The implementation of a smartphone-based fall detection system using a high-level fuzzy Petri net

The falling down problem has become one of the very important issues of global public health in an aging society. The specific equipment was adopted as the detection device of falling-down in the early studies, but it is inconvenient for the elderly and difficult for future application. The smart phone more commonly used than the specific fall detection equipment is selected as a mobile device for human fall detection, and a fall detection algorithm is developed for this purpose. What the user has to do is to put the smart phone in his/her thigh pocket for falling down detection. The signals detected by the tri-axial G-sensor are converted into signal vector magnitudes as the basis of detecting a human body in a stalling condition. The Z-axis data sets are captured for identification of human body inclination and the occurrence frequencies at the peak of the area of use are used as the input parameters. A high-level fuzzy Petri net is used for the analysis and the development of identifying human actions, including normal action, exercising, and falling down. The results of this study can be used in the relevant equipments or in the field of home nursing.     

Robust and ubiquitous smartphone-based lane detection

Lane-level positioning is required for several location-based services such as advanced driver assistance systems, driverless cars, predicting driver’s intent, among many other emerging applications. Yet, current outdoor localization techniques fail to provide the required accuracy for estimating the car’s lane.In this paper, we present LaneQuest: an accurate and energy-efficient smartphone-based lane detection system. LaneQuest leverages hints from the ubiquitous and low-power inertial sensors available in commodity off-the-shelf smartphones about the car’s motion and its surrounding environment to provide an accurate estimate of the car’s current lane position. For example, a car making a u-turn, most probably, will be in the left-most lane; a car passing by a pothole will be in the pothole’s lane; and the car angular velocity when driving through a curve reflects its lane. Our investigation shows that there are amble opportunities in the environment, i.e. lane “anchors”, that provide cues about the car lane. To handle the ambiguous location, sensors noise, and fuzzy lane anchors; LaneQuest employs a novel probabilistic lane estimation algorithm. Furthermore, it uses an unsupervised crowd-sourcing approach to learn the position and lane span distribution of the different lane-level anchors.Our evaluation results from implementation on different Android devices and driving traces in different cities covering 260 km shows that LaneQuest can detect the different lane-level landmarks with an average precision and recall of more than 91%. This leads to an accurate detection of the exact car lane position 84% of the time, increasing to 92% of the time to within one lane. This comes with a low-energy footprint, allowing LaneQuest to be implemented on the energy-constrained mobile devices.     

可穿戴式跌倒检测智能系统设计

为提高对老年人跌倒检测的正确率,设计一种可穿戴式跌倒检测系统.研制基于三轴加速度计的跌倒检测设备,给出系统硬件和软件的实现方案;提出基于反向传播(BP)神经网络的跌倒检测算法,将训练好的网络参数植入研制的可穿戴式跌倒检测设备,实现对跌倒的实时检测.实验结果表明:所研制的跌倒检测智能系统能够有效地区分跌倒与非跌倒,正确率达97.37％.     

基于ZigBee的定位和人体跌倒检测系统

提出了一个具有跌倒定位和远程报警功能的无线跌倒监控系统。跌倒监测是基于人体跌倒过程中加速度曲线的变化特性,由三轴加速度传感器和ARM处理器实现;同时介绍了一种新颖的基于ZigBee的定位方法,当监测到人体跌倒时,一个带有跌倒位置的报警信息将立即发送到医护人员的移动手机上。实验结果表明,本系统可以100%监测到人体跌倒,提供精度为1 m的精确定位,使医护人员在5 s内收到跌倒报警信息。     

A smartphone-based system for detecting hand tremors in unconstrained environments

The detection of tremors can be crucial for the early diagnosis and proper treatment of some disorders such as Parkinson’s disease. A smartphone-based application has been developed for detecting hand tremors. This application runs in background and distinguishes hand tremors from common daily activities. This application can facilitate the continuous monitoring of patients or the early detection of this symptom. The evaluation analyzes 1770 accelerometer samples with cross-validation for assessing the ability of the system for processing unknown data, obtaining a sensitivity of 95.8 % and a specificity of 99.5 %. It also analyzes continuous data for some volunteers for several days, which corroborated its high performance.     

SmartMic: a smartphone-based meeting support system

Meetings play an important role in our daily lives. Verbal communication and social relationship development are the primary activities of meeting attendees. In this paper, we propose a meeting support system, namely SmartMic, to enhance user experiences and facilitate social interactions during meetings. SmartMic uses smartphone and readily available facilities in common meeting venues to support easy speaking and establishing new social connections. Meeting attendees in the system speak through smartphone instead of microphone and contact with each other conveniently. Preliminary experiment results show that SmartMic can facilitate the social interaction among attendees and promote the meeting productivity efficiently.     

A smartphone-based virtual white cane

The objective of our research was to develop assistive technology for visually impaired people, with a high appreciation for the human potential to achieve, to learn, and to achieve goals. In this document, we describe a virtual white cane made of a combination of a Smartphone and a laser pointer. In our device, the laser pointer beam reflection is captured by the Smartphone camera. The distance from the virtual white cane to the reflection is computed through active triangulation. Then, a personalized vibration, the magnitude of which corresponds to distance, is generated in the Smartphone. In this way, the users receive information that could prevent collisions with obstacles in the environment. Our contributions include the development of a virtual white cane around a Smartphone and other off-the-shelf accessories and a methodology to provide personalized vibratory feedback to the user. Our experiments show that to navigate, our instrument is better option, in terms of travel time, that the use of the hands. However, the travel time is still better using a traditional white cane than our instrument.     

基于惯性传感器件的跌倒检测系统设计

设计了一种基于MEMS三轴加速度计和双轴陀螺仪的可穿戴式跌倒实时检测系统,阐述了系统的传感单元选择与配置、硬件电路设计和软件设计,并给出了基于人体运动特征参数的跌倒识别算法.实验结果表明:系统可实现正常人体活动和跌倒行为的有效区分.     

基于半监督学习的跌倒检测系统设计

针对老人跌倒时的复杂运动情况,进行跌倒标注的较难实现,提出了基于Tri-training半监督算法的跌倒检测系统。本系统使用3D加速度传感器采集运动加速度数据,然后对数据进行特征提取与部分样本标注,使用Tri-training算法训练分类器,最后使用训练好的分类器进行跌倒识别。具体的数据采集传感器设计为可穿戴式设备,服务器端使用Java编写了一个服务器的程序实现对数据的分析与处理。实验结果表明：该方法使用了大量无标签数据的信息,有效提高了跌倒识别的准确率。实验结果表明：本系统能够满足老年人在日常生活中的需求,对于一些意外跌倒能够给予及时的检测与报警。     

基于阈值分析法的人体跌倒检测系统

为了在老年人跌倒时及时发现并进行救助,设计了一个跌倒检测、定位报警求救的智能系统。系统使用STM32F103ZET6作为微处理器,采用ADXL345三轴加速度传感器采集数据,并用ATK—NEO—6M实现全球定位,跌倒发生时,SIM900A发送包含位置信息的求救短信给特定人员。提出了一种跌倒检测算法,根据设定的合加速度阈值和时间阈值,来检测失重、撞击、静止三个过程是否顺序发生,根据设定的姿态角阈值,检测人体姿态角是否超过正常范围,从而判断是否跌倒。测试结果表明:系统性能稳定,检测跌倒的准确率达到97%,满足人体跌倒检测的标准。     

数据融合的跌倒检测系统设计

为解决跌倒检测中检测设备功耗高、报警范围受限、携带不便等难题,结合Arduino与Android设计了基于MPU6050的跌倒检测系统,提出了基于数据融合的并行阈值算法,通过对5位实验者的模拟测试,该算法实现了97.6%的精确度和99.2%的特异性.实验表明:算法和方案在方便携带的基础上能较为准确地实现人体跌倒检测并及时定位报警.     

A study on a fall detection monitoring system for falling elderly using open source hardware

Multimedia Tools and Applications - Due to the rapid increase in the elderly population and single-person households, it is absolutely necessary to observe the indoor activities of marginalized...     

3D measures exploitation for a monocular semi-supervised fall detection system

Falls have been reported as the leading cause of injury-related visits to emergency departments and the primary etiology of accidental deaths in elderly. Thus, the development of robust home surveillance systems is of great importance. In this article, such a system is presented, which tries to address the fall detection problem through visual cues. The proposed methodology utilizes a fast, real-time background subtraction algorithm, based on motion information in the scene and pixels intensity, capable to operate properly in dynamically changing visual conditions, in order to detect the foreground object. At the same time, it exploits 3D space’s measures, through automatic camera calibration, to increase the robustness of fall detection algorithm which is based on semi-supervised learning approach. The above system uses a single monocular camera and is characterized by minimal computational cost and memory requirements that make it suitable for real-time large scale implementations.     

A simple fall detection algorithm for powered two wheelers

The aim of this study is to evaluate a low-complexity fall detection algorithm, that use both acceleration and angular velocity signals to trigger an alert-system or to inflate an airbag jacket. The proposed fall detection algorithm is a threshold-based algorithm, using data from three-accelerometers and three-gyroscopes sensors mounted on the motorcycle. In the first step, the commonly fall accident configurations were selected and analyzed in order to identify the main causation factors. In the second step, these fall scenarios were replayed by a stuntman using an instrumented motorcycle. Both accelerations and rotational velocities were monitored. These measurements constitute a valuable experimental database to analyze and to understand motorcycle fall mechanism. Based on the analysis of this database, a fall detection algorithm has been developed. This paper presents initial results of a work in progress that aims to provide knowledge about the development of such passive safety systems.     

Mobile phone-based pervasive fall detection

Falls are a major health risk that diminishes the quality of life among the elderly people. The importance of fall detection increases as the elderly population surges, especially with aging “baby boomers”. However, existing commercial products and academic solutions all fall short of pervasive fall detection. In this paper, we propose utilizing mobile phones as a platform for developing pervasive fall detection system. To our knowledge, we are the first to do so. We propose PerFallD, a pervasive fall detection system tailored for mobile phones. We design two different detection algorithms based on the mobile phone platforms for scenarios with and without simple accessories. We implement a prototype system on the Android G1 phone and conduct extensive experiments to evaluate our system. In particular, we compare PerFallD’s performance with that of existing work and a commercial product. The experimental results show that PerFallD achieves superior detection performance and power efficiency.     

跌倒检测在远程健康监管系统中的应用研究

利用三轴加速度传感器对人体活动产生的加速度信号进行采集,提出了将数据分析分割成用户终端信号的预处理和在后台处理两部分。在用户终端采取基于1-class SVM分类算法对疑似数据进行提取,在后台通过分析不同动作事件下其能量损耗的阈值范围的不同进行跌倒判断,并分析了人体在特定时域的速度、位移以及倾角作为判断跌倒的辅助判据。实验表明,该应用能够为老年人的健康提供一种新的保障。     

Power management techniques in smartphone-based mobility sensing systems: A survey

The rapidly enhancing sensing capabilities of smartphones are enabling the development of a wide range of innovative mobile sensing applications that are impacting on everyday life of mobile users. However, supporting long-term sensing applications is challenging because of their key requirements for continuous access to embedded sensors for gathering raw data, which can deplete the device’s battery in a few hours. This problem is expected to remain in the near future because the improvements on the capacity of batteries are coming at a slower pace than those advances in computing and sensing capabilities. The research community has highlighted the need for power-aware and context-aware sensing techniques deployed at different levels of mobile platforms for making a more efficient use of energy resources. Previous studies have analyzed the optimization of power consumption in mobile devices over different critical axes, like data transmission, computing, and hardware design. However, a comprehensive study focused in the challenges of power-aware smartphone-based sensing and strategies for addressing them has not been produced yet. This survey aims to fill this void with a particular focus on mobility sensing systems (e.g., human activity recognition, location-based services), presenting a comprehensive review of relevant strategies aimed at solving this issue. Also, this survey defines a taxonomy for such solutions, highlighting their strengths and limitations. Finally, most relevant open challenges and trends are discussed for providing insights for future research in the field.     

基于双流卷积的实时跌倒行为检测

针对独居老人摔倒问题,构建一种基于双流卷积神经网络(TwoStream CNN)的实时跌倒检测模型.将提取人物轮廓的RGB单帧作为输入的空间流,将连续多帧运动历史图(motion history image,M HI)作为输入的时间流融合,在一个特定维度的全连接层将两个网络的同shape张量Concatenation相...     

Human fall detection using normalized shape aspect ratio

In video surveillance, automatic human fall detection is important to protect vulnerable groups such as the elderly. When the camera layout varies, the shape aspect ratio (SAR) of a human body may change substantially. In order to rectify these changes, in this paper, we propose an automatic human fall detection method using the normalized shape aspect ratio (NSAR). A calibration process and bicubic interpolation are implemented to generate the NSAR table for each camera. Compared with some representative fall detection methods using the SAR, the proposed method integrates the NSAR with the moving speed and direction information to robustly detect human fall, as well as being able to detect falls toward eight different directions for multiple humans. Moreover, while most of the existing fall detection methods were designed only for indoor environment, experimental results demonstrate that this newly proposed method can effectively detect human fall in both indoor and outdoor environments.