Journal of Electronics Technology Exploration

Detection of Breast Cancer Patient Mortality Status Using Machine Learning with SMOTE-Based Class Imbalance Treatment

2026-05-11T01:53:40+00:00

Breast cancer is a disease with a high mortality rate, making early detection of patients at risk of death crucial for supporting medical decision-making. This study aims to develop a model for detecting patients at risk of death by comparing several machine learning algorithms. The research process included data collection, exploratory data analysis, data preprocessing, feature engineering, oversampling, modeling, and model evaluation. Data balancing was performed using SMOTE, and model optimization was conducted through hyperparameter tuning using GridSearchCV. The results show that Random Forest combined with GridSearchCV delivers the best performance in prediction, with an accuracy of 0.7491, precision of 0.2953, recall of 0.4634, an F1-score of 0.3608, and an ROC-AUC of 0.7030. This study demonstrates that the combination of Random Forest, SMOTE, and GridSearchCV is capable of optimizing the performance of the prediction model.

Classification of Pancreatic Cancer Diagnosis with CatBoost Using Urine Biomarker Combination

2026-01-24T06:31:34+00:00

Uncontrolled cell growth in the pancreatic gland, is one of the most aggressive types of cancer with a high mortality rate, called pancreatic cancer. This research focuses on improving early diagnosis methods for pancreatic cancer by using CatBoost. Urine biomarker datasets were collected and subjected to pre-processing, including label coding, standardized scaling, and balancing via the Synthetic Minority Oversampling Technique (SMOTE). The CatBoost model achieved an accuracy of 98.89%, specificity of 99.35%, sensitivity of 98.71%, and Area Under the Curve (AUC) of 0.9951. These results show that the CatBoost model significantly outperforms the diagnosis models in previous studies, overcoming the challenges of early detection and classification of pancreatic cancer. This study shows that CatBoost is effective for diagnosing pancreatic cancer and suggests that future research explore other models on larger and more diverse datasets.

Strategic Evolution Of Digital Transformation And Information Technology Governance: A Systematic Literature Review

2026-06-06T08:30:44+00:00

Digital transformation and information technology (IT) strategy have become critical pillars of contemporary organizational management. This article presents a systematic literature review of 80 articles published between 2020 and 2025 in reputable international journals indexed in Scopus and/or Web of Science. The review examines digital transformation and IT strategy within business and organizational management using the PRISMA protocol and a structured thematic synthesis approach. The analysis covers digital transformation strategy, IT governance and strategic alignment, cloud computing and IT infrastructure, big data analytics and business intelligence, artificial intelligence, digital leadership and change management, cybersecurity, e-business and digital innovation, and enterprise resource planning and system integration. A systematic coding process was used to extract and synthesize bibliographic information, research methods, organizational contexts, key constructs, and major findings. The review shows that digital transformation is a multidimensional process of organizational change that extends beyond technology adoption and depends on the interaction of strategy, leadership, culture, governance, and the broader business ecosystem. It also highlights research gaps concerning developing-country contexts, integration across research themes, and sustainability. These findings provide an integrated overview of the field and inform a future research agenda for scholars and practitioners.

Novelty Half-Bridge LLC Resonant Converter with Magnetizing Inductance and Hybrid Rectifier

2026-05-04T02:58:33+00:00

Half-Bridge LLC Resonant converters are widely used in high-power supply applications due to their high efficiency and ability to operate at high frequencies. However, under hold-up conditions or during large fluctuations in input voltage, conventional topologies often experience reduced output stability and increased losses. Therefore, a method that can maintain efficiency and output voltage stability without excessively broadening the switching frequency range is required. To address this, this study proposes a Novelty Half-Bridge LLC Resonant Converter with Magnetizing Inductor and Hybrid Rectifier (NHB-LLCRC-MIHR), incorporating a magnetizing inductor (Lm) in the primary path and a MOSFET-based hybrid rectifier on the secondary side. The research methodology was conducted using MATLAB/Simulink simulation, focusing on five main areas, including optimal switching frequency conditions, operating thresholds, DC conversion ratio (Vo/Vs), comparison of output voltage with conventional topologies, and analysis of output voltage ripple. Simulation results demonstrate that NHB-LLCRC-MIHR can maintain a more stable output voltage, lower ripple, and increase efficiency compared to conventional converters. Thus, this topology shows significant potential for industrial applications that demand high efficiency and optimal power stability.

A Comparative Review of Performance and Energy Efficiency in ARM and RISC-V SoCs

2026-06-09T13:27:22+00:00

The demand for energy-efficient computing systems is growing as workloads on embedded devices, edge computing, and scientific computing continue to expand. In this context, a comparison between the ARM and RISC-V architectures is important because both are widely used in System-on-Chip (SoC) designs but have different performance and energy efficiency characteristics. This article presents a comparative review of various benchmark studies on the Odroid XU4, Rock960, and Nezha D1 platforms using the NAS Benchmark, TensorFlow Lite Benchmark, and OpenFOAM. The summarized results show that RISC-V implementations generally have lower average power consumption but do not always yield a better performance-per-watt ratio. For some workloads, ARM platforms still demonstrate superior throughput and energy efficiency, while RISC-V performance is heavily influenced by the number of cores, accelerator support, and the maturity of the software ecosystem. Therefore, ARM remains more competitive for high-performance workloads, whereas RISC-V remains promising for power-efficient applications and continues to evolve.