Abstract
The average ranking method (AR) is one of the simplest and effective algorithms selection methods. This method uses metadata in the form of test results of a given set of algorithms on a given set of datasets and calculates an average rank for each algorithm. The ranks are used to construct the average ranking. In this paper we investigate the problem of how the rankings can be reduced by removing non-competitive and redundant algorithms, thereby reducing the number of tests a user needs to conduct on a new dataset to identify the most suitable algorithm. The method proposed involves two phases. In the first one, the aim is to identify the most competitive algorithms for each dataset used in the past. This is done with the recourse to a statistical test. The second phase involves a covering method whose aim is to reduce the algorithms by eliminating redundant variants. The proposed method differs from one earlier proposal in various aspects. One important one is that it takes both accuracy and time into consideration. The proposed method was compared to the baseline strategy which consists of executing all algorithms from the ranking. It is shown that the proposed method leads to much better performance than the baseline.

Abstract
Recently, soft attention mechanisms have been successfully used in a wide variety of applications such as the generation of image captions, text translation, etc. This mechanism attempts to mimic the visual cortex of a human brain by not analyzing all the objects in a scene equally, but by looking for clues (or salient features) which might give a more compact representation of the environment. In doing so, the human brain can process information more quickly and without overloading. Having learned this lesson, in this paper, we try to make a bridge from the visual to the audio scene classification problem, namely the classification of heart sound signals. To do so, a novel approach merging soft attention mechanisms and recurrent neural nets is proposed. Using the proposed methodology, the algorithm can successfully learn automatically significant audio segments when detecting and classifying abnormal heart sound signals, both improving these classification results and somehow creating a simple justification for them.

Abstract
Information provided by geotagged photos allow us to know where and when people have been, supporting a better understanding about tourist's movement patterns across a destination. The aim of this paper is to study tourists' movement patterns during their staying in Porto through the analysis of geotagged photos in order to fulfill marketing segmentation in an innovative way. For that purpose, the SPADE algorithm was used to find sequence patterns of tourists paths based on the time and location of the photos collected. Then, the K-Mode clustering algorithm was applied to these sequences in order to find identical behaviors in terms of paths followed by tourists. At the same time, in order to understand the influence of the different attractions on tourists' paths, we performed a Social Network Analysis of the touristic attractions (spots, museums, streets, monuments, etc.). Based on the time and location of the photos collected, along with personal information, it was possible to understand tourists' frequent movements across the city and to identify market segments based on a hybrid strategy.

Abstract
The automation of tasks is increasingly a current practice in the organizational environment, and this practice reduces the need for manpower and often reduces the errors associated with the human factor. In the present document a solution will be presented to automatically generate the source code of a mockup, having as input an image corresponding to the prototype. In the development of this project techniques of Deep Learning will be used, especially Convolutional Neural Networks for the detection and classification of objects in images. The developed solution provides the code base of a mockup in less than 60 seconds, with an average error rate 15.85%.

Abstract
Grapevine yield prediction during phenostage and particularly, before harvest is highly significant as advanced forecasting could be a great value for superior grapevine management. The main contribution of the current study is to develop predictive model for each phenology that predicts yield during growing stages of grapevine and to identify highly relevant predictive variables. Current study uses climatic conditions, grapevine yield, phenological dates, fertilizer information, soil analysis and maturation index data to construct the relational dataset. After words, we use several approaches to pre-process the data to put it into tabular format. For instance, generalization of climatic variables using phenological dates. Random Forest, LASSO and Elasticnet in generalized linear models, and Spikeslab are feature selection embedded methods which are used to overcome dataset dimensionality issue. We used 10-fold cross validation to evaluate predictive model by partitioning the dataset into training set to train the model and test set to evaluate it by calculating Root Mean Squared Error (RMSE) and Relative Root Mean Squared Error (RRMSE). Results of the study show that rf_PF, rf_PC and rf_MH are optimal models for flowering (PF), colouring (PC) and harvest (MH) phenology respectively which estimate 1484.5, 1504.2 and 1459.4 (Kg/ha) low RMSE and 24.6%, 24.9% and 24.2% RRMSE, respectively as compared to other models. These models also identify some derived climatic variables as major variables for grapevine yield prediction. The reliability and early-indication ability of these forecast models justify their use by institutions and economists in decision making, adoption of technical improvements, and fraud detection. © 2019 Asian Agricultural and Biological Engineering Association

Abstract
The objective of this study is to understand to what extent hedonic and utilitarian consumer profiles are affected by situational factors and how in turn they impact shopping centre patronage. A six step multiple regression analysis corresponding to six different shopping centres has been applied to two clusters of consumers. The data are based on consumers' hedonic/utilitarian customer profile. First, results show that in general the impact on shopping centre patronage is largely affected by proximity, convenience and accessibility variables, which are more relevant among the utilitarian profile consumers. On the other hand, in the hedonic profile segment, affect, that is, the experience of feeling or emotion is the relevant variable explaining patronage. Second, the predictive contribution of these variables on patronage varied according to the shopping centres' positioning. With the findings of the present study, retail managers can formulate marketing strategies, which will attract retail consumers towards their shopping centre and also help them to enhance the significant factors that influence retail store consumer's purchase decision. Also, this investigation contributes to the diagnosis of how consistent is the retailers' in their positioning strategy in targeting the market segments. The present research integrates both situational factors and hedonic as well as utilitarian consumer profiles along with the role of situational dynamics to explain shopping centres' patronage.