Gotowa bibliografia na temat „Classification de documents Inter-modaux”

This article introduces a new advanced tri-layered segmentation and bi-leveled-classifier-based Hindi printed document classification system, which categorizes imaged documents into pre-defined mutually exclusive categories by using SVM and Fuzzy matching at character and document classifications, respectively. During training, the improved and noise-free image is segmented into lines and words by profiling. Then it obtains Shirorekha Less (SL) isolated characters along with upper, left and right modifier components from the SL words. These components use their locations and inter character-modifier component distance to get associate with their corresponding characters only. Further, confidence values of all characters are calculated with SVM training and all characters are mapped into Romanized labels to generate the words. Finally, documents are classified by Fuzzy based matching of Romanized detected words and predefined classes. The average execution times of SL characters are 0.22675 sec. and 0.20375 sec. and classification accuracy are 74.61% and 80.73% for training and testing, respectively.

TREC text documents are complex to analyze the features its relevant similar documents using the traditional document similarity measures. As the size of the TREC repository is increasing, finding relevant clustered documents from a large collection of unstructured documents is a challenging task. Traditional document similarity and classification models are implemented on homogeneous TREC data to find essential features for document entities that are similar to the TREC documents. Also, most of the traditional models are applicable to limited text document sets for text analysis. The main issues in the traditional text mining models in TREC repository include :1) Each document is represented in vector form with many sparsity values 2) Failed to find the document semantic similarity between the intra and inter clusters 3) High mean squared error rate. In this paper, novel feature selection based clustered and classification model is proposed on large number of different TREC repositories. Traditional latent Semantic Indexing and document clustering models are failed to find the topic relevance on large number of TREC clinical text document sets due to computational memory and time. Proposed document feature selection and clustered based classification model is applied on TREC clinical benchmark datasets. From the experimental results, it is proved that the proposed model is efficient than the existing models in terms of computational memory, accuracy and error rate are concerned.

Nowadays, a large number of information can not be reached by the reader because of the misclassification of text-based documents. The misclassified data can also make the readers obtain the wrong information. The method which is proposed by this paper is aiming to classify the documents into the correct group. Each document will have a membership value in several different classes. The method will be used to find the degree of similarity between the two documents is the semantic similarity. In fact, there is no document that doesn’t have a relationship with the other but their relationship might be close to 0. This method calculates the similarity between two documents by taking into account the level of similarity of words and their synonyms. After all inter-document similarity values obtained, a matrix will be created. The matrix is then used as a semi-supervised factor. The output of this method is the value of the membership of each document, which must be one of the greatest membership value for each document which indicates where the documents are grouped. Classification result computed by the method shows a good value which is 90 %. Index Terms - Fuzzy co-clustering, Heuristic, Semantica Similiarity, Semi-supervised learning.

Clustering is one of the most significant research area in the field of data mining and considered as an important tool in the fast developing information explosion era.Clustering systems are used more and more often in text mining, especially in analyzing texts and to extracting knowledge they contain. Data are grouped into clusters in such a way that the data of the same group are similar and those in other groups are dissimilar. It aims to minimizing intra-class similarity and maximizing inter-class dissimilarity. Clustering is useful to obtain interesting patterns and structures from a large set of data. It can be applied in many areas, namely, DNA analysis, marketing studies, web documents, and classification. This paper aims to study and compare three text documents clustering, namely, k-means, k-medoids, and SOM through F-measure.

For the last two decades, various studies on determining the quality of online product reviews have been concerned with the classification of complete documents into helpful or unhelpful classes using supervised learning methods. As in any supervised machine-learning task, a manually annotated corpus is required to train a model. Corpora annotated for helpful product reviews are an important resource for the understanding of what makes online product reviews helpful and of how to rank them according to their quality. However, most corpora for helpfulness are annotated on the document level: the full review. Little attention has been paid to carrying out a deeper analysis of helpful comments in reviews. In this article, a new annotation scheme is proposed to identify helpful sentences from each product review in the dataset. The annotation scheme, guidelines and the inter-annotator agreement scores are presented and discussed. A high level of inter-annotator agreement is obtained, indicating that the annotated corpus is suitable to support subsequent research.

This article argues and documents that diasporic networking and guanxi relationships in North Sulawesi Province in East Indonesia are not essential for doing business within the Chinese business community. The main argument forwarded is that guanxi governed business networks are but one strategy among several other business strategies employed, when engaging in inter-ethnic and intra-ethnic business transactions. Furthermore, a discussion of the relationship between local Chinese and non-Chinese business environment as well as of the inter-ethnic environment in general constitutes a framework for how to position the Chinese in an overall societal context. Of special interest in this connection are questions of inter-ethnic integration versus assimilation together with questions of descent and ethnic classification in the relation to the surrounding non-Chinese community.

The article considers the experience of classification documents of the territorial planning and management of urban agglomerations in the Russian Federation. We have analyzed the documents of the federal level the main aim of which is regulating the processes of formation and development of agglomerations in the country. The documents developed in the regions over the past ten years, which regulate the functioning of all Russian urban agglomerations including laws, concepts, strategies, territorial planning schemes, inter-municipal agreements, and regulations on the activities of coordination councils are considered in detail. A comparative analysis of the documents allowed us to group agglomerations according to the degree of representation of the regulatory and documentary basis. There are five groups of agglomerations that differ in the number of documents and the degree of elaboration of agglomeration issues. The results revealed a significant gap between the selected groups. For agglomerations of the first and second groups we have prepared the complete sets of documentation, which reflect sufficiently the main parameters of agglomerations as integral system formations. For agglomerations included in the fourth group, there are no special documents, there are also some relevant materials in the regional documents of strategic and territorial planning which are characterized by poor elaboration. Agglomerations of the fifth group are not provided with regulatory documents at all, they are not considered as special formations. The analysis can contribute to improving the methodology of agglomeration development, understanding the need to expand and improve approaches to the management of urban agglomerations as integral objects. It is obvious that the urgent problem of sustainable development and functioning of urban agglomerations is the need to develop an innovative management model, its coordination with the regulatory framework of regional management structures, and a clear definition of conceptual and terminological and spatial-structural parameters.

Extractive text summarization selects the most important sentences from a document, preserves their original meaning, and produces an objective and fact-based summary. It is faster and less computationally intensive than abstract summarization techniques. Learning cross-sentence relationships is crucial for extractive text summarization. However, most of the language models currently in use process text data sequentially, which makes it difficult to capture such inter-sentence relations, especially in long documents. This paper proposes an extractive summarization model based on the graph neural network (GNN) to address this problem. The model effectively represents cross-sentence relationships using a graph-structured document representation. In addition to sentence nodes, we introduce two nodes with different granularity in the graph structure, words and topics, which bring different levels of semantic information. The node representations are updated by the graph attention network (GAT). The final summary is obtained using the binary classification of the sentence nodes. Our text summarization method was demonstrated to be highly effective, as supported by the results of our experiments on the CNN/DM and NYT datasets. To be specific, our approach outperformed baseline models of the same type in terms of ROUGE scores on both datasets, indicating the potential of our proposed model for enhancing text summarization tasks.

This article examines land privatization in late nineteenth-century Ottoman Palestine through the extension of possession in miri lands, on the one hand, and its transformation into fee-simple property through change in land category classification (i.e., miri to mülk), on the other. Using primary sources, particularly Ottoman documents and correspondence of the German Consulate in Jerusalem, we analyze this process, as reflected in several cases involving foreign subjects and Ottoman authorities. We argue that privatization began as informal violations of the law, proceeded with the struggle of landholders against authorities who tried to reverse the process, and ended in victory for the landholders after the state ceded to their demands, inter alia, as a result of pressure from foreign nations and their consuls. Thus did de facto land privatization become de jure privatization.

Les modèles développés dans cette thèse sont le résultat d'un processus itératif d'analyse et de synthèse entre les théories existantes et nos études réalisées. Plus spécifiquement, nous souhaitons étudier l'apprentissage inter-modal pour la compréhension contextualisée sur les composants des documents à travers le langage et la vision. Cette thèse porte sur l'avancement de la recherche sur l'apprentissage inter-modal et apporte des contributions sur quatre fronts : (i) proposer une approche inter-modale avec des réseaux profonds pour exploiter conjointement les informations visuelles et textuelles dans un espace de représentation sémantique commun afin d'effectuer et de créer automatiquement des prédictions sur les documents multimodaux; (ii) à étudier des stratégies concurrentielles pour s'attaquer aux tâches de classification de documents intermodaux, de récupération basée sur le contenu et de classification few-shot de documents ; (iii) pour résoudre les problèmes liés aux données comme l'apprentissage lorsque les données ne sont pas annotées, en proposant un réseau qui apprend des représentations génériques à partir d'une collection de documents non étiquetés ; et (iv) à exploiter les paramètres d'apprentissage few-shot lorsque les données ne contiennent que peu d’exemples
The frameworks developed in this thesis were the outcome of an iterative process of analysis and synthesis between existing theories and our performed studies. More specifically, we wish to study cross-modality learning for contextualized comprehension on document components across language and vision. The main idea is to leverage multimodal information from document images into a common semantic space. This thesis focuses on advancing the research on cross-modality learning and makes contributions on four fronts: (i) to proposing a cross-modal approach with deep networks to jointly leverage visual and textual information into a common semantic representation space to automatically perform and make predictions about multimodal documents (i.e., the subject matter they are about); (ii) to investigating competitive strategies to address the tasks of cross-modal document classification, content-based retrieval and few-shot document classification; (iii) to addressing data-related issues like learning when data is not annotated, by proposing a network that learns generic representations from a collection of unlabeled documents; and (iv) to exploiting few-shot learning settings when data contains only few examples

L’analyse de mesures longitudinales –appelées trajectoires– est de plus en plus fréquente en recherche médicale. L’un des intérêts de cette analyse est d’identifier des groupes d’individus ayant des trajectoires similaires. La classification obtenue peut être utilisée pour mieux comprendre l’hétérogénéité des évolutions entre individus. La classification peut être déterminée à partir d’un modèle pour lequel les trajectoires des individus correspondent à la trajectoire du groupe auquel ils sont affectés. L’objectif de la thèse est de développer une extension de ce modèle de classification standard permettant une meilleure prise en compte de la variabilité au sein des groupes, (i) variabilité des valeurs du marqueur (variance résiduelle) et (ii) variabilité des profils d’évolution (variance inter-individuelle). Deux modèles de classification sont développés : 1) un premier modèle qui prend en compte une variance résiduelle au sein de chaque groupe variable d’un groupe à l’autre, et 2) un deuxième modèle qui prend en compte une variabilité des trajectoires au sein des groupes au lieu de de prédire la même trajectoire pour tous les individus d’un même groupe, variabilité qui peut être identique ou variable d’un groupe à l’autre. L’intérêt de ces deux modèles a été montré par des travaux de simulations et par des applications cliniques. Globalement, lorsque le nombre de mesures et de trajectoires est suffisant, ces modèles donnent de meilleures classifications que celles du modèle de classification standard. Par ailleurs, en dehors de plans expérimentaux très contrôlés, les deux sources de variabilité sont inhérentes à la recherche en santé. Ces modèles sont donc très pertinents d’un point de vue clinique
The analysis of longitudinal measures –called trajectories– is more and more frequent in clinical research. One of the interests of this analysis is to identify groups of individuals with similar trajectories. The obtained classification is used to understand and explore the heterogeneity of trajectories among subjects. The classification can be performed by a model that predicts the same trajectory for all the subjects that are classified in the same group. The objective of this thesis is to develop an extension to the standard classification model that gives greater consideration to the variability within groups, (i) the variability of marker values (residual variance), and (ii) the variability of the individual trajectories inside a group (between-individual variance). Two classification models were developed: 1) a first model that allows unequal residual variance across groups, and 2) a second model that takes into account a between-individual variance within each group instead of predicting the same trajectory for all subjects in the same group, a variance that can be equal or unequal across groups. The interest of these two models has been studied by simulations and through clinical applications. Overall, when the number of trajectories and measurements per trajectory is sufficient, these models gives better classification compared to the standard classification model. Moreover, except for highly controlled experimental designs, the two sources of variability are inherent to research in health. Therefore, these models are very relevant from a clinical point of view

L’avènement des aimants permanents et les progrès récents dans l’électronique de puissance ont joué un rôle majeur dans l’évolution de la motorisation électrique des véhicules. Actuellement, les machines synchrones à aimants permanents (MSAP) grâce à leurs performances, et surtout leur efficacité énergétique, sont considérées comme les candidats idéaux pour les chaînes de traction des véhicules hybrides et électriques. Toutefois, en raison du vieillissement des matériaux, des défauts de fabrication ou des conditions de fonctionnement assez sévères, différents types de défauts sont capables de survenir dans les composants de la machine, ses organes de commande ou de mesure. Pour répondre aux exigences de sûreté, de fiabilité et de disponibilité, l’intégration d’une approche de surveillance et de diagnostic de défauts, dans le groupe motopropulseur électrique automobile, devient de plus en plus primordiale. Dans ce contexte, l’objectif de la thèse est de contribuer au diagnostic et à la caractérisation de défauts dans la MSAP par une analyse vibratoire. En premier temps, des approches analytiques de modélisation de la MSAP et des défauts : de court-circuit inter-spires, d’excentricité et de démagnétisation rotoriques serontproposées. L’intérêt majeur de tels modèles, dans le cadre du diagnostic, est d’étudier le comportement de la machine en présence de défauts étudiés afin d’en déduire les méthodes de détection les plus adaptées. En outre, des modèles numériques seront développés afin de les confronter aux parties magnétique et mécanique analytiques de la machine ainsi qu’au défaut de démagnétisation. Dans la phase d’analyse des impacts de défauts, nous allons nous focaliser sur les cas d’excentricité et de démagnétisation rotoriques. Les indicateurs de défauts seront extraits des représentations du signal vibratoire dans le temps et l’espace et de leurs transformées de Fourier, pour les cas de défauts simples et les cas de deux défauts combinés. Pour les cas simples, deux approches de localisation seront proposées : la première utilise le principe de tests statistiques et de tables de signatures, inspirée des méthodes de diagnostic à base de modèles, alors que la deuxième repose sur un banc de trois réseaux de neurones, où chacun est à une entrée et une sortie et destiné à localiser un type de défaut. Enfin, les performances des deux approches, en termes de robustesse et d’adaptabilité, seront comparées pour les mêmes ensembles de seuillage/d’apprentissage et de test
The advent of new magnetic materials and recent advances in power electronics have played a major role in the progress of hybrid electric vehicles. Nowadays, permanent magnet synchronous machines (PMSM) thanks to their performances, especially their energy efficiency, are considered as ideal candidates for the traction chains of hybrid and electric vehicles. However, due to material aging, manufacturing defects or severe operating conditions, different types of faults are capable to occur in the machine components, its control or measuring devices. In order to ensure safety, reliability and availability, the integration of a fault diagnosis and condition monitoring approach in the automotive electrical powertrain system is becoming more and more important. In this context, the aim of the thesis is to contribute to the diagnosis and characterization of faults in the PMSM based on a vibration analysis. First, analytical modeling approaches for the PMSM and inter-turn short-circuits, eccentricity and rotor demagnetization faults will be proposed. The major interest of such models, in a diagnosis context, is to study the behavior of the machine in the presence of studied faults in order to deduce the most suitable detection methods. In addition, numerical models will be developed in order to validate the analytical magnetic and mechanical parts of the machine as well as the demagnetization fault. In the phase of fault impact analysis, we will focus on the cases of rotor eccentricity and demagnetization. The fault indicators will be extracted from the vibratory signal representations in time and space domains and their Fourier transforms, in the cases of single faults and the cases of two combined faults. For single fault cases, two diagnosis approaches will be proposed: the first uses the principle of statistical tests and fault signature tables, inspired by model-based diagnosis methods, while the second relies on a set of three neural networks, such as each one is with a single input and a single output and dedicated to isolate one type of fault. Finally, the performance of these two approaches, in terms of robustness and adaptability, will be compared for the same training and test sets

AbstractThe history of macroeconometric model-building is comprehensively documented in Fair (1984, 1994), Bodkin et al. (1991), Hendry and Mizon (2000), Favero (2001), Pagan (2003a, b), Bårdsen et al. (2004, 2005), Valadkhani (2004), Hendry and Muellbauer (2018), Jelić and Ravnik (2021) inter alia. Also, history and macroeconometric modeling activities over the world and their classification are documented in Welfe (2013).

Inter-religious dialogue is expected to increasingly take on the form of online creative conversations that rely on digital data and documents. The first part of this chapter is about the current symbolic obstacles on the road to cultural and religious “intercomprehension” in this context: mainly the incompatibility and the cultural biases of classification systems. To overcome these obstacles (and some others), the authors propose using IEML (Information Economy MetaLanguage), a computable language specially suited to the online intercultural dialogue that was developed at the Canada Research Chair in collective intelligence at the University of Ottawa. The second and main part of this chapter presents some examples of the application of basic IEML categories to the religious domain.

The general principles developed during the latter part of the twentieth century and continued into the twenty-first century guiding support for people with intellectual disabilities remain those of social inclusion and the provision of services to enable people to make, as far is possible, their own choices and to participate as full citizens in society. These are articulated in national policy documents, such as the White Paper for England, ‘Valuing people and also at an international level in the UN Declaration on the rights of people with disability. However, given that people with intellectual disabilities represent a highly complex and heterogenous group with very varied needs, in order for such objectives to be achieved, a range of community based support and interagency and inter-disciplinary collaboration is required. It is acknowledged that people with intellectual disabilities experience considerable health inequalities with the presence of additional disabilities due to the presence of physical and sensory impairments and co-morbid physical and mental ill-health, much of which goes unrecognized, and also the occurrence of behaviours that impact on their lives and the lives of those supporting them. In the twenty-first century, few would now challenge the objectives of social inclusion and community support. The tasks for Government and society are to provide special educational support in childhood and also support to the families of children with intellectual disabilities, and the necessary range of services to meet the social and health needs of this diverse group of people in their adult life. This includes enabling adults with intellectual disabilities to gain meaningful support or full employment and to exercise their rights as citizens and to participate fully in society. To achieve such objectives there is a need to be able to characterize the nature and level of need, to establish the presence and significance of co-morbid illnesses and/or challenging behaviours, and to organize and provide support and services to meet such identified needs. This complexity of need has meant that no single ‘label’, such as ‘intellectual disability’, can adequately describe this group of people. What individuals have in common is a difficulty in the acquisition of basic living, educational, and social skills that is apparent early in life, together with evidence of a significant intellectual impairment. However, for some this may be of such severity that, for example, meaningful language is never acquired and there are very substantial care needs. For others, there is the presence of subtle signs of early developmental delay, and evidence of learning difficulties that only becomes clearly apparent at school when there is an expectation that more sophisticated skills will be acquired. The nature and extent of disability and of any functional impairments in general, distinguishing those people with intellectual disabilities from those with specific learning difficulties, such as dyslexia. In infancy and early childhood, the reason for any apparent developmental delay needs to be established. This is primarily the responsibility of paediatric and clinical genetic services. Such information helps parents understand the reasons for their child's difficulties and may guide, in a limited way, an understanding of future needs and potential risks. Later in childhood, the nature and extent of a child's learning difficulties and a statement of special educational needs is the main task and later still, the main focus may be the assessment of longer-term social care needs. Throughout life, there may also be questions about a child's or adult's behaviour or mental state or the nature and extent of physical or sensory impairments and disabilities. The role of assessment is essentially to determine need and to inform the types of intervention and treatments, whether educational, medical, psychological, or social, which are likely to be effective and of benefit to the person concerned. Systems of classification provide useful frameworks for such assessments.

Document classification is an essential task in many real world applications. Existing approaches adopt both text semantics and document structure to obtain the document representation. However, these models usually require a large collection of annotated training instances, which are not always feasible, especially in low-resource settings. In this paper, we propose a multi-task learning framework to jointly train multiple related document classification tasks. We devise a hierarchical architecture to make use of the shared knowledge from all tasks to enhance the document representation of each task. We further propose an inter-attention approach to improve the task-specific modeling of documents with global information. Experimental results on 15 public datasets demonstrate the benefits of our proposed model.