I-Corps: A Smartphone-Human Hybrid System to Measure Human Behavior and Well-Being

这个i-Corps项目的更广泛的影响/商业潜力集中在准确和全面地收集人类行为和福祉数据，以改进决策和商业运营。拟议的系统提供了一种收集人类行为和幸福感数据的新方法。它有潜力帮助政府机构设计更宜居的社区、城市和地区，以增进人类福祉。这项技术还可能帮助公司证明，他们的产品和服务改善了行为和福祉。此外，越来越多的人拥有智能手机，这使得拟议的系统可以广泛使用，以便进行大规模部署。这个i-Corps项目以智能手机-人类混合智能系统为特色，该系统结合了先进的数据挖掘和机器学习技术以及复杂的用户界面设计，允许智能手机和人类生成的数据之间进行交互。具体地说，智能手机传感器数据在手机上进行本地分析，并使用数据挖掘和机器学习算法实时分析，以提取日常活动和旅行的客观时空细节。提取的信息减轻了受访者的负担，并作为初始信息基础，以附加关于日常活动和旅行的更详细和准确的信息。来自人类用户的信息反过来又优化了用于分析智能手机传感器数据的数据挖掘和机器学习算法，并随着时间的推移提高了智能手机生成数据的准确性。其结果是一个新的系统，在该系统中，智能手机传感与人类输入合作，生成与人类行为和福祉相关的准确和全面的数据。该奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

The broader impact/commercial potential of this I-Corps project centers on accurate and comprehensive collection of human behavioral and well-being data for improved policymaking and business operations. The proposed system provides a new way to collect human behavior and well-being data. It has the potential to help government agencies design more livable neighborhoods, cities, and regions for greater human well-being. The technology may also help companies demonstrate that their products and services improve behavioral and well-being outcomes. In addition, the increasing prevalence of smartphone ownership makes the proposed system widely accessible for large-scale deployment. This I-Corps project features a smartphone-human hybrid intelligence system that incorporates advanced data mining and machine learning techniques and sophisticated user interface design to allow interactions between smartphone- and human-generated data. Specifically, smartphone sensor data are analyzed locally on the phone and in real time using data mining and machine learning algorithms to extract objective, spatiotemporal details of daily activities and trips. The extracted information reduces respondent burden and serves as an initial information basis to attach more detailed and accurate information on daily activities and trips. The information from the human user, in turn, optimizes the data mining and machine learning algorithms for analyzing smartphone sensor data and increases accuracy in smartphone-generated data over time. The result is a novel system in which smartphone sensing collaborates with human input to generate accurate and comprehensive data related to human behavior and well-being.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.