Epilepsy, a widespread neurological disorder, creates substantial physical and psychological challenges for patients. Accurate seizure prediction allows for prompt symptom intervention and treatment guidance. To achieve this goal, we introduce a classification model for epilepsy using variational mode quadratic decomposition. It first processes EEG signals from epilepsy patients with variational mode decomposition. Then, a second variational mode decomposition filters and breaks down the residual signal further. After decomposition, signals are reconstructed into continuous wavelet transform feature images. A combination of convolutional neural network and temporal convolutional network then classifies epileptic seizure periods, including ictal, preictal, interictal, and non-ictal phases. The extensive experimental results show the model reaches 85% accuracy and 88.8% precision in classifying epileptic seizure, pre-ictal, inter-ictal, and non-ictal periods, evidencing the proposed method's effectiveness.

Over time, repeated mouse-dragging manipulation may cause discomfort in the upper extremities. This study compared biomechanical parameters, mouse movement data, and the discomfort perception index between 2-min mouse dragging and moving manipulation tasks with higher or normal target objectives. We recruited 20 non-symptomatic graphic design students who frequently engage in intensive mouse-dragging manipulation. We assessed the impact of continued dragging versus non-dragging manipulation using electromyographic data, mouse fingertip pressure data, and mouse trajectory velocity data. We also performed a temporal correlation analysis between EMG, mouse velocity, and fingertip pressure to investigate the relationship between physiological data and mouse movement performance. The study revealed significant differences between the dragging and moving tasks regarding muscle activity, mouse velocity, and fingertip pressure. In particular, the percentage of muscle activation on the right side of the extensor carpi radialis longus (ECR) and the lateral head of the triceps brachii (TB) differed significantly between the two tasks, with higher muscle activation levels during the dragging task. Moreover, the average muscle activation of ECR and TB was significantly higher at high target operation levels. In addition, the study revealed that the horizontal, vertical, and mean mouse velocities were significantly higher for the dragging manipulation in the high target task than for the mouse moving manipulation. In the temporal correlation analysis, the correlation coefficients of muscle activation, fingertip pressure, and mouse mean velocity differed between the two mouse manipulation behaviors, with a higher correlation between muscle activation levels and pressure values during the dragging manipulation.

With the proliferation of shape-change research in affective computing, there is a need to deepen understandings of affective responses to shape-change display. Little research has focused on affective reactions to tactile experiences in shape-change, particularly in the absence of visual information. It is also rare to study response to the shape-change as it unfolds, isolated from a final shape-change outcome. We report on two studies on touch-affect associations, using the crossmodal “Bouba-Kiki” paradigm, to understand affective responses to shape-change as it unfolds. We investigate experiences with a shape-change gadget, as it moves between rounded (“Bouba”) and spiky (“Kiki”) forms. We capture affective responses via the circumplex model, and use a motion analysis approach to understand the certainty of these responses. We find that touch-affect associations are influenced by both the size and the frequency of the shape-change and may be modality-dependent, and that certainty in affective associations is influenced by association-consistency.