New Technique for Posture Identification in Smart Prayer

electronics

Article

NewArticle Technique for Posture Identiﬁcation in SmartNew Technique Prayer Mat for Posture Identification in Smart Prayer Mat Kasman Kasman * and Vasily G. Moshnyaga

GraduateKasman SchoolKasman* of Engineering, and Vasily FukuokaG. Moshnyaga University, Fukuoka 814-0180, Japan; [email protected] * Correspondence:Graduate School of [email protected]; Engineering, Fukuoka University, Tel.: +81-92-801-0833 Fukuoka 814‐0180, Japan; vasily@fukuoka‐u.ac.jp Received:* Correspondence: 26 July 2017; [email protected]; Accepted: 21 August 2017; Tel.: +81 Published:‐92‐801‐0833 23 August 2017 Received: 26 July 2017; Accepted: 21 August 2017; Published: 23 August 2017 Abstract: Smart praying mats are essential to help old and forgetful Muslims perform their religious needs.Abstract: Due Smart to the praying binary mats representation are essential ofto help pressure old and sensors forgetful embedded Muslims intoperform the their mat forreligious posture identification,needs. Due to existing the binary smart representation praying systems of pressure either sensors use largeembedded sensing into arrays, the mat thus for posture becoming expensiveidentification, and bulky,existing or smart utilize praying only a limitedsystems number either use of sensors,large sensing minimizing arrays, the thus cost becoming of posture recognitionexpensive and accuracy. bulky, Thisor utilize article only presents a limited a number new technique of sensors, for minimizing detecting humanthe cost posturesof posture and countingrecognition posture accuracy. cycles This by a article smart mat.presents Unlike a new related technique solutions, for thedetecting proposed human technique postures identifies and posturescounting by posture voltage cycles levels by observed a smart mat. from Unlike five sensorsrelated solutions, only. The the technique proposed has technique been implemented identifies inpostures a prototype by voltage smart levels mat and observed experimentally from five sensors evaluated only. by The 30 technique Islam worshipers. has been implemented The results show in thata prototype it provides smart unobtrusive mat and experimentally and robust (100%) evaluated recognition by 30 Islam of all worshipers. six postures The of the results Muslim show praying that cycleit provides and reliable unobtrusive cycle counting. and robust The (100%) implementation recognition is of inexpensive, all six postures easy of to the use Muslim and quite praying helpful cycle and reliable cycle counting. The implementation is inexpensive, easy to use and quite helpful for users. for users. Keywords: smart mat; pressure sensors; sensor systems and applications; assistive living Keywords: smart mat; pressure sensors; sensor systems and applications; assistive living

1. Introduction 1. Introduction PrayingPraying is is a a central central pillar pillar of of thethe Muslim faith; faith; a a mandatory mandatory religious religious ritual ritual performed performed five five times times a daya day at at prescribed prescribed times. times. TheThe ritualritual is quite challenging for for elders elders whose whose attentive attentive and and cognitive cognitive capabilitiescapabilities are are deteriorating deteriorating with age. age. When When praying, praying, a worshiper a worshiper has hasto perform to perform a sequence a sequence of six of sixpostures postures (Figure (Figure 1)1 )called called Rakah Rakah (in (in singular) singular) and and Rakat Rakat (in (in plural). plural). Because Because the the sequence sequence must must be be repeatedrepeated a a number number of of times times while while recitingreciting passages from from the the Quran, Quran, elders elders frequently frequently have have difficulty difficulty rememberingremembering which which cycle is is being being performed. performed. Incomplete Incomplete sequence, sequence, however, however, is not acceptable. is not acceptable. Once Onceforgotten, forgotten, a worshiper a worshiper must must go back go back and and fulfill fulfill an extra an extra sequence sequence to ensure to ensure that that he hehas has done done the the properproper number number of of Rakat. Rakat.

(a) (b) (c) (d) (e) (f)

FigureFigure 1. 1.The The sequence sequence of of postures postures to complete a a single single Rakah Rakah in in a aprayer: prayer: (a, (ca), cstanding) standing (b) ( bowing;b) bowing; (d,(fd),f prostration;) prostration; (e ()e) sitting. sitting.

Electronics 2017, 6, 61; doi:10.3390/electronics6030061 www.mdpi.com/journal/electronics Electronics 2017, 6, 61; doi:10.3390/electronics6030061 www.mdpi.com/journal/electronics Electronics 2017, 6, 61 2 of 13

Furthermore, the number of cycles, which must be repeated by a worshiper in a pray, varies according to the time of day as well as the day. For example, two Rakat must be performed at dawn prayer, four at each prayer at noon, afternoon and evening, and three at sunset prayer. Old and forgetful people have problems not only remembering how many ritual cycles have to be performed in a prayer but also losing track of the cycles that they have already completed [1]. Although Muslims with severe mental illness or intellectual disability are allowed to be exempted from praying, those with mild and moderate cognitive impairment are not. The options they currently have are quite limited: either to perform in a congregation following the leader or ask someone to inform them which Rakah is currently performed. Elders with cognitive impairment usually practice their rituals at home. They live independently and frequently do not have someone close to ask. At the same time, those who can usually hesitate being a burden to others and showing their cognitive problems, and may eventually lead to bad mood, depression, more extensive cognitive decay, and a stronger association with dementia [2]. Therefore, information and communication technologies capable of assisting forgetful Muslims in praying are important. In this article, we present a new technique for automatic sensing and recognition of Rakat postures by using a smart mat.

2. Related Research Over the years, various technologies have been proposed to help Muslims with prayers and Rakat counting. Google Play and Apple Store nowadays contain a number of software applications which can automatically count the number of Rakat on mobile devices (smartphones or tablet PC) with embedded accelerometers. In order to use the applications, a worshiper must possess a proper device in addition to a prayer mat (which is not always the case for old and forgetful people), and also be within the area of Global System for Mobile Communications (GSM) or Wiﬁ coverage in order to access the application server. Therefore, research efforts have been concentrated on incorporating Rakat counting electronics into the prayer mat itself. Khatri [3] proposed the use of a solar-powered electrical switch pad and liquid crystal display (LCD) operable by a forehead of a worshipper when he or she prostrates on the mat. Faouaz [4] also used LCD with a switch, built in the prayer mat, with the difference that the switch is turned on and off by the user. Abdelmohsen [5] advocated placing a so-called “pressurable plate” under an ordinary mat to detect a prostration posture anytime the user’s forehead touches the mat, and incrementing the Rakat counter on display by every even prostration posture. Arrar [6] developed a portable cycle counter based on IR sensors embedded into the prayer rug. Kantarceken [7] presented a prayer assistance device with built-in camera, infra-red sensors, microphones, Bluetooth and acoustic transducers for detecting physical gestures and spoken words of a prayer. Ismail et al. [8] used pressure sensors embedded in the mat under the forehead area to detect the prostration posture. When a second prostration is recognized, the counter is incremented, and its value is displayed on an MP3 player and replayed as an audible cue. Despite differences in implementation, all of these smart prayer mats have several features in common. Namely, they differentiate human postures by patterns of binary signals (0 and 1) generated from switches or pressure sensors embedded into the mat. The sensors operate locally while the postures span the entire area of the prayer mat. Therefore, the devices either employ a large number of sensors distributed over the mat, as shown in Figure2a, in order to improve the detection accuracy on expense of cost (e.g., [6,8]), or use a few sensors placed under the forehead (see Figure2b) to detect the prostration posture only (e.g., [4,5,7]). These cost-oriented solutions do not take into account the other postures of the Rakah sequence and thus might increment the counter when the user skips a posture or makes two prostrations consequently; which is unacceptable. Besides, to our knowledge, none of the existing prayer mats proposed so far can differentiate the standing posture from the bowing posture, thus impeding the correct posture recognition. Electronics 2017, 6, 61 3 of 13 Electronics 2017, 6, 61 3 of 13

(a) (b)

Figure 2. Distribution of pressure sensor in existing smart mats: (a) distributed over the mat area; (b) Figure 2. Distribution of pressure sensor in existing smart mats: (a) distributed over the mat area; (localizedb) localized in the in theforehead forehead area. area.

It should be noted that research on smart mats/carpets capable of recognizing human postures and Itanalyzing should be the noted human that research gait has on intensified smart mats/carpets recently, capable especially of recognizing for health human‐care and postures medical and analyzingapplications. the Middleton, human gait et has al. intensified [9] developed recently, a gate especially‐recognition for health-care “floor sensor” and medicalthat had applications. 1536 small Middleton et al. [9] developed a gate-recognition “floor sensor” that had 1536 small sensing elements sensing elements arranged in a 3 × 0.5 m2 rectangular strip with an individual sensor area of 3 cm2. × 2 2 arrangedAud et al. in[10] a presented 3 0.5 m a rectangularfall‐detecting strip smart with carpet an individual built from an sensor array area of signal of 3 cm‐scavenging. Aud et sensors al. [10] presentedthat use energy a fall-detecting available throughout smart carpet the built environment. from an arrayAlthough of signal-scavenging this design does not sensors have thata power use energysupply, available the electronics throughout put into the the environment. carpet make Although it thick and this heavy. design For does example, not have a small a power mat supply, of the thecarpet electronics has four put blocks into of the foil carpet reading make electronics it thick and parts, heavy. four For AD example, convertors, a small one matmicrocontroller, of the carpet and has fourone wireless blocks of transmitter. foil reading Miguel electronics et al. parts, [11] fourand Cheng AD convertors, et al. [12] one advocated microcontroller, using arrays and one of pressure wireless transmitter.sensors made Miguel of electrostatic et al. [11] anddischarge Cheng protection et al. [12] advocated foam mixed using with arrays carbon of pressurefiber to identify sensors madestatic ofactivities electrostatic on the discharge carpet. Tanaka protection et al. foam [13] designed mixed with a smart carbon carpet fiber from to identify an array static of pressure activities‐sensing on the carpet.tiles that Tanaka can be et easily al. [13 assembled] designed on a smart a floor carpet to monitor from an user array position, of pressure-sensing motion and falls. tiles Chaccour that can beet easilyal. [14] assembled embedded on a a floormatrix to monitorof differential user position, piezoresistive motion andpressure falls. sensors Chaccour into et al. a [carpet14] embedded for fall adetection. matrix of Ho differential et al. [15] proposed piezoresistive a textile pressure technology sensors for into making a carpet smart for carpets fall detection. from tension Ho‐ etsensitive al. [15] proposedelectro‐conductive a textile technology yarns. The for sensing making smartyarn has carpets an fromelastic tension-sensitive core wound around electro-conductive by two tension yarns.‐ Thesensitive sensing electro yarn‐ hasconductive an elastic threads core wound of polyester around by and two stainless tension-sensitive steel fibers electro-conductive separated by threadsa non‐ ofconductive polyester basal and layer. stainless The steel technology fibers separated can detect by light a non-conductive touch, tactile perception, basal layer. and The tensile technology forces, canand detectseems lightto be touch,promising tactile though perception, its application and tensile in smart forces, mats and has seems not been to be revealed promising yet. though its applicationIn addition in smart to the mats abovementioned has not been revealed research, yet. a number of successful products have been already deployed.In addition An example to the abovementioned is a smart yoga research, mat [16] a numberthat employs of successful over 21,000 products built have‐in piezoresistive been already deployed.sensors to Andetect example human is aposes smart and yoga display mat [16 them] that on employs a smartphone over 21,000 or tablet built-in PC. piezoresistive The device provides sensors torobust detect identification human poses of and various display yoga them postures, on a smartphone thus allowing or tablet the PC.user The to deviceimprove provides his/her robust yoga identificationpractice. However, of various it is quite yoga expensive postures, (450 thus US$ allowing retail price). the user to improve his/her yoga practice. However,In this it isarticle, quite we expensive propose (450 a new US$ technique retail price). for posture detection and identification by using smartIn mats. this article, In contrast we propose to related a new methods, technique the forproposed posture technique detection anddifferentiates identification postures by using based smart on mats.voltage In contrastlevels generated to related methods,by mat sensors. the proposed According technique to differentiatesexperimental postures evaluation, based it on provides voltage levelsunobtrusive generated and by robust mat sensors. detection According of all tosix experimental Rakah postures evaluation, and reliable it provides Rakat unobtrusive counting. and Its robustimplementation detection is of simple all six Rakahand efficient, postures yet and inexpensive. reliable Rakat counting. Its implementation is simple and efficient,The rest yetof inexpensive.the article is organized as follows. In the next section, we discuss the proposed technique.The rest Section of the 4 describes article is organizedthe prototype’s as follows. implementation In the next in a section, smart mat we and discuss presents the proposedresults of technique.experimental Section evaluation.4 describes Section the 5 prototype’s summarizes implementation our findings and in aoutlines smart mat work and for presents the future. results of experimental evaluation. Section5 summarizes our findings and outlines work for the future. 3. The Proposed Technique 3. The Proposed Technique

3.1. An Overview The key ideaidea behindbehind our our method method emanates emanates from from empirical empirical analysis analysis of of output output voltages voltages produced produced by aby pressure a pressure sensor sensor of a singleof a single zone force-sensing zone force‐sensing resistor resistor (FSR) family, (FSR) which family, are which largely are used largely nowadays used innowadays automotive in electronics,automotive medical electronics, systems, medical and various systems, industrial and andvarious robotics industrial applications. and Arobotics FSR is aapplications. two-wire device A FSR made is a fromtwo‐wire polymer device thick made ﬁlm from that polymer “exhibits thick a decrease film that in resistance “exhibits witha decrease increase in inresistance force applied with increase to the surface in force of applied the sensor” to the [17 surface]. As the of force the sensor” grows, the[17]. output As the voltage force grows, increases. the Whenoutput a voltage person increases. steps over When the sensor, a person his weightsteps over causes the the sensor, sensor his to weight generate causes an output the sensor voltage to generate an output voltage proportional to the product of person’s mass and the gravitational acceleration. For example, if a FSR sensor is tied to a measuring resistor RM in a configuration shown

Electronics 2017, 6, 61 4 of 13

Electronics 2017, 6, 61 4 of 13 proportional to the product of person’s mass and the gravitational acceleration. For example, if a FSR in sensorFigure is3a, tied the to output a measuring voltage, resistor VOUT, RincreasesM in a conﬁguration with weight, shown as depicted in Figure in 3Figurea, the output 3b. Under voltage, a constantVOUT, force, increases the output with weight, voltage as remains depicted constant. in Figure Note,3b. the Under weight a constant in the article force, is the shown output in terms voltage of remainskilogram constant.‐force (1 kgf Note, = 9.8 the N). weight in the article is shown in terms of kilogram-force (1 kgf = 9.8 N).

(a) (b)

Figure 3. Results of force-sensing resistor (FSR) sensor testing: (a) a test circuit; (b) FSR voltage as Figure 3. Results of force‐sensing resistor (FSR) sensor testing: (a) a test circuit; (b) FSR voltage as a a function of applied weight and output resistance RM. function of applied weight and output resistance RM.

AsAs a force, a force, weight weight has has both both a amagnitude magnitude and and a adirection direction associated associated with with it. it. While While the the direction direction of of the weight force always remainsremains towardtoward the the center center of of the the earth, earth, the the distribution distribution of of the the weight weight over over the thebody’s body’s center center of of gravitygravity changes with with human human posture. posture. For For instance, instance, when when a person a person stands stands straight, straight, hishis weight weight concentrates concentrates over over his his feet. feet. So Sothe the weight weight force force is maximal. is maximal. When When a person a person bows, bows, sits sits or or prostrates,prostrates, his his body’s body’s center center of ofgravity gravity shifts shifts and and so sodoes does the the weight weight distribution. distribution. Because Because a posture a posture affectsaffects the the weight weight force force applied applied to tothe the sensor, sensor, it changes it changes the the voltage voltage produced produced by by the the sensor. sensor. FigureFigure 4 depicts4 depicts the the FSR FSR voltage voltage variations variations with with postures, postures, accumulated accumulated (at (atRM R= M600= Ω 600) fromΩ) from a testa in test which in which 30 people 30 people of different of different weight weight were were standing, standing, sitting sitting and and prostrating prostrating while while a FSR a FSR sensor sensor waswas under under their their feet. feet. As As one one can can see, see, the the postures postures induce induce distinguishable distinguishable voltages voltages though though the the levels of of the voltages vary with the mass. OurOur posture posture detection detection technique technique exploits exploits this this posture posture-voltage‐voltage dependency. dependency. In Incontrast contrast to to existingexisting approaches, approaches, which which differentiate differentiate human human postures postures by binary by binary patterns patterns of active of activesensors, sensors, the proposedthe proposed technique technique identifies identiﬁes postures postures by voltage by voltage levels levelsproduced produced by the by sensors. the sensors. It assumes It assumes that the that prayerthe prayer mat contains mat contains an array an arrayof FSR of strip FSR‐ strip-lineline sensors sensors connected connected to an to embedded an embedded microcontroller. microcontroller. TheThe microcontroller microcontroller reads reads the thesensor sensor voltages, voltages, and andbased based on them, on them, detects detects postures postures performed performed by the by user.the user.

3.2.3.2. Positioning Positioning of Sensors of Sensors Inside Inside a Mat a Mat In orderIn order to determine to determine sensor sensor placement placement within within the the mat, mat, we we experimentally experimentally studied studied the the mat mat usage usage in ina prayer. a prayer. The The study study involved involved 30 30Muslims Muslims aged aged from from 20 20to to60 60years years old. old. The The participants participants varied varied in in heightheight (140~178 (140~178 cm), cm), weight weight (40~72 (40~72 kg), kg), shape shape (slim, (slim, ordinary, ordinary, fat), fat), gender, gender, and and feet feet size size (23~26 (23~26 cm). cm). In Inthe the study, study, each each participant participant was was asked asked to pray to pray using using same same mat mat lined lined by squares by squares of 5 ofcm 5 × cm 5 cm× 5in cm size.in size. WeWe measured measured the the positions positions of of participants participants over over the the mat mat and and recorded thethe squaressquares touched touched by by the theparticipant’s participant’s feet, feet, knees, knees, forehead forehead or or hands hands in in different different postures. postures.

Electronics 2017, 6, 61 5 of 13 ElectronicsElectronics 2017 2017, 6, 616, 61 5 of5 13of 13

StandingStanding Sitting ProstrationProstration 3.53.5

3 3

2.52.5 V VOUT OUT 2 2 (V)(V) 1.51.5

1 1 0.5 0.5 0 0

Weight (kgf) Weight (kgf)

FigureFigure 4. 4.The The FSR FSR sensor sensor voltage voltage variation variation withwith the user’s posture posture and and weight. weight. Figure 4. The FSR sensor voltage variation with the user’s posture and weight. The results revealed three distinguishable areas of the mat usage, associated with the user’s feet The results revealed three distinguishable areas of the mat usage, associated with the user’s feet (AreaThe 1), results knees, revealed (Area 2) threeand head distinguishable (Area 3), respectively, areas of the as matshown usage, in Figure associated 5. Without with being the user’s asked, feet (Area 1), knees, (Area 2) and head (Area 3), respectively, as shown in Figure5. Without being asked, (Areaall participants 1), knees, (Area used 2)same and areahead for (Area feet, 3), identified respectively, from aas picture shown printed in Figure on 5.the Without mat. Namely, being asked, the all participants used same area for feet, identiﬁed from a picture printed on the mat. Namely, the Area all Areaparticipants 1 was used used in samestanding area and for bowing feet, identified postures; from Area a2 picturein sitting printed and prostrating on the mat. postures; Namely, and the 1Area wasArea used1 was3 in in theused standing prostrating in standing and posture bowing and only.bowing postures; postures; Area 2 in Area sitting 2 in and sitting prostrating and prostrating postures; andpostures; Area 3and in theArea prostrating 3 in the prostrating posture only. posture only.

Figure 5. Sensing areas associated with praying postures: (a) standing, (b) bowing, (c) sitting, (d)

prostration. Figure 5. Sensing areas associated with praying postures: (a) standing, (b) bowing, (c) sitting, (d) Figure 5. Sensing areas associated with praying postures: (a) standing, (b) bowing, (c) sitting, prostration.Figure 6 shows the details of mat area usage for each posture. In this figure, lines and columns (d) prostration. determine the squares within the mat areas (see Figure 7); the vertical axis shows the square usage in termsFigure of the 6 shows number the of details participants of mat that area touched usage fora particular each posture. square In inthis a posture.figure, lines The twoand visiblecolumns determinepeaksFigure in the6the shows squaresgraphs, the withinassociated details the of with mat areaareasAreas usage (see 1 and Figure for 2, eachcorrespond 7); posture.the vertical to Inthe thisaxis mat figure,shows regions linesthe used square and by columnsthe usage left in determinetermsand ofthe the right the number squares legs, respectively; of within participants the the mat graph that areas attouched the (see bottom Figure a particular reflects7); the the vertical square regions axisin of a Area showsposture. 3 touched the The square two by head. usagevisible inpeaks termsAs the in of resultsthe the graphs, number demonstrate, associated of participants every with participant Areas that touched 1 inand the 2, atest correspond particular placed their square to feetthe in matover a posture. regionsLine 3 of Theused Area two by 1 in the visible the left peaksandstanding the in right the posture, graphs, legs, respectively; pressed associated Line the with 3 graphof AreasArea at 1 the 1 and and bottom Line 2, correspond 2 reflects of Area the 2 to inregions the the mat sitting of regions Area posture, 3 touched used and by byin the thehead. left andAsprostration the the results right legs,posturedemonstrate, respectively; had their every feet the participant over graph Line at 4 in the of the Area bottom test 1, placedtheir reflects knees their the over feet regions Lineover 4Line of of Area Area 3 of 3 2Area touched and 1their in the by head.standingforehead As theposture, over results Line pressed demonstrate, 3 of Area Line 3. 3 everyThus, of Area participantto detect 1 and all Line in of the the2 testof postures Area placed 2 ofin their thethe Rakah feet sitting over sequence, posture, Line 3 of onlyand Area fivein 1 the in theprostrationstrip standing‐type posture(Model posture, 408)had pressed FSRtheir sensors Linefeet over 3 [16] of AreaLine are needed. 4 1 andof Area Line A standard1, 2 their of Area knees strip 2 in‐ typeover the FSR sittingLine‐408 4 posture, ofsensor Area is 2 and 622 and mm in their the prostrationforeheadlong and over posture6.35 Line mm had 3wide, of theirArea and feet3. 1 Thus,mm over thin. to Line detectBecause 4 of all Area it of responds the 1, their postures to knees pressure of over the applied LineRakah 4 ofsequence,from Area up 2 to and only ±5 cm their five foreheadstripfrom‐type its over (Modeledge, Line we 408) position 3 of FSR Area sensorsthe 3. sensors Thus, [16] toon are detect the needed. mat all as of Ashown the standard postures in Figure strip of 7.‐type the Rakah FSR‐408 sequence, sensor is only 622 fivemm strip-typelong and 6.35 (Model mm 408) wide, FSR and sensors 1 mm [ 16thin.] are Because needed. it A responds standard to strip-type pressure FSR-408applied sensorfrom up is to 622 ±5 mm cm longfrom and its edge, 6.35 mm we position wide, and the 1 sensors mm thin. on Becausethe mat as it responds shown in to Figure pressure 7. applied from up to ±5 cm from its edge, we position the sensors on the mat as shown in Figure7.

ElectronicsElectronics2017, 62017, 61, 6, 61 6 of 136 of 13 Electronics 2017, 6, 61 6 of 13

(a) (d) (a) (d)

(b) (e) (b) (e)

(c) (f) (c) (f) Figure 6. The mat area usage in different postures. (a) Area 1 usage at standing posture; (b) Area 1 Figure 6. The mat area usage in different postures. (a) Area 1 usage at standing posture; (b) Area 1 usageFigure at 6. sitting The mat posture; area usage(c) Area in 1different usage at postures.prostration (a )posture; Area 1 usage(d) Area at 2standing usage at posture; sitting posture; (b) Area (e )1 usageAreausage at sitting 2 atusage sitting posture; at posture;prostration (c) ( Areac) Areaposture; 1 1 usage usage (f) Area at prostration 3 usage at posture;prostration posture; (d) (posture.Aread) Area 2 usage 2 usage at sitting at sitting posture; posture; (e) (e) AreaArea 2 usage2 usage at at prostration prostration posture; (f (f) )Area Area 3 3usage usage at prostration at prostration posture. posture.

Figure 7. The FSR sensor voltage variation with the user’s posture. FigureFigure 7. The 7. The FSR FSR sensor sensor voltage voltage variation variation with the the user’s user’s posture. posture.

Now consider output voltages induced by these ﬁve FSR sensors when a mat user implements the Rakah postures. Table1 presents an example observed for a 40 kg user (R M = 600 Ω). The standing Electronics 2017, 6, 61 7 of 13

Electronics 2017, 6, 61 7 of 13 posture leads to the maximal voltage in comparison to the other voltages listed in the Table. This is because theNow user consider in this output posture voltages presses induced the mat by bythese his five entire FSR weight. sensors when When a themat user user bows,implements the Area 1 sensorsthe generateRakah postures. voltages Table around 1 presents 90–100% an example of the observed maximal for level. a 40 kg The user sitting (RM = posture600 Ω). The causes standing only 80% of theposture maximal leads voltage to the maximal on sensors voltage in Area in comparison 1, and around to the 60% other of voltages the maximal listed levelin the on Table. sensors This inis Area because the user in this posture presses the mat by his entire weight. When the user bows, the Area 2. When the user takes the prostrating posture, the sensors of Areas 2 and 3 produce voltages in the 1 sensors generate voltages around 90–100% of the maximal level. The sitting posture causes only 80% range of 50–75% and 4–25% of the maximal level, respectively. of the maximal voltage on sensors in Area 1, and around 60% of the maximal level on sensors in Area 2. When the user takes the prostrating posture, the sensors of Areas 2 and 3 produce voltages in the 1 range of 50–75% and 4–25%Table 1.of Sensorthe maximal readings level, (in respectively. volts) at different postures .

Area1 Area 21 Area 3 Posture Table 1. Sensor readings (in volts) at different postures . Sensor 1Area1 Sensor 2 SensorArea 3 2 SensorArea 4 3 Sensor 5 Posture Standing 1.89Sensor 1 Sensor 1.69 2 Sensor 0 3 Sensor 4 0Sensor 5 0 BowingStanding 1.791.89 1.721.69 0 00 00 0 SittingBowing 1.471.79 1.151.72 0 0.750 0.020 0 Prostration 0 0.98 0.04 1.21 0.2 Sitting 1.47 1.15 0.75 0.02 0 1 Prostration 0 RM 0.98= 600 Ω; 40 kg0.04 user. 1.21 0.2

1 RM = 600 Ω; 40 kg user. To study the relationship between the user’s posture, weight, and voltage ranges, we empirically measuredTo the study sensor the relationship outputs induced between bythe 30user’s different posture, users weight, of and the voltage prayer ranges, mat. Figure we empirically8 shows the measured the sensor outputs induced by 30 different users of the prayer mat. Figure 8 shows the results in terms of sensor voltages (VOUT) normalized to the peak voltage levels (V0) of the Area results in terms of sensor voltages (VOUT) normalized to the peak voltage levels (V0) of the Area 1 1 sensors. sensors.

(a)

(b)

Figure 8. Normalized voltage variations observed on outputs of sensors in Area 1–3 when 30 users of Figure 8. Normalized voltage variations observed on outputs of sensors in Area 1–3 when 30 users of different weight performed the bowing and sitting postures (a), and the prostration posture (b). different weight performed the bowing and sitting postures (a), and the prostration posture (b).

Electronics 2017, 6, 61 8 of 13 Electronics 2017, 6, 61 8 of 13

ForFor the the sake sake of simplicity,of simplicity, we depict we depict only the only maximal the maximal values of values the normalized of the normalized voltages generated voltages bygenerated sensors inby Areas sensors 1 andin Areas 2 for 1 the and bowing, 2 for the the bowing, sitting andthe sitting the prostration and the prostration postures. Thepostures. absolute The variationabsolute ofvariation peak voltage of peak (V voltage0) with (V the0) weightwith the is weight given in is Figuregiven in4. Figure Interestingly, 4. Interestingly, the voltage the ranges voltage associatedranges associated with the with postures the postures are quite are distinguishable quite distinguishable and do not and depend do not much depend on much the user’s on the weight. user’s Inweight. the sequel, In the we sequel, exploit we these exploit voltage–posture these voltage–posture correlation correlation for posture for detection. posture detection.

3.3.3.3. The The Posture Posture Detection Detection and and Rakat Rakat Counting Counting Technique Technique TheThe proposedproposed posture posture detection detection technique technique is based is based on identifying on identifying patterns patterns of sensor of readings sensor readingsassociated associated with each with posture each postureof the Rakah of the Rakahsequence. sequence. In contrast In contrast to related to related techniques, techniques, which whichdifferentiate differentiate postures postures by logic by patterns logic patterns associated associated with positions with positions of active of active sensors sensors within within the mat, the it mat,distinguishes it distinguishes patterns patterns (and hence (and hence postures) postures) by voltage by voltage levels levels produced produced by the by sensors. the sensors. At each At each time timeof prayer, of prayer, the thevoltage voltage levels levels of the of the sensor sensor outputs outputs are are compared compared to tothe the pre pre-defined‐defined thresholds. thresholds. A Aposture posture is is considered considered detected detected if if and and only only if all of thethe sensorssensors associatedassociated withwith the the posture posture produce produce voltagesvoltages within within the the specified specified range. range. If If the the completed completed sequence sequence of posturesof postures matches matches the the correct correct order order of theof the Rakah Rakah sequence sequence (Figure (Figure1), the 1), Rakatthe Rakat counter counter is incremented. is incremented. Otherwise, Otherwise, it remains it remains unchanged. unchanged. FigureFigure9 illustrates9 illustrates the the proposed proposed posture posture generation generation and and Rakat Rakat counting counting technique technique in in terms terms of of statestate transition transition diagram. diagram. In In this this figure, figure, circles circles represent represent postures; postures; arrows arrows show show their their execution execution order order in Rakahin Rakah sequence, sequence, the formulas the formulas above theabove arrows the representarrows represent conditions conditions at which the at posturewhich the is considered posture is detectedconsidered i.e., detected the state i.e., transition the state occurs. transition The thresholdsoccurs. The associated thresholds with associated the conditions with the have conditions been obtainedhave been from obtained an analysis from ofan experimental analysis of experimental data, of which data, a part of which is shown a part in Figureis shown8. in Figure 8.

Figure 9. State diagram of the Rakat Counter. Figure 9. State diagram of the Rakat Counter. The state machine works as follows. As the user activates the machine, it evaluates the outputs of sensorsThe in state Area machine 1 for 3 s inworks order as to follows. identify As the the peak user voltage activates of the the machine, standing it posture. evaluates If the the voltage outputs levelof sensors is less in than Area a given 1 for 3 threshold s in order (L to0), identify i.e., no the pressure peak voltage on sensors, of the the standing system remainsposture. inIf the the voltage initial stage.level Otherwise,is less than thea given calculated threshold peak (L voltage0), i.e., no is appliedpressure as on a referencesensors, the (V0 system) for computing remains in ten the voltage initial thresholdsstage. Otherwise, (Li) of the the detection calculated conditions. peak voltage Namely, is applied as a reference (V0) for computing ten voltage thresholds (Li) of the detection conditions. Namely, L1 = 0.9 × V0, (1) L1 = 0.9 × V0, (1)

L2L=2 1= ×1 ×V V0,0, (2)

L3 = 0.5 × V0, (3)

Electronics 2017, 6, 61 9 of 13

L3 = 0.5 × V0, (3)

L4 = 0.65 × V0, (4)

L5 = 0.5 × V0, (5)

L6 = 0.12 × V0, (6)

L7 = 0.1 × V0, (7)

L8 = 0.8 × V0, (8)

L9 = 0.05 × V0, (9)

L10 = 0.65 × V0, (10)

For example, if the reference voltage V0 = 1.89 V, the L1 = 1.7 V, L2 = 1.89 V, L3 = 0.945 V, and so on. The bowing posture is detected when the output voltages of Area 1 sensors are within the range L1 ≤ V1 ≤ L2. Otherwise, the system waits until the user implements the posture correctly i.e., the outputs of sensors 1 and 2 satisfy the specified condition. Note that even if the specified condition is satisfied but there is non-zero output from other sensors, the system will remain in the current state. To detect the prostration posture, we use Areas 2 and 3 sensors. If the outputs of the Area 2 sensors satisfy the condition: L3 ≤ V2 ≤ L4, and the outputs of the Area 3 sensors satisfy the condition: L5 ≤ V3 ≤ L6, then the system identifies the prostration posture. Otherwise, it continues waiting for the correct implementation of the required posture. To detect the sitting posture, we check whether the Area 1 voltages (V1) and the Area 2 voltages (V2) are within the ranges: L7 ≤ V1 ≤ L8 and L9 ≤ V2 ≤ L10. If either of these two conditions is unsatisfied, or there is a non-zero voltage output from the Area 3 sensors, the posture is rejected as incorrect. Thus, we proceed to the next state if the user correctly implements the postures. As the second prostration is identified, the system increments the Rakat Counter (RC) by 1 and repeats the cycle.

4. Implementation and Evaluation

4.1. Implementation The proposed technique was implemented in a smart mat prototype [18] that additionally to Rakah counting also determined the start time of a next prayer and the direction to Mekkah (or Qibla). The praying mat was 120 cm × 70 cm in size, which is conventional for a medium height user. Figure 10 shows a block diagram of electronics embedded into the mat. The sensor array contained ﬁve force-sensing resistive strips (FSR 406) placed under Areas 1–3 of the mat, as shown in Figure7. To reduce sensor displacement and eliminate undesirable effects of dirt, the sensors were ﬁxed in special pockets made of cloth that were sewn to the backside of the praying mat. The processing unit (depicted by gray pattern in Figure 10) includes an 8-bit microcontroller (AVR ATmega32, from Atmel Crop., Chandler, AR, USA), a GPS receiver (Ublox NEO 6M, from Thalwil, Switzerland), a digital compass (CMPS10, from Robot Electroncs, Norfolk, UK), a real-time clock (RTC) unit, and an interface circuitry. The control panel contains a 128 × 64 graphical LCD display, a digital buzzer and a number of switches. By pushing a corresponding button on the control panel, the user can display on the screen either the ST (start time of the next prayer), QD (Qibla Direction), and RC (Rakah Counter). He or she can also reset RC, deactivate the buzzer (alarm off) or power off the smart mat if necessary. Electronics 2017, 6, 61 10 of 13 Electronics 2017, 6, 61 10 of 13 Electronics 2017, 6, 61 10 of 13

Figure 10. Block diagram of smart mat. Figure 10. Block diagram of smart mat. On the mat, the FSR sensingFigure strips 10. Block were diagram attached of smart to the mat. backside of the mat, while the microcontrollerOn the mat, and the FSRthe control sensing panel strips shared were the attached board placed to the on backside the foreside of the of mat, the mat. while The the microcontrollerproposedOn the posturemat, and the the detection controlFSR sensing and panel Rakat sharedstrips counting thewere board techniqueattached placed wasto on theimplemented the foresidebackside of inof the software. the mat. mat, The while proposed the posturemicrocontrollerFigure detection 11a,b and and shows the Rakat control photographs counting panel technique of shared the smart the was mat board implemented prototype placed and inon software. itsthe usage foreside in a prayer. of the Themat. user The proposedactivatesFigure posture 11thea,b smart shows detection mat photographs by andpushing Rakat the of counting power the smart bottom technique mat on prototype the was control implemented and panel. its usage By default,in insoftware. a prayer. the RC Theis zero. user activatesWhenFigure theactivated, 11a,b smart shows matthe system by photographs pushing displays the of powerthe the value smart bottom of matRC on andprototype the the control next and posture panel. its usage By to default,be in taken a prayer. the by RCthe The isuser, zero.user Whenactivatesthus activated, guiding the smart him the mat or system her by through pushing displays the the Rakah the power value sequence. bottom of RC Ifon and the the system the control next recognizes panel. posture By that to default, be the taken user the completed by RC the is zero. user, thusWhena Rakah, guiding activated, it him increments the or her system through the RCdisplays value. the Rakah theOtherwise, value sequence. of the RC value If and the of systemthe RC next remains recognizes posture unchanged. to that be thetaken user by completed the user, athus Rakah, guidingFigure it increments him 11c orexemplifies her the through RC data value. the shown Rakah Otherwise, on sequence. the thedisplay value If the as of systemthe RC user remains recognizes completed unchanged. that the thesitting user posture completed of a Rakah,theFigure second it increments 11 Rakahc exempliﬁes sequence. the RC data value.At shownany Otherwise, time, on the the user display the can value reset as of the theRC user counterremains completed or unchanged. switch the the sitting power posture OFF if of thenecessary. secondFigure Rakah11c exemplifies sequence. data At anyshown time, on the the user display can as reset the the user counter completed or switch the sitting the power posture OFF of ifthe necessary. second Rakah sequence. At any time, the user can reset the counter or switch the power OFF if necessary.

(a) (b) (c)

Figure 11. Photographs: (a) the smart mat prototype (b) the smart mat usage; (c) displayed data.

4.2. Evaluation(a) and Results (b) (c) Figure 11. Photographs: (a) the smart mat prototype (b) the smart mat usage; (c) displayed data. FigureTo evaluate 11. Photographs: the quality ( aof) the the smart proposed mat prototype posture recognition (b) the smart and mat Rakat usage; counting (c) displayed algorithm, data. we performed a number of tests, which involved 30 participants (of ages 10 to 60). The tests have been 4.2.conducted Evaluation in and laboratory Results conditions with the smart mat placed on a flat, smooth, clean flooring. The 4.2. Evaluation and Results temperature and humidity levels in the room were normal. The participants had different heights To evaluate the quality of the proposed posture recognition and Rakat counting algorithm, we (fromTo evaluate 128 cm to the 180 quality cm), feet of size the (from proposed 18 cm posture to 29 cm), recognition and shapes and (from Rakat 26 to counting 94 kg). During algorithm, the performed a number of tests, which involved 30 participants (of ages 10 to 60). The tests have been wetests, performed each participant a number was of tests, asked which to perform involved the praying 30 participants ritual with (of three ages Rakat 10 to correctly 60). The and tests then have conducted in laboratory conditions with the smart mat placed on a flat, smooth, clean flooring. The beenrandomly conducted skip in or laboratory perform incorrectly conditions (e.g., with sitting the instead smart mat bowing placed or vs. on versa) a ﬂat, one smooth, or several clean postures ﬂooring. temperature and humidity levels in the room were normal. The participants had different heights Thein temperature a “faulty” Rakah and humidity sequence. levels These inscenarios the room were were repeated normal. three The times participants by each hadsubject different in a random heights (from 128 cm to 180 cm), feet size (from 18 cm to 29 cm), and shapes (from 26 to 94 kg). During the (fromorder. 128 In cm between to 180 the cm), tests, feet the size power (from was 18 switched cm to 29 OFF. cm), The and tests shapes totaled (from 120 26 simulated to 94 kg). cycles During of six the tests, each participant was asked to perform the praying ritual with three Rakat correctly and then tests,postures each participant each. was asked to perform the praying ritual with three Rakat correctly and then randomly skip or perform incorrectly (e.g., sitting instead bowing or vs. versa) one or several postures randomlyThe skip evaluation or perform revealed incorrectly several (e.g., results. sitting First, instead when bowing the system or vs. versa) was switched one or several ON and postures no in a “faulty” Rakah sequence. These scenarios were repeated three times by each subject in a random in apressure “faulty” asserted Rakah sequence. to the mat, These the voltage scenarios readings were repeatedfrom the FSR three sensors times bywere each almost subject 0, causing in a random the order. In between the tests, the power was switched OFF. The tests totaled 120 simulated cycles of six

postures each. The evaluation revealed several results. First, when the system was switched ON and no pressure asserted to the mat, the voltage readings from the FSR sensors were almost 0, causing the

Electronics 2017, 6, 61 11 of 13 order. In between the tests, the power was switched OFF. The tests totaled 120 simulated cycles of six postures each. The evaluation revealed several results. First, when the system was switched ON and no pressure asserted to the mat, the voltage readings from the FSR sensors were almost 0, causing the system to remain in the initial state. The system operation started only when someone stepped over sensing Area 1, and when the level of voltage generated from the sensors of this area exceeds L0. (Though we used L0 = 1, the threshold level can be calibrated to reduce external noise if any. According to [17], the FSR sensors are no more prone to noise pickup than a passive resistor). Second, the posture detection ratio of the proposed technique was 100%, even though the participants in the tests had different styles for sitting, standing, and prostration. Some of them inclined or moved forward/backward more than others; some used their hands to support their body when standing. Despite variations in posture style, the proposed method was able to effectively distinguish all six postures of the Rakah sequence and correctly count the Rakat. At the same time, we should notice that the posture detection and recognition might depend on the person’s height. Namely, it might be possible that a mat designated for a person of an average height may fail to correctly identify postures of a very tall or a short person or vice versa. We assume that this issue will not pose a problem in reality, because worshippers usually use mats of sizes proportional to their height. Finally, the tests showed that the sensors in the mat successfully detect gait characteristics and are not perceptible to the people as they stay, sit, or prostrate. Overall, all the participants of the evaluation experiments reported the proposed smart mat useful and quite helpful.

5. Limitations and Future Work In this section, we discuss the limitations of our study. Recognizing human activity is a challenge for any cyber-physical system application, as it requires modeling the peculiarities of an application environment, as well as the complex behavioral, psychological, and physiological aspects of human beings. The level of modeling for each of these aspects depends on application requirements. In the current work, we modeled the application environment through laboratory settings that resembled environmental conditions in a Mosque or at home (flat, smooth, dry, and clean surfaces), i.e., conditions typical to the majority of Muslims. In the future, we will consider other settings to cover praying outdoors. For example, people may pray in open air and place the mat on a bumpy, sandy and dusty surface. Though worshipers usually pray in dry and clean places outdoors and do not pray in the event of rain or snow, several external factors such as dirt, moisture, liquids, and trapped air bubbles can cause the FSR sensors to generate faulty signals. Also, proximity to high intensity radio frequency (RF) sources may require special measures to reduce electro-magnetic noise. To investigate these issues, we plan to conduct a larger study of outdoor mat use. We should also acknowledge that the developed system prototype is just a testbed to evaluate the efficiency of the proposed method, as well as other techniques [18]. Though the strip-type sensors are flexible, neither the sensors nor the control panel can be folded, as this may cause shearing or breakup. We are now working on providing a foldable and portable solution of battery-operated smart-mat electronics which is reliable, easy to use and attach/detach whenever necessary. Another limitation of the current work deals with the user modeling. The number of old and forgetful people involved in the study was very limited, and so it is hard to draw a statistically significant conclusion. Though all subjects considered in the study are real prayer mat users, some old people may implement postures differently than others or use assistive tools such as a cane to support their body. Also, people suffering from memory loss or cognitive impairment may also have different behavior. Extending the study to cover more elders and forgetful people will be performed in the near future. Further, the current study assumed that the mat user is the only person who asserts force to the mat during a prayer. Moreover, the worshiper performs praying activities and takes postures within Electronics 2017, 6, 61 12 of 13 the mat area. Someone unfamiliar with Islam may argue that a mat user hypothetically might jump, step out of the mat during a prayer, go out, return back, and so on. Moreover, a prayer might be interrupted by a child, another person (e.g., caregiver), or a pet, for example, who might step over the mat and cause an error. While these events might happen hypothetically, they are far from reality. Religious people are very serious in their beliefs, obligations, and rituals. Preparations to pray are actually taken with a large care to prevent any external interruption. When a prayer starts, everyone in a Muslim family prays, including kids. During a prayer, each worshiper uses his own mat and is fully concentrated on the spiritual act of praying, i.e., communicating with God. So it is a realistic consideration that a Muslim will not be doing anything else other than praying if someone near them is also engaged in prayer. However, even if a hypothetical case takes place and a faulty action or posture is detected, the system will remain in its current state until the required posture is done correctly.

6. Conclusions In this paper, we presented a new technique for unobtrusive human posture identification by a smart mat to assist Muslims in praying. As the experimental evaluation revealed, the proposed technique provides robust recognition of postures taken by a worshiper in a prayer and correct counting of the Rakat cycles in real time. Finally, we would like to notice that the proposed voltage based posture identification technique is not limited to the smart prayer mat and Rakat counting, even though the paper has been focused on this specific application only. We think that it can be used in other applications as well. In healthcare, for example, the technique can be applied to identify the sleeping postures, or for monitoring the frequency of posture change of in-bed patients to decrease the development of ulcers. Similarly, it can be applied to detect sitting postures from sensors placed inside a chair. We are currently investigating further applications.

Acknowledgments: The authors thank colleagues from Tele-communication Laboratory of Moslem University of Makassar, Indonesia for assistance in accumulating experimental data and helpful discussions. Author Contributions: All authors have contributed to the work presented in this article. Kasman Kasman conceived and designed the smart mat prototype, performed experiments and wrote the text; Vasily G. Moshnyaga directed the work, analyzed and interpreted the obtained results and revised the manuscript. Conﬂicts of Interest: The authors declare no conﬂict of interest.

References

1. Ismail, J.; Noor, N.L.M.; Isa, W.A.R.W.M. Addressing cognitive impairment among elderly people: A techno-spiritual perspective. In Proceedings of the 5th International Conference on Information and Communication Technology for the Muslim World (ICT4M), Kuching, Malaisia, 17–18 November 2014; pp. 1–5. 2. Speck, C.E.; Kukull, W.A.; Brenner, D.E.; Bowen, J.D.; McCormick, W.C.; Teri, L.; Pfanschmidt, M.L.; Thompson, J.D.; Larson, E.B. History of depression as a risk factor for Alzheimer’s disease. Epidemiology 1995, 6, 366–369. [CrossRef][PubMed] 3. Khatri, A.E.S. Prayer Mat. UK Patent 2,263,003-A, 7 July 1993. 4. Faouaz, H. Muslim Prayer Counter. U.S. Patent 6,783,822, 31 August 2004. 5. Abdelmohsen, A.M.E. Prayer Carpet (for Muslims) Provided with a Number of Bowings (Rak’a) Digital Displayer Apparatus. WO Patent 2,007,104,321 A1, 20 September 2007. 6. Arrar, R.B.J. Portable Interactive Islamic Prayer Counter. U.S. Patent 7,508,316 B1, 24 March 2009. 7. Kantarceken, I. Prayer Assistance Device for Use As e.g. Personal Digital Assistant, Has Electronic Memory Unit Storing Program Flow that Acoustically Corrects Spoken Words and Physical Gestures of Prayer by Sound Transducer Unit. Patent DE 102,010,048,504 B3, 5 April 2012. 8. Ismail, J.; Noor, N.L.M.; Isa, W.A.R.W.M. Smart prayer mat: A textile-based pressure sensor to assist elderly with cognitive impairment in praying Activity. In Proceedings of the 5th International Conference on Computing & Informatics (ICOCI), Istanbul, Turkey, 11–13 August 2015; pp. 241–246. Electronics 2017, 6, 61 13 of 13

9. Middleton, L.; Buss, A.A.; Nixon, M.S. A floor sensor system for gait recognition. In Proceedings of the 2005 4th IEEE Workshop on Automatic Identification Advanced Technologies, Buffalo, NY, USA, 17–18 October 2005; pp. 171–176. 10. Aud, M.A.; Abbott, C.C.; Tyrer, H.W.; Neelgund, R.V.; Shriniwar, U.G.; Mohammed, A.; Devarakonda, K.K. Smart Carpet: Developing a sensor system to detect falls and summon assistance. J. Gerontol. Nurs. 2010, 36, 8–12. [CrossRef][PubMed] 11. Miguel, J.; Morgado, A.; Konig, A. Low-Power concept and prototype of distributed resistive pressure sensor array for smart floor and surfaces in intelligent environments. In Proceedings of the International Conference on Systems, Signals and Devices, Chemnitz, Germany, 20–23 March 2012; pp. 1–6. 12. Cheng, J.; Sandholm, M.; Zhou, B.; Kreil, M.; Lukowicz, P. Recognizing subtle user activities and person identity with cheap resistive pressure sensing carpet. In Proceedings of the International Conference on Intelligent Environments, Shanghai, China, 30 June–4 July 2014; pp. 148–153. 13. Tanaka, O.; Ryu, T.; Hayashida, A.; Moshnyaga, V.G.; Hashimoto, K. A Smart Carpet Design for Monitoring People with Dementia. In Progress in System Engineering, Advances in Intelligent Systems and Computing; Selvaraj, H., Zydek, D., Chmaj, G., Eds.; Springer: Berlin, Germany, 2015; pp. 653–659. 14. Chaccour, K.; Darazi, R.; El Hassani, A.H.; Andres, E. Smart carpet using differential piezoresistive pressure sensors for elderly fall detection. In Proceedings of the 2015 IEEE 11th International Conference on Wireless and Mobile Computing, Networking and Communications (WiMob), Abu Dhabi, United Arab Emirates, 19–21 October 2015; pp. 225–229. 15. Ho, V.A.; Imai, S.; Hirai, S. Multimodal flexible sensor for healthcare system. In Proceedings of the 2014 36th Annual International Conference of the IEEE on Engineering in Medicine and Biology Society (EMBS), Chicago, IL, USA, 26–30 August 2014; pp. 5976–5979. 16. The World’s First Intelligent Yoga Mat. Available online: https://smartmat.com/ (accessed on 25 May 2017). 17. FSR 400 Series Data Sheet, Interlink Electronics. Available online: http://www.steadlands.com/data/ interlink/fsrdatasheet.pdf (accessed on 25 May 2017). 18. Kasman, K.; Moshnyaga, V.G. A smart mat for assisting Muslims in praying. In Proceedings of the 2017 IEEE International Conference on Consumer Electronics (ICCE), Las Vegas, NV, USA, 8–10 January 2017; pp. 481–484.

© 2017 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (http://creativecommons.org/licenses/by/4.0/).