This paper presents an approach for the detection and localization of abnormal events in pedestrian areas. The goal is to design a model to detect abnormal events in video sequences using motion and appearance information. Motion information is represented through the use of the velocity and acceleration of optical flow and the appearance information is represented by texture and optical flow gradient. Unlike literature methods, our proposed approach provides a general solution to detect both global and local abnormal events. Furthermore, in the detection stage, we propose a classification by local regions. Experimental results on UMN and UCSD datasets confirm that the detection accuracy of our method is comparable to state-of-the-art methods.

En el sur del Perú se encuentran 8 volcanes activos ubicados en la zona volcánica central de los andes (ZVC), dentro de ellos se encuentran los volcanes Ubinas, Sabancaya y Misti. El volcán Ubinas se ubica a 80 km al sureste de la ciudad de Arequipa, en la provincia de Sánchez Cerro. Tiene una altura aproximada de 5672 msnm., el volcán Sabancaya se encuentra a 80 km al noroeste de la ciudad de Arequipa en el distrito de Achoma provincia de Caylloma y el volcán Misti se ubica a 18 Km al este de la ciudad de Arequipa (Figura. 1). Estos volcanes han presentado actividad reciente generando productos que afectan a las poblaciones cercanas, uno de los principales productos es la ceniza volcánica: partículas de lava fragmentada con un tamaño menor a 2 mm que es expulsada en las explosiones de los volcanes. Durante los últimos 5 años, los volcanes Ubinas y Sabancaya presentaron episodios eruptivos generando miles de toneladas de ceniza volcánica que se deposita alrededor del edificio volcánico. Este material no es utilizado y provoca daños en la salud de la población y animales.

Big data visualization is a main task for data analysis. Due to its complexity in terms of volume and variety, very large datasets are unable to be queried for similarities among entries in traditional Database Management Systems. In this paper, we propose an effective approach for indexing millions of elements with the purpose of performing single and multiple visual similarity queries on multidimensional data associated with geographical locations. Our approach makes use of Z-Curve algorithm to map into 1D space considering similarities between data. Additionally, we present a set of results using real data of different sources and we analyze the insights obtained from the interactive exploration.

Geopolymeric mortars with volumetric fractions of 0.6:1:0.3 for a binder powder, fine sand and sodium hydroxide solution (12M), respectively; have been fabricated by mixing the solid materials and the subsequent addition of sodium hydroxide solution 12M to form a workable paste, to later be cured for 28 days at room temperature. The microstructures of the fabricated materials reveal the existence of two phases with notable difference, one continuous to the geopolymer binder phase and another discontinuous of fine sand particles agglutinated by the binder phase. Mechanical compression tests are performed at a constant compression rate of 0.05 mm/min and at temperatures ranged from room temperature to 500°C. The mechanical results are ranged from 19 and 69 MPa for all the materials studied. On the other hand, there was an increase in mechanical resistance up to test temperatures of 200°C and the progressive reduction of resistance at temperatures above 200°C, with a fragile-ductile transition zone between 400 and 500°C and completely ductile behavior from test temperatures of 500°C.

Worldwide, chronic pain has established as one of the foremost medical issues due to its 35% of comorbidity with depression and many other psychological problems. Traditionally, self-report (VAS scale) or physicist inspection (OPI scale) perform the pain assessment; nonetheless, both methods do not usually coincide [14]. Regarding self-assessment, several patients are not able to complete it objectively, like young children or patients with limited expression abilities. The lack of objectivity in the metrics draws the main problem of the clinical analysis of pain. In response, various efforts have tried concerning the inclusion of objective metrics, among which stand out the Prkachin and Solomon Pain Intensity (PSPI) metric defined by face appearance [5]. This work presents an in-depth learning approach to pain recognition considering deep facial representations and sequence analysis. Contrasting current state-of-the-art deep learning techniques, we correct rigid deformations caught since registration. A preprocessing stage is applied, which includes facial frontalization to untangle facial representations from non-affine transformations, perspective deformations, and outside noises passed since registration. After dealing with unbalanced data, we fine-tune a CNN from a pre-trained model to extract facial features, and then a multilayer RNN exploits temporal relation between video frames. As a result, we overcome state-of-the-art in terms of average accuracy at frames level (80.44%) and sequence level (84.54%) in the UNBC-McMaster Shoulder Pain Expression Archive Database.

A neural network is a mathematical model that is able to perform a task automatically or semi-automatically after learning the human knowledge that we provided. Moreover, a Convolutional Neural Network (CNN) is a type of neural network that has shown to efficiently learn tasks related to the area of image analysis, such as image segmentation, whose main purpose is to find regions or separable objects within an image. A more specific type of segmentation, called semantic segmentation, guarantees that each region has a semantic meaning by giving it a label or class. Since CNNs can automate the task of image semantic segmentation, they have been very useful for the medical area, applying them to the segmentation of organs or abnormalities (tumors). This work aims to improve the task of binary semantic segmentation of volumetric medical images acquired by Magnetic Resonance Imaging (MRI) using a pre-existing Three-Dimensional Convolutional Neural Network (3D CNN) architecture. We propose a formulation of a loss function for training this 3D CNN, for improving pixel-wise segmentation results. This loss function is formulated based on the idea of adapting a similarity coefficient, used for measuring the spatial overlap between the prediction and ground truth, and then using it to train the network. As contribution, the developed approach achieved good performance in a context where the pixel classes are imbalanced. We show how the choice of the loss function for training can affect the nal quality of the segmentation. We validate our proposal over two medical image semantic segmentation datasets and show comparisons in performance between the proposed loss function and other pre-existing loss functions used for binary semantic segmentation.

Biomorphic SiC/Si compounds were fabricated from copaiba wood (Copaifera officinalis, natural wood native to Peru), by reactive infiltration of molten silicon in a porous carbon preform obtained by a controlled pyrolysis process of wood. Structural and microstructural characterization tests by X-ray diffraction and scanning electron microscopy, respectively, revealed, on the one hand, the presence of crystalline phases of SiC, Si and C, and on the other, the typical morphology of this type of material, which it consists of a continuous SiC scaffold with elongated channels in the direction of tree growth and the presence of residual Si and C located mainly in the porosities of the material. The mechanical behavior in uniaxial compression was also studied at a constant compression rate of 0.05 mm/min and as a function of temperature (from ambient to 1400 ºC) and test atmosphere (ambient air, humid air, dry air, Ar, N2 and reducing mixture (95% Ar + 5% H2). The mechanical results were evaluated based on values of maximum stress and modulus of elasticity (stiffness), finding a clear reduction in the values of maximum stress and stiffness of the material when the samples passed of ambient test temperatures at 1400 ºC. On the other hand, mechanical tests in a controlled atmosphere were carried out at a constant temperature of 1100 ºC and the results showed that the mechanical behavior of the studied compounds is slightly influenced by the working atmosphere. Mechanical data found in the various test conditions will be an important support for the definition of the maximum allowable stress (considering the safety factor applied for a particular case) in the industrial application of the materials studied in this work.

This paper explores the development of a low-cost instrument using a similar architecture to a one-port vector receiver intended for estimating Arsenic (As) ions diluted in water. The instrument is implemented with modular off-the-shelf-components. The measurements are performed with the designed prototype connected to a dielectric assessment kit 3.5 from Schmidt Partner Engineering AG and are compared for different levels of Arsenic solved in water. The preliminary results obtained are promising to continue the study of this instrumentation and pave the way to develop further sensor and instrumentation for water-sensing and monitoring applications.

Object recognition in the field of computer vision is a constant challenge to achieve better precision in less time. In this research, is proposed a new 3D descriptor, to work with depth cameras called CPPFL, based on the PPF descriptor from [1]. This proposed descriptor takes advantage of color information and groups it more effectively and lightly than the CPPF descriptor from [2], which uses the color information too. Also, it is proposed as an alternative descriptor called CPPFL+, which differs in the construction taking advantage of the same concept of grouping colors, so it gains a “plus” in speed. This change makes the descriptor more efficient compared to PPF and CPPF descriptors. Optimizing the object recognition process [3], it can reach a rate of ten frames per second or more depending on the size of the object. The proposed descriptor is more tolerant to illuminations changes since the hue of a color is more relevant than the other components.

This work presents the results of the thermomechanical evaluation of geopolymeric concrete fabricated from mining tailings, rice husk ash and fine sand. Ten types of geopolymeric concrete were studied and the relationship between the initial volumetric concentrations of the components in the mixtures and the maximum resistance in uniaxial compression under conditions of variable temperature (between ambient and 600 °C) was analyzed. The results revealed that increases in the concentration of mining tailings and fine sand lead to an increase in the value of the maximum mechanical resistance, in contrast, the increase in the concentration of rice husk ash led to a reduction in the value of the maximum mechanical resistance. Furthermore, increases in test temperature, up to 500 °C, led to systematic increases in maximum mechanical strength. Finally, the geopolymeric concretes presented a brittle-ductile transition between 500 and 600 °C showing only a ductile behavior when tested at 600 °C and only brittle up to test temperatures of 500 °C.

This paper presents a compact and modular system based on Internet-of- Things for monitoring cattle behavior and stress in real-time. It will help to model certain parameters such as temperature and certain weather variables such as relative humidity, solar radiation, among others thanks to Internet-of- Things (IoT) sensors localized in different points of barns and the fields for cattle farming. A main benefit of the system is that it is built with low-cost hardware and low battery consumption. The wireless system also allows the collection of data in real-time and obtains the temperature-humidity index. This index will give an approach to the heat stress in cattle not only on the farm but in the vicinity of the farm. Finally, the high amount of collected data will allow employing Big Data solutions for estimating the impact on milk productivity. In the future, more sensors will be deployed for a more detailed reading of weather variables and their impact on dairy cattle.

Currently, IoT has evolved to such an extent to extend to all corners of each place through devices that are connected to a network and generate information. In most cases, to be processed for a specific purpose or storage as historical data, an IoT ecosystem is implemented to manage those tasks between different devices, frameworks, or applications. Besides, more complex IoT ecosystems require more complex architecture to manage the information flow; at this level, we found a problem called interoperability. This problem is not limited to the compatibility of adding/removing devices to an ecosystem; it is also expected that the information generated by devices and processed complies with a standard optimizing the data transmission. In this work, we present a new software architecture pattern to avoid the problem of interoperability through the process of exchange information between devices and prevent and store heterogeneous information coming from different layers of an IoT ecosystem.

Digital libraries represent the most valuable resource for storing, querying, and retrieving scientific literature. Traditionally, the reader/analyst aims to compose a set of articles based on keywords, according to his/her preferences, and manually inspect the resulting list of documents. Except for the articles which share citations or common keywords, the results retrieved will be limited to those which fulfill a syntactic match. Besides, if instead of having an article as a reference, the user has an image, the process of finding and exploring articles with similar content becomes infeasible. This paper proposes a visual analytic methodology for exploring and analyzing scientific document collections that consider both textual and image content. The proposed technique relies on combining multiple Content-Based Image Retrieval (CBIR) components and multidimensional projection to map the documents to a visual space based on their similarity, thus enabling an interactive exploration. Moreover, we extend its analytical capabilities with visual resources to display complementary information on selected documents that uncover hidden patterns and semantic relations. We evidence the effectiveness of our methodology through three case studies and a user evaluation, which attest to its usefulness during the process of scientific collections exploration.

Many authors have been working on approaches that can be applied to social robots to allow a more realistic/comfortable relationship between humans and robots in the same space. This paper proposes a new navigation strategy for social environments by recognizing and considering the social conventions of people and groups. To achieve that, we proposed the application of Delaunay triangulation for connecting people as vertices of a triangle network. Then, we defined a complete asymmetric Gaussian function (for individuals and groups) to decide zones where the robot must avoid passing. Furthermore, a feature generalization scheme called socialization feature was proposed to incorporate perception information that can be used to change the variance of the Gaussian function. Simulation results have been presented to demonstrate that the proposed approach can modify the path according to the perception of the robot compared to a standard A* algorithm.

La combinación de diferentes calidades de residuos de cuero con diferentes polímeros y las propiedades mecánicas resultantes son potencialmente importantes en la obtención de nuevos materiales. En este estudio, experimentos combinando residuos de viruta de cuero, resina vinnapas ®400 y agua destilada produjeron un nuevo material compuesto con propiedades mecánicas interesantes. En la elaboración se controló el pH de la viruta de cuero, tamaño de viruta, temperatura de la resina, temperatura de ablandamiento, la presión y el tiempo de presionado ejercido sobre la plancha de cuero reconstituido. Empleando diseño factorial fraccionado se determinó la influencia de las variables independientes seleccionadas: tamaño de la viruta, relación viruta/resina, porcentaje de agua, temperatura de la resina, la presión y el tiempo de presionado sobre las propiedades mecánicas del material compuesto. Los resultados experimentales mostraron que había un efecto principal de la variable relación Viruta/Resina en su valor mínimo sobre el esfuerzo máximo de tracción, llegándose a obtener un valor de 2.657 MPa. Adicionalmente, en el ensayo mecánico de fluencia se encontró que el material compuesto denominado cuero reconstituido muestra un comportamiento viscoelástico, lo que lo asemeja al comportamiento de un cuero curtido.

The traditional method of manufacturing SiC compounds is associated with a serious environmental problem, mainly due to the need for large amounts of energy (generally derived from oil) to reach processing temperatures (typically above 2500 ºC). In addition, the chemical reaction that gives rise to the formation of SiC has CO and CO2 as by-products. Therefore, in this work an alternative method to manufacture SiC/Si composites using waste from the wood industry as the main raw material was developed. SiC/Si composites were fabricated by infiltration of molten silicon into carbon preforms at 1500 °C. The carbon preforms were obtained by pyrolysis (in an inert Ar atmosphere) of four types of resin-carbon mixtures. The carbon used in the mixtures was obtained by pyrolysis of sawdust powder. The mechanical and thermomechanical behavior in uniaxial compression was studied at a constant compression rate of 0.05 mm/min at different temperatures (ambient, 1100 °C and 1400 °C). The maximum resistance values found were in the range of 58 and 384 MPa, while the Young's modulus values were between 40 and 120 GPa. The porosity found in the materials was between 1 and 4%. Finally, the fabricated compounds presented a homogeneous microstructure of interconnected silicon carbide in gray contrast and dispersed and unconnected whitish phases of uniformly distributed silicon.

High directivity and large bandwidth directional couplers are foreseen in future electronic systems. These devices are expected in measurement, monitoring, control and protection applications. In this work, a novel design methodology of a directional coupler using microstrip technology is proposed. This design is based on traditional coupled line theory enhanced with capacitive compensation and matching network. Using this methodology, a directional coupler is implemented in microstrip technology using FR4 substrate obtaining a large bandwidth (ranging from 1 GHz to 8 GHz) and a directivity better than 20 dB.

In order to increase agricultural productivity, it is necessary to manage the nutrients that the plants receive. In this sense, nitrogen is one of the most important nutrients for the adequate development and growth of plants and whose control contributes to the conservation of the environment. Traditionally, the quantification of nitrates is performed employing methods such as ion chromatography conducted in a laboratory, which leads to problems such as processing time, complexity in the analysis process itself and the need to have people trained to handle such analysis equipment. To alleviate these difficulties, some sensors use electrochemical principles; however, they present several limitations such as manufacturing complexity, cost, and difficulties in conducting real-time measurements. On the other hand, capacitive sensors have also been developed whose operating principle is based on analyzing the changes in the electrical characteristics of these devices produced by variations in the environment surrounding the sensor. For example, solutions with different concentrations of nitrates will produce an alteration of the electric field generated by the electrodes of the capacitor, producing changes in parameters such as its electrical impedance. However, the materials used to manufacture these sensors are metals, being unattractive for agricultural applications due to the corrosion they may suffer. To counteract this problem, it is possible to use other types of materials, among which graphene emerge as it has been shown to have excellent properties such as being a mechanically strong material and presenting good electrical conductivity. For this reason, in this work, the study of the sensitivity of a graphene-based interdigital capacitive sensor applied to the measurements of nitrate concentrations is performed. Different analytical methods were used. In general, the interdigital capacitive sensor shows repeatability in the measurements, especially for concentrations greater than 10 ppm with variability of . Also, parameters such as the detection limit of the sensor were calculated, the result of which was 1.71 ppm. Also, measurements were made on agricultural soil samples showing differences in readings with respect to the ion chromatography method. Differences that are attributable to the different methodologies used in the calculation of the nitrate concentration and the fertilization process that was applied to the crop field a few weeks before. Despite the difference between the sensor measurements and the results obtained by ion chromatography, both procedures showed a high amount of nitrate concentration.

Background In order to detect threats to public health and to be well-prepared for endemic and pandemic illness outbreaks, countries usually rely on event-based surveillance (EBS) and indicator-based surveillance systems. Event-based surveillance systems are key components of early warning systems and focus on fast capturing of data to detect threat signals through channels other than traditional surveillance. In this study, we develop Natural Language Processing tools that can be used within EBS systems. In particular, we focus on information extraction techniques that enable digital surveillance to monitor Internet data and social media. Results We created an annotated Spanish corpus from ProMED-mail health reports regarding disease outbreaks in Latin America. The corpus has been used to train algorithms for two information extraction tasks: named entity recognition and relation extraction. The algorithms, based on deep learning and rules, have been applied to recognize diseases, hosts, and geographical locations where a disease is occurring, among other entities and relations. In addition, an in-depth analysis of micro-average F1 metrics shows the suitability of our approaches for both tasks. Conclusions The annotated corpus and algorithms presented could leverage the development of automated tools for extracting information from news and health reports written in Spanish. Moreover, this framework could be useful within EBS systems to support the early detection of Latin American disease outbreaks.

The prediction of university dropout is a complex problem, given the number and diversity of variables involved. Therefore, different strategies are applied to understand this educational phenomenon, although the most outstanding derive from the joint application of statistical approaches and computational techniques based on machine learning. Student Dropout Prediction (SDP) is a challenging problem that can be addressed following various strategies. On the one hand, machine learning approaches formulate it as a classification task whose objective is to compute the probability of belonging to a class based on a specific feature vector that will help us to predict who will drop out. Alternatively, survival analysis techniques are applied in a time-varying context to predict when abandonment will occur. This work considered analytical mechanisms for supporting the decision-making process on higher education dropout. We evaluated different computational methods from both approaches for predicting who and when the dropout occurs and sought those with the most-consistent results. Moreover, our research employed a longitudinal dataset including demographic, socioeconomic, and academic information from six academic departments of a Latin American university over thirteen years. Finally, this study carried out an in-depth analysis, discusses how such variables influence estimating the level of risk of dropping out, and questions whether it occurs at the same magnitude or not according to the academic department, gender, socioeconomic group, and other variables.