Currently there is no model available that would facilitate the task of finding similar time series based on partial information that interest users. We studied a novel query problem class that we termed micro similar...
详细信息
In this paper, an incremental method for learning Bayesian networks based on evolutionary computing, IEMA, is put forward. IEMA introduces the evolutionary algorithm and EM algorithm into the process of incremental le...
详细信息
The technique of full text retrieval for modern Chinese has been studied for a long time, but the same cannot be said for ancient Chinese books, especially in China. This paper tries to find the characteristics of Chi...
详细信息
The technique of full text retrieval for modern Chinese has been studied for a long time, but the same cannot be said for ancient Chinese books, especially in China. This paper tries to find the characteristics of Chinese ancient books which can be used for information retrieval. Statistical analysis was carried out on ancient Chinese books of over 35,000,000 words, including most of the works in common use. Based on these experiments some characteristics of ancient Chinese works are analyzed and compared with modern Chinese, including the basic unit of ancient works, the proportion of double character words, sentence length, and the field dependency of ancient Chinese works. We then give conclusions on ancient Chinese which is useful for information retrieval, especially when building inverted indexes and selecting the index unit. Depending on the conclusion, a full-text retrieval system for ancient Chinese books has been designed and realized. It shows that statistical learning and analyses are a great help in ancient Chinese information retrieval.
An incremental method for learning Bayesian networks based on evolutionary computing, IEMA, is put forward. IEMA introduces the evolutionary algorithm and EM algorithm into the process of incremental learning; it can ...
详细信息
ISBN:
(纸本)0769511198
An incremental method for learning Bayesian networks based on evolutionary computing, IEMA, is put forward. IEMA introduces the evolutionary algorithm and EM algorithm into the process of incremental learning; it can avoid getting into local maxima, and also incrementally learn Bayesian networks with high accuracy in the presence of missing values and hidden variables. In addition, we improved the incremental learning process by N. Friedman and M. Goldschmidt (1997). The experimental results verified the validity of IEMA. In terms of storage cost, IEMA is comparable with the incremental learning method of Friedman et al, while it is more accurate.
A new method of Chinese grammar rules learning is put forward in this paper. The key point of this method is to use part-of-speech (POS), semantic and contextual information together in learning and expressing Chinese...
详细信息
A new method of Chinese grammar rules learning is put forward in this paper. The key point of this method is to use part-of-speech (POS), semantic and contextual information together in learning and expressing Chinese grammar rules. In this way, not only Context Free Grammar (CFG) rules can be learnt, but also the ambiguous structures in POS can be identified automatically. Furthermore, non-ambiguous semantic rules and forbidden rules can be produced from ambiguous rules by using semantic and contextual information. Experimental results demonstrate that the complexity of Chinese parsing is greatly reduced using the different rules learnt by our method.
It is well known, the design of an intelligent control engineering system often applies a top-down strategy, which emphasizes centralized control. But for life systems and life-like systems, adaptation is an important...
详细信息
It is well known, the design of an intelligent control engineering system often applies a top-down strategy, which emphasizes centralized control. But for life systems and life-like systems, adaptation is an important property of such systems, and the description of a life system is a bottom-up strategy, which emphasizes a distributed system. From the view point of complexity, the adaptation property of a system emerges by interaction between subsystems of the system, as well as interaction between subsystems and environment. The difference between the concepts of control and emergence is briefly discussed.
Chinese words classification based on statistics plays an important role in natural language processing, such as speech recognition, intelligent Chinese input method, and so on. We first do statistics and calculation ...
详细信息
Chinese words classification based on statistics plays an important role in natural language processing, such as speech recognition, intelligent Chinese input method, and so on. We first do statistics and calculation work on the large-scale corpus text, and then use the average mutual information as the global cost function for clustering all Chinese words into a predefined number of classes with a hybrid top-down splitting and bottom-up merging approach. The result of classification is encouraging and can be used in the class-based language model.
The study of an integrated human-machine discussion system for supporting economic decisions requires establishing a computer-supporting environment, which can discover the knowledge about economics from heterogeneous...
详细信息
The study of an integrated human-machine discussion system for supporting economic decisions requires establishing a computer-supporting environment, which can discover the knowledge about economics from heterogeneous information sources, and then utilize them to provide useful information for the experts in different locations. It also should allow real-time discussion among such economic experts and finally upgrade the overall correctness of economic decisions. ODIIPSA98 (Open Distributed intelligent Information Processing system Architecture '98), a pragmatic structural model of open intelligentsystems, is MAS-based and information (including multi-media information, knowledge and such like) accessing oriented. The paper first introduces the fundamental ideas and design principles of ODIIPSA98, and then moves to the computer supporting system for upgrading economic decisions, in which ODIIPSA98 serves as its basic framework. After some analyses and comparisons, it is obvious that, such a system, established under the instruction of ODIIPSA98, would gradually show its advantages of open flexibility, reliability, efficiency, and so on.
Presents a method to improve the performance of a Chinese character classifier. The method examines the candidates of an existing classifier using a linear decision function to select the most probable one. The algori...
详细信息
Presents a method to improve the performance of a Chinese character classifier. The method examines the candidates of an existing classifier using a linear decision function to select the most probable one. The algorithm together with a complete scheme has been proposed. The possible improvement of the performance has been estimated based on the experimental inspection of the separability of Chinese characters. The result shows that recognition accuracy can be increased dramatically. This means that the algorithm is practical.
Segmentation is the most difficult problem in a handwritten character recognition system and often contributes major errors to its performance. To reach a balance of speed and accuracy, a filter distinguishing a conne...
详细信息
ISBN:
(纸本)0769503187
Segmentation is the most difficult problem in a handwritten character recognition system and often contributes major errors to its performance. To reach a balance of speed and accuracy, a filter distinguishing a connected image from an isolated image is required for multi-stage segmentation. The Fourier spectrum is promising in this problem. Since it is influenced by the stroke width, we propose a Fourier spectrum standardization method. Based on the standardized Fourier spectrum, a set of features and a fine-tuned criterion are presented to classify connected/isolated images. A theoretical analysis proves their rationality. Experimental results demonstrate that this criterion is better than other methods.
暂无评论