Slip and fall event detection using Bayesian Belief Network

This paper proposes a method to detect slip-only events and fall events based on the motion activity measure and human silhouette shape variations. Here, we also apply the Bayesian Belief Network (BBN) to model the causality of the events before and after the fall and slip-only events. The motion measure is obtained by analyzing the energy of the motion active (MA) area in the integrated spatiotemporal energy (ISTE) map. Unlike the motion history image (MHI), the ISTE map can be applied to detect fall and slip-only events. The contributions of this study are: (a) proposing the ISTE map; (b) detecting the fall parallel to the optical axis; (c) application to non-fixed frame rate video; (d) identifying the slip-only event; and (e) using BBN to model the causality of the slip or fall events with other events. Early identification of a slip-only event can help prevent falls and injuries. In the experiments, we demonstrate that our method is effective in detecting both fall and slip-only events.     

Facial expression recognition using radial encoding of local Gabor features and classifier synthesis

Primarily motivated by some characteristics of the human visual cortex (HVC), we propose a new facial expression recognition scheme, involving a statistical synthesis of hierarchical classifiers. In this scheme, the input images of the database are first subjected to local, multi-scale Gabor-filter operations, and then the resulting Gabor decompositions are encoded using radial grids, imitating the topographical map-structure of the HVC. The codes are fed to local classifiers to produce global features, representing facial expressions. Experimental results show that such a hybrid combination of the HVC structure with a hierarchical classifier significantly improves expression recognition accuracy when applied to wide-ranging databases in comparison with the results in the literature. Furthermore, the proposed system is not only robust to corrupted data and missing information, but can also be generalized to cross-database expression recognition.     

A new scheme for covert communication via 3G encoded speech

Mobile communication through 3G network has grown rapidly in recent years. It might be of interest to transmit secret messages over 3G voice channels. In this paper, we introduce a new covert communication scheme via Adaptive Multi-Rate Wideband (AMR-WB) encoded speech. An adaptive suboptimal pulse combination constrained (ASOPCC) method is presented to embed data on compressed speech signal of AMR-WB codec. The method takes advantage of the “redundancy”, created by non-exhaustive search of algebraic codebook, to encode secret information. An embedding factor η is used to control embedding bits. By properly setting η, ASOPCC can offer a better trade-off between speech quality and embedding capacity in the process of coding mode switching. Experimental results show that the proposed method is quite promising for both high capacity and good imperceptivity. Although ASOPCC is only applied to AMR-WB codec in this article, it can be further used by any other speech coding based on Algebraic Coded Exited Linear Prediction (ACELP).     

Exploring context and content links in social media: a latent space method

Social media networks contain both content and context-specific information. Most existing methods work with either of the two for the purpose of multimedia mining and retrieval. In reality, both content and context information are rich sources of information for mining, and the full power of mining and processing algorithms can be realized only with the use of a combination of the two. This paper proposes a new algorithm which mines both context and content links in social media networks to discover the underlying latent semantic space. This mapping of the multimedia objects into latent feature vectors enables the use of any off-the-shelf multimedia retrieval algorithms. Compared to the state-of-the-art latent methods in multimedia analysis, this algorithm effectively solves the problem of sparse context links by mining the geometric structure underlying the content links between multimedia objects. Specifically for multimedia annotation, we show that an effective algorithm can be developed to directly construct annotation models by simultaneously leveraging both context and content information based on latent structure between correlated semantic concepts. We conduct experiments on the Flickr data set, which contains user tags linked with images. We illustrate the advantages of our approach over the state-of-the-art multimedia retrieval techniques.     

Identification of Breast Cancer Prognosis Markers via Integrative Analysis

In breast cancer research, it is of great interest to identify genomic markers associated with prognosis. Multiple gene profiling studies have been conducted for such a purpose. Genomic markers identified from the analysis of single datasets often do not have satisfactory reproducibility. Among the multiple possible reasons, the most important one is the small sample sizes of individual studies. A cost-effective solution is to pool data from multiple comparable studies and conduct integrative analysis. In this study, we collect four breast cancer prognosis studies with gene expression measurements. We describe the relationship between prognosis and gene expressions using the accelerated failure time (AFT) models. We adopt a 2-norm group bridge penalization approach for marker identification. This integrative analysis approach can effectively identify markers with consistent effects across multiple datasets and naturally accommodate the heterogeneity among studies. Statistical and simulation studies demonstrate satisfactory performance of this approach. Breast cancer prognosis markers identified using this approach have sound biological implications and satisfactory prediction performance.     

Performance evaluation of enhancement of the layered self-scheduling approach for heterogeneous multicore cluster systems

Previously we have proposed a Layered Self-Scheduling (LSS) approach that is a hybrid MPI and OpenMP based loop self-scheduling approach for dealing with the heterogeneity problem on a cluster system consisting of multi-core compute nodes, where the allocation functions of several well-known schemes have been modified for better performance. Though LSS provides better performance than the conventional self-scheduling schemes, we found the performance can be improved further after our comprehensive experiments and analyses. The newly proposed task scheduling strategy, called Enhanced Layered Self-Scheduling (ELSS), aims at how to utilize the compute powers of multiple processor cores more efficiently in the master compute node and how to schedule tasks to have more stable performance improvements. We have evaluated the new task scheduling strategy by three benchmark applications: Matrix Multiplication, Monte Carlo Integration, and Mandelbrot Set Computation. It is recommended that the global scheduler adopts Guided Self-Scheduling (GSS) for all, and the local scheduler adopts the static scheme for applications with regular workload distribution but any scheme for applications with irregular workload distribution. Experimental results show the best speedups obtained by ELSS for the three benchmark programs are 1.373, 13.34 and 2.4, respectively, compared with that scheduled by LSS.     

Probing and diagnosis of slider–disk interactions in nanometer clearance regime using artificial neural network

This paper addresses the issue of system identification for an active-head slider used to form a stable and reliable head–disk interface with a spacing of sub 3?nm. A new identification method is proposed to fit the highly non-stationary and highly nonlinear slider dynamics. The estimated model can be used for design of a model based nonlinear controller to control the flying height within the desired range. The effectiveness of the proposed system identification method is verified with simulation examples.     

Task-driven e-manufacturing resource configurable model

Manufacturing resource configuration (MRC) plays a very important role in an e-Manufacturing system. Higher requirements for optimal configuration under online resource visibility and traceability have led to two main challenges. One is that more features of manufacturing tasks affecting the optimization results should be taken into consideration when establishing the MRC mathematical model for a manufacturing cell. The other is that manufacturing information should be given equal attention as MRC to realize real-time visibility and traceability of the resulting manufacturing cells. This paper presents a comprehensive mathematical model which considers more practical features of manufacturing tasks (e.g. batch volume and alternative processing routes) for manufacturing cell formation. This model adopts a fuzzy clustering method to group the manufacturing tasks and machines. Moreover, it is enabled by a smart equipment model to realize the configurable model of real-time manufacturing information and corresponding visualization and tracing methods. A case study is given to demonstrate the proposed models and methods.     

Laguerre超群上的Hardy-Littlewood-Sobolev不等式

利用Laguerre超群K上的广义次拉普拉斯算子L定义K上的Riesz位势,并证明它是Lp(1p+∞)有界和弱(1,1)有界的,即证明K上的Hardy-Littlewood-Sobolev不等式.它为进一步分析K上的偏微分方程问题提供了一个有利的工具.