Skip to main content

Mehmet Can

Followers

45

Following

35

Co-authors

2

Public Views

A life dedicated to science.

less

Tijuana Institute of Technology

Sofiane Achiche

École Polytechnique de Montréal

University of Dunaújváros

George Fragulis

University of Western Macedonia (UOWM)

Yannis L Karnavas

Democritus University of Thrace

Jose Luis Verdegay

University of Granada

Radu-Emil Precup

Politehnica University of Timisoara

muhammet öztürk

International University of Sarajevo

Interests

Uploads

Books by Mehmet Can

Authorship Authentication of Short Messages from Social Networks Recurrent Artificial Neural Networks

Southeast Europe Journal of Soft Computing, 2018

Dataset consists of 17000 tweets collected from Twitter, as 500 tweets for each of 34 authors tha... more Dataset consists of 17000 tweets collected from Twitter, as 500 tweets for each of 34 authors that meet certain criteria. Raw data is collected by using the software Nvivo. The collected raw data is preprocessed to extract frequencies of 200 features. In the data analysis 128 of features are eliminated since they are rare in tweets. As a progressive presentation, five – ten – fifteen – twenty - thirty and thirty four of these 34 authors are selected each time. Since recurrent artificial neural networks are more stable and iterations converge more quickly, in this work this architecture is preferred. In general, ANNs are more successful in distinguishing two classes, therefore for N authors, N×N neural networks are trained for pair wise classification. These N×N experts then organized as N special teams (CANNT) to aggregate decisions of these N×N experts. Number of authors is seen not so effective on the accuracy of the authentication, and around 80% accuracy is achieved for any number of authors.

Validation Tools for Predicted Linear B

Southeast Europe Journal of Soft Computing, 2018

It is claimed thatamino acid replacements in surface loops usually do notperturb the three-dimens... more It is claimed thatamino acid replacements in surface loops usually do notperturb the three-dimensional structure of the protein,since surface loops are relatively flexible (Saunders andBaker 2002). Thus, the conservation variability of epitopesmight be biased by the abundance of loops inepitopes. These results imply that epitopes do not tendto overlap functional regions, but rather cover separateregions. Pellequera, et. al., (1993), developed new turn scales based on the occurrence of amino acids at each of the four positions of a turn using a structural database comprised of 87 proteins. It is found that the scales correctly predicted a fraction of the turn regions in proteins with approximately 80% confidence. They used the turn scales for predicting the location of antigenic sites in proteins. The method was developed with the specific aim of predicting only a few peaks for each protein. They found that it leads to a high level of accurate prediction around 70% of correct prediction of known epitopes. In this article we update turn scales using large numbers of proteins and epitopes. Improved method will be more helpful in selecting protein regions to be synthesized in order to produce anti-peptide antibodies cross-reacting with the parent protein.

Artificial Neural Networks in

Southeast Europe Journal of Soft Computing, 2018

In 1980s, the face of the microbiology dramatically changed with the rRNA-based phylogenetic clas... more In 1980s, the face of the microbiology dramatically changed with the rRNA-based phylogenetic classifications, by Carl Woese. He delineated the three main branches of life. He used the technique not only to explore microbial diversity but also as a method for bacterial annotation. Today, rRNA-based analysis remains a central method in microbiology. Many researchers followed this track, using several new generations of Artificial Neural Networks they obtained high accuracies using available datasets of their time. Recently the number of known bacteria increased enormously. In this article we used ANN's to annotate bacterial 16S rRNA gene sequences from five selected phylums in Greengenes database taxonomy: Proteobacteria, Firmicutes, Bacteroidetes, Actinobacteria, and Chloroflexi. 93% average accuracy is obtained in classif-ications. When we used the bundle testing technique, the average accuracy easily raised to 100%.

Validation Tools for Predicted Linear B

Southeast Journal of Soft Computing, 2018

It is claimed thatamino acid replacements in surface loops usually do notperturb the three-dimens... more It is claimed thatamino acid replacements in surface loops usually do notperturb the three-dimensional structure of the protein,since surface loops are relatively flexible (Saunders andBaker 2002). Thus, the conservation variability of epitopesmight be biased by the abundance of loops inepitopes. These results imply that epitopes do not tendto overlap functional regions, but rather cover separateregions. Pellequera, et. al., (1993), developed new turn scales based on the occurrence of amino acids at each of the four positions of a turn using a structural database comprised of 87 proteins. It is found that the scales correctly predicted a fraction of the turn regions in proteins with approximately 80% confidence. They used the turn scales for predicting the location of antigenic sites in proteins. The method was developed with the specific aim of predicting only a few peaks for each protein. They found that it leads to a high level of accurate prediction around 70% of correct prediction of known epitopes. In this article we update turn scales using large numbers of proteins and epitopes. Improved method will be more helpful in selecting protein regions to be synthesized in order to produce anti-peptide antibodies cross-reacting with the parent protein.

Forecasting Conditional Variance of S&P100 Returns Using Feedforward and Recurrent Neural Networks

It is shown that time series about financial market variables are highly nonlinearly dependent on... more It is shown that time series about financial market variables are highly nonlinearly dependent on time. Fluctuations or volatility of returns on assets is one of them. Portfolio managers, option traders and market makers are all interested in volatility forecasting in order to get higher profits and less risky positions. The nonlinear dependence on time is very complex and parametric approaches, and linear models fail. Therefore as nonparametric tools artificial neural networks (ANNs) are candidates to deal with the volatility and/or return forecasting problems. On the other hand, based on the fact that volatility is time varying and that periods of high volatility tend to cluster, the most popular models in modeling volatility are GARCH type models because they can account excess kurtosis and asymmetric effects of financial time series. A standard GARCH(1,1) model usually indicates high persistence in the conditional variance, which may originate from structural changes. Hence it is natural that artificial neural networks (ANN) will be constructed to capture the nonlinear relationship between past return innovations and conditional variance which may be missed by linear regression models. First a usual feedforward, back propagation network is used. The structure of the return data makes FFANN difficult to converge. To overcome this difficulty a neural network with appropriate recurrent connections in the context of nonlinear ARMA models are used. These are the Jordan neural networks (JNN). Then Elman recurrent networks (ENN) and a mixture of the two (EJNN) are also used. The data set consists of returns of the S&P100 index daily closing prices obtained from the S&P100 website. The results indicate that the selected JNN(1,1,1) model has superior performances compared to the standard GARCH(1,1) model. The contribution of this paper can be seen in determining the appropriate NN that is comparable to the standard GARCH(1,1) model and its application in forecasting conditional variance of stock returns. Moreover, from the econometric perspective, NN models are used as a semi-parametric method that combines flexibility of nonparametric methods and the interpretability of parameters of parametric methods.

Accuracy of Identical Subsequences Based Protein Secondary Structure Prediction

by Mehmet Can, Muhamed Adilovic, and mehmet can

Chou, and Fasman developed the first empirical prediction method to predict secondary structure o... more Chou, and Fasman developed the first empirical prediction method to predict secondary structure of proteins from their amino acid sequences. Subsequently, a more sophisticated GOR method has been developed. Although it became very popular among biologists, their accuracy was only slightly better than random. A significant improvement in prediction accuracy >70% has been achieved by ‘second generation’ methods such as PHD, SAM-T98, and PSIPRED, which utilized information concerning sequence conservation. Only recently F. B. Akcesme developed a local similarity based method to obtain an accuracy >90%in secondary structure prediction of any new protein. In this article we examined the possibility of sequence similarity based secondary structure prediction of proteins. To deal with this issue, all proteins of PDB dataset are searched for identical subsequences in the other larger proteins of PDB dataset. It is seen that around 17% of proteins in the PDB dataset have identical subsequences in other larger proteins of PDB dataset. When the secondary structures of proteins are assigned as the corresponding secondary structures of identical parts in other larger proteins, the average prediction accuracy is found to be 90.39 %. Therefore, we concluded that an unknown protein has a chance of 17 % to have an identical subsequence in a larger protein in Protein Data Bank (PDB), and there is a possibility that its secondary structure be predicted with around 90% accuracy with this method.

On the Accuracy of Sequence Similarity Based Protein 3D Prediction

by Mehmet Can, Muhamed Adilovic, and mehmet can

In an article (Akcesme, and Can 2015), authors examined the relation between primary and secondar... more In an article (Akcesme, and Can 2015), authors examined the relation between primary and secondary structure mismatches of the substrings of length seventeen residues from two different proteins. They have shown that the mismatches in the corresponding secondary structure sequence substrings of the same length mostly lag behind primary mismatches. In the PhD dissertation thesis (Akcesme 2016) author examined the possibility of secondary structure prediction by the use of smaller conserved segments and created a software AVISENNA that outperforms PSIPRED and all other available secondary structure prediction tools. In another article (Akcesme, et. al. 2017), the issue of how far secondary structure of proteins can be predicted based on hosts (larger proteins that contain the query protein as a subchain) of this protein in the set of solved structures currently deposited in PDB. It is seen that around 17% of proteins have hosts in PDB, and secondary structures of them can be predicted with a mean accuracy of 90.39 %. This accuracy of the host based secondary structure prediction set also an upper bound for the homology based tertiary structure predictions. In this article the impact of the mentioned inaccuracy on the homology based 3D structure predictions by the three predictors I-Tasser, Phyre2, and SwissModel are studied. Inaccuracies in predicted tertiary structures are seen in the visual comparison of the 3D structures of query proteins and their predicted 3D images by the three 3D predictors, and their counterparts in host proteins.

Papers by Mehmet Can

Imitation of Fuzzy Logic Controller Based Artificial Neural Network, and Application of Inverted Pendulum System Control

European Journal of Technic, Dec 30, 2019

Fuzzy Logic Controllers (FLCs) are effective solutions for nonlinear and parameter variability sy... more Fuzzy Logic Controllers (FLCs) are effective solutions for nonlinear and parameter variability systems, but it contains multiple mathematical operations causing the controller to react slowly. This study aims to obtain a controller that can imitate the effective control performance of the FLC, which is easy to design both in software and hardware, and has a short response time. Artificial neural networks (ANNs) provide effective solutions in system modeling. Modeling of FLC has been realized by using of ANN's learning and parallel processing capability. The design process of the FLC and the training processes of the ANN were studied in Matlab SIMULINK environment. In the study, FLC was modelled at high similarity ratio with small ANN structure. ANN results were obtained very faster than the FLC control performance. The control performances of two controllers were observed to be very close to each other. As a result, ANN model has smaller structure than FLC, which makes it possible to implement the controller easily in terms of hardware and software.

Sharing and Managing Risk in Islamic Finance

For most of the people the prohibition on interest is the well known part of Islamic finance howe... more For most of the people the prohibition on interest is the well known part of Islamic finance however the rest is considered as an unknown finance system that is based on the rules which are written thousands years ago. Indeed, the concept of Islamic finance is not be discussed enough till financial crisis, after crisis it started to be seen as an alternative financial system. However some new approaches are needed to demonstrate Islamic finance as an alternative of conventional finance. Sharing the risks is main concept in investments but question is what the investments are. In the new approach of risk management the idea is consumers can follow their money and investments and banks have to inform the consumers.

Digital Image Techniques for the Comet-FISH Assay in the Search for DNA Damage and Repair

Southeast Europe Journal of Soft Computing, 2016

Three Variable Cancer Angiogenesis models

Southeast Europe Journal of Soft Computing, 2012

In this paper we present several mathematical models of tumor growth and angiogenesis expressed b... more In this paper we present several mathematical models of tumor growth and angiogenesis expressed by systems of ODE' s encoding the most essential observations and assumptions about the complex hierarchical interactive processes of tumor neovascularization (angiogenesis). The simplest modeling option presented merely captures the three independent variables mentioned earlier-tumor size N, total vessel volume V and the amount of protein P. We modify this model assuming that the protein is additionally consumed by growing vessels and obtain a model with protein consumption. Next models with time-delays are introduced. To make our models more realistic, two more compartments representing more complex vascularity and protein effects are introduced.

Distribution of Unemployment Spells and Survival Analysis: The Case of Bosnia and Herzegovina

Southeast Europe Journal of Soft Computing, 2013

Using Neural Networks to Forecast the Implied Volatility: the Case of S&P100XEO

Southeast Europe Journal of Soft Computing, 2014

Currently the most popular method of estimating volatility is the implied volatility. It is calcu... more Currently the most popular method of estimating volatility is the implied volatility. It is calculated using the Black-Scholes option price formula, and is considered by traders to be a significant factor in signaling price movements in the underlying market. A trader is able to establish the proper strategic position in anticipation of changes in market trends if she/he could accurately forecast future volatility. There is an abundance of ways to compute the volatility. For two decades neural networks has been developed to forecast future volatility, using past volatilities and other options market factors. In this article a network is created for this purpose whose performance demonstrates the value of neural networks as a predictive tool in volatility analysis.

Lie Symmetries of Differential Equations by Computer Algebra

Mathematical and Computational Applications, 1996

Secondly combining group theory and singularity analysis we obtained some information about the s... more Secondly combining group theory and singularity analysis we obtained some information about the similarity solutions of the fourth order generalized Boussinesq equation GBE4. It has been shown that this equation possess a three dimensional Lie algebra of the point symmetries and the similarity reductions due to these symmetries have been obtained.

Global Nonexistence of Solutions of the Vibrations of a Riser

Mathematical and Computational Applications, 1997

In this 'MJrk, the nonexistence of the global solutions of a quasilinear hyperbolic boundary valu... more In this 'MJrk, the nonexistence of the global solutions of a quasilinear hyperbolic boundary value problem with dissipative term in the equation is considered. In one space dimension this initial value problem models the behavior of a riser vibrating dl1e to the effects of\Wves and current. The nonexistence proof is achieved by the use of the so called concavity method. In thiS method one writes do""n a functional which represents the norm of the solution in some sense. Then it is proved that this functional satisfies the hypotheses of the concavity lemma. Hence one concludes that one cannot continue the solution for all time by sho•.•.•-ing that this functional and hence the norm of the solution, lMJuld otherwise blow up in finite time.

Comparison of Islamic, Traditional and Alternative Utility Theories

Decision making under uncertainty is always trying to be explained by utility theory. And utility... more Decision making under uncertainty is always trying to be explained by utility theory. And utility theory‘s roots rely on moral philosophy. Moral philosophy is concerning concepts about good and bad, right and wrong, virtue, justice, etc. It can be say that utilitarianism, which is a field of moral philosophy, is more directly about utility theory. Throughout the human history, from Prophet Abraham to Greek philosophers; Socrates, Aristotle, Epicurus, to Islam scholars al Kindi, al-Farabi, al-Razi, Ibn-i Sina, Ibni Rushd, Ibn-i Haldun, all discussed about ethics and utility concept.

Self similar solutions of the nonlinear Schrödinger equation

Nonexistense of global solutions of a quasilinear bi-hyperbolic equation with dynamical boundary conditions

Electronic Journal of Qualitative Theory of Differential Equations, 1999

In this work, the nonexistence of the global solutions to a class of initial boundary value probl... more In this work, the nonexistence of the global solutions to a class of initial boundary value problems with dissipative terms in the boundary conditions is considered for a quasilinear bi-hyperbolic equation. The nonexistence proof is achieved by the use of a lemma due to O. Ladyzhenskaya and V.K. Kalantarov and by the usage of the so called generalized convexity method. In this method one writes down a functional which reflects the properties of dissipative boundary conditions and represents the norm of the solution in some sense, then proves that this functional satisfies the hypotheses of Ladyzhenskaya-Kalantarov lemma. Hence from the conclusion of the lemma one deduces that in a finite time t 2 , this functional and hence the norm of the solution blows up.

Resonant non-linear waves—III. Elastic continuum with quadratic non-linearity

International Journal of Non-Linear Mechanics, 1985

The paper derives the relevant non-linear integro-differential evolution equation by the method d... more The paper derives the relevant non-linear integro-differential evolution equation by the method due to Collins expanding on a procedure by Keller. The quadratically non-linear case is not a trivial variation over the cubically non-linear case that was presented in preceding papers. As expected a different scaling and ordering of terms is needed and the first order perturbation solution provides no information on resonance. Nevertheless, although obtained by much longer calculations, the final equation for the present case is of identical form, with differences only in numerical coefficients, with the cubic case that was presented and solved earlier.

Self-Similar Isomonodromy Solutions of Nonlinear Schrödinger Equation

NATO ASI Series, 1994

Recent works of a group of Japanese mathematicians M. Sato, T. Miwa, M. Jimbo, K. Ueno, E. Date a... more Recent works of a group of Japanese mathematicians M. Sato, T. Miwa, M. Jimbo, K. Ueno, E. Date and others [1–2] have attracted major attention of researchers in various areas of mathematics and mathematical physics. One of the interesting gains of the theory of nonlinear equations of mathematical physics is the concept of “isomonodromy” solutions of nonlinear equations admitting a Lax representation. Isomonodromy solutions are a natural generalization of their self similar solutions. Within the framework of the formalism of the matrix Riemann-Hilbert problem finally adopted, isomonodromy solutions are characterized by the constancy in the “spectral parameter” λ of all junction matrices. This leads to the situation that the function corresponding to an isomonodromy solution satisfies, together with the original U – V system, also a third equation in λ. The data of the Riemann-Hilbert problem here acquire the meaning of monodromy data for the λ-equation. The apriori independence of the monodromy data from the dynamical variables x and t means that the original nonlinear equation describes isomonodromy deformations of the coefficients of the λ-equation. This is the motivation for the term isomonodromy solution.

Authorship Authentication of Short Messages from Social Networks Recurrent Artificial Neural Networks

Southeast Europe Journal of Soft Computing, 2018

Dataset consists of 17000 tweets collected from Twitter, as 500 tweets for each of 34 authors tha... more Dataset consists of 17000 tweets collected from Twitter, as 500 tweets for each of 34 authors that meet certain criteria. Raw data is collected by using the software Nvivo. The collected raw data is preprocessed to extract frequencies of 200 features. In the data analysis 128 of features are eliminated since they are rare in tweets. As a progressive presentation, five – ten – fifteen – twenty - thirty and thirty four of these 34 authors are selected each time. Since recurrent artificial neural networks are more stable and iterations converge more quickly, in this work this architecture is preferred. In general, ANNs are more successful in distinguishing two classes, therefore for N authors, N×N neural networks are trained for pair wise classification. These N×N experts then organized as N special teams (CANNT) to aggregate decisions of these N×N experts. Number of authors is seen not so effective on the accuracy of the authentication, and around 80% accuracy is achieved for any number of authors.

Validation Tools for Predicted Linear B

Southeast Europe Journal of Soft Computing, 2018

It is claimed thatamino acid replacements in surface loops usually do notperturb the three-dimens... more It is claimed thatamino acid replacements in surface loops usually do notperturb the three-dimensional structure of the protein,since surface loops are relatively flexible (Saunders andBaker 2002). Thus, the conservation variability of epitopesmight be biased by the abundance of loops inepitopes. These results imply that epitopes do not tendto overlap functional regions, but rather cover separateregions. Pellequera, et. al., (1993), developed new turn scales based on the occurrence of amino acids at each of the four positions of a turn using a structural database comprised of 87 proteins. It is found that the scales correctly predicted a fraction of the turn regions in proteins with approximately 80% confidence. They used the turn scales for predicting the location of antigenic sites in proteins. The method was developed with the specific aim of predicting only a few peaks for each protein. They found that it leads to a high level of accurate prediction around 70% of correct prediction of known epitopes. In this article we update turn scales using large numbers of proteins and epitopes. Improved method will be more helpful in selecting protein regions to be synthesized in order to produce anti-peptide antibodies cross-reacting with the parent protein.

Artificial Neural Networks in

Southeast Europe Journal of Soft Computing, 2018

In 1980s, the face of the microbiology dramatically changed with the rRNA-based phylogenetic clas... more In 1980s, the face of the microbiology dramatically changed with the rRNA-based phylogenetic classifications, by Carl Woese. He delineated the three main branches of life. He used the technique not only to explore microbial diversity but also as a method for bacterial annotation. Today, rRNA-based analysis remains a central method in microbiology. Many researchers followed this track, using several new generations of Artificial Neural Networks they obtained high accuracies using available datasets of their time. Recently the number of known bacteria increased enormously. In this article we used ANN's to annotate bacterial 16S rRNA gene sequences from five selected phylums in Greengenes database taxonomy: Proteobacteria, Firmicutes, Bacteroidetes, Actinobacteria, and Chloroflexi. 93% average accuracy is obtained in classif-ications. When we used the bundle testing technique, the average accuracy easily raised to 100%.

Validation Tools for Predicted Linear B

Southeast Journal of Soft Computing, 2018

It is claimed thatamino acid replacements in surface loops usually do notperturb the three-dimens... more It is claimed thatamino acid replacements in surface loops usually do notperturb the three-dimensional structure of the protein,since surface loops are relatively flexible (Saunders andBaker 2002). Thus, the conservation variability of epitopesmight be biased by the abundance of loops inepitopes. These results imply that epitopes do not tendto overlap functional regions, but rather cover separateregions. Pellequera, et. al., (1993), developed new turn scales based on the occurrence of amino acids at each of the four positions of a turn using a structural database comprised of 87 proteins. It is found that the scales correctly predicted a fraction of the turn regions in proteins with approximately 80% confidence. They used the turn scales for predicting the location of antigenic sites in proteins. The method was developed with the specific aim of predicting only a few peaks for each protein. They found that it leads to a high level of accurate prediction around 70% of correct prediction of known epitopes. In this article we update turn scales using large numbers of proteins and epitopes. Improved method will be more helpful in selecting protein regions to be synthesized in order to produce anti-peptide antibodies cross-reacting with the parent protein.

Forecasting Conditional Variance of S&P100 Returns Using Feedforward and Recurrent Neural Networks

It is shown that time series about financial market variables are highly nonlinearly dependent on... more It is shown that time series about financial market variables are highly nonlinearly dependent on time. Fluctuations or volatility of returns on assets is one of them. Portfolio managers, option traders and market makers are all interested in volatility forecasting in order to get higher profits and less risky positions. The nonlinear dependence on time is very complex and parametric approaches, and linear models fail. Therefore as nonparametric tools artificial neural networks (ANNs) are candidates to deal with the volatility and/or return forecasting problems. On the other hand, based on the fact that volatility is time varying and that periods of high volatility tend to cluster, the most popular models in modeling volatility are GARCH type models because they can account excess kurtosis and asymmetric effects of financial time series. A standard GARCH(1,1) model usually indicates high persistence in the conditional variance, which may originate from structural changes. Hence it is natural that artificial neural networks (ANN) will be constructed to capture the nonlinear relationship between past return innovations and conditional variance which may be missed by linear regression models. First a usual feedforward, back propagation network is used. The structure of the return data makes FFANN difficult to converge. To overcome this difficulty a neural network with appropriate recurrent connections in the context of nonlinear ARMA models are used. These are the Jordan neural networks (JNN). Then Elman recurrent networks (ENN) and a mixture of the two (EJNN) are also used. The data set consists of returns of the S&P100 index daily closing prices obtained from the S&P100 website. The results indicate that the selected JNN(1,1,1) model has superior performances compared to the standard GARCH(1,1) model. The contribution of this paper can be seen in determining the appropriate NN that is comparable to the standard GARCH(1,1) model and its application in forecasting conditional variance of stock returns. Moreover, from the econometric perspective, NN models are used as a semi-parametric method that combines flexibility of nonparametric methods and the interpretability of parameters of parametric methods.

Accuracy of Identical Subsequences Based Protein Secondary Structure Prediction

by Mehmet Can, Muhamed Adilovic, and mehmet can

Chou, and Fasman developed the first empirical prediction method to predict secondary structure o... more Chou, and Fasman developed the first empirical prediction method to predict secondary structure of proteins from their amino acid sequences. Subsequently, a more sophisticated GOR method has been developed. Although it became very popular among biologists, their accuracy was only slightly better than random. A significant improvement in prediction accuracy >70% has been achieved by ‘second generation’ methods such as PHD, SAM-T98, and PSIPRED, which utilized information concerning sequence conservation. Only recently F. B. Akcesme developed a local similarity based method to obtain an accuracy >90%in secondary structure prediction of any new protein. In this article we examined the possibility of sequence similarity based secondary structure prediction of proteins. To deal with this issue, all proteins of PDB dataset are searched for identical subsequences in the other larger proteins of PDB dataset. It is seen that around 17% of proteins in the PDB dataset have identical subsequences in other larger proteins of PDB dataset. When the secondary structures of proteins are assigned as the corresponding secondary structures of identical parts in other larger proteins, the average prediction accuracy is found to be 90.39 %. Therefore, we concluded that an unknown protein has a chance of 17 % to have an identical subsequence in a larger protein in Protein Data Bank (PDB), and there is a possibility that its secondary structure be predicted with around 90% accuracy with this method.

On the Accuracy of Sequence Similarity Based Protein 3D Prediction

by Mehmet Can, Muhamed Adilovic, and mehmet can

In an article (Akcesme, and Can 2015), authors examined the relation between primary and secondar... more In an article (Akcesme, and Can 2015), authors examined the relation between primary and secondary structure mismatches of the substrings of length seventeen residues from two different proteins. They have shown that the mismatches in the corresponding secondary structure sequence substrings of the same length mostly lag behind primary mismatches. In the PhD dissertation thesis (Akcesme 2016) author examined the possibility of secondary structure prediction by the use of smaller conserved segments and created a software AVISENNA that outperforms PSIPRED and all other available secondary structure prediction tools. In another article (Akcesme, et. al. 2017), the issue of how far secondary structure of proteins can be predicted based on hosts (larger proteins that contain the query protein as a subchain) of this protein in the set of solved structures currently deposited in PDB. It is seen that around 17% of proteins have hosts in PDB, and secondary structures of them can be predicted with a mean accuracy of 90.39 %. This accuracy of the host based secondary structure prediction set also an upper bound for the homology based tertiary structure predictions. In this article the impact of the mentioned inaccuracy on the homology based 3D structure predictions by the three predictors I-Tasser, Phyre2, and SwissModel are studied. Inaccuracies in predicted tertiary structures are seen in the visual comparison of the 3D structures of query proteins and their predicted 3D images by the three 3D predictors, and their counterparts in host proteins.

Imitation of Fuzzy Logic Controller Based Artificial Neural Network, and Application of Inverted Pendulum System Control

European Journal of Technic, Dec 30, 2019

Fuzzy Logic Controllers (FLCs) are effective solutions for nonlinear and parameter variability sy... more Fuzzy Logic Controllers (FLCs) are effective solutions for nonlinear and parameter variability systems, but it contains multiple mathematical operations causing the controller to react slowly. This study aims to obtain a controller that can imitate the effective control performance of the FLC, which is easy to design both in software and hardware, and has a short response time. Artificial neural networks (ANNs) provide effective solutions in system modeling. Modeling of FLC has been realized by using of ANN's learning and parallel processing capability. The design process of the FLC and the training processes of the ANN were studied in Matlab SIMULINK environment. In the study, FLC was modelled at high similarity ratio with small ANN structure. ANN results were obtained very faster than the FLC control performance. The control performances of two controllers were observed to be very close to each other. As a result, ANN model has smaller structure than FLC, which makes it possible to implement the controller easily in terms of hardware and software.

Sharing and Managing Risk in Islamic Finance

For most of the people the prohibition on interest is the well known part of Islamic finance howe... more For most of the people the prohibition on interest is the well known part of Islamic finance however the rest is considered as an unknown finance system that is based on the rules which are written thousands years ago. Indeed, the concept of Islamic finance is not be discussed enough till financial crisis, after crisis it started to be seen as an alternative financial system. However some new approaches are needed to demonstrate Islamic finance as an alternative of conventional finance. Sharing the risks is main concept in investments but question is what the investments are. In the new approach of risk management the idea is consumers can follow their money and investments and banks have to inform the consumers.

Digital Image Techniques for the Comet-FISH Assay in the Search for DNA Damage and Repair

Southeast Europe Journal of Soft Computing, 2016

Three Variable Cancer Angiogenesis models

Southeast Europe Journal of Soft Computing, 2012

In this paper we present several mathematical models of tumor growth and angiogenesis expressed b... more In this paper we present several mathematical models of tumor growth and angiogenesis expressed by systems of ODE' s encoding the most essential observations and assumptions about the complex hierarchical interactive processes of tumor neovascularization (angiogenesis). The simplest modeling option presented merely captures the three independent variables mentioned earlier-tumor size N, total vessel volume V and the amount of protein P. We modify this model assuming that the protein is additionally consumed by growing vessels and obtain a model with protein consumption. Next models with time-delays are introduced. To make our models more realistic, two more compartments representing more complex vascularity and protein effects are introduced.

Distribution of Unemployment Spells and Survival Analysis: The Case of Bosnia and Herzegovina

Southeast Europe Journal of Soft Computing, 2013

Using Neural Networks to Forecast the Implied Volatility: the Case of S&P100XEO

Southeast Europe Journal of Soft Computing, 2014

Currently the most popular method of estimating volatility is the implied volatility. It is calcu... more Currently the most popular method of estimating volatility is the implied volatility. It is calculated using the Black-Scholes option price formula, and is considered by traders to be a significant factor in signaling price movements in the underlying market. A trader is able to establish the proper strategic position in anticipation of changes in market trends if she/he could accurately forecast future volatility. There is an abundance of ways to compute the volatility. For two decades neural networks has been developed to forecast future volatility, using past volatilities and other options market factors. In this article a network is created for this purpose whose performance demonstrates the value of neural networks as a predictive tool in volatility analysis.

Lie Symmetries of Differential Equations by Computer Algebra

Mathematical and Computational Applications, 1996

Secondly combining group theory and singularity analysis we obtained some information about the s... more Secondly combining group theory and singularity analysis we obtained some information about the similarity solutions of the fourth order generalized Boussinesq equation GBE4. It has been shown that this equation possess a three dimensional Lie algebra of the point symmetries and the similarity reductions due to these symmetries have been obtained.

Global Nonexistence of Solutions of the Vibrations of a Riser

Mathematical and Computational Applications, 1997

In this 'MJrk, the nonexistence of the global solutions of a quasilinear hyperbolic boundary valu... more In this 'MJrk, the nonexistence of the global solutions of a quasilinear hyperbolic boundary value problem with dissipative term in the equation is considered. In one space dimension this initial value problem models the behavior of a riser vibrating dl1e to the effects of\Wves and current. The nonexistence proof is achieved by the use of the so called concavity method. In thiS method one writes do""n a functional which represents the norm of the solution in some sense. Then it is proved that this functional satisfies the hypotheses of the concavity lemma. Hence one concludes that one cannot continue the solution for all time by sho•.•.•-ing that this functional and hence the norm of the solution, lMJuld otherwise blow up in finite time.

Comparison of Islamic, Traditional and Alternative Utility Theories

Decision making under uncertainty is always trying to be explained by utility theory. And utility... more Decision making under uncertainty is always trying to be explained by utility theory. And utility theory‘s roots rely on moral philosophy. Moral philosophy is concerning concepts about good and bad, right and wrong, virtue, justice, etc. It can be say that utilitarianism, which is a field of moral philosophy, is more directly about utility theory. Throughout the human history, from Prophet Abraham to Greek philosophers; Socrates, Aristotle, Epicurus, to Islam scholars al Kindi, al-Farabi, al-Razi, Ibn-i Sina, Ibni Rushd, Ibn-i Haldun, all discussed about ethics and utility concept.

Self similar solutions of the nonlinear Schrödinger equation

Nonexistense of global solutions of a quasilinear bi-hyperbolic equation with dynamical boundary conditions

Electronic Journal of Qualitative Theory of Differential Equations, 1999

In this work, the nonexistence of the global solutions to a class of initial boundary value probl... more In this work, the nonexistence of the global solutions to a class of initial boundary value problems with dissipative terms in the boundary conditions is considered for a quasilinear bi-hyperbolic equation. The nonexistence proof is achieved by the use of a lemma due to O. Ladyzhenskaya and V.K. Kalantarov and by the usage of the so called generalized convexity method. In this method one writes down a functional which reflects the properties of dissipative boundary conditions and represents the norm of the solution in some sense, then proves that this functional satisfies the hypotheses of Ladyzhenskaya-Kalantarov lemma. Hence from the conclusion of the lemma one deduces that in a finite time t 2 , this functional and hence the norm of the solution blows up.

Resonant non-linear waves—III. Elastic continuum with quadratic non-linearity

International Journal of Non-Linear Mechanics, 1985

The paper derives the relevant non-linear integro-differential evolution equation by the method d... more The paper derives the relevant non-linear integro-differential evolution equation by the method due to Collins expanding on a procedure by Keller. The quadratically non-linear case is not a trivial variation over the cubically non-linear case that was presented in preceding papers. As expected a different scaling and ordering of terms is needed and the first order perturbation solution provides no information on resonance. Nevertheless, although obtained by much longer calculations, the final equation for the present case is of identical form, with differences only in numerical coefficients, with the cubic case that was presented and solved earlier.

Self-Similar Isomonodromy Solutions of Nonlinear Schrödinger Equation

NATO ASI Series, 1994

Recent works of a group of Japanese mathematicians M. Sato, T. Miwa, M. Jimbo, K. Ueno, E. Date a... more Recent works of a group of Japanese mathematicians M. Sato, T. Miwa, M. Jimbo, K. Ueno, E. Date and others [1–2] have attracted major attention of researchers in various areas of mathematics and mathematical physics. One of the interesting gains of the theory of nonlinear equations of mathematical physics is the concept of “isomonodromy” solutions of nonlinear equations admitting a Lax representation. Isomonodromy solutions are a natural generalization of their self similar solutions. Within the framework of the formalism of the matrix Riemann-Hilbert problem finally adopted, isomonodromy solutions are characterized by the constancy in the “spectral parameter” λ of all junction matrices. This leads to the situation that the function corresponding to an isomonodromy solution satisfies, together with the original U – V system, also a third equation in λ. The data of the Riemann-Hilbert problem here acquire the meaning of monodromy data for the λ-equation. The apriori independence of the monodromy data from the dynamical variables x and t means that the original nonlinear equation describes isomonodromy deformations of the coefficients of the λ-equation. This is the motivation for the term isomonodromy solution.

Nonexistence of global solutions of a quasilinear hyperbolic equation

Mathematical Inequalities & Applications, 1998

In this work, the nonexistence of the global solutions to a class of initial boundary value probl... more In this work, the nonexistence of the global solutions to a class of initial boundary value problems with dissipative terms in the boundary conditions is considered for a quasilinear hyperbolic equation. The nonexistence proof is achieved by the use of a lemma due to O. Ladyzhenskaya and V. K. Kalantarov and by the usage of the so called concavity method. In this method one writes down a functional which reflects the properties of dissipative boundary conditions and represents the norm of the solution in some sense, then proves that this functional satisfies the hypotheses of Ladyzhenskaya-Kalantarov lemma. Hence from the conclusion of the lemma one concludes that in finite time t 2 , this functional and hence the norm of the solution blows up.

Nonexistence of Global Solutions of Some Quasilinear Hyperbolic Equations

Journal of Mathematical Analysis and Applications, 1997

In this work, the nonexistence of the global solutions to a class of initial boundary value probl... more In this work, the nonexistence of the global solutions to a class of initial boundary value problems with dissipative terms in the boundary conditions is considered for a quasilinear hyperbolic equation. The nonexistence proof is achieved by the use of a lemma due to O. Ladyzhenskaya and V. K. Kalantarov and by the usage of the so called concavity method. In this method one writes down a functional which reflects the properties of dissipative boundary conditions and represents the norm of the solution in some sense, then proves that this functional satisfies the hypotheses of Ladyzhenskaya-Kalantarov lemma. Hence from the conclusion of the lemma one concludes that in finite time t 2 , this functional and hence the norm of the solution blows up.

Four and Five Dimensional Metapopulation Models

Iranian Journal of Science and Technology,(submitted), 2006

Abstract: Two models with four and five components of chain populations are considered. In the fi... more

Clustering 16S rRNA for OTU prediction: A similarity based method

Heritage and Sustainable Development, ISSN 2712-0554, 2019

To study the phylogeny and taxonomy of samples from complex environments Next-generation sequenci... more To study the phylogeny and taxonomy of samples from complex environments Next-generation sequencing (NGS)-based 16S rRNA sequencing , which has been successfully used jointly with the PCR amplification and NGS technology. First step for many downstream analyses is clustering 16S rRNA sequences into operational taxonomic units (OTUs). Heuristic clustering is one of the most widely employed approaches for generating OTUs in which one or more seed sequences to represent each cluster are selected. In this work we chose five random seeds for each cluster from a genes library, and we present a novel distance measure to cluster bacteria in the sample. Artificially created sets of 16S rRNA genes selected from databases are successfully clustered with more than %98 accuracy, sensitivity, and specificity.

Authorship Authentication of Short Messages from Social Networks Machines

Southeast Europe Journal of Soft Computing, 2018

Dataset consists of 17000 tweets collected from Twitter each of 34 authors that meet certain crit... more Dataset consists of 17000 tweets collected from Twitter each of 34 authors that meet certain criteria. Raw data using the software Nvivo. The collected raw data is preproce extract frequencies of 200 features. In the data analysis 128 of features are eliminated since they are rare in tweets. As a progressive presentation, five-fifteen-twenty-twenty five-thirty and thirty authors are selected each time. Since recurrent artificial neural networks are more stable and in general ANNs are more successful distinguishing two classes, for N authors, N×N neural networks are trained for classification. These experts then organized in N c (CANNT) to aggregate decisions of these NXN expert procedure is repeated seven times and committees wit voted for final decision. By a commonest type voting boosted around ten percent. Number of authors is seen not so effective on the accuracy of the authentication, and around 80% accuracy is achieved for any number of authors.

Recurrent Neural Networks for Linear B-Epitope Prediction in Antigens

Southeast Europe Journal of Soft Computing, 2018

Experimental methods used for characterizing epitopes that play a vital role in the development o... more Experimental methods used for characterizing epitopes that play a vital role in the development of peptide vaccines, in diagnosis of diseases, and also for allergy research are time consuming and need There are many online epitope prediction tools that can help experimenters in short listing the candidate peptides. To predict B epitopes in an antigenic sequence, Jordan recurrent neural network (JRNN) are found to be more successful. To train and test neural networks, 262.583 B epitopes are retrieved from IEDB database. 99.9% of these epitopes have lengths in the interval 6-25 amino acids. For each of these lengths, committees of 11 expert recurrent neural networks are trained. To train these experts alongside epitopes, non needed. Non-epitopes are created as random sequences of amino acids of the same length followed by a filtering process. To distinguish epitopes and non-epitopes, the votes of eleven experts are aggrega vote. An overall accuracy of 97.23% is achieved. Then these experts are used to predict the linear b epitopes of antigen, ESAT6 (Tuberculosis).

On the Accuracies of Sequence Based Linear B Cell Epitope Predictors

Southeast Europe Journal of Soft Computing, 2018

The accuracy of online tools employed in attempts to predict B epitopes based on sequence are ver... more The accuracy of online tools employed in attempts to predict B epitopes based on sequence are very poor. In order to improve the accuracy of these predictions it is essential to design algorithms from the features achieved in wet lab in vivo experimental models. T shed some light on accuracy and reliability of these online tools, we set an insilico experiment on five selected online tools using five antigens b-cell epitopes are known through wet lab experiments successes of online tools, we defined two measures, accuracy, and reliability. To the findings of this experiment, the most accurate tool is ABCpred with a score of 43.59 %. That is peptides that are predicted as b epitopes, cover in average 43.59 % of the wet lab listed b most reliable predictors are BCpred and AAPred with scores of 52.54%, and 52.60% respectively, which means that in average peptides that are predicted as a b-epitope by these predictors have a chance to be a real b-epitope. Combining several predictors predictors is not an advisable technique. From this experiment it is concluded that the accuracy and reliability of online away being satisfactory. The human body is a wonderful machine, which has the ability, to fight off attacking microorganisms and adapt to Very often, microorganisms or foreign particles enter the body and the body causing diseases. isease is a condition where an organism experiences impaired function often with detrimental symptoms. According to the World Health Organization, as of 2017 there were 7,186 classified different diseases and health-related ailments. 1 Virus is one of these organisms that can cause severe health issues. They invade living, normal cells and hijacks their normal molecular balance 1 http://www.who.int/classifications/ICD11January2017Ne wsletter.pdf?ua=1 Linear B Cell Epitope Predictors tools employed in attempts to predict B-cell In order to improve the algorithms to benefit xperimental models. To shed some light on accuracy and reliability of these online tools, we set an five selected online tools using five antigens whose experiments. To evaluate sures, accuracy, and , the most accurate tool is That is peptides that are predicted as bed b-epitopes. The most reliable predictors are BCpred and AAPred with scores of 52.54%, around half of the epitope by these predictors have a ombining several predictors to get better. From this experiment it is tools still are far 186 classified different diseases and Virus is one of these organisms that can cause severe health issues. They invade living, normal cells and hijacks their normal molecular balance