Permata, Rizka
Unknown Affiliation

Published : 4 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 4 Documents
Search

IMPLEMENTASI PATH SMOOTHING MENGGUNAKAN ALGORITMA GRADIENT DESCENT MENGGUNAKAN SIMULASI V-REP Jayadi, Akhmad; Handoko, Dwi; Permata, Rizka; Arpan, Atika; Meilantika, Dian
HOAQ (High Education of Organization Archive Quality) : Jurnal Teknologi Informasi Vol. 15 No. 2 (2024): Jurnal HOAQ - Teknologi Informasi
Publisher : STIKOM Uyelindo Kupang

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52972/hoaq.vol15no2.p107-115

Abstract

Perkembangan teknologi robot mobile telah mengubah berbagai sektor industri, dan salah satu tantangan utama dalam pengoperasian robot mobile adalah perencanaan jalur (path planning). Jalur yang direncanakan sering kali tidak mempertimbangkan gerakan robot, terutama saat menghadapi belokan tajam yang dapat menyebabkan inefisiensi gerak robot, untuk mengatasi hal ini, teknik path smoothing digunakan untuk mereduksi ketajaman belokan, memungkinkan robot bergerak lebih lancar dan efisien. Salah satu algoritma yang digunakan dalam path smoothing adalah Gradient Descent, yang secara iteratif memperbaiki jalur dengan meminimalkan jarak antara titik-titik. Simulasi menggunakan platform V-REP sangat berguna untuk menguji efektivitas algoritma, dengan harapan dapat meningkatkan kinerja navigasi robot dan berkontribusi pada pengembangan robot mobile yang lebih efisien dan aman. Setelah jalur optimal ditentukan, langkah selanjutnya adalah memperlancar lintasan menggunakan path smoothing. Proses ini mengoptimalkan koordinat yang dihaluskan  untuk mengurangi jarak antara jalur asli  dan jalur yang dihaluskan dengan persamaan  Pembaruan pertama memindahkan y untuk meminimalkan jarak antara koordinat asli dan yang dihaluskan, sedangkan pembaruan kedua mengurangi penyimpangan antara koordinat yang berdekatan, dengan parameter beta yang mengontrol pembaruan tersebut. Hasilnya, jalur menjadi lebih mulus dan efisien untuk dilalui robot. Hasil dari penelitian yang telah dilakukan menunjukan algoritma yang diterapkan telah mampu membuat jalur yang lebih halus dari sebelum diterapkannya algoritma ini.   The development of mobile robot technology has transformed various industrial sectors, with one of the main challenges in mobile robot operation being path planning. Planned paths often do not take into account the robot's movement, especially when facing sharp turns that can cause inefficiencies in the robot's motion. To address this, path smoothing techniques are used to reduce the sharpness of turns, allowing the robot to move more smoothly and efficiently. One algorithm used in path smoothing is Gradient Descent, which iteratively refines the path by minimizing the distance between points. Simulations using the V-REP platform are very useful for testing the effectiveness of the algorithm, with the aim of improving robot navigation performance and contributing to the development of more efficient and safer mobile robots. After the optimal path is determined, the next step is to smooth the trajectory using path smoothing. This process optimizes the smoothed coordinates  to reduce the distance between the original path  and the smoothed path using the equation . The first update moves y to minimize the distance between the original and smoothed coordinates, while the second update reduces deviations between adjacent coordinates, with the beta parameter controlling the update. As a result, the path becomes smoother and more efficient for the robot to follow. The results of the research indicate that the applied algorithm has successfully created a smoother path compared to the original path before the algorithm was applied.
Evaluasi Kinerja Algoritma Naïve Sylvia, Sylvia; Purnomo, Hendri; Arifin, Oki; Arpan, Atika; Permata, Rizka; Handoko, Dwi; Fitriyah, Fitriyah
Jusikom : Jurnal Sistem Komputer Musirawas Vol 9 No 2 (2024): Jusikom : Jurnal Sistem Komputer Musirawas DESEMBER
Publisher : LPPM UNIVERSITAS BINA INSAN

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.32767/jusikom.v9i2.2447

Abstract

Social media sentiment analysis has become increasingly important with the rise of platforms like Twitter and Facebook as sources of public opinion. This study evaluates the performance of three machine learning algorithms—Naïve Bayes, k-Nearest Neighbors (KNN), and Support Vector Machines (SVM)—in classifying sentiment from social media data. Using a dataset in Indonesian, we apply cross-validation techniques to measure accuracy, precision, recall, F1-score, and computation time for each algorithm. The results show that SVM achieves the highest accuracy and F1-score, while Naïve Bayes offers better computational speed. KNN demonstrates the lowest performance in terms of accuracy and efficiency. These findings provide guidance for practitioners and researchers in selecting the appropriate algorithm for sentiment analysis based on their specific needs.
IMPLEMENTASI LOOKER STUDIO UNTUK VISUALISASI DATA PUBLIKASI DOSEN DI JURUSAN TEKNOLOGI INFORMASI POLITEKNIK NEGERI LAMPUNG permata, rizka
Journal of Software Engineering and Technology. Vol 5, No 2 (2025): SEAT: Journal Of Software Engineering and Technology
Publisher : Institut Teknologi dan Bisnis Diniyyah Lampung

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.69769/seat.v5i2.255

Abstract

Publikasi ilmiah dosen merupakan indikator utama dalam menilai kinerja akademik dan kontribusi institusi pendidikan tinggi terhadap pengembangan ilmu pengetahuan dan teknologi. Namun, penyajian data publikasi dosen yang tersebar dan kurang terintegrasi sering menyulitkan proses pemantauan, analisis, serta pelaporan. Penelitian ini bertujuan untuk mengimplementasikan Looker Studio sebagai platform visualisasi data publikasi dosen di Jurusan Teknologi Informasi Politeknik Negeri Lampung. Fokus visualisasi meliputi jumlah publikasi, jumlah sitasi, dan bidang keahlian dosen. Data dikumpulkan dari Google Scholar dan sumber resmi lainnya, kemudian diolah melalui Google Sheets dan divisualisasikan dalam bentuk dashboard interaktif menggunakan Looker Studio. Hasil penelitian menunjukkan bahwa implementasi dashboard ini mempermudah jurusan dalam memonitor kinerja publikasi dosen, memetakan kompetensi keilmuan, dan mendukung pengambilan keputusan berbasis data. Selain itu, visualisasi ini juga mempercepat proses pelaporan untuk keperluan akreditasi dan evaluasi institusional. Dengan demikian, Looker Studio terbukti menjadi alat yang efektif dalam mendukung tata kelola publikasi dosen secara digital dan transparan.
Enhancing Chronic Kidney Disease Classification Using Decision Tree And Bootstrap Aggregating: Uci Dataset Study With Improved Accuracy And Auc-Roc Zuriati, Zuriati; Meilantika, Dian; Arpan, Atika; Permata, Rizka; Sriyanto, Sriyanto; Mas'ud, Mohd. Zaki
Jurnal Teknik Informatika (Jutif) Vol. 6 No. 5 (2025): JUTIF Volume 6, Number 5, Oktober 2025
Publisher : Informatika, Universitas Jenderal Soedirman

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.52436/1.jutif.2025.6.5.5271

Abstract

Chronic Kidney Disease (CKD) is a progressive medical disorder that requires timely and precise identification to avoid permanent impairment of kidney function. However, Decision Tree models, although widely used in clinical applications due to their transparency, ease of implementation, and ability to handle both categorical and numerical data, are prone to overfitting and instability when applied to small or imbalanced datasets. The purpose of this study is to optimize CKD classification by integrating Bootstrap Aggregating (Bagging) with Decision Tree to enhance accuracy and robustness. The methodology involves testing two model variants a standalone Decision Tree and a Bagging-supported Decision Tree using 10-fold cross-validation and evaluating performance with accuracy, precision, recall, F1-score, and the area under the ROC curve (AUC-ROC). Findings reveal that Bagging enhances model accuracy from 0.980 to 0.987, raises precision from 0.976 to 1.000, and improves recall from 0.954 to 0.954, and increases F1-score from 0.965 to 0.976. These results demonstrate that Bagging significantly improves the reliability and generalizability of Decision Tree classifiers, making them more effective for CKD prediction.