The purpose of this study was to examine the effect of immersion in sodium hypochlorite on nickel titanium rotary files and determine whether resistance to fracture was influenced by the immersion time. 70 ISO size 25 0.04 taper nickel titanium K3 and Profile rotary instruments were immersed in 5.25% sodium hypochlorite for 1, 5, 15, 30, 60, and 120 minutes (n=5 each). Resistance to fracture was tested by rotating files at a 30 degree angle at 350 rpm in a universal testing machine. Time to fracture was recorded and analyzed by a two-way ANOVA. Within both file types, there was a decreased time to fracture with increased immersion time in sodium hypochlorite. K3 files required an average of 327 rotations to fracture, while Profiles required 420 rotations to fracture. Profiles required significantly more rotations to failure than K3 files.

The purpose of this study was to compare the number of rotations to failure of three different rotary file systems. ProFile, Sequence, and Liberator files in sizes 25 and 40 with 0.04 taper were divided into groups of five and rotated against a grooved metal block mounted to a Universal testing machine at 31 and 34 degrees. Each file was rotated at 300 rpm until fracture occurred. The number of rotations to fracture were calculated. Use of a three-way ANOVA and Tukey's HSD multiple comparison tests revealed significant differences for the angle of deflection, size, and type of file. An increased angle of deflection resulted in a decreased number of rotations to failure for all three file types. An increased size of file also resulted in a decreased number of rotations to failure in all the groups. Liberator and Sequence files required fewer rotations to failure than ProFiles in all groups tested except the size 25 files rotated at the less severe angle. ProFiles appear to be more resistant to flexural fracture than Liberator and Sequence files unless the files are of smaller size with a less severe curvature. Care should be taken to limit the number of uses when using larger size files, especially Liberator and Sequence files, around severe curvatures.

As bandwidth constraints on LAN/WAN environments decrease, the demand for distributed services will continue to increase. In particular, the proliferation of user-level applications requiring high-capacity distributed file storage systems will demand that such services be universally available. At the same time, the advent of high-speed networks have made the deployment of application and communication solutions based upon an Intelligent Mobile Agent (IMA) framework practical. Agents have proven to present an ideal development paradigm for the creation of autonomous large-scale distributed systems, and an agent-based communication scheme would facilitate the creation of independently administered distributed file services. This thesis thus outlines an architecture for such a distributed file system based upon an IMA communication framework.

This work is an investigation into reconstructing fragmented ASCII files based on content analysis motivated by a desire to demonstrate machine learning's applicability to Digital Forensics. Using a categorized corpus of Usenet, Bulletin Board Systems, and other assorted documents a series of experiments are conducted using machine learning techniques to train classifiers which are able to identify fragments belonging to the same original file. The primary machine learning method used is the Support Vector Machine with a variety of feature extractions to train from. Additional work is done in training committees of SVMs to boost the classification power over the individual SVMs, as well as the development of a method to tune SVM kernel parameters using a genetic algorithm. Attention is given to the applicability of Information Retrieval techniques to file fragments, as well as an analysis of textual artifacts which are not present in standard dictionaries.

No final do século XIX, a emergência do conceito de periculosidade forjou uma série de ações de controle social que ainda hoje encontram espaço fecundo de legitimação. Os desdobramentos dessa noção, que se articulou da fusão do Direito Penal com a Psiquiatria, encontram no manicômio judiciário o seu exemplo mais sólido. No Brasil, a emergência do Manicômio Judiciário do Estado de São Paulo (MJES) no início da década de 1930 consolidou um ideal há muito defendido pela Criminologia Positivista. No entanto, a despeito do intenso fluxo de internações ocorridas ao longo dos anos e da imprescindibilidade que desempenhou e ainda desempenha no circuito repressivo do Estado atualmente, sua história segue opaca, inaudita e, por vezes, tão fundida à história do Hospital do Juqueri a ponto de ter o seu próprio registro tangenciado. A intenção deste trabalho consistiu em recuperar o arquivamento que se produziu sobre a loucura criminosa e analisar os discursos e as práticas empregadas pelo saber médico e jurídico para justificar a reclusão no MJES entre os anos de 1927 a 1940. Considerando que se trata de um espaço de natureza médico-jurídica que há anos sustenta a função de controle social alicerçado na justificativa de proteção contra a periculosidade, o problema de pesquisa delimitado para este trabalho se organizou em torno de algumas questões fundamentais, a saber: (1) problematizar as condições de emergência do MJES; (2) mostrar como os discursos sobre a loucura criminosa foram organizados e distribuídos no arquivo médico-legal; (3) identificar e caracterizar o sujeito da periculosidade para o qual se designou a internação manicomial durante o período referido acima; (4) analisar sob quais circunstâncias infracionais ou não a periculosidade foi utilizada como justificativa para a interdição médico-legal; (5) analisar os pressupostos técnicoscientíficos que sustentam a realização do exame médico-legal ou da chamada avaliação de cessação de periculosidade nos prontuários médicos. A escolha por documentos que registraram estas vidas infames sob a insígnia da loucura, do crime e da marginalidade abrem a possibilidade de problematizar as verdades estabelecidas pelos saberes que os redigiram. Desse modo, o mesmo registro que um dia serviu para cumprir sua finalidade disciplinar foi aqui recuperado para produzir perguntas e subverter a própria razão que uma vez justificou a sua existência / At the end of the 19th century, the rise of the dangerousness concept forged a series of actions aimed at social control legitimized by many to this day. The unfolding of this notion, articulated by the merger of Criminal Law with Psychiatry, found its best example in the legal asylum. In Brazil, the foundation of the Legal Asylum of the State of São Paulo (MJES) in the early 1930s consolidated an ideal long advocated by Positivist Criminology. Yet, despite the intense number of hospitalizations over the years and the essential role the institution has played (and still plays) in a repressive system, its history remains opaque, unprecedented, and so fused with the history of Juqueri Hospital that their records converge. The intent of this work was to recover the files about the ones considered criminals and insane and analyze the speeches and practices used by the medical and law communities to justify the reclusion of individuals in the MJES between 1927 and 1940. Considering that for years the psychiatric hospital has been a legal and medical space of social control, sustained by the assumption that it protects society against dangerousness, some fundamental issues organized this research: (1) to discuss the MJES conditions; (2) to show how the medical and legal files organized discourses about criminal insanity; (3) to identify and characterize the \"subject of dangerousness\", that is the types of people sent to the asylum during the period referred above; (4) to analyze under what circumstances dangerousness justified the medical and legal prohibition; (5) to analyze the technical-scientific assumptions that supported the forensic medical examination or the so-called \"medical termination assessment\" in the records. The decision to use documents that reported these infamous lives under the guise of madness, crime and marginality make it possible to discuss some established truths of the scientific community. Thus, the same files that once served to fulfil a disciplinary purpose here raise questions and subvert the very reason that once justified its existence

Este trabalho apresenta um estudo sobre o gargalo no acesso a disco sob arquiteturas com sistemas multiprocessadores e processadores multicore e apresenta uma proposta de solução para o problema e sua implementação. A solução desenvolvida é chamada de FPA. A estratégia desenvolvida no trabalho aproveita os recursos de memória compartilhada da arquitetura e utiliza buffers de dados compartilhados entre as diversas threads das aplicações, bem como tenta otimizar o acesso ao disco rígido. Para que seja diminuída a concorrência no acesso a disco, é permitido que apenas uma thread realize leituras ou gravações no disco por vez, e nas situações de escrita é feita a sobreposição entre o processamento e o envio dos dados ao disco. As operações de escrita são realizadas por uma thread adicional, que é inicializada e gerenciada pela FPA. Foram executados diversos testes com diferentes números de threads, tamanhos de arquivo e quantidade de processamento de cálculos na aplicação. Os resultados apresentaram ganho de desempenho com a FPA em diversas situações, onde um dos fatores mais significativos para o ganho de desempenho é a quantidade de processamento existente na aplicação. De modo geral, as operações de leitura apresentaram ganho de desempenho em relação ao uso de streams nas situações onde existe pouco processamento de cálculos na aplicação, e as operações de escrita mostraram vantagem nas situações onde existe uma quantidade de processamento de cálculos maior na aplicação. Nas operações de escrita é obtido vantagem com a sobreposição entre processamento e escrita de dados. Porém, quando a quantidade de processamento de cálculos é muito alta, o tempo de espera pela gravação em disco torna-se irrisório perante o tempo gasto no processamento dos cálculos, ocasionando perda de desempenho da FPA em relação aos streams. / This work presents a study on disk access bottlenecks for multiprocessor architecture systems and also proposes a specification to solve this problem and its implementation. The developed strategy is called FPA. The developed strategy makes use of shared memory architecture and uses shared data buffers among several application threads and also tries to optimize disk access time. In order to decrease disk concurrency, is allowed to just one application thread to read/write simultaneously and processing thread operations run parallelly to disk operations. Write operations are performed by an internal thread, which is started and managed by FPA. Several tests were performed concerning different amounts of application threads instances, file sizes and computing instructions. Results show performance gain with FPA in several situations. The main factor that affects performance is the amount of computing instructions on each application. In general, read operations showed a better performance compared to use of streams in situations where there is few computing instructions in the application, and write operations showed advantages on situations where there are more computing instructions in the application. Write operations are advantageous using data writing and computing instructions overlap. However, in cases of a large amount of computing instructions compared to disk operations, the time to perform disk operations becomes too few compared to computing time, occurring FPA performance loss compared to streams.

Os arquivos pessoais estão cada vez mais em evidência e na pauta de discussão entre estudiosos e profissionais da área arquivística. Contribuindo para a discussão em crescimento, apresentamos a defesa de um novo método de pesquisa com arquivos pessoais, fundamentado, desenvolvido e demonstrado a partir da criação de um instrumento de pesquisa desenvolvido paralelamente: o Inventário cronológico do arquivo de Epifânio Dória. Filho de proprietários de terras, Epifânio da Fonseca Dória e Menezes nasceu no ano de 1884, em Campos (Sergipe). O titular do arquivo participou da formação de praticamente todos os centros de estudo, arquivos, bibliotecas, revistas e instituições dedicadas às humanidades no Estado de Sergipe. Dedicou-se com afinco à organização de arquivos por seis décadas reunindo documentos, angariando recursos e adquirindo fundos. Figura representativa em Sergipe por sua contribuição à guarda, preservação de documentos históricos e arquivos pessoais de personalidades sergipanas, notabilizou-se também pela incansável pesquisa histórica desenvolvida ao longo de sua vida. Falecido em 1976, Epifânio Dória nos deixou um precioso conjunto documental, que perfaz um período riquíssimo da história do Brasil, marcado por acontecimentos e transições importantes, que apresentam para o pesquisador inúmeras possibilidades de pesquisa em diversas áreas do conhecimento. O arquivo de Epifânio Dória possui 35.193 documentos, estando distribuído, e consequentemente fragmentado, em três importantes instituições sergipanas, a saber: Instituto Histórico e Geográfico de Sergipe (IHGSE), Arquivo Público do Estado de Sergipe (APES) e Biblioteca Pública Estadual Epifânio Dória (BPED). Apesar de fisicamente fragmentado, trata-se de um arquivo íntegro, preservado pela família e, posteriormente, pelas instituições de custódia que o receberam. Entrar em contato, conhecer e trabalhar com a documentação reunida por este importante intelectual, historiador e bibliotecário sergipano foi nossa tarefa. Nesta nova proposta metodológica percorremos: a funcionalidade, o contexto de produção dos documentos e o vínculo documental. Essa tarefa foi potencializada com a criação, o desenvolvimento, a alimentação e o uso de um banco de dados, que contribuiu para a recuperação das informações e para a construção dos verbetes formadores da cronologia elementos de classificação que deram um sentido mais imediato aos documentos. Nesta proposta, a classificação assumiu o patamar mais próximo dos documentos, classificados um a um, sendo priorizada a escala micro e levando em conta as especificidades da trajetória de vida do titular do arquivo. A construção do inventário cronológico permitiu um diálogo exaustivo entre a documentação produzida e acumulada por seu titular e sua trajetória de vida. Entendendo-se diálogo não como uma interpretação histórica, mas como a construção de uma ponte entre o documento e a atividade/evento que lhe deu origem. O arquivo de Epifânio Dória nos impôs problemas práticos e teóricos complexos, mas, em contrapartida, nos ofereceu a chance de discuti-los, buscando soluções e propostas no desenvolvimento da pesquisa. A tese apresentada fornece novas nuances a metodologia arquivística de forma a fundamentar a organização, descrição e contextualização dos documentos pessoais, sem ferir os princípios da área; além de aprofundar, com base na documentação, a própria biografia de Epifânio Dória. / Personal files are increasingly in evidence and on the agenda for discussion between scholars and professionals in the area of archives. Contributing to the discussion on growth, introducing the defense of a search method with personal files, reasoned and demonstrated from research instrument developed in parallel: The Inventory of chronological file of Epifânio Dória. Son of landowners, Epifânio da Fonseca Dória e Menezes was born in the year of 1884, in Campos (Sergipe). The holder of the file participated in the formation of virtually all study centers, archives, libraries, magazines and institutions dedicated to the humanities in the State of Sergipe. He devoted himself diligently to organize files by six decades gathering documents, gaining resources and acquiring funds. Representative Figure in Sergipe by its contribution to guard, preservation of historical documents and personal files of State of Segipe personalities, studious also by tireless historical research developed over the course of his life. Dead in 1976, Epifânio Dória left us a precious records, which makes a very rich period of the Brazil history, marked by events and transitions, which have for the researcher countless possibilities of research in various areas of knowledge. The file of Epifânio Dória has 35,193 documents, being distributed, and consequently fragmented, in three important institutions sergipanas, namely: Historical and Geographic Institute of Sergipe (IHGSE), Public Archives of the State of Sergipe (APES) and Public State Library Epiphanius Doria (BPED). Although physically fragmented, it is a file intact, preserved by the family and, subsequently, by the institutions of custody that the received. Contact, knowing and working with the documentation gathered by an important intellectual, historian and librarian from Sergipe were was our task. We offer with the work presented a new approach to personal files. In this proposal the classification assumes the closest level to the documents, classified one by one, being prioritized the micro scale and taking into account the specificities of the life trajectory of the holder of the file. In this sense, the record sheets created are the elements of classification that give a sense more immediately to documents. This way, we build a chronological inventory, performing, from this survey instrument, a comprehensive dialog between the documentation produced and accumulated by its holder and their life trajectory. Understanding dialog is not as a historical interpretation, but as the construction of a bridge between the document and the activity/event that you gave rise. The file of Epifânio Dória spurred us on practical problems and theoretical complex, but, on the other hand, offered us the chance to discuss them, seeking solutions and proposals in the development of the research. The thesis presented provides new nuances the methodology archives in order to substantiate the organization, description and contextualization of personal documents, without violating the principles of the area, and further, on the basis of the documentation, the own biography of Epifânio Dória.

O desenvolvimento de instrumentos endodônticos em ligas de níquel-titânio (Ni-Ti) derivou maior rapidez na modelagem do canal radicular o que nos leva a questionar se realmente estariam as substâncias químicas auxiliares tendo oportunidade de agir convenientemente, considerando que o tempo de atuação das mesmas foi significantemente encurtado. Tendo em vista esse aspecto foi objeto deste trabalho avaliar, com auxílio de microscopia eletrônica de varredura (MEV) e leituras computadorizadas, a limpeza da superfície dentinária radicular, terços cervical, médio e apical, em canais radiculares de incisivos inferiores humanos, preparados pelo sistema rotatório K3?ENDO diante do uso de hipoclorito de sódio a 2,5%, (pH 11,0), do creme de Endo PTC reagindo com hipoclorito de sódio a 0,5%, (pH 11,0), empregando-se essa substância em duas diferentes consistências; sua consistência normal (Endo PTC-N) e uma outra de menor densidade (Endo-PTC-L); e, de um gel de clorexidina (Endogel®) com dois tipos de irrigação final. Concluída a fase de preparo todos os grupos receberam irrigação-aspiração final com soluções de hipoclorito de sódio a 0,5%, (pH 11,0) e de EDTA-T a 17%, exceção feita ao grupo em que se empregou o Endogel®, para o qual seguiu-se dois regimes de irrigação, em um grupo, irrigação-aspiração final com 20 mL de soro fisiológico, conforme recomendações do fabricante e em outro grupo empregou-se irrigação com EDTA-T. As amostras foram então preparadas para MEV e suas imagens analisadas pelo programa Scion Image. Os resultados revelaram haver diferença estatisticamente significante entre os grupos, sendo que o grupo do Endo-PTC-L se mostrou superior aos demais grupos testados no terço médio e apical já o grupo do Endogel seguido da irrigação final com EDTA-T apenas no terço médio, não havendo diferença estatística entre eles. / The development of nickel-titanium (NiTi) endodontic instruments results in more quickness during the root canal shaping phase that induce us to discuss if really would be the chemical substances are having opportunities to act properly, considering that the time of action of the same was significantly reduced. The object of this research was evaluate, using the scanning electron microscopy (SEM) and computerized analysis, the cleaning on root canal walls in coronal, middle and apical thirds in mandibular human incisives prepared with K3 NiTi rotary instruments and different chemical substances: 2,5% sodium hypochlorite (pH 11,0), Endo PTC cream at normal consistency (Endo PTC-N) neutralized by 0,5% sodium hypochlorite (pH 11,0), Endo PTC cream with lower density (Endo PTC-L) neutralized by 0,5% sodium hypochlorite (pH 11,0) and chlorhexidine gel (Endogel). Concluded the cleaning and shaping phase, all the groups received a final irrigation with of 0,5% sodium hypochlorite solution (pH 11,0) followed by 17% EDTA-T solution, except the Endogel group that received two different regimens of final irrigation, one group with 20 ml of physiological serum and another with the 17% EDTA-T solution. The samples were prepared for the SEM analysis and the images obtained were analyzed using the Scion Image program. The results showed a significant difference between the groups tested seeing that the Endo PTC-L group, in middle and apical thirds and Endogel followed by the final irrigation with EDTA-T group, in middle third were superiors in comparation with the other groups.

Hoi, Chu-Hong. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2004. / Includes bibliographical references (leaves 89-103). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgement --- p.iv / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Content-based Image Retrieval --- p.1 / Chapter 1.2 --- Relevance Feedback --- p.3 / Chapter 1.3 --- Contributions --- p.4 / Chapter 1.4 --- Organization of This Work --- p.6 / Chapter 2 --- Background --- p.8 / Chapter 2.1 --- Relevance Feedback --- p.8 / Chapter 2.1.1 --- Heuristic Weighting Methods --- p.9 / Chapter 2.1.2 --- Optimization Formulations --- p.10 / Chapter 2.1.3 --- Various Machine Learning Techniques --- p.11 / Chapter 2.2 --- Support Vector Machines --- p.12 / Chapter 2.2.1 --- Setting of the Learning Problem --- p.12 / Chapter 2.2.2 --- Optimal Separating Hyperplane --- p.13 / Chapter 2.2.3 --- Soft-Margin Support Vector Machine --- p.15 / Chapter 2.2.4 --- One-Class Support Vector Machine --- p.16 / Chapter 3 --- Relevance Feedback with Biased SVM --- p.18 / Chapter 3.1 --- Introduction --- p.18 / Chapter 3.2 --- Biased Support Vector Machine --- p.19 / Chapter 3.3 --- Relevance Feedback Using Biased SVM --- p.22 / Chapter 3.3.1 --- Advantages of BSVM in Relevance Feedback --- p.22 / Chapter 3.3.2 --- Relevance Feedback Algorithm by BSVM --- p.23 / Chapter 3.4 --- Experiments --- p.24 / Chapter 3.4.1 --- Datasets --- p.24 / Chapter 3.4.2 --- Image Representation --- p.25 / Chapter 3.4.3 --- Experimental Results --- p.26 / Chapter 3.5 --- Discussions --- p.29 / Chapter 3.6 --- Summary --- p.30 / Chapter 4 --- Optimizing Learning with SVM Constraint --- p.31 / Chapter 4.1 --- Introduction --- p.31 / Chapter 4.2 --- Related Work and Motivation --- p.33 / Chapter 4.3 --- Optimizing Learning with SVM Constraint --- p.35 / Chapter 4.3.1 --- Problem Formulation and Notations --- p.35 / Chapter 4.3.2 --- Learning boundaries with SVM --- p.35 / Chapter 4.3.3 --- OPL for the Optimal Distance Function --- p.38 / Chapter 4.3.4 --- Overall Similarity Measure with OPL and SVM --- p.40 / Chapter 4.4 --- Experiments --- p.41 / Chapter 4.4.1 --- Datasets --- p.41 / Chapter 4.4.2 --- Image Representation --- p.42 / Chapter 4.4.3 --- Performance Evaluation --- p.43 / Chapter 4.4.4 --- Complexity and Time Cost Evaluation --- p.45 / Chapter 4.5 --- Discussions --- p.47 / Chapter 4.6 --- Summary --- p.48 / Chapter 5 --- Group-based Relevance Feedback --- p.49 / Chapter 5.1 --- Introduction --- p.49 / Chapter 5.2 --- SVM Ensembles --- p.50 / Chapter 5.3 --- Group-based Relevance Feedback Using SVM Ensembles --- p.51 / Chapter 5.3.1 --- (x+l)-class Assumption --- p.51 / Chapter 5.3.2 --- Proposed Architecture --- p.52 / Chapter 5.3.3 --- Strategy for SVM Combination and Group Ag- gregation --- p.52 / Chapter 5.4 --- Experiments --- p.54 / Chapter 5.4.1 --- Experimental Implementation --- p.54 / Chapter 5.4.2 --- Performance Evaluation --- p.55 / Chapter 5.5 --- Discussions --- p.56 / Chapter 5.6 --- Summary --- p.57 / Chapter 6 --- Log-based Relevance Feedback --- p.58 / Chapter 6.1 --- Introduction --- p.58 / Chapter 6.2 --- Related Work and Motivation --- p.60 / Chapter 6.3 --- Log-based Relevance Feedback Using SLSVM --- p.61 / Chapter 6.3.1 --- Problem Statement --- p.61 / Chapter 6.3.2 --- Soft Label Support Vector Machine --- p.62 / Chapter 6.3.3 --- LRF Algorithm by SLSVM --- p.64 / Chapter 6.4 --- Experimental Results --- p.66 / Chapter 6.4.1 --- Datasets --- p.66 / Chapter 6.4.2 --- Image Representation --- p.66 / Chapter 6.4.3 --- Experimental Setup --- p.67 / Chapter 6.4.4 --- Performance Comparison --- p.68 / Chapter 6.5 --- Discussions --- p.73 / Chapter 6.6 --- Summary --- p.75 / Chapter 7 --- Application: Web Image Learning --- p.76 / Chapter 7.1 --- Introduction --- p.76 / Chapter 7.2 --- A Learning Scheme for Searching Semantic Concepts --- p.77 / Chapter 7.2.1 --- Searching and Clustering Web Images --- p.78 / Chapter 7.2.2 --- Learning Semantic Concepts with Relevance Feed- back --- p.73 / Chapter 7.3 --- Experimental Results --- p.79 / Chapter 7.3.1 --- Dataset and Features --- p.79 / Chapter 7.3.2 --- Performance Evaluation --- p.80 / Chapter 7.4 --- Discussions --- p.82 / Chapter 7.5 --- Summary --- p.82 / Chapter 8 --- Conclusions and Future Work --- p.84 / Chapter 8.1 --- Conclusions --- p.84 / Chapter 8.2 --- Future Work --- p.85 / Chapter A --- List of Publications --- p.87 / Bibliography --- p.103

Chan Chi Hang. / Thesis submitted in: August 2004. / Thesis (M.Phil.)--Chinese University of Hong Kong, 2005. / Includes bibliographical references (leaves 105-114). / Abstracts in English and Chinese. / Abstract --- p.i / Acknowledgement --- p.iv / Chapter 1 --- Introduction --- p.1 / Chapter 1.1 --- Problem Statement --- p.3 / Chapter 1.2 --- Major Contributions --- p.5 / Chapter 1.3 --- Publication List --- p.6 / Chapter 1.4 --- Thesis Organization --- p.7 / Chapter 2 --- Background Survey --- p.9 / Chapter 2.1 --- Relevance Feedback Framework --- p.9 / Chapter 2.1.1 --- Relevance Feedback Types --- p.11 / Chapter 2.1.2 --- Data Distribution --- p.12 / Chapter 2.1.3 --- Training Set Size --- p.14 / Chapter 2.1.4 --- Inter-Query Learning and Intra-Query Learning --- p.15 / Chapter 2.2 --- History of Relevance Feedback Techniques --- p.16 / Chapter 2.3 --- Relevance Feedback Approaches --- p.19 / Chapter 2.3.1 --- Vector Space Model --- p.19 / Chapter 2.3.2 --- Ad-hoc Re-weighting --- p.26 / Chapter 2.3.3 --- Distance Optimization Approach --- p.29 / Chapter 2.3.4 --- Probabilistic Model --- p.33 / Chapter 2.3.5 --- Bayesian Approach --- p.39 / Chapter 2.3.6 --- Density Estimation Approach --- p.42 / Chapter 2.3.7 --- Support Vector Machine --- p.48 / Chapter 2.4 --- Presentation Set Selection --- p.52 / Chapter 2.4.1 --- Most-probable strategy --- p.52 / Chapter 2.4.2 --- Most-informative strategy --- p.52 / Chapter 3 --- Biased Support Vector Machine for Content-Based Image Retrieval --- p.57 / Chapter 3.1 --- Motivation --- p.57 / Chapter 3.2 --- Background --- p.58 / Chapter 3.2.1 --- Regular Support Vector Machine --- p.59 / Chapter 3.2.2 --- One-class Support Vector Machine --- p.61 / Chapter 3.3 --- Biased Support Vector Machine --- p.63 / Chapter 3.4 --- Interpretation of parameters in BSVM --- p.67 / Chapter 3.5 --- Soft Label Biased Support Vector Machine --- p.69 / Chapter 3.6 --- Interpretation of parameters in Soft Label BSVM --- p.73 / Chapter 3.7 --- Relevance Feedback Using Biased Support Vector Machine --- p.74 / Chapter 3.7.1 --- Advantages of BSVM in Relevance Feedback . . --- p.74 / Chapter 3.7.2 --- Relevance Feedback Algorithm By BSVM --- p.75 / Chapter 3.8 --- Experiments --- p.78 / Chapter 3.8.1 --- Synthetic Dataset --- p.80 / Chapter 3.8.2 --- Real-World Dataset --- p.81 / Chapter 3.8.3 --- Experimental Results --- p.83 / Chapter 3.9 --- Conclusion --- p.86 / Chapter 4 --- Self-Organizing Map-based Inter-Query Learning --- p.88 / Chapter 4.1 --- Motivation --- p.88 / Chapter 4.2 --- Algorithm --- p.89 / Chapter 4.2.1 --- Initialization and Replication of SOM --- p.89 / Chapter 4.2.2 --- SOM Training for Inter-Query Learning --- p.90 / Chapter 4.2.3 --- Incorporate with Intra-Query Learning --- p.92 / Chapter 4.3 --- Experiments --- p.93 / Chapter 4.3.1 --- Synthetic Dataset --- p.95 / Chapter 4.3.2 --- Real-World Dataset --- p.95 / Chapter 4.3.3 --- Experimental Results --- p.97 / Chapter 4.4 --- Conclusion --- p.98 / Chapter 5 --- Conclusion --- p.102 / Bibliography --- p.104