of plastic bottles is used to reduce costs and be effective in maintaining the quality of mineral water, but its impact can affect natural conditions if not managed properly. Plastic bottle waste if left buried in the ground will have difficulty expanding, which can cause environmental pollution. Therefore, we can take advantage of technology to sort plastic bottle waste using a camera based on the size of plastic bottles. Differentiating the size of bottles aims to distinguish the economic value when exchanged at the waste bank. This technology utilizes object detection and recognition functions such as the YOLO (You Only Look Once) method. YOLO is a detection method that is a development of the CNN (Convolutional Neural Network) algorithm. By using YOLOv5, we can detect objects in the form of plastic bottle waste of various different sizes. To maximize object detection according to size, data annotation is done by creating a Bounding Box on each dataset according to its size. The test was carried out with several different distance configurations including 40cm, 80cm and 1m. Detection results using YOLOv5 produce up to 84% accuracy in real-time.
Klasifikasi Sampah Logam dan Plastik Berbasis Raspberry Pi dengan Metode Convolutional Neural Network Ahmad Afifur Rahman; Ahmad Fauzi; Jamaludin Indra
Scientific Student Journal for Information, Technology and Science Vol. 6 No. 1 (2025): Scientific Student Journal for Information, Technology and Science
Publisher : Scientific Student Journal for Information, Technology and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar

Abstract

Hasil Susenas menunjukkan hanya 1,2 persen rumah tangga melakukan daur ulang sampah. Permasalahan tersebut dapat diatasi dengan peran teknologi, yaitu dengan membuat alat yang dapat mengklasifikasikan jenis sampah. Raspberry Pi mengklasifikasikan sampah bekas minuman kemasan logam, plastik, dan other. Gambar dari Pi Camera diproses pada Raspberry Pi untuk mengetahui jenis sampah logam, plastik, dan other. Pada proses klasifikasi terdapat 2 tahapan, yaitu train model dan predict. Proses klasifikasi menggunakan metode CNN. Train model adalah proses pelatihan model untuk mengenal sampah. Hasil proses training dengan 20 kali epoch diperoleh nilai akurasi training sebesar 0.9866. Dari model yang sudah dilatih, dilakukan proses prediksi untuk melakukan klasifikasi sampah. Dari 20 kali percobaan, diperoleh rata-rata akurasi pengujian model sebesar 81,387%.
Machine Learning Models for Predicting Flood Events Using Weather Data: An Evaluation of Logistic Regression, LightGBM, and XGBoost Maharina, Maharina; Paryono, Tukino; Fauzi, Ahmad; Indra, Jamaludin; Sihabudin, Sihabudin; Harahap, Muhammad Khoiruddin; Rizki, Lutfi Trisandi
Journal of Applied Data Sciences Vol 6, No 1: JANUARY 2025
Publisher : Bright Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47738/jads.v6i1.503

Abstract

This study examines flood prediction in Jakarta, Indonesia, a pressing concern due to its significant implications for public safety and urban management. Machine Learning (ML) presents promising methodologies for accurately forecasting floods by leveraging weather data. However, flood prediction in Jakarta remains challenging due to the city’s highly variable weather patterns, including fluctuations in rainfall, humidity, temperature, and wind characteristics. Existing methods often struggle with these complexities, as they rely on traditional ML models such as K-Nearest Neighbors (KNN), which may not capture certain patterns or provide high accuracy and robustness. Therefore, this study proposes three ML methods—Logistic Regression (LR), LightGBM, and XGBoost—to predict floods accurately. Five performance metrics (i.e., accuracy, area under the curve (AUC), precision, recall, and F1-score) were used to measure and compare the accuracy of the algorithms. The proposed method consists of three main processes. The first process involves data preprocessing and evaluation using 14 different ML models. In the second process, additional feature engineering is applied to improve the quality of the data. Finally, the third process combines the previous steps with oversampling techniques and cross-validation methods. This structured approach aims to enhance the overall performance of the analysis. The experimental results show that Process 3 significantly improves performance compared to Processes 1 and 2. The model predicts floods with an accuracy score of 93.82% for LR, 96.67% for XGBoost, and 96.81% for LightGBM, respectively. Thus, the proposed model offers a solution for operational decision-making in flood risk management, including flood mitigation planning.
KLASIFIKASI PECAHAN UANG KERTAS RUPIAH MENGGUNAKAN TRANSFER LEARNING DENGAN MODEL MOBILENETV2 Rissa Ilmia Agustin; Jamaludin Indra; Sutan Faisal; Ahmad Fauzi; Rija Nur Hijriyya
Jurnal INSTEK (Informatika Sains dan Teknologi) Vol 9 No 2 (2024): OCTOBER
Publisher : Department of Informatics Engineering, Faculty of Science and Technology, Universitas Islam Negeri Alauddin, Makassar, Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24252/instek.v9i2.49123

Abstract

Memanfaatkan mesin sebagai perantara dalam proses pembelian dan penjualan adalah bagaimana teknologi otomasi diterapkan. Mesin berfungsi sebagai penjual dan memiliki kemampuan seperti otak, seperti kecepatan dan keakuratan dalam membaca dan mengidentifikasi nominal uang. Dengan menggunakan teknologi otomatis ini, transaksi jual beli menjadi lebih nyaman. Metode Convolutional Neural Network (CNN) merupakan salah satu komponen dari teknologi Deep Transfer Learning digunakan dalam penelitian ini untuk mengenali uang kertas rupiah. Selain itu, penelitian ini memilih arsitektur model MobileNetV2 yang sesuai dan memodifikasi laju pembelajaran keduanya berdampak pada kinerja model klasifikasi. Untuk menjamin bahwa model memiliki kesempatan yang memadai untuk belajar dari data pelatihan, jumlah epoch yang ideal juga diperhitungkan. Selain itu, hal ini dapat berdampak pada pencapaian kinerja tinggi dengan waktu komputasi yang efisien, pemanfaatan ukuran batch yang optimal juga diselidiki. Evaluasi kinerja model selama pelatihan memberikan hasil sebagai berikut : f1-score 98% recall 98%, presisi 98%, dan akurasi pada set pengujian 97.86%.
SEGMENTASI PELANGGAN MENGGUNAKAN K-MEANS CLUSTERING DI TOKO RETAIL Achmad, Syifa Latifah; Fauzi, Ahmad; Rahmat, Rahmat; Indra, Jamaludin
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 2 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i2.1226

Abstract

Advancements in information technology have transformed various aspects of human life, including the business world. Companies are required to use technology and data effectively to enhance their competitive advantage. One increasingly relevant strategy is Customer Relationship Management (CRM), where customer data is the main focus. Consumer data segmentation is an approach used to group customers based on certain characteristics. In this study, the K-Means Clustering algorithm is applied to consumer data segmentation to improve the marketing strategy of a store. The study begins with the collection of customer data from the Dan+Dan Telukjambe 2 store, followed by Exploratory Data Analysis (EDA) to understand the patterns and characteristics of the data. Preprocessing steps are carried out to ensure the data is ready for use, including removing irrelevant columns, handling missing values, and data transformation. Principal Component Analysis (PCA) is used to reduce data dimensions before applying K-Means Clustering. The Elbow Method and Silhouette Score are used to determine the optimal number of clusters. The study results indicate that the optimal number of clusters is six. Evaluation using the Silhouette Coefficient provides an average coefficient value of 0.66, indicating good clustering quality. Further analysis shows different distributions of age, purchasing power, occupation, and marital status in each cluster, providing deep insights into customer segments. The resulting clusters offer valuable information for developing more effective and targeted marketing strategies
PENGARUH SMOTE TERHADAP PERFORMA ALGORITMA RANDOM FOREST DAN ALGORITMA GRADIENT BOOSTING DALAM MEMPREDIKSI PENYAKIT STROKE Fadmadika, Fadilla; Handayani, Hanny Hikmayanti; Mudzakir, Tohirin Al; Indra, Jamaludin
Jurnal Tekinkom (Teknik Informasi dan Komputer) Vol 7 No 2 (2024)
Publisher : Politeknik Bisnis Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.37600/tekinkom.v7i2.1575

Abstract

Stroke is a disease that can occur suddenly, causing progressive brain damage due to non-traumatic blood flow disruption in the brain. Common symptoms of stroke include numbness in the limbs and impaired communication. Stroke is the second leading cause of death in the world and the third leading cause of mental retardation globally. Predictive machine learning-based technology can help identify early symptoms of stroke for prevention and early intervention. This study aims to compare the performance of the Random Forest and Gradient Boosting algorithms in predicting stroke. By applying the SMOTE method to address class accuracy in the dataset, this study shows that the Random Forest model is superior, with an accuracy of 95.5%, a precision of 78.8%, a recall of 93.1%, and an f1-score of 84.2%. In conclusion, the Random Forest algorithm performs better than Gradient Boosting in predicting stroke, showing significant potential in assisting early detection and medical decision making.
SOSIALISASI PENGGUNAAN DETEKSI KENDARAAN BERMOTOR DENGAN COMPUTER VISION Kiki Ahmad Baihaqi; Ahmad Fauzi; Jamaludin Indra
JURNAL BUANA PENGABDIAN Vol 7 No 1 (2025): JURNAL BUANA PENGABDIAN
Publisher : Lembaga Penelitian dan Pengabdian Kepada Masyarakat, Universitas Buana Perjuangan Karawang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.36805/jurnalbuanapengabdian.v7i1.9949

Abstract

erkembangan teknologi pengolahan cita digital berkembang pesat dari waktu kewaktu, merambah semua sendi-sendi dan bidang kehidupan. Pada Pengabdian masyarakat ini bertujuan untuk mengimplementasikan teknologi computer vision dalam deteksi kendaraan bermotor sebagai solusi untuk memantau dan mengontrol lalu lintas secara efisien. Dengan memanfaatkan metode deteksi objek yang canggih, penelitian ini akan mengembangkan sistem yang mampu mengenali jenis-jenis kendaraan, menghitung jumlah kendaraan yang melintas, serta memonitor kondisi lalu lintas secara real-time. Implementasi teknologi ini diharapkan dapat meningkatkan pengaturan lalu lintas yang lebih efektif dan mengurangi potensi kemacetan di area yang diuji coba. Hasilnya berupa pengetahuan yang diberikan ke peserta dan menunjukan hasil penelitian berupa prototype.
Analisis Prediksi Banjir di Indonesia Menggunakan Algoritma Support Vector Machine dan Random Forest Purnomo, Indarto Aditya; Indra, Jamaludin; Awal, Elsa Elvira; Rohana, Tatang
Journal of Information System Research (JOSH) Vol 6 No 1 (2024): Oktober 2024
Publisher : Forum Kerjasama Pendidikan Tinggi (FKPT)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.47065/josh.v6i1.5958

Abstract

Natural disasters frequently occur in Indonesia, such as floods, landslides, and volcanic eruptions. Geological factors, such as the convergence of four major tectonic plates, make Indonesia vulnerable to natural disasters. Statistical data from the National Disaster Management Agency show an increase in flood occurrences each year, peaking in 2021 with 1,794 incidents. Early anticipation is necessary to minimize the impact of natural disasters, and predictive patterns are becoming new knowledge for preventing and managing these disasters. This study applies the Support Vector Machine and Random Forest algorithms. The results of this study predict that the largest number of floods from 2024 to 2026 in Indonesia will occur in Aceh with 240 floods, North Sumatra with 215 floods, West Java with 210 floods, and Central Java with 160 floods. The best algorithm comparison results were achieved with Random Forest, which had an accuracy of 99.6% and an average RMSE value of 3.834.
Internet of Things-Based Water Dirt Detection System Using Fuzzy Logic Sugeno Algorithm Ardiansyah, Fikri; Indra, Jamaludin; Juwita, Ayu Ratna; Faisal, Sutan
Eduvest - Journal of Universal Studies Vol. 5 No. 3 (2025): Eduvest - Journal of Universal Studies
Publisher : Green Publisher Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.59188/eduvest.v5i3.1778

Abstract

Water turbidity is one of the important indicators of water quality that affects human health and the environment. Many water sources are susceptible to pollution that can increase water turbidity. Traditional methods require manual sampling inefficiently and do not provide real-time data. Internet of Things (IoT) technology allows real-time and remote monitoring of water turbidity, The water turbidity detection system program created will use the Sugeno fuzzy logic method where this method can provide a percentage of water cleanliness based on selected input and apply predetermined rules so that it can produce NTUs output and percentage of water cleanliness. Based on the results of tests that have been carried out in this study, the System has a good level of functionality. the level of accuracy of the results of the system and manual calculations. obtained a level of error difference (error) of 13% meaning that from 100% error rate, the accuracy level value reaches 87% that the program is concluded to be running well. With the website, it can monitor and help make it easier for users to control the level of water turbidity in the environment without having to come to the location. From the tests carried out for the turbidity sensor components, it works well.
Co-Authors AA Sudharmawan, AA Abdul Gapur Achmad, Syifa Latifah Adi Rizky Pratama Adi Rizky Pratama Agung Susilo Yuda Irawan Ahmad Afifur Rahman Ahmad Fauzi Ahmad Fauzi Ahmad Rahman Al Fathir Rizal Januar Alif Kirana Anton Romadoni Junior Apriade Voutama April Hananto Ardiansyah, Fikri Arif Nurman Arip Solehudin Aris Martin Kobar Arum Puspita Lestari, Santi Asep Jamaludin Aviv Yuniar Rahman Awal, Elsa Elvira Ayu Juwita Ayu Ratna Juwita Azis Saputra Azzahra, Wava Lativa Baihaqi, Kiki Ahmad Cici Emilia Sukmawati Dadang Yusup Deden Wahiddin Deny Maulana Dwi Sulistya Kusumaningrum Dwi Vina Wijaya Eko Pramono Fadmadika, Fadilla Faisal, Sutan Fauzi Ahmad Muda Fauzi, Ahmad Firdaus, Thoriq Janati Firmansyah Maulana Fitri Nur Masruriyah, Anis Garno . Garno, Garno Gugy Guztaman Munzi Hanny Hikmayanti Handayani Hanung Pangestu Rahman Hilda Fitriana Dewi Hilda Novita Hilda Yulia Novita Irma Putri Rahayu Juwita, Ayu Ratna Karyanto, Dony Dwi Khoirull Munazzal Kusumaningrum, Dwi Sulistya Lestari, Santi Arum Puspita M Andrian Agustyan Maharina, Maharina Maliah Andriyani Mudzakir, Tohirin Al Muhammad Cesar Afriansyah Arief Muhammad Deden Miftah Fauzi Muhammad Imam Naufal Muhammad Khoiruddin Harahap Muhammad Raja Nurhusen Muhammad Romadhon Nazori AZ Novalia, Elfina Nugraha, Najmi Cahaya Nurdin, Cherry Januar Nurlaelasari, Euis Nursyawalni, Reva Paryono, Tukino Pratama, Adi Rizky Purnama, Ariya Purnomo, Indarto Aditya Rahmat Hidayat Rahmat Rahmat Rahmat Rahmat Rija Nur Hijriyya Rissa Ilmia Agustin Rizki, Lutfi Trisandi Rizky Rifaldi Robinson Nababan Rohana, Tatang Romlah Saefulloh, Nandang Sandi Susanto Santi Lestari Sihabudin Sihabudin, Sihabudin Siregar, Amril Mutoi Siti Robiah Suparno Sutan Faisal Syahrul Azis Tatang Rohana Tia Astiyah Hasan Tohirin Al Mudzakir Tohirin Mudzakir Toif Muhayat Tri Vicika, Vikha Ulfa Amelia Wahiddin, Deden Wildan Amin Wiharja Yana Cahyana Yogi Firman Alfiansyah