Claim Missing Document
Check
Articles

Found 10 Documents
Search

Monitoring Stasiun Pengisian Bahan Bakar Umum Berbasis Augmented-Reality Angkoso, Cucun Very; Wahedah, Wahedah; Joni, Koko
Rekayasa Vol 9, No 2: Oktober 2016
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (772.106 KB) | DOI: 10.21107/rekayasa.v9i2.3346

Abstract

Virtual Reality Museum Sunan Drajat Lamongan Berbasis Rulebased System untuk Pembelajaran Sejarah Ari Kusumaningsih; Cucun Very Angkoso; Novian Anggraeny
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 5 No 4: Agustus 2018
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (668.135 KB) | DOI: 10.25126/jtiik.201854818

Abstract

Perkembangan peradaban suatu bangsa dapat dilihat melalui museum yang dimilikinya. Dalam hal upaya untuk mencerdaskan masyarakat, museum diwajibkan selalu kreatif dalam menarik minat pengunjung, sehingga tujuan pendirian museum tetap terlaksana. Antusias masyarakat dalam menjelajahi museum saat ini semakin menurun, sehingga museum perlu melakukan inovasi agar tetap mampu menarik minat masyarakat untuk berkunjung. Pada penelitian ini berhasil dibuat aplikasi Virtual Reality Museum Sunan Drajat berbasis Android dalam memudahkan seseorang untuk belajar sejarah yang mampu membawa pengguna ke dalam dunia maya dengan merasakan sensasi nyata mengunjungi museum, dengan menerapkan metode Rule-Based System sebagai desain skenario sistem dalam penjelajahan museum. Diharapkan setelah menggunakan aplikasi ini, museum dapat menarik perhatian masyarakat sehingga kembali tertarik untuk mempelajari sejarah bangsanya. Dari hasil pengujian aplikasi diketahui bahwa 95.8% responden sangat setuju bahwa aplikasi ini dapat dijadikan sebagai pembelajaran sejarah. Berdasarkan hasil uji keefektifan aplikasi rata-rata nilai Report Score yang diperoleh pada menu evaluation yaitu 92% yang berarti aplikasi Virtual Reality Museum Sunan Drajat sangat efektif digunakan sebagai pembelajaran sejarah. Abstract Historical journey of the nation's civilization can be seen through their museum. In terms of efforts to educate the public, the museum is always required to be creative in attracting visitors so that the purpose of establishment of the museum is still carried out. The enthusiasm of people in exploring the museum is now declining so that the museum need to innovate in order to remain able to attract the public interest to visit. In this research, the application of Virtual Reality Museum Sunan Drajat based on Android in facilitating someone to learn history that can bring users into the virtual world by feeling the real sensation of visiting the museum, by applying Rule-Based System method as a system scenario design in museum exploration. It is hoped that after using this application, it can attract the public's attention so that it is interested to learn about the history of the nation. From the results of application testing known that 95.8% of respondents strongly agree that this application can be used as a learning history. Based on the results of test effectiveness of the average application score Report Score obtained on the evaluation menu is 92% which means the application Virtual Reality Museum Sunan Drajat very effectively used as a learning history.
Implementasi Metode Euclidean Distance untuk Rekomendasi Ukuran Pakaian pada Aplikasi Ruang Ganti Virtual Rezky Rizaldi; Arik Kurniawati; Cucun Very Angkoso
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 5 No 2: April 2018
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (413.146 KB) | DOI: 10.25126/jtiik.201852592

Abstract

Perkembangan jual beli garmen secara online, dihadapkan pada kenyataan adanya 70% pengembalian produk oleh pembeli, akibat ketidaksesuaian antara harapan dan kenyataan model serta ukuran garmen. Kehadiran virtual fitting room secara online, diharapkan mampu mengurangi adanya pengembalian produk, memberikan pengaruh positif terhadap keistimewaan suatu produk, keinginan untuk membeli dan kepastian membeli secara online. Virtual Fitting Room ini bisa diimplementasikan pada toko online ataupun toko baju seperti biasa. Tahapan penelitian meliputi : penerapan teknologi kinect untuk mendapatkan data skeleton dari calon pembeli yang digunakan sebagai dasar untuk memberikan rekomendasi ukuran pakaian, selanjutnya perhitungan euclidean distance digunakan untuk menghitung ukuran punggung calon pembeli dan terakhir penerapan teknologi augmented reality untuk menampilkan pakaian virtual 3 dimensi yang melekat tepat di badan calon pembeli. Sistem rekomendasi ini mampu menampilkan calon pembeli dengan menggunakan baju virtual 3 dimensi yang sesuai dengan ukuran rekomendasi dari sistem (S,M,L, atau XL). Sistem ini juga memberikan fitur bagi calon pembeli untuk mencoba model pakaian lainnya. Sistem dapat memperlihatkan baju virtual 3 dimensi yang tetap melekat pada badan calon pembeli, ketika melakukan rotasi ke kanan 900, ke kiri 900, balik kanan 1800 dan balik kiri 1800. Hasil uji coba sistem rekomendasi ukuran pakaian ini akan berjalan secara optimal jika pengaturan ketinggian kinect sebesar 55 cm dari tanah. Untuk ketinggian kinect 55cm, 65cm dan 75 cm dari tanah, sistem ini mampu menyajikan kesesuaian rekomendasi ukuran dibandingkan dengan ukuran asli dari calon pembeli sebesar 70%. Kata kunci: kinect, augmented reality, euclidean distance, virtual fitting room  AbstractThe development of online garment sale, faced with the fact that there is 70% return of product by the buyer, due to a mismatch between expectation and reality of model and garment size. The presence of virtual fitting room in the online store is expected to reduce the return of products, give a positive influence on the privilege of a product, the desire to buy and certainty to buy online. Virtual Fitting Room can be implemented in the online store or clothing store as usual. The research stages include the application of Kinect technology to obtain skeleton data from prospective buyers used as a basis for providing system recommendations, then euclidean distance calculation is used to calculate the size back potential buyers, and lastly application of augmented reality technology to display the right three-dimensional virtual clothing in potential buyer body. This recommendation system can present potential buyers by using 3-dimensional virtual shirts attached to their bodies by the recommended size of the system (S, M, L, or XL). This system also provides features for potential buyers to try other clothing models. The system can show a 3-dimensional virtual shirt that remains attached to the body of potential buyers, while rotating right 900, left 900, right turn 1800 and left turn 1800. The test results of this clothing size recommendation system will run optimally if the Kinect height setting of 55 cm from the ground. For the Kinect height of 55cm, 65cm and 75cm from the ground, the system can present the recommended size with the original size of the potential buyer of 70%. Keywords: kinect, augmented reality, euclidean distance, virtual fitting room
Automatic Segmentation on Glioblastoma Brain Tumor Magnetic Resonance Imaging Using Modified U-Net Hapsari Peni Agustin Tjahyaningtijas; Andi Kurniawan Nugroho; Cucun Very Angkoso; I Ketut Edy Purnama; Mauridhi Hery Purnomo
EMITTER International Journal of Engineering Technology Vol 8 No 1 (2020)
Publisher : Politeknik Elektronika Negeri Surabaya (PENS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.24003/emitter.v8i1.505

Abstract

Glioblastoma is listed as a malignant brain tumor. Due to its heterogeneous composition in one area of the tumor, the area of tumor is difficult to segment from healthy tissue. On the other side, the segmentation of brain tumor MRI imaging is also erroneous and takes time because of the large MRI image data. An automated segmentation approach based on fully convolutional architecture was developed to overcome the problem. One of fully convolutional network that used is U-Net framework. U-Net architecture is evaluated base on the number of epochs and drop-out values to achieve the most suitable architecture for the automatic segmentation of glioblastoma brain tumors. Through experimental findings, the most fitting architectural model is mU-Net architecture with an epoch number of 90 and a drop out layer value of 0.5. The results of the segmentation performance are shown by a dice value of 0.909 which is greater than that of the previous research.
Performance Analysis of Color Cascading Framework on Two Different Classifiers in Malaria Detection Cucun Very Angkoso; Yonathan Ferry Hendrawan; Ari Kusumaningsih; Rima Tri Wahyuningrum
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 5: EECSI 2018
Publisher : IAES Indonesia Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (327.072 KB) | DOI: 10.11591/eecsi.v5.1605

Abstract

Malaria, as a dangerous disease globally, can be reduced its number of victims by finding a method of infection detection that is fast and reliable. Computer-based detection methods make it easier to identify the presence of plasmodium in blood smear images. This kind of methods is suitable for use in locations far from the availability of health experts. This study explores the use of two methods of machine learning on Cascading Color Framework, ie Backpropagation Neural Network and Support Vector Machine. Both methods were used as classifier in detecting malaria infection. From the experimental results it was found that Cascading Color Framework improved the classifier performance for both in Support Vector Machine and Backpropagation Neural Network.
Virtual Reality for Introducing Informatics Laboratory on University of Trunojoyo Madura muzamil muzamil; Cucun Very Angkoso; ari kusumaningsih
International Journal of Science, Engineering, and Information Technology Vol 1, No 1 (2016): IJSEIT Volume. 01 Issue. 01 DECEMBER 2016
Publisher : Universitas Trunojoyo Madura

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (215.452 KB) | DOI: 10.21107/ijseit.v1i1.6476

Abstract

Nowadays, the development of increasingly advanced technology, one of the rapidly evolving technology at this time that smartphones based on Android. However, the development of technology is not comparable with the needs of students, for example in the introduction of the laboratory environment. During the introduction of the lab environment is still done manually without involving a technology to introduce a laboratory environment and it is less effective and efficient because need effort and a long time. For of these problem is make a Virtual Reality(VR) based android of 3D architectural visualization with a study area of information Technology Laboratory (TIF) UTM. From this application, students can explore and get to know Laboratories TIF simply using a smartphone based on Android, so students do not need to come lively. From the test result data, laboratory TIF VR applications can run well in 6 test device but the device Andromax R1 gyroscope is not functioning properly. From the results of testing applications using a questionnaire obtained, the average value of the respondents based user verification is 89% good, 11% Less good, and 0% unfavorable. And the average value of the entire question by 95%.
IN-APP PURCHASE SYSTEM BASED ON AUGMENTED REALITY TECHNOLOGY:A CASE STUDY IN HEROES OF SURABAYA MOBILE GAMES Ari Kusumaningsih; Cucun Very Angkoso; Ubaidillah Ubaidillah
Journal of International Conference Proceedings (JICP) Vol 1, No 1 (2018): Proceedings of the 1st International Conference of Project Management (ICPM) Mal
Publisher : AIBPM Publisher

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (13.91 KB) | DOI: 10.32535/jicp.v1i1.222

Abstract

The way on selling software applications today is much changed. Among all of the changes, it is the IAP (In-App Purchase) method for freemium software where users can download and use the application for free but there is a premium feature to be paid. This payment method is believed to be more effective to attract consumers than the payment / purchase made at the beginning by the consumer.When the app developer uses the app's sales option that is an “in-app purchase” then the potential profit or revenuewill be greater because the app-developer may get the revenue many times from one user. Unlike paid-apps where app developers typically only get one-timerevenue from one user for each app they have sold.Some problems with in-app purchase system in mobile games is when choosing the type of payment media for buying items as well as when making a payment when an interruption occurs in the mobile game server that played.Wepropose a solution to this problem by applying Augmented Reality technology to “in-app purchase system” so the system no longer requires internet connection to the game server so users easier for making purchases.This application is made for android smartphone, by combining the in-app purchase system of mobile games heroes of Surabaya with augmented reality using game engine unity and library ARSDK Fuvoria. With augmented reality the app can recognize markers and interact with 3D objects from markers, as well as purchase items from scanned markers. This application can be an alternative solution for purchasing premium items that must be paid using digital money that not everyone understands and have payment media, so smartphone users who want to buy premium items in mobile games only need to buy marker card to make purchases of items to be purchased in mobile games heroes of Surabaya. From the experimental result, the app is get 96% user satisfaction from an attractive sales innovation, but the speed-performance gets only 35% of the user satisfaction level.The light and distance of markers are the key factor of successful rate in maker detection. Keywords: Augmented Reality, In-App Purchase, Marker, Mobile Game, Payment Method
Optimasi Klasifikasi Sentimen Menggunakan Random Forest dengan Preprocessing K-Means Clustering dan SMOTE Angkoso, Cucun Very; Thrisna, Mochamad Adrian Nuradha; Satoto, Budi Dwi; Kusumaningsih, Ari
JEPIN (Jurnal Edukasi dan Penelitian Informatika) Vol 10, No 3 (2024): Volume 10 No 3
Publisher : Program Studi Informatika

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26418/jp.v10i3.84514

Abstract

Salah satu topik penelitian terkini dalam bidang pengolahan informasi adalah opinion mining atau analisis sentimen dimana didalamnya terdapat pekerjaan utama yaitu klasifikasi sentimen pada data teks. Penelitian ini bertujuan mengoptimalkan proses klasifikasi sentimen dengan mengatasi tantangan-tantangan umum seperti ketidakseimbangan kelas dan kualitas data input dengan mengusulkan metode baru untuk meningkatkan kinerja mesin klasifikasi yang digunakan. Data yang digunakan untuk mengevaluasi metode yang diusulkan adalah satu topik yang diperbincangkan di media sosial Twitter yaitu terkait kebijakan peralihan mobil listrik di Indonesia. Jumlah data yang dikumpulkan adalah tweet berbahasa Indonesia dimulai pada tanggal 01 Januari 2019 hingga 27 Februari 2023 dengan jumlah data yang diperoleh adalah 7.745 data tweet. Penelitian ini mengikuti model penelitian data science CRISP-DM, dimulai dengan observasi topik, pengumpulan data, pelabelan, dan preprocessing data. Data yang telah diberi label dibagi menjadi data train dan data test, kemudian melalui tahap ekstraksi fitur menggunakan TF-IDF (Term Frequency-Inverse Document Frequency). Model Random Forest diterapkan untuk klasifikasi sentimen, dan teknik SMOTE (Synthetic Minority Over-sampling Technique) digunakan untuk menangani ketidakseimbangan kelas. Hasil eksperimen menunjukkan bahwa kombinasi preprocessing K-Means Clustering dan SMOTE secara signifikan meningkatkan kinerja model klasifikasi sentimen. Model Random Forest menghasilkan akurasi sebesar 98,47% dengan 5-fold cross validation, dan setelah penambahan teknik SMOTE, akurasi meningkat menjadi 99,55%.
Analisis Sentimen Pada Sosial Media Twitter Terhadap Kualitas Jaringan Internet Telkomsel Menggunakan Ensemble K-Nearest Neighbour -Support Vector Machine Angkoso, Cucun Very; Fatah, Doni Abdul; Fachrudin, Muchammad Farchan
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 11 No 6: Desember 2024
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.1168713

Abstract

Di Indonesia, PT Telekomunikasi Seluler, yang mengoperasikan layanan jaringan internet seluler melalui Telkomsel, merupakan salah satu perusahaan penyedia layanan internet. Opini pengguna Telkomsel mengenai kualitas layanan jaringan internet sering dijadikan representasi kepuasan pengguna, yang menjadi indikator penilaian dan evaluasi bagi perusahaan. Analisis sentimen, dengan melakukan klasifikasi opini pengguna ke dalam kelas positif, negatif, atau netral, dapat digunakan sebagai metode untuk mengukur kepuasan pengguna terhadap layanan tersebut. Dalam penelitian analisis sentimen ini menggunakan model algoritma machine learning yaitu K-Nearest Neighbour, Support Vector Machine, dan Ensemble KNN-SVM yang berbasis majority vote dan berbasis average. Dalam penelitian ini data yang diambil berasal dari Twitter dengan rentang waktu 7 Juli 2020 hingga 31 Desember 2022 dengan total jumlah data sebesar 30004 data dan diambil sampel yang diberi label sebesar 3900 data. Dari penggunaan data sampel tersebut, nilai akurasi pada model KNN pada K=15 memberikan hasil akurasi sebesar 83.21%, model SVM pada C=100 memberikan hasil akurasi sebesar 84.33%, model Ensemble KNN-SVM Majority Vote atau Hard Vote memberikan hasil akurasi sebesar 83.26%, dan model Ensemble KNN-SVM Average atau Soft Vote memberikan hasil akurasi sebesar 84.79%. Selain itu keempat model tersebut melakukan prediksi sentimen terhadap data yang belum dilabel dan keempat model tersebut memprediksi mayoritas sentimennya yaitu negatif. Sehingga dapat disimpulkan bahwa opini masyarakat terhadap kualitas layanan jaringan internet telkomsel adalah negatif. Secara keseluruhan, penggunaan model klasifikasi KNN, SVM, dan Ensemble KNN-SVM dalam melakukan analisis sentimen dapat dikatakan baik dan mampu untuk memprediksi sentimen pada sebuah data yang belum berlabel dan yang berlabel.   Abstract In Indonesia, PT Telekomunikasi Cellular, which operates cellular internet network services through Telkomsel, is one of the internet service provider companies. Telkomsel users' opinions regarding the quality of internet network services are often used as a representation of user satisfaction, which is an indicator of assessment and evaluation for the company. Sentiment analysis, by classifying user opinions into positive, negative, or neutral classes, can be used as a method to measure user satisfaction with the service. This sentiment analysis research uses machine learning algorithm models, namely K-Nearest Neighbor, Support Vector Machine, and KNN-SVM Ensemble which are majority vote-based and average-based. In this study, the data taken came from Twitter with a period of July 7, 2020, to December 31, 2022, with a total amount of data of 30004 data and a labeled sample of 3900 data was taken. From the use of the sample data, the accuracy value of the KNN model at K = 15 gave an accuracy result of 83.21%, the SVM model at C = 100 gave an accuracy result of 84.33%, the KNN-SVM Majority Vote or Hard Vote Ensemble model gave an accuracy result of 83.26%, and the KNN-SVM Average or Soft Vote Ensemble model gave an accuracy result of 84.79%. In addition, the four models predict sentiment against unlabeled data and all four models predict the majority of sentiment is negative. So it can be concluded that public opinion on the quality of Telkomsel's internet network services is negative. Overall, the use of KNN, SVM, and Ensemble KNN-SVM classification models in conducting sentiment analysis can be said to be good and able to predict sentiment on unlabeled and labeled data.  
Optimasi Algoritma Support Vector Machine Berbasis Kernel Radial Basis Function (RBF) Menggunakan Metode Particle Swarm Optimization Untuk Analisis Sentimen Angkoso, Cucun Very; Asror, Khozainul; Kusumaningsih, Ari; Nugroho, Andi Kurniawan
Jurnal Teknologi Informasi dan Ilmu Komputer Vol 12 No 3: Juni 2025
Publisher : Fakultas Ilmu Komputer, Universitas Brawijaya

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.25126/jtiik.2025129317

Abstract

Di era digital, aplikasi Financial Technology (Fintech) telah menjadi bagian penting dalam kehidupan sehari-hari masyarakat. Kemudahan dan efisiensi yang ditawarkan oleh aplikasi Fintech menarik jutaan pengguna, yang aktif memberikan umpan balik dan ulasan di platform seperti Google Play Store. Ulasan ini menjadi sumber informasi berharga bagi pengembang untuk memahami persepsi pengguna, mengidentifikasi masalah, dan meningkatkan kualitas layanan. Penelitian ini bertujuan mengevaluasi efektivitas algoritma Particle Swarm Optimization (PSO) dalam meningkatkan akurasi analisis sentimen pada algoritma Support Vector Machine (SVM) dengan kernel Radial Basis Function (RBF). Data ulasan dikumpulkan melalui web scraping dari komentar di Google Play untuk tiga aplikasi Fintech, yaitu Flip, Neobank, dan Bank Jago. Tahapan pemrosesan meliputi pelabelan, preprocessing untuk membersihkan data, dan pembobotan kata menggunakan metode TF-IDF (Term Frequency-Inverse Document Frequency). Teknik Random Oversampling diterapkan untuk mengatasi ketidakseimbangan kelas dalam dataset. Hasil penelitian menunjukkan bahwa optimasi parameter dengan PSO mampu meningkatkan kinerja analisis sentimen, dengan peningkatan rata-rata sebesar 11,33% untuk setiap aplikasi. PSO juga meningkatkan akurasi model dalam menghadapi tantangan data tidak seimbang, memberikan wawasan yang lebih dalam bagi pengembang aplikasi untuk meningkatkan layanan.   Abstract Financial technology (Fintech) applications have become part of people's daily lives in the digital era. The convenience and efficiency offered by Fintech applications have attracted millions of users, who actively provide feedback and reviews on platforms such as the Google Play Store. These reviews are an important source of information for application developers to understand user perceptions, identify problems, and improve service quality. The study investigates the effectiveness of the Particle Swarm Optimization (PSO) method for balanced and unbalanced datasets and how well it improves sentiment analysis accuracy when applied to the Support Vector Machine (SVM) algorithm when using Radial Basis Function (RBF) kernel. We conducted web scraping to collect user review data from Google Play for three FinTech applications: Flip, Neobank, and Bank Jago as research objects. Following data collection, the review data underwent preprocessing steps, such as word weighting using the TF-IDF (Term Frequency-Inverse Document Frequency), labeling, and preprocessing to clean the data. Random Oversampling resolved the dataset's class imbalance, making all classes representative in the study. The results of this study indicate that parameter optimization with PSO can improve the performance of sentiment analysis on the subjects studied. Furthermore, based on the results of SVM testing using parameter optimization of the PSO algorithm, an average performance increase of 11.33% was obtained for each application that had been analyzed. The results also show that PSO improves model accuracy in sentiment analysis with imbalanced data challenges, providing deeper insights for application developers to improve services.