Hyeon-O Choe

Environmental monitoring in smart greenhouses depends on both the continuity of reported records and the plausibility of their sensor values. The literature distinguishes transport-level availability from data-level fault patterns such as spikes, drift, erratic variation, and stuck-at readings. This study develops an operational-condition-aware description of these anomaly patterns for an ESP32-based Wi-Fi/MQTT greenhouse sensing architecture. Four candidate data-pattern categories—Spike, Oscillation, Drift, and Dropout/Stale-Value—are described using explicit decision rules. Reliability Index (RI), Collapse Frequency (CF), and Collapse Severity Score (CSS) are introduced as descriptive metrics. The physical update period of the SCD30 CO₂ sensor (2 s) is distinguished from the ESP32 polling and MQTT publishing intervals (0.5, 1, and 5 s), avoiding the classification of routine repeated CO₂ publications as proven packet loss. An approximately one-month greenhouse monitoring campaign included nominal polling/publishing, RSSI, supply, and humidity configurations. Retained condition-level indices show greater candidate-anomaly burden in several stressed configurations. Historical auxiliary-log summaries record 132 matches among 165 evaluable selected events (80.0%), including 32 of 50 Oscillation candidates (64.0%). These ratios indicate concurrence under prespecified criteria, not independently established detection accuracy; 25 additional selected events were not evaluable. An integrated quantitative assessment reports within-study descriptive contrasts, explains nominal CO₂ value reuse arising from the SCD30’s 2 s update period, and separates metric identities from event-level confirmation. The revised stale-value screen has a physical timing rationale, but its change in historical Dropout totals has not been measured. Independent Drift confirmation and multi-factor interaction testing are not claimed. This evidence-bounded framework supports targeted greenhouse monitoring diagnostics and clearly identifies the measurements needed for reproducible validation.

Recently, high-frequency wireless sensing technologies have been widely adopted in smart greenhouse environments for real-time environmental monitoring and automated control. However, long-term sensor data reliability can degrade due to wireless communication instability, power fluctuation, and environmental variations under high-frequency sensing conditions. Existing studies have mainly focused on anomaly detection and abnormal data filtering, while reliability degradation under real operational conditions has received limited attention. In this study, abnormal sensor data fluctuation phenomena occurring in high-frequency wireless smart greenhouse environments were defined as Reliability Collapse. The proposed Reliability Collapse was classified into Spike Collapse, Oscillation Collapse, Drift Collapse, and Dropout Collapse. In addition, Collapse Frequency (CF), Reliability Index (RI), and Collapse Severity Score (CSS) were defined to quantitatively evaluate sensing reliability degradation. Experiments were conducted for approximately one month using MQTT-based ESP32 wireless sensor nodes under different operational conditions, including sampling interval variations, RSSI conditions, power stability, and high-humidity/condensation environments. Experimental results showed that shorter sampling intervals, degraded RSSI conditions, unstable power supply, and high-humidity environments significantly increased Reliability Collapse occurrence and reduced long-term sensing reliability. In particular, the 0.5 s sensing condition increased Spike Collapse and Oscillation Collapse occurrence, while weak RSSI conditions increased Dropout Collapse frequency. The results demonstrate that multiple operational conditions, including sampling interval, wireless communication quality, power stability, and environmental conditions, are associated with degradation in long-term sensing reliability.

Vertical farming requires precise environmental control, yet long-term multivariable analyses linking environmental dynamics and crop growth remain limited. This study analyzes a two-year operational dataset from a commercial vertical farm in South Korea to evaluate the suitability of advanced artificial intelligence models for harvest yield prediction. Conventional machine learning models and recent deep learning architectures were systematically benchmarked under identical conditions. Among them, the patch-based Transformer model achieved the highest predictive accuracy (R² = 0.942; RMSE = 5.81 g per plant). The variable-importance analysis revealed that daily light integral and CO₂ concentration were the dominant drivers of harvest yield variability, jointly accounting for more than 76% of total contribution. These findings demonstrate the effectiveness of Transformer-based architectures for long-term multivariate time series modeling and provide actionable insights for the data-driven optimization of vertical farming systems.

To address the limitations of sensor deployment and high maintenance costs in smart swine barns, this study proposes a digital twin (DT)-based virtual sensor prediction and visualization method. Spatial constraints and harsh barn environments often cause sensor blackout zones, hindering precise environmental monitoring. To overcome these challenges, a virtual sensor was defined at the central position between Zone 1 and Zone 2, and its data were generated using a hybrid model that combines inverse distance weighting (IDW)-based spatial interpolation with long short-term memory (LSTM)-based time-series prediction. The proposed method was evaluated using 34,992 datasets collected from January to August 2025. Performance analysis demonstrated that the hybrid model achieved high prediction accuracy, particularly for variables with strong spatial heterogeneity, such as carbon dioxide (CO₂) and ammonia (NH₃), with overall coefficients of determination (R²) exceeding 0.95. Furthermore, a Web-based graphics library (WebGL) digital twin visualization environment was developed to intuitively observe spatiotemporal changes in sensor data. The system integrates sensor placement, risk-level assessment, and time-series graphs, thereby supporting users in real-time environmental monitoring and decision-making. This approach improves the precision and reliability of smart barn management and contributes to the stabilization of farm income.

In Korea, agricultural policy increasingly promotes high-efficiency digital agriculture; however, insufficient sensor reliability and data accuracy continue to limit the practical adoption of smart farm technologies. To address these limitations, this study aims to develop and field-validate an AI-based Prognostics and Health Management (PHM) framework for anomaly detection and remaining useful life (RUL) estimation of sensors and actuators in commercial smart farms. To collect smart farm data, we developed a switch voltage and current data acquisition system and selected problematic switches and environmental sensors in operating greenhouses as PHM targets. Using PHM techniques, we implemented mathematical and artificial intelligence (AI)-based anomaly detection and failure prediction algorithms. In experiments, sensor behavior was predicted with mathematical and AI models, achieving over 90% predictive accuracy compared with observations. Based on these predictions, thresholds were estimated and the remaining useful life (RUL) of sensors was predicted up to 80 h in advance. For switches, vibration, noise, and voltage data were collected to detect anomalies. Actuator anomaly detection employed thresholds derived from statistical indicators and machine learning; a hybrid approach combining interquartile range, Z-score, and Isolation Forest leveraged the strengths of both paradigms to provide robust and adaptive detection. Deviation features were then combined with environmental factors to construct an RUL model, and the remaining life of devices in operation was estimated using a k-nearest neighbors approach. In field validation, the lifetime of four switches was predicted, yielding a mean RUL of 1655 d. Finally, we implemented a web-based platform that enables farms to monitor and manage equipment health. Compared with prior studies, the key novelty of this work lies in integrating sensor-and-actuator PHM, providing real-field validation in operating greenhouses, and delivering an operational web platform that supports practical smart farm maintenance. By integrating these methods, the study aims to improve system efficiency, reduce energy consumption, and extend the operating life of smart farm components. We anticipate substantial benefits as the proposed approach is applied to smart farm equipment, enabling more reliable data acquisition and stable maintenance in practice.

Despite the recent increase in smart farming practices, system uncertainty and difficulties associated with maintaining farming sites hinder their widespread adoption. Agricultural production systems are extremely sensitive to operational downtime caused by malfunctions because it can damage crops. To resolve this problem, the types of abnormal data, the present error determination techniques for each data type, and the accuracy of anomaly data determination based on spatial understanding of the sensed values are classified in this paper. We design and implement a system to detect and predict abnormal data using a recurrent neural network algorithm and diagnose malfunctions using an ontological technique. The proposed system comprises the cloud in charge of the IoT equipment installed in the farm testbed, communication and control, system management, and a common framework based on machine learning and deep learning for fault diagnosis. It exhibits excellent prediction performance, with a root mean square error of 0.073 for the long short-term memory model. Considering the increasing number of agricultural production facilities in recent years, the results of this study are expected to prevent damage to farms due to downtime caused by mistakes, faults, and aging.