Improvement of q 2 IF 1.5 4区 物理与天体物理 Q3 PHYSICS, PARTICLES & FIELDS Advances in High Energy Physics Pub Date : 2023-03-27 DOI:10.1155/2023/8127604 Panting Ge, Xiaotao Huang, M. Saur, Liang Sun 求助PDF {"title":"Improvement of <math xmlns=\"http://www.w3.org/1998/Math/MathML\" id=\"M1\">\n <msup>\n <mrow>\n <mi>q</mi>\n </mrow>\n <mrow>\n <mn>2</mn>\n </mro","authors":"Panting Ge, Xiaotao Huang, M. Saur, Liang Sun","doi":"10.1155/2023/8127604","DOIUrl":null,"url":null,"abstract":"The neutrino closure method is often used to obtain kinematics of semileptonic decays with one unreconstructed particle in hadron collider experiments. The kinematics of decays can be deducted by a twofold ambiguity with a quadratic equation. To resolve the twofold ambiguity, a novel method based on machine learning (ML) is proposed. We study the effect of different sets of features and regressors on the improvement of reconstructed invariant mass squared of \n \n ℓ\n ν\n \n system (\n \n \n \n q\n \n \n 2\n \n \n \n ). The result shows that the best performance is obtained by using the flight vector as the features and the multilayer perceptron (MLP) model as the regressor. Compared with the random choice, the MLP model improves the resolution of reconstructed \n \n \n \n q\n \n \n 2\n \n \n \n by ~40%. Furthermore, the possibility of using this method on various semileptonic decays is shown.","PeriodicalId":7498,"journal":{"name":"Advances in High Energy Physics","volume":" ","pages":""},"PeriodicalIF":1.5000,"publicationDate":"2023-03-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Advances in High Energy Physics","FirstCategoryId":"101","ListUrlMain":"https://doi.org/10.1155/2023/8127604","RegionNum":4,"RegionCategory":"物理与天体物理","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q3","JCRName":"PHYSICS, PARTICLES & FIELDS","Score":null,"Total":0} 引用次数: 0 引用 批量引用 Abstract The neutrino closure method is often used to obtain kinematics of semileptonic decays with one unreconstructed particle in hadron collider experiments. The kinematics of decays can be deducted by a twofold ambiguity with a quadratic equation. To resolve the twofold ambiguity, a novel method based on machine learning (ML) is proposed. We study the effect of different sets of features and regressors on the improvement of reconstructed invariant mass squared of ℓ ν system ( q 2 ). The result shows that the best performance is obtained by using the flight vector as the features and the multilayer perceptron (MLP) model as the regressor. Compared with the random choice, the MLP model improves the resolution of reconstructed q 2 by ~40%. Furthermore, the possibility of using this method on various semileptonic decays is shown. 分享 查看原文 本刊更多论文 q2 在强子对撞机实验中，通常采用中微子闭包法来获得单粒子半光子衰变的运动学。衰变的运动学可以用二次方程的双重模糊来推导。为了解决双重歧义，提出了一种基于机器学习的新方法。研究了不同的特征集和回归量对改进重构不变质量平方(q2)的影响。结果表明，以飞行向量为特征，以多层感知器(MLP)模型为回归量，可以获得最佳的性能。与随机选择相比，MLP模型将重构q2的分辨率提高了约40%。此外，还证明了将这种方法应用于各种半光子衰变的可能性。 本文章由计算机程序翻译，如有差异，请以英文原文为准。 求助全文 约1分钟内获得全文 求助全文 来源期刊 Advances in High Energy Physics PHYSICS, PARTICLES & FIELDS- CiteScore 3.40 自引率 5.90% 发文量 55 审稿时长 6-12 weeks 期刊介绍： Advances in High Energy Physics publishes the results of theoretical and experimental research on the nature of, and interaction between, energy and matter. Considering both original research and focussed review articles, the journal welcomes submissions from small research groups and large consortia alike. 相关文献 × 引用 GB/T 7714-2015 复制 MLA 复制 APA 复制 导出至 BibTeX EndNote RefMan NoteFirst NoteExpress × 求助内容： 期刊论文 学位论文 图书 其他 (专利、报告等) 只需要正文 仅需补充材料 应助结果提醒方式： 微信（请自行确认已关注Book学术公众号） 邮件 保存 保存后同步修改账户信息中的邮箱 确认发布求助 × 处理提示 您的部分求助已有人上传文件，您还尚未处理，请先处理完毕再发起新的求助 点击查看 × 努力提交中 提交成功 继续求助查看详情 × 提示 您的信息不完整，为了账户安全，请先补充。 现在去补充 × 没积分了 多种获得积分方式，供你选择！ 查看如何获取积分 × 提示 您因"违规操作" 具体请查看互助需知 我知道了 × 提示 现在去查看 取消 × 提示 确定 × 快捷登录 密码登录 用户名： 密码： 验证码： 两周内记住我 忘记密码？ 手机号： 验证码： 没有帐号？现在注册 请完成安全验证× 微信好友 朋友圈 QQ好友 复制链接 取消 已复制链接 快去分享给好友吧! 我知道了 点击右上角分享 0 $(function () { var title = $("#title").val(); var id = $("#id").val(); $.post("/Literature/GetRelatedLiterature", { id: id, title: title }, function (result) { if (result != null) { var html = ``; for (var i = 0; i < result.length; i++) { html += `<div class="sslist">`; html += `<a class="caption" href="` + $("#url1").val() + result[i].ArticleID + `.htm">` + result[i].Title + `</a>`; html += ` <div class="substance">`; html += `<span class="IF">IF ` + result[i].PeriodicalIF + ` </span>`; if (result[i].RegionNum > 0) { html += `<span class="fq` + result[i].RegionNum + `">` + result[i].RegionNum + `区 ` + result[i].RegionCategory + `</span>`; } //var EmployDataBaseShoreName = result[i].EmployDataBaseShoreName; //if (EmployDataBaseShoreName != "" && EmployDataBaseShoreName!=null) { // var names = EmployDataBaseShoreName.split('||') // for (var j = 0; j < names.length; j++) { // html += `<span class="fq5">` + names[j] + `</span>`; // } //} //html += ``; html += `</div>`; html += `<div class="substance">`; html += `<a href="` + $("#url2").val() + "_d" + result[i].PeriodicalID + `.htm" target="_blank">` + result[i].PeriodicalName + `</a>`; html += `<span class="Pub">Pub Date : ` + result[i].PublishDate + `</span>`; html += `</div>`; html += ` <div class="author">`; html += result[i].AuthorName; html += `</div>`; html += `</div>`; } if (html.length > 0) { $("#xglist").show(); $("#xglist").append(html); } } }); getReferenceCount(); }); function getReferenceCount() { var LocalId = localStorage.getItem("referenceName"); if (LocalId != null) { $.get("/Literature/GetBatchReferenceCountByLocalId", { LocalId: LocalId }, function (result) { $("#referencecount").html(result.Code); }, "json"); } else { $("#referencecount").html('0'); } } wx.config({ debug: false, appId: 'wx999b2eb01732df2e', timestamp: '1735244027', nonceStr: 'uieuJH6uEdLyP5Cg', signature: '528cffa5869aa91f1f0c34cb360a0691ab57db04', jsApiList: [ 'onMenuShareTimeline', 'onMenuShareAppMessage', 'hideMenuItems' ] });

Abstract

The neutrino closure method is often used to obtain kinematics of semileptonic decays with one unreconstructed particle in hadron collider experiments. The kinematics of decays can be deducted by a twofold ambiguity with a quadratic equation. To resolve the twofold ambiguity, a novel method based on machine learning (ML) is proposed. We study the effect of different sets of features and regressors on the improvement of reconstructed invariant mass squared of ℓ ν system ( q 2 ). The result shows that the best performance is obtained by using the flight vector as the features and the multilayer perceptron (MLP) model as the regressor. Compared with the random choice, the MLP model improves the resolution of reconstructed q 2 by ~40%. Furthermore, the possibility of using this method on various semileptonic decays is shown.