cover
Contact Name
Erna Piantari
Contact Email
jcs@upi.edu
Phone
+6285222044331
Journal Mail Official
jcs@upi.edu
Editorial Address
Department of Computer Science Education, Universitas Pendidikan Indonesia, Jl. Setiabudhi 229, Bandung, Indonesia
Location
Kota bandung,
Jawa barat
INDONESIA
Journal of Computers for Society
ISSN : -     EISSN : 27234088     DOI : https://doi.org/10.17509/jcs.v5i2
The Journal invites original articles and not simultaneously submitted to another journal or conference. The whole spectrum of computer science are welcome, which includes, but is not limited to - Artificial Intelligence, IoT and Robotics - Data Analysis and Big Data - Multimedia and Design, - Software Engineering, - Computer Networking, - Information System, and - Applications of computer science in education, agriculture, government, smart city, bioinformatics, astrophysics, simulation and modelling, etc.
Articles 5 Documents
Search results for , issue "Vol 4, No 2 (2023): JCS: September 2023" : 5 Documents clear
Predicting Solar Flares Using Data Products Vector Magnetic SDO/HMI dan Random Ferns Rooseno Rahman Dewanto; Lala Septem Riza; Judhistira Aria Utama
Journal of Computers for Society Vol 4, No 2 (2023): JCS: September 2023
Publisher : Universitas Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/jcs.v4i2.71184

Abstract

Solar flares (SFs) are the most powerful bursts of energy in the solar system that often have a bad effect on space weather. Until now, the cause of its appearance is not known for sure. Nevertheless, SFs are known to have magnetic properties attached to them. Therefore, understanding the configuration of the magnetic field on the sun plays an important role in SFs prediction efforts. Using SFs flux data recorded by X-ray Sensors on the Geostationary Operational Environmental Satellite (GOES) which is mapped with 13 parameters of the magnetic vector data of the solar photosphere layer recorded by the Helioseismic and Magnetic Imager (HMI) at the Solar Dynamic Observatory (SDO) and the Machine Learning (ML) Random Ferns (RFe) algorithm,  This study tries to predict the emergence of multiclass SFs (B, C, M, and X) along with binary SFs (BC and MX). This study uses data from May 1, 2010 to May 10, 2020, with a total of 30 classes X, 443 classes M, 1032 classes C, 751 classes B, 473 classes MX, and 1783 classes BC. This study also applies the oversampling method to handle the imbalanced nature of the data on SFs data. Overall, it can be seen that predicting the occurrence of SFs using RFe is a valid effort. The highest average scores achieved by this study for sensitivity/recall, precision, and True Skill Statistics (TSS) in multiclass SFs were 74.4%, 50.3%, and 58.7%, respectively; and in binary SFs are 87.7%, 77.7%, and 72.8%.
Exemplar Based Convolutional Neural Network for Face Search on CCTV Video Recording Winda Mauli Kristy; Yaya Wihardi; Erlangga Erlangga
Journal of Computers for Society Vol 4, No 2 (2023): JCS: September 2023
Publisher : Universitas Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/jcs.v4i2.71185

Abstract

Many techniques can perform effective face searches, but generally, these methods require numerous samples, particularly when using deep learning approaches. However, there are scenarios where face searches must be conducted with limited samples, such as those obtained from CCTV video recordings, making prior training infeasible. In these situations, a method based on exemplars must be implemented. This investigation utilizes a convolutional neural network (CNN) approach coupled with two unique matching techniques: cross-correlation matching (CCM) and normalized cross-correlation matching (NCC). The study makes use of the Chokepoint Face Dataset, training the data through the optimization of triplet loss. The goal of the study is to evaluate the performance of these combined methods. Two different architectures are created and tested within each method to determine the accuracy of each architecture. The CNN-NCC method has been found to yield accuracy rates that surpass those of the CNN-CCM method by 2 to 17.9%. Nevertheless, it is important to note that the accuracy of the results is greatly influenced by the variations observed in the CCTV video recordings.
Stemming Algorithm Modification for Overstemming Cases Stephanie Betha R.H.
Journal of Computers for Society Vol 4, No 2 (2023): JCS: September 2023
Publisher : Universitas Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/jcs.v4i2.71186

Abstract

The stemming process plays an important role in the preprocessing of the text. One of the problems that occur in the stemming process is overstemming. Overstemming is an exaggerated word cut causing situations where a word has a very different meaning, but it produces the same stem. Therefore, to overcome these problems, it will be modified on the stemming process. This modification is done by combining two stemming algorithms (hybrid stemming) that is the look-up algorithm of dictionary table and affix removal algorithm using stemming porter. The modification of this stemming algorithm will be tested on title in scientific publication documents. The test results show that stemming process with modification of stemming algorithm can increase the recall value in the title attribute, although not very significant. The recall in an experiment using title attribute is 89,9%.
Security Analysis and The Effect of Codec Changes on Quality of Service of Encrypted Voice Phones on Voice Over IP Freepbx Asep Saepul Achmad; Muhammad Nursalman; Rizky Rachman J.
Journal of Computers for Society Vol 4, No 2 (2023): JCS: September 2023
Publisher : Universitas Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/jcs.v4i2.71181

Abstract

VoIP is one of the technologies as communication with audio and video media online. The server secures voice phone data on VoIP supporting VoIP phone data encryption. In addition to security, in order to improve sound quality FreePBX also uses the latest codecs such as Alaw, Ulaw, G722, G729. The purpose of this study was to display the results of VoIP voice phone security testing on FreePBX Server, analyze the Quality of Service of voice codecs on VoIP phones, and compare encrypted and unencrypted VoIP voice phones. The Quality-of-Service criteria of voice telephony consist of packet loss, jitter, and delay or delta. Then, test VoIP security using the Man in The Middle Attack (ARP Poisioning) attack method on the Cain and Abel application. Next, analyze the comparison between encrypted and unencrypted phones using SoftPhone SIPSoercery. Test results for QoS of encrypted VoIP phones with different audio codecs are very good and this assessment is based on the TIPHON QoS standard. The best delta value is found in the Ulaw codec and the best jitter value is found in the Alaw codec. After VoIP phones are attacked with ARP Poisoning, there is a decrease in QoS quality. For all codecs tested, the delta value decreased from 9.34% to 104.12%, the jitter value decreased from 235.49% to 767.97%, and the packet loss value decreased from 5.56% to 181.82%.
Implementation of Inverse Document Frequency (TF-IDF) and Cosine Similarity Terms in Determining Research Reviewers for Indonesian Education University Lecturers Hazmi Ramadhan Adli; M. Munir; Rani Megasari
Journal of Computers for Society Vol 4, No 2 (2023): JCS: September 2023
Publisher : Universitas Pendidikan Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.17509/jcs.v4i2.71183

Abstract

Research is a mandatory activity for lecturers at the Indonesian Education University. The Institute for Research and Community Service (LPPM) oversees these research activities. Before research can commence, the research proposal must be tested or reviewed by an Examining Lecturer (reviewer). Reviewers are selected based on the similarity between the researcher's and the reviewer's variables and the availability of the reviewer's quota. This selection process utilizes the Term Frequency Inverse Document Frequency (TF-IDF) and Cosine Similarity methods to measure the similarity between queries and documents, specifically abstracts and scientific fields. This approach results in reviewer recommendations with an accuracy of 83.3%, as validated by experts.

Page 1 of 1 | Total Record : 5