ISBN:378-26-138420-0286
INTERNATIONAL CONFERENCE ON CIVIL AND MECHANICAL ENGINEERING, ICCME-2014
HABITUAL DESCEND RECOGNITION SCHEME BY SMART PHONE APPLICATION Dr.R.Dhaya, Dept. of CSE, Velammal Engineering College, Chennai-66., dhayavel2005@gmail.com
Ambhika.C., PG Student, Dept. of CSE, Velammal Engineering College, Chennai-66. ambhikac@gmail.com
Anjana Devi.J, PG Student, Dept. of CSE, Velammal Engineering College, Chennai-66 anjanajavar@gmail.com
. ABSTRACT: The mobile application being proposed is capable of detecting possible falls, through the use of special sensors and through a user friendly interface that can be used to alert relatives, doctors or other people who take care of the elderly. The alert messages contain useful information about the people in danger, such as his/her geo-location and also corresponding directions on a map. In occasions of false alerts, the supervised person is given the ability to estimate the value of importance of a possible alert and to stop it before being transmitted. The system is capable of monitoring elderly people in real time. The Accidental Fall Detection System will be able to assist care takers as well as the elderly. This fall detection system is designed to detect the accidental fall of the elderly and to alert relatives, doctors or other people who take care of the elderly via Messaging Services (SMS) immediately. In this application, the accelerometer is used as to detect the sudden movement or fall and the Global System for Mobile (GSM) modem, to send out SMS to the care taker. The objective of this paper is to provide the security for the people who may suffer a fall, by an advanced android application with Android mobiles. Key Words: Fall Detection, Sensors, Geo Location, SMS, GSM 1.
INTRODUCTION
Falls increase risk for serious injuries, chronic pain, long-term disability, and loss of independence, psychological and social limitations due to institutionalization. Nearly 50% of older adults hospitalized for fall- related injuries are discharged to nursing homes or long-term care facilities. A fall can cause psychological damage even if the person did not suffer a physical injury. Those who fall often experience decrease activities of daily living and selfcare due to fear of falling again. This behavior decreases their mobility, balance and fitness and leads to reduced social interactions and increased depression. The mortality rate for falls increases
progressively with age. Falls caused 57% of deaths due to injuries among females and 36% of deaths among males, age 65 and older . Majority of falls result from an interaction between multiple long-term and short-term factors in person’s environment . Common risk factors include problems with balance and stability, arthritis, muscle weakness, multiple medications therapy, depressive symptoms, cardiac disorders, stroke, impairment in cognition and vision Detection of a fall possibly leading to injury in timely manner is crucial for providing adequate medical response and care. Present fall detection systems can be categorized under one of the following groups: • User activated alarm systems (wireless tags), • Floor vibration-based fall detection, • Wearable sensors (contact sensors and switches, sensors for heart rate and temperature, accelerometers, gyroscopes), • Acoustic fall detection, • Visual fall detection. The most common method for fall detection is using a triaxial accelerometers or bi-axial gyroscopes. Accelerometer is a device for measuring acceleration, but is also used to detect free fall and shock, movement, speed and vibration. Using the threshold algorithms while measuring changes in acceleration in each direction, it is possible do detect falls with very high accuracy. Using two or more triaxial accelerometers and combining them with gyroscopes at different body locations it is possible to recognize several kinds of postures (sitting, standing, etc.) and movements, thereby detecting falls with much better accuracy. An easy and simple method to detect fall detection of people is using accelerometer together with ZigBee transceiver to communicate with Monitoring System through wireless network, and in this paper a system for monitoring and fall detection of people using mobile MEMS accelerometers will be presented. The first three functions provide recording in a database, and also a text message is sent to the
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT 80
www.iaetsd.in
ISBN:378-26-138420-0287
INTERNATIONAL CONFERENCE ON CIVIL AND MECHANICAL ENGINEERING, ICCME-2014 supervisor with latitude, longitude and other useful broken or fractured bones, cuts, abrasions, soft tissue data. Afterwards, you can detect the elder person damage, and even death. They have psychological through Google maps. Additionally, an application consequences, fear of falling leads to isolation, worsening of mental health, and general degradation was implemented for the attending physician, which of quality of living. If falls cannot be is connected with the database, through which s/he prevented, the next best option is detecting them can obtain a complete picture of the patients’ status, accurately, and summoning the required help to draw useful conclusions and proceed to possible immediately. An automatic fall detection system can change in medical treatment. do this; however, to be usable, the system should not Today, majority of people are smart phone be prohibitively expensive, should be convenient to users Falls increase risk for serious injuries, chronic carry on one's person, and should be capable of pain, long-term disability, and loss of independence, generating alerts even if the user is rendered psychological and social limitations due to unconscious due to fall. Smartphone’s are thus institutionalization. Nearly 50% of older adults uniquely positioned; they can gather information hospitalized for fall- related injuries are discharged to about their surroundings using built-in sensors, nursing homes or long-term care facilities. A fall can process it in real-time, and generate alerts in various cause psychological damage even if the person did forms. In this paper, we design and develop an not suffer a physical injury. The mobile application Android application that monitors device sensors to being proposed is capable of detecting possible falls, calculate device acceleration and orientation, and in case of an elderly person or an unhealthy person, detects occurrence of fall using these inputs and realsuch that the delay in treatment may be avoided due time pattern recognition techniques. We also describe to inefficient communication in situations where the sensor data collection, including fall signature person is unconscious. This can be done through the patterns, and alternative approaches tried for fall use of special sensors and through a user friendly detection. On detecting a fall, the application interface that can be used to alert relatives, doctors or generates alerts like emails, text messages, and voice other people who take care of the elderly. calls. The specifics of alerts to be generated and 2. OBJECTIVE OF THIS PAPER persons to be contacted are configured by user. We use speech recognition to reduce false positives and The system is capable of monitoring elderly improve fall detection accuracy. We also test this people in real time. The accidental fall detection application against a number of daily activities and system will be able to assist care takers as well as the falls, and present the results. elderly. It is an application with the ability of automatic fall detection, by using the mobile sensors, 3. LITERATURE SURVEY warning signal by pressing a button in cases of emergency, detection and automatic notification to The authors [1] presented an application for supervisors as well as visual display to passerbies. mobile phones which can monitor physical activities The application uses basically two incorporated of users and detect unexpected emergency situations mobile sensors, namely the accelerometer and the such as a sudden fall or accident. Upon detection of gyroscope sensor. A counter starts counting loudly on such an event, the mobile phone can inform a the screen from 30 to 0. If the counter reaches 0, then designated centre (by automatically calling or an SMS message is sent to the caregiver or relative sending message) about the incident and its location. and an entry is made to the database. The first service The application operates based on analysis of user detects the patient’s position and calculates whether movements using data provided by accelerometers the patient is further away than a set distance. When integrated in mobile phones. The authors [3] used a activated can give directions to the patient what route common Android-based smart phone with an to follow to return back to home. This fall detection integrated tri-axial accelerometer. The threshold is system is designed to detect the accidental fall of the adaptive based on user provided parameters such as: elderly and to alert relatives, doctors or other people height, weight, and level of activity. These variables who take care of the elderly via messaging services also adapt to the unique movements that a cell phone (SMS) immediately. In this application, the experiences as opposed to similar system which accelerometer is used as to detect the sudden require users to mount accelerometers to their chest movement or fall and the global system for mobile or trunk. If a fall is suspected a notification is raised (GSM) modem, to send out SMS to the care taker. requiring the user’s response. If the user does not respond, the system alerts prespecified, social 2.1 SCOPE contacts with an informational message via SMS. When a contact responds with an incoming call the Falls in people happen due to reasons like system commits an audible notification, old age, dementia, Parkinson’s disease, learning automatically answers the call, and enables disabilities and poor motor control. Falls result in speakerphone. If a social contact confirms a fall, an
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT 81
www.iaetsd.in
ISBN:378-26-138420-0288
INTERNATIONAL CONFERENCE ON CIVIL AND MECHANICAL ENGINEERING, ICCME-2014 between the patient-caregiver and performing a party appropriate emergency service is alerted. Our system call between the caregiver-patient and patient’s local provides a realizable, cost effective solution to fall 911. As patients use this monitoring system more, it detection using a simple graphical interface while not will better learn and identify normal behavioural overwhelming the user with uncomfortable sensors. patterns which increases the accuracy of the The authors [5] proposed a fall detector that uses the Bayesian network for all patients. Normal behaviour accelerometers available in smart phones and classifications are also used to alert the caregiver or incorporates different algorithms for robust fall help patients navigate home if they begin to wander detection such as thresholding and wavelet while driving allowing for functional transforms. We implemented our fall detector on a independence.Wandering is a behavioural disorder, smart phone running the Android 2 operating system. which occurs in Alzheimer’s disease or other Our experimental results show that compared to a dementia. People who wander are at risk of physical simple thresholding algorithm, using wavelet harm and untimely death. Moreover, wandering transforms achieve better true positive performance behaviour causes a lot of stress to the caregivers. In while decreasing the rate of false positives the last few years, different geolocation devices have drastically. Besides the fall detection capability, our been developed in order to minimize risk and manage implementation also provides location information unsafe wandering[11]. These detection systems rarely using Google Maps about the person experienced the meet patients and caregivers’ needs because they are fall, using the available GPS interface on the smart not involved in the devices building process. phone and a warning about the fall and the location information are transmitted to the users, 4. EXISTING SYSTEM such as the caregivers, via SMS, email and Twitter messages. The authors [8] proposed a mechanism An application for Apple IOS by using an which suit the Elderly persons with Alzheimer’s accelerometer to detect falls. A possible drawback is disease and dementia have many behavior disorders that the development platform Apple IOS is not such as wandering, repeatedly questioning and being accessible to the average user. An application in uncooperative during the day. Their wandering Symbian s60 using machine learning algorithm takes behavior is a major cause of death, so it is an 64 samples every two seconds from the especially serious problem for caregivers. It is accelerometer and decides whether there is a fall. therefore very important to monitor the wanderer’s Disadvantage location. Numerous mobile phone-based location o Not secure and not preserving detection systems have been developed. The location privacy is obtained by the caregivers accessing the mobile o The patient can’t be in observation company; however, the caregiver is not notified that at all times. the wanderer has left home, which is a major problem o In Emergency cases it causes of these systems. In this study, the newly-developed serious hospitalization for cardiac system immediately detects that the wanderer is away Patient. from home and then automatically transmits o The health care system is not notification of the wandering elderly person’s available for the patients, aged location to the caregiver once a minute. The persons who are out of the facility. authors [9] explored the use of mobile social network technology combined with modern mobile phone 5. PROPOSED SYSTEM hardware as a platform for programming applications in the elder care area. An application that covers two In this paper, we designed an application use cases for outdoors monitoring and detecting with the ability of automatic fall detection, by using disorientations of the elderly is introduced. The the mobile sensors, warning signal by pressing a system leverages on standard mobile terminals button in cases of emergency, detection and (Android G1) equipped with GPS and compass automatic notification to supervisors as well as visual devices and on Liber Geo-Social, a mobile social display to passerbies. The application uses basically framework we are developing. two incorporated mobile sensors, namely the The data collected from the device is accelerometer and the gyroscope sensor. A counter evaluated using Bayesian network techniques which starts counting loudly on the screen from 30 to 0. If estimate the probability of wandering behavior the counter reaches 0, then an SMS message is sent to [10].Upon evaluation several courses of action can be the caregiver or relative and an entry is made to the taken based on the situation’s severity, dynamic Database. The first service detects the patient’s settings and probability. These actions include position and calculates whether the patient is further issuing audible prompts to the patient, offering away than a set distance. When activated can give directions to navigate them home, sending directions to the patient what route to follow to return notifications to the caregiver containing the location back to home. of the patient, establishing a line of communication
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT 82
www.iaetsd.in
ISBN:378-26-138420-0289
INTERNATIONAL CONFERENCE ON CIVIL AND MECHANICAL ENGINEERING, ICCME-2014 Advantages: location details of Elderly people. That message contain Emergency alert of URL based Location link. When care taker • Fall detection along with the patient’s get alert message, He can find out the landmark location with the location is sent to the care taker. help of Google map. • Helpline video helps the on-goers and Helpline video: Helpline video containing elderly people’s passerby to take the immediate action. information’s like address, caretaker numbers, blood group and the personal medical details. It will be play automatically when 5.1 ARCHITECTURE DIAGRAM the user getting fall down condition. These Information’s are The FALL DETECTION is something that we have very useful when somebody trying to help that elderly people in developed at Alert1 so you can be safe at all times. Whether you that situation. are a senior citizen and want to maintain your independence,Route a map Integration: If care taker click that URL link from concerned family member looking for peace of mind, or the a message, He will get Elderly people fall down exact location caregiver with patients, this tool has been developed for you. which is Destination place for care taker. It then integrates this Prevention is Automatic process here. Use it to inspect and information into Google Maps through Google Maps API which detect hazardous areas in where your people who could result displays in the position on a map. Since the positional information a fall. All Android mobiles have its own sensors like is retrieved every second and the maps updated at the same Accelerometer and gyroscope which are having angle frequency, a real time GPS tracking effect is achieved. Maybe he monitoring process. Using that angle monitoring sensors we are wants to know about Destination place information like predict the fall detection of elderly people based on the angle Distance, Route map, etc from source.The integration of spatial change of mobile and the help of timer. Fall detection conformed maps in mobile was investigated using a spatial analog to by particular time limitation. The following figure sensory 1 preconditioning. The GPS chip outputs the positioning shows the system architecture information which is transferred over a GPRS link to the mobile operator’s GGSN (Gateway GPRS Support Node) and then to a remote server over a TCP connection.
Figure 1: System Architecture
Location Tracking: Real-time locating systems (RTLS) are used to automatically identify and track the location of objects or Figure 2: Activity Diagram people in real time, usually within a building or other contained area. Wireless RTLS tags are attached to objects or worn by The figure 2 shows the activity diagram people, and in most RTLS, fixed reference points receive which includes the following steps wireless signals from GPS to determine their location. The physical layer of RTLS technology is usually some form of radio • The fall is detected via in-built sensors and it frequency (RF) communication, but some systems use optical is detected by the Android application (usually infrared) or acoustic (usually ultrasound) technology • The Timer counts from 30-0 sec. and an instead of or in addition to RF. Gps and fixed reference points alarm is rangif person responds, the can be transmitters, receivers, or both, resulting in numerous person is safe. Else the following step takes possible technology combinations. RTLS are a form of global place. positioning system, and usually refer to GPS, mobile phone • The Timer again counts from 30-60 Sec. tracking, or systems that used only for Effective • Two Actions Takes Place Location tracking. Location information usually shows Elderly Example: The current location is tracked via people Fall down place. G-Maps and it is sent to the care taker the Communication: SMS Communication that maintained between details and the current location. the care taker and the elderly people which contain the fall down
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT 83
www.iaetsd.in
ISBN:378-26-138420-0290
INTERNATIONAL CONFERENCE ON CIVIL AND MECHANICAL ENGINEERING, ICCME-2014 • The Pre-Recorded Video of the person is played which includes person’s details which can be used by the passerby to alert the necessary authorities. • The current location is updated for every two minutes and is sent to caretaker 6. RESULTS AND DISCUSSION.
This paper has been implemented using ASP.Net frame. ASP.NET is compiled common language runtime code running on the server. Unlike its interpreted predecessors, ASP.NET can take advantage of early binding, just-in-time compilation, native optimization, and caching services right out of the box. This amounts to dramatically better performance before you ever write a line of code. The figure 3 shows the android based system for eldered support system which has the value of geographical parameters like longitude, gratitude and login details for people for finding their locations.
Figure 5: Date base of caretaker
Figure 6 supports the database system which is having , all details about the Caretaker .
Figure 6: Database Figure 3: Android Based System For Eldered Support System
Figure 4: Details of the caretaker
The figure 4, 5 show the login details which includes name, address and phone number. These values are stored in the database and if anything happened means the information has been passed to the contact person.
Figure 7: Updated Caretaker
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT 84
www.iaetsd.in
ISBN:378-26-138420-0291
INTERNATIONAL CONFERENCE ON CIVIL AND MECHANICAL ENGINEERING, ICCME-2014 Accessibility, pp. 241-242, Pittsburgh, USA, 2009 [2] Zhongtang Zhao,Yiqiang Chen,Junfa Liu: Fall Detecting and Alarming Based on Mobile Phone, Ubiquitous Intelligence & Computing and 7th International Conference on Autonomic & Trusted Computing (UIC/ATC), 2010. [3] Frank Sposaro, Gary Tyson: iFall: An Android Application for Fall Monitoring and Response, Engineering in Medicine and Biology Society, 2009. EMBC 2009. Annual International Conference of the IEEE. [4] Jiangpeng Dai, Xiaole Bai, Zhimin Yang, Zhaohui Shen and Dong Xuan: PerFallD: A Pervasive Fall Detection System Using Mobile Phone, Pervasive Computing and Communications Workshops (PERCOM Workshops), 8th IEEE International Conference, 2010. [5] Gokhan Remzi Yavuz, Mustafa Eray Kocak, Gokberk Ergun, Hande Alemdar, Hulya Yalcin, Ozlem Durmaz Incel, Lale Akarun, Cem Figure 8:SMS Format Ersoy: A Smartphone Based Fall Detector with Online Location Support, In Proceedings of Figure 7 shows the updated values of PhoneSense, November 2010. caretaker. If you want to change any details about the [6] Global Positioning System: caretaker, you can edit and these values are added to http://el.wikipedia.org/wiki/Global_Positioning_Syst the database. The figure 8 shows the final view called em as SMS Format wich informs the happen of the [7] Koichi Shimizu, Kuniaki Kawamura and patient about the caretaker with the help of google Katsuyuki Yamamoto: Location System for map. Dementia Wandering, Proceedings of the 22nd Annual EMBS International Conference, July 23-28, 7. CONCLUSION AND FUTURE WORK Chicago IL, 2000. [8] Hidekuni Ogawa, Yoshiharu Yonezawa, This fall detection technique can be used for Hiromichi Maki, Haruhiko Sato and W. Morton detecting fall of any ailing people. They offer low Caldwell: A mobile phone-based Safety Support cost solution, and together with wireless connectivity System for wandering elderly persons, Proceedings solutions such as ZigBee provide efficient solution of the 26th Annual International Conference of the for both patients and medical personnels. In this IEEE EMBS, San Francisco, CA, USA, September 1paper,we have presented an intelligent mobile 5, 2004. multimedia application that can be incorporated into [9] Roberto Calvo-Palomino, Pedro de las mobile smartphones in order to be used for the needs Heras-Quiros,Jose Antonio Santos-Cadenas, Raul of any people who may suffer a fall. It is in our future Roman-Lopez and Daniel Izquierdo-Cortazar: plans to evaluate this system in order to test its Outdoors Monitoring of Elderly People Assisted by efficiency in actually helping these people Compass, GPS and Mobile Social Network, 10th sufficiently.It is also in our future plans to extend the international work-conference on artificial neural system’s capabilities by incorporating new services. networks, IWANN 2009 workshops, Salamanca, These services include the following: Spain, June 10-12, 2009. Proceedings, Part II. Berlin: • Embed a belt measuring heart rate as an Springer (ISBN 978-3-642-02480-1/pbk). Lecture external sensor Notes in Computer Science 5518, 808-811, 2009. • Integrate a gyroscope sensor instead of an [10] Frank Sposaro, Justin Danielson, Gary orientation sensor, for more accurate results Tyson: iWander: An Android Application for • Integration of social networks to alert Dementia Patients, 32nd Annual International senders Conference of the IEEE EMBS, Buenos Aires, • Integrate public agency to alert senders Argentina, August 31 -September 4, 2010. • Add a system administrator feature. [11] V. Faucounaua, M. Rigueta, G. REFERENCES Orvoena, A. Lacombeb, V. Riallec, J. Extrac, A.-S. [1] Hamed Ketabdar,Tim Polzehl: Fall and Rigauda: Electronic tracking system and wandering Emergency Detection with Mobile Phones, in Alzheimer’s disease: A case study, Annals of Proceedings of the Eleventh International ACM Physical and Rehabilitation Medicine ,pp.579–587, SIGACCESS Conference on Computers and 2009.
INTERNATIONAL ASSOCIATION OF ENGINEERING & TECHNOLOGY FOR SKILL DEVELOPMENT 85
www.iaetsd.in