IRANIAN JOURNAL OF BIOMEDICAL ENGINEERING
Year:2019 | Volume:13 | Issue:2 |Papers Count:9

Emotion is one of the most important human quality that plays an important role in life. Also, one way of communicating between human and computer is based on emotion recognition. One way of emotion recognition is based on electroencephalographic signal (EEG). In this paper, according to the non-stationary property of EEG, intrinsic mode functions (IMF) extracted by using empirical mode decomposition (EMD) and then first 3 IMFs selected. Each IMF converts into smaller pieces with a one-second window and power feature has been extracted from each piece. Then, by using a suitable mapping, the position of the electrodes in the 10-20 system becomes the position of the pixels in the picture. The extracted features are considered as pixel color components. To determine the class of valence, the set of all generated pictures is given as input to a deep learning network and output determine the high or low class of valence. The same process is used to determine the class of arousal. To examining the method, the DEAP dataset is used. By choosing 17×17 for the image size, the mean accuracy and standard deviation were obtained of 78. 58% and 3. 9 for the valence and 78. 66% and 3. 1 for the arousal which that shows a significant improvement compared to similar tasks.

Today, in order to decide on many cardiac surgeries, and whether the patient is able to get under surgery or the time of surgery is passed, it is necessary to measure pulmonary vascular resistance and if the resistance is above a threshold, the patient is considered to be non-surgery; and sometimes, some therapies are used to reduce the resistance of the pulmonary arteries to the initial disease of the arteries, in which, in order to track down the resistance of the pulmonary vascular, a re-measurement of this parameter is required. Currently, the golden standard of this measure is the use of catheterization procedures, which are aggressive and associated with complications. The purpose of this study is to replace a non-invasive method, rather than an invasive method of cardiac catheterization, by predicting pulmonary vascular resistance based on echocardiographic data by artificial neural networks. Research was performed on 591 patients. Echocardiography was recorded for all subjects, and the echocardiographic data (mPAP, dPAP, sPAP, PCWP, CO) as the neural network input and pulmonary vascular resistance of all patients who were subjected to previous catheterization was evaluated as the output of the neural network and thus, it was obtained, the relationship between echocardiography data and PVRcath. The proposed neural network was typically learned with 75% of the data, and was tested with 25% of the data, and these ratios were modified to better learn the neural network. As a result of implementation, the mean squared error, respectively, for the learning and testing data for the proposed neural network, was 0. 37 and 0. 27 for the first model, 14. 67 and 10. 76 for the second model, and 15. 82 and 9. 58 for the third model.

In this study, a neuromarketing project was conducted via EEG signal processing in which the individuals’ interest for buying a relatively luxurious decorative product (which has a relative advantage in exports based on commonly evaluated criteria and indicators in economic) was evaluated. EEG signals of 24 participants during observing and selecting gemstone images were recorded and processed in order to analyze statistical significance of brain activity variations involved in the emotional (liking) and the decision making (choosing) processes. The recorded signals during the stimulation and selection phases were pre-processed in several steps to remove the existing noises and artifacts. Then, the 19-channel EEGs were processed via multiple tools to indicate active brain regions while watching gemstones. Brain mapping and regional analysis indicated that the occipital>frontal>limbic regions were more activated than other regions. Moreover, the left hemisphere has been more active than the right hemisphere. At the next step, nonlinear entropy feature of each signal segment was extracted to be used for training a neurofuzzy system which is an automatic classifier that learns to classify the individuals’ choices. The classification has resulted in 86. 25% precision and 87. 4% accuracy in a three-class classification task (including two pleasant selections and one unpleasant selection). At the final step, using a questionnaire filled by participants following the recording session, a number of statistical analyses were performed over the self-conscious and unconscious by means of statistical tools including t-test, analysis of variance and regression. The results of statistical tests indicated that there are significant differences for the cognition of liking or preferring among different choices and based on the selections made by women and men. Furthermore, the lack of existence of a significant difference between conscious and unconscious choices were rejected.

Since electroencephalography (EEG) signal contains temporal information and fMRI carries spatial information, we can reasonably expect that a combination of the two contributes greatly to precise localization of epileptic focuses. With that in mind, we have first extracted spike patterns from outside of scanner EEG, through detecting and averaging the interictal epileptiform discharges (IED). Then, having implemented the correlation between the identified pattern and inside-scanner EEG, an automated system was developed to extract the temporal information when an epileptic seizure is triggered. We proceeded to convolve the obtained regressor with the hemodynamic response function (HRF) using the general linear model (GLM) for the purpose of localizing the epileptic focus. This study was conducted on 6 medication-resistant patients with epilepsy whose data was recorded in the National Brain Mapping Lab (NBML). The results of the proposed method are in line with the information provided in EEG for each of the 6 patients, and for the 4 patients who were candidates for brain surgery, they provided further information. The results suggest a significant improvement in localization accuracy and precision compared to existing methods in the literature.

Brain as the most complex organ in the human body has been investigated from various aspects. The greatest origin of this complexity is due to the fact that, despite the fixed architecture of brain structure (physical connections), the functional connectivity is in a constantly changing state, resulting to different behaviors. In many mental diseases, both brain structural and functional connectivities and their relationship are changed and cause different symptoms. Investigation of brain connectivity variations in the disease may help to better understanding of the relationship between brain structure and function. One of the most severe and debilitating brain disorders is Schizophrenia in which both brain structure and function are involved. Among all available methods, multimodal analysis of data has been recently gained great interest to provide the capability of extracting association between separate neuroimaging data. However, due to their voxel based viewpoint, relationship between brain connectivities cannot be inferred. In this study, the joint independent component analysis (jICA) has been proposed to investigate the relationship between brain functional and structural connectivity. We applied the suggested approach to combine functional and structural connectivity, in order to assess abnormalities underlying schizophrenic patients relative to healthy people. The findings suggest that the correspondence between brain function and structure is not necessarily one-to-one. The results also indicated that variations in several structural fibers, such as superior longitudinal fasciculus and inferior longitudinal fasciculus, are associated with functional changes in the temporal and frontal lobes. Besides, analyzing the nodal strength and shortest path length in the obtained subnetworks demonstrates that the functional subnetworks efficiency in parallel information transfer in schizophrenic patients is reduced. Overall, the outcomes point out the capability of the proposed method to better understanding of brain functional and structural connectivity association and its variations in brain disorders.

Cancer is a leading cause of death in the world. Mathematical and computer models may help scientists to better understand it, and improve current treatments. They may also introduce new aspects of therapy. In this paper, a Cellular Automata model of tumor by emphasizing on immune system is presented. Considering the spetio-temporal heterogeneity that is’ t considered in most mathematical models, is one of the novelity of this work. Each tumor cell in a square lattice can interact with both immune and normal cells in its Moore neighborhood. The rules for updating the states of the model are stochastic. Modeling tumor cells scaping from immune system and their survivance and considering immune system recurrement into the studied tissue is another innovation of this model. The results of our simulations are presented with/without considering immune system. The growth fraction and necrotic fraction are used as output parameters beside a 2-D graphical growth presentation. The results of this paper show that considering the heterogeneity will improve the compatibility of the model with biological reality and experimental studies. It can be seen that the number of immune cells increases during the tumor growth and follows the same dynamics as tumor cells. In this paper, we have innovatively focused on the effect of model parameters on different steps of tumor growth from the cancer therapy viewpoint.

According to the literature, changes in muscle activity patterns are considered as one of the causes of non-specific chronic low back pain. Recent studies have introduced muscle synergy as a valuable tool for analyzing how muscles work in body movements. In this way, a new study method is proposed for modeling the upper body and extracting time-varying muscle synergies in a flexural motion of the waist. In this way, a new study method is proposed for modeling trunk and extracting time-varying muscle synergies in-plane bending movements of lumbar flexion. Considering 18 effective muscles and function of the combined cost of the minimum jerk-energy, 24 different movements, and their corresponding muscle patterns have been simulated. To evaluate the role of velocity, the pattern of muscle activity was divided into two parts: tonic, to overcome the gravity force and phasic, proportional to the trunk movement velocity. In the following, three fast-reaching times of 0. 75, 1, and 2 seconds were considered for each direction. The results showed that 77% of the lumbar muscle pattern of movement was achieved by four phasic synergies and four tonic synergies. The resulting synergies are quite influenced by the movement direction and velocity so that each pair of phasic and tonic synergy is most effective in one of the main directions. On the other hand, the increase in velocity causes elevated amplitude coefficient and accelerated the activation of phasic synergies compared to normal mode. Considering the 45 ° flexion combination with 30 ° left lateral bending, 77. 2% of the muscle pattern of movement has been reconstructed using time-varying synergies. It can be argued that the use of muscle synergies expresses a good explanation for how muscles work in the movement in different directions and velocities.