Central Sleep apnea is a serious condition that affects many individuals and is associated with severe health complications. During sleep, people with this condition stop breathing because the signals in the brain that tell the body to breathe don't work properly. There is no effort is made to inhale and chest movements almost come to a standstill. Central Sleep apnea is associated with a number of different neurologic problems, as well as heart or kidney failure. Existing medical sleep measurement systems are costly, disturb sleep quality, and are only suited for short-term measurement. As sleeping problems are affecting about 30% of the population ^[2] , new approaches for everyday sleep measurement are needed. This paper presents a simple, low cost measurement technique that involves use of a Force Sensing Resistor placed over the patient's chest to record chest movements and hence record the breathing signal. Analysis of the obtained Breathing signals using signal processing and machine learning algorithms possesses high potential for the noninvasive detection of central sleep apnea, which may reduce the need for uncomfortable sleep studies. The proposed method involves using Wavelet Transform based feature extraction, followed by classification using Least Square Support Vector Machine. A 95% true detection rate was obtained using the proposed method. Finally, a real time breathing monitoring and Central Sleep Apnea diagnosis system is built using the proposed method.