Important note: Elsevier and IEEE are the only authorised publishers of the papers mentioned below respectively. Moreover, the content of both papers is available only to subscribers, or to non-subscribers for a small charge by the respective publishers. Thus, as authors, we would like to ask the Award Committee not to make the papers publicly available but to use the attached copies of the manuscripts for the sole purpose of assessing the suitability of our results to be human-competitive. 1. Title of the first paper: “Decision support system to improve postoperative discharge: A novel multi-class classification approach”. Title of the second paper: “Genetic Algorithms and Unsupervised Machine Learning for Predicting Robotic Manipulation Failures for Force-Sensitive Tasks”. 2. Name: Mr Luca Parisi Mailing address: 70 Symonds Street, Grafton, Auckland 1010, New Zealand. E-mail address: luca.parisi@ieee.org. Phone number: +39 3395901660. Name: Mr Narrendar RaviChandran Mailing address: 20 Symonds Street, Grafton, Auckland 1010, New Zealand. E-mail address: narrendar@ieee.org. Phone number: +64 223917812. Name: Ms Marianne Lyne Manaog Mailing address: 424a Panama Road, Mt Wellington, Auckland 1062, New Zealand. E-mail address: marianne@medintellego.com. Phone number: +64 223917807. 3. Mr Luca Parisi 4. Abstract of the first paper: Postoperative discharge decision-making is a critical process that determines not only postoperative patient outcomes and, in some cases, their survival, but also the management of the hospital resources, both financial and human ones. Existing decision-making support systems for aiding postoperative discharge heavily rely on statistical-based methods that lack objectivity in predicting optimal recovery area on a subject-specific basis. Machine Learning (ML)-based methods can enable these predictions, but current modelling implementations are inaccurate to be applied clinically or too sophisticated for the relatively low gain in classification performance. As an accurate and reliable method to predict where patients in a postoperative recovery area should be sent to next, the clinical potential of a novel hybrid multi- class classification algorithm was assessed. Data on 90 patients regarding their body temperature, oxygen saturation, blood pressure and perceived comfort upon discharge were obtained from the University of California-Irvine (UCI) Machine Learning repository. A multi-class classification was performed on such data using a ‘controlled’ All-vs-All approach by optimising kernel and hyperparameters via Genetic Algorithms. The novel hybrid algorithm was found to yield the highest classification accuracy, improving the highest accuracy from the literature by almost 12%. Achieving maximum accuracy and reliability, whilst retaining the lowest computational cost amongst the classifiers tested, the hybrid model is deemed an accurate, reliable and clinically viable solution to assist clinicians and nurses in improving postoperative discharge decision making. Abstract of the second paper: Recent advances in the state-of-the-art force-torque sensors have improved the close-loop control of robotic manipulators. However, it is still challenging to perform a force-sensitive pick-and-place task, unless a considerable number of sensors monitor the process. The predictive capability of failures in conventional robotic object-sorting systems are limited. Using fifteen force-torque samples from the University of California-Irvine (UCI) database, we demonstrate the viability of failure prediction using an unsupervised Machine Learning (ML)-based method, whose learning parameters were optimised via Genetic Algorithms (GAs). This hybrid algorithm was deployed for discriminating between manipulation failure and successful object placement. GA was used to avoid overfitting or overtraining. The proposed model could detect robotic manipulation failures with 91.95% classification accuracy, thus improving on the performance of previous classification methods. This study validates the use of GAs and unsupervised ML to predict the extent of success for force-sensitive object placement using information on forces and torques alone. 5. List relative to the first paper: B, C, E and F. List relative to the second paper: B, C, E and F. 6. The international scientific community, the editors and peer-reviewers involved in the assessment of our papers for publication in the respective Elsevier journal and IEEE conference proceedings, my institution and colleagues working with Artificial Intelligence (AI)-based classifiers thankfully judged our contributions as achieving better results with respect to the best results published in the literature prior to our studies, i.e., with an accuracy 11.46% higher than that obtained by Abuaqel et al. (2017) for prediction of postoperative discharge and with an accuracy 7.95% higher than that attained by Avci et al. (2015) in the prediction of manipulation failures for force-sensitive tasks respectively. Not only we managed to improve the performance in achieving both the above-mentioned tasks, but our results achieved by applying Genetic Algorithm optimise the ability of the learning-based classifiers to truly understand the underlying data patterns. 7. Full citation of the first paper: Parisi, L., RaviChandran, N., & Manaog, M. L. (2018). Decision support system to improve postoperative discharge: A novel multi-class classification approach. Knowledge-Based Systems. Full citation of the second paper: Parisi, L., & RaviChandran, N. (2018, in press). Genetic Algorithms and Unsupervised Machine Learning for Predicting Robotic Manipulation Failures for Force-Sensitive Tasks. In 2018 4th International Conference on Control, Automation and Robotics (ICCAR 2018). IEEE. 8. Any monetary prize, if any, is to be divided equally amongst the three co-authors, i.e., LP, NR, MLM. 9. We expect to be the 'best' by virtue of the outstanding contribution that, as researchers in the fields of Evolutionary Computation and Artificial Intelligence, we believe to have given to the scientific and clinical communities with the first paper, and to the scientific and industrial communities with the second paper, by extending the use of GA to improve the performance of Artificial Intelligence-based algorithms to aid predictions of postoperative discharge and manipulation failures respectively. 10. GA (genetic algorithms) and LCS (learning classifier systems), in particular: four multi-class classification algorithms in the paper published in Knowledge-Based Systems (Parisi et al., 2018), namely the supervised Artificial Neural Network (ANN)-based Multi-Layer Perceptron (M-MLP) and three Machine Learning (ML)-based ones, M-Support Vector Machine (M-SVM), Lagrangian Support Vector Machine (M-LSVM) and the GA-M-LSVM; two unsupervised ML-based classification algorithms, namely the self-organising map (SOM) and the GA-SOM in the paper currently in press that will be published by the IEEE (Parisi and RaviChandran, 2018). 11. First paper (Parisi et al., 2018): March 2018 (online) Second paper (Parisi and RaviChandran, 2018): in press (supporting documentation provided).