aditya chakraborty - Academia.edu (original) (raw)
Papers by aditya chakraborty
Agricultural productivity has a vital role in the Indian economy, but it is seriously hampered by... more Agricultural productivity has a vital role in the Indian economy, but it is seriously hampered by pests and plant diseases. Neural networks have been a major step forward in solving this problem in the past two decades. However, the existing systems in place are computation-heavy and costly to implement. Such tasks also ideally require a dataset of leaf images that simulates real environment conditions, which is hard to find. The motivation of this paper therefore is to solve all these issues by building a light-weight and cost efficient deep learning architecture with the proposed DenseNet-121 model that classifies leaf images from a dataset called ’PlantDoc’ across 28 classes with 1874 training images and 468 validation images. A separate test dataset is held out only for checking model performance on unknown data. Implementation is done using Fastai framework, because of its faster computational power, easy workflow and unique data cleaning functionalities. Overall, the classification accuracy achieved is 92.5%.
2021 5th International Conference on Computing Methodologies and Communication (ICCMC), 2021
Agricultural productivity has a vital role in the Indian economy, but it is seriously hampered by... more Agricultural productivity has a vital role in the Indian economy, but it is seriously hampered by pests and plant diseases. Neural networks have been a major step forward in solving this problem in the past two decades. However, the existing systems in place are computation-heavy and costly to implement. Such tasks also ideally require a dataset of leaf images that simulates real environment conditions, which is hard to find. The motivation of this paper therefore is to solve all these issues by building a light-weight and cost efficient deep learning architecture with the proposed DenseNet-121 model that classifies leaf images from a dataset called ’PlantDoc’ across 28 classes with 1874 training images and 468 validation images. A separate test dataset is held out only for checking model performance on unknown data. Implementation is done using Fastai framework, because of its faster computational power, easy workflow and unique data cleaning functionalities. Overall, the classification accuracy achieved is 92.5%.
Zenodo (CERN European Organization for Nuclear Research), Sep 4, 2022
Coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus. COVID-19 ... more Coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus. COVID-19 affects different peoplein different ways. Most infected people will develop mild to moderate illness and recover without hospitalization. Face mask detection had seen significant progress in the domains of Image processing and Computer vision, since the rise of the Covid-19 pandemic. The model uses proposed approach of deep learning, Tensorflow, Keras and OpenCV to detect face masks. This model can be used for safety purposes since it is very resource efficient to deploy. The technique deployed in this model gives an accuracy score of 0.9264.
Journal of Cancer Research and Treatment
Journal of Statistical Theory and Applications
Pancreatic cancer is one of the deadliest carcinogenic diseases affecting people all over the wor... more Pancreatic cancer is one of the deadliest carcinogenic diseases affecting people all over the world. The majority of patients are usually detected at Stage III or Stage IV, and the chances of survival are very low once detected at the late stages. This study focuses on building an efficient data-driven analytical predictive model based on the associated risk factors and identifying the most contributing factors influencing the survival times of patients diagnosed with pancreatic cancer using the XGBoost (eXtreme Gradient Boosting) algorithm. The grid-search mechanism was implemented to compute the optimum values of the hyper-parameters of the analytical model by minimizing the root mean square error (RMSE). The optimum hyperparameters of the final analytical model were selected by comparing the values with 243 competing models. To check the validity of the model, we compared the model’s performance with ten deep neural network models, grown sequentially with different activation fun...
In today’s world, there is a continuous need for automated appliances. With the increase in the l... more In today’s world, there is a continuous need for automated appliances. With the increase in the living standards, there is an immediate need for developing circuits that would change the complexity of life to simplicity. This Project title “Bidirectional Visitor Counter with Automatic Room Light Controller and Arduino as the master controller” is designed and presented in order to count the visitors of an auditorium, hall, offices, malls, sports venue, etc. The system counts both the entering and exiting visitor of the auditorium or hall or other place, where it is placed. Depending upon the sensors interruption, the system identifies the entry and exit of the visitor. On the successful implementation of the system, it displays the number of visitor present in the auditorium or hall. This is an economical cost reducing system when implemented in places where the visitors have to be counted and controlled. Counting the visitors can be time consuming so it helps to maximize the effici...
Objective: A nationally representative sample of US adults was used to examine the prevalence of ... more Objective: A nationally representative sample of US adults was used to examine the prevalence of COVID-19 cases, testing, symptoms, and vaccine uptake, and associations with tobacco product use. Methods: Data came from the 2021 National Health Interview Survey. The 2021 Sample Adult component included 29,482 participants with a response rate of 50.9%. We investigated COVID-19-related outcomes by tobacco product use status and reported national estimates. Multivariable regression models were performed accounting for demographics (e.g., age, sex, poverty level), serious psychological distress, disability, and chronic health condition. Results: In our regression analyses, odds of self-reported COVID-19 infection were significantly lower for combustible tobacco product users (vs. non-users; Adjusted Odds ratio [AOR=0.73; 95% confidence interval [CI]=0.62-0.85]. Combustible tobacco users also were less likely to report ever testing for COVID-19 (AOR=0.88; 95% CI=0.79-0.98), ever testing ...
In machine learning and data science literature, clustering is the task of dividing the observati... more In machine learning and data science literature, clustering is the task of dividing the observations (data points) into several categories in such a way that data points falling into one group are being dissimilar than the data points falling to the other groups such that the variation within a group is minimized and the variation between the groups is maximized. It falls under the class of unsupervised learning techniques. It is primarily a tool to classify individuals on the basis of similarity and dissimilarity between them. Our present study utilizes the world happiness data of 156 countries collected by the Gallup World Poll. Our study proposes a useful clustering approach with a very high degree of accuracy to classify different countries of the world based on several economic and social indicators. The most appropriate clustering algorithm has been selected based on different statistical methods. We also proceed to rank the top ten countries in each of the three clusters according to their happiness score. The three leading countries in terms of happiness from cluster 1 (medium happiness), cluster 2 (high happiness), and cluster 3 (low happiness) are Oman, Denmark, and Guyana, respectively, followed by United Arab Emirates, Finland, and Pakistan. Finally, we use four popular machine learning classification algorithms to validate our cluster-based algorithm and obtained very consistent results with high accuracy.
Scholars Journal of Physics, Mathematics and Statistics
Original Research Article Purpose: Philosophers and many modern-day researchers are convinced by ... more Original Research Article Purpose: Philosophers and many modern-day researchers are convinced by the fact that the pursuit of happiness is the ultimate goal for humankind. Aristotle believed that the utmost goal of human life was eudaimonia (interpreted as "happiness," "human flourishing," or "a good life."). Recently, many economists and physiologists have been doing applied research in the areas of subjective well-being (SWB) or happiness and trying to understand how it improves the quality of life of individual beings. Thus, searching for a data-driven analytical model is crucial to predict SWB and enhance the quality of life. Methods: Our present study utilizes the world happiness database obtained from the GallupWorld Poll on the happiness of 156 countries. However, our study focuses on using only the data of fiftyfour developed countries, based on the human development index (HDI). We have developed a non-linear analytical model that predicts the average happiness score based on eleven risk factors with a high degree of accuracy. We also compared our analytical model with three other statistical models, and our model outperformed the rest of the three in terms of RMSE and MAE. Results: Our analytical model includes five important findings. The response of the proposed model is the average score of happiness of individuals in developed countries. In addition to predicting the happiness score, our model identifies the individual risk factors and their corresponding interactions that significantly contribute to happiness. We rank these risk factors by their percentage of contributions to the happiness score. We also proceed to rank the developed countries with respect to their predicted happiness score from our developed model. From our study, we found Finland being number one, followed by Denmark. The U.S is fifth and Romania being 54th. Conclusion: The proposed model offers other useful information on the subject area. Our analytical model has been validated and tested to be of high quality, and our prediction of happiness is with a high degree of accuracy. We created a survey questionnaire (appendix 1) based on the data that can be used along with our model by any company for the strategic planning or decision making.
arXiv (Cornell University), May 18, 2020
American journal of cancer research, 2021
Pancreatic cancer is one of the deadliest diseases and becoming an increasingly common cause of c... more Pancreatic cancer is one of the deadliest diseases and becoming an increasingly common cause of cancer mortality. It continues to give rise to massive challenges to clinicians and cancer researchers. One of the main goals of our present study is to determine if there exists any statistically significant difference in the survival probabilities of male and female pancreatic cancer patients in different cancer stages and irrespective of stages. Another goal is to investigate if there exists any parametric probability distribution function that best fits the male and female patient survival times in different stages of cancer, irrespective of stages, and compare the survival probabilities with the non-parametric Kaplan-Meier (KM) method. We employed both parametric and non-parametric statistical approaches to examine the survival probabilities of 10,000 patients diagnosed with pancreatic cancer and showed that there is no significant difference in male and female survival times at any ...
2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), 2020
Most of the existing video storage systems rely on offline processing to support the feature-base... more Most of the existing video storage systems rely on offline processing to support the feature-based indexing on video streams. The feature-based indexing technique provides an effective way for users to search video content through visual features, such as object categories (e.g., cars and persons). However, due to the reliance on offline processing, video streams along with their captured features cannot be searchable immediately after video streams are recorded. According to our investigation, buffering and storing live video steams are more time-consuming than the YOLO v3 object detector. Such observation motivates us to propose a real-time feature indexing (RTFI) system to enable instantaneous feature-based indexing on live video streams after video streams are captured and processed through object detectors. RTFI achieves its real-time goal via incorporating the novel design of metadata structure and data placement, the capability of modern object detector (i.e., YOLO v3), and the deduplication techniques to avoid storing repetitive video content. Notably, RTFI is the first system design for realizing real-time feature-based indexing on live video streams. RTFI is implemented on a Linux server and can improve the system throughput by upto 10.60x, compared with the base system without the proposed design. In addition, RTFI is able to make the video content searchable within 20 milliseconds for 10 live video streams after the video content is received by the proposed system, excluding the network transfer latency.
Short documentary on our work on the use of network cameras to observe COVID-19 social distancing... more Short documentary on our work on the use of network cameras to observe COVID-19 social distancing measures
Global Journal of Medical Research, 2021
Pancreatic cancer is comparatively rare but extremely lethal. In the United States, pancreatic ca... more Pancreatic cancer is comparatively rare but extremely lethal. In the United States, pancreatic cancer is the 4thleading cause of cancer death, and in Europe, it is the 6th. Though Pancreatic cancer remains incurable if detected late, research into improving the therapeutic strategy has increased significantly in recent years. However, it is ambiguous if sustained improvements have been achieved by identifying the most prominent risk factors responsible for cancer. In this article, we studied the survival times of 677 pancreatic cancer patients with fifteen risk factors. The semi-parametric Cox proportional hazard (CPH) model was used to examine the covariate effect taking into account all of the statistically significant risk factors and their significant two way interactions. A careful and rigorous assessment of the risk factors based on the AIC of the stepwise selection technique revealed seven risk factors, and ten interaction terms are statistically significantly contributing to...
Open Journal of Applied Sciences, 2021
Background: Acute Myeloid leukemia (AML) is the most prominent acute leukemia in adults. In the U... more Background: Acute Myeloid leukemia (AML) is the most prominent acute leukemia in adults. In the United States, we experience over 20,000 cases per year. Over the past decade, improvements in the diagnosis of subtypes of AML and advances in therapeutic approaches have improved the outlook for patients with AML. However, despite these advancements, the survival rate among patients who are less than 65 years of age is only 40 percent. Purpose: The purpose of the paper is to study if there exists any significant difference in the survival probabilities of male and female AML patients. Also, we want to investigate if there is any parametric probability distribution that best fits the male and female patient survival and compare the survival probabilities with the non-parametric Kaplan-Meier (KM) method. Methods: We used both parametric and non-parametric statistical methods to perform the survival analysis to assess the survival probabilities of 2015 patients diagnosed with AML. Results: We found evidence of a statistically significant difference between the mean survival time of male and female patients diagnosed with AML. We performed parametric survival analysis and found a Generalized Extreme Value (GEV) distribution best fitting the data of the survival time for male and female patients. We then estimated the survival probabilities and compared them with the frequently used non-parametric Kaplan-Meier (KM) survival method. Conclusion: The comparison between the survival probability estimates of the two methods revealed a better survival probability estimate by the parametric method than the Kaplan-Meier. We also compared the median survival time of male and female patients individually with descriptive, parametric, and non-parametric methods of analysis. The parametric survival analysis is more robust and efficient because it is based on a well-defined parametric probabilistic distribution, hence preferred over the non-parametric Kaplan-Meier estimate. This study offers therapeutic signi-How to cite this paper: Chakraborty, A. and Tsokos, C.P. (2021) Parametric and Non-Parametric Survival Analysis of Patients with Acute Myeloid Leukemia (AML).
IEEE Communications Surveys & Tutorials, 2020
The Internet of Things (IoT) extends the Internet connectivity into billions of IoT devices aroun... more The Internet of Things (IoT) extends the Internet connectivity into billions of IoT devices around the world, where the IoT devices collect and share information to reflect status of the physical world. The Autonomous Control System (ACS), on the other hand, performs control functions on the physical systems without external intervention over an extended period of time. The integration of IoT and ACS results in a new concept-autonomous IoT (AIoT). The sensors collect information on the system status, based on which the intelligent agents in the IoT devices as well as the Edge/Fog/Cloud servers make control decisions for the actuators to react. In order to achieve autonomy, a promising method is for the intelligent agents to leverage the techniques in the field of artificial intelligence, especially reinforcement learning (RL) and deep reinforcement learning (DRL) for decision making. In this paper, we first provide a tutorial of DRL, and then propose a general model for the applications of RL/DRL in AIoT. Next, a comprehensive survey of the state-of-art research on DRL for AIoT is presented, where the existing works are classified and summarized under the umbrella of the proposed general DRL model. Finally, the challenges and open issues for future research are identified.
Public Policy Research, 2011
Fuel, 1978
A study of the effect of ash yield on the maximum thickness of the plastic layer (MTPL) of some c... more A study of the effect of ash yield on the maximum thickness of the plastic layer (MTPL) of some coking coals (as measured by the Sapozhnikov plastometer) has revealed that with an increase in the former the latter in general decreases. A rectilinear relation approximately exists between the ash percentage (dry basis) and log MTPL values of coals. For the samples studied, a multiple correlation incorporating the rank factor was found to be unnecessary. Higher Fe203 and SO3 contents from the coal were found to be associated with higher MTPL values.
Agricultural productivity has a vital role in the Indian economy, but it is seriously hampered by... more Agricultural productivity has a vital role in the Indian economy, but it is seriously hampered by pests and plant diseases. Neural networks have been a major step forward in solving this problem in the past two decades. However, the existing systems in place are computation-heavy and costly to implement. Such tasks also ideally require a dataset of leaf images that simulates real environment conditions, which is hard to find. The motivation of this paper therefore is to solve all these issues by building a light-weight and cost efficient deep learning architecture with the proposed DenseNet-121 model that classifies leaf images from a dataset called ’PlantDoc’ across 28 classes with 1874 training images and 468 validation images. A separate test dataset is held out only for checking model performance on unknown data. Implementation is done using Fastai framework, because of its faster computational power, easy workflow and unique data cleaning functionalities. Overall, the classification accuracy achieved is 92.5%.
2021 5th International Conference on Computing Methodologies and Communication (ICCMC), 2021
Agricultural productivity has a vital role in the Indian economy, but it is seriously hampered by... more Agricultural productivity has a vital role in the Indian economy, but it is seriously hampered by pests and plant diseases. Neural networks have been a major step forward in solving this problem in the past two decades. However, the existing systems in place are computation-heavy and costly to implement. Such tasks also ideally require a dataset of leaf images that simulates real environment conditions, which is hard to find. The motivation of this paper therefore is to solve all these issues by building a light-weight and cost efficient deep learning architecture with the proposed DenseNet-121 model that classifies leaf images from a dataset called ’PlantDoc’ across 28 classes with 1874 training images and 468 validation images. A separate test dataset is held out only for checking model performance on unknown data. Implementation is done using Fastai framework, because of its faster computational power, easy workflow and unique data cleaning functionalities. Overall, the classification accuracy achieved is 92.5%.
Zenodo (CERN European Organization for Nuclear Research), Sep 4, 2022
Coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus. COVID-19 ... more Coronavirus disease (COVID-19) is an infectious disease caused by the SARS-CoV-2 virus. COVID-19 affects different peoplein different ways. Most infected people will develop mild to moderate illness and recover without hospitalization. Face mask detection had seen significant progress in the domains of Image processing and Computer vision, since the rise of the Covid-19 pandemic. The model uses proposed approach of deep learning, Tensorflow, Keras and OpenCV to detect face masks. This model can be used for safety purposes since it is very resource efficient to deploy. The technique deployed in this model gives an accuracy score of 0.9264.
Journal of Cancer Research and Treatment
Journal of Statistical Theory and Applications
Pancreatic cancer is one of the deadliest carcinogenic diseases affecting people all over the wor... more Pancreatic cancer is one of the deadliest carcinogenic diseases affecting people all over the world. The majority of patients are usually detected at Stage III or Stage IV, and the chances of survival are very low once detected at the late stages. This study focuses on building an efficient data-driven analytical predictive model based on the associated risk factors and identifying the most contributing factors influencing the survival times of patients diagnosed with pancreatic cancer using the XGBoost (eXtreme Gradient Boosting) algorithm. The grid-search mechanism was implemented to compute the optimum values of the hyper-parameters of the analytical model by minimizing the root mean square error (RMSE). The optimum hyperparameters of the final analytical model were selected by comparing the values with 243 competing models. To check the validity of the model, we compared the model’s performance with ten deep neural network models, grown sequentially with different activation fun...
In today’s world, there is a continuous need for automated appliances. With the increase in the l... more In today’s world, there is a continuous need for automated appliances. With the increase in the living standards, there is an immediate need for developing circuits that would change the complexity of life to simplicity. This Project title “Bidirectional Visitor Counter with Automatic Room Light Controller and Arduino as the master controller” is designed and presented in order to count the visitors of an auditorium, hall, offices, malls, sports venue, etc. The system counts both the entering and exiting visitor of the auditorium or hall or other place, where it is placed. Depending upon the sensors interruption, the system identifies the entry and exit of the visitor. On the successful implementation of the system, it displays the number of visitor present in the auditorium or hall. This is an economical cost reducing system when implemented in places where the visitors have to be counted and controlled. Counting the visitors can be time consuming so it helps to maximize the effici...
Objective: A nationally representative sample of US adults was used to examine the prevalence of ... more Objective: A nationally representative sample of US adults was used to examine the prevalence of COVID-19 cases, testing, symptoms, and vaccine uptake, and associations with tobacco product use. Methods: Data came from the 2021 National Health Interview Survey. The 2021 Sample Adult component included 29,482 participants with a response rate of 50.9%. We investigated COVID-19-related outcomes by tobacco product use status and reported national estimates. Multivariable regression models were performed accounting for demographics (e.g., age, sex, poverty level), serious psychological distress, disability, and chronic health condition. Results: In our regression analyses, odds of self-reported COVID-19 infection were significantly lower for combustible tobacco product users (vs. non-users; Adjusted Odds ratio [AOR=0.73; 95% confidence interval [CI]=0.62-0.85]. Combustible tobacco users also were less likely to report ever testing for COVID-19 (AOR=0.88; 95% CI=0.79-0.98), ever testing ...
In machine learning and data science literature, clustering is the task of dividing the observati... more In machine learning and data science literature, clustering is the task of dividing the observations (data points) into several categories in such a way that data points falling into one group are being dissimilar than the data points falling to the other groups such that the variation within a group is minimized and the variation between the groups is maximized. It falls under the class of unsupervised learning techniques. It is primarily a tool to classify individuals on the basis of similarity and dissimilarity between them. Our present study utilizes the world happiness data of 156 countries collected by the Gallup World Poll. Our study proposes a useful clustering approach with a very high degree of accuracy to classify different countries of the world based on several economic and social indicators. The most appropriate clustering algorithm has been selected based on different statistical methods. We also proceed to rank the top ten countries in each of the three clusters according to their happiness score. The three leading countries in terms of happiness from cluster 1 (medium happiness), cluster 2 (high happiness), and cluster 3 (low happiness) are Oman, Denmark, and Guyana, respectively, followed by United Arab Emirates, Finland, and Pakistan. Finally, we use four popular machine learning classification algorithms to validate our cluster-based algorithm and obtained very consistent results with high accuracy.
Scholars Journal of Physics, Mathematics and Statistics
Original Research Article Purpose: Philosophers and many modern-day researchers are convinced by ... more Original Research Article Purpose: Philosophers and many modern-day researchers are convinced by the fact that the pursuit of happiness is the ultimate goal for humankind. Aristotle believed that the utmost goal of human life was eudaimonia (interpreted as "happiness," "human flourishing," or "a good life."). Recently, many economists and physiologists have been doing applied research in the areas of subjective well-being (SWB) or happiness and trying to understand how it improves the quality of life of individual beings. Thus, searching for a data-driven analytical model is crucial to predict SWB and enhance the quality of life. Methods: Our present study utilizes the world happiness database obtained from the GallupWorld Poll on the happiness of 156 countries. However, our study focuses on using only the data of fiftyfour developed countries, based on the human development index (HDI). We have developed a non-linear analytical model that predicts the average happiness score based on eleven risk factors with a high degree of accuracy. We also compared our analytical model with three other statistical models, and our model outperformed the rest of the three in terms of RMSE and MAE. Results: Our analytical model includes five important findings. The response of the proposed model is the average score of happiness of individuals in developed countries. In addition to predicting the happiness score, our model identifies the individual risk factors and their corresponding interactions that significantly contribute to happiness. We rank these risk factors by their percentage of contributions to the happiness score. We also proceed to rank the developed countries with respect to their predicted happiness score from our developed model. From our study, we found Finland being number one, followed by Denmark. The U.S is fifth and Romania being 54th. Conclusion: The proposed model offers other useful information on the subject area. Our analytical model has been validated and tested to be of high quality, and our prediction of happiness is with a high degree of accuracy. We created a survey questionnaire (appendix 1) based on the data that can be used along with our model by any company for the strategic planning or decision making.
arXiv (Cornell University), May 18, 2020
American journal of cancer research, 2021
Pancreatic cancer is one of the deadliest diseases and becoming an increasingly common cause of c... more Pancreatic cancer is one of the deadliest diseases and becoming an increasingly common cause of cancer mortality. It continues to give rise to massive challenges to clinicians and cancer researchers. One of the main goals of our present study is to determine if there exists any statistically significant difference in the survival probabilities of male and female pancreatic cancer patients in different cancer stages and irrespective of stages. Another goal is to investigate if there exists any parametric probability distribution function that best fits the male and female patient survival times in different stages of cancer, irrespective of stages, and compare the survival probabilities with the non-parametric Kaplan-Meier (KM) method. We employed both parametric and non-parametric statistical approaches to examine the survival probabilities of 10,000 patients diagnosed with pancreatic cancer and showed that there is no significant difference in male and female survival times at any ...
2020 IEEE 44th Annual Computers, Software, and Applications Conference (COMPSAC), 2020
Most of the existing video storage systems rely on offline processing to support the feature-base... more Most of the existing video storage systems rely on offline processing to support the feature-based indexing on video streams. The feature-based indexing technique provides an effective way for users to search video content through visual features, such as object categories (e.g., cars and persons). However, due to the reliance on offline processing, video streams along with their captured features cannot be searchable immediately after video streams are recorded. According to our investigation, buffering and storing live video steams are more time-consuming than the YOLO v3 object detector. Such observation motivates us to propose a real-time feature indexing (RTFI) system to enable instantaneous feature-based indexing on live video streams after video streams are captured and processed through object detectors. RTFI achieves its real-time goal via incorporating the novel design of metadata structure and data placement, the capability of modern object detector (i.e., YOLO v3), and the deduplication techniques to avoid storing repetitive video content. Notably, RTFI is the first system design for realizing real-time feature-based indexing on live video streams. RTFI is implemented on a Linux server and can improve the system throughput by upto 10.60x, compared with the base system without the proposed design. In addition, RTFI is able to make the video content searchable within 20 milliseconds for 10 live video streams after the video content is received by the proposed system, excluding the network transfer latency.
Short documentary on our work on the use of network cameras to observe COVID-19 social distancing... more Short documentary on our work on the use of network cameras to observe COVID-19 social distancing measures
Global Journal of Medical Research, 2021
Pancreatic cancer is comparatively rare but extremely lethal. In the United States, pancreatic ca... more Pancreatic cancer is comparatively rare but extremely lethal. In the United States, pancreatic cancer is the 4thleading cause of cancer death, and in Europe, it is the 6th. Though Pancreatic cancer remains incurable if detected late, research into improving the therapeutic strategy has increased significantly in recent years. However, it is ambiguous if sustained improvements have been achieved by identifying the most prominent risk factors responsible for cancer. In this article, we studied the survival times of 677 pancreatic cancer patients with fifteen risk factors. The semi-parametric Cox proportional hazard (CPH) model was used to examine the covariate effect taking into account all of the statistically significant risk factors and their significant two way interactions. A careful and rigorous assessment of the risk factors based on the AIC of the stepwise selection technique revealed seven risk factors, and ten interaction terms are statistically significantly contributing to...
Open Journal of Applied Sciences, 2021
Background: Acute Myeloid leukemia (AML) is the most prominent acute leukemia in adults. In the U... more Background: Acute Myeloid leukemia (AML) is the most prominent acute leukemia in adults. In the United States, we experience over 20,000 cases per year. Over the past decade, improvements in the diagnosis of subtypes of AML and advances in therapeutic approaches have improved the outlook for patients with AML. However, despite these advancements, the survival rate among patients who are less than 65 years of age is only 40 percent. Purpose: The purpose of the paper is to study if there exists any significant difference in the survival probabilities of male and female AML patients. Also, we want to investigate if there is any parametric probability distribution that best fits the male and female patient survival and compare the survival probabilities with the non-parametric Kaplan-Meier (KM) method. Methods: We used both parametric and non-parametric statistical methods to perform the survival analysis to assess the survival probabilities of 2015 patients diagnosed with AML. Results: We found evidence of a statistically significant difference between the mean survival time of male and female patients diagnosed with AML. We performed parametric survival analysis and found a Generalized Extreme Value (GEV) distribution best fitting the data of the survival time for male and female patients. We then estimated the survival probabilities and compared them with the frequently used non-parametric Kaplan-Meier (KM) survival method. Conclusion: The comparison between the survival probability estimates of the two methods revealed a better survival probability estimate by the parametric method than the Kaplan-Meier. We also compared the median survival time of male and female patients individually with descriptive, parametric, and non-parametric methods of analysis. The parametric survival analysis is more robust and efficient because it is based on a well-defined parametric probabilistic distribution, hence preferred over the non-parametric Kaplan-Meier estimate. This study offers therapeutic signi-How to cite this paper: Chakraborty, A. and Tsokos, C.P. (2021) Parametric and Non-Parametric Survival Analysis of Patients with Acute Myeloid Leukemia (AML).
IEEE Communications Surveys & Tutorials, 2020
The Internet of Things (IoT) extends the Internet connectivity into billions of IoT devices aroun... more The Internet of Things (IoT) extends the Internet connectivity into billions of IoT devices around the world, where the IoT devices collect and share information to reflect status of the physical world. The Autonomous Control System (ACS), on the other hand, performs control functions on the physical systems without external intervention over an extended period of time. The integration of IoT and ACS results in a new concept-autonomous IoT (AIoT). The sensors collect information on the system status, based on which the intelligent agents in the IoT devices as well as the Edge/Fog/Cloud servers make control decisions for the actuators to react. In order to achieve autonomy, a promising method is for the intelligent agents to leverage the techniques in the field of artificial intelligence, especially reinforcement learning (RL) and deep reinforcement learning (DRL) for decision making. In this paper, we first provide a tutorial of DRL, and then propose a general model for the applications of RL/DRL in AIoT. Next, a comprehensive survey of the state-of-art research on DRL for AIoT is presented, where the existing works are classified and summarized under the umbrella of the proposed general DRL model. Finally, the challenges and open issues for future research are identified.
Public Policy Research, 2011
Fuel, 1978
A study of the effect of ash yield on the maximum thickness of the plastic layer (MTPL) of some c... more A study of the effect of ash yield on the maximum thickness of the plastic layer (MTPL) of some coking coals (as measured by the Sapozhnikov plastometer) has revealed that with an increase in the former the latter in general decreases. A rectilinear relation approximately exists between the ash percentage (dry basis) and log MTPL values of coals. For the samples studied, a multiple correlation incorporating the rank factor was found to be unnecessary. Higher Fe203 and SO3 contents from the coal were found to be associated with higher MTPL values.