Distance-driven fusion of gait and face for human identification in video

Gait and face are two important biometrics for human identification. Complementary properties of these two biometrics suggest fusion of them. The relationship between gait and face in the fusion is affected by the subject-to-camera distance. On the one hand, gait is a suitable biometric trait for human recognition at a distance. On the other hand, face recognition is more reliable when the subject is close to the camera. This paper proposes an adaptive fusion method called distance-driven fusion to combine gait and face for human identification in video. Rather than predefined fixed fusion rules, distance-driven fusion dynamically adjusts its rule according to the subject-to-camera distance in real time. Experimental results show that distance-driven fusion performs better than not only single biometric, but also the conventional
static fusion rules including MEAN, PRODUCT, MIN, and MAX.

Adaptive fusion of gait and face for human identification in video

Most work on multi-biometric fusion is based on static fusion rules which cannot respond to the changes of the environment and the individual users. This paper proposes adaptive multi-biometric fusion, which dynamically adjusts the fusion rules to suit the real-time external conditions. As a typical example, the adaptive fusion of gait and face in video is studied. Two factors that may affect the relationship between gait and face in the fusion are considered, i.e., the view angle and the subject-to-camera distance. Together they determine the way gait and face are fused at an arbitrary time. Experimental results show that the adaptive fusion performs significantly better than not only single biometric traits, but also those widely adopted static fusion rules including SUM, PRODUCT, MIN, and MAX.

A neural network based human identification framework using ear images

This paper presents a framework that uses ear images for human identification. The framework makes use of Principal Component Analysis (PCA) for ear image feature extraction and Multilayer Feed Forward Neural Network for classification. Framework are proposed to improve recognition accuracy of human identification. The framework was tested on an ear image database to evaluate its reliability and recognition accuracy. The experimental results showed that our framework achieved higher stable recognition accuracy and over-performed other existing methods. The recognition accuracy stability and computation time with respect to different image sizes and factors were investigated thoroughly as well in the experiments.

A review of vision-based gait recognition methods for human identification

Human identification by gait has created a great deal of interest in computer vision community due to its advantage of inconspicuous recognition at a relatively far distance. This paper provides a comprehensive survey of recent developments on gait recognition approaches. The survey emphasizes on three major issues involved in a general gait recognition system, namely gait image representation, feature dimensionality reduction and gait classification. Also, a review of the available public gait datasets is presented. The concluding discussions outline a number of research challenges and provide promising future directions for the field.

Human identification from ECG signals via sparse representation of local segments

This work proposes a novel framework to extract compact and discriminative features from Electrocardiogram (ECG) signals for human identification based on sparse representation of local segments. Specifically, local segments extracted from an ECG signal are projected to a small number of basic elements in a dictionary, which is learned from training data. A final representation is extracted by performing a max pooling procedure over all the sparse coefficient vectors in the ECG signal. Unlike most of existing methods for human identification from ECG signals which require segmentation of individual heartbeats or extraction of fiducial points, the proposed method does not need to segment individual heartbeats or detect any fiducial points. The method achieves an 99.48% accuracy on a 100 subjects dataset constructed from a publicly available database, which demonstrates that both local and global structural information are well captured to characterize the ECG signals.

Extracting fingerprint features using textures

Personal identification of individuals is becoming increasingly adopted in society today. Due to the large number of electronic systems that require human identification, faster and more secure identification systems are pursued. Biometrics is based upon the physical characteristics of individuals; of these the fingerprint is the most common as used within law enforcement. Fingerprint-based systems have been introduced into the society but have not been well received due to relatively high rejection rates and false acceptance rates. This limited acceptance of fingerprint identification systems requires new techniques to be investigated to improve this identification method and the acceptance of the technology within society. Electronic fingerprint identification provides a method of identifying an individual within seconds quickly and easily. The fingerprint must be captured instantly to allow the system to identify the individual without any technical user interaction to simplify system operation. The performance of the entire system relies heavily on the quality of the original fingerprint image that is captured digitally. A single fingerprint scan for verification makes it easier for users accessing the system as it replaces the need to remember passwords or authorisation codes. The identification system comprises of several components to perform this function, which includes a fingerprint sensor, processor, feature extraction and verification algorithms. A compact texture feature extraction method will be implemented within an embedded microprocessor-based system for security, performance and cost effective production over currently available commercial fingerprint identification systems. To perform these functions various software packages are available for developing programs for windows-based operating systems but must not constrain to a graphical user interface alone. MATLAB was the software package chosen for this thesis due to its strong mathematical library, data analysis and image analysis libraries and capability. MATLAB enables the complete fingerprint identification system to be developed and implemented within a PC environment and also to be exported at a later date directly to an embedded processing environment. The nucleus of the fingerprint identification system is the feature extraction approach presented in this thesis that uses global texture information unlike traditional local information in minutiae-based identification methods. Commercial solid-state sensors such as the type selected for use in this thesis have a limited contact area with the fingertip and therefore only sample a limited portion of the fingerprint. This limits the number of minutiae that can be extracted from the fingerprint and as such limits the number of common singular points between two impressions of the same fingerprint. The application of texture feature extraction will be tested using variety of fingerprint images to determine the most appropriate format for use within the embedded system. This thesis has focused on designing a fingerprint-based identification system that is highly expandable using the MATLAB environment. The main components that are defined within this thesis are the hardware design, image capture, image processing and feature extraction methods. Selection of the final system components for this electronic fingerprint identification system was determined by using specific criteria to yield the highest performance from an embedded processing environment. These platforms are very cost effective and will allow fingerprint-based identification technology to be implemented in more commercial products that can benefit from the security and simplicity of a fingerprint identification system.

Identification of a by-product of nitric oxide synthase activity in human acute brain injury with in vivo proton magnetic resonance spectroscopy

BACKGROUND AND PURPOSE: Laboratory studies have been used to identify nitric oxide as a notable mediator in neuronal death after acute brain injury. To our knowledge, this has not previously been confirmed with in vivo study in humans. Our purpose was to seek in vivo evidence for the induction of nitric oxide synthase (NOS) in human acute brain injury by using proton MR spectroscopy.

METHODS: In vitro proton MR spectra were obtained in neural extracts from 30 human cadavers, and in vivo spectra were obtained in 20 patients with acute brain injury and in a similar number of control subjects.

RESULTS: We identified a unique peak at 3.15 ppm by using in vivo proton MR spectroscopy in eight of 20 patients with acute brain injury but not in 20 healthy volunteers (P < .002). On the basis of in vitro data, we have tentatively assigned this peak to citrulline, a NOS by-product.

CONCLUSION: To our knowledge, our findings suggest, for the first time, that excitotoxicity may occur in human acute brain injury. Confirmation with the acquisition of spectra in very early acute cerebral injury would provide a rationale for the use of neuroprotective agents in these conditions, as well as a new noninvasive method for quantification.

Identification of tRNAs incorporated into wild-type and mutant human immunodeficiency virus type 1

We have identified the tRNAs which are incorporated into both wild-type human immunodeficiency virus type 1 strain IIIB (HIV-1IIIB) produced in COS-7 cells transfected with HIV-1 proviral DNA and mutant, noninfectious HIV-1Lai particles produced in a genetically engineered Vero cell line. The mutant proviral DNA contains nucleotides 678 to 8944; i.e., both long terminal repeats and the primer binding site are absent. As analyzed by two-dimensional polyacrylamide gel electrophoresis, both mutant and wild-type HIV-1 contain four major-abundance tRNA species, which include tRNA(1,2Lys), tRNA(3Lys) (the putative primer for HIV-1 reverse transcriptase) and tRNA(Ile). Identification was accomplished by comparing the electrophoretic mobilities and RNase T1 digests with those of tRNA(3Lys) and tRNA(1,2Lys) purified from human placenta and comparing the partial nucleotide sequence at the 3' end of each viral tRNA species with published tRNA sequences. Thus, the absence of the primer binding site in the mutant virus does not affect tRNA(Lys) incorporation into HIV-1. However, only the wild-type virus contains tRNA(3Lys) tightly associated with the viral RNA genome. The identification of the tightly associated tRNA as tRNA(3Lys) is based upon an electrophoretic mobility identical to that of tRNA(3Lys) and the ability of this RNA to hybridize with a tRNA(3Lys)-specific DNA probe. In addition to the four wild-type tRNA species, the mutant HIV-1-like particle contains two tRNA(His) species and three tRNA-sized species that we have been unable to identify. Their absence in wild-type virus makes it unlikely that they are required for viral infectivity.

Identification of fatty acid translocase on human skeletal muscle mitochondrial membranes: essential role in fatty acid oxidation

Fatty acid translocase (FAT/CD36) is a transport protein with a high affinity for long-chain fatty acids (LCFA). It was recently identified on rat skeletal muscle mitochondrial membranes and found to be required for palmitate uptake and oxidation. Our aim was to identify the presence and elucidate the role of FAT/CD36 on human skeletal muscle mitochondrial membranes. We demonstrate that FAT/CD36 is present in highly purified human skeletal mitochondria. Blocking of human muscle mitochondrial FAT/CD36 with the specific inhibitor sulfo-N-succimidyl-oleate (SSO) decreased palmitate oxidation in a dose-dependent manner. At maximal SSO concentrations (200 μM) palmitate oxidation was decreased by 95% (P < 0.01), suggesting an important role for FAT/CD36 in LCFA transport across the mitochondrial membranes. SSO treatment of mitochondria did not affect mitochondrial octanoate oxidation and had no effect on maximal and submaximal carnitine palmitoyltransferase I (CPT I) activity. However, SSO treatment did inhibit palmitoylcarnitine oxidation by 92% (P < 0.001), suggesting that FAT/CD36 may be playing a role downstream of CPT I activity, possibly in the transfer of palmitoylcarnitine from CPT I to carnitine-acylcarnitine translocase. These data provide new insight regarding human skeletal muscle mitochondrial fatty acid (FA) transport, and suggest that FAT/CD36 could be involved in the cellular and mitochondrial adaptations resulting in improved and/or impaired states of FA oxidation.

The impact of socially responsible human resource management on employees' organizational citizenship behaviour: the mediating role of organizational identification

Based on insights from social exchange and social identity theories, this paper examines the influence of three dimensions of socially responsible human resource management (SR-HRM), namely legal compliance HRM, employee-oriented HRM and general CSR facilitation HRM, on employees' organizational citizenship behaviour (OCB). Structural equation modelling of dyadic data collected from Chinese employees and their direct supervisors in three phases revealed that whilst organizational identification fully mediated the relationship between employee-oriented HRM and employee OCB, general CSR facilitation HRM had a direct effect on employee OCB. In contrast, legal compliance HRM neither influenced employee OCB directly, nor indirectly through organizational identification. The findings highlight the important but complex role played by SR-HRM in eliciting positive employee work outcomes, and contribute to our knowledge of the mechanisms underlying this relationship.

ORP-3, a human oxysterol-binding protein gene differentially expressed in hematopoietic cells

Using differential display polymerase chain reaction, a gene was identified in CD34+-enriched populations that had with low or absent expression in CD34- populations. The full coding sequence of this transcript was obtained, and the predicted protein has a high degree of homology to oxysterol-binding protein. This gene has been designated OSBP-related protein 3 (ORP-3). Expression of ORP-3 was found to be 3- to 4-fold higher in CD34+ cells than in CD34- cells. Additionally, expression of this gene was 2-fold higher in the more primitive subfraction of hematopoietic cells defined by the CD34+38- phenotype and was down-regulated with the proliferation and differentiation of CD34+ cells. The ORP-3 predicted protein contains an oxysterol-binding domain. Well-characterized proteins expressing this domain bind oxysterols in a dose-dependent fashion. Biologic activities of oxysterols include inhibition of cholesterol biosynthesis and cell proliferation in a variety of cell types, among them hematopoietic cells. Characterization and differential expression of ORP-3 implicates a possible role in the mediation of oxysterol effects on hematopoiesis.

Identification and characterization of a lymphocytic Rho-GTPase effector: rhotekin-2

Rhotekin belongs to the group of proteins containing a Rho-binding domain that are target peptides (effectors) for the Rho-GTPases. We previously identified a novel cDNA with homology to human rhotekin and in this study we cloned and characterized the coding region of this novel 12-exon gene. The ORF encodes a 609 amino-acid protein comprising a Class I Rho-binding domain and pleckstrin homology (PH) domain. Cellular cDNA expression of this new protein, designated Rhotekin-2 (RTKN2), was shown in the cytosol and nucleus of CHO cells. Using bioinformatics and RTPCR we identified three major splice variants, which vary in both the Rho-binding and PH domains. Real-time PCR studies showed exclusive RTKN2 expression in pooled lymphocytes and further purification indicated sole expression in CD4^_pos T-cells and bone marrow-derived B-cells. Gene expression was increased in quiescent T-cells but negligible in activated proliferating cells. In malignant samples expression was absent in myeloid leukaemias, low in most B-cell malignancies and CD8^pos T-cell malignancies, but very high in CD4^pos/CD8^pos T-lymphoblastic lymphoma. As the Rho family is critical in lymphocyte development and function, RTKN2 may play an important role in lymphopoiesis.

Identification of novel genes expressed during rhabdomyosarcoma differentiation using cDNA microarrays

Rhabdomyosarcomas (RMS) are highly aggressive tumors that are thought to arise as a consequence of the regulatory disruption of the growth and differentiation of skeletal muscle progenitor cells. Normal myogenesis is characterized by the expression of the myogenic regulatory factor gene family but, despite their expression in RMS, these tumor cells fail to complete the latter stages of myogenesis. The RMS cell line RD-A was treated with 12-O-tetradecanoylphorbol-13-acetate to induce differentiation and cultured for 10 days. RNA was extracted on days 1, 3, 6, 8 and 10. A human skeletal muscle cDNA microarray was developed and used to analyze the global gene expression of RMS tumors over the time-course of differentiation. As a comparison, the genes identified were subsequently examined during the differentiated primary human skeletal muscle cultures. Prothymosin alpha (PTMA), and translocase of inner mitochondrial membrane 10 (Tim10), two genes not previously implicated in RMS, showed reduced expression during differentiation. Marked differences in the expression of PTMA and Tim10 were observed during the differentiation of human primary skeletal muscle cells. These results identify several new genes with potential roles in the myogenic arrest present in rhabdomyosarcoma. PTMA expression in RMS biopsy samples might prove to be an effective diagnostic marker for this disease.

Identification of genes differentially regulated by the P210 BCR/ABL1 fusion oncogene using cDNA microarrays

Objective: The t(9;22) translocation is associated with more than 95% of cases of chronic myeloid leukemia. The resulting fusion of the BCR and ABL1 loci produces the constitutively active BCR/ABL1 tyrosine kinase. A wide range of signal transduction molecules are activated by BCR/ABL1, including MYC, PI-3 kinase, and different STAT molecules. In contrast, relatively few genes are known to be regulated by BCR/ABL1 at the level of transcription.

Materials and Methods: In an effort to better understand the transcriptional program activated by BCR/ABL1, we used cDNA microarrays to evaluate the relative expression of approximately 6450 human genes in U937 myelomonocytic cells expressing P210 BCR/ABL1 via a tetracycline-inducible promoter.

Results: We confirmed the previously reported up-regulation of the PIM1 and JUN oncogenes by BCR/ABL1. In addition, we identified 59 more genes up-regulated by BCR/ABL1. Interestingly, roughly one third of these were genes previously reported to be interferon (IFN)-responsive, including the OAS1, IFIT1, IFI16, ISGF3G, and STAT1 genes. An additional seven BCR/ABL1-regulated genes were found to be IFN-responsive in U937 cells. The expression profile also included genes encoding transcription factors, kinases, and signal transduction molecules, as well as genes regulating cell growth, differentiation, apoptosis, and cell adhesion, features previously suggested to be affected by BCR/ABL1.

Conclusion: These observations shed novel insight into the mechanism of BCR/ABL1 action and provide a range of targets for further investigation.