Pijush Kanti Dutta Pramanik
@nitdgp.ac.in
National Institute of Technology, Durgapur
Scopus Publications
Scholar Citations
Scholar h-index
Scholar i10-index
Scopus Publications
Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, Saurav Mallik, and Zhongming Zhao
Public Library of Science (PLoS)
Chronic kidney disease (CKD) has become a major global health crisis, causing millions of yearly deaths. Predicting the possibility of a person being affected by the disease will allow timely diagnosis and precautionary measures leading to preventive strategies for health. Machine learning techniques have been popularly applied in various disease diagnoses and predictions. Ensemble learning approaches have become useful for predicting many complex diseases. In this paper, we utilise the boosting method, one of the popular ensemble learnings, to achieve a higher prediction accuracy for CKD. Five boosting algorithms are employed: XGBoost, CatBoost, LightGBM, AdaBoost, and gradient boosting. We experimented with the CKD data set from the UCI machine learning repository. Various preprocessing steps are employed to achieve better prediction performance, along with suitable hyperparameter tuning and feature selection. We assessed the degree of importance of each feature in the dataset leading to CKD. The performance of each model was evaluated with accuracy, precision, recall, F1-score, Area under the curve-receiving operator characteristic (AUC-ROC), and runtime. AdaBoost was found to have the overall best performance among the five algorithms, scoring the highest in almost all the performance measures. It attained 100% and 98.47% accuracy for training and testing sets. This model also exhibited better precision, recall, and AUC-ROC curve performance.
Mehdi Gheisari, Fereshteh Ebrahimzadeh, Mohamadtaghi Rahimi, Mahdieh Moazzamigodarzi, Yang Liu, Pijush Kanti Dutta Pramanik, Mohammad Ali Heravi, Abolfazl Mehbodniya, Mustafa Ghaderzadeh, Mohammad Reza Feylizadeh,et al.
Institution of Engineering and Technology (IET)
Pijush Kanti Dutta Pramanik, Tarun Biswas, and Prasenjit Choudhury
Springer Science and Business Media LLC
Souvik Sengupta, Saurabh Pal, and Pijush Kanti Dutta Pramanik
Scalable Computing: Practice and Experience
Inquiry-based learning supports the independent knowledge development of the learner in an e-learning environment. It is crucial for the learner to obtain the appropriate Learning Object (LO) for the intended query. Mapping a learner's query to the right LO is a challenging task, as keyword-based searching on the topics or content does not guarantee the best result for various reasons. A query that apparently connects a topic may also implicitly refer to multiple other topics. Besides, the content of an LO with the same topic name often varies over different portals. Therefore, there is always a need for a method to automatically identify the latent topics of the query and then find the most relevant LO that covers the query. This paper aims to build a recommender system that maps a given input query to a suitable LO based on the most appropriate matching of learning contents. The proposed work employs an amalgamation of different supervised and unsupervised methods of natural language processing and machine learning. The machine learning model is trained on a handcrafted dataset to map queries into predefined topics. The proposed algorithm also leverages a dynamic topic modeling technique on learning content collected from three popular e-learning portals and uses a similarity score to map the learner's (user) query to the most appropriate LO.
Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, Majid Bashir Malik, Saurav Mallik, and Hong Qin
Frontiers Media SA
Introduction: Diabetes is considered one of the leading healthcare concerns affecting millions worldwide. Taking appropriate action at the earliest stages of the disease depends on early diabetes prediction and identification. To support healthcare providers for better diagnosis and prognosis of diseases, machine learning has been explored in the healthcare industry in recent years.Methods: To predict diabetes, this research has conducted experiments on five boosting algorithms on the Pima diabetes dataset. The dataset was obtained from the University of California, Irvine (UCI) machine learning repository, which contains several important clinical features. Exploratory data analysis was used to identify the characteristics of the dataset. Moreover, upsampling, normalisation, feature selection, and hyperparameter tuning were employed for predictive analytics.Results: The results were analysed using various statistical/machine learning metrics and k-fold cross-validation techniques. Gradient boosting achieved the greatest accuracy rate of 92.85% among all the classifiers. Precision, recall, f1-score, and receiver operating characteristic (ROC) curves were used to further validate the model.Discussion: The suggested model outperformed the current studies in terms of prediction accuracy, demonstrating its applicability to other diseases with similar predicate indications.
Pijush Kanti Dutta Pramanik, Saurabh Pal, and Prasenjit Choudhury
Springer Science and Business Media LLC
Shahid Mohammad Ganie, Pijush Kanti Dutta Pramanik, Majid Bashir Malik, Anand Nayyar, and Kyung Sup Kwak
Computers, Materials and Continua (Tech Science Press)
Pradeep Kumar Singh, Pijush Kanti Dutta Pramanik, and Prasenjit Choudhury
Springer Science and Business Media LLC
Pijush Kanti Dutta Pramanik, Saurabh Pal, and Moutan Mukhopadhyay
IGI Global
Big data has unlocked a new opening in healthcare. Thanks to the considerable benefits and opportunities, it has attracted the momentous attention of all the stakeholders in the healthcare industry. This chapter aims to provide an overall but thorough understanding of healthcare big data. The chapter covers the 10 ‘V's of healthcare big data as well as different healthcare data analytics including predictive and prescriptive analytics. The obvious advantages of implementing big data technologies in healthcare are meticulously described. The application areas and a good number of practical use cases are also discussed. Handling big data always remains a big challenge. The chapter identifies all the possible challenges in realizing the benefits of healthcare big data. The chapter also presents a brief survey of the tools and platforms, architectures, and commercial infrastructures for healthcare big data.
Pradeep Kumar Singh, Pijush Kanti Dutta Pramanik, Madhumita Sardar, Anand Nayyar, Mehedi Masud, and Prasenjit Choudhury
Computers, Materials and Continua (Tech Science Press)
Pijush Kanti Dutta Pramanik, Nilanjan Sinhababu, Anand Nayyar, Mehedi Masud, and Prasenjit Choudhury
Computers, Materials and Continua (Tech Science Press)
In mobile crowd computing (MCC), people’s smart mobile devices (SMDs) are utilized as computing resources. Considering the ever-growing computing capabilities of today’s SMDs, a collection of them can offer significantly high-performance computing services. In a local MCC, the SMDs are typically connected to a local Wi-Fi network. Organizations and institutions can leverage the SMDs available within the campus to form local MCCs to cater to their computing needs without any financial and operational burden. Though it offers an economical and sustainable computing solution, users’ mobility poses a serious issue in the QoS of MCC. To address this, before submitting a job to an SMD, we suggest estimating that particular SMD’s availability in the network until the job is finished. For this, we propose a convolutional GRU-based prediction model to assess how long an SMD is likely to be available in the network from any given point of time. For experimental purposes, we collected real users’mobility data (in-time and outtime) with respect to a Wi-Fi access point. To build the prediction model, we presented a novel feature extraction method to be applied to the time-series data. The experimental results prove that the proposed convolutional GRU model outperforms the conventional GRU model.
Arpan Sardar and Pijush Kanti Dutta Pramanik
Springer Singapore
Nilanjan Sinhababu and Pijush Kanti Dutta Pramanik
Springer Singapore
Pijush Kanti Dutta Pramanik, Sanjib Biswas, Saurabh Pal, Dragan Marinković, and Prasenjit Choudhury
MDPI AG
In mobile crowd computing (MCC), smart mobile devices (SMDs) are utilized as computing resources. To achieve satisfactory performance and quality of service, selecting the most suitable resources (SMDs) is crucial. The selection is generally made based on the computing capability of an SMD, which is defined by its various fixed and variable resource parameters. As the selection is made on different criteria of varying significance, the resource selection problem can be duly represented as an MCDM problem. However, for the real-time implementation of MCC and considering its dynamicity, the resource selection algorithm should be time-efficient. In this paper, we aim to find out a suitable MCDM method for resource selection in such a dynamic and time-constraint environment. For this, we present a comparative analysis of various MCDM methods under asymmetric conditions with varying selection criteria and alternative sets. Various datasets of different sizes are used for evaluation. We execute each program on a Windows-based laptop and also on an Android-based smartphone to assess average runtimes. Besides time complexity analysis, we perform sensitivity analysis and ranking order comparison to check the correctness, stability, and reliability of the rankings generated by each method.
Saurabh Pal, Pijush Kanti Dutta Pramanik, and Prasenjit Choudhury
Springer Science and Business Media LLC
Pijush Kanti Dutta Pramanik, Bulbul Mukherjee, Saurabh Pal, Tanmoy Pal, and Simar Preet Singh
IGI Global
Non-sustainable buildings have threatened the ecosystem globally. In this chapter, a comprehensive discussion on the green and smart building is presented, considering how the buildings are made green and smart and how they support in developing sustainable cities. Though smart buildings are the positive catalyst towards sustainability, the excessive use of electronic devices puts a check in attaining the overall green goal. This chapter suggests merging green and smart technologies to have green smart building (GSB) with the aim of offering the populations a smart and eco-friendly living. Promises and challenges in attaining this goal are meticulously explored. The GSB concept is discussed in detail, suitably supported with the architectural models of overall and the various components of a GSB. The communication architecture is also presented emphasizing on various entities and activities in different levels of communication between various digital components of a GSB. A few cases have been presented showing practical applications of green and smart technologies in buildings.
Pijush Kanti Dutta Pramanik, Nilanjan Sinhababu, Anand Nayyar, and Prasenjit Choudhury
IEEE
The QoS of mobile crowd computing (MCC), in which the public’s smart mobile devices (SMDs) are used for job execution, hampers due to users’ mobility. In this paper, we propose a model to predict SMDs’ availability in a campus-based MCC, where, generally, a set of users are available for a certain period regularly. Predicting the user’s availability before the job submission would help avoid unnecessary job offloading or job loss due to the designated SMD’s early departure. We recorded the real mobility traces of the users connected to a Wi-Fi access point of our research lab. We applied ConvLSTM on the mobility dataset to predict the availability of the SMD. A job submission scenario is simulated. The extensive evaluation of our approach shows that our method has an average accuracy of 78%, making the job submission more reliable.
Avick Kumar Dey, Pijush Kanti Dutta Pramanik, Prasenjit Choudhury, and Goutam Bandopadhyay
Springer Science and Business Media LLC
The productivity and impact of a researcher can be measured by considering the total number of articles authored by him/her and corresponding citations. Several techniques exist to evaluate the cumulative impact of the author’s scholarly output & performance by comparing publications to citations. However, all of them fail to rank each author uniquely, resulting in the same index value assigned to two or more authors, although they have diverse citation patterns. In some indexing, beyond a certain number of citations of a particular article, the subsequent citations do not add any value to the overall indexing. In this paper, a new indexing scheme, based on data envelopment analysis, is proposed which ensures the unique ranking by identifying the different index values of the authors who have even a minimal difference in the citation pattern. Furthermore, the proposed scheme ensures that every citation will have impact without any ceiling. The index is applied to a consistent data set having publications data of the last 40 years in the field of Computer Science. The outcome, when compared with the existing metrics, confirms that the proposed index provides more effective results by ranking authors distinctively.
Saurabh Pal, Pijush Kanti Dutta Pramanik, Anand Nayyar, and Prasenjit Choudhury
ACM
The traditional e-learning has been developed into personalised and ubiquitous learning, in which the learners find learning materials (LMs) that are suitable to their contextual requirements, and can access them from anywhere and anytime. In this paper, we propose a framework for a personalised recommendation in a ubiquitous learning platform, following a knowledge-based approach. The framework comprises modules like query processing, information storage and retrieval, and learner context mapping and reasoning. Learner's implicit and explicit contexts are used for assessing the preference and suitability and mapping with the LMs that are retrieved based on the learner's query analysis, with the help of educational metadata. Selecting suitable LMs based on different factors is a multi-criteria decision making (MCDM) problem. For prioritising the selection factors, we use SWARA, and for multi-objective decision making, we apply MOORA. Utilising these two techniques, the LMs are ranked and are recommended accordingly.
Pijush Kanti Dutta Pramanik, Nilanjan Sinhababu, Kyung-Sup Kwak, and Prasenjit Choudhury
Institute of Electrical and Electronics Engineers (IEEE)
Mobile crowd computing (MCC) that utilizes public-owned (crowd’s) smart mobile devices (SMDs) collectively can give adequate computing power without any additional financial and ecological cost. However, the major challenge is to cope with the mobility (or availability) issue of SMDs. User’s unpredicted mobility makes the SMDs really unstable resources. Selecting such erratic resources for job schedule would result in frequent job offloading and, in the worst case, job loss, which would affect the overall performance and the quality of service of MCC. In a Local MCC, generally, a set of users are available for a certain period regularly. Based on this information, the chances of a user being available for a certain duration from a given point of time can be predicted. In this paper, we provide an effective model to predict the availability of the users (i.e., their SMDs) in such an MCC environment. We argue that before submitting a job to an SMD, the stability of it is to be assessed for the duration of execution of the job to be assigned. If the predicted availability period is greater than the job size, then only the job should be assigned to the SMD. An accurate prediction will minimize the unnecessary job offloading or job loss due to the early departure of the designated SMD. We propose an advanced convolutional feature extraction mechanism that is applied to LSTM and GRU-based time-series prediction models for predicting SMD availability. To collect user mobility data, we considered a research lab scenario, where real mobility traces were recorded with respect to a Wi-Fi access point. We compared the prediction performances of convolutional LSTM and GRU with the basic LSTM and GRU and ARIMA in terms of MAE, RMSE, R2, accuracy, and perplexity. In all the measurements, the proposed convolutional LSTM exhibited considerably better prediction performance.
Pijush Kanti Dutta Pramanik, Saurabh Pal, Aditya Brahmachari, and Prasenjit Choudhury
IGI Global
This chapter describes how traditionally, Cloud Computing has been used for processing Internet of Things (IoT) data. This works fine for the analytical and batch processing jobs. But most of the IoT applications demand real-time response which cannot be achieved through Cloud Computing mainly because of inherent latency. Fog Computing solves this problem by offering cloud-like services at the edge of the network. The computationally powerful edge devices have enabled realising this idea. Witnessing the exponential rise of IoT applications, Fog Computing deserves an in-depth exploration. This chapter establishes the need for Fog Computing for processing IoT data. Readers will be able to gain a fair comprehension of the various aspects of Fog Computing. The benefits, challenges and applications of Fog Computing with respect to IoT have been mentioned elaboratively. An architecture for IoT data processing is presented. A thorough comparison between Cloud and Fog has been portrayed. Also, a detailed discussion has been depicted on how the IoT, Fog, and Cloud interact among them.
Pijush Kanti Dutta Pramanik, Saurabh Pal, Moutan Mukhopadhyay, and Simar Preet Singh
Elsevier
Pijush Kanti Dutta Pramanik, Moutan Mukhopadhyay, and Saurabh Pal
Springer Singapore
Saurabh Pal, Pijush Kanti Dutta Pramanik, Musleh Alsulami, Anand Nayyar, Mohammad Zarour, and Prasenjit Choudhury
Computers, Materials and Continua (Tech Science Press)
Bhawna Suri, Pijush K.D. Pramanik, and Shweta Taneja
Bentham Science Publishers Ltd.
Background: The abundant use of personal vehicles has raised the challenge of parking the vehicle in crowded places such as shopping malls. To help the driver with efficient and troublefree parking, a smart and innovative parking assistance system is required. In addition to discussing the basics of smart parking, Internet of Things (IoT), Cloud computing, and Fog computing, this chapter proposes an IoT-based smart parking system for shopping malls. Methods: To process the IoT data, a hybrid Fog architecture is adopted in order to reduce the latency, where the Fog nodes are connected across the hierarchy. The advantages of this auxiliary connection are discussed critically by comparing with other Fog architectures (hierarchical and P2P). An algorithm is defined to support the proposed architecture and is implemented on two real- world use-cases having requirements of identifying the nearest free car parking slot. The implementation is simulated for a single mall scenario as well as for a campus with multiple malls with parking areas spread across them. Results: The simulation results have proved that our proposed architecture shows lower latency as compared to the traditional smart parking systems that use Cloud architecture. Conclusion: The hybrid Fog architecture minimizes communication latency significantly. Hence, the proposed architecture can suitably be applied for other IoT-based real-time applications.