Acoustic emission (AE) based algorithms have been employed to distinguish different damage scenarios that are evolved in the reinforced concrete T-beams submitted to four-point bending tests. The study aims at evaluating the efficiency of different parameters, namely average frequency (AF), RA-value, b-value, etc. in the identification of various damage mechanisms. Although the algorithms are different and may use different AE-feature/s, however able to identify the change in the damage mechanisms by showing a corresponding change in their respective indices. For instance, AE features used in average frequency (AF) and RA-value are different, however these two algorithms separately able to distinguish the stages of tension type cracking from shear type cracking, effectively. This work shows also that the different b-value algorithms can distinguish occurrence of micro- damage and macro-damage cases. On the other hand, results show that a higher rate of acoustic activities correspond to a higher value of the inter‐event time function. Since the inter-event time function only uses the time information of the detected AE hits, a new index normalized index (i.e., Indexnorml) on the base of the AE hits as well as their energy and amplitude. This new index is found to be very effective in the monitoring of damage stages. The AE data are also analyzed using machine learning (ML) algorithms with a view to cluster them and fruitful results have been obtained.