Stefan Conrad
YOU?
Author Swipe
View article: A dataset of study program availability in German higher education between 1971 and 1996
A dataset of study program availability in German higher education between 1971 and 1996 Open
Educational systems are dynamic. They shape human capital, technological and societal progress, and also economic growth. Higher education, in particular, fosters innovation, with varying fields of study contributing differently to this pr…
View article: Nano-ESG: Extracting Corporate Sustainability Information from News Articles
Nano-ESG: Extracting Corporate Sustainability Information from News Articles Open
Determining the sustainability impact of companies is a highly complex subject which has garnered more and more attention over the past few years. Today, investors largely rely on sustainability-ratings from established rating-providers in…
View article: (Un)certainty of (Un)fairness: Preference-Based Selection of Certainly Fair Decision-Makers
(Un)certainty of (Un)fairness: Preference-Based Selection of Certainly Fair Decision-Makers Open
Fairness metrics are used to assess discrimination and bias in decision-making processes across various domains, including machine learning models and human decision-makers in real-world applications. This involves calculating the disparit…
View article: A Framework for the Construction of a Sentiment-Driven Performance Index: The Case of DAX40
A Framework for the Construction of a Sentiment-Driven Performance Index: The Case of DAX40 Open
We extract the sentiment from german and english news articles on companies in the DAX40 stock market index and use it to create a sentiment-powered pendant. Comparing it to existing products which adjust their weights at pre-defined dates…
View article: (Un)certainty of (Un)fairness: Preference-Based Selection of Certainly Fair Decision-Makers
(Un)certainty of (Un)fairness: Preference-Based Selection of Certainly Fair Decision-Makers Open
Fairness metrics are used to assess discrimination and bias in decision-making processes across various domains, including machine learning models and human decision-makers in real-world applications. This involves calculating the disparit…
View article: Multi-Objective Optimisation for the Selection of Clusterings across Time
Multi-Objective Optimisation for the Selection of Clusterings across Time Open
Nowadays, time series data are ubiquitous, encompassing various domains like medicine, economics, energy, climate science and the Internet of Things. One crucial task in analysing these data is clustering, aiming to find patterns that indi…
View article: Measuring and Mitigating Bias for Tabular Datasets with Multiple Protected Attributes
Measuring and Mitigating Bias for Tabular Datasets with Multiple Protected Attributes Open
Motivated by the recital (67) of the current corrigendum of the AI Act in the European Union, we propose and present measures and mitigation strategies for discrimination in tabular datasets. We specifically focus on datasets that contain …
View article: Trusting Fair Data: Leveraging Quality in Fairness-Driven Data Removal Techniques
Trusting Fair Data: Leveraging Quality in Fairness-Driven Data Removal Techniques Open
In this paper, we deal with bias mitigation techniques that remove specific data points from the training set to aim for a fair representation of the population in that set. Machine learning models are trained on these pre-processed datase…
View article: Let's Talk About Image Quality Improvement in Underwater Images for Object Detection
Let's Talk About Image Quality Improvement in Underwater Images for Object Detection Open
Object detection (OD) is one of the most difficult tasks of computer vision. Even more difficult is the recognition of objects in underwater images, not least because of the numerous difficulties that images of this type contain (e.g. blur…
View article: Prediction models of incontinence and sexual function one year after radical prostatectomy based on data from 20 164 prostate cancer patients
Prediction models of incontinence and sexual function one year after radical prostatectomy based on data from 20 164 prostate cancer patients Open
Background Incontinence and sexual dysfunction are long-lasting side effects after surgical treatment (radical prostatectomy, RP) of prostate cancer (PC). For an informed treatment decision, physicians and patients should discuss expected …
View article: Efficient Iterative Semi-supervised Object Detection Training for Counting of Fruits and Vegetables
Efficient Iterative Semi-supervised Object Detection Training for Counting of Fruits and Vegetables Open
Object recognition could be successfully applied to problems such as object counting [3]. This transition makes this kind of technology interesting for numerous industries where automation and quality assurance based on visual information …
View article: Frontmatter
Frontmatter Open
it -Information Technology is a strictly peer-reviewed scientific journal.It is the oldest German journal in the field of information technology.Today, the major aim of it -Information Technology is highlighting issues on ongoing newsworth…
View article: Exploring Knowledge Composition for ESG Impact Type Determination
Exploring Knowledge Composition for ESG Impact Type Determination Open
In this paper, we discuss our (Team HHU's) submission to the Multi-Lingual ESG Impact Type Identification task (ML-ESG-2). The goal of this task is to determine if an ESG-related news article represents an opportunity or a risk. We use an …
View article: HHU at SemEval-2023 Task 3: An Adapter-based Approach for News Genre Classification
HHU at SemEval-2023 Task 3: An Adapter-based Approach for News Genre Classification Open
This paper describes our approach for Subtask 1 of Task 3 at SemEval-2023. In this subtask, task participants were asked to classify multilingual news articles for one of three classes: Reporting, Opinion Piece or Satire. By training an Ad…
View article: Cluster-based stability evaluation in time series data sets
Cluster-based stability evaluation in time series data sets Open
In modern data analysis, time is often considered just another feature. Yet time has a special role that is regularly overlooked. Procedures are usually only designed for time-independent data and are therefore often unsuitable for the tem…
View article: Alone We Can Do So Little; Together We Cannot Be Detected
Alone We Can Do So Little; Together We Cannot Be Detected Open
It is no longer possible to imagine our everyday life without time series data. This includes, for example, market developments, COVID-19 cases, electricity prices, and other data from a wide variety of domains. An important task in the an…
View article: Sense disambiguation of compound constituents
Sense disambiguation of compound constituents Open
In distributional semantic accounts of the meaning of noun-noun compounds (e.g. starfish, bank account, houseboat) the important role of constituent polysemy remains largely unaddressed(cf. the meaning of star in starfish vs. star cluster …
View article: Developing an argument annotation scheme based on a semantic classification of arguments
Developing an argument annotation scheme based on a semantic classification of arguments Open
Corpora of argumentative discourse are commonly analyzed in terms of argumentative units, consisting of claims and premises. Both argument detection and classification are complex discourse processing tasks. Our paper introduces a semantic…
View article: Efficient Fruit and Vegetable Classification and Counting for Retail Applications Using Deep Learning
Efficient Fruit and Vegetable Classification and Counting for Retail Applications Using Deep Learning Open
The process of manual classification and counting of fruits and vegetables, from the moment the customer places items on the conveyor belt to their weighing by the cashier on the checkout scale is time consuming and may be burdensome for c…
View article: Fast Multi-Level Foreground Estimation
Fast Multi-Level Foreground Estimation Open
Alpha matting aims to estimate the translucency of an object in a given image. The resulting alpha matte describes pixel-wise to what amount foreground and background colors contribute to the color of the composite image. While most method…
View article: Citizen Involvement in Urban Planning - How Can Municipalities Be Supported in Evaluating Public Participation Processes for Mobility Transitions?
Citizen Involvement in Urban Planning - How Can Municipalities Be Supported in Evaluating Public Participation Processes for Mobility Transitions? Open
Public participation processes allow citizens to engage in municipal decision-making processes by expressing their opinions on specific issues. Municipalities often only have limited resources to analyze a possibly large amount of textual …
View article: Combining text and vision in compound semantics: Towards a cognitively plausible multimodal model
Combining text and vision in compound semantics: Towards a cognitively plausible multimodal model Open
In the current state-of-the art distributionalsemantics model of the meaning of noun-noun compounds (such aschainsaw, but-terfly, home phone),CAOSS(Marelli et al.2017), the semantic vectors of the individ-ual constituents are combined, and…
View article: Automated Analysis of Alignment in Long-Leg Radiographs by Using a Fully Automated Support System Based on Artificial Intelligence
Automated Analysis of Alignment in Long-Leg Radiographs by Using a Fully Automated Support System Based on Artificial Intelligence Open
Fully automated analysis of LLRs yielded accurate results across a wide range of clinical and pathologic indications and is fast enough to enhance and accelerate clinical workflows.Supplemental material is available for this article.© RSNA…
View article: Charaterizing RDF graphs through graph-based measures – framework and assessment
Charaterizing RDF graphs through graph-based measures – framework and assessment Open
The topological structure of RDF graphs inherently differs from other types of graphs, like social graphs, due to the pervasive existence of hierarchical relations (TBox), which complement transversal relations (ABox). Graph measures captu…
View article: mazlo/lodcc: v0.5.1
mazlo/lodcc: v0.5.1 Open
With this minor release refactorings and changes in the package structure were expanded. This concerns in particular the util and graph.helpers package. Code in these packages was split up. New packages extras and graph.extras were introdu…
View article: A Software Framework and Datasets for the Analysis of Graph Measures on RDF Graphs
A Software Framework and Datasets for the Analysis of Graph Measures on RDF Graphs Open
As the availability and the inter-connectivity of RDF datasets grow, so does the necessity to understand the structure of the data. Understanding the topology of RDF graphs can guide and inform the development of, e.g. synthetic dataset ge…