Article Per Year (5 Year)
p-Index From 2021 - 2026
0.61
P-Index
This Author published in this journals
All Journal International Journal of Electrical and Computer Engineering Jurnal Informatika Proceedings of KNASTIK TELKOMNIKA (Telecommunication Computing Electronics and Control) JUTI: Jurnal Ilmiah Teknologi Informasi Journal of Mathematical and Fundamental Sciences Journal of Engineering and Technological Sciences Journal of ICT Research and Applications Proceeding of the Electrical Engineering Computer Science and Informatics Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) IT JOURNAL RESEARCH AND DEVELOPMENT Jambura Journal of Informatics
Benhard Sitohang
Institut Teknologi Bandung
Astronomy Chemistry Computer Science & IT Control & Systems Engineering Dentistry Earth & Planetary Sciences Education Electrical & Electronics Engineering Engineering Library & Information Science Mathematics Physics

Published : 24 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 24 Documents
Search

 1   2   3 
The Evaluation of DyHATR Performance for Dynamic Heterogeneous Graphs Nasy`an Taufiq Al Ghifari; Gusti Ayu Putri Saptawati; Masayu Leylia Khodra; Benhard Sitohang
Journal of ICT Research and Applications Vol. 17 No. 2 (2023)
Publisher : DRPM - ITB

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.5614/itbj.ict.res.appl.2023.17.2.7

Abstract

Dynamic heterogeneous graphs can represent real-world networks. Predicting links in these graphs is more complicated than in static graphs. Until now, research interest of link prediction has focused on static heterogeneous graphs or dynamically homogeneous graphs. A link prediction technique combining temporal RNN and hierarchical attention has recently emerged, called DyHATR. This method is claimed to be able to work on dynamic heterogeneous graphs by testing them on four publicly available data sets (Twitter, Math-Overflow, Ecomm, and Alibaba). However, after further analysis, it turned out that the four data sets did not meet the criteria of dynamic heterogeneous graphs. In the present work, we evaluated the performance of DyHATR on dynamic heterogeneous graphs. We conducted experiments with DyHATR based on the Yelp data set represented as a dynamic heterogeneous graph consisting of homogeneous subgraphs. The results show that DyHATR can be applied to identify link prediction on dynamic heterogeneous graphs by simultaneously capturing heterogeneous information and evolutionary patterns, and then considering them to carry out link predicition. Compared to the baseline method, the accuracy achieved by DyHATR is competitive, although the results can still be improved.
Folk Games Image Captioning using Object Attention Akbar, Saiful; Sitohang, Benhard; Pardede, Jasman; Amal, Irfan; Yunastrian, Kurniandha; Ahmada, Marsa; Prameswari, Anindya
Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Vol 7 No 4 (2023): August 2023
Publisher : Ikatan Ahli Informatika Indonesia (IAII)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29207/resti.v7i4.4708

Abstract

The result of a deep learning-based image captioning system with encoder-decoder framework relies heavily on the image feature extraction technique and the caption-based model. The accuracy of the model is heavily influenced by the proposed attention mechanism. The inability to distinguish between the output of the attention model and the input expectation of the decoder can cause the decoder to give incorrect results. In this paper, we proposed an object-attention mechanism using object detection. Object detection outputs a bounding box and an object category label, which is then used as an image input into VGG16 for feature extraction and into a caption-based LSTM model. The experimental results showed that the system with object attention performed better than the system without object attention. BLEU-1, BLEU-2, BLEU-3, BLEU-4, and CIDER scores for the image captioning system with object attention improved 12.48%, 17.39%, 24.06%, 36.37%, and 43.50% respectively compared to the system without object attention.
INTEGRASI ALGORITMA POHON KEPUTUSAN C4.5 YANG DIKEMBANGKAN KE DALAM OBJECT-RELATIONAL DBMS Veronica S. Moertini; Benhard Sitohang; Oerip S. Santosa
JUTI: Jurnal Ilmiah Teknologi Informasi Vol 6, No 2 Juli 2007
Publisher : Department of Informatics, Institut Teknologi Sepuluh Nopember

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (482.712 KB) | DOI: 10.12962/j24068535.v6i2.a186

Abstract

Integrasi teknik-teknik data mining ke dalam DBMS, khususnya Object-Relational DBMS (ORDBMS), masih merupakan bidang penelitian yang aktif. Isu utama pada integrasi ini adalah: peleburan algoritma data mining ke dalam ORDBMS dengan memanfaatkan fitur-fiturnya untuk memperbaiki kualitas teknik tersebut. Pada penelitian ini, algoritma klasifikasi C4.5 dikembangkan dengan pendekatan aljabar relasional dan diintegrasikan ke dalam ORDBMS sebagai prosedur-prosedur tersimpan Java dan berbasis SQL, dengan tujuan untuk meningkatkan skalabilitas dan efisiensinya. Hasil eksperimen menunjukkan bahwa algoritma yang sudah diintegrasikan berhasil memperbaiki skalabilitas dan pada kasus khusus juga memperbaiki  efisiensi.   Kata kunci: pengembangan algoritma C.5, integrasi C4.5 ke dalam Object-Relational DBMS, algoritma C4.5, perbaikan skalabilitas C4.5.
Exploring a Better Search–based Implementation on Second–Order Mutant Generation Tuloli, Mohamad Syafri; Sitohang, Benhard; Hendradjaya, Bayu
Jambura Journal of Informatics VOL 1, NO 1: APRIL 2019
Publisher : Universitas Negeri Gorontalo

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (545.479 KB) | DOI: 10.37905/jji.v1i1.2329

Abstract

Pengujian perangkat lunak adalah bagian dari proses pengembangan perangkat lunak, dengan tujuan utama untuk mengurangi/menghilangkan kesalahan pada perangkat lunak, hal ini umumnya dilakukan dengan menjalankan kasus-uji. Salah satu teknik untuk mengukur dan meningkatkan kualitas dari kasus uji adalah pengujian mutasi, tetapi walaupun sudah terbukti keefektifannya, teknik ini masih memiliki suatu kendala besar, yaitu tidak praktis untuk digunakan karena melibatkan pembangkitan dan eksekusi dari jumlah mutan yang besar. Belakangan ini penggunaan optimisasi berbasis-pencarian pada permasalahan pengujian perangkat lunak sedang popular. Pada penelitian ini, dilakukan eksplorasi penggunaan optimasi berbasis-pencarian pada pembangkitan mutan (variasi dari program), dengan tujuan untuk menghasilkan mutan yang tidak dapat dideteksi oleh kasus-uji, karena mutan jenis ini memiliki dapat kekurangan dari kasus-uji. Metode usulan dibandingkan dengan algoritma pembangkitan second-order mutant yang umum digunakan, dan juga dibandingkan dengan pendekatan berbasis pencarian lainnya. Hasil menunjukkan bahwa metode usulan dapat membangkitkan lebih banyak mutan tidak-terdeteksi (undetected-mutant) daripada dengan metode pembangkitan mutan yang umum. Metode usulan memiliki performansi yang lebih rendah daripada metode pembangkitan berbasis-pencarian benchmark, tetapi performansinya dapat ditingkatkan dengan melakukan perubahan pada representasi solusi, dan dengan adopsi parameter optimasi yang digunakan oleh metode pembanding. Software testing is a part of a software development process with a major concern is to reduce/eliminate fault in the software, and mainly done by executing a test case. One of the techniques for measuring and improving test case quality is mutation testing, but despite it is good effectiveness, this technique has a major problem that is impractical because it involves generation and execution of huge amount of mutant. This trend also happens in software testing, with the main focus on optimizing the test case generation. In this research, we explore the used of search-based optimization to the mutant (program variant) generation, with a goal to generate mutants that can escape test case detection, because these mutants have a probability to show test case deficiency. In this research, the proposed method is compared with a general second-order mutant generation algorithm and with other search-based mutant generation. The result shows that the proposed method can generate more undetected-mutant than a general second-order mutant generation. The proposed method performs worse than the benchmark search-based mutant generation, but this performance improved by altering it is solution representation and by the adoption of an optimization parameter.
Co-Authors Adikara, Fransiskus Ahmad Dahlan Ahmada, Marsa Akbar, Saiful Amal, Irfan Bayu Hendradjaya Bayu Hendradjaya Dwi H. Widyantoro Fazat Nur Azizah G. A. Putri Saptawati G.A. Putri Saptawati Gede Indrawan Guido P. Bakema Gusti Ayu Putri Saptawati Hendradjaya, Bayu Hery Heryanto I Nyoman Prama Pradnyana Inne Gartina Husein Jasman Pardede Masayu Leylia Khodra Mohamad Syafri Tuloli mohammad syafri tuloli Nasy`an Taufiq Al Ghifari Nasy`an Taufiq Al Ghifari Oerip S. Santosa Oerip S. Santoso Prameswari, Anindya Putri Saptawati Putri Saptawati Regina Yulia Yasmin Regina Yulia Yasmin Shelvie Nidya Neyman Sudarso Kaderi Wiryono Suhono H. Supangkat Tjahjanto, Tjahjanto Tricya Esterina Widagdo Veronica S. Moertini Veronica S. Moertini Veronica S. Moertini Yunastrian, Kurniandha