@article{AdnanSrsicVenticichetal.2020,
  author    = {Adnan, Hassan Sami and Srsic, Amanda and Venticich, Pete Milos and Townend, David M.R.},
  title     = {Using AI for mental health analysis and prediction in school surveys},
  series = {European journal of public health},
  volume    = {30},
  journal   = {European journal of public health},
  publisher = {Oxford Univ. Press},
  address   = {Oxford [u.a.]},
  issn      = {1101-1262},
  doi       = {10.1093/eurpub/ckaa165.336},
  pages     = {V125 -- V125},
  year      = {2020},
  abstract  = {Background: Childhood and adolescence are critical stages of life for mental health and well-being. Schools are a key setting for mental health promotion and illness prevention. One in five children and adolescents have a mental disorder, about half of mental disorders beginning before the age of 14. Beneficial and explainable artificial intelligence can replace current paper- based and online approaches to school mental health surveys. This can enhance data acquisition, interoperability, data driven analysis, trust and compliance. This paper presents a model for using chatbots for non-obtrusive data collection and supervised machine learning models for data analysis; and discusses ethical considerations pertaining to the use of these models. Methods: For data acquisition, the proposed model uses chatbots which interact with students. The conversation log acts as the source of raw data for the machine learning. Pre-processing of the data is automated by filtering for keywords and phrases. Existing survey results, obtained through current paper-based data collection methods, are evaluated by domain experts (health professionals). These can be used to create a test dataset to validate the machine learning models. Supervised learning can then be deployed to classify specific behaviour and mental health patterns. Results: We present a model that can be used to improve upon current paper-based data collection and manual data analysis methods. An open-source GitHub repository contains necessary tools and components of this model. Privacy is respected through rigorous observance of confidentiality and data protection requirements. Critical reflection on these ethics and law aspects is included in the project. Conclusions: This model strengthens mental health surveillance in schools. The same tools and components could be applied to other public health data. Future extensions of this model could also incorporate unsupervised learning to find clusters and patterns of unknown effects.},
  language  = {en}
}
@misc{PickEffenbergerZhelavskayaetal.2019,
  author    = {Pick, Leonie and Effenberger, Frederic and Zhelavskaya, Irina and Korte, Monika},
  title     = {A Statistical Classifier for Historical Geomagnetic Storm Drivers Derived Solely From Ground-Based Magnetic Field Measurements},
  series = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Postprints der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {982},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-47499},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-474996},
  pages     = {2000 -- 2015},
  year      = {2019},
  abstract  = {Solar wind observations show that geomagnetic storms are mainly driven by interplanetary coronal mass ejections (ICMEs) and corotating or stream interaction regions (C/SIRs). We present a binary classifier that assigns one of these drivers to 7,546 storms between 1930 and 2015 using ground-based geomagnetic field observations only. The input data consists of the long-term stable Hourly Magnetospheric Currents index alongside the corresponding midlatitude geomagnetic observatory time series. This data set provides comprehensive information on the global storm time magnetic disturbance field, particularly its spatial variability, over eight solar cycles. For the first time, we use this information statistically with regard to an automated storm driver identification. Our supervised classification model significantly outperforms unskilled baseline models (78\% accuracy with 26[19]\% misidentified interplanetary coronal mass ejections [corotating or stream interaction regions]) and delivers plausible driver occurrences with regard to storm intensity and solar cycle phase. Our results can readily be used to advance related studies fundamental to space weather research, for example, studies connecting galactic cosmic ray modulation and geomagnetic disturbances. They are fully reproducible by means of the underlying open-source software (Pick, 2019, http://doi.org/10.5880/GFZ.2.3.2019.003)},
  language  = {en}
}
@article{PickEffenbergerZhelavskayaetal.2019,
  author    = {Pick, Leonie and Effenberger, Frederic and Zhelavskaya, Irina and Korte, Monika},
  title     = {A Statistical Classifier for Historical Geomagnetic Storm Drivers Derived Solely From Ground-Based Magnetic Field Measurements},
  series = {Earth and Space Science},
  volume    = {6},
  journal   = {Earth and Space Science},
  publisher = {American Geophysical Union},
  address   = {Malden, Mass.},
  issn      = {2333-5084},
  doi       = {10.1029/2019EA000726},
  pages     = {2000 -- 2015},
  year      = {2019},
  abstract  = {Solar wind observations show that geomagnetic storms are mainly driven by interplanetary coronal mass ejections (ICMEs) and corotating or stream interaction regions (C/SIRs). We present a binary classifier that assigns one of these drivers to 7,546 storms between 1930 and 2015 using ground-based geomagnetic field observations only. The input data consists of the long-term stable Hourly Magnetospheric Currents index alongside the corresponding midlatitude geomagnetic observatory time series. This data set provides comprehensive information on the global storm time magnetic disturbance field, particularly its spatial variability, over eight solar cycles. For the first time, we use this information statistically with regard to an automated storm driver identification. Our supervised classification model significantly outperforms unskilled baseline models (78\% accuracy with 26[19]\% misidentified interplanetary coronal mass ejections [corotating or stream interaction regions]) and delivers plausible driver occurrences with regard to storm intensity and solar cycle phase. Our results can readily be used to advance related studies fundamental to space weather research, for example, studies connecting galactic cosmic ray modulation and geomagnetic disturbances. They are fully reproducible by means of the underlying open-source software (Pick, 2019, http://doi.org/10.5880/GFZ.2.3.2019.003)},
  language  = {en}
}