[신간의 별자리x] 우리/미술, 그리고 ‘슬픔의 박물관’

Computer and Robot Vision Vol. 1, by R.M. Haralick and Linda G. Shapiro, Addison-Wesley, 1992, ISBN 0-201-10887-1.

Computer and Robot Vision

The demand for various multimedia applications is rapidly increasing due to the recent advance in the computing and network infrastructure, together with the widespread use of digital video technology. Among the key elements for the success of these applications is how to effectively and efficiently manage and store a huge amount of audio visual information, while at the same time providing user-friendly access to the stored data. This has fueled a quickly evolving research area known as video abstraction. As the name implies, video abstraction is a mechanism for generating a short summary of a video, which can either be a sequence of stationary images (keyframes) or moving images (video skims). In terms of browsing and navigation, a good video abstract will enable the user to gain maximum information about the target video sequence in a specified time constraint or sufficient information in the minimum time. Over past years, various ideas and techniques have been proposed towards the effective abstraction of video contents. The purpose of this article is to provide a systematic classification of these works. We identify and detail, for each approach, the underlying components and how they are addressed in specific works.

Video abstraction: A systematic review and classification

International Joint Conference on Neural Networks

Content delivery over the Internet needs to address both the multimedia nature of the content and the capabilities of the diverse client platforms the content is being delivered to. We present a system that adapts multimedia Web documents to optimally match the capabilities of the client device requesting it. This system has two key components. 1) A representation scheme called the InfoPyramid that provides a multimodal, multiresolution representation hierarchy for multimedia. 2) A customizer that selects the best content representation to meet the client capabilities while delivering the most value. We model the selection process as a resource allocation problem in a generalized rate distortion framework. In this framework, we address the issue of both multiple media types in a Web document and multiple resource types at the client. We extend this framework to allow prioritization on the content items in a Web document. We illustrate our content adaptation technique with a web server that adapts multimedia news stories to clients as diverse as workstations, PDA's and cellular phones.

/pdf/adapting-multimedia-internet-content-for-universal-access-57szh9nlkc.pdf

Adapting multimedia Internet content for universal access

Clinical coding is an administrative process that involves the translation of diagnostic data from episodes of care into a standard code format such as ICD10. It has many critical applications such as billing and aetiology research. The automation of clinical coding is very challenging due to data sparsity, low interoperability of digital health systems, complexity of real-life diagnosis coupled with the huge size of ICD10 code space. Related work suffer from low applicability due to reliance on many data sources, inefficient modelling and less generalizable solutions. We propose a novel collaborative residual learning based model to automatically predict ICD10 codes employing only prescriptions data. Extensive experiments were performed on two real-world clinical datasets (outpatient & inpatient) from Maharaj Nakorn Chiang Mai Hospital with real case-mix distributions. We obtain multi-label classification accuracy of 0.71 and 0.57 of average precision, 0.57 and 0.38 of F1-score and 0.73 and 0.44 of accuracy in predicting principal diagnosis for inpatient and outpatient datasets respectively.

Collaborative residual learners for automatic icd10 prediction using prescribed medications.

The translation of medical diagnosis to clinical coding has wide range of applications in billing, aetiology analysis, and auditing. Currently, coding is a manual effort while the automation of such task is not straight forward. Among the challenges are the messy and noisy clinical records, case complexities, along with the huge ICD10 code space. Previous work mainly relied on discharge notes for prediction and was applied to a very limited data scale. We propose an ensemble model incorporating multiple clinical data sources for accurate code predictions. We further propose an assessment mechanism to provide confidence rates in predicted outcomes. Extensive experiments were performed on two new real-world clinical datasets (inpatient & outpatient) with unaltered case-mix distributions from Maharaj Nakorn Chiang Mai Hospital. We obtain multi-label classification accuracies of 0.73 and 0.58 for average precision, 0.56 and 0.35 for F1-scores and 0.71 and 0.4 accuracy in predicting principal diagnosis for inpatient and outpatient datasets respectively.

Ensemble model for pre-discharge icd10 coding prediction.

For many years, one of the problems in pattern recognition is classification. There are many methods that deal with this type of problem. The data sets are sometimes in the binary form (real number) and represented by vectors of binary numbers (real numbers) although there are uncertainties in the data, e.g., data collected in management questionnaires. In this paper, we developed a linguistic K-nearest prototype algorithm with vectors of fuzzy numbers as inputs. This algorithm is based on the extension principle and the decomposition theorem. We apply this algorithm to linguistic vectors derived from a set of thirty-nine subjects answering questions about students' satisfaction with communication to their university.

A linguistic K-nearest prototype with an application to management surveys

Laser line scanner are becoming very popular very recently because there is no touching the surface to determine coordinates. However, there are some missing points because of some parts of objects are out of sight from the laser. Therefore, in this research we introduce an automatic method to estimate missing points in a Cartesian coordinate system using fuzzy support vector regression (FSVR). We also compare our result with the one from support vector regression (SVR). The results show that the FSVR is a suitable method in missing 3D coordinates estimation.

3D missing point estimation using fuzzy support vector regression

Fuzzy C-means (FCM) has been a prominent clustering algorithm for a long time. It was extended to a type-2 framework by the Linguistic Fuzzy C-means (LFCM) that operates on vectors of fuzzy numbers utilizing the extension principle, the decomposition theorem, and interval analyses. The purpose of this paper is to study the effects of the iterative type-2 fuzzy clustering algorithm. The LFCM incorporates uncertainty through type-2 fuzzy sets, but it is prone to membership spread, i.e., the uncertainty in a membership function can become too large or broad during the iterative alternating optimization procedure. We devise three dampening approaches to mitigate the problem. Vertical cut dampening, linear dampening, and reflection dampening are defined along with the experiments conducted on a synthetic dataset named the butterfly dataset. We also illustrate the updated memberships (fuzzy numbers) and the resulting cluster prototypes (fuzzy vectors) from visual standpoints. Applying any of these dampening approaches will result in thinner membership functions and helps us control the uncertainty not to grow rapidly, and in fact, aid in convergence.

Sansanee Auephanwiriyakul

Papers

Collaborative residual learners for automatic icd10 prediction using prescribed medications.

Ensemble model for pre-discharge icd10 coding prediction.

A linguistic K-nearest prototype with an application to management surveys

3D missing point estimation using fuzzy support vector regression

Controlling Membership Spread in Type-2 Fuzzy Clustering