Guanjin Wang

Artificial Intelligence (AI) has emerged as a transformative tool in precision agriculture, facilitating datadriven decision-making and crop improvement. In the context of agricultural crops, data from multiple modalities, such as phenotypic traits, genomic markers, and environmental conditions, offer diverse insights into crop development and yield potential. However, single-modality approaches may fail to capture the complex interplay between genomics, environment, and other factors affecting crop traits. To address this challenge, this study investigates the integration of multimodal data to improve genotype-to-phenotype predictions. Focusing on barley (Hordeum vulgare L.), a globally and nationally important cereal crop, we propose a new barley-Multimodal Deep Learning (barley-MMDL) model to predict flowering time and grain yield using heterogeneous multimodal datasets. The model combines Convolutional Neural Networks (CNNs) to process high-dimensional genomic markers with Long Short-Term Memory (LSTM) networks to capture temporal patterns in environmental data. These modality-specific latent features are then fused to enable joint optimization of feature extraction and prediction in an end-to-end manner. The proposed barleyMMDL model achieved the lowest RMSE values of 8.84 for flowering time and 778.50 for grain yield, outperforming baseline unimodal and multimodal models. These results demonstrate the improved predictive capability of barleyMMDL and underscore the potential of multimodal data integration to advance prediction capability in precision agriculture and contribute to sustainable agricultural practices.

Early detection of individuals with a high risk of dementia is crucial for prompt intervention and clinical care. This study aims to identify high-risk groups for developing dementia by predicting the outcome of the Mini-Mental State Examination (MMSE), using historical data collected from community-based primary care services. To mitigate the effect of inter-individual variability and enhance the accuracy of the prediction, we implemented a multi-stage method powered by supervised and unsupervised machine learning methods. Firstly, we preprocessed the original data by imputing missing values and using a wrapper-based feature selection algorithm to pick significant features, resulting in ten variables out of 567 being selected for further modeling. Secondly, we optimized hierarchical clustering to partition the unlabeled data into groups by their similarities, and then applied supervised machine learning models to build subgroup-specific prediction models for the identified groups. The results demonstrate that the proposed subgroup-specific prediction models generated from the multi-stage method achieved satisfactory performance in predicting the outcome classes of dementia risk. This study highlights the potential of incorporating unsupervised and supervised learning models to predict high-risk cases of dementia early and facilitate better clinical decision-making.

Aboriginal perinatal mothers are at a significant risk of experiencing mental health problems, which can have profound negative impacts, despite their overall resilience. This work aimed to build prediction models for identifying high psychological distress among Aboriginal perinatal mothers by coupling machine learning models with an innovative and culturally-safe screening tool. The original dataset of 179 Aboriginal mothers with 337 variables was obtained from twelve perinatal health settings at Perth metropolitan and regional centers in Western Australia between July and September 2022, using a specifically designed web-based rubric for the perinatal mental health assessment. After data preprocessing and feature selection, 23 variables related to emotional manifestations, the problematic partner, worries about daily living, and the need for follow-up wraparound support were identified as significant predictors for the high risk of psychological distress measured by the Kessler 5 plus adaptation. The selected predictors were used to train prediction models, and most of the chosen machine learning models achieved satisfactory results, with Random Forest and Support Vector Machine yielding the highest AUC of over 0.95, accuracy over 0.86, and F1 score above 0.87. This study demonstrates the potential of using machine learning-based models in clinical decision-making to facilitate healthcare and social and emotional well-being for Aboriginal families.