Mental stress is a significant factor in the development of a wide variety of psychological, emotional, behavioral, and physical illnesses. It is critical to accurately quantify mental stress, which needs reliable neuroimaging to monitor stress levels. In this work, we used a modified Stroop Color Word Task (SCWT) with time constraints and negative feedback to elicit two distinct degrees of stress in the workplace. We then used salivary alpha amylase (SAA) concurrently with functional near-infrared spectroscopy (fNIRS) to quantify the level of stress. We propose Long Short-Term Memory (LSTM) to decode the two classes of mental stress based on the fNIRS time series. Five-fold cross validation, two LSTM layers, as well as many trainable characteristics were used to construct the network. The induced mental stress increased the level of salivary alpha amylase significantly (p<0.001) by 32.09%. Likewise, we found that LSTM classified mental stress with an average accuracy, sensitivity, and specificity, equal to 72.5%, 72%, and 73% respectively. The findings indicated that the developed LSTM could be used to effectively classify mental stress using fNIRS time series.