Article Per Year (5 Year)
p-Index From 2021 - 2026
0.23
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 Engineering and Technological Sciences Proceeding of the Electrical Engineering Computer Science and Informatics Jurnal RESTI (Rekayasa Sistem dan Teknologi Informasi) Jambura Journal of Informatics
Benhard Sitohang
Institut Teknologi Bandung
Computer Science & IT Dentistry Education Electrical & Electronics Engineering Engineering Library & Information Science

Published : 13 Documents Claim Missing Document
Claim Missing Document
Check
Articles

Found 13 Documents
Search

 1   2 
Minimizing the Estimated Solution Cost with A* Search to Support Minimal Mapping Repair Inne Gartina Husein; Benhard Sitohang; Saiful Akbar
Proceeding of the Electrical Engineering Computer Science and Informatics Vol 4: EECSI 2017
Publisher : IAES Indonesia Section

Show Abstract | Download Original | Original Source | Check in Google Scholar | Full PDF (1322.664 KB) | DOI: 10.11591/eecsi.v4.1080

Abstract

Incoherent alignment has been the main focus in the matching process since 2010.  Incoherent means that there is semantic or logic conflict in the alignment. This condition encouraged researches in ontology matching field to improve the alignment by repairing the incoherent alignment. Repair mapping will restore the incoherent to coherent mapping, by deleting unwanted mappings from the alignment. In order to minimize the impacts in the input alignment, repair process should be done as as minimal as possible. Definition of minimal could be (1) reducing the number of deleted mappings, or (2) reducing the total amount of deleted mappings’ confidence values. Repair process with new global technique conducted the repair with both minimal definitions. This technique could reduce the number of deleted mappings and total amount of confidence values at the same time. We proposed A * Search method to implement new global technique. This search method was capable to search the shortest path which representing the fewest number of deleted mappings, and also search the cheapest cost which representing the smallest total amount of deleted mappings’ confidence value. A* Search was both complete and optimal to minimize mapping repair size.
Exploring a Better Search–based Implementation on Second–Order Mutant Generation Mohamad Syafri Tuloli; Benhard Sitohang; Bayu Hendradjaya
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.
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.
Co-Authors Ahmada, Marsa Akbar, Saiful Amal, Irfan Bayu Hendradjaya G.A. Putri Saptawati Gede Indrawan Hendradjaya, Bayu Hery Heryanto I Nyoman Prama Pradnyana Inne Gartina Husein Jasman Pardede Mohamad Syafri Tuloli mohammad syafri tuloli Oerip S. Santosa Prameswari, Anindya Putri Saptawati Regina Yulia Yasmin Shelvie Nidya Neyman Sudarso Kaderi Wiryono Tjahjanto, Tjahjanto Tricya Esterina Widagdo Veronica S. Moertini Yunastrian, Kurniandha