Search results for: Yuan Tian

Authors: Men An Pan, Ho Hsiung Huang, Jui Chuan Lin, Tsui Hsun Wu, Hsing Yuan Yen

Abstract:

Pingtung County, located in the southernmost region of Taiwan, has the largest number of pig farms in the country. In the past, livestock operators in Dongpian Village discharged their wastewater into the nearby water bodies, causing water pollution in the local rivers and polluting the air with the stench of the pig excrement. These resulted in many complaints from the local residents. In response to a long time fighting back of the community against the livestock farms due to the confrict, the County Government's Environmental Protection Bureau (PTEPB) examined potential wayouts in addition to heavy fines to the perpetrators. Through helping the livestock farms to upgrade their pollution prevention equipment, promoting the reuse of biogas residue and slurry from the pig excrement, and environmental education, the confrict was successfully resolved. The properly treated wastewater from the livestock farms has been freely provided to the neighboring farmlands via pipelines and tankers. Thus, extensive cultivation of bananas, papaya, red dragon fruit, Inca nut, and cocoa has resulted in 34% resource utilization of biogas residue as a fertilizer. This has encouraged farmers to reduce chemical fertilizers and use microbial materials like photosynthetic bacteria after banning herbicides while lowering the cost of wastewater treatment in livestock farms and alleviating environmental pollution simultaneously. That is, the livestock farms fully demonstrate the determination to fulfill their corporate social responsibility (CSR). Due to the success, Eight farms jointly established a social enterprise - "Dongpian Gemstone Village Co., Ltd." to promote organic farming through a "shared farm." The company appropriates 5% of its total revenue back to the community through caregiving services for the elderly and a fund for young local farmers. The community adopted the Satoyama Initiative in accordance with the Conference of the CBD COP10. Through the positive impact of environmental education, the community seeks to realize the coexistence between society and nature while maintaining and developing socio-economic activities (including agriculture) with respect for nature and building a harmonic relationship between humans and nature. By way of sustainable management of resources and ensuring biodiversity, the community is transforming into a socio-ecological production landscape. Apart from nature conservation and watercourse ecology, preserving local culture is also a key focus of the environmental education. To mitigate the impact of global warming and climate change, the community and the government have worked together to develop a disaster prevention and relief system, strive to establish a low-carbon emitting homeland, and become a model for resilient communities. By the power of environmental education, this community has turned its residents’ hearts and minds into concrete action, fulfilled social responsibility, and moved towards realizing the UN SDGs. Even though it is not the only community to integrate government agencies, research institutions, and NGOs for environmental education, it is a prime example of a low-carbon sustainable community that achieves more than 9 SDGs, including responsible consumption and production, climate change action, and diverse partnerships. The community is also leveraging environmental education to become a net-zero carbon community targeted by COP26.

Keywords: environmental education, biogas residue, biogas slurry, CSR, SDGs, climate change, net-zero carbon emissions

Procedia PDF Downloads 122

Authors: Dongping Fang, Lian Duan, Xiaojing Yuan, Mike Xu, Allyn Klunder, Kevin Tan, Suiting Cao, Yeqing Ji

Abstract:

Accurate prediction of a medical condition with straight clinical evidence is a long-sought topic in the medical management and health insurance field. Although great progress has been made with machine learning algorithms, the medical community is still, to a certain degree, suspicious about the model's accuracy and interpretability. This paper presents an innovative hierarchical attention deep learning model to achieve good prediction and clear interpretability that can be easily understood by medical professionals. This deep learning model uses a hierarchical attention structure that matches naturally with the medical history data structure and reflects the member’s encounter (date of service) sequence. The model attention structure consists of 3 levels: (1) attention on the medical code types (diagnosis codes, procedure codes, lab test results, and prescription drugs), (2) attention on the sequential medical encounters within a type, (3) attention on the medical codes within an encounter and type. This model is applied to predict the occurrence of stage 3 chronic kidney disease (CKD3), using three years’ medical history of Medicare Advantage (MA) members from a top health insurance company. The model takes members’ medical events, both claims and electronic medical record (EMR) data, as input, makes a prediction of CKD3 and calculates the contribution from individual events to the predicted outcome. The model outcome can be easily explained with the clinical evidence identified by the model algorithm. Here are examples: Member A had 36 medical encounters in the past three years: multiple office visits, lab tests and medications. The model predicts member A has a high risk of CKD3 with the following well-contributed clinical events - multiple high ‘Creatinine in Serum or Plasma’ tests and multiple low kidneys functioning ‘Glomerular filtration rate’ tests. Among the abnormal lab tests, more recent results contributed more to the prediction. The model also indicates regular office visits, no abnormal findings of medical examinations, and taking proper medications decreased the CKD3 risk. Member B had 104 medical encounters in the past 3 years and was predicted to have a low risk of CKD3, because the model didn’t identify diagnoses, procedures, or medications related to kidney disease, and many lab test results, including ‘Glomerular filtration rate’ were within the normal range. The model accurately predicts members A and B and provides interpretable clinical evidence that is validated by clinicians. Without extra effort, the interpretation is generated directly from the model and presented together with the occurrence date. Our model uses the medical data in its most raw format without any further data aggregation, transformation, or mapping. This greatly simplifies the data preparation process, mitigates the chance for error and eliminates post-modeling work needed for traditional model explanation. To our knowledge, this is the first paper on an interpretable deep-learning model using a 3-level attention structure, sourcing both EMR and claim data, including all 4 types of medical data, on the entire Medicare population of a big insurance company, and more importantly, directly generating model interpretation to support user decision. In the future, we plan to enrich the model input by adding patients’ demographics and information from free-texted physician notes.

Keywords: deep learning, interpretability, attention, big data, medical conditions

Procedia PDF Downloads 67