Sina Khanmohammadi | University of Oklahoma (original) (raw)

Books by Sina Khanmohammadi

a new fuzzy approach is developed for defining the general criticality of activities where some o... more a new fuzzy approach is developed for defining the general criticality of activities where some other features such as probability of finishing on time zone, probability of impact, impact threat and ability to retaliate are considered as criticality factors of activities in project management process. In this way the risky situation (vulnerability) of activities are calculated by using fuzzy inference system. Activities are prioritized and classified by means of a fuzzy decision making procedure. The effect of considering such factors on project duration and cost are compared with classic PERT - where only the slack times are considered as criticality factors of activities. The calculated factors of criteria are used for path planning of rescue robot in disaster situations by means of GERT.

Papers by Sina Khanmohammadi

Clinical Neurophysiology, 2018

Objective: We devise a data-driven framework to assess the level of consciousness in etiologicall... more Objective:
We devise a data-driven framework to assess the level of consciousness in etiologically heterogeneous comatose patients using intrinsic dynamical changes of resting-state Electroencephalogram (EEG) signals.

Methods:
EEG signals were collected from 54 comatose patients (GCS≤8) and 20 control patients (GCS>8). We analyzed the EEG signals using a new technique, termed Intrinsic Network Reactivity Index (INRI), that aims to assess the overall lability of brain dynamics without the use of extrinsic stimulation. The proposed technique uses three sigma EEG events as a trigger for ensuing changes to the directional derivative of signals across the EEG montage.

Results:
The INRI had a positive relationship with GCS and was significantly different between various levels of consciousness. In comparison, classical band-limited power analysis did not show any specific patterns correlated to GCS.

Conclusions:
These findings suggest that reaching low variance EEG activation patterns becomes progressively harder as the level of consciousness of patients deteriorate, and provide a quantitative index based on passive measurements that characterize this change.

Significance:
Our results emphasize the role of intrinsic brain dynamics in assessing the level of consciousness in coma patients and the possibility of employing simple electrophysiological measures to recognize the severity of disorders of consciousness (DOC).

2017 51st Asilomar Conference on Signals, Systems, and Computers, 2018

Recent studies suggest that disruptions in resting state functional connectivity - a measure of s... more Recent studies suggest that disruptions in resting state functional connectivity - a measure of stationary statistical association between brain regions - can be used as an objective marker of brain injury. However, fewer characterizations have examined the disruption of intrinsic brain dynamics after brain injury. Here, we examine this issue using electroencephalo-graphic (EEG) data from brain-injured patients, together with a control analysis wherein we quantify the effect of the injury on the ability of intrinsic event responses to traverse their respective state spaces. More specifically, the lability of intrinsically evoked brain activity was assessed by collapsing three sigma event responses in all channels of the obtained EEG signals into a low-dimensional space. The directional derivative of these responses was then used to assay the extent to which brain activity reaches low-variance subspaces. Our findings suggest that intrinsic dynamics extracted from resting state EEG signals can differentiate various levels of consciousness in severe cases of coma. More specifically the cost of moving from one state to another in the state-space trajectories of the underlying dynamics becomes lower as the level of consciousness of patients deteriorates.

IISE Annual Conference, 2016

Understanding the behavior of a terrorist group is a complex phenomenon because of the uncertaint... more Understanding the behavior of a terrorist group is a complex phenomenon because of the uncertainty in strategies and tactics used by terrorists. Current literature suggests that terrorism has an evolutionary nature and terrorist groups change behavior according to a government's counter-terrorism policies. The goal of this research is to model how terrorist groups and government influence each other. In this regards, an agent-based modeling with network topology is used to model the system composed of interacting agents (attacks) and groups. The terrorist groups' tactics are modeled based on the success rate of attacks and the defense level of a particular location. The proposed model is validated using real-world data of suicide attacks in Iraq. The model can be used to support governmental counter-terrorism policy-making.

Indirect quantification of the synchronization between two dynamical systems from measured experi... more Indirect quantification of the synchronization between two dynamical systems from measured experimental data has gained much attention in recent years, especially in the computational neuroscience community where the exact model of the neuronal dynamics is unknown. In this regard, one of the most promising methods for quantifying the interrelationship between nonlinear non-stationary systems is known as Synchronization Likelihood (SL), which is based on the likelihood of the auto-recurrence of embedding vectors (similar patterns) in multiple dynamical systems. However, synchronization likelihood method uses the Euclidean distance to determine the similarity of two patterns, which is known to be sensitive to outliers. In this study, we propose a discrete synchronization likelihood (DSL) method to overcome this limitation by using the Manhattan distance in the discrete domain (l1 norm on discretized signals) to identify the auto-recurrence of embedding vectors. The proposed method was tested using unidirectional and bidirectional identical/non-identical coupled Hénon Maps, a Watts-Strogatz small-world network with nonlinearly coupled nodes based on Kuramoto model and the real world ADHD-200 fMRI benchmark dataset. According to the results, the proposed method shows comparable and in some cases better performance than the conventional SL method, especially when the underlying highly connected coupled dynamical system goes through subtle changes in the bivariate case or sudden shifts in the multivariate case.

Epilepsy is one of the most common neurological disorders in the world. Prompt detection of seizu... more Epilepsy is one of the most common neurological disorders in the world. Prompt detection of seizure onset from electroencephalogram (EEG) signals can improve the treatment of epileptic patients. This paper presents a new adaptive patientspecific seizure onset detection framework that dynamically selects a feature from enhanced EEG signals to discriminate seizures from normal brain activity. The proposed framework employs principle component analysis (PCA) and common spatial patterns (CSP) to enhance the EEG signals and uses the extracted discriminative feature as an input for adaptive distance-based change point detector to identify the seizure onsets. Experimental results from the CHB-MIT dataset show the computational efficiency of the proposed method (analyzing EEG signals in a time window of 3 seconds within 0.1 seconds using a Core i7 PC) while providing comparable results to the existing methods in terms of average sensitivity, latency, and false detection rate. The proposed method is advantageous for real-time monitoring of epileptic patients and could be used to improve early diagnosis and treatment of patients suffering from recurrent seizures.

One of the biggest problems for major airline is predicting flight delay. Airlines try to reduce ... more One of the biggest problems for major airline is predicting flight delay. Airlines try to reduce delays to gain the loyalty of their customers. Hence, a prediction model that airliners can use to forecast possible delays is of significant importance. In this regards, artificial neural network (ANN) techniques can be beneficial for this application. One of the main challenges of using ANNs is handling nominal variables. 1-of-N encoding is widely used to deal with this problem, however, this method is known to reduce the performance of ANN's by introducing multicollinearity. In this paper, we introduce a new type of multilevel input layer ANN that can handle nominal variables and is interpretable in a sense that one can easily see the relationships between different input variables and output variables. As a case study, the proposed method was applied to predict the delay of incoming flights at JFK airport, where the neurons of each sublayer of the input layer symbolize the delay sources at different levels of the system, and the activation of each neuron represents the possibility of being the source of overall delay. Finally, we compared the proposed approach with the traditional gradient descent back propagation ANN model and the proposed model was able to outperform the traditional backpropagation method in terms of the prediction error (root mean squared error) and time required to train the ANN model.

Existing seizure onset detection methods usually rely on a large number of extracted features reg... more Existing seizure onset detection methods usually rely on a large number of extracted features regardless of computational efficiency, which reduces their applicability for real-time seizure detection. In this study, a simple distance based seizure onset detection algorithm is proposed to distinguish seizure and non-seizure EEG signals. The proposed framework first applies the common spatial patterns (CSP) method to enhance the signal-to-noise ratio and reduce the dimensionality of EEG signals, and then uses the autocorrelation of the averaged spatially filtered signal to classify incoming signals into a seizure or non-seizure state. The proposed approach was tested using CHB-MIT dataset that contains continuous scalp EEG recordings from 23 patients. The results showed ∼∼95.87 % sensitivity with an average latency of 2.98 s and 2.89 % false detection rate. More interestingly, the average process time required to classify each window (1–5 s of EEG signals) was 0.09 s. The outcome of this study has a high potential to improve the automatic seizure onset detection from EEG recordings and could be used as a basis for developing real-time monitoring systems for epileptic patients.

Data clustering has been proven to be an effective method for discovering structure in medical da... more Data clustering has been proven to be an effective method for discovering structure in medical datasets. The majority of clustering algorithms produce exclusive clusters meaning that each sample can belong to one cluster only. However, most real-world medical datasets have inherently overlapping information, which could be best explained by overlapping clustering methods that allow one sample belong to more than one cluster. One of the simplest and most efficient overlapping clustering methods is known as overlapping k-means (OKM), which is an extension of the traditional k-means algorithm. Being an extension of the k-means algorithm, the OKM method also suffers from sensitivity to the initial cluster centroids. In this paper, we propose a hybrid method that combines k-harmonic means and overlapping k-means algorithms (KHM-OKM) to overcome this limitation. The main idea behind KHM-OKM method is to use the output of KHM method to initialize the cluster centers of OKM method. We have tested the proposed method using FBCubed metric, which has been shown to be the most effective measure to evaluate overlapping clustering algorithms regarding homogeneity, completeness, rag bag, and cluster size-quantity tradeoff. According to results from ten publicly available medical datasets, the KHM-OKM algorithm outperforms the original OKM algorithm and can be used as an efficient method for clustering medical datasets.

Hospital readmission prediction continues to be a highly-encouraged area of investigation mainly ... more Hospital readmission prediction continues to be a highly-encouraged area of investigation mainly because of the readmissions reduction program by the Centers for Medicare and Medicaid services (CMS). The overall goal is to reduce
the number of early hospital readmissions by identifying the key risk factors that cause hospital readmissions. This is
especially important in Intensive Care Unit (ICU), where patient readmission increases the likelihood of mortality due
to the worsening of the patient condition. Traditional approaches use simple logistic regression or other linear classification methods to identify the key features that provide high prediction accuracy. However, these methods are not
sufficient since they cannot capture the complex patterns between different features. In this paper, we propose a hybrid
Evolutionary Simulating Annealing LASSO Logistic Regression (ESALOR) model to accurately predict the hospital
readmission rate and identify the important risk factors. The proposed model combines the evolutionary simulated
annealing method with a sparse logistic regression model of Lasso. The ESALOR model was tested on a publicly
available diabetes readmission dataset, and the results show that the proposed model provides better results compared
to conventional classification methods including Support Vector Machines (SVM), Decision Tree, Naive Bayes, and
Logistic Regression.

In recent years, terrorist attacks around the world have begun to develop more complex strategies... more In recent years, terrorist attacks around the world have begun to develop more complex strategies and tactics that are
not easily recognizable. Furthermore, in uncertain situations, agencies need to know whether the perpetrator was a
terrorist or someone motivated by other factors (e.g. criminal activity) so that they can develop appropriate strategies
to capture the responsible organizations and people. In most research studies, terrorist activity detection focuses
on either individual incidents, which do not take into account the dynamic interactions among them, or network
analysis, which leaves aside the functional roles of individuals while capturing interactions and giving a general idea
about networks. In this study, we propose a unified approach that applies pattern classification techniques to network
topology and features of incidents. The detected patterns are used in conjunction with an evolutionary adaptive neural
fuzzy inference system to detect future incidents of terrorism. Finally, the proposed approach was tested and validated
using a real world case study that consists of incidents in Iraq. The experimental results show that our approach
outperforms other traditional detection approaches. Policymakers can use the approach for timely understanding and detection of terrorist activity thus enabling precautions to be taken against future attacks.

Terrorists are increasingly using suicide attacks to attack different targets. The government fin... more Terrorists are increasingly using suicide attacks to attack different targets. The government finds it challenging to
track these attacks since the terrorists have learned from experience to avoid unsecured communications such as
social media. Therefore, we propose a new approach that will predict the characteristics of future suicide attacks
by analyzing the relationship between past attacks. The proposed approach first identifies relevant features using a
graph-based feature selection (GBFS) method, then calculates the relationship between selected features via a new
similarity measure capable of handling both categorical and numerical features. The proposed approach was tested
using a second terrorism data set; we were able to successfully predict the characteristics of this new testing data set
using patterns extracted from the original data set. The results could potentially enable law enforcement agencies to
propose reactive strategies

Understanding the behavior of a terrorist group is a complex phenomenon because of the uncertaint... more Understanding the behavior of a terrorist group is a complex phenomenon because of the uncertainty in strategies and
tactics used by terrorists. Current literature suggests that terrorism has an evolutionary nature and terrorist groups
change behavior according to a government’s counter-terrorism policies. The goal of this research is to model how
terrorist groups and government influence each other. In this regards, an agent-based modeling with network topology
is used to model the system composed of interacting agents (attacks) and groups. The terrorist groups’ tactics are
modeled based on the success rate of attacks and the defense level of a particular location. The proposed model is
validated using real-world data of suicide attacks in Iraq. The model can be used to support governmental counterterrorism
policy-making.

Knowledge-based systems such as expert systems are of particular interest in medical applications... more Knowledge-based systems such as expert systems are of particular interest in medical applications as extracted if-then rules can provide interpretable results. Various rule induction algorithms have been proposed to effectively extract knowledge from data, and they can be combined with classification methods to form rule-based classifiers. However, most of the rule-based classifiers can not directly handle numerical data such as blood pressure. A data preprocessing step called discretization is required to convert such numerical data into a categorical format. Existing discretization algorithms do not take into account the multimodal class densities of numerical variables in datasets, which may degrade the performance of rule-based classifiers. In this paper, a new Gaussian Mixture Model based Discretization Algorithm (GMBD) is proposed that preserve the most frequent patterns of the original dataset by taking into account the multimodal distribution of the numerical variables. The effectiveness of GMBD algorithm was verified using six publicly available medical datasets. According to the experimental results, the GMBD algorithm outperformed five other static discretization methods in terms of the number of generated rules and classification accuracy in the associative classification algorithm. Consequently, our proposed approach has a potential to enhance the performance of rule-based classifiers used in clinical expert systems.

The present study aims to build a classification model that discriminates between chronological a... more The present study aims to build a classification model that discriminates between chronological ages of subjects based on resting-state electroencephalography (EEG) data collected from a community sample of 269 children aged 7 to 11. Specifically, spectral power densities in four classical frequency bands: Delta (0.5–3 Hz), Theta (4–7 Hz), Alpha (8–12 Hz) and Beta (14–25 Hz) were extracted for each electrode as features, and fed to three classification algorithms including logistic regression (LR), support vector machine (SVM), and least absolute shrinkage and selection operator (Lasso). In addition, principal component analysis (PCA) was used to reduce the dimensions of the feature space. The results demonstrated that SVM and Lasso evidenced better performance (maximal accuracy = 80.68 ± 2.01% by SVM and 77.82 ± 2.11% by Lasso) when applied to original feature space, but LR yielded the best performance with PCA (80.72 ± 1.73%). The accuracy of binary classification exhibited a decreasing trend with diminishing chronological gaps between the groups.

In this paper a new fuzzy approach is developed for defining the general criticality of activitie... more In this paper a new fuzzy approach is developed for defining the general criticality of activities where some other features such as probability of finishing on time zone, probability of impact, impact threat and ability to retaliate are considered as criticality factors of activities in project management process. In this way the risky situation (vulnerability) of activities are calculated by using fuzzy inference system. Activities are prioritized and classified by means of a fuzzy decision making procedure. The effect of considering such ...

Today, there is a significant demand for fast, accurate, and automated methods for the discrimina... more Today, there is a significant demand for fast, accurate, and automated methods for the discrimination of latent patterns in neuroelectric waveforms. One of the main challenges is the development of efficient feature extraction tools to utilize the rich spatio-temporal information inherent in large scale human electrocortical activity. In this paper, our aim is to isolate the most suitable feature extraction method for accurate classification of EEG data related to distinct modes of sensorimotor integration. Our results demonstrate that with some user-dependent input for feature space constraint, a simple classification framework can be developed to accurately distinguish between brain electrical activity patterns during two distinct conditions.

Supervised classification algorithms have become very popular because of their potential applicat... more Supervised classification algorithms have become very popular because of their potential application in developing intelligent data analytic software. These algorithms are known to be sensitive to the characteristic and structure of input datasets, therefore, researchers use different algorithm selection methods to select the most suitable classification algorithm for specific dataset. These methods do not consider the uncertainty about input dataset, and relative importance of different performance measurements (such as speed, accuracy, and memory usage) in the target application domain. Therefore, these methods are not appropriate for software development. This is especially true in medical field where various high dimensional noisy data might be used with the software. Hence, software developers need to select one supervised classification algorithm that has the highest potential to provide good performance in wide variety of datasets. In this regard, an Analytic Hierarchy Process (AHP) based meta-learning algorithm is proposed to identify the most suitable supervised classification algorithm for developing clinical decision support system (CDSS). The results from ten publicly available medical datasets indicate that Support Vector Machine (SVM) has the highest potential to perform well on variety of medical datasets.

The aircraft landings scheduling problem at an airport has become very challenging due to the inc... more The aircraft landings scheduling problem at an airport has become very challenging due to the increase of air traffic. Traditionally, this problem has been widely studied by formulating it as an optimization model solved by various operation research approaches. However, these approaches are not able to capture the dynamic nature of the aircraft landing scheduling problem appropriately and handle uncertainty easily. A systems approach provides an alternative to solve such a problem from a systematic perspective. In this regard, the concept of general systems problem solving (GSPS) was first introduced in 1970s, and yet the power of the GSPS methodology is not fully discovered as it had only been applied to few domains. In this paper, a new general systems problem solving framework integrating computational intelligence techniques (GSPS-CI) is introduced. The two main functions of the framework are: (1) adaptive network based fuzzy inference system (ANFIS) to predict flight delays, and (2) fuzzy decision making procedure to schedule aircraft landings. The effectiveness of the GSPS-CI framework is tested on the JFK airport in USA, one of the most complex real-life systems.

Human resources are essential in manufacturing and service industries, and one of the main issues... more Human resources are essential in manufacturing and service industries, and one of the main issues regarding human resources is how to predict the risk of human errors in different circumstances. Human errors play a significant role in the overall performance of manufacturing and service industries. For example, according to the Institute of Medicine (IOM) report, called “To Err Is Human”, 44,000 to 98,000 patients die each year as a result of human caused medical errors in healthcare service industry.In this paper, a new fuzzy inference system approach is proposed to predict the risk of human errors. A hierarchical fuzzy inference system consisting of different sub FISs is applied, where each FIS represents different levels of the system. The independent variables including personal and environmental factors are fed to sub FISs to determine the intermediate variables that affect the level of human errors. The output of these FISs are fed into a mathematical model to determine the level of human errors in different circumstances. An example is provided to demonstrate how the results of the model can be interpreted and used for identifying appropriate strategies to decrease the risk of human errors.

Clinical Neurophysiology, 2018

2017 51st Asilomar Conference on Signals, Systems, and Computers, 2018

IISE Annual Conference, 2016

Understanding the behavior of a terrorist group is a complex phenomenon because of the uncertaint... more Understanding the behavior of a terrorist group is a complex phenomenon because of the uncertainty in strategies and
tactics used by terrorists. Current literature suggests that terrorism has an evolutionary nature and terrorist groups
change behavior according to a government’s counter-terrorism policies. The goal of this research is to model how
terrorist groups and government influence each other. In this regards, an agent-based modeling with network topology
is used to model the system composed of interacting agents (attacks) and groups. The terrorist groups’ tactics are
modeled based on the success rate of attacks and the defense level of a particular location. The proposed model is
validated using real-world data of suicide attacks in Iraq. The model can be used to support governmental counterterrorism
policy-making.

Association rule based classification is one of the popular data mining techniques applied in med... more Association rule based classification is one of the popular data mining techniques applied in medical domain. The major advantage is its interpretable results that medical doctors can easily adopt for diagnostic decision-making. The classification framework consists of data discretization, association rule generation, and classification. The discretization step is required to convert numerical features such as blood pressure into a categorical format, to make it suitable for association rules mining. Existing discretization methods such as Omega algorithm construct several non-adjacent intervals to represent new categorical variables. However, such algorithms are not generalizable because of failure to recognize new observations that lie between constructed intervals; this will impact the accuracy of association rules based classification. To overcome this problem, an associative classification framework based on an improved discretization algorithm is proposed. In the discretization step, a centroid of each constructed interval is identified to represent that interval. Using the identified centroids, numerical data is discretized and fed to an Apriori algorithm for rule induction. Consequently, a new observation is classified using a majority-voting scheme of the generated rules. The framework was tested on various medical datasets from the University of California Irvine repository and the Aneurisk dataset repository. The results show that the proposed framework gives a higher accuracy when compared to existing approaches.