@article{ArtusAlabassyKoch, author = {Artus, Mathias and Alabassy, Mohamed Said Helmy and Koch, Christian}, title = {A BIM Based Framework for Damage Segmentation, Modeling, and Visualization Using IFC}, series = {Applied Sciences}, volume = {2022}, journal = {Applied Sciences}, number = {volume 12, issue 6, article 2772}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/app12062772}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20220314-46059}, pages = {1 -- 24}, abstract = {Paper-based data acquisition and manual transfer between incompatible software or data formats during inspections of bridges, as done currently, are time-consuming, error-prone, cumbersome, and lead to information loss. A fully digitized workflow using open data formats would reduce data loss, efforts, and the costs of future inspections. On the one hand, existing studies proposed methods to automatize data acquisition and visualization for inspections. These studies lack an open standard to make the gathered data available for other processes. On the other hand, several studies discuss data structures for exchanging damage information among different stakeholders. However, those studies do not cover the process of automatic data acquisition and transfer. This study focuses on a framework that incorporates automatic damage data acquisition, transfer, and a damage information model for data exchange. This enables inspectors to use damage data for subsequent analyses and simulations. The proposed framework shows the potentials for a comprehensive damage information model and related (semi-)automatic data acquisition and processing.}, subject = {Building Information Modeling}, language = {en} } @article{HarirchianKumariJadhavetal., author = {Harirchian, Ehsan and Kumari, Vandana and Jadhav, Kirti and Raj Das, Rohan and Rasulzade, Shahla and Lahmer, Tom}, title = {A Machine Learning Framework for Assessing Seismic Hazard Safety of Reinforced Concrete Buildings}, series = {Applied Sciences}, volume = {2020}, journal = {Applied Sciences}, number = {Volume 10, issue 20, article 7153}, publisher = {MDPI}, address = {Basel}, doi = {10.3390/app10207153}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20201022-42744}, pages = {18}, abstract = {Although averting a seismic disturbance and its physical, social, and economic disruption is practically impossible, using the advancements in computational science and numerical modeling shall equip humanity to predict its severity, understand the outcomes, and equip for post-disaster management. Many buildings exist amidst the developed metropolitan areas, which are senile and still in service. These buildings were also designed before establishing national seismic codes or without the introduction of construction regulations. In that case, risk reduction is significant for developing alternatives and designing suitable models to enhance the existing structure's performance. Such models will be able to classify risks and casualties related to possible earthquakes through emergency preparation. Thus, it is crucial to recognize structures that are susceptible to earthquake vibrations and need to be prioritized for retrofitting. However, each building's behavior under seismic actions cannot be studied through performing structural analysis, as it might be unrealistic because of the rigorous computations, long period, and substantial expenditure. Therefore, it calls for a simple, reliable, and accurate process known as Rapid Visual Screening (RVS), which serves as a primary screening platform, including an optimum number of seismic parameters and predetermined performance damage conditions for structures. In this study, the damage classification technique was studied, and the efficacy of the Machine Learning (ML) method in damage prediction via a Support Vector Machine (SVM) model was explored. The ML model is trained and tested separately on damage data from four different earthquakes, namely Ecuador, Haiti, Nepal, and South Korea. Each dataset consists of varying numbers of input data and eight performance modifiers. Based on the study and the results, the ML model using SVM classifies the given input data into the belonging classes and accomplishes the performance on hazard safety evaluation of buildings.}, subject = {Erdbeben}, language = {en} } @unpublished{MosaviTorabiHashemietal., author = {Mosavi, Amir and Torabi, Mehrnoosh and Hashemi, Sattar and Saybani, Mahmoud Reza and Shamshirband, Shahaboddin}, title = {A Hybrid Clustering and Classification Technique for Forecasting Short-Term Energy Consumption}, doi = {10.25643/bauhaus-universitaet.3755}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20180907-37550}, abstract = {Electrical energy distributor companies in Iran have to announce their energy demand at least three 3-day ahead of the market opening. Therefore, an accurate load estimation is highly crucial. This research invoked methodology based on CRISP data mining and used SVM, ANN, and CBA-ANN-SVM (a novel hybrid model of clustering with both widely used ANN and SVM) to predict short-term electrical energy demand of Bandarabbas. In previous studies, researchers introduced few effective parameters with no reasonable error about Bandarabbas power consumption. In this research we tried to recognize all efficient parameters and with the use of CBA-ANN-SVM model, the rate of error has been minimized. After consulting with experts in the field of power consumption and plotting daily power consumption for each week, this research showed that official holidays and weekends have impact on the power consumption. When the weather gets warmer, the consumption of electrical energy increases due to turning on electrical air conditioner. Also, con-sumption patterns in warm and cold months are different. Analyzing power consumption of the same month for different years had shown high similarity in power consumption patterns. Factors with high impact on power consumption were identified and statistical methods were utilized to prove their impacts. Using SVM, ANN and CBA-ANN-SVM, the model was built. Sine the proposed method (CBA-ANN-SVM) has low MAPE 5 1.474 (4 clusters) and MAPE 5 1.297 (3 clusters) in comparison with SVM (MAPE 5 2.015) and ANN (MAPE 5 1.790), this model was selected as the final model. The final model has the benefits from both models and the benefits of clustering. Clustering algorithm with discovering data structure, divides data into several clusters based on similarities and differences between them. Because data inside each cluster are more similar than entire data, modeling in each cluster will present better results. For future research, we suggest using fuzzy methods and genetic algorithm or a hybrid of both to forecast each cluster. It is also possible to use fuzzy methods or genetic algorithms or a hybrid of both without using clustering. It is issued that such models will produce better and more accurate results. This paper presents a hybrid approach to predict the electric energy usage of weather-sensitive loads. The presented methodutilizes the clustering paradigm along with ANN and SVMapproaches for accurate short-term prediction of electric energyusage, using weather data. Since the methodology beinginvoked in this research is based on CRISP data mining, datapreparation has received a gr eat deal of attention in thisresear ch. Once data pre-processing was done, the underlyingpattern of electric energy consumption was extracted by themeans of machine learning methods to precisely forecast short-term energy consumption. The proposed approach (CBA-ANN-SVM) was applied to real load data and resulting higher accu-racy comparing to the existing models. 2018 American Institute of Chemical Engineers Environ Prog, 2018 https://doi.org/10.1002/ep.12934}, subject = {Data Mining}, language = {en} } @phdthesis{Anderka, author = {Anderka, Maik}, title = {Analyzing and Predicting Quality Flaws in User-generated Content: The Case of Wikipedia}, doi = {10.25643/bauhaus-universitaet.1977}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20130709-19778}, school = {Bauhaus-Universit{\"a}t Weimar}, abstract = {Web applications that are based on user-generated content are often criticized for containing low-quality information; a popular example is the online encyclopedia Wikipedia. The major points of criticism pertain to the accuracy, neutrality, and reliability of information. The identification of low-quality information is an important task since for a huge number of people around the world it has become a habit to first visit Wikipedia in case of an information need. Existing research on quality assessment in Wikipedia either investigates only small samples of articles, or else deals with the classification of content into high-quality or low-quality. This thesis goes further, it targets the investigation of quality flaws, thus providing specific indications of the respects in which low-quality content needs improvement. The original contributions of this thesis, which relate to the fields of user-generated content analysis, data mining, and machine learning, can be summarized as follows: (1) We propose the investigation of quality flaws in Wikipedia based on user-defined cleanup tags. Cleanup tags are commonly used in the Wikipedia community to tag content that has some shortcomings. Our approach is based on the hypothesis that each cleanup tag defines a particular quality flaw. (2) We provide the first comprehensive breakdown of Wikipedia's quality flaw structure. We present a flaw organization schema, and we conduct an extensive exploratory data analysis which reveals (a) the flaws that actually exist, (b) the distribution of flaws in Wikipedia, and, (c) the extent of flawed content. (3) We present the first breakdown of Wikipedia's quality flaw evolution. We consider the entire history of the English Wikipedia from 2001 to 2012, which comprises more than 508 million page revisions, summing up to 7.9 TB. Our analysis reveals (a) how the incidence and the extent of flaws have evolved, and, (b) how the handling and the perception of flaws have changed over time. (4) We are the first who operationalize an algorithmic prediction of quality flaws in Wikipedia. We cast quality flaw prediction as a one-class classification problem, develop a tailored quality flaw model, and employ a dedicated one-class machine learning approach. A comprehensive evaluation based on human-labeled Wikipedia articles underlines the practical applicability of our approach.}, subject = {Data Mining}, language = {en} } @phdthesis{Lipka, author = {Lipka, Nedim}, title = {Modeling Non-Standard Text Classification Tasks}, doi = {10.25643/bauhaus-universitaet.1862}, url = {http://nbn-resolving.de/urn:nbn:de:gbv:wim2-20130307-18626}, school = {Bauhaus-Universit{\"a}t Weimar}, abstract = {Text classification deals with discovering knowledge in texts and is used for extracting, filtering, or retrieving information in streams and collections. The discovery of knowledge is operationalized by modeling text classification tasks, which is mainly a human-driven engineering process. The outcome of this process, a text classification model, is used to inductively learn a text classification solution from a priori classified examples. The building blocks of modeling text classification tasks cover four aspects: (1) the way examples are represented, (2) the way examples are selected, (3) the way classifiers learn from examples, and (4) the way models are selected. This thesis proposes methods that improve the prediction quality of text classification solutions for unseen examples, especially for non-standard tasks where standard models do not fit. The original contributions are related to the aforementioned building blocks: (1) Several topic-orthogonal text representations are studied in the context of non-standard tasks and a new representation, namely co-stems, is introduced. (2) A new active learning strategy that goes beyond standard sampling is examined. (3) A new one-class ensemble for improving the effectiveness of one-class classification is proposed. (4) A new model selection framework to cope with subclass distribution shifts that occur in dynamic environments is introduced.}, subject = {Text Classification}, language = {en} }