{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2023,10,23]],"date-time":"2023-10-23T12:43:34Z","timestamp":1698065014209},"reference-count":13,"publisher":"Wiley","issue":"9","license":[{"start":{"date-parts":[[2007,3,22]],"date-time":"2007-03-22T00:00:00Z","timestamp":1174521600000},"content-version":"vor","delay-in-days":6289,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Systems &amp;amp; Computers in Japan"],"published-print":{"date-parts":[[1990,1]]},"abstract":"<jats:title>Abstract<\/jats:title><jats:p>This paper proposes a method of constructing a multilayered neural network, using the multiple logistic model (MLM). The model is a nonlinear multivariate analysis considering the output logistic function of each unit, which is used in the back\u2010propagation method (BP). The idea can be applied directly to the determination of the multilayered neural network structure. The model can also be utilized as a systematic method to introduce such information as pattern distribution into the neural network structure. Considering the speaker\u2010independent vowel recognition as the problem, this paper compares the results by the proposed method (MLM), the construction by the linear multiple regression analysis (MRA), the learning by BP with the weight being defined at random as the initial value, and the learning by BP with the initial weight determined by MLM or MRA. It is seen as a result that the recognition rate is the best when BP is applied after introducing the speaker distribution information by the proposed method. It is seen also that the computation time is reduced compared with the BP, with the initial weight being defined at random.<\/jats:p>","DOI":"10.1002\/scj.4690210908","type":"journal-article","created":{"date-parts":[[2007,7,7]],"date-time":"2007-07-07T19:33:12Z","timestamp":1183836792000},"page":"80-88","source":"Crossref","is-referenced-by-count":0,"title":["A method for designing neural networks using nonlinear multivariate analysis\u2014application to speaker\u2010independent vowel recognition"],"prefix":"10.1002","volume":"21","author":[{"given":"Toshio","family":"Irino","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Hideki","family":"Kawahara","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2007,3,22]]},"reference":[{"key":"e_1_2_1_2_2","doi-asserted-by":"publisher","DOI":"10.7551\/mitpress\/5236.001.0001"},{"key":"e_1_2_1_3_2","unstructured":"D. S.BroomheadandD.Lowe.Radial Basis Functions Multivariable Functional Interpolation and Adaptive Networks. RSRE Memorandum No. 4148 (March1988)."},{"key":"e_1_2_1_4_2","volume-title":"CUED\/F\u2010INFENG\/TR22","author":"Niranjan M.","year":"1988"},{"key":"e_1_2_1_5_2","unstructured":"H.KawaharaandT.Irino.A procedure for designing three\u2010layer neural networks which approximate arbitrary continuous mapping: Applications to Pattern Processing. Papers of Technical Group on Pattern Recognition and Understanding. I.E.I.C.E. Japan PRU88\u201054 (Sept.1988)."},{"key":"e_1_2_1_6_2","unstructured":"H.KawaharaandT.Irino.A procedure for designing three\u2010layer neural networks for pattern recognition applications. Tech. Report I.E.I.C.E. Japan SP88\u201086 (Oct.1988)."},{"key":"e_1_2_1_7_2","doi-asserted-by":"crossref","unstructured":"P.Gallinari S.Thiria andF.Souli\u00e9.Multilayer Perceptrons and Data Analysis. Proc. of the IEEE ICNN'88 pp.I\u2010391\u2013399(1988).","DOI":"10.1109\/ICNN.1988.23871"},{"key":"e_1_2_1_8_2","article-title":"Adaptation of Multiple Regression Coefficients and Recognition of Chinese Four Tones","volume":"1","author":"Li G.","year":"1988","journal-title":"Proc. J. Acoust. Soc., Japan"},{"key":"e_1_2_1_9_2","volume-title":"Handbook for Multivariate Analysis","author":"Yanai H.","year":"1986"},{"key":"e_1_2_1_10_2","volume-title":"Hearing and Speech","author":"I.E.C.E., Japan","year":"1980"},{"key":"e_1_2_1_11_2","volume-title":"Speech and Hearing in Communication","author":"Fletcher","year":"1972"},{"key":"e_1_2_1_12_2","article-title":"Digital simulation of basilar membrane by IT(Z) transform","volume":"1","author":"Kirihata T.","year":"1986","journal-title":"Proc. Acoust. Soc., Japan"},{"key":"e_1_2_1_13_2","article-title":"Vowel\u2010feature feature extraction from cochlear vibration by neural networks","volume":"3","author":"Irino T.","year":"1988","journal-title":"Proc. Acoust. Soc., Japan"},{"key":"e_1_2_1_14_2","article-title":"An analysis on auditory perception models for vowels using neural networks","volume":"2","author":"Irino T.","year":"1988","journal-title":"Proc. Acoust. Soc., Japan"}],"container-title":["Systems and Computers in Japan"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/api.wiley.com\/onlinelibrary\/tdm\/v1\/articles\/10.1002%2Fscj.4690210908","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1002\/scj.4690210908","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,22]],"date-time":"2023-10-22T20:24:01Z","timestamp":1698006241000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1002\/scj.4690210908"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[1990,1]]},"references-count":13,"journal-issue":{"issue":"9","published-print":{"date-parts":[[1990,1]]}},"alternative-id":["10.1002\/scj.4690210908"],"URL":"https:\/\/doi.org\/10.1002\/scj.4690210908","archive":["Portico"],"relation":{},"ISSN":["0882-1666","1520-684X"],"issn-type":[{"value":"0882-1666","type":"print"},{"value":"1520-684X","type":"electronic"}],"subject":[],"published":{"date-parts":[[1990,1]]}}}