Wearable-Sensor-Based Weakly Supervised Parkinson's Disease Assessment with Data Augmentation.

Parkinson's disease (PD) is the second most prevalent dementia in the world. Wearable technology has been useful in the computer-aided diagnosis and long-term monitoring of PD in recent years. The fundamental issue remains how to assess the severity of PD using wearable devices in an efficient and accurate manner. However, in the real-world free-living environment, there are two difficult issues, poor annotation and class imbalance, both of which could potentially impede the automatic assessment of PD. To address these challenges, we propose a novel framework for assessing the severity of PD patient's in a free-living environment. Specifically, we use clustering methods to learn latent categories from the same activities, while latent Dirichlet allocation (LDA) topic models are utilized to capture latent features from multiple activities. Then, to mitigate the impact of data imbalance, we augment bag-level data while retaining key instance prototypes. To comprehensively demonstrate the efficacy of our proposed framework, we collected a dataset containing wearable-sensor signals from 83 individuals in real-life free-living conditions. The experimental results show that our framework achieves an astounding 73.48% accuracy in the fine-grained (normal, mild, moderate, severe) classification of PD severity based on hand movements. Overall, this study contributes to more accurate PD self-diagnosis in the wild, allowing doctors to provide remote drug intervention guidance.

Towards sustainability: An integrated life cycle environmental-economic insight into cow manure management.

Waste management signifies an equilibrium between environmental and economic factors. However, a comprehensive understanding of the integrated life cycle environmental-economic performance of waste management activities remains unclear. To facilitate a systematic linkage between the economic and environmental sectors, a regionalized life cycle assessment-based life cycle costing method was developed based on China's actual status quo. The cow manure utilization was set as an entry point to explored long-term environmental-economic performance of milk production under various manure utilization pathways. The results show that trade-offs were observed between internal and external costs as well as various environmental indicators. The choice of waste utilization is the focal point of environmental-economic trade-offs in the cow raising system. The optimal environmental-economic performance was achieved through the manure fertilizer utilization pathway, yielding a remarkable three-fold increase in marginal environmental benefits. Compared with fertilizer utilization, the manure direct returning to field reduced the carbon footprint by 12% while induced an external cost of $14.3. The wastewater treatment pathway is $ 5.5 lower in internal costs but $ 11.7 higher in external costs than those of fertilizer utilization. Overall, utilizing manure has potential to mitigate the upward trend of carbon footprint and external costs. However, achieving the carbon peak remains a significant challenge. A promising solution is the recycling of straw resources within cropping systems, particularly in hotspot regions (e.g., Inner Mongolia, Heilongjiang, Hebei, and Shandong). A comprehensive analysis of the dynamic interplay between cropping systems and cow raising systems is critical steps towards realizing a carbon-neutral future within the dairy production.

Uncovering the energy-carbon-water footprint of waste rubber recycling: Integrated environmental and economic perspectives.

The commitment to waste management has gained increasing momentum as global waste generation continues to skyrocket and threaten the environment. However, detailed assessments and clear insights remain absent to address the global waste utilization conundrum. This study evaluated the impact-oriented energy, carbon, and water (ECW) footprints of three typical scenarios for a waste recycling activity (i.e., waste rubber recycling) from environmental and economic dimensions, and explored key factors, nexus characteristics, and optimization measures. Results indicated that the rubber powder as an asphalt modifier scenario had a 93% greater environmental impact and 87% higher economic cost compared with the pyrolysis and reclaimed rubber production scenarios. Key processes, such as direct processes, electricity generation, and transportation, were identified as the major contributors to the ECW footprints, with the internal costs of raw materials, equipment, and taxes coupled with the external costs of human health dominating the economic impact. The nexus analysis results highlighted the urgent need to optimize the energy system for waste rubber recycling. Greening the production process revealed the benefits, with natural additives mitigating 85% of the environmental burden and 97% of the external costs compared with conventional additives. Industrial green microgrids, clean energy generation, proximity waste management, and electrified transportation were explored to foster sustainable optimization of waste rubber recycling systems. Moreover, a joint tax-subsidy mechanism for rubber production-recycling systems can stimulate recycling-oriented product design and increase the motivation to recycle waste rubber.