Xulong Wang

Objective: Achieving effective and robust free-living PD severity assessment with wearable intelligence technologies requires a deep understanding of clinically relevant features, representative activities, and machine learning algorithms. Methods: We designed a unified analytic framework (PDWearML) to optimise wearable ML approaches with simple daily activities for fast assessment of PD severity. It comprises annotation criteria, feature importance analysis, representative activity combination, and PD severity assessment. We conducted a 12-month study, developing a supervised PD wearable dataset containing 100 PD patients and 35 age-matched healthy controls using Huawei smartwatches and Shimmer. PD severity, assessed by trained physicians using the Hoehn and Yahr (H&Y) scale. Results: The results reveal that through optimising multi-level feature extraction and combining three representative daily activities (WALK, ARISING-FROM-CHAIR, and DRINK), our smartwatch-based machine learning approach can assess PD severity in supervised settings within 2 minutes with an accuracy of up to 84.7%. Significance: This work holds significant clinical value, offering a potential auxiliary tool for faster, more tailored interventions in PD healthcare. Code is availableat code ocean platform and https://github.com/wang-xulong/PDWearML.

Parkinson's Disease (PD) is a prevalent and progressive neurodegenerative disorder. Wearable sensors enable automated analysis of human activities in daily life, providing a promising solution for continuous monitoring of motor symptoms. However, the scarcity of labeled data limits the effectiveness of supervised learning approaches in this context. To address this limitation, we propose a novel cycle-aware masked self-supervised learning framework that leverages unlabeled wearable sensor data for pre-training. Unlike conventional masking strategies that operate on individual time points or random continuous spans, our method introduces cycle-level masking that exploits the intrinsic periodicity of human activities, encouraging the model to learn structured temporal representations aligned with motor patterns. Extensive experiments on real-world wearable datasets demonstrate that our approach consistently outperforms state-of-the-art self-supervised learning baselines across multiple clinical and non-clinical tasks. In particular, our method achieves 3%-5% absolute accuracy improvement over the strongest competing masking-based methods across clinical diagnostic tasks, and delivers consistent gains across multiple daily activity recognition settings. These results validate the effectiveness of incorporating cycle-aware inductive bias into self-supervised learning for time-series clinical analysis, highlighting its potential for improving PD diagnosis in real-world scenarios.

Severity assessment of Parkinson's disease (PD) using wearable sensors offers an effective, objective basis for clinical management. However, general-purpose time series models often lack pathological specificity in feature extraction, making it difficult to capture subtle signals highly correlated with PD.Furthermore, the temporal sparsity of PD symptoms causes key diagnostic features to be easily "diluted" by traditional aggregation methods, further complicating assessment. To address these issues, we propose the Multi-scale Frequency-Aware Adversarial Multi-Instance Network (MFAM). This model enhances feature specificity through a frequency decomposition module guided by medical prior knowledge. Furthermore, by introducing an attention-based multi-instance learning (MIL) framework, the model can adaptively focus on the most diagnostically valuable sparse segments.We comprehensively validated MFAM on both the public PADS dataset for PD versus differential diagnosis (DD) binary classification and a private dataset for four-class severity assessment. Experimental results demonstrate that MFAM outperforms general-purpose time series models in handling complex clinical time series with specificity, providing a promising solution for automated assessment of PD severity.

Objective: Recent quantification research on Parkinson's disease (PD) integrates wearable technology with machine learning methods, indicating a strong potential for practical applications. However, the effectiveness of these techniques is influenced by environmental settings and is hardly applied in real-world situations. This paper aims to propose an effective feature assessment framework to automatically rate the severity of PD motor symptoms from short-term motor tasks, and then classify different PD severity levels in the real world. Methods: This paper identified specific PD motor symptoms using a novel feature-assessment framework at both segment-level and sample-level. Features were selected after calculating SHapley Additive exPlanation(SHAP) value, and verified by different machine learning methods with appropriate parameters. This framework has been verified on real-world data from 100 PD patients performing Unified Parkinson's Disease Rating Scale(UPDRS)-recommended short motor tasks, each task lasting 20-50 seconds. Results: The sensitivity for recognizing motor fluctuations reached 88% in tremor recognition. Additionally, LightGBM achieved the highest accuracy for early detection(92.59%) and achieved 71.58% in fine-grained severity classification using 31 selected features. Conclusion: This paper reports the first effort to assess multi-level and multi-scale features for automatic quantification of motor symptoms and PD severity levels. The proposed framework has been proven effective in assessing key PD information for recognition during short-term tasks. Significance: The explanatory analysis of digital features in this study provides more prior knowledge for PD self-assessment in a free-living environment.

Precision fertilization is essential in agricultural systems for balancing soil nutrients, conserving fertilizer, decreasing emissions, and increasing crop yields. Access to comprehensive and diverse agricultural data is problematic due to the lack of sophisticated sensor and network technologies on the majority of farms, and available agricultural data are generally unstructured and difficult to mine. The absence of agricultural data is, consequently, a significant impediment to the utilization of machine learning approaches for precision fertilization. In this research, we investigate newly gathered genuine agricultural dataset from nine real winter wheat farms in the United Kingdom, which encompass an extensive variety of agricultural variables, including climate, soil nutrients, and farming data. To deal with the spatio-temporal characteristics of agricultural dataset and to address the problem of scarcity in agricultural data, we propose a novel machine learning approach integrating multi-task learning and one-shot learning, which utilizes a multi-dimensional tensor constructed from original data combined with fertilization temporal patterns extracted by contrasting with environmental information from existing real farms to accurately predict the quantity and timing of base and top dressing fertilization. Specifically, agricultural data are converted into a 3-D tensor and tensor decomposition technique is utilized to derive a set of comprehensible spatio-temporal latent factors from the original data. The latent factors are subsequently utilized to construct the spatio-temporal tensor prediction model as multi-task relationships. The proposed one-shot learning approach utilizes the Mahalanobis distance to evaluate the similarity of environmental information between the target farm and existing real-world farms as a determinant of whether to transfer the fertilization temporal pattern of existing farm to the target farm. Comprehensive experiments are conducted to compare the proposed approach with standard regression models utilizing the real-world agricultural dataset. The experimental results demonstrate that our proposed approach presents superior accuracy and stability for fertilization prediction.