2893 research outputs found
Sort by
Image Analysis Using Human Body Geometry and Size Proportion Science for Action Classification
Get PDFGestures 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
Comparative Analysis of Artificial Intelligence Models for Accurate Estimation of Groundwater Nitrate Concentration
No full textPrediction of the groundwater nitrate concentration is of utmost importance for pollution control and water resource management. This research aims to model the spatial groundwater nitrate concentration in the Marvdasht watershed, Iran, based on several artificial intelligence methods of support vector machine (SVM), Cubist, random forest (RF), and Bayesian artificial neural network (Baysia-ANN) machine learning models. For this purpose, 11 independent variables affecting groundwater nitrate changes include elevation, slope, plan curvature, profile curvature, rainfall, piezometric depth, distance from the river, distance from residential, Sodium (Na), Potassium (K), and topographic wetness index (TWI) in the study area were prepared. Nitrate levels were also measured in 67 wells and used as a dependent variable for modeling. Data were divided into two categories of training (70%) and testing (30%) for modeling. The evaluation criteria coefficient of determination (R2), mean absolute error (MAE), root mean square error (RMSE), and Nash–Sutcliffe efficiency (NSE) were used to evaluate the performance of the models used. The results of modeling the susceptibility of groundwater nitrate concentration showed that the RF (R2 = 0.89, RMSE = 4.24, NSE = 0.87) model is better than the other Cubist (R2 = 0.87, RMSE = 5.18, NSE = 0.81), SVM (R2 = 0.74, RMSE = 6.07, NSE = 0.74), Bayesian-ANN (R2 = 0.79, RMSE = 5.91, NSE = 0.75) models. The results of groundwater nitrate concentration zoning in the study area showed that the northern parts of the case study have the highest amount of nitrate, which is higher in these agricultural areas than in other areas. The most important cause of nitrate pollution in these areas is agriculture activities and the use of groundwater to irrigate these crops and the wells close to agricultural areas, which has led to the indiscriminate use of chemical fertilizers by irrigation or rainwater of these fertilizers is washed and penetrates groundwater and pollutes the aquifer
Evaluating the Efficiency of Different Regression, Decision Tree, and Bayesian Machine Learning Algorithms in Spatial Piping Erosion Susceptibility Using ALOS/PALSAR Data
No full textPiping erosion is one form of water erosion that leads to significant changes in the landscape and environmental degradation. In the present study, we evaluated piping erosion modeling in the Zarandieh watershed of Markazi province in Iran based on random forest (RF), support vector machine (SVM), and Bayesian generalized linear models (Bayesian GLM) machine learning algorithms. For this goal, due to the importance of various geo-environmental and soil properties in the evolution and creation of piping erosion, 18 variables were considered for modeling the piping erosion susceptibility in the Zarandieh watershed. A total of 152 points of piping erosion were recognized in the study area that were divided into training (70%) and validation (30%) for modeling. The area under curve (AUC) was used to assess the effeciency of the RF, SVM, and Bayesian GLM. Piping erosion susceptibility results indicated that all three RF, SVM, and Bayesian GLM models had high efficiency in the testing step, such as the AUC shown with values of 0.9 for RF, 0.88 for SVM, and 0.87 for Bayesian GLM. Altitude, pH, and bulk density were the variables that had the greatest influence on the piping erosion susceptibility in the Zarandieh watershed. This result indicates that geo-environmental and soil chemical variables are accountable for the expansion of piping erosion in the Zarandieh watershed
Der Einfluss kommunaler Planung auf die Gestaltung von Neubauvorhaben am Beispiel der Weimarer Innenstadt
Get PDFDie massive Neubautätigkeit in Deutschland hat die Diskussion um Baukultur wieder verstärkt angestoßen. Dabei wird der Einfluss der kommunalen Planung auf die Baugestaltung sowohl in der Öffentlichkeit als auch der Fachliteratur nur unzureichend thematisiert. Die vorliegende Arbeit von Cornelius Hutfless untersucht die Thematik am konkreten Beispiel der Weimarer Innenstadt. Hierzu wurden die neun formellen und informellen Instrumente analysiert und bewertet, mit denen die kommunale Planung in Weimar seit dem Jahr 1990 unmittelbaren Einfluss auf die Baugestaltung von Neubauprojekten genommen hat: Bebauungspläne, der Denkmalschutz, Sanierungssatzungen, Gestaltungssatzungen, Wettbewerbe, der Gestaltungsbeirat, die Bauberatung, Fachkonzepte und die Öffentlichkeitsbeteiligung. Methodisch kamen die Quellenanalyse, die Fallanalyse und die Stärken-Schwächen-Analyse zum Einsatz. Die Recherchearbeit wurde durch sechs leitfadengestützte Expert*inneninterviews mit Schlüsselpersonen der Weimarer Baugestaltung ergänzt. Dieser Forschungsansatz veranschaulicht den Einfluss kommunaler Planung auf die Gestaltung von Neubauvorhaben erstmalig am Fallbeispiel einer einzelnen deutschen Stadt, indem alle angewendeten Instrumente analysiert wurden. Für Forscher*innen ermöglicht der Bezug auf ein konkretes Untersuchungsgebiet einen praxisnahen Zugang zum Thema Baugestaltung. Stadtplaner*innen veranschaulicht das Beispiel Weimar außerdem, wie umfangreich und restriktiv die kommunalen Möglichkeiten sind, auf die Baugestaltung einzuwirken. Vorbildlich im Sinne einer konsequenten Strategie der Baugestaltung sind in Weimar zum einen die strengen Festsetzungen in den Bebauungsplänen des Untersuchungsgebietes, deren Umsetzung durch die Einsetzung von Baubeiräten gesichert wird. Zum anderen ist der kommunalpolitische Rückhalt ein grundlegender Erfolgsfaktor, der u. a. den Empfehlungen des Gestaltungsbeirates Nachdruck verleiht. Zudem verfügt Weimar über eine umfangreiche Denkmalausweisung. Durch die umfassende Nutzung und Kombination der Instrumente, hat die kommunale Planung in Weimar erfolgreich einen Rahmen geschaffen, der baugestalterische Standards gewährleistet. Der Charakter der Weimarer Innenstadt konnte erhalten werden, obwohl moderne Neubauentwicklungen zugelassen wurden. Das Beispiel Weimar zeigt also, dass Baugestaltungsqualität wesentlich von dem klaren Anspruch einer Kommune nach Prozess- und Verfahrensqualität abhängt. Verbesserungswürdig ist in Weimar hingegen die Öffentlichkeitsbeteiligung bei Gestaltungsfragen. Schon vor der Schaffung planungsrechtlicher Tatsachen sollte zukünftig die Öffentlichkeit umfangreicher in Baugestaltungsprozesse eingebunden und dafür die Möglichkeiten ergänzender, informeller Verfahren ausgeschöpft werden. Nur dann ist eine restriktive Stadtgestaltungspolitik, im Sinne der Wahrung öffentlicher Interessen ganzheitlich positiv zu bewerten
Gesten des Denkens. Vilém Flussers Medienphilosophie
Get PDFIn einer systematischen Interpretation von Vilém Flussers Werk schlägt die Arbeit vor, Flussers Ansatz als einen medienphilosophischen zu verstehen, insofern er das „wie“ der medienphilosophischen Fragestellung in den Mittelpunkt rückt. Medien werden nicht erst dann zu einem wesentlichen Bestandteil von Flussers Philosophie, wenn er sie explizit zum Gegenstand seiner Untersuchungen der gegenwärtigen Kultur und Gesellschaft oder historischer Rückblicke macht; Denken vollzieht sich immer in Medien oder medialen Praktiken, es wird nicht nur von ihnen (mit) geprägt – ohne Medien gäbe es kein Denken und umgekehrt verändert sich Philosophie mit den (jeweils) neuen Medien. Ausgehend von Begriffen oder eher Denkfiguren, die neben dem „was“ des jeweils verhandelten Themas auch das „wie“ der Reflexion selbst adressieren, wird der „Umbruch in der Struktur des Denkens“ zugleich als Beschreibung von Medienumbrüchen verstanden – mit dem Fluchtpunkt des Sprungs in das Universum der Komputation – und als Vollzug der gegenwärtigen Veränderung der „Methode des Denkens“. Flussers (Ver)Suche einer Reflexion, die nicht mehr durch das Medium Schrift strukturiert ist, sondern sowohl alten Medien wie dem Bild – bzw. Praktiken des Abbildens, Darstellens, Einbildens usw. – als auch neuen Medien – dem Komputieren – Geltung verschafft, laufen auf eine widersprüchliche Diagnose des neuen Universums der Komputation (anders: der technischen Bilder) hinaus : eine kybermetisch inspirierte Vision der frei modellierbaren Wirklichkeit(en) einerseits und die Dystopie einer Welt, in der Apparaten Denken, Wahrnehmen und Handeln beherrschen andererseits. Die Arbeit zeigt auf, wie Flusser zu dieser Aporie der Medienreflexion – die weit über Flussers Werk hinaus virulent bleibt – gelangt und wie sie, ausgehend von seiner Figur der Geste, im Sinne einer performativen Medienreflexion gelöst werden könnte
Estimating longitudinal dispersion coefficient in natural streams using empirical models and machine learning algorithms
Get PDFThe longitudinal dispersion coefficient (LDC) plays an important role in modeling the transport of pollutants and sediment in natural rivers. As a result of transportation processes, the concentration of pollutants changes along the river. Various studies have been conducted to provide simple equations for estimating LDC. In this study, machine learning methods, namely support vector regression, Gaussian process regression, M5 model tree (M5P) and random forest, and multiple linear regression were examined in predicting the LDC in natural streams. Data sets from 60 rivers around the world with different hydraulic and geometric features were gathered to develop models for LDC estimation. Statistical criteria, including correlation coefficient (CC), root mean squared error (RMSE) and mean absolute error (MAE), were used to scrutinize the models. The LDC values estimated by these models were compared with the corresponding results of common empirical models. The Taylor chart was used to evaluate the models and the results showed that among the machine learning models, M5P had superior performance, with CC of 0.823, RMSE of 454.9 and MAE of 380.9. The model of Sahay and Dutta, with CC of 0.795, RMSE of 460.7 and MAE of 306.1, gave more precise results than the other empirical models. The main advantage of M5P models is their ability to provide practical formulae. In conclusion, the results proved that the developed M5P model with simple formulations was superior to other machine learning models and empirical models; therefore, it can be used as a proper tool for estimating the LDC in rivers
Short-Term Hydrological Drought Forecasting Based on Different Nature-Inspired Optimization Algorithms Hybridized With Artificial Neural Networks
No full textHydrological drought forecasting plays a substantial role in water resources management. Hydrological drought highly affects the water allocation and hydropower generation. In this research, short term hydrological drought forecasted based on the hybridized of novel nature-inspired optimization algorithms and Artificial Neural Networks (ANN). For this purpose, the Standardized Hydrological Drought Index (SHDI) and the Standardized Precipitation Index (SPI) were calculated in one, three, and six aggregated months. Then, three states where proposed for SHDI forecasting, and 36 input-output combinations were extracted based on the cross-correlation analysis. In the next step, newly proposed optimization algorithms, including Grasshopper Optimization Algorithm (GOA), Salp Swarm algorithm (SSA), Biogeography-based optimization (BBO), and Particle Swarm Optimization (PSO) hybridized with the ANN were utilized for SHDI forecasting and the results compared to the conventional ANN. Results indicated that the hybridized model outperformed compared to the conventional ANN. PSO performed better than the other optimization algorithms. The best models forecasted SHDI1 with R2 = 0.68 and RMSE = 0.58, SHDI3 with R 2 = 0.81 and RMSE = 0.45 and SHDI6 with R 2 = 0.82 and RMSE = 0.40
State of the art in damage information modeling for RC bridges – A literature review
No full textIn Germany, bridges have an average age of 40 years. A bridge consumes between 0.4% and 2% of its construction cost per year over its entire life cycle. This means that up to 80% of the construction cost are additionally needed for operation, inspection, maintenance, and destruction. Current practices rely either on paperbased inspections or on abstract specialist software. Every application in the inspection and maintenance sector uses its own data model for structures, inspections, defects, and maintenance. Due to this, data and properties have to be transferred manually, otherwise a converter is necessary for every data exchange between two applications. To overcome this issue, an adequate model standard for inspections, damage, and maintenance is necessary. Modern 3D models may serve as a single source of truth, which has been suggested in the Building Information Modeling (BIM) concept. Further, these models offer a clear visualization of the built infrastructure, and improve not only the planning and construction phases, but also the operation phase of construction projects. BIM is established mostly in the Architecture, Engineering, and Construction (AEC) sector to plan and construct new buildings. Currently, BIM does not cover the whole life cycle of a building, especially not inspection and maintenance. Creating damage models needs the building model first, because a defect is dependent on the building component, its properties and material. Hence, a building information model is necessary to obtain meaningful conclusions from damage information. This paper analyzes the requirements, which arise from practice, and the research that has been done in modeling damage and related information for bridges. With a look at damage categories and use cases related to inspection and maintenance, scientific literature is discussed and synthesized. Finally, research gaps and needs are identified and discussed
Synergistic Framework for Analysis and Model Assessment in Bridge Aerodynamics and Aeroelasticity
No full textWind-induced vibrations often represent a major design criterion for long-span bridges. This work deals with the assessment and development of models for aerodynamic and aeroelastic analyses of long-span bridges.
Computational Fluid Dynamics (CFD) and semi-analytical aerodynamic models are employed to compute the bridge response due to both turbulent and laminar free-stream. For the assessment of these models, a comparative methodology is developed that consists of two steps, a qualitative and a quantitative one. The first, qualitative, step involves an extension
of an existing approach based on Category Theory and its application to the field of bridge aerodynamics. Initially, the approach is extended to consider model comparability and completeness. Then, the complexity of the CFD and twelve semi-analytical models are evaluated based on their mathematical constructions, yielding a diagrammatic representation of model quality.
In the second, quantitative, step of the comparative methodology, the discrepancy of a system response quantity for time-dependent aerodynamic models is quantified using comparison metrics for time-histories. Nine metrics are established on a uniform basis to quantify the discrepancies in local and global signal features that are of interest in bridge aerodynamics. These signal features involve quantities such as phase, time-varying frequency and magnitude content, probability density, non-stationarity, and nonlinearity.
The two-dimensional (2D) Vortex Particle Method is used for the discretization of the Navier-Stokes equations including a Pseudo-three dimensional (Pseudo-3D) extension within an existing CFD solver. The Pseudo-3D Vortex Method considers the 3D structural behavior for aeroelastic analyses by positioning 2D fluid strips along a line-like structure. A novel turbulent Pseudo-3D Vortex Method is developed by combining the laminar Pseudo-3D VPM and a previously developed 2D method for the generation of free-stream turbulence. Using analytical derivations, it is shown that the fluid velocity correlation is maintained between the CFD strips.
Furthermore, a new method is presented for the determination of the complex aerodynamic admittance under deterministic sinusoidal gusts using the Vortex Particle Method. The sinusoidal gusts are simulated by modeling the wakes of flapping airfoils in the CFD domain with inflow vortex particles. Positioning a section downstream yields sinusoidal forces that are used for determining all six components of the complex aerodynamic admittance. A closed-form analytical relation is derived, based on an existing analytical model. With this relation, the inflow particles’ strength can be related with the target gust amplitudes a priori.
The developed methodologies are combined in a synergistic framework, which is applied to both fundamental examples and practical case studies. Where possible, the results are verified and validated. The outcome of this work is intended to shed some light on the complex wind–bridge interaction and suggest appropriate modeling strategies for an enhanced design