For a particular section of a road network, there are multiple sources of quantitative and qualitative traffic information. Quantitative sensors are usually hardware-based, including loop detectors and GPS devices that produce numerical data. Qualitative sensors are usually processed data, including the traffic department's websites and radio broadcasts that produce subjective categorical data based on hidden processes. Each sensor is characterized by a specific level of error and sampling frequency. It is a challenge to combine and utilize multiple sources of data for estimating real-time traffic conditions. By using Single-Constraint-At-A-Time (SCAAT) Kalman filters, this paper combines multiple data sources from a section of a highway. However, in real-life, true traffic conditions are unknown because all sensors have associated errors with them. A micro-simulation package is used in order to have access to the true traffic conditions of a simulated environment that has been calibrated for a particular road section in Toronto. Then, the performance of predictions made by the developed SCAAT filters are compared with the true traffic conditions under different sampling strategies with varying number of probes and varying sampling frequencies. SCAAT filters are found to be effective for fusing the data and estimating current traffic conditions.