摘要
由一名新闻记者-机器人与机器学习的工作人员新闻编辑-每日新闻-一项关于人工智能的新研究现在可用。根据NewsRx编辑来自英国诺丁汉的新闻报道，这项研究指出：“导言&决策者积极改变粮食环境的能力需要强有力的经济证据来为决策提供信息。目前，英国关于粮食不安全的数据有限，可以用来为当地政府的干预提供信息。”"由于纵向调查的成本过高和后勤挑战."新闻记者从诺丁汉大学商学院获得了这项研究的一句话:“这项研究建立在现有研究和一个关键的试点s tudy的基础上。Olio是一个食品共享应用程序,截至2023年已注册用户700万人,诺丁汉大学和哈弗林委员会于2020年合作开发的。”这导致了世界上第一个粮食不安全地图原型。Obj ectives&Approach我们的方法利用机器学习方法，应用于前所未有的粮食获取行为数据和开放地区层面的剥夺统计数据，来模拟和预测伦敦各地个人的粮食安全体验。我们利用Olio的广泛用户网络分发了2849份调查，询问了伦敦各地的受访者关于他们的粮食安全体验。这份调查是在网上发布的，调整美国农业部的食品安全模块。受访者被问及他们的经历，包括：(1)吃小餐或不吃饭；(2)饥饿但无法吃饭；(3)因为负担不起食物或无法获得食物而一整天不吃饭。利用家庭，相反，粮食不安全模块的个人层面版本有助于阐明弱势群体的经验，如儿童。与数字足迹的相关性调查答复提供了用户贫困经历的基本真相。贫困衡量标准和数字足迹数据以食物获取行为数据的形式被用于随机森林机器学习模型，以预测家庭是否处于贫困状态。经历过食物不安全的经历，准确率很高。在Olio的平台上，来自近50000名伦敦用户的食物分享数据被用来识别相关的寻求食物的行为，并汇总社区(MSOA)级公认的食物不安全案例。
Abstract
By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News-A new study on artificial intelligence is now available. According to news originating from Nottingham, United Kingdom , by NewsRx editors, the research stated, "Introduction & The abil ity of policymakers to positively transform food environments requires robust em pirical evidence that can inform decisions. At present, there is limited data on food-insecurity in the UK that can be used to inform interventions by local aut horities, due to the prohibitive costs and logistical challenges of administerin g longitudinal surveys." The news correspondents obtained a quote from the research from Nottingham Unive rsity Business School: "This study builds on existing research and a key pilot s tudy developed in partnership between Olio - a food-sharing app with 7 million r egistered users as of 2023, the University of Nottingham and Havering Council in 2020, which resulted in the world's first map prototype of food-insecurity. Obj ectives & Approach Our approach leverages Machine Learning methods applied to unprecedented food-acquisition behavioural data and open area-level deprivation statistics to model and predict individuals' experience of food-inse curity across London. We used Olio's extensive network of users to distribute 2, 849 surveys, asking respondents across London about their experiences of food-in security. The survey was distributed online, adapting the US Department of Agric ulture Food Security module. Respondents were asked about their experiences, inc luding (1) eating smaller meals or skipping meals, (2) being hungry but being un able to eat, and (3) not eating for a whole day, because they could not afford f ood or because they could not get access to food. Using the household, rather th an the individual-level version of the food insecurity module helped shed light on the experience of vulnerable groups - such as children. Relevance to Digital Footprints The survey responses provided a ground truth about users' experiences of destitution. Deprivation metrics and digital footprint data in the form of f ood-acquisition behavioural data were then used in a Random Forests Machine Lear ning model to predict whether households were experiencing foodinsecurity, achi eving high accuracy. Food-sharing data from almost 50,000 London-based users act ive on Olio's platform were then used to identify relevant food-seeking behaviou rs and aggregate recognised instances of food-insecurity at neighbourhood (MSOA) level."
NETL
NSTL