Human action recognition using a fast learning fully complex-valued classifier

In this paper, we use optical flow based complex-valued features extracted from video sequences to recognize human actions. The optical flow features between two image planes can be appropriately represented in the Complex plane. Therefore, we argue that motion information that is used to model the human actions should be represented as complex-valued features and propose a fast learning fully complex-valued neural classifier to solve the action recognition task. The classifier, termed as, ``fast learning fully complex-valued neural (FLFCN) classifier'' is a single hidden layer fully complex-valued neural network. The neurons in the hidden layer employ the fully complex-valued activation function of the type of a hyperbolic secant function. The parameters of the hidden layer are chosen randomly and the output weights are estimated as the minimum norm least square solution to a set of linear equations. The results indicate the superior performance of FLFCN classifier in recognizing the actions compared to real-valued support vector machines and other existing results in the literature. Complex valued representation of 2D motion and orthogonal decision boundaries boost the classification performance of FLFCN classifier. (c) 2012 Elsevier B.V. All rights reserved.

Fully complex-valued ELM classifiers for human action recognition

In this paper, we present a fast learning neural network classifier for human action recognition. The proposed classifier is a fully complex-valued neural network with a single hidden layer. The neurons in the hidden layer employ the fully complex-valued hyperbolic secant as an activation function. The parameters of the hidden layer are chosen randomly and the output weights are estimated analytically as a minimum norm least square solution to a set of linear equations. The fast leaning fully complex-valued neural classifier is used for recognizing human actions accurately. Optical flow-based features extracted from the video sequences are utilized to recognize 10 different human actions. The feature vectors are computationally simple first order statistics of the optical flow vectors, obtained from coarse to fine rectangular patches centered around the object. The results indicate the superior performance of the complex-valued neural classifier for action recognition. The superior performance of the complex neural network for action recognition stems from the fact that motion, by nature, consists of two components, one along each of the axes.

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.

RAPID HUMAN ACTION RECOGNITION IN H.264/AVC COMPRESSED DOMAIN FOR VIDEO SURVEILLANCE

This paper discusses a novel high-speed approach for human action recognition in H. 264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of our work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can effect in reduced hardware utilization and fast recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust in outdoor as well as indoor testing scenarios. We have tested our method on two benchmark action datasets and achieved more than 85% accuracy. The proposed algorithm classifies actions with speed (>2000 fps) approximately 100 times more than existing state-of-the-art pixel-domain algorithms.

Human Action Recognition in Compressed Domain using PBL-McRBFN Approach

Large variations in human actions lead to major challenges in computer vision research. Several algorithms are designed to solve the challenges. Algorithms that stand apart, help in solving the challenge in addition to performing faster and efficient manner. In this paper, we propose a human cognition inspired projection based learning for person-independent human action recognition in the H.264/AVC compressed domain and demonstrate a PBL-McRBEN based approach to help take the machine learning algorithms to the next level. Here, we use gradient image based feature extraction process where the motion vectors and quantization parameters are extracted and these are studied temporally to form several Group of Pictures (GoP). The GoP is then considered individually for two different bench mark data sets and the results are classified using person independent human action recognition. The functional relationship is studied using Projection Based Learning algorithm of the Meta-cognitive Radial Basis Function Network (PBL-McRBFN) which has a cognitive and meta-cognitive component. The cognitive component is a radial basis function network while the Meta-Cognitive Component(MCC) employs self regulation. The McC emulates human cognition like learning to achieve better performance. Performance of the proposed approach can handle sparse information in compressed video domain and provides more accuracy than other pixel domain counterparts. Performance of the feature extraction process achieved more than 90% accuracy using the PTIL-McRBFN which catalyzes the speed of the proposed high speed action recognition algorithm. We have conducted twenty random trials to find the performance in GoP. The results are also compared with other well known classifiers in machine learning literature.

An Optical How Feature and McFIS Based Approach for 3-Dimensional Human Action Recognition

We propose to develop a 3-D optical flow features based human action recognition system. Optical flow based features are employed here since they can capture the apparent movement in object, by design. Moreover, they can represent information hierarchically from local pixel level to global object level. In this work, 3-D optical flow based features a re extracted by combining the 2-1) optical flow based features with the depth flow features obtained from depth camera. In order to develop an action recognition system, we employ a Meta-Cognitive Neuro-Fuzzy Inference System (McFIS). The m of McFIS is to find the decision boundary separating different classes based on their respective optical flow based features. McFIS consists of a neuro-fuzzy inference system (cognitive component) and a self-regulatory learning mechanism (meta-cognitive component). During the supervised learning, self-regulatory learning mechanism monitors the knowledge of the current sample with respect to the existing knowledge in the network and controls the learning by deciding on sample deletion, sample learning or sample reserve strategies. The performance of the proposed action recognition system was evaluated on a proprietary data set consisting of eight subjects. The performance evaluation with standard support vector machine classifier and extreme learning machine indicates improved performance of McFIS is recognizing actions based of 3-D optical flow based features.

Human action recognition in H.264/AVC compressed domain using meta-cognitive radial basis function network

In this paper, we propose a H.264/AVC compressed domain human action recognition system with projection based metacognitive learning classifier (PBL-McRBFN). The features are extracted from the quantization parameters and the motion vectors of the compressed video stream for a time window and used as input to the classifier. Since compressed domain analysis is done with noisy, sparse compression parameters, it is a huge challenge to achieve performance comparable to pixel domain analysis. On the positive side, compressed domain allows rapid analysis of videos compared to pixel level analysis. The classification results are analyzed for different values of Group of Pictures (GOP) parameter, time window including full videos. The functional relationship between the features and action labels are established using PBL-McRBFN with a cognitive and meta-cognitive component. The cognitive component is a radial basis function, while the meta-cognitive component employs self-regulation to achieve better performance in subject independent action recognition task. The proposed approach is faster and shows comparable performance with respect to the state-of-the-art pixel domain counterparts. It employs partial decoding, which rules out the complexity of full decoding, and minimizes computational load and memory usage. This results in reduced hardware utilization and increased speed of classification. The results are compared with two benchmark datasets and show more than 90% accuracy using the PBL-McRBFN. The performance for various GOP parameters and group of frames are obtained with twenty random trials and compared with other well-known classifiers in machine learning literature. (C) 2015 Elsevier B.V. All rights reserved.

Compressed domain human action recognition in H.264/AVC video streams

This paper discusses a novel high-speed approach for human action recognition in H.264/AVC compressed domain. The proposed algorithm utilizes cues from quantization parameters and motion vectors extracted from the compressed video sequence for feature extraction and further classification using Support Vector Machines (SVM). The ultimate goal of the proposed work is to portray a much faster algorithm than pixel domain counterparts, with comparable accuracy, utilizing only the sparse information from compressed video. Partial decoding rules out the complexity of full decoding, and minimizes computational load and memory usage, which can result in reduced hardware utilization and faster recognition results. The proposed approach can handle illumination changes, scale, and appearance variations, and is robust to outdoor as well as indoor testing scenarios. We have evaluated the performance of the proposed method on two benchmark action datasets and achieved more than 85 % accuracy. The proposed algorithm classifies actions with speed (> 2,000 fps) approximately 100 times faster than existing state-of-the-art pixel-domain algorithms.

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).

A survey on compressed domain video analysis techniques

Image and video analysis requires rich features that can characterize various aspects of visual information. These rich features are typically extracted from the pixel values of the images and videos, which require huge amount of computation and seldom useful for real-time analysis. On the contrary, the compressed domain analysis offers relevant information pertaining to the visual content in the form of transform coefficients, motion vectors, quantization steps, coded block patterns with minimal computational burden. The quantum of work done in compressed domain is relatively much less compared to pixel domain. This paper aims to survey various video analysis efforts published during the last decade across the spectrum of video compression standards. In this survey, we have included only the analysis part, excluding the processing aspect of compressed domain. This analysis spans through various computer vision applications such as moving object segmentation, human action recognition, indexing, retrieval, face detection, video classification and object tracking in compressed videos.

Action of N-bromosuccinimide on human hemoglobin and its possible bearing on heme-globin linkage

A reaction of N-bromosuccinimide with the heme groups of hemoglobin has been studied spectrophotometrically. The reaction brings about the disappearance of characteristic absorption peaks of hemoglobin and is accompanied by the release of inorganic iron from the heme groups. Urea is obligatory for the reaction to take place at pH 4.0, while it can occur in the absence of urea at pH 7.0. The spectrum of hemoglobin which does not show any peak in the Soret region at pH 4.0 is “normalized” in the presence of urea or sucrose at the same pH. The effect of “normalization” in 8 M urea is apparent over the pH range 3.0–4.5. From the obligatory requirement of urea and sucrose for “normalization” of spectrum and the dependence of the release of inorganic iron on the concentration of urea, it is suggested that heme groups are “buried” within the globin at pH 4.0 and not dissociated from globin as supposed before.

Design and Synthesis of New Benzimidazole-Carbazole Conjugates for the Stabilization of Human Telomeric DNA, Telomerase Inhibition, and Their Selective Action on Cancer Cells

Cell-permeable small molecules that enhance the stability of the G-quadruplex (G4) DNA structures are currently among the most intensively pursued ligands for inhibition of the telomerase activity. Herein we report the design and syntheses of four novel benzimidazole carbazole conjugates and demonstrate their high binding affinity to G4 DNA. Si nuclease assay confirmed the ligand mediated G-quadruplex DNA protection. Additional evidence from Telomeric Repeat Amplification Protocol (TRAP-LIG) assay demonstrated efficient telomerase inhibition activity by the ligands. Two of the ligands showed IC50 values in the sub-micromolar range in the TRAP-LIG assay, which are the best among the benzimidazole derivatives reported so far. The ligands also exhibited cancer cell selective nuclear internalization, nuclear condensation, fragmentation, and eventually antiproliferative activity in long-term cell viability assays. Annexin V-FITC/PI staining assays confirm that the cell death induced by the ligands follows an apoptotic pathway. An insight into the mode of ligand binding was obtained from the molecular dynamics simulations.

Expression Profiling of Nucleotide Metabolism-Related Genes in Human Breast Cancer Cells After Treatment with 5-Fluorouracil

5-Fluorouracil (5-FU) is one of the most widely used drugs for treatment of cancers, including breast cancer that exhibits its anticancer activity by inhibiting DNA synthesis and also incorporated into DNA and RNA. The objective of this investigation was to find out the total nucleotide metabolism genes regulated by 5-FU in breast cancer cell line. The breast cancer cell line MCF-7 was treated with the drug 5-FU. To analyze the expression of genes, we have conducted the experiment using 1.7k and 19k human microarray slide and confirmed the expression of genes by semiquantitative reverse transcription-polymerase chain reaction. The expression of 44 genes involved in the nucleotide metabolism pathway was quantified. Of these 44 genes analyzed, transcription of 6 genes were upregulated and 9 genes were downregulated. Earlier studies revealed that the transcription of genes for key enzymes like thymidylate synthase, thymidinekinase, and dihydropyrimidine dehydrogenase are regulated by 5-FU. This study identified some novel genes like thioredoxin reductase, ectonucleotide triphosphate dephosphorylase, and CTP synthase are regulated by 5-FU. The data also reveal large-scale perturbation in transcription of genes not involved directly in the known mechanism of action of 5-FU.

Regulation of oxidative-stress responsive genes by arecoline in human keratinocytes

Background and Objective: Arecoline, an arecanut alkaloid present in the saliva of betel quid chewers, has been implicated in the pathogenesis of a variety of inflammatory oral diseases, including oral submucous fibrosis and periodontitis. To understand the molecular b asis of arecoline action in epithelial changes associated with these diseases, we investigated the effects of arecoline on human keratinocytes with respect to cell growth regulation and the expression of stress-responsive genes.Material and Methods:Human keratinocyte cells (of the HaCaT cell line) were treated with arecoline, following which cell viability was assessed using the Trypan Blue dye-exclusion assay, cell growth and proliferation were analyzed using the MTT (3-[4,5-dimethylthiazol-2-yl]-2,5-diphenyltetrazolium bromide) and 5-bromo-2-deoxyuridine incorporation assays, cell cycle arrest and generation of reactive oxygen species were examined using flow cytometry, and gene expression changes were investigated using the reverse transcription-polymerase chain reaction technique. The role of oxidative stress, muscarinic acetylcholine receptor and mitogen-activated protein kinase (MAPK) pathways were studied using specific inhibitors. Western blot analysis was performed to study p38 MAPK activation.Results:Arecoline induced the generation of reactive oxygen species and cell cycle arrest at the G1/G0 phase in HaCaT cells without affecting the expression of p21/Cip1. Arecoline-induced epithelial cell death at higher concentrations was caused by oxidative trauma without eliciting apoptosis. Sublethal concentrations of arecoline upregulated the expression of the following stress-responsive genes: heme oxygenase-1; ferritin light chain; glucose-6-phosphate dehydrogenase; glutamate-cysteine ligase catalytic subunit; and glutathione reductase.Additionally, there was a dose-dependent induction of interleukin-1alfa mRNA by arecoline via oxidative stress and p38 MAPK activation. Conclusion:our data highlight the role of oxidative stress in arecoline-mediated cell death, gene regulation and inflammatory processes in human keratinocytes.

Inhibition of Human Two-Pore Domain K+ Channel TREK1 by Local Anesthetic Lidocaine: Negative Cooperativity and Half-of-Sites Saturation Kinetics

TWIK-related K+ channel TREK1, a background leak K+ channel, has been strongly implicated as the target of several general and local anesthetics. Here, using the whole-cell and single-channel patch-clamp technique, we investigated the effect of lidocaine, a local anesthetic, on the human (h) TREK1 channel heterologously expressed in human embryonic kidney 293 cells by an adenoviral-mediated expression system. Lidocaine, at clinical concentrations, produced reversible, concentration-dependent inhibition of hTREK1 current, with IC50 value of 180 mu M, by reducing the single-channel open probability and stabilizing the closed state. We have identified a strategically placed unique aromatic couplet (Tyr352 and Phe355) in the vicinity of the protein kinase A phosphorylation site, Ser348, in the C-terminal domain (CTD) of hTREK1, that is critical for the action of lidocaine. Furthermore, the phosphorylation state of Ser348 was found to have a regulatory role in lidocaine-mediated inhibition of hTREK1. It is interesting that we observed strong intersubunit negative cooperativity (Hill coefficient = 0.49) and half-of-sites saturation binding stoichiometry (half-reaction order) for the binding of lidocaine to hTREK1. Studies with the heterodimer of wild-type (wt)-hTREK1 and Delta 119 C-terminal deletion mutant (hTREK1(wt)-Delta 119) revealed that single CTD of hTREK1 was capable of mediating partial inhibition by lidocaine, but complete inhibition necessitates the cooperative interaction between both the CTDs upon binding of lidocaine. Based on our observations, we propose a model that explains the unique kinetics and provides a plausible paradigm for the inhibitory action of lidocaine on hTREK1.