Recent research:
Across the published works, the researcher applies artificial intelligence, machine learning, and data science to health, agriculture, energy, and environmental monitoring, integrating advanced analytics with practical applications. The work on Speech Emotion Recognition using a deep convolutional network (DSCNN) demonstrates how deep learning can extract salient features from speech spectrograms to classify emotions, with potential implications for diagnosing and treating depression and anxiety. In agriculture and smart farming, IoT- and ML-driven models monitor soil, weather, irrigation, pests, and diseases to improve yield and farm management. Healthcare-focused studies benchmark activation functions for breast cancer detection, identifying ReLU as highly effective and highlighting the role of ML function selection in clinical accuracy. Power systems and irrigation infrastructure are analyzed through simulation and voltage-regulation optimization to ensure reliable operation of pumping and distribution networks. Environmental monitoring work proposes IoT-enabled real-time data capture and ML-based water quality forecasting for the Guayas River, stressing long-term decision benefits despite upfront costs. A framework using fuzzy maps and multicriteria methods guides the selection of ML algorithms for breast cancer recognition, underscoring the importance of choosing algorithms aligned with outcomes and tested performance. Collectively, the research highlights a methodological emphasis on model benchmarking, system optimization, and decision-support in health, agriculture, and environmental domains, with a clear impact on improving diagnostic accuracy, operational efficiency, and data-driven policy guidance.