Smart grids are essentially distribution networks equipped with technology for providing electricity suppliers and users with information to optimize the use of energy and therefore in favor of the energy providers and consumers since the energy providers benefit from the more balancing energy distribution and generation and the energy customers benefit from the lower cost of energy price and higher reliable electricity utility. The sub-project I on the progress in realizing the soft skill of the intelligent computing has developed the machine learning-based energy saving models. Three interacting inference engines were evolved to achieve the best energy saving strategy for smart home. With those application information and user’s activity preference, we developed a smart activity schedule system, it would give a schedule according to price tariff, renewable energy and battery storage system that compromise the users preference.
The number of dementia patients increases rapidly in Taiwan recently. Dementia has great impact on personal healthy, families’ and the national economy. Caregivers have to not only care daily living and social functioning of patients, but also to respond to the individual and demand of patients. As a result, caregivers are usually exhausted due to the pressure and burden of dementia patients. The objective of this project is therefore to develop innovative mobile technologies that assist both dementia patients and caregivers. More concretely, we want to develop mobile technologies that “observe”, “aware”, “empathize”, “prevent crisis” and “promote doing health behavior of patients with dementia”. By constructing smart healthcare environment and by recording the view with first-person perspective camera. In addition, we also propose a social care information platform to assist dementia patient. Our research results are able to reduce the pressure and cost of caring to patients with dementia and improve the quality of life of patients with dementia. Finally, we also investigate “filial piety” and “family resilience” that may cause impact to families care dementia patient in order to further understand whether development of mobile technology really improves quality of lives of the caregivers and patients with dementia.
M-CHESS: Machine to Machine-based Context-aware Home Energy Saving System
Mchess is aim to find a optimal solution to reduce the cost of users meanwhile preserve the user’s activity preference even in the multiple users environment. It is a combination of three engines, they are 1. Energy-Responsive Context Inference Engine, 2. User Comfort Evaluation Engine, 3. Energy Saving Decision Support Engine. By using machine learning, we can know about what activity that user is doing, and use this information with the environment sensor data, to decide which action the system can do automatically to help user feels better and reduce his/her cost.
Cyber Physical System
信息物理融合系統(Cyber Physical System)是一個透過結合電腦運算、感測器、及制動裝置的整合控制系統，讓人得以在時間、空間方面的感測及控制得以延伸；而隨著電腦軟硬體技術的進步，信息物理融合系統已逐漸普及於日常生活之中，並創造出各種不同於以往的生活體驗與應用。而在信息物理融合系統眾多可能的應用之中，能夠深入一般生活與人們頻繁互動的智慧空間是其中最重要的一項；而隨著醫療科技大幅躍進使得人們平均壽命延長，人口老化進而步入高齡化社會成為全球包括台灣在內所面臨的重要議題後，「在地老化(Aging in Place)」的理念逐漸興起，打造智慧空間以「家」為照護資源的概念為目前各國照護趨勢，而台灣的行政院衛生署於2008年起也開始推廣遠端照護計畫。本計畫將發展一個基於信息物理融合系統的智慧空間用以輔助年長者在地養老，提供一套健全完整之年長者居家照護系統。藉由信息物理融合系統為基礎並以活動辨識及分析為目的建構上述智慧照護環境，不僅隨時掌握年長者之日常生活活動(Activities of Daily Living, ADL)狀況，也提供分析行為特性與各行為間發生順序之關聯性解析。預期本計畫能夠深化信息物理融合系統於智慧空間的應用和以人為中心的最佳化協調方式，且設計實作出之系統所提供的服務可使家屬與醫護人員更加瞭解長者行為特性，並提昇年長者居家照護之生活品質。
A cyber-physical system (CPS) is a system of collaborating computational elements sensing and controlling physical entities, and it enables humans to extend the sensing/controlling capability in space and time. As the advance of computer technology in hardware and software, CPS has been applied in daily living pervasively and created lots of innovative experiences. Among all these applications, an important one is intelligent spaces, which interacts with humans frequently in daily living. With a substantial leap in medical technology makes it an average life expectancy, an aging population. Thus the aging society has become an important issue of the world, so a concept of "Aging in Place" has gradually rise. The current trend of the world is to build "smart care home" as care resources. And in 2008, the Taiwan Department of Health also began to promote the tele-healthcare plan. Therefore, this project will develop a CPS-based intelligent space for aging in place, which will focus on activity recognition and analysis. This intelligent space can help not only know elders' activities of daily living (ADL), but also understand the corresponding behavior patterns. This project will deliver a demonstration application of CPS in intelligent space with human-centric optimal coordination among CPS, which can improve the living quality of aging in place by further understanding the behavior patterns of elders.
Despite the prolonging of citizens’ life expectancy, the elderly cancer survivors still need to face disease itself and the discomfort and stress brought by the treatment. How to use emerging technology to enhance the quality of life for elderly cancer survivors in Taiwan is obviously one of the most important issues in the next few decades. Among them, physical activity and health management, social activity, and quality of sleep are the key points to determine the quality of life of elderly cancer survivors. This project aims to integrate the experts from the fields of computer science, electrical engineering, cancer medicine, nursing and psychology to build a Cancer-survivor HEalth Enhancing and Recovery System (CHEERS) focusing on "Physical Activity and Health Management", "social mobility," and "sleep quality" which are the key topics for the quality of life of elderly cancer survivors. In the last three years, we build a wireless sensor platform, and personal health models from different perspectives. First, we apply support vector data description to build Health Alert Context Model by analyzing circadian rhythm. Second, we give a health preliminary estimation by dynamic Bayesian network.