Detection and characterization of fibropapilloma associated herpesvirus of marine turtles in Rio Grande do Sul, Brazil

Fibropapillomatosis (FP) is a benign tumoral disease that affects sea turtles, hampering movement, sight and feeding, ultimately leading to death. In Brazil, the disease was described for the first time in 1986. Research suggests the involvement of a herpesvirus in association with environmental and genetic factors as causal agents of FP. The objective of the present study was to detect and characterize this herpesvirus in sea turtles living in the coast of state Rio Grande do Sul (RS), Brazil. From October 2008 to July 2010, 14 turtles were observed between the beaches of Torres and Tavares, of which 11 were green turtles (Chelonia mydas) and 3 were loggerhead turtles (Caretta caretta). All turtles were young and mean curved carapace length was 37.71±7.82cm, and varied from 31 to 55cm. Only one green turtle presented a 1cm, papillary, pigmented fibropapilloma. Skin and fibropapilloma samples were analyzed by conventional and real time PCR assays to detect and quantify herpesvirus. All skin samples were negative, though the fibropapilloma specimen was positive in both tests. Viral load was 9,917.04 copies of viral genome per milligram of tissue. The DNA fragment amplified from the fibropapilloma sample was sequenced and allocated in the Atlantic phylogeographic group. This study reports the first molecular characterization of herpesvirus associated with fibropapilloma in turtles from the coast of RS.

Brazilian avian metapneumovirus subtypes A and B: experimental infection of broilers and evaluation of vaccine efficacy

Avian metapneumovirus (aMPV) is a respiratory pathogen associated with the swollen head syndrome (SHS) in chickens. In Brazil, live aMPV vaccines are currently used, but subtypes A and, mainly subtype B (aMPV/A and aMPV/B) are still circulating. This study was conducted to characterize two Brazilian aMPV isolates (A and B subtypes) of chicken origin. A challenge trial to explore the replication ability of the Brazilian subtypes A and B in chickens was performed. Subsequently, virological protection provided from an aMPV/B vaccine against the same isolates was analyzed. Upon challenge experiment, it was shown by virus isolation and real time PCR that aMPV/B could be detected longer and in higher amounts than aMPV/A. For the protection study, 18 one-day-old chicks were vaccinated and challenged at 21 days of age. Using virus isolation and real time PCR, no aMPV/A was detected in the vaccinated chickens, whereas one vaccinated chicken challenged with the aMPV/B isolate was positive. The results showed that aMPV/B vaccine provided a complete heterologous virological protection, although homologous protection was not complete in one chicken. Although only one aMPV/B positive chicken was detected after homologous vaccination, replication in vaccinated animals might allow the emergence of escape mutants.

Real-time Image-based RGB-D Camera Motion Tracking and Environment Mapping

In this work, image based estimation methods, also known as direct methods, are studied which avoid feature extraction and matching completely. Cost functions use raw pixels as measurements and the goal is to produce precise 3D pose and structure estimates. The cost functions presented minimize the sensor error, because measurements are not transformed or modified. In photometric camera pose estimation, 3D rotation and translation parameters are estimated by minimizing a sequence of image based cost functions, which are non-linear due to perspective projection and lens distortion. In image based structure refinement, on the other hand, 3D structure is refined using a number of additional views and an image based cost metric. Image based estimation methods are particularly useful in conditions where the Lambertian assumption holds, and the 3D points have constant color despite viewing angle. The goal is to improve image based estimation methods, and to produce computationally efficient methods which can be accomodated into real-time applications. The developed image-based 3D pose and structure estimation methods are finally demonstrated in practise in indoor 3D reconstruction use, and in a live augmented reality application.

Comparison between dSPACE and NI systems based on real-time intelligent control of a teleoperated hydraulic servo system

The Laboratory of Intelligent Machine researches and develops energy-efficient power transmissions and automation for mobile construction machines and industrial processes. The laboratory's particular areas of expertise include mechatronic machine design using virtual technologies and simulators and demanding industrial robotics. The laboratory has collaborated extensively with industrial actors and it has participated in significant international research projects, particularly in the field of robotics. For years, dSPACE tools were the lonely hardware which was used in the lab to develop different control algorithms in real-time. dSPACE's hardware systems are in widespread use in the automotive industry and are also employed in drives, aerospace, and industrial automation. But new competitors are developing new sophisticated systems and their features convinced the laboratory to test new products. One of these competitors is National Instrument (NI). In order to get to know the specifications and capabilities of NI tools, an agreement was made to test a NI evolutionary system. This system is used to control a 1-D hydraulic slider. The objective of this research project is to develop a control scheme for the teleoperation of a hydraulically driven manipulator, and to implement a control algorithm between human and machine interaction, and machine and task environment interaction both on NI and dSPACE systems simultaneously and to compare the results.

Evaluation of stunned and infarcted canine myocardium by real time myocardial contrast echocardiography

Differentiation between stunned and infarcted myocardium in the setting of acute ischemia is challenging. Real time myocardial contrast echocardiography allows the simultaneous assessment of myocardial perfusion and function. In the present study we evaluated infarcted and stunned myocardium in an experimental model using real time myocardial contrast echocardiography. Sixteen dogs underwent 180 min of coronary occlusion followed by reperfusion (infarct model) and seven other dogs were submitted to 20 min of coronary occlusion followed by reperfusion (stunned model). Wall motion abnormality and perfusional myocardial defect areas were measured by planimetry. Risk and infarct areas were determined by tissue staining. In the infarct model, the wall motion abnormality area during coronary occlusion (5.52 ± 1.14 cm²) was larger than the perfusional myocardial defect area (3.71 ± 1.45 cm²; P < 0.001). Reperfusion resulted in maintenance of wall motion abnormality (5.45 ± 1.41 cm²; P = 0.43 versus occlusion) and reduction of perfusional myocardial defect (1.51 ± 1.29 cm²; P = 0.004 versus occlusion). Infarct size determined by contrast echocardiography correlated with tissue staining (r = 0.71; P = 0.002). In the stunned model, the wall motion abnormality area was 5.49 ± 0.68 cm² during occlusion and remained 5.1 ± 0.63 cm² after reperfusion (P = 0.07). Perfusional defect area was 2.43 ± 0.79 cm² during occlusion and was reduced to 0.2 ± 0.53 cm² after reperfusion (P = 0.04). 2,3,5-Triphenyl tetrazolium chloride staining confirmed the absence of necrotic myocardium in all dogs in the stunned model. Real time myocardial contrast echocardiography is a noninvasive technique capable of distinguishing between stunned and infarcted myocardium after acute ischemia.

Relationship of macrophage migration inhibitory factor levels in PBMCs, lesional skin and serum with disease severity and activity in vitiligo vulgaris

Melanocyte loss in vitiligo vulgaris is believed to be an autoimmune process. Macrophage migration inhibitory factor (MIF) is involved in many autoimmune skin diseases. We determined the possible role of MIF in the pathogenesis of vitiligo vulgaris, and describe the relationship between MIF expressions and disease severity and activity. Serum MIF concentrations and mRNA levels in PBMCs were measured in 44 vitiligo vulgaris patients and 32 normal controls, using ELISA and real-time RT-PCR. Skin biopsies from 15 patients and 6 controls were analyzed by real-time RT-PCR. Values are reported as median (25th-75th percentile). Serum MIF concentrations were significantly increased in patients [35.81 (10.98-43.66) ng/mL] compared to controls [7.69 (6.01-9.03) ng/mL]. MIF mRNA levels were significantly higher in PBMCs from patients [7.17 (3.59-8.87)] than controls [1.67 (1.23-2.42)]. There was also a significant difference in MIF mRNA levels in PBMCs between progressive and stable patients [7.86 (5.85-9.13)vs 4.33 (2.23-8.39)] and in serum MIF concentrations [40.47 (27.71-46.79) vs 26.80 (10.55-36.07) ng/mL]. In addition, the vitiligo area severity index scores of patients correlated positively with changes of both serum MIF concentrations (r = 0.488) and MIF mRNA levels in PBMCs (r = 0.426). MIF mRNA levels were significantly higher in lesional than in normal skin [2.43 (2.13-7.59)vs 1.18 (0.94-1.83)] and in patients in the progressive stage than in the stable stage [7.52 (2.43-8.84)vs 2.13 (1.98-2.64)]. These correlations suggest that MIF participates in the pathogenesis of vitiligo vulgaris and may be useful as an index of disease severity and activity.

Inhibitory effect of liposomal quercetin on acute hepatitis and hepatic fibrosis induced by concanavalin A

Immune response plays an important role in the development of hepatic fibrosis. In the present study, we investigated the effects of quercetin on hepatitis and hepatic fibrosis induced by immunological mechanism. In the acute hepatitis model, quercetin (2.5 mg/kg) was injected iv into mice 30 min after concanavalin A (Con A) challenge. Mice were sacrificed 4 or 24 h after Con A injection, and aminotransferase tests and histopathological sections were performed. Treatment with quercetin significantly decreased the levels of alanine aminotransferase (ALT) and aspartate aminotransferase (AST). Consistent with this observation, treatment with quercetin markedly attenuated the pathologic changes in the liver. A hepatic fibrosis model was also generated in mice by Con A challenge once a week for 6 consecutive weeks. Mice in the experimental group were treated with daily iv injections of quercetin (0.5 mg/kg). Histopathological analyses revealed that treatment with quercetin markedly decreased collagen deposition, pseudolobuli development, and hepatic stellate cells activation. We also examined the effects of quercetin on the nuclear factor kappa-light-chain-enhancer of activated B cells (NF-κB) and transforming growth factor beta (TGF-β) pathways by immunohistochemistry and real-time reverse transcriptase-polymerase chain reaction (RT-PCR). NF-κB and TGF-β production was decreased after treatment with quercetin, indicating that the antifibrotic effect of quercetin is associated with its ability to modulate NF-κB and TGF-β production. These results suggest that quercetin may be an effective therapeutic strategy in the treatment of patients with liver damage and fibrosis.

Advanced glycation end products (AGEs) and their receptor (RAGE) induce apoptosis of periodontal ligament fibroblasts

Diabetics have an increased prevalence of periodontitis, and diabetes is one of the causative factors of severe periodontitis. Apoptosis is thought to be involved in this pathogenic relationship. The aim of this study was to investigate apoptosis in human periodontal ligament (PDL) fibroblasts induced by advanced glycation end products (AGEs) and their receptor (RAGE). We examined the roles of apoptosis, AGEs, and RAGE during periodontitis in diabetes mellitus using cultured PDL fibroblasts that were treated by AGE-modified bovine serum albumin (AGE-BSA), bovine serum albumin (BSA) alone, or given no treatment (control). Microscopy and real-time quantitative PCR indicated that PDL fibroblasts treated with AGE-BSA were deformed and expressed higher levels of RAGE and caspase 3. Cell viability assays and flow cytometry indicated that AGE-BSA reduced cell viability (69.80±5.50%, P<0.01) and increased apoptosis (11.31±1.73%, P<0.05). Hoechst 33258 staining and terminal-deoxynucleotidyl transferase-mediated nick-end labeling revealed that AGE-BSA significantly increased apoptosis of PDL fibroblasts. The results showed that the changes in PDL fibroblasts induced by AGE-BSA may explain how AGE-RAGE participates in and exacerbates periodontium destruction.

Real-Time Automatic Object Classification and Tracking using Genetic Programming and NVIDIA R CUDA TM

Genetic Programming (GP) is a widely used methodology for solving various computational problems. GP's problem solving ability is usually hindered by its long execution times. In this thesis, GP is applied toward real-time computer vision. In particular, object classification and tracking using a parallel GP system is discussed. First, a study of suitable GP languages for object classification is presented. Two main GP approaches for visual pattern classification, namely the block-classifiers and the pixel-classifiers, were studied. Results showed that the pixel-classifiers generally performed better. Using these results, a suitable language was selected for the real-time implementation. Synthetic video data was used in the experiments. The goal of the experiments was to evolve a unique classifier for each texture pattern that existed in the video. The experiments revealed that the system was capable of correctly tracking the textures in the video. The performance of the system was on-par with real-time requirements.

Development and use of a multiplex real-time quantitative polymerase chain reaction assay for detection and differentiation of Porcine circovirus-2 genotypes 2a and 2b in an epidemiological survey.

By the end of 2004, the Canadian swine population had experienced a severe 2 increase in the incidence of Porcine circovirus-associated disease (PCVAD), a problem that was 3 associated with the emergence of a new Porcine circovirus-2 genotype (PCV-2b), previously 4 unrecovered in North America. Thus it became important to develop a diagnostic tool that could 5 differentiate between the old and new circulating genotypes (PCV-2a and -2b, respectively). 6 Consequently, a multiplex real-time quantitative polymerase chain reaction (mrtqPCR) assay that 7 could sensitively and specifically identify and differentiate PCV-2 genotypes was developed. A 8 retrospective epidemiological survey that used the mrtqPCR assay was performed to determine if 9 cofactors could affect the risk of PCVAD. From 121 PCV-2–positive cases gathered for this 10 study, 4.13%, 92.56% and 3.31% were positive for PCV-2a, PCV-2b, and both genotypes, 11 respectively. In a data analysis using univariate logistic regressions, PCVAD compatible 12 (PCVAD/c) score was significantly associated with the presence of Porcine reproductive and 13 respiratory syndrome virus (PRRSV), PRRSV viral load, PCV-2 viral load, and PCV-2 14 immunohistochemistry (IHC) results. Polytomous logistic regression analysis revealed that 15 PCVAD/c score was affected by PCV-2 viral load (P = 0.0161) and IHC (P = 0.0128), but not by 16 the PRRSV variables (P > 0.9); suggesting that mrtqPCR in tissue is a reliable alternative to IHC. 17 Logistic regression analyses revealed that PCV-2 increased the odds ratio of isolating 2 major 18 swine pathogens of the respiratory tract, Actinobacillus pleuropneumoniae and Streptococcus 19 suis serotypes 1/2, 1, 2, 3, 4, and 7, which are serotypes commonly associated with clinical 20 diseases.

GABAA and GABAB Receptor Gene Expression and Functional Regulation During Pancreatic Regeneration and Insulin Secretion in Rats

The present study demonstrate the functional alterations of the GABAA and GABAB receptors and the gene expression during the regeneration of pancreas following partial pancreatectomy. The role of these receptors in insulin secretion and pancreatic DNA synthesis using the specific agonists and antagonists also are studied in vitro. The alterations of GABAA and GABAR receptor function and gene expression in the brain stem, crebellum and hypothalamus play an important role in the sympathetic regulation of insulin secretion during pancreatic regeneration. Previous studies have given much information linking functional interaction between GABA and the peripheral nervous system. The involvement of specific receptor subtypes functional regulation during pancreatic regeneration has not given emphasis and research in this area seems to be scarce. We have observed a decreased GABA content, down regulation of GABAA receptors and an up regulation of GABAB receptors in the cerebral cortex, brain stem and hypothalamus. Real Time-PCR analysis confirmed the receptor data in the brain regions. These alterations in the GABAA and GABAB receptors of the brain are suggested to govern the regenerative response and growth regulation of the pancreas through sympathetic innervation. In addition, receptor binding studies and Real Time-PCR analysis revealed that during pancreatic regeneration GABAA receptors were down regulated and GABAB receptors were up regulated in pancreatic islets. This suggests an inhibitory role for GABAA receptors in islet cell proliferation i.e., the down regulation of this receptor facilitates proliferation. Insulin secretion study during 1 hour showed GABA has inhibited the insulin secretion in a dose dependent manner in normal and hyperglycaemic conditions. Bicuculline did not antagonize this effect. GABAA agonist, muscimol inhibited glucose stimulated insulin secretion from pancreatic islets except in the lowest concentration of 1O-9M in presence of 4mM glucose.Musclmol enhanced insulin secretion at 10-7 and 10-4M muscimol in presence of 20mM glucose- 4mM glucose represents normal and 20mM represent hyperglycaemic conditions. GABAB agonist, baclofen also inhibited glucose induced insulin secretion and enhanced at the concentration of 1O-5M at 4mM glucose and at 10-9M baclofen in presence of 20mM glucose. This shows a differential control of the GABAA and GABAB receptors over insulin release from the pancreatic islets. During 24 hours in vitro insulin secretion study it showed that low concentration of GABA has inhibited glucose stimulated insulin secretion from pancreatic islets. Muscimol, the GABAA agonist, inhibited the insulin secretion but, gave an enhanced secretion of insulin in presence of 4mM glucose at 10-7 , 10-5 and 1O-4M muscimol. But in presence of 20mM glucose muscimol significantly inhibited the insulin secretion. GABAB agonist, baclofen also inhibited glucose induced insulin secretion in presence of both 4mM and 20mM glucose. This shows the inhibitory role of GABA and its specific receptor subtypes over insulin synthesis from pancreatic bete-islets. In vitro DNA synthesis studies showed that activation of GABAA receptor by adding muscimol, a specific agonist, inhibited islet DNA synthesis. Also, the addition of baclofen, a specific agonist of GABAB receptor resulted in the stimulation of DNA synthesis.Thus the brain and pancreatic GABAA and GABAB receptor gene expression differentially regulates pancreatic insulin secretion and islet cell proliferation during pancreatic regeneration. This will have immense clinical significance in therapeutic applications in the management of Diabetes mellitus.

Real Time Raga Detection and Analysis Using Computer

Department of Computer Applications, Cochin University of Science and Technology

Biochemical and molecular characterization of pathogenic vibrios from hatcheries and aquaculture farms

Vibrio are important during hatchery rearing. aquaculture phase and post-harvest quality of shrimps. Vibrio spp are of concern to shrimp farmers and hatchery operators because certain species can cause Vibriosis. Vibrio species are of concern to humans because certain species cause serious diseases.With the progress in aquaculture, intensive systems used for shrimp aquaculture create an artificial environment that increases bacterial growth. To maintain the productivity of such an intensive aquaculture, high inputs of fish protein have to be employed for feeding together with high levels of water exchange and the massive use of antibiotics/ probiotics / chemicals. It seems that the combination of these conditions favours the proliferation of vibrios and enhances their virulence and disease prevalence. The risk of a microbial infection is high, mainly at larval stages. The effect and severity are related to Vibrio species and dose, water, feed, shrimp quality and aquaculture management.Consumption of seafood can occasionally result in food-bome illnesses due to the proliferation of indigenous pathogens like Vibrio.Of the l2 pathogenic Vibrio species, 8 species are known to be directly food associated. Strict quality guidelines have been laid by the importing nations, for the food products that enter their markets. The microbiological quality requirement for export of frozen shrimp products is that V.cholerae, V.parahaemolyticus and V. vulnificus should be absent in 25g of the processed shrimp (Export Inspection Council of India, 1995). The mere presence of these pathogenic Vibrios is sufficient for the rejection of the exported product.The export rejections cause serious economic loss to the shrimp industry and might harm the brand image of the shrimp products from the countiy.There is a need for an independent study on the incidence of different pathogenic vibrios in shrimp aquaculture and investigate their biochemical characteristics to have a better understanding about the growth and survival of these organisms in the shrimp aquaculture niche. PCR based methods (conventional PCR, duplex PCR, multiplex-PCR and Real Time PCR) for the detection of the pathogenic Vibrios is important for rapid post-harvest quality assessment. Studies on the genetic heterogeneity among the specific pathogenic vibrio species isolated from shrimp aquaculture system provide; valuable information on the extent of genetic diversity of the pathogenic vibrios, the shrimp aquaculture system.So the present study was undertaken to study the incidence of pathogenic Vibrio spp. in Penaeus monodon shrimp hatcheries and aquaculture farms, to carry out biochemical investigations of the pathogenic Vibrio spp isolated from P. monodon hatchery and. aquaculture environments, to assess the effect of salt (NaCl) on the growth and enzymatic activities of pathogenic Vibrio spp., to study the effect of preservatives, and chemicals on the growth of pathogenic Vibrio spp. and to employ polymerase chain reaction (PCR) methods for the detection of pathogenic V ibrio spp.Samples of water (n=7) and post-larvae (n=7) were obtained from seven Penaeus monodon hatcheries and samples of water (n=5), sediment (n=5) and shrimp (n=5) were obtained from five P. monodon aquaculture farms located on the East Coast of lndia. The microbiological examination of water, sediment, post-larvae and shrimp samples was carried out employing standard methods and by using standard media.The higher bacterial loads were obtained in pond sediments which can be attributed to the accumulation of organic matter at the pond bottom which stimulated bacterial growth.Shrimp head. (4.78 x 105 +/- 3.0 x 104 cfu/g) had relatively higher bacterial load when compared to shrimp muscle 2.7 x 105 +/- 1.95 x 104 cfu/g). ln shrimp hatchery samples, the post-larvae (2.2 x 106 +/- 1.9 x 106 cfu/g) had higher bacterial load than water (5.6 x 103 +/- 3890 cfu/ml).The mean E.coli counts were higher in aquaculture pond sediment (204+/-13 cfu/g) and pond water (124+/-88 cfu/ml). Relatively lower Escherichia coli counts were obtained from shrimp samples (12+/-11 to 16+/-16.7 cfu/g). The presence of E.coli in aquaculture environment might have been from the source water. E.coli was not detected in hatchery waters and post-larvae.

Adaptive Real-time Anomaly-based Intrusion Detection using Data Mining and Machine Learning Techniques

Die zunehmende Vernetzung der Informations- und Kommunikationssysteme führt zu einer weiteren Erhöhung der Komplexität und damit auch zu einer weiteren Zunahme von Sicherheitslücken. Klassische Schutzmechanismen wie Firewall-Systeme und Anti-Malware-Lösungen bieten schon lange keinen Schutz mehr vor Eindringversuchen in IT-Infrastrukturen. Als ein sehr wirkungsvolles Instrument zum Schutz gegenüber Cyber-Attacken haben sich hierbei die Intrusion Detection Systeme (IDS) etabliert. Solche Systeme sammeln und analysieren Informationen von Netzwerkkomponenten und Rechnern, um ungewöhnliches Verhalten und Sicherheitsverletzungen automatisiert festzustellen. Während signatur-basierte Ansätze nur bereits bekannte Angriffsmuster detektieren können, sind anomalie-basierte IDS auch in der Lage, neue bisher unbekannte Angriffe (Zero-Day-Attacks) frühzeitig zu erkennen. Das Kernproblem von Intrusion Detection Systeme besteht jedoch in der optimalen Verarbeitung der gewaltigen Netzdaten und der Entwicklung eines in Echtzeit arbeitenden adaptiven Erkennungsmodells. Um diese Herausforderungen lösen zu können, stellt diese Dissertation ein Framework bereit, das aus zwei Hauptteilen besteht. Der erste Teil, OptiFilter genannt, verwendet ein dynamisches "Queuing Concept", um die zahlreich anfallenden Netzdaten weiter zu verarbeiten, baut fortlaufend Netzverbindungen auf, und exportiert strukturierte Input-Daten für das IDS. Den zweiten Teil stellt ein adaptiver Klassifikator dar, der ein Klassifikator-Modell basierend auf "Enhanced Growing Hierarchical Self Organizing Map" (EGHSOM), ein Modell für Netzwerk Normalzustand (NNB) und ein "Update Model" umfasst. In dem OptiFilter werden Tcpdump und SNMP traps benutzt, um die Netzwerkpakete und Hostereignisse fortlaufend zu aggregieren. Diese aggregierten Netzwerkpackete und Hostereignisse werden weiter analysiert und in Verbindungsvektoren umgewandelt. Zur Verbesserung der Erkennungsrate des adaptiven Klassifikators wird das künstliche neuronale Netz GHSOM intensiv untersucht und wesentlich weiterentwickelt. In dieser Dissertation werden unterschiedliche Ansätze vorgeschlagen und diskutiert. So wird eine classification-confidence margin threshold definiert, um die unbekannten bösartigen Verbindungen aufzudecken, die Stabilität der Wachstumstopologie durch neuartige Ansätze für die Initialisierung der Gewichtvektoren und durch die Stärkung der Winner Neuronen erhöht, und ein selbst-adaptives Verfahren eingeführt, um das Modell ständig aktualisieren zu können. Darüber hinaus besteht die Hauptaufgabe des NNB-Modells in der weiteren Untersuchung der erkannten unbekannten Verbindungen von der EGHSOM und der Überprüfung, ob sie normal sind. Jedoch, ändern sich die Netzverkehrsdaten wegen des Concept drif Phänomens ständig, was in Echtzeit zur Erzeugung nicht stationärer Netzdaten führt. Dieses Phänomen wird von dem Update-Modell besser kontrolliert. Das EGHSOM-Modell kann die neuen Anomalien effektiv erkennen und das NNB-Model passt die Änderungen in Netzdaten optimal an. Bei den experimentellen Untersuchungen hat das Framework erfolgversprechende Ergebnisse gezeigt. Im ersten Experiment wurde das Framework in Offline-Betriebsmodus evaluiert. Der OptiFilter wurde mit offline-, synthetischen- und realistischen Daten ausgewertet. Der adaptive Klassifikator wurde mit dem 10-Fold Cross Validation Verfahren evaluiert, um dessen Genauigkeit abzuschätzen. Im zweiten Experiment wurde das Framework auf einer 1 bis 10 GB Netzwerkstrecke installiert und im Online-Betriebsmodus in Echtzeit ausgewertet. Der OptiFilter hat erfolgreich die gewaltige Menge von Netzdaten in die strukturierten Verbindungsvektoren umgewandelt und der adaptive Klassifikator hat sie präzise klassifiziert. Die Vergleichsstudie zwischen dem entwickelten Framework und anderen bekannten IDS-Ansätzen zeigt, dass der vorgeschlagene IDSFramework alle anderen Ansätze übertrifft. Dies lässt sich auf folgende Kernpunkte zurückführen: Bearbeitung der gesammelten Netzdaten, Erreichung der besten Performanz (wie die Gesamtgenauigkeit), Detektieren unbekannter Verbindungen und Entwicklung des in Echtzeit arbeitenden Erkennungsmodells von Eindringversuchen.

Rotation Invariant Real-time Face Detection and Recognition System

In this report, a face recognition system that is capable of detecting and recognizing frontal and rotated faces was developed. Two face recognition methods focusing on the aspect of pose invariance are presented and evaluated - the whole face approach and the component-based approach. The main challenge of this project is to develop a system that is able to identify faces under different viewing angles in realtime. The development of such a system will enhance the capability and robustness of current face recognition technology. The whole-face approach recognizes faces by classifying a single feature vector consisting of the gray values of the whole face image. The component-based approach first locates the facial components and extracts them. These components are normalized and combined into a single feature vector for classification. The Support Vector Machine (SVM) is used as the classifier for both approaches. Extensive tests with respect to the robustness against pose changes are performed on a database that includes faces rotated up to about 40 degrees in depth. The component-based approach clearly outperforms the whole-face approach on all tests. Although this approach isproven to be more reliable, it is still too slow for real-time applications. That is the reason why a real-time face recognition system using the whole-face approach is implemented to recognize people in color video sequences.