VMD-WSLSTM Load Prediction Model Based on Shapley Values

Accurate short-term load forecasting can ensure the safe operation of the grid. Decomposing load data into smooth components by decomposition algorithms is a common approach to address data volatility. However, each component of the decomposition must be modeled separately for prediction, which leads to overly complex models. To solve this problem, a VMD-WSLSTM load prediction model based on Shapley values is proposed in this paper. First, the Shapley value is used to select the optimal set of special features, and then the VMD decomposition method is used to decompose the original load into several smooth components. Finally, WSLSTM is used to predict each component. Unlike the traditional LSTM model, WSLSTM can simplify the prediction model and extract common features among the components by sharing the parameters among the components. In order to verify the effectiveness of the proposed model, several control groups were used for experiments. The results show that the proposed method has higher prediction accuracy and training speed compared with traditional prediction methods.

‘What about the dads?’ Linking fathers and children in administrative data: A systematic scoping review

Research has shown that paternal involvement positively impacts on child health and development. We aimed to develop a conceptual model of dimensions of fatherhood, identify and categorise methods used for linking fathers with their children in administrative data, and map these methods onto the dimensions of fatherhood. We carried out a systematic scoping review to create a conceptual framework of paternal involvement and identify studies exploring the impact of paternal exposures on child health and development outcomes using administrative data. We identified four methods that have been used globally to link fathers and children in administrative data based on family or household identifiers using address data, identifiable information about the father on the child's birth registration, health claims data, and Personal Identification Numbers. We did not identify direct measures of paternal involvement but mapping linkage methods to the framework highlighted possible proxies. The addition of paternal National Health Service numbers to birth notifications presents a way forward in the advancement of fatherhood research using administrative data sources.

Few-Shot Learning for Post-Earthquake Urban Damage Detection

Among natural disasters, earthquakes are recorded to have the highest rates of human loss in the past 20 years. Their unexpected nature has severe consequences on both human lives and material infrastructure, demanding urgent action to be taken. For effective emergency relief, it is necessary to gain awareness about the level of damage in the affected areas. The use of remotely sensed imagery is popular in damage assessment applications; however, it requires a considerable amount of labeled data, which are not always easy to obtain. Taking into consideration the recent developments in the fields of Machine Learning and Computer Vision, this study investigates and employs several Few-Shot Learning (FSL) strategies in order to address data insufficiency and imbalance in post-earthquake urban damage classification. While small datasets have been tested against binary classification problems, which usually divide the urban structures into collapsed and non-collapsed, the potential of limited training data in multi-class classification has not been fully explored. To tackle this gap, four models were created, following different data balancing methods, namely cost-sensitive learning, oversampling, undersampling and Prototypical Networks. After a quantitative comparison among them, the best performing model was found to be the one based on Prototypical Networks, and it was used for the creation of damage assessment maps. The contribution of this work is twofold: we show that oversampling is the most suitable data balancing method for training Deep Convolutional Neural Networks (CNN) when compared to cost-sensitive learning and undersampling, and we demonstrate the appropriateness of Prototypical Networks in the damage classification context.

AN ALTERNATIVE 3D ADDRESS VISUALIZATION METHOD FOR BUILDINGS AND BUILDING INDEPENDENT SECTIONS WITH GIS-BASED 3D MODELLING APPROACH

Most commonly used detail type in 3D city modelling is building layer. One of the most important distinguishing point of buildings is independent sections. When the independent sections are examined in the context of Urban Information System (UIS), they have a multi-layered structure with their own characteristics. In address management processes, definition of the area belonging to a person, family or organization is realized through independent sections of buildings. In this study, it is aimed to model one the most important components of city objects such as building independent sections and road networks with GIS-based 3D modelling techniques. According to the results obtained from literature studies, answers were researched to the questions of what should be workflow of producing 3D models in the system and what should be in ideal 3D GIS database. Buildings and building independent sections were geocoded to provide some additional innovations to address mapping methods. Procedural modelling method was preferred as a GIS-based 3D modelling technique. Created models enable both the visualization of address data and their transfer to the 3D environment, as well as navigation. It provides some practical information. The designed system has been tested practically in Trabzon city.

Embedded trials within national clinical audit programmes: A qualitative interview study of enablers and barriers

Background Audit and feedback entails systematic documentation of clinical performance based on explicit criteria or standards which is then fed back to professionals in a structured manner. There are potential significant returns on investment from partnerships between existing clinical audit programmes in coordinated programmes of research to test ways of improving the effect of their feedback to drive greater improvements in health care delivery and population outcomes. We explored barriers to and enablers of embedding audit and feedback trials within clinical audit programmes. Methods We purposively recruited participants with varied experience in embedded trials in audit programmes. We conducted qualitative semi-structured interviews, guided by behavioural theory, with researchers, clinical audit programme staff and health care professionals. Recorded interviews were transcribed, and data coded and thematically analysed. Results We interviewed 31 participants (9 feedback researchers, 14 audit staff and 8 healthcare professionals, many having dual roles). We identified barriers and enablers for all 14 theoretical domains but no relationship between domains and participant role. We identified four optimal conditions for sustainable collaboration from the perspectives of stakeholders: resources, that is, recognition that audit programmes need to create capacity to participate in research, and research must be adapted to fit within each programme’s constraints; logistics, namely, that partnerships need to address data sharing and audit quality, while securing research funding to ensure operational success; leadership, that is, enthusiastic and engaged audit programme leaders must motivate their team and engage local stakeholders; and relationships, meaning that trust between researchers and audit programmes must be established over time by identifying shared priorities and meeting each partner’s needs. Conclusion Successfully embedding research within clinical audit programmes is likely to require compromise, logistical expertise, leadership and trusting relationships to overcome perceived risks and fully realise benefits.

Aspects of Data Quality in Psychology: Missing Data and Aberrant Responses

Data preprocessing is an integral step prior to analyzing data in the social sciences. The purpose of this article is to report the current practices psychological researchers use to address data preprocessing or quality concerns with a focus on issues pertaining to aberrant responses and missing data in self report measures. 240 articles were sampled from four journals: Psychological Science, Journal of Personality and Social Psychology, Developmental Psychology, and Abnormal Psychology from 2012 to 2018. We found that nearly half of the studies did not report any missing data treatment (111/240; 46.25%) and if they did, the most common approach to handle missing data was listwise deletion (71/240; 29.6%). Studies that remove data due to missingness removed, on average, 12% of the sample. We also found that most studies do not report any methodology to address aberrant responses (194/240; 80.83%). For studies that reported issues with aberrant responses, a study would classify 4% of the sample, on average, as suspect responses. These results suggest that most studies are either not transparent enough about their data preprocessing steps or maybe leveraging suboptimal procedures. We outline recommendations for researchers to improve the transparency and/or the data quality of their study.

Semi-Automatic Generation of Training Samples for Detecting Renewable Energy Plants in High-Resolution Aerial Images

Deep learning (DL)—in particular convolutional neural networks (CNN)—methods are widely spread in object detection and recognition of remote sensing images. In the domain of DL, there is a need for large numbers of training samples. These samples are mostly generated based on manual identification. Identifying and labelling these objects is very time-consuming. The developed approach proposes a partially automated procedure for the sample creation and avoids manual labelling of rooftop photovoltaic (PV) systems. By combining address data of existing rooftop PV systems from the German Plant Register, the Georeferenced Address Data and the Official House Surroundings Germany, a partially automated generation of training samples is achieved. Using a selection of 100,000 automatically generated samples, a network using a RetinaNet-based architecture combining ResNet101, a feature pyramid network, a classification and a regression network is trained, applied on a large area and post-filtered by intersection with additional automatically identified locations of existing rooftop PV systems. Based on a proof-of-concept application, a second network is trained with the filtered selection of approximately 51,000 training samples. In two independent test applications using high-resolution aerial images of Saarland in Germany, buildings with PV systems are detected with a precision of at least 92.77 and a recall of 84.47.

Distributionally robust stochastic programs with side information based on trimmings

We consider stochastic programs conditional on some covariate information, where the only knowledge of the possible relationship between the uncertain parameters and the covariates is reduced to a finite data sample of their joint distribution. By exploiting the close link between the notion of trimmings of a probability measure and the partial mass transportation problem, we construct a data-driven Distributionally Robust Optimization (DRO) framework to hedge the decision against the intrinsic error in the process of inferring conditional information from limited joint data. We show that our approach is computationally as tractable as the standard (without side information) Wasserstein-metric-based DRO and enjoys performance guarantees. Furthermore, our DRO framework can be conveniently used to address data-driven decision-making problems under contaminated samples. Finally, the theoretical results are illustrated using a single-item newsvendor problem and a portfolio allocation problem with side information.

Ethnic inequalities in health in later life, 1993–2017: the persistence of health disadvantage over more than two decades

Ethnic inequalities in health and wellbeing across the early and mid-lifecourse have been well-documented in the United Kingdom. What is less known is the prevalence and persistence of ethnic inequalities in health in later life. There is a large empirical gap focusing on older ethnic minority people in ethnicity and ageing research. In this paper, we take a novel approach to address data limitations by harmonising six nationally representative social survey datasets that span more than two decades. We investigate ethnic inequalities in health in later life, and we examine the effects of socio-economic position and racial discrimination in explaining health inequalities. The central finding is the persistence of stark and significant ethnic inequalities in limiting long-term illness and self-rated health between 1993 and 2017. These inequalities tend to be greater in older ages, and are partially explained by contemporaneous measures of socio-economic position, racism, and discrimination. Future data collection endeavours must better represent older ethnic minority populations and enable more detailed analyses of the accumulation of socio-economic disadvantage and exposure to racism over the lifecourse, and its effects on poorer health outcomes in later life.

Quantifying the impact of addressing data challenges in prediction of length of stay

Background Prediction of length of stay (LOS) at admission time can provide physicians and nurses insight into the illness severity of patients and aid them in avoiding adverse events and clinical deterioration. It also assists hospitals with more effectively managing their resources and manpower. Methods In this field of research, there are some important challenges, such as missing values and LOS data skewness. Moreover, various studies use a binary classification which puts a wide range of patients with different conditions into one category. To address these shortcomings, first multivariate imputation techniques are applied to fill incomplete records, then two proper resampling techniques, namely Borderline-SMOTE and SMOGN, are applied to address data skewness in the classification and regression domains, respectively. Finally, machine learning (ML) techniques including neural networks, extreme gradient boosting, random forest, support vector machine, and decision tree are implemented for both approaches to predict LOS of patients admitted to the Emergency Department of Odense University Hospital between June 2018 and April 2019. The ML models are developed based on data obtained from patients at admission time, including pulse rate, arterial blood oxygen saturation, respiratory rate, systolic blood pressure, triage category, arrival ICD-10 codes, age, and gender. Results The performance of predictive models before and after addressing missing values and data skewness is evaluated using four evaluation metrics namely receiver operating characteristic, area under the curve (AUC), R-squared score (R2), and normalized root mean square error (NRMSE). Results show that the performance of predictive models is improved on average by 15.75% for AUC, 32.19% for R2 score, and 11.32% for NRMSE after addressing the mentioned challenges. Moreover, our results indicate that there is a relationship between the missing values rate, data skewness, and illness severity of patients, so it is clinically essential to take incomplete records of patients into account and apply proper solutions for interpolation of missing values. Conclusion We propose a new method comprised of three stages: missing values imputation, data skewness handling, and building predictive models based on classification and regression approaches. Our results indicated that addressing these challenges in a proper way enhanced the performance of models significantly, which led to a more valid prediction of LOS.