cover
Contact Name
Heri Nurdiyanto
Contact Email
Heri Nurdiyanto
Phone
-
Journal Mail Official
internationaljournalair@gmail.com
Editorial Address
-
Location
Kota metro,
Lampung
INDONESIA
International Journal of Artificial Intelligence Research
Published by STMIK Dharma Wacana
ISSN : -     EISSN : 25797298     DOI : -
International Journal Of Artificial Intelligence Research (IJAIR) is a peer-reviewed open-access journal. The journal invites scientists and engineers throughout the world to exchange and disseminate theoretical and practice-oriented topics of Artificial intelligent Research which covers four (4) majors areas of research that includes 1) Machine Learning and Soft Computing, 2) Data Mining & Big Data Analytics, 3) Computer Vision and Pattern Recognition, and 4) Automated reasoning. Submitted papers must be written in English for initial review stage by editors and further review process by minimum two international reviewers.
Arjuna Subject : -
Articles 621 Documents
Enhancing Dynamic Capabilities through the Implementation of the Electronic Corruption Prevention Program (E-Proksi) in Kendari City Sartono, Sartono; Alam, Syamsul; Yusuf, Muhammad; Taufik, Taufik; Afdal, Andi Ahmad Malikul; Laxmi, Laxmi
International Journal of Artificial Intelligence Research Vol 8, No 1.1 (2024)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v8i1.1.1188

Abstract

This study aims to explore the role of information technology innovation, particularly E-Government, in enhancing governance dynamics and efficiency in addressing challenges related to corruption. Employing a qualitative approach with phenomenology, the research focuses on elucidating individual experiences with the implementation of E-Proksi at the Kendari City Inspectorate. Data collection involved interviews and observations, with data validation conducted through triangulation to ensure accuracy and consistency. The findings indicate that the technological innovation introduced by the E-Proksi application in Kendari City has positively influenced both corruption prevention and the enhancement of public services. However, the application encounters challenges such as public preference for traditional methods, insufficient socialization, and suboptimal political and regulatory support. Adaptive organizational culture and dynamic capabilities emerge as crucial factors in ensuring the program's success. Continued efforts to increase public participation and responsiveness to change are essential for achieving governance that is efficient, transparent, and accountable. Through ongoing strategic updates and attentive consideration of community feedback, E-Proksi is anticipated to significantly contribute to fostering a more effective, cleaner, and adaptable government in Kendari City.
Improving Performance Sentiment Analysis Movie Review Film using Random Forest with Feature Selection Information Gain Adiguna, Vinsent Brilian; Aqqad, Muslihul; Purwanto, Purwanto; Jaluanto Sunu, Jaluanto Sunu; Honorata Ratnawati, Honorata Ratnawati
International Journal of Artificial Intelligence Research Vol 8, No 1.1 (2024)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v8i1.1.1227

Abstract

Sentiment analysis in film reviews is an important task to understand the audience's opinion towards a cinematic work. However, the complexity and subjectivity of language in film reviews pose a challenge. This research explores the application of Random Forest algorithm, an ensemble learning method, to perform sentiment classification on film reviews. Random Forest is built from a set of decision trees, each of which provides a prediction, and the final result is obtained from majority voting. This approach has the advantage of handling overfitting data. This research uses 500 review datasets along with positive and negative sentiment labels. The review text is represented as Information Gain and TF-IDF features to model the weight of each word. The Random Forest model is then trained using these features to predict sentiment labels. The performance of the model is evaluated using metrics such as accuracy, precision, recall and f1-score. The experimental results show that Random Forest is able to achieve 95.20% accuracy in sentiment classification of film reviews, surpassing the Support Vector Machine classification algorithm which in previous studies only achieved 92%. These findings provide a new perspective on the benefits of ensemble learning in sentiment analysis and its potential application in other domains such as marketing and public opinion analysis.
Fuzzy Preference Relations-Based AHP for Multi-Criteria Supplier Segmentation Nurdiyanto, Heri; Fauzi, Chairani; Lestari, Sri
International Journal of Artificial Intelligence Research Vol 8, No 1 (2024): June 2024
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v7i1.1.1103

Abstract

Supplier segmentation is a strategic activity for businesses. It involves dividing suppliers into distinct categories and managing them differently. Various supplier typologies based on different dimensions and factors are available in the existing literature. By highlighting two main characteristics the skills and the desire of suppliers to work with a specific company this article integrates many typologies. Almost all of the supplier segmentation criteria stated in the literature are covered by these dimensions. These dimensions can be defined utilizing a multi-criteria decision-making process for each specific case. To account for the inherent ambiguities and uncertainties in human judgment, a fuzzy Analytic Hierarchy Process (AHP) is suggested as part of the technique. This approach makes use of fuzzy preference relations. A broiler firm uses the suggested process to divide up its suppliers. A categorization of vendors according to two aggregated criteria is the end outcome. Lastly, we offer some suggestions for future research, draw some conclusions, and talk about some techniques to address distinct sectors
Analysis of Critical Success Factors for KM Foundation in a Consulting Company Tanjung, Aldiyan Muhammad; Sensuse, Dana Indra
International Journal of Artificial Intelligence Research Vol 8, No 1 (2024): June 2024
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v8i1.1182

Abstract

In the business world, Knowledge Management (KM) is increasingly recognized as a crucial factor for organizational success, especially within consulting firms. This research investigates the Critical Success Factors (CSFs) necessary for the effective implementation of KM in consulting firms. Faced with the complexities and challenges of a dynamic business environment, where efficient KM is vital for delivering high-quality services, this study conducts a thorough review of the CSFs related to KM foundations in consulting firms. The aim is to identify the CSFs essential to KM foundations. Using a Systematic Literature Review (SLR) based on the PRISMA methodology, the study synthesizes findings from five databases. From an initial pool of 1,173 papers, the selection was narrowed down to 20 papers with the most relevant content for analysis, detailing the CSFs essential to KM foundations. These factors are categorized into several dimensions, including technology, strategy, leadership, organizational culture, and regulatory policies, each contributing uniquely to the effective implementation of KM in consulting firms.
Ensuring Trust and Integrity: A Revolutionary Approach to Electronic Voting Through Blockchain Misni, HM; Jokonowoa, Bambang; Santoso, Hadi
International Journal of Artificial Intelligence Research Vol 7, No 2 (2023): December 2023
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v7i1.1.1034

Abstract

The voting method has recently been a subject of continuous discourse in numerous countries. Nevertheless, the utilization of electronic voting systems raises apprehensions about several security aspects, including but not limited to eligibility, anonymity, privacy, integrity, accuracy, and impartiality. This paper introduces an innovative strategy for augmenting the security and dependability of an electronic voting system by utilizing Blockchain technology. By eliminating the requirement for physical receipts, countering coercion (specifically, vote-selling), and guaranteeing universal verifiability, this approach aims to mitigate voter distrust in the government or governing body. This technology effectively upholds the principles of voter secrecy and verifiability. Election transparency is upheld through Blockchain technology, which serves as a secure repository for all voting transactions. Concurrently, individual voters' anonymity is preserved through a sophisticated procedure that integrates ring and within-blind signatures. In addition, the system has incorporated sophisticated card-based voter authentication and security procedures, which have been implemented with the assistance of the governing body and executed through the Dapp platform. This technology will provide a comprehensive solution and provide more excellent compatibility for elections conducted on a large scale.
Development of Detection and Mitigation of Advanced Persistent Threats Using Artificial Intelligence and Multi-Layer Security on Cloud Computing Infrastructure Hartono, Hartono; Wijaya, Ryan Aji; Khotimah, Khusnul
International Journal of Artificial Intelligence Research Vol 8, No 2 (2024): December 2024
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v8i2.1250

Abstract

This research proposes a novel approach for detecting and mitigating Advanced Persistent Threats (APTs) in cloud computing infrastruc ture, offering more comprehensive protection compared to previous methods. By integrating detection and mitigation, this study addresses the shortcomings of prior research that focused solely on detection. Based on the conducted research, Artificial Intelligence (AI) detected Cross-Site Scripting (XSS) attacks with an accuracy of 0.9951, SQL Injection (SQLI) at 0.9964, and Remote Code Execution (RCE) at 0.9876. In trials against new attacks, the detection success rates reached 70% for XSS, 98% for SQLI, and 100% for RCE. During the deployment phase, the system successfully identified 23.040 out of 108.394 requests as XSS attacks, 2.684 out of 128.750 as SQLI attacks, and 1.135 out of 46.450 as RCE attacks. The detection and mitigation methods were directly tested on cloud server experiencing APT attacks. The daily attacks on the server reached 1.980, with 663.000 requests. Additionally, the number of attacks directed at authentication or sensitive pages reached 17.913.701. Attack mitigation was tested through seven layers of security, including DNS Protection, Config Server Firewall (CSF), OWASP ModSecurity, HTTP middleware, data filter or sanitizer, template engine, and manual mitigation successfully blocking million of persistent attacks. The DNS protection layer successfully mitigated 59,000 out of a total of 19 million requests. The CSF layer mitigated 173 sources IP of DDoS attacks. The ModSecurity layer mitigated 17,916,204 attacks. All attacks were successfully mitigated before reaching the HTTP Middleware stage or next layer. The use of NIST 2.0 standards helps manage security risks through identification, protection, detection, response, and recovery. Test results indicate that this multi-layered system is more efficient and effective in detecting and mitigating attacks compared to traditional methods. However, the complexity of implementation and maintenance poses challenges that must be addressed. This research significantly contributes to a more adaptive and sustainable cybersecurity strategy.
Development of Intellectual Testing for Electric Motor Installation in Vocational Education Taruno, Djoko Laras Budiyo; Nugroho, Nur Rohman Eko
International Journal of Artificial Intelligence Research Vol 7, No 2 (2023): December 2023
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v7i2.1256

Abstract

This study aims to understand the functionality of computerized adaptive testing software based on a website application model for the competency of electric motor installation in vocational education. The research method in this research uses research and development and the waterfall model. The research subjects are teachers and students in the electric motor installation subject. Data collection is done using the Noeeriat software instrument. The results of this study are as follows: (1) This tool can function well. This is indicated by testing on the authority of teachers (86.22%) and students (87.50%). (2) The usability level of the tool is considered very feasible in terms of functionality, display, and usefulness. (3) This tool contributes to an improvement in student learning outcomes. This tool can be used to measure the level of students' competency achievement, as a basis for compiling progress reports on learning outcomes, and as a foundation for improving the learning process.
Investigating the Higher Education Students' Perception of an Interactive Virtual Processing Station Application Maryadi, Totok Heru Tri; Badarudin, Rohjai; Bintoro, Kukuh
International Journal of Artificial Intelligence Research Vol 8, No 1 (2024): June 2024
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v8i1.1255

Abstract

This study aims to evaluate the Virtual Processing Station as a simulation-based learning medium in the context of engineering education, based on student perceptions. Student perceptions of this medium were evaluated based on four main aspects: relevance, attention, interest, and usefulness. This study involved 30 students from the Department of Electrical Engineering Education at Yogyakarta State University who had used the Virtual Processing Station in laboratory practice sessions. Data were collected through a questionnaire with 17 statements using a Likert scale and supplemented with qualitative feedback from respondents. The results showed that this learning medium was very well received by students, with an average rating of 90.59%. The relevance aspect received the highest score (92.92%), followed by the interest aspect (90.83%) and usefulness (90.56%). Although the attention aspect received a slightly lower score (84.72%), the medium was still considered quite effective in capturing students' attention during the learning process. Positive comments from respondents emphasized the effectiveness of this medium in helping students understand both the practical and theoretical concepts of PLC-based industrial automation systems. The conclusion of this study indicates that the Virtual Processing Station has great potential in supporting more interactive and efficient engineering learning. However, there is still room for improvement in areas such as the user interface and visualization. Future research should focus on assessing the short-term and long-term impacts of this medium, particularly through larger sample sizes and objective assessments of student performance before and after using the Virtual Processing Station. This approach will provide deeper insights into how these medium influences learning outcomes and the development of practical skills in engineering education.
Digital Transformation of Balian Tradition Among The Dayak Siang Community: A Phenomenological Analysis with an Artificial Intelligence Approach Manik, Resmin; Jimmy, Andreas; Andriyanto, Yustinus Dwi
International Journal of Artificial Intelligence Research Vol 8, No 1.1 (2024)
Publisher : STMIK Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v8i1.1.1290

Abstract

The Balian tradition represents a significant local wisdom within the Dayak Siang community in Puruk Cahu, Central Kalimantan. This tradition embodies deep-rooted spiritual and social values that have been integral to the local community's life. However, the existence of the Balian tradition is currently threatened by the increasingly rapid flow of modernity. This research aims to explore the potential utilization of Artificial Intelligence (AI) technology as a strategy for preserving the Balian tradition through digital transformation. Using qualitative methods and a phenomenological approach, data were collected through in-depth interviews and participatory observation. Informants in this study included Damang (Traditional Leaders), community leaders, church figures, academics, and young people concerned with preserving local culture. The results show that the Balian tradition contains rich philosophical values reflecting inter-subjective relationships, compassion, and strong mutual cooperation within the Dayak Siang community. This practice is also believed to connect humans, nature, and the spirit world. AI technology has the potential to document, analyze, educate, and disseminate information about local cultural heritage efficiently and affordably, thereby contributing to maintaining the existence of the Balian tradition amid modernization.
Influence Of Innovation Strategy Model To Improving Organizational Performance Regional Government In Indonesia Mauladi, Andri; Rahayu, Agus; Wibowo, Lili Adi; Sofia, Alfira
International Journal of Artificial Intelligence Research Vol 8, No 1.1 (2024)
Publisher : Universitas Dharma Wacana

Show Abstract | Download Original | Original Source | Check in Google Scholar | DOI: 10.29099/ijair.v8i1.1.1354

Abstract

This research is aimed at testing the innovation strategy model to improving organizational performance regional government in Indonesia The performance of the Regional Government organization is the overall achievement of the results that have been achieved and achieved in handling all activities carried out by the Regional Government in a certain period (Muhamad F., 2009) as well as a description of the achievement of the government's goals and objectives as an elaboration of the vision, mission and strategy The following agencies indicate the level of success or failure in implementing activities determined by the Regional Government in accordance with established programs and policies. And this research uses the Partial Least Squares Structural Equation Modeling analysis technique (PLS-SEM), to model many variables in research.