Abnormal Operation Detection of Automated Orchard Irrigation System Actuators by Power Consumption Level

Sensors, Journal Year: 2025, Volume and Issue: 25(2), P. 331 - 331

Published: Jan. 8, 2025

Information and communication technology (ICT) components, especially actuators in automated irrigation systems, are essential for managing precise optimal soil moisture, enhancing orchard growth yield. However, actuator malfunctions can lead to inefficient irrigation, resulting water imbalances that impact crop health reduce productivity. The objective of this study was develop a signal processing technique detect potential based on the power consumption level operating status an system. A demonstration with four apple trees set up 3 m × test bench inside greenhouse, divided into two sections enable independent schedules management. system consisted single pump solenoid valves controlled by Python-programmed microcontroller. microcontroller managed cycling 'On' 'Off' states every 60 s while storing transmitting sensor data smartphone application remote monitoring. Commercial current sensors measured consumption, enabling identification normal abnormal operations applying threshold values distinguish activation deactivation states. Analysis control commands, effectively detected operations, confirming reliability identifying valve failures. For second channel 2, 333 actual instances operation operation, model accurately 316 58 instances. proposed method achieved mean average precision 99.9% detecting 1 99.7% 2. approach detects malfunctions, demonstrating enhance management Future research will integrate advanced machine learning improve fault detection accuracy evaluate scalability adaptability larger orchards diverse agricultural applications.

Language: Английский

Traumatic Brain Injury Structure Detection Using Advanced Wavelet Transformation Fusion Algorithm with Proposed CNN-ViT

Information, Journal Year: 2024, Volume and Issue: 15(10), P. 612 - 612

Published: Oct. 6, 2024

Detecting Traumatic Brain Injuries (TBI) through imaging remains challenging due to limited sensitivity in current methods. This study addresses the gap by proposing a novel approach integrating deep-learning algorithms and advanced image-fusion techniques enhance detection accuracy. The method combines contextual visual models effectively assess injury status. Using dataset of repeat mild TBI (mTBI) cases, we compared various algorithms: PCA (89.5%), SWT (89.69%), DCT (89.08%), HIS (83.3%), averaging (80.99%). Our proposed hybrid model achieved significantly higher accuracy 98.78%, demonstrating superior performance. Metrics including Dice coefficient (98%), (97%), specificity (98%) verified that strategy is efficient improving image quality feature extraction. Additional validations with “entropy”, “average pixel intensity”, “standard deviation”, “correlation coefficient”, “edge similarity measure” confirmed robustness fused images. CNN-ViT model, curvelet transform features, was trained validated on comprehensive 24 types brain injuries. overall 99.8%, precision, recall, F1-score 99.8%. PSNR” 39.0 dB, “SSIM” 0.99, MI 1.0. Cross-validation across five folds proved model’s “dependability” “generalizability”. In conclusion, this introduces promising for detection, leveraging techniques, enhancing medical diagnostic capabilities

Language: Английский