Subject independent human action recognition using spatio-depth information and meta-cognitive RBF network

In this paper, we present a machine learning approach for subject independent human action recognition using depth camera, emphasizing the importance of depth in recognition of actions. The proposed approach uses the flow information of all 3 dimensions to classify an action. In our approach, we have obtained the 2-D optical flow and used it along with the depth image to obtain the depth flow (Z motion vectors). The obtained flow captures the dynamics of the actions in space time. Feature vectors are obtained by averaging the 3-D motion over a grid laid over the silhouette in a hierarchical fashion. These hierarchical fine to coarse windows capture the motion dynamics of the object at various scales. The extracted features are used to train a Meta-cognitive Radial Basis Function Network (McRBFN) that uses a Projection Based Learning (PBL) algorithm, referred to as PBL-McRBFN, henceforth. PBL-McRBFN begins with zero hidden neurons and builds the network based on the best human learning strategy, namely, self-regulated learning in a meta-cognitive environment. When a sample is used for learning, PBLMcRBFN uses the sample overlapping conditions, and a projection based learning algorithm to estimate the parameters of the network. The performance of PBL-McRBFN is compared to that of a Support Vector Machine (SVM) and Extreme Learning Machine (ELM) classifiers with representation of every person and action in the training and testing datasets. Performance study shows that PBL-McRBFN outperforms these classifiers in recognizing actions in 3-D. Further, a subject-independent study is conducted by leave-one-subject-out strategy and its generalization performance is tested. It is observed from the subject-independent study that McRBFN is capable of generalizing actions accurately. The performance of the proposed approach is benchmarked with Video Analytics Lab (VAL) dataset and Berkeley Multimodal Human Action Database (MHAD). (C) 2013 Elsevier Ltd. All rights reserved.

Influence of anthropogenic contamination on fluoride concentration in groundwater: A study of Mulbagal town, Kolar district, Karnataka

Groundwater contamination is a serious concern in India. Major geogenic contaminants include fluoride, arsenic and iron, while common anthropogenic contaminants include nitrate, metals, organics and microbial contamination. Besides, known point and diffuse sources, groundwater c ontamination from inf iltration of pit to ilet leachate is an emerging concern. The study area of this paper is Kolar district in Karnataka that is hot spot of fluoride contamination. The absence of fluoride contamination in Mulbagal town and the alterations in groundwater chemistry from infiltration of pit toilet leachate motivated the author to examine the possible linkages between anthropogenic contamination and fluoride concentration in groundwater of Mulbagal town. Analysis of the groundwater chemistry revealed that the groundwater in Mulbagal town is under saturated with respect to calcite that suppresses the dissolution of fluorite and the fluoride concentration in the groundwater. The slightly acidic pH of the groundwater is considered responsible to facilitate calcite dissolution under saturation.

An extended finite element model coupled with level set method for stable pitting corrosion

Mass balance between metal and electrolytic solution, separated by a moving interface, in stable pit growth results in a set of governing equations which are solved for concentration field and interface position (pit boundary evolution), which requires only three inputs, namely the solid metal concentration, saturation concentration of the dissolved metal ions and diffusion coefficient. A combined eXtended Finite Element Model (XFEM) and level set method is developed in this paper. The extended finite element model handles the jump discontinuity in the metal concentrations at the interface, by using discontinuous-derivative enrichment formulation for concentration discontinuity at the interface. This eliminates the requirement of using front conforming mesh and re-meshing after each time step as in conventional finite element method. A numerical technique known as level set method tracks the position of the moving interface and updates it over time. Numerical analysis for pitting corrosion of stainless steel 304 is presented. The above proposed method is validated by comparing the numerical results with experimental results, exact solutions and some other approximate solutions.

An extended finite-element model coupled with level set method for analysis of growth of corrosion pits in metallic structures

Mass balance between metal and electrolytic solution, separated by a moving interface, in stable pit growth results in a set of governing equations which are solved for concentration field and interface position (pit boundary evolution). The interface experiences a jump discontinuity in metal concentration. The extended finite-element model (XFEM) handles this jump discontinuity by using discontinuous-derivative enrichment formulation, eliminating the requirement of using front conforming mesh and re-meshing after each time step as in the conventional finite-element method. However, prior interface location is required so as to solve the governing equations for concentration field for which a numerical technique, the level set method, is used for tracking the interface explicitly and updating it over time. The level set method is chosen as it is independent of shape and location of the interface. Thus, a combined XFEM and level set method is developed in this paper. Numerical analysis for pitting corrosion of stainless steel 304 is presented. The above proposed model is validated by comparing the numerical results with experimental results, exact solutions and some other approximate solutions. An empirical model for pitting potential is also derived based on the finite-element results. Studies show that pitting profile depends on factors such as ion concentration, solution pH and temperature to a large extent. Studying the individual and combined effects of these factors on pitting potential is worth knowing, as pitting potential directly influences corrosion rate.

Growth and electrical transport properties of InGaN/GaN heterostructures grown by PAMBE

InGaN epitaxial films were grown on GaN template by plasma-assisted molecular beam epitaxy. The composition of indium incorporation in single phase InGaN film was found to be 23%. The band gap energy of single phase InGaN was found to be similar to 2.48 eV: The current-voltage (I-V) characteristic of InGaN/GaN heterojunction was found to be rectifying behavior which shows the presence of Schottky barrier at the interface. Log-log plot of the I-V characteristics under forward bias indicates the current conduction mechanism is dominated by space charge limited current mechanism at higher applied voltage, which is usually caused due to the presence of trapping centers. The room temperature barrier height and the ideality factor of the Schottky junction were found to 0.76 eV and 4.9 respectively. The non-ideality of the Schottky junction may be due to the presence of high pit density and dislocation density in InGaN film. (C) 2014 Elsevier Ltd. All rights reserved.

Timing Recovery Algorithms and Architectures for 2-D Magnetic Recording Systems

We investigate the problem of timing recovery for 2-D magnetic recording (TDMR) channels. We develop a timing error model for TDMR channel considering the phase and frequency offsets with noise. We propose a 2-D data-aided phase-locked loop (PLL) architecture for tracking variations in the position and movement of the read head in the down-track and cross-track directions and analyze the convergence of the algorithm under non-separable timing errors. We further develop a 2-D interpolation-based timing recovery scheme that works in conjunction with the 2-D PLL. We quantify the efficiency of our proposed algorithms by simulations over a 2-D magnetic recording channel with timing errors.

Use of permeable reactive barrier to mitigate groundwater nitrate contamination from on-site sanitation

Nearly 50% of India's population depends on variants of pit-toilet systems for human waste disposal. Nitrate contamination of groundwater by pit-toilet leachate is a major environmental concern in the country as it sources a major proportion (50-80%) of potable water from aquifers. Therefore, minimizing nitrate contamination of groundwater due to leachate infiltration from pit-toilet systems is essential. Batch and column experiments demonstrated the capability of bentonite-enhanced sand (BES) specimens to reduce nitrate concentrations in synthetic solutions (initial NO3-N concentration = 22.7 mg/L, C/N = 3) by about 85-90% in 10 to 24 hour by a heterotrophic denitrification process. Based on the laboratory results, it is recommended that use of a BES-permeable reactive barrier layer at the base of pit-toilets will facilitate heterotrophic denitrification and mitigate nitrate contamination of the underlying aquifer.

Action Recognition from Motion Capture Data using Meta-cognitive RBF Network Classifier

Action recognition plays an important role in various applications, including smart homes and personal assistive robotics. In this paper, we propose an algorithm for recognizing human actions using motion capture action data. Motion capture data provides accurate three dimensional positions of joints which constitute the human skeleton. We model the movement of the skeletal joints temporally in order to classify the action. The skeleton in each frame of an action sequence is represented as a 129 dimensional vector, of which each component is a 31) angle made by each joint with a fixed point on the skeleton. Finally, the video is represented as a histogram over a codebook obtained from all action sequences. Along with this, the temporal variance of the skeletal joints is used as additional feature. The actions are classified using Meta-Cognitive Radial Basis Function Network (McRBFN) and its Projection Based Learning (PBL) algorithm. We achieve over 97% recognition accuracy on the widely used Berkeley Multimodal Human Action Database (MHAD).

Numerical study of laminar, standing hydraulic jumps in a planar geometry

We solve the two-dimensional, planar Navier-Stokes equations to simulate a laminar, standing hydraulic jump using a Volume-of-Fluid method. The geometry downstream of the jump has been designed to be similar to experimental conditions by including a pit at the edge of the platform over which liquid film flows. We obtain jumps with and without separation. Increasing the inlet Froude number pushes the jump downstream and makes the slope of the jump weaker, consistent with experimental observations of circular jumps, and decreasing the Reynolds number brings the jump upstream while making it steeper. We study the effect of the length of the domain and that of a downstream obstacle on the structure and location of the jump. The transient flow which leads to a final steady jump is described for the first time to our knowledge. In the moderate Reynolds number regime, we obtain steady undular jumps with a separated bubble underneath the first few undulations. Interestingly, surface tension leads to shortening of wavelength of these undulations. We show that the undulations can be explained using the inviscid theory of Benjamin and Lighthill (Proc. R. Soc. London, Ser. A, 1954). We hope this new finding will motivate experimental verification.

A Dynamic Comprehensive Method for Landslide Control

A slope failure is developed due to progressive external loads and deteriorations of slope geomaterials, thus forming a progressive and dynamic development and occurrence of landslides. Site geological properties and other active factors such as hydrodynamic load and human activities are complex and usually unknown, thus this dynamic development and occurrence of landslides can only be understood through the progressive accumulation of knowledge on the landslides. For such a progressive process, this paper proposes a dynamic comprehensive control method for landslide control. This control method takes full advantage of updated monitoring data and site investigations of landslides, and emphasizes the implementation of possible measures for landslide control at reasonable stages and in different groups. These measures are to prevent the occurrence of a landslide disaster. As a case study, a landslide project at the Panluo open-pit iron mine is analyzed to illustrate this dynamic comprehensive control method.

露天矿边坡动态整治方法及其应用--以福建潘洛铁矿滑坡整治为例

露天矿边坡属于人工边坡,它的形成不仅时间长,而且一直处于动态过程中.露天矿滑坡在一定范围内是允许的,滑坡治理的目的是保证矿山在开采期限内安全采出设计境界内的矿石.基于这些特征,在文中提出了适合露天矿滑坡治理的新方法-动态治理法及其可行性,并以潘洛铁矿露天矿滑坡灾害治理为例,对该方法的应用进行了论述.可为露天矿滑坡治理所借鉴.

Análisis de riesgo de plagas de importancia fitosanitaria para Nicaragua en la importación de semilla de cebolla (Allium cepa L.) procecedente de Canadá

El presente Análisis de riesgo de Plagas (ARP) se realizó en el Centro Nacional de Diagnóstico Fitosanitario (CNDF) y Cuarentena del MAG-FOR en Managua, Nicaragua, e1 cual tuvo por objetivo evaluar el riesgo de introducción, establecimiento y dispersión de plagas de importancia fitosanitaria para Nicaragua en semilla de cebolla (Allium cepa L.) importada de Canadá, así como determinar las medidas adecuadas de protección fitosanitarias para evitar la introducción de las mismas a Nicaragua. De un listado inicial de 18 plagas, sólo 6 plagas son sujetas a evaluación y manejo del riesgo después de pasar por las tres etapas de evaluación de un ARP según la Norma Centroamericana del OIRSA, por considerarse que estas presentan capacidad biológica y de comportamiento, así como rangos óptimos de temperaturas que se asemejan a las condiciones de clima de las zonas productoras de Allium cepa L. del país. (Anexo1). El cuadro 1 contiene la lista de las plagas no sujetas a Evaluación del Riesgo Puccinia allii ( DC) Rudolphi y Urocistis Cepulae. Frost que causan la Roya y el carbón de la cebolla respectivamente son consideradas plagas específicas de los cultivos del género Allium P. allí es considerada plaga de bajo riesgo de introducción al país siendo la limitante para su establecimiento que su óptimo de temperatura ( 1 O" a 15" C), no se asemeja a las condiciones de temperatura de las zonas productoras del país( Anexo l ), mientras que U. cepulae es considerado como un hongo muy peligroso capaz de provocar pérdidas en la producción de hasta 80 por ciento tiene alta probabilidad de establecimiento v diseminación en las zonas productoras del país va que las condiciones de edafoclímaticas (16-22" C y pH 5-8) le favorecen( Anexo 1) Botryotinia squamosa. Viennot-Bourgín es un hongo que causa la pudrición blanda de la cebolla, se considera una plaga especifica de cultivos del género Allium con probabilidad alta de establecimiento v disemmac1ón en las zonas productoras de cebolla del país ya que el rango superior óptimo de temperatura (23" C) se asemeja a las condiciones de temperatura de las mismas (Anexo 11. Sclerotium cepivorum. Berkeley (1841 ). Es un hongo que causa la pudrición blanca de la cebolla y es considerado una plaga general de corto rango de hospedero quien además de atacar a cultivos del género Allium ataca también a lycopersicum esculentum (tomate) puede causar pérdidas en la producción de hasta un 70 por ciento (promedio) Y, con riesgo Alto de establecimiento en el país ya que temperaturas de 1 0"-20" C y baja humedad 40%. (pariona et. al) inclusive 30"- 5"C cuando hay humedad (Agrios 1985) y pH desde 1.4 a 8.8 le favorecen y las condiciones edafoclimáticas de las zonas productoras de cebolla del país se asemejan (Anexo ll). El nemátodo Ditylenchus dipsaci es un endoparásito destructor, y es considerado plaga general de cultivos del género Allium que ataca otros cultivos como cucurbitáceas. Zea mays (Maíz), Solanum tuberosum (Papa) y Nicotiana Tabacum (Tabaco). Es capaz de reducir la producción hasta un 75 por ciento (promedio) y la probabilidad de ingreso al país es media, a pesar de que su óptimo de temperatura (15º C) no se asemejan a la temperatura de las zonas productoras de cebolla del país. se considera de gran importancia sus características como: gran capacidad reproductiva es endoparásito y podemos encontrarlo dentro de cualquier parte de la planta inclusive dentro de la semilla. Aphelenchoides fragariae es un nematodo que tiene por hospedero secundario a Allium cepa. L puede ser capaz de ocasionar pérdidas en la producción de hasta 66.5% (promedio), es considerado plaga general de cultivos del género Allium con baja probabilidad de ingreso al país, va que su hospedero primario es la fresa y no se reportan daños en cebolla (no preferencia por Allium cepa L que es hospedero secundario) Todas estas plagas son consideradas de categoría A 1 1 para Nicaragua (no presentes en el país), lo que justifica plenamente la realización de este ARP a fin de tomar las medidas pertinentes que acompañen la importación de semilla y así evitar la introducción de nuevas plagas de difícil control.

Effect of Surface Condition of Electrode on the Surface Melting of Material by Laser-Guided Micro-Arc Discharge

This paper studies the surface melting in the atmosphere by YAG laser-guided micro-arc discharge. In three kinds of surface conditions (free, oiled, and polyethylene covered), we try to control the diameter and the power density of discharge pit. It is found that the power density of 3 x 10(6) W/cm(2) of discharge pit on the oiled surface is moderate to form the melted layer thicker than that of the others, adapting to strengthen the surface of material, and the power density of 1.07 x 10(7) W/cm(2) of discharge pit on the polyethylene-covered surface is highest to form the deepest discharge pit among them, adapting to remove the material.