1966 IEEE SENSORS JOURNAL, VOL. 12, NO. 6, JUNE 2012If many sensors can be installed for the monitor of allappliances used by the elderly in a newly constructed house,it provides necessary data for elderly monitoring . Thismay not be possible in most practical scenario as the elderlyusually lives in their homes, which were built, during theiryoung age. Hence the elderly houses are basically old andexisting houses.Systems like remote human monitoring using wirelesssensor networks [11, 12] were introduced in recent times.Software systems with different machine learning techniquesare incorporated into the wireless systems like . Also,monitoring and modeling of elderly activities of daily livingwere incorporated [14, 15]. Though technology is effectivelyimplemented but, these systems are limited to a few activities.There is a huge demand for an electronic system withintelligent mechanism, low cost, ﬂexible, easy to install, robustand accurate for monitoring basic Activities of Daily Living(ADLs) of elderly living alone so that help can be providedat the right time.The ultimate goal of personal wellness systems is to providecare for elderly people in the right time no matter where theylive, but technology could assist with transitions from one levelof care to the next and help prevent premature placement inexpensive assistance domains .Activity recognition and Wellness determination are twoimportant functions to be done in a timely manner ratherthan ofﬂine. Hence, real-time processing of data is a mustfor recognizing activity behaviour and predicting abnormalsituations of the elderly.To deal with issues such as monitoring the dailyactivities, performance tracking of normal behaviour andwell-being of the elderly living alone a system which isnoninvasive, ﬂexible, low-cost and safe to use is designedand developed. An initial decline or change in regular dailyactivities can be identiﬁed by the home monitoring sys-tem and trigger messages to the appropriate care providerabout the changes in the functional abilities of the elderlyperson.II. SYSTEM DESCRIPTIONThe system consists of two basic modules as developed in[17, 18]. At the low level module, Wireless sensor networkintegrated with Zigbee modules of mesh structure exists cap-turing the sensor data based on the usage of house-hold appli-ances and stores data in the computer system for further dataprocessing. Collected sensor data are of low level informationcontaining only status of the sensor as active or inactive andidentity of the sensor. To sense the activity behaviour of elderlyin real time, the next level software module will analyze thecollected data by following an intelligent mechanism at variouslevel of data abstraction based on time and sequence behaviourof sensor usage.The low level module consists of a number of sensors inter-connected to detect usage of electrical devices, bed usage andchairs along with a panic button. The fabricated sensing unit asshown in Fig.1 communicates at 2.4GHz (Industrial Scientiﬁcand Medical band) through radio frequency protocols andFig. 1. Fabricated sensing unit with ZigBee module.Fig. 2. Electrical appliance monitoring units connected to various house-holdappliances.MainpowersupplyElectricalapplianceProcessingcircuitCurrenttransformerADC-ZigBeemoduleFig. 3. Block diagram representation of interfacing current sensor withZigBee module.provides sensor information that can be used to monitor thedaily activities of an elderly person.A smart sensor coordinator collects data from the sensingunits and forward to the computer system for data processing.The major task of our work is to recognize the essentialactivities of daily living behaviour of the elderly throughsensor fusion by using minimal sensors at elderly home.For this, WSN consisting of different types of sensors likeelectrical, force, contact sensors with zigbee module sensingunits are installed at elderly home.The uses of electrical appliances are monitored by theelectrical appliance monitoring sensing units as shown inFig.2. These operate based on the detection of current ﬂowconnected to appliances such as microwave, water kettle,toaster, room Heater, television and dishwasher as theyare regularly used by the elderly at home. Fig.3 illustratesinter-connection structure of developed current sensor unit
SURYADEVARA AND MUKHOPADHYAY: WSN BASED HOME MONITORING SYSTEM FOR WELLNESS DETERMINATION OF ELDERLY 1967Fig. 4. Sensing units connected to bed, toilet and chair house-hold appliancesof elderly home.Bed/couch/chair/toiletAmplifier/signalconditioningcircuitADCZigBeemoduleFig. 5. Block diagram representation of interfacing force sensor to ZigBeemodule.Fig. 6. Developed contact sensing units connected to grooming cabinet andfridge.with zigbee module for transmitting digital ON/OFF signal.The output of electrical appliance monitoring sensor unit iseither ON or OFF based on the use of connected electricalappliance. Normally, one electric sensing unit is required tosense each electrical appliance. In order to have minimumsensing units to monitor more electrical appliances and reducecost, the electrical appliance monitoring units are fabricatedto support two electrical appliances on a single power inlet,having the intelligence to detect which particular device ison. We have tested by connecting water kettle and toasterappliances through different analog channels of ZigBee mod-ule to be monitored by single sensing unit thereby reducingthe number of sensing units and cost for monitoring elderlyactivity behaviour.The system uses force sensors attached to bed, couch, toiletand dining chair as shown in Fig. 4 to monitor their dailyusage. Based on the analog values of the force sensor receivedby the coordinator, the system can recognize the usage of thesedevices as active or inactive. Whenever the elderly person usedthese devices, developed system has monitored and recordedthe event effectively for further data processing.Fig. 5 illustrates inter-connection structure of developedforce sensor unit with zigbee module for transmitting analogvalue.Developed contact sensing units as shown in Fig.6 are ﬁxedto the fridge and grooming cabinet of the elderly home todetect the open and close of the door operations. Events relatedTemperature sensorHumidity sensorLight intensity sensorAssociated indicatorOn/sleep LED indicatorMonitoring LEDindicatorsZigBee chip (series 2)3.3 V voltage regulatorFig. 7. Developed ambient sensing unit for recording temperature, humidity,and light intensity.to these actions were effectively recorded to recognize thecorresponding activities.Designed and developed temperature, humidity and lightintensity sensing unit with only one zigbee module as shownin Fig.7 is used to record the ambient readings of room foranalyzing the data.Rationale for observing usage of house-hold appliances isbased on the fact that these are regularly used by the elderlyin various behaviours like preparation of food, during rest,toileting, sleeping and grooming activities. They are usefulto determine the wellness of the person in performing theseactivities. Also, Emergency help and deactivate operations aremade-up with zigbee module to facilitate the correspondingoperations during the real-time activity monitoring of theelderly.A. Data AcquisitionCaptured data are dynamically changing and demandingfast, real-time response time for forecasting the irregularbehaviour of the elderly. To analyze the data properly, anefﬁcient process of storage mechanism of sensor data onto thecomputer system is executed. Issues like storage requirementsfor continuous ﬂow of data streams and processing of data togenerate patterns/abnormal events in real time were effectivelydealt in the current system.Since there is a continuous in ﬂow of sensor streams wehave stored the sensor data in the processing system only whenthere is a change in the sensor events - Event based storage(i.e) when status (active or inactive) of the sensor is changedthen the sensor fusion data is recorded. This is most efﬁcienttechnique, as it reduces the size of storage to a large extentand more ﬂexible for processing of data in real time.Event monitoring collection of data has enormous beneﬁtover continuous ﬂow collection of data in terms of the amountof data storage and processing of data in real-time applicationslike home monitoring.B. Activity AnnotationActivity labeling for the activities of daily living of theelderly during real-time monitoring of appliances use isdirectly done with the help of ‘sensor events’. Activities likesleeping, preparing breakfast/lunch/dinner, dining, toiletingand self grooming were recognized based on the Sensor-IDstatus and Time of the Day. Other activities like watching
1968 IEEE SENSORS JOURNAL, VOL. 12, NO. 6, JUNE 2012TABLE IACTIVITY LABELLING PROCESS DURING RUN-TIME OF THE SYSTEMSensor-ID/StatusConnected toApplianceType of Sensor Time of Usage Annotated Activity Run Time Data1818(Active) Bed Pressure Sensor 09:00 pm to 06:00 am Sleeping(SL)2011-6-9 21:02:10 18 ON SL begin2011-6-10 05:50:10 18 OFF SL end11/12/13 (active)Microwave /Oven/ WaterkettleElectrical Sensor 06:00 am to 10:00 am Breakfast(BF) 2011-6-5 06:16:42 11 ON BF begin2011-6-5 06:21:35 11 OFF BF end10(Active) Toilet Pressure Sensor Anytime Toileting(TO)2011-6-7 02:15:30 10 ON TO begin2011-6-7 02:16:07 10 OFF TO end19(Active) Couch Pressure Sensor Anytime Toileting(TO)2011-6-8 05:20:45 19 ON RE begin2011-6-8 05:35:30 19 OFF RE end26(Active)GroomingCabinet Contact Anytime Self Grooming(SG)2011-6-8 09:20:10 26 ON SG begin2011-6-8 09:22:40 26 OGG SG endFig. 8. Sensor data acquisition and activity recognition in real-time.television, preparing tea are done with the help of respectivesequence patterns of sensor ids which are active. Fig.8 elu-cidates the ﬂow of sensor data and preprocessing for activityannotation.Table. I depict the activity annotation involving recognizingelderly activity behaviour over time and storage of data insystem. Sensor fusion data was not segmented into separatesequences for each activity rather it was processed as acontinuous stream.Activity annotation process will help the monitoring systemto recognize the various behaviours of the elderly at differentinstant of time. This process is done based on the collectionof sensor identity from the sensor fusion of various sensingunits connected to different house-hold appliances.Appropriate time slot size is to consider for labelling theactivity based on the sensor id and time of the day. It providessufﬁcient information for doing data analysis. Even if thesensors are active for multiple times during a particular timeslot, activity labeling is done according to the deﬁnitionspeciﬁed in the system. We experimented with models thatused time slot sizes of one hour, three hours, four hours and sixhours duration. Activity recognition in terms of three hours andfour hour time slot sizes are giving more modelling accuracyfor labelling the activity processing.Table. I show that sensors id 11, 12, 13 are used for kitchenappliances. If multiple times of sensor id 11, 12 or 13 areactive during four hour time slot the event is annotated withdeﬁned activity as breakfast, lunch and dinner respectively.Obviously an event like preparing breakfast, lunch or dinnerdoesn’t happen at the same time every day, but it is usuallyhappened within a speciﬁed time interval. Hence preparationof food between 6:00 am to 10 am been considered as prepa-ration of breakfast. So sensor event generated in the kitchenbetween 6:00 am to 10:00 am used labeling as breakfast.We are interested in accuracy of the model to be build basedon the activity annotation rather than accuracy of the activityannotation. Activity annotation is validated by cross checkingwith the ground truth (manually recording the events by theelderly).C. Wellness Determination of ElderlyHealth care providers assisting the elderly can have amore comprehensive, longitudinal evaluation of the monitoredelderly activities than the snap shot assessment obtained duringan annual physical examination.If the elderly person needs assistance with some of theirActivities of Daily Living (ADLs) - An index or scale whichmeasures a patient’s degree of independence in bathing, dress-ing, using the toilet, eating and transferring (moving from abed to a chair, for example)  as these are usedto determinethe need for long-term care or Instrumental Activities of DailyLiving (IADLs), professional caregivers accessing the elderlyactivity reports will have an objective assessment of theiractual needs and appropriate care services based on the dailyfunctional assessments of the person.There are numerous wellness concepts suggested by expertsfrom various domains, each of which is deﬁned from their spe-cialist perspective and contain several dimensions of wellness[20, 21, 22].Several authors are of the same opinion that wellness isnot just the state of mind or free from illness and disease;it is not a single state [20, 21]. Wellness does have multipledimensions or levels. However, an integrated deﬁnition doesnot exist. Hence, there are various instruments and methodsfor wellness assessment.Wellness is a very wide and multifaceted perception. It isdifﬁcult to deﬁne the term wellness completely because theterm wellness is developed overtime and changed by differentinﬂuential factors such as culture, experience, belief, religion,context etc [20, 23, 24].Wellness meaning in our context is how “healthy” theelderly living alone is able to perform his essential daily
SURYADEVARA AND MUKHOPADHYAY: WSN BASED HOME MONITORING SYSTEM FOR WELLNESS DETERMINATION OF ELDERLY 1969S SE TN RS EO AR MDataacquisition&ActivityannotationWellnessfunctionβ1, β2Fig. 9. Functional description of wellness computation functions.activities in terms of the usage of the house-hold appliances.We introduced two wellness functions to determine the well-ness of the elderly person under the monitoring environment.The ﬁrst function (β1) is determined from the non-usage orinactive duration of the appliances. The second function (β2)is determined from the over-usage of a few speciﬁc appliances.The two functions β1 and β2 determine the wellness of elderlyare based on the usage of house-hold appliances. Fig. 9shows the functional description in determining the Wellnessfunctions.The wellness functions were calculated during the run-time of the system as background process taking the activitydurations from the respective ﬁles of the computer system.These indices were simultaneously recorded in the database forfuture data processing and prediction of the unusual behaviourof the elderly.β1 and β2 are helpful in deriving the reliability of per-forming ADLs as regular or irregular over a long period ofexecution of the system.1) Wellness Function 1, β1: The wellness function 1, des-ignated as ‘β1’ is deﬁned by the following equationβ1 = 1 −tT(1)where β1 = Wellness function of the elderly based on themeasurement of inactive duration of appliancest = Time of Inactive duration of all appliances (i.e.) durationtime no appliances are used.T = Maximum inactive duration during which no appli-ances are used, leading to an unusual situationIf β1 is equal to 1.0 indicates the elderly is in healthy well-being situation. If β1 is less than 1.0 the situation indicatessome unusual situation. If β1 goes below 0.5 then care isrequired.2) Wellness Function 2, β2: The wellness function 2, des-ignated as ‘β2’ is deﬁned by the following equationβ2 = 1 + 1 −TaTn(2)Where β2 = Wellness function of the elderly based onexcess usage measurement of appliance.Ta = Actual usage duration of any appliance.Tn = Maximum usage duration use of appliances undernormal situation.Under normal condition, Ta < Tn; No AbnormalityOnly if Ta > Tn then β2 is calculated using the eq. (2).The value of β2 close to 1 to 0.8 or so may be consideredas normal situation. If β2 goes less than 0.8, then it indicatesElectircal monitoring sensorForce sensorPanic buttonCOM 1ExitClose portWater flow monitoringsensorToasterDchairCouchToiletBedTVW.kettleM.OvenFig. 10. Front end of the data acquisition unit.the excess usage of the appliance corresponding to an unusualsituation.In ideal case, β1 and β2 equals to one indicate the elderlyactivities are recurring with equal durations every time. How-ever, human behavior is not consistent; hence the optimumalarm level for β1 and β2 are determined so that false warningmessages are minimized.Based on the experiments conducted at different elderlyhouses (as further discussed in section III) there are instancesof the maximum inactive and active duration of the appliances.Deriving β1 and β2 accordingly from the experiments at theelderly houses, warning messages are generated when β1 goesbelow 0.5 and β2 goes less than 0.8.Maximum inactive duration and Maximum usage durationuse of appliances can be obtained during the trial run periodof the system. The trial run period may be varied dependingon the elderly activities of daily living conditions. Once thesystem learns the daily activity behaviour (i.e.) once the dailyactivities are cyclic then the trial run execution phase will beshifted to test phase and wellness indices are determined. (e.g)Section III, table II depicts the obtained maximum duration ofthe different appliances at the end of one week trial run.III. EXPERIMENTAL RESULTS AND DISCUSSIONThe experimental setup is as follows: WSN consisting ofsix electrical sensors, four force sensors, two contact switchsensors, one combined temperature/humidity monitoring sen-sor and one alarm/reset button are installed in the home tomonitor elderly behaviour and assist the elderly living aloneif there is any irregular behaviour at a particular time. Alongwith the wireless sensor network a laptop installed with thedeveloped intelligent software connected with zigbee moduleacting as coordinator is associated with WSN to collect andmonitor the elderly behaviour. Program for data acquisition,activity recognition and wellness determination are writtenusing Microsoft Visual Studio.The fabricated sensing modules along with Zigbee com-ponents are conﬁgured as mesh topology to have effectivecommunication with zigbee coordinator for recording sensorvalues in the system for further machine learning process. Thissection concludes with a presentation of the acquired results.Fig. 10 depicts the front end of the developed software systemindicating which sensor is active or inactive.
1970 IEEE SENSORS JOURNAL, VOL. 12, NO. 6, JUNE 2012TABLE IISUBJECT 1 MAXIMUM ACTIVE DURATION OF THE APPLIANCESDURING ONE WEEK TRIAL RUNDate/Appliance Maximum Active Duration(hh:mm:ss)Bed Toilet Chair TV Couch05/06/2011(Sun) 9:35:40 0:12:20 0:17:45 1:10:50 0:57:4506/06/2011(Mon) 7:50:10 0:10:35 0:15:35 0:45:20 1:45:5007/06/2011(Tue) 9:20:10 0:14:45 0:25:28 2:15:10 2:30:1008/06/2011(Wed) 8:45:50 0:13:55 0:10:20 1:45:50 0:55:2009/06/2011(Thu) 8:35:25 0:12:20 0:19:45 1:55:30 2:20:1010/06/2011(Fri) 8:50:25 0:15:45 0:20:35 1:30:20 1:30:4511/06/2011(Sat) 9:25:15 0:10:55 0:28:30 1:40:10 2:10:35Maximum 9:35:40 0:15:45 0:28:30 2:15:10 2:20:10Subject: 1 Subject: 2Subject: 3 Subject: 4MOTRWKADHTTVDCBDCOTONAFig. 11. Depict the percentage use of different appliances1 at various subjecthouses.Real-time activity status of the elderly can be easily seenon the front-end of the system. This interface enables the careprovider to know immediately the present activity status of theelderly (i.e) whenver a house–hold appliance connected by asensing unit is in use then the interface will highlight the iconindicating the location of the elderly. System can also simu-lataneously store the sensor activity information and analyzethe wellness indices. Another advantage of the interface is thatremote monitoring of the elderly can be easily done.Real-time sensor activity status at the corresponding hour ofthe day is recorded simultaneously in the respective ﬁles of thecomputer for data processing. Continuous sensor activity statusis recorded in respective ﬁles of the computer for effectivedata processing. Fig.13 shows the various activity sequencesperformed by the elderly during one week trial run.The pie-chart as shown in Fig.11 indicates the uses ofdifferent appliances at four different subject homes. It can beinferred from the ﬁgure that the bed is very important for thelife of the elderly person.During one week trial run maximum active duration of theappliances is given in Table II.Fig.13 gives the pictorial representation of activityoccurrence-based on data obtained from a running system.During the testing phase β2 is calculated using the eq. (2).Table III shows the corresponding β2 values for four differentappliances. The value of β2 close to 1 to 0.8 or so may be1MO:MicrowaveOven, TR:Toaster, WK:WaterKettle, AD:Audiodevice, HT:Room Heater, TV:Telivison, DC:Dinning Chair, BD:Bed, CO:Couch,TO:Toilet.NA:No Appliance.TABLE IIISUBJECT 1 MAXIMUM ACTIVE DURATION OF THE APPLIANCESDURING ONE WEEK TESTING PHASEDate/Appliance Maximum Active Duration(hh:mm:ss)12/06/2011(Sun) 9:25:20,1.017950:11:10,1.2910050:18:55,1.3362571:27:45,1.373613/06/2011(Mon) 7:20:45,1.2343660:12:15,1.2222220:16:25,1.4239773:15:50,0.6028514/06/2011(Tue) 8:50:37,1.0782570:10:45,1.317460:20:18,1.2877190:20:18,1.28771915/06/2011(Wed) 9:15:15,1.0354660:12:55,1.1798940:34:30,0.7894741:15:20,1.4625316/06/2011(Thu) 9:35:35,1.0001450:15:20,1.0264550:15:20,1.0264552:50:40,0.7820417/06/2011(Fri) 8:30:55,1.1124780:13:45,1.1269840:13:45,1.1269841:45:50,1.2445618/06/2011(Sat) 10:25:150.913860:12:15,1.2222220:18:40,1.3846751:55:35,1.17538S4S3S2SubjectlocationsS10.00 0.10 0.20 0.30 0.40Wellness function “β1”0.50β10.60 0.70 0.80 0.90 1.00Fig. 12. β1 indices at four different elderly home for one week of trial andone week testing phase. β1 close to 1 indicates more healthy of the personin performing the regular daily activities.considered as normal situation. If the value β2 is less than0.8 indicate, excess usage of the appliance corresponds to anabnormal condition.“β1 and β2 ” functions can inform how well the elderly isperforming daily activity behaviour is executed. Fig 12 andFig 14 show the wellness indices at different elderly homes.In Fig.12 it is seen that the β1 for the subject 2 on aparticular day has gone below 0.5.In practice it has beenobserved that the elderly went outside the house for quite along duration without deactivating the monitoring system.In Fig.14 it is seen β2 for subject 2 has gone to very lowvalue for the use of chair. It has been observed that on thatparticular day, the elderly had a visitor and took lunch sittingon the chair for a long duration. For the subject 3, it has beenobserved that the elderly slept quite a long time as he was notfeeling well.These observations tell clearly about the wellness determi-nation of the system. The alarm can be set depending on valuesof β1 and β2. These should be diverse for different elderlypeople. While the alarm is set, the system can generate a soundto inform the elderly that a message is going to be sent to thecare provider.
SURYADEVARA AND MUKHOPADHYAY: WSN BASED HOME MONITORING SYSTEM FOR WELLNESS DETERMINATION OF ELDERLY 1971Activity occurrences2011-06-042011-06-052011-06-062011-06-072011-06-082011-06-092011-06-102011-06-1112 am 3 am 6 am 9 am 12 pm 3 pm 6 pm 9 pm 12 amBFRELNDNSKTODISLCUSG21Fig. 13. Pictorial representation of activity+ occurrence-based on data obtained from a running system.1 2 3 4Dayβ2at subject 1β2at subject 25 6 22.214.171.124.126.96.36.199.188.8.131.52.184.108.40.206.220.127.116.11.18.104.22.168.22.214.171.124.126.96.36.199.201 2 3 4Dayβ2at subject 35 6 71 2 3 4Dayβ2at subject 45 6 71 2 3 4DayBedToiletChairCouch5 6 7β2β2β2β2Fig. 14. β2 values at four different elderly homes indicating their activitywith the corresponding house-hold appliances.To deactivate the alarm, considering as regular in future,corresponding event can be reset to regular if the elderly pressthe reset button.It can be inferred that as the system run for a longerperiod of time continuously then the maximum and minimumduration usage time of the house-hold appliances will bemore accurate and the wellness state of the elderly will beprecisely determined.The calculations of β1 and β2 are done simultaneously whenthe sensor activity status is plotted on the respective ﬁles ofthe system. Wellness functions were helpful in deducing noappliance and excess used by the elderly at their houses. Theseare also helpful in predicting the early abnormal situation ofthe elderly in performing their ADLs.IV. CONCLUSIONWellness is a wide and multifaceted phrase. In this researchWellness is about well-being of elderly in performing theirdaily activities effectively at their home. This will facilitatethe care providers in assessing the performance of the elderlyactivities doing independently. The developed home moni-toring system using WSN is low cost, robust, ﬂexible andefﬁciently monitor and assess the elderly activities at home inreal-time.Real-time activity behaviour recognition of elderly anddetermination of wellness function of the elderly using theactivity of appliances was encouraging as the system wasstable in executing the tasks for few weeks. If the system isexecuted for required number of months the optimal maximumutilization of the appliances used by the elderly will bederived. Also, the efﬁciency of wellness functions to predictthe abnormal behaviour of the elderly in using the dailyhousehold appliances will also increase.In the near future, the system will be augmented withthe physiological parameter monitoring sub-system. This willsupplement to get information about health parameters likebody temperature, heart rate etc., so that elderly health per-ception and daily activity behaviour recognition together canbe assessed to determine the wellness of the elderly.REFERENCES A. H. Nasution and S. Emmanuel, “Intelligent video surveillance formonitoring elderly in home environments,” in Proc. IEEE 9th WorkshopMultimedia Signal Process., Oct. 2007, pp. 203–206. Z. Zhongna, D. Wenqing, J. Eggert, J. T. Giger, J. Keller, M. Rantz,and H. Zhihai, “A real-time system for in-home activity monitoring ofelders,” in Proc. Annu. Int. Conf. IEEE Eng. Med. Biol. Soc., Sep. 2009,pp. 6115–6118.
1972 IEEE SENSORS JOURNAL, VOL. 12, NO. 6, JUNE 2012 S. J. Hyuk, L. Boreom, and S. P. Kwang, “Detection of abnormal livingpatterns for elderly living alone using support vector data description,”IEEE Trans. Inf. Technol. Biomed., vol. 15, no. 3, pp. 438–448, May2011. A. Wood, J. Stankovic, G. Virone, L. Selavo, H. Zhimin, C. Qiuhua,D. Thao, W. Yafeng, F. Lei, and R. Stoleru, “Context-aware wirelesssensor networks for assisted living and residential monitoring,” IEEENetw., vol. 22, no. 4, pp. 26–33, Jul.–Aug. 2008. J. K. Wu, L. Dong, and W. Xiao, “Real-time physical activity classiﬁ-cation and tracking using wearble sensors,” in Proc. 6th Int. Conf. Inf.,Commun. Signal Process., Dec. 2007, pp. 1–6. Z. Bing, “Health care applications based on ZigBee standard,” in Proc.Int. Conf. Comput. Design Appl., vol. 1. Jun. 2010, pp. V1-605–V1-608. K. P. Hung, G. Tao, X. Wenwei, P. P. Palmes, Z. Jian, W. L. Ng, W.T. Chee, and H. C. Nguyen, “Context-aware middleware for pervasiveelderly homecare,” IEEE J. Sel. Areas Commun., vol. 27, no. 4, pp.510–524, May 2009. H. Yu-Jin, K. Ig-Jae, C. A. Sang, and K. Hyoung-Gon, “Activityrecognition using wearable sensors for elder care,” in Proc. 2ndInt. Conf. Future Generat. Commun. Netw., vol. 2. Dec. 2008, pp.302–305. A. A. Moshaddique and K. Kyung-Sup, “Social issues in wireless sensornetworks with healthcare perspective,” Int. Arab J. Inf. Technol., vol. 8,no. 1, pp. 34–39, Jan. 2011. K. Hara, T. Omori, and R. Ueno, “Detection of unusual human behaviorin intelligent house,” in Proc. 12th IEEE Workshop Neural Netw. SignalProcess., Nov. 2002, pp. 697–706. S.-W. Lee, Y.-J. Kim, G.-S. Lee, B.-O. Cho, and N.-H. Lee, “A remotebehavioral monitoring system for elders living alone,” in Proc. Int. Conf.Control, Autom. Syst., Oct. 2007, pp. 2725–2730. D. Lymberopoulos, A. Bamis, T. Eixeira, and A. Savvides, “Behav-iorScope: Real-time remote human monitoring using sensor net-works,” in Proc. Int. Conf. Inf. Process. Sensor Netw., Apr. 2008, pp.533–534. E. Nazerfard, P. Rashidi, and D. J. Cook, “Discovering temporal featuresand relations of activity patterns,” in Proc. IEEE Int. Conf. Data Min.Workshops, Dec. 2010, pp. 1069–1075. P. George, X. George, and P. George, “Monitoring and modeling simpleeveryday activities of the elderly at home,” in Proc. 7th IEEE ConsumerCommun. Netw. Conf., vol. 7. Jan. 2010, pp. 1–5. H. Medjahed, D. Istrate, J. Boudy, and B. Dorizzi “Human activities ofdaily living recognition using fuzzy logic for elderly home monitoring,”in Proc. IEEE Int. Conf. Fuzzy Syst., Aug. 2009, pp. 2001–2006. E. Dishman, “Inventing wellness systems for aging in place,” IEEEComput., vol. 37, no. 5, pp. 34–41, May 2004. A. Gaddam, S. C. Mukhopadhyay, and G. S. Gupta, “Elder care based oncognitive sensor network,” IEEE Sensors J., vol. 11, no. 3, pp. 574–581,Mar. 2011. N. K. Suryadevara and S. C. Mukhopadhyay, “Wireless sensors networkbased safe home to care elderly people: A realistic approach,” in Proc.IEEE Recent Adv. Intell. Comput. Syst., Sep. 2011, pp. 1–5. Covering Health Issues, 6th ed., Alliance Health Reform, WashingtonD.C., 2005. C. Soomlek and L. Benedicenti, “Operational wellness model: A well-ness model designed for an agent-based wellness visualization system,”in Proc. 2nd Int. Conf. eHealth, Telemed. Social Med., 2010, pp.45–50. A. Kailas, “A generic conceptual model linking wellness, healthlifestyles, and user assistance,” in Proc. 13th IEEE Int. Conf. eHealthNetw. Appl. Serv., Jun. 2011, pp. 266–269. A. Kailas, C.-C. Chong, and F. Watanabe, “A simple iterative algorithmfor wellness applications,” in Proc. IEEE Wireless Commun. Netw. Conf.,Apr. 2010, pp. 1–6. M. Alwan, “Passive in-home health and wellness monitoring: Overview,value and examples,” in Proc. IEEE Annu. Int. Conf. Eng. Med. Biol.Soc., Sep. 2009, pp. 4307–4310. J. Healey and B. Logan, “Wearable wellness monitoring using ECG andaccelerometer data,” in Proc. 9th IEEE Int. Symp. Wearable Comput.,Oct. 2005, pp. 220–221.Nagender Kumar Suryadevara (S’11) received theBachelors degree from Sri Krishnadevaraya Uni-versity, Anantapur, India, and the Masters degreefrom Madurai Kamaraj University, Madurai, India,in 1996 and 1998, respectively. He is currently pur-suing the Ph.D. degree with the School of Engineer-ing and Advanced Technology, Massey University,Palmerston North, New Zealand.His career demonstrates consistent success as anAdministrator and Educator with the graduate andpost-graduate education levels in India, Ethiopia, andOman. He is currently involved in the development of software systems forthe home monitoring project using wireless sensors networks. His currentresearch interests include domains of wireless sensor networks and machinelearning.Subhas Chandra Mukhopadhyay (M’97–SM’02–F’11) received the Degree from the Departmentof Electrical Engineering, Jadavpur University,Kolkata, India, the Masters degree in electrical engi-neering from the Indian Institute of Science, Ban-galore, India, the Ph.D. degree in engineering fromJadavpur University, and the Doctor of Engineeringdegree from Kanazawa University, Kanazawa-Shi,Japan.He is currently a Professor of sensing technologywith the School of Engineering and Advanced Tech-nology, Massey University, Palmerston North, New Zealand. He has over21 years of teaching and research experience. He has authored/co-authoredover 250 papers in different international journals, conferences, and books.He has edited ten conference proceedings, ten special issues of internationaljournals as a Lead Guest Editor and eleven books, nine of which were withSpringer-Verlag. His current research interests include sensors and sensingtechnology, electromagnetics, controls, electrical machines, and numericalﬁeld calculation.Dr. Mukhopadhyay has been awarded numerous awards in his career. Heis a Fellow of the Institution of Engineering and Technology, U.K. Heis an Associate Editor of the IEEE SENSORS JOURNAL and the IEEETRANSACTIONS ON INSTRUMENTATION AND MEASUREMENTS. He is withthe Editorial Board of e-Journal on Non-Destructive Testing, Sensors andTransducers, the Transactions on Systems, Signals, and Devices, and theJournal on the Patents on Electrical Engineering. He is the Co-Editor-in-Chief of the International Journal on Smart Sensing and Intelligent Systems.He is with the Technical Program Committee of the IEEE Sensors Conference,the IEEE Instrumentation and Measurement Technology Conference, andnumerous other conferences. He was the Technical Program Chair of ICARA2004, ICARA 2006, and ICARA 2009. He was the General Chair/Co-Chairof ICST 2005, ICST 2007, IEEE ROSE 2007, IEEE EPSA 2008, ICST 2008,IEEE Sensors 2008, ICST 2010, IEEE Sensors 2010, and ICST 2011. He hasorganized the IEEE Sensors Conference at Christchurch, New Zealand, as theGeneral Chair in October 2009. He is the Chair of the IEEE Instrumentationand Measurement Society New Zealand Chapter. He is a DistinguishedLecturer of the IEEE Sensors Council.