Stress is typically characterized as a disruption in emotional homeostasis. Stress awareness is an essential study subject in bioengineering because good stress detection may easily avoid many psychophysiological disorders such as heart rhythm irregularities or arrhythmias. There are various bio-signals accessible (for example, EEG, ECG, EMG, breathing rate, GSR, and so on) that may be used to determine stress levels since these signals exhibit typical changes when stressed. For this project, we will analyse the ECG signal. The key candidate's ECG signal, available recording (i.e., various mobile effective functioning recorders are currently on the market), and ECG extracting features algorithms. Additional benefit of ECG is that breathing signal characteristics may be identified from it, which is termed as EDR (ECG derived Respiration), without the need for a separate various sensor for expiratory measurements. The characteristics of ECG signals are unique, and signal collection is cost-effective. A number of machine learning models such as SVM, NB, RF, DTC, and KNN are used to predict, and each classification algorithm is fine-tuned by model parameters before predicting if the data is stressing or healthy. Google Collab may be used for the whole development. © 2024 Elsevier B.V., All rights reserved.