Sudarshan Nandy
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Previous Organizations / Institutes
The organizations / institutes from the scholar's other articles in the past ten years
Research Subjects
Sudarshan Nandy has a total of 43 co-authors. Here are the top co-authors by number of shared publications:
- Mainak Adhikari
Indian Institute of Science Education and Research Thiruvananthapuram
6 shared publications Partha Pratim Sarkar
5 shared publicationsAchintya Das
4 shared publications- Abhishek Hazra
Department of Computer Science and Engineering, Indian Institute of Information Technology, Sri City, India
3 shared publications Mainak Adhikari
2 shared publications- Varun Girijan Menon
SCMS School of Engineering and Technology
2 shared publications
Latest Publications
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11  (3) , 3832-3839
Edge-Centric Intelligent Early Warning System for Residual Soil Stability Prediction in Slope
Different geospatial and geotechnical parameters change over time and can affect the residual soil stability on a slope. Thus, it is essential to analyze the stability of slopes continuously to identify the potential landslide sections. The stability of slopes is defined by the factor of safety (FOS). To track the immediate changes in soil stability, it is essential to monitor multiple environmental parameters using Internet of Things (IoT) devices for real-time decision making. Further, the relation between the environmental parameters and FOS is nonlinear which makes it a multivariate and complex problem. To motivate the above-mentioned challenges, in this article, we propose a new fusion-based bag-of-neural network (FuBoNN) model for predicting FOS using a set of IoT devices in edge networks. Besides that, for increasing the prediction accuracy of FOS, multiple laboratory data related to FOS are fused over the monitoring parameters and prepare a rich data set. The newly created fused data set is fed into the population-based neural network (NN) and the best NN is selected in each iteration that transfers its knowledge to the population. The fused data set is categorized into four class labels to simulate the stability issue of residual soil and fed to the input of the proposed FuBoNN model, which provides a 0.0003% of error in predicting the multiple categories of the FOS. The proposed work is compared to the standard machine learning models that demonstrate the efficiency of the proposed model and produce 2.5% improved prediction accuracy over the existing ones.
- 11 July 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Internet of Things Journal
- Vol. 11  (3) , 3832-3839
Edge-Centric Intelligent Early Warning System for Residual Soil Stability Prediction in Slope
Different geospatial and geotechnical parameters change over time and can affect the residual soil stability on a slope. Thus, it is essential to analyze the stability of slopes continuously to identify the potential landslide sections. The stability of slopes is defined by the factor of safety (FOS). To track the immediate changes in soil stability, it is essential to monitor multiple environmental parameters using Internet of Things (IoT) devices for real-time decision making. Further, the relation between the environmental parameters and FOS is nonlinear which makes it a multivariate and complex problem. To motivate the above-mentioned challenges, in this article, we propose a new fusion-based bag-of-neural network (FuBoNN) model for predicting FOS using a set of IoT devices in edge networks. Besides that, for increasing the prediction accuracy of FOS, multiple laboratory data related to FOS are fused over the monitoring parameters and prepare a rich data set. The newly created fused data set is fed into the population-based neural network (NN) and the best NN is selected in each iteration that transfers its knowledge to the population. The fused data set is categorized into four class labels to simulate the stability issue of residual soil and fed to the input of the proposed FuBoNN model, which provides a 0.0003% of error in predicting the multiple categories of the FOS. The proposed work is compared to the standard machine learning models that demonstrate the efficiency of the proposed model and produce 2.5% improved prediction accuracy over the existing ones.
- 23 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30  (1) , 73-80
Nanorobot-Based Intelligent Symptoms Analysis and Recommendation Framework in Edge Networks
Nanorobots are microscopic robots that operate at the molecular and cellular level and can potentially revolutionize fields such as medicine, manufacturing, and environmental monitoring due to their precision. However, the challenge for researchers is to analyze the data and provide a constructive recommendation framework instantly, as most nanorobots demand on-time and near-edge processing. To tackle this challenge, this research presents a novel edge-enabled intelligent data analytics framework called Transfer Learning Population Neural Network (TLPNN) to predict glucose levels and associated symptoms from invasive and non-invasive wearable devices. The TLPNN is designed to be unbiased in predicting symptoms during the initial phase but later modified based on the best-performing neural networks during the learning phase. The effectiveness of the proposed method is validated using two publicly available glucose datasets with various performance metrics. The simulation results demonstrate the effectiveness of the proposed TLPNN method over existing ones.
- 23 May 2023
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 30  (1) , 73-80
Nanorobot-Based Intelligent Symptoms Analysis and Recommendation Framework in Edge Networks
Nanorobots are microscopic robots that operate at the molecular and cellular level and can potentially revolutionize fields such as medicine, manufacturing, and environmental monitoring due to their precision. However, the challenge for researchers is to analyze the data and provide a constructive recommendation framework instantly, as most nanorobots demand on-time and near-edge processing. To tackle this challenge, this research presents a novel edge-enabled intelligent data analytics framework called Transfer Learning Population Neural Network (TLPNN) to predict glucose levels and associated symptoms from invasive and non-invasive wearable devices. The TLPNN is designed to be unbiased in predicting symptoms during the initial phase but later modified based on the best-performing neural networks during the learning phase. The effectiveness of the proposed method is validated using two publicly available glucose datasets with various performance metrics. The simulation results demonstrate the effectiveness of the proposed TLPNN method over existing ones.
- 7 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 20  (4) , 2468-2479
Deep Transfer Learning for Communicable Disease Detection and Recommendation in Edge Networks
Considering the increasing number of communicable disease cases such as COVID-19 worldwide, the early detection of the disease can prevent and limit the outbreak. Besides that, the PCR test kits are not available in most parts of the world, and there is genuine concern about their performance and reliability. To overcome this, in this paper, we develop a novel edge-centric healthcare framework integrating with wearable sensors and advanced machine learning (ML) model for timely decisions with minimum delay. Through wearable sensors, a set of features have been collected that are further preprocessed for preparing a useful dataset. However, due to limited resource capacity, analyzing the features in resource-constrained edge devices is challenging. Motivated by this, we introduce an advanced ML technique for data analysis at edge networks, namely Deep Transfer Learning (DTL). DTL transfers the knowledge from the well-trained model to a new lightweight ML model that can support the resource-constraint nature of distributed edge devices. We consider a benchmark COVID-19 dataset for validation purposes, consisting of 11 features and 2 Million sensor data. The extensive simulation results demonstrate the efficiency of the proposed DTL technique over the existing ones and achieve 99.8% accuracy while diseases prediction.
- 7 June 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE/ACM Transactions on Computational Biology and Bioinformatics
- Vol. 20  (4) , 2468-2479
Deep Transfer Learning for Communicable Disease Detection and Recommendation in Edge Networks
Considering the increasing number of communicable disease cases such as COVID-19 worldwide, the early detection of the disease can prevent and limit the outbreak. Besides that, the PCR test kits are not available in most parts of the world, and there is genuine concern about their performance and reliability. To overcome this, in this paper, we develop a novel edge-centric healthcare framework integrating with wearable sensors and advanced machine learning (ML) model for timely decisions with minimum delay. Through wearable sensors, a set of features have been collected that are further preprocessed for preparing a useful dataset. However, due to limited resource capacity, analyzing the features in resource-constrained edge devices is challenging. Motivated by this, we introduce an advanced ML technique for data analysis at edge networks, namely Deep Transfer Learning (DTL). DTL transfers the knowledge from the well-trained model to a new lightweight ML model that can support the resource-constraint nature of distributed edge devices. We consider a benchmark COVID-19 dataset for validation purposes, consisting of 11 features and 2 Million sensor data. The extensive simulation results demonstrate the efficiency of the proposed DTL technique over the existing ones and achieve 99.8% accuracy while diseases prediction.
- 14 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23  (2) , 914-921
Analysis of Communicable Disease Symptoms Using Bag-of-Neural Network at Edge Networks
Considering the increasing growth of communicable diseases worldwide such as COVID-19, it is recommended to stay at home for patients with fewer chronic health problems. In recent times, the high chance of COVID-19 spread and the lack of an excellent remote monitoring system make the situation challenging for hospital administrators. Inspired by these challenges, in this paper, we develop a new edge-centric healthcare framework for remote health monitoring and disease prediction using Wearable Sensors (WSs) and advanced Machine Learning (ML) model, namely Bag-of-Neural Network (BoNN), respectively. The epidemic model collects the health symptoms of the patient using various a set of WSs and preprocesses the data in distributed edge devices for preparing a useful dataset. Finally, the proposed BoNN model is applied over the refined dataset for detecting COVID-19 disease at centralized cloud servers using a set of random neural networks. To demonstrate the efficiency of the proposed BoNN model over the standard ML models, the system is fine-tuned and trained over a synthetic COVID-19 dataset before being evaluated on a benchmark Brazil COVID-19 dataset using various performance metrics. The experimental results demonstrate that the proposed BoNN model achieves 99.8% accuracy while analyzing the Brazil dataset.
- 14 April 2022
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 23  (2) , 914-921
Analysis of Communicable Disease Symptoms Using Bag-of-Neural Network at Edge Networks
Considering the increasing growth of communicable diseases worldwide such as COVID-19, it is recommended to stay at home for patients with fewer chronic health problems. In recent times, the high chance of COVID-19 spread and the lack of an excellent remote monitoring system make the situation challenging for hospital administrators. Inspired by these challenges, in this paper, we develop a new edge-centric healthcare framework for remote health monitoring and disease prediction using Wearable Sensors (WSs) and advanced Machine Learning (ML) model, namely Bag-of-Neural Network (BoNN), respectively. The epidemic model collects the health symptoms of the patient using various a set of WSs and preprocesses the data in distributed edge devices for preparing a useful dataset. Finally, the proposed BoNN model is applied over the refined dataset for detecting COVID-19 disease at centralized cloud servers using a set of random neural networks. To demonstrate the efficiency of the proposed BoNN model over the standard ML models, the system is fine-tuned and trained over a synthetic COVID-19 dataset before being evaluated on a benchmark Brazil COVID-19 dataset using various performance metrics. The experimental results demonstrate that the proposed BoNN model achieves 99.8% accuracy while analyzing the Brazil dataset.
- 5 January 2022
- Published by Elsevier in Future Generation Computer Systems
- Vol. 130, 241-252
IBoNN: Intelligent Agent-based Internet of Medical Things framework for detecting brain response from Electroencephalography signal using Bag-of-Neural Network
- 5 January 2022
- Published by Elsevier in Future Generation Computer Systems
- Vol. 130, 241-252
IBoNN: Intelligent Agent-based Internet of Medical Things framework for detecting brain response from Electroencephalography signal using Bag-of-Neural Network
- 6 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26  (5) , 1969-1976
An Intrusion Detection Mechanism for Secured IoMT Framework Based on Swarm-Neural Network
The seamless integration of medical sensors and the Internet of Things (IoT) in smart healthcare has leveraged an intelligent Internet of Medical Things (IoMT) framework to detect the criticality of the patients. However, due to the limited storage capacity and computation power of the local IoT devices, patient's health data needs to transfer to remote computing devices for analysis, which can easily result in privacy leakage due to lack of control over the patient's health data and the vulnerability of the network for various types of attacks. Motivated by this, in this paper, an Empirical Intelligent Agent (EIA) based on a unique Swarm-Neural Network (Swarm-NN) method is proposed to identify attackers in the edge-centric IoMT framework. The major outcome of the proposed strategy is to identify the attacks during data transmission through a network and analyze the health data efficiently at the edge of the network with higher accuracy. The proposed Swarm-NN strategy is evaluated with a real-time secured dataset, namely the ToN-IoT dataset that collected Telemetry, Operating systems, and Network data for IoT application and compares the performance over the standard classification models using various performance metrics. The test results demonstrate that the proposed Swarm-NN strategy achieves 99.5% accuracy over the ToN-IoT dataset.
- 6 August 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Journal of Biomedical and Health Informatics
- Vol. 26  (5) , 1969-1976
An Intrusion Detection Mechanism for Secured IoMT Framework Based on Swarm-Neural Network
The seamless integration of medical sensors and the Internet of Things (IoT) in smart healthcare has leveraged an intelligent Internet of Medical Things (IoMT) framework to detect the criticality of the patients. However, due to the limited storage capacity and computation power of the local IoT devices, patient's health data needs to transfer to remote computing devices for analysis, which can easily result in privacy leakage due to lack of control over the patient's health data and the vulnerability of the network for various types of attacks. Motivated by this, in this paper, an Empirical Intelligent Agent (EIA) based on a unique Swarm-Neural Network (Swarm-NN) method is proposed to identify attackers in the edge-centric IoMT framework. The major outcome of the proposed strategy is to identify the attacks during data transmission through a network and analyze the health data efficiently at the edge of the network with higher accuracy. The proposed Swarm-NN strategy is evaluated with a real-time secured dataset, namely the ToN-IoT dataset that collected Telemetry, Operating systems, and Network data for IoT application and compares the performance over the standard classification models using various performance metrics. The test results demonstrate that the proposed Swarm-NN strategy achieves 99.5% accuracy over the ToN-IoT dataset.
- 12 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21  (18) , 20504-20511
Intelligent Health Monitoring System for Detection of Symptomatic/Asymptomatic COVID-19 Patient
The outbreak of the coronavirus is in its growing stage due to the lack of standard diagnosis for the patients. The situation of any populous area in a geographic location is very critical due to the quick virus spread from an infected individual to the rest. Currently, medical administration is at a crisis point due to the rapidly increasing number of cases and limited medical facilities. Thus, it is time to explore and design an intelligent model to monitor patient health symptoms remotely and predict and detect the abnormality of the patient’s health status in quick succession. Thus, the health status of a coronavirus-affected patient can be identified via a well-adjusted predictive model by analyzing the observed parameters of the health. In the proposed model, an Auto-regressive Integrated Moving Average is incorporated to design a predictive model to find the kth forecast of the observed health symptoms of a patient, and Akaike Information Criteria based selection is introduced to find the current best-fit prediction model. Further, the features are extracted from the forecast over each symptom to find a pattern of each patient, and the patterns are learned by the K-Means algorithm to detect the symptomatic and asymptomatic patient intelligently. To demonstrate the efficiency of the proposed model, we evaluate the model using a synthetic dataset, generated from the health symptoms of 400 patients and compare the performance of the model with the standard methods.
- 12 July 2021
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Sensors Journal
- Vol. 21  (18) , 20504-20511
Intelligent Health Monitoring System for Detection of Symptomatic/Asymptomatic COVID-19 Patient
The outbreak of the coronavirus is in its growing stage due to the lack of standard diagnosis for the patients. The situation of any populous area in a geographic location is very critical due to the quick virus spread from an infected individual to the rest. Currently, medical administration is at a crisis point due to the rapidly increasing number of cases and limited medical facilities. Thus, it is time to explore and design an intelligent model to monitor patient health symptoms remotely and predict and detect the abnormality of the patient’s health status in quick succession. Thus, the health status of a coronavirus-affected patient can be identified via a well-adjusted predictive model by analyzing the observed parameters of the health. In the proposed model, an Auto-regressive Integrated Moving Average is incorporated to design a predictive model to find the kth forecast of the observed health symptoms of a patient, and Akaike Information Criteria based selection is introduced to find the current best-fit prediction model. Further, the features are extracted from the forecast over each symptom to find a pattern of each patient, and the patterns are learned by the K-Means algorithm to detect the symptomatic and asymptomatic patient intelligently. To demonstrate the efficiency of the proposed model, we evaluate the model using a synthetic dataset, generated from the health symptoms of 400 patients and compare the performance of the model with the standard methods.
- 20 April 2020
- Published by Walter de Gruyter GmbH
- p. 131-136
7 Conclusion
Rapid use of social media for communication and information sharing, use of world wide web as a huge information repository, advancement in data and image capturing techniques have drastically increased the volume and size of the data. Analyzing, processing and searching such a huge volume of data is a complex task. This also reduces the accuracy as well as diminishes performance. To overcome these problems dimension reduction techniques are used to reduce the size of data and features without the loss of valuable information. Dimension of features can be reduced by projecting the features to a low dimensional space or using feature selection or feature encoding techniques. These techniques can be linear or non-linear depending on the relationship between data in higher and lower dimensions. In this chapter, a detailed analysis has been performed on some of the non-linear dimensionality reduction techniques and their applications. With the growth of the internet and social media, music data is growing at an enormous rate. Music analytics has a wide canvas covering all aspects related to music. This chapter provides a glimpse of this large canvas with sample applications covered in detail. Machine learning has taken a central role in the progress of many domains including music analytics. This chapter will help the readers to understand various applications of machine learning in computational musicology. Music feature learning and musical pattern recognition give conceptual understanding and the challenges involved. Feature engineering algorithms for pitch detection or tempo estimation are covered in more detail with available popular feature extraction tools. Music classification and clustering examples explore the use of machine learning. Various applications ranging from the query by humming to music recommendations are provided for efficient music information retrieval. Future directions and challenges with deep learning as a new approach and incorporation of human cognition and perception as a challenge makes this domain a challenging research domain. Character recognition is a challenging area in Machine Learning, Pattern Recognition or Image Processing. The accuracy to recognize handwritten character by human is far better compared to machine recognition. To develop an interface which can differentiate characters written by human yet requires intensive research. Though number of researches have presented in this area, still research is going on to achieve human like accuracy. Both handwritten and printed character recognition are categorized into two types, online and offline. A good number of researches have done work in the area of optical character recognition in different languages but for the Odia language, development is negligible. Odia (formerly it was Oriya), one of the 22 scheduled language recognized by the constitution of India and it is the official language of the state of Odisha (Orissa), more than 40 million people speak Odia. Due to the roundish shape of Odia character, large number of modified and compound characters and similarity between different characters makes this language very hard to create a satisfactory classifier. In the present survey undertaken we have discussed what are challenges be for Odia language and the machine learning techniques used in the recognition of Odia character recognition. This chapter describes complete process of character recognition i. e. pre-processing, extraction and selection of feature set and character recognition elaborately with comparison analysis and the metrics used to evaluate machine learning algorithms. Recommendation systems have been the integral part of web and mobile applications in the domains of e commerce, e learning, e health, e governance, social networking and search engines. The problem of spending more time in getting the required relevant information from the many options available, also called as the information overload problem is addressed by the recommendation systems. The context based recommendation systems are the types of recommendation systems which use the context information to provide the recommended items. The context is the data about the application or the surroundings or the purpose with which the user is interacting with the system which can be like time, location, type of product, user’s purpose or any situation describing the interaction. In this work the architecture of the context based recommendation system is proposed with the pre filtering method with context rules. The class and object based model of context with rules and recommendation system is proposed which can be converted into a relational model for data storage for the recommendation system. One of the actions like rating is used to predict the preference of items for the current user. The analysis of the system is carried out with the Het Rec 2011 Movielens data set. The accuracy measure MAE (Mean Absolute Error) is analysed in the proposed work and the relevance is measured in terms of precision, recall and F1 measure. The experimental result shows the influence of context on action and improvement in quality of recommendation with the proposed method. In some underdeveloped and developing countries, the identification of crop diseases depends on the farmer’s field experience and may lead to a degradation in the quality of production. The production quality can be improved, if the diseases detected in an earlier stage and machine-learning techniques are applied for detection of the crop diseases. The implementation of the decision support system is also an important part because the farmer needs to know proper information in a real-time manner and hence proper action can be taken in an earlier stage. Several advanced techniques are proposed for early detection of the crop diseases and it is inspired to survey on the techniques of machine learning based decision support system, address the issues...
- 20 April 2020
- Published by Walter de Gruyter GmbH
- p. 131-136
7 Conclusion
Rapid use of social media for communication and information sharing, use of world wide web as a huge information repository, advancement in data and image capturing techniques have drastically increased the volume and size of the data. Analyzing, processing and searching such a huge volume of data is a complex task. This also reduces the accuracy as well as diminishes performance. To overcome these problems dimension reduction techniques are used to reduce the size of data and features without the loss of valuable information. Dimension of features can be reduced by projecting the features to a low dimensional space or using feature selection or feature encoding techniques. These techniques can be linear or non-linear depending on the relationship between data in higher and lower dimensions. In this chapter, a detailed analysis has been performed on some of the non-linear dimensionality reduction techniques and their applications. With the growth of the internet and social media, music data is growing at an enormous rate. Music analytics has a wide canvas covering all aspects related to music. This chapter provides a glimpse of this large canvas with sample applications covered in detail. Machine learning has taken a central role in the progress of many domains including music analytics. This chapter will help the readers to understand various applications of machine learning in computational musicology. Music feature learning and musical pattern recognition give conceptual understanding and the challenges involved. Feature engineering algorithms for pitch detection or tempo estimation are covered in more detail with available popular feature extraction tools. Music classification and clustering examples explore the use of machine learning. Various applications ranging from the query by humming to music recommendations are provided for efficient music information retrieval. Future directions and challenges with deep learning as a new approach and incorporation of human cognition and perception as a challenge makes this domain a challenging research domain. Character recognition is a challenging area in Machine Learning, Pattern Recognition or Image Processing. The accuracy to recognize handwritten character by human is far better compared to machine recognition. To develop an interface which can differentiate characters written by human yet requires intensive research. Though number of researches have presented in this area, still research is going on to achieve human like accuracy. Both handwritten and printed character recognition are categorized into two types, online and offline. A good number of researches have done work in the area of optical character recognition in different languages but for the Odia language, development is negligible. Odia (formerly it was Oriya), one of the 22 scheduled language recognized by the constitution of India and it is the official language of the state of Odisha (Orissa), more than 40 million people speak Odia. Due to the roundish shape of Odia character, large number of modified and compound characters and similarity between different characters makes this language very hard to create a satisfactory classifier. In the present survey undertaken we have discussed what are challenges be for Odia language and the machine learning techniques used in the recognition of Odia character recognition. This chapter describes complete process of character recognition i. e. pre-processing, extraction and selection of feature set and character recognition elaborately with comparison analysis and the metrics used to evaluate machine learning algorithms. Recommendation systems have been the integral part of web and mobile applications in the domains of e commerce, e learning, e health, e governance, social networking and search engines. The problem of spending more time in getting the required relevant information from the many options available, also called as the information overload problem is addressed by the recommendation systems. The context based recommendation systems are the types of recommendation systems which use the context information to provide the recommended items. The context is the data about the application or the surroundings or the purpose with which the user is interacting with the system which can be like time, location, type of product, user’s purpose or any situation describing the interaction. In this work the architecture of the context based recommendation system is proposed with the pre filtering method with context rules. The class and object based model of context with rules and recommendation system is proposed which can be converted into a relational model for data storage for the recommendation system. One of the actions like rating is used to predict the preference of items for the current user. The analysis of the system is carried out with the Het Rec 2011 Movielens data set. The accuracy measure MAE (Mean Absolute Error) is analysed in the proposed work and the relevance is measured in terms of precision, recall and F1 measure. The experimental result shows the influence of context on action and improvement in quality of recommendation with the proposed method. In some underdeveloped and developing countries, the identification of crop diseases depends on the farmer’s field experience and may lead to a degradation in the quality of production. The production quality can be improved, if the diseases detected in an earlier stage and machine-learning techniques are applied for detection of the crop diseases. The implementation of the decision support system is also an important part because the farmer needs to know proper information in a real-time manner and hence proper action can be taken in an earlier stage. Several advanced techniques are proposed for early detection of the crop diseases and it is inspired to survey on the techniques of machine learning based decision support system, address the issues...
- 1 February 2019
- Published by Elsevier in Journal of Network and Computer Applications
- Vol. 128, 64-77
Meta heuristic-based task deployment mechanism for load balancing in IaaS cloud
- 1 February 2019
- Published by Elsevier in Journal of Network and Computer Applications
- Vol. 128, 64-77
Meta heuristic-based task deployment mechanism for load balancing in IaaS cloud
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 12-17
Big data architecture with mobile cloud in CDroid operating system for storing huge data
We are stepping frontward for an epoch of zeta bytes from Giga/Tera/Peta/Exa bytes in this era of computer science. The data storage in clouds is not the only preference as big data technology is obtainable for processing of both structured and unstructured data. Today a colossal sum of data is engendered by mobile phones (Smartphone) of both the composition types. For the sake of faster processing and elegant data utilization for gigantic quantity of data CDroid operating systems can be implemented with big data. Big data architecture is realized with mobile cloud for paramount deployment of wherewithal. The faster execution can be ended feasible for the make use of a new data centric architecture of MapReduce technology where as HDFS (Hadoop Distributed File System) also plays a big accountability in using data with dissimilar structures. As time advances the degree of data and information generated from smartphone augments and faster execution is call for the same. As per our research and development the only resolution for this mammoth amount of data is to put into practice Big data with CDroid scheme for best use of it. We believe this effort will budge a step ahead on the road to healthier civilization in close proximity to expectations.
- 1 December 2016
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 12-17
Big data architecture with mobile cloud in CDroid operating system for storing huge data
We are stepping frontward for an epoch of zeta bytes from Giga/Tera/Peta/Exa bytes in this era of computer science. The data storage in clouds is not the only preference as big data technology is obtainable for processing of both structured and unstructured data. Today a colossal sum of data is engendered by mobile phones (Smartphone) of both the composition types. For the sake of faster processing and elegant data utilization for gigantic quantity of data CDroid operating systems can be implemented with big data. Big data architecture is realized with mobile cloud for paramount deployment of wherewithal. The faster execution can be ended feasible for the make use of a new data centric architecture of MapReduce technology where as HDFS (Hadoop Distributed File System) also plays a big accountability in using data with dissimilar structures. As time advances the degree of data and information generated from smartphone augments and faster execution is call for the same. As per our research and development the only resolution for this mammoth amount of data is to put into practice Big data with CDroid scheme for best use of it. We believe this effort will budge a step ahead on the road to healthier civilization in close proximity to expectations.