| 講演名 | 2022-06-28 Joint-Conditional Mutual Information Based Feature Subset Selection for Remotely Sensed Hyperspectral Image Classification U A Md Ehsan Ali(Univ. Tsukuba), Keisuke Kameyama(Univ. Tsukuba), |
|---|---|
| PDFダウンロードページ |  PDFダウンロードページへ |
| 抄録(和) | Hundreds of contiguous bands of remotely sensed hyperspectral image (HSI) capture the spectral signatures of observed objects or materials on the earth’s surface. Although the HSI data is able to provide huge information with great details, it poses challenges to image analysis because of the high computational cost due to the large dimensionality of the feature space, redundancy in information, and curse of dimensionality. To overcome these difficulties, feature reduction techniques are used to extract informative features from hyperspectral images. This paper proposes an information-theoretic feature selection approach for selecting an informative feature subset considering the maximum of the minimum approach. The minimum of conditional mutual information based estimation is used to select a feature among the selected feature subset. This selected feature with the corresponding candidate feature is then exploited using the mutual information and joint mutualinformation based valuation to find the maximum relevance of the candidate features with the target classes. The effectiveness of the proposed approach, called joint-conditional mutual information for selecting informative feature (JCIF), is assessed by implementing it in some synthetic data and two remotely sensed HSI data. Several known feature selection algorithms are also used for comparison purposes. The results of the experiments with K-Nearest Neighbors and Support Vector Machine classifiers reveal that JCIF performs better in selecting informative features. |
| 抄録(英) | Hundreds of contiguous bands of remotely sensed hyperspectral image (HSI) capture the spectral signatures of observed objects or materials on the earth’s surface. Although the HSI data is able to provide huge information with great details, it poses challenges to image analysis because of the high computational cost due to the large dimensionality of the feature space, redundancy in information, and curse of dimensionality. To overcome these difficulties, feature reduction techniques are used to extract informative features from hyperspectral images. This paper proposes an information-theoretic feature selection approach for selecting an informative feature subset considering the maximum of the minimum approach. The minimum of conditional mutual information based estimation is used to select a feature among the selected feature subset. This selected feature with the corresponding candidate feature is then exploited using the mutual information and joint mutualinformation based valuation to find the maximum relevance of the candidate features with the target classes. The effectiveness of the proposed approach, called joint-conditional mutual information for selecting informative feature (JCIF), is assessed by implementing it in some synthetic data and two remotely sensed HSI data. Several known feature selection algorithms are also used for comparison purposes. The results of the experiments with K-Nearest Neighbors and Support Vector Machine classifiers reveal that JCIF performs better in selecting informative features. |
| キーワード(和) | Hyperspectral imaging / Feature selection / Mutual Information |
| キーワード(英) | Hyperspectral imaging / Feature selection / Mutual Information |
| 資料番号 | NC2022-16,IBISML2022-16 |
| 発行日 | 2022-06-20 (NC, IBISML) |
| 研究会情報 | |
| 研究会 | NC / IBISML / IPSJ-BIO / IPSJ-MPS |
|---|---|
| 開催期間 | 2022/6/27(から3日開催) |
| 開催地（和） | 琉球大学50周年記念館 |
| 開催地（英） | |
| テーマ（和） | 機械学習によるバイオデータマイニング、一般 |
| テーマ（英） | |
| 委員長氏名（和） | 山川 宏(東大) / 杉山 将(東大) |
| 委員長氏名（英） | Hiroshi Yamakawa(Univ of Tokyo) / Masashi Sugiyama(Univ. of Tokyo) |
| 副委員長氏名（和） | 田中 宏和(東京都市大学) / 神嶌 敏弘(産総研) / 津田 宏治(東大) |
| 副委員長氏名（英） | Hirokazu Tanaka(Tokyo City Univ.) / Toshihiro Kamishima(AIST) / Koji Tsuda(Univ. of Tokyo) |
| 幹事氏名（和） | 寺島 裕貴(NTT) / 西田 知史(NICT) / 岩田 具治(NTT) / 中村 篤祥(北大) |
| 幹事氏名（英） | Hiroki Terashima(NTT) / Satoshi Nishida(NICT) / Tomoharu Iwata(NTT) / Atsuyoshi Nakamura(Hokkaido Univ.) |
| 幹事補佐氏名（和） | 田和辻 可昌(早大) / 栗川 知己(関西医科大) / 河原 吉伸(阪大) / 鈴木 大慈(東工大) |
| 幹事補佐氏名（英） | Yoshimasa Tawatsuji(Waseda Univ.) / Tomoki Kurikawa(KMU) / Yoshinobu Kawahara(Osaka Univ.) / Taiji Suzuki(Tokyo Inst. of Tech.) |
| 講演論文情報詳細 | |
| 申込み研究会 | Technical Committee on Neurocomputing / Technical Committee on Infomation-Based Induction Sciences and Machine Learning / Special Interest Group on Bioinformatics and Genomics / Special Interest Group on Mathematical Modeling and Problem Solving |
|---|---|
| 本文の言語 | ENG |
| タイトル（和） | |
| サブタイトル（和） | |
| タイトル（英） | Joint-Conditional Mutual Information Based Feature Subset Selection for Remotely Sensed Hyperspectral Image Classification |
| サブタイトル（和） | |
| キーワード(1)（和/英） | Hyperspectral imaging / Hyperspectral imaging |
| キーワード(2)（和/英） | Feature selection / Feature selection |
| キーワード(3)（和/英） | Mutual Information / Mutual Information |
| 第 1 著者 氏名（和/英） | U A Md Ehsan Ali / U A Md Ehsan Ali |
| 第 1 著者 所属（和/英） | University of Tsukuba(略称：Univ. Tsukuba) University of Tsukuba(略称：Univ. Tsukuba) |
| 第 2 著者 氏名（和/英） | Keisuke Kameyama / Keisuke Kameyama |
| 第 2 著者 所属（和/英） | University of Tsukuba(略称：Univ. Tsukuba) University of Tsukuba(略称：Univ. Tsukuba) |
| 発表年月日 | 2022-06-28 |
| 資料番号 | NC2022-16,IBISML2022-16 |
| 巻番号（vol） | vol.122 |
| 号番号（no） | NC-89,IBISML-90 |
| ページ範囲 | pp.115-122(NC), pp.115-122(IBISML), |
| ページ数 | 8 |
| 発行日 | 2022-06-20 (NC, IBISML) |