Claim Missing Document
Check
Articles

Found 15 Documents
Search

Algoritma K-Nearest Neighbor Pada Analisa Sentimen Review Produk Router Rizqi Agung Permana; Sucitra Sahara
Jurnal Sistem Informasi dan Sistem Komputer Vol 8 No 2 (2023): Vol 8 No 2 - 2023
Publisher : STIMIK Bina Bangsa Kendari

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.51717/simkom.v8i2.129

Abstract

Review komentar yang telah dikumpulkan datanya dan akan diproses yaitu berupa text positif dan text negatif yang dilakukan pada pengklasifikasian data menggunakan k-Nearest Neighbors (k-NN) method. k-NN method merupakan salah satu algoritma yang cukup tepat untuk pengenalan pola data pada klasifikasi text. Pertumbuhan penggunaan router yang lekat berkaitan dengan kegiatan harian bagi pengguna laptop, smartphone dan tablet agar jaringan internet dapat dijalankan secara optimal, karena fungsi router yaitu dapat mengelola lalu lintas antar jaringan dengan meneruskan paket data ke alamat IP yang dituju. Maka dari itu peneliti mencoba memberikan kemudahan dalam pemilihan perangkat router yang tepat bagi pengguna mulai dari kualitas dan performa yang tinggi hingga kualitas yang sering dipertanyakan, sehingga peneliti mengadakan screening perangkat untuk opini atau komentar mengenai produk router oleh pengguna yang sudah menggunakan perangkat tersebut dan dituliskan ke dalam media online atau publik komentar. Dan dari pengolahan data sampel komentar yang telah dilakukan yaitu dengan mencoba beberapa metode algoritma seperti Naive Bayes, Neural Network, k-NN, Decision Tree dan Machine Support Vector Machine dengan berbagai tahap pengujian, barulah akan mendapatkan nilai akurasi dan AUC dari masing-masing algoritma tersebut sehingga didapatkan hasil pengujian tertinggi yaitu dengan menggunakan algoritma k-NN.
Assessing the Role of E-Govqual in Improving Public Satisfaction with the MyPertamina Application in Setiabudi District: Mengkaji Peran E-Govqual dalam Meningkatkan Kepuasan Masyarakat terhadap Aplikasi MyPertamina di Kecamatan Setiabudi Yulian Surya Saputra; Sucitra Sahara; Rizqi Agung Permana
NUANSA INFORMATIKA Vol. 19 No. 2 (2025): Nuansa Informatika 19.2 Juli 2025
Publisher : FKOM UNIKU

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25134/ilkom.v19i2.379

Abstract

This research aims to analyze the influence of Customer Satisfaction on the quality of e-government services (E-Govqual) on the use of the My Pertamina application in Setiabudi District. The research method used was quantitative with a survey approach by distributing questionnaires to 150 respondents. The data collected was analyzed using validity tests, reliability tests, and hypothesis testing through linear regression analysis. The research results show that there is no significant influence between Customer Satisfaction and E-Govqual. This is proven by a correlation value of 0.160, which indicates a very weak relationship, as well as a coefficient of determination (R²) value of 2.56%, which indicates that variations in E-Govqual are only slightly influenced by Customer Satisfaction. The results of the hypothesis test show a significance value of 0.050 > 0.05 and Fcount (3.891) < Ftable (3.905), so that the null hypothesis (H₀) is accepted and the alternative hypothesis (H₁) is rejected. Satisfaction (X) on E-Govqual (Y) is 0.050 > 0.05, and the calculated F-value (F-count) is less than the F-table value, namely 3.891 < 3.905. These findings suggest that other factors beyond Customer Satisfaction may have a greater influence on e-government service quality. Based on the results, it is recommended that the development of the My Pertamina application be more focused on improving system quality, ease of use, and other technical aspects to improve overall service quality.
User Experience Questionnaire Method In Evaluation And Improved Platform Starup With Kebon Kelapa Region Users Saputra, Yogi; Sahara , Sucitra; Permana, Rizqi Agung
JEECS (Journal of Electrical Engineering and Computer Sciences) Vol. 10 No. 2 (2025): JEECS (Journal of Electrical Engineering and Computer Sciences)
Publisher : Fakultas Teknik Universitas Bhayangkara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.54732/jeecs.v10i2.2

Abstract

The rapid growth of e-commerce in Indonesia has led to the widespread use of platforms like Shopee among the public. However, it remains unclear how users in specific areas, such as the Kebon Kelapa Subdistrict, perceive their experiences while using the platform. This study aims to evaluate the user experience of Shopee in that area to provide recommendations for improving service quality. This research utilized the User Experience Questionnaire (UEQ), which assesses six aspects: Attractiveness, Perspicuity, Efficiency, Dependability, Stimulation, and Novelty. Data were collected from active Shopee users in Kebon Kelapa and analyzed quantitatively to determine perception scores for each aspect. The results indicate that, overall, users reported a positive experience, particularly in the areas of Attractiveness, Efficiency, Perspicuity, Dependability, and Stimulation. However, the Novelty aspect received a neutral score, suggesting that Shopee should enhance its innovation in features and interface design. These findings offer valuable insights for Shopee’s development, aiming to create a more inventive, innovative, and engaging platform for its users.
Inovasi Artificial Intelligence dalam Mengidentifikasi Pneumonia Anak untuk Meningkatkan Efisiensi Diagnostik Menggunakan Model CNN Kresna Ramanda; Monikka Nur Winnarto; Sucitra Sahara
Jurnal Infortech Vol. 7 No. 2 (2025): Desember 2025
Publisher : LPPM Universitas Bina Sarana Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31294/infortech.v7i2.11383

Abstract

Pneumonia adalah salah satu jenis infeksi yang paling sering ditemui dan berisiko tinggi di seluruh dunia, yang mengakibatkan angka penyakit dan kematian yang tinggi, khususnya di kalangan populasi yang rentan seperti anak-anak. Dengan demikian, penelitian ini bertujuan untuk menciptakan sistem pintar yang mampu mengidentifikasi pneumonia secara otomatis melalui gambar thorax dengan memanfaatkan arsitektur Convolutional Neural Networks (CNN). Dalam penelitian ini, beberapa arsitektur CNN, yaitu MobileNet V2, ResNet, dan EfficientNet diuji untuk mencari model terbaik, dengan mempertimbangkan risiko overfitting dan penggunaan optimizer yang tepat. Metode yang digunakan mencakup pengumpulan data, preprocessing, pembagian dataset menjadi data train, test dan validasi, serta penerapan teknik transfer learning. Evaluasi dilakukan berdasarkan parameter kinerja seperti akurasi, sensitivitas dan presisi untuk menilai performa model. Hasil penelitian menunjukkan bahwa arsitektur MobileNet V2 memberikan kinerja terbaik dengan akurasi mencapai 93%. Model ini kemudian diimplementasikan dalam sistem cerdas yang dapat mempercepat dan mempermudah proses diagnosis pneumonia sehingga memberikan manfaat signifikan bagi sektor kesehatan dan masyarakat luas. Penelitian ini juga menekankan pentingnya teknik optimasi yang tepat dalam memastikan model dapat bekerja secara optimal di aplikasi dunia nyata.
Optimization of Real-Time Object Detection in Viola-Jones Method with Enhanced AdaBoost Sucitra Sahara; Rizqi Agung Permana; Mely Mailasari
ZERO: Jurnal Sains, Matematika dan Terapan Vol 10, No 1 (2026): Zero: Jurnal Sains Matematika dan Terapan
Publisher : UIN Sumatera Utara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.30829/zero.v10i1.27876

Abstract

Face recognition is a widely used biometric technology in security systems, automated attendance, and surveillance applications. This study proposes an enhanced real-time face detection method by integrating a modified AdaBoost-based feature selection strategy into the Viola–Jones framework. The applied mathematical contribution of this study lies in formulating the optimization process as an empirical risk minimization model with adaptive boosting weight updates to reduce face recognition error. The proposed approach optimizes the weighting of weak classifiers by prioritizing Haar-like features with minimal weighted classification error at each boosting iteration, thereby improving discriminative capability. Experiments were conducted on a camera-based dataset consisting of face and non-face samples under varying illumination and pose conditions. Prior to optimization, the system achieved a precision of 70.04% and a recall of 70.05%. After applying the proposed enhancement, precision increased to 81.04% and recall to 90.02%. These results demonstrate that the modified AdaBoost integration significantly improves detection accuracy while remaining suitable for real-time face detection applications.