Publication Search

This study explores the role of artificial intelligence in strengthening cybersecurity threat detection frameworks for next-generation network environments. The rapid expansion of cloud computing, Internet of Things ecosystems, and distributed digital infrastructures has significantly increased cybersecurity risks and operational vulnerabilities. Traditional cybersecurity systems often struggle to detect sophisticated and evolving threats due to their dependence on static detection mechanisms. Using a qualitative research approach and content analysis method, this study examines recent developments in artificial intelligence, machine learning algorithms, and intelligent cybersecurity frameworks. The findings indicate that AI-driven cybersecurity systems improve real-time threat detection, anomaly identification, automated monitoring, and predictive security analysis. Machine learning technologies such as Random Forest, Support Vector Machine, and deep learning models demonstrate strong potential for enhancing intrusion detection accuracy and reducing false positive rates. The study also identifies critical challenges related to ethical governance, privacy protection, computational complexity, and adversarial attacks in AI-based cybersecurity systems

Political disinformation has become one of the most critical challenges in contemporary digital democracies due to the rapid expansion of social media ecosystems. This study investigates the effectiveness of machine learning approaches in detecting political disinformation across online platforms such as Twitter, Facebook, and political discussion forums. Using a qualitative research design with a content analysis approach, the study examines linguistic manipulation, emotional narratives, sentiment polarity, and behavioral communication patterns embedded in misleading political content. The findings indicate that deep learning models, particularly Long Short-Term Memory (LSTM) architectures, demonstrate superior performance in identifying contextual and semantic inconsistencies compared to traditional machine learning algorithms. The study also reveals that algorithmic amplification, echo chambers, and coordinated bot activities significantly contribute to the rapid spread of political misinformation. Furthermore, the research highlights the importance of ethical artificial intelligence governance, transparency, and digital literacy in strengthening democratic resilience and protecting information integrity within digital communication environments

Predictive maintenance (PdM) plays a crucial role in modern industrial systems by minimizing downtime, reducing maintenance costs, and optimizing asset performance. However, many predictive models operate as “black box” systems, limiting transparency and making it difficult for operators to interpret their outputs. This study aims to integrate Explainable Artificial Intelligence (XAI) techniques with Remaining Useful Life (RUL) prediction models to improve both accuracy and interpretability. Various machine learning and deep learning approaches, including Support Vector Machines (SVM), Random Forest (RF), XGBoost, Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNN), are employed to predict RUL using real-time sensor data from rotating machinery. XAI methods such as SHAP, LIME, and attention mechanisms are applied to provide human-understandable explanations of model predictions. The models are evaluated based on accuracy, Root Mean Square Error (RMSE), and interpretability scores. The results show that XAI-enhanced models outperform traditional approaches in predictive performance while offering greater transparency. These explanations help maintenance engineers better understand the factors influencing predictions, thereby improving decision-making and trust in the system. Nevertheless, the integration of XAI introduces additional computational complexity, which may pose challenges for large-scale industrial implementation. Overall, this study highlights the potential of combining XAI with RUL prediction to develop more reliable, transparent, and effective predictive maintenance solutions.

The integration of Artificial Intelligence (AI) into precision agriculture has significantly improved plant disease recognition; however, many existing deep learning models remain computationally expensive and feature-redundant, limiting their deployment on low-power and edge devices. To address these limitations, this study proposes a lightweight framework for maize leaf disease recognition based on serial deep feature extraction, dimensionality reduction, and machine-learning–based classification. A pre-trained MobileNetV2 network is employed as a fixed feature extractor to obtain discriminative visual representations, while Principal Component Analysis (PCA) is applied to reduce feature dimensionality by approximately 76%, retaining 95% of the original variance and improving computational efficiency. The compressed features are subsequently classified using a Radial Basis Function Support Vector Machine (RBF-SVM), optimized via grid search and cross-validation. Experiments conducted on a four-class maize leaf disease dataset (Northern Leaf Blight, Common Rust, Gray Leaf Spot, and Healthy), with class imbalance handled during training, demonstrate that the proposed MobileNetV2–PCA–SVM pipeline achieves 97.58% accuracy, 96.60% precision, 96.59% recall, and 96.59% F1-score, outperforming the DenseNet201 + Bayesian-optimized SVM baseline (94.60%, 94.40%, 94.40%, and 94.40%, respectively). This improvement corresponds to a 2.98% accuracy gain, a 55% reduction in error rate, an 86% reduction in model parameters (20.31M to 2.75M), and an 85% reduction in model size (81 MB to 12 MB). These results indicate that the proposed framework provides a compact and efficient solution with strong potential for deployment in resource-constrained agricultural environments.

Financial distress is a condition of declining financial health of a company that can develop gradually and lead to business failure if not detected early. With the increasing complexity of the business environment and the limitations of conventional statistical methods, Artificial Intelligence/AI is increasingly being adopted in the development of early warning systems (EWS) to predict financial distress. This study aims to examine the development of AI-based EWS research, identify the most widely used algorithms, and evaluate the effectiveness of AI models compared to conventional methods in predicting financial distress. The method used is a comprehensive systematic literature review of 15 relevant scientific articles. The results show that the paradigm has shifted from statistical models to machine learning and deep learning. Random Forest and Artificial Neural Network are the most widely used algorithms and have better predictive performance. This study offers a conceptual synthesis of the progress, effectiveness, and challenges of applying AI in predicting financial distress and opens opportunities for further research on the development of contextual and interpretative EWS.

Explainable Artificial Intelligence (XAI) has become a critical area of research within artificial intelligence, focusing on improving the transparency and interpretability of machine learning (ML) models, often referred to as "black-box" models. The need for XAI techniques arises from the inherent complexity of ML models, which can make their decision-making processes difficult for users to understand. This study investigates various XAI techniques, including LIME (Local Interpretable Model-agnostic Explanations) and SHAP (SHapley Additive exPlanations), to assess their impact on model interpretability without significantly compromising predictive performance. A comparative experimental design was used, applying these XAI methods to different ML models, including deep neural networks and ensemble methods, within large-scale enterprise data analytics systems. The results indicate that XAI methods significantly enhance model transparency and decision traceability, allowing users to understand the influence of individual features on predictions. While a slight reduction in predictive accuracy was observed, especially with simpler models, the trade-off between interpretability and performance was deemed acceptable, particularly in fields requiring transparency, such as healthcare, finance, and autonomous systems. The use of XAI in enterprise data systems has practical implications for fostering trust and enabling informed decision-making among stakeholders. Furthermore, the study discusses the challenges and limitations of applying XAI techniques, such as complexity, scalability, and model-specific limitations. Future research is suggested to focus on developing more scalable and efficient XAI methods, enhancing their applicability across various model types, and addressing the challenges of real-time applications. This will be crucial in ensuring the widespread adoption of XAI in critical domains, promoting the ethical use of AI while maintaining predictive accuracy.

This study evaluates the efficiency of two artificial intelligence models, DeepSeek and OpenAI, in generating code for algorithmic systems. Efficiency is assessed through execution speed, code accuracy, and the number of code characters produced. Data were collected from 100 tests covering search, sorting, graph, dynamic programming, optimization, data processing, text, and machine learning algorithms. The objective is to compare the performance of both models to support the development of efficient information retrieval systems. The method involves algorithm testing with statistical analysis of execution time, accuracy, and code length. Results indicate that DeepSeek has an average execution time of 28.74 seconds, slightly slower than OpenAI’s 28.49 seconds. However, DeepSeek’s accuracy (85.88%) surpasses OpenAI’s (85.03%). The average number of code characters is identical at 96.35 characters. The study concludes that DeepSeek excels in accuracy, while OpenAI is faster in certain cases, providing valuable insights for developers in selecting AI models for information retrieval applications.

Background: The development of industrial technology in the Industry 4.0 era has encouraged the implementation of intelligent monitoring systems to improve machine reliability and operational efficiency. However, machine fault diagnosis systems based on artificial intelligence often face limitations in terms of interpretability because the models used are complex and difficult to explain. Objective: This study aims to develop a deep learning-based industrial machine fault diagnosis system integrated with an Explainable Artificial Intelligence (XAI) approach to improve diagnostic accuracy while providing interpretable insights for users. Method: The research method involves collecting data from industrial machine sensors consisting of vibration signals, temperature measurements, and acoustic signals, followed by data preprocessing and feature extraction processes. The processed data are then used to train a deep learning-based diagnostic model, after which explainability methods such as SHAP or LIME are applied to analyze the contribution of each feature to the model’s prediction results. Model performance is evaluated using accuracy, precision, recall, and F1-score metrics. Results: The results indicate that the proposed deep learning model achieves better performance compared to conventional machine learning methods such as Support Vector Machine and Random Forest. Furthermore, the explainability analysis reveals that vibration amplitude, increases in machine component temperature, and anomalies in acoustic signals are the main factors influencing machine fault detection. Therefore, the proposed system not only improves the accuracy of machine fault diagnosis but also provides transparency in the decision-making process, thereby supporting the implementation of predictive maintenance in smart manufacturing environments.

The integration of artificial intelligence (AI) in forensic investigation has significantly transformed the analysis and authentication of digital evidence. This paper explores the role of AI technologies, specifically machine learning and deep learning algorithms, in examining digital evidence from various sources, including computers, mobile devices, and network systems. We provide an in-depth analysis of current AI-based forensic tools, their efficiency in evidence authentication, and the challenges they face regarding legal admissibility. Our findings indicate that AI-powered forensic systems can detect digital evidence tampering with 94.7% accuracy, drastically reducing analysis time from weeks to hours. However, challenges remain, particularly in areas such as algorithmic transparency, bias prevention, and ensuring the integrity of the chain of custody. This research offers a framework for incorporating AI in forensic laboratories, while also addressing crucial legal and ethical concerns to ensure the admissibility of AI-analyzed evidence in court. These considerations are essential for the widespread acceptance and use of AI in forensic investigations.

The interval between 2018 and 2025 represents a defining epoch in financial assurance, characterized by a systemic collision between traditional audit methodologies and the exponential sophistication of fraudulent actors. This research employs a comprehensive library research methodology, utilizing Systematic Literature Review (SLR) to evaluate the evolving landscape of audit and fraud. The study traces the theoretical migration from Cressey’s Fraud Triangle to multidimensional frameworks like the Fraud Pentagon, which emphasizes the roles of arrogance and competence. Through a forensic examination of catastrophic audit failures including Wirecard, FTX, and the emerging risks of crypto-assets, the research identifies recurring patterns of auditor failure in assessing operational risks and internal controls. Furthermore, the report analyzes the dual-edged impact of Artificial Intelligence (AI); while machine learning algorithms offer enhanced detection capabilities, the rise of Generative AI (GenAI) and deepfake technology has empowered perpetrators to execute sophisticated "synthetic reality" frauds. The study critically evaluates regulatory responses, particularly the revision of International Standard on Auditing (ISA) 240, which mandates a more proactive "fraud lens." The findings suggest that the auditing profession faces an existential crisis of relevance, necessitating a fundamental shift toward a forensic mindset supported by advanced technological integration.

The rapid growth of web technologies and online services has increased the exposure of web applications to cyber threats such as Cross-Site Scripting (XSS) and SQL Injection (SQLi). Conventional rule-based mechanisms, such as Web Application Firewalls (WAFs), often fail to detect emerging attack patterns. To address this, Machine Learning (ML) and Deep Learning (DL) have emerged as adaptive approaches for enhancing web attack detection. This study performs a Systematic Literature Review (SLR) following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) 2020 guidelines to analyze recent ML/DL-based detection methods. Of the 263 retrieved studies, 15 met the inclusion criteria for detailed review. The findings reveal that Random Forest (RF), Support Vector Machine (SVM), Convolutional Neural Network (CNN), and Long Short-Term Memory (LSTM) are the most applied algorithms. At the same time, recent works emphasize Transformer-based and hybrid ML–DL models. These approaches achieved robust performance (accuracy 85–97%, F1-score >90%) but still face challenges in dataset representativeness, class imbalance, and computational cost. This review highlights future research directions in Explainable Artificial Intelligence (XAI), Federated Learning (FL), and adversarial robustness to develop more efficient and trustworthy web attack detection systems.

This study presents a Systematic Literature Review on Artificial Intelligence (AI) and Natural Language Processing (NLP) applications for customer support automation and digital service optimization. The review follows the PRISMA framework to ensure methodological rigor and transparency, focusing on literature published between 2020 and 2025 from the Scopus database. The findings reveal that AI-driven technologies, including Machine Learning, Deep Learning, and Large Language Models, have significantly improved efficiency, response time, and customer satisfaction in customer support and digital service. Common NLP applications include sentiment analysis, ticket classification, and automated response generation. Among these, hybrid and transformer-based models demonstrate superior accuracy and contextual understanding compared to traditional algorithms. However, several challenges persist, including data quality limitations, privacy and security concerns, algorithmic bias, and linguistic ambiguities such as sarcasm and negation. Moreover, issues related to trust and ethical adoption continue to influence user acceptance of AI systems. This review provides a comprehensive synthesis of current methodologies, trends, and research gaps, offering insights for future studies to develop explainable, secure, and human-centered AI systems that enhance the sustainability and transparency of digital customer support services.

This community service activity aims to increase educational technology literacy among Vocational High School (SMK) teachers by introducing the basic concept of Deep Learning and its application in the world of education. This training was motivated by the urgent need to equip educators with basic understanding and skills regarding artificial intelligence (AI), especially Deep Learning, to be able to keep up with rapid technological developments and relevant to vocational education. Through practice-based training using simple tools such as Teachable Machine, teachers are given hands-on experience in creating simple machine learning models that are applicable in the school environment. The results of the pre-test and post-test showed a significant increase in understanding in the participants. The group discussions also produced various ideas for the application of AI such as a face-based attendance system, student voice recognition, and recommendations for learning materials according to students' interests. Despite challenges such as limited infrastructure and teacher learning time, this activity proves that a practical and contextual training approach can increase teachers' motivation to integrate technology into learning. Similar training is highly recommended to be replicated in other schools to support equitable access to modern educational technology.

This study aims to deeply examine the role and impact of AI implementation in the B2B sales process, including implementation challenges. The method used is a qualitative approach with descriptive studies, through a literature review of scientific journals, industry reports, and relevant previous studies. The analysis results show that the application of AI in B2B sales not only improves the accuracy of marketing strategies and lead conversion, but also strengthens the concept of value co-creation through collaboration between salespeople and AI systems. Technologies such as machine learning, predictive analytics, and NLP-based chatbots have been proven to accelerate sales cycles, expand service reach, and increase productivity by up to 30%. However, implementation challenges remain, including limited digital infrastructure, a lack of competent human resources, and organizational resistance to technological transformation. Therefore, optimal AI integration requires institutional readiness, adaptive strategies, and continuous investment in technology and human resource development. These findings provide theoretical and practical contributions to the development of AI-based B2B sales strategies, particularly in the context of the digital industry in Indonesia. Furthermore, the application of AI in B2B sales also opens up new opportunities for service personalization. With the support of real-time data analysis, companies can better understand the specific preferences and needs of their business partners. This enables the development of more targeted communication strategies and the enhancement of long-term relationships with business customers. AI also plays a role in reducing human error through automated systems that can validate data, provide predictive recommendations, and support faster and more accurate strategic decision-making. Furthermore, the adoption of AI in B2B requires clear regulations and governance, particularly regarding ethical data use and information security. Companies must be able to balance the use of technology to increase efficiency with the protection of privacy and consumer rights.

Number recognition is a critical skill in early education, laying the foundation for digital literacy and mathematical understanding. However, traditional methods of teaching number recognition often lack the interactivity and engagement necessary for effective learning, particularly for young learners. This study proposes the development of a deep learning-based Android application aimed at enhancing the number recognition process by providing an interactive and visual learning experience. The application utilizes a Convolutional Neural Network (CNN), a type of deep learning model, to recognize handwritten numbers, offering users an innovative and engaging way to learn and practice number recognition.In the proposed application, users can draw numbers on their devices, and the system will immediately provide feedback regarding the accuracy of the drawn numbers. The CNN model will be trained on a comprehensive dataset of handwritten digits to ensure high accuracy in recognition. This real-time feedback loop is designed to help users learn the correct form of numbers while also introducing the foundational concepts of deep learning. The main objective of this application is to provide an accessible, interactive platform for learning number recognition, especially for novice learners who may be unfamiliar with basic concepts in machine learning and digital literacy. By integrating deep learning technology, the application not only supports the learning of number recognition but also serves as an introduction to artificial intelligence (AI) concepts in a practical, easy-to-understand format. Furthermore, the application is designed to be user-friendly, ensuring that it is suitable for a wide range of learners, including children and beginners. The application aims to combine the fundamental principles of deep learning with a practical, hands-on learning experience, fostering a deeper understanding of both number concepts and the potential of AI in everyday life.

Pemrosesan dokumen digital yang semakin kompleks mendorong pemanfaatan kecerdasan buatan Artificial Intelligence (AI) untuk meningkatkan akurasi dan efisiensi dalam sistem verifikasi dokumen. Penelitian ini menyajikan sebuah tinjauan literatur sistematis untuk mengkaji berbagai metode berbasis AI yang digunakan dalam inspeksi dan validasi dokumen secara otomatis. Sebanyak 42 artikel ilmiah yang diterbitkan antara tahun 2020 hingga 2025 dianalisis untuk mengidentifikasi pendekatan AI yang paling dominan, tantangan utama implementasi, serta kelebihan dan keterbatasan dari masing-masing metode. Hasil kajian menunjukkan bahwa natural language processing (NLP) merupakan teknik yang paling banyak digunakan, diikuti oleh machine learning (ML) dan deep learning (DL). Ketiga pendekatan ini menunjukkan efektivitas dalam mengurangi beban kerja manual, mempercepat waktu pemrosesan, serta memiliki fleksibilitas untuk diterapkan pada berbagai jenis dokumen, seperti dokumen keuangan, kontrak hukum, dokumen pendidikan, dan catatan medis. Meskipun demikian, penerapan metode AI dalam verifikasi dokumen masih menghadapi berbagai tantangan, termasuk format data yang tidak seragam, kemampuan generalisasi model yang terbatas, kebutuhan komputasi yang tinggi, dan kesulitan dalam menafsirkan hasil model. Tinjauan ini memberikan pemahaman yang lebih mendalam mengenai tren terkini dalam verifikasi dokumen berbasis AI dan menawarkan wawasan praktis untuk merancang sistem yang andal dan dapat diskalakan. Diharapkan, hasil dari studi ini dapat menjadi landasan bagi penelitian lanjutan dan penerapan teknologi analisis dokumen cerdas di berbagai sektor seperti keuangan, pendidikan, kesehatan, dan administrasi hukum.

Learners are continually faced with choosing appropriate courses or making career choices due to increased educational opportunities. The emergence of machine learning-based course and career recommender systems has the potential to address this issue, offering personalized course recommendations tailored to individual learning pathways, preferences, and learning history. The optimization and feature engineering techniques and practical deployment environments have not been collectively examined in the previous research, despite the significant advancements in this area of research. Furthermore, previous research has rarely synthesized how these technical components help students choose appropriate courses and careers. This systematic review was carried out to investigate the current state of machine learning-based course and career recommender systems, focusing on key elements, such as primary data sources, feature engineering methods, algorithms, optimization techniques, evaluation metrics, and the environments where the existing course recommendation models are deployed. The PRISMA method for conducting a systematic review was used to choose studies that met the requirements for inclusion and exclusion. The study findings show significant reliance on interpretable and traditional machine learning algorithms, such as K-Nearest Neighbor and Random Forest, to develop recommender models. Feature engineering remains basic, as most studies rely on normalization, while optimization processes are often underreported. Also, evaluation metrics varied widely, impeding comparability, while most of the recommender models are deployed in an e-learning environment, leaving the traditional learning environment underrepresented. Furthermore, the study findings identified issues including data sparsity and diversity, data security and privacy, and changes in learner preferences that may have an impact on the performance of recommender systems while recommending further studies to make use of standardized optimization methods, and automated domain-informed feature engineering frameworks, benchmark and annotated datasets in developing models the gives priority to learners’ success and educational relevance.

The advancement of information and communication technology in the era of the Industrial Revolution 4.0 has given rise to various digital innovations, one of which is deepfake technology that utilizes artificial intelligence and machine learning to manipulate audio-visual content convincingly. Although it has positive potentials in entertainment and education, the misuse of deepfake on social media has caused various legal and ethical issues, such as the spread of hoaxes, defamation, privacy violations, and non-consensual pornography. This study aims to analyze the use of deepfake from the perspective of Indonesian law, particularly through Law Number 11 of 2008 on Electronic Information and Transactions (ITE Law) and its amendments. Using a qualitative descriptive approach and literature study methods, this research examines the technical aspects of deepfake development, the relevance of ITE Law articles in regulating manipulative content, and the challenges of law enforcement amid low digital literacy in society. The findings show that although there are no explicit provisions concerning deepfake in the ITE Law, several articles can serve as a legal basis to prosecute offenders, albeit with interpretative and technical implementation challenges. Therefore, regulatory updates and improvements in digital literacy are necessary to prevent and effectively handle the misuse of deepfake technology.

Artificial Intelligence (AI) has become an essential tool in the world of management for decision-making. This article examines the ways in which AI can be used to improve the quality and speed of decision-making, and how AI can improve the operational efficiency of companies. In addition, this article also examines the challenges and opportunities that companies face in adopting AI.In the rapidly evolving digital era, AI has become an essential component of modern business strategies. Today's managers are often faced with the challenge of analyzing very large and complex volumes of data. To make good and timely decisions, AI offers a potential solution with fast and precise data analysis capabilities.The use of AI in decision-making involves machine learning algorithms and models to efficiently process and analyze large amounts of data. This helps managers gain deeper and more accurate insights, enabling more effective decision-making.

This study explores the integration of Artificial Intelligence (AI) with thermal optimization in Waste-to-Energy (WtE) systems to enhance both energy recovery and emission control. Introduction: The growing need for sustainable urban waste management has highlighted the importance of optimizing WtE systems. AI technologies, including machine learning and deep learning, have shown potential in improving the efficiency of WtE processes, especially in reducing emissions and enhancing energy recovery. Literature Review: Previous research indicates that AI has been successfully applied to various WtE technologies such as pyrolysis, gasification, and incineration, yet the integration of AI specifically for thermal optimization remains underexplored. Most studies focus on predictive models for emission reduction rather than real time thermal optimization. Materials and Method: The study proposes the development of an AI-driven framework that integrates real time data collection from IoT sensors, predictive modeling, and real time control algorithms. The system optimizes key parameters such as combustion temperature and fuel flow to enhance energy recovery and minimize emissions. The method includes data collection from operational WtE plants, followed by model development using machine learning algorithms. Results and Discussion: Initial simulations and pilot testing showed significant improvements in energy efficiency and emission reduction. AI-driven systems outperformed conventional WtE systems by optimizing operational parameters in real time. The study identifies gaps in AI integration for thermal optimization and suggests future research directions, including the integration of AI with smart grids and carbon credit systems for more sustainable WtE operations.