Air toxicity and pollution phenomena are on the rise across the planet. Thus, the detection and control of gas pollution are nowadays major economic and environmental challenges. There exists a wide variety of sensors that can detect gas pollution events. However, they are either gas-specific or weak in the presence of gas mixtures. This paper handles this issue by presenting method based on a Temporal-based Support Vector Machine for for the detection and identification of several toxic gases in a gas mixture. The considered gases are carbon monoxide (CO), ozone (O 3 ) and nitrogen dioxide (NO 2 ). Furthermore, an incremental algorithm is proposed in this paper for the selection of the best performing kernel function in terms of accuracy and simplicity of implementation. Then, a decision-making algorithm based on the rate of appearance of a class on a moving window is proposed to improve decision making in presence of uncertainties. This algorithm allows the user to master the false-alarms and no-detection dilemma, and quantify the level of confidence attributed to the decision. Experimental results, obtained with different gas mixtures, show the effectiveness of the proposed approach with 100% of accuracy in the learning and testing stages.