Hanne, Thomas

Profilbild
E-Mail-Adresse
Geburtsdatum
Projekt
Organisationseinheiten
Berufsbeschreibung
Nachname
Hanne
Vorname
Thomas
Name
Hanne, Thomas

Filter

2008 - 200972010 - 2019472020 - 202467

Einstellungen

Suchergebnisse

Gerade angezeigt 1 - 10 von 122
  • Vorschaubild
    Publikation
    Effects and challenges of the COVID-19 pandemic in supply chain management: a text analytics approach
    (Taylor & Francis, 2024) Khodoomi, Mohammad Reza; Seif, Marziye; Hanne, Thomas
    The coronavirus has had many effects on supply chains and logistics, most of which are negative. Due to the importance of logistics and supply chain in the world, any disruption or mismanagement causes many problems not only in the countries directly affected but also globally. In this article, new textual data are collected from reputable commercial and news websites related to the effects of COVID-19 on logistics and supply chains. After collecting textual data, valuable information about the impact of the coronavirus is extracted using various text mining techniques performed with R programming. Finally, issues related to COVID-19 and supply chains are identified and divided into five categories: suppliers and products, governments and organisations, health, evaluation, problems, and barriers. Also, categorising the problems and limitations of supply chains and logistics will provide managerial insights to minimise obstacles and disruptions. In particular, managers should consider several suppliers to reduce dependencies and also focus on domestic suppliers because of transportation limitations. Moreover, companies should pay attention to the health of societies and employ new policies, as well as pay attention to consumer behaviour such as their tendency to buy online.
    01A - Beitrag in wissenschaftlicher Zeitschrift
  • Vorschaubild
    Publikation
    An analysis of weight initialization methods in connection with different activation functions for feedforward neural networks
    (Springer, 2024) Wong, Kit; Dornberger, Rolf; Hanne, Thomas
    The selection of weight initialization in an artificial neural network is one of the key aspects and affects the learning speed, convergence rate and correctness of classification by an artificial neural network. In this paper, we investigate the effects of weight initialization in an artificial neural network. Nguyen-Widrow weight initialization, random initialization, and Xavier initialization method are paired with five different activation functions. This paper deals with a feedforward neural network, consisting of an input layer, a hidden layer, and an output layer. The paired combination of weight initialization methods with activation functions are examined and tested and compared based on their best achieved loss rate in training. This work aims to better understand how weight initialization methods in neural networks, in combination with activation functions, affect the learning speed in comparison after a fixed number of training epochs.
    01A - Beitrag in wissenschaftlicher Zeitschrift
  • Vorschaubild
    Publikation
    An intelligent platform-based tool for the development of digital transformation strategies
    (Elsevier, 2024) Gatziu Grivas, Stella; Hanne, Thomas; Imhof, Denis; Bugmann, Diego; Schmitter, Paul
    Digital transformation strategies are of elementary importance for organizations competing in the digital age. Challenges such as faster changing customer needs, new value creation structures in digital eco-systems, or the use of collective intelligence to innovate business models require leveraging digital technologies. To achieve this and remain competitive, appropriate digital transformation strategies need to be in place. Yet, studies show that organizations struggle with strategy formulation and implementation. Based on workshops with practitioners the authors obtained concrete needs, pains, and gains as requirements for the development of an own, new intelligent and platform-based assessment tool. The proposed tool collects, calculates, and visualizes in a self-service manner, relevant company data to support decision-makers and organizations in digital transformation strategy development and implementation.
    01A - Beitrag in wissenschaftlicher Zeitschrift
  • Vorschaubild
    Publikation
    Unveiling drivers of sustainability in Chinese transport: an approach based on principal component analysis and neural networks
    (Routledge, 2023) Wanke, Peter Fernandes; Yazdi, Amir Karbassi; Hanne, Thomas; Tan, Yong
    The paper analyzes the sustainability of the Chinese transportation sector by examining the relationship between energy consumption (and CO2 emissions), transportation modes, and macroeconomic variables. Principal Component Analysis (PCA) and Neural Networks (NN) are combined using monthly data from January 1999 to December 2017. Our goal is to propose a model that links China's transportation footprint to major macroeconomic factors while simultaneously controlling each mode of transportation. Inflation and credit policies exert relatively weak effects on the explained variable. In contrast, trade and fixed asset investments, as well as monetary and fiscal policies, show a positive and significant impact. The use of waterways and airways plays an imperative role in sustainable development compared to the use of roads.
    01A - Beitrag in wissenschaftlicher Zeitschrift
  • Kein Vorschaubild vorhanden
    Publikation
    Echtzeit Ressourcendisposition von Personal und Rollmaterial in der Eisenbahnbranche
    (Innosuisse, 2023) Ehrenthal, Joachim; Hanne, Thomas; Telesko, Rainer; Gachnang, Phillip
    Zu wenig Personal und Rollmaterial, kurzfristig angesagte Arbeiten an der Infrastruktur mit den entsprechenden betrieblichen Behinderungen und Einschränkungen sowie kurzfristig auftretende Störungen prägen zurzeit die Berichterstattung über die Entwicklungen im öffentlichen Verkehr der Schweiz. Es ist absehbar, dass sich diese unbefriedigende Situation über eine längere Zeitspanne kaum massgeblich verbessern wird. Umso wichtiger ist es, vorhandene Ressourcen optimal einzusetzen und den zukünftigen Bedarf an Mitarbeitenden und Rollmaterial in den Griff zu kriegen. Die Fachhochschulen der Ostschweiz (OST) und der Nordwestschweiz FHNW entwickelten mit der Südostbahn (SOB), den luxemburgischen Eisenbahnen (CFL) und der Eisenbahn-Softwareherstellerin Qnamic eine zukunftsweisende Software zur Unterstützung der Eisenbahn-Disposition, um in Echtzeit über situationsspezifische Massnahmenpakete zur Störungsbehebung zu verfügen.
    05 - Forschungs- oder Arbeitsbericht
  • Kein Vorschaubild vorhanden
    Publikation
    Decision support for technology transfer using fuzzy quality function deployment and a fuzzy inference system
    (IOS Press, 2023) Sarfaraz, Amir Homayoun; Yazdi, Amir Karbassi; Hanne, Thomas; Hosseini, Raheleh Sadat
    Technology transfer plays an essential role in developing an organization’s capabilities to perform better in the market. Several protocols are defined for technology transfer. One of the main techniques in technology transfer is licensing, which significantly impacts profit and income. This study intends to develop a decision framework that integrates both a Fuzzy Inference System (FIS) and a two steps Fuzzy Quality Function Deployment (F-QFD) to assist an organization in selecting a licensor. To illustrate the decision framework’s performance, it has been implemented in an Iranian lubricant producer to select the best licensor among the 13 targeted companies. A complete product portfolio, brand image enhancement, increasing the market share of the high-value products, and improving the technical knowledge of manufacturing products were identified as the most important expectations of the licensees. A sensitivity analysis for the recommended framework has been conducted. For doing so, 27 rules of the FIS were categorized into four group and then changed. The results are compared using the Pearson correlation coefficient. Inference rules detect unconventional changes, while logical changes are appropriately considered.
    01A - Beitrag in wissenschaftlicher Zeitschrift
  • Vorschaubild
    Publikation
    Multilingual text summarization for German texts using transformer models
    (MDPI, 2023) Alcantara, Tomas Humberto Montiel; Krütli, David; Ravada, Revathi; Hanne, Thomas
    The tremendous increase in documents available on the Web has turned finding the relevant pieces of information into a challenging, tedious, and time-consuming activity. Text summarization is an important natural language processing (NLP) task used to reduce the reading requirements of text. Automatic text summarization is an NLP task that consists of creating a shorter version of a text document which is coherent and maintains the most relevant information of the original text. In recent years, automatic text summarization has received significant attention, as it can be applied to a wide range of applications such as the extraction of highlights from scientific papers or the generation of summaries of news articles. In this research project, we are focused mainly on abstractive text summarization that extracts the most important contents from a text in a rephrased form. The main purpose of this project is to summarize texts in German. Unfortunately, most pretrained models are only available for English. We therefore focused on the German BERT multilingual model and the BART monolingual model for English, with a consideration of translation possibilities. As the source of the experiment setup, took the German Wikipedia article dataset and compared how well the multilingual model performed for German text summarization when compared to using machine-translated text summaries from monolingual English language models. We used the ROUGE-1 metric to analyze the quality of the text summarization.
    01A - Beitrag in wissenschaftlicher Zeitschrift
  • Kein Vorschaubild vorhanden
    Publikation
    Computational Intelligence in Logistik und Supply Chain Management
    (Springer Gabler, 2023) Hanne, Thomas; Dornberger, Rolf
    Präsentiert den aktuellen Stand der Technik beim Einsatz von Computational Intelligence in der Lieferkette. Behandelt Probleme in den Bereichen Bestands- und Produktionsplanung, Scheduling, Transportplanung. Überprüft die verfügbare Software und Informationssysteme für jeden der behandelten Problembereiche.
    02 - Monographie
  • Vorschaubild
    Publikation
    Determination of weights for multiobjective combinatorial optimization in incident management with an evolutionary algorithm
    (IEEE, 2023) Gachnang, Phillip; Ehrenthal, Joachim; Telesko, Rainer; Hanne, Thomas
    Incident management in railway operations includes dealing with complex and multiobjective planning problems with numerous constraints, usually with incomplete information and under time pressure. An incident should be resolved quickly with minor deviations from the original plans and at acceptable costs. The problem formulation usually includes multiple objectives relevant to a railway company and the employees involved in controlling operations. Still, there is little established knowledge and agreement regarding the relative importance of objectives such as expressed by weights. Due to the difficulties in assessing weights in a multiobjective context directly involving decision makers, we elaborate on the autoconfiguration of weighted fitness functions based on nine objectives used in a related Integer Linear Programming (ILP) problem. Our approach proposes an evolutionary algorithm and tests it on real-world railway incident management data. The proposed method outperforms the baseline, where weights are equally distributed. Thus, the algorithm shows the capability to learn weights in future applications based on the priorities of employees solving railway incidents which is not yet possible due to an insufficient availability of real-life data from incident management. https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10339298&tag=1
    01A - Beitrag in wissenschaftlicher Zeitschrift
  • Vorschaubild
    Publikation
    Using the fuzzy best worst method for evaluating strategic planning models
    (MDPI, 2023) Ajripour, Iman; Hanne, Thomas
    During the last few decades, various strategic planning models have been suggested in the literature. It is difficult for a company to decide which of these models is most useful to adopt, as each of them shows different strengths and weaknesses. We consider this problem a multicriteria decision problem and investigate the evaluation of six strategic planning models in the context of smaller and medium-sized manufacturing companies in Iran. We consider a methodology that supports the analysis of the input from several decision-makers based on multiple criteria and assume vagueness in the input data elicited from them. For the purpose considered, the fuzzy best worst method (FBWM) appears appropriate. Based on a literature review, six evaluation criteria for strategic management models are considered: formality, clarity, measurability, objectivity, coverage, and consistency. These criteria are evaluated based on the input provided by thirteen managers using linguistic variables. FBWM is used to provide criteria weights that are used to determine fuzzy scores for the six considered strategic planning models. Finally, a defuzzification of the scores indicates the model by Wright is best suited for the application purpose. A consistency analysis included in FBWM shows that the input provided by the managers is sufficiently consistent.
    01A - Beitrag in wissenschaftlicher Zeitschrift