In this paper, we tend to think about the matter of following fine-grained speeds variations of vehicles victimization signal strength traces from GSM enabled phones. Existing speed estimation techniques victimization mobile signals will offer longer-term speed averages however cannot track short speed variations. Understanding short- term speed variations, however, is very important in a very form of traffic engineering applications—for example, it should facilitate distinguish slow speeds thanks to traffic lights from hold up when collecting real time traffic information. Using mobile phones in such applications is especially enticing as a result of it is without delay obtained from an oversize range of vehicles. This approach is based on the observation that the big scale path loss and shadow weakening parts of signal strength readings (signal profile) obtained from the mobile on any given road phase seem similar over multiple visits on constant road phase apart from distortions on the time axis thanks to speed variations. We therefore propose a speed tracking technique that uses a Derivative Dynamic Time Warping (DDTW) algorithm to realign a given signal profile with a known training profile from the same road. The speed following technique then interprets the deformation path (i.e., the degree of stretching associate degrees compression required for alignment) into a calculable speed trace. Using 6.4 this of GSM signal strength traces collected from a vehicle, we tend to show that this rule will estimate conveyance speed with a median error of ±5mph compared to employing a GPS and might capture vital speed variations on road segments with a exactness of sixty eight and a recall of eighty this.