Semantic-Based Knowledge Categorization and Organization for Product Design Enterprises

Former knowledge engineering research aimed at boosting automatic reasoning.However recent knowledge management research focused on promoting the knowledge sharing and reusing among the people.Because of the different aims between the two directions,former knowledge representation schemata,such as rule based representation,frame from knowledge engineering research does not fit to the current knowledge management scenarios.In this paper,for the purpose of building knowledge management systems for product design enterprises,knowledge items are classified into seven types based on the semantics of their usage.Then their representations are discussed respectively.Based on the above classification,a knowledge representation meta-model and a basic domain ontology reference model for cooperative knowledge management systems are put forward.The reference model is an abstraction that can be reused and extended in knowledge management systems of different enterprises.Finally,the patterns of knowledge acquisition processes in cooperative knowledge management scenarios of product design processes are studied.     

Exploiting Local and Global Characteristics for Contrast Based Visual Saliency Detection

Visual saliency is an important cue in human visual system to identify salient region in the image;it can be useful in many applications including image retrieval,object recognition,image segmentation,etc.Image contrast has been used as an effective feature to detect visual salient region.However,the conventional contrast measures either in spectral domain or in spatial domain fail to give sufficient consideration towards the local and global characteristics of the image.This paper presents a visual saliency detection algorithm based on a novel contrast measurement.This measurement extracts the spectral information of image block using the 2D discrete Fourier transform(DFT),and combines with the total variation(TV)of image block in spatial domain.The proposed algorithm is used to perform salient region detection in the image,and compared with state-of-the-art algorithms.The experimental results from the MSRA dataset validate the effectiveness of the proposed algorithm.     

Automatic semantic analysis of software requirements through machine learning and ontology approach

Nowadays, software requirements are still mainly analyzed manually, which has many drawbacks (such as a large amount of labor consumption, inefficiency, and even inaccuracy of the results). The problems are even worse in domain analysis scenarios because a large number of requirements from many users need to be analyzed. In this sense, automatic analysis of software requirements can bring benefits to software companies. For this purpose, we proposed an approach to automatically analyze software requirement specifications (SRSs) and extract the semantic information. In this approach, a machine learning and ontology based semantic role labeling (SRL) method was used. First of all, some common verbs were calculated from SRS documents in the E-commerce domain, and then semantic frames were designed for those verbs. Based on the frames, sentences from SRSs were selected and labeled manually, and the labeled sentences were used as training examples in the machine learning stage. Besides the training examples labeled with semantic roles, external ontology knowledge was used to relieve the data sparsity problem and obtain reliable results. Based on the SemCor and WordNet corpus, the senses of nouns and verbs were identified in a sequential manner through the K-nearest neighbor approach. Then the senses of the verbs were used to identify the frame types. After that, we trained the SRL labeling classifier with the maximum entropy method, in which we added some new features based on word sense, such as the hypernyms and hyponyms of the word senses in the ontology. Experimental results show that this new approach for automatic functional requirements analysis is effective.     

Ant colony optimization for feature selection in software product lines

Software product lines （SPLs） are important software engineering techniques for creating a collection of similar software systems. Software products can be derived from SPLs quickly. The process of software product derivation can be modeled as feature selection optimization with resource constraints, which is a non- deterministic polynomial-time hard （NP-hard） problem. In this paper, we present an approach that using ant colony optimization to get an approximation solution of the problem in polynomial time. We evaluate our approach by comparing it to two important approximation techniques. One is filtered Cartesian flattening and modified heuristic （FCF＋M-HEU） algorithm, the other is genetic algorithm for optimized feature selection （GAFES）. The experimental results show that our approach performs 6% worse than FCF＋M-HEU with reducing much running time. Meanwhile, it performs 10% better than GAFES with taking more time.     

Ontology-based approach for legal provision retrieval

In this paper, we present an ontology-based approach for legal provision retrieval. The approach aims at assisting the man who knows little about legal knowledge to inquire appropriate provisions. Legal ontology and legal concept probability model are main functional components in our approach. Legal ontology is extracted from Chinese laws by the natural language processing (NLP) techniques. Legal concept probability model is built from corpus, and the model is used to bridge the gap between legal ontology and natural language inquiries.     

Multiobjective particle swarm optimization without the personal best

The personal best is an interesting topic, but little work has focused on whether it is still efficient for multiobjective particle swarm optimization. In dealing with single objective optimization problems, a single global best exists, so the personal best provides optimal diversity to prevent premature convergence. But in multi- objective optimization problems, the diversity provided by the personal best is less optimal, whereas the global archive contains a series of global bests, thus provides optimal diversity. If the algorithm excluding the personal best provides sufficient randomness, the personal best becomes worthless. Therefore we propose no personal best strategy that no longer uses the personal best when the global archive exceeds the population size. Experimental results validate the efficiency of our strategy.     

Towards a Formalized Ontology-Based Requirements Model

The goal of this paper is to take a further step towards an ontological approach for representing requirements information. The motivation for ontologies was discussed. The definitions of ontology and requirements ontology were given. Then, it presented a collection of informal terms, including four subject areas. It also discussed the formalization process of ontology. The underlying meta-ontology was determined, and the formalized requirements ontology was analyzed. This formal ontology is built to serve as a basis for requirements model. Finally, the implementation of software system was given.     

A multiscale superpixel-level salient object detection model using local-global contrast cue

The goal of salient object detection is to estimate the regions which are most likely to attract human’s visual attention. As an important image preprocessing procedure to reduce the computational complexity, salient object detection is still a challenging problem in computer vision. In this paper, we proposed a salient object detection model by integrating local and global superpixel contrast at multiple scales. Three features are computed to estimate the saliency of superpixel. Two optimization measures are utilized to refine the resulting saliency map. Extensive experiments with the state-of-the-art saliency models on four public datasets demonstrate the effectiveness of the proposed model.     

Genetic Algorithm Based Feature Selection and Parameter Optimization for Support Vector Regression Applied to Semantic Textual Similarity

Semantic textual similarity(STS) is a common task in natural language processing(NLP). STS measures the degree of semantic equivalence of two textual snippets. Recently, machine learning methods have been applied to this task, including methods based on support vector regression(SVR). However, there exist amounts of features involved in the learning process, part of which are noisy features and irrelative to the result.Furthermore, different parameters will significantly influence the prediction performance of the SVR model. In this paper, we propose genetic algorithm(GA) to select the effective features and optimize the parameters in the learning process, simultaneously. To evaluate the proposed approach, we adopt the STS-2012 dataset in the experiment. Compared with the grid search, the proposed GA-based approach has better regression performance.     

CASE STORAGE BASED ON RELATIONAL DATABASE

IntroductionCase- Based Reasoning ( CBR) ,as a relativelynew methodology,has attracted wide concern ofAI researchers since1 980 's.The number of suc-cessful applications of CBR is growing rapidly,especially in the fields of architecture and indus-try,e.g. ARCHI- II[1] for the architecture designof courthouse and MIDAS[2 ] for the conceptualdesign of aircraft.The currently prevailing CBD systems mostlytreat cases as instances of some predeterminedand static case template.Such an appro…