IRANIAN JOURNAL OF BIOMEDICAL ENGINEERING
Year:2015 | Volume:8 | Issue:4|Papers Count:9

In recent years, Brain-Computer Interface (BCI) has been noted as a new means of communication between the human brain and his surroundings. In order to set up such a system, the collaboration of several blocks, such as data recording, signal processing and user interface are needed. The signal processing block, includes two units of preprocessing and pattern recognition. Pattern recognition block itself involves two phases: feature extraction and classification. In this paper, the sparse representation based classification (SRC) has been used in the classification block. There are two important issues in using the SRC. These are creating an appropriate dictionary matrix and adopting a proper method for finding the sparse solution for an input data. In this research study, the dictionary matrix is formed by extracting an optimal set of features from the training data. Toward this goal, the common spatial patterns algorithm (CSP) is first used. Sensitivity to noise and the over learning phenomena are the main drawbacks of the CSP algorithm. In order to remove these problems, the regularized common spatial patterns algorithm (RCSP) is employed. In previous studies in within the BCI framework, the standard BP algorithm has been used to find a sparse solution. The main disadvantage of the BP algorithm is that the method is computationally expensive. To overcome this weakness, a recently proposed algorithm namely the SL0 approach is used instead. Our experimental results show that when the number of training samples is limited, the RCSP algorithm outperforms the CSP one. Using the features derived from the RCSP, the average detection rate is in average increased by a factor of 7.53 %. Our classification results also show that using the SL0 algorithm, the classification process is highly speeded up as compared to the BP algorithm while an almost equivalent accuracy is achieved.

IVUS imaging is a minimally invasive blood vessel cross-sectional imaging procedure in which accurate data is obtained from what is in there. Processing on these images or raw signals can provide a wide range information for experts and practitioners, and can help them in making an accurate diagnosis and appropriate treatment. Extraction of tissue boundaries in the blood vessels is one of the challenging part as a first step in this direction. In this paper a new method was proposed based on the minimax technique and connected components for extracting Adventitia tissue boundary in intravascular ultrasound images. For this purpose, initial boundary will be extracted using improved minimax technique. Then final boundary is extracted with high precision using a connected components. The method was tested on a set of real data with regard to the Hausdorff distance and Jaccard index to evaluate its performance. Mean of Hausdorff distance and mean of Jaccard index were obtained 95% and 0.45 millimeter, consequently. These results show that the proposed method in this paper can extract Adventitia tissue boundaries more accurately than existing methods with regard to the distance Hausdorff distance and Jaccard index.

In this study, we propose decision level fusion of multimodal physiological signals to design an affect identification system using the MIT database. Four types of physiological signals, including blood volume pressure (BVP), respiration rate (RSP), skin conductance and facial muscles activities (fEMG) were utilized as affective modalities. To collect the above-mentioned database, researchers used personalized imagery to elicit the desired affective states from a single subject and recorded the corresponding physiological signals simultaneously. In this study, the best subset of features for each signal was determined using previously calculated time and frequency domain features. To this end, sequential floating forward selection (SFFS) and RELIEF feature selection algorithms were evaluated. A new feature set, formed by concatenating the selected features, was partitioned into three subsets. Each subset was then fed into a classifier to identify the desired affective states. The majority voting method was applied to fuse the results obtained by the subsystems. Three types of classification methods, namely SVM, LDA and KNN were evaluated to design an affect identification system. The results showed remarkable performance from the system in identifying the desired scenarios with an acceptable accuracy and speed of response. Using the RELIEF feature selection method, along with SVM as a classifier, an overall recognition accuracy of 93.8% was obtained, which is better than the results reported with the use of the above-mentioned database so far.

Constitutive model of passive myocardium of lamb: Experimental tests and equations on the continuum mechanics are used in order to obtaining the constitutive models of soft tissue using in predictive heart simulation. Considering the myocardium as one of the important tissues, in this paper first the morphology and structure of myocardium has been reviewed and the mechanical response of passive form of this tissue has been investigated. The myocardium of left ventricle was considered as non linear elastic, in-compressible and non homogeneous material and using of bi-axial test in 3 lambs myocardium on fiber direction; a constitutive model of this tissue has been proposed. The model so constructed is then evaluated against the biaxial data, and values of the material constants have been obtained by curve fitting so the final model states the strain-energy function as cauchy's invariants which can be helpful in heart simulation.

Human visual system operates superior than best machine vision systems in object recognition. So, researchers in machine vision and neuroscience try to model human visual system in order to employ it in machines. HMAX is one of the best operating models in this area. It is based on the function of brain cells in the ventral stream of visual cortex and contains four computational layers. In the learning stage, many image partitions called image patches are extracted randomly with different sizes from training images. This random selection of image patches is one of the drawbacks of HMAX which decreases the performance and increases the computational complexity of the algorithm. In this paper, a novel patch selection from the set of random patches is proposed. In this method, using a recursive approach, optimal patches are selected from optimal features of training images by mutual information maximization feature selection. The performance of proposed algorithm in binary classification (existence or non-existence of objects in the images) is compared with HMAX and the superiority is proved.

The aim of this research is a preparation of a system based on mesoporous silica nanoparticles (MSN) for delivery of Rivastigmine hydrogen tartrate and study of the system cytotoxicity, with or without drug, on the human brain neuroblastoma cells (SY5Y). Rivastigmine is a hydrophilic and hydrophobic drug which is used for treatment of Alzimerʾs disease. In this study MSN were synthesized and characterized by scanning electron microscopy, transmission electron microscopy, Fourier transform infrared spectroscopy, x-ray diffraction, N2 adsorption isotherms, and z-potential analysis. Results showed that all MSN were spherical with the same structure. The mean size of nanoparticles was 100±13 nm and the mean diameter of pores was 2.15 nm. The loading capacity and efficiency of rivastigmine hydrogen tartrate were obtained 20.88, and 25%, respectively. Release of rivastigmine from nanoparticles in the simulated gastric and body fluid during 24 h were obtained 70.5 and 79.6%, respectively which was shown the slightly fast release of rivastigmine in simulated gastric fluid. The cytotoxicity effect of nanoparticles with and without rivastigmine was done by MTT assay on SY5Y cell lines. Results showed that the in vitro rivastigmine release from the nanoparticles containing of it exhibited the more treatment property as free rivastigmine on SY5Y.

In this study, we fabricated 3-dimentional PLGA-gelatin scaffolds with aligned-oriented pores by freeze casting technique which is similar to Extra Cellular Matrix (ECM), and evaluated its effect on both physical and mechanical features. Dissolving synthetic (PLGA) and natural (Gelatin) polymers in common solvent was one of the strengths of this investigation. Scanning electron microscopy (SEM) micrographs indicated that scaffolds contained 95% interconnected pores with diameter about 50 - 400 µm in horizontal direction and 50 - 200 mm in vertical direction. Moreover, the results of mercury intrusion porosimetry represented diameter of pores in range of 100 – 300 mm. According to fourier transform infrared (FTIR) spectrum there was no inappropriate interactions during processing. Additionally, mechanical analysis (3.2 MPa) of PLGA-gelatin constructs illustrated that polymeric scaffolds can withstand mechanical loads in freezing direction. Based on the water absorption (950%) and biodegradation results, samples can support cellular interactions and prevent their integrity during tissue regeneration. In brief, freeze casted PLGA-gelatin scaffolds can provide unidirectional matrix with desired physical and mechanical characters to regenerate lesions.

Classification of distal limb movements based on surface electromyography (sEMG) of proximal muscles is an important issue in the control of myoelectric hand prosthesis. In most of previous studies, classification of a limited number of hand motions is investigated. In this paper, we have used NINAPRO database containing kinematics and sEMG of upper limbs while performing 52 finger, hand and wrist movements. We evaluated performance of LDA and LS-SVM with RBF kernel classifiers using different combination of features. First by windowing the signal with two different methods, the major part of the signal was selected and eight various temporal features (MAV, IAV, RMS, WL, E, ER1, ER2, CC) were extracted. Then performance of each classifier with single, double and multiple combinations of features was evaluated. For LDA classifier, the best average classification accuracy of 84.23% was achived for first windowing method and MAV (or IAV)+CC features, The corresponding accuracy for LS-SVM classifier with second windowing method and IAV+MAV+RMS+WL features, was 85.19%.