A pattern recognition approach to transistor array parameter variance

Autor(es)

Costa, Luciano da F. ^[1] ; Silva, Filipi N. ^[1] ; Comin, Cesar H. ^[2]

Afiliação do(s) autor(es)

^[1] Univ Sao Paulo, Sao Carlos Inst Phys, Sao Carlos, SP - Brazil

^[2] Univ Fed Sao Carlos, Dept Comp Sci, Sao Carlos, SP - Brazil

• Tipo de documento: Artigo Científico
• Fonte: PHYSICA A-STATISTICAL MECHANICS AND ITS APPLICATIONS; v. 499, p. 176-185, JUN 1 2018.
• Citações Web of Science: 0

Resumo

The properties of semiconductor devices, including bipolar junction transistors (BJTs), are known to vary substantially in terms of their parameters. In this work, an experimental approach, including pattern recognition concepts and methods such as principal component analysis (PCA) and linear discriminant analysis (LDA), was used to experimentally investigate the variation among BJTs belonging to integrated circuits known as transistor arrays. It was shown that a good deal of the devices variance can be captured using only two PCA axes. It was also verified that, though substantially small variation of parameters is observed for BJT from the same array, larger variation arises between BJTs from distinct arrays, suggesting the consideration of device characteristics in more critical analog designs. As a consequence of its supervised nature, LDA was able to provide a substantial separation of the BJT into clusters, corresponding to each transistor array. In addition, the LDA mapping into two dimensions revealed a clear relationship between the considered measurements. Interestingly, a specific mapping suggested by the PCA, involving the total harmonic distortion variation expressed in terms of the average voltage gain, yielded an even better separation between the transistor array clusters. All in all, this work yielded interesting results from both semiconductor engineering and pattern recognition perspectives. (c) 2018 Elsevier B.V. All rights reserved. (AU)

• Processo FAPESP: 15/18942-8 - Associando Redes Complexas com Espaços Efetivos de Atributos
• Beneficiário: Cesar Henrique Comin
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 15/22308-2 - Representações intermediárias em Ciência Computacional para descoberta de conhecimento
• Beneficiário: Roberto Marcondes Cesar Junior
• Modalidade de apoio: Auxílio à Pesquisa - Temático
• Processo FAPESP: 15/08003-4 - Abordagem de redes complexas em e-Science e dados dinâmicos
• Beneficiário: Filipi Nascimento Silva
• Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado
• Processo FAPESP: 11/50761-2 - Modelos e métodos de e-Science para ciências da vida e agrárias
• Beneficiário: Roberto Marcondes Cesar Junior
• Modalidade de apoio: Auxílio à Pesquisa - Temático