Ontology learning and its application to automated terminology translation

Our OntoLearn system is an infrastructure for automated ontology learning from domain text. It is the only system, as far as we know, that uses natural language processing and machine learning techniques, and is part of a more general ontology engineering architecture. We describe the system and an experiment in which we used a machine-learned tourism ontology to automatically translate multiword terms from English to Italian. The method can apply to other domains without manual adaptation.     

ECG waveform feature extraction and its application to automated prognosis

Automated correlation of ECG history for early detection of heart disease, especially among the young, has been a matter of increasing interest. However, each electrocardiogram, recorded say a few months apart, generates anywhere from 600 to 2400 digitized data, so that statistical methods cannot directly be applied. An information compression step suitable for such data is presented in this paper and a prediction procedure is developed for forecasting the waveform changes. Specifically, each ECG lead is digitized and represented by itsz-domain modes. These modes are found to exhibit continuity in time, from month to month and year to year, except in the event of major physiological changes such as after surgery, thus lending themselves ideally to statistic al prediction. To enhance discrimination of the subtle changes inP, QRS, andT complexes, the derivatives of the waves are employed for extraction of the modes. This signifies a departure from previous efforts in ECG representation. Indeed, otherwise, important changes in the waves can remain undetected through mode extraction while the human eye can perceive them rather easily from the recorded traces.     

Ultrasonic sensor data integration and its application to environment perception

To move in an unknown or uncertain environment, a mobile robot must collect information from various sensors and use it to construct a representation of the external world. Ultrasonic sensors can provide range data for this purpose in a simple and cost-effective way. However, most ultrasonic sensors are not sufficient for environment recognition because of their large beam opening angles. In this article the beam-opening-angle problem is solved by fusing data from multiple ultrasonic sensors. We propose two methods for sensor data fusion. One uses an artificial neural network (ANN), and the other is based on a mathematical model. Simulations and experiments show that the mathematical model is more accurate when there is no noise in the sensor readings, but the ANN method is better when the sensors are subject to much noise. To extract line segments from the ultrasonic image, we develop a line extractor that is more efficient than traditional line fitting methods in this application. Experimental results show that this method is effective for environment perception in a robotic system. © 1996 John Wiley & Sons, Inc.     

Principal kurtosis analysis and its application for remote-sensing imagery

Fast Independent Component Analysis (FastICA) is the commonly used feature extraction method for non-Gaussian structure data and it is often used in multispectral/hyperspectral image processing. However, FastICA requires all pixels to be involved at each iteration. Therefore, it is a very time-consuming method when the total number of iterations is large. In this study, we propose an equivalent algebraic method for FastICA when selecting kurtosis as a non-Gaussian index. We name this new method principal kurtosis analysis (PKA). The feature extraction result of PKA is equivalent to that of FastICA when considering kurtosis as the measurement of non-Gaussianity. Similar to FastICA, PKA also applies the fixed-point iteration method to search for extreme kurtosis directions. However, when computing the projected direction in the iteration process, PKA only requires a co-kurtosis tensor and not all of the pixels. Therefore, this reduces the time complexity. The proposed algorithm (PKA) has been applied on multispectral and hyperspectral images and shows its time advantage in the experiments.     

Extraction of landslide-related factors from ASTER imagery and its application to landslide susceptibility mapping

The aim of this study is to extract landslide-related factors from remote-sensing data, such as Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER) satellite imagery, and to examine their applicability to landslide susceptibility near Boun, Korea, using a geographic information system (GIS). Landslide was mapped from interpretation of aerial photographs and field surveying. Factors that influence landslide occurrence were extracted from ASTER imagery. The slope, aspect and curvature were calculated from the digital elevation model (DEM) with 25.77 m root mean square error (RMSE), which was derived from ASTER imagery. Lineaments, land-cover and normalized difference vegetation index (NDVI) layers were also estimated from ASTER imagery. Landslide-susceptible areas were analysed and mapped using the occurrence factors by a frequency ratio and logistic regression model. Validation results were 84.78% in frequency ratio and 84.20% in logistic regression prediction accuracy for the susceptibility map with respect to ground-truth data.     

A domain-specific language for model mutation and its application to the automated generation of exercises

Model-Driven Engineering (MDE) is a software engineering paradigm that uses models as main assets in all development phases. While many languages for model manipulation exist (e.g., for model transformation or code generation), there is a lack of frameworks to define and apply model mutations.A model mutant is a variation of an original model, created by the application of specific model mutation operations. Model mutation has many applications, for instance, in the areas of model transformation testing, model-based testing or education.In this paper, we present a domain-specific language called Wodel for the specification and generation of model mutants. Wodel is domain-independent, as it can be used to generate mutants of models conformant to arbitrary meta-models. Its development environment is extensible, permitting the incorporation of post-processors for different applications. In particular, we describe Wodel-Edu, a post-processing extension directed to the automated generation of exercises for particular domains and their automated correction. We show the application of Wodel-Edu to the generation of exercises for deterministic automata, and report on an evaluation of the quality of the generated exercises, obtaining overall good results.     

A community-centric approach to automated service composition

In the recent years, the web has kept growing rapidly and undergone tremendous changes towards a user-centric environment. With the proliferation of services available on the Internet, millions of users are able to voluntarily participate in and collaborate for their own interests and benefits by means of service composition. However, due to the ever increasing number of services, it then becomes a challenging issue to enable the users to rapidly select and compose the proper services. In this paper, we pro...     

分散混杂自适应模糊H∞控制器及其在自动化公路系统中的应用

本文针对一类SISO不确定非线性大系统,提出了一种混杂间接和直接自适应分散模糊H∞控制器.通过组合模糊系统和H∞跟踪技术开发的分散自适应模糊控制算法避免了控制设计中含有的符号函数.两种自适应模糊控制器的组合消除了它们各自均不能够同时融合被控对象知识与控制知识的局限.闭环大系统被证明是稳定的,且具有H∞跟踪性能.该算法应用于自动化公路系统中车辆的纵向跟随控制,仿真结果表明混杂自适应模糊H∞控制系统的跟踪性能更好而相应的控制幅值却更小.     

Shape "break-and-repair" strategy and its application to automated medical image segmentation

In three-dimensional medical imaging, segmentation of specific anatomy structure is often a preprocessing step for computer-aided detection/diagnosis (CAD) purposes, and its performance has a significant impact on diagnosis of diseases as well as objective quantitative assessment of therapeutic efficacy. However, the existence of various diseases, image noise or artifacts, and individual anatomical variety generally impose a challenge for accurate segmentation of specific structures. To address these problems, a shape analysis strategy termed "break-and-repair" is presented in this study to facilitate automated medical image segmentation. Similar to surface approximation using a limited number of control points, the basic idea is to remove problematic regions and then estimate a smooth and complete surface shape by representing the remaining regions with high fidelity as an implicit function. The innovation of this shape analysis strategy is the capability of solving challenging medical image segmentation problems in a unified framework, regardless of the variability of anatomical structures in question. In our implementation, principal curvature analysis is used to identify and remove the problematic regions and radial basis function (RBF) based implicit surface fitting is used to achieve a closed (or complete) surface boundary. The feasibility and performance of this strategy are demonstrated by applying it to automated segmentation of two completely different anatomical structures depicted on CT examinations, namely human lungs and pulmonary nodules. Our quantitative experiments on a large number of clinical CT examinations collected from different sources demonstrate the accuracy, robustness, and generality of the shape "break-and-repair" strategy in medical image segmentation.     

Dynamic planning approach to automated web service composition

In this paper, novel ideas are presented for solving the automated web service composition problem. Some of the possible real world problems such as partial observability of the environment, nondeterministic effects of web services and service execution failures are solved through a dynamic planning approach. The proposed approach is based on a novel AI planner that is designed for working in highly dynamic environments under time constraints, namely Simplanner. World altering service calls are done according to the WS-Coordination and WS-Business Activity web service transaction specifications in order to physically recover from failure situations and prevent the undesired side effects of the aborted web service composition efforts.     

人眼灰度感知建模及其在图像增强中的应用

原直方图均衡化算法处理结果不理想,主要是图像灰度域上实现的均衡化并不代表人眼感知亮度域上的均衡化,对此提出人眼感知亮度域上的直方图均衡化算法,但由于使用的灰度人眼感知模型不准确,处理效果也没有得到明显的改善。提出一种灰度人眼感知模型的建模方法,利用实验测试的方法得到人眼视觉系统临界可见偏差曲线;再推导得到人眼对不同灰度背景下同等灰度差别的敏感度曲线;接着利用上一步结果再通过积分和归一化方法得到灰度人眼感知模型;根据以上灰度人眼感知模型对直方图均衡化算法进行改进。对比实验结果表明,提出算法相比于原直方图均衡化具有明显的改善效果,相比于CLAHE、BBHE以及HMF等直方图改进算法,也具有无需参数调节,增强效果显著和适应性强等优点。     

A modified object-oriented classification algorithm and its application in high-resolution remote-sensing imagery

High-resolution satellite images offer abundant information on the Earth's surface for remote-sensing applications. The traditional pixel-based image classification method only used by spectral information has been proved to have several drawbacks. To satisfactorily interpret high-resolution imagery, other important information such as geometry, texture and semantics must be used, which are represented not only in single pixels but in meaningful image objects. So, a modified high-resolution image classification algorithm with multi-characteristics based on objects is presented in this article. First, image objects are extracted by multi-scale multi-characteristic segmentation. Second, characteristics such as spectral information, geometry, texture and semantics are extracted by the corresponding extraction algorithm. Finally, the image objects are classified by means of fuzzy-logic classification with a weighted average calculation method. Preliminary results show promise in terms of classification quality and accuracy.     

Visualization-informed noise elimination and its application in processing high-spatial-resolution remote sensing imagery

Noise removal is perhaps one of the most fundamental and challenging tasks for extracting useful information from a spatial data set. One of the challenges is that there is no general agreement on the definition of noise that can be universally applied to all different domains. This paper proposes a novel technique called Visualization-Informed Noise Elimination (VINE) to support a customized noise removal through incorporation of domain knowledge. The VINE technique consists of three steps of consecutive operations. First, a k-mutual neighbor graph is derived from a spatial data set to model the spatial proximity among data points. Next, a fast partitioning method is employed to reassemble graph nodes into groups. Last, a 3-dimensional (3D) visualization model is created to provide a layered view of the partitioned data, which allows an informed identification and elimination of noise by tailoring to the requirements of a specific domain. The flexibility and customizability provided by this novel technique ensures an effective differentiation of noise from valid data and demonstrates various advantages over traditional methods with improved results. When adapted in post-classification smoothing of high-spatial-resolution remotely sensed images, this approach was able to discover and reassign noise (such as shadows often seen in high-spatial-resolution images) to its proper target class. By incorporating domain knowledge and making use of spatial contextual information, the VINE technique could produce results significantly superior to existing approaches such as majority filter and size-based noise removal.     

Resolution of ambiguity in Chinese and its application to machine translation

In this paper, we present a typology of ambiguity in Chinese, which includes morphological, lexical, syntactic, semantic, and contextual ambiguities. Examples are shown for each type of ambiguity and sometimes for subtypes. Ambiguity resolution strategies used in the ALICE machine translation system are presented in various levels of detail. A disambiguation model, called Four-Step, is proposed for resolving syntactic ambiguities involving serial verb construction and predication. As the name suggests, the model comprises four steps-well-formedness checking, preference for argument readings, precondition checking, and late closure. For resolving semantic ambiguity, we propose a new formalism, called Semantic Functional Grammar (SFG), to deal with the resolution problem. SFG integrates the concept of Semantic Grammar into Lexical-Functional Grammar (LFG) such that the functional structure (f-structures) include semantic functions in addition to grammatical functions. For dealing with lexical and contextual ambiguities, we briefly describe the mechanisms used in the ALICE system. As for morphological ambiguity, the resolution is a problem of word-boundary decision (segmentation) and is beyond the scope of this research. The mechanisms presented in the paper have been successfully applied to the translation of Chinese news headlines in the ALICE system.This research was supported partly by the Industrial Technology Research Institute, Taiwan under a grant for doctoral study to this author.     

Depth perception using blurring and its application in VLSI wafer probing

In this paper, we present a technique for measuring the amount of blur of an edge and using this information to determine the distance of a micromanipulator probe from a wafer surface in very large scale integration (VLSI) wafer probing. In this application, a soft and reliable touch of the probe with a metal pad in the wafer is a sensitive operation. The wafer is focused and several images of the probe while approaching the wafer are analyzed. In our theory, the amount of blur is calculated from the height of the step edge and the slope of the intensity profile at the zero crossing. Hence, our formula is simple and easy to use. We estimate the distance of the probe from the surface of the wafer and obtain a robust measure, i.e., one which is valid even in the presence of significant noise in the images. In order to validate our methods, we have experimented with various VLSI patterns as backgrounds.     

Repositioning of a rigid body with a flexible sheet and its application to an automated rehabilitation bed

A new method for repositioning a rigid body with a flexible sheet is developed and is applied to a rehabilitation bed for turning and transferring a bedridden patient to alleviate bedsores and other ailments. The patient position and orientation are fully controlled by manipulating a flexible bed sheet under no-slip conditions. The use of a flexible sheet and the untethered nature of manipulation make the repositioning method particularly well suited to handling the human body. First, the basic design concept of the rehabilitation bed for automated patient repositioning is presented. The kinematic and static behaviors of body-sheet interactions are analyzed, and conditions for no-slip, quasi-static repositioning are obtained. In order to prevent injury to the patient's fragile skin, it must be ensured that the patient does not slip on the sheet during repositioning. A prototype bed with a pair of servoed arms for manipulating the bed sheet is developed, and the no-slip conditions and the repositioning method are experimentally verified. A closed-loop control based on the measurement of a patient's position and orientation is implemented and tested. Note to Practitioners-This work was motivated by the problems faced by bedridden patients as well as caregivers in the healthcare industry. The labor-intensive repositioning and transfer of bedridden patients are performed with a robotic system supervised by a single caregiver. Our repositioning scheme uses the bed sheet for rolling and moving the patient and closely mimics the current practice prevalent in nursing homes and hospitals. Our approach will be a natural alternative to manual repositioning and transfer and will be acceptable for most caregivers and patients. Initial prototyping and experiments have been completed in consultation with a professional caregiver.     

Student perception and usage of an automated programming assessment tool

Automated assessment systems are gaining popularity within computer programming courses. In this paper we perform an empirical evaluation of Mooshak, an online judge that verifies program correctness, in order to determine its usefulness in classroom settings. In particular, we provide a detailed study on how students use the tool, analyze their opinions and critiques about it, and measure other features like its capability to reduce dropout rates. The experience was carried out within a course on algorithm design and analysis where we collected information through several questionnaires and data generated by the tool during the course. Among the main findings we highlight: (1) the usage of the tool was adequate in relation to students’ own testing; (2) its feedback needs to be richer in order to improve its acceptance among students; and (3) there was no statistical evidence to claim Mooshak reduced the dropout rate.     

An ancient Chinese mathematical algorithm and its application to nonlinear oscillators

An ancient Chinese mathematical method is briefly introduced, and its application to nonlinear oscillators is elucidated where He’s amplitude–frequency formulation is outlined. Three examples are given to show the extremely simple solution procedure and remarkably accurate solutions.