Jurnal Teknik Informatika C.I.T Medicom

A Unified Artificial Intelligence Driven Data Governance Framework for Decision Intelligence in Smart Digital Ecosystems

2026-04-14T09:42:07+00:00

This research proposes a Unified Artificial Intelligence–Driven Data Governance Framework to enhance decision intelligence in smart digital ecosystems. The rapid growth of technologies such as the Internet of Things (IoT), smart cities, and digital platforms has led to an exponential increase in data volume and complexity, creating challenges related to data silos, poor data quality, lack of governance standards, and ineffective decision-making. While artificial intelligence (AI) has been widely adopted to address analytical needs, existing approaches often fail to integrate data governance with AI-driven decision processes, resulting in unreliable and less transparent outcomes. To address this gap, this study develops a multi-layered framework that integrates data governance, AI, and decision intelligence into a unified architecture. The proposed framework consists of a data layer, governance layer, AI layer, decision layer, and application layer, supported by key components such as data integration modules, data quality engines, policy enforcement mechanisms, AI model management, and decision support systems. A prototype-based methodology is employed to evaluate the framework using machine learning models and optimization techniques within simulated smart ecosystem environments. The results demonstrate that the proposed framework significantly improves decision accuracy, data quality, and system reliability while maintaining acceptable processing time and scalability. Compared to traditional systems and non-governed AI models, the framework provides enhanced transparency, accountability, and compliance. However, challenges related to computational cost, system complexity, scalability, and ethical considerations such as bias and fairness remain. This research contributes to the field by presenting a comprehensive and scalable solution that bridges the gap between AI and data governance.

Enhancing Product Recommendation Systems Using Hybrid Filtering: A Comparative Analysis of Collaborative and Content-Based Approaches

2026-04-10T08:29:47+00:00

The rapid growth of e-commerce platforms has led to an overwhelming number of product choices, creating challenges for users in identifying items that match their preferences. Recommendation systems have become essential tools to address this issue; however, traditional approaches such as Collaborative Filtering and Content-Based Filtering suffer from limitations including data sparsity, cold-start problems, and limited recommendation diversity. This study proposes a Hybrid Filtering-based product recommendation system that integrates both Collaborative Filtering and Content-Based Filtering techniques to overcome these challenges. The proposed model utilizes user-item interaction data and product metadata to generate personalized recommendations through a hybrid approach, combining algorithms such as K-Nearest Neighbors (KNN), Matrix Factorization, Term Frequency–Inverse Document Frequency (TF-IDF), and cosine similarity. The system is evaluated using multiple performance metrics, including accuracy (precision, recall, and F1-score), ranking quality (Mean Average Precision and Normalized Discounted Cumulative Gain), and prediction error (Root Mean Square Error and Mean Absolute Error). The results demonstrate that the Hybrid Filtering model outperforms individual methods in all evaluation aspects. It achieves higher accuracy, better ranking performance, lower prediction error, and greater diversity in recommendations. These findings indicate that the hybrid approach effectively addresses the limitations of traditional recommendation systems and provides more reliable and personalized recommendations. In conclusion, this research confirms that Hybrid Filtering is a robust and efficient method for improving the performance of product recommendation systems. The proposed model has significant practical implications for e-commerce platforms, as it enhances user experience, increases engagement, and supports better decision-making processes.

Wearable Device-Based Health Monitoring System with AI-Driven Predictive Analytics for Real-Time and Preventive Healthcare

2026-04-15T06:25:16+00:00

This study proposes a wearable device-based health monitoring system integrated with artificial intelligence (AI) predictive analytics to enable continuous, real-time, and proactive healthcare management. The system utilizes wearable sensors to collect physiological and activity data, including heart rate, blood oxygen saturation (SpO?), body temperature, and movement patterns. These data are transmitted through IoT-based communication to a cloud platform, where they undergo preprocessing, feature extraction, and analysis using machine learning and deep learning models. The proposed approach incorporates algorithms such as Random Forest, Support Vector Machine (SVM), and Long Short-Term Memory (LSTM) networks to perform disease prediction, anomaly detection, and risk scoring. Experimental results demonstrate that the models achieve high performance across multiple evaluation metrics, including accuracy, precision, recall, F1-score, and ROC-AUC, with LSTM showing superior performance in handling time-series data. The system effectively supports real-time monitoring, enabling early detection of potential health risks and providing timely alerts to users and healthcare providers. Compared to existing systems, the proposed framework offers enhanced predictive capabilities, improved responsiveness, and better integration of wearable technology with AI-driven analytics. The findings highlight the significant potential of combining wearable devices and AI in advancing healthcare innovation, particularly in remote patient monitoring, telemedicine, and preventive medicine. Despite challenges related to data privacy, device limitations, and computational requirements, this research demonstrates a scalable and intelligent solution for modern healthcare systems, emphasizing the critical role of predictive analytics in the future of preventive healthcare.

Machine Learning-Based Malware Detection Using Behavioral Pattern Analysis for Enhanced Cybersecurity

2026-04-11T08:36:12+00:00

The rapid growth and increasing sophistication of malware pose significant challenges to traditional cybersecurity systems, particularly those relying on signature-based detection methods. These conventional approaches are often ineffective against new and evolving threats, such as polymorphic and zero-day malware. To address these limitations, this study proposes a machine learning-based malware detection framework that leverages behavioral pattern analysis to improve detection accuracy and adaptability. A comprehensive methodology is implemented, involving dataset collection from publicly available sources, feature extraction using frequency-based, sequence-based, and graph-based techniques, and data preprocessing to ensure quality and balance. Multiple machine learning models, including Random Forest, XGBoost, and Long Short-Term Memory (LSTM), are employed to capture both statistical and temporal patterns in the data. The models are evaluated using standard performance metrics such as accuracy, precision, recall, F1-score, and ROC-AUC. The experimental results demonstrate that the proposed model achieves high classification performance and effectively distinguishes between malware and benign software. Behavioral features, particularly sequence-based representations, are found to significantly enhance detection capability. Furthermore, the model shows strong generalization when tested on unseen data, indicating its robustness against new malware variants. Compared to traditional signature-based methods, the proposed approach provides improved detection of zero-day attacks and reduces false positives. This study contributes to the advancement of cybersecurity by presenting a scalable and adaptive malware detection framework that integrates machine learning with behavioral analysis.

A Unified Artificial Intelligence and Stochastic Optimization Framework for Decision-Making in Highly Complex Systems

2026-04-13T12:05:42+00:00

Decision-making in highly complex systems is increasingly challenged by uncertainty, dynamic environments, and the availability of large-scale, high-dimensional data. Traditional optimization methods often lack adaptability, while standalone Artificial Intelligence models struggle to explicitly handle uncertainty in a principled manner. To address these limitations, this research proposes a unified framework that integrates Artificial Intelligence with Stochastic Optimization for enhanced decision-making in complex and uncertain environments. The proposed framework combines data-driven learning and probabilistic optimization within a closed-loop architecture consisting of data input, AI-based prediction, stochastic decision-making, and continuous feedback. Advanced AI models, including deep learning and reinforcement learning, are employed to extract patterns and generate predictive insights from real-time and historical data. These outputs are then incorporated into stochastic optimization models, which evaluate decisions under uncertainty using probabilistic constraints and scenario-based analysis. The framework is further strengthened by an adaptive feedback mechanism that continuously updates both learning and optimization components. Experimental evaluation demonstrates that the proposed approach outperforms traditional optimization and pure AI models in terms of decision accuracy, robustness under uncertainty, and adaptability to dynamic environments. The framework also shows improved stability and computational efficiency when applied to large-scale systems. Practical applications in domains such as finance, logistics, and smart city management highlight its real-world relevance. Overall, this research contributes to decision science by bridging the gap between learning and uncertainty modeling, providing a scalable and integrated solution for intelligent decision-making in highly complex systems.