TELK OMNIKA Indonesian Journal of Electrical Engineering V ol. 14, No . 3, J une 2015, pp . 557 564 DOI: 10.11591/telk omnika.v14.i3.7833 557 Finding Kic king Rang e of Sepak T akra w Game: A Fuzzy Logic Appr oac h Andino Maseleno*, Md. Mahm ud Hasan 1 Computer Science Prog r am, Univ ersiti Br unei Dar ussalam, Negar a Br unei Dar ussalam F aculty of Inf or mation T echnology , Kazakh Br itish T echnical Univ ersity , Kazakhstan * Corresponding author , e-mail: andinomaseleno@mail.r u Abstract This paper presents a method to find kic king r ange of sepak takr a w game when pla y er kic ks bac k the ball to the other team. This research w or ks considered ho w fuzzy logic can be applied f or the sepak takr a w game - f or addressing uncer tainty in kic king r ange of the ball. Six diff ere nt conditions are descr ibed. This research has chosen Tsukamoto’ s fuzzy reasoning scheme , because the individual r ule outputs are cr isp n umbers , and theref ore , the functional relationship betw een the input v ector and the system output can be relativ ely easily identified. The result re v eals that the f ar thest r ange of the ball coming to the other team in condition 1 obtained r ange 10.1% of f ar , condition 2 obtained r ange 10.23% of v er y f ar , condition 3 obtained r ange 10.16% of v er y f ar , condition 4 obtained r ange 10.03% of f ar , condition 5 obtaine d r ange 10.28% of f ar , and condition 6 obtained r ange 10.42% of f ar . K e yw or ds: sepak takr a w; fuzzy logic; Tsukamoto method; kic king r ange Cop yright c 2015 Institute of Ad v anced Engineering and Science 1. Intr oduction Sepak takr a w or kic k v olle yball is a spor t nativ e to Southeast Asia, resemb ling v olle yball, e xcept that it uses a r attan ball and only allo ws pla y ers to use their f eet and head to touch the ball. A cross betw een f ootball and v olle yball, it is a popular spor t in Thailand, Cambodia, Mala ysia, Laos , Philippines and Indonesia. The str ategies in Sepak takr a w are also v er y similar to those in v olle yball. The receiving team will attempt to pla y the takr a w ball to w ards the front of the net, making the best use of their 3 hits , to set and spik e the ball [1]. Some research related with kic ks and sepak takr a w ha v e been de v eloped which w ere the study to identify diff erences in kic k- ing kinematics betw een the kuda and sila ser vice techniques [2], data’ s researcher sho w ed that angular v elocity patter n betw een both techniques w ere compar ab le with no significant diff erence obser v ed f or the thigh, shank and f oot angular v elocities at ball-contact. Sam uel et al. [3] intro- duced an approach to enab le humanoid soccer robots to e x ecute kic ks quic kly and ensure that the y mo v e the ball do wn field, this paper presents a kic k engine capab le of kic king at a v ar iety of distances and angles and then descr ibes a kic k decision method f or selecting from amon g a large set of possib le kic ks . This method pr unes and ord ers the kic ks according to a metr ic and then chooses the first possib le kic k that ensures that their field position is impro v ed. Currently , the use of Fuzzy Logic is widespread and also n umerous system ha v e been de v eloped f or the spor ts [4], [5], [6], [7], [8], [9]. This research has chosen Tsukamoto’ s fuzzy reasoning scheme , because t he individual r ule outputs are cr isp n umbers , and theref ore , the functional relationship betw een the input v ector and the system output can be relativ ely easily identified. 2. Sc hematic Representation of Sepak T akra w Game Sepak takr a w is a highly comple x net-barr ier kic king spor t that in v olv es dazzling displa ys of quic k re fle x es , acrobatic twists , tur ns and s w er v es of the agile human body . The r ules of the game allo w pla y ers to mak e contact to the ball up to three consecutiv e times per side [1]. Figure 1 sho ws a schematic representation of sepak takr a w game . A match is pla y ed b y tw o regus , each Receiv ed J an uar y 26, 2015; Re vised Apr il 17, 2015; Accepted Ma y 9, 2015 Evaluation Warning : The document was created with Spire.PDF for Python.
558 ISSN: 2302-4046 consisting of th ree pla y ers . One of the three pla y ers shall be at the bac k and the pla y er is called a ”T ek ong” which include Pla y er P and Pla y er S . The other tw o pla y ers shall be in front, one on the left and the other on the r ight which include Pla y er Q, Pla y er R, Pla y er T and Pla y er U . The pla y er on the left is called a ”Left Inside” and the pla y er on the r ight is called a ”Right Inside”. Area of 13.4 m x 6.1 m free from all obstacles up to the height of 8 m measured from the floor surf ace . The width of the lines bounding the cou r t should not be more than 0.04 m measured and dr a wn inw ards from the edge of the cour t measurements . All the boundar y lines should be dr a wn at least 3.0 m a w a y from all obstacles . The Centre line of 0.02 m should be dr a wn equally dividing the r ight and left cour t. At the cor ner of each at the Centre Line , the quar ter circle shall be dr a wn from the sideline to the Centre Line with a r adius of 0.9 m measured and dr a wn outw ards from the edge of the 0.9 m r adius . (a) Pla y er P and Pla y er Q, ho w the ball coming to Pla y er S (b) Pla y er P and Pla y er Q, ho w the ball coming to Pla y er T (c) P la y er P and Pla y er Q, ho w the ball coming to Pla y er U (d) Pla y er P and Pla y er R, ho w the ball coming to Pla y er S (e) Pla y er P and Pla y er R, ho w the ball coming to Pla y er T (f) Pla y er P and Pla y er R, ho w the ball coming to Pla y er U Figure 1. Schematic representation of sepak takr a w game Figure 1(a) sho ws schematic representation of sepak takr a w game from Pla y er P and Pla y er Q with re f erence to ho w the ball coming t o Pla y er S . Figure 1(b) sho ws schematic repre- sentation of sepak takr a w game from Pla y er P and Pla y er Q with ref erence to ho w the ball coming TELK OMNIKA V ol. 14, No . 3, J une 2015 : 557 564 Evaluation Warning : The document was created with Spire.PDF for Python.
TELK OMNIKA ISSN: 2302-4046 559 to Pla y er T . Figure 1(c) sho ws schematic representation of sepak takr a w game from Pla y er P and Pla y er Q with ref erence to ho w the ball coming to Pla y er U . Figure 1(d) sho ws schematic repre- sentation of sepak takr a w game from Pla y er P and Pla y er R with ref erence to ho w the ball coming to Pla y er S . Figure 1(e) sho ws schematic representation of sepak takr a w game from Pla y er P and Pla y er R with ref erence to ho w the ball coming to Pla y er T . Figure 1(f) sho ws schematic represen- tation of sepak takr a w game from Pla y er P and Pla y er R with ref erence to ho w the ball coming to Pla y er U . 3. Using Fuzzy Logic in Sepak T akra w Game Prof essor L.A. Zadeh introduced the concept of Fuzzy Logic [10], Tsukamoto Fuzzy rea- soning are models based on Fuzzy Logic [ 11]. These r ules are easy to lear n and use and can be modified according to the situation. It helps to mak e decisions and can be used in decision analysis . Tsukamoto Fuzzy reasoning does mapping from giv en input to an output using Fuzzy Logic. Figure 2 sho ws Tsukamoto model of Fuzzy inf erence . Tsukamoto Fuzzy reasoning has a n umber of r ules based on if then conditions . In this method, the consequence of each Fuzzy r ule is represented b y a Fuzzy set with a monotonic membership function. The r ule base has the f or m as: R i : if u is A i and v is B i , then w is C i , i = 1, 2, , n. Where C i (w) is a monotonic function. As a result, the inf erred output of each r ule is defined as a cr isp v alue induced b y the r ules matching deg ree (fir ing strength). The o v er all output is tak en as the w eighted a v er age of each r ules output. Suppose , that the set C i has a monotonic membership function C i (w) and that i is the matching deg ree of its r ule . F or the Fuzzy set input (A’, B’) is giv en b y the equation 1: i = min [max u ( A 0 ( u ) ^ A i ( u ) ; max v ( B 0 ( v ) ^ B i ( v ))] (1) In this case , IF Pla y er P is SER VE VE R Y NEAR AND Pla y er Q is KICKING VER Y F AR, THEN the ball should be [COMING RIGHT ON Pla y er S] Figure 2. Tsukamoto model of Fuzzy Inf erence A linguistic v ar iab le is a v ar iab le whose v alues can be e xpressed b y means of natur al Finding Kic king Range of Sepak T akr a w Game: A Fuzzy Logic Approach (Andino Maseleno) Evaluation Warning : The document was created with Spire.PDF for Python.
560 ISSN: 2302-4046 language ter ms [12], [13], [14]. The diff erent ter ms or linguistic v alues are represented b y Fuzzy sets char acter ised b y membership functions defined on the univ erse of discourse . Linguistic v ar iab les to find kic king r ange of sepak takr a w game are sho wn in T ab le 1. T ab le 1. Linguistic v ar iab les Pla y er P ser v e V er y Near Near Right On F ar V er y F ar (PSVN) (PSN) (PSR O) (PSF) (PSVF) Pla y er Q Kic king V er y Near Near Right On F ar V er y F ar (QKVN) (QKN) (QKR O) (QKF) (QKVF) Pla y er R Kic king V er y Near Near Right On F ar V er y F ar (RKVN) (RKN) (RKR O) (RKF) (RKVF) Coming to Pla y er S V er y Near Near Right On F ar V er y F ar (CVNS) (CNS) (CR OS) (CFS) (CVFS) Coming to Pla y er T V er y Near Near Right On F ar V er y F ar (CVNT) (CNT) (CR O T) (CFT) (CVFT) Coming to Pla y er U V er y Near Near Right On F ar V er y F ar (CVNU) (CNU) (CR OU) (CFU) (CVFU) T ab le 2 sho ws kic king r ange f or inputs to find kic king r ange of sepak takr a w game . Condi- tion 1 is Pla y er P and Pla y er Q, ho w the ball coming to Pla y er S; Condition 2 is Pla y er P and Pla y er Q, ho w the ball coming to Pla y er T ; Condition 3 is Pla y er P and Pla y er Q, ho w the ball coming to Pla y er U; Condition 4 is Pla y er P and Pla y er R, ho w the ball coming to Pla y er S; Condition 5 is Pla y er P and Pla y er R, ho w the ball coming to Pla y er T ; Condition 6 is Pla y er P and Pla y er R, ho w the ball coming to Pla y er U; T ab le 2. Kic king r ange f or inputs to find kic king r ange of sepak takr a w game Condition Action Range V er y Near Near Right On F ar V er y F ar Condition 1 Pla y er P ser v e 3.50 4.50 6.00 5.50 7.00 Pla y er Q kic king 1.50 2.50 4.50 5.00 8.00 Condition 2 Pla y er P ser v e 3.20 4.10 5.20 6.60 6.70 Pla y er Q kic king 1.00 1.50 3.50 7.60 7.70 Condition 3 Pla y er P ser v e 3.40 4.20 5.40 6.80 7.20 Pla y er Q kic king 1.30 1.75 3.90 7.70 7.90 Condition 4 Pla y er P ser v e 3.70 4.30 5.60 6.90 7.20 Pla y er R kic king 1.70 2.20 4.20 3.50 8.30 Condition 5 Pla y er P ser v e 3.80 4.70 5.80 7.30 7.60 Pla y er R kic king 1.90 2.70 5.50 4.50 8.50 Condition 6 Pla y er P ser v e 3.90 4.80 6.30 7.40 7.90 Pla y er R kic king 2.20 2.90 6.90 5.50 8.70 The matr ix on Figure 3 presents a g roup of 25 Fuzzy r ules that associate Pla y er P and Pla y er Q with ref erence to ho w Pla y er S should be changed. The matr ix on figure 3(a) presents a g roup of 25 Fuzzy r ules that associate Pla y er P and Pla y er Q with ref erence to ho w the ball coming to Pla y er S should be changed. F or e xample , the r ule w ould be read as: IF Pla y er P is [SER VE VER Y NEAR] AND Pla y er Q is [KICKING VER Y F AR], THEN the ball should be [COMING RIGHT ON Pla y er S]. The matr ix on figure 3(b) presents a g roup of 25 Fuzzy r ules that associate Pla y er P and Pla y er Q with ref erence to ho w the ball coming to Pla y er T should be changed. The matr ix on figure 3(c) presents a g roup of 25 Fuzzy r ules that associate Pla y er P and Pla y er Q with ref erence to ho w the ball coming to Pla y er U should be changed. The matr ix on figure 3(d) presents a g roup of 25 Fuzzy r ules that associate Pla y er P and Pla y er R with ref erence to ho w the ball coming TELK OMNIKA V ol. 14, No . 3, J une 2015 : 557 564 Evaluation Warning : The document was created with Spire.PDF for Python.
TELK OMNIKA ISSN: 2302-4046 561 to Pla y er S should be changed. The matr ix on figure 3(e) presents a g roup of 25 Fuzzy r ules that associate Pla y er P and Pla y er R with ref erence to ho w the ball coming to Pla y er T should be changed. The matr ix on figure 3(f) presents a g roup of 25 Fuzzy r ules that associat e Pla y er P and Pla y er R with ref erence to ho w the ball coming to Pla y er U should be changed. (a) Rule matr ix of Fuzzy r ules betw een Pla y er P and Pla y er Q, ho w the ball coming to Pla y er S (b) Rule matr ix of Fuzzy r ules betw een Pla y er P and Pla y er Q, ho w the ball coming to Pla y er T (c) Rule matr ix of Fuzzy r ules betw een Pla y er P and Pla y er Q, ho w the ball coming to Pla y er U (d) Rule matr ix of Fuzzy r ules betw een Pla y er P and Pla y er R, ho w the ball coming to Pla y er S (e) Rule matr ix of Fuzzy r ules betw een Pla y er P and Pla y er R, ho w the ball coming to Pla y er T (f) Rule matr ix of Fuzzy r ules betw een Pla y er P and Pla y er R, ho w the ball coming to Pla y er U Figure 3. Rule matr ix of Fuzzy r ules When a game begins b y one ser v e , a ball can be touched b y the attac k of one time to three times . The pla y er can use a head, a bac k, legs , and an ywhere e xcept f or the ar m from the shoulder to the point of the finger . Assume that pla y er position and kic king r ange in the be- Finding Kic king Range of Sepak T akr a w Game: A Fuzzy Logic Approach (Andino Maseleno) Evaluation Warning : The document was created with Spire.PDF for Python.
562 ISSN: 2302-4046 ginning of sepak takr a w game can be defined as f ollo ws: Pla y er P v er y near = 3; Pla y er P near = 4; Pla y er P r ight on = 5; Pla y er P f ar = 6.5; Pla y er P v er y f ar = 7.5. Pla y er Q v er y near = 1; Pla y er Q near = 2; Pla y er Q r ight on = 3; Pla y er Q f ar = 7.5; Pla y er Q v er y f ar = 8.5. Pla y er S v er y near = 3.5; Pla y er S near = 4.5; Pla y er S r ight on = 5.5; Pla y er S f ar = 9.5; Pla y er S v er y f ar = 10.5 Pla y er S v er y near is used to define the v ar iab le v er y near . The w eight is calculated b y the f ollo wing f or m ula: ( Pla y er S v er y near [ w ]) = 8 > < > : 1 ; w 3 : 5 4 : 5 w 4 : 5 3 : 5 ; 3 : 5 w 4 : 5 0 ; w 4 : 5 (2) Pla y er S near is used to define the v ar iab le near . The w eight is calculated b y the f ollo wing f or m ula: ( Pla y er S near [ w ]) = 8 > < > : 0 ; w 3 : 5 or w 5 : 5 w 3 : 5 4 : 5 3 : 5 ; 3 : 5 w 4 : 5 5 : 5 w 5 : 5 4 : 5 ; 4 : 5 w 5 : 5 (3) Pla y er S r ight on is used to define the v ar iab le r ight on. The w eight is calculated b y the f ollo wing f or m ula: ( Pla y er S r ight on [ w ]) = 8 > < > : 0 ; w 4 : 5 or w 9 : 5 w 4 : 5 5 : 5 4 : 5 ; 4 : 5 w 5 : 5 9 : 5 w 9 : 5 5 : 5 ; 5 : 5 w 9 : 5 (4) Pla y er S f ar is used to define the v ar iab le f ar . The w eight is calculated b y the f ollo wing f or m ula: ( Pla y er S f ar [ w ]) = 8 > < > : 0 ; w 5 : 5 or w 10 : 5 w 5 : 5 9 : 5 5 : 5 ; 5 : 5 w 9 : 5 10 : 5 w 10 : 5 9 : 5 ; 9 : 5 w 10 : 5 (5) Pla y er S v er y f ar is used to define the v ar iab le v er y f ar . The w eight is calculated b y the f ollo wing f or m ula: ( Pla y er S v er y f ar [ w ]) = 8 > < > : 0 ; w 9 : 5 w 9 : 5 10 : 5 9 : 5 ; 9 : 5 w 10 : 5 1 ; w 10 : 5 (6) Dur ing the Sepak takr a w game , both teams will mak e diff erent po w erful mo v es to kic k and spik e the ball to go to the opponent side and f all within the boundar y line of the cour t, pla y ers tr y to pla y the ball to w ard the front of the net, making the best use of their three hits to pass , set and spik e . Figure 4 sho ws a v er age kic king r ange . Figure 5 sho ws kic king r ange of the ball coming to the other team. The ball coming to pla y er S in condition 1 obtained r ange 4.09 of v er y near , 5.11 of near , 8.36 of medium, 10.1 of high, 7.97 of v er y high. Condition 2 obtained r ange 4.13 of v er y near , 4.02 of near , 5.04 of medium, 9.73 of high, 10.23 of v er y hi gh. Condition 3 obtained r ange 3.91 of v er y near , 4.11 of near , 5.16 of med ium, 9.79 of high, 10.16 of v er y high. Condition 4 obtained r ange 3.86 of v er y near , 4.13 of near , 4.98 of medium, 10.03 of high, 9.8 7 of v er y high. Condition 5 obtained r ange 3.78 of v er y near , 4.11 of near , 4.76 of medium, 10.28 of high, 9.57 of v er y high. Condition 6 obtained r ange 4.36 of v er y near , 3.51 of near , 4.61 of medium, 10.42 of high, 9.55 of v er y high. TELK OMNIKA V ol. 14, No . 3, J une 2015 : 557 564 Evaluation Warning : The document was created with Spire.PDF for Python.
TELK OMNIKA ISSN: 2302-4046 563 (a) A v er age kic king r ange of condition 1 (b) A v er age kic king r ange of condition 2 (c) A v er age kic king r ang e of condition 3 (d) A v er age ki c kin g r ange of condition 4 (e) A v er age kic king r ange of condition 5 (f) A v er ag e kic king r ange of condition 6 Figure 4. A v er age kic king r ange Figure 5. Range of the ball coming to the other team 4. Conc lusion This research has descr ibed a method to find kic king r ange of sepak takr a w game using Tsukamoto’ s Fuzzy reasoning. T o ser v e , one pla y er stands in the r ight semi-circle on their side of the cour t. The pla y er thro ws the ball to the ser v er , who stands in the circle on their side of the cour t. The pla y er kic ks the ball up and o v er the net then opponent pla y er kic ks bac k the ball. The v agueness present in the definition of ter ms is consistent with the inf or mation contained in the conditional r ules . Ev en though the set of linguistic v ar iab les and their meanings is compatib le and consistent with the set of conditional r ules used, the o v er all outcome of the qualitativ e process is tr anslated into obje c t iv e and quantifiab le results . Fuzzy mathematical tools and the calculus Finding Kic king Range of Sepak T akr a w Game: A Fuzzy Logic Approach (Andino Maseleno) Evaluation Warning : The document was created with Spire.PDF for Python.
564 ISSN: 2302-4046 of Fuzzy IF-THEN r ules pro vide a most useful par adigm f or the automation and implementation of an e xtensiv e body of human kno wledge heretof ore not embodied in the quantitativ e modelling process . These mathematical tools pro vide a means of shar ing, comm u nicating, and tr ansf err ing this human subjectiv e kno wledge of systems and processes . The result re v eals that the f ar thest r ange of the ball coming to the other team in condition 1 obtained r ange 10.1% of f ar , condition 2 obtained r ange 10.23% of v er y f ar , condition 3 obtained r ange 10.16% of v er y f ar , condition 4 obtained r ange 10.03% of f ar , condition 5 obtained r ange 10.28% of f ar , and condition 6 obtained r ange 10.42% of f ar . The f ar thest r ange in condition 6 (10.42%), f ollo w ed b y Condition 5 (10.28%), condition 2 (10.23%), condition 3 (10.16%) and condition 1 (10.1%). Ac kno wledg ements This w or k w as suppor ted b y Gr aduate Research Scholarship (GRS), ref erence: UBD/GSR- ADM/01, from Univ ersiti Br u nei Dar ussalam in Br unei Dar ussalam. W e g r atefully appreciate this suppor t. Ref erences [1] Inter national Sepak T akr a w F eder ation. La ws of the Game Sepak T akr a w in The 24th Kings Cup Sepaktakr a w W or ld Championship 2009 Prog r am. Bangk ok, Thailand, J uly 2-7, 2009. [2] Michael K , T eik H, Ian HS . 3D Kinematic Analysis of The K uda and Sila Ser vice T echnique , 24 Inter national Symposium on Biomechanics in Spor ts , 2006. [3] Sam uel B , Katie G, T odd H, Michael Q, P eter S . Controlled Kic king under Uncer tainty , The Fifth W or kshop on Humanoid Soccer Robots (HSR-10), Nashville , TN, 2010. [4] Cur tis KM, K elly M, and Cr a v en MP . Cr ic k et Batting T echnique Analyser/T r ainer using Fuzzy Logic , 16th Inter national Conf erence on Digital Signal Processing, Santor ini-Helas , pp . 1 6, 2009. [5] Ref ae y MA, Elsa y ed KM, Hanafy SM, and Da vis LS . Concurrent T r ansition and Shot Detection in F ootball Videos using Fuzzy Logic , 16th IEEE Inter national Conf erence on Image Process- ing, Cairo , Egypt, pp . 4341-4344, 2009. [6] Hang Y , T ang Z, Zhongcai P . Str ategies f or Shooting based on Fuzzy Logic and Ar tificial P o- tential Field in Robot Soccer Systems . Inter national Conf erence on Computer Application and System Modeling (ICCASM), T aiyuan, China, pp . V4-399 - V4-403, 2010. [7] K uo JY , Ou YC . An Ev olutionar y Fuzzy Beha viour Controller using Genetic Algor ithm in RoboCup Soccer Game . Ninth Inter national Conf erence on Hybr id Intelligent Systems , Shen y ang, China, pp . 281-286, 2009. [8] Hag r as H, Ramadan R, Na wito M, Gabr H, Zaher M, F ahm y H. A Fuzzy Based Hier archical Coordination and Control System f or a Robot ic Agent T eam in the Robot Hoc k e y Competition. IEEE Inter national Conf erence on Fuzzy Systems , pp . 1-8, Barcelona, 2010. [9] T r a winski K A. Fuzzy Classification System f or Prediction of the Results of the Bask etball Games , IEEE Inter national Conf erence on Fuzzy Systems , pp . 1-7, Barcelona, 2010. [10] Zadeh LA. Fuzzy Sets . Inf or mation and Control, V ol.8, pp .338-353, 1965. [11] Tsukamoto Y . Gupta MM, Ragade RK, and Y ager RR, Eds .. An approach to fuzzy reasoning method in adv ances in Fuzzy Set Theor y and Application. Nor th Holland, Amsterdam, 1979. [12] Zadeh LA. The Concept of Lin guistic v ar iab le and its applications to appro ximate reasoning, P ar t I. Inf or mation Sciences , V ol.8, pp .199-251, 1975. [13] Zadeh LA. The Concept of Lin guistic v ar iab le and its applications to appro ximate reasoning, P ar t II. Inf or mation Sciences , V ol.8, pp .301-357, 1975. [14] Zadeh LA. The Concept of Lin guistic v ar iab le and its applications to appro ximate reasoning, P ar t III. Inf or mation Sciences , V ol.9, pp .43-80, 1975. TELK OMNIKA V ol. 14, No . 3, J une 2015 : 557 564 Evaluation Warning : The document was created with Spire.PDF for Python.