Early prediction of mental health issues among individuals is paramount for early diagnosis and treatment by mental health professionals. One of the promising approaches to achieving fully automated computer-based approaches for predicting mental health problems is via machine learning. As such, this study aims to empirically evaluate several popular machine learning algorithms in classifying and predicting mental health problems based on a given data set, both from a single classifier approach as well as an ensemble machine learning approach. The data set contains responses to a survey questionnaire that was conducted by Open Sourcing Mental Illness (OSMI). Machine learning algorithms investigated in this study include Logistic Regression, Gradient Boosting, Neural Networks, K-Nearest Neighbours, and Support Vector Machine, as well as an ensemble approach using these algorithms. Comparisons were also made against more recent machine learning approaches, namely Extreme Gradient Boosting and Deep Neural Networks. Overall, Gradient Boosting achieved the highest overall accuracy of 88.80% followed by Neural Networks with 88.00%. This was followed by Extreme Gradient Boosting and Deep Neural Networks at 87.20% and 86.40%, respectively. The ensemble classifier achieved 85.60% while the remaining classifiers achieved between 82.40 and 84.00%. The findings indicate that Gradient Boosting provided the highest classification accuracy for this particular mental health bi-classification prediction task. In general, it was also demonstrated that the prediction results produced by all of the machine learning approaches studied here were able to achieve more than 80% accuracy, thereby indicating a highly promising approach for mental health professionals toward automated clinical diagnosis.
The study aims to characterize the structural relaxation times of quench-cooled co-amorphous systems using Kohlrausch-Williams-Watts (KWW) and to correlate the relaxation data with the onset of crystallization. Comparison was also made between the relaxation times obtained by KWW and the width of glass transition temperature (ΔTg) methods (simple and quick). Differential scanning calorimetry, Fourier-transformed infrared spectroscopy, and polarized light microscopy were used to characterize the systems. Results showed that co-amorphous systems yielded a single Tg and ΔCp, suggesting the binary mixtures exist as a single amorphous phase. A narrow step change at Tg indicates the systems were fragile glasses. In co-amorphous nap-indo and para-indo, experimental Tgs were in good agreement with the predicted Tg. However, the Tg of co-amorphous nap-cim and indo-cim were 20°C higher than the predicted Tg, possibly due to stronger molecular interactions. Structural relaxation times below the experimental Tg were successfully characterized using the KWW and ΔTg methods. The comparison plot showed that KWW data are directly proportional to the ½ power of ΔTg data, after adjusting for a small offset. A moderate positive correlation was observed between the onset of crystallization and the KWW data. Structural relaxation times may be useful predictor of physical stability of co-amorphous systems.