Ashok Samal
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
Ashok Samal has a total of 25 co-authors. Here are the top co-authors by number of shared publications:
- Deepti Joshi
Department of Cyber and Computer Sciences, The Citadel, Charleston, SC, USA
3 shared publications - Leen-Kiat Soh
School of Computing, University of Nebraska - Lincoln, Lincoln, NE, USA
3 shared publications - Jacob M. Williams
Ocuvera, LLC
2 shared publications - Matthew R. Johnson
Inciteful, LLC
2 shared publications - Praval Sharma
School of Computing, University of Nebraska-Lincoln, Lincoln, USA
2 shared publications - Anup Adhikari
University of Nebraska-Lincoln
1 shared publication
Latest Publications
- 16 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 316
Modeling social unrest: The geographical influence on social unrest prediction
- 16 February 2026
- Published by Elsevier in Expert Systems with Applications
- Vol. 316
Modeling social unrest: The geographical influence on social unrest prediction
- Open Access
Introducing Concurrent Imaging and Unidimensional Analytics for Plant Stress Responses
Advancements in phenotyping technologies, including object imaging, high-throughput monitoring, and soft computing, are pivotal for understanding plant responses to environmental stresses. These technologies enable detailed analyses of morphological, physiological, and structural adaptations under abiotic and biotic stresses, such as drought. Current work using multimodal and multi-perspective image processing methods can capture the essential processes that enhance plant resilience and counteract stress by identifying morphological and biochemical indicators. However, the dynamic and complex nature of plant responses poses multiple challenges for generating precise analytics and descriptors of evolving phenotypes. This work introduces analytics for concurrent imaging, adopting the underlying principle of cosegmentation to create taxonomies for new phenotypes. Here, unidimensional refers to the concurrent analysis of multiple images within a single phenotyping dimension: temporal, modal, or perspective, rather than combining information across dimensions. The proposed unidimensional phenotypes integrate concurrent images within individual temporal, modal, or perspective dimensions to capture dynamic morphological and physiological responses that are not observable with conventional single-image or cumulative metrics. Within a high-throughput imagery production system, these phenotypes enable more nuanced quantification of phenotypic changes, leveraging the strengths of simultaneous image analysis to enhance insight into plant adaptations. This workflow aligns with the investigation of plants’ adaptive strategies under abiotic stress and provides quantitative indicators of plant health under adverse environmental conditions.
Open AccessIntroducing Concurrent Imaging and Unidimensional Analytics for Plant Stress Responses
Advancements in phenotyping technologies, including object imaging, high-throughput monitoring, and soft computing, are pivotal for understanding plant responses to environmental stresses. These technologies enable detailed analyses of morphological, physiological, and structural adaptations under abiotic and biotic stresses, such as drought. Current work using multimodal and multi-perspective image processing methods can capture the essential processes that enhance plant resilience and counteract stress by identifying morphological and biochemical indicators. However, the dynamic and complex nature of plant responses poses multiple challenges for generating precise analytics and descriptors of evolving phenotypes. This work introduces analytics for concurrent imaging, adopting the underlying principle of cosegmentation to create taxonomies for new phenotypes. Here, unidimensional refers to the concurrent analysis of multiple images within a single phenotyping dimension: temporal, modal, or perspective, rather than combining information across dimensions. The proposed unidimensional phenotypes integrate concurrent images within individual temporal, modal, or perspective dimensions to capture dynamic morphological and physiological responses that are not observable with conventional single-image or cumulative metrics. Within a high-throughput imagery production system, these phenotypes enable more nuanced quantification of phenotypic changes, leveraging the strengths of simultaneous image analysis to enhance insight into plant adaptations. This workflow aligns with the investigation of plants’ adaptive strategies under abiotic stress and provides quantitative indicators of plant health under adverse environmental conditions.
- Open Access
- 11 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 10 (1) , 1-34
A Spatially-Aware Data-Driven Approach to Automatically Geocoding Non-Gazetteer Place Names
Human and natural processes such as navigation and natural calamities are intrinsically linked to the geographic space and described using place names. Extraction and subsequent geocoding of place names from text are critical for understanding the onset, progression, and end of these processes. Geocoding place names extracted from text requires using an external knowledge base such as a gazetteer. However, a standard gazetteer is typically incomplete. Additionally, widely used place name geocoding—also known as toponym resolution—approaches generally focus on geocoding ambiguous but known gazetteer place names. Hence, there is a need for an approach to automatically geocode non -gazetteer place names. In this research, we demonstrate that patterns in place names are not spatially random. Places are often named based on people, geography, and history of the area and thus exhibit a degree of similarity. Similarly, places that co-occur in text are likely to be spatially proximate as they provide geographic reference to common events. We propose a novel data-driven spatially-aware algorithm, Bhugol , that leverages the spatial patterns and the spatial context of place names to automatically geocode the non-gazetteer place names. The efficacy of Bhugol is demonstrated using two diverse geographic areas – USA and India. The results show that Bhugol outperforms well-known state-of-the-art geocoders.
- 11 December 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 10 (1) , 1-34
Open AccessA Spatially-Aware Data-Driven Approach to Automatically Geocoding Non-Gazetteer Place Names
Human and natural processes such as navigation and natural calamities are intrinsically linked to the geographic space and described using place names. Extraction and subsequent geocoding of place names from text are critical for understanding the onset, progression, and end of these processes. Geocoding place names extracted from text requires using an external knowledge base such as a gazetteer. However, a standard gazetteer is typically incomplete. Additionally, widely used place name geocoding—also known as toponym resolution—approaches generally focus on geocoding ambiguous but known gazetteer place names. Hence, there is a need for an approach to automatically geocode non -gazetteer place names. In this research, we demonstrate that patterns in place names are not spatially random. Places are often named based on people, geography, and history of the area and thus exhibit a degree of similarity. Similarly, places that co-occur in text are likely to be spatially proximate as they provide geographic reference to common events. We propose a novel data-driven spatially-aware algorithm, Bhugol , that leverages the spatial patterns and the spatial context of place names to automatically geocode the non-gazetteer place names. The efficacy of Bhugol is demonstrated using two diverse geographic areas – USA and India. The results show that Bhugol outperforms well-known state-of-the-art geocoders.
- Open Access
- 23 June 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 9 (3) , 1-31
Agent Based Modeling of the Spread of Social Unrest Using Infectious Disease Models
Prior research suggests that the timing and location of social unrest may be influenced by similar unrest activities in another nearby region, potentially causing a spread of unrest activities across space and time. In this paper, we model the spread of social unrest across time and space using a novel approach, grounded in agent-based modeling (ABM) . In it, regions (geographic polygons) are represented as agents that transition from one state to another based on changes in their environment. Our approach involves (1) creating a vector for each region/agent based on socio-demographic, infrastructural, economic, geographic, and environmental (SIEGE) factors, (2) formulating a neighborhood distance function to identify an agent's neighbors based on geospatial distance and SIEGE proximity, (3) designing transition probability equations based on two distinct compartmental models—i.e., the Susceptible-Infected-Recovered (SIR) and the Susceptible-Infected-Susceptible (SIS) models, and (4) building a ground truth for evaluating the simulations. We use ABM to determine the individualized probabilities of each region/agent to transition from one state to another. The models are tested using the districts of three states in India as agents at a monthly scale for 2016-2019. For ground truth of unrest events, we use the Armed Conflict Location and Event Data (ACLED) dataset. Our findings include that (1) the transition probability equations are viable, (2) the agent-based modeling of the spread of social unrest is feasible while treating regions as agents (Brier's score < 0.25 for two out of three regions), and (3) the SIS model performs comparatively better than the SIR model.
- 23 June 2023
- Published by Association for Computing Machinery (ACM) in ACM Transactions on Spatial Algorithms and Systems
- Vol. 9 (3) , 1-31
Open AccessAgent Based Modeling of the Spread of Social Unrest Using Infectious Disease Models
Prior research suggests that the timing and location of social unrest may be influenced by similar unrest activities in another nearby region, potentially causing a spread of unrest activities across space and time. In this paper, we model the spread of social unrest across time and space using a novel approach, grounded in agent-based modeling (ABM) . In it, regions (geographic polygons) are represented as agents that transition from one state to another based on changes in their environment. Our approach involves (1) creating a vector for each region/agent based on socio-demographic, infrastructural, economic, geographic, and environmental (SIEGE) factors, (2) formulating a neighborhood distance function to identify an agent's neighbors based on geospatial distance and SIEGE proximity, (3) designing transition probability equations based on two distinct compartmental models—i.e., the Susceptible-Infected-Recovered (SIR) and the Susceptible-Infected-Susceptible (SIS) models, and (4) building a ground truth for evaluating the simulations. We use ABM to determine the individualized probabilities of each region/agent to transition from one state to another. The models are tested using the districts of three states in India as agents at a monthly scale for 2016-2019. For ground truth of unrest events, we use the Armed Conflict Location and Event Data (ACLED) dataset. Our findings include that (1) the transition probability equations are viable, (2) the agent-based modeling of the spread of social unrest is feasible while treating regions as agents (Brier's score < 0.25 for two out of three regions), and (3) the SIS model performs comparatively better than the SIR model.
- Open Access
Trial Averaging for Deep EEG Classification
Many signals, particularly of biological origin, suffer from a signal-to-noise ratio sufficiently low that it can be difficult to classify individual examples reliably, even with relatively sophisticated machine-learning techniques such as deep learning. In some cases, the noise can be high enough that it is even difficult to achieve convergence during training. We considered this problem for one data type that often suffers from such difficulties, namely electroencephalography (EEG) data from cognitive neuroscience studies in humans. One solution to increase signal-to-noise is, of course, to perform averaging among trials, which has been employed before in other studies of human neuroscience but not, to our knowledge, investigated rigorously, particularly not in deep learning. Here, we parametrically studied the effects of different amounts of trial averaging during training and/or testing in a human EEG dataset, and compared the results to that of a related algorithm, Mixup. Broadly, we found that even a small amount of averaging could significantly improve classification, particularly when both training and testing data were subjected to averaging. Simple averaging clearly outperformed Mixup, although the benefits of averaging differed across classification categories. Overall, our results confirm the value of averaging during training and testing when single-trial classification is not strictly necessary for the application in question. Highlights: Averaging trials can dramatically improve performance in classification of EEG data The benefits can be seen when averaging on both training and test datasets Simple trial averaging outperformed a popular related algorithm, Mixup However, effects of averaging differed across different stimulus categories
Open AccessTrial Averaging for Deep EEG Classification
Many signals, particularly of biological origin, suffer from a signal-to-noise ratio sufficiently low that it can be difficult to classify individual examples reliably, even with relatively sophisticated machine-learning techniques such as deep learning. In some cases, the noise can be high enough that it is even difficult to achieve convergence during training. We considered this problem for one data type that often suffers from such difficulties, namely electroencephalography (EEG) data from cognitive neuroscience studies in humans. One solution to increase signal-to-noise is, of course, to perform averaging among trials, which has been employed before in other studies of human neuroscience but not, to our knowledge, investigated rigorously, particularly not in deep learning. Here, we parametrically studied the effects of different amounts of trial averaging during training and/or testing in a human EEG dataset, and compared the results to that of a related algorithm, Mixup. Broadly, we found that even a small amount of averaging could significantly improve classification, particularly when both training and testing data were subjected to averaging. Simple averaging clearly outperformed Mixup, although the benefits of averaging differed across classification categories. Overall, our results confirm the value of averaging during training and testing when single-trial classification is not strictly necessary for the application in question. Highlights: Averaging trials can dramatically improve performance in classification of EEG data The benefits can be seen when averaging on both training and test datasets Simple trial averaging outperformed a popular related algorithm, Mixup However, effects of averaging differed across different stimulus categories
- 4 November 2022
- Published by Springer Nature in GeoInformatica
- Vol. 27 (4) , 645-679
A spatially-aware algorithm for location extraction from structured documents
- 4 November 2022
- Published by Springer Nature in GeoInformatica
- Vol. 27 (4) , 645-679
A spatially-aware algorithm for location extraction from structured documents
- Open Access
Deep-Learning-Based Multivariate Pattern Analysis (dMVPA): A Tutorial and a Toolbox
In recent years, multivariate pattern analysis (MVPA) has been hugely beneficial for cognitive neuroscience by making new experiment designs possible and by increasing the inferential power of functional magnetic resonance imaging (fMRI), electroencephalography (EEG), and other neuroimaging methodologies. In a similar time frame, “deep learning” (a term for the use of artificial neural networks with convolutional, recurrent, or similarly sophisticated architectures) has produced a parallel revolution in the field of machine learning and has been employed across a wide variety of applications. Traditional MVPA also uses a form of machine learning, but most commonly with much simpler techniques based on linear calculations; a number of studies have applied deep learning techniques to neuroimaging data, but we believe that those have barely scratched the surface of the potential deep learning holds for the field. In this paper, we provide a brief introduction to deep learning for those new to the technique, explore the logistical pros and cons of using deep learning to analyze neuroimaging data – which we term “deep MVPA,” or dMVPA – and introduce a new software toolbox (the “Deep Learning In Neuroimaging: Exploration, Analysis, Tools, and Education” package, DeLINEATE for short) intended to facilitate dMVPA for neuroscientists (and indeed, scientists more broadly) everywhere.
Open AccessDeep-Learning-Based Multivariate Pattern Analysis (dMVPA): A Tutorial and a Toolbox
In recent years, multivariate pattern analysis (MVPA) has been hugely beneficial for cognitive neuroscience by making new experiment designs possible and by increasing the inferential power of functional magnetic resonance imaging (fMRI), electroencephalography (EEG), and other neuroimaging methodologies. In a similar time frame, “deep learning” (a term for the use of artificial neural networks with convolutional, recurrent, or similarly sophisticated architectures) has produced a parallel revolution in the field of machine learning and has been employed across a wide variety of applications. Traditional MVPA also uses a form of machine learning, but most commonly with much simpler techniques based on linear calculations; a number of studies have applied deep learning techniques to neuroimaging data, but we believe that those have barely scratched the surface of the potential deep learning holds for the field. In this paper, we provide a brief introduction to deep learning for those new to the technique, explore the logistical pros and cons of using deep learning to analyze neuroimaging data – which we term “deep MVPA,” or dMVPA – and introduce a new software toolbox (the “Deep Learning In Neuroimaging: Exploration, Analysis, Tools, and Education” package, DeLINEATE for short) intended to facilitate dMVPA for neuroscientists (and indeed, scientists more broadly) everywhere.
- Open Access
- 21 October 2020
- Published by Taylor & Francis
- p. 93-118
Structural High-Throughput Plant Phenotyping Based on Image Sequence Analysis
The complex interaction between genotype and the environment determines the observable morphological and biophysical characteristics of plants, i.e., phenotypes, which influence the yield and acquisition of resources. Image-based plant phenotyping refers to the proximal sensing and quantification of plant traits, based on 94analyzing their images, captured at regular intervals with precision. The process is generally non-destructive, allowing the same traits to be quantified periodically during a plant’s life cycle. However, extracting meaningful numerical phenotypes based on image-based automated plant phenotyping remains a critical bottleneck in the effort to link intricate plant phenotypes to genetic expression.
- 21 October 2020
- Published by Taylor & Francis
- p. 93-118
Open AccessStructural High-Throughput Plant Phenotyping Based on Image Sequence Analysis
The complex interaction between genotype and the environment determines the observable morphological and biophysical characteristics of plants, i.e., phenotypes, which influence the yield and acquisition of resources. Image-based plant phenotyping refers to the proximal sensing and quantification of plant traits, based on 94analyzing their images, captured at regular intervals with precision. The process is generally non-destructive, allowing the same traits to be quantified periodically during a plant’s life cycle. However, extracting meaningful numerical phenotypes based on image-based automated plant phenotyping remains a critical bottleneck in the effort to link intricate plant phenotypes to genetic expression.
- 1 June 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 5 (4) , 1231-1242
A Statistical Approach for Automatic Detection of Ocean Disturbance Features From SAR Images
Extraction of features from images has been a goal of researchers since the early days of remote sensing. This paper presents a statistical approach to detect dark curvilinear features due to ocean disturbances caused by wind, movements of surface or underwater objects, and oil spill from SAR images. The image is first enhanced to emphasize the dark curvilinear features using a statistical approach. Then, the curvilinear features are segmented using an iterative approach. The holes in the segmented image are then filled using a recursive scanning method. The image is thinned and unwanted branches are removed using a graph-theory-based technique. Finally, an efficient linking algorithm based on geometric properties is proposed to detect the disturbance features. Our algorithm is evaluated using on both synthetic images with by various levels of added Gaussian noise and on actual SAR images from ERS-2, SEASAT, ENVISAT, and RADARSAT. The results of our approach is compared with those from existing approaches. Results show that, in comparison with the algorithms in literature, our algorithm is more accurate in extracting the features both in terms of the area and shape. In addition, our algorithm runs significantly faster.
- 1 June 2012
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
- Vol. 5 (4) , 1231-1242
A Statistical Approach for Automatic Detection of Ocean Disturbance Features From SAR Images
Extraction of features from images has been a goal of researchers since the early days of remote sensing. This paper presents a statistical approach to detect dark curvilinear features due to ocean disturbances caused by wind, movements of surface or underwater objects, and oil spill from SAR images. The image is first enhanced to emphasize the dark curvilinear features using a statistical approach. Then, the curvilinear features are segmented using an iterative approach. The holes in the segmented image are then filled using a recursive scanning method. The image is thinned and unwanted branches are removed using a graph-theory-based technique. Finally, an efficient linking algorithm based on geometric properties is proposed to detect the disturbance features. Our algorithm is evaluated using on both synthetic images with by various levels of added Gaussian noise and on actual SAR images from ERS-2, SEASAT, ENVISAT, and RADARSAT. The results of our approach is compared with those from existing approaches. Results show that, in comparison with the algorithms in literature, our algorithm is more accurate in extracting the features both in terms of the area and shape. In addition, our algorithm runs significantly faster.
- Open Access
- 27 August 2011
- Published by International Speech Communication Association
- p. 277-280
Quantifying articulatory distinctiveness of vowels
- 27 August 2011
- Published by International Speech Communication Association
- p. 277-280
Open AccessQuantifying articulatory distinctiveness of vowels