Transmissia Semiawan
Department Of Computer Engineering And Informatics, Bandung State Polytechnic, Indonesia

Published : 4 Documents Claim Missing Document
Claim Missing Document

Found 4 Documents

Mask R-CNN and GrabCut Algorithm for an Image-based Calorie Estimation System Tiara Lestari Subaran; Transmissia Semiawan; Nurjannah Syakrani
Journal of Information Systems Engineering and Business Intelligence Vol. 8 No. 1 (2022): April
Publisher : Universitas Airlangga

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.20473/jisebi.8.1.1-10


Background: A calorie estimation system based on food images uses computer vision technology to recognize and count calories. There are two key processes required in the system: detection and segmentation. Many algorithms can undertake both processes, each algorithm with different levels of accuracy. Objective: This study aims to improve the accuracy of calorie calculation and segmentation processes using a combination of Mask R-CNN and GrabCut algorithms. Methods: The segmentation mask generated from Mask R-CNN and GrabCut were combined to create a new mask, then used to calculate the calorie. By considering the image augmentation technique, the accuracy of the calorie calculation and segmentation processes were observed to evaluate the method’s performance. Results: The proposed method could achieve a satisfying result, with an average calculation error value of less than 10% and an F1 score above 90% in all scenarios. Conclusion: Compared to earlier studies, the combination of Mask R-CNN and GrabCut could obtain a more satisfying result in calculating food calories with different shapes. Keywords: Augmentation, Calorie Calculation, Detection
Tugas Akhir Program Diploma III Bidang Teknologi Informasi dan Komunikasi Inggriani Liem; Transmissia Semiawan; Uuf Brajawidagda
JURNAL INTEGRASI Vol 2 No 2 (2010): Jurnal Integrasi Edisi Khusus (Seminar Nasional) - Juli 2010
Publisher : Politeknik Negeri Batam

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


Pada makalah ini diusulkan suatu kriteria umum untuk tugas akhir diploma untuk program studi terkait teknologi informasi, dan juga dipaparkan pelaksanaan tugas akhir di Politeknik Negeri Bandung Jurusan Teknik Komputer dan Informatika, Politeknik Batam Program Studi Teknik Informatika dan di Politeknik Informatika Del, Program Studi Sistem Informasi, Teknik Informatika dan Teknik Komputer konsentrasi Administrasi Jaringan Komputer. Makalah ini dituliskan dengan tujuan untuk menjawab pertanyaan yang menjadi tema seminar yaitu ”What Is The Appropriate Research Level And Criteria For A Final Project -D3?”, lebih khusus lagi untuk program Diploma tiga yang diselenggarakan oleh Politeknik, untuk program Studi terkait Informatika. Semoga tulisan ini berguna untuk memperbaiki mutu tugas akhir bagi banyak pendidikan program diploma tiga bidang informatika yang diselenggarakan di Indonesia.
Penerapan Convolutional Long Short-Term Memory untuk Klasifikasi Teks Berita Bahasa Indonesia Yudi Widhiyasana; Transmissia Semiawan; Ilham Gibran Achmad Mudzakir; Muhammad Randi Noor
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 10 No 4: November 2021
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1150.961 KB) | DOI: 10.22146/jnteti.v10i4.2438


Text classification is now a well-studied field, particularly in Natural Language Processing (NLP). The text classification can be carried out using various methods, one of which is deep learning. Deep learning methods such as RNN, CNN, and LSTM are the most frequent methods used for text classification. This research aims to analyze the implementation of two deep learning methods combination, namely CNN and LSTM (C-LSTM), to classify Indonesian news texts. News texts used as data in this study were collected from Indonesian news portals. The obtained data were then divided into three categories based on their scope: "National," "International," and "Regional." Three research variables were tested in this study: the number of documents, the batch size value, and the learning rate value of the built C-LSTM. The experimental results showed that the F1-score obtained from the classification results using the C-LSTM method was 93.27%. The F1-score value generated by the C-LSTM method was higher than that of CNN (89.85%) and LSTM (90.87%). In summary, the combination method of two deep learning methods, namely CNN and LSTM (C-LSTM), outperforms CNN and LSTM.
Pemodelan Data Relasional pada NoSQL Berorientasi Dokumen Muhammad Riza Alifi; Transmissia Semiawan; Djoko C.U. Lieharyani; Hashri Hayati
Jurnal Nasional Teknik Elektro dan Teknologi Informasi Vol 11 No 3: Agustus 2022
Publisher : Departemen Teknik Elektro dan Teknologi Informasi, Fakultas Teknik, Universitas Gadjah Mada

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.22146/jnteti.v11i3.3704


Data management technology that continues to develop and boost the popularity of document-based not only structured query language (NoSQL) has become the most-used data model. Behind its popularity, data management technology offers an intriguing advantage, namely flexible data storage, whether in terms of data forms and sizes or structured and unstructured data. However, this data modeling flexibility has its challenge due to its impact on more complex scheme creations, without being accompanied by any need-based design patterns. This study aims to model relational data on the document-based NoSQL at its conceptual, logical, and physical levels. The conceptual design was developed based on processes, rules, and business requirements. The logical and physical designs were developed based on the extended references and computed design patterns determined from the operating workload. The relational data model design on the document-based NoSQL was successfully formed using the entity relationship diagram (ERD) with Chen notation for the conceptual, and collection relationship diagram (CRD) for both logical and physical levels. The conceptual design focused on the representation of entities, attributes, and relationships. Unlike the conceptual design which tends to be abstract, the focus of the logical design is on the collection schema (embedded and reference) representation, including design patterns influenced by the formation of relationships. Furthermore, the focus of physical level design is to represent the schema in a more concrete form. The physical design is almost the same as the logical one, the difference lies only in the detail addition for data types and structures. The evaluation of data model designs was also carried out for each level. This study contributes to designing a data model with the advantage of read-intensive capability since a joint operation among collections is not required and the computation process recurrence for derivative attributes is not necessary.