New Method For Automatic Generation Research Articles

Generation of a dictionary of abstract/concrete words by a multilayer neural network

Large dictionaries of abstract/concrete words were compiled for several languages by interviewing native speakers. The Russian dictionary contains only one thousand words. This article proposes a new method for automatic generation of a large (tens of thousands of words) Russian dictionary of abstract/concrete words by using neural networks trained on the Google Books Ngram corpus. Estimates of the quality of the dictionary compiled using this method are obtained. The correlation coefficient between the estimates obtained using a neural network for the level of word concreteness and the estimates obtained based on the native speakers‵ responds is 0.778.

A novel approach for automatic model-based test case generation

This paper proposes a new method for automatic generation of test cases using model based testing. As test model, class and state diagrams are used, and constraints are expressed using OCL. First, the state machineis converted into a mathematical representation in AMPL. Then, using a search algorithm and based upon coverage criteria, the abstract paths are selected from state machine. Second, using symbolic execution,the generated abstract path along with the constraints on this path is converted into the data of generated mathematical model. Third, the generated mathematical problem is solved with solvers that have interfacewith AMPL, and the test data is produced for each abstract test case. Finally, the generated test data and abstract paths are transformed into executable test cases. All-Transitions and All-States coverage criteria areused for conduct search algorithm, as well as the criteria for evaluate the quality of generated test cases. To validate the work, by utilizing various solvers, the test cases are generated for various problems.The proposed technique is implemented as a tool, named MoBaTeG. The tool shows good result in terms of test case generation execution time, test goals satisfaction rate, source code instructions coverage, andalso boundary values generation.

상품 속성정보를 이용한 분류체계 자동생성

온라인상에서 거래되는 상품들을 분류하고 관리하기 위해서는 많은 시간과 비용을 들여 상품분류체계를 유지하여야 한다. 일반적으로 상품을 다루는 모든 분야에서 분류체계는 분류전문가에 의하여 수동으로 관리되고 있으며 이는 경제적인 측면, 시간적인 측면에서 많은 낭비를 초래하게 된다. 현대사회에서는 산업의 급속한 발전으로 상품의 다양화 융합화 등이 활발하게 이루어져 상품을 효율적으로 관리하기 위한 분류체계의 필요성은 더더욱 증가하고 있다. 따라서 상품분류체계를 자동화 하고자 하는 연구들이 많이 진행되어 왔으며 이런 연구의 일환으로 본 논문에서는 분류체계를 자동으로 생성하는 방안을 제안한다. 각각의 상품은 속성의 집합이다 라는 관점에서 출발하여 각 상품, 즉 속성집합 간 존재하는 포함관계를 활용하여 계층 트리구조의 분류체계를 자동으로 생성하는 알고리즘을 제시하고 구현하였으며, 실험을 통하여 제안한 알고리즘의 실효성을 입증하였다. In order to classify and manage on-line trading goods, the product classification scheme must be maintained. In most systems for handling product information, the classification scheme is managed manually by experts, which in general incurs a lot of time and cost. Effective management of classification system becomes more important as rapid development of industry expedites diversity and convergence of goods and services. There have been many researches on developing classification scheme, and continuing in this line of research, this paper proposes a new method for automatic generation of product classification scheme. Our main idea starts from the concept that a product is a set of attributes, and we propose a novel algorithm for automatically creating hierarchical classification scheme by utilizing inclusive relationships between products. We then prove the effectiveness of proposed algorithm by conducting an experiment.

A Fast Method for Image Mosaicing using Geometric Hashing

The general problem of mosaicing is to create a single seamless image by aligning a series of spatially overlapped images. The result is an image with a field of view greater than that of a single image. Traditionally this research has been aimed at stitching together images taken by aerial or satellite reconnaissance equipment. With the advancement of personal computing equipment, the creation of image mosaic has entered the consumer market. Thus, automation of the process is an important issue. This paper proposes a new method for automatic generation of mosaics using Geometric Hashing. This speeds up the matching process. We show the application of our method on two important cases namely, rigid planar motion and panoramic mosaics. We provide experimental results in support of our proposed method.

Automatic creation of drug candidate structures based on receptor structure. Starting point for artificial lead generation.

We have developed a new method for automatic generation of drug candidate structures based on a known receptor structure. In our method, various structures which fit well to the receptor cavity are generated, by adding atoms one by one using a force field and random numbers. The usefulness of the program was exemplified by application to the E. coli dihydrofolate reductase system. From dozens of generated structures, we could obtain several promising new structures with considerable internal stability and having favorable interactions with the receptor cavity. It is expected that this method will become an essential starting point for artificial lead generation, which has been impossible so far.

Parallel scheduling of recursively defined arrays

This paper describes a new method of automatic generation of concurrent programs which construct arrays defined by sets of recursive equations. We assume that the time of computation of an array element is a linear combination of its indices, and we use integer programming to seek a succession of hyperplanes along which array elements can be computed concurrently. The method can be used to schedule equations involving variable length dependency vectors and mutually recursive arrays. Portions of the work reported here have been implemented in the PS automatic program generation system.