{"id":5182,"date":"2026-05-18T14:11:04","date_gmt":"2026-05-18T06:11:04","guid":{"rendered":"https:\/\/www.15zhi.net\/blog\/?p=5182"},"modified":"2026-05-18T14:11:04","modified_gmt":"2026-05-18T06:11:04","slug":"202605-%e8%ae%ba%e6%96%87%e7%a0%94%e8%af%bb-a-comparison-of-methods-for-modeling-soundscape-dimensions-based-on-different-datasets","status":"publish","type":"post","link":"https:\/\/www.15zhi.net\/blog\/202605-%e8%ae%ba%e6%96%87%e7%a0%94%e8%af%bb-a-comparison-of-methods-for-modeling-soundscape-dimensions-based-on-different-datasets\/","title":{"rendered":"202605 \u8bba\u6587\u7814\u8bfb-A comparison of methods for modeling soundscape dimensions based on different datasets"},"content":{"rendered":"\n

\u4f5c\u8005: Siegbert Vers\u00fcmer\u3001Patrick Bl\u00e4ttermann\u3001Fabian Rosenthal\u3001Stefan Weinzierl<\/em><\/em><\/em>
\u5355\u4f4d: \u5fb7\u56fd\u675c\u585e\u5c14\u591a\u592b\u5e94\u7528\u79d1\u6280\u5927\u5b66\u58f0\u5b66\u4e0e\u632f\u52a8\u5de5\u7a0b\u7814\u7a76\u6240, \u5fb7\u56fd\u67cf\u6797\u5de5\u4e1a\u5927\u5b66\u97f3\u9891\u901a\u4fe1\u7ec4<\/em><\/em><\/em>
\u6765\u6e90: JASA<\/em><\/em>
\u65f6\u95f4: 2025<\/em>\u5e741\u6708<\/p>\n\n\n\n

\u4e00\u3001\u7814\u7a76\u80cc\u666f<\/h2>\n\n\n\n
\"\"<\/figure>\n\n\n\n

\u4e8c\u3001\u6838\u5fc3\u8d21\u732e<\/h2>\n\n\n\n
\"\"<\/figure>\n\n\n\n

\u4e09\u3001\u65b9\u6cd5<\/h2>\n\n\n\n
\"\"<\/figure>\n\n\n\n
\"\"<\/figure>\n\n\n\n

\u5916\u5c42 5 \u6298\u7528\u4e8e\u65e0\u504f\u4f30\u8ba1<\/mark>\u6a21\u578b\u6027\u80fd\uff0c\u5185\u5c42 5 \u6298\u7528\u4e8e\u9009\u62e9\u8d85\u53c2\u6570\u548c\u6a21\u578b<\/mark>\uff1b\u540c\u65f6\u5212\u5206\u65f6\u8003\u8651\u6807\u7b7e\u5206\u5e03\u548c group \u7ed3\u6784\uff0c\u907f\u514d<\/mark>\u5c0f\u6837\u672c\u58f0\u666f\u6570\u636e\u4e2d\u56e0\u4e3a\u6807\u7b7e\u4e0d\u5e73\u8861\u6216 group \u6cc4\u6f0f\u5bfc\u81f4\u7684\u865a\u9ad8\u6027\u80fd<\/mark>\u3002<\/p>\n\n\n\n

\u56db\u3001\u5b9e\u9a8c<\/h2>\n\n\n\n

1.\u5b9e\u9a8c\u51c6\u5907<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

2.\u5b9e\u9a8c\u7ed3\u679c\u2014\u2014Predictability of Pleasantness and Eventfulness<\/strong><\/p>\n\n\n\n

(1)\u5728MSE\u7ed3\u679c\u8868\u4e2d\uff0c\u5927\u591a\u6570Eventfulness\u7684MSE\u6bd4Pleasantness\u7684\u66f4\u4f4e \u3002
(2)\u5728out-of-sample R\u00b2 \u7ed3\u679c\u8868\u4e2d\uff0cEventfulness \u7684 R\u00b2 \u901a\u5e38\u9ad8\u4e8e Pleasantness\u3002(3)\u5728R\u00b2 \u7bb1\u7ebf\u56fe\u4e2d\uff0cARAUSD \u548c HSDD \u7684 Eventfulness \u7bb1\u4f53\u6574\u4f53\u9ad8\u4e8e Pleasantness\uff0c\u800c ISD \u6bd4\u8f83\u7279\u6b8a\u3002
(4)\u5728\u65b9\u5dee\u89e3\u91ca\u8868\u4e2d\uff0cISD \u4e2dEventfulness \u7684 MSE \u66f4\u4f4e\uff0c\u4f46 R\u00b2 \u53cd\u800c\u6bd4 Pleasantness \u4f4e\uff0c\u662f\u5176\u603b\u65b9\u5dee\u66f4\u5c0f\u3002<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

3.\u5b9e\u9a8c\u7ed3\u679c\u2014\u2014Method comparison and FE NR vs LR models<\/strong><\/p>\n\n\n\n

(1)\u8868\u4e94\u548c\u8868\u516d\u4e2d\u5927\u90e8\u5206\u4f8b\u5b50\u4e2d\uff0c\u975e\u7ebf\u6027\u56de\u5f52 NR \u4f18\u4e8e\u7ebf\u6027\u56de\u5f52 LR\u3002
(2)\u6811\u6a21\u578b RF\/XGBoost \u5728 19\/27 \u4e2a\u6bd4\u8f83\u4e2d\u4f18\u4e8e MARS \u548c SVR\uff1b\u5c24\u5176\u5728 HSDD Eventfulness \u4e0a\uff0cRF\/XGBoost \u660e\u663e\u6bd4 MARS\/SVR \u66f4\u5f3a\u3002<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n
\"\"<\/figure>\n\n\n\n

4.\u5b9e\u9a8c\u7ed3\u679c\u2014\u2014Effect of data leakage in FE and ME methods<\/strong><\/p>\n\n\n\n

(1)\u6bd4\u8f83\u8868\u4e94\u548c\u8868\u516d\u4e2d\u4e09\u79cd\u5212\u5206\uff0c\u5f53group\u88ab\u5206\u6563\u5230\u4e0d\u540cfold\u540e\uff0c\u6a21\u578b\u6027\u80fd\u666e\u904d\u4e0a\u5347\u3002
(2)ARAUS\u63d0\u5347\u8f83\u5c0f\u662f\u56e0\u4e3a\u5176\u672c\u8eab\u8bbe\u8ba1\u5f97\u5f88\u5e73\u8861\u3002
(3)\u6df7\u5408\u6548\u5e94\u6a21\u578b\u5728\u6709group\u6cc4\u9732\u7684\u65f6\u5019\uff0c\u603b\u662f\u4f18\u4e8e\u56fa\u5b9a\u6548\u5e94\u6a21\u578b\uff0c\u4f46\u4e0d\u4ee3\u8868\u771f\u5b9e\u6cdb\u5316\u80fd\u529b\u3002
(4)\u901a\u8fc7\u4e0b\u8868\u7684\u989d\u5916\u68c0\u67e5\uff0c\u6570\u636e\u6cc4\u6f0f\u4f1a\u8ba9 MSE \u964d\u4f4e\u3001R\u00b2 \u5c0f\u5e45\u5347\u9ad8\u3002<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n

5.\u5b9e\u9a8c\u7ed3\u679c\u2014\u2014Model robustness<\/strong><\/p>\n\n\n\n

(1)\u5927\u591a\u6570\u6709\u6548\u6a21\u578b\u4e2d\uff0cinner CV \u7684 dMSE \u90fd\u80fd\u63a7\u5236\u5728 0.05 \u4ee5\u4e0b\uff0c\u8bf4\u660e objective function \u57fa\u672c\u8d77\u4f5c\u7528\u3002
(2)\u4f46\u65e0\u6cd5\u5b8c\u5168\u9632\u6b62\u8fc7\u62df\u5408\uff0ctrain MSE\u548ctestMSE\u63a5\u8fd1\uff0c\u4f46R\u00b2\u4ecd\u7136\u4e0b\u964d\u5f88\u591a\uff0c\u8bf4\u660e\u58f0\u666f\u4efb\u52a1\u672c\u8eab\u5f88\u96be\u6cdb\u5316\u3002<\/p>\n\n\n\n

\"\"<\/figure>\n\n\n\n
\"\"<\/figure>\n\n\n\n

\u4e94\u3001\u603b\u7ed3<\/h2>\n\n\n\n

(1)\u672c\u6587\u7684\u6838\u5fc3\u8d21\u732e\u662f\u63d0\u51fa\u4e86\u4e00\u5957\u66f4\u4e25\u683c\u3001\u66f4\u7edf\u4e00\u7684\u58f0\u666f\u5efa\u6a21\u4e0e\u8bc4\u4f30\u6846\u67b6\uff0c\u7528\u4e8e\u516c\u5e73\u6bd4\u8f83\u4e0d\u540c\u65b9\u6cd5\u548c\u6570\u636e\u96c6\u3002
(2)\u58f0\u666f\u8bc4\u4ef7\u4e2d\uff0cEventfulness \u901a\u5e38\u6bd4 Pleasantness \u66f4\u5bb9\u6613\u9884\u6d4b\uff0c\u5c24\u5176\u5728 HSDD \u548c ARAUSD \u4e0a\u8868\u73b0\u660e\u663e\u3002
(3)\u975e\u7ebf\u6027\u6a21\u578b\uff08RF\u3001XGBoost\uff09\u6574\u4f53\u4f18\u4e8e\u7ebf\u6027\u56de\u5f52\uff0c\u8bf4\u660e\u58f0\u666f\u611f\u77e5\u4e0e\u58f0\u5b66\u53d8\u91cf\u4e4b\u95f4\u5b58\u5728\u660e\u663e\u975e\u7ebf\u6027\u5173\u7cfb\u3002
(4)group leakage \u4f1a\u663e\u8457\u62ac\u9ad8\u6a21\u578b\u6027\u80fd\uff0c\u56e0\u6b64 participant\/location \u7684\u5206\u7ec4\u5212\u5206\u548c nested cross-validation \u5bf9\u58f0\u666f\u4efb\u52a1\u975e\u5e38\u91cd\u8981\u3002<\/p>\n\n\n\n

\u516d\u3001\u5bf9\u9f50\u601d\u8003<\/h2>\n\n\n\n

1.\u65b9\u6cd5\u521b\u65b0\u70b9\u2014\u2014\u5168\u57df\u6570\u636e\u62d3\u6251\u5efa\u6a21:\u7ed9\u51fa\u6765\u4e00\u4e2a\u7cfb\u7edf\u6027\u4e14\u5408\u7406\u7684\u8bc4\u4f30\u6846\u67b6\uff0c\u7528\u4e8e\u8bc4\u4f30\u4e0d\u540c\u6570\u636e\u96c6\uff0c\u53ef\u4ee5\u91c7\u7528\u6587\u4e2d\u65b9\u6cd5\u7528\u6765\u548c\u5176\u4ed6\u8bba\u6587\u65b9\u6cd5\u5bf9\u6bd4\u3002<\/p>\n\n\n\n

2.\u6280\u672f\u76ee\u6807\u70b9\u2014\u2014\u8de8\u57df\u77e5\u8bc6\u7ed3\u6784\u5bf9\u9f50: \u5176\u4ed6\u6216\u8005\u65e9\u671f\u8bba\u6587\u8fdb\u884c\u58f0\u666f\u9884\u6d4b\u65f6\uff0c\u67d0\u4e9b\u53ef\u80fd\u4f1a\u6709\u9690\u85cf\u7684\u6570\u636e\u6cc4\u9732\uff0c\u6587\u4e2d\u7ed9\u51fa\u4e86\u4e00\u79cd\u4e25\u683c\u6d4b\u8bd5\u7684\u65b9\u6cd5\uff0c\u5e76\u7ed9\u51fa\u4e86\u4e00\u79cd\u9632\u6b62\u8fc7\u62df\u5408\u4ee5\u53ca\u6b20\u62df\u5408\u7684\u76ee\u6807\u51fd\u6570\u3002<\/p>\n\n\n\n

3.\u4e2d\u8bd5\u4ea7\u54c1\u70b9\u2014\u2014\u57c3\u89c5\u6587\u65c5: \u5bf9\u4e8e\u4e0d\u540c\u7684\u58f0\u666f\uff0c\u53ef\u4ee5\u901a\u8fc7\u4e25\u683c\u7684\u8bc4\u4f30\u65b9\u5f0f\uff0c\u9632\u6b62\u6027\u80fd\u5047\u865a\u9ad8\u3002<\/p>\n","protected":false},"excerpt":{"rendered":"

\u4f5c\u8005: Siegbert Vers\u00fcmer\u3001Patrick Bl\u00e4ttermann\u3001Fabian Rosent […]<\/p>\n","protected":false},"author":74,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[1],"tags":[],"class_list":["post-5182","post","type-post","status-publish","format-standard","hentry","category-events"],"_links":{"self":[{"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/posts\/5182","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/users\/74"}],"replies":[{"embeddable":true,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/comments?post=5182"}],"version-history":[{"count":1,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/posts\/5182\/revisions"}],"predecessor-version":[{"id":5195,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/posts\/5182\/revisions\/5195"}],"wp:attachment":[{"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/media?parent=5182"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/categories?post=5182"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/www.15zhi.net\/blog\/wp-json\/wp\/v2\/tags?post=5182"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}