Xishuang Dong

Vegetation health prediction is one of the most important research questions in precision agriculture. The Normalized Difference Vegetation Index (NDVI) is one of the most widely adopted indicators of crop vigor and stress. Traditional NDVI estimation relies on multispectral or hyperspectral imaging, which is expensive and inaccessible for small-scale farming. Recent advances in deep learning enable the prediction of NDVI from low-cost RGB imagery; however, the limited availability of paired RGB-NDVI datasets and domain discrepancies between existing sources hinder robust generalization. In this work, we construct two UAV-based RGB-NDVI paired datasets and investigate multiple deep learning architectures, including an FCNN, an RSCNN, and an ADL, for NDVI prediction. Our experimental results show that RSCNN consistently delivers the strongest regression performance across both datasets, achieving R² values of 82.43% and 89.53%, and the lowest MAE of 1.87% and 1.57% on two of the created datasets, respectively. Furthermore, we studied transfer learning and proposed a self-learning approach that relied on pseudo-labeled target samples. The results demonstrate improved performance that varied with the chosen confidence threshold and the transfer direction.

Student learning outcome (SLO) tracing aims to monitor students’ learning progress by predicting their likelihood of passing or failing courses using Deep Knowledge Tracing (DKT). However, conventional DKT models often lack interpretability, limiting their adoption in educational settings that require transparent decision-making. To address this challenge, this quantitative study proposes an interpretable ensemble framework that integrates Item Response Theory (IRT) with DKT. Specifically, multiple IRT-based DKT models are developed to capture student ability and item characteristics, and these models are combined using a bagging strategy to enhance predictive performance and robustness. The framework is evaluated on an SLO tracing dataset from Prairie View A&M University (PVAMU), a historically Black college and university (HBCU). Result analysis includes comparisons of evaluation metrics such as Area Under the Curve (AUC), accuracy (ACC), and precision across individual and ensemble models, as well as visualizations of student ability, item difficulty, and predicted probabilities to assess interpretability. Experimental results demonstrate that the ensemble approach consistently outperforms single models while providing clear, interpretable insights into student learning dynamics. These findings suggest that integrating ensemble methods with IRT can simultaneously improve prediction accuracy and transparency in SLO tracing.

In the area of explainable artificial intelligence, Symbolic Regression (SR) has emerged as a promising approach by discovering interpretable mathematical expressions that fit data. However, SR faces two main challenges: most methods are evaluated on scientific datasets with well-understood relationships, limiting generalization, and SR primarily targets single-output regression, whereas many real-world problems involve multi-target outputs with interdependent variables. To address these issues, we propose multi-task regression GINN-LP (MTRGINN-LP), an interpretable neural network for multi-target symbolic regression. By integrating GINN-LP with a multi-task deep learning, the model combines a shared backbone including multiple power-term approximator blocks with task-specific output layers, capturing inter-target dependencies while preserving interpretability. We validate multi-task GINN-LP on practical multi-target applications, including energy efficiency prediction and sustainable agriculture. Experimental results demonstrate competitive predictive performance alongside high interpretability, effectively extending symbolic regression to broader real-world multi-output tasks.

Attention-based models have become the leading approach in modeling medical language for Natural Language Processing (NLP) in clinical notes. These models outperform traditional techniques by effectively capturing contextual representations of language. In this research a comparative analysis is done amongst pre-trained attention based models namely Bert Base, BioBert, two variations of Bio+Clinical Bert, RoBerta, and Clinical Longformer on task related to Electronic Health Record (EHR) information extraction. The tasks from Track 1 of Harvard Medical School's 2022 National Clinical NLP Challenges (n2c2) are considered for this comparison, with the Contextualized Medication Event Dataset (CMED) given for these task. CMED is a dataset of unstructured EHRs and annotated notes that contain task relevant information about the EHRs. The goal of the challenge is to develop effective solutions for extracting contextual information related to patient medication events from EHRs using data driven methods. Each pre-trained model is fine-tuned and applied on CMED to perform medication extraction, medical event detection, and multi-dimensional medication event context classification. Processing methods are also detailed for breaking down EHRs for compatibility with the applied models. Performance analysis has been carried out using a script based on constructing medical terms from the evaluation portion of CMED with metrics including recall, precision, and F1-Score. The results demonstrate that models pre-trained on clinical data are more effective in detecting medication and medication events, but Bert Base, pre-trained on general domain data showed to be the most effective for classifying the context of events related to medications.

Personalized learning is a student-centered educational approach that adapts content, pace, and assessment to meet each learner's unique needs. As the key technique to implement the personalized learning, learning path recommendation sequentially recommends personalized learning items such as lectures and exercises. Advances in deep learning, particularly deep reinforcement learning, have made modeling such recommendations more practical and effective. This paper proposes a multi-task LSTM model that enhances learning path recommendation by leveraging shared information across tasks. The approach reframes learning path recommendation as a sequence-to-sequence (Seq2Seq) prediction problem, generating personalized learning paths from a learner's historical interactions. The model uses a shared LSTM layer to capture common features for both learning path recommendation and deep knowledge tracing, along with task-specific LSTM layers for each objective. To avoid redundant recommendations, a non-repeat loss penalizes repeated items within the recommended learning path. Experiments on the ASSIST09 dataset show that the proposed model significantly outperforms baseline methods for the learning path recommendation.

Identification of key variables such as medications, diseases, relations from health records and clinical notes has a wide range of applications in the clinical domain. n2c2 2022 provided shared tasks on challenges in natural language processing for clinical data analytics on electronic health records (EHR), where it built a comprehensive annotated clinical data Contextualized Medication Event Dataset (CMED). This study focuses on subtask 2 in Track 1 of this challenge that is to detect and classify medication events from clinical notes through building a novel BERT-based ensemble model. It started with pretraining BERT models on different types of big data such as Wikipedia and MIMIC. Afterwards, these pretrained BERT models were fine-tuned on CMED training data. These fine-tuned BERT models were employed to accomplish medication event classification on CMED testing data with multiple predictions. These multiple predictions generated by these fine-tuned BERT models were integrated to build final prediction with voting strategies. Experimental results demonstrated that BERT-based ensemble models can effectively improve strict Micro-F score by about 5% and strict Macro-F score by about 6%, respectively.

Historically Black Colleges and Universities in the United States serve a vital role in providing educational opportunities and training, particularly for underrepresented students, facing a challenge of lower retention and graduation rates compared to other institutions. To overcome this challenge, this study explores the application of generative artificial intelligence models to generate synthetic data, augmenting real datasets to improve student learning outcome tracing at these colleges and universities using Deep Knowledge Tracing techniques, which potentially offers actionable insights to identify at-risk students and enables proactive interventions to enhance retention and graduation rates in Science, Technology, Engineering and Math education. Utilizing two years of educational data from Prairie View A&M University, it applied data augmentation with tabular generative artificial intelligence models. The experimental results indicate that augmenting training data with synthetic samples generated by these models improved tracing performance measured by AUC and accuracy by approximately 5% and 3%, respectively, underscoring the potential of synthetic data to enhance the monitoring of student learning outcomes in diverse educational contexts. These findings highlight the critical role of data augmentation through generative artificial intelligence in improving the student learning outcome tracing, offering valuable insights for strategies to enhance retention and graduation rates.

Mass-shooting events pose a significant challenge to public safety, generating large volumes of unstructured textual data that hinder effective investigations and the formulation of public policy. Despite the urgency, few prior studies have effectively automated the extraction of key information from these events to support legal and investigative efforts. This paper presented the first dataset designed for knowledge acquisition on mass-shooting events through the application of named entity recognition (NER) techniques. It focuses on identifying key entities such as offenders, victims, locations, and criminal instruments, that are vital for legal and investigative purposes. The NER process is powered by Large Language Models (LLMs) using few-shot prompting, facilitating the efficient extraction and organization of critical information from diverse sources, including news articles, police reports, and social media. Experimental results on real-world mass-shooting corpora demonstrate that GPT-4o is the most effective model for mass-shooting NER, achieving the highest Micro Precision, Micro Recall, and Micro F1-scores. Meanwhile, o1-mini delivers competitive performance, making it a resource-efficient alternative for less complex NER tasks. It is also observed that increasing the shot count enhances the performance of all models, but the gains are more substantial for GPT-4o and o1-mini, highlighting their superior adaptability to few-shot learning scenarios.

Introduction: AI fairness seeks to improve the transparency and explainability of AI systems by ensuring that their outcomes genuinely reflect the best interests of users. Data augmentation, which involves generating synthetic data from existing datasets, has gained significant attention as a solution to data scarcity. In particular, diffusion models have become a powerful technique for generating synthetic data, especially in fields like computer vision.Methods: This paper explores the potential of diffusion models to generate synthetic tabular data to improve AI fairness. The Tabular Denoising Diffusion Probabilistic Model (Tab-DDPM), a diffusion model adaptable to any tabular dataset and capable of handling various feature types, was utilized with different amounts of generated data for data augmentation. Additionally, reweighting samples from AIF360 was employed to further enhance AI fairness. Five traditional machine learning models—Decision Tree (DT), Gaussian Naive Bayes (GNB), K-Nearest Neighbors (KNN), Logistic Regression (LR), and Random Forest (RF)—were used to validate the proposed approach.Results and discussion: Experimental results demonstrate that the synthetic data generated by Tab-DDPM improves fairness in binary classification.