The quality of sleep is an important factor in maintaining a healthy life style. To date, technology has not enabled personalized, in-place monitoring and analysis. Current systems are often difficult to use hence limited clinics, or invasive users, e.g., requiring users wear device during sleep. This paper presents iSleep -- practical system monitor individual's using off-the-shelf smartphone. uses the built-in microphone smartphone detect events that closely related quality, including body...

This paper presents COBRA - a visible light communication (VLC) system for off-the-shelf smartphones. encodes information into specially designed 2D color barcodes and streams them between screen camera of Due to the directionality short range light, can preserve user privacy security in many near field scenarios such as opportunistic data exchange We develop new barcode that is optimized streaming small-size low-speed adapts size layout code blocks streamed deal with significant image blur...

Recent advances in wearable sensor technologies have led to a variety of approaches for detecting physiological stress. Even with over decade research the domain, there still exist many significant challenges, including near-total lack reproducibility across studies. Researchers often use some sensors (custom-made or off-the-shelf), conduct study collect data, and build machine-learning models detect There is little effort test applicability model similar data collected from different...

As one of the most popular exercises, running is accomplished through a tight cooperation between respiratory and locomotor systems. Research has suggested that proper rhythm -- coordination breathing strides helps improve exercise efficiency postpone fatigue. This paper presents RunBuddy first smartphone-based system for continuous monitoring. designed to be convenient unobtrusive feedback system, only utilizes commodity devices including smartphone Bluetooth headset. A key challenge in...

With a wealth of scientifically proven health benefits, meditation was enjoyed by about 18 million people in the U.S. alone, as 2012. Yet, there remains stunning lack convenient tools for promoting long-term and effective practice. In this paper, we present MindfulWatch, practical smartwatch-based sensing system that monitors respiration real-time during -- offering essential biosignals can potentially be used to empower various future applications such tracking changes breathing pattern,...

Irrigated arid oasis areas experience shortages in water resources and imbalances between supply demand. A rational allocation strategy must be devised to solve such problems; however, this remains a challenging issue overcome. In study, multi-objective optimization model based on metaheuristic algorithm was established for the Manas River irrigation area Xinjiang. First, considering future population growth development of ecological environment areas, resource established. This developed...

Solar powered air conditioning system is a hot issue in the study field of building energy conservation. An experimental platform solar with microencapsulated phase change material (MEPCM) cooling storage was carried out to evaluate efficiency and coupled relation radiation intensity. The outdoor indoor environmental test used collect performance parameter data room verify effect. combined MEPCM cold which tested Chengdu city, China. According analysis result, transient thermal would decline...

To study Semi-Transparent photovoltaic (STPV) windows, experiments were conducted to test the energy potential of STPV window installed in buildings. Two identical rooms built up as experimental units; one was fitted with amorphous silicon (a-silicon) (PV) and another a conventional window. The interactional influence analyzed among air conditioning consumption, lighting generation. It can be concluded that windows could provide 0.26 kWh/per day save 29% on comprehensive building load...

Typical R-convolution graph kernels invoke the kernel functions that decompose graphs into non-isomorphic substructures and compare them. However, overlooking implicit similarities topological position information between those limits their performances. In this paper, we introduce Deep Hierarchical Graph Alignment Kernels (DHGAK) to resolve problem. Specifically, relational are hierarchically aligned cluster distributions in deep embedding space. The belonging same assigned feature map...

The energy performance of the semi-transparent PV (STPV) window was carried out in a hot-summer and cold-winter zone China. Semi-transparent windows generate electric, reduce heating load aim to utilize daylighting efficiently. In order analyze windows, comparison test rig set up which includes two rooms same size. One room installed with STPV other conventional window. lighting, thermal, electrical tested compared those ambient environment. It observed that maximum power generation (a-SiGe)...

Knowing the dynamics of one's daily stress is essential to effective management in context smart and connected health. However, there lacks a practical unobtrusive means obtain real-time longitudinal information. In this paper, we attempt derive convenient HRV-based (heart rate variability) biomarker named cHRV, which can be used reliably reflect dynamics. cHRV's key advantage lies its low maintenance high practicality. It efficiently calculated only using data from photoplethysmography...

Thermal comfort is an important aspect to take into consideration for the indoor environment of a building integrated with semi-transparent Photovoltaics (STPV) system. The thermal units photovoltaic windows and that conventional windows, which ordinary without PV, were evaluated via on-site tests questionnaires. Using investigation test rig, maximum difference in air temperature was found be around 5 °C between unit comparison unit. predicted mean vote (PMV)–predicted percentage...

In order to make the high permeability of renewable energy distribution network reconfiguration work more practical and effective, this paper put forward a new model which can absorb wind photovoltaic generation. Firstly, we setup mathematical power generation unit conclude generation, made output discretization, divide day time into three partition depend on load characteristic. Secondly, improve basic genetic algorithm about chromosome coding method, reduce initial population infeasible...

如何构造紧凑而有效的特征描述子是机器视觉和模式识别领域重要的研究课题之一。针对SURF (Speeded Up Robust Features)算法的Haar描述子不能充分利用特征点周围信息的缺陷，该文提出了一种新的局部不变描述子加窗灰度差直方图(Windowed Intensity Difference Histogram, WIDH)，该描述子基于特征点周围邻域一个较小的核心区域，通过窗口模板的移动充分利用外围作用区域的灰度差信息，构造了一个维度低且辨识力很强，运算简单高效的描述矢量。实验表明，将WIDH用于改进SURF算法的Haar描述子时，可以用更低维的矢量获取与SURF相近或更好的辨识能力。在抗模糊性和抗噪性方面，WIDH明显优于SURF的Haar描述子，相同的错误率下查全率分别提高了大约35%和50%。

We design and implement an intelligent advisor system for assisting individuals in changing their physical activity behavior. This monitors individual's provides personalized, dynamic, pace-based recommendations to help individual attain his/her goal. It adapts a person's real-life constraints generates using data from the own history as well cohort of people similar individual. Our relies on frequent predictions likelihood goal attainment throughout day, so that current conditions context...

Typical R-convolution graph kernels invoke the kernel functions that decompose graphs into non-isomorphic substructures and compare them. However, overlooking implicit similarities topological position information between those limits their performances. In this paper, we introduce Deep Hierarchical Graph Alignment Kernels (DHGAK) to resolve problem. Specifically, relational are hierarchically aligned cluster distributions in deep embedding space. The belonging same assigned feature map...

The first author has recently received a 3 million RMB, 4 year grant to build Chinapsilas artificial brain, starting in 2008, that will consist of approximately 15,000 interconnected neural net modules, evolved one at time special accelerator board (which is 50 times faster than using an ordinary PC) control the hundreds behaviors autonomous robot. approach taken building this brain fast and cheap (e.g. $1500 for FPGA board, $1000 robot, $500 PC, total $3000), so we hope other groups around...

Abstract Building integrated photovoltaic (BIPV) is an important application of solar cells. In this paper, the experiments were conducted to test performance panels installed in buildings. The carried out Chengdu, Southwest China which located climate zone hot summer and cold winter. real-time power generation, simultaneous generation heat impact on indoor lighting are factors for building energy consumption. Two identical rooms built up as experimental units, one was fitted with amorphous...

PV windows can potentially produce electricity, reduce the air-conditioning load, and provide natural light. Cross-seasonal experimental tests for long period could eliminate gap between real outdoor test simulation estimation. In this research, lighting-thermal-electricity performance of high-efficiency c-silicon was tested, improvement has been put forward according to conditions. The long-term experiment conducted cross different seasons, including summer, autumn, winter seasons. highest...