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.

Petri net based performance modeling for effective DVFS for multithreaded programs

Dynamic Voltage and Frequency Scaling (DVFS) is a very effective tool for designing trade-offs between energy and performance. In this paper, we use a formal Petri net based program performance model that directly captures both the application and system properties, to find energy efficient DVFS settings for CMP systems, that satisfy a given performance constraint, for SPMD multithreaded programs. Experimental evaluation shows that we achieve significant energy savings, while meeting the performance constraints.

Evaluation of dynamic voltage and frequency scaling for stream programs

Dynamic Voltage and Frequency Scaling (DVFS) offers a huge potential for designing trade-offs involving energy, power, temperature and performance of computing systems. In this paper, we evaluate three different DVFS schemes - our enhancement of a Petri net performance model based DVFS method for sequential programs to stream programs, a simple profile based Linear Scaling method, and an existing hardware based DVFS method for multithreaded applications - using multithreaded stream applications, in a full system Chip Multiprocessor (CMP) simulator. From our evaluation, we find that the software based methods achieve significant Energy/Throughput2(ET−2) improvements. The hardware based scheme degrades performance heavily and suffers ET−2 loss. Our results indicate that the simple profile based scheme achieves the benefits of the complex Petri net based scheme for stream programs, and present a strong case for the need for independent voltage/frequency control for different cores of CMPs, which is lacking in most of the state-of-the-art CMPs. This is in contrast to the conclusions of a recent evaluation of per-core DVFS schemes for multithreaded applications for CMPs.

Dataflow analysis for data-race free programs

Memory models for shared-memory concurrent programming languages typically guarantee sequential consistency (SC) semantics for datarace-free (DRF) programs, while providing very weak or no guarantees for non-DRF programs. In effect programmers are expected to write only DRF programs, which are then executed with SC semantics. With this in mind, we propose a novel scalable solution for dataflow analysis of concurrent programs, which is proved to be sound for DRF programs with SC semantics. We use the synchronization structure of the program to propagate dataflow information among threads without requiring to consider all interleavings explicitly. Given a dataflow analysis that is sound for sequential programs and meets certain criteria, our technique automatically converts it to an analysis for concurrent programs.

Automatic compilation of MATLAB programs for synergistic execution on heterogeneous processors

MATLAB is an array language, initially popular for rapid prototyping, but is now being increasingly used to develop production code for numerical and scientific applications. Typical MATLAB programs have abundant data parallelism. These programs also have control flow dominated scalar regions that have an impact on the program's execution time. Today's computer systems have tremendous computing power in the form of traditional CPU cores and throughput oriented accelerators such as graphics processing units(GPUs). Thus, an approach that maps the control flow dominated regions to the CPU and the data parallel regions to the GPU can significantly improve program performance. In this paper, we present the design and implementation of MEGHA, a compiler that automatically compiles MATLAB programs to enable synergistic execution on heterogeneous processors. Our solution is fully automated and does not require programmer input for identifying data parallel regions. We propose a set of compiler optimizations tailored for MATLAB. Our compiler identifies data parallel regions of the program and composes them into kernels. The problem of combining statements into kernels is formulated as a constrained graph clustering problem. Heuristics are presented to map identified kernels to either the CPU or GPU so that kernel execution on the CPU and the GPU happens synergistically and the amount of data transfer needed is minimized. In order to ensure required data movement for dependencies across basic blocks, we propose a data flow analysis and edge splitting strategy. Thus our compiler automatically handles composition of kernels, mapping of kernels to CPU and GPU, scheduling and insertion of required data transfer. The proposed compiler was implemented and experimental evaluation using a set of MATLAB benchmarks shows that our approach achieves a geometric mean speedup of 19.8X for data parallel benchmarks over native execution of MATLAB.

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.

TCP: thread contention predictor for parallel programs

With proliferation of chip multicores (CMPs) on desktops and embedded platforms, multi-threaded programs have become ubiquitous. Existence of multiple threads may cause resource contention, such as, in on-chip shared cache and interconnects, depending upon how they access resources. Hence, we propose a tool - Thread Contention Predictor (TCP) to help quantify the number of threads sharing data and their sharing pattern. We demonstrate its use to predict a more profitable shared, last level on-chip cache (LLC) access policy on CMPs. Our cache configuration predictor is 2.2 times faster compared to the cycle-accurate simulations. We also demonstrate its use for identifying hot data structures in a program which may cause performance degradation due to false data sharing. We fix layout of such data structures and show up-to 10% and 18% improvement in execution time and energy-delay product (EDP), respectively.

Static analysis for checking data format compatibility of programs

Large software systems are developed by composing multiple programs. If the programs manip-ulate and exchange complex data, such as network packets or files, it is essential to establish that they follow compatible data formats. Most of the complexity of data formats is associated with the headers. In this paper, we address compatibility of programs operating over headers of network packets, files, images, etc. As format specifications are rarely available, we infer the format associated with headers by a program as a set of guarded layouts. In terms of these formats, we define and check compatibility of (a) producer-consumer programs and (b) different versions of producer (or consumer) programs. A compatible producer-consumer pair is free of type mismatches and logical incompatibilities such as the consumer rejecting valid outputs gen-erated by the producer. A backward compatible producer (resp. consumer) is guaranteed to be compatible with consumers (resp. producers) that were compatible with its older version. With our prototype tool, we identified 5 known bugs and 1 potential bug in (a) sender-receiver modules of Linux network drivers of 3 vendors and (b) different versions of a TIFF image library.

Antithyroid drugs and their analogues: synthesis, structure, and mechanism of action

Thyroid hormones are essential for the development and differentiation of all cells of the human body. They regulate protein, fat, and carbohydrate metabolism. In this Account, we discuss the synthesis, structure, and mechanism of action of thyroid hormones and their analogues. The prohormone thyroxine (14) is synthesized on thyroglobulin by thyroid peroxidase (TPO), a heme enzyme that uses iodide and hydrogen peroxide to perform iodination and phenolic coupling reactions. The monodeiodination of T4 to 3,3',5-triiodothyronine (13) by selenium-containing deiodinases (ID-1, ID-2) is a key step in the activation of thyroid hormones. The type 3 deiodinase (ID-3) catalyzes the deactivation of thyroid hormone in a process that removes iodine selectively from the tyrosyl ring of T4 to produce 3,3',5'-triiodothyronine (rT3). Several physiological and pathological stimuli influence thyroid hormone synthesis. The overproduction of thyroid hormones leads to hyperthyroidism, which is treated by antithyroid drugs that either inhibit the thyroid hormone biosynthesis and/or decrease the conversion of T4 to T3. Antithyroid drugs are thiourea-based compounds, which indude propylthiouracil (PTU), methimazole (MM I), and carbimazole (CBZ). The thyroid gland actively concentrates these heterocyclic compounds against a concentration gradient Recently, the selenium analogues of PTU, MMI, and CBZ attracted significant attention because the selenium moiety in these compounds has a higher nucleophilicity than that of the sulfur moiety. Researchers have developed new methods for the synthesis of the selenium compounds. Several experimental and theoretical investigations revealed that the selone (C=Se) in the selenium analogues is more polarized than the thione (C=S) in the sulfur compounds, and the selones exist predominantly in their zwitterionic forms. Although the thionamide-based antithyroid drugs have been used for almost 70 years, the mechanism of their action is not completely understood. Most investigations have revealed that MMI and PTU irreversibly inhibit TPO. PTU, MTU, and their selenium analogues also inhibit ID-1, most likely by reacting with the selenenyl iodide intermediate. The good ID-1 inhibitory activity of Pill and its analogues can be ascribed to the presence of the -N(H)-C(=O)- functionality that can form hydrogen bonds with nearby amino add residues in the selenenyl sulfide state. In addition to the TPO and ID-1 inhibition, the selenium analogues are very good antioxidants. In the presence of cellular reducing agents such as GSH, these compounds catalytically reduce hydrogen peroxide. They can also efficiently scavenge peroxynitrite, a potent biological oxidant and nitrating agent.

Differential Action of Glycoprotein Hormones: Significance in Cancer Progression

Growth of multicellular organisms depends on maintenance of proper balance between proliferation and differentiation. Any disturbance in this balance in animal cells can lead to cancer. Experimental evidence is provided to conclude with special reference to the action of follicle-stimulating hormone (FSH) on Sertoli cells, and luteinizing hormone (LH) on Leydig cells that these hormones exert a differential action on their target cells, i.e., stimulate proliferation when the cells are in an undifferentiated state which is the situation with cancer cells and promote only functional parameters when the cell are fully differentiated. Hormones and growth factors play a key role in cell proliferation, differentiation, and apoptosis. There is a growing body of evidence that various tumors express some hormones at high levels as well as their cognate receptors indicating the possibility of a role in progression of cancer. Hormones such as LH, FSH, and thyroid-stimulating hormone have been reported to stimulate cell proliferation and act as tumor promoter in a variety of hormone-dependent cancers including gonads, lung, thyroid, uterus, breast, prostate, etc. This review summarizes evidence to conclude that these hormones are produced by some cancer tissues to promote their own growth. Also an attempt is made to explain the significance of the differential action of hormones in progression of cancer with special reference to prostate cancer.