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).

High-Performance Sensors Based on Resistance Fluctuations of Single-Layer-Graphene Transistors

One of the most interesting predicted applications of graphenemonolayer-based devices is as high-quality sensors. In this article, we show, through systematic experiments, a chemical vapor sensor based on the measurement of lowfrequency resistance fluctuations of single-layer-graphene field-effect-transistor devices. The sensor has extremely high sensitivity, very high specificity, high fidelity, and fast response times. The performance of the device using this scheme of measurement (which uses resistance fluctuations as the detection parameter) is more than 2 orders of magnitude better than a detection scheme in which changes in the average value of the resistance is monitored. We propose a number-densityfluctuation-based model to explain the superior characteristics of a noisemeasurement-based detection scheme presented in this article.

A New Iterative FIR Filter for Image and Video Restoration

Image and video filtering is a key image-processing task in computer vision especially in noisy environment. In most of the cases the noise source is unknown and hence possess a major difficulty in the filtering operation. In this paper we present an error-correction based learning approach for iterative filtering. A new FIR filter is designed in which the filter coefficients are updated based on Widrow-Hoff rule. Unlike the standard filter the proposed filter has the ability to remove noise without the a priori knowledge of the noise. Experimental result shows that the proposed filter efficiently removes the noise and preserves the edges in the image. We demonstrate the capability of the proposed algorithm by testing it on standard images infected by Gaussian noise and on a real time video containing inherent noise. Experimental result shows that the proposed filter is better than some of the existing standard filters

Mixed ionic and electronic conduction in zirconia and its applications in metallurgy

Mixed ionic and electronic conduction in Zr02-based solid electrolytes was studied.The effect of impurities and second-phase particles on the mixed conduction parameter, P,, was measured for different types of ZrOZ electrolytes. The performance of solid-state sensors incorporating ZrOZ electrolytes is sometimes limited by electronic conduction in ZrOZ, especially at temperatures >I800 K. Methods for eliminating or minimizing errors in measured emf due to electronically driven transport of oxygen anions are discussed. Examples include probes for monitoring oxygen content in liquid steel as well as the newly developed sulfur sensor based on a ZrOz(Ca0) + CaS electrolyte. The use of mixed conducting ZrOZ as a semipermeable membrane or chemically selective sieve for oxygen at high temperatures is discussed. Oxygen transport from liquid iron to CO + C& gas mixtures through a ZrOZ membrane driven by a chemical potential gradient, in the absence of electrical leads or imposed potentials, was experimentally observed.

CO2 sensing at room temperature using carbon nanotubes coated core fiber Bragg grating

The sensing of carbon dioxide (CO2) at room temperature, which has potential applications in environmental monitoring, healthcare, mining, biotechnology, food industry, etc., is a challenge for the scientific community due to the relative inertness of CO2. Here, we propose a novel gas sensor based on clad-etched Fiber Bragg Grating (FBG) with polyallylamine-amino-carbon nanotube coated on the surface of the core for detecting the concentrations of CO2 gas at room temperature, in ppm levels over a wide range (1000 ppm-4000 ppm). The limit of detection observed in polyallylamine-amino-carbon nanotube coated core-FBG has been found to be about 75 ppm. In this approach, when CO2 gas molecules interact with the polyallylamine-amino-carbon nanotube coated FBG, the effective refractive index of the fiber core changes, resulting in a shift in Bragg wavelength. The experimental data show a linear response of Bragg wavelength shift for increase in concentration of CO2 gas. Besides being reproducible and repeatable, the technique is fast, compact, and highly sensitive. (C) 2013 AIP Publishing LLC.

Real time monitoring of petroleum leakage detection using etched fiber Bragg grating

Detection of petroleum leakages in pipelines and storage tanks is a very important as it may lead to significant pollution of the environment, accidental hazards, and also it is a very important fuel resource. Petroleum leakage detection sensor based on fiber optics was fabricated by etching the fiber Bragg grating (FBG) to a region where the total internal reflection is affected. The experiment shows that the reflected Bragg's wavelength and intensity goes to zero when etched FBG is in air and recovers Bragg's wavelength and intensity when it is comes in contact with petroleum or any external fluid. This acts as high sensitive, fast response fluid optical switch in liquid level sensing, petroleum leakage detection etc. In this paper we present our results on using this technique in petroleum leakage detection.

Optimisation of an asymmetric polymerase chain reaction assay for the amplification of single-stranded DNA from Wuchereria bancrofti for electrochemical detection

Single-stranded DNA (ssDNA) is a prerequisite for electrochemical sensor-based detection of parasite DNA and other diagnostic applications. To achieve this detection, an asymmetric polymerase chain reaction method was optimised. This method facilitates amplification of ssDNA from the human lymphatic filarial parasite Wuchereria bancrofti. This procedure produced ssDNA fragments of 188 bp in a single step when primer pairs (forward and reverse) were used at a 100:1 molar ratio in the presence of double-stranded template DNA. The ssDNA thus produced was suitable for immobilisation as probe onto the surface of an Indium tin oxide electrode and hybridisation in a system for sequence-specific electrochemical detection of W. bancrofti. The hybridisation of the ssDNA probe and target ssDNA led to considerable decreases in both the anodic and the cathodic currents of the system's redox couple compared with the unhybridised DNA and could be detected via cyclic voltammetry. This method is reproducible and avoids many of the difficulties encountered by conventional methods of filarial parasite DNA detection; thus, it has potential in xenomonitoring.

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.

Design and development of Fiber Bragg Grating sensing plate for plantar strain measurement and postural stability analysis

This paper describes an ab initio design and development of a novel Fiber Bragg Grating (FBG) sensor based strain sensing plate for the measurement of plantar strain distribution in human foot. The primary aim of this work is to study the feasibility of usage of FBG sensors in the measurement of plantar strain in the foot; in particular, to spatially resolve the strain distribution in the foot at different regions such as fore-foot, mid-foot and hind-foot. This study also provides a method to quantify and compare relative postural stability of different subjects under test; in addition, traditional accelerometers have been used to record the movements of center of gravity (second lumbar vertebra) of the subject and the results obtained have been compared against the outcome of the postural stability studies undertaken using the developed FBG plantar strain sensing plate. (C) 2013 Elsevier Ltd. All rights reserved.

Strength and fatigue life evaluation of composite laminate with embedded sensors

Prognosis regarding durability of composite structures using various Structural Health Monitoring (SHM) techniques is an important and challenging topic of research. Ultrasonic SHM systems with embedded transducers have potential application here due to their instant monitoring capability, compact packaging potential toward unobtrusiveness and non-invasiveness as compared to non-contact ultrasonic and eddy current techniques which require disassembly of the structure. However, embedded sensors pose a risk to the structure by acting as a flaw thereby reducing life. The present paper focuses on the determination of strength and fatigue life of the composite laminate with embedded film sensors like CNT nanocomposite, PVDF thin films and piezoceramic films. First, the techniques of embedding these sensors in composite laminates is described followed by the determination of static strength and fatigue life at coupon level testing in Universal Testing Machine (UTM). Failure mechanisms of the composite laminate with embedded sensors are studied for static and dynamic loading cases. The coupons are monitored for loading and failure using the embedded sensors. A comparison of the performance of these three types of embedded sensors is made to study their suitability in various applications. These three types of embedded sensors cover a wide variety of applications, and prove to be viable in embedded sensor based SHM of composite structures.

Effect of ambient on the resistance fluctuations of graphene

In this letter, we present the results of systematic experimental investigations of the effect of different chemical environments on the low frequency resistance fluctuations of single layer graphene field effect transistors. The shape of the power spectral density of noise was found to be determined by the energetics of the adsorption-desorption of molecules from the graphene surface making it the dominant source of noise in these devices. We also demonstrate a method of quantitatively determining the adsorption energies of chemicals on graphene surface based on noise measurements. We find that the magnitude of noise is extremely sensitive to the nature and amount of the chemical species present. We propose that a chemical sensor based on the measurement of low frequency resistance fluctuations of single layer graphene field effect transistor devices will have extremely high sensitivity, very high specificity, high fidelity, and fast response times. (c) 2015 AIP Publishing LLC.