Search

The settling of drilling cuttings is important for the drilling and clean-out operations. The current article provides a Computational Fluid Dynamics (CFD) modeling study of particle settling behavior during the drilling operations, with a special focus on the impact of fluid rheology, flow regime, particle size and shape on the settling rate. The Eulerian-Lagrangian method are adopted to track particle trajectories in a shear-thinning fluid under quiescent conditions. The rheological properties of the drilling fluids are described by different rheological models. Settling of spherical and ellipsoidal cuttings, with various aspect ratios, is studied for particles with a diameter ranging between 2 and 6 mm. The settling behavior is predicted for particles with narrow (0.5–2 mm), medium (0.5–6 mm) and broad (0.5–10 mm) particle size distributions (PSD). Applying a non-Newtonian power-law model at low shear rates, where the fluid is in the Newtonian regime, resulted in 11–19% over-prediction of settling velocities as compared to the experimental data. On the other hand, ignoring the particle-induced shear rate by assuming a Newtonian fluid behavior in the transition regime showed 8–10% difference between the estimated and experimental settling rates. Therefore, the CFD computations of settling rates suggest that Cross and Carreau models provide more accurate predictions than a simple power-law model. The selection of the suitable rheological model is a key factor in predicting settling in drilling fluids. This is more important for small particles where the Newtonian behavior is dominant and particle-induced shear rate is low. Ellipsoidal cuttings exhibited significantly greater resistance to settling as compared to spherical particles, mainly due to the increased drag force. Further, the terminal settling velocity of ellipsoidal cuttings consistently increased with the particle aspect ratio. Cuttings with broad PSD showed ~32 times higher settling velocity than particles with narrow PSD. CFD results are validated with experimental measurements. Moreover, results for settling of non-spherical particles are validated with an empirical correlation. Agreement of experimental and theoretical predictions is observed when the fluid and flow regimes are well identified and described This work was made possible by the support of a National Priorities Research Program (NPRP) grant from the Qatar National Research Fund (QNRF), grant reference number NPRP11S-1228?170140. The statements made herein are solely the responsibility of the authors. The authors would like to acknowledge Qatar National Library (QNL) for providing open access to this article. Scopus

Smart health systems improve the efficiency of healthcare infrastructures and biomedical systems by integrating information and technology into health and medical practices. However, reliability, scalabilty and latency are among the many challenges hindering the realization of next-generation healthcare. In fact, with the exponential increases in the volume of patient data being produced and processed, many healthcare system' are being overwhelmed with the deluge of data they are facing. Many systems have been proposed to improve the system latency and scalability. However, there are concerns related to some of theses systems regarding the increasing levels of required human interaction which impact their efficiency. Recently, machine learning techniques are gaining a lot of interest in health applications as they exhibit fast processing with realtime predictions. In this paper, we propose a new healthcare system to reduce the waiting time in emergency department and improve the network scalability in any distributed system. The proposed model integrates the power of edge computing with machine learning techniques for providing a good quality of healthcare services. The machine learning algorithm is used to generate a classifier that can predict with high levels of accuracy the likelyhood of a patient to have a heart attack using his physiological signals ECG. The proposed system stores the patient data in a centralized database and generates a unique index using a new data-dependent Indexing algorithm that transforms the patient data into unique code to be sent for any medical data exchange. Multiple machine learning algorithms are studied and the best algorithm will be selected based on efficient performance result for the prediction of heart attack problem. simulation results show that the proposed model can effectively detect the abnormal heart beats with 91% using SVM algorithm. We show also that the proposed system outperforms conventional indexing algorithm systems in terms of collisions rate. 2020 IEEE. Qatar National Research Fund Scopus

In this paper we propose a novel action tube extractor for RGB-D action recognition in trimmed videos. The action tube extractor takes as input a video and outputs an action tube. The method consists of two parts: spatial tube extraction and temporal sampling. The first part is built upon MobileNet-SSD and its role is to define the spatial region where the action takes place. The second part is based on the structural similarity index (SSIM) and is designed to remove frames without obvious motion from the primary action tube. The final extracted action tube has two benefits: 1) a higher ratio of ROI (subjects of action) to background; 2) most frames contain obvious motion change. We propose to use a two-stream (RGB and Depth) I3D architecture as our 3D-CNN model. Our approach outperforms the state-of-the-art methods on the OA and NTU RGB-D datasets. © 2018 IEEE.

Conference of 16th IEEE International Conference on Computer Vision Workshops, ICCVW 2017 ; Conference Date: 22 October 2017 Through 29 October 2017; Conference Code:134301; International audience; When textual annotations of Web and social media images are poor or missing, content-based image retrieval is an interesting way to access them. Finding an optimal trade-off between accuracy and scalability for CBIR is challenging in practice. We propose a retrieval method whose complexity is nearly independent of the collection scale and does not degrade results quality. Images are represented with sparse semantic features that can be stored as an inverted index. Search complexity is drastically reduced by (1) considering the query feature dimensions independently and thus turning search into a concatenation operation and (2) pruning the index in function of a retrieval objective. To improve precision, the inverted index look-up is complemented with an exhaustive search over a fixed size list of intermediary results. We run experiments with three public collections and results show that our much faster method slightly outperforms an exhaustive search done with two competitive baselines.

Given a string S, the compressed indexing problem is to preprocess S into a compressed representation that supports fast substring queries. The goal is to use little space relative to the compressed size of S while supporting fast queries. We present a compressed index based on the Lempel–Ziv 1977 compression scheme. We obtain the following time–space trade-offs: For constant-sized alphabets (i) O ( m + occ lg ⁡ lg ⁡ n ) time using O ( z lg ⁡ ( n / z ) lg ⁡ lg ⁡ z ) space, or (ii) O ( m ( 1 + lg ϵ ⁡ z lg ⁡ ( n / z ) ) + occ ( lg ⁡ lg ⁡ n + lg ϵ ⁡ z ) ) time using O ( z lg ⁡ ( n / z ) ) space, For integer alphabets polynomially bounded by n (iii) O ( m ( 1 + lg ϵ ⁡ z lg ⁡ ( n / z ) ) + occ ( lg ⁡ lg ⁡ n + lg ϵ ⁡ z ) ) time using O ( z ( lg ⁡ ( n / z ) + lg ⁡ lg ⁡ z ) ) space, or (iv) O ( m + occ ( lg ⁡ lg ⁡ n + lg ϵ ⁡ z ) ) time using O ( z ( lg ⁡ ( n / z ) + lg ϵ ⁡ z ) ) space, where n and m are the length of the input string and query string respectively, z is the number of phrases in the LZ77 parse of the input string, occ is the number of occurrences of the query in the input and ϵ > 0 is an arbitrarily small constant. In particular, (i) improves the leading term in the query time of the previous best solution from O ( m lg ⁡ m ) to O ( m ) at the cost of increasing the space by a factor lg ⁡ lg ⁡ z . Alternatively, (ii) matches the previous best space bound, but has a leading term in the query time of O ( m ( 1 + lg ϵ ⁡ z lg ⁡ ( n / z ) ) ) . However, for any polynomial compression ratio, i.e., z = O ( n 1 − δ ) , for constant δ > 0 , this becomes O ( m ) . Our index also supports extraction of any substring of length l in O ( l + lg ⁡ ( n / z ) ) time. Technically, our results are obtained by novel extensions and combinations of existing data structures of independent interest, including a new batched variant of weak prefix search.

cited By 10; International audience; A comparison of the performance of X-ray diffraction tomography, a near-field diffraction technique, and a far-field diffraction technique for indexing X-ray diffraction data of polycrystalline materials has been carried out by acquiring two sets of diffraction data from the same polycrystalline sample volume. Both approaches used in this study are variants of the three-dimensional X-ray diffraction (3DXRD) methodology, but they rely on different data-collection and analysis strategies. Previous attempts to assess the quality of 3DXRD indexing results from polycrystalline materials have been restricted to comparisons with two-dimensional electron backscatter diffraction cross sections containing a limited number of grains. In the current work, the relative performance of two frequently used polycrystalline-material indexing algorithms is assessed, comparing the indexing results obtained from a three-dimensional sample volume containing more than 1500emgrains. The currently achievable accuracy of three-dimensional grain maps produced with these algorithms has been assessed using a statistical analysis of the measurement of the size, position and orientation of the grains in the sample. The material used for this comparison was a polycrystalline commercially pure titanium gradeem2 sample, which has a hexagonal close-packed crystal structure. The comparison of the two techniques shows good alphaeement for the measurements of the grain position, size and orientation. Cross-validation between the indexing results shows that about 99% of the sample volume has been indexed correctly by either of these indexing approaches. The remaining discrepancies have been analysed and the strengths and limitations of both approaches are discussed. © 2014 International Union of Crystallography.

The electronic properties of the passive film formed on pure chromium in an acidic sulfate medium at 30 °C was studied by using the multi-frequency Mott–Schottky approach and the point defect model. Conversely to common Mott–Schottky experiments, the relevance of the multi-frequency Mott–Schottky analysis relies on the determination of the space charge capacitance from a large frequency range impedance diagram. To analyze the Constant-Phase-Element behavior commonly observed for the impedance diagrams which characterize the passive film, the power-law model was used and allowed to determine the space charge capacitance. The consistency of the results showed that it was relevant to combine the power-law model to the predictive point defect model. The aim of this study is to extract the semi-conductive parameters of a passive film from impedance measurements using a sensitive analytical method. Keywords: Passive films, EIS, Mott–Schottky theory, Power law model, Point defect model

We present a query formulation language (called MashQL) in order to easily query and fuse structured data on the web. The main novelty of MashQL is that it allows people with limited IT skills to explore and query one (or multiple) data sources without prior knowledge about the schema, structure, vocabulary, or any technical details of these sources. More importantly, to be robust and cover most cases in practice, we do not assume that a data source should havean offline or inlineschema. This poses several language-design and performance complexities that we fundamentally tackle. To illustrate the query formulation power of MashQL, and without loss of generality, we chose the Data web scenario. We also chose querying RDF, as it is the most primitive data model hence, MashQL can be similarly used for querying relational databases and XML. We present two implementations of MashQL, an online mashup editor, and a Firefox add on. The former illustrates how MashQL can be used to query and mash up the Data web as simple as filtering and piping web feeds and the Firefox add on illustrates using the browser as a web composer rather than only a navigator. To end, we evaluate MashQL on querying two data sets, DBLP and DBPedia, and show that our indexing techniques allow instant user interaction. © 1989-2012 IEEE. 24 5 783 798 Cited By :15

Conference of 13th International Workshop on Content-Based Multimedia Indexing, CBMI 2015 ; Conference Date: 10 June 2015 Through 12 June 2015; Conference Code:113803; International audience; We consider the problem of indexing and searching image duplicates in streaming visual data. This task requires a fast image descriptor, a small memory footprint for each signature and a quick search algorithm. To this end, we propose a new descriptor satisfying the aforementioned requirements. We evaluate our method on two different datasets with the use of different sets of distractor images, leading to large-scale image collections (up to 85 million images). We compare our method to the state of the art and show it exhibits among the best detection performances but is much faster (one to two orders of magnitude).

The importance of a research article is routinely measured by counting how many times it has been cited. However, treating all citations with equal weight ignores the wide variety of functions that citations perform. We want to automatically identify the subset of references in a bibliography that have a central academic influence on the citing paper. For this purpose, we examine the effectiveness of a variety of features for determining the academic influence of a citation. By asking authors to identify the key references in their own work, we created a data set in which citations were labeled according to their academic influence. Using automatic feature selection with supervised machine learning, we found a model for predicting academic influence that achieves good performance on this data set using only four features. The best features, among those we evaluated, were those based on the number of times a reference is mentioned in the body of a citing paper. The performance of these features inspired us to design an influence-primed h-index (the hip-index). Unlike the conventional h-index, it weights citations by how many times a reference is mentioned. According to our experiments, the hip-index is a better indicator of researcher performance than the conventional h-index.

The increasing availability of large motion databases, in addition to advancements in motion synthesis, has made motion indexing and classification essential for better motion composition. However, in order to achieve good connectivity in motion graphs, it is important to understand human behaviour human movement though is complex and difficult to completely describe. In this paper, we investigate the similarities between various emotional states with regards to the arousal and valence of the Russell's circumplex model. We use a variety of features that encode, in addition to the raw geometry, stylistic characteristics of motion based on Laban Movement Analysis (LMA). Motion capture data from acted dance performances were used for training and classification purposes. The experimental results show that the proposed features can partially extract the LMA components, providing a representative space for indexing and classification of dance movements with regards to the emotion. This work contributes to the understanding of human behaviour and actions, providing insights on how people express emotional states using their body, while the proposed features can be used as complement to the standard motion similarity, synthesis and classification methods. © 2015 The Eurographics Association and John Wiley & Sons Ltd. 34 6 262 276 Cited By :4

Flash memory is the most prevalent storage medium found on modern wireless sensor devices (WSDs) . In this article we present two external memory index structures for the efficient retrieval of records stored on the local flash memory of a WSD. Our index structures, MicroHash and MicroGF (micro grid files) , exploit the asymmetric read/write and wear characteristics of flash memory in order to offer high-performance indexing and searching capabilities in the presence of a low-energy budget, which is typical for the devices under discussion. Both structures organize data and index pages on the flash media using a sorted by timestamp file organization. A key idea behind these index structures is that expensive random access deletions are completely eliminated. MicroHash enables equality searches by value in constant time and equality searches by timestamp in logarithmic time at a small cost of storing index pages on the flash media. Similarly, MicroGF enables spatial equality and proximity searches in constant time. We have implemented these index structures in nesC, the programming language of the TinyOS operating system. Our trace-driven experimentation with several real datasets reveals that our index structures offer excellent search performance at a small cost of constructing and maintaining the index.

Expressive facial animation synthesis of human like characters has had many approaches with good results. MPEG-4 standard has functioned as the basis of many of those approaches. In this paper we would like to lay out the knowledge of some of those approaches inside an ontology in order to support the modeling of emotional facial animation in virtual humans (VH). Inside this ontology we will present MPEG-4 facial animation concepts and its relationship with emotion through expression profiles that utilize psychological models of emotions. The ontology allows storing, indexing and retrieving prerecorded synthetic facial animations that can express a given emotion. Also this ontology can be used a refined knowledge base in regards to the emotional facial animation creation. This ontology is made using Web Ontology Language and the results are presented as answered queries. Copyright © 2006 John Wiley and Sons, Ltd.

Crawling the Web quickly and entirely is an expensive, unrealistic goal because of the required hardware and network resources. We started with a focused-crawling approach designed by Soumen Chakrabarti, Martin van den Berg, and Byron Dom, and we implemented the underlying philosophy of their approach to derive our baseline crawler. This crawler employs a canonical topic taxonomy to train a naive-Bayesian classifier, which then helps determine the relevancy of crawled pages. The crawler also relies on the assumption of topical locality to decide which URLs to visit next. Building on this crawler, we developed a rule-based crawler, which uses simple rules derived from interclass (topic) linkage patterns to decide its next move. This rule-based crawler also enhances the baseline crawler by supporting tunneling. A focused crawler gathers relevant Web pages on a particular topic. This rule-based Web-crawling approach uses linkage statistics among topics to improve a baseline focused crawler's harvest rate and coverage.

There has been an increasing use of pre-recorded motion capture data for animating virtual characters and syn- thesising different actions it is although a necessity to establish a resultful method for indexing, classifying and retrieving motion. In this paper, we propose a method that can automatically extract motion qualities from dance performances, in terms of Laban Movement Analysis (LMA), for motion analysis and indexing pur- poses. The main objectives of this study is to analyse the motion information of different dance performances, using the LMA components, and extract those features that are indicative of certain emotions or actions. LMA encodes motions using four components, Body, Effort, Shape and Space, which represent a wide array of structural, geometric, and dynamic features of human motion. A deeper analysis of how these features change on different movements is presented, investigating the correlations between the performers' acting emotional state and its characteristics, thus indicating the importance and the effect of each feature for the classification of the motion. Understanding the quality of the movement helps to apprehend the intentions of the performer, providing a representative search space for indexing motions. 277 287 Sponsors: of Information, Control and Communication (INSTICC) Institute for Systems and Technologies Conference code: 107310 Cited By :9

Recent research has studied how to measure the size of a search engine, in terms of the number of pages indexed. In this paper, we consider a different measure for search engines, namely the quality of the pages in a search engine index. We provide a simple, effective algorithm for approximating the quality of an index by performing a random walk on the Web, and we use this methodology to compare the index quality of several major search engines.

Recently, there has been an increasing use of pre-recorded motion capture data, making motion indexing and classification essential for animating virtual characters and synthesising different actions. In this paper, we use a variety of features that encode characteristics of motion using the Body, Effort, Shape and Space components of Laban Movement Analysis (LMA), to explore the motion quality from acted dance performances. Using Principal Component Analysis (PCA), we evaluate the importance of the proposed features - with regards to their ability to separate the performer's emotional state - indicating the weight of each feature in motion classification. PCA has been also used for dimensionality reduction, laying the foundation for the qualitative and quantitative classification of movements based on their LMA characteristics. Early results show that the proposed features provide a representative space for indexing and classification of dance movements with regards to the emotion, which can be used for synthesis and composition purposes. Copyright © ACM. Sponsors: ACM Special Interest Group on Computer-Human Interaction (SIGCHI) ACM Special Interest Group on Computer Graphics and Interactive Techniques (SIGGRAPH) Conference code: 101663 Cited By :4

This paper studies the problem of imposing an existing hierarchical semantic structure onto a corresponding spoken document in which the structures are embedded, with the goal of indexing such documents for easier access. We propose a graph-partitioning framework to solve a semantic tree-to-string alignment problem through optimizing a normalized-cut criterion. We present models with different modeling capabilities and time complexities in this framework and provide experimental evidence of their performance. We relate graph partitioning to conventional dynamic time warping (DTW) as it applies to this problem, and show that the proposed framework can naturally include topic segmentation to accommodate cohesion constraints. © 2006-2012 IEEE.

We propose a new data structure for manipulating graphs, called h-graph, which is particularly suited for designing dynamic algorithms. The structure itself is simple, consisting basically of a triple of elements, for each vertex of the graph. The overall size of all triples is O(n+m), for a graph with n vertices and m edges. We describe algorithms for performing the basic operations related to dynamic applications, as insertions and deletions of vertices or edges, and adjacency queries. The data structure employs a technique first described by Chiba and Nishizeki [Chiba, Nishizeki, Arboricity and subgraph listing algorithms, SIAM J. Comput. 14 (1) (1985) 210223], and relies on the arboricity of graphs. Using the proposed data structure, we describe several dynamic algorithms for solving problems as listing the cliques of a given size, recognizing diamond-free graphs, and finding simple, simplicial and dominated vertices. These algorithms are the first of their kind to be proposed in the literature. In fact, the dynamic algorithms for the above problems lead directly to new static algorithms, and using the data structure we also design new static algorithms for the problems of counting subgraphs of size 4, recognizing cop-win graphs and recognizing strongly chordal graphs. The complexities of all of the proposed static algorithms improve over the complexities of the so far existing algorithms, for graphs of low arboricity. In addition, for the problems of counting subgraphs of size 4 and recognizing diamond-free graphs, the improvement is general. © 2011 Elsevier B.V. All rights reserved. Fil:Lin, M.C. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina. Fil:Soulignac, F.J. Universidad de Buenos Aires. Facultad de Ciencias Exactas y Naturales; Argentina.

Complex systems, such as proteins, are inherently difficult to describe, analyse and interpret. A multimodal methodology which utilizes various diverse representations is needed to further our understanding of such intrinsically multifaceted systems. This paper presents a multimodal system designed to describe and interpret the content of the Protein Data Bank, a repository which contains tens of thousands of known proteins. We describe how complimentary modalities based on the amino acid sequence, the protein's backbone (or topology) and the envelope (the outer shape), are used when furthering our understanding of proteins' functionalities, behaviours and interactions. We illustrate our methodology against the human haemoglobin and show that the interplay between modalities allows our system to find unexpected, complimentary results with different domains of validity. © 2011 Springer-Verlag., 24th International Conference on Industrial Engineering and Other Applications of Applied Intelligent Systems (IEA/AIE 2011), June 28-July 1 2011, Syracuse, New York, USA, Series: Lecture Notes in Computer Science; no. 6703

This study presents delays at signalized intersection resulting from TRANSYT traffic model (TTM) for 3 and 4 phase individual junctions to develop new forms of delays to set up timing manual for practical users. Proposed total delay estimation (TDE) is solved with quasi-Newton method to obtain weighting parameters for delays resulting from TTM. With 3- and 4-legs signalized intersections, uniform and random plus over-saturation component of total delay may be estimated in a single model.

Date of Conference: 23-26 June, 2008 Conference name: IEEE International Conference on Multimedia and Expo, 2008 We describe a method to automatically extract important video objects for object-based indexing. Most of the existing salient object detection approaches detect visually conspicuous structures in images, while our method aims to find regions that may be important for indexing in a video database system. Our method works on a shot basis. We first segment each frame to obtain homogeneous regions in terms of color and texture. Then, we extract a set of regional and inter-regional color, shape, texture and motion features for all regions, which are classified as being important or not using SVMs trained on a few hundreds of example regions. Finally, each important region is tracked within each shot for trajectory generation and consistency check. Experimental results from news video sequences show that the proposed approach is effective. © 2008 IEEE.

Date of Conference: 20-22 April 2008 Conference name: 2008 IEEE 16th Signal Processing, Communication and Applications Conference Bu çalışma, genel olarak nesneye dayalı endekslemeyi destekleyen, özel olarak MPEG-7 uyumlu veritabanları için, videolardan önemli nesnelerin otomatik olarak çıkarılmasını saglayabilecek bir yöntem sunmaktadır. Şimdiye kadar yapılan benzer çalışmalar genellikle resimler üzerinde yoğunlaşmış ve sadece ilk bakışta dikkati çeken alanları bulmaya çalışmıştır. Önerilen yöntem ise videolar üzerinde çalışmak için tasarlanmış olup sadece ilk bakışta dikkat çeken bölgelerin değil, videonun endekslenmesi için önemli sayılabilecek bölgelerin de bulunabilmesini amaçlamaktadır. Bunun için önce video kareleri bölütlere ayrılmakta, sonra her bölüt için yerel ve genel renk, biçim, doku ve hareket bilgileri hesaplanmakta, son olarak bu özellikler kullanılarak eğitilmiş bir destek vektor makinesi (SVM) kullanılarak bölgelerin önemli olup olmadığına karar verilmektedir. İlk deney sonuçları önerilen y öntemin başarılı olduğunu ve elde edilen nesnelerin öncekilere g öre anlamsal olarak daha iyi olduğunu göstermektedir. We describe a method to automatically extract video objects, which are important for object-based indexing of videos in an MPEG-7 compliant video database system. Most of the existing salient object detection approaches detect visually conspicuous image structures, while our method aims to find regions that may be important for indexing in a video database system. Our method works on a shot basis. We first segment each frame to obtain homogeneous regions in terms of color and texture. Then, we extract a set of local and global color, shape, texture and motion features for each region. Finally, the regions are classified as being salient or non-salient using SVMs trained on a few hundreds of example regions. Experimental results from news video segments show that the proposed method is more effective in extracting the important regions in terms of human visual perception. ©2008 IEEE.

Date of Conference: 11-12 April 2008 Conference name: First International Workshop on Similarity Search and Applications, SISAP 2008 Among the metric space indexing methods, AESA is known to produce the lowest query costs in terms of the number of distance computations. However, its quadratic construction cost and space consumption makes it infeasiblefor large dataseis. There have been some work on reducing the space requirements of AESA. Instead of keeping all the distances between objects, LAESA appoints a subset of the database as pivots, keeping only the distances between objects and pivots. Kvp uses the idea of prioritizing the pivots based on their distances to objects, only keeping pivot distances that it evaluates as promising. FQA discretizes the distances using a fixed amount of bits per distance instead of using system's floating point types. Varying the number of bits to produce a performance-space trade-off was also studied in Kvp. Recently, BAESA has been proposed based on the same idea, but using different distance ranges for each pivot. The t-spanner based indexing structure compacts the distance matrix by introducing an approximation factor that makes the pivots less effective. In this work, we show that the Kvp prioritization is oriented toward symmetric distance distributions. We offer a new method that evaluates the effectiveness of pivots in a better fashion by making use of the overall distance distribution. We also simulate the performance of our method combined with distance discretization. Our results show that our approach is able to offer very good space-performance trade-offs compared to AESA and tree-based methods. © 2008 IEEE.

Date of Conference: 20-22 April 2008 Conference name: IEEE 16th Signal Processing, Communication and Applications Conference, 2008 Son yıllarda çok geniş veri tabanlarının kullanımıyla birlikte içerik tabanlı görüntü indekslemesi ve erişimi önemli bir araştırma konusu halini almıştır. Bu çalışmada, görüntü indekslemesi için sahne sınıflandırmasını baz alan bir görüntü erişim sistemi tanımlanmıştır. Görüntülerden çıkarılan alt düzey öznitelikler görüntü indekslemesinde doğrudan kullanılmak yerine, bu öznitelikler sahne sınıflandırması için kullanılmış ve görüntüler sınıflandırma sonucunda elde edilen anlamsal sınıf bilgileriyle indekslenmiştir. Sahne sınıflandırması için “kelime kümesi” (bag of words) dokuman analizi yöntemi olarak bilinen tekniğin bir uyarlaması kullanılmıştır. Görüntü erişim sistemini insan algısıyla desteklemek ve anlambilimsel uçurumu en aza indirgemek için erişim senaryosuna tek sınıf sınıflandırıcı bazlı ilgililik geri beslemesi eklenmiştir. Bunun için, ilgili görüntüleri çok iyi modelleyen, ilgili olmayan görüntülerden de bir o kadar uzak duran bir hiperkure oluşturan destek vektör veri tanımlaması kullanılmıştır. Önerilen yöntemler Corel veri kümesinde denenmiş ve başarılı sonuçlar elde edilmiştir. Content-based image indexing and retrieval have become important research problems with the use of large databases in a wide range of areas. In this study, a content-based image retrieval system that is based on scene classification for image indexing is proposed. Instead of using low-level features directly, semantic class information that is obtained as a result of scene classification is used during indexing. The traditional "bag of words" approach is modified for classifying the scenes. In order to minimize the semantic gap, a relevance feedback approach that is based on one-class classification is also integrated. The support vector data description is used for learning during feedback iterations. The experiments using the Corel data set show good results for both classification and retrieval. ©2008 IEEE.

MediaCampaign's scope is on discovering and inter-relating advertisements and campaigns, i.e. to relate advertisements semantically belonging together, across different countries and different media. The project's main goal is to automate to a large degree the detection and tracking of advertisement campaigns on television, Internet and in the press. For this purpose we introduce a first prototype of a fully integrated semantic analysis system based on an ontology which automatically detects new creatives and campaigns by utilizing a multimodal analysis system and a framework for the resolution of semantic identity. ©2008 IEEE.

MediaCampaign's scope is on discovering and inter-relating advertisements and campaigns, i.e. to relate advertisements semantically belonging together, across different countries and different media. The project's main goal is to automate to a large degree the detection and tracking of advertisement campaigns on television, Internet and in the press. For this purpose we introduce a first prototype of a fully integrated semantic analysis system based on an ontology which automatically detects new creatives and campaigns by utilizing a multimodal analysis system and a framework for the resolution of semantic identity. ©2008 IEEE.

Date of Conference: 25-27 June 2007 Conference name: International Workshop on Content-Based Multimedia Indexing, 2007 The management and exchange of multimedia data is challenging due to the variety of formats, standards and intended applications. In addition, production of multimedia data is rapidly increasing due to the availability of off-the-shelf, modern digital devices that can be used by even inexperienced users. It is likely that this volume of information will only increase in the future. A key goal of the MUSCLE (Multimedia Understanding through Semantics, Computation and Learning) network is to develop tools, technologies and standards to facilitate the interoperability of multimedia content and support the exchange of such data. One approach for achieving this was the creation of a specific "E-Team", composed of the authors, to discuss core questions and practical issues based on the participant's individual work. In this paper, we present the relevant points of view with regards to sharing experiences and to extracting and integrating multimedia data and metadata from different modes (text, images, video). © 2007 IEEE.

Date of Conference: 26 27 October, 2006 Conference name: MIR '06 Proceedings of the 8th ACM international workshop on Multimedia information retrieval There is a growing need to access historical Ottoman documents stored in large archives and therefore managing tools for automatic searching, indexing and transcription of these documents is required. In this paper, we present a method for the retrieval of Ottoman documents based on word matching. The method first successfully segments the documents into word images and then uses a hierarchical matching technique to find the similar instances of the word images. The experiments show that even with simple features promising results can be achieved. Copyright 2006 ACM.

In this paper we describe our TRECVID 2006 experiments. The MediaMill team participated in two tasks: concept detection and search. For concept detection we use the MediaMill Challenge as experimental platform. The MediaMill Challenge divides the generic video indexing problem into a visual-only, textual-only, early fusion, late fusion, and combined analysis experiment. We provide a baseline implementation for each experiment together with baseline results, which we made available for the TRECVID community. The Challenge package was downloaded more than 80 times and we anticipate that it has been used by several teams for their 2006 submission. Our Challenge experiments focus specifically on visual-only analysis of video (run id: B\_MM). We extract image features, on global, regional, and keypoint level, which we combine with various supervised learners. A late fusion approach of visual-only analysis methods using geometric mean was our most successful run. With this run we conquer the Challenge baseline by more than 50\%. Our concept detection experiments have resulted in the best score for three concepts: i.e. \emph{desert}, \emph{flag us}, and \emph{charts}. What is more, using LSCOM annotations, our visual-only approach generalizes well to a set of 491 concept detectors. To handle such a large thesaurus in retrieval, an engine is developed which automatically selects a set of relevant concept detectors based on text matching and ontology querying. The suggestion engine is evaluated as part of the automatic search task (run id: A-MM) and forms the entry point for our interactive search experiments (run id: A-MM). Here we experiment with query by object matching and two browsers for interactive exploration: the CrossBrowser and the novel NovaBrowser. It was found that the NovaBrowser is able to produce the same results as the CrossBrowser, but with less user interaction. Similar to previous years our best interactive search runs yield top performance, ranking 2nd and 6th overall. Again a lot has been learned during this year's TRECVID campaign, we highlight the most important lessons at the end of this paper.

In this paper we describe our TRECVID 2006 experiments. The MediaMill team participated in two tasks: concept detection and search. For concept detection we use the MediaMill Challenge as experimental platform. The MediaMill Challenge divides the generic video indexing problem into a visual-only, textual-only, early fusion, late fusion, and combined analysis experiment. We provide a baseline implementation for each experiment together with baseline results, which we made available to the TRECVID community. The Challenge package was downloaded more than 80 times and we anticipate that it has been used by several teams for their 2006 submission. Our Challenge experiments focus specifically on visual-only analysis of video (run id: B MM). We extract image features, on global, regional, and keypoint level, which we combine with various supervised learners. A late fusion approach of visual-only analysis methods using geometric mean was our most successful run. With this run we conquer the Challenge baseline by more than 50%. Our concept detection experiments have resulted in the best score for three concepts: i.e. desert, flag us, and charts. What is more, using LSCOM annotations, our visual-only approach generalizes well to a set of 491 concept detectors. To handle such a large thesaurus in retrieval, an engine is developed which automatically selects a set of relevant concept detectors based on text matching and ontology querying. The suggestion engine is evaluated as part of the automatic search task (run id: A-MM) and forms the entry point for our interactive search experiments (run id: A-MM). Here we experiment with query by object matching and two browsers for interactive exploration: the CrossBrowser and the novel RotorBrowser. It was found that the RotorBrowser is able to produce the same results as the CrossBrowser, but with less user interaction. Similar to previous years our best interactive search runs yield top performance, ranking 2nd and 6th overall. Again a lot has been learned during this year's TRECVID campaign, we highlight the most important lessons at the end of this paper.

Date of Conference: 1-3 November, 2006 21th International Symposium on Computer and Information Sciences – ISCIS 2006 Shared-nothing, parallel text retrieval systems require an inverted index, representing a document collection, to be partitioned among a number of processors. In general, the index can be partitioned based on either the terms or documents in the collection, and the way the partitioning is done greatly affects the query processing performance of the parallel system. In this work, we investigate the effect of these two index partitioning schemes on query processing. We conduct experiments on a 32-node PC cluster, considering the case where index is completely stored in disk. Performance results are reported for a large (30 GB) document collection using an MPI-based parallel query processing implementation. © Springer-Verlag Berlin Heidelberg 2006.

Present day information retrieval systems largely ignore the issues of lexical and compositional semantics, and rely mainly on some statistical measures for choosing or evolving an indexing scheme. This has been the reason for the decreasing precision in their responses, given an exponentially increasing number of Web pages. The work reported in this paper addresses this issue from a linguistic point of view. We show that the detection of domain-specific phrases can capture the task-specific semantics of documents. We introduce the notion of n*-gram formalism to characterize the domain-specific phrases and their variants, taking a few sample domains. A method to construct a phrase grammar from a small set of documents is proposed. A method of conceptual indexing based on the phrase grammar has also been proposed. In order to demonstrate the effectiveness of the proposed method, we have designed a versatile system that can perform concept-based retrieval, in addition to several document-processing tasks, such as text classification, extraction-based summarization, context tracking, and semantic tagging. Collectively, the system can address the semantic content of documents. Considering the fact that an average user prefers highly relevant results in the top-ranked subset to an exhaustively retrieved set, it is shown that the proposed system performs better in that it retrieves documents that are more conceptually relevant than those retrieved by Google, and at 95% confidence level. Copyright ? 2005 Taylor & Francis Inc.

Cataloged from PDF version of article. Our research shows that for large databases, without considerable additional storage overhead, cluster-based retrieval (CBR) can compete with the time efficiency and effectiveness of the inverted index-based full search (FS). The proposed CBR method employs a storage structure that blends the cluster membership information into the inverted file posting lists. This approach significantly reduces the cost of similarity calculations for document ranking during query processing and improves efficiency. For example, in terms of in-memory computations, our new approach can reduce query processing time to 39% of FS. The experiments confirm that the approach is scalable and system performance improves with increasing database size. In the experiments, we use the cover coefficient-based clustering methodology ((CM)-M-3), and the Financial Times database of TREC containing 210 158 documents of size 564 MB defined by 229 748 terms with total of 29 545 234 inverted index elements. This study provides CBR efficiency and effectiveness experiments using the largest corpus in an environment that employs no user interaction or user behavior assumption for clustering. (C) 2003 Elsevier Ltd. All rights reserved.

Date of Conference: June 27th~30th, 2004 In this paper, we examine the problem of automatic image captioning. Given a training set of captioned images, we want to discover correlations between image features and keywords, so that we can automatically find good keywords for a new image. We experiment thoroughly with multiple design alternatives on large datasets of various content styles, and our proposed methods achieve up to a 45% relative improvement on captioning accuracy over the state of the art.

A baseline crawler was developed at the Bilkent University based on a focused-crawling approach. The focused crawler is an agent that targets a particular topic and visits and gathers only a relevant, narrow Web segment while trying not to waste resources on irrelevant materials. The rule-based Web-crawling approach uses linkage statistics among topics to improve a baseline focused crawler's harvest rate and coverage. The crawler also employs a canonical topic taxonomy to train a naïve-Bayesian classifier, which then helps determine the relevancy of crawled pages.

Cataloged from PDF version of article. Measuring the information retrieval effectiveness of World Wide Web search engines is costly because of human relevance judgments involved. However, both for business enterprises and people it is important to know the most effective Web search engines, since such search engines help their users find higher number of relevant Web pages with less effort. Furthermore, this information can be used for several practical purposes. In this study we introduce automatic Web search engine evaluation method as an efficient and effective assessment tool of such systems. The experiments based on eight Web search engines, 25 queries, and binary user relevance judgments show that our method provides results consistent with human-based evaluations. It is shown that the observed consistencies are statistically significant. This indicates that the new method can be successfully used in the evaluation of Web search engines. (C) 2003 Elsevier Ltd. All rights reserved.

Date of Conference: 8-14 February 1997 Conference name: Electronic Imaging '97 - Proceedings Visual Communications and Image Processing '97 This paper describes a method for selecting key frames by using a number of parameters extracted from the MPEG video stream. The parameters are directly extracted from the compressed video stream without decompression. A combination of these parameters are then used in a rule based decision system. The computational complexity for extracting the parameters and for key frame decision rule is very small. As a results, the overall operation is very quickly performed and this makes our algorithm handy for practical purposes. The experimental results show that this method can select the distinctive frames of video streams successfully.