Zoekresultaten

Nul op de Trafo Analysis

The neighborhood of Houtlaan in Assen, the Netherlands, has ambitious targets for reducing the neighborhood’scarbon emissions and increasing their production of their own, sustainable energy. Specifically, they wish toincrease the percentage of houses with a heat pump, electric vehicle (EV) and solar panels (PV) to 60%, 70%and 80%, respectively, by the year 2030. However, it was unclear what the impacts of this transition would be onthe electricity grid, and what limitations or problems might be encountered along the way.Therefore, a study was carried out to model the future energy load and production patterns in Houtlaan. Thepurpose of the model was to identify and quantify the problems which could be encountered if no steps are takento prevent these problems. In addition, the model was used to simulate the effectiveness of various proposedsolutions to reduce or eliminate the problems which were identified.

Continuous Gait Velocity Analysis Using Ambient Sensors in a Smart Home

We present a method for measuring gait velocity using data from an existing ambient sensor network. Gait velocity is an important predictor of fall risk and functional health. In contrast to other approaches that use specific sensors or sensor configurations our method imposes no constraints on the elderly. We studied different probabilistic models for the description of the sensor patterns. Experiments are carried out on 15 months of data and include repeated assessments from an occupational therapist. We showed that the measured gait velocities correlate with these assessments.

How Is grandma doing?

Ambient activity monitoring systems produce large amounts of data, which can be used for health monitoring. The problem is that patterns in this data reflecting health status are not identified yet. In this paper the possibility is explored of predicting the functional health status (the motor score of AMPS = Assessment of Motor and Process Skills) of a person from data of binary ambient sensors. Data is collected of five independently living elderly people. Based on expert knowledge, features are extracted from the sensor data and several subsets are selected. We use standard linear regression and Gaussian processes for mapping the features to the functional status and predict the status of a test person using a leave-oneperson-out cross validation. The results show that Gaussian processes perform better than the linear regression model, and that both models perform better with the basic feature set than with location or transition based features. Some suggestions are provided for better feature extraction and selection for the purpose of health monitoring. These results indicate that automated functional health assessment is possible, but some challenges lie ahead. The most important challenge is eliciting expert knowledge and translating that into quantifiable features.

Point Cloud Analysis of Railway Infrastructure: A Systematic Literature Review

FinTDA: Python package for estimating market change through persistent homology diagrams

This paper presents a user-friendly version of Persistent Homology (PH) graph code to model financial market structures and changes. By leveraging Topological Data Analysis (TDA), the code offers an effective approach for analyzing high-dimensional stock data, enabling the identification of persistent topological features indicative of market changes. The code’s potential applications in financial stability prediction, investment strategy development, and educational advancement are discussed. This contribution aims to facilitate the adoption of PH techniques in finance, promising significant implications for academic research and practical market analysis.

A novel loss function for neural network models exploring stock realized volatility using Wasserstein Distance

This study proposes a novel loss function for neural network models that explores the topological structure of stock realized volatility (RV) data by adding Wasserstein Distance (WD). The study shows that the proposed loss statistically significantly improves the forecast accuracy of neural network models for magnitude-dependent error measures, for example, Root Mean Square Error (RMSE) and Mean Absolute Error (MAE), but not necessarily for relative error measures, such as Quasi-likelihood (QLIKE). Additionally, this research provides user-friendly open-source code for researchers and practitioners to implement the proposed loss function efficiently and quickly.