Categorizing WSNs Sensory Data Using Self                      Organizing Maps                                            ...
requirement to implement inexpensive Wireless Sensor                 ConsumptionNetworks and hence given rise to the conce...
An input sample taken from the training data set at a certain       updating of winning neuron . The function can be Gauss...
Fig. 4: Sample two dimensional data                                                                                       ...
From 4 to 24 hrs interv between transmissions                                                 al          50 r - - - - , -...
VI.        CONCLUSIONWireless Sensor Networks suffer greatly due to inherent loss              [6]    A. Kulakov, D. Davce...
Upcoming SlideShare
Loading in …5



Published on

Sir Abdul Manan Research Journal

Published in: Technology, Business
  • Be the first to comment

  • Be the first to like this

No Downloads
Total views
On SlideShare
From Embeds
Number of Embeds
Embeds 0
No embeds

No notes for slide


  1. 1. Categorizing WSNs Sensory Data Using Self Organizing Maps Abdul Mannariand Haroon A. Babre Department of Electronic and Computer Engineering, NFC Institute of Engg and Tech. Training, Multan, Pakistan. 2Department of Electrical Engineering, University of Engineering and Technology, Lahore, Pakistan., Wireless Sensor Networks suffer greatly from their after their deployment, self organization feature, rapidlimited battery power whose utilization is increased manifolds as deployment and inherent intelligence [2].a node has to transmit or receive fairly large amount of data. SOMs have been applied to localize/ place sensor nodes inSeveral algorithms, some for scheduling battery power e.g. order to reduce communication overheads [11]. ART andDynamic Voltage Scheduling, Static Voltage Scheduling, Fuzzy ART algorithms have also been applied to sensorDynamic Power Management etc and other with emphasis ondesigning efficient routing protocols have been designed in past. networks to increase battery life time and tendency forSome algorithms, however, address this very issue at software hierarchy building [6]. On the other hand, some researcherslevel by writing memory and CPU friendly programs. This have tried techniques like Static Voltage Scheduling andpaper proposes Self Organizing Maps (SOM) based Dynamic Power Management to activate electronic circuitryunsupervised Artificial Neural Network learning technique to only when it is required [12]. The batterys life timeenhance average battery life. Proposed system allows all active enhancement is still an important problem. Efficient linknodes to transmit their sensory data to the base station node layer protocol design for the network has also been addressed(BSN) which has a 2X3 SOM running on it. Sensor nodes start with interesting results [14]sending data to the BSN; it keeps on making categories and putsrelevant data in appropriate categories/ classes. SOM is trainedafter it has received anum ber of such transmissions from active This paper presents a novel scheme for implementing a twonodes. Class definitions are then broadcast to all active nodes by dimensional Self Organizing Map on a sample WirelessBSN and from then onwards they transmit only the class Sensor Network to lower the volume of data packetsdefinitions (that are fairly lesser in size) to BSN and hence transmitted and received within the network and hencesignificant battery power is conserved. We have showed an reduction in overall battery consumption is realized. Resultsoverall 48.5% battery power saving using the above technique. show that (1) Battery power saving monitored versus number of data samples transmitted for training (2) Battery powerIndex-Term - Base Station Node, Self Organizing Maps, Artificial saving versus time interval between two consecutiveNeural Networks, Wireless Sensor Networks, Sampling, transmissions and finally (3) an optimum operating conditionCompetition, Adaptation was calculated by combining both of the above two I. INTRODUCTION dimensional plots.Self Organizing Maps (SOM) is an unsupervised learningtechnique inspired by the physical arrangement of neurons Section II discusses the details of Wireless Sensor Networks/within human brain. A Self Organizing Map can be one, two IEEE 802.15.4 standard with possible routing architecture.or three dimensional depending on the complexity of Section III discusses Self Organization Maps briefly. Sectionrecognition or prediction task and the computational IV describes how sensory data is categorized and Section Vcapabilities of hardware [1]. describes Results and AnalysesA Wireless Sensor Network (WSN) consists of very low cost II. WIRELESS SENSOR NETWORKSand low power multifunctional sensors deployed in largenumber to monitor some physical activity happening within Recent developments in wireless communications, integratedtheir surroundings e.g. movement of troops, measurement of communication electronic design and Micro Electrotemperature, humidity, vibration etc. Their implementation Mechanical Systems have led to the development of cheapbecame possible due to recent developments in micro-electro- and efficient Wireless Sensor Networks. They targetmechanical systems (MEMS) and state of the art primarily the very low cost and ultra low power consumptioncommunication electronics. Many real world applications are applications. Data throughput of the network and reliabilitypotential applications of Wireless Sensor Networks and have of a node can however be compromised to be of secondarycaught the interest of researchers from various concern [2].interdisciplinary fields due to their unique characteristics environment with large number of sensors distributed at Non-critical and non-real time applications in residential,physically scarce locations, flexibility of movement even business and industrial sectors have accelerated the978-1-4244-4361-1/09/$25.00 ©2009 IEEE
  2. 2. requirement to implement inexpensive Wireless Sensor ConsumptionNetworks and hence given rise to the concept of a modelcheap wireless personal area network (LR-WPANs: Low Cost Highest High LowRate Wireless Personal Area Network) [2]. Consequently, in Size Large Small Very Smallyear 2003, the LR-WPANs standard was accepted by IEEEand was given the name IEEE 802.15.4 [3]. Star topology Peer to Peer topologySuitability of Wireless Standards subsisted before the adventof IEEE 802.15.4 for applications insisting massivedeployment of Wireless Transceivers was dubious due totheir high cost and unnecessarily high data rate. IEEE802.15.4 however, has revolutionized the deployment ofvarious small sensor nodes in great numbers for monitoringvarious physical phenomenon, conveniently distributed at @ Coordinator o Active Nodescarce locations and keeping their cost low at a compromiseof low data rate and range of communication. A comparison Fig 1. Star and Peer to Peer topologyof the 802.15.4 LR-WPANs with 802.11b WLAN and802.15.1 Bluetooth ™ is shown in Table 1. ~ 1 ..4-bytes •r- --1-- 2-127 bytes --I~"------~------..IIEEE 802.15.4 is distinct from other wireless technologies inthe sense that its goal is to achieve cheap short distance Prea- Le- Start Payloadcommunication at low data rate and hence realization of a mble ngthnetwork of large number of very small sized nodes possiblein contrast with its competitors. Fig 2. The] EEE 802.15.4 packet structureThe 802.15.4 LR-WPANs standard provisions two different The 802.15.4 standard uses a packet structure as in Fig. 2.topologies for network formation [3]: Each packet or physical layer protocol data unit contains a • Star/ Hub Topology preamble, a start of packet delimiter, a packet length and payload field or physical layer service data unit. The payload • Peer to Peer Topology length can vary from 2 to 127 bytes depending on size of dataInspired by conventional Ethernet Hub Architecture Startopology only allows all active nodes to be in direct being exchanged. In our design, preamble carries node ID while Payload bears data from various active nodescommunication with Coordinator or Base station node. Twoactive nodes cannot be in direct communication. In Peer to III. SELF ORGANIZING MAPSPeer topology, in contrast, any node can communicate withany other node irrespective of active or base station node. An SOM [1] is a neural network that learns applicationData communication in peer to peer topology is easier as information as a set of weights associated with the neurons.compared to star topology but at the cost of increased In comparison with other techniques (e.g. Multi-Layernetwork complexity. Perceptron), SOMs are unique because the neurons are arranged in regular geometric structure which can be one orWireless Sensor Network/ IEEE 802.15.4 are worth using in two dimensional. Three dimensional structures can also existtwo frequency bands (1) 868/915 MHz or (2) 2.4 GHz with but are not very common. Neurons can be arranged either (1)the same data packet structure. However data rate can range Grid or (2) Hexagonal or (3) Random topology beforefrom 20 kbps to 250 kbps as central carrier frequency training starts.increases from lowest value i.e. 868 MHz to maximum valuei.e. 2.4 GHz Topology plays a central role in learning process and on final TABLE I arrangement of neurons after they have learned. Training of COMPARISON OF VARIOUS WIRELESS ECHNOLOGIES Self Organizing Maps in unsupervised i.e. total number of target classes is known before hand but their exact defmitions are not obvious unless network is adequately trained. 802.11b 802.15.1 802.15.4 Supposing input samples and the map weights to be Range (m) 100 Up to 100 10 multidimensional real valued vectors, the three phases of the Throughput training algorithm are as follows: 10 1 0.25 Max (Mbps) Power High Low Very Low 1. Sampling:
  3. 3. An input sample taken from the training data set at a certain updating of winning neuron . The function can be Gaussianiteration is called x(n) and is applied to the network. Synaptic and the effect should be decreasing as Euclidean distanceweight vector corresponding to a neuron j is Wj where j from the winning neuron increases.ranges from 0 to t with t representing total number of . .) (d(i,j)2)neurons. h( l , j = exp - 2r(n) Winning Ne uron where d(i,j) is the distance between two neurons on the map. Weight change is significant near the winning neuron and becomes negligible on the boundary of the neighborhood range. One last parameter to be discussed is r(n) which is the radial distance from the winning neuron and is calculated as monotonously decreasing function: r(n) = ro exp(-n / k 2 ) where ro is initial value and k2 is another time constant. r(n) is high initially, ensures early convergence of the network and becomes small as epochs increase, which causes individual neurons to become sensitive for various features contained by input data set. Fig. 3: A 2-dimenstional Self-Organ izing Map IV. CATEGORIZING SENSORY DATA2. Competition: Wireless Sensor Networks suffer greatly due to inherent lossThe sample x(n) is compared with the map weights of each of battery power as they process information sensed fromneuron through the use of a discriminating functionf=j{x,w). their surroundings and then transmitting and! or receiving thisThe neuron that scores the maximum value wins the information. We have targeted this very drawback and havecompetition and becomes the Winning Neuron (WN) . There come up with an unsupervised learning techniqu e i.e. Selfcan be various choices for calculating distance associated Organizing Maps which is trained on sample two dimensionalwith the discriminating function e.g. Euclidean, grid or box. data collected from various active nodes. Once training isHowever , if it is implemented using the Euclidean distance, complete active nodes are allowed to transmit only the classthe selection will be governed by the following expression: titles which is less bulky as compared to full sensed data transmission. Sample input data was first plotted on a two dimensional scale to exploit any potential clusters present as shown in Fig. 4.3. Synaptic Adaptation: A Self Organizing Maps based network was trained with theFinally, the synaptic weights associated with Winning same training data. Output neurons were connected as a 2X3Neuron along with its neighbors are adapted according to the map as shown in Fig. 5.following rule: A Self Organizing Map orders various data samples Wj (n + 1) = w j (n) + .,,(n)h(j, WN(n))[x(n) - w j (n)] according to their mutual similarity. The neighborhood function used was a decreasing exponential function and aSynaptic update is controlled by the global learning rate variable learning rate was selected to be 0.9 initially and thenparameter IJ and by a neighborhood function h =h(i, j ) decreased to O.Olas the last epoch reached.Learning rate must decrease with increasing number ofiterations. Typical range of learning rate is from 0.1 to 0.01 asnumber of epochs increase. One possibl e choice for IJ is adecreasing exponential function given by: lJ(n) = lJo exp(-n / k[)where no is initial value and k, is a time constant.Synaptic update also involves neighborhood function whichdecides how much and how far neighboring neurons shouldbe affected in terms of their weights along with weight
  4. 4. Fig. 4: Sample two dimensional data TABLE II in1 POWER CONSUMPTION OF VARIOUS OPERATIONS Power in2 Operation Consumption Central Processing Unit 3mW (CPU) Transmitter 30mW Receiver 40mW Sleep 5JlW There are two major factors affecting overall power savings achieved by the scheme. • Total number of training data samples Fig. 5: A 2X3 Self-Organizing Map • Interval between two consecutive transmissions (after the network is trained) oute -~ In each case the power saving was the calculated difference between "power consumed if there is no training" and "power outO consumed by training/ trained network". -~ If the total number of training data samples is kept low, the inA outE network will not be able to converge. However, power -~ consumption will be small. On the other hand, as the number of training samples is increased, the network will be outF converged adequately but at a cost of increased power -- --v:.;;::: ~: . . Jf/ -~ consumption. inB outG The time interval between two consecutive transmissions was :::::.:~~:~..~~:~ <, -~ kept constant and power saving was calculated for varying values of training data samples which, in each case, were . varied from 18 to 23. This is done by reading data of Table 3 <. . outH -~ one row at a time. TABLE III POWER SAVING CHART Fig. 6: Feedforward network with 6 output neurons Interval Power SavingThe performance of the above 2X3 Self Organizing Map was b/w (mW)compared with a feed forward backpropagation network with consecutiveone hidden layer and six output neurons as shown in Fig. 6. Training Data Samples transm- 18 19 20 21 22 23 issionsThe SOM was found advantageous in terms of its very early (hours)convergence. Performance of Self Organizing Maps 2 23 23 22.5 22.5 22 21.5algorithm was verified for input samples described in next 4 37 36 35 34.5 33.5 32.5section. 6 44.5 43 41.5 40.5 39 37.5 v. RESULTS AND ANALYSES 8 48.5 46.5 44.5 42.5 40.5 39 10 49.5 47 44 42 39.5 37.5Implementation of a 2x3 Self Organizing Map neural network 12 48.5 45.5 42.5 39.5 37 34.5learning on one wireless sensor network active node can 14 44.5 41 38.5 34 30.5 27.5result in a significant power saving which will be obvious as 16 38.5 34 30 26 22.5 19we move further in this section. 18 34.5 30.5 25.5 21 17 14.5 20 30 25.5 21 16.5 12.5 9Power dissipation of a typical WSN node for various 22 25.5 20 16.5 11.5 8 4.5operations is given in Table 2. 24 21 15.5 11 6.5 2 2
  5. 5. From 4 to 24 hrs interv between transmissions al 50 r - - - - , - - - - - r - - - - r - - - - - , - - - - - - - , , , From 18 to 23 data samples ~"~," ~ 5 0 , - - --,-----:::;:;::=:::= - -- - , - - - , - - - - - - , : :: :::::::::::;::::::~::::p~~;~:~:~;~:~~:::: I I : 45 I I I - - " _ J. 40 " 35 _ _ ____ ~_ :-.. ~_ .. I --l-----------t:::::::::. . . .s zn 35 " , .!O ~ 30 -----------~ --------- .". :--.::: -.- - - - - - - - - ~ ----------- ~ ----------- , -..... , I Q) : : I -- -- : - +-. : , ..----- --- - --.-----..:;-- - ---.------ - ---- iii 30 " Q; - - 08=18 OS: o 25 - - - - - - - -- --" ---- - -- - - :;: 25 ---.r --..--.-i--.-.---.--:---.--_-. . -..- -- ~ -- _ : (L - - TI=4 : o - - 08=19 0- ~ 20 ~ g;, 20 -- ---- -- 08=20 - · - TI=8 : : " ?ft. 15 -- ------- TI=12 - - - -~- - - - -- - - - -- ~ - - - ------~----------- " - - - - 08=21 ?f. 15 - ---- TI=16 : : - 08=22 10 - -- - j- - --- -- - - j - - - --- -- - -- i - - --- -- 10 - ----- ---- - -------~- - --------- ~- - --"-,---"-- TI=20 : : : , , , , -----#--- ~ 0 8 =23 5 ---+- TI=24 --- -;--- ----- --- ;--- --- ---;--- --- ----- 5 -- ---- - --- - ~---~-- ------- ~ - -- - - -- - - -- -~ ---- -- ---- , , , , , , , , , , 0------------------------"----- 18 19 22 23 5 20 25 Fig. 7: Power Saving versus Training Data Sampl es Fig. 8: Power Saving versus Time Interval between tran smissionsSix different plots were obtained by changing time intervalbetween two consecutive transmissions from 4 to 24 hours asshown in Fig 7. ········.L 50 "" . ....A. POWER SAVING VS INTERVAL BETW EEN RANSMISSIONS ; ........ 40 OJ .sAfter the network is trained, if transrmssions are made > ~ 30frequent, the battery will exhaust drastically but with thebenefit of continuous monitoring. On the other hand, if ~ c 0.. 20interval between two consecutive transmissions is larger, the ~ OJ ~life time of voltage source will increas e (with some "#. 10conditions discusses later in this section) but at a cost of weakmonitoring. o 23Training Data Samples were kept constant and power saving 25was plotted versus interval between two transmissions whichin each case, was varied from 2 to 24 hours. This is done byreading data of Table 3 one column at a time. 18 0 Number oftraining data samples Timeint rval betwentrans ssions (hrs) e miSix different plots were created by varying trammg datasamples from 18 to 23 which are shown in Fig. 8 Fig 9. Power Saving versus Time Interval and Training Data SamplesFig 8 reveals that the power saving increases initially with From this plot we can infer the optimum values of trainingincreasing time interval between transmissions but as time data samples and time interval between consecutiveinterval crosses a certain value, it starts decreasing. It is due transmissions required to maximize overall power the fact that if data transmi ssion s are not frequ ent then the Optimum parameters derived from Fig 9 are given in Table 4.power consum ed to train the network initially, becom es an TABLE IVoverh ead . OPTIMUM PARAMETERSB. POWER SAVING VS TIME INTERVAL AND Optimum number of training data samples 18 TRAINING DATA SAMPLES Optimum Time interval between two 9.5 hrs consecutive transmissionsThe effect of "Time interval between transmissions" and the Maximum Normalized Power Saving achi eved 48.5%"N umber of training data samples" on " Power Saving" isshown in Fig 9.
  6. 6. VI. CONCLUSIONWireless Sensor Networks suffer greatly due to inherent loss [6] A. Kulakov, D. Davcev, "Tracking of unusual events in wirelessof battery power as they process information sensed from sensor networks based on artificial neural-networks algorithms",their surroundings and then transmitting and! or receiving this Proceedings ofthe ICIT, Vol. 2, pp-532-539, 2005 [7] Mohammad Ilyas and Imad Mahgoub, "Handbook of sensorinformation. We have targeted this very drawback and have Networks: Compact Wireless and Wired Sensing Systems" CRCcome up with an unsupervised learning technique i.e. Self Press, 2005Organizing Maps which is trained on sample two dimensional [8] P. Radivojac, U. Korad, K. M. Sivalingam, Z. Obradovic,data collected from various active nodes. Once training is "Learning from Class-Imbalanced Data in Wireless Sensor Networks", Vehicular Technology Conference, Vol. 5, 2003,complete active nodes are allowed to transmit only the class pp.3030-3034titles which is less bulky as compared to full sensed data [9] Ethem Alpaydin, "Introduction to Machine Learning", The MITtransmission. We have shown that applying this technique to Press, 2004two dimensional sensed data has resulted in enormous battery [10] T. Kohonen, "Self-organized formation of topologically correct feature maps" Biological Cybernetics, Vol. 43, no. 1, 1982, pp.power saving which is around 48.5%. 59-69 [11] Gianni Giorgetti, Sandeep K. S. Gupta, Gianfranco Manes, ACKNOWLEDGEMENT "Wireless Localization Using Self-Organizing Maps", Proceedings of the 6th International conference on Information processing in sensor networks, 2007, pp. 293-302The authors gratefully acknowledge Jameel Ahmed of NFC [12] Min, R. Bhardwaj, M. Seong-Hwan Cho Shih, E. Sinha, A.Institute of Engineering and Technological Training, Multan Wang, A. Chandrakasan, A. "Low-power wireless sensorand Asim Loan of University of Engineering and networks", Proceedings of the Fourth International ConferenceTechnology, Lahore for discussions and valuable input. on VLSI Design, 2001, pp. 205-210 [13] Vijay Degalahal, Tim Tuan, "Methodology for High Level Estimation of FPGA Power Consumption", Proceedings of the REFERENCES 2005 conference on Asia South Pacific design automation, 2005, pp. 657 - 660, 2005[1] S. Haykin, Neural Network: A Comprehensive Foundation, 2nd [14] Tan et aI, "Power efficient data gathering and aggregation in Edition, Prentice Hall, 1998 wireless sensor networks", SIGMOD Record, Vol. 32, No.4,[2] I. F. Akyildiz, W. Su, Y. Sankarasubramaniam, and E. Cayirci, December 2003 "A survey on sensor networks," IEEE Communications [15] A. Mannan "Realization of an unsupervised learning scheme for Magazine, vol. 40, 2002, pp. 102-114 categorization of sensory data of WSNs" MSc Thesis,[3] G. 1. Pottie and W. 1. Kaiser, "Wireless integrated network Department of Electrical Engineering, UET, Lahore, Pakistan Oct sensors," Communications of the ACM, vol. 43, no. 5, 2000, pp. 2007 51-58[4] S. Lindsey, K. M. Sivalingam, and C. S. Raghavendra, "Data gathering algorithms in sensor networks using energy metrics," IEEE Transactions on Parallel and Distributed Systems, vol. 13, 2002,pp.924-935[5] P. Emmanauel , C. Nick, "Unsupervised categorization and category learning", The Quarterly Journal of experimental psychology, vol. 58, no. 4, 2005, pp-733-752