1,797 Result(s)
-
Chapter
Quantum Learning Algorithm for Multilayered Neural Network
Back propagation rule has been shown to be an efficientlearning algorithm for multilayerd neural network. However,it is limited because it only finds local minima. Boltzmannmachine has also been shown to be an...
-
Chapter and Conference Paper
Beschreibung von Konturen medizinischer Objekte durch Krümmungsanalyse und Attribuierung
In der Literatur werden Verfahren und Datenstrukturen zur Darstellung von Konturen beschrieben: Das Streifenbaumverfahren (Strip Tree) ist ein iteratives Schema für eine hierarchische Zerlegung von Konturen. D...
-
Chapter and Conference Paper
Hierarchical Robot Multi-Sensor Data Fusion System
The objective of this paper is to develop a knowledge-based hierarchical paradigm for the effective fusion of multiple sensors into the operation of an intelligent system.
-
Chapter and Conference Paper
Causal Networks and their toolkit in KSE
Causal Networks have recently received much attention in AI, and have been used in many areas as a knowledge representation. First, from the knowledge engineering point of view, we present causal networks, int...
-
Chapter and Conference Paper
An Integrated Approach for Flexible Workflow Modeling
This paper proposes an integrated workflow model known as the Multi-Agent Workflow Model (MAWM). MAWM was designed to offer high flexibility in business process modeling. The central idea of MAWM is based on o...
-
Chapter and Conference Paper
A Logical Approach to Fuzzy Data Analysis
In this paper, we investigate the extraction of fuzzy rules from data tables based on possibility theory. A possibilistic decision language is used to represent the extracted fuzzy rules. The algorithm for rul...
-
Chapter and Conference Paper
Sensitive Words and Their Application to Chinese Processing
Sensitive words are the compound words whose syntactic category is different from those of their components. According to the segmentation, a sensitive word may play different roles, leading to significantly d...
-
Chapter and Conference Paper
A Hybrid Approach of Text Segmentation Based on Sensitive Word Concept for NLP
Natural language processing, such as Checking and Correc- tion of Texts, Machine Translation, and Information Retrieval, usually starts from words. The identification of words in Indo-European lan- guages is a...
-
Chapter and Conference Paper
Coordinating Interorganizational Workflows Based on Process-Views
In multi-enterprise cooperation, an enterprise must monitor the progress of private processes as well as those of the partners to streamline interorganizational workflows. In this work, a process-view model, w...
-
Chapter and Conference Paper
Construction of Chinese Chess Endgame Databases by Retrograde Analysis
Retrograde analysis is well-known and has been successfully developed in the design ofWestern chess1 endgame databases. However, there is little achievement using this technique in the construction of Chinese che...
-
Chapter and Conference Paper
An Empirical Study of the Minimum Required Size and the Minimum Number of Targets for Pen Input on the Small Display
Two experiments were conducted to compare target pointing performance with a pen (stylus) and with a cursor key. on small displays. In experiment 1, we examined participants’ performance of target pointing wit...
-
Chapter and Conference Paper
A Probabilistic Multi-scale Model for Contour Completion Based on Image Statistics
We derive a probabilistic multi-scale model for contour completion based on image statistics. The boundaries of human segmented images are used as “ground truth”. A probabilistic formulation of contours demand...
-
Chapter and Conference Paper
An Estimate Method of the Minimum Entropy of Natural Languages
The study of minimum entropy of English has a long history and has made a great progress, but only a few studies on other languages have been reported in literature so far. In this paper, we present a new meth...
-
Chapter and Conference Paper
Efficient Density Clustering Method for Spatial Data
Data mining for spatial data has become increasingly important as more and more organizations are exposed to spatial data from sources such as remote sensing, geographical information systems, astronomy, compu...
-
Chapter and Conference Paper
Chinese Utterance Segmentation in Spoken Language Translation
This paper presents an approach to segmenting Chinese utterances for a spoken language translation (SLT) system in which Chinese speech is the source input. We propose this approach as a supplement to the func...
-
Chapter and Conference Paper
Discovering Role-Relevant Process-Views for Recommending Workflow Information
Workflow technology automates business processes to increase managerial efficiency. However, workers (representing organizational roles) cannot easily obtain a global view of a complex and large workflow. This...
-
Chapter and Conference Paper
Multimedia Data Mining Using P-Trees
Peano count trees (P-trees) provide efficient, lossless, data mining ready representations of tabular data and make possible the mining of multiple very large data sets, including time-sequences of Remotely Se...
-
Chapter
Sinica Treebank
This paper describes the design criteria and annotation guidelines of the Sinica Treebank. The three design criteria are: Maximal Resource Sharing, Minimal Structural Complexity, and Optimal Semantic Informati...
-
Chapter and Conference Paper
Application of Neural Network on Wave Impact Force Prediction
This paper investigates the regular wave impact force on open-piled wharf deck by Artificial Neural Network. A three-layered neural network is employed and the units of input layer are wave period, T, incident...
-
Chapter and Conference Paper
Automatic Video Shot Boundary Detection Using Machine Learning
In this paper we present a machine learning system that can accurately predict the transitions between frames in a video sequence. We propose a set of novel features and describe how to use dominant features b...