{"created":"2023-05-15T14:21:33.672978+00:00","id":3257,"links":{},"metadata":{"_buckets":{"deposit":"496a00f1-51ea-4e49-a932-90014e8d94d8"},"_deposit":{"created_by":3,"id":"3257","owners":[3],"pid":{"revision_id":0,"type":"depid","value":"3257"},"status":"published"},"_oai":{"id":"oai:bunkyo.repo.nii.ac.jp:00003257","sets":["1:26:232"]},"author_link":["4216"],"item_5_biblio_info_13":{"attribute_name":"書誌情報","attribute_value_mlt":[{"bibliographicIssueDates":{"bibliographicIssueDate":"2002-01-01"},"bibliographicPageEnd":"67","bibliographicPageStart":"37","bibliographicVolumeNumber":"28","bibliographic_titles":[{"bibliographic_title":"情報研究"},{"bibliographic_title":"Information and Communication Studies"}]}]},"item_5_date_43":{"attribute_name":"作成日","attribute_value_mlt":[{"subitem_date_issued_datetime":"2011-02-23"}]},"item_5_description_12":{"attribute_name":"抄録","attribute_value_mlt":[{"subitem_description":"　遺伝(的)アルゴリズム(GA)は初期化・再生或いは選択・交叉・突然変異・終了判定の手順を踏んで実行される.GAでは,世代間の,各遺伝子型の出現についての相対頻度の時間的発展は進化差分方程式で記述されている.\n　本論文では,この遺伝(的)アルゴリズムにおける在来の適合度比例戦略場面での進化方程式を進化ポテンシャルを導入することによって微分方程式へと一般化される.提案された進化微分方程式を簡単な諸条件下で離散近似すれば,在来の進化差分方程式が得られる.この一般化進化方程式が,処理の対象とする問題のパターンを多段階にわたって変換しながら認識する手法における類似度変換に応用され,得られた認識法は多段階類似度変換認識法(multi-stage similarity-transformational recognition; MSSTR)と呼ばれる.\n　類似度分布の不動点を求める多段階類似度変換が1-0類似度分布(ある1つのカテゴリの類似度が1になり,他のすべてのカテゴリの類似度が0である類似度分布)へ収束するための諸条件が研究される.\n　多段階にわたってパターンモデル変換を行い,構造受精変換の不動点(あるカテゴリの代表パターンのモデル)を探索する形で想起し,認識する手法,つまり,不動点探索型・多段階パターンモデル帰納推理変換・想起認識法(SS-想起多段階認識法)においても,提案されるこの類似度変換は最終認識への収束を速めるのに用いることができる.SS認識法も類似度分布の不動点を求める認識動作を遂行するが,MSSTRは任意の認識の働きをシミュレートできる万能性のSS認識法の,1種の簡単化であることが明らかにされる.\n\\n　Genetic algorithms(GA) consists of initializations, reproductions or selections, crossovers ,mutations, and judgements of termination. Relative occurrences of each genotype between generations are described by an evolutionary equation of a finite-difference.\n　It is presented here that a conventional finite-difference equation of evolution about a proportional-selective strategy of a fitness using a propotional-selective strategy can be generalized to a differential equation by newly introducing an evolution potential. A discrete approximation of a differential equation presented here is the conventional equation under selected conditions. We apply this generalized evolutionary equation to successively transforming similarities between a pattern to be processed in question and typical patterns of categories. As a result a multi-stage similarity-transformational recognition(MSSTR) follows.\n　Subsequently we study some conditions for an algorithm which aims at seeking for a fixed point of distributions of occurrences using the multi-stage similarity-transformation to converge to 1-0 distribution which is characterized by the similarity between the pattern and a typical pattern of only category being 1, and similarities between the pattern and the typical patterns of other categories being 0.\n　A multi-stage similarity-transformation(MSST) can be used so as to speed up a convergence of SS method of associative recognition, which transforms pattern-models through multi-stage, and searches for a fixed-point(a model corresponding to a typical pattern of a category) of a structural fertilization transformation. It is called a method(SSMAR) of associative recognition which is a type of searching for a fixed-point by inductively reasoning the desired pattern-model through the multi-stage pattern-transformation. In the same way of that SSMAR operates the fixed-point of the distribution, MSSTR is a simplified method of SSMAR which has been proven to be universal in a sense of that any faculty of recognition can be simulated by SSMAR.","subitem_description_type":"Abstract"}]},"item_5_description_38":{"attribute_name":"フォーマット","attribute_value_mlt":[{"subitem_description":"application/pdf","subitem_description_type":"Other"}]},"item_5_source_id_19":{"attribute_name":"ISSN","attribute_value_mlt":[{"subitem_source_identifier":"03893367"}]},"item_5_text_39":{"attribute_name":"本文言語","attribute_value_mlt":[{"subitem_text_value":"日本語"}]},"item_5_text_42":{"attribute_name":"ID","attribute_value_mlt":[{"subitem_text_value":"BKSJ280005"}]},"item_5_text_7":{"attribute_name":"Author","attribute_value_mlt":[{"subitem_text_value":"Suzuki, Shoichi"}]},"item_5_text_8":{"attribute_name":"所属機関","attribute_value_mlt":[{"subitem_text_value":"文教大学情報学部"}]},"item_5_text_9":{"attribute_name":"Institution","attribute_value_mlt":[{"subitem_text_value":"Bunkyo University Faculty of Information and Communications"}]},"item_5_version_type_35":{"attribute_name":"著者版フラグ","attribute_value_mlt":[{"subitem_version_type":"VoR"}]},"item_creator":{"attribute_name":"著者","attribute_type":"creator","attribute_value_mlt":[{"creatorNames":[{"creatorName":"鈴木, 昇一"}],"nameIdentifiers":[{}]}]},"item_files":{"attribute_name":"ファイル情報","attribute_type":"file","attribute_value_mlt":[{"accessrole":"open_date","date":[{"dateType":"Available","dateValue":"2018-03-24"}],"displaytype":"detail","filename":"BKSJ280005.pdf","filesize":[{"value":"2.0 MB"}],"format":"application/pdf","licensetype":"license_note","mimetype":"application/pdf","url":{"label":"BKSJ280005.pdf","url":"https://bunkyo.repo.nii.ac.jp/record/3257/files/BKSJ280005.pdf"},"version_id":"36fdf54d-eadd-41ca-856c-f270837dd672"}]},"item_keyword":{"attribute_name":"キーワード","attribute_value_mlt":[{"subitem_subject":"類似度分布"},{"subitem_subject":"不動点"},{"subitem_subject":"遺伝的アルゴリズム"},{"subitem_subject":"進化ポテンシャル"},{"subitem_subject":"進化方程式"},{"subitem_subject":"SS-多段階認識"},{"subitem_subject":"distribution of similarities"},{"subitem_subject":"fixed point"},{"subitem_subject":"genetic algorithm"},{"subitem_subject":"evolutional potential"},{"subitem_subject":"evolutional equation"},{"subitem_subject":"SS-multi-stage recognition"}]},"item_language":{"attribute_name":"言語","attribute_value_mlt":[{"subitem_language":"jpn"}]},"item_resource_type":{"attribute_name":"資源タイプ","attribute_value_mlt":[{"resourcetype":"departmental bulletin paper","resourceuri":"http://purl.org/coar/resource_type/c_6501"}]},"item_title":"遺伝的アルゴリズムにおける適合度比例選択戦略を採用した進化方程式の,パターン多段階変換に基づく認識への応用","item_titles":{"attribute_name":"タイトル","attribute_value_mlt":[{"subitem_title":"遺伝的アルゴリズムにおける適合度比例選択戦略を採用した進化方程式の,パターン多段階変換に基づく認識への応用"},{"subitem_title":"An Application of an Evolutional Equation about a Proportional-Selective Strategy of a Fitness Employed in the Genetic Algorithm to a Recognition Based on Multi-Stage Transformation of Patterns"}]},"item_type_id":"5","owner":"3","path":["232"],"pubdate":{"attribute_name":"公開日","attribute_value":"2011-02-23"},"publish_date":"2011-02-23","publish_status":"0","recid":"3257","relation_version_is_last":true,"title":["遺伝的アルゴリズムにおける適合度比例選択戦略を採用した進化方程式の,パターン多段階変換に基づく認識への応用"],"weko_creator_id":"3","weko_shared_id":-1},"updated":"2023-05-16T16:44:39.627868+00:00"}