ISSN: 2394-6881 International Journal of Engineering Technology and Management (IJETM) Available Online at www.ijetm.org Volume 2, Issue 3, May-June 2015, Page No. 117-119 Corresponding author: Anshul Sharma Page117 Design & Analysis of Performance of K-means algorithm for skin detection using wearable Sensors Anshul Sharma 1 , Varun Sharma 2 , Anil Saroliya 3 1,2,3 Amity School of Engineering & Technology Amity University Rajasthan, India 1 ansh.zeuss@gmail.com, 2 vsharma@jpr.amity.edu, 3 asaroliya@jpr.amity.edu ABSTRACT This paper provides an alternative technique of analysis of K-means algorithm for health and skin detection wearable sensors. Today wearable sensors can be used in activity of recognition system and various devices. These activity monitors are used in automatic calculation metabolic equivalent of task and the activity recognition wearable kinematic sensors for development of interactive games. It is explained in literature of the most large variance and feature set overlap and quite challenges for classifier trained on one intensity level. The K-means is a well-known classification approach for clustering in data representation. This paper verify and motivation of presented method which increase the advantage intensity independent activity recognition. the various reasons of face/people detection, image content interpretation; de-identification for privacy protection in multimedia content, etc. there is no perfect solution for skin detection so it is compromise on speed simplicity and detection quality. It is also used the RGB (Red, Green, Blue) model for the different components detection. It is also present the design, implementation and testing of the K-means algorithm through complete experimentation by using wearable sensors. Keywords: Skin detection, K-means and wearable sensors 1. Introduction: Skin detection is a very important pre-processing step in many different applications, such as face detection, people detection, image content interpretation, de- identification for privacy protection in multimedia content. A skin color is the main descriptor in skin detection. It has a low computational cost and it is invariant to position and scaling. Also, it covers only a small part of the whole color model. That means that any presence of such colored pixels in an image can be related to presence of a skin. The skin conductance is used to determine the electrical conductance of the skin. This is control and dependent on the value of sweat induced skin moisture. The skin detection are represented by different name that are Galvanic Skin Response (GSR), Electro dermal Response (EDR), Psycho Galvanic Reflex (PGR), Skin Conductance Response(SCR) and Skin Conductance Level (SCL). The skin conductance can compute the emotional and sympathetic response. The exact difference between the galvanic skin resistance and galvanic skin potential is represented the term of Galvanic Skin Response (GSR). The GSR identify as a recorded electrical resistance between two electrodes when a fragile current passed between them. The electrodes are sited about the inch separately, and recorded resistance is modified with respect to emotional state of the user. The Galvanic skin potential represented to the computed voltage between two electrodes without any externally applied current. The compound modification between galvanic skin resistance and galvanic skin potential make up the galvanic skin response. The skin conductance response is the component of that is represented to fast changing signal element. The measurement of the skin conductance level is based on the amount of continuity over time(tonic value) and skin conductance response which is represented to change in sc with in short duration of time as reaction towards a discrete stimulus. The SCR is the good measurement of stress, anxiety, fear and anger. The non specific SCR fluctuations that occur spontaneously with any internal stimulus and the SCR can be classified according the working of four parameters like amplitude, latency of response onset, rise time of the response peak, and half recovery time. Both SCL and SCR and the Bayesian NN for pattern recognition use first absolute difference. Their system comprised of HR, SC and driving habits. The Galvanic Skin Response GSR or Electro dermal Activity is perform modification in human skin conductivity (resistance) under different psychological situations. There is no a perfect solution for skin