CAREER: Toward Embedding Perpetual Intelligence into Ultra-Low-Power Sensing and Inference Systems

多年来的技术进步使今天的小型便携式电子设备能够依靠电池供电持续数年，并通过从周围环境中收集能量来供电。不幸的是，这些超低功耗系统的寿命延长带来了一个根本性的新问题。虽然这些设备可以使用多年，但当感觉输入的性质或操作条件发生变化时，在其上运行的程序就会过时。 继续执行这样一个过时的程序的后果可能是灾难性的。例如，如果心脏起搏器无法识别即将发生的心脏骤停，因为患者已经老化或生理变化，这些设备将造成更多的伤害。因此，能够反应，适应和发展是这些系统保证其准确性和响应时间的必要条件。该项目旨在设计算法，工具，系统和应用程序，使超低功耗，传感器，计算设备能够执行复杂的机器学习算法，同时仅通过收集能量供电。与固定分类器在设备上运行的常见做法不同，该项目采取了一种根本不同的方法，其中分类器的构建方式可以适应和发展系统的感官输入，或特定于应用程序的要求，如系统的时间，能量和内存约束，在系统的延长寿命期间发生变化。为了证明所提出的系统的有效性，将开发和部署几个特定应用的无电池系统，其中包括：（1）哮喘患者的个性化空气质量指数预测器，（2）超低功耗语音助手，为日常物品提供语音，以及（3）共享资源的实时跟踪器。 这项研究将使更智能，更智能的微型机器人和自主系统，将有助于改善医疗保健，农业，制造业和环境。这项研究的结果有可能通过开发无电池医疗植入物和可穿戴设备来改变医疗保健，这些设备将能够监测和学习个人特定的生理参数，从而能够在发病时检测到异常，这可能是发展疾病的原因。这项研究的直接影响是开发出一种低成本、便携式、实时的空气质量监测仪，这将改变哮喘和慢性阻塞性肺疾病（COPD）的管理。硬件和软件工具将是开源的。暑期研究机会将向高中生和本科生开放。将提供以物联网为重点的跨学科课程，以扩大健康信息学课程学生的参与。将确保妇女和代表性不足群体成员的参与。与当地创客空间、一个科学中心和一所高中合作开展的外展活动将提供研究曝光，并提高对能源收集的认识。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

Years of technological advancements have made it possible for small, portable, electronic devices of today to last for years on battery power, and last forever - when powered by harvesting energy from their surrounding environment. Unfortunately, the prolonged life of these ultra-low-power systems poses a fundamentally new problem. While the devices last for years, programs that run on them become obsolete when the nature of sensory input or the operating conditions change. The effect of continued execution of such an obsolete program can be catastrophic. For example, if a cardiac pacemaker fails to recognize an impending cardiac arrest because the patient has aged or their physiology has changed, these devices will cause more harm than any good. Hence, being able to react, adapt, and evolve is necessary for these systems to guarantee their accuracy and response time. This project is aimed at devising algorithms, tools, systems, and applications that will enable ultra-low-power, sensor-enabled, computing devices capable of executing complex machine learning algorithms while being powered solely by harvesting energy. Unlike common practices where a fixed classifier runs on a device, this project takes a fundamentally different approach where a classifier is constructed in a manner that it can adapt and evolve as the sensory input to the system, or the application-specific requirements, such as the time, energy, and memory constraints of the system, change during the extended lifetime of the system. To demonstrate the efficacy of the proposed systems, several application-specific, battery-less systems will be developed and deployed, which includes – (1) a personalized air quality index predictor for asthmatic individuals, (2) an ultra-low-power voice assistant that gives voice to everyday objects, and (3) a real-time tracker for shared resources. This research will enable smarter and more intelligent microbots and autonomous systems that will help improve healthcare, agriculture, manufacturing, and the environment. Outcomes of this research bear the potential to transform healthcare through the development of batteryless medical implants and wearable devices that will be able to monitor and learn person-specific physiologic parameters and thus be able to detect anomalies at their onset, which could be the cause of developing the disease. A direct impact of this research is the development of a low-cost, portable, real-time air quality monitor that will transform asthma and chronic obstructive pulmonary disease (COPD) management. Hardware and software tools will be open-sourced. Summer research opportunities will be opened up to high school students and undergrads. An Internet of Things-focused curriculum of interdisciplinary courses will be offered to broaden the participation of students from the health informatics program. Participation of women and members of underrepresented groups will be ensured. Outreach activities in collaboration with local makerspaces, a science center, and a high school will be performed to provide research exposure and to increase awareness of energy harvesting.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.