Academic literature on the topic 'Structural approaches to representation'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the lists of relevant articles, books, theses, conference reports, and other scholarly sources on the topic 'Structural approaches to representation.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Journal articles on the topic "Structural approaches to representation"
1
Fasoulis, Romanos, Georgios Paliouras, and Lydia E. Kavraki. "Graph representation learning for structural proteomics." Emerging Topics in Life Sciences 5, no. 6 (October 19, 2021): 789–802. http://dx.doi.org/10.1042/etls20210225.
Full textAbstract:
The field of structural proteomics, which is focused on studying the structure–function relationship of proteins and protein complexes, is experiencing rapid growth. Since the early 2000s, structural databases such as the Protein Data Bank are storing increasing amounts of protein structural data, in addition to modeled structures becoming increasingly available. This, combined with the recent advances in graph-based machine-learning models, enables the use of protein structural data in predictive models, with the goal of creating tools that will advance our understanding of protein function. Similar to using graph learning tools to molecular graphs, which currently undergo rapid development, there is also an increasing trend in using graph learning approaches on protein structures. In this short review paper, we survey studies that use graph learning techniques on proteins, and examine their successes and shortcomings, while also discussing future directions.
2
Zhang, Kai Song, Luo Zhong, and Xuan Ya Zhang. "Image Restoration via Group l2,1 Norm-Based Structural Sparse Representation." International Journal of Pattern Recognition and Artificial Intelligence 32, no. 04 (December 13, 2017): 1854008. http://dx.doi.org/10.1142/s0218001418540083.
Full textAbstract:
Sparse representation has recently been extensively studied in the field of image restoration. Many sparsity-based approaches enforce sparse coding on patches with certain constraints. However, extracting structural information is a challenging task in the field image restoration. Motivated by the fact that structured sparse representation (SSR) method can capture the inner characteristics of image structures, which helps in finding sparse representations of nonlinear features or patterns, we propose the SSR approach for image restoration. Specifically, a generalized model is developed using structured restraint, namely, the group [Formula: see text]-norm of the coefficient matrix is introduced in the traditional sparse representation with respect to minimizing the differences within classes and maximizing the differences between classes for sparse representation, and its applications with image restoration are also explored. The sparse coefficients of SSR are obtained through iterative optimization approach. Experimental results have shown that the proposed SSR technique can significantly deliver the reconstructed images with high quality, which manifest the effectiveness of our approach in both peak signal-to-noise ratio performance and visual perception.
3
Gebser, Martin, Tomi Janhunen, and Jussi Rintanen. "Declarative encodings of acyclicity properties." Journal of Logic and Computation 30, no. 4 (September 8, 2015): 923–52. http://dx.doi.org/10.1093/logcom/exv063.
Full textAbstract:
Abstract Many knowledge representation tasks involve trees or similar structures as abstract datatypes. However, devising compact and efficient declarative representations of such structural properties is non-obvious and can be challenging indeed. In this article, we take a number of acyclicity properties into consideration and investigate various logic-based approaches to encode them. We use answer set programming as the primary representation language but also consider mappings to related formalisms, such as propositional logic, difference logic and linear programming. We study the compactness of encodings and the resulting computational performance on benchmarks involving acyclic or tree structures.
4
Wang, Yifei, Shiyang Chen, Guobin Chen, Ethan Shurberg, Hang Liu, and Pengyu Hong. "Motif-Based Graph Representation Learning with Application to Chemical Molecules." Informatics 10, no. 1 (January 11, 2023): 8. http://dx.doi.org/10.3390/informatics10010008.
Full textAbstract:
This work considers the task of representation learning on the attributed relational graph (ARG). Both the nodes and edges in an ARG are associated with attributes/features allowing ARGs to encode rich structural information widely observed in real applications. Existing graph neural networks offer limited ability to capture complex interactions within local structural contexts, which hinders them from taking advantage of the expression power of ARGs. We propose motif convolution module (MCM), a new motif-based graph representation learning technique to better utilize local structural information. The ability to handle continuous edge and node features is one of MCM’s advantages over existing motif-based models. MCM builds a motif vocabulary in an unsupervised way and deploys a novel motif convolution operation to extract the local structural context of individual nodes, which is then used to learn higher level node representations via multilayer perceptron and/or message passing in graph neural networks. When compared with other graph learning approaches to classifying synthetic graphs, our approach is substantially better at capturing structural context. We also demonstrate the performance and explainability advantages of our approach by applying it to several molecular benchmarks.
5
Joaristi, Mikel, and Edoardo Serra. "SIR-GN: A Fast Structural Iterative Representation Learning Approach For Graph Nodes." ACM Transactions on Knowledge Discovery from Data 15, no. 6 (May 19, 2021): 1–39. http://dx.doi.org/10.1145/3450315.
Full textAbstract:
Graph representation learning methods have attracted an increasing amount of attention in recent years. These methods focus on learning a numerical representation of the nodes in a graph. Learning these representations is a powerful instrument for tasks such as graph mining, visualization, and hashing. They are of particular interest because they facilitate the direct use of standard machine learning models on graphs. Graph representation learning methods can be divided into two main categories: methods preserving the connectivity information of the nodes and methods preserving nodes’ structural information. Connectivity-based methods focus on encoding relationships between nodes, with connected nodes being closer together in the resulting latent space. While methods preserving structure generate a latent space where nodes serving a similar structural function in the network are encoded close to each other, independently of them being connected or even close to each other in the graph. While there are a lot of works that focus on preserving node connectivity, only a few works focus on preserving nodes’ structure. Properly encoding nodes’ structural information is fundamental for many real-world applications as it has been demonstrated that this information can be leveraged to successfully solve many tasks where connectivity-based methods usually fail. A typical example is the task of node classification, i.e., the assignment or prediction of a particular label for a node. Current limitations of structural representation methods are their scalability, representation meaning, and no formal proof that guaranteed the preservation of structural properties. We propose a new graph representation learning method, called Structural Iterative Representation learning approach for Graph Nodes ( SIR-GN ). In this work, we propose two variations ( SIR-GN: GMM and SIR-GN: K-Means ) and show how our best variation SIR-GN: K-Means : (1) theoretically guarantees the preservation of graph structural similarities, (2) provides a clear meaning about its representation and a way to interpret it with a specifically designed attribution procedure, and (3) is scalable and fast to compute. In addition, from our experiment, we show that SIR-GN: K-Means is often better or, in the worst-case comparable than the existing structural graph representation learning methods present in the literature. Also, we empirically show its superior scalability and computational performance when compared to other existing approaches.
6
LLADÓS, JOSEP, MARÇAL RUSIÑOL, ALICIA FORNÉS, DAVID FERNÁNDEZ, and ANJAN DUTTA. "ON THE INFLUENCE OF WORD REPRESENTATIONS FOR HANDWRITTEN WORD SPOTTING IN HISTORICAL DOCUMENTS." International Journal of Pattern Recognition and Artificial Intelligence 26, no. 05 (August 2012): 1263002. http://dx.doi.org/10.1142/s0218001412630025.
Full textAbstract:
Word spotting is the process of retrieving all instances of a queried keyword from a digital library of document images. In this paper we evaluate the performance of different word descriptors to assess the advantages and disadvantages of statistical and structural models in a framework of query-by-example word spotting in historical documents. We compare four word representation models, namely sequence alignment using DTW as a baseline reference, a bag of visual words approach as statistical model, a pseudo-structural model based on a Loci features representation, and a structural approach where words are represented by graphs. The four approaches have been tested with two collections of historical data: the George Washington database and the marriage records from the Barcelona Cathedral. We experimentally demonstrate that statistical representations generally give a better performance, however it cannot be neglected that large descriptors are difficult to be implemented in a retrieval scenario where word spotting requires the indexation of data with million word images.
7
Zahnitko, Anatolii, Lubomira Hnatiuk, and Mariia Antonova. "Structural Configuration of the Text World Polymentality Representation." Studies about Languages 1, no. 40 (July 13, 2022): 5–16. http://dx.doi.org/10.5755/j01.sal.40.1.29962.
Full textAbstract:
The article highlights the problem of structural configuration of the representation of polymentality of the textual world. It focuses on the problem of polymentality (ambiguity) of the text. It is proposed to address it in the context of psycholinguistics and cognitive linguistics. On that ground, the study substantiates the figure-background relations as a necessary characteristic of the manifestation of the author's sensorics. Such an approach allows not only revealing cognitive mechanisms that underlie polymentality of the literary text but also systematizing the structural configuration of its representation. The dynamics of figure-background relations (as a way of cognition) is fully manifested in the author's sensorics, often performing certain communicative tasks. The identification of common mechanisms of specificity of the interaction of figure and background in the interpretation of text meaning promotes the use of psychological approaches. The last represent the process of formation and perception of a new meaning as a process of self-organization of a complex system. The results show that the problem of the structural configuration of the representation of the polymentality of the literary text can be solved through the psychological analysis of the author's sensory in terms of figure-background relations in the gestalt-psychological discourse.
8
Jinpa, Tenzin, and Yong Gao. "Code Representation Learning Using Prüfer Sequences (Student Abstract)." Proceedings of the AAAI Conference on Artificial Intelligence 36, no. 11 (June 28, 2022): 12977–78. http://dx.doi.org/10.1609/aaai.v36i11.21625.
Full textAbstract:
An effective and efficient encoding of the source code of a computer program is critical to the success of sequence-to-sequence deep neural network models for code representation learning. In this study, we propose to use the Prufer sequence of the Abstract Syntax Tree (AST) of a computer program to design a sequential representation scheme that preserves the structural information in an AST. Our representation makes it possible to develop deep-learning models in which signals carried by lexical tokens in the training examples can be exploited automatically and selectively based on their syntactic role and importance. Unlike other recently-proposed approaches, our representation is concise and lossless in terms of the structural information of the AST. Results from our experiment show that prufer-sequence-based representation is indeed highly effective and efficient.
9
Chaabane, Marwa, Majdi Mansouri, Kamaleldin Abodayeh, Ahmed Ben Hamida, Hazem Nounou, and Mohamed Nounou. "Effective fault detection in structural health monitoring systems." Advances in Mechanical Engineering 11, no. 9 (September 2019): 168781401987323. http://dx.doi.org/10.1177/1687814019873234.
Full textAbstract:
A new fault detection technique is considered in this article. It is based on kernel partial least squares, exponentially weighted moving average, and generalized likelihood ratio test. The developed approach aims to improve monitoring the structural systems. It consists of computing an optimal statistic that merges the current information and the previous one and gives more weight to the most recent information. To improve the performances of the developed kernel partial least squares model even further, multiscale representation of data will be used to develop a multiscale extension of this method. Multiscale representation is a powerful data analysis way that presents efficient separation of deterministic characteristics from random noise. Thus, multiscale kernel partial least squares method that combines the advantages of the kernel partial least squares method with those of multiscale representation will be developed to enhance the structural modeling performance. The effectiveness of the proposed approach is assessed using two examples: synthetic data and benchmark structure. The simulation study proves the efficiency of the developed technique over the classical detection approaches in terms of false alarm rate, missed detection rate, and detection speed.
10
Demidovskij, Alexander, and Eduard Babkin. "Adapting Neural Turing Machines for linguistic assessments aggregation in neural-symbolic decision support systems." Information and Control Systems, no. 5 (October 26, 2021): 40–50. http://dx.doi.org/10.31799/1684-8853-2021-5-40-50.
Full textAbstract:
Introduction: The construction of integrated neurosymbolic systems is an urgent and challenging task. Building neurosymbolic decision support systems requires new approaches to represent knowledge about a problem situation and to express symbolic reasoning at the subsymbolic level. Purpose: Development of neural network architectures and methods for effective distributed knowledge representation and subsymbolic reasoning in decision support systems in terms of algorithms for aggregation of fuzzy expert evaluations to select alternative solutions. Methods: Representation of fuzzy and uncertain estimators in a distributed form using tensor representations; construction of a trainable neural network architecture for subsymbolic aggregation of linguistic estimators. Results: The study proposes two new methods of representation of linguistic assessments in a distributed form. The first approach is based on the possibility of converting an arbitrary linguistic assessment into a numerical representation and consists in converting this numerical representation into a distributed one by converting the number itself into a bit string and further forming a matrix storing the distributed representation of the whole expression for aggregating the assessments. The second approach to translating linguistic assessments to a distributed representation is based on representing the linguistic assessment as a tree and coding this tree using the method of tensor representations, thus avoiding the step of translating the linguistic assessment into a numerical form and ensuring the transition between symbolic and subsymbolic representations of linguistic assessments without any loss of information. The structural elements of the linguistic assessment are treated as fillers with their respective positional roles. A new subsymbolic method of aggregation of linguistic assessments is proposed, which consists in creating a trainable neural network module in the form of a Neural Turing Machine. Practical relevance: The results of the study demonstrate how a symbolic algorithm for aggregation of linguistic evaluations can be implemented by connectionist (or subsymbolic) mechanisms, which is an essential requirement for building distributed neurosymbolic decision support systems.
Dissertations / Theses on the topic "Structural approaches to representation"
1
Wachelke, Joao. "Structural relations among social representations: cognem association within a representational system." Doctoral thesis, Università degli studi di Padova, 2010. http://hdl.handle.net/11577/3427383.
Full textAbstract:
Theory and research results about the structure of social representations have been built usually from the study of isolated representations. The studies aiming at identifying structural relations involving two or more representations are more recent. In the literature, different terms have been employed to refer to inter-related social representation sets, managed or not by a superior ideological stance; in those cases, we refer to representation families, systems or networks. In this context, there are coordination relations, in which associations can be identified at the same level of a social thinking architecture. Traditionally, the studies of representations in conjunction – presenting element intersections at the level of their cores or object labels – have been privileged. The present research aims at contributing to the knowledge about disjoint representations. When, at an inter-representation level, there are two or more representation structures linked by relations between cognems or between object-label words, we propose the name of representational system to the macrostructure that is formed, with relations formalized by the basic cognitive schemes model. The main research aim was to identify relations among elements of different social representations, submitting to test the existence of connection points among representations at the same level of the social thinking architecture. It is a model that conceives inter-representation relations at the level of cognems. All the studies concerned the investigation of a representational system including the social representation on aging. Most of the studies were conducted with university undergraduate samples from Padua, Italy – and Studies 1-A and 1-B also had a Brazilian sample of undergraduates and an Italian sample of elderly people. The first studies had the purpose of characterizing the representation system. After a preliminary qualitative study conducted with interviews with people from different age groups, which has allowed to identify the cognems of the social representation on aging, Studies 1-A and 1-B were comparative investigations that characterized the structural status of the elements of that representation and also structural differences linked to age groups and cultural context. Study 2 was a survey marked by paired evaluations of proximity between objects linked to the aging theme which allowed the identification of three social representations highly connected to aging, by means prototypical and similarity analyses: death, health and family. Study 3 had a mixed nature, with characteristics of both a quasi-experiment and a survey. It provided the characterization of the structures of the chosen social representations in the system and also assessed the intensity of relations between social objects in that system. Additionally, participants evaluated pairs of elements of the representation on aging and the other representations and indicated if they perceived a connection or not, enabling the identification of possible connection points. After the identification of those possible relationships, the focus shifted to testing the plausibility of a model for connection points including a bridge relation between those elements. Study 4 consisted of context manipulations of emphasis or relativization of a peripheral element of the social representation on health that was connected to elements from the social representation on aging. It was observed that a context change relative to a peripheral element of a representation interferes on the activation of schemes relative to a second representation, regardless of their structural status; it is a first empirical evidence of the validity of a theoretical conception of coordination relations involving disjoint representations of a same system by means of connection points. Finally, Studies 5-A and 5-B aimed at verifying if denying or confirming the information of cognems from connection points would be associated with activation differences of semantic and evaluative relations (bridge relations) with elements connected to them, from the representation on aging. Differences were identified in the sense that compatibility with the content of the manipulated cognem was associated with higher valences of at least one of the hyperconnectors. As a conclusion, evidence was found of relations among social representations at the level of their elements, and the conception of a theoretical model of inter-representation connection points presented promising results. The model contributes to the understanding of mechanisms of association of social representations in disjunction and also opens possibilities for application especially concerning social representation dynamics, which might also take representation systems into account.Le teorie e i risultati di ricerca sulla struttura delle rappresentazioni sociali sono stati costruiti, in generale, a partire dallo studio di rappresentazioni isolate. Gli studi volti a identificare le relazioni strutturali che coinvolgono due o più rappresentazioni sono più recenti. In letteratura, termini diversi sono stati impiegati per riferirsi a insiemi interconnessi di rappresentazioni sociali, gestiti o non da un’istanza ideologica superiore; in questi casi, ci riferiamo a famiglie, sistemi o reti di rappresentazioni. In questo contesto, vi sono relazioni di coordinamento, in cui le associazioni possono essere identificate allo stesso livello dell’architettura del pensiero sociale. Tradizionalmente, sono stati privilegiati gli studi di rappresentazioni in congiunzione, che presentano intersezioni di elementi al livello dei loro nuclei o etichette di oggetto. La presente ricerca si propone di contribuire alla conoscenza di rappresentazioni disgiunte. Quando, a livello inter-rappresentazione, ci sono due o più strutture legate da relazioni tra cognemi o tra etichette di oggetti, proponiamo il nome di sistema rappresentazionale per la macrostruttura che ne risulta, con relazioni formalizzate dal modello di schemi cognitivi di base. L'obiettivo principale della ricerca è consistito nell’identificazione di relazioni tra elementi di rappresentazioni sociali diverse, sottoponendo a prova l'esistenza di punti di connessione tra rappresentazioni allo stesso livello dell’architettura del pensiero sociale. Si tratta di un modello che concepisce le relazioni interrappresentazione al livello dei cognemi. Tutti i cinque studi condotti hanno coinvolto un sistema di rappresentazioni, tenendo la rappresentazione sociale dell’invecchiamento come punto di riferimento. La maggior parte degli studi è stata svolta con campioni di convenienza di studenti universitari di Padova, Italia. Gli Studi 1-A e 1-B hanno avuto anche un campione brasiliano di studenti e un campione italiano di anziani. I primi studi avevano lo scopo di caratterizzare il sistema rappresentazionale. Dopo un’indagine preliminare qualitativa condotta con interviste a persone di diverse fasce di età, la quale ha permesso di identificare i cognemi della rappresentazione sociale sull’invecchiamento, gli Studi 1-A e 1-B sono stati realizzati tramite ricerche comparative che hanno caratterizzato lo statuto strutturale degli elementi di quella rappresentazione e anche delle differenze strutturali legate a gruppi di età e contesti culturali diversi. Lo Studio 2 è consistito in una ricerca caratterizzata da valutazioni appaiate di prossimità tra oggetti legati al tema dell'invecchiamento, la quale ha permesso l'identificazione di tre rappresentazioni sociali altamente connesse all'invecchiamento attraverso analisi prototipiche e di similitudine: morte, salute e famiglia. Lo Studio 3 ha avuto un carattere misto, con caratteristiche sia di quasi-esperimento sia di survey. Ha fornito la caratterizzazione delle strutture delle rappresentazioni sociali scelte dal sistema ed anche permesso di valutare l'intensità delle relazioni tra oggetti sociali in quel sistema. Inoltre, i partecipanti hanno valutato le coppie di elementi della rappresentazione sull’invecchiamento e sugli altri tre oggetti e hanno indicato se percepivano una relazione o meno tra di loro, permettendo l’individuazione di possibili punti di connessione. Dopo l'individuazione delle relazioni possibili, l'attenzione è stata rivolta a verificare la plausibilità di un modello di punti di connessione tra elementi con una relazione ponte. Lo Studio 4 è consistito nella manipolazione di un elemento periferico della rappresentazione sociale della salute (tramite sua enfasi o relativizzazione), collegata ad elementi della rappresentazione sociale dell’ invecchiamento. E' stato osservato che un cambiamento di contesto rispetto ad un elemento periferico di una rappresentazione interferisce sull’attivazione di schemi relativi ad una seconda rappresentazione del sistema, indipendentemente dal suo statuto strutturale. Si tratta di una prima evidenza empirica della validità di una concezione teorica che sottolinea le relazioni di coordinamento fra rappresentazioni disgiunte in uno stesso sistema per mezzo di punti di connessione. Infine, gli Studi 5-A e 5-B avevano lo scopo di verificare se il negare o confermare le informazioni di cognemi in punti di connessione fosse associato a differenze di attivazione di relazioni semantiche e valutative (relazioni ponte) con elementi ad essi connessi, della rappresentazione dell’invecchiamento. Sono state individuate delle differenze, nel senso che una compatibilità con il contenuto del cognema manipolato è stata associata con valenze più alte di almeno uno degli iperconnettori. In conclusione, si sono trovate evidenze empiriche riguardo relazioni tra rappresentazioni sociali a livello dei loro elementi, e ha trovato sostegno, con risultati promettenti, la concezione di un modello teorico di punti di connessione tra rappresentazioni. Il modello conntribuisce alla comprensione dei meccanismi di associazione di rappresentazioni sociali in disgiunzione e apre anche la possibilità di applicazioni soprattutto per quanto riguarda le dinamiche delle rappresentazioni sociali, attraverso interventi mirati sui sistemi di rappresentazione presi in esame.
2
Alexander, Gutkin. "Towards formal structural representation of spoken language : an evolving transformation system (ETS) approach." Thesis, University of Edinburgh, 2006. http://hdl.handle.net/1842/3527.
Full textAbstract:
Speech recognition has been a very active area of research over the past twenty years. Despite an evident progress, it is generally agreed by the practitioners of the field that performance of the current speech recognition systems is rather suboptimal and new approaches are needed. The motivation behind the undertaken research is an observation that the notion of representation of objects and concepts that once was considered to be central in the early days of pattern recognition, has been largely marginalised by the advent of statistical approaches. As a consequence of a predominantly statistical approach to speech recognition problem, due to the numeric, feature vector-based, nature of representation, the classes inductively discovered from real data using decision-theoretic techniques have little meaning outside the statistical framework. This is because decision surfaces or probability distributions are difficult to analyse linguistically. Because of the later limitation it is doubtful that the gap between speech recognition and linguistic research can be bridged by the numeric representations. This thesis investigates an alternative, structural, approach to spoken language representation and categorisation. The approach pursued in this thesis is based on a consistent program, known as the Evolving Transformation System (ETS), motivated by the development and clarification of the concept of structural representation in pattern recognition and artificial intelligence from both theoretical and applied points of view. This thesis consists of two parts. In the first part of this thesis, a similarity-based approach to structural representation of speech is presented. First, a linguistically well-motivated structural representation of phones based on distinctive phonological features recovered from speech is proposed. The representation consists of string templates representing phones together with a similarity measure. The set of phonological templates together with a similarity measure defines a symbolic metric space. Representation and ETS-inspired categorisation in the symbolic metric spaces corresponding to the phonological structural representation are then investigated by constructing appropriate symbolic space classifiers and evaluating them on a standard corpus of read speech. In addition, similarity-based isometric transition from phonological symbolic metric spaces to the corresponding non-Euclidean vector spaces is investigated. Second part of this thesis deals with the formal approach to structural representation of spoken language. Unlike the approach adopted in the first part of this thesis, the representation developed in the second part is based on the mathematical language of the ETS formalism. This formalism has been specifically developed for structural modelling of dynamic processes. In particular, it allows the representation of both objects and classes in a uniform event-based hierarchical framework. In this thesis, the latter property of the formalism allows the adoption of a more physiologically-concreteapproach to structural representation. The proposed representation is based on gestural structures and encapsulates speech processes at the articulatory level. Algorithms for deriving the articulatory structures from the data are presented and evaluated.
3
Ling, Suiyi. "Perceptual representations of structural and geometric information in images : bio-inspired and machine learning approaches : application to visual quality assessment of immersive media." Thesis, Nantes, 2018. http://www.theses.fr/2018NANT4061/document.
Full textAbstract:
Ce travail vise à mieux évaluer la qualité perceptuelle des images contenant des distorsions structurelles et géométriques notamment dans le contexte de médias immersifs. Nous proposons et explorons un cadre algorithmique hiérarchique de la perception visuelle. Inspiré par le système visuel humain, nous investiguons plusieurs niveaux de représentations des images : bas niveau (caractéristiques élémentaires comme les segments), niveau intermédiaire (motif complexe, encodage de contours), haut niveau (abstraction et reconnaissance des données visuelles). La première partie du manuscrit traite des représentations bas niveau pour la structure et texture. U n modèle basé filtre bilatéral est d’abord introduit pour qualifier les rôles respectifs de l’information texturale et structurelle dans diverses tâches d’évaluation (utilité, qualité. . . ). Une mesure de qualité d’image/vidéo est proposée pour quantifier les déformations de structure spatiales et temporelles perçues en utilisant une métrique dite élastique. La seconde partie du mémoire explore les représentations de niveaux intermédiaires. Un modèle basé « schetch token » et un autre basé sur codage d’un arbre de contexte sont présentés pour évaluer la qualité perçue. La troisième partie traite des représentations haut niveau. Deux approches d’apprentissage machine sont proposées pour apprendre ces représentations : une basée sur un technique de convolutional sparse coding, l’autre sur des réseaux profonds de type generative adversarial network. Au long du manuscrit, plusieurs expériences sont menées sur différentes bases de données pour plusieurs applications (FTV, visualisation multi-vues, images panoramiques 360. . . ) ainsi que des études utilisateursThis work aims to better evaluate the perceptual quality of image/video that contains structural and geometric related distortions in the context of immersive multimedia. We propose and explore a hierarchical framework of visual perception for image/video. Inspired by representation mechanism of the visual system, low-level (elementary visual features, e.g. edges), mid-level (intermediate visual patterns, e.g. codebook of edges), and higher-level (abstraction of visual input, e.g. category of distorted edges) image/video representations are investigated for quality assessment. The first part of this thesis addresses the low-level structure and texture related representations. A bilateral filter-based model is first introduced to qualify the respective role of structure and texture information in various assessment tasks (utility, quality . . . ). An image quality/video quality measure is proposed to quantify structure deformation spatially and temporally using new elastic metric. The second part explores mid-level structure related representations. A sketch-token based model and a context tree based model are presented in this part for the image and video quality evaluation. The third part explores higher-level structure related representations. Two machine learning approaches are proposed to learn higher-level representation: a convolutional sparse coding based and a generative adversarial network. Along the thesis, experiments an user studies have been conducted on different databases for different applications where special structure related distortions are observed (FTV, multi-view rendering, omni directional imaging . . . )
4
Race, David Andrew. "Structural accounts of mathematical representation." Thesis, University of Leeds, 2014. http://etheses.whiterose.ac.uk/7123/.
Full textAbstract:
Attempts to solve the problems of the applicability of mathematics have gen- erally originated from the acceptance of a particular mathematical ontology. In this thesis I argue that a proper approach to solving these problems comes from an ‘application first’ approach. If one attempts to form the problems and answer them from a position that is agnostic towards mathematical ontology, the difficulties surrounding these problems fall away. I argue that there are nine problems that require answering, and that the problems of representation are the most interesting questions to answer. The applied metaphysical problem can be answered by structural relations, which are adopted as the starting point for accounts of representation. The majority of the thesis concerns arguing in favour of structural accounts of representation, in particular deciding between the Inferential Conception of the Applicability of Mathematics and Pincock’s Mapping Account. Through the case study of the rainbow, I argue that the Inferential Conception is the more viable account. It is capable of answering all of the problems of the applicability of mathematics, while the methodology adopted by Pincock trivialises the answer it can supply to the vital question of how the faithfulness and usefulness of representations are related.
5
Tayar, Memduh Ali. "Design approaches to structural optimization." Thesis, Massachusetts Institute of Technology, 1986. http://hdl.handle.net/1721.1/78067.
Full textAbstract:
Thesis (M.S.)--Massachusetts Institute of Technology, Dept. of Architecture, 1986.MICROFICHE COPY AVAILABLE IN ARCHIVES AND ROTCH.
Includes bibliographical references (leaves 84-86).
The objective of this thesis is to develop design approaches to structural optimization. In the example of three-dimensional grid structures, widely known as 'space frames', possible configurations are explored which maximize the load-bearing capacity of the system in relation to its weight. The study has been organized in two chapters: The first chapter starts with a brief review of structural concepts. Along with Gothic as a historical example to optimization, modem analytical methods to optimal structural design are presented which include Maxwell's Lemma, Michell's Fields and Ultimate Strength Analysis. In the second part of the thesis the design solutions are presented. The emphasis lies on a deployable space frame which is based on bar-joist like elements.
by Memduh Ali Tayar.
M.S.
6
Herraiz, Cobo Jesús. "Mayotlide: synthetic approaches and structural elucidation." Doctoral thesis, Universitat de Barcelona, 2017. http://hdl.handle.net/10803/462881.
Full textAbstract:
Mayotlide is a marine peptide isolated by PharmaMar S.A. from Spongia sp.. The sequence of the aminoacids were achieved by MS-MS spectrometry, where two of them were tryptophans. The NMR spectroscopy revealed the presence of N1-C3a bond between the tryptophans, which means that one of them was cyclized. On the first structure proposal, the aminoacids were forming two macrocyclic rings: on the ring B, all the aminoacids of molecule were tied by amide bond, remarking the presence of the cyclized tryptophan as a hexahydropyrroloindole unit (HPI). The ring A was established by three aminoacids of the ring B: one tryptophan, one isoleucine and the HPI, which became closed by the N1-C3a bond between the two tryptophans. The aminoacid analysis demonstrated the L configuration of all of them, just remaining the HPI with unknown stereochemistry.
Due to the configuration of the HPI system, there can be four diasteromers. To the best of our knowledge, there were not empirical evidences about which one could be more favorable. Hence, a computational study of the ring A through the MOE program was performed, evidencing that the rings A with the exo HPI adducts (L and D) were more stable than the endo ones. Among the exo ones, another computational study with the whole molecule revealed that the mayotlide with the exo-L adduct of the HPI was more stable.
Once that there was established a starting point with the HPI, it was necessary to find out a synthetic strategy that could fulfill the necessary requirements. A methodology developed by Baran and coworkers for the synthesis of the Trp-HPI fragment on molecules related to mayotlide was adapted to our proposal. On the first step of this strategy, under reaction conditions, the starting tryptophan cyclizes, providing exclusively the HPI with the exo configuration, at the same time that the N1-C3a bond between the HPI and 2-iodoaniline is formed. The 2-iodoaniline, along with a disubstituted alkyne, condense together yielding the upper tryptophan without loss of the former stereochemistry, reaching the Trp-HPI framework in two steps with high yields.
Taking advantage of this methodology and an appropriate use of the protecting groups in order to perform the corresponding cyclizations of the two macrocyclic rings, the mayotlide with the exo-L HPI was accomplished. Nevertheless, nor the NMR neither the MS-MS fragmentation pattern of the final compound coincided with the natural product ones. Thus, the next alternative would consist on repeating the synthesis but with the exo-D adduct of the HPI instead.
During the last synthesis, the bibliography and the analytical data of the natural product were extensively revised. There were no documented precedents of natural peptides with the Trp- HPI motif, and the initial structure did not justify the most important data extracted from the MS-MS spectrometry. the main fragmentation concerned to the isoleucine, and on the first proposal such aminoacid was not forming part of a conflictive scaffold. Likewise, among the eight proposed linear sequences for the ring B, the isoleucine just appear in one as C-terminus of the b-ions, when it is one of the aminoacids that forms part of both macrocycles.
The most related family of peptides to mayotlide are the kapakahines. Kapakahines, instead of having a Trp-HPI moiety as the central part of the molecule, exhibit a Trp-α carboline, with an
aminoacid establishing the bridge for a very tensioned tetracyclic system. Such structure may justify the isoleucine fragmentation pattern, but on the other hand the sequence of the aminoacids did not fix. It was necessary to invert the central sequence of the aminoacids to reach out a final structure proposal which justifies all the requirements, relabeled as “kapakahine H”.La mayotlida es un producto natural de origen marino aislado por PharmaMar. SA.. En la primera propuesta que se hizo, se elucidó como un péptido con dos anillos macrocíclicos: en el anillo B estaban contenidos todos los aminoácidos de la molécula, destacando la presencia de una unidad de HPI, que procede de la ciclación intramolecular del extremo amino de un triptófano con el C2 del anillo de indol. El anillo A está formado por tres aminoácidos del anillo B: un triptófano, una isoleucina y el HPI, quedando cerrado por la formación de un enlace entre el N1 del triptófano y el C3a del HPI. El análisis de aminoácidos demostró la configuración L de todos ellos, quedando desconocida la estereoquímica del HPI. El HPI posee tres estereocentros: los C3a y C8a, que siempre están en cis por la propia configuración del anillo y se pueden considerar como un conjunto, y el estereocentro del Cα. Por tanto, son cuatro el número total de diasterómeros posibles. El anillo A con las cuatro posibilidades de HPI fue estudiado energéticamente con el programa MOE, llegando a la conclusión que los aductos exo son más estables que los endo, y que el aducto exo-L es más estable que el exo-D. Para abordar la síntesis de la mayotlida exo-L se adaptó una metodología desarrollada por Phil Baran y colaboradores para moléculas con una estructura relacionada a la mayotlida. Tras conseguir la síntesis de la mayotlida con el aducto exo-L del HPI, se comprueba que los espectros de RMN y de MS-MS presentan grandes divergencias. Ante la incapacidad de interpretar las diferencias existentes entre el producto natural y la mayotlida exo-L, se tomó la decisión de abordar la síntesis de la mayotlida con el aducto exo-D del HPI. En el transcurso de la síntesis exo-D se revisó extensivamente la bibliografía y los datos analíticos relacionados con la mayotlida: no existían antecedentes de productos naturales peptídicos con estructura Trp-HPI, y la estructura no encajaba con los datos más transcendentales del MS-MS. La estructura fue revisada, llegando a la conclusión de que podía pertenecer a la familia de las kapakahines, con una estructura central Trp-α carbolina y con la secuencia central de los aminoácidos invertida, rebautizada como kapakahina H.
7
Yu, Xun. "3D Face Recognition Based on Structural Representation." Thesis, Griffith University, 2017. http://hdl.handle.net/10072/365949.
Full textAbstract:
3D face recognition has gained favour in the scientific community and industry due to the rapid development and decreasing cost of 3D sensors, with various novel techniques for face recognition presented in recent years. In comparison to 2D face images, 3D face images contain more explicit information, which is very useful to manage pose and illumination problems. However, the field of 3D face recognition is yet to fully mature and become widely used in industrial or commercial communities, mainly because of high error in non-cooperative and uncontrolled scenarios—particularly in challenging conditions of occlusions and partial data. Further, many existing 3D face recognition techniques require a training stage in their approach, which can suffer dramatic performance drop or even fail to work if only one training sample per person is available to the system. Thus, the one training sample issue is an important factor hindering the performance of 3D face recognition systems. In this thesis, we propose several 3D face recognition approaches to address the above issues. In the first half of this thesis, we propose two low-level structural representations 3D polygonal line chains (3DPLC) and 3D directional vertices (3D2V) to encode and match 3D faces.Thesis (PhD Doctorate)
Doctor of Philosophy (PhD)
Griffith School of Engineering
Science, Environment, Engineering and Technology
Full Text
8
Delli, Ponti Riccardo 1987. "Approaches to characterize structural properties of RNA." Doctoral thesis, Universitat Pompeu Fabra, 2019. http://hdl.handle.net/10803/665962.
Full textAbstract:
The secondary structure of an RNA molecule is fundamental for its function. However, structural conservation and the structure of RNA in vivo are still poorly understood. Data from recent high-throughput experiments can provide new insights, but they have not yet been systematically exploited. The aim of my doctoral studies was to exploit these experimental data to develop computational approaches for discovering and analyzing structural properties of RNA. I developed two algorithms: CROSS predicts the secondary structure propensity profile of an RNA, and CROSSalign discovers structural similarities among different RNAs. In addition, I studied the effect of the presence of protein binding motifs on the prediction of the RNA structure, in vivo and investigated how the propensity of RNAs to bind to proteins could be exploited to create a predictive tool. The suite of tools that I developed opens new possibilities for studying the structural properties of long RNA molecules and for investigating structural conservation in large-scale analyses.La estructura secundaria del ARN es fundamental para su función. Sin embargo, la conservación estructural y la estructura del ARN in vivo son poco conocidas. Los datos provenientes de experimentos de alto rendimiento pueden proporcionar nuevos conocimientos, pero aun no han sido usados sistemáticamente. El objetivo de mis estudios de doctorado fue emplear estos datos experimentales con el fin de desarrollar metodos computacionales para el descubrimiento y el analisis de las propiedades estructurales del ARN. Como resultado de mi tesis desarrollé dos algoritmos: CROSS, que predice el perfil de propensión de estructura secundaria de un ARN; y CROSSalign, que busca similitudes estructurales entre diferentes ARNs. Además, estudié el efecto de la presencia de dominios de unión protéinica en la predicción de la estructura del ARN in vivo; e investigué como la propensión de los ARNs a unirse a las proteínas podría usarse para crear un modelo predictivo. El conjunto de herramientas que desarrollé abre nuevas posibilidades para estudiar las propiedades estructurales de moléculas de ARN largas y para investigar la conservación estructural en análisis a gran escala.
9
Giger, Mathias. "Representation concepts in evolutionary algorithm-based structural optimization /." Zürich : ETH, 2006. http://e-collection.ethbib.ethz.ch/show?type=diss&nr=17017.
Full text
10
De, Boyrie Maria Eugenia. "Out-of-sample exchange rate forecasting structural and non-structural nonlinear approaches." FIU Digital Commons, 1994. http://digitalcommons.fiu.edu/etd/2727.
Full textAbstract:
Forecasting foreign exchange rates is a perennial dilemma for exporters, importers, foreign exchange rate traders, and the business community as a whole. Foreign exchange rate models using popular linear and non-linear specifications do not produce particularly accurate forecasts. In point of fact, these models have not improved much upon the random walk model, especially in out-of-sample forecasting. Given these results, this dissertation constructs and evaluates new forecasting models to generate as accurate as possible out-of-sample forecasts of foreign exchange rates.
The information content of futures contracts on foreign exchange rates is investigated and used to forecast future exchange rates using alternative techniques, both structural (econometric) and non-structural (fuzzy) models. The results of two specifications of a structural model are compared against the well-known random walk model. The first specification assumes future exchange rates are determined by futures prices and a lagged structure of spot rates. The second specification assumes that future spot rates are a function of only a lagged structure of the futures prices.
The forecasting accuracy of the models is tested for both in-sample and out-of-sample periods; out-of-sample tests range from the short term to the long term (30- to 180-day forecasts). The results indicate that the random walk model remains a competitive alternative. In out-of-sample predictions, however, we can improve upon it in certain cases. The results also show that the predictive accuracy of the models is better in the short term (30 to 60 days) than in the longer term (180 days).
Books on the topic "Structural approaches to representation"
1
India) International Congress of Mathematicians Satellite Conference on Algebraic and Combinatorial Approaches to Representation Theory (2010 Bangalore. Recent developments in algebraic and combinatorial aspects of representation theory: International Congress of Mathematicians Satellite Conference on Algebraic and Combinatorial Approaches to Representation Theory, August 12-16, 2010, National Institute of Advanced Studies, Bangalore, India : Conference on Algebraic and Combinatorial Approaches to Representation Theory, May 18-20, 2012, University of California, Riverside, CA. Edited by Chari, Vyjayanthi, editor of compilation and Conference on Algebraic and Combinatorial Approaches to Representation Theory (2012 : Riverside, Calif.). Providence, Rhode Island: American Mathematical Society, 2013.
Find full text
2
Hugh, Clapin, Staines Phillip James, and Slezak Peter P. 1947-, eds. Representation in mind: New approaches to mental representation. Amsterdam: Elsevier, 2004.
Find full text
3
Linguistic representation: Structural analogy and stratification. Berlin: Mouton de Gruyter, 1992.
Find full text
4
Bastolla, Ugo, Markus Porto, H. Eduardo Roman, and Michele Vendruscolo, eds. Structural Approaches to Sequence Evolution. Berlin, Heidelberg: Springer Berlin Heidelberg, 2007. http://dx.doi.org/10.1007/978-3-540-35306-5.
Full text
5
1957-, Insam Heribert, and Rangger Andrea 1966-, eds. Microbial communities: Functional versus structural approaches. Berlin: Springer, 1997.
Find full text
6
Stroud, Robert, and Janet Finer-Moore, eds. Computational and Structural Approaches to Drug Discovery. Cambridge: Royal Society of Chemistry, 2007. http://dx.doi.org/10.1039/9781847557964.
Full text
7
Pattern recognition: Statistical, structural, and neural approaches. New York: J. Wiley, 1992.
Find full text
8
Center, Langley Research, ed. Further generalization of an equivalent plate representation for aircraft structural analysis. Hampton, Va: National Aeronautics and Space Administration, Langley Research Center, 1987.
Find full text
9
R, Calladine C., Drew Horace R, and Pellegrino S, eds. New approaches to structural mechanics, shells, and biological structures. Boston: Kluwer Academic Publishers, 2002.
Find full text
10
Katherine, Beissner, and Yacci Michael, eds. Structural knowledge: Techniques for representing, conveying, and acquiring structural knowledge. Hillsdale, N.J: L. Erlbaum, 1993.
Find full textBook chapters on the topic "Structural approaches to representation"
1
Arrivault, Denis, Noël Richard, Christine Fernandez-Maloigne, and Philippe Bouyer. "Collaboration Between Statistical and Structural Approaches for Old Handwritten Characters Recognition." In Graph-Based Representations in Pattern Recognition, 291–300. Berlin, Heidelberg: Springer Berlin Heidelberg, 2005. http://dx.doi.org/10.1007/978-3-540-31988-7_28.
Full text
2
Delalandre, Mathieu, Éric Trupin, and Jean-Marc Ogier. "Symbols Recognition System for Graphic Documents Combining Global Structural Approaches and Using a XML Representation of Data." In Lecture Notes in Computer Science, 425–33. Berlin, Heidelberg: Springer Berlin Heidelberg, 2004. http://dx.doi.org/10.1007/978-3-540-27868-9_45.
Full text
3
Qin, Zhen-tao, Wu-nian Yang, Xiao-pin Wu, and Ru Yang. "Hyperspectral Image Classification Using a New Dictionary Learning Approach with Structured Sparse Representation." In Geostatistical and Geospatial Approaches for the Characterization of Natural Resources in the Environment, 719–22. Cham: Springer International Publishing, 2016. http://dx.doi.org/10.1007/978-3-319-18663-4_109.
Full text
4
Wilson, Katy M., Jane W. Baldwin, and Rachel M. Young. "Estimating Tropical Cyclone Vulnerability: A Review of Different Open-Source Approaches." In Hurricane Risk in a Changing Climate, 255–81. Cham: Springer International Publishing, 2022. http://dx.doi.org/10.1007/978-3-031-08568-0_11.
Full textAbstract:
AbstractTropical cyclone (TC) risk assessments are critical for disaster preparedness and response. Alongside hazard and exposure, accurate TC risk assessment requires understanding the vulnerability of populations and assets. In this chapter, we examine multiple methods that have been used to assess and quantify TC vulnerability with a focus on open-source methods. We separately discuss structural, economic, and social (or demographic) vulnerability approaches. Structural vulnerability assesses the susceptibility of buildings to be affected by their exposure to hazards; in this section, we provide a detailed overview of how FEMA’s Hazus model quantifies damages by utilizing engineering principles. Economic vulnerability employs regression analysis to relate wind speeds to damages; this discussion explores typical functional forms used to represent vulnerability in such analysis and efforts to constrain parameters in these functions. Finally, social approaches use demographic data to characterize the varying susceptibility of populations to TC risk; we provide some representative examples of this methodology. We conclude with a comparative discussion of these three classes of methods, suggest directions for future work, and ask whether the different approaches can be combined to yield a more holistic view of both the human and structural aspects of TC vulnerability.
5
Myers, Robert S. R., Stefan Milius, and Henning Urbat. "Nondeterministic Syntactic Complexity." In Lecture Notes in Computer Science, 448–68. Cham: Springer International Publishing, 2021. http://dx.doi.org/10.1007/978-3-030-71995-1_23.
Full textAbstract:
AbstractWe introduce a new measure on regular languages: their nondeterministic syntactic complexity. It is the least degree of any extension of the ‘canonical boolean representation’ of the syntactic monoid. Equivalently, it is the least number of states of any subatomic nondeterministic acceptor. It turns out that essentially all previous structural work on nondeterministic state-minimality computes this measure. Our approach rests on an algebraic interpretation of nondeterministic finite automata as deterministic finite automata endowed with semilattice structure. Crucially, the latter form a self-dual category.
6
Boothe, Brigitte. "Die Unergründlichkeit der Traummitteilung und die Unabschließbarkeit der Deutung." In Edition Kulturwissenschaft, 91–110. Bielefeld, Germany: transcript Verlag, 2021. http://dx.doi.org/10.14361/9783839459287-009.
Full textAbstract:
In this article Rainer J. Kaus devotes himself to a reading of Freud's foundational work, The Interpretation of Dreams, as structural hermeneutics. The task is to show that Freud's »dream-work« comprising 1) the work of condensation, 2) the work of displacement, 3) the dream's means of representation and 4) secondary processing, amounts to an implicit structural hermeneutics. This approach is shown to be the opposite of merely associative, arbitrary interpretation of texts and interrelated human actions and also to be related to literary hermeneutics. However, psychoanalysis encompasses also a negative hermeneutics of the repressed.
7
Santosh, K. C. "Structural Approaches." In Document Image Analysis, 81–119. Singapore: Springer Singapore, 2018. http://dx.doi.org/10.1007/978-981-13-2339-3_5.
Full text
8
Jackson, William A. "Structural approaches." In Markets, 79–100. Abingdon, Oxon; New York, NY: Routledge, 2019. |: Routledge, 2019. http://dx.doi.org/10.4324/9781315676593-6.
Full text
9
Ahad, Md Atiqur Rahman. "Action Representation Approaches." In Atlantis Ambient and Pervasive Intelligence, 39–76. Paris: Atlantis Press, 2011. http://dx.doi.org/10.2991/978-94-91216-20-6_3.
Full text
10
Lima-De-Faria, J. "Representation of crystal structures." In Structural Mineralogy, 52–62. Dordrecht: Springer Netherlands, 1994. http://dx.doi.org/10.1007/978-94-015-8392-3_6.
Full textConference papers on the topic "Structural approaches to representation"
1
Gopal, Kreshna, James C. Sacchettini, and Thomas R. Ioerger. "Database Approaches and Data Representation in Structural Bioinformatics." In 2007 IEEE 7th International Symposium on BioInformatics and BioEngineering. IEEE, 2007. http://dx.doi.org/10.1109/bibe.2007.4375597.
Full text
2
Chapman, Colin D., Kazuhiro Saitou, and Mark J. Jakiela. "Genetic Algorithms As an Approach to Configuration and Topology Design." In ASME 1993 Design Technical Conferences. American Society of Mechanical Engineers, 1993. http://dx.doi.org/10.1115/detc1993-0338.
Full textAbstract:
Abstract The Genetic Algorithm, a search and optimization technique based on the theory of natural selection, is applied to problems of structural topology optimization. Given a structure’s boundary conditions and maximum allowable design domain, a discretized design representation is created. Populations of genetic algorithm “chromosomes” are then mapped into the design representation, creating potentially optimal structure topologies. Utilizing genetics-based operators such as crossover and mutation, generations of increasingly-desirable structure topologies are created. In this paper, the use of the genetic algorithm (GA) in structural topology optimization is presented. An overview of the genetic algorithm will describe the genetics-based representations and operators used in a typical genetic algorithm search. After defining topology optimization and its relation to the broader area of structural optimization, a review of previous research in GA-based and non-GA-based structural optimization is provided. The design representations, and methods for mapping genetic algorithm “chromosomes” into structure topology representations, are then detailed. Several examples of genetic algorithm-based structural topology optimization are provided: we address the optimization of beam cross-section topologies and cantilevered plate topologies, and we also investigate efficient techniques for using finite element analysis in a genetic algorithm-based search. Finally, a description of potential future work in genetic algorithm-based structural topology optimization is offered.
3
Dumancic, Sebastijan, and Hendrik Blockeel. "Clustering-Based Relational Unsupervised Representation Learning with an Explicit Distributed Representation." In Twenty-Sixth International Joint Conference on Artificial Intelligence. California: International Joint Conferences on Artificial Intelligence Organization, 2017. http://dx.doi.org/10.24963/ijcai.2017/226.
Full textAbstract:
The goal of unsupervised representation learning is to extract a new representation of data, such that solving many different tasks becomes easier. Existing methods typically focus on vectorized data and offer little support for relational data, which additionally describes relationships among instances. In this work we introduce an approach for relational unsupervised representation learning. Viewing a relational dataset as a hypergraph, new features are obtained by clustering vertices and hyperedges. To find a representation suited for many relational learning tasks, a wide range of similarities between relational objects is considered, e.g. feature and structural similarities. We experimentally evaluate the proposed approach and show that models learned on such latent representations perform better, have lower complexity, and outperform the existing approaches on classification tasks.
4
Kong, Fang, and Fu Jian. "Incorporating Structural Information for Better Coreference Resolution." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/700.
Full textAbstract:
Coreference resolution plays an important role in text understanding. In the literature, various neural approaches have been proposed and achieved considerable success. However, structural information, which has been proven useful in coreference resolution, has been largely ignored in previous neural approaches. In this paper, we focus on effectively incorporating structural information to neural coreference resolution from three aspects. Firstly, nodes in the parse trees are employed as a constraint to filter out impossible text spans (i.e., mention candidates) in reducing the computational complexity. Secondly, contextual information is encoded in the traversal node sequence instead of the word sequence to better capture hierarchical information for text span representation. Lastly, additional structural features (e.g., the path, siblings, degrees, category of the current node) are encoded to enhance the mention representation. Experimentation on the data-set of the CoNLL 2012 Shared Task shows the effectiveness of our proposed approach in incorporating structural information into neural coreference resolution.
5
Atia, Mohamed, Ahmed Abdelkhalek, Anjan Sarkar, Matt Keys, Mahesh Patel, Mohammed Eissa, and Tarek Omar. "Reliability Based Structural Risk Assessments and Associated Economic Gains." In Abu Dhabi International Petroleum Exhibition & Conference. SPE, 2021. http://dx.doi.org/10.2118/207810-ms.
Full textAbstract:
Abstract Managing a large fleet of offshore structures is a dynamic process that aims at minimising risks to personnel, environment, and businesses, as well as minimising the associated Operations Expenditure. Through the collaborative efforts of ADNOC Offshore and Kent, formerly Atkins Oil & Gas, (Atkins, 2020), revised structural evaluation and integrity approaches have yielded significant cost savings. The considerable savings were associated with the elimination of the requirement for installing many new offshore structures and through reducing the subsea inspection associated efforts. The approach for evaluating the offshore assets’ structural performance was developed based on adopting target probability of failure figures subject to each asset's consequence of failure. Accordingly, structural reliability analyses were conducted specific to each structure, where the analysis considered structure specific environmental hazard curves and failure surfaces. Through mapping the evaluated structural probability of failure and ADNOC's corporate risk matrix's HSE Likelihood, each structure was precisely placed on the risk matrix. Furthermore, the inspection intervals and Topsides, Splash Zone, Subsea Levels I, II and III were mapped to each risk evaluation on the risk matrix. The optimisation approach of adopting a structure specific reliability analysis and mapping with ADNOC's corporate risk matrix yielded considerable cost benefits while providing a more accurate representation of each asset's risk. As a result of the implementation of the developed process, approximately 41% of the assets got lower risk evaluation compared to the legacy approach and presented extra structural capacities that can be utilised for future expansions and eliminating the requirement for installation of new assets. As the process expanded to include asset inspections, the subsea inspection requirements reduced by approximately 43% reflecting a considerable decrease in operating costs. A major contribution of the risk improvement is attributed to the consideration of the storm prevailing approach directions, the joint probability of wave and current magnitudes and directions, as well as the relative alignment of each structure. The developed approaches provide a framework that allows continuous update of the risk assessment and enables executives and management to make risk-based-decision supported by a consistent measure of structural risk. This has been translated into the generation of the Structural Passports (Summary reports) clearly demonstrating the assets current risk and recommendations for mitigation measures, if deemed required.
6
Jung, Sangjin, Timothy W. Simpson, and Oyku Asikoglu. "Using Interfaces to Drive Module Definition: Investigating the Impact of a New Design Dependency Measure." In ASME 2014 International Design Engineering Technical Conferences and Computers and Information in Engineering Conference. American Society of Mechanical Engineers, 2014. http://dx.doi.org/10.1115/detc2014-34555.
Full textAbstract:
Structural representations for interfaces between modules and components in a product vary widely in the literature. After reviewing several structural approaches to interface definition, a new weighted design dependency measure is described. The new representation takes into account both six different types of interfaces as well as their relative strength and frequency within a product architecture. The resulting design dependency measure provides a means for designers to quantify the change resistance in a product. In this paper, we investigate the use of this new design dependency measure to drive module identification. Specifically, we compare the resulting modules obtained by optimizing Design Structure Matrices (DSMs) using standard 0-1 representations of the interfaces to those obtained using the new design dependency measure. The results indicate that the weighted design dependency measure leads to more a logical definition of modules that maximizes within module dependencies and minimizes interactions between modules.
7
Lee, Chung-Yeon, Youngjae Yoo, and Byoung-Tak Zhang. "PlaceNet: Neural Spatial Representation Learning with Multimodal Attention." In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/144.
Full textAbstract:
Spatial representation capable of learning a myriad of environmental features is a significant challenge for natural spatial understanding of mobile AI agents. Deep generative models have the potential of discovering rich representations of observed 3D scenes. However, previous approaches have been mainly evaluated on simple environments, or focused only on high-resolution rendering of small-scale scenes, hampering generalization of the representations to various spatial variability. To address this, we present PlaceNet, a neural representation that learns through random observations in a self-supervised manner, and represents observed scenes with triplet attention using visual, topographic, and semantic cues. We evaluate the proposed method on a large-scale multimodal scene dataset consisting of 120 million indoor scenes, and show that PlaceNet successfully generalizes to various environments with lower training loss, higher image quality and structural similarity of predicted scenes, compared to a competitive baseline model. Additionally, analyses of the representations demonstrate that PlaceNet activates more specialized and larger numbers of kernels in the spatial representation, capturing multimodal spatial properties in complex environments.
8
Guan, Sheng, Hanchao Ma, and Yinghui Wu. "RoboGNN: Robustifying Node Classification under Link Perturbation." In Thirty-First International Joint Conference on Artificial Intelligence {IJCAI-22}. California: International Joint Conferences on Artificial Intelligence Organization, 2022. http://dx.doi.org/10.24963/ijcai.2022/420.
Full textAbstract:
Graph neural networks (GNNs) have emerged as powerful approaches for graph representation learning and node classification. Nevertheless, they can be vulnerable (sensitive) to link perturbations due to structural noise or adversarial attacks. This paper introduces RoboGNN, a novel framework that simultaneously robustifies an input classifier to a counterpart with certifiable robustness, and suggests desired graph representation with auxiliary links to ensure the robustness guarantee. (1) We introduce (p,θ)-robustness, which characterizes the robustness guarantee of a GNN-based classifier if its performance is insensitive for at least θ fraction of a targeted set of nodes under any perturbation of a set of vulnerable links up to a bounded size p. (2) We present a co-learning framework that interacts model learning with graph structural learning to robustify an input model M to a (p,θ)-robustness counterpart. The framework also outputs the desired graph structures that ensure the robustness. Using real-world benchmark graphs, we experimentally verify that roboGNN can effectively robustify representative GNNs with guaranteed robustness, and desirable gains on accuracy.
9
Li, Yu, Ying Wang, Tingting Zhang, Jiawei Zhang, and Yi Chang. "Learning Network Embedding with Community Structural Information." In Twenty-Eighth International Joint Conference on Artificial Intelligence {IJCAI-19}. California: International Joint Conferences on Artificial Intelligence Organization, 2019. http://dx.doi.org/10.24963/ijcai.2019/407.
Full textAbstract:
Network embedding is an effective approach to learn the low-dimensional representations of vertices in networks, aiming to capture and preserve the structure and inherent properties of networks. The vast majority of existing network embedding methods exclusively focus on vertex proximity of networks, while ignoring the network internal community structure. However, the homophily principle indicates that vertices within the same community are more similar to each other than those from different communities, thus vertices within the same community should have similar vertex representations. Motivated by this, we propose a novel network embedding framework NECS to learn the Network Embedding with Community Structural information, which preserves the high-order proximity and incorporates the community structure in vertex representation learning. We formulate the problem into a principled optimization framework and provide an effective alternating algorithm to solve it. Extensive experimental results on several benchmark network datasets demonstrate the effectiveness of the proposed framework in various network analysis tasks including network reconstruction, link prediction and vertex classification.
10
Ganian, Robert, Tomáš Peitl, Friedrich Slivovsky, and Stefan Szeider. "Fixed-Parameter Tractability of Dependency QBF with Structural Parameters." In 17th International Conference on Principles of Knowledge Representation and Reasoning {KR-2020}. California: International Joint Conferences on Artificial Intelligence Organization, 2020. http://dx.doi.org/10.24963/kr.2020/40.
Full textAbstract:
We study dependency quantified Boolean formulas (DQBF), an extension of QBF in which dependencies of existential variables are listed explicitly rather than being implicit in the order of quantifiers. DQBF evaluation is a canonical NEXPTIME-complete problem, a complexity class containing many prominent problems that arise in Knowledge Representation and Reasoning. One approach for solving such hard problems is to identify and exploit structural properties captured by numerical parameters such that bounding these parameters gives rise to an efficient algorithm. This idea is captured by the notion of fixed-parameter tractability (FPT). We initiate the study of DQBF through the lens of fixed-parameter tractability and show that the evaluation problem becomes FPT under two natural parameterizations: the treewidth of the primal graph of the DQBF instance combined with a restriction on the interactions between the dependency sets, and also the treedepth of the primal graph augmented by edges representing dependency sets.
Reports on the topic "Structural approaches to representation"
1
Yan, Yujie, and Jerome F. Hajjar. Automated Damage Assessment and Structural Modeling of Bridges with Visual Sensing Technology. Northeastern University, May 2021. http://dx.doi.org/10.17760/d20410114.
Full textAbstract:
Recent advances in visual sensing technology have gained much attention in the field of bridge inspection and management. Coupled with advanced robotic systems, state-of-the-art visual sensors can be used to obtain accurate documentation of bridges without the need for any special equipment or traffic closure. The captured visual sensor data can be post-processed to gather meaningful information for the bridge structures and hence to support bridge inspection and management. However, state-of-the-practice data postprocessing approaches require substantial manual operations, which can be time-consuming and expensive. The main objective of this study is to develop methods and algorithms to automate the post-processing of the visual sensor data towards the extraction of three main categories of information: 1) object information such as object identity, shapes, and spatial relationships - a novel heuristic-based method is proposed to automate the detection and recognition of main structural elements of steel girder bridges in both terrestrial and unmanned aerial vehicle (UAV)-based laser scanning data. Domain knowledge on the geometric and topological constraints of the structural elements is modeled and utilized as heuristics to guide the search as well as to reject erroneous detection results. 2) structural damage information, such as damage locations and quantities - to support the assessment of damage associated with small deformations, an advanced crack assessment method is proposed to enable automated detection and quantification of concrete cracks in critical structural elements based on UAV-based visual sensor data. In terms of damage associated with large deformations, based on the surface normal-based method proposed in Guldur et al. (2014), a new algorithm is developed to enhance the robustness of damage assessment for structural elements with curved surfaces. 3) three-dimensional volumetric models - the object information extracted from the laser scanning data is exploited to create a complete geometric representation for each structural element. In addition, mesh generation algorithms are developed to automatically convert the geometric representations into conformal all-hexahedron finite element meshes, which can be finally assembled to create a finite element model of the entire bridge. To validate the effectiveness of the developed methods and algorithms, several field data collections have been conducted to collect both the visual sensor data and the physical measurements from experimental specimens and in-service bridges. The data were collected using both terrestrial laser scanners combined with images, and laser scanners and cameras mounted to unmanned aerial vehicles.
2
Norris, Adele. Thesis review: The storytellers: Identity narratives by New Zealand African youth – participatory visual methodological approach to situating identity, migration and representation by Makanaka Tuwe. Unitec ePress, October 2018. http://dx.doi.org/10.34074/thes.revw4318.
Full textAbstract:
This fascinating and original work explores the experiences of third-culture children of African descent in New Zealand. The term ‘third-culture kid’ refers to an individual who grows up in a culture different from the culture of their parents. Experiences of youth of African descent is under-researched in New Zealand. The central research focus explores racialised emotions internalised by African youth that are largely attributed to a lack of positive media representation of African and/or black youth, coupled with daily experiences of micro-aggressions and structural racism. In this respect, the case-study analysis is reflective of careful, methodological and deliberative analysis, which offers powerful insights into the grass-roots strategies employed by African youth to resist negative stereotypes that problematise and marginalise them politically and economically.
3
Tarr, Michael J., and David J. Kriegman. Computational Approaches to Human Shape Representation. Fort Belvoir, VA: Defense Technical Information Center, December 1994. http://dx.doi.org/10.21236/ada298894.
Full text
4
Salata, Steven E., and Clive L. Dym. Representation of Strategic Choices in Structural Modeling. Fort Belvoir, VA: Defense Technical Information Center, June 1990. http://dx.doi.org/10.21236/ada226437.
Full text
5
McDougall, Cynthia, Lone Badstue, Annet Mulema, Gundula Fischer, Dina Najjar, Rhiannon Pyburn, Marlène Elias, Deepa Joshi, and Andrea Vos. Toward structural change: Gender transformative approaches. Washington, DC: International Food Policy Research Institute, 2021. http://dx.doi.org/10.2499/9780896293915_10.
Full text
6
Lutz, Carsten. Interval-based Temporal Reasoning with General TBoxes. Aachen University of Technology, 2000. http://dx.doi.org/10.25368/2022.109.
Full textAbstract:
Aus der Motivation: Description Logics (DLs) are a family of formalisms well-suited for the representation of and reasoning about knowledge. Whereas most Description Logics represent only static aspects of the application domain, recent research resulted in the exploration of various Description Logics that allow to, additionally, represent temporal information, see [4] for an overview. The approaches to integrate time differ in at least two important aspects: First, the basic temporal entity may be a time point or a time interval. Second, the temporal structure may be part of the semantics (yielding a multi-dimensional semantics) or it may be integrated as a so-called concrete domain. Examples for multi-dimensional point-based logics can be find in, e.g., [21;29], while multi-dimensional interval-based logics are used in, e.g., [23;2]. The concrete domain approach needs some more explanation. Concrete domains have been proposed by Baader and Hanschke as an extension of Description Logics that allows reasoning about 'concrete qualities' of the entities of the application domain such as sizes, length, or weights of real-worlds objects [5]. Description Logics with concrete domains do usually not use a fixed concrete domain; instead the concrete domain can be thought of as a parameter to the logic. As was first described in [16], if a 'temporal' concrete domain is employed, then concrete domains may be point-based, interval-based, or both.
7
Fair, Ray. Does Monetary Policy Matter? Narrative Versus Structural Approaches. Cambridge, MA: National Bureau of Economic Research, July 1989. http://dx.doi.org/10.3386/w3045.
Full text
8
Heckman, James. Building Bridges Between Structural and Program Evaluation Approaches to Evaluating Policy. Cambridge, MA: National Bureau of Economic Research, June 2010. http://dx.doi.org/10.3386/w16110.
Full text
9
Lew, J. Y., D. W. Cannon, D. P. Magee, and W. J. Book. Structural vibration control of micro/macro-manipulator using feedforward and feedback approaches. Office of Scientific and Technical Information (OSTI), September 1995. http://dx.doi.org/10.2172/115635.
Full text
10
Dodele, Kathryn. Approaches to composition in selected directing texts: a structural analysis and assessment. Portland State University Library, January 2000. http://dx.doi.org/10.15760/etd.2467.
Full text