Claim Missing Document
Check
Articles

Found 18 Documents
Search

Deepfake detection using convolutional neural networks: a deep learning approach for digital security Twince Tobing, Fenina Adline; Kusnadi, Adhi; Pane, Ivransa Zuhdi; Winantyo, Rangga
Indonesian Journal of Electrical Engineering and Computer Science Vol 39, No 2: August 2025
Publisher : Institute of Advanced Engineering and Science

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.11591/ijeecs.v39.i2.pp1092-1099

Abstract

The development of artificial intelligence technology, especially deep learning, has facilitated the emergence of increasingly sophisticated deepfake technology. Deepfakes utilize generative adversarial networks (GANs) to manipulate images or videos, making it appear as if someone said or did things that never actually happened. As a result, deepfake detection has become a critical challenge, particularly in the context of the spread of false information and digital crime. The purpose of this research is to create a method for detecting deepfakes using a convolutional neural network (CNN) approach, which has been proven effective in visual pattern recognition. Through training with a dataset of original facial images and deepfakes, the CNN model achieved an accuracy of 81.3% in detecting deepfakes. The evaluation results for metrics such as precision, recall, and F1-score indicated good performance overall, although there is still room for improvement. This study is expected to make a significant contribution to enhancing digital security, especially in detecting visual manipulations based on deepfakes.
Implementation of Scrum Method in ERP-Based Employee Performance Evaluation System Chandra, Darren Denisson; Tobing, Fenina Adline Twince; Kusnadi, Adhi; Nainggolan, Rena; Hassolthine, Cian Ramadhona
METHOMIKA: Jurnal Manajemen Informatika & Komputerisasi Akuntansi Vol. 9 No. 1 (2025): METHOMIKA: Jurnal Manajemen Informatika & Komputersisasi Akuntansi
Publisher : Universitas Methodist Indonesia

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46880/jmika.Vol9No1.pp201-209

Abstract

Human capital is a key factor in realizing an organization’s vision and mission. To ensure optimal performance, employee output must be evaluated consistently through a well-organized appraisal process. Although PT Kompas Media Nusantara has adopted such evaluations, they are still carried out using traditional methods, such as distributing physical documents. To address these inefficiencies, an ERP-based Employee Performance Evaluation System has been designed to streamline workflows, enhance accessibility, and support a more standardized and systematic assessment process. This system utilizes Key Performance Indicators (KPIs) aligned with individual job responsibilities to measure performance. The development process adopts the Scrum methodology, while system validation is carried out through Black Box Testing. The test results reveal that the system performs reliably, achieving a 100% accuracy rate in matching inputs and expected outputs. To assess user satisfaction, the End User Computing Satisfaction (EUCS) framework combined with a Likert scale was employed. The evaluation produced high satisfaction scores across various dimensions: content (89.12%), accuracy (87.02%), layout and design (88.07%), user-friendliness (89.12%), and timeliness (86.84%). These findings indicate strong user acceptance of the ERP-based system, reinforced by consistently positive user feedback regarding its effectiveness and ease of use
Designing Halal Product Traceability System using UML and Integration of Blockchain with ERP Kusnadi, Adhi; Arkeman, Yandra; Syamsu , Khaswar; Wijaya, Sony Hartono
Register: Jurnal Ilmiah Teknologi Sistem Informasi Vol 9 No 1 (2023): January
Publisher : Information Systems - Universitas Pesantren Tinggi Darul Ulum

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26594/register.v9i1.3045

Abstract

Consuming halal food is mandatory for Muslims, but meeting the growing demand for halal products has been a challenge for Muslim producers. Importing halal products from non-Muslim countries can raise doubts about their halal status. Therefore, a traceability system is needed to ensure the halalness of products. This research proposes a new traceability system by utilizing ERP, Blockchain, and smart contract technologies based on HAS 23000. This study is the first to combine these technologies. Using the System Development Life Cycle (SDLC) method, the design diagram has been successfully developed into an application system prototype. The use of ERP can help companies reduce operational costs, while the combination with blockchain technology ensures more transparent information, data protection, and system security. The system also uses smart contracts to make automated decisions. By managing the procurement of halal products, companies can ensure that products with halal assurance reach consumers.
Implementation of AHP Algorithm for Design and Development Halal Food Recommendation System at Cirebon Regional Geneva, Erick Abraham; kusnadi, adhi; Tobing, Fenina Adline Twince
IJNMT (International Journal of New Media Technology) Vol 10 No 2 (2023): IJNMT
Publisher : Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ijnmt.v10i2.3491

Abstract

Cirebon is one of the cities in Indonesia that has a variety of unique culinary delights. One of the most famous Cirebonese halal culinary delights is nasi jamblang. However, the many choices of halal Cirebonese food can make tourists struggle to choose food that suits their taste and preferences. This research aims to design and build a halal Cirebonese food recommendation system using the Analytical Hierarchy Process (AHP) method. The AHP method is used to determine the weights of the factors that influence the selection of halal Cirebonese food. This recommendation system is built using PHP and JavaScript programming languages, as well as Laravel, React, and MySQL frameworks. This recommendation system has been tested by distributing questionnaires using End User Computing Satisfaction method with google form to 35 respondents The test results show that this recommendation system produces a user satisfaction value of 87.92%. This value indicates that this recommendation system has met user expectations.
Certainty Factor-based Expert System for Meat Classification within an Enterprise Resource Planning Framework Kusnadi, Adhi; Arkeman, Yandra; Syamsu, Khaswar; Wijaya, Sony Hartono
Jurnal Ilmiah Teknik Elektro Komputer dan Informatika Vol. 9 No. 3 (2023): September
Publisher : Universitas Ahmad Dahlan

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.26555/jiteki.v9i3.26443

Abstract

The demand for halal products in the Islamic context continues to be high, requiring adherence to halal and haram laws in consuming food and beverages. However, individuals face the challenge of distinguishing between haram meat and permissible halal meat. This study aims to answer these challenges by designing an expert system application within the ERP framework to increase the usability functionality of the system that can differentiate between beef, pork, or a mixture of both based on the physical characteristics of the meat. The aim is to determine halal products permissible for consumption by Muslims. The research methodology includes a data collection process that involves taking 30 meat samples from various sources, and the criteria used to classify the meat will be determined based on an analysis of the physical characteristics of the meat. System administrators use expert systems to ensure proper treatment of meat during administration processes, including separating halal beef from pork and implementing different inventory procedures. The Certainty Factor (CF) inference engine deals with uncertainty even though the expert system's accuracy level is relatively good with several rules. However, these results must be studied further because the plan relies on expert opinion. Therefore, it is necessary to set the correct CF value for accurate height classification. The CF inference engine facilitates reasoned conclusions in meat classification. Functional testing confirms the smooth running of the system, validating its reliability and performance. In addition, the expert system accuracy assessment produces a commendable accuracy rate of 90%. In addition, the expert system works powerfully on various meat samples, accurately classifying meat types with high precision. This study explicitly highlights the expert system's design for meat classification in determining halal products by using the Expert System Certainty Factor. In conclusion, this expert system provides an efficient and reliable approach to classifying meat and supports the production and consumption of Halal products according to Islamic principles.
Implementation of SAW Method for Design and Development Apartment Recommendation System in Tangerang Using Mobile-Based Nugraha, Achmad Ilyasa; Kusnadi, Adhi; Tobing, Fenina Adline Twince
ULTIMATICS Vol 15 No 2 (2023): Ultimatics : Jurnal Teknik Informatika
Publisher : Faculty of Engineering and Informatics, Universitas Multimedia Nusantara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.31937/ti.v15i2.3492

Abstract

The house is no longer the sole type of residence available while looking for a place to live. Apartments are a solution for those who need a place to live in locations with limited land, such as Tangerang, in today's period. However, criteria are needed to choose an apartment based on a person's needs, thus in this project, we will develop and create an apartment recommendation system in Tangerang using the SAW approach to make it easy for people to choose the best apartment. The user's choice will be determined by the recommendation system based on their interests, activity, and other data. To put the recommendation system into action, the FMADM method must be employed. A Simple Additive Weighing (SAW) approach is required to complete this FMADM, which is a mechanism for computing the number of performance appraisals for each alternative based on all criteria. This recommendation system is called APARTKU, and it was created with HTML5, CSS, and AngularJS, as well as the Ionic Framework and the Firebase Database. The system was then put to the test by administering questionnaires to 32 respondents using the DeLone and McLean methodologies, and the results were tallied using the Likert Scale method, yielding a score of 90.64 percent, based on the interval on the Likert Scale technique, these results imply that the application has been constructed and designed very well.
Motorcycle workshop selection recommendation system in gading serpong using the topsis method Natapura, Septaria Dwi; Twince, Fenina Adline; Kusnadi, Adhi; Nainggolan, Rena
Jurnal Mandiri IT Vol. 12 No. 3 (2024): January: Computer Science and Field.
Publisher : Institute of Computer Science (IOCS)

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.35335/mandiri.v12i3.249

Abstract

In Indonesia, motorbike repair shops have become a necessity for motorbike riders. The large number of motorcycle repair shops makes it difficult for users to determine the right repair shop according to their needs. Thus, the role of the recommendation system is needed. In order to meet the need for various criteria, a recommendation system for selecting a motorbike repair shop was built using a case study in Gading Serpong. The criteria used are distance, service, speed, price, and comfort of the waiting area. The TOPSIS method (Technique for Order Preference by Similarity to Ideal Solution) is a multi-criteria method that is computationally efficient and is able to measure the relative performance of various decision alternatives in simple mathematical form. Therefore, this research system was built using the TOPSIS method. The test results in this research show that the TOPSIS method has been implemented correctly. Apart from that, a success test of the recommendation system has been carried out by distributing questionnaires, with a success percentage of 82.24%. The questionnaire results obtained have also been tested using Cronbach Alpha, with a result of 0.81, which means that the questionnaire results obtained can be trusted
Assessment System of Halal Product Assurance Implementation in Indonesian Companies Using ID3 and Forward Chaining Algorithm Adline Twice Tobing, Fenina; Kusnadi, Adhi; Harjono, Marco Keegan Shandry; Tjoang, Stephen
International Journal of Science, Technology & Management Vol. 4 No. 3 (2023): May 2023
Publisher : Publisher Cv. Inara

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.46729/ijstm.v4i3.805

Abstract

The majority of the population in Indonesia practices Islam, making halal products important and necessary to meet the rights and needs of Muslim consumers in Indonesia. Therefore, a halal assurance system is required, not only for obtaining halal certification, but also for maintaining continuity in halal production. The existing halal assurance system has been manual, hence the need for an automated computer-based information system that can assess the halal assurance system implemented by companies. This can make it easier and faster for novice users to assess the implementation of halal practices in a company. The ID3 algorithm is used to create decision trees, and the forward chaining algorithm is used for comparison. The web-based system is developed using PHP language and MySQL for data storage. Testing the system by comparing the final results with the manual calculations, as well as using the ID3 and forward chaining algorithms, yields the same results, indicating the successful development of assessment system of halal product assurance. In addition, user satisfaction testing resulted in a score of 87.34%, indicating that users are highly satisfied with the JaminHalal information system.