FALL DETECTION SYSTEM FOR ELDER PEOPLE MONITORING USING HOME NETWORKS

FALL DETECTION SYSTEM FOR ELDER PEOPLE MONITORING USING HOME NETWORKS M. KESHAVANANDA 1, V. PANDU RANGA 2, NISHI CHANDRA 3 1 M. Keshavananda, PG Scholor, Dept of ECE, CMR College of Engineering And Technology, Kandlakoya, Hyderabad, Telangana, India, Email: keshavananda.m@gmail.com 2 V. Pandu Ranga, Assistant professor, Dept of ECE, CMR College of Engineering And Technology, Kandlakoya, Hyderabad, Telangana, India, Email: panduvemula1983@gmail.com 3 Nishi Chandra, Assistant Professor, Dept of ECE, CMR College of Engineering and Technology Kandlakoya, Hyderabad, India, Email: lognishi@gmail.com. Abstract: The population of 65-and over aged people in the developed countries will approach 20% of total population in the next 20 years and will obviously become a serious healthcare issue in the near future. Among the elderly, the fall events can be an unpredictable and dangerous event. Various falldetection solutions have been previously proposed to create a reliable surveillance system for elderly people with high requirements on accuracy, sensitivity and specificity. In this paper, an enhanced fall detection system is proposed for elderly person monitoring that is based on smart sensors worn on the body and operating through consumer home networks. With treble thresholds, accidental falls can be detected in the home healthcare environment. By utilizing information gathered from an accelerometer, B.P. Machine and smart sensors, the impacts of falls can be logged and distinguished from normal daily activities. Furthermore, the cost of healthcare is highly related to the response and rescue time, and can be greatly reduced by fast detection and delivering signals to the specified operator for immediate consideration. Key words: B.P. Machine, GSM, ZIGBEE, Sensors. I. INTRODUCTION In recent years, many types of consumer electronics devices have been developed for home network applications. A consumer home network usually contains various types of electronic devices, e.g. sensors and actuators, so that home users can control them in an intelligent and automatic way to improve their quality of life. Some representative technologies to implement a home network include: IEEE 802.11, Ultra Wide Band (UWB), Bluetooth and ZigBee, etc. ZigBee is suitable for consumer home networks because various sensors can be deployed to collect home data information in a distributed, self-organizing manner with relatively low power. Some typical applications include home automation, home activity detection (like fall detection) and home healthcare, etc., Kinsella and Phillips found that the population of 65-andover aged people in the developed countries will approach 20% of total population in the next 20 years and will obviously become a serious healthcare issue in the near future. In China alone, the population over the age of 60 years old is 133.9 Million. Among the elderly, the fall events can be an unpredictable and dangerous event. Statistics show that one among three 65-and-over aged person falls every year. Among these fall events, 55% occur at home and 23% occur near the home. In 2003, the global number of deaths caused by fall events was approximately 391,000 and specifically 40% of the falls were from people over 70 years of age. Thus, reliable consumer based fall detection systems need to be designed, tested and commercially deployed to countries all around the world. Furthermore, the cost of healthcare is highly related to the response and rescue time, and can be greatly reduced by fast detection and delivering signals to the specified operator for immediate consideration. In this paper, an enhanced fall detection system for elderly person monitoring through a consumer home network environment is proposed that based on smart sensors which are worn on the body. II. DESIGN AND IMPLEMENTATION Sensor section: The structure of proposed fall detection system is shown in Fig. 1 & Fig. 2, whose

core structure is based on a Microprogrammed Controller Unit (MCU). The Accelerometer sensor, BP machine and other smart sensors including temperature sensor all integrated on one single board, recording real time acceleration and Temperature of the body is measures and send to the Microcontroller. The MMA7660FC is a ±1.5 g 3-Axis Accelerometer with Digital Output (I2C) is used to find the fall of the elder person. The DS1621 Digital Thermometer is used to detect the body temperature of the elder person. These digital outputs are continuously monitored and send to the LPC 1768 microcontroller. If the threshold value of the Accelerometer is exceeded then it checks for the Blood pressure of the person. And these values are displayed on the LCD. Whenever the fall is occurred to differentiate the accidental fall from the Normal daily activities Blood pressure of the person is measured. These data is transmitted to the data storage section wirelessly by using Zigbee technology Data storage section: If the fall of the person is conformed as accidental then the message is send to the either to relatives or to the Ambulance by using GSM. If the BP of the person is exceeds the threshold value then the message is send to the Ambulance along with the GPS location. So that, they can find the location of the elderly person easily and can give the treatment at the early stage only. And the data is stored in the Personnel computer to identify the patient condition for the complete day, which is useful for the personnel doctor to give the right treatment. The data is transferred from the microcontroller LPC 2103 to the PC by using Ethernet. POWER SUPPLY ARM7 LPC 2103 ZIGBEE Fig.2: Data Storage Section Flow chart: LCD DISPLAY (16*2 LINES) MAX 232 PC GSM POWER SUPPLY B.P. MACHINE ACCELEROME TER TEMPERATURE SENSOR ARM7 LPC1768 Fig.1: Sensor Section LCD DISPLAY (16*2 LINES) GPS ZIGBEE Fig.3: Flow chart of the Project Steps to Implement the Proposed System: 1. Give the power supply to the hardware board. 2. Set up the Network and make sure that both Zigbee modules are in the network range. 3. Turn on all the sensors. 4. Collect the data from the MEMS accelerometer.

5. Find whether it exceeded the threshold value of the MEMS accelerometer. 6. If it not Exceeded then check for the temperature threshold value. 7. If the temperature threshold value is exceeded then send message to the relatives. If not go to the step-4. 8. Once MEMS threshold is crossed then check for the Blood pressure threshold. 9. If Blood pressure Threshold is exceeded then send the message to the Ambulance along with the GPS location of the elder person. 10. If Blood pressure is not exceeded then check for the Temperature of the person, if it exceeded then send message to the Relative. 11. If temperature is not exceeded the threshold then go to step-4. III. HARDWARE SYSTEM A. ARM Based LPC1768: The LPC1768/66/65/64 is ARM Cortex-M3 based microcontrollers for embedded applications featuring a high level of integration and low power consumption. The ARM Cortex-M3 is a next generation core that offers system enhancements such as enhanced debug features and a higher level of support block integration. It operates at CPU frequencies of up to 100 MHz. The ARM Cortex-M3 CPU incorporates a 3-stage pipeline and uses Harvard architecture with separate local instruction and data buses as well as a third bus for peripherals. The ARM Cortex-M3 CPU also includes an internal prefetch unit that supports speculative branching. B. ARM Based LPC 2103: The LPC2103 microcontrollers are based on a 16- bit/32-bit ARM7TDMI-S CPU with real-time emulation that combines the microcontroller with 8 kb, 16 kb or 32 kb of embedded high-speed flash memory. Due to their tiny size and low power consumption, the LPC2103 is ideal for applications where miniaturization is a key requirement. A blend of serial communications interfaces ranging from multiple UARTs, SPI to SSP and two I 2 C-buses make these devices very well suited for communication gateways and protocol converters. Various 32-bit and 16-bit timers, an improved 10-bit ADC, PWM features through output match on all timers, and 32 fast GPIO lines with up to nine edge or level sensitive external interrupt pins make these microcontrollers particularly suitable for industrial control and medical systems. C. Temperature sensor (DS1621): The DS1621 Digital Thermometer and Thermostat provides 9-bit temperature readings, which indicate the temperature of the device. The DS1621 measures temperature using a band gapbased temperature sensor. A delta-sigma analog-todigital converter (ADC) converts the measured temperature to a digital value that is calibrated in C; for F applications, a lookup table or conversion routine must be used. Features Simply Adds Temperature Monitoring and Control to Any System Measures Temperatures From -55 C to +125 C in 0.5 C Increments. Fahrenheit Equivalent is -67 F to 257 F in 0.9 F Increments Temperature is Read as a 9-Bit Value (2- Byte Transfer) Converts Temperature to Digital Word in Less than 1s Can Be Used in a Wide Variety of Applications Power Supply Range (2.7V to 5.5V) Data is Read From/Written Via a 2-Wire Serial Interface (Open Drain I/O Lines) D. GSM: Fig.4: DS1621 IC GSM (Global System for Mobile communications) is an open, digital cellular technology used for transmitting mobile voice and data services. GSM

supports voice calls and data transfer speeds of up to 9.6 Kbit/s, together with the transmission of SMS (Short Message Service). GSM operates in the 900MHz and 1.8GHz bands in Europe and the 1.9GHz and 850MHz bands in the US. Terrestrial GSM networks now cover more than 80% of the world s population. GSM satellite roaming has also extended service access to areas where terrestrial coverage is not available. Architecture and Building Blocks: GSM is mainly built on 3 building blocks. GSM Radio Network This is concerned with the signaling of the system. Hand-overs occur in the radio network. Each BTS is allocated a set of frequency channels. GSM Mobile switching Network This network is concerned with the storage of data required for routing and service provision. GSM Operation and Maintenance The task carried out by it include Administration and commercial operation, Security management, Network configuration, operation, performance management and maintenance tasks. Space segment. Control segment. User segment. The following points provide a summary of the technology at work: The control segment constantly monitors the GPS constellation and uploads information to satellites to provide maximum user accuracy Your GPS receiver collects information from the GPS satellites that are in view. Your GPS receiver accounts for errors. For more information, refer to the Sources of Errors. Your GPS receiver can calculate other information, such as bearing, track, trip distance, and distance to destination, sunrise and sunset time so forth. Your GPS receiver displays the applicable information on the screen. F. ZIGBEE: Fig.6: GPS Working E. GPS: Fig.5: GSM architecture Global Positioning System (GPS) technology is changing the way we work and play. You can use GPS technology when you are driving, flying, fishing, sailing, hiking, running, biking, working, or exploring. With a GPS receiver, you have an amazing amount of information at your fingertips. Here are just a few examples of how you can use GPS technology. GPS technology requires the following three segments. Zig-bee is a specification for a suite of high level communication protocols using small, lowpower digital radios based on the IEEE 802.15.4,2006 standard for wireless personal area networks (WPANs), such as wireless headphones connecting with cell phones via short-range radio. The technology defined by the Zig-bee specification is intended to be simpler and less expensive than other WPANs, such as Bluetooth. Zig-bee is targeted at radio-frequency (RF) applications that require a low data rate, long battery life, and secure networking. Characteristics Dual PHY (2.4GHz and 868/915 MHz)

Data rates of 250 kbps (@2.4 GHz), 40 kbps (@ 915 MHz), and 20 kbps (@868 MHz) Optimized for low duty-cycle applications (<0.1%) CSMA-CA channel access Yields high throughput and low latency for low duty cycle devices like sensors and controls Multiple topologies: star, peer-to-peer, mesh 65,535 network nodes. Fully hand-shaked protocol for transfer reliability Range: 50m typical (5-500m based on environment) Fig.7: ZIGBEE Module G. MEMS accelerometer: The MMA7660FC is a ±1.5 g 3-Axis Accelerometer with Digital Output(I2C). It is a very low power, low profile capacitive MEMS sensor featuring a low pass filter, compensation for 0g offset and gain errors, and conversion to 6-bit digital values at user configurable samples per second. The device can be used for sensor data changes, product orientation, and gesture detection through an interrupt pin (INT). The device is housed in a small 3mm x 3mm x 0.9mm DFN package. Features Digital Output (I2C) 3mm x 3mm x 0.9mm DFN Package Low Power Current Consumption: Off Mode: 0.4 μa, Standby Mode: 3 μa, Active Mode: 47 μa at 1 ODR Configurable Samples per Second from 1 to 120 samples a second. Low Voltage Operation: Analog Voltage: 2.4 V - 3.6 V Digital Voltage: 1.71 V - 3.6 V Auto-Wake/Sleep Feature for Low Power Consumption Tilt Orientation Detection for Portrait/Landscape Capability Low Cost Principle: The Free scale Accelerometer consists of a MEMS capacitive sensing g-cell and a signal conditioning ASIC contained in a single package. The sensing element is sealed hermetically at the wafer level using a bulk micro machined cap wafer. The g-cell is a mechanical structure formed from semiconductor materials (polysilicon) using masking and etching processes. The sensor can be modeled as a movable beam that moves between two mechanically fixed beams. Two gaps are formed; one being between the movable beam and the first stationary beam and the second between the movable beam and the second stationary beam. The ASIC uses switched capacitor techniques to measure the g-cell capacitors and extract the acceleration data from the difference between the two capacitors. The ASIC also signal conditions and filters (switched capacitor) the signal, providing a digital output that is proportional to acceleration. H. Liquid-crystal display (LCD): It is a flat panel display, electronic visual display that uses the light modulation properties of liquid crystals. Liquid crystals do not emit light directly. LCDs are available to display arbitrary images or fixed images which can be displayed or hidden, such as preset words, digits, and 7-segment displays as in a digital clock. I. Blood Pressure sensor: Blood Pressure & Pulse reading are shown on display with serial out for external projects of embedded circuit processing and display. Shows Systolic, Diastolic and Pulse Readings. Compact design fits over your wrist like a watch. Easy to use wrist style eliminates pumping. Features Intelligent automatic compression and decompression Intelligent device debugging, automatic power to detect Local tests for : wrist circumference as 135-195mm

Large-scale digital liquid crystal display screen, Easy to Read Display Fully Automatic, Clinical Accuracy, Highaccuracy Power by External +5V DC Serial output data for external circuit processing or display. can then execute each tool with the correct options. It is also possible to create new projects in KEIL. Source files are added to the project and the tool options are set as required. The project can then be saved to preserve the settings. The project is reloaded and the simulator or debugger started, all the desired windows are opened. KEIL project files have the extension IV. SOFTWARE TOOLS KEIL SOFTWARE: It is possible to create the source files in a text editor such as Notepad, run the Compiler on each C source file, specifying a list of controls, run the Assembler on each Assembler source file, specifying another list of controls, run either the Library Manager or Linker (again specifying a list of controls) and finally running the Object-HEX Converter to convert the Linker output file to an Intel Hex File. Once that has been completed the Hex File can be downloaded to the target hardware and debugged. Alternatively KEIL can be used to create source files; automatically compile, link and covert using options set with an easy to use user interface and finally simulate or perform debugging on the hardware with access to C variables and memory. Unless you have to use the tolls on the command line, the choice is clear. KEIL Greatly simplifies the process of creating and testing an embedded application. V. RESULTS Fig.8: Keil Software- internal stages Projects: The user of KEIL centers on projects. A project is a list of all the source files required to build a single application, all the tool options which specify exactly how to build the application, and if required how the application should be simulated. A project contains enough information to take a set of source files and generate exactly the binary code required for the application. Because of the high degree of flexibility required from the tools, there are many options that can be set to configure the tools to operate in a specific manner. It would be tedious to have to set these options up every time the application is being built; therefore they are stored in a project file. Loading the project file into KEIL informs KEIL which source files are required, where they are, and how to configure the tools in the correct way. KEIL Fig.9: Sensor and Data storage section of the Project Fig.10: Data stored in the PC VI. CONCLUSION In this paper, an enhanced fall detection system based on on-body smart sensors was proposed, implemented, and deployed that successfully detected accidental falls in a consumer home application. By using information from an accelerometer, smart

sensor and cardio tachometer, the impacts of falls can successfully be distinguished from activities of daily lives reducing the false detection of falls. From the dataset of 30 participants, it is found that the proposed fall detection system achieved a high accuracy of 97.5%, and the sensitivity and specificity are 96.8% and 98.1% respectfully. The proposed system is ready to be implemented in a consumer device. VII.REFERENCES [1] I. Akyildiz, W. Su, Y. Sankarasubramaniam, and E. Cayirci, Wireless sensor networks: a survey, Journal of Computer Networks, vol. 38, no.4, pp. 393-422, March 2002. [2] J. Yick, B. Mukherjee, and D. Ghosal, Wireless sensor network survey, Journal of Computer Networks, vol. 52, no. 12, pp. 2292-2330, Aug. 2008. fall detection algorithm in realworld falls, PLoS ONE, vol. 7, no. 5, pp. 1-8, May 2012. Name: M Keshavananda B.Tech: Mahatma Gandhi Institute of Technology passed in 2013 M.Tech: CMR College of Engineering and Technology (pursuing) [3] K. Kinsella and D. R. Phillips, Global aging: the challenge of success, Population Bulletin, vol. 60, 2005. [4] Tabulation on the 2010 population census of the people s republic of China, China Statistics, May 2013, on-line. [5] S. Demura, S. Shin, S. Takahashi, and S. Yamaji, Relationships between gait properties on soft surfaces, physical function, and fall risk for the elderly, Advances in Aging Research, vol. 2, pp. 57-64, May 2013. [6] S. R. Lord and J. Dayhew, Visual risk factors for falls in older people, Journal of American Geriatrics Society, vol. 49, no. 5, pp. 508-515, Dec. 2001. Name: Mr.V Pandu Ranga B.Tech: PVP Sidhrtha Institute of technology M.Tech: HITAM Engineering College. [7] WHO, The injury chart-book: a graphical overview of the global burden of injury, Geneva: WHO, pp. 43-50, 2012. [8] M. Mubashir, L. Shao, and L. Seed, A survey on fall detection: Principles and approaches, Neurocomputing, vol. 100, no. 16, pp. 144-152, Jan. 2013. [9] Q. Zhang, L. Ren, and W. Shi, HONEY a multimodality fall detection and telecare system, Telemedicine and e-health, vol. 19, no. 5, pp. 415-429, Apr. 2013. [10] F. Bagalà, C. Becker, A. Cappello, L. Chiari, and K. Aminian, Evaluation of accelerometer-based Name: Nishi Chandra, B.tech: IET,Dr.B.R.Ambedkar University, Agra(UP). PG: HBTI(UPTU) Lacknow.