Pointwise and pairwise clothing annotation: combining features from social media

In this paper, we present effective algorithms to automatically annotate clothes from social media data, such as Facebook and Instagram. Clothing annotation can be informally stated as recognizing, as accurately as possible, the garment items appearing in the query photo. This task brings huge opportunities for recommender and e-commerce systems, such as capturing new fashion trends based on which clothes have been used more recently. It also poses interesting challenges for existing vision and recognition algorithms, such as distinguishing between similar but different types of clothes or identifying a pattern of a cloth even if it has different colors and shapes. We formulate the annotation task as a multi-label and multi-modal classification problem: (i) both image and textual content (i.e., tags about the image) are available for learning classifiers, (ii) the classifiers must recognize a set of labels (i.e., a set of garment items), and (iii) the decision on which labels to assign to the query photo comes from a set of instances that is used to build a function, which separates labels that should be assigned to the query photo, from those that should not be assigned. Using this configuration, we propose two approaches: (i) the pointwise one, called MMCA, which receives a single image as input, and (ii) a multi-instance classification, called M3CA, also known as pairwise approach, which uses pair of images to create the classifiers. We conducted a systematic evaluation of the proposed algorithms using everyday photos collected from two major fashion-related social media, namely pose.com and chictopia.com. Our results show that the proposed approaches provide improvements when compared to popular first choice multi-label, multi-modal, multi-instance algorithms that range from 20 % to 30 % in terms of accuracy.     

Online identification of appliances from power consumption data collected by smart meters

The efficient use of resources is a matter of great concern in today’s society, especially in the energy sector. Although the main strategy to decrease energy use has long been focused on supply, over the last few years, there has been a shift to the demand side. Under this new line of action, demand-side management networks have emerged and extended from the household level to larger installations, with the appearance of the concepts of Smart Grids and even Smart Cities. The extended use of Smart Meters for measuring residential electricity consumption facilitates the creation of such intelligent environments. In this context, this article proposes a system which extracts value from the collected consumer information to identify the appliances belonging to that smart environment by means of machine learning techniques. Considering the large amount of information that would be handled when millions of homes were sending data, big data technology has been used. An experiment to evaluate the classification method was carried out with seven devices and three different configurations. The results are also reported, achieving promising results, with recognition rates of 75 % after 1 h of training and 100 % after 4 h.     

Measuring the role of age in user performance during interaction with computers

The influence of aging on computer interaction has been widely analyzed in human–computer interaction research literature. Despite this, there are no age-based user maps that could support the user-interface customization. Studying the specific needs and constraints of these groups is crucial in order to adapt a user interface to the user’s interaction requirements. This work studies the performance of a sample of participants on three different basic tasks (pointing, dragging and dropping, and text selection) and the influence of age for each of them. It is concluded that this influence differs between specific activities. A group profile map that can support automatic classification in the future has been obtained.     

Is It Possible to Retain Customer Loyalty When a Service Has Failed?

This article aims to analyze the impact of recovery on loyalty in the context of a service chain characterized by the e‐quality–perceived value–loyalty relationship. A sample of 91 out of 1,201 respondents claimed to have had service problems with an online travel agency website. A causal model to test relationships was performed using structural equations modeling, and it was found that data fit with the proposed model. The really important point to retaining customers is quality. It is not so clear that the recovery effort might affect loyalty. Our findings underpin some previous stream of literature confirming that recovery does not always affect loyalty. Although the literature has not reached a consensus in this topic, we add new elements in this debate.     

Semi-parametric nonlinear regression and transformation using functional networks

Functional networks are used to solve some nonlinear regression problems. One particular problem is how to find the optimal transformations of the response and/or the explanatory variables and obtain the best possible functional relation between the response and predictor variables. After a brief introduction to functional networks, two specific transformation models based on functional networks are proposed. Unlike in neural networks, where the selection of the network topology is arbitrary, the selection of the initial topology of a functional network is problem driven. This important feature of functional networks is illustrated for each of the two proposed models. An equivalent, but simpler network may be obtained from the initial topology using functional equations. The resultant model is then checked for uniqueness of representation. When the functions specified by the transformations are unknown in form, families of linear independent functions are used as approximations. Two different parametric criteria are used for learning these functions: the constrained least squares and the maximum canonical correlation. Model selection criteria are used to avoid the problem of overfitting. Finally, performance of the proposed method are assessed and compared to other methods using a simulation study as well as several real-life data.     

Single-mode, optical-fiber sensors and tunable wavelength filters based on the resonant excitation of metal-clad modes

The resonant excitation of metal-clad modes, including fundamental and higher-order modes, in a multilayer structure deposited on the polished cladding of a single-mode optical fiber is theoretically analyzed and experimentally demonstrated. The excitation of metal-clad modes is shown as a resonant power transfer from the fiber to the metal-clad mode that takes place for an external refractive-index value such that the effective index of the metal-clad mode reaches the cladding level. The observed attenuation on the TM polarization provides a suitable transducing mechanism for refractive-index sensor devices as well as the principle for developing tunable wavelength-polarized filters with a wide range of optical performance characteristics.     

Partitioned data objects in distributed databases

In many distributed databases locality of reference is crucial to achieve acceptable performance. However, the purpose of data distribution is to spread the data among several remote sites. One way to solve this contradiction is to use partitioned data techniques. Instead of accessing the entire data, a site works on a fraction that is made locally available, thereby increasing the site's autonomy. We present a theory of partitioned data that formalizes the concept and establishes the basis to develop a correctness criterion and a concurrency control protocol for partitioned databases. Set-serializability is proposed as a correctness criterion and we suggest an implementation that integrates partitioned and non-partitioned data. To complete this study, the policies required in a real implementation are also analyzed. Recommended by: Hector Garcia-Molina     

Secondary bioreceptivity of granite: effect of salt weathering on subaerial biofilm growth

Salt crystallisation is a very common and powerful weathering agent that can modify the petrophysical properties of building stone such as granite. In addition, the weathering can affect the susceptibility of the stone to biological colonisation. The aims of the present study were to examine the properties of a granite weathered by sodium chloride crystallisation and to evaluate the effects of the weathering on the secondary bioreceptivity of the stone to subaerial phototrophic biofilms. For this purpose, granite samples were subjected to a laboratory-based accelerated salt weathering test, and changes in weight, open porosity, bulk density, capillary water content, abrasion pH and surface roughness of the samples were determined. Samples of both weathered and non-weathered granite were then inoculated with a multi-species phototrophic culture derived from a natural subaerial biofilm and incubated under standardised laboratory conditions for 3 months. The weight loss produced by the weathering process was consistent with significant changes in abrasion pH and surface roughness. The bioreceptivity of the stone was also altered. According to the bioreceptivity index, the granite under study was characterised by ‘mild primary bioreceptivity’, but ‘high secondary bioreceptivity’ after the salt weathering process. Study of the secondary bioreceptivity of stone materials can provide very useful information about response to weathering effects, and the findings can be used to improve the selection of materials for building purposes.