Fisher's Linear Discriminant Function Analysis and its Potential Utility as a Tool for the Assessment of Health-and-Wellness Programs in Indigenous Communities

Tongue image fusion and analysis of thermal and visible images in diabetes mellitus using machine learning techniques

The study aimed to achieve the following objectives: (1) to perform the fusion of thermal and visible tongue images with various fusion rules of discrete wavelet transform (DWT) to classify diabetes and normal subjects; (2) to obtain the statistical features in the required region of interest from the tongue image before and after fusion; (3) to distinguish the healthy and diabetes using fused tongue images based on deep and machine learning algorithms. The study participants comprised of 80 normal subjects and age- and sex-matched 80 diabetes patients. The biochemical tests such as fasting glucose, postprandial, Hba1c are taken for all the participants. The visible and thermal tongue images are acquired using digital single lens reference camera and thermal infrared cameras, respectively. The digital and thermal tongue images are fused based on the wavelet transform method. Then Gray level co-occurrence matrix features are extracted individually from the visible, thermal, and fused tongue images. The machine learning classifiers and deep learning networks such as VGG16 and ResNet50 was used to classify the normal and diabetes mellitus. Image quality metrics are implemented to compare the classifiers' performance before and after fusion. Support vector machine outperformed the machine learning classifiers, well after fusion with an accuracy of 88.12% compared to before the fusion process (Thermal-84.37%; Visible-63.1%). VGG16 produced the classification accuracy of 94.37% after fusion and attained 90.62% and 85% before fusion of individual thermal and visible tongue images, respectively. Therefore, this study results indicates that fused tongue images might be used as a non-contact elemental tool for pre-screening type II diabetes mellitus.

Identification of mine water sources using a multi-dimensional ion-causative nonlinear algorithmic model

Based on the nonlinear algorithmic theory, the R-SVM water source discrimination model and prediction method were established by using the piper qualitatively to compare the differences between the ionic components and R-type factor approximation indicator input dimensions. Taking the mine water samples of Zhaogezhuang Coal Mine as an example, according to the chemical composition analysis of the water samples from different monitoring points, six indexes of Na+, Ca2+, Mg2+, Cl-, SO42- and HCO3- were selected as the discrimination factors. According to the water characteristics of each aquifer and the actual needs of discrimination, the water inrush sources in the mining area were divided into four categories: The goaf water is class I, Ordovician carbonate is class II, Sandstone fracture water from the 13 coal system is class III, and Sandstone fracture water from the 12 coal system is class IV. Taking 56 typical water inrush samples as training samples, 11 groups for prediction samples, establish the input index as typical ion content, output as water source type, using SPSS statistics and MATLAB to realize the R-SVM water source discriminant analysis model, automatically establishing the mapping relationship between the water quality indexes and the evaluation standards, which can achieve the purpose of rapid and accurate discrimination of the water sample data. The results showed that the accuracy of the R-SVM model classification was 90.90% in the verification of the water source discrimination example of Zhaogezhuang mine and the coupled model has high accuracy, good applicability and discriminant ability, and has certain guiding significance for the prevention and control of water damage and the related field work.

Traditional activities and general and mental health of adult Indigenous peoples living off-reserve in Canada

Introduction

We examined associations between traditional Indigenous activities and self-perceived general and mental health in adult Indigenous persons living off-reserve in Canada using the 2012 and 2017 Aboriginal Peoples Surveys (APS), the two most recent datasets. We utilized four traditional Indigenous activities including hunting, making clothes or footwear, making arts or crafts, and gathering wild plants to investigate these self-reported data.

Methods

Data from 9,430 and 12,598 respondents from the 2012 and 2017 APS, respectively, who responded to 15 questions concerning traditional activities were assessed using multivariable logistic regression to produce odds ratios (OR) and 95% confidence intervals (CI). Covariates included age, sex, education-level, income-level, Indigenous identity, residential school connection, ability to speak an Indigenous language, smoking status, and alcohol consumption frequency.

Results

Using the 2012 APS, clothes-making was associated with poor self-reported general (OR = 1.50, 95%CI: 1.12-1.99) and mental (OR = 1.59, 95%CI: 1.14-2.21) health. Hunting was associated with good mental health (OR = 0.71 95%CI: 0.56-0.93). Similarly, 2017 analyses found clothes-making associated with poor general health (OR = 1.25, 95%CI: 1.01-1.54), and hunting associated with good general (OR = 0.76, 95%CI: 0.64-0.89) and mental (OR = 0.69, 95%CI: 0.58-0.81) health. Artmaking was associated with poor general (OR = 1.37, 95%CI: 1.17-1.60) and mental (OR = 1.85, 95%CI: 1.58-2.17) health.

Conclusion

Hunting had protective relationships with mental and general health, which may reflect benefits of participation or engagement of healthier individuals in this activity. Clothes-making and artmaking were associated with poor general and poor mental health, possibly representing reverse causation as these activities are often undertaken therapeutically. These findings have implications for future research, programs and policies concerning Indigenous health.