kamol roy - Academia.edu (original) (raw)

Papers by kamol roy

Research paper thumbnail of Understanding the Socio-infrastructure Systems During Disaster from Social Media Data

Our socio-infrastructure systems are becoming more and more vulnerable due to the increased sever... more Our socio-infrastructure systems are becoming more and more vulnerable due to the increased severity and frequency of extreme events every year. Effective disaster management can minimize the damaging impacts of a disaster to a large extent. The ubiquitous use of social media platforms in GPS enabled smartphones offers a unique opportunity to observe, model, and predict human behavior during a disaster. This dissertation explores the opportunity of using social media data v TABLE OF CONTENT

Research paper thumbnail of Performance of crossbred dairy cattle under commercial farming conditions in the Chattogram district, Bangladesh

Bangladesh Journal of Veterinary and Animal Sciences

The study was conducted in 10 different farms under 6 upazilas, i.e., Hathazari, Patiya, Anwara, ... more The study was conducted in 10 different farms under 6 upazilas, i.e., Hathazari, Patiya, Anwara, Boalkhali, Bakalia and Patenga of Chattogram district. The records of 50 crossbred dairy cattle (CDC) were collected for two crossbred dairy breeds, i.e., Holstein Friesian × Jersey (HF × J) and Holstein Friesian × Local (HF × L) from March to June 2019. Farms having ≥50 CDC with complete records of each cattle were selected for the study purpose. Results indicated that the genotype, supply of green roughage and concentrate, and feeding of CDC immediate before milking had significant (p<0.001) positive linear effect on average daily milk yield (ADMY). Supply of green roughage and concentrate had further positive quadratic and cubic effects (p<0.001) on ADMY. Postpartum period quadratically influenced the ADMY (p<0.05) although linear and cubic effects were nil (p>0.05). Parity and genotype had significant (p<0.05) positive effect on lactation period of the CDC. Among the H...

Research paper thumbnail of Understanding the Socio-infrastructure Systems During Disaster from Social Media Data

Our socio-infrastructure systems are becoming more and more vulnerable due to the increased sever... more Our socio-infrastructure systems are becoming more and more vulnerable due to the increased severity and frequency of extreme events every year. Effective disaster management can minimize the damaging impacts of a disaster to a large extent. The ubiquitous use of social media platforms in GPS enabled smartphones offers a unique opportunity to observe, model, and predict human behavior during a disaster. This dissertation explores the opportunity of using social media data v TABLE OF CONTENT

Research paper thumbnail of Understanding the Influence of Multiple Information Sources on Risk Perception Dynamics and Evacuation Decisions: An Agent-Based Modeling Approach

SSRN Electronic Journal, 2021

Research paper thumbnail of Understanding the Effectiveness of Social Media Based Crisis Communication During Hurricane Sandy

Research paper thumbnail of Understanding Crisis Communication and Mobility Resilience during Disasters from Social Media

A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science... more A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in the Department of Civil, Environmental and Construction Engineering in the College of Engineering and Computer Science at

Research paper thumbnail of Predicting Individual Mobility Behavior of Ride-Hailing Service Users considering Heterogeneity of Trip Purposes

2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 2021

The emergence of on-demand ride-hailing service platforms, such as Uber, Lyft and Didi, can provi... more The emergence of on-demand ride-hailing service platforms, such as Uber, Lyft and Didi, can provide innovative data sources to understand and model individual mobility behavior. Compared to the previously used data sources such as mobile phone and social media, mobility data extracted from ride-hailing service platforms contain more specific, detailed, and longitudinal information of individual travel mode and coordinates of the visited locations. In this study, using large-scale data extracted from 50,000 ride-hailing service users' mobility records, we apply an input-output hidden Markov model (IOHMM) to predict the origin and destination of the next ride-hailing service trip of an individual. The results indicate that the IOHMM model can achieve 71% accuracy for predicting the origin and 67% for predicting the destination of a trip made for commuting purposes. The IOHMM model can capture the influence of different time periods as the prediction performance of the model varies over different time periods. Since individual mobility behavior shows both regularity and uncertainty, we analyze the performance of IOHMM by investigating the predictability of each mobility sequence. We find that model accuracy is proportional to the predictability of individual movement. Using the concept of predictability, we can determine the limits of the accuracy of mobility prediction models.

Research paper thumbnail of Understanding Network Wide Hurricane Evacuation Traffic Pattern from Large-scale Traffic Detector Data

2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 2021

In this study, we develop a data pipeline incorporating automated data quality checking, data imp... more In this study, we develop a data pipeline incorporating automated data quality checking, data imputation, and spatiotemporal visualization of large-scale traffic data to understand the changes in traffic patterns during hurricane evacuation as it unfolds. We collect large-scale Microwave Vehicle Detection System (MVDS) data during Hurricane Irma from four highways in Florida: I–75, I–95, I–4, and Florida Turnpike that served majority of the evacuation traffic. Based on an extensive analysis, we provide insights on network wide spatiotemporal evacuation traffic patterns of Hurricane Irma. Such insights will help transportation agencies recognize the utility of large-scale real-time data, previously unused, to better understand the extent and spatiotemporal distribution of evacuation traffic. To demonstrate this, we analyze the processed data to understand the influence of different spatiotemporal factors on the changes in evacuation traffic pattern. Our results show at least an 18-hour (approximately) time lag between the time of issuing an evacuation order and the time when people first started to evacuate in large numbers. Such findings have potential implications to deal with the challenges of mass evacuation in real time and allows us to develop large-scale network level evacuation traffic prediction model.

Research paper thumbnail of Real-Time Twitter Data Mining Approach to Infer User Perception Toward Active Mobility

Transportation Research Record: Journal of the Transportation Research Board, 2021

This study evaluates the level of service of shared transportation facilities through mining geot... more This study evaluates the level of service of shared transportation facilities through mining geotagged data from social media and analyzing the perceptions of road users. An algorithm is developed adopting a text classification approach with contextual understanding to filter out relevant information related to users’ perceptions toward active mobility. Using a heuristic-based keyword matching approach produces about 75% tweets that are out of context, so that approach is deemed unsuitable for information extraction from Twitter. This study implements six different text classification models and compares the performance of these models for tweet classification. The model is applied to real-world data to filter out relevant information, and content analysis is performed to check the distribution of keywords within the filtered data. The text classification model “term frequency-inverse document frequency” vectorizer-based logistic regression model performed best at classifying the tw...

Research paper thumbnail of Predicting traffic demand during hurricane evacuation using Real-time data from transportation systems and social media

Transportation Research Part C: Emerging Technologies, 2021

In recent times, hurricanes Matthew, Harvey, and Irma have disrupted the lives of millions of peo... more In recent times, hurricanes Matthew, Harvey, and Irma have disrupted the lives of millions of people across multiple states in the United States. Under hurricane evacuation, efficient traffic operations can maximize the use of transportation infrastructure, reducing evacuation time and stress due to massive congestion. Evacuation traffic prediction is critical to plan for effective traffic management strategies. However, due to the complex and dynamic nature of evacuation participation, predicting evacuation traffic demand long ahead of the actual evacuation is a very challenging task. Real-time information from various sources can significantly help us reliably predict evacuation demand. In this study, we use traffic sensor and Twitter data during hurricanes Matthew and Irma to predict traffic demand during evacuation for a longer forecasting horizon (greater than 1 hour). We present a machine learning approach using Long-Short Term Memory Neural Networks (LSTM-NN), trained over real-world traffic data during hurricane evacuation (hurricanes Irma and Matthew) using different combinations of input features and forecast horizons. We compare our prediction results against a baseline prediction and existing machine learning models. Results show that the proposed model can predict traffic demand during evacuation well up to 24 hours ahead. The proposed LSTM-NN model can significantly benefit future evacuation traffic management.

Research paper thumbnail of Modeling the dynamics of hurricane evacuation decisions from twitter data: An input output hidden markov modeling approach

Transportation Research Part C: Emerging Technologies, 2021

Evacuations play a critical role in saving human lives during hurricanes. But individual evacuati... more Evacuations play a critical role in saving human lives during hurricanes. But individual evacuation decision-making is a complex dynamic process, often studied using post-hurricane survey data. Alternatively, ubiquitous use of social media generates a massive amount of data that can be used to predict evacuation behavior in real time. In this paper, we present a method to infer individual evacuation behaviors (e.g., evacuation decision, timing, destination) from social media data. We develop an input output hidden Markov model (IO-HMM) to infer evacuation decisions from user tweets. To extract the underlying evacuation context from tweets, we first estimate a word2vec model from a corpus of more than 100 million tweets collected over four major hurricanes. Using input variables such as evacuation context, time to landfall, type of evacuation order, and the distance from home, the proposed model infers what activities are made by individuals, when they decide to evacuate, and where they evacuate to. To validate our results, we have created a labeled dataset from 38,256 tweets posted between September 2, 2017 and September 19, 2017 by 2,571 users from Florida during hurricane Irma. Our findings show that the proposed IO-HMM method can be useful for inferring evacuation behavior in real time from social media data. Since traditional surveys are infrequent, costly, and often performed at a post-hurricane period, the proposed approach can be very useful for predicting evacuation demand as a hurricane unfolds in real time.

Research paper thumbnail of A multilabel classification approach to identify hurricane‐induced infrastructure disruptions using social media data

Computer-Aided Civil and Infrastructure Engineering, 2020

Rapid identification of infrastructure disruptions during a disaster plays an important role in r... more Rapid identification of infrastructure disruptions during a disaster plays an important role in restoration and recovery operations. Due to the limitations of using physical sensing technologies, such as the requirement to cover a large area in a short period of time, studies have investigated the potential of social sensing for damage/disruption assessment following a disaster. However, previous studies focused on identifying whether a social media post is damage related or not. Hence, advanced methods are needed to infer actual infrastructure disruptions and their locations from such data. In this paper, we present a multilabel classification approach to identify the co‐occurrence of multiple types of infrastructure disruptions considering the sentiment toward a disruption—whether a post is reporting an actual disruption (negative), or a disruption in general (neutral), or not affected by a disruption (positive). In addition, we propose a dynamic mapping framework for visualizing ...

Research paper thumbnail of Relation between the thermal conductivity and grain size in a polycrystalline silicene sheet

AIP Conference Proceedings, 2018

Silicene, a two-dimensional allotrope of silicon, has outstanding mechanical and electrical prope... more Silicene, a two-dimensional allotrope of silicon, has outstanding mechanical and electrical properties which have triggered extensive research on its application in the field of developing faster computer chips, more efficient solar cells, improved medical technologies, vehicle, and aircraft parts, etc. In this work, we have demonstrated a way to use large-scale molecular dynamics to explore the effective thermal conductivity of nano-grained polycrystalline 2-D Silicene sheets and compare it with a pristine one. By performing non-equilibrium molecular dynamics (NEMD) simulations, the effect of grain size on the thermal conductivity of polycrystalline Silicene sheets has been investigated. For both pristine and polycrystalline Silicene sheet, structures of 30 nm × 30 nm are considered and Stillinger-Weber potential is used to investigate the atoms’ interaction with theneighborhood. The temperature profiles are used to find the thermal conductivity by Fourier’s Law of conduction. Comparing with the pristine Silicene sheet we have found a very intriguing result. Our results reveal that the ultra-fine nano-grained Silicene structures have an increasing trend for thermal conductivity commensurate with grain size. Larger the grain size becomes, higher the thermal conductivity is. However, for very small grain size the thermal conductivity is considerably less than the pristine structure. It is also noticed that the thermal conductivity of smaller grain size structures shows more grain size dependency while the thermal conductivity for larger grain size exhibits trivial gradient and almost converges to some certain range of values.The grain size based rising trend is then evaluatedby specific heat calculation.The density of states (DOS) is ultimately calculated for different grain sizes to verify the trend of changing thermal conductivities on the basis of noise sensitivity.Silicene, a two-dimensional allotrope of silicon, has outstanding mechanical and electrical properties which have triggered extensive research on its application in the field of developing faster computer chips, more efficient solar cells, improved medical technologies, vehicle, and aircraft parts, etc. In this work, we have demonstrated a way to use large-scale molecular dynamics to explore the effective thermal conductivity of nano-grained polycrystalline 2-D Silicene sheets and compare it with a pristine one. By performing non-equilibrium molecular dynamics (NEMD) simulations, the effect of grain size on the thermal conductivity of polycrystalline Silicene sheets has been investigated. For both pristine and polycrystalline Silicene sheet, structures of 30 nm × 30 nm are considered and Stillinger-Weber potential is used to investigate the atoms’ interaction with theneighborhood. The temperature profiles are used to find the thermal conductivity by Fourier’s Law of conduction. Comparing with the pristine...

Research paper thumbnail of Sharing Real-Time Traffic Information With Travelers Using Twitter: An Analysis of Effectiveness and Information Content

Frontiers in Built Environment, 2019

Ubiquitous smartphone technologies and virtual social networks offer us a unique opportunity to i... more Ubiquitous smartphone technologies and virtual social networks offer us a unique opportunity to instantly share information to a large number of people. Online social media platforms facilitate easy and rapid communication of real-time information by producing a huge amount of digital content. In this paper, we present an analysis of the data collected from 14 Florida Department of Transportation (FDOT) Twitter accounts created for sharing real-time traffic information. We analyze the activities, influence, attention received, and the effectiveness of gaining attention by these accounts. We propose several metrics in disseminating real-time traffic information. Using topic models, we also analyze the content of the shared information given in the tweets. Finally, we estimate an ordered logit model to determine the information value of a shared content based on its chance of getting retweeted. Based on the study, we propose a framework called Social Media-based Adaptive Real-time Traffic feed (SMART-Feed) that will significantly improve the effectiveness of real-time traffic information sharing through social media. Moreover, it will help to assess the value of real-time traffic information to travelers and developing social media strategies for sharing information.

Research paper thumbnail of Quantifying human mobility resilience to extreme events using geo-located social media data

EPJ Data Science, 2019

Mobility is one of the fundamental requirements of human life with significant societal impacts i... more Mobility is one of the fundamental requirements of human life with significant societal impacts including productivity, economy, social wellbeing, adaptation to a changing climate, and so on. Although human movements follow specific patterns during normal periods, there are limited studies on how such patterns change due to extreme events. To quantify the impacts of an extreme event to human movements, we introduce the concept of mobility resilience which is defined as the ability of a mobility system to manage shocks and return to a steady state in response to an extreme event. We present a method to detect extreme events from geo-located movement data and to measure mobility resilience and transient loss of resilience due to those events. Applying this method, we measure resilience metrics from geo-located social media data for multiple types of disasters occurred all over the world. Quantifying mobility resilience may help us to assess the higher-order socioeconomic impacts of extreme events and guide policies towards developing resilient infrastructures as well as a nation's overall disaster resilience strategies.

Research paper thumbnail of Grid Technologies for Social Science: the SAMD Project

IASSIST Quarterly, 2005

Grid Technologies for Social Science: the SAMD Project

Research paper thumbnail of A Study On Feasible Traffic Operation Alternatives At Signalized Intersection In Dhaka City

Research paper thumbnail of Estimation of Traffic Arrival Pattern at Signalized Intersection using ARIMA Model

International Journal of Computer Applications, 2015

Traffic arrival pattern is an important parameter in delay estimation at signalized intersection.... more Traffic arrival pattern is an important parameter in delay estimation at signalized intersection. Usually, arrival pattern is assumed to be Poisson distribution. However, it varies widely under different volume-capacity ratio at signalized intersection of an arterial road. Therefore, conventional Poisson model cannot predict traffic pattern properly. A time series ARIMA model was proposed in this study to compare with Poisson model. A Paramics simulation model of Route 18 arterial road located in New Brunswick, New Jersey, USA was studied for the research purpose. Three intersections in Route 18-Naricon Place intersection, South Woodland Avenue intersection and West Ferris Street intersection-were considered where traffic arrivals were under dispersed, random and over dispersed under different simulation scenarios respectively. Later, traffic arrival patterns obtained from simulation were compared with Poisson and ARIMA model using SAS statistical software. Arrival headway, vehicle counts per signal cycle, variance to mean ratio were considered and statistical analysis were performed between two candidate models. Study found that, ARIMA model predicts arrival pattern more accurately than Poisson model.

Research paper thumbnail of Seamless Access to Multiple Datasets (SAMD)–An ESRC e-Science Demonstrator

Research paper thumbnail of Understanding the efficiency of social media based crisis communication during hurricane Sandy

International Journal of Information Management, 2020

Research paper thumbnail of Understanding the Socio-infrastructure Systems During Disaster from Social Media Data

Our socio-infrastructure systems are becoming more and more vulnerable due to the increased sever... more Our socio-infrastructure systems are becoming more and more vulnerable due to the increased severity and frequency of extreme events every year. Effective disaster management can minimize the damaging impacts of a disaster to a large extent. The ubiquitous use of social media platforms in GPS enabled smartphones offers a unique opportunity to observe, model, and predict human behavior during a disaster. This dissertation explores the opportunity of using social media data v TABLE OF CONTENT

Research paper thumbnail of Performance of crossbred dairy cattle under commercial farming conditions in the Chattogram district, Bangladesh

Bangladesh Journal of Veterinary and Animal Sciences

The study was conducted in 10 different farms under 6 upazilas, i.e., Hathazari, Patiya, Anwara, ... more The study was conducted in 10 different farms under 6 upazilas, i.e., Hathazari, Patiya, Anwara, Boalkhali, Bakalia and Patenga of Chattogram district. The records of 50 crossbred dairy cattle (CDC) were collected for two crossbred dairy breeds, i.e., Holstein Friesian × Jersey (HF × J) and Holstein Friesian × Local (HF × L) from March to June 2019. Farms having ≥50 CDC with complete records of each cattle were selected for the study purpose. Results indicated that the genotype, supply of green roughage and concentrate, and feeding of CDC immediate before milking had significant (p<0.001) positive linear effect on average daily milk yield (ADMY). Supply of green roughage and concentrate had further positive quadratic and cubic effects (p<0.001) on ADMY. Postpartum period quadratically influenced the ADMY (p<0.05) although linear and cubic effects were nil (p>0.05). Parity and genotype had significant (p<0.05) positive effect on lactation period of the CDC. Among the H...

Research paper thumbnail of Understanding the Socio-infrastructure Systems During Disaster from Social Media Data

Our socio-infrastructure systems are becoming more and more vulnerable due to the increased sever... more Our socio-infrastructure systems are becoming more and more vulnerable due to the increased severity and frequency of extreme events every year. Effective disaster management can minimize the damaging impacts of a disaster to a large extent. The ubiquitous use of social media platforms in GPS enabled smartphones offers a unique opportunity to observe, model, and predict human behavior during a disaster. This dissertation explores the opportunity of using social media data v TABLE OF CONTENT

Research paper thumbnail of Understanding the Influence of Multiple Information Sources on Risk Perception Dynamics and Evacuation Decisions: An Agent-Based Modeling Approach

SSRN Electronic Journal, 2021

Research paper thumbnail of Understanding the Effectiveness of Social Media Based Crisis Communication During Hurricane Sandy

Research paper thumbnail of Understanding Crisis Communication and Mobility Resilience during Disasters from Social Media

A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science... more A thesis submitted in partial fulfillment of the requirements for the degree of Master of Science in the Department of Civil, Environmental and Construction Engineering in the College of Engineering and Computer Science at

Research paper thumbnail of Predicting Individual Mobility Behavior of Ride-Hailing Service Users considering Heterogeneity of Trip Purposes

2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 2021

The emergence of on-demand ride-hailing service platforms, such as Uber, Lyft and Didi, can provi... more The emergence of on-demand ride-hailing service platforms, such as Uber, Lyft and Didi, can provide innovative data sources to understand and model individual mobility behavior. Compared to the previously used data sources such as mobile phone and social media, mobility data extracted from ride-hailing service platforms contain more specific, detailed, and longitudinal information of individual travel mode and coordinates of the visited locations. In this study, using large-scale data extracted from 50,000 ride-hailing service users' mobility records, we apply an input-output hidden Markov model (IOHMM) to predict the origin and destination of the next ride-hailing service trip of an individual. The results indicate that the IOHMM model can achieve 71% accuracy for predicting the origin and 67% for predicting the destination of a trip made for commuting purposes. The IOHMM model can capture the influence of different time periods as the prediction performance of the model varies over different time periods. Since individual mobility behavior shows both regularity and uncertainty, we analyze the performance of IOHMM by investigating the predictability of each mobility sequence. We find that model accuracy is proportional to the predictability of individual movement. Using the concept of predictability, we can determine the limits of the accuracy of mobility prediction models.

Research paper thumbnail of Understanding Network Wide Hurricane Evacuation Traffic Pattern from Large-scale Traffic Detector Data

2021 IEEE International Intelligent Transportation Systems Conference (ITSC), 2021

In this study, we develop a data pipeline incorporating automated data quality checking, data imp... more In this study, we develop a data pipeline incorporating automated data quality checking, data imputation, and spatiotemporal visualization of large-scale traffic data to understand the changes in traffic patterns during hurricane evacuation as it unfolds. We collect large-scale Microwave Vehicle Detection System (MVDS) data during Hurricane Irma from four highways in Florida: I–75, I–95, I–4, and Florida Turnpike that served majority of the evacuation traffic. Based on an extensive analysis, we provide insights on network wide spatiotemporal evacuation traffic patterns of Hurricane Irma. Such insights will help transportation agencies recognize the utility of large-scale real-time data, previously unused, to better understand the extent and spatiotemporal distribution of evacuation traffic. To demonstrate this, we analyze the processed data to understand the influence of different spatiotemporal factors on the changes in evacuation traffic pattern. Our results show at least an 18-hour (approximately) time lag between the time of issuing an evacuation order and the time when people first started to evacuate in large numbers. Such findings have potential implications to deal with the challenges of mass evacuation in real time and allows us to develop large-scale network level evacuation traffic prediction model.

Research paper thumbnail of Real-Time Twitter Data Mining Approach to Infer User Perception Toward Active Mobility

Transportation Research Record: Journal of the Transportation Research Board, 2021

This study evaluates the level of service of shared transportation facilities through mining geot... more This study evaluates the level of service of shared transportation facilities through mining geotagged data from social media and analyzing the perceptions of road users. An algorithm is developed adopting a text classification approach with contextual understanding to filter out relevant information related to users’ perceptions toward active mobility. Using a heuristic-based keyword matching approach produces about 75% tweets that are out of context, so that approach is deemed unsuitable for information extraction from Twitter. This study implements six different text classification models and compares the performance of these models for tweet classification. The model is applied to real-world data to filter out relevant information, and content analysis is performed to check the distribution of keywords within the filtered data. The text classification model “term frequency-inverse document frequency” vectorizer-based logistic regression model performed best at classifying the tw...

Research paper thumbnail of Predicting traffic demand during hurricane evacuation using Real-time data from transportation systems and social media

Transportation Research Part C: Emerging Technologies, 2021

In recent times, hurricanes Matthew, Harvey, and Irma have disrupted the lives of millions of peo... more In recent times, hurricanes Matthew, Harvey, and Irma have disrupted the lives of millions of people across multiple states in the United States. Under hurricane evacuation, efficient traffic operations can maximize the use of transportation infrastructure, reducing evacuation time and stress due to massive congestion. Evacuation traffic prediction is critical to plan for effective traffic management strategies. However, due to the complex and dynamic nature of evacuation participation, predicting evacuation traffic demand long ahead of the actual evacuation is a very challenging task. Real-time information from various sources can significantly help us reliably predict evacuation demand. In this study, we use traffic sensor and Twitter data during hurricanes Matthew and Irma to predict traffic demand during evacuation for a longer forecasting horizon (greater than 1 hour). We present a machine learning approach using Long-Short Term Memory Neural Networks (LSTM-NN), trained over real-world traffic data during hurricane evacuation (hurricanes Irma and Matthew) using different combinations of input features and forecast horizons. We compare our prediction results against a baseline prediction and existing machine learning models. Results show that the proposed model can predict traffic demand during evacuation well up to 24 hours ahead. The proposed LSTM-NN model can significantly benefit future evacuation traffic management.

Research paper thumbnail of Modeling the dynamics of hurricane evacuation decisions from twitter data: An input output hidden markov modeling approach

Transportation Research Part C: Emerging Technologies, 2021

Evacuations play a critical role in saving human lives during hurricanes. But individual evacuati... more Evacuations play a critical role in saving human lives during hurricanes. But individual evacuation decision-making is a complex dynamic process, often studied using post-hurricane survey data. Alternatively, ubiquitous use of social media generates a massive amount of data that can be used to predict evacuation behavior in real time. In this paper, we present a method to infer individual evacuation behaviors (e.g., evacuation decision, timing, destination) from social media data. We develop an input output hidden Markov model (IO-HMM) to infer evacuation decisions from user tweets. To extract the underlying evacuation context from tweets, we first estimate a word2vec model from a corpus of more than 100 million tweets collected over four major hurricanes. Using input variables such as evacuation context, time to landfall, type of evacuation order, and the distance from home, the proposed model infers what activities are made by individuals, when they decide to evacuate, and where they evacuate to. To validate our results, we have created a labeled dataset from 38,256 tweets posted between September 2, 2017 and September 19, 2017 by 2,571 users from Florida during hurricane Irma. Our findings show that the proposed IO-HMM method can be useful for inferring evacuation behavior in real time from social media data. Since traditional surveys are infrequent, costly, and often performed at a post-hurricane period, the proposed approach can be very useful for predicting evacuation demand as a hurricane unfolds in real time.

Research paper thumbnail of A multilabel classification approach to identify hurricane‐induced infrastructure disruptions using social media data

Computer-Aided Civil and Infrastructure Engineering, 2020

Rapid identification of infrastructure disruptions during a disaster plays an important role in r... more Rapid identification of infrastructure disruptions during a disaster plays an important role in restoration and recovery operations. Due to the limitations of using physical sensing technologies, such as the requirement to cover a large area in a short period of time, studies have investigated the potential of social sensing for damage/disruption assessment following a disaster. However, previous studies focused on identifying whether a social media post is damage related or not. Hence, advanced methods are needed to infer actual infrastructure disruptions and their locations from such data. In this paper, we present a multilabel classification approach to identify the co‐occurrence of multiple types of infrastructure disruptions considering the sentiment toward a disruption—whether a post is reporting an actual disruption (negative), or a disruption in general (neutral), or not affected by a disruption (positive). In addition, we propose a dynamic mapping framework for visualizing ...

Research paper thumbnail of Relation between the thermal conductivity and grain size in a polycrystalline silicene sheet

AIP Conference Proceedings, 2018

Silicene, a two-dimensional allotrope of silicon, has outstanding mechanical and electrical prope... more Silicene, a two-dimensional allotrope of silicon, has outstanding mechanical and electrical properties which have triggered extensive research on its application in the field of developing faster computer chips, more efficient solar cells, improved medical technologies, vehicle, and aircraft parts, etc. In this work, we have demonstrated a way to use large-scale molecular dynamics to explore the effective thermal conductivity of nano-grained polycrystalline 2-D Silicene sheets and compare it with a pristine one. By performing non-equilibrium molecular dynamics (NEMD) simulations, the effect of grain size on the thermal conductivity of polycrystalline Silicene sheets has been investigated. For both pristine and polycrystalline Silicene sheet, structures of 30 nm × 30 nm are considered and Stillinger-Weber potential is used to investigate the atoms’ interaction with theneighborhood. The temperature profiles are used to find the thermal conductivity by Fourier’s Law of conduction. Comparing with the pristine Silicene sheet we have found a very intriguing result. Our results reveal that the ultra-fine nano-grained Silicene structures have an increasing trend for thermal conductivity commensurate with grain size. Larger the grain size becomes, higher the thermal conductivity is. However, for very small grain size the thermal conductivity is considerably less than the pristine structure. It is also noticed that the thermal conductivity of smaller grain size structures shows more grain size dependency while the thermal conductivity for larger grain size exhibits trivial gradient and almost converges to some certain range of values.The grain size based rising trend is then evaluatedby specific heat calculation.The density of states (DOS) is ultimately calculated for different grain sizes to verify the trend of changing thermal conductivities on the basis of noise sensitivity.Silicene, a two-dimensional allotrope of silicon, has outstanding mechanical and electrical properties which have triggered extensive research on its application in the field of developing faster computer chips, more efficient solar cells, improved medical technologies, vehicle, and aircraft parts, etc. In this work, we have demonstrated a way to use large-scale molecular dynamics to explore the effective thermal conductivity of nano-grained polycrystalline 2-D Silicene sheets and compare it with a pristine one. By performing non-equilibrium molecular dynamics (NEMD) simulations, the effect of grain size on the thermal conductivity of polycrystalline Silicene sheets has been investigated. For both pristine and polycrystalline Silicene sheet, structures of 30 nm × 30 nm are considered and Stillinger-Weber potential is used to investigate the atoms’ interaction with theneighborhood. The temperature profiles are used to find the thermal conductivity by Fourier’s Law of conduction. Comparing with the pristine...

Research paper thumbnail of Sharing Real-Time Traffic Information With Travelers Using Twitter: An Analysis of Effectiveness and Information Content

Frontiers in Built Environment, 2019

Ubiquitous smartphone technologies and virtual social networks offer us a unique opportunity to i... more Ubiquitous smartphone technologies and virtual social networks offer us a unique opportunity to instantly share information to a large number of people. Online social media platforms facilitate easy and rapid communication of real-time information by producing a huge amount of digital content. In this paper, we present an analysis of the data collected from 14 Florida Department of Transportation (FDOT) Twitter accounts created for sharing real-time traffic information. We analyze the activities, influence, attention received, and the effectiveness of gaining attention by these accounts. We propose several metrics in disseminating real-time traffic information. Using topic models, we also analyze the content of the shared information given in the tweets. Finally, we estimate an ordered logit model to determine the information value of a shared content based on its chance of getting retweeted. Based on the study, we propose a framework called Social Media-based Adaptive Real-time Traffic feed (SMART-Feed) that will significantly improve the effectiveness of real-time traffic information sharing through social media. Moreover, it will help to assess the value of real-time traffic information to travelers and developing social media strategies for sharing information.

Research paper thumbnail of Quantifying human mobility resilience to extreme events using geo-located social media data

EPJ Data Science, 2019

Mobility is one of the fundamental requirements of human life with significant societal impacts i... more Mobility is one of the fundamental requirements of human life with significant societal impacts including productivity, economy, social wellbeing, adaptation to a changing climate, and so on. Although human movements follow specific patterns during normal periods, there are limited studies on how such patterns change due to extreme events. To quantify the impacts of an extreme event to human movements, we introduce the concept of mobility resilience which is defined as the ability of a mobility system to manage shocks and return to a steady state in response to an extreme event. We present a method to detect extreme events from geo-located movement data and to measure mobility resilience and transient loss of resilience due to those events. Applying this method, we measure resilience metrics from geo-located social media data for multiple types of disasters occurred all over the world. Quantifying mobility resilience may help us to assess the higher-order socioeconomic impacts of extreme events and guide policies towards developing resilient infrastructures as well as a nation's overall disaster resilience strategies.

Research paper thumbnail of Grid Technologies for Social Science: the SAMD Project

IASSIST Quarterly, 2005

Grid Technologies for Social Science: the SAMD Project

Research paper thumbnail of A Study On Feasible Traffic Operation Alternatives At Signalized Intersection In Dhaka City

Research paper thumbnail of Estimation of Traffic Arrival Pattern at Signalized Intersection using ARIMA Model

International Journal of Computer Applications, 2015

Traffic arrival pattern is an important parameter in delay estimation at signalized intersection.... more Traffic arrival pattern is an important parameter in delay estimation at signalized intersection. Usually, arrival pattern is assumed to be Poisson distribution. However, it varies widely under different volume-capacity ratio at signalized intersection of an arterial road. Therefore, conventional Poisson model cannot predict traffic pattern properly. A time series ARIMA model was proposed in this study to compare with Poisson model. A Paramics simulation model of Route 18 arterial road located in New Brunswick, New Jersey, USA was studied for the research purpose. Three intersections in Route 18-Naricon Place intersection, South Woodland Avenue intersection and West Ferris Street intersection-were considered where traffic arrivals were under dispersed, random and over dispersed under different simulation scenarios respectively. Later, traffic arrival patterns obtained from simulation were compared with Poisson and ARIMA model using SAS statistical software. Arrival headway, vehicle counts per signal cycle, variance to mean ratio were considered and statistical analysis were performed between two candidate models. Study found that, ARIMA model predicts arrival pattern more accurately than Poisson model.

Research paper thumbnail of Seamless Access to Multiple Datasets (SAMD)–An ESRC e-Science Demonstrator

Research paper thumbnail of Understanding the efficiency of social media based crisis communication during hurricane Sandy

International Journal of Information Management, 2020