Machine learning models have proven to be reliable methods in classification tasks. However, little research has been done on classifying dwelling characteristics based on smart meter & weather data before. Gaining insights into dwelling characteristics can be helpful to create/improve the policies for creating new dwellings at NZEB standard. This paper compares the different machine learning algorithms and the methods used to correctly implement the models. These methods include the data pre-processing, model validation and evaluation. Smart meter data was provided by Groene Mient, which was used to train several machine learning algorithms. The models that were generated by the algorithms were compared on their performance. The results showed that Recurrent Neural Network (RNN) 2performed the best with 96% of accuracy. Cross Validation was used to validate the models, where 80% of the data was used for training purposes and 20% was used for testing purposes. Evaluation metrices were used to produce classification reports, which can indicate which of the models work the best for this specific problem. The models were programmed in Python.
DOCUMENT
Machine learning models have proven to be reliable methods in classification tasks. However, little research has been conducted on the classification of dwelling characteristics based on smart meter and weather data before. Gaining insights into dwelling characteristics, which comprise of the type of heating system used, the number of inhabitants, and the number of solar panels installed, can be helpful in creating or improving the policies to create new dwellings at nearly zero-energy standard. This paper compares different supervised machine learning algorithms, namely Logistic Regression, Support Vector Machine, K-Nearest Neighbor, and Long-short term memory, and methods used to correctly implement these algorithms. These methods include data pre-processing, model validation, and evaluation. Smart meter data, which was used to train several machine learning algorithms, was provided by Groene Mient. The models that were generated by the algorithms were compared on their performance. The results showed that the Long-short term memory performed the best with 96% accuracy. Cross Validation was used to validate the models, where 80% of the data was used for training purposes and 20% was used for testing purposes. Evaluation metrics were used to produce classification reports, which indicates that the Long-short term memory outperforms the compared models on the evaluation metrics for this specific problem.
DOCUMENT
Within Human Activity Recognition (HAR), there is an insurmountable gap between the range of activities performed in life and those that can be captured in an annotated sensor dataset used in training. Failure to properly handle unseen activities seriously undermines any HAR classifier's reliability. Additionally within HAR, not all classes are equally dissimilar, some significantly overlap or encompass other sub-activities. Based on these observations, we arrange activity classes into a structured hierarchy. From there, we propose Hi-OSCAR: a Hierarchical Open-set Classifier for Activity Recognition, that can identify known activities at state-of-the-art accuracy while simultaneously rejecting unknown activities. This not only enables open-set classification, but also allows for unknown classes to be localized to the nearest internal node, providing insight beyond a binary “known/unknown” classification. To facilitate this and future open-set HAR research, we collected a new dataset: NFI_FARED. NFI_FARED contains data from multiple subjects performing nineteen activities from a range of contexts, including daily living, commuting, and rapid movements, which is fully public and available for download.
MULTIFILE
Lifelong learning is necessary for nurses and caregivers to provide good, person-centred care. To facilitate such learning and embed it into regular working processes, learning communities of practice are considered promising. However, there is little insight into how learning networks contribute to learning exactly and what factors of success can be found. The study is part of a ZonMw-funded research project ‘LeerSaam Noord’ in the Netherlands, which aims to strengthen the professionalization of the nursing workforce and promote person-centred care. We describe what learning in learning communities looks like in four different healthcare contexts during the start-up phase of the research project. A thematic analysis of eleven patient case-discussions in these learning communities took place. In addition, quantitative measurements on learning climate, reciprocity behavior, and perceptions of professional attitude and autonomy, were used to underpin findings. Reflective questioning and discussing professional dilemma's i.e. patient cases in which conflicting interests between the patient and the professional emerge, are of importance for successful learning.
MULTIFILE
To adequately deal with the challenges faced within residential care for older people, such as the increasing complexity of care and a call for more person-centred practices, it is important that health care providers learn from their work. This study investigates both the nature of learning, among staff and students working within care for older people, and how workplace learning can be promoted and researched. During a longitudinal study within a nursing home, participatory and democratic research methods were used to collaborate with stakeholders to improve the quality of care and to promote learning in the workplace. The rich descriptions of these processes show that workplace learning is a complex phenomenon. It arises continuously in reciprocal relationship with all those present through which both individuals and environment change and co-evolve enabling enlargement of the space for possible action. This complexity perspective on learning refines and expands conventional beliefs about workplace learning and has implications for advancing and researching learning. It explains that research on workplace learning is itself a form of learning that is aimed at promoting and accelerating learning. Such research requires dialogic and creative methods. This study illustrates that workplace learning has the potential to develop new shared values and ways of working, but that such processes and outcomes are difficult to control. It offers inspiration for educators, supervisors, managers and researchers as to promoting conditions that embrace complexity and provides insight into the role and position of self in such processes.
DOCUMENT
Athlete impairment level is an important factor in wheelchair mobility performance (WMP) in sports. Classification systems, aimed to compensate impairment level effects on performance, vary between sports. Improved understanding of resemblances and differences in WMP between sports could aid in optimizing the classification methodology. Furthermore, increased performance insight could be applied in training and wheelchair optimization. The wearable sensor-based wheelchair mobility performance monitor (WMPM) was used to measure WMP of wheelchair basketball, rugby and tennis athletes of (inter-)national level during match-play. As hypothesized, wheelchair basketball athletes show the highest average WMP levels and wheelchair rugby the lowest, whereas wheelchair tennis athletes range in between for most outcomes. Based on WMP profiles, wheelchair basketball requires the highest performance intensity, whereas in wheelchair tennis, maneuverability is the key performance factor. In wheelchair rugby, WMP levels show the highest variation comparable to the high variation in athletes’ impairment levels. These insights could be used to direct classification and training guidelines, with more emphasis on intensity for wheelchair basketball, focus on maneuverability for wheelchair tennis and impairment-level based training programs for wheelchair rugby. Wearable technology use seems a prerequisite for further development of wheelchair sports, on the sports level (classification) and on individual level (training and wheelchair configuration).
DOCUMENT
The prevention and diagnosis of frailty syndrome (FS) in cardiac patients requires innovative systems to support medical personnel, patient adherence, and self-care behavior. To do so, modern medicine uses a supervised machine learning approach (ML) to study the psychosocial domains of frailty in cardiac patients with heart failure (HF). This study aimed to determine the absolute and relative diagnostic importance of the individual components of the Tilburg Frailty Indicator (TFI) questionnaire in patients with HF. An exploratory analysis was performed using machine learning algorithms and the permutation method to determine the absolute importance of frailty components in HF. Based on the TFI data, which contain physical and psychosocial components, machine learning models were built based on three algorithms: a decision tree, a random decision forest, and the AdaBoost Models classifier. The absolute weights were used to make pairwise comparisons between the variables and obtain relative diagnostic importance. The analysis of HF patients’ responses showed that the psychological variable TFI20 diagnosing low mood was more diagnostically important than the variables from the physical domain: lack of strength in the hands and physical fatigue. The psychological variable TFI21 linked with agitation and irritability was diagnostically more important than all three physical variables considered: walking difficulties, lack of hand strength, and physical fatigue. In the case of the two remaining variables from the psychological domain (TFI19, TFI22), and for all variables from the social domain, the results do not allow for the rejection of the null hypothesis. From a long-term perspective, the ML based frailty approach can support healthcare professionals, including psychologists and social workers, in drawing their attention to the nonphysical origins of HF.
DOCUMENT
Insight into current scientific applications of Big Data in the precision dairy farming area may help us to understand the inflated expectations around Big Data. The objective of this invited review paper is to give that scientific background and determine whether Big Data has overcome the peak of inflated expectations. A conceptual model was created, and a literature search in Scopus resulted in 1442 scientific peer reviewed papers. After thorough screening on relevance and classification by the authors, 142 papers remained for further analysis. The area of precision dairy farming (with classes in the primary chain (dairy farm,feed, breed, health, food, retail, consumer) and levels for object of interest (animal, farm, network)), the Big Data-V area (with categories on Volume, Velocity, Variety and other V’s) and the data analytics area (with categories in analysis methods(supervised learning, unsupervised learning, semi-supervised classification, reinforcement learning) and data characteristics (time-series, streaming, sequence, graph, spatial, multimedia)) were analysed. The animal sublevel, with 83% of the papers, exceeds the farm sublevel and network sublevel. Within the animal sublevel, topics within the dairy farm level prevailed with 58% over the health level (33%). Within the Big Data category, the Volume category was most favoured with 59% of the papers, followed by 37% of papers that included the Variety category. None of the papers included the Velocity category. Supervised learning, representing 87% of the papers, exceeds unsupervised learning (12%). Within supervised learning, 64% of the papers dealt with classification issues and exceeds the regression methods (36%). Time-series were used in 61% of the papers and were mostly dealing with animal-based farm data. Multimedia data appeared in a greater number of recent papers. Based on these results, it can be concluded that Big Data is a relevant topic of research within the precision dairy farming area, but that the full potential of Big Data in this precision dairy farming area is not utilised yet. However, the present authors expect the full potential of Big Data, within the precision dairy farming area, will be reached when multiple Big Data characteristics (Volume, Variety and other V’s) and sources (animal, groups, farms and chain parts) are used simultaneously, adding value to operational and strategic decision.
LINK
Movement is an essential part of our lives. Throughout our lifetime, we acquire many different motor skills that are necessary to take care of ourselves (e.g., eating, dressing), to work (e.g., typing, using tools, care for others) and to pursue our hobbies (e.g., running, dancing, painting). However, as a consequence of aging, trauma or chronic disease, motor skills may deteriorate or become “lost”. Learning, relearning, and improving motor skills may then be essential to maintain or regain independence. There are many different ways in which the process of learning a motor skill can be shaped in practice. The conceptual basis for this thesis was the broad distinction between implicit and explicit forms of motor learning. Physiotherapists and occupational therapists are specialized to provide therapy that is tailored to facilitate the process of motor learning of patients with a wide range of pathologies. In addition to motor impairments, patients suffering from neurological disorders often also experience problems with cognition and communication. These problems may hinder the process of learning at a didactic level, and make motor learning especially challenging for those with neurological disorders. This thesis focused on the theory and application of motor learning during rehabilitation of patients with neurological disorders. The overall aim of this thesis was to provide therapists in neurological rehabilitation with knowledge and tools to support the justified and tailored use of motor learning in daily clinical practice. The thesis is divided into two parts. The aim of the first part (Chapters 2‐5) was to develop a theoretical basis to apply motor learning in clinical practice, using the implicit‐explicit distinction as a conceptual basis. Results of this first part were used to develop a framework for the application of motor learning within neurological rehabilitation (Chapter 6). Afterwards, in the second part, strategies identified in first part were tested for feasibility and potential effects in people with stroke (Chapters 7 and 8). Chapters 5-8 are non-final versions of an article published in final form in: Chapter 5: Kleynen M, Moser A, Haarsma FA, Beurskens AJ, Braun SM. Physiotherapists use a great variety of motor learning options in neurological rehabilitation, from which they choose through an iterative process: a retrospective think-aloud study. Disabil Rehabil. 2017 Aug;39(17):1729-1737. doi: 10.1080/09638288.2016.1207111. Chapter 6: Kleynen M, Beurskens A, Olijve H, Kamphuis J, Braun S. Application of motor learning in neurorehabilitation: a framework for health-care professionals. Physiother Theory Pract. 2018 Jun 19:1-20. doi: 10.1080/09593985.2018.1483987 Chapter 7: Kleynen M, Wilson MR, Jie LJ, te Lintel Hekkert F, Goodwin VA, Braun SM. Exploring the utility of analogies in motor learning after stroke: a feasibility study. Int J Rehabil Res. 2014 Sep;37(3):277-80. doi: 10.1097/MRR.0000000000000058. Chapter 8: Kleynen M, Jie LJ, Theunissen K, Rasquin SM, Masters RS, Meijer K, Beurskens AJ, Braun SM. The immediate influence of implicit motor learning strategies on spatiotemporal gait parameters in stroke patients: a randomized within-subjects design. Clin Rehabil. 2019 Apr;33(4):619-630. doi: 10.1177/0269215518816359.
DOCUMENT
Background A variety of options and techniques for causing implicit and explicit motor learning have been described in the literature. The aim of the current paper was to provide clearer guidance for practitioners on how to apply motor learning in practice by exploring experts’ opinions and experiences, using the distinction between implicit and explicit motor learning as a conceptual departure point. Methods A survey was designed to collect and aggregate informed opinions and experiences from 40 international respondents who had demonstrable expertise related to motor learning in practice and/or research. The survey was administered through an online survey tool and addressed potential options and learning strategies for applying implicit and explicit motor learning. Responses were analysed in terms of consensus ( 70%) and trends ( 50%). A summary figure was developed to illustrate a taxonomy of the different learning strategies and options indicated by the experts in the survey.
MULTIFILE
