The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. ex. Some numerals are expressed as "XNUMX".
Copyrights notice
The original paper is in English. Non-English content has been machine-translated and may contain typographical errors or mistranslations. Copyrights notice
Durante a execução de sistemas de software, seus dados de execução podem ser registrados. Ao explorar plenamente esses dados, os profissionais de software podem descobrir modelos comportamentais que descrevem a execução real do sistema de software subjacente. Os dados de execução de software não estruturados registrados podem ser muito complexos, abrangendo vários dias, etc. A aplicação de técnicas de descoberta existentes resulta em modelos semelhantes a espaguete, sem estrutura clara e sem informações valiosas para compreensão. Partindo da observação de que um sistema de software é composto por um conjunto de componentes lógicos, Liu et ai. propõem decompor o problema de descoberta de comportamento de software em problemas menores e independentes, descobrindo um modelo comportamental por componente em [1]. No entanto, a eficácia da abordagem proposta não é totalmente avaliada e comparada com as abordagens existentes. Neste artigo, avaliamos a qualidade (em termos de compreensibilidade/complexidade) dos modelos de comportamento de componentes descobertos de maneira quantitativa. Com base na avaliação, mostramos que esta abordagem pode reduzir a complexidade do modelo descoberto e proporcionar um melhor entendimento.
Cong LIU
Shandong University of Technology
The copyright of the original papers published on this site belongs to IEICE. Unauthorized use of the original or translated papers is prohibited. See IEICE Provisions on Copyright for details.
Copiar
Cong LIU, "Quantitative Evaluation of Software Component Behavior Discovery Approach" in IEICE TRANSACTIONS on Information,
vol. E104-D, no. 1, pp. 117-120, January 2021, doi: 10.1587/transinf.2020MPL0001.
Abstract: During the execution of software systems, their execution data can be recorded. By fully exploiting these data, software practitioners can discover behavioral models describing the actual execution of the underlying software system. The recorded unstructured software execution data may be too complex, spanning over several days, etc. Applying existing discovery techniques results in spaghetti-like models with no clear structure and no valuable information for comprehension. Starting from the observation that a software system is composed of a set of logical components, Liu et al. propose to decompose the software behavior discovery problem into smaller independent ones by discovering a behavioral model per component in [1]. However, the effectiveness of the proposed approach is not fully evaluated and compared with existing approaches. In this paper, we evaluate the quality (in terms of understandability/complexity) of discovered component behavior models in a quantitative manner. Based on evaluation, we show that this approach can reduce the complexity of the discovered model and gives a better understanding.
URL: https://global.ieice.org/en_transactions/information/10.1587/transinf.2020MPL0001/_p
Copiar
@ARTICLE{e104-d_1_117,
author={Cong LIU, },
journal={IEICE TRANSACTIONS on Information},
title={Quantitative Evaluation of Software Component Behavior Discovery Approach},
year={2021},
volume={E104-D},
number={1},
pages={117-120},
abstract={During the execution of software systems, their execution data can be recorded. By fully exploiting these data, software practitioners can discover behavioral models describing the actual execution of the underlying software system. The recorded unstructured software execution data may be too complex, spanning over several days, etc. Applying existing discovery techniques results in spaghetti-like models with no clear structure and no valuable information for comprehension. Starting from the observation that a software system is composed of a set of logical components, Liu et al. propose to decompose the software behavior discovery problem into smaller independent ones by discovering a behavioral model per component in [1]. However, the effectiveness of the proposed approach is not fully evaluated and compared with existing approaches. In this paper, we evaluate the quality (in terms of understandability/complexity) of discovered component behavior models in a quantitative manner. Based on evaluation, we show that this approach can reduce the complexity of the discovered model and gives a better understanding.},
keywords={},
doi={10.1587/transinf.2020MPL0001},
ISSN={1745-1361},
month={January},}
Copiar
TY - JOUR
TI - Quantitative Evaluation of Software Component Behavior Discovery Approach
T2 - IEICE TRANSACTIONS on Information
SP - 117
EP - 120
AU - Cong LIU
PY - 2021
DO - 10.1587/transinf.2020MPL0001
JO - IEICE TRANSACTIONS on Information
SN - 1745-1361
VL - E104-D
IS - 1
JA - IEICE TRANSACTIONS on Information
Y1 - January 2021
AB - During the execution of software systems, their execution data can be recorded. By fully exploiting these data, software practitioners can discover behavioral models describing the actual execution of the underlying software system. The recorded unstructured software execution data may be too complex, spanning over several days, etc. Applying existing discovery techniques results in spaghetti-like models with no clear structure and no valuable information for comprehension. Starting from the observation that a software system is composed of a set of logical components, Liu et al. propose to decompose the software behavior discovery problem into smaller independent ones by discovering a behavioral model per component in [1]. However, the effectiveness of the proposed approach is not fully evaluated and compared with existing approaches. In this paper, we evaluate the quality (in terms of understandability/complexity) of discovered component behavior models in a quantitative manner. Based on evaluation, we show that this approach can reduce the complexity of the discovered model and gives a better understanding.
ER -