Submitted by (edna.saturno@ufrpe.br) on 2017-02-23T12:25:14Z No. of bitstreams: 1 Williams Dantas Charles.pdf: 2829415 bytes, checksum: bf5d0ed2319bb047d509bf6837ebad7e (MD5) / Made available in DSpace on 2017-02-23T12:25:14Z (GMT). No. of bitstreams: 1 Williams Dantas Charles.pdf: 2829415 bytes, checksum: bf5d0ed2319bb047d509bf6837ebad7e (MD5) Previous issue date: 2007-02-15 / Since 50`s, industrial fisheries have been damaged by cetaceans in all oceans, with different intensity levels. According to specialists, this behavior is named depredation, which occurs when the animals eat the fishes caught by a fishing gear. Killer whale has been cited as an animal that shows this kind of behavior often, otherwise other species as a false killer whale or sperm whale have been recorded doing fishing gear interactions. After the creation of the On Board Observers Program (PROBORDO) it was possible to cover all tuna fleet working in northeast of Brazil, based on Natal-RN, Cabedelo-PB and Recife-PE ports. The covering was made by board observers that get important information to the fisheries dynamic knowledge made by pelagic long line. Interactions between false killer whales and killer whales are cited as an important scientific subject, in relation to these fisheries type, that the present study pretends to show up. Factors like interactions type, groups’ size, qualitative and quantitative descriptions of depredated fishes and spatial location of the interactions were analyzed. The false killer whale showed greater occurrence on the study area than other species, generally within groups of few individuals, however, there were situations that the group was composed by hundreds of individuals. This species showed food preference about the target species of this fisheries kind, in other words, tuna and swordfishes instead of others catched, but in case of low productivity, they feed with squid used as a bait on the hooks. Killer whales were observed in the Tropical Western Atlantic, interacting with the fisheries. Also, there were accidental catches of the cited cetaceans by the fishing gear, what can bring serious damage to the individuals caughted. / Desde a década de 50, a indústria pesqueira vem sofrendo perdas provocadas por cetáceos, em todos os oceanos, com diferentes níveis de intensidade, num comportamento denominado pelos especialistas como depredação, que ocorre quando esses animais se alimentam do peixe capturado pela arte de pesca. Orcas verdadeiras têm sido citadas como as que exibem esse comportamento com maior freqüência, porém outras espécies como as falsas orcas e cachalotes, são registradas interagindo com a pesca. Com a criação do Programa de Observadores de Bordo (PROBORDO) foi possível a cobertura de toda a frota atuneira arrendada que opera no nordeste, sediada nos portos de Natal-RN, Cabedelo-PB e Recife-PE por observadores de bordo, que coletam informações relevantes para o conhecimento da dinâmica da pesca realizada com espinhel pelágico monofilamento. Dentre os assuntos de grande valor científico cita-se a ocorrência de interações entre as falsas orcas e as orcas verdadeiras, com esse tipo de pescaria, que o presente trabalho pretende apresentar. Fatores como o tipo de interação, tamanho de grupo, descrição quali-quantitativa dos peixes depredados e localização espacial das interações, foram analisados. A falsa orca apresentou maior ocorrência na área de estudo, geralmente em grupos de poucos indivíduos, porém houve situações em que o grupo era composto por centenas de espécimens. Elas demonstraram preferência alimentar pelas espécies-alvo deste tipo de pescaria, ou seja, atuns e espadartes em detrimento da fauna acompanhante, mas no caso de produtividade baixa, também se alimentavam das lulas, utilizadas nos anzóis como isca. Orcas verdadeiras também foram observadas na região do Atlântico oeste tropical, interagindo com a pesca. Também houveram capturas dos referidos cetáceos pelo espinhel, o que pode causar danos sérios aos espécimens capturados.

Made available in DSpace on 2014-07-29T15:25:24Z (GMT). No. of bitstreams: 1 Tese-Edna Manrique.pdf: 787735 bytes, checksum: c22ee105b30898fd35080c35bcd1fc80 (MD5) Previous issue date: 2009-06-30 / Objectives: analyze the performance of the 100% rapid re-screening in detecting falsenegative results of cervical screening cervical, in quality control, after routine screening, using the average time of one and two minutes, according to final diagnosis. Methodology: a total 5,235 smears, classified as negative and unsatisfactory by routine screening, were submitted to 100% rapid re-screening method, using the time average of one and two minutes. In these reviews, the smears classified as unsatisfactory or suspects were subjected to detailed review. The concordant results were considered final diagnosis; the differences were meeting for a consensus that defined the final diagnosis. Results: of 5,235 smears submitted rapid re-screening method, of using the time of one minute and two minutes there was sensitivity and specificity of the final method of 64.3% and 99.2% for the time of one minute and two minutes was 63.8% and 99.5%. In smears, with satisfy adequacy for analysis, the sensitivity and specificity of this method, using the time of one and two minutes, were 64.2%, 98.9%, 61.5% and 99.4% respectively. The smears, with the adequacy of the smears presented for analysis limits, the sensitivity and specificity, using the time of one minute, was 64.7%, 99.9% and for two minutes were 70.6% and 99.8%. Of the total of 5,121 cervical smears, had 958 (18.7%) clinical information, after being submitted to rapid rescreening, using the time of one minute, 18 of those were suspects, of which ten were confirmed by final diagnosis as abnormal. When submitted to rapid re-screening using the time of two minutes, 13 were suspects, nine of these were confirmed by final diagnosis as abnormal. A total 4,163 (81.3%) smears had no clinical information, after being submitted to rapid re-screening, using the time of one minute were 70 suspects, of which 35 were classified as abnormal. When submitted to rapid re-screening using the time of two minutes were 54 suspects, of which 35 were confirmed by final diagnosis as abnormal. A rapid re-screening showed a sensitivity to smear with clinical information, using the time of one minute of 83.3% and for two minutes of 75%. Conclusions: the rapid re-screening method of 100% showed no difference in the detection of falsenegative results using the time of a minute or two. The adequacy of the sample does not influence the detection of false-negative results, using both a time as two minutes, and there was no difference in the detection of false-negative smears with and without clinical information using a time-two minutes and finally, in smears with clinical information / Objetivos: analisar o desempenho da revisão rápida de 100% na detecção de resultados falso-negativos dos exames citopatológicos cervicais, no controle da qualidade, após o escrutínio de rotina, utilizando o tempo médio de um e dois minutos, de acordo com o diagnóstico final. Metodologia: um total 5.235 esfregaços, classificados como negativos e insatisfatórios pelo escrutínio de rotina, foram submetidos à revisão rápida, utilizando os tempos médios de um e dois minutos. Nessas revisões, os esfregaços classificados como insatisfatórios ou suspeitos foram submetidos à revisão detalhada. Os resultados concordantes foram considerados como diagnóstico final, os divergentes foram para reunião de consenso que definiu o diagnóstico final. Resultados: dos 5.235 esfregaços submetidos ao método de revisão rápida utilizando o tempo de um e dois minutos, verificou-se uma sensibilidade e especificidade final desse método de 64,3% e 99,2% para o tempo de um minuto e para dois minutos foi 63,8% e 99,5%. Em esfregaços, com a adequabilidade da amostra satisfatória para análise, a sensibilidade e especificidade desse método, utilizando os tempos de um e dois minutos, foram de 64,2%, 98,9%, 61,5% e 99,4%, respectivamente. Em esfregaços, com a adequabilidade da amostra apresentando limitação para análise, a sensibilidade e especificidade, utilizando o tempo de um minuto, foi de 64,7% e 99,9%, para dois minutos foram de 70,6% e 99,8%. Do total de 5.121 esfregaços citopatológicos, 958 (18,7%) tinham informações clínicas, após serem submetidos à revisão rápida, utilizando o tempo de um minuto, 18 desses foram suspeitos, dos quais 10 foram confirmados pelo diagnóstico final como alterados. Quando submetidos à revisão rápida, utilizando o tempo de dois minutos, 13 foram suspeitos, entre eles, nove foram confirmados pelo diagnóstico final como alterados. Um total de 4.163 (81,3%) esfregaços não tinha informações clínicas, após serem submetidos à revisão rápida, utilizando o tempo de um minuto, 70 foram suspeitos, dos quais 35 foram classificados como alterados. Quando submetidos à revisão rápida, utilizando o tempo de dois minutos, 54 foram suspeitos, dos quais 35 foram confirmados pelo diagnóstico final como alterados. A revisão rápida apresentou uma sensibilidade, para esfregaços com informações clínicas, utilizando o tempo de um minuto de 83,3% e para dois minutos de 75%. Conclusões: o método de revisão rápida de 100% não apresentou diferença na detecção de resultados falso-negativos utilizando o tempo de um ou dois minutos. A adequabilidade da amostra não influencia na detecção de resultados falso-negativos, utilizando tanto o tempo de um como dois minutos, bem como não houve diferença na detecção de resultados falso-negativos em esfregaços com e sem informações clínicas através do método de revisão rápida, utilizando o tempo de um e dois minutos.

Submitted by Rosivalda Pereira (mrs.pereira@ufma.br) on 2017-05-30T21:09:57Z No. of bitstreams: 1 JoaoDiniz.pdf: 2606559 bytes, checksum: 262a9c98db11667d3a482c378ab78b50 (MD5) / Made available in DSpace on 2017-05-30T21:09:57Z (GMT). No. of bitstreams: 1 JoaoDiniz.pdf: 2606559 bytes, checksum: 262a9c98db11667d3a482c378ab78b50 (MD5) Previous issue date: 2017-02-03 / Coordenação de Aperfeiçoamento de Pessoal de Nível Superior (CAPES) / Breast cancer is the type of cancer that most affects women and is one of the leading causes of death worldwide. Aiming to aid the detection and diagnosis of this pathology, several techniques in the image area are being created serving as a second opinion. It is known that mammograms of the left and right breast present a high degree of symmetry, and when there is a sudden difference between the pairs, it can be considered suspicious. It is also emphasized that the breast can present different density of the tissue and this can be a factor that makes difficult the detection and diagnosis of the lesions. Thus, the objective of this work is to develop an automatic methodology for the detection of mass regions in pairs of digitized mammograms adapted to breast density, using image processing and species comparison techniques to determine asymmetric regions in the breasts together with neural convolutional networks for Classification of breast density and regions in masses and not masses. The proposed methodology is divided into two phases: training phase and test phase. In the training phase will be created three models using convolutional neural networks, the first able to classify the breast as density and the last two to classify regions of mass and non-mass in dense and non-dense breasts.The steps are in aligning the breasts so that it is possible to make a comparison between the pairs. When comparing, asymmetric regions will be segmented, these regions will undergo a process of reduction of false positives in order to eliminate regions that are not masses. Before classifying the remaining regions, the breasts undergo the process of density classification by the model obtained in the training phase. Finally, for each type of breast, a model will classify the regions segmented into masses and not masses. The methodology presented excellent results, in the non-dense breasts reaching sensitivity of 91.56 %, specificity of 90.73 %, accuracy of 91.04 % and rate of 0.058 false positives per image. Dense breasts showed 90.36 % sensitivity, 96.35 % specificity, 94.84 % accuracy and 0.027 false positives per image. The results show that the methodology is promising and can be used to compose a CAD system, serving as a second option for the expert in the task of detecting mass regions. / O cãncer de mama é o tipo de câncer que mais acomete as mulheres e uma das principais causas de morte em todo o mundo. Visando auxiliar a detecção e diagnóstico desta patologia, diversas técnicas na érea de imagem estão sendo criadas servindo como um auxílio ao especialista. Sabe-se que mamografias esquerda e direita apresentam alto grau simetria, e quanto há uma diferença brusca entre os pares, pode-se considerar algo de suspeito. Ressalta-se também que a mama pode apresentar densidade diferente do tecido e isso pode ser um fator que dificulte na detecção e diagnóstico das lesões. Assim, o objetivo deste trabalho é desenvolver uma metodologia automática de detecção de regiões de massa em pares de mamografias digitalizadas adaptada à densidade da mama, utilizando técnicas de processamento de imagens e comparação de espécies para determinar regiões assimétricas nas mamas juntamente com redes neurais convolucionais para classificação de densidade da mama e de regiões em massas e não massas. A metodologia proposta é dividida em duas fases: fase de treinamento e fase de teste. Na fase de treinamento serão criados três modelos utilizando redes neurais convolucionais, o primeiro capaz de classificar a mama quanto a densidade e os dois últimos classificam regiões de massa e não massa em mamas densas e não densas. Na fase de teste, imagens de mamografia da base DDSM passarão por várias etapas a fim de segmentar regiões assimétricas que serão posteriormente classificadas. As etapas resumem-se em alinhar as mamas para que seja possível fazer uma comparação entre os pares. Ao comparar, serão segmentadas regiões assimétricas, essas regiões passarão por processo de redução de falsos positivos a fim de eliminar regiões que não são massas. Antes de classificar as regiões restantes, as mamas passam pelo processo de classificação de densidade pelo modelo obtido na fase de treinamento. Por fim, para cada tipo de mama, um modelo irá classificar as regiões segmentadas em massas e não massas. O método proposto apresentou resultados promissores, nas mamas não densas atingiu sensibilidade de 91,56%, especificidade de 90,73%, 91,04% de acurácia e taxa de 0,058 falsos positivos por imagem. As mamas densas, apresentaram resultados de 90,36% de sensibilidade, 96,35% de especificidade, 94,84% de acurácia e 0,027 falsos positivos por imagem. Os resultados mostram que a metodologia é promissora e pode ser utilizada para compor um sistema CAD na tarefa de detectar regiões de massas.

Submitted by Jorge Silva (jorgelmsilva@ufrrj.br) on 2018-05-17T18:02:00Z No. of bitstreams: 1 2015 - Fabr?cio de Azevedo Silva.pdf: 2083796 bytes, checksum: d9a26681bab37d5289f5f06f93a62cc8 (MD5) / Made available in DSpace on 2018-05-17T18:02:04Z (GMT). No. of bitstreams: 1 2015 - Fabr?cio de Azevedo Silva.pdf: 2083796 bytes, checksum: d9a26681bab37d5289f5f06f93a62cc8 (MD5) Previous issue date: 2015-08-31 / CAPES / The main objective of this research is to see whether the false position method, used to solve some problems Rhind Papyrus, can be an alternative for solving problems that involve the 1st degree equations with one unknown for students from the 7th grade of elementary school. The Egyptians used this method and this is a way to find the solution of the problem by requiring an initial value, considered the false position, which should be adjusted immediately to obtain the correct value. As we noted not rare that this strategy is adopted by students nowadays, we believe this is a plausible alternative to the teaching content. To check the effectiveness of the method, We conducted a case study ? adopting a qualitative approach to analyze the data collected in search ? with a group of the 7th grade in a municipal school in Rio de Janeiro. We propose a sequence of three activities, applied in a single meeting, where after the resolution of problems by students, we began a discussion of what strategies adopted. After the resolution of the first activity, a problem taken from the Rhind Papyrus, during the period for the discussion of the problem, we show how the Egyptians resolved. We can see that a considerable amount of them identified with the method, by the way they decided later activities. / O principal objetivo desta pesquisa ? verificar se o m?todo da falsa posi??o, utilizado para resolver alguns problemas do Papiro de Rhind, pode ser uma alternativa para resolu??o de problemas que envolvem equa??es do 1? grau com uma inc?gnita para alunos do 7? ano do ensino fundamental. Esse m?todo era utilizado pelos eg?pcios e trata-se de um caminho para encontrar a solu??o do problema atrav?s da estipula??o de um valor inicial, considerado a falsa posi??o, que dever? ser ajustado imediatamente ap?s para se obter o valor correto. Como observamos n?o ser raro que essa estrat?gia seja adotada pelos discentes nos dias atuais, acreditamos ser essa uma alternativa plaus?vel para o ensino do conte?do. Para verificar a efic?cia do m?todo, realizamos um estudo de caso ? adotando uma abordagem qualitativa para analisar os dados recolhidos na pesquisa ? com uma turma do 7? ano em uma escola da rede municipal do Rio de Janeiro. Propomos uma sequ?ncia de tr?s atividades, aplicada em um ?nico encontro, onde ap?s a resolu??o dos problemas pelos discentes, inici?vamos uma discuss?o sobre quais estrat?gias adotaram. Ap?s a resolu??o da primeira atividade, um problema retirado do Papiro de Rhind, durante o per?odo destinado ? discuss?o do problema, mostramos como os eg?pcios o resolviam. Podemos perceber que uma quantidade consider?vel deles se identificou com o m?todo, pela forma como resolveram as atividades posteriores.

<p>U ovoj doktorskoj disertaciji predložena je nova metoda za detekciju malicioznih napada injektiranjem loših merenja na elektroenergetski sistem. Predloženi algoritam baziran je na sinergiji statičke i dinamičke estimacije stanja, i u stanju je da detektuje ovaj tip napada u realnom vremenu, za najkritičniji scenario gde napadač ima potpuno znanje o sistemu, i neograničen pristup resursima.</p> / <p>This PhD thesis proposes a novel method for detection of malicious false data<br />injection attacks on power system. The proposed algorithm is based on<br />synergy between static and dynamic state estimators, and is capable of<br />detecting the forementioned attacks in real time, for the most critical scenarios,<br />where an attacker has complete knowledge about the compromised power<br />system and unlimited resources to stage an attack.</p>

False memories happen when someone mis-remembers a past event that occurred. The study of false memories is commonly done using the DRM paradigm which can form false memories through semantic list learning. The current study is evaluating false memory, deception, and truth-telling using the DRM paradigm while measuring cortical activation with fNIRS. Results indicated no interactions between specific condition responses and brain regions in the prefrontal cortex. A main effect of condition was found indicating that correct responses have the lowest level of activation. Additionally, there were no significant differences found between deception and false memory responses. Further research needs to be conducted to help further analyze possible differences between these conditions as well as in more subcortical regions of the prefrontal cortex.

<p>This dissertation proposes an approach to reduce the cost of manual inspections for as large a number of false positive warnings that are being reported by Static Code Analysis (SCA) tools as much as possible using Machine Learning (ML) techniques. The proposed approach neither assume to use the particular SCA tools nor depends on the specific programming language used to write the target source code or the application. To reduce the number of false positive warnings we first evaluated a number of SCA tools in terms of software engineering metrics using a highlighted synthetic source code named the Juliet test suite. From this evaluation, we concluded that the SCA tools report plenty of false positive warnings that need a manual inspection. Then we generated a number of datasets from the source code that forced the SCA tool to generate either true positive, false positive, or false negative warnings. The datasets, then, were used to train four of ML classifiers in order to classify the collected warnings from the synthetic source code. From the experimental results of the ML classifiers, we observed that the classifier that built using the Random Forests</p> <p>(RF) technique outperformed the rest of the classifiers. Lastly, using this classifier and an instance-based transfer learning technique, we ranked a number of warnings that were aggregated from various open-source software projects. The experimental results show that the proposed approach to reduce the cost of the manual inspection of the false positive warnings outperformed the random ranking algorithm and was highly correlated with the ranked list that the optimal ranking algorithm generated.</p>

Les entreprises, les administrations, et parfois les particuliers, doivent faire face à de nombreuses fraudes sur les documents qu’ils reçoivent de l’extérieur ou qu’ils traitent en interne. Les factures, les notes de frais, les justificatifs... tout document servant de preuve peut être falsifié dans le but de gagner plus d’argent ou de ne pas en perdre. En France, on estime les pertes dues aux fraudes à plusieurs milliards d’euros par an. Étant donné que le flux de documents échangés, numériques ou papiers, est très important, il serait extrêmement coûteux en temps et en argent de les faire tous vérifier par des experts de la détection des fraudes. C’est pourquoi nous proposons dans notre thèse un système de détection automatique des faux documents. Si la plupart des travaux en détection automatique des faux documents se concentrent sur des indices graphiques, nous cherchons quant à nous à vérifier les informations textuelles du document afin de détecter des incohérences ou des invraisemblances. Pour cela, nous avons tout d’abord constitué un corpus de tickets de caisse que nous avons numérisés et dont nous avons extrait le texte. Après avoir corrigé les sorties de l’OCR et fait falsifier une partie des documents, nous en avons extrait les informations et nous les avons modélisées dans une ontologie, afin de garder les liens sémantiques entre elles. Les informations ainsi extraites, et augmentées de leurs possibles désambiguïsations, peuvent être vérifiées les unes par rapport aux autres au sein du document et à travers la base de connaissances constituée. Les liens sémantiques de l’ontologie permettent également de chercher l’information dans d’autres sources de connaissances, et notamment sur Internet. / Companies, administrations, and sometimes individuals, have to face many frauds on documents they receive from outside or process internally. Invoices, expense reports, receipts...any document used as proof can be falsified in order to earn more money or not to lose it. In France, losses due to fraud are estimated at several billion euros per year. Since the flow of documents exchanged, whether digital or paper, is very important, it would be extremely costly and time-consuming to have them all checked by fraud detection experts. That’s why we propose in our thesis a system for automatic detection of false documents. While most of the work in automatic document detection focuses on graphic clues, we seek to verify the textual information in the document in order to detect inconsistencies or implausibilities.To do this, we first compiled a corpus of documents that we digitized. After correcting the characters recognition outputs and falsifying part of the documents, we extracted the information and modelled them in an ontology, in order to keep the semantic links between them. The information thus extracted, and increased by its possible disambiguation, can be verified against each other within the document and through the knowledge base established. The semantic links of ontology also make it possible to search for information in other sources of knowledge, particularly on the Internet.

This thesis investigates the application of index based, region segmentation, and deep learning methods to the sensor fusion of omnidirectional (O-D) Infrared (IR) sensors, Kinnect sensors, and O-D vision sensors to increase the level of intelligent perception for unmanned robotic platforms. The goals of this work is first to provide a more robust calibration approach and improve the calibration of low resolution and noisy IR O-D cameras. Then our goal was to explore the best approach to sensor fusion for vegetation detection. We looked at index based, region segmentation, and deep learning methods and compared them with a goal of significant reduction in false positives while maintaining reasonable vegetation detection. The results are as follows: Direct Spherical Calibration of the IR camera provided a more consistent and robust calibration board capture and resulted in the best overall calibration results with sub-pixel accuracy The best approach for sensor fusion for vegetation detection was the deep learning approach, the three methods are detailed in the following chapters with the results summarized here. Modified Normalized Difference Vegetation Index approach achieved 86.74% recognition and 32.5% false positive, with peaks to 80% Thermal Region Fusion (TRF) achieved a lower recognition rate at 75.16% but reduced false positives to 11.75% (a 64% reduction) Our Deep Learning Fusion Network (DeepFuseNet) results demonstrated that deep learning approach showed the best results with a significant (92%) reduction in false positives when compared to our modified normalized difference vegetation index approach. The recognition was 95.6% with 2% false positive. Current approaches are primarily focused on O-D color vision for localization, mapping, and tracking and do not adequately address the application of these sensors to vegetation detection. We will demonstrate the contradiction between current approaches and our deep sensor fusion (DeepFuseNet) for vegetation detection. The combination of O-D IR and O-D color vision coupled with deep learning for the extraction of vegetation material type, has great potential for robot perception. This thesis will look at two architectures: 1) the application of Autoencoders Feature Extractors feeding a deep Convolution Neural Network (CNN) fusion network (DeepFuseNet), and 2) Bottleneck CNN feature extractors feeding a deep CNN fusion network (DeepFuseNet) for the fusion of O-D IR and O-D visual sensors. We show that the vegetation recognition rate and the number of false detects inherent in the classical indices based spectral decomposition are greatly improved using our DeepFuseNet architecture. We first investigate the calibration of omnidirectional infrared (IR) camera for intelligent perception applications. The low resolution omnidirectional (O-D) IR image edge boundaries are not as sharp as with color vision cameras, and as a result, the standard calibration methods were harder to use and less accurate with the low definition of the omnidirectional IR camera. In order to more fully address omnidirectional IR camera calibration, we propose a new calibration grid center coordinates control point discovery methodology and a Direct Spherical Calibration (DSC) approach for a more robust and accurate method of calibration. DSC addresses the limitations of the existing methods by using the spherical coordinates of the centroid of the calibration board to directly triangulate the location of the camera center and iteratively solve for the camera parameters. We compare DSC to three Baseline visual calibration methodologies and augment them with additional output of the spherical results for comparison. We also look at the optimum number of calibration boards using an evolutionary algorithm and Pareto optimization to find the best method and combination of accuracy, methodology and number of calibration boards. The benefits of DSC are more efficient calibration board geometry selection, and better accuracy than the three Baseline visual calibration methodologies. In the context of vegetation detection, the fusion of omnidirectional (O-D) Infrared (IR) and color vision sensors may increase the level of vegetation perception for unmanned robotic platforms. A literature search found no significant research in our area of interest. The fusion of O-D IR and O-D color vision sensors for the extraction of feature material type has not been adequately addressed. We will look at augmenting indices based spectral decomposition with IR region based spectral decomposition to address the number of false detects inherent in indices based spectral decomposition alone. Our work shows that the fusion of the Normalized Difference Vegetation Index (NDVI) from the O-D color camera fused with the IR thresholded signature region associated with the vegetation region, minimizes the number of false detects seen with NDVI alone. The contribution of this work is the demonstration of two new techniques, Thresholded Region Fusion (TRF) technique for the fusion of O-D IR and O-D Color. We also look at the Kinect vision sensor fused with the O-D IR camera. Our experimental validation demonstrates a 64% reduction in false detects in our method compared to classical indices based detection. We finally compare our DeepFuseNet results with our previous work with Normalized Difference Vegetation index (NDVI) and IR region based spectral fusion. This current work shows that the fusion of the O-D IR and O-D visual streams utilizing our DeepFuseNet deep learning approach out performs the previous NVDI fused with far infrared region segmentation. Our experimental validation demonstrates an 92% reduction in false detects in our method compared to classical indices based detection. This work contributes a new technique for the fusion of O-D vision and O-D IR sensors using two deep CNN feature extractors feeding into a fully connected CNN Network (DeepFuseNet).

Research questions, results and Empirical Data This book studies the allocation of scarce resources among competing needs and wants. Chapter 1 – Luck, effort and Redistribution on procedural justice provides one possible explanation for the vast differences between US and Western European tax an redistribution levels. Chapter 2- Participation and Peers in Social Dilemmas on social norms investigates two potential reasons why solutions to social dilemmas in for instance insurance systems can persist without being destroyed by the negative forces of free-riding. Chapter 3 - Commitment and Impasses in Negotiation on conflict shifts focus to bilateral bargaining and the reasons for conflict and impasses. Whether they manifest as strikes, job resignations, or trade embargoes, failures of the negotiation process create tremendous loss of social welfare and are therefore important to further understand. Each chapter is based on observations of real human behavior in the lab. The empirical data consists of: 204 M.B.A. students and 96 M.Sc. students from Harvard university, the Stockholm School of Economics, the Royal Institute of Technology, Stockholm university and Karolinska Institutet; 5 experiments over 21 experimental sessions generated 2,520 observations.