Modelling human behaviour and event detection from videos

Automatic analysis of human behaviour in large collections of videos is gaining interest, even more so with the advent of file sharing sites such as YouTube. However, challenges still exist owing to several factors such as inter- and intra-class variations, cluttered backgrounds, occlusion, camera motion, scale, view and illumination changes. This research focuses on modelling human behaviour for action recognition in videos. The developed techniques are validated on large scale benchmark datasets and applied on real-world scenarios such as soccer videos. Three major contributions are made. The first contribution is in the area of proper choice of a feature representation for videos. This involved a study of state-of-the-art techniques for action recognition, feature extraction processing and dimensional reduction techniques so as to yield the best performance with optimal computational requirements. Secondly, temporal modelling of human behaviour is performed. This involved frequency analysis and temporal integration of local information in the video frames to yield a temporal feature vector. Current practices mostly average the frame information over an entire video and neglect the temporal order. Lastly, the proposed framework is applied and further adapted to real-world scenario such as soccer videos. A dataset consisting of video sequences depicting events of players falling is created from actual match data to this end and used to experimentally evaluate the proposed framework.

Molecular and serological detection of occult hepatitis B virus among healthy hepatitis B surface antigen-negative blood donors in Malaysia.

Background: Occult hepatitis B infections are becoming a major global threat, but the available data on its prevalence in various parts of the world are often divergent. Objective: This study aimed to detect occult hepatitis B virus in hepatitis B surface antigen-negative serum using anti-HBc as a marker of previous infection. Patient and Methods: A total of 1000 randomly selected hepatitis B surface antigen-negative sera from blood donors were tested for hepatitis B core antibody and hepatitis B surface antibody using an ELISA and nested polymerase chain reaction was done using primers specific to the surface gene (S-gene). Results: Of the 1000 samples 55 (5.5%) were found to be reactive, of which 87.3% (48/55) were positive for hepatitis B surface antibody, indicating immunity as a result of previous infection however, that does not exclude active infection with escaped mutant HBV. Nested PCR results showed the presence of hepatitis B viral DNA in all the 55 samples that were positive for core protein, which is in agreement with the hepatitis B surface antibody result. Conclusion: This study reveals the 5.5% prevalence of occult hepatitis B among Malaysian blood donors as well as the reliability of using hepatitis B core antibody in screening for occult hepatitis B infection in low endemic, low socioeconomic settings.

The Prevalence of Depression among patients and its detection by Primary Health Care Workers at Matawale Health Centre (Zomba)

Background Little information is available on the prevalence of depression in Malawi in primary health care settings and yet there is increased number of cases of depression presenting at tertiary level in severe form. Aim The aim of the study was to determine the prevalence of depression among patients and its detection by health care workers at a primary health care clinic in Zomba. Methods A cross-sectional survey was done among patients attending outpatient department at Matawale Health Centre, in Zomba from 1st July 2009 through to 31st July 2009. A total of 350 adults were randomly selected using systematic sampling. The “Self Reporting Questionnaire”, a questionnaire measuring social demographic factors and the Structured Clinical Interview for DSM-IV Axis I disorders Non-Patient Version (SCID-NP) were administered verbally to the participants. Findings The prevalence of depression among the patients attending the outpatients department was found to be 30.3% while detection rate of depression by clinician was 0%. Conclusion The results revealed the magnitude of depression which is prevalent in the primary health care clinic that goes undiagnosed and unmanaged. It is therefore recommended that primary health care providers do thorough assessments to address common mental disorders especially depression and they should be educated to recognise and manage depression appropriately at primary care level.

Behavioral and molecular genetics of reading-related AM and FM detection thresholds

Auditory detection thresholds for certain frequencies of both amplitude modulated (AM) and frequency modulated (FM) dynamic auditory stimuli are associated with reading in typically developing and dyslexic readers. We present the first behavioral and molecular genetic characterization of these two auditory traits. Two extant extended family datasets were given reading tasks and psychoacoustic tasks to determine FM 2 Hz and AM 20 Hz sensitivity thresholds. Univariate heritabilities were significant for both AM (h2 = 0.20) and FM (h2 = 0.29). Bayesian posterior probability of linkage (PPL) analysis found loci for AM (12q, PPL = 81 %) and FM (10p, PPL = 32 %; 20q, PPL = 65 %). Bivariate heritability analyses revealed that FM is genetically correlated with reading, while AM was not. Bivariate PPL analysis indicates that FM loci (10p, 20q) are not also associated with reading.

Radio frequency communication and fault detection for railway signalling

The continuous and swift progression of both wireless and wired communication technologies in today's world owes its success to the foundational systems established earlier. These systems serve as the building blocks that enable the enhancement of services to cater to evolving requirements. Studying the vulnerabilities of previously designed systems and their current usage leads to the development of new communication technologies replacing the old ones such as GSM-R in the railway field. The current industrial research has a specific focus on finding an appropriate telecommunication solution for railway communications that will replace the GSM-R standard which will be switched off in the next years. Various standardization organizations are currently exploring and designing a radiofrequency technology based standard solution to serve railway communications in the form of FRMCS (Future Railway Mobile Communication System) to substitute the current GSM-R. Bearing on this topic, the primary strategic objective of the research is to assess the feasibility to leverage on the current public network technologies such as LTE to cater to mission and safety critical communication for low density lines. The research aims to identify the constraints, define a service level agreement with telecom operators, and establish the necessary implementations to make the system as reliable as possible over an open and public network, while considering safety and cybersecurity aspects. The LTE infrastructure would be utilized to transmit the vital data for the communication of a railway system and to gather and transmit all the field measurements to the control room for maintenance purposes. Given the significance of maintenance activities in the railway sector, the ongoing research includes the implementation of a machine learning algorithm to detect railway equipment faults, reducing time and human analysis errors due to the large volume of measurements from the field.

Query Library Development and Anomaly Detection on Flight Data

During the last semester of the Master’s Degree in Artificial Intelligence, I carried out my internship working for TXT e-Solution on the ADMITTED project. This paper describes the work done in those months. The thesis will be divided into two parts representing the two different tasks I was assigned during the course of my experience. The First part will be about the introduction of the project and the work done on the admittedly library, maintaining the code base and writing the test suits. The work carried out is more connected to the Software engineer role, developing features, fixing bugs and testing. The second part will describe the experiments done on the Anomaly detection task using a Deep Learning technique called Autoencoder, this task is on the other hand more connected to the data science role. The two tasks were not done simultaneously but were dealt with one after the other, which is why I preferred to divide them into two separate parts of this paper.

Rapid and sensitive measurements of nitrate ester explosives using microchip electrophoresis with electrochemical detection

This article describes an effective microchip protocol based on electrophoretic-separation and electrochemical detection for highly sensitive and rapid measurements of nitrate ester explosives, including ethylene glycol dinitrate (EGDN), pentaerythritol tetranitrate (PETN), propylene glycol dinitrate (PGDN) and glyceryl trinitrate (nitroglycerin, NG). Factors influencing the separation and detection processes were examined and optimized. Under the optimal separation conditions obtained using a 15 mM borate buffer (pH 9.2) containing 20 mM SDS, and applying a separation voltage of 1500 V, the four nitrate ester explosives were separated within less than 3 min. The glassy-carbon amperometric detector (operated at -0.9 V vs. Ag/AgCl) offers convenient cathodic detection down to the picogram level, with detection limits of 0.5 ppm and 0.3 ppm for PGDN and for NG, respectively, along with good repeatability (RSD of 1.8-2.3%; n = 6) and linearity (over the 10-60 ppm range). Such effective microchip operation offers great promise for field screening of nitrate ester explosives and for supporting various counter-terrorism surveillance activities.

HYBRID AND INCREMENTAL FUZZY LEARNING FOR HUMAN SKIN DETECTION

In this paper, a framework for detection of human skin in digital images is proposed. This framework is composed of a training phase and a detection phase. A skin class model is learned during the training phase by processing several training images in a hybrid and incremental fuzzy learning scheme. This scheme combines unsupervised-and supervised-learning: unsupervised, by fuzzy clustering, to obtain clusters of color groups from training images; and supervised to select groups that represent skin color. At the end of the training phase, aggregation operators are used to provide combinations of selected groups into a skin model. In the detection phase, the learned skin model is used to detect human skin in an efficient way. Experimental results show robust and accurate human skin detection performed by the proposed framework.

Quality control of Toxoplasma gondii in meat packages: Standardization of an ELISA test and its use for detection in rabbit meat cuts

Toxoplasma gondii causes severe disease both to man and livestock and its detection in meat after slaughtering requires PCR or biological tests. Meat packages contain retained exudate that could be used for serology due to its blood content. Similar studies reported false negative assays in those tests. We standardized an anti-T. gondii IgG ELISA in muscle juices from experimentally infected rabbits, with blood content determination by cyanhemoglobin spectrophotometry. IgG titers and immunoblotting profiles were similar in blood, serum or meat juice, after blood content correction. These assays were adequate regardless of the storage time up to 120 days or freeze-thaw cycles, without false negative results. We also found 1.35% (1/74) positive sample in commercial Brazilian rabbit meat cuts, by this assay. The blood content determination shows ELISA of meat juice may be useful for quality control for toxoplasmosis monitoring. (C) 2011 Elsevier Ltd. All rights reserved.

Multiplex semi-nested RT-PCR with exogenous internal control for simultaneous detection of bovine coronavirus and group A rotavirus

Neonatal calf diarrhea is a multi-etiology syndrome of cattle and direct detection of the two major agents of the syndrome, group A rotavirus and Bovine coronavirus (BCoV) is hampered by their fastidious growth in cell culture. This study aimed at developing a multiplex semi-nested RT-PCR for simultaneous detection of BCoV (N gene) and group A rotavirus (VP1 gene) with the addition of an internal control (mRNA ND5). The assay was tested in 75 bovine feces samples tested previously for rotavirus using PAGE and for BCoV using nested RT-PCR targeted to RdRp gene. Agreement with reference tests was optimal for BCoV (kappa = 0.833) and substantial for rotavirus detection (kappa = 0.648). the internal control, ND5 mRNA, was detected successfully in all reactions. Results demonstrated that this multiplex semi-nested RT-PCR was effective in the detection of BCoV and rotavirus, with high sensitivity and specificity for simultaneous detection of both viruses at a lower cost, providing an important tool for studies on the etiology of diarrhea in cattle. (C) 2010 Elsevier B.V. All rights reserved.

Detection of West Nile Virus Infection in birds in the United States by blocking ELISA and immunohistochemistry

A blocking ELISA targeting an immunodominant West Nile epitope on the West Nile Virus NS1 protein was assessed for the detection of West Nile-specific antibodies in blood samples collected from 584 sentinel chickens and 238 wild birds collected in-New Jersey from May-December 2000. Ten mallard ducks (Anas platyrhynchos) experimentally infected with West Nile virus and six uninfected controls were also tested. The ELISA proved specific in detecting WNV antibodies in 9/10 chickens and 4/4 wild birds previously confirmed as positive by Plaque Reduction Neutralization test (PRNT) at the Center for Disease Control, Division of Vector Borne Diseases, Fort Collins, CO, USA (CDC). Nine out of the ten experimentally infected mallard ducks also tested positive for WN antibodies in the blocking ELISA, while 6/6 uninfected controls did not. Additionally, 1705 wild birds, collected in New Jersey from December 2000-November 2001 and Long Island, New York between November 1999 and August 2001 were also tested for WN antibodies by the blocking ELISA. These tests identified 30 positive specimens, 12 of which had formalin-fixed tissues available to allow detection of WN specific viral antigen in various tissues by WNV-specific immunohistochemistry. Our results indicate that rapid and specific detection of antibodies to WN virus in sera from a range of avian species by blocking ELISA is an effective strategy for WN Virus surveillance in avian hosts. In combination with detection of WN-specific antigens in tissues by immunohistochemistry (IHC) the blocking ELISA will also be useful for confirming WN infection in diseased birds.

Central nervous system virion detection in acute measles: histopathological, ultrastructural and pathogenetic aspects

Histopathological and ultrastructural studies of 23 patients who died with clinical diagnosis of measles were carried out. In 12 cases viral nucleocapsids were searched by electron microscopy and detected in 100% of the cases in the lungs and in 50% of the cases in the central nervous system. They were mostly intranuclear. Histopathological changes associated to neurological alterations and the detection of virion are discussed in relation to acute and delayed clinical manifestations.