Miloš Kovačević

Landslide Susceptibility Assessment with Machine Learning Algorithms

Case study addresses NW slopes of Fruška GoraMountain, Serbia. Landslide activity is quite notorious in this region, especially along the Danube’s right river bank, and recently intensified seismicity coupled with atmospheric precipitation might be critical for triggering new landslide occurrences. Hence, it is not a moment too soon for serious landslide susceptibility assessment in this region. State-of-the-art approaches had been taken into consideration, cutting down to the Support Vector Machine (SVM) and k-Nearest Neighbor (k-NN) algorithms, trained upon expert based model of landslide susceptibility (a multi-criteria analysis). The latter involved Analytical Hierarchy Process (AHP) for weighting influences of different input parameters. These included elevation, slope angle, aspect, distance from flows, vegetation cover, lithology, and rainfall, to represent the natural factors of the slope stability. Processed in a GIS environment (as discrete or float raster layers) trough AHP, those parameters yielded susceptibility pattern, classified by the entropy model into four classes. Subsequently the susceptibility pattern has been featured as training set in SVM and k-NN algorithms. Detailed fitting involved several cases, among which SVM with Gaussian kernel over geo-dataset (coordinates and input parameters) reached the highest accuracy (88%)outperforming other considered cases by far.

Geological Units Classification of Multispectral Images by Using Support Vector Machines

Quantitative techniques for spatial prediction and classification in geological survey are developing rapidly. The recent applications of machine learning techniques confirm possibilities of their application in this field of research. The paper introduces Support Vector Machines, a method derived from recent achievements in the statistical learning theory, in classification of geological units based on the source of the Landsat multispectral images. The initial experiments suggest the usefulness of the proposed classification approach.

Modeling Urban Land Use Changes Using Support Vector Machines

Support Vector Machines (SVM) is a machine learning (ML) algorithm commonly applied to the classification of remotely sensing data and more recently for modeling land use changes. However, in most geospatial applications the current literature does not elaborate on specifications of the SVM method with respect to data sampling, attribute selection and optimal parameters choices. Therefore the main objective of this study is to present and investigate the SVM technique for modeling urban land use change. The SVM model building procedure is presented together with the detailed evaluation of the output results with respect to the choice of datasets, attributes and the change of SVM parameters. Geospatial datasets containing nine land use classes and spatial attributes for the Municipality of Zemun, Republic of Serbia were used for years 2001, 2003, 2007 and 2011. The Correlation-based Feature Subset method, kappa coefficient, Area Under Receiver Operating Characteristic Curve (AUC) and kappa simulation were used to perform the model evaluation and compare the model outputs with the real land use datasets. The obtained results indicate that the SVM-based models perform better when implementing balanced data sampling, reduced data sets to informative subsets of attributes and properly identify the optimal learning parameters.

The successful delivery of megaprojects: a novel research method

Megaprojects are often associated with poor delivery performance and poor benefits realization. This article provides a method of identifying, in a quantitative and rigorous manner, the characteristics related to project management success in megaprojects. It provides an investigation of how stakeholders can use this knowledge to ensure more effective design and delivery for megaprojects. The research is grounded in 44 mega-projects and a systematic, empirically based methodology that employs the Fishers exact test and machine learning techniques to identify the correlation between megaprojects’ characteristics and performance, paving the way to an understanding of their causation.

Searching for web information more efficiently using presentational layout analysis

Extracting and processing information from web pages is an important task in many areas such as constructing search engines, information retrieval, and data mining from the web. A common approach in the extraction process is to represent a page as a bag of words and then to perform additional processing on such a flat representation. In this paper, we propose a new, hierarchical representation that includes browser screen coordinates for every HTML object on a page. Using visual information one is able to define heuristics for recognition of common page areas such as a header, left and right menu, footer and the centre of a page. Initial experiments have shown that, using our heuristics, defined areas are recognised properly in 73%; of cases. Finally, we introduce a classification system which, taking into account the proposed document layout analysis clearly outperforms standard systems by 10%; or more.

CRAWLING THE CONSTRUCTION WEB-A MACHINE-LEARNING APPROACH WITHOUT NEGATIVE EXAMPLES

Professionals and craftsmen in the construction sector make an intensive use of information in their decision-making processes but only make limited use of the abundant information that is potentially available to them, particularly on the web. Consequently, designs are impoverished, construction is defective, and innovation is delayed. To facilitate convivial access to focused information, we have developed a question-and-answer (Q-A) system (reported elsewhere). To support this system, we have developed an automated crawler that permits the establishment of a bank of relevant pages, adapted to the needs of this particular industry-user community. It is based on the machine-learning framework in which an intelligent decision unit is trained to distinguish between nontopic and informative pages. We show that standard approaches which use both positive and negative classes are sensitive to the noise in the negative class. We propose different techniques for learning without negative examples, since initially one only has limited, positive information labeled by human experts; they are evaluated. Our crawler that uses the positive examples-based learning (PEBL) framework is able to collect construction-oriented pages with high precision and discovery rate. It can also be used to build domain-specific collections of pages in different scientific or professional contexts.

Machine Learning and Landslide Assessment in a GIS Environment

This chapter introduces theoretical and practical aspects for applying GIS and geocomputation methods in landslide assessment problems. Machine Learning techniques in combination with GIS are proven useful for computation and building of complex non-linear spatial models, which is why they have been chosen in our work. Modeling principles that include basic Machine Learning techniques (Artificial Neural Networks, Decision trees, Support Vector Machines) and additional useful procedures are described to show how they can be applied to address a complex problem such as landslide assessment. Two types of models are proposed in the work herein that are useful for describing landslide susceptibility and landslide prediction. The region of Halenkovice in Czech Republic is presented as a case study to illustrate and bring closer the practical aspects of landslide assessment. These aspects consider data preparation and preprocessing, scale effects, model optimization, and evaluation. The results show that Support Vector Machines and similar Machine Learning (ML) techniques can be successfully applied to address the zoning of landslide susceptibility, which might be an important breakthrough for potential applications in regional planning and decision-making.

Building a Construction Project Key-Phrase Network from Unstructured Text Documents

AbstractDuring a construction project lifecycle, an extensive corpus of unstructured or semistructured text documents is generated. The nature of unstructured sources impedes users’ acquisition, an...

Machine Learning Techniques for Modelling Short Term Land-Use Change

The representation of land use change (LUC) is often achieved by using data-driven methods that include machine learning (ML) techniques. The main objectives of this research study are to implement three ML techniques, Decision Trees (DT), Neural Networks (NN), and Support Vector Machines (SVM) for LUC modeling, in order to compare these three ML techniques and to find the appropriate data representation. The ML techniques are applied on the case study of LUC in three municipalities of the City of Belgrade, the Republic of Serbia, using historical geospatial data sets and considering nine land use classes. The ML models were built and assessed using two different time intervals. The information gain ranking technique and the recursive attribute elimination procedure were implemented to find the most informative attributes that were related to LUC in the study area. The results indicate that all three ML techniques can be used effectively for short-term forecasting of LUC, but the SVM achieved the highest agreement of predicted changes.