Material process in grinding involves three phenomena namely: rubbing, ploughing and cutting. Rubbing and ploughing, which usually occur before or after cutting, essentially mean the energy is being applied less efficiently in terms of material removal. It is therefore important to identify the effects of these different phenomena experienced during grinding. To identify the different phenomena, two channel Acoustic Emission (AE) signals were extracted by two AE sensors which would give verified energy information relating to the horizontal groove profile in terms of the material plastic deformation and material removal. With the use of a Fogale Photomap Profiler, accurate material surface profile measurements of the cut groove would be made and compared against the corresponding AE signal scratch hit data. A combination of filters, Short-Time Fourier Transform (STFT) would provide the salient components for comparison and classification of the three different levels of Single Grit (SG) processing phenomena. Verified classification was achieved from both Neural Networks and Fuzzy-c Genetic Algorithm Clustering Techniques and is discussed in the second part of this work.