{"id":3853,"date":"2016-12-06T00:09:39","date_gmt":"2016-12-05T15:09:39","guid":{"rendered":"http:\/\/www.is.doshisha.ac.jp\/news\/?p=3853"},"modified":"2016-12-06T00:09:39","modified_gmt":"2016-12-05T15:09:39","slug":"ssci2016","status":"publish","type":"post","link":"https:\/\/is.doshisha.ac.jp\/news\/?p=3853","title":{"rendered":"SSCI2016"},"content":{"rendered":"

2016<\/span><\/span>\u5e74<\/span><\/span>12<\/span><\/span>\u6708<\/span><\/span>6<\/span><\/span>\u65e5\u304b\u3089<\/span><\/span>9<\/span><\/span>\u65e5\u304b\u3051\u3066\u30ae\u30ea\u30b7\u30e3\uff08\u30a2\u30c6\u30cd\uff09\u306e<\/span><\/span>Royal Olympic Hotel<\/span><\/span>\u306b\u3066\u958b\u50ac\u3055\u308c\u307e\u3057\u305f\uff0c<\/span><\/span>The 2016 IEEE Symposium Series on Computational Intelligence<\/span><\/span>\uff08<\/span><\/span>SSCI2016<\/span><\/span>\uff09\u306b\u53c2\u52a0\u3044\u305f\u3057\u307e\u3057\u305f\uff0e\u672c\u7814\u7a76\u5ba4\u304b\u3089\u306f\uff0c\u5ee3\u5b89\u5148\u751f\u3068\u90e1<\/span><\/span>(M1)<\/span><\/span>\u304c\u53c2\u52a0\u3057\uff0c\u767a\u8868\u5f62\u5f0f\u306f\u90e1\u304c\u53e3\u982d\u767a\u8868\u3067\u3057\u305f\uff0e\u767a\u8868\u6f14\u984c\u306f\u4ee5\u4e0b\u306e\u901a\u308a\u3067\u3059\uff0e<\/span><\/span>
\n“Region-of-Interest Extraction of fMRI data using Genetic Algorithms “<\/span><\/span>
\nSatoru HIWA, Yuuki KOHRI, Keisuke HACHISUKA, Tomoyuki HIROYASU<\/span><\/span>
\n\"\"<\/a>\"\"<\/a>
\nSSCI2016<\/span><\/span>\u306f\uff0c<\/span><\/span>IEEE Computational Intelligence Society<\/span><\/span>\u304c\u4e3b\u50ac\u3059\u308b\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30fc\u30a4\u30f3\u30c6\u30ea\u30b8\u30a7\u30f3\u30b9\u306b\u95a2\u3059\u308b\u4e16\u754c\u7684\u306b\u91cd\u8981\u306a\u5b66\u4f1a\u3067\uff0c\u7406\u8ad6\u3084\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u8a2d\u8a08\u3001\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u306a\u3069\u306e\u65b0\u3057\u3044\u6280\u8853\u306b\u3064\u3044\u3066\u30bb\u30c3\u30b7\u30e7\u30f3\u304c\u958b\u304b\u308c\uff0c\u69d8\u3005\u306a\u5206\u91ce\u306e\u8b1b\u6f14\u3092\u805e\u304f\u3053\u3068\u304c\u51fa\u6765\u307e\u3057\u305f\uff0e<\/span><\/span> \u79c1\u81ea\u8eab\u521d\u3081\u3066\u306e\u56fd\u969b\u5b66\u4f1a\u3067\u521d\u3081\u3066\u306e\u82f1\u8a9e\u3067\u306e\u53e3\u982d\u767a\u8868\u3068\u3044\u3046\u3053\u3068\u3082\u3042\u308a\uff0c\u3068\u3066\u3082\u7dca\u5f35\u3057\u307e\u3057\u305f\uff0e\u672c\u756a\u3067\u306f\uff0c\u7dca\u5f35\u304b\u3089\u306a\u304b\u306a\u304b\u7df4\u7fd2\u901a\u308a\u306b\u767a\u8868\u306f\u3067\u304d\u307e\u305b\u3093\u3067\u3057\u305f\u304c\uff0c\u5143\u6c17\u3088\u304f\u306f\u767a\u8868\u3067\u304d\u305f\u3068\u601d\u3044\u307e\u3059\uff0e\u3064\u305f\u306a\u3044\u82f1\u8a9e\u3067\u306f\u3042\u308a\u307e\u3057\u305f\u304c\u5185\u5bb9\u3082\u7406\u89e3\u3057\u3066\u3044\u305f\u3060\u3051\u305f\u3088\u3046\u3067\uff0c\u591a\u304f\u306e\u8cea\u554f\u3082\u9802\u304d\u3068\u3066\u3082\u5145\u5b9f\u3057\u305f\u767a\u8868\u3068\u306a\u308a\u307e\u3057\u305f\uff0e\u4eca\u56de\u521d\u3081\u3066\u306e\u56fd\u969b\u5b66\u4f1a\u3067\uff0c\u6d77\u5916\u7d4c\u9a13\u306e\u5c11\u306a\u3044\u79c1\u306b\u3068\u3063\u3066\u306f\u5168\u3066\u304c\u8cb4\u91cd\u306a\u7d4c\u9a13\u3068\u306a\u308a\u307e\u3057\u305f\uff0e\u3053\u306e\u7d4c\u9a13\u3092\u3082\u3068\u306b\u4eca\u5f8c\u3082\u3088\u308a\u4e00\u5c64\u9811\u5f35\u3063\u3066\u3044\u304d\u305f\u3044\u3068\u601d\u3044\u307e\u3057\u305f\uff0e<\/span><\/span>
\n\"\"<\/a>
\n\u00a0<\/a>
\n\u3010\u6587\u8cac\uff1aM1 \u90e1\u3011
\n
\n\u5b66\u4f1a\u53c2\u52a0\u5831\u544a\u66f8<\/strong><\/p>\n\n\n\n\n\n\n\n\n\n\n
\u00a0<\/strong>
\n\u5831\u544a\u8005\u6c0f\u540d<\/strong><\/td>\n		 
\n\u90e1\u3000\u60a0\u5e0c<\/td>\n<\/tr>\n
\u767a\u8868\u8ad6\u6587\u30bf\u30a4\u30c8\u30eb<\/strong><\/td>\n\u907a\u4f1d\u7684\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u7528\u3044\u305ffMRI\u30c7\u30fc\u30bf\u306b\u304a\u3051\u308b\u95a2\u5fc3\u9818\u57df\u306e\u62bd\u51fa<\/td>\n<\/tr>\n
\u767a\u8868\u8ad6\u6587\u82f1\u30bf\u30a4\u30c8\u30eb<\/strong><\/td>\nRegion-of-Interest Extraction of fMRI data using Genetic Algorithms<\/td>\n<\/tr>\n
\u8457\u8005<\/strong><\/td>\nSatoru HIWA, Yuuki KOHRI, Keisuke HACHISUKA, Tomoyuki HIROYASU<\/td>\n<\/tr>\n
\u4e3b\u50ac<\/strong><\/td>\nThe IEEE Computational Intelligence Society<\/td>\n<\/tr>\n
\u8b1b\u6f14\u4f1a\u540d<\/strong><\/td>\nThe 2016 IEEE Symposium Series on Computational Intelligence
\n\uff08http:\/\/ssci2016.cs.surrey.ac.uk\/\uff09<\/td>\n<\/tr>\n
\u4f1a\u5834<\/strong><\/td>\nRoyal Olympic Hotel (ATHENS, GREECE)<\/td>\n<\/tr>\n
\u958b\u50ac\u65e5\u7a0b<\/strong><\/td>\n2016\/12\/06-2016\/12\/09<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

 
\n 
\n <\/p>\n

    \n
  1. \u8b1b\u6f14\u4f1a\u306e\u8a73\u7d30<\/li>\n<\/ol>\n

    2016\/12\/06\u304b\u30892016\/12\/09\u306b\u304b\u3051\u3066\uff0c\u30a2\u30c6\u30cd\uff08\u30ae\u30ea\u30b7\u30e3\uff09\u306eRoyal Olympic Hotel\u306b\u3066\u958b\u50ac\u3055\u308c\u307e\u3057\u305f2016 IEEE Symposium Series on Computational Intelligence\u306b\u53c2\u52a0\u3044\u305f\u3057\u307e\u3057\u305f\uff0e\u672c\u7814\u7a76\u5ba4\u304b\u3089\u306f\uff0c\u90e1(M1)\u3068\u5ee3\u5b89\u5148\u751f\u306e\u8a082\u540d\u304c\u53c2\u52a0\u3044\u305f\u3057\u307e\u3057\u305f\uff0e
    \n\u3053\u306e\u5b66\u4f1a\u306f\uff0cIEEE Computational Intelligence Society\u304c\u4e3b\u50ac\u3059\u308b\u30b3\u30f3\u30d4\u30e5\u30fc\u30bf\u30fc\u30a4\u30f3\u30c6\u30ea\u30b8\u30a7\u30f3\u30b9\u306b\u95a2\u3059\u308b\u4e16\u754c\u7684\u306b\u91cd\u8981\u306a\u5b66\u4f1a\u3067\uff0c\u7406\u8ad6\u3084\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u8a2d\u8a08\u3001\u30a2\u30d7\u30ea\u30b1\u30fc\u30b7\u30e7\u30f3\u306a\u3069\u69d8\u3005\u306a\u5206\u91ce\u306e\u65b0\u3057\u3044\u6280\u8853\u306b\u3064\u3044\u3066\u30bb\u30c3\u30b7\u30e7\u30f3\u304c\u958b\u304b\u308c\uff0c\u69d8\u3005\u306a\u5206\u91ce\u306e\u65b9\u3005\u304c\u96c6\u307e\u3063\u3066\u3044\u307e\u3057\u305f\uff0e
    \n 
    \n <\/p>\n

      \n
    1. \u7814\u7a76\u767a\u8868\n
        \n
      • \u767a\u8868\u6982\u8981<\/li>\n<\/ul>\n<\/li>\n<\/ol>\n

        \u79c1\u306f7\u65e5\u5348\u524d\u306b\uff0c\u753b\u50cf\u3084\u30d1\u30bf\u30fc\u30f3\u8a8d\u8b58\u306b\u304a\u3051\u308b\u7279\u5fb4\u5206\u6790\u3001\u9078\u629e\u3001\u5b66\u7fd2\u306e\u30bb\u30c3\u30b7\u30e7\u30f3\u300cFASLIP Session 1\u300d\u306b\u53c2\u52a0\u3044\u305f\u3057\u307e\u3057\u305f\uff0e\u767a\u8868\u306e\u5f62\u5f0f\u306f\u53e3\u982d\u767a\u886820\u5206(\u8cea\u7591\u5fdc\u7b54\u542b\u3080)\u3067\u3057\u305f\uff0e
        \n\u4eca\u56de\u306f\uff0c\u907a\u4f1d\u7684\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u7528\u3044\u305f\u7279\u5fb4\u91cf\u9078\u629e\u306b\u3088\u308afMRI\u30c7\u30fc\u30bf\u304b\u3089\u91cd\u8981\u306a\u8133\u6a5f\u80fd\u30cd\u30c3\u30c8\u30ef\u30fc\u30af\u3092\u62bd\u51fa\u3059\u308b\u624b\u6cd5\u306e\u691c\u8a0e\u306b\u3064\u3044\u3066\u767a\u8868\u81f4\u3057\u307e\u3057\u305f\uff0e\u4ee5\u4e0b\u306b\u6284\u9332\u3092\u8a18\u8f09\u81f4\u3057\u307e\u3059\uff0e<\/p>\n\n\n\n
        Functional connectivity, which is indicated by time course correlations of brain activities among different brain regions, is one of the most useful metrics to represent human brain states. In functional connectivity analysis (FCA), the whole brain is parcellated into a certain number of regions based on anatomical atlases, and the mean time series of brain activities are calculated. Then, the correlation between mean signals of two regions is repeatedly calculated for all combinations of regions, and finally, we obtain the correlation matrix of the whole brain. FCA allows us to understand which regions activate cooperatively during specific stimulus or tasks. In this study, we attempt to represent human brain states using functional connectivity as feature vectors. As there are a number of brain regions, it is difficult to determine which regions are prominent to represent the brain state. Therefore, we proposed an automatic region of- interest (ROI) extraction method to classify human brain states. Time-series brain activities were measured by functional magnetic resonance imaging (fMRI), and FCA was performed. Each element of the correlation matrix was used as a feature vector for brain state classification, and element characteristics were learned using supervised learning methods. The elements used as feature vectors, i.e., ROIs, were determined automatically using a genetic algorithm to maximize the classification accuracy of brain states. fMRI data measured during two emotional conditions, i.e., pleasant and unpleasant emotions, were used to show the effectiveness of the proposed method. Numerical experiments revealed that the proposed method could extract the superior frontal gyrus, orbitofrontal cortex, cuneus, cerebellum, and cerebellar vermis as ROIs associated with pleasant and unpleasant emotions.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

         <\/p>\n

          \n
        • \u8cea\u7591\u5fdc\u7b54<\/li>\n<\/ul>\n

          \u4eca\u56de\u306e\u8b1b\u6f14\u767a\u8868\u3067\u306f\uff0c\u4ee5\u4e0b\u306e\u3088\u3046\u306a\u8cea\u7591\u3092\u53d7\u3051\u307e\u3057\u305f\uff0e
          \n\u82f1\u8a9e\u306b\u3088\u308b\u8cea\u7591\u5fdc\u7b54\u3067\u3042\u3063\u305f\u3081\uff0c\u79c1\u81ea\u8eab\u3067\u56de\u7b54\u3059\u308b\u3053\u3068\u304c\u51fa\u6765\u305a\uff0c\u5148\u751f\u304c\u4ee3\u308f\u308a\u306b\u56de\u7b54\u3057\u3066\u304f\u3060\u3055\u3044\u307e\u3057\u305f\uff0e
          \n 
          \n\u30fb\u8cea\u554f\u5185\u5bb9<\/strong>1<\/strong>
          \nGA\u306f\u4f55\u4e16\u4ee3\u884c\u3063\u3066\u3044\u308b\u306e\u304b\uff1f\u3068\u3044\u3046\u3082\u306e\u3067\u3057\u305f\uff0e
          \n\u3053\u306e\u8cea\u554f\u306b\u5bfe\u3057\u3066\uff0c200\u4e16\u4ee3\uff0e\u3068\u56de\u7b54\u3057\u3066\u3044\u305f\u3060\u304d\u307e\u3057\u305f\uff0e
          \n 
          \n\u30fb\u8cea\u554f\u5185\u5bb9<\/strong>2<\/strong>
          \nGA\u3092\u56de\u3059\u306e\u306b\u3069\u308c\u3060\u3051\u6642\u9593\u304c\u304b\u304b\u308b\u306e\u304b\uff1f\u3068\u3044\u3046\u3082\u306e\u3067\u3057\u305f\uff0e
          \n\u3053\u306e\u8cea\u554f\u306b\u5bfe\u3057\u3066\u306f,\u7d0430\u5206\u524d\u5f8c\uff0e\u3068\u56de\u7b54\u3057\u3066\u3044\u305f\u3060\u304d\u307e\u3057\u305f\uff0e
          \n 
          \n\u30fb\u8cea\u554f\u5185\u5bb9<\/strong>3<\/strong>
          \n\u985e\u4f3c\u5ea6\u306e\u8a08\u7b97\u306f\u3069\u3046\u3057\u3066\u3044\u308b\u306e\u304b\uff1f\u3068\u3044\u3046\u3082\u306e\u3067\u3057\u305f\uff0e
          \n\u3053\u306e\u8cea\u554f\u306b\u5bfe\u3057\u3066\u306f\uff0c\u304a\u305d\u3089\u304fcos\u8a08\u7b97\u3067\u3042\u308b\uff0e\u3068\u56de\u7b54\u3057\u3066\u3044\u305f\u3060\u304d\u307e\u3057\u305f\uff0e
          \n <\/p>\n

            \n
          • \u611f\u60f3<\/li>\n<\/ul>\n

            \u521d\u3081\u3066\u306e\u56fd\u969b\u5b66\u4f1a\u3067\u521d\u3081\u3066\u306e\u82f1\u8a9e\u3067\u306e\u53e3\u982d\u767a\u8868\u3068\u3044\u3046\u3053\u3068\u3082\u3042\u308a\uff0c\u3068\u3066\u3082\u7dca\u5f35\u3057\u307e\u3057\u305f\uff0e\u672c\u756a\u3067\u306f\uff0c\u7dca\u5f35\u304b\u3089\u306a\u304b\u306a\u304b\u7df4\u7fd2\u901a\u308a\u306b\u767a\u8868\u306f\u3067\u304d\u307e\u305b\u3093\u3067\u3057\u305f\u304c\uff0c\u5143\u6c17\u3088\u304f\u306f\u767a\u8868\u3067\u304d\u305f\u3068\u601d\u3044\u307e\u3059\uff0e\u3064\u305f\u306a\u3044\u82f1\u8a9e\u3067\u306f\u3042\u308a\u307e\u3057\u305f\u304c\u5185\u5bb9\u3082\u7406\u89e3\u3057\u3066\u3044\u305f\u3060\u3051\u305f\u3088\u3046\u3067\uff0c\u591a\u304f\u306e\u8cea\u554f\u3082\u9802\u304d\u307e\u3057\u305f\uff0e\u3057\u304b\u3057\uff0c\u82f1\u8a9e\u3092\u306a\u304b\u306a\u304b\u805e\u304d\u53d6\u308b\u3053\u3068\u304c\u51fa\u6765\u305a\uff0c\u7b54\u3048\u306a\u308c\u306a\u304b\u3063\u305f\u3053\u3068\u304c\u3068\u3066\u3082\u6b8b\u5ff5\u3067\u3057\u305f\uff0e\u4eca\u56de\u521d\u3081\u3066\u306e\u56fd\u969b\u5b66\u4f1a\u3067\uff0c\u6d77\u5916\u7d4c\u9a13\u306e\u5c11\u306a\u3044\u79c1\u306b\u3068\u3063\u3066\u306f\u5168\u3066\u304c\u8cb4\u91cd\u306a\u7d4c\u9a13\u3068\u306a\u308a\u307e\u3057\u305f\uff0e\u6d77\u5916\u306e\u65b9\u306e\u6c17\u3055\u304f\u3055\u306f\u672c\u5f53\u306b\u898b\u7fd2\u3046\u3079\u304d\u3082\u306e\u3067\u3042\u308b\u3068\u611f\u3058\uff0c\u4eca\u5f8c\u306f\u3082\u3063\u3068\u7a4d\u6975\u7684\u306b\u30b3\u30df\u30e5\u30cb\u30b1\u30fc\u30b7\u30e7\u30f3\u3092\u3068\u3063\u3066\u3044\u304f\u5fc5\u8981\u304c\u3042\u308b\u3068\u611f\u3058\u307e\u3057\u305f\uff0e\u307e\u305f\uff0c\u79c1\u306f\u82f1\u8a9e\u304c\u82e6\u624b\u306a\u305f\u3081\uff0c\u4ed6\u306e\u65b9\u306e\u767a\u8868\u3092\u805e\u3044\u3066\u3044\u3066\u3082\u306a\u304b\u306a\u304b\u805e\u304d\u53d6\u308b\u3053\u3068\u304c\u51fa\u6765\u306a\u3044\u305f\u3081\uff0c\u30b9\u30e9\u30a4\u30c9\u306e\u308f\u304b\u308a\u3084\u3059\u3055\u3084\u898b\u6613\u3055\u306e\u91cd\u8981\u6027\u3092\u3088\u308a\u611f\u3058\u307e\u3057\u305f\uff0e\u3057\u304b\u3057\u672c\u5b66\u4f1a\u3067\u306f\uff0c\u69d8\u3005\u306a\u5206\u91ce\u306e\u304a\u8a71\u3092\u805e\u304f\u3053\u3068\u304c\u51fa\u6765\uff0c\u3068\u3066\u3082\u9762\u767d\u304b\u3063\u305f\u3067\u3059\uff0e\u6b21\u56de\u306f\u82f1\u8a9e\u3092\u3088\u308a\u52c9\u5f37\u3057\u3066\u69d8\u3005\u306a\u4eba\u3068\u7a4d\u6975\u7684\u306b\u4ea4\u6d41\u3067\u304d\u308b\u3088\u3046\u306b\u3057\u305f\u3044\u3068\u601d\u3044\u307e\u3057\u305f\u3000\uff0e
            \n <\/p>\n

              \n
            1. \u8074\u8b1b<\/li>\n<\/ol>\n

              \u4eca\u56de\u306e\u8b1b\u6f14\u4f1a\u3067\u306f\uff0c\u4e0b\u8a18\u306e4\u4ef6\u306e\u767a\u8868\u3092\u8074\u8b1b\u3057\u307e\u3057\u305f\uff0e
              \n <\/p>\n\n\n\n
              \u767a\u8868\u30bf\u30a4\u30c8\u30eb\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a\u3000Quality Estimation for Japanese Haiku Poems Using Neural Network
              \n\u8457\u8005\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a Shinji Kikuchi, Keizo Kato, Junya Saito, Seiji Okura, Kentaro Murase, Takaya Yamamoto, Akira Nakagawa
              \n\u30bb\u30c3\u30b7\u30e7\u30f3\u540d\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a CIHLI Session 4
              \nAbstruct\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a We propose a method to estimate the artistic quality of Haiku (Japanese style short poem) texts using a machine learning approach. Based on the assumption that the artistry of a text stems from its sound factors as well as its meanings, we first constructed two types of vector models, a word-based model and a syllable-based model, converted from Haiku texts. Next, we conducted machine learning for these two models using a convolutional neural network to construct a Haiku quality estimation function. We then evaluated the precision of quality estimation for 40,000 Japanese Haiku poems obtained from a Haiku community site, assuming that the number of \u201clikes\u201d given from viewers to a Haiku corresponds to its artistic quality. Through the experiment, we confirmed that by conducting a quality estimation based on the consensus between different models, we can improve the precision of quality estimation up to 0.64. We also found that if we evaluate Haiku poems for which we have high confidence in quality estimation certainty, the F-measure of the estimation improved from 0.57 to 0.64.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

              \u3053\u306e\u767a\u8868\u306f\uff0c\u6a5f\u68b0\u5b66\u7fd2\u3092\u4f7f\u3063\u3066\u4ff3\u53e5\u306e\u82b8\u8853\u7684\u306a\u30af\u30aa\u30ea\u30c6\u30a3\u3092\u8a55\u4fa1\u3059\u308b\u624b\u6cd5\u306e\u63d0\u6848\u3092\u884c\u3063\u3066\u3044\u307e\u3057\u305f\uff0e\u307e\u305a\uff0c\u4ff3\u53e5\u304b\u3089\u8a00\u8449\u30d9\u30fc\u30b9\u306e\u30e2\u30c7\u30eb\u3068\u97f3\u7bc0\u30d9\u30fc\u30b9\u306e\u30e2\u30c7\u30eb\u3092\u4f5c\u308a\uff0c convolutional neural network\u3092\u4f7f\u7528\u3057\u3066\u3053\u308c\u3089\u306e\u30e2\u30c7\u30eb\u306e\u6a5f\u68b0\u5b66\u7fd2\u3092\u884c\u3063\u3066\u3044\u307e\u3057\u305f\uff0e\u305d\u3057\u3066\uff0c\u4ff3\u53e5\u30b3\u30df\u30e5\u30cb\u30c6\u30a3\u30b5\u30a4\u30c8\u306740,000\u306e\u4ff3\u53e5\u306b\u5bfe\u3057\u3066\u201dlike\u201d\u3092\u3082\u3068\u306b\u54c1\u8cea\u8a55\u4fa1\u30fb\u5b66\u7fd2\u3092\u884c\u3044\uff0c\u65b0\u3057\u3044\u4ff3\u53e5\u306b\u5bfe\u3057\u3066\u8a55\u4fa1\u5b9f\u9a13\u3092\u884c\u3063\u3066\u3044\u307e\u3057\u305f\uff0e\u8eab\u8fd1\u306a\u4ff3\u53e5\u3092\u7814\u7a76\u5bfe\u8c61\u306b\u3057\u3066\u304a\u308a\uff0c\u9762\u767d\u3044\u3068\u601d\u3044\u307e\u3057\u305f\uff0e\u4ff3\u53e5\u306f\u65e5\u672c\u72ec\u81ea\u306e\u3082\u306e\u306a\u306e\u3067\uff0c\u7814\u7a76\u3092\u9032\u3081\u308c\u3070\u5916\u56fd\u8a9e\u3068\u9055\u3044\uff0c\u65e5\u672c\u8a9e\u306e\u7279\u5fb4\u306a\u3069\u3082\u8003\u3048\u3089\u308c\uff0c\u7ffb\u8a33\u6a5f\u80fd\u306a\u3069\u306b\u3082\u5fdc\u7528\u3067\u304d\u308b\u6df1\u3044\u7814\u7a76\u3067\u306f\u306a\u3044\u304b\u3068\u611f\u3058\u307e\u3057\u305f\uff0e
              \n 
              \n <\/p>\n\n\n\n
              \u767a\u8868\u30bf\u30a4\u30c8\u30eb\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a\u3000Constructing a Human-like agent for the Werewolf Game using a psychological model based multiple perspectives
              \n\u8457\u8005\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a Noritsugu Nakamura, Michimasa Inaba, Kenichi Takahashi, Fujio Toriumi, Hirotaka Osawa, Daisuke Katagami, Kousuke Shinoda
              \n\u30bb\u30c3\u30b7\u30e7\u30f3\u540d\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a CIHLI Session 4
              \nAbstruct\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a In this paper, we focus on the Werewolf\u00a0 Game. The Werewolf Game is an advanced communication-game in which winning or losing is directly linked to one\u2019s success or failure in communication. Therefore, we expect exponential developments in artificial intelligence by studying the Werewolf Game. In this current study, we propose a psychological model that considers multiple perspectives to model the play of a human such as inferring the intention of the other side. As one of the psychological models, we constructed a \u201cone\u2019s self model\u201d that models the role of others as viewed from their own viewpoint. In addition, to determine whether one\u2019s opinion is reliable after inferring other\u2019s intentions, we also constructed an \u201cothers models\u201d that models the role of others as viewed form their viewpoints. Combining these models, we showed through experimentation that a combined approach achieved better results, i.e., higher win percentages.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

              \u3053\u306e\u767a\u8868\u3067\u306f\uff0c\u8fd1\u5e74\u6d41\u884c\u3057\u3066\u3044\u308b\u52dd\u3061\u8ca0\u3051\u306b\u30b3\u30df\u30e5\u30cb\u30b1\u30fc\u30b7\u30e7\u30f3\u304c\u76f4\u63a5\u95a2\u4fc2\u3057\u3066\u3044\u308b\u4eba\u72fc\u30b2\u30fc\u30e0\u306b\u3064\u3044\u3066\u30d5\u30a9\u30fc\u30ab\u30b9\u3057\u3066\u3044\u307e\u3057\u305f\uff0e\u672c\u7814\u7a76\u3067\u306f\uff0c\u76f8\u624b\u5074\u306e\u610f\u56f3\u3092\u63a8\u8ad6\u3059\u308b\u3088\u3046\u306a\u30d7\u30ec\u30fc\u3092\u30e2\u30c7\u30eb\u5316\u3059\u308b\u305f\u3081\u306b\u591a\u6570\u306e\u8996\u70b9\u3092\u8003\u616e\u3057\u305f\u5fc3\u7406\u7684\u306a\u30e2\u30c7\u30eb\u3092\u63d0\u6848\u3057\u3066\u3044\u307e\u3057\u305f\uff0e\u5fc3\u7406\u7684\u306a\u30e2\u30c7\u30eb\u306e1\u3064\u3068\u3057\u3066\uff0c\u5f7c\u3089\u81ea\u8eab\u306e\u8996\u70b9\u304b\u3089\u898b\u305f\u4ed6\u306e\u5f79\u5272\u3092\u30e2\u30c7\u30eb\u5316\u3059\u308b\u300cone\u2019s self model\u300d\u3092\u4f5c\u6210\u3057\uff0c\u52a0\u3048\u3066\u305d\u306e\u4eba\u306e\u610f\u898b\u304c\u4ed6\u306e\u610f\u56f3\u3092\u63a8\u8ad6\u3057\u305f\u5f8c\u306b\u4fe1\u983c\u3067\u304d\u308b\u304b\u3069\u3046\u304b\u6c7a\u5b9a\u3059\u308b\u305f\u3081\u306b\uff0c\u4ed6\u306e\u4eba\u306e\u8996\u70b9\u304b\u3089\u898b\u305f\u4ed6\u306e\u5f79\u5272\u3092\u30e2\u30c7\u30eb\u5316\u3059\u308b\u300cothers models\u300d\u3082\u4f5c\u6210\u3057\u3066\u3044\u307e\u3057\u305f\uff0e\u3053\u308c\u3089\u306e\u30e2\u30c7\u30eb\u3092\u7d44\u307f\u5408\u308f\u305b\u308b\u3053\u3068\u3067\u9ad8\u3044\u52dd\u7387\u3092\u5f97\u305f\u3068\u5b9f\u9a13\u3092\u901a\u3057\u3066\u793a\u3057\u3066\u3044\u307e\u3057\u305f\uff0e\u3053\u306e\u7814\u7a76\u3092\u805e\u304d\uff0c\u5fc3\u7406\u30b2\u30fc\u30e0\u3068\u3057\u3066\u8003\u3048\u3066\u3044\u305f\u4eba\u72fc\u30b2\u30fc\u30e0\u3082\u8ad6\u7406\u7684\u306b\u8003\u3048\u308b\u3053\u3068\u3067\u52dd\u7387\u3092\u4e0a\u3052\u308b\u3053\u3068\u304c\u51fa\u6765\u308b\u306e\u3060\u3068\u6539\u3081\u3066\u611f\u3058\u307e\u3057\u305f\uff0e\u8eab\u8fd1\u306a\u30b2\u30fc\u30e0\u306b\u5bfe\u3057\u3066\u7591\u554f\u3092\u62b1\u304d\uff0c\u7814\u7a76\u5bfe\u8c61\u3068\u3059\u308b\u8003\u3048\u65b9\u306f\u7d20\u6674\u3089\u3057\u3044\u3068\u601d\u3044\u307e\u3057\u305f\uff0e\u3053\u306e\u7814\u7a76\u304c\u9032\u3081\u3070\uff0c\u4eba\u5de5\u77e5\u80fd\u306e\u30b3\u30df\u30e5\u30cb\u30b1\u30fc\u30b7\u30e7\u30f3\u80fd\u529b\u30821\u5bfe1\u3067\u306f\u306a\u304f\uff0c\u4ed6\u306e\u8981\u56e0\u3082\u8003\u616e\u3057\u305f\u30b3\u30df\u30e5\u30cb\u30b1\u30fc\u30b7\u30e7\u30f3\u306b\u3057\u3066\u3044\u304f\u3053\u3068\u304c\u51fa\u6765\u308b\u306e\u3067\u306f\u306a\u3044\u304b\u3068\u611f\u3058\u307e\u3057\u305f\uff0e
              \n <\/p>\n\n\n\n
              \u767a\u8868\u30bf\u30a4\u30c8\u30eb\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a\u3000Eye Movements as Information Markers in EEG Data
              \n\u8457\u8005\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a Sherif M. Abdelfattah, Kathryn E. Merrick, Hussein A. Abbass
              \n\u30bb\u30c3\u30b7\u30e7\u30f3\u540d\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a CIHLI Session 4
              \nAbstruct\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a\u3000Artifacts such as voluntarily and involuntarily muscle movements are usually seen as a source of noise in EEG signals. In this paper, we see artifacts as a source of information in a signal. For example, eye movements can generate a traceable change in the EEG signals. We use eye movements as an effective marker for direction of movement. We propose two experiments for classification of four eye movement directions (left, right, up and down). In the first experiment, we utilize feature partitioning method based on J48 decision tree to tackle the effect of concept drift in the training dataset resulting from dynamic non-stationarity characteristics of EEG signals. Afterward, we feed the extracted partitions to three different classifiers: multilayer perceptron (MLP) (with 10 hidden layers), logistic regression (LR) and random forest decision tree (RFDT) respectively, while comparing their classification accuracy. In the second experiment, we explored an ensemble learning mechanism as an alternative criterion to deal with the dynamic nature EEG signals. We trained the last three classifiers simultaneously on each training example, followed by a voting method to determine the dominant class label. The ensemble approach increased classification accuracy from 86.2% in the first experiment to 90.1% in the second.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

              \u3053\u306e\u767a\u8868\u306f\uff0c\u773c\u7403\u904b\u52d5\u3068EEG\u4fe1\u53f7\u3092\u540c\u6642\u8a08\u6e2c\u3057\u3066\u3044\u307e\u3057\u305f\uff0eEEG\u4fe1\u53f7\u3067\u306f\u7121\u610f\u8b58\u306a\u7b4b\u8089\u904b\u52d5\u304c\u30ce\u30a4\u30ba\u306e\u539f\u56e0\u3068\u8003\u3048\u3089\u308c\u307e\u3059\uff0e\u305d\u3053\u3067\uff0c\u773c\u7403\u904b\u52d5\u3092\u7528\u3044\u3066EEG\u4fe1\u53f7\u306e\u8ffd\u8de1\u3092\u884c\u3063\u3066\u3044\u307e\u3057\u305f\uff0e\u672c\u7814\u7a76\u3067\u306f\uff0c\u773c\u7403\u306e\u4e0a\u4e0b\u5de6\u53f3\u904b\u52d5\u65b9\u5411\u306e\u5206\u985e\u306e\u305f\u3081\u306b2\u3064\u306e\u5b9f\u9a13\u3092\u884c\u3063\u3066\u3044\u307e\u3057\u305f\uff0e1\u3064\u76ee\u306e\u5b9f\u9a13\u3067\u306f\uff0c\u307e\u305aJ48\u6c7a\u5b9a\u6728\u306b\u57fa\u3065\u304f\u7279\u5fb4\u5206\u5272\u65b9\u6cd5\u3092\u5229\u7528\u3057\uff0cmultilayer perceptron\u30fb\u30ed\u30b8\u30b9\u30c6\u30a3\u30c3\u30af\u56de\u5e30\u30fb\u30e9\u30f3\u30c0\u30e0\u30d5\u30a9\u30ec\u30b9\u30c8\u306e3\u3064\u3092\u305d\u308c\u305e\u308c\u7528\u3044\u3066\u5206\u985e\u3057\uff0c\u7cbe\u5ea6\u3092\u6bd4\u8f03\u3057\u3066\u3044\u307e\u3057\u305f\uff0e2\u3064\u76ee\u306e\u5b9f\u9a13\u3067\u306f\u3001\u30c0\u30a4\u30ca\u30df\u30c3\u30af\u306aEEG\u4fe1\u53f7\u306b\u5bfe\u51e6\u3059\u308b\u4ee3\u66ff\u57fa\u6e96\u3068\u3057\u3066\u30a2\u30f3\u30b5\u30f3\u30d6\u30eb\u5b66\u7fd2\u306e\u30e1\u30ab\u30cb\u30ba\u30e0\u3092\u8abf\u67fb\u3057\uff0c\u30b5\u30f3\u30d7\u30eb\u4f8b\u30923\u3064\u306e\u8b58\u5225\u5668\u306b\u5b66\u7fd2\u3055\u305b\uff0c\u30af\u30e9\u30b9\u30e9\u30d9\u30eb\u306e\u6c7a\u5b9a\u3092\u884c\u3063\u3066\u3044\u307e\u3057\u305f\uff0e\u3053\u306e\u30a2\u30d7\u30ed\u30fc\u30c1\u3067\u8b58\u5225\u7cbe\u5ea6\u304c\u4e0a\u304c\u3063\u305f\u3068\u793a\u3055\u308c\u3066\u3044\u307e\u3057\u305f\uff0e\u81ea\u5206\u306e\u7814\u7a76\u5ba4\u3067\u3082\u773c\u7403\u904b\u52d5\u3068EEG\u306e\u540c\u6642\u8a08\u6e2c\u3092\u3057\u3066\u3044\u308b\u306e\u3067\u8208\u5473\u304c\u3042\u308a\uff0c\u306a\u304b\u306a\u304b\u5185\u5bb9\u306e\u7406\u89e3\u306f\u8ffd\u3044\u3064\u304b\u306a\u304b\u3063\u305f\u3067\u3059\u304c\u8074\u8b1b\u3057\u3066\u307f\u307e\u3057\u305f\uff0e\u7814\u7a76\u5ba4\u3067\u884c\u308f\u308c\u3066\u3044\u308b\u7814\u7a76\u3068\u306f\u307e\u305f\u5c11\u3057\u9055\u3063\u305f\u5185\u5bb9\u3067\u3042\u308b\u3068\u611f\u3058\u307e\u3057\u305f\uff0e
              \n <\/p>\n\n\n\n
              \u767a\u8868\u30bf\u30a4\u30c8\u30eb\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a\u3000The Graph Matching Optimization Methodology for Thin Object Recognition in Pick and Place Tasks
              \n\u8457\u8005\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a Pierre Willaume, Pierre Parrend, Etienne Gancel, Aline Deruyver
              \n\u30bb\u30c3\u30b7\u30e7\u30f3\u540d\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1a FASLIP Session 3
              \nAbstruct\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0\u00a0 \uff1aBin-picking emerges as a major interest in the industry. The aim is to replace current \u2018pick and place\u2019 systems, where one must place mechanical components in dedicated distribution devices such as bowl feeders for picking them up with a robot arm. A large number of image processing methods are available for recognizing these components. For instance, the stereovision approach provides fine results by comparing several images of the objects taken from different angles. However, when several types of components are available or for thin components, the identification remains a delicate task. We propose the Graph Matching Optimization methodology, which uses graph comparison with evolutionary algorithms between stereoscopic images and a model, in order to identify thin pieces in a constrained time frame. First, we extract characteristic component information by binarization and skeletonization of the images. Then, we retrieve the position of the objects in a 3 threedimensional space through an evolutionary algorithm derived from Harmony Search Optimisation (HSO). Lastly, we extract and validate optimal parameter ranges for which the devised algorithm shows a high efficiency for representative component positions of randomly arranged thin objects.<\/td>\n<\/tr>\n<\/tbody>\n<\/table>\n

              \u3053\u306e\u767a\u8868\u3067\u306f\uff0c\u7523\u696d\u754c\u3067\u7269\u3092\u9078\u629e\u3057\uff0c\u7279\u5b9a\u306e\u5834\u6240\u306b\u7f6e\u304f\u30b7\u30b9\u30c6\u30e0\u3092\u517c\u306d\u5099\u3048\u305f\u30ed\u30dc\u30c3\u30c8\u30a2\u30fc\u30e0\u306e\u958b\u767a\u3092\u884c\u3063\u3066\u3044\u307e\u3057\u305f\uff0e\u7269\u306e\u8a8d\u8b58\u3067\u306f\uff0c\u8907\u6570\u306e\u89d2\u5ea6\u304b\u3089\u64ae\u5f71\u3057\u305f\u753b\u50cf\u3092\u3082\u3068\u306b\u3057\u305f\u7acb\u4f53\u8996\u30a2\u30d7\u30ed\u30fc\u30c1\u306b\u3088\u308a\u9ad8\u7cbe\u5ea6\u3067\u884c\u3048\u307e\u3059\uff0e\u3057\u304b\u3057\uff0c\u8907\u6570\u306e\u7269\u4f53\u304c\u3042\u308b\u5834\u5408\u3084\u8584\u3044\u3082\u306e\u306e\u8a8d\u8b58\u306f\u56f0\u96e3\u3067\u3059\uff0e\u305d\u3053\u3067\uff0c\u5236\u7d04\u3055\u308c\u305f\u6642\u9593\u306e\u4e2d\u3067\u8584\u3044\u7269\u4f53\u3092\u8b58\u5225\u3059\u308b\u305f\u3081\u306b\uff0c\u9032\u5316\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u7528\u3044\u3066\u7acb\u4f53\u30a4\u30e1\u30fc\u30b8\u3068\u30e2\u30c7\u30eb\u304c\u4e00\u81f4\u3059\u308b\u3088\u3046\u306a\u6700\u9069\u5316\u624b\u6cd5\u3092\u63d0\u6848\u3057\u3066\u3044\u307e\u3057\u305f\uff0e\u307e\u305a\uff0c\u4e8c\u5024\u5316\u3068\u7d30\u7dda\u5316\u306b\u3088\u3063\u3066\u7269\u4f53\u306e\u9aa8\u683c\u3092\u53d6\u308a\u51fa\u3057\uff0cHSO\u3092\u3082\u3068\u306b\u3057\u305f\u9032\u5316\u30a2\u30eb\u30b4\u30ea\u30ba\u30e0\u3092\u7528\u3044\u30663\u6b21\u5143\u7a7a\u9593\u5185\u306e\u7269\u4f53\u306e\u4f4d\u7f6e\u3092\u53d6\u308a\u51fa\u3057\u3066\u3044\u307e\u3057\u305f\uff0e\u3053\u306e\u767a\u8868\u3067\u306f\uff0c\u3068\u3066\u3082\u30b9\u30e9\u30a4\u30c9\u306b\u9b45\u5165\u3089\u308c\u307e\u3057\u305f\uff0e\u7814\u7a76\u306e\u30d5\u30ed\u30fc\u56f3\u304c\u30a4\u30e9\u30b9\u30c8\u4ed8\u304d\u3067\u307e\u3068\u3081\u3066\u3042\u308a\uff0c\u3068\u3066\u3082\u30a4\u30e1\u30fc\u30b8\u3057\u3084\u3059\u304f\u308f\u304b\u308a\u3084\u3059\u3044\u3082\u306e\u3067\u3057\u305f\uff0e\u521d\u3081\u306b\u30b3\u30f3\u30bb\u30d7\u30c8\u304c\u308f\u304b\u308b\u767a\u8868\u306f\u7814\u7a76\u5185\u5bb9\u3082\u5206\u304b\u308a\u3084\u3059\u304f\uff0c\u4f55\u3092\u3057\u3066\u3044\u308b\u306e\u304b\u76f8\u624b\u306b\u5206\u304b\u3063\u3066\u3082\u3089\u3046\u305f\u3081\u306b\u306f\u3068\u3066\u3082\u91cd\u8981\u3060\u3068\u6539\u3081\u3066\u611f\u3058\u307e\u3057\u305f\uff0e\u4eca\u5f8c\u306e\u767a\u8868\u306b\u3082\u751f\u304b\u3057\u3066\u3044\u304d\u305f\u3044\u3068\u601d\u3044\u307e\u3057\u305f\uff0e
              \n 
              \n <\/p>\n","protected":false},"excerpt":{"rendered":"

              2016\u5e7412\u67086\u65e5\u304b\u30899\u65e5\u304b\u3051\u3066\u30ae\u30ea\u30b7\u30e3\uff08\u30a2\u30c6\u30cd\uff09\u306eRoyal Olympic Hotel\u306b\u3066\u958b\u50ac\u3055\u308c\u307e\u3057\u305f\uff0cThe 2016 IEEE Symposium Series on Computational Intell … <\/p>\n

              “SSCI2016” \u306e<\/span>\u7d9a\u304d\u3092\u8aad\u3080<\/a><\/p>\n","protected":false},"author":3,"featured_media":0,"comment_status":"closed","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[10,3],"tags":[],"class_list":["post-3853","post","type-post","status-publish","format-standard","hentry","category-10","category-3"],"_links":{"self":[{"href":"https:\/\/is.doshisha.ac.jp\/news\/index.php?rest_route=\/wp\/v2\/posts\/3853","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/is.doshisha.ac.jp\/news\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/is.doshisha.ac.jp\/news\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/is.doshisha.ac.jp\/news\/index.php?rest_route=\/wp\/v2\/users\/3"}],"replies":[{"embeddable":true,"href":"https:\/\/is.doshisha.ac.jp\/news\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=3853"}],"version-history":[{"count":0,"href":"https:\/\/is.doshisha.ac.jp\/news\/index.php?rest_route=\/wp\/v2\/posts\/3853\/revisions"}],"wp:attachment":[{"href":"https:\/\/is.doshisha.ac.jp\/news\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=3853"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/is.doshisha.ac.jp\/news\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=3853"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/is.doshisha.ac.jp\/news\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=3853"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}