Proceedings
Authors
| Filter results4 paper(s) found. |
|---|
1. Optimizing Frost Prediction with a Multi-Window CNN–XGBoost Soft-Voting EnsembleRecent global climate change has increased the frequency of late-spring frost events, causing more severe and widespread damage to orchard growers. Frost formation occurs due to rapid temperature drops over short periods combined with overnight air stagnation; thus, effective prediction requires analyzing patterns across multiple time scales. We introduce a hybrid frost-forecasting framework that combines a multi-window 1-D convolutional neural network (CNN), utilizing 6-, 12-, and 24-hour... D. Kim |
2. Deep Learning-Based Vocal Signature Analysis for Rumination Belching IdentificationAnimal vocalizations provide important information about various behaviors, including courtship, parental care, foraging, and vigilance, as well as physiological states such as estrus, parturition, stress, and disease. In ruminants, eructation-related sounds are primarily produced when methane, generated by microbial fermentation of plant fibers in the rumen, is released orally. The acoustic characteristics of these sounds—such as frequency, intensity, and duration—are closely associated... C. Wu |
3. Development of Methane Monitoring System for Dairy Cow EructationMethane emissions from dairy cow eructation constituted a significant greenhouse gas source in livestock production and were closely linked to rumination activity. Accurate, continuous, and non-invasive monitoring of eructation events was proven essential for assessing animal health, optimizing feed strategies, and reducing environmental impact. Conventional approaches— including manual observation, jaw-movement sensors, and respiration chambers—remained costly, labor-intensive, and... C. Wu |
4. Performance Study of Triboelectric Nanogenerator with Laser-induced Graphene ElectrodesAs wearable electronics increasingly demand a continuous power supply, conventional batteries—requiring frequent recharging or replacement—pose both user inconvenience and environmental risks. This study develops a wristwatch‐ shaped triboelectric nanogenerator that employs solid‐ state semiconductor laser‐ induced graphene electrodes patterned directly onto a polyimide (PI) film and utilizes an independent sliding interface to harvest 1 to 3 Hz low‐frequency... C. Wu |