Unconstrained monocular 3D human pose estimation by action detection and cross-modality regression forest

This work addresses the challenging problem of unconstrained 3D human pose estimation (HPE) from a novel perspective. Existing approaches struggle to operate in realistic applications, mainly due to their scene-dependent priors, such as background segmentation and multi-camera network, which restrict their use in unconstrained environments. We therfore present a framework which applies action detection and 2D pose estimation techniques to infer 3D poses in an unconstrained video. Action detection offers spatiotemporal priors to 3D human pose estimation by both recognising and localising actions in space-time. Instead of holistic features, e.g. silhouettes, we leverage the flexibility of deformable part model to detect 2D body parts as a feature to estimate 3D poses. A new unconstrained pose dataset has been collected to justify the feasibility of our method, which demonstrated promising results, significantly outperforming the relevant state-of-the-arts. © 2013 IEEE.

Direct detection of underivatized chitooligosaccharides produced through chitinase action using capillary zone electrophoresis

Capillary electrophoresis with capacitively coupled contactless conductivity detection was successfully used to quantify N-acetylglucosamine and five N-acetyl-chitooligosaccharides (C2-C6) produced after reaction with a purified chitinase (TmChi) from Tenebrio molitor (Coleoptera). No derivatization process was necessary. The separation was developed using 10 mM NaOH with 10% (v/v) acetonitrile as background electrolyte and homemade equipment with a system that avoids the harmful effect of electrolysis. The limit of detection for all oligosaccharides was ca. 3 mu M, and the results indicated that the larger the oligosaccharide, the higher the sensitivity. Analysis of the chitooligosaccharides produced revealed that TmChi has an endolytic cleavage pattern with C5 as the best substrate (higher catalytic efficiency k(cat)/K-M) releasing C2 and C3. (c) 2007 Elsevier Inc. All rights reserved.

Conjugated polymer−titania nanoparticle hybrid films : random lasing action and ultrasensitive detection of explosive vapors

We have first demonstrated that a random laser action generated by a hybrid film composed of a semiconducting organic polymer (SOP) and TiO₂ nanoparticles can be used to detect 2,4,6-trinitrotoluene (TNT) vapors. The hybrid film was fabricated by spin-casting SOP solution dispersed with nanosized TiO₂ particles on quartz glass. The SOP in the hybrid film functioned as both the gain medium and the sensory transducer. A random lasing action was observed with a certain pump power when the size (diameter of 50 nm) and concentration (8.9 - 10¹²/cm³) of TiO₂ nanoparticles were optimized. Measurements of fluorescence quenching behavior of the hybrid film in TNT vapor atmosphere (10 ppb) showed that attenuated lasing in optically pumped hybrid film displayed a sensitivity to vapors of explosives more than 20 times higher than was observed from spontaneous emission. This phenomenon has been explained with the four-level laser model. Since the sensory transducer used in the hybrid polymer/nanoparticles system could be replaced by other functional materials, the concept developed could be extended to more general domains of chemical or environment detection.

Using response action with Intelligent Intrusion detection and prevention System against web application malware

Findings: After evaluating the new system, a better result was generated in line with detection efficiency and the false alarm rate. This demonstrates the value of direct response action in an intrusion detection system.

Immunohistochemical detection of estrogen receptor beta in alveolar bone cells of estradiol-treated female rats: possible direct action of estrogen on osteoclast life span

Conselho Nacional de Desenvolvimento Científico e Tecnológico (CNPq)

Early detection of action potential duration alternans using an autoregressive model

Annual Meeting of the Biophysical Society, San Diego, USA

Using an adaptive autoregressive model for the early detection of action potential duration alternans

Cardiostim 2012, Nice, France

Design and standardization of PCR primers and protocols for detection of clonal immunoglobulin and T-cell receptor gene recombinations in suspect lymphoproliferations: report of the BIOMED-2 Concerted Action BMH4-CT98-3936.

In a European BIOMED-2 collaborative study, multiplex PCR assays have successfully been developed and standardized for the detection of clonally rearranged immunoglobulin (Ig) and T-cell receptor (TCR) genes and the chromosome aberrations t(11;14) and t(14;18). This has resulted in 107 different primers in only 18 multiplex PCR tubes: three VH-JH, two DH-JH, two Ig kappa (IGK), one Ig lambda (IGL), three TCR beta (TCRB), two TCR gamma (TCRG), one TCR delta (TCRD), three BCL1-Ig heavy chain (IGH), and one BCL2-IGH. The PCR products of Ig/TCR genes can be analyzed for clonality assessment by heteroduplex analysis or GeneScanning. The detection rate of clonal rearrangements using the BIOMED-2 primer sets is unprecedentedly high. This is mainly based on the complementarity of the various BIOMED-2 tubes. In particular, combined application of IGH (VH-JH and DH-JH) and IGK tubes can detect virtually all clonal B-cell proliferations, even in B-cell malignancies with high levels of somatic mutations. The contribution of IGL gene rearrangements seems limited. Combined usage of the TCRB and TCRG tubes detects virtually all clonal T-cell populations, whereas the TCRD tube has added value in case of TCRgammadelta(+) T-cell proliferations. The BIOMED-2 multiplex tubes can now be used for diagnostic clonality studies as well as for the identification of PCR targets suitable for the detection of minimal residual disease.

Exploring visual features through Gabor representations for facial expression detection

Gabor representations have been widely used in facial analysis (face recognition, face detection and facial expression detection) due to their biological relevance and computational properties. Two popular Gabor representations used in literature are: 1) Log-Gabor and 2) Gabor energy filters. Even though these representations are somewhat similar, they also have distinct differences as the Log-Gabor filters mimic the simple cells in the visual cortex while the Gabor energy filters emulate the complex cells, which causes subtle differences in the responses. In this paper, we analyze the difference between these two Gabor representations and quantify these differences on the task of facial action unit (AU) detection. In our experiments conducted on the Cohn-Kanade dataset, we report an average area underneath the ROC curve (A`) of 92.60% across 17 AUs for the Gabor energy filters, while the Log-Gabor representation achieved an average A` of 96.11%. This result suggests that small spatial differences that the Log-Gabor filters pick up on are more useful for AU detection than the differences in contours and edges that the Gabor energy filters extract.

Cluster-based Intrusion Detection (CBID) architecture for mobile ad hoc networks

The ad hoc networks are vulnerable to attacks due to distributed nature and lack of infrastructure. Intrusion detection systems (IDS) provide audit and monitoring capabilities that offer the local security to a node and help to perceive the specific trust level of other nodes. The clustering protocols can be taken as an additional advantage in these processing constrained networks to collaboratively detect intrusions with less power usage and minimal overhead. Existing clustering protocols are not suitable for intrusion detection purposes, because they are linked with the routes. The route establishment and route renewal affects the clusters and as a consequence, the processing and traffic overhead increases due to instability of clusters. The ad hoc networks are battery and power constraint, and therefore a trusted monitoring node should be available to detect and respond against intrusions in time. This can be achieved only if the clusters are stable for a long period of time. If the clusters are regularly changed due to routes, the intrusion detection will not prove to be effective. Therefore, a generalized clustering algorithm has been proposed that can run on top of any routing protocol and can monitor the intrusions constantly irrespective of the routes. The proposed simplified clustering scheme has been used to detect intrusions, resulting in high detection rates and low processing and memory overhead irrespective of the routes, connections, traffic types and mobility of nodes in the network. Clustering is also useful to detect intrusions collaboratively since an individual node can neither detect the malicious node alone nor it can take action against that node on its own.

Automatically detecting pain in video through facial action units

In a clinical setting, pain is reported either through patient self-report or via an observer. Such measures are problematic as they are: 1) subjective, and 2) give no specific timing information. Coding pain as a series of facial action units (AUs) can avoid these issues as it can be used to gain an objective measure of pain on a frame-by-frame basis. Using video data from patients with shoulder injuries, in this paper, we describe an active appearance model (AAM)-based system that can automatically detect the frames in video in which a patient is in pain. This pain data set highlights the many challenges associated with spontaneous emotion detection, particularly that of expression and head movement due to the patient's reaction to pain. In this paper, we show that the AAM can deal with these movements and can achieve significant improvements in both the AU and pain detection performance compared to the current-state-of-the-art approaches which utilize similarity-normalized appearance features only.

Damage detection in cable structures using vibration characteristics

Cable structures find many applications such as in power transmission, in anchors and especially in bridges. They serve as major load bearing elements in suspension bridges, which are capable of spanning long distances. All bridges, including suspension bridges, are designed to have long service lives. However, during this long life, they become vulnerable to damage due to changes in loadings, deterioration with age and random action such as impacts. The main cables are more vulnerable to corrosion and fatigue, compared to the other bridge components, and consequently reduces the serviceability and ultimate capacity of the bridge. Detecting and locating such damage at the earliest stage is challenging in the current structural health monitoring (SHM) systems of long span suspension bridges. Damage or deterioration of a structure alters its stiffness, mass and damping properties which in turn modify its vibration characteristics. This phenomenon can therefore be used to detect damage in a structure. The modal flexibility, which depends on the vibration characteristics of a structure, has been identified as a successful damage indicator in beam and plate elements, trusses and simple structures in reinforced concrete and steel. Successful application of the modal flexibility phenomenon to detect and locate the damage in suspension bridge main cables has received limited attention in recent research work. This paper, therefore examines the potential of the modal flexibility based Damage Index (DI) for detecting and locating damage in the main cable of a suspension bridge under four different damage scenarios. Towards this end, a numerical model of a suspension bridge cable was developed to extract the modal parameters at both damaged and undamaged states. Damage scenarios considered in this study with varied location and severity were simulated by changing stiffness at particular locations of the cable model. Results confirm that the DI has the potential to successfully detect and locate damage in suspension bridge main cables. This simple method can therefore enable bridge engineers and managers to detect and locate damage in suspension bridges at an early stage, minimize expensive retrofitting and prevent bridge collapse.