Author

Pandu Wicaksono

View on Semantic Scholar

2 papers indexed here

We haven’t gathered this author’s papers yet. Follow them and we’ll fetch their work.

Not the right person? Other researchers publish under this name.

Conference Jul 2026

IoT-Based Smart Irrigation System Using DHT-11 and Soil Moisture Sensors with Real-Time Monitoring and Automated Water Pump Control

Water scarcity and inefficient irrigation management present ongoing challenges for sustainable agricultural practice. This paper presents the design and implementation of an Internet of Things (IoT)-based smart irrigation system integrating DHT11 temperature-humidity sensors, capacitive soil moisture sensors, an ESP32 microcontroller, and automated water pump control with real-time remote monitoring capability. The system employs the Message Queuing Telemetry Transport (MQTT) protocol for secure, lightweight communication among the ESP32 firmware layer, a Golang backend server, and a ReactJS-based web dashboard, enabling remote supervision and actuation via standard web browsers. A threshold-based hysteresis control algorithm governs pump activation, triggering irrigation when soil moisture analog readings exceed 3000 (indicative of dry soil) and halting operation when readings fall below 2000 (indicative of adequately moist soil), effectively preventing rapid pump cycling. A fourteen-day evaluation demonstrated 99.29 percent MQTT message delivery reliability, a mean end-to-end latency of 555 ms, and 100 percent successful irrigation activations across eight distinct irrigation cycles with zero false-positive triggers. Sensor validation revealed a mean temperature deviation of 1.3 degrees Celsius, a humidity deviation of 3.2 percent relative humidity (RH), and a soil moisture correlation coefficient (R2) of 0.94 against gravimetric reference measurements. The system was assembled at a total hardware expenditure of under 30 United States Dollars (USD), positioning it as an accessible solution for small-scale and urban agricultural settings. Distinguishing features include integrated automated and manual control, Transport Layer Security (TLS)-secured MQTT communication, real-time Telegram-based notifications, and PostgreSQL-backed time-series data persistence.

Sheraldo Halim, D. N. Utama, Pandu Wicaksono · International Conference on... · 0 citations

Conference Jul 2026

Multi-Objective Optimization for Credit Card Fraud Classification: Achieving a Balance between Accuracy and Carbon Footprint within a Green AI Framework

As financial fraud becomes increasingly sophisticated, the demand for complex machine learning models has surged, inadvertently leading to a significant increase in computational energy consumption. This study addresses the critical trade-off between predictive accuracy and environmental sustainability within a Green AI framework. We propose a multi-objective optimization approach to evaluate Logistic Regression, Random Forest, and XGBoost on a highly imbalanced credit card fraud dataset. Experimental results reveal a non-linear “Carbon Cost of Complexity,” where the transition from linear to tree-based architectures yields diminishing returns; a 3.4% improvement in detection accuracy requires a 163% increase in training carbon emissions. The Random Forest model $(\mathbf{n}=\mathbf{2 0 0}, \mathbf{d}=\mathbf{1 5})$ emerged as the Pareto Optimal solution, achieving a superior F1-Score of 0.7512 and an AUPRC of 0.8031. Although XGBoost proved to be 62% more energy-efficient during the training phase, Random Forest demonstrated a distinct advantage in inference latency, achieving a throughput of 664,576 Transactions Per Second (TPS). We conclude that while Random Forest incurs a higher carbon footprint $\left(\mathbf{7. 1 5} \times \mathbf{1 0}^{-\mathbf{6}} \mathbf{~ k g C O} \mathbf{2 e q}\right.$ per cycle), this expenditure is justified by its robustness in preventing financial loss and its capability for real-time processing in high-stakes environments.

Ebenhaezer George Renaldi Muljadi, Albert Justin, F. Ardan et al. · 2026 11th International Conf... · 0 citations