Igor Griva
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Igor Griva has a total of 39 co-authors. Here are the top co-authors by number of shared publications:
- Nikolai Lebedev
Center for Bio/Molecular Science and Engineering US Naval Research Laboratory Washington, DC 20375 USA
4 shared publications - Roman A. Polyak
George Mason University
4 shared publications - Leonard M. Tender
Center for Bio/Molecular Science and Engineering, Naval Research Laboratory, Washington, USA
3 shared publications - Matthew D. Yates
Center for Biomolecular Science and Engineering, US Naval Research Laboratory, Washington, USA
3 shared publications - Jason M. Kinser
George Mason University
2 shared publications - John Kalung Leung
Computational and Data Sciences Department Computational Sciences and Informatics College of Science George Mason University 4400 University Drive 22030 Fairfax Virginia USA
2 shared publications
Latest Publications
- Open Access
An extreme Gradient Boosting (XGBoost) Trees approach to Detect and Identify Unlawful Insider Trading (UIT) Transactions
Corporate insiders have control of material non-public preferential information (MNPI). Occasionally, the insiders strategically bypass legal and regulatory safeguards to exploit MNPI in their execution of securities trading. Due to a large volume of transactions a detection of unlawful insider trading becomes an arduous task for humans to examine and identify underlying patterns from the insider's behavior. On the other hand, innovative machine learning architectures have shown promising results for analyzing large-scale and complex data with hidden patterns. One such popular technique is eXtreme Gradient Boosting (XGBoost), the state-of-the-arts supervised classifier. We, hence, resort to and apply XGBoost to alleviate challenges of identification and detection of unlawful activities. The results demonstrate that XGBoost can identify unlawful transactions with a high accuracy of 97 percent and can provide ranking of the features that play the most important role in detecting fraudulent activities.
Open AccessAn extreme Gradient Boosting (XGBoost) Trees approach to Detect and Identify Unlawful Insider Trading (UIT) Transactions
Corporate insiders have control of material non-public preferential information (MNPI). Occasionally, the insiders strategically bypass legal and regulatory safeguards to exploit MNPI in their execution of securities trading. Due to a large volume of transactions a detection of unlawful insider trading becomes an arduous task for humans to examine and identify underlying patterns from the insider's behavior. On the other hand, innovative machine learning architectures have shown promising results for analyzing large-scale and complex data with hidden patterns. One such popular technique is eXtreme Gradient Boosting (XGBoost), the state-of-the-arts supervised classifier. We, hence, resort to and apply XGBoost to alleviate challenges of identification and detection of unlawful activities. The results demonstrate that XGBoost can identify unlawful transactions with a high accuracy of 97 percent and can provide ranking of the features that play the most important role in detecting fraudulent activities.
- Open Access
- 26 July 2025
- Published by Springer Nature in Journal of Optimization Theory and Applications
- Vol. 207 (2) , 1-34
Finding Equilibrium in Some Economics and Game Models
We consider numerical aspects of finding classical J. Nash’s equilibrium in concave n-persons game, nonlinear equilibrium (NE), as an alternative to primal and dual linear programming (LP) problems, and recently introduced nonlinear production-consumption equilibrium (NPCE). The problems are particular cases of a general nonlinear equilibrium problem, which is equivalent to a variational inequality (VI). The corresponding VIs have simple feasible sets, that the projection on them is a low cost operation. Therefore, we apply two projection methods for finding the equilibrium: pseudo-gradient projection (PGP) and extra pseudo-gradient (EPG). We present and analyze results obtained on random generated sets of these three classes of problems. The obtained results show expected advantages of the EPG over PGP. What is most important: the number of iterations requited by EPG method to find an approximation for the equilibrium with a given accuracy grows linearly with the number of products in case of NE and NPCE, or with the number of active strategies in case of J. Nash’s equilibrium. The number of operations, or solution time grows as a cube of the corresponding parameters. These results corroborate the complexity bounds established in [18–20] under reasonable assumptions on the input data.
- 26 July 2025
- Published by Springer Nature in Journal of Optimization Theory and Applications
- Vol. 207 (2) , 1-34
Open AccessFinding Equilibrium in Some Economics and Game Models
We consider numerical aspects of finding classical J. Nash’s equilibrium in concave n-persons game, nonlinear equilibrium (NE), as an alternative to primal and dual linear programming (LP) problems, and recently introduced nonlinear production-consumption equilibrium (NPCE). The problems are particular cases of a general nonlinear equilibrium problem, which is equivalent to a variational inequality (VI). The corresponding VIs have simple feasible sets, that the projection on them is a low cost operation. Therefore, we apply two projection methods for finding the equilibrium: pseudo-gradient projection (PGP) and extra pseudo-gradient (EPG). We present and analyze results obtained on random generated sets of these three classes of problems. The obtained results show expected advantages of the EPG over PGP. What is most important: the number of iterations requited by EPG method to find an approximation for the equilibrium with a given accuracy grows linearly with the number of products in case of NE and NPCE, or with the number of active strategies in case of J. Nash’s equilibrium. The number of operations, or solution time grows as a cube of the corresponding parameters. These results corroborate the complexity bounds established in [18–20] under reasonable assumptions on the input data.
- Open Access
The Application of Affective Measures in Text-based Emotion Aware Recommender Systems
This paper presents an innovative approach to address the problems researchers face in Emotion Aware Recommender Systems (EARS): the difficulty and cumbersome collecting voluminously good quality emotion-tagged datasets and an effective way to protect users' emotional data privacy. Without enough good-quality emotion-tagged datasets, researchers cannot conduct repeatable affective computing research in EARS that generates personalized recommendations based on users' emotional preferences. Similarly, if we fail to fully protect users' emotional data privacy, users could resist engaging with EARS services. This paper introduced a method that detects affective features in subjective passages using the Generative Pre-trained Transformer Technology, forming the basis of the Affective Index and Affective Index Indicator (AII). Eliminate the need for users to build an affective feature detection mechanism. The paper advocates for a separation of responsibility approach where users protect their emotional profile data while EARS service providers refrain from retaining or storing it. Service providers can update users' Affective Indices in memory without saving their privacy data, providing Affective Aware recommendations without compromising user privacy. This paper offers a solution to the subjectivity and variability of emotions, data privacy concerns, and evaluation metrics and benchmarks, paving the way for future EARS research.
Open AccessThe Application of Affective Measures in Text-based Emotion Aware Recommender Systems
This paper presents an innovative approach to address the problems researchers face in Emotion Aware Recommender Systems (EARS): the difficulty and cumbersome collecting voluminously good quality emotion-tagged datasets and an effective way to protect users' emotional data privacy. Without enough good-quality emotion-tagged datasets, researchers cannot conduct repeatable affective computing research in EARS that generates personalized recommendations based on users' emotional preferences. Similarly, if we fail to fully protect users' emotional data privacy, users could resist engaging with EARS services. This paper introduced a method that detects affective features in subjective passages using the Generative Pre-trained Transformer Technology, forming the basis of the Affective Index and Affective Index Indicator (AII). Eliminate the need for users to build an affective feature detection mechanism. The paper advocates for a separation of responsibility approach where users protect their emotional profile data while EARS service providers refrain from retaining or storing it. Service providers can update users' Affective Indices in memory without saving their privacy data, providing Affective Aware recommendations without compromising user privacy. This paper offers a solution to the subjectivity and variability of emotions, data privacy concerns, and evaluation metrics and benchmarks, paving the way for future EARS research.
- Open Access
Diversification Across Mining Pools: Optimal Mining Strategies under PoW
Mining is a central operation of all proof-of-work (PoW) based cryptocurrencies. The vast majority of miners today participate in "mining pools" instead of "solo mining" in order to lower risk and achieve a more steady income. However, this rise of participation in mining pools negatively affects the decentralization levels of most cryptocurrencies. In this work, we look into mining pools from the point of view of a miner: We present an analytical model and implement a computational tool that allows miners to optimally distribute their computational power over multiple pools and PoW cryptocurrencies (i.e. build a mining portfolio), taking into account their risk aversion levels. Our tool allows miners to maximize their risk-adjusted earnings by diversifying across multiple mining pools which enhances PoW decentralization. Finally, we run an experiment in Bitcoin historical data and demonstrate that a miner diversifying over multiple pools, as instructed by our model/tool, receives a higher overall Sharpe ratio (i.e. average excess reward over its standard deviation/volatility).
Open AccessDiversification Across Mining Pools: Optimal Mining Strategies under PoW
Mining is a central operation of all proof-of-work (PoW) based cryptocurrencies. The vast majority of miners today participate in "mining pools" instead of "solo mining" in order to lower risk and achieve a more steady income. However, this rise of participation in mining pools negatively affects the decentralization levels of most cryptocurrencies. In this work, we look into mining pools from the point of view of a miner: We present an analytical model and implement a computational tool that allows miners to optimally distribute their computational power over multiple pools and PoW cryptocurrencies (i.e. build a mining portfolio), taking into account their risk aversion levels. Our tool allows miners to maximize their risk-adjusted earnings by diversifying across multiple mining pools which enhances PoW decentralization. Finally, we run an experiment in Bitcoin historical data and demonstrate that a miner diversifying over multiple pools, as instructed by our model/tool, receives a higher overall Sharpe ratio (i.e. average excess reward over its standard deviation/volatility).
- Open Access
- 1 November 2022
- Published by IACSIT Press in International Journal of Modeling and Optimization
- p. 136-141
Optimizing Searchers that can Transport and Deploy another Searcher Using an Agent Based Model and Nonlinear Optimization Methods in a Maritime Domain
This paper introduces a new methodology, nicknamed Pathfinder, for finding optimal search paths for searchers that can transport and deploy other searchers. The methodology applies an Agent-Based Model to model target movement, then uses nonlinear optimization methods to find optimal search plans. This methodology can optimize these search teams effectively and quickly. Pathfinder significantly increase probability of detection and decreases travel distance. In addition to advancing Search Theory, this methodology also has the potential to enhance current search and rescue (SAR) and anti-submarine warfare (ASW) operations.
- 1 November 2022
- Published by IACSIT Press in International Journal of Modeling and Optimization
- p. 136-141
Open AccessOptimizing Searchers that can Transport and Deploy another Searcher Using an Agent Based Model and Nonlinear Optimization Methods in a Maritime Domain
This paper introduces a new methodology, nicknamed Pathfinder, for finding optimal search paths for searchers that can transport and deploy other searchers. The methodology applies an Agent-Based Model to model target movement, then uses nonlinear optimization methods to find optimal search plans. This methodology can optimize these search teams effectively and quickly. Pathfinder significantly increase probability of detection and decreases travel distance. In addition to advancing Search Theory, this methodology also has the potential to enhance current search and rescue (SAR) and anti-submarine warfare (ASW) operations.
- Open Access
- 19 April 2022
- Published by MDPI AG in Atmosphere
- Vol. 13 (5) , 643
An Advanced Artificial Intelligence System for Identifying the Near-Core Impact Features to Tropical Cyclone Rapid Intensification from the ERA-Interim Data
Prediction of tropical cyclone (TC) intensity is one of the ground challenges in weather forecasting, and rapid intensification (RI) is a key part of that prediction. Most of the current RI studies are based on a selected variable (feature) set, which is accumulated based on expert expertise in past studies of TC intensity changes and RI. Are there any more important variables in TC intensity predictions that were not identified in past studies? A systematic and comprehensive search for those variables from vast amounts of gridded data, satellite images, and other historically collected data could be helpful for answering the above question. Artificial intelligence (AI) has the capabilities to distill features in large array data, and it is helpful in identifying new features related to TC intensity changes in general and RI in particular. Here, we leverage the local linear embedding (LLE) dimension reduction techniques to the European Centre for Medium-Range Weather Forecasts ERA-Interim reanalysis data for identifying new variables related to RI. In addition to the well-known features in the SHIPS (statistical hurricane intensity prediction scheme) database, we identified other significant features, such as 400 and 450 hPa meridional wind, 1000 hPa potential vorticity, and vertical pressure speed, that could help the understanding and prediction of RI occurrences. Furthermore, our AI system outperforms our baseline model with SHIPS data only by 26.6% and 8.4% in kappa and PSS (Peirce’s skill score), respectively.
- 19 April 2022
- Published by MDPI AG in Atmosphere
- Vol. 13 (5) , 643
Open AccessAn Advanced Artificial Intelligence System for Identifying the Near-Core Impact Features to Tropical Cyclone Rapid Intensification from the ERA-Interim Data
Prediction of tropical cyclone (TC) intensity is one of the ground challenges in weather forecasting, and rapid intensification (RI) is a key part of that prediction. Most of the current RI studies are based on a selected variable (feature) set, which is accumulated based on expert expertise in past studies of TC intensity changes and RI. Are there any more important variables in TC intensity predictions that were not identified in past studies? A systematic and comprehensive search for those variables from vast amounts of gridded data, satellite images, and other historically collected data could be helpful for answering the above question. Artificial intelligence (AI) has the capabilities to distill features in large array data, and it is helpful in identifying new features related to TC intensity changes in general and RI in particular. Here, we leverage the local linear embedding (LLE) dimension reduction techniques to the European Centre for Medium-Range Weather Forecasts ERA-Interim reanalysis data for identifying new variables related to RI. In addition to the well-known features in the SHIPS (statistical hurricane intensity prediction scheme) database, we identified other significant features, such as 400 and 450 hPa meridional wind, 1000 hPa potential vorticity, and vertical pressure speed, that could help the understanding and prediction of RI occurrences. Furthermore, our AI system outperforms our baseline model with SHIPS data only by 26.6% and 8.4% in kappa and PSS (Peirce’s skill score), respectively.
- Open Access
Using Affective Features from Media Content Metadata for Better Movie Recommendations
This paper investigates the causality in the decision making of movie recommendations through the users' affective profiles. We advocate a method of assigning emotional tags to a movie by the auto-detection of the affective features in the movie's overview. We apply a text-based Emotion Detection and Recognition model, which trained by tweets short messages and transfers the learned model to detect movie overviews' implicit affective features. We vectorized the affective movie tags to represent the mood embeddings of the movie. We obtain the user's emotional features by taking the average of all the movies' affective vectors the user has watched. We apply five-distance metrics to rank the Top-N movie recommendations against the user's emotion profile. We found Cosine Similarity distance metrics performed better than other distance metrics measures. We conclude that by replacing the top-N recommendations generated by the Recommender with the reranked recommendations list made by the Cosine Similarity distance metrics, the user will effectively get affective aware top-N recommendations while making the Recommender feels like an Emotion Aware Recommender.
Open AccessUsing Affective Features from Media Content Metadata for Better Movie Recommendations
This paper investigates the causality in the decision making of movie recommendations through the users' affective profiles. We advocate a method of assigning emotional tags to a movie by the auto-detection of the affective features in the movie's overview. We apply a text-based Emotion Detection and Recognition model, which trained by tweets short messages and transfers the learned model to detect movie overviews' implicit affective features. We vectorized the affective movie tags to represent the mood embeddings of the movie. We obtain the user's emotional features by taking the average of all the movies' affective vectors the user has watched. We apply five-distance metrics to rank the Top-N movie recommendations against the user's emotion profile. We found Cosine Similarity distance metrics performed better than other distance metrics measures. We conclude that by replacing the top-N recommendations generated by the Recommender with the reranked recommendations list made by the Cosine Similarity distance metrics, the user will effectively get affective aware top-N recommendations while making the Recommender feels like an Emotion Aware Recommender.
- Open Access
Unsupervised Selective Manifold Regularized Matrix Factorization
Manifold regularization methods for matrix factorization rely on the cluster assumption, whereby the neighborhood structure of data in the input space is preserved in the factorization space. We argue that using the k-neighborhoods of all data points as regularization constraints can negatively affect the quality of the factorization, and propose an unsupervised and selective regularized matrix factorization algorithm to tackle this problem. Our approach jointly learns a sparse set of representatives and their neighbor affinities, and the data factorization. We further propose a fast approximation of our approach by relaxing the selectivity constraints on the data. Our proposed algorithms are competitive against baselines and state-of-the-art manifold regularization and clustering algorithms.
Open AccessUnsupervised Selective Manifold Regularized Matrix Factorization
Manifold regularization methods for matrix factorization rely on the cluster assumption, whereby the neighborhood structure of data in the input space is preserved in the factorization space. We argue that using the k-neighborhoods of all data points as regularization constraints can negatively affect the quality of the factorization, and propose an unsupervised and selective regularized matrix factorization algorithm to tackle this problem. Our approach jointly learns a sparse set of representatives and their neighbor affinities, and the data factorization. We further propose a fast approximation of our approach by relaxing the selectivity constraints on the data. Our proposed algorithms are competitive against baselines and state-of-the-art manifold regularization and clustering algorithms.
- Open Access
Investigating Functional Roles for Positive Feedback and Cellular Heterogeneity in the Type I Interferon Response to Viral Infection
Secretion of type I interferons (IFN) by infected cells mediates protection against many viruses, but prolonged or excessive type I IFN secretion can lead to immune pathology. A proper type I IFN response must therefore maintain a balance between protection and excessive IFN secretion. It has been widely noted that the type I IFN response is driven by positive feedback and is heterogeneous, with only a fraction of infected cells upregulating IFN expression even in clonal cell lines, but the functional roles of feedback and heterogeneity in balancing protection and excessive IFN secretion are not clear. To investigate the functional roles for feedback and heterogeneity, we constructed a mathematical model coupling IFN and viral dynamics that extends existing mathematical models by accounting for feedback and heterogeneity. We fit our model to five existing datasets, reflecting different experimental systems. Fitting across datasets allowed us to compare the IFN response across the systems and suggested different signatures of feedback and heterogeneity in the different systems. Further, through numerical experiments, we generated hypotheses of functional roles for IFN feedback and heterogeneity consistent with our mathematical model. We hypothesize an inherent tradeoff in the IFN response: a positive feedback loop prevents excessive IFN secretion, but also makes the IFN response vulnerable to viral antagonism. We hypothesize that cellular heterogeneity of the IFN response functions to protect the feedback loop from viral antagonism. Verification of our hypotheses will require further experimental studies. Our work provides a basis for analyzing the type I IFN response across systems.
Open AccessInvestigating Functional Roles for Positive Feedback and Cellular Heterogeneity in the Type I Interferon Response to Viral Infection
Secretion of type I interferons (IFN) by infected cells mediates protection against many viruses, but prolonged or excessive type I IFN secretion can lead to immune pathology. A proper type I IFN response must therefore maintain a balance between protection and excessive IFN secretion. It has been widely noted that the type I IFN response is driven by positive feedback and is heterogeneous, with only a fraction of infected cells upregulating IFN expression even in clonal cell lines, but the functional roles of feedback and heterogeneity in balancing protection and excessive IFN secretion are not clear. To investigate the functional roles for feedback and heterogeneity, we constructed a mathematical model coupling IFN and viral dynamics that extends existing mathematical models by accounting for feedback and heterogeneity. We fit our model to five existing datasets, reflecting different experimental systems. Fitting across datasets allowed us to compare the IFN response across the systems and suggested different signatures of feedback and heterogeneity in the different systems. Further, through numerical experiments, we generated hypotheses of functional roles for IFN feedback and heterogeneity consistent with our mathematical model. We hypothesize an inherent tradeoff in the IFN response: a positive feedback loop prevents excessive IFN secretion, but also makes the IFN response vulnerable to viral antagonism. We hypothesize that cellular heterogeneity of the IFN response functions to protect the feedback loop from viral antagonism. Verification of our hypotheses will require further experimental studies. Our work provides a basis for analyzing the type I IFN response across systems.
- Open Access
- 25 July 2018
- Published by Wiley in Chemphyschem
- Vol. 19 (15) , 1801
Internal Redox Polarity of an Individual G. sulfurreducens Bacterial Cell Attached to an Inorganic Substrate
Invited for this month cover is the work of a multidisciplinary dynamic team from the U.S. Naval Research Laboratory, consisting of the biophysicist Dr. Nikolai Lebedev, the bioengineer Dr. Matthew Yates, the electrochemist Dr. Leonard Tender and the mathematician Prof. Igor Griva from George Mason University. The image shows how the information about the cell environment is coded inside an individual bacterium and how the researchers can read this code with a Raman microscope. Read the full text of the Article at 10.1002/cphc.201800289.
- 25 July 2018
- Published by Wiley in Chemphyschem
- Vol. 19 (15) , 1801
Open AccessInternal Redox Polarity of an Individual G. sulfurreducens Bacterial Cell Attached to an Inorganic Substrate
Invited for this month cover is the work of a multidisciplinary dynamic team from the U.S. Naval Research Laboratory, consisting of the biophysicist Dr. Nikolai Lebedev, the bioengineer Dr. Matthew Yates, the electrochemist Dr. Leonard Tender and the mathematician Prof. Igor Griva from George Mason University. The image shows how the information about the cell environment is coded inside an individual bacterium and how the researchers can read this code with a Raman microscope. Read the full text of the Article at 10.1002/cphc.201800289.