000 Informatik, Informationswissenschaft, allgemeine Werke
Refine
Has Fulltext
- yes (38) (remove)
Document Type
- Article (38) (remove)
Institute
- Institut für Strukturmechanik (ISM) (16)
- Junior-Professur Computational Architecture (9)
- Professur Informatik in der Architektur (5)
- Bauhaus-Institut für zukunftsweisende Infrastruktursysteme (b.is) (1)
- Junior-Professur Augmented Reality (1)
- Materialforschungs- und -prüfanstalt an der Bauhaus-Universität (1)
- Professur Kulturgeschichte der Moderne (1)
- Professur Modellierung und Simulation - Konstruktion (1)
- Professur Siedlungswasserwirtschaft (1)
- Theorie und Geschichte des Design (1)
Keywords
- Maschinelles Lernen (10)
- Machine learning (7)
- Deep learning (4)
- OA-Publikationsfonds2020 (4)
- machine learning (4)
- Architektur (3)
- OA-Publikationsfonds2018 (3)
- CAD (2)
- Computational Urban Design (2)
- Künstliche Intelligenz (2)
The release of the large language model-based chatbot ChatGPT 3.5 in November 2022 has brought considerable attention to the subject of artificial intelligence, not only to the public. From the perspective of higher education, ChatGPT challenges various learning and assessment formats as it significantly reduces the effectiveness of their learning and assessment functionalities. In particular, ChatGPT might be applied to formats that require learners to generate text, such as bachelor theses or student research papers. Accordingly, the research question arises to what extent writing of bachelor theses is still a valid learning and assessment format. Correspondingly, in this exploratory study, the first author was asked to write his bachelor’s thesis exploiting ChatGPT. For tracing the impact of ChatGPT methodically, an autoethnographic approach was used. First, all considerations on the potential use of ChatGPT were documented in logs, and second, all ChatGPT chats were logged. Both logs and chat histories were analyzed and are presented along with the recommendations for students regarding the use of ChatGPT suggested by a common framework. In conclusion, ChatGPT is beneficial for thesis writing during various activities, such as brainstorming, structuring, and text revision. However, there are limitations that arise, e.g., in referencing. Thus, ChatGPT requires continuous validation of the outcomes generated and thus fosters learning. Currently, ChatGPT is valued as a beneficial tool in thesis writing. However, writing a conclusive thesis still requires the learner’s meaningful engagement. Accordingly, writing a thesis is still a valid learning and assessment format. With further releases of ChatGPT, an increase in capabilities is to be expected, and the research question needs to be reevaluated from time to time.
Zu den diversen Unternehmungen sozialbewegter „Gegenwissenschaft“, die um 1980 auf der Bildfläche der BRD erschienen, zählte der 1982 gegründete Berliner Wissenschaftsladen e. V., kurz WILAB – eine Art „alternatives“ Spin-off der Technischen Universität Berlin. Der vorliegende Beitrag situiert die Ausgründung des „Ladens“ im Kontext zeitgenössischer Fortschritte der (regionalen) Forschungs- und Technologiepolitik. Gezeigt wird, wie der deindustrialisierenden Inselstadt, qua „innovationspolitischer“ Gegensteuerung, dabei sogar eine gewisse Vorreiterrolle zukam: über die Stadtgrenzen hinaus sichtbare Neuerungen wie die Gründermesse BIG TECH oder das 1983 eröffnete Berliner Innovations- und Gründerzentrum (BIG), der erste „Incubator“ [sic] der BRD, etwa gingen auf das Konto der 1977/78 lancierten Technologie-Transferstelle der TU Berlin, TU-transfer.
Anders gesagt: tendenziell bekam man es hier nun mit Verhältnissen zu tun, die immer weniger mit den Träumen einer „kritischen“, nicht-fremdbestimmten (Gegen‑)Wissenschaft kompatibel waren. Latent konträr zur historiographischen Prominenz des wissenschaftskritischen Zeitgeists fristeten „alternativen“ Zielsetzungen verpflichtete Unternehmungen wie „WILAB“ ein relativ marginalisiertes Nischendasein. Dennoch wirft das am WILAB verfolgte, so gesehen wenig aussichtsreiche Anliegen, eine andere, nämlich „humanere“ Informationstechnologie in die Wege zu leiten, ein instruktives Licht auf die Aufbrüche „unternehmerischer“ Wissenschaft in der BRD um 1980.
This paper outlines an important step in characterizing a novel field of robotic construction research where a cable-driven parallel robot is used to extrude cementitious material in three-dimensional space, and thus offering a comprehensive new approach to computational design and construction, and to robotic fabrication at larger scales. Developed by the Faculty of Art and Design at Bauhaus-University Weimar (Germany), the faculty of Architecture at the University of Applied Sciences Dortmund (Germany) and the Chair of Mechatronics at the University of Duisburg-Essen (Germany), this approach offers unique advantages over existing additive manufacturing methods: the system is easily transportable and scalable, it does not require additional formwork or scaffolding, and it offers digital integration and informational oversight across the entire design and building process. This paper considers 1) key research components of cable robotic 3D-printing (such as computational design, material exploration, and robotic control), and 2) the integration of these parameters into a unified design and building process. The demonstration of the approach at full-scale is of particular concern.
Multi-criteria decision analysis (MCDA) is an established methodology to support the decision-making of multi-objective problems. For conducting an MCDA, in most cases, a set of objectives (SOO) is required, which consists of a hierarchical structure comprised of objectives, criteria, and indicators. The development of an SOO is usually based on moderated development processes requiring high organizational and cognitive effort from all stakeholders involved. This article proposes elementary interactions as a key paradigm of an algorithm-driven development process for an SOO that requires little moderation efforts. Elementary interactions are self-contained information requests that may be answered with little cognitive effort. The pairwise comparison of elements in the well-known analytical hierarchical process (AHP) is an example of an elementary interaction. Each elementary interaction in the development process presented contributes to the stepwise development of an SOO. Based on the hypothesis that an SOO may be developed exclusively using elementary interactions (EIs), a concept for a multi-user platform is proposed. Essential components of the platform are a Model Aggregator, an Elementary Interaction Stream Generator, a Participant Manager, and a Discussion Forum. While the latter component serves the professional exchange of the participants, the first three components are intended to be automatable by algorithms. The platform concept proposed has been evaluated partly in an explorative validation study demonstrating the general functionality of the algorithms outlined. In summary, the platform concept suggested demonstrates the potential to ease SOO development processes as the platform concept does not restrict the application domain; it is intended to work with little administration moderation efforts, and it supports the further development of an existing SOO in the event of changes in external conditions. The algorithm-driven development of SOOs proposed in this article may ease the development of MCDA applications and, thus, may have a positive effect on the spread of MCDA applications.
Polylactic acid (PLA) is a highly applicable material that is used in 3D printers due to some significant features such as its deformation property and affordable cost. For improvement of the end-use quality, it is of significant importance to enhance the quality of fused filament fabrication (FFF)-printed objects in PLA. The purpose of this investigation was to boost toughness and to reduce the production cost of the FFF-printed tensile test samples with the desired part thickness. To remove the need for numerous and idle printing samples, the response surface method (RSM) was used. Statistical analysis was performed to deal with this concern by considering extruder temperature (ET), infill percentage (IP), and layer thickness (LT) as controlled factors. The artificial intelligence method of artificial neural network (ANN) and ANN-genetic algorithm (ANN-GA) were further developed to estimate the toughness, part thickness, and production-cost-dependent variables. Results were evaluated by correlation coefficient and RMSE values. According to the modeling results, ANN-GA as a hybrid machine learning (ML) technique could enhance the accuracy of modeling by about 7.5, 11.5, and 4.5% for toughness, part thickness, and production cost, respectively, in comparison with those for the single ANN method. On the other hand, the optimization results confirm that the optimized specimen is cost-effective and able to comparatively undergo deformation, which enables the usability of printed PLA objects.
This research aims to model soil temperature (ST) using machine learning models of multilayer perceptron (MLP) algorithm and support vector machine (SVM) in hybrid form with the Firefly optimization algorithm, i.e. MLP-FFA and SVM-FFA. In the current study, measured ST and meteorological parameters of Tabriz and Ahar weather stations in a period of 2013–2015 are used for training and testing of the studied models with one and two days as a delay. To ascertain conclusive results for validation of the proposed hybrid models, the error metrics are benchmarked in an independent testing period. Moreover, Taylor diagrams utilized for that purpose. Obtained results showed that, in a case of one day delay, except in predicting ST at 5 cm below the soil surface (ST5cm) at Tabriz station, MLP-FFA produced superior results compared with MLP, SVM, and SVM-FFA models. However, for two days delay, MLP-FFA indicated increased accuracy in predicting ST5cm and ST 20cm of Tabriz station and ST10cm of Ahar station in comparison with SVM-FFA. Additionally, for all of the prescribed models, the performance of the MLP-FFA and SVM-FFA hybrid models in the testing phase was found to be meaningfully superior to the classical MLP and SVM models.
Image Analysis Using Human Body Geometry and Size Proportion Science for Action Classification
(2020)
Gestures are one of the basic modes of human communication and are usually used to represent different actions. Automatic recognition of these actions forms the basis for solving more complex problems like human behavior analysis, video surveillance, event detection, and sign language recognition, etc. Action recognition from images is a challenging task as the key information like temporal data, object trajectory, and optical flow are not available in still images. While measuring the size of different regions of the human body i.e., step size, arms span, length of the arm, forearm, and hand, etc., provides valuable clues for identification of the human actions. In this article, a framework for classification of the human actions is presented where humans are detected and localized through faster region-convolutional neural networks followed by morphological image processing techniques. Furthermore, geometric features from human blob are extracted and incorporated into the classification rules for the six human actions i.e., standing, walking, single-hand side wave, single-hand top wave, both hands side wave, and both hands top wave. The performance of the proposed technique has been evaluated using precision, recall, omission error, and commission error. The proposed technique has been comparatively analyzed in terms of overall accuracy with existing approaches showing that it performs well in contrast to its counterparts.
The economic losses from earthquakes tend to hit the national economy considerably; therefore, models that are capable of estimating the vulnerability and losses of future earthquakes are highly consequential for emergency planners with the purpose of risk mitigation. This demands a mass prioritization filtering of structures to identify vulnerable buildings for retrofitting purposes. The application of advanced structural analysis on each building to study the earthquake response is impractical due to complex calculations, long computational time, and exorbitant cost. This exhibits the need for a fast, reliable, and rapid method, commonly known as Rapid Visual Screening (RVS). The method serves as a preliminary screening platform, using an optimum number of seismic parameters of the structure and predefined output damage states. In this study, the efficacy of the Machine Learning (ML) application in damage prediction through a Support Vector Machine (SVM) model as the damage classification technique has been investigated. The developed model was trained and examined based on damage data from the 1999 Düzce Earthquake in Turkey, where the building’s data consists of 22 performance modifiers that have been implemented with supervised machine learning.
Wind effects can be critical for the design of lifelines such as long-span bridges. The existence of a significant number of aerodynamic force models, used to assess the performance of bridges, poses an important question regarding their comparison and validation. This study utilizes a unified set of metrics for a quantitative comparison of time-histories in bridge aerodynamics with a host of characteristics. Accordingly, nine comparison metrics are included to quantify the discrepancies in local and global signal features such as phase, time-varying frequency and magnitude content, probability density, nonstationarity and nonlinearity. Among these, seven metrics available in the literature are introduced after recasting them for time-histories associated with bridge aerodynamics. Two additional metrics are established to overcome the shortcomings of the existing metrics. The performance of the comparison metrics is first assessed using generic signals with prescribed signal features. Subsequently, the metrics are applied to a practical example from bridge aerodynamics to quantify the discrepancies in the aerodynamic forces and response based on numerical and semi-analytical aerodynamic models. In this context, it is demonstrated how a discussion based on the set of comparison metrics presented here can aid a model evaluation by offering deeper insight. The outcome of the study is intended to provide a framework for quantitative comparison and validation of aerodynamic models based on the underlying physics of fluid-structure interaction. Immediate further applications are expected for the comparison of time-histories that are simulated by data-driven approaches.
In this study, machine learning methods of artificial neural networks (ANNs), least squares support vector machines (LSSVM), and neuro-fuzzy are used for advancing prediction models for thermal performance of a photovoltaic-thermal solar collector (PV/T). In the proposed models, the inlet temperature, flow rate, heat, solar radiation, and the sun heat have been considered as the input variables. Data set has been extracted through experimental measurements from a novel solar collector system. Different analyses are performed to examine the credibility of the introduced models and evaluate their performances. The proposed LSSVM model outperformed the ANFIS and ANNs models. LSSVM model is reported suitable when the laboratory measurements are costly and time-consuming, or achieving such values requires sophisticated interpretations.