Volume 12, 2018
Title of the Paper: Speedy’O’Brain: a Neuro-Feedback Videogame Driven by Electroencephalographic Signals
Authors: Luigi Bianchi
Abstract: In this manuscript, a simple videogame driven by electrical brain activity is described. It was designed to train people to improve their ability to maintain a high degree of concentration for some tens of seconds and to be calibrated in few minutes. It is hosted on a PC running Microsoft Windows and can be combined with several commercially available EEG systems because a simple TCP/IP based communication protocol is used to receive data from them. Preliminary results show that it can be used even in a very noisy environment and that users can be able to operate it after few minutes and by using just 4 sensors. This means that it could be of great help to people that suffers for several different diseases such as Attention Deficit Hyperactivity Disorder, epilepsy, depression, schizophrenia, dementia and even in stroke patients as it was shown in several previous works that neuro-feedback could improve their quality of life.
Title of the Paper: A Computational Method that Uses Protein Structures to Detect Horizontal Gene Transfer
Authors: Peter Z. Revesz, Swetha Billa, Mark A. Griep, Venkat R. B. Santosh
Abstract: No current method to detect Horizontal Gene Transfer (HGT) events between organisms is accurate in all cases. This paper presents a novel computational method that uses protein structures to detect HGT. The use of protein structures instead of protein sequences increases the accuracy of our method. The new method uses Z-score similarities between the protein structures and DaliLite to search efficiently for similarities in both protein sequences and structures. In addition, the java viewer tool Jmol is used for visual structural comparisons and sequence alignment. The experimental results include six previously unreported cases of HGTs between various Firmicutes and Proteobacteria bacteria. Various methods of handling false positives are also described.
Title of the Paper: Prevalence of Intestinal Parasites in Children of an Invasion Community in a Municipality of Colombia
Authors: Beatriz Giraldo-Ospina, Paola-Andrea Fontal-Vargas, Diego-Fernando López-Muñoz, Leonardo Beltrán-Angarita, Viviana Morales-Jiménez, María-Nohemy Gómez
Abstract: According to World Health Organization, (WHO), intestinal parasites are present in one in four people, estimated that these agents constitute the 15% burden of disease in the Americas caused by neglected infectious diseases. To determine the prevalence of intestinal parasites in the “La Carrilera” invasion community Tuluá-Valle del Cauca. Cross-sectional study, the included boys and girls were part of an induced demand program using a sample of 150 children. The parasitological analysis was performed with saline solution, Lugol, formalin-ether concentration and Graham’s method. For the assessment of the nutritional status, standards of the WHO were taken as reference with the use and interpretation of the Anthro and Anthro Plus software. The overall prevalence of enteroparasites 93.3%. The cases of monoinfection and polyparasitism were presented with 38% and 55.3% respectively. The pathogenic enteroparasites found according to their frequency predominated Blastocystis and Giardia duodenalis. The group of 6 to 10 years had higher percentages of pathogenic parasites Entamoeba Complex 19.5%, Ascaris lumbricoides 15.9%, Enterobius vermicularis 15.9%, Trichuris trichiura 6.1%. Among the non-pathogenic protozoa were Iodamoeba bütschlii 18%, Entamoeba coli 24.4%, Endolimax nana 30.5%, corresponding to this group since it is the one that presents the highest risk of suffering infections by protozoa and geohelminths. There is an association between parasitic infection in subjects with a BMI of 16.3 ± 4.5 and a statistical significance of p <0.001. High prevalence was found, surpassing that found in other studies.
Title of the Paper: Analysis of Brain Waves According to their Frequency
Authors: Z. Koudelková, M. Strmiska, R. Jašek
Abstract: The primary purpose of this article is to show and analyse the brain waves, which are activated during different activities. At the first part of the paper, we describe the theoretical information about Brain-Computer Interface and the types of this technology. The article mainly focuses on the non-invasive Brain-Computer Interface, which is used in the experimental part. Experimental part is based on EEG technology, which is represented by devices from Emotiv System. This article provides the measurement with the Emotiv EPOC headset and the application Emotiv Brain Activity Map. There are used two type of analysis. The first type of measure engaged logical-analytical reasoning by solving the mathematical exercise. The second type is a dedicated relaxed mind during listening to relaxing music. At the last of the paper, we display the result as the visualization of brain activity. There are shown the brain waves, which are activated in each situation.
Title of the Paper: Better Classification of Pathological Tissue Classes from EIS Data of Breast Tissue
Authors: Hyontai Sug
Abstract: Electrical impedance spectroscopy (EIS) is an important technique to collect data from pathological tissue of breast tissue, and data mining algorithms are used to analyze and diagnose pathological tissue classes from the measured data. In order to build accurate data mining models the diversity and size of data are very important because such properties can make the trained data mining models cover more unseen cases. Neural networks and decision tree based machine learning algorithms are widely accepted for the related data mining task because of their robustness in errors and comprehensibility respectively. In order to confirm the diversity and size in data are important factors in the performance of machine learning algorithms experimentally, multilayer perceptron (MLP) and random forest algorithms are selected and used. A real world data set called breast tissue which consists of six classes and continuous attributes only was used. Over-sampling algorithm called SMOTE was applied for all classes in the data set to generate more diverse data. But, some of the over-sampled data may have wrong class values due to the property of the algorithm, so that those data instances may hinder our data mining task, because these instances may cause lower accuracy of our final data mining models. In order to avoid such things happen MLP and random forest are used to check the class of each training instances, and the class values were changed if the two algorithms generate the same result for the artificial instances whose original class values are different from the classification of the two algorithms. Extensive experiments using breast tissue data set in various over-sampling rates showed very good results.
Title of the Paper: Identification of Contact Angle and Heterogenity Detection in Tactile Images
Authors: Dmitriy E. Alexandrov, Stepan A. Nersisyan
Abstract: Introduction. Automated analysis of tactile images registered by specialized medical tools is a novel domain, which results promptly find their applications in clinical practice. Medical Tactile Endosurgical Complex (MTEC) is currently the only commercially available device for intraoperative instrumental mechanoreceptoric palpation. One of the main challenges related to processing data generated by MTEC is heterogeneity detection in tactile images. This problem is highly important because it is a key step of localization of visually undetectable pathologies using instrumental palpation. Objectives. One of the main difficulties related to the problem of heterogeneity detection is a possibility to vary contact angle between mechanoreceptor and sample during tactile examination, so the aim of the research was to develop a method for automated contact angle identification and detection of heterogeneity in tactile images registered by MTEC. Methods. The proposed method of a tactile press contact angle estimation is based on classification with a specifically designed feature space. For heterogeneity detection we developed two different approaches. The first one is based on separation of heterogeneity detector into several components corresponding to similar contact angles. The second approach uses standard classification approach with contact angle as a high weighted element of the feature space. Results. Validation on a set of samples modeling normal tissues and pathologies showed high accuracy for contact angle identification. Both methods of heterogenity detection provided approximately the same accuracy clearly outperforming previously available methods in case of significant deviations of a contact angle from zero. Conclusion. The methods developed provide an accurat solution for problems of contact angle identification and detection of heterogeneity even in case of significant contact angle deviations, and such deviations are unavoidable in clinical practice, especially in minimally-invasive surgery.
Title of the Paper: The Evaluation Module of the Crisis Preparedness for the Hospitals
Authors: Katerina Vichova, Martin Hromada
Abstract: This paper is focused on the evaluation module of the crisis preparedness for the hospitals. At the first part of the paper, we describe the situation about security threats and crisis preparedness of the hospital. Based on this introduction we can say, that there is no evaluation system or tool, which evaluate the crisis preparedness of the hospital in times of crisis. In this paper, we assess the selected hospital and their crisis preparedness in the area of the emergency supplies. At the last of the paper, we propose a new evaluation module of the crisis preparedness for the hospitals. This part shows a few diagrams of how the module could evaluate. There is the part with the feedback – hospital, and supplier. At the end of the paper is the discussion about the crisis preparedness.
Title of the Paper: The Use of Information Systems in the Hospital in Times of Crisis
Authors: Katerina Vichova, Martin Hromada
Abstract: There is increasing number of crisis in the world and we need to support hospital preparedness in this time. The crisis preparedness of the hospital is different and we need the hospital to be ready for all situations. In many fields are used information systems and in the hospital too. These systems are used in peaceful state and in the crisis state. There is the action plan of the electronic health system in the European Union and in the Czech Republic too. this plan creates support for further electronisation of healthcare. This paper is focused on the use of information system in the hospital in times of crisis. There was used the analysis of the selected system. At the end of this article we propose the new algorithm for the evaluation of the crisis preparedness of the hospital.
Title of the Paper: Using Classification to Determine whether Personality Profiles of Countries Affect Various National Indexes
Authors: Emine Yaman, Azra Musić – Kılıç, Zaid Zerdo
Abstract: Nations are consisted of individuals, which makes it natural that these individuals affect a nation’s social structure. The effect is stronger when large groups of like-minded people are present. In this paper, we analyze do personality types, according to the MBTI theory, affect various national indexes, such as the Human Development Index (HDI), GDP per capita, Gay Happiness Index (GHI), religiosity, democracy index, etc. This is done by using four different classifiers that try to classify a country in every index provided. A few other datasets, such as the population in 1998 and surface area of a country, are used as reference points of classifiers with low classification rates. Results show that classification is possible using the national personality profile. The highest classification rates are connected with the GHI and average IQ of a country, while the lowest is scored with the reference datasets and the military budget per capita index.
Title of the Paper: The Dynamics of Thalassemia Management in the United Arab Emirates
Authors: Hamda Al Dhaheri, Sehjeong Kim, So-Yeun Kim
Abstract: We consider a genetic disease called Thalassemia. Thalassemia is a genetic blood disorder caused by abnormal hemoglobin. Hemoglobin is a composite of proteins in red blood cells that carries oxygen and is made of two proteins from four alpha-globin genes and two beta-globin genes. Individuals with thalassemia have defects in one or more of such genes. The treatment of thalassemia requires a life-long blood transfusion and removal of excessive iron in the blood stream from the frequent blood transfusion. These life-long treatments demand a strong personal commitment and a constant supply of blood stock that leads to a high medical cost, which can be a burden on a health care system in some countries like the United Arab Emirates. To reduce thalassemia major population, various forms of thalassemia control measures have been used and hence, the substantial reduction of thalassemia major population has been achieved. However, the prevalence of thalassemia carrier population still remains high, which leads to a potential growth of thalassemia major population through carrier-carrier marriages. Thus, in this paper, we investigate a long term effectiveness of thalassemia control measures. We develop a mathematical model including three age groups and thalassemia control measures, and analyze the stability of two types of equilibrium points that reflect the eventual status of thalassemia prevention. Through the stability analysis of the two types of equilibrium points, we reveal that control measures are positively effective only in the short term to reduce the prevalence of the disease but not enough to eradicate thalassemia in the long term. We illustrate our stability results via computer simulations by using the demographic data of the United Arab Emirates.
Title of the Paper: Comparison of the SVM Classification Results Between Original and DWT Denoised Respiratory Signals Considering to the Transients Noise
Authors: Igor Mazic, Anamaria Bjelopera, Luka Strazicic
Abstract: Asthma and COPD are the most common breathing diseases nowadays. Analysis and processing of breathing records are important diagnosis tools. This paper compares efficiency results of SVM classification of two classes: first the breathing noise and second the pause of signal samples recorded on subjects in real-life clinical conditions. In these conditions there is an appearance of noise and short impulse signals (transients) which are in this paper reduced by using DWT and different thresholding techniques to see if the denoised signal samples give better validation results. Classification results show that the best results are obtained when energy, Renyi entropy and standard deviation are taken as features for SVM classification. Testing of data revealed that original signal samples give better results of accuracy than the denoised signal samples.
Title of the Paper: Combined Nested PCR and High Resolution Melting for the Screening of Cryptosporidium Parvum
Authors: Elena Hatalová, Alexandra Valenčáková
Abstract: The aim of this study was focused on the capability of HRM (high resolution melting) analysis with the use of combined nested PCR for Cryptosporidium GP60 gene amplification in distinguishing positive, false-positive, negative and non-specific amplifications based on the melting curve structure and Tm difference. From 12 samples, successful amplification was seen on gel electrophoresis in 9 samples, one sample showed two bends and the other two samples were negative. Comparing result from electrophoresis with melt curve genotyping and Tm calling shown that all samples positive on gel electrophoresis had a same structure of the melting curve, with a temperature difference within 0.52 °C range (max = 86.74 °C; min = 86.22 °C, average 86.34°C). On the other hand, samples, where no amplification occurred, had different structures of melting curves with a different Tm (approx. ± 1 °C in comparison with an average of positive samples). Sample with double bands on gel electrophoresis showed two different melting domains with a temperature shift from average. We have concluded that the size of the GP60 final amplicon (450 base pairs), although larger than those commonly used for melting curve analysis, can be used as a screening tool for distinguishing samples positive for Cryptosporidium parvum.
Title of the Paper: A Modelling Technique for Controlling the Spread of Tuberculosis
Authors: O. P. Ogundile, S. O. Edeki, S. O. Adewale
Abstract: In this paper, a new modelling technique is considered for the study of tuberculosis and its spread. The model serves as a means of controlling the spread of tuberculosis. The mathematical analysis of the model equations is carried out to investigate the transmission dynamics of the disease. Also, solutions on how to reduce the spread of the disease in the community is proposed, and some simulations are performed to determine the consequence of the effective contact rate for Tuberculosis infection. Three hypothetical cases are considered and it is discovered that as the effective contact rate increases, the contact rate also increases. Results are illustrated graphically with the aid of MATLAB mathematical software.
Title of the Paper: Lipid Metabolism and Functions of Pituitary-Thyroid Axis in Children with Arterial Hypotension
Authors: Anatoly V. Sikorsky, Menizibeya O. Welcome, Vladimir A. Pereverzev
Abstract: The aim of this study was to investigate the features of lipid metabolism and the functions of pituitary-thyroid axis in primary school children with arterial hypotension. A total of 416 primary school children were involved in the study. Of these, 113 children had primary arterial hypotension (PAH); 111 children had symptomatic arterial hypotension (SAH), which developed on the background of chronic gastroduodenal pathology; 104 children had chronic pathology of gastroduodenal zone without arterial hypotension (conditional control); 88 were healthy children of comparable age and sex. The determination of lipidogram indices was carried out on a biochemical analyzer “RANDOX kits” and computation of atherogenic indices. The level of hormones of the pituitary and thyroid glands was determined by the method of immunoradiometric analysis. Children with SAH, which arose on the background of chronic pathology of the gastroduodenal zone, compared with healthy children, had dysfunction of the thyroid gland with a decrease in the levels of free and bound thyroxine in blood and dyslipidemia with predominance of atherogenic over antisclerotic factors. Children with SAH also had more pronounced disorder of thyroid function and lipid metabolism than children of the conditional control who had isolated form of chronic gastroduodenal pathology. In conclusion, the results of this study indicate that children with any form of arterial hypotension (PAH or SAH) have the similar disorders of lipid metabolism and thyroid function, which predispose them to early atherosclerotic process.
Title of the Paper: Time-Frequency Integration of Variable-Bandwidth Signals and Supplementary Data Packets
Authors: Piotr Augustyniak
Abstract: Integration of multimodal measurement signals is necessary for extending the experiment scope, for avoiding accidental data or synchronization loss or for building authorization-dependent data supplement. Instead of signal modulation or packet transmission widely used in such cases, we propose using of efficient watermarking technique based on the bandgap occasionally appearing between the instantaneous bandwidth of the signal and the Nyquist frequency. Usage of the method requires anticipating studies of the carrier (i.e. main signal) to determine band limits and a confident detection method of its components. Resulting statistics lead to a signalspecific standardized instantaneous bandwidth function. The method starts with detection of signal components, estimating the expected local bandwidth and measuring of noise properties in the bandgap. The supplementary data are tailored and packetized as so mimic the noise, therefore are not interfering with the carrier message and not conspicuous for an unauthorized reader. Finally an individual description of each packet is made and encoded with optional encryption. As long as the total data streams volume does not excess the channel throughput, the proposed integrating uses the carrier’s original transmission channel (with no carrier delay) and data storage structures. The research was showcased by three applications of watermarking the ECG signal for its best methods for automatic components detection, best knowledge on physiological backgrounds and best documented annotated databases of reference records. Nevertheless, the results of our research will be applicable for any digital measurement series (signals) recorded in biology and industry in which the instantaneous bandwidth could be estimated.
Title of the Paper: Signal Processing Methods of Diagnosing Alzheimer’s Disease Alzheimer’s Disease Alzheimer’s Disease Alzheimer’s Disease Using EEG – A Technical Review
Authors: Bibina V. C., Upasana Chakraborty, Mary Lourde R., Ajit Kumar
Abstract: Alzheimer’s is the most common form of Dementia prevailing in the elderly people. This review paper aims to put forward recent developments in the diagnosis of Alzheimer’s disease (AD) using Electroencephalograms (EEG). The extraction of useful information from rough EEG signal using only mathematical algorithm is a tough but promising task. Various modern techniques have enhanced the computerized analysis of EEG in elderly people. All these techniques can exploit the information contained in the EEG signals in time, frequency and time-frequency domain analyses. This work provides an integration of various time, frequency and time-frequency domain methods which facilitate the analysis independently as well as combined thus making it easier to analyze nonstationary and non-deterministic EEG signals. Among these various methods, time-frequency domain tools offer most efficient methods as it can uncover features that remain invisible when only time or frequency domain methods are used. Several of the methods discussed here can be utilized to develop an efficient algorithm for early detection of Alzheimer’s disease.
Title of the Paper: Role of the Autonomic Nervous System and Endothelial Vasoregulators in the Development of Primary Arterial Hypotension in Children
Authors: Anatoly V. Sikorsky, Menizibeya O. Welcome, Vladimir A. Pereverzev
Abstract: The aim of the study was to investigate the role of the autonomic nervous system and endothelial vasoregulators in the development of primary arterial hypotension (PAH) in children. The cardiointervalography results of 113 children with PAH were compared with 88 healthy children of comparable age (7–11 years). The findings revealed that children with PAH had higher activity of the sympathetic (p < 0.001) and parasympathetic (p < 0.001) divisions of the autonomic nervous system at the initial (resting) position of clinoorthostatic test. The activity of these divisions of the autonomic nervous system correlated with the activity of cardiac pacemaker. The change of position from horizontal into vertical was accompanied by a rise only in sympathetic activity (p < 0.001). However, there was a decline in the sympathetic nervous system (p < 0.001) compared to the indices of the initial (resting) position is registered in the tenth minute of the vertical position. This decrease may be due to the adaptational or compensatory abilities of the sympathetic nervous system. The parasympathetic division of the autonomic nervous system based on heart rate variability showed high activity in all positions of the clinoorthostatic test in the patients with PAH compared with healthy children. The activity of the parasympathetic nervous system was associated with increased synthesis of endothelial factors (e.g. nitric oxide, endothelins) in blood. In conclusion, the results of this study indicate that inadequate response of the autonomic nervous system to clinoorthostatic test in children with PAH is associated with disorders of both divisions of the autonomic nervous system as well as vascular endothelial factors. Keywords—primary arterial hypotension; autonomic nervous system; cardiointervalography; clinoorthostatic test; nitric oxide; endothelial vasoregulators; endothelin
Title of the Paper: Contrast Enhancement and Detection of Microcalcifications Mammary Using Hidden Markov Chains
Authors: A. Mehidi, M. Mimi, M. Bentoumi, A. Taleb Ahmed
Abstract: Breast cancer is continually one of the mean causes of female mortality. Mammography is the most widely used imaging technique for detecting tumors at a premature stage. This investigation is currently the best for breast cancer screening. The presence of microcalcifications in mammography images is particularly interesting for the early detection of breast cancer. The objective of our work is the automation of microcalcifications’ detection by mammographic images’ processing. This helps the experts in their work because the number of images to be inspected and evaluated is very large. For this purpose, an automated algorithm is proposed for the detection of microcalcification clusters following a specific methodology. First, mammography is preprocessed using a technique that involves improving the quality of mammography (improvement of local contrast). Then, the clusters are identified using a stochastic analysis based on hidden Markov chains, together with a Hilbert-Peano analysis of the medical images. This may allow detecting nodular components such as microcalcifications with precision by introducing size information. The obtained results are visually very clear, precise and show that the proposed approach permits to successfully extract the microcalcifications from the referential mammographic images of the MIAS database. Furthermore, we have showed that the use of hidden Markov chains (HMM) is more efficient for the detection of microcalcifications because HMMs rely mainly on the spatial regularity constraint for image processing. On the other hand, based on objective performance measures namely true positive rate (TPR) and false positive rate (FPR), the comparative study carried out on the three breast densities has shown the efficiency of our method whatever the type of the breast density.
Title of the Paper: Drift Diffusion Modeling of Response Time in Heading Estimation Based on Motion and Form Cues
Authors: Nadejda B. Bocheva, Bilyana Z. Genova, Miroslava D. Stefanova
Abstract: Decision making in perceptual tasks is considered as a process of accumulation of evidence for a particular response that depends on the task difficulty, the instruction, and the non-decision processes. We performed a study on discrimination of simulated heading direction based on form and motion cues with different age groups in a task where the observers determined the time to respond. In the single-cue conditions, the stimuli were either radial Glass patterns supposed to provide information similar to motion streaks in real motion or moving radial patterns. In the combined condition the motion and form information provided consistent information about the simulated heading as the dots in the Glass patterns moved along trajectories parallel to the orientation of the dot pairs. When compared to optimal cue combination, the accuracy performance in combined condition greatly exceeded the predictions. Applying a hierarchical drift diffusion modeling on the reaction time and the observers’ responses we showed that the conditions requiring temporal integration increase the time for the non-decision processing, while the information reliability changes the rate of evidence accumulation for a particular response. Moreover, age affects the amount of necessary evidence for making a decision and the non-decision time. The rate of evidence accumulation in elderly is lowered in conditions requiring spatial information integration.
Title of the Paper: A Two-Step Bayesian Approach for Modeling a Complex Neurophysiological System
Authors: Ioannis I. Spyroglou, Alexandros G. Rigas
Abstract: Our purpose in this paper is to model in a better way a complex neurophysiological system called muscle spindle. This system involves point processes as input and output. A two-step approach based on Bayesian logistic regression is used when a weakly informative and an informative prior is chosen. The parameters of the model which are of great interest are the threshold, the recovery, the summation and the carry-over effect function. The results show that the estimates derived from the Bayesian approach are similar to the ones obtained by the maximum likelihood method with the advantage of smaller confidence intervals. These results show the great importance of the two-step Bayesian approach which gives more representative models.
Title of the Paper: Numerical Modeling of the Dynamics of Blood Flow through Thrombosis
Authors: S. D. Maussumbekova, A. O. Beketaeva
Abstract: Thrombosis not only helps of stopping excessive bleeding in case of trauma, but is also often associated with pathological conditions of blood that interferes with its flow. The study of thrombosis is crucial for understanding and developing new methods for treating deep vein thrombosis, pulmonary embolism, etc. For the last two decades, there has been an exponential growth in studies related to the formation of a blood clot using computational tools and experiments. Despite this growth, a full the mechanism of thrombus formation is not yet known. In this paper, we considered the mathematical model of blood flow through region with thrombus. Blood flow is modelled as homogeneous incompressible fluid by the two-dimensional Navier-Stokes equations, when the formation of the thrombus described by equations of main regulators of fibrin polymerization. The numerical algorithm of solution of the basic equations is based on the immersed boundary method. It allows to take into account the moving thrombus. The presence of the immersed boundary is accomplished by adding a special function to the equations of motion, which make it possible to accurately represent the boundary of the streamlined region. In the present study, we analyze the effects of influence of various fluid parameters as Reynolds, Peclet numbers, gradient of pressure. It has been revealed that the increase of blood flow velocity leads to a change in the qualitative structure of the thrombus, that is, instead of simple form of thrombus appear thrombus with a complex f structure.
Title of the Paper: Molecular Dynamics Simulation of Complexes of Lysine Dendrimer and Dendrigraft with AENG Tetrapeptide
Authors: D. N. Khamidova, V. V. Bezrodnyi, A. V. Popova, S. E. Mikhtaniuk, I. M. Neelov, E. V. Popova
Abstract: Computer simulation of complexes of lysine dendrimer and dendrigraft with therapeutic AENG tetrapeptide was carried out using molecular dynamics simulation method. Dendrimers were tested earlier for drug and gene delivery to different cells.. In this study two systems consisting of one lysine dendrimer or dendrigraft of the second generation and 16 tetrapeptides were studied.. It was obtained that in both cases the peptide molecules become adsorbed by branched lysine molecules and forms stable nanocomplex with them. The size and internal structure of the nanocomplexes were compared. Similar complexes and conjugates could be used in future for delivery of different therapeutic peptides to the target organs.
Title of the Paper: Techniques for De-noising of Bio-Medical Images
Authors: Nalini Bodaisingi, Balaji Narayanam
Abstract: In the field of biomedical imaging, diagnosis of the patient is mainly based on images of different body parts using different types of equipment. Some of the examples of biomedical images are MRI (magnetic resonance imaging), retinal image, mammograms. These types of images involve a unique type of capturing and acquisition. In this process, images are subjected to various types of noises at various levels. Most common noises like Gaussian noise, speckle noise, salt and pepper noise, Poisson noise corrupts the important detail and makes the diagnosis mostly difficult and sometimes impossible. In order to overcome this problem different de-noising techniques like the median filter, averaging filter, wiener filter, order statistic filter de-noises the image and gives various results. In order to conclude the best filter metrics like PSNR (peak signal to noise ratio), MSE (mean square error), and SSIM (structural similarity index measure) are used. In this paper based on universal standard thresholds for metrics used graphs are drawn for each type of noise for each type of biomedical image for different variance values. Based on above thresholds we can conclude that median filter is best suited for all three types of biomedical images.
Title of the Paper: Fast Virus and Bacteria Genome Sequencing by Compatible Restriction Enzyme Fingerprinting
Authors: Peter Z. Revesz, Dipty Singh
Abstract: Early identification of a dangerous strain of a virus or bacteria that may cause a pandemic requires practical methods for sequencing of their genomes. This paper describes the concept of compatible restriction enzymes, and a fast and cost-efficient genome map assembly and sequencing method. Computer experiments on plasmid and virus genomes show that the genome map assembly and sequencing can be done in an approximately linear time in the sizes of the genomes.
Title of the Paper: Locked-in Patients’ Activities Enhancement via Brain-Computer Interface System Using Neural Network
Authors: Anas A. Magour, K. Sayed, Wael A. Mohamed, M. M. El Bahy
Abstract: Nowadays, there are millions of people around the world suffer from the disability caused by big stroke. In recent years we have seen a rising interest in brain computer interface (BCI) systems that help those patients to practice their normal lives. Therefore, this work presents a GUI application based on an offline BCI system to test their mental capacities. This application was designed based on three tests are alphabet, arithmetic operations and Raven’s progressive matrices. The success of this system depends on the choice of the processing techniques. Therefore, Discrete Wavelet Transform (DWT) and Principal Components Analysis (PCA) were used to extract a set of statistical features from the recorded brain signals. These features were classified into four classes are head movement to up, down, right or left using three classifiers are Artificial Neural Network (ANN), Support Vector Machine (SVM) and Linear Discriminant Analysis (LDA). The performance of classifiers was measured using the most frequently statistical parameters: the sensitivity, specificity, precision, classification accuracy, and area under receiver operating characteristics (ROC) curve (AUC). It was concluded that when DWT was used as a feature extraction, ANN and SVM achieved the highest classification accuracy with a value of 95.24% but when using PCA, ANN achieved the highest classification accuracy with a value of 92.86%. On the other hand, LDA classifier was the worst among the three classifiers.
Title of the Paper: Variations in the Functional Properties of Soybean Flour Fermented with Lactic Acid Bacteria
Authors: Alloysius Chibuike Ogodo, Ositadinma Chinyere Ugbogu, Reginald Azu Onyeagba
Abstract: The functional properties of soybean flour fermented with lactic acid (LAB)-consortium was evaluated. Soybean was processed into flour, fermented spontaneously and with LAB-consortium previously isolated from maize (Lactobacillus plantarum WCFS1+Lactobacillus rhamnosus GG, ATCC 53/03+Lactobacillus nantensis LP33+Lactobacillus fermentum CIP 102980+Lactobacillus reuteri DSM 20016) and sorghum (Pediococcus acidilactici DSM 20284+Lactobacillus fermentum CIP 102980+Lactobacillus brevis ATCC 14869+Lactobacillus nantensis LP33+Lactobacillus plantarum WCFS1) to evaluate their effects on the functional properties of the flour at 12 h intervals using standard techniques. The result shows gradual decrease in bulk density with increasing fermentation period ranging from 0.74±0.03 g/mL to 0.72±0.03 g/mL (natural), from 0.74±0.03 g/mL to 0.70±0.02 g/mL (LAB-consortium from maize) and from 0.74±0.03 g/mL to 0.70±0.02 g/mL (LAB-consortium from sorghum) fermentation. The swelling capacity decreased from 0.77±0.03 g/mL to 0.64±0.01 g/mL, from 0.77±0.03 g/mL to 0.59±0.01 g/mL and from 0.77±0.03 g/mL to 0.61±0.03 g/mL in natural, LAB-consortium from maize and sorghum fermentations respectively. Water holding capacity decreased from 2.4±0.03 mL/g to 1.9±0.03 mL/g, from 2.4±0.03 mL/g to 2.0±0.03 mL/g and from 2.4±0.03 mL/g to 1.9±0.03 mL/g in natural, LAB-consortium from maize and sorghum fermentation respectively. Oil holding capacity increased significantly (p<0.05) with increasing fermentation time, ranging from 8.92 ± 0.02 mL/g to 9.30±0.03 mL/g (natural), 8.92±0.01 mL/g to 9.63±0.03 mL/g (LAB-consortium from maize) and from 8.92±0.03 mL/g to 9.69±0.03 mL/g (LAB-consortium from sorghum) fermentations. The least gelation concentration ranged from 3.0% (unfermented) to 6.0% (other fermentation products). Emulsion capacity (EC) increased from 35.88±3.12% to 44.33±1.33%, from 35.88±3.12% to 46.83±3.18% and from 35.88±3.12 % to 45.99±2.21% in natural, LAB-consortium from maize and sorghum fermentations respectively. This suggests the potentials of LAB-consortia fermentation in improving nutritional and functional properties of soybean flour.