0020-0255/$ see front matter 2012 Elsevier Inc http://dx.doi.org/10.1016/j.ins.2012.10.039 ⇑ Corresponding author. E-mail addresses: [email protected] (P. Cor In this paper, we propose a new visualization approach based on a Sensitivity Analysis (SA) to extract human understandable knowledge from supervised learning black box data mining models, such as Neural Networks (NNs), Support Vector...

Machine vision based on deep learning is gaining more and applications in structural health monitoring (SHM) due to the rich information that can be achieved images. Bolts are widely used connection of steel structures, their loosening compromise safety structures lead serious accidents. Therefore, this paper proposes a method for automatic detection bolt angle latest key point technology using...

the improvement in the temporal resolution of seismic data is a critical issue in hydrocarbonexploration. it is important for obtaining more detailed structural and stratigraphic information. manymethods have been introduced to improve the vertical resolution of reflection seismic data. eachmethod has advantages and disadvantages which are due to the assumptions and theories governingtheir issu...

Fuzzy C-mean (FCM) is the most well-known and widely-used fuzzy clustering algorithm. However, one of the weaknesses of the FCM is the way it assigns membership degrees to data which is based on the distance to the cluster centers. Unfortunately, the membership degrees are determined without considering the shape and density of the clusters. In this paper, we propose an algorithm which takes th...

In the context of a spatiotemporal research environment, it is very important to be able to systematically generate data with predictable characteristics. For instance, it allows one to use the same datasets, or others similarly characterized, for benchmarking access structures or mining techniques. This paper presents a survey of existing generators of synthetic spatiotemporal data. It also co...