Effective strategies for the prediction of aircraft passenger seat (dis-)comfort based on Time Series Classification

IF 6.2 2区经济学 Q1 ECONOMICS

Socio-economic Planning Sciences Pub Date : 2025-05-08 DOI:10.1016/j.seps.2025.102240

Amalia Vanacore, Armando Ciardiello

{"title":"Effective strategies for the prediction of aircraft passenger seat (dis-)comfort based on Time Series Classification","authors":"Amalia Vanacore, Armando Ciardiello","doi":"10.1016/j.seps.2025.102240","DOIUrl":null,"url":null,"abstract":"<div><div>Aircraft seat is one of the factors which mostly impact on passenger's flight experience and her/his willingness to choose the same airline in future occasions. The focus of this paper is on the prediction of passenger seat (dis-)comfort via objective methods based on the analysis of pressure distribution at seat interface. The aim is identifying the best strategy for predicting seat (dis-)comfort via the combination of well-known pressure indexes and Time Series Classification (TSC) algorithms applied in a univariate as well as a multivariate setting. To leverage the full potential of TSC algorithms, a comparison across different Data Augmentation (DA) techniques has been conducted. The comparison of seat (dis-)comfort prediction strategies provides useful insights on the informativeness of pressure features to accurately predict seat (dis-)comfort. Adopting a multivariate setting and expanding dataset size artificially have not enhanced predictive performance of TSC algorithms. The only exception results ResNet algorithm which in multivariate TSC benefits from DA, showing satisfactory predictive performance.</div></div>","PeriodicalId":22033,"journal":{"name":"Socio-economic Planning Sciences","volume":"100 ","pages":"Article 102240"},"PeriodicalIF":6.2000,"publicationDate":"2025-05-08","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":null,"platform":"Semanticscholar","paperid":null,"PeriodicalName":"Socio-economic Planning Sciences","FirstCategoryId":"96","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0038012125000898","RegionNum":2,"RegionCategory":"经济学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECONOMICS","Score":null,"Total":0}

引用次数: 0

Abstract

Aircraft seat is one of the factors which mostly impact on passenger's flight experience and her/his willingness to choose the same airline in future occasions. The focus of this paper is on the prediction of passenger seat (dis-)comfort via objective methods based on the analysis of pressure distribution at seat interface. The aim is identifying the best strategy for predicting seat (dis-)comfort via the combination of well-known pressure indexes and Time Series Classification (TSC) algorithms applied in a univariate as well as a multivariate setting. To leverage the full potential of TSC algorithms, a comparison across different Data Augmentation (DA) techniques has been conducted. The comparison of seat (dis-)comfort prediction strategies provides useful insights on the informativeness of pressure features to accurately predict seat (dis-)comfort. Adopting a multivariate setting and expanding dataset size artificially have not enhanced predictive performance of TSC algorithms. The only exception results ResNet algorithm which in multivariate TSC benefits from DA, showing satisfactory predictive performance.

查看原文本刊更多论文

基于时间序列分类的飞机乘客座椅（不）舒适预测策略

飞机座位是影响乘客飞行体验和在未来场合选择同一家航空公司意愿的主要因素之一。本文的重点是在分析座椅界面压力分布的基础上，用客观的方法预测乘客的座椅（不）舒适。目的是通过将众所周知的压力指数和时间序列分类（TSC）算法结合起来，在单变量和多变量设置中确定预测座椅（不）舒适的最佳策略。为了充分利用TSC算法的潜力，对不同的数据增强（DA）技术进行了比较。座椅（非）舒适预测策略的比较，为准确预测座椅（非）舒适提供了压力特征信息量的有用见解。采用多变量设置和人为地扩大数据集大小并没有提高TSC算法的预测性能。唯一例外的结果是，ResNet算法在多元TSC中受益于DA，表现出令人满意的预测性能。

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

Socio-economic Planning Sciences OPERATIONS RESEARCH & MANAGEMENT SCIENCE-

CiteScore

9.40

自引率

13.10%

发文量

294

审稿时长

58 days

期刊介绍： Studies directed toward the more effective utilization of existing resources, e.g. mathematical programming models of health care delivery systems with relevance to more effective program design; systems analysis of fire outbreaks and its relevance to the location of fire stations; statistical analysis of the efficiency of a developing country economy or industry. Studies relating to the interaction of various segments of society and technology, e.g. the effects of government health policies on the utilization and design of hospital facilities; the relationship between housing density and the demands on public transportation or other service facilities: patterns and implications of urban development and air or water pollution. Studies devoted to the anticipations of and response to future needs for social, health and other human services, e.g. the relationship between industrial growth and the development of educational resources in affected areas; investigation of future demands for material and child health resources in a developing country; design of effective recycling in an urban setting.