Claim Missing Document
Check
Articles

Found 3 Documents
Search
Journal : Jurnal ULTIMA Computing

Rancang Bangun Sistem Rekomendasi Restoran Menggunakan Metode AHP dan VIKOR pada Platform LINE Andre Utomo Martliong; Ni Made Satvika Iswari
Ultima Computing : Jurnal Sistem Komputer Vol 10 No 1 (2018): Ultima Computing : Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2159.293 KB) | DOI: 10.31937/sk.v10i1.847

Abstract

Since 2012 until 2017, culinary business in Indonesia has increased by an average 7% to 14% per year. Nowadays, application technology such as Zomato, helps consumers to find information about restaurant’s promos, advantages and disadvantages of a restaurant, and variations of the menu their provided. People who owned the culinary business can interact directly with consumers through social media such as LINE. LINE has 90 million users that communicate with each other by using features that LINE’s provided, such as stickers, news portals, voice and video calls, and LINE Message API service. With 90 million LINE’s users in Indonesia and growing culinary business, developing a restaurant recommendation system in LINE will provide solutions to many people, which inspired the author to develop this system. Data of restaurant it’s taken using Zomato API. Developing this system needs a method of AHP (Analytic Hierarchy Process) and VIKOR (VIsektriterijumsko KOmpromisno Rangiranje), where the application will be built using PHP language. The AHP method is used to assign a weighting value to criteria, and the VIKOR method is used to sort the best alternative option. Based on research through questionnaires, this system’s design and implementation has reached 71,13 value of usability, which mean that system is useful to help people to find restaurant their looking for. Index Terms - Culinary, Zomato API, LINE Message API, AHP, VIKOR
Rancang Bangun Aplikasi Face Tracking dan Filter Berdasarkan Raut Wajah Menggunakan Algoritma Fisher-Yates Berbasis iOS Malik Abdul Ghani; Andre Rusli; Ni Made Satvika Iswari
Ultima Computing : Jurnal Sistem Komputer Vol 11 No 1 (2019): Ultima Computing : Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (2134.646 KB) | DOI: 10.31937/sk.v11i1.1046

Abstract

Expressions of facial expressions in addition to providing important emotional indicators, are very important objects in our daily lives too. Real-time video processing on mobile devices is a hot topic and has a very broad application. Photos that have used the filter have 21% more possibilities to be seen and 45% more likely to be commented on by photo consumers. The use of the Fisher-Yates algorithm is used as a filter scrambler for each facial expression emotion. The application is made for the iOS operating system with the Swift programming language that utilizes the Core ML and Vision framework. Custom Vision is used as a tool for creating and training models. In making a model, this study uses a dataset from Cohn-Kanade AU-Coded Facial Expression Database and Karolinska Directed Emotional Faces. Custom Vision can provide performance result training and provide precision and recall values ​​for data that has been trained. The facial expression match with the model is determined by the confidence level value. The results of trials with Hedonic Motivation System Adoption Model method produce a percentage of pleasure in using the application (joy) of 79.39% of the users agree that the application provides joy.
Preliminary Study on Indonesian Word Recognition for Elder Companion Robot MB Nugraha; Dyah Ayu Anggreini Tuasikal; Ni Made Satvika Iswari; Luthfialmas Fakhrizki
Ultima Computing : Jurnal Sistem Komputer Vol 14 No 1 (2022): Ultima Computing : Jurnal Sistem Komputer
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/sk.v14i1.2696

Abstract

Word recognition using deep learning is a simple approach to speech recognition in general. From this word-level recognition, the emotional expression recognition model. The emotion recognition model can be used to describe the important level of action on future planned hardware implementation. This research was conducted using MFCC as the feature extraction method from the audio data and using the CNN-LSTM approach for the emotional expression classifier. The model itself will be implemented into a humanoid robot to become a companion robot for the elderly. The model itself has 67% accuracy for emotion recognition and 97% accuracy for word recognition. However, the model only attained 20% accuracy in real-life testing using the humanoid robot as the model tends to overfitting as a result of the lack of data used in model training.