Hochschule Bonn-Rhein-Sieg
Publikationsserver der Hochschule Bonn-Rhein-Sieg - pub H-BRSNot a member yet
7939 research outputs found
Sort by
Bildung im Kontext des Befähigungsansatzes von Amartya Sen - Versuch eines Streitgesprächs
No full textForecastExplainer: Explainable household energy demand forecasting by approximating shapley values using DeepLIFT
No full textThe rapid progress in sensor technology has empowered smart home systems to efficiently monitor and control household appliances. AI-enabled smart home systems can forecast household future energy demand so that the occupants can revise their energy consumption plan and be aware of optimal energy consumption practices. However, deep learning (DL)-based demand forecasting models are complex and decisions from such black-box models are often considered opaque. Recently, eXplainable Artificial Intelligence (XAI) has garnered substantial attention in explaining decisions of complex DL models. The primary objective is to enhance the acceptance, trust, and transparency of AI models by offering explanations about provided decisions. We propose ForecastExplainer, an explainable deep energy demand forecasting framework that leverages Deep Learning Important Features (DeepLIFT) to approximate Shapley values to map the contribution of different appliances and features with time. The generated explanations can shed light to explain the prediction highlighting the impact of energy consumption attributes corresponding to time, such as responsible appliances, consumption by household areas and activities, and seasonal effects. Experiments on household datasets demonstrated the effectiveness of our method in accurate forecasting. We designed a new metric to evaluate the effectiveness of the generated explanations and the experiment results indicate the comprehensibility of the explanations. These insights might empower users to optimize energy consumption practices, fostering AI adoption in smart applications
Increasing Teaching Efficacy in Engineering Graduate Students through the Development and Facilitation of Summer Middle and High School STEM Experience
No full textGeschäftsordnung der Hochschulwahlversammlung der Hochschule Bonn-Rhein-Sieg vom 7.12.2023
No full text
Challenges in the determination of reactive oxygen species evolving during membrane water electrolysis for in situ ozone production
No full textThe treatment of ultrapure water with electrochemically produced O3 is a common means for disinfection yet leads to the formation of a variety of reactive oxygen species (ROS). The present study draws a comprehensive comparison between three commonly used photometric and fluorometric assays for ROS analysis and quantifies the individual signal responses for dissolved O3, ·OH and H2O2, respectively, to account for cross-sensitivities. By calibrating all combinations of assays and analytes, we developed a quantification procedure to reliably determine the actual ROS composition in ultrapure water environments for different operation conditions of a membrane water electrolyzer with PbO2 anodes down to concentrations of 0.97 μg L−1. While the ·OH formation rate can be described linearly over the observed current density range, substantial O3 evolution is only found for current densities of 0.75 A cm−2 and above (up to 3.7 μmol h−1 for J = 1.25 A cm−2). The formation of H2O2 is only observed when an organic carbon source is introduced into the solution. We further quantify the interference of H2O2 with the reading of the oxidation-reduction potential as a common water parameter and elaborate on its validity to monitor the peroxone process when both H2O2 and O3 are present simultaneously
Transformation of an Extracurricular Project to a Student-Driven Academic Institution — Success Criteria and Benefits for Students and Faculty
No full textInformation Security Policy Usability Scale: A Questionnaire for Evaluating the Usability of Information Security Policies
No full textEffective information security policies are crucial for organisations to mitigate information security threats and risks. However, poorly designed information security policies can lead to hidden costs and decreased compliance in daily work routines. While behavioural factors like social norms, positive attitudes, and knowledge are well known to influence compliance, the usability of information security policies, which takes the context of use seriously, remains understudied,. To address this, we introduce the Information Security Policy Usability Scale (ISPUS), an adaptation of the widely recognised System Usability Scale (SUS). ISPUS assesses the usability of information security policies. Thereby, it supports both companies and works councils in ensuring the fit of the work context, individual skills, tools and the policy. By applying ergonomic principles, ISPUS aims to enhance information security policy design and support organisational security efforts