Mohamed Mneimneh - Academia.edu (original) (raw)
Papers by Mohamed Mneimneh
Due to the increasing prices of medical care, and especially due to cardiovascular injury; scient... more Due to the increasing prices of medical care, and especially due to cardiovascular injury; scientists are looking for inexpensive and less invasive ways to diagnose myocardial ischemia. Many studies have shown that the variations of the ST-segment in the ECG signal are an indicator for ischemia. For this purpose, this work proposes an approach based on a heart cell group model and principle component analysis, using a decision tree classifier to differentiate between the ischemic and healthy beats. The cardiac based model is based on a physiological model of the electrical cycle of depolarization and repolarization of the atria and ventricles. The model parameters are estimated by minimizing the squared error between the generated signal and the recorded ECG. The approach is applied to beats from the Long-Term ST database, which consists of 86 subjects and more than 20,000 beats in which 80% of the beats are ischemic and 20% are healthy. A 10-fold cross validation test is performed over the dataset. The accuracy of this approach is 91.62%, with sensitivity of 95.09% and specificity of 75.66%
A Recursive Fuzzy Logic Classifier, R-FL-C model is presented in this work for the design optimiz... more A Recursive Fuzzy Logic Classifier, R-FL-C model is presented in this work for the design optimization of Permanent Magnet Synchronous generators. The aim of the optimization process is to minimize the current level of harmonics, total losses and maximizing the developed power. The optimization technique uses the data obtained offline from the Finite Element State Space, FE-SS model of aerospace PM synchronous generators. Moreover, the R-FL-C consists of two modules. The first module is a Classification Module that utilizes a Fuzzy Logic Classifier to project the two dimensional discrete search space into one dimensional discrete search space. It also analyzes the statistics such as the range and cluster of the net cost function in order to create the knowledge to perform the projection. The second is a Recursive-Fuzzy Logic module which is recursively utilized to search for the optimal solution by minimizing the resulting one dimensional cost function
A novel electrophysiological cardiac model is introduced in this book. The proposed framework for... more A novel electrophysiological cardiac model is introduced in this book. The proposed framework for cardiac modeling considers six key regions that characterize the cardiac electrical activity. This allows the model to solve the forward and inverse electrocardiology problems in near real time. The major drawback of the current cardiac modeling methods is the computational complexity because they model more than 100,000 cells of the heart. This complexity does not allow the current techniques to be used in near real time diagnostics. In contrast to the previous models, the proposed cardiac model is used as a basis for two near real time clinical diagnostic applications. The first is the detection of an ischemic heart. The second is the localization of myocardial infarction. A brief overview of the cardiac activity is presented. Additionally, a historical review of the related fields is discussed. The proposed electrophysiological cardiac modeling method, including the cardiac model, fo...
Because the direction of regulatory agencies requires the study of potential proarrhythmic side e... more Because the direction of regulatory agencies requires the study of potential proarrhythmic side effects of drugs be conducted by skilled readers, the 2006 Physionet/Computers in Cardiology Challenge focuses on the need for clinically acceptable automatic measurement of the QT duration. This entry to the challenge approaches the problem from an inverse ECG perspective. The model parameters are estimated through the minimization of the squared error between the generated ECG signal from the activity of the AV node, endocardium and epicardium, and the recorded ECG. The PQ junction and the end of the T wave are determined from the activation and deactivation of the ventricular activity. This approach is tested on the PTB Diagnostic ECG Database, which contains 549 records from 294 subjects. The final score for this method was substantially improved from 130.70ms to 51.69ms as compared to the best score of 17.33ms for automatic methods.
The 2006 Physionet/Computers in Cardiology Challenge is motivated by the expected requirement of ... more The 2006 Physionet/Computers in Cardiology Challenge is motivated by the expected requirement of regulatory agencies for skilled readers to conduct QT duration studies of all drugs in clinical trials. However, clinically valid automatic methods would reduce the cost and time need to conduct such QT studies, which are crucial in determining potential proarrhythmic side effects, such as torsade de pointes, of non-antiarrhythmic drugs. The challenge dataset is the PTB Diagnostic ECG Database, which consists of 549 records from 294 subjects. This work proposes an integrative approach for the identification of the PQ junction and T-end of the QT interval. This novel approach uses the curvature of the Q- wave and the T-wave in order to identify an accurate isoelectric curve, between two consecutive peaks, that intersects the extremities of the features. The score for the challenge is 35.19 ms for this method compared to top score of 17.33
Proceedings of the 38th Design Automation Conference (IEEE Cat. No.01CH37232), 2001
We introduce a new verification methodology for modern microprocessors that uses a simple checker... more We introduce a new verification methodology for modern microprocessors that uses a simple checker processor to validate the execution of a companion high-performance processor. The checker can be viewed as an at-speed emulator that is formally verified to be compliant to an ISA specification. This verification approach enables the practical deployment of formal methods without impacting overall performance.
ASP-DAC 2004: Asia and South Pacific Design Automation Conference 2004 (IEEE Cat. No.04EX753), 2004
Proceedings 2002 Design, Automation and Test in Europe Conference and Exhibition, 2002
We introduce a new approach to Boolean satisfiability (SAT) that combines backtrack search techni... more We introduce a new approach to Boolean satisfiability (SAT) that combines backtrack search techniques and zero-suppressed binary decision diagrams (ZBDDs). This approach implicitly represents SAT instances using ZBDDs, and performs search using an efficient implementation of unit propagation on the ZBDD structure. The adaptation of backtrack search algorithms to such an implicit representation allows for a potential exponential increase in the size of problems that can be handled.
Proceedings of the ASP-DAC Asia and South Pacific Design Automation Conference, 2003., 2003
Determining the depth of sequential circuits is a crucial step towards the completeness of bounde... more Determining the depth of sequential circuits is a crucial step towards the completeness of bounded model checking proofs in hardware verification. In this paper, we formulate sequential depth computation as a logical inference problem for Quantified Boolean Formulas. We introduce a novel technique to simplify the complexity of the constructed formulas by applying simple transformations to the circuit netlist. We also study the structure of the resulting simplified QBFs and construct an efficient SAT-based algorithm to check their satisfiability. We report promising experimental results on some of the ISCAS 89 benchmarks.
IEEE Design and Test of Computers, 2005
CHECKING WHETHER two models of a design are functionally equivalent is a crucial step in a transf... more CHECKING WHETHER two models of a design are functionally equivalent is a crucial step in a transforma-tion-based design flow, in which a designer obtains lower-level implementation models by manual or automatic translation from higher-level specification models. In a ...
2007 Computers in Cardiology, 2007
2008 Computers in Cardiology, 2008
The 2008 Computers in Cardiology Challenge is to automatically identify and measure T-wave altern... more The 2008 Computers in Cardiology Challenge is to automatically identify and measure T-wave alternans. The study presented here applies an electrophysiological cardiac model to the problem of characterizing the Twave variability. Thus, the hypothesis is that the existence and magnitude of T-wave alternans can be identified and measured using a cardiac inverse problem approach, where the magnitude of the alternans are measured in the model space. The dataset used in this study is a collection of records from selected databases in the Physionet databank. Additionally, a simulated ECG dataset is used to study the sensitivity and specificity of the proposed approach under various noise conditions. Results on the simulated ECG data set show that the approach is able to differentiate between 5, 10, 20, and 100 microvolt T-wave alternans in the presence of various noises between -25 and 5dB SNR. The score from the challenge, which is the Kendall rank correlation coefficient, is 0.331.
2007 Computers in Cardiology, 2007
Due to the lack between clinical methods and applications used to diagnose ischemic heart disease... more Due to the lack between clinical methods and applications used to diagnose ischemic heart disease, the 2007 Physionet/Computers in Cardiology challenge focuses on the ability to identify the segments, extent, and centroid of infarcts through ECG signals and body surface maps. The results from the participants are compared to a gold standard that consists of expert analysis of gadoliniumenhanced MRI data. The main hypothesis in this work is that the ordinary 12 ordinary leads contain the necessary information to identify the segment of the infarct. This hypothesis is tested using a reconstructed phase space and Gaussian Mixture Model approach in order to identify the infarcted segments. Since the challenge dataset consists of only two records for training and two for testing, the RPS/GMM approach is trained on the infarcted records from the PTB Diagnostics database and tested on the challenge data. The final score for the classification method was 1.15 out of maximum of 2.
2006 12th Biennial IEEE Conference on Electromagnetic Field Computation, 2006
A novel recursive fuzzy-logic classifying (R-FL-C) approach for the design optimization of perman... more A novel recursive fuzzy-logic classifying (R-FL-C) approach for the design optimization of permanent magnet generators is presented. This approach is used to cut the search space and to avoid local minima during the optimization process. The search space database is established using knowledge obtained off-line from finite-element state-space models. The application of the approach to a prototype aerospace type PM generator resulted in a toothless stator design with lower weight and improved performance. The results are validated by comparison to test data.
INTERMAG Asia 2005. Digests of the IEEE International Magnetics Conference, 2005., 2005
AC actuators are considered simple devices when it comes to their construction. However, due to t... more AC actuators are considered simple devices when it comes to their construction. However, due to the coupled nature of its electromagnetic and mechanical forces; it is very difficult to accurately characterize its performance. The drawback with such approaches is that some are in accurate and make many simplifying assumptions and others are computationally intensive. As appreciated from above, these approaches
IEEE Conference on Electromagnetic Field Computation, 2006
A novel recursive fuzzy-logic classifying (R-FL-C) approach for the design optimization of perman... more A novel recursive fuzzy-logic classifying (R-FL-C) approach for the design optimization of permanent magnet generators is presented. This approach is used to cut the search space and to avoid local minima during the optimization process. The search space database is established using knowledge obtained off-line from finite-element state-space models. The application of the approach to a prototype aerospace type PM generator resulted in a toothless stator design with lower weight and improved performance. The results are validated by comparison to test data.
Due to the increasing prices of medical care, and especially due to cardiovascular injury; scient... more Due to the increasing prices of medical care, and especially due to cardiovascular injury; scientists are looking for inexpensive and less invasive ways to diagnose myocardial ischemia. Many studies have shown that the variations of the ST-segment in the ECG signal are an indicator for ischemia. For this purpose, this work proposes an approach based on a heart cell group model and principle component analysis, using a decision tree classifier to differentiate between the ischemic and healthy beats. The cardiac based model is based on a physiological model of the electrical cycle of depolarization and repolarization of the atria and ventricles. The model parameters are estimated by minimizing the squared error between the generated signal and the recorded ECG. The approach is applied to beats from the Long-Term ST database, which consists of 86 subjects and more than 20,000 beats in which 80% of the beats are ischemic and 20% are healthy. A 10-fold cross validation test is performed over the dataset. The accuracy of this approach is 91.62%, with sensitivity of 95.09% and specificity of 75.66%
A Recursive Fuzzy Logic Classifier, R-FL-C model is presented in this work for the design optimiz... more A Recursive Fuzzy Logic Classifier, R-FL-C model is presented in this work for the design optimization of Permanent Magnet Synchronous generators. The aim of the optimization process is to minimize the current level of harmonics, total losses and maximizing the developed power. The optimization technique uses the data obtained offline from the Finite Element State Space, FE-SS model of aerospace PM synchronous generators. Moreover, the R-FL-C consists of two modules. The first module is a Classification Module that utilizes a Fuzzy Logic Classifier to project the two dimensional discrete search space into one dimensional discrete search space. It also analyzes the statistics such as the range and cluster of the net cost function in order to create the knowledge to perform the projection. The second is a Recursive-Fuzzy Logic module which is recursively utilized to search for the optimal solution by minimizing the resulting one dimensional cost function
A novel electrophysiological cardiac model is introduced in this book. The proposed framework for... more A novel electrophysiological cardiac model is introduced in this book. The proposed framework for cardiac modeling considers six key regions that characterize the cardiac electrical activity. This allows the model to solve the forward and inverse electrocardiology problems in near real time. The major drawback of the current cardiac modeling methods is the computational complexity because they model more than 100,000 cells of the heart. This complexity does not allow the current techniques to be used in near real time diagnostics. In contrast to the previous models, the proposed cardiac model is used as a basis for two near real time clinical diagnostic applications. The first is the detection of an ischemic heart. The second is the localization of myocardial infarction. A brief overview of the cardiac activity is presented. Additionally, a historical review of the related fields is discussed. The proposed electrophysiological cardiac modeling method, including the cardiac model, fo...
Because the direction of regulatory agencies requires the study of potential proarrhythmic side e... more Because the direction of regulatory agencies requires the study of potential proarrhythmic side effects of drugs be conducted by skilled readers, the 2006 Physionet/Computers in Cardiology Challenge focuses on the need for clinically acceptable automatic measurement of the QT duration. This entry to the challenge approaches the problem from an inverse ECG perspective. The model parameters are estimated through the minimization of the squared error between the generated ECG signal from the activity of the AV node, endocardium and epicardium, and the recorded ECG. The PQ junction and the end of the T wave are determined from the activation and deactivation of the ventricular activity. This approach is tested on the PTB Diagnostic ECG Database, which contains 549 records from 294 subjects. The final score for this method was substantially improved from 130.70ms to 51.69ms as compared to the best score of 17.33ms for automatic methods.
The 2006 Physionet/Computers in Cardiology Challenge is motivated by the expected requirement of ... more The 2006 Physionet/Computers in Cardiology Challenge is motivated by the expected requirement of regulatory agencies for skilled readers to conduct QT duration studies of all drugs in clinical trials. However, clinically valid automatic methods would reduce the cost and time need to conduct such QT studies, which are crucial in determining potential proarrhythmic side effects, such as torsade de pointes, of non-antiarrhythmic drugs. The challenge dataset is the PTB Diagnostic ECG Database, which consists of 549 records from 294 subjects. This work proposes an integrative approach for the identification of the PQ junction and T-end of the QT interval. This novel approach uses the curvature of the Q- wave and the T-wave in order to identify an accurate isoelectric curve, between two consecutive peaks, that intersects the extremities of the features. The score for the challenge is 35.19 ms for this method compared to top score of 17.33
Proceedings of the 38th Design Automation Conference (IEEE Cat. No.01CH37232), 2001
We introduce a new verification methodology for modern microprocessors that uses a simple checker... more We introduce a new verification methodology for modern microprocessors that uses a simple checker processor to validate the execution of a companion high-performance processor. The checker can be viewed as an at-speed emulator that is formally verified to be compliant to an ISA specification. This verification approach enables the practical deployment of formal methods without impacting overall performance.
ASP-DAC 2004: Asia and South Pacific Design Automation Conference 2004 (IEEE Cat. No.04EX753), 2004
Proceedings 2002 Design, Automation and Test in Europe Conference and Exhibition, 2002
We introduce a new approach to Boolean satisfiability (SAT) that combines backtrack search techni... more We introduce a new approach to Boolean satisfiability (SAT) that combines backtrack search techniques and zero-suppressed binary decision diagrams (ZBDDs). This approach implicitly represents SAT instances using ZBDDs, and performs search using an efficient implementation of unit propagation on the ZBDD structure. The adaptation of backtrack search algorithms to such an implicit representation allows for a potential exponential increase in the size of problems that can be handled.
Proceedings of the ASP-DAC Asia and South Pacific Design Automation Conference, 2003., 2003
Determining the depth of sequential circuits is a crucial step towards the completeness of bounde... more Determining the depth of sequential circuits is a crucial step towards the completeness of bounded model checking proofs in hardware verification. In this paper, we formulate sequential depth computation as a logical inference problem for Quantified Boolean Formulas. We introduce a novel technique to simplify the complexity of the constructed formulas by applying simple transformations to the circuit netlist. We also study the structure of the resulting simplified QBFs and construct an efficient SAT-based algorithm to check their satisfiability. We report promising experimental results on some of the ISCAS 89 benchmarks.
IEEE Design and Test of Computers, 2005
CHECKING WHETHER two models of a design are functionally equivalent is a crucial step in a transf... more CHECKING WHETHER two models of a design are functionally equivalent is a crucial step in a transforma-tion-based design flow, in which a designer obtains lower-level implementation models by manual or automatic translation from higher-level specification models. In a ...
2007 Computers in Cardiology, 2007
2008 Computers in Cardiology, 2008
The 2008 Computers in Cardiology Challenge is to automatically identify and measure T-wave altern... more The 2008 Computers in Cardiology Challenge is to automatically identify and measure T-wave alternans. The study presented here applies an electrophysiological cardiac model to the problem of characterizing the Twave variability. Thus, the hypothesis is that the existence and magnitude of T-wave alternans can be identified and measured using a cardiac inverse problem approach, where the magnitude of the alternans are measured in the model space. The dataset used in this study is a collection of records from selected databases in the Physionet databank. Additionally, a simulated ECG dataset is used to study the sensitivity and specificity of the proposed approach under various noise conditions. Results on the simulated ECG data set show that the approach is able to differentiate between 5, 10, 20, and 100 microvolt T-wave alternans in the presence of various noises between -25 and 5dB SNR. The score from the challenge, which is the Kendall rank correlation coefficient, is 0.331.
2007 Computers in Cardiology, 2007
Due to the lack between clinical methods and applications used to diagnose ischemic heart disease... more Due to the lack between clinical methods and applications used to diagnose ischemic heart disease, the 2007 Physionet/Computers in Cardiology challenge focuses on the ability to identify the segments, extent, and centroid of infarcts through ECG signals and body surface maps. The results from the participants are compared to a gold standard that consists of expert analysis of gadoliniumenhanced MRI data. The main hypothesis in this work is that the ordinary 12 ordinary leads contain the necessary information to identify the segment of the infarct. This hypothesis is tested using a reconstructed phase space and Gaussian Mixture Model approach in order to identify the infarcted segments. Since the challenge dataset consists of only two records for training and two for testing, the RPS/GMM approach is trained on the infarcted records from the PTB Diagnostics database and tested on the challenge data. The final score for the classification method was 1.15 out of maximum of 2.
2006 12th Biennial IEEE Conference on Electromagnetic Field Computation, 2006
A novel recursive fuzzy-logic classifying (R-FL-C) approach for the design optimization of perman... more A novel recursive fuzzy-logic classifying (R-FL-C) approach for the design optimization of permanent magnet generators is presented. This approach is used to cut the search space and to avoid local minima during the optimization process. The search space database is established using knowledge obtained off-line from finite-element state-space models. The application of the approach to a prototype aerospace type PM generator resulted in a toothless stator design with lower weight and improved performance. The results are validated by comparison to test data.
INTERMAG Asia 2005. Digests of the IEEE International Magnetics Conference, 2005., 2005
AC actuators are considered simple devices when it comes to their construction. However, due to t... more AC actuators are considered simple devices when it comes to their construction. However, due to the coupled nature of its electromagnetic and mechanical forces; it is very difficult to accurately characterize its performance. The drawback with such approaches is that some are in accurate and make many simplifying assumptions and others are computationally intensive. As appreciated from above, these approaches
IEEE Conference on Electromagnetic Field Computation, 2006
A novel recursive fuzzy-logic classifying (R-FL-C) approach for the design optimization of perman... more A novel recursive fuzzy-logic classifying (R-FL-C) approach for the design optimization of permanent magnet generators is presented. This approach is used to cut the search space and to avoid local minima during the optimization process. The search space database is established using knowledge obtained off-line from finite-element state-space models. The application of the approach to a prototype aerospace type PM generator resulted in a toothless stator design with lower weight and improved performance. The results are validated by comparison to test data.