eng Oriental Scientific Publishing Company Biomedical and Pharmacology Journal 0974-6242 2026-09-30 19 3 2379 2386 10.13005/bpj/3500 73350 article Thota Apparao 1 Hiren Kumar Mewada 2 Lingala Syam Sundar 3 Department of Chemistry, University of Aveiro, Aveiro, Portugal. Department of Electrical Engineering, College of Engineering, Prince Mohammad Bin Fahd University, Al Khobar, Saudi Arabia. Department of Mechanical Engineering, College of Engineering, Prince Mohammad Bin Fahd University, Al Khobar, Saudi Arabia. Brain’s electroencephalograms (EEG) signals, which represent human actions, are a crucial stage in human-machine interaction. It is essential to develop user-machine interfaces that are dependable, robust, and affordable. Complex and computationally intensive methods were formerly necessary to accurately classify brain signals. This study presents a classification of hand movements using the brain’s EEG signals with reduced computational complexity. A novel approach of integrated RandOm Convolutional KErnel Transform (ROCKET) and ridge classifier (RC) was proposed for feature extraction and classification. Brain signals associated with three hand movements left, right, and up are classified using the proposed model. The proposed algorithm achieves an accuracy of 89.53% with precision scores of 98.93%, 96.82%, and 91.67% for the three movements. The comparison with state-of-the-art models shows that the proposed model improves classification by 19.93% compared to the base model of the LSTM network.  Simple linear classifiers integrated with ROCKET can attain high accuracy while minimizing computational complexity. It is illustrated how the proposed method can classify brain signals with minimal parameter adjustment needs, presenting a viable solution to the human brain and machine interface. https://biomedpharmajournal.org/vol19no3/electroencephalograms-eeg-signal-based-hand-movements-classification-for-human-brain-interface-using-random-kernel-convolutional-filters/ Electroencephalograms Health-care Human-brain interface Human-machine interface Machine learning