Arafat Febriandirza
@uhamka.ac.id
Informatics Engineering
UNIVERSITAS MUHAMMADIYAH PROF DR HAMKA
RESEARCH INTERESTS
IT Strategic Plan , Machine Learning , Modeling , Simulation
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Muhammad Yudhi Rezaldi, Ambar Yoganingrum, Abdurrakhman Prasetyadi, Aang Gunawan Sutyawan, Arafat Febriandirza, Cahyo Trianggoro, and Ridwan Suhud
Informa UK Limited
Ridwan Suhud, Arafat Febriandirza, Intan Permatasari, and Farhan Ramadan
IEEE
Merdeka Belajar Kampus Merdeka (MBKM) is a policy governed by the Minister of Education and Culture to improve college students’ capability, creativity, and innovation. Several programs are offered to realize MBKM, one is Kampus Mengajar which gives the opportunity for the participants in problem-solving, strategic development, effective, innovative, and fun learning. The teaching campus program gets different responses from the public which is conveyed on social media, various comments in the form of comments that are positive, negative, or neutral. To recognize public opinions of Kampus Mengajar’s implementation, this research conducted a sentiment analysis using A thousand and five hundred Twitter datasets containing Kampus Mengajar as a keyword. We apply pre-processing before classifying the dataset in Naive Bayes. Thus, SMOTE is carried out to overcome imbalanced data. The results showed that the level of accuracy in determining categories was 77.45% and the micro average was 77.45% in determining sentiment and had a precision level of 81.46% and a recall of 77.45%.
Arafat Febriandirza, Muhammad Rizky Kurniawan, and Arti Dian Nastiti
IEEE
Human resources management is needed to find the right person in the right place specifically in the admitting process. The process has to meet the criteria which required will be easier with the accurate method of employee admission. To build a thriving company, they must have excellent and qualified employees. Currently, the admission system is manual using paper that will be calculated by Human Resource Department (HRD). Decision support system is needed to help HRD deciding and determining the right employee in admission process so as finding the excellent and qualified employee that meet the criteria required will be faster. In this study, Multi Attribute Utility Theory (MAUT) method was chosen in employee admitting process based on criteria required by HRD which are major, GPA, work experience, test result, and job interview result. Based on the accuracy value calculation was obtained accuracy value of 80% or as many as 12 applicants are qualified to required criteria.
Abdurrakhman Prasetyadi, Muhammad Yudhi Rezaldi, Cahyo Trianggoro, Arafat Febriandirza, Ridwan Suhud, Aang Gunawan, and Haidaruddin Muhammad Ramdhan
IEEE
In this study, we explore the metaverse, a virtual realm blending the digital and real worlds. The metaverse promises immersive experiences, and we focus on creating lifelike avatars and environments within a scientific hub called the Science and Technology Region (KST). We use a method called terrestrial photogrammetry to make 3D avatars, focusing on researchers at KST. The results show that Agisoft Metashape makes highly precise 3D models with symmetrical details, while the KIRI Engine is faster in processing. These findings suggest that we can make better avatars and environments in the metaverse, but the choice between precision and speed depends on the specific application.
Ambar Yoganingrum, Rulina Rachmawati, Cahyo Trianggoro, Arafat Febriandirza, Koharudin Koharudin, Muhammad Yudhi Rezaldi, and Abdurrakhman Prasetyadi
IGI Global
Artificial intelligence and machine learning have become prominent fields of science and are believed to be powerful tools to achieve the Sustainable Development Goals (SDGs). Therefore, it is necessary to discuss the relationship of AI and ML to the SDGs. This chapter aims to provide information about the focus of AI and ML research on the 17 SDGs. This article finds that the amount of AI and ML research for several SDGs is very high.
Budi Nugroho, Ambar Yoganingrum, Arafat Febriandirza, and Abdurrakhman Prasetyadi
ACM
The term “herd stupidity” has recently gone viral as an innuendo for our country’s stuttering in dealing with the Covid-19 pandemic. We assessed indications of “science denial” text analysis on social media (Twitter). We developed a science denial indication dataset by utilizing the social network analysis (SNA) tool and taking geolocation data and the active cases data from the Covid-19 National Task Force regarding the distribution of clusters. We applied regression as prediction algorithms to predict areas that could become new clusters of Covid-19 spread. We tested the performance of the prediction algorithm using the mean absolute error (MAE). The experimental results show a correlation between the level of “science denial” and the formation of new clusters. The results of the prediction performance measurement show that the prediction algorithm gives acceptable results with a value of 843 MAE. This study demonstrated that Banten is the province with the highest percentage of negative sentiment and science denial text. The output provides a basis for policymakers to determine appropriate interventions in the context of controlling the Covid-19 pandemic, especially in Indonesia.