Figure 2 - uploaded by Nilanjan Dey
Content may be subject to copyright.
![Overview architecture of big data computing [55]](profile/Nilanjan-Dey-2/publication/310461857/figure/fig2/AS:480003684081667@1491453204440/Overview-architecture-of-big-data-computing-55.png)
![Figure 1: Various datasets growth from 2000 to 2012 [16]](profile/Nilanjan-Dey-2/publication/310461857/figure/fig1/AS:480003684081666@1491453204414/Various-datasets-growth-from-2000-to-2012-16_Q320.jpg)
![Figure 2: Overview architecture of big data computing [55]](profile/Nilanjan-Dey-2/publication/310461857/figure/fig2/AS:480003684081667@1491453204440/Overview-architecture-of-big-data-computing-55_Q320.jpg)
![Figure 3: The overall mobile health technologies process [70]](profile/Nilanjan-Dey-2/publication/310461857/figure/fig3/AS:669337304178705@1536593857655/The-overall-mobile-health-technologies-process-70_Q320.jpg)
Context in source publication
Context 1
... to big data computing, service-oriented technologies such as cloud computing is also capable of storing data, analyzing and manipulating large size of data but sometimes it becomes challenging working with cloud computing, that time big data computing is must. The overall architecture of big data was demonstrated in Figure 2. Figure 2 illustrated the big data computing along with closer innovation or discussion on architecture, technologies, tools, mobile technologies, health technologies and many more paradigms working behind big data computing. ...
Similar publications
Citations
... Discovery of knowledge in records is regarded as the planned, tentative study and modelling of large data repositories [4]. KDD is an organized process of identifying valid, useful and understandable patterns from large and complex data sets. ...
... Smartphone sensors have been used effectively in intelligent transport systems to alert aggressive driver behaviour and hazardous road conditions for reducing road accidents (Ali, Atia, & Mostafa, 2017). Data mining for diagnosing and decision-making on widespread diseases through machine learning have enhanced disease information processing greatly (Kamal, Dey, & Ashour, 2017). ...
Industry 4.0 can be considered the 21st century's industrial revolution and will soon be the new form of manufacturing delight. The definitive customer would experience manufacturing requests determined by artificial intelligence, machine learning, and automated technologies linked with data science support for gauging customer necessities. Phenomenally, Industry 4.0 is rapidly changing the firm's management, organizational systems, and competencies as well as making its environment much more explored, even if more complexed than in the past. This new industrial revolution would possess systems with transformative technologies for managing interconnected systems between its physical assets and computational capabilities. Such enterprises would require a skilled workforce to improve and operate advanced manufacturing tools and systems; and investigate the machine data, clients, and global capitals that will result in the following: an escalating need for trained employees proficient in cross-functional capacities and competencies to cope with new processes and IT systems.
... However, false positive rate was not minimized. Multiple aspects of large scale knowledge mining was covered in [26] for medical and diseases examination. A new image-based features selection method was planned in [27] to categorize the lung computed tomography images with a higher accuracy. ...
Accurate diagnosis of Lung Cancer Disease (LCD) is an essential process to provide timely treatment to the lung cancer patients. Artificial Neural Networks (ANN) is a recently proposed Machine Learning (ML) algorithm which is used on both large-scale and small-size datasets. In this paper, an ensemble of Weight Optimized Neural Network with Maximum Likelihood Boosting (WONN-MLB) for LCD in big data is analyzed. The proposed method is split into two stages, feature selection and ensemble classification. In the first stage, the essential attributes are selected with an integrated Newton Raphsons Maximum Likelihood and Minimum Redundancy (MLMR) preprocessing model for minimizing the classification time. In the second stage, Boosted Weighted Optimized Neural Network Ensemble Classification algorithm is applied to classify the patient with selected attributes which results to improve the cancer disease diagnosis accuracy and to minimize the false positive rate. Experimental results demonstrate that the proposed approach achieves better false positive rate, accuracy of prediction, and reduced delay in comparison to the conventional techniques.
... The data responds to relying upon the medical information and constant recording of the patients under various conditions. To help these sorts of frameworks, few methods like data mining for presuming present medical condition of a patient, applying algorithm to group data have been proposed by various research groups [66,67]. Another approach for simple data mining is introduced as object oriented database system for server and customer [68]. ...
... Before the deep learning phase, it is recommended to compress the data, for improving the rapidity of the learning, but also for allowing an easy visualization by the people manipulating the raw information and by the data provider, that is the patient. The compression can be obtained by i) reducing the dimensionality of the observables (e.g., using Principal Component Analysis or Independent Component Analysis), ii) discretizing (even binarizing) the data [31][32][33] (e.g., using fuzzy or Fourier transform, which retain respectively only Boolean or few parameters values) before the steps of classification [34][35][36] or data mining [35][36][37]. ...
... Before the deep learning phase, it is recommended to compress the data, for improving the rapidity of the learning, but also for allowing an easy visualization by the people manipulating the raw information and by the data provider, that is the patient. The compression can be obtained by i) reducing the dimensionality of the observables (e.g., using Principal Component Analysis or Independent Component Analysis), ii) discretizing (even binarizing) the data [31][32][33] (e.g., using fuzzy or Fourier transform, which retain respectively only Boolean or few parameters values) before the steps of classification [34][35][36] or data mining [35][36][37]. ...
This chapter aims to show that big data techniques can serve for dealing with the information coming from medical signal devices such as bio-arrays, electro-physiologic recorders, mass spectrometers and wireless sensors in e-health applications, in which data fusion is needed for the personalization of Internet services allowing chronic patients, such as patients suffering cardio-respiratory diseases, to be monitored and educated in order to maintain a comfortable lifestyle at home or at their place of life. Therefore, after describing the main tools available in the big data approach for analyzing and interpreting data, several examples of medical signal devices are presented, such as physiologic recorders and actimetric sensors used to monitor a person at home. The information provided by the pathologic profiles detected and clustered thanks to big data algorithms, is exploited to calibrate the surveillance at home, personalize alarms and give adapted preventive and therapeutic education.
... Millions and billions of data are created everyday by people be it on any social networking sites, finance, medicine, sensors, mobile applications and so on. due to the massive amount of the biological information, big data in biological processing become a common phenomenon in current industry and laboratories (Kamal et al, 2017). To manage, analyze and process all these data new processing methodologies, techniques and tools have to be used (Shukla et al., 2016). ...
During the last two decades, a number of new nations emerged and played their intense role in changing human lifestyle. The growing demand for smart city and big data stimulates innovation, and the development of new smart applications is becoming important. Internet of things comprises billions of devices, people, and services, and entitles each to connect through sensor devices. The economic development of a city leads to better life quality and improved citizen services. Thus, this chapter discusses the background of big data, IoT, and smart city. It also discusses the collaborative approach of all the above. The various related work and future research direction for implementing smart city with the concept of big data and IoT would be addressed in this chapter.
... Several modified statistical classification methods, combined or not with health-related indices such as logistic regression [14], classification and regression trees [15], neural networks [16] and machine-learning techniques such as neural networks or support vector machines (SVMs) [17] aim to increase the predictive accuracy of medical data in classifying individuals as healthy or not. Data mining methods are applied in a variety of medical sets for classifying healthy and unhealthy individuals in order to get accurate diagnoses [18], for measuring morbidly and mortality of specific diseases [19] and for exploring medical data deeply aiming to find hidden relations between variables/features [20]. ...
... But, extra powerful strategies, algorithms, software and incorporated gear are required for the organic processing. System studying is one of the key techniques for managing organic datasets [35]. 5 represents data after preprocessing by converting string format into the nominal format, convert nominal data into numeric ones. ...
In the midst of this large gap in the size of the data and the diversity of its sources of production, many problems have emerged, especially in the Biomedical data. Big Data is characterized by their large size, whereas Biomedical data are characterized by missing, ambiguous, and inconsistent data. It is necessary to remove mislabelled instances by learning algorithm for finding accurate data and increasing classification accuracy.
In this paper, we proposed a framework for removing misclassified instances to improve classification performance of Biomedical Big Data. Our framework has four main stages, which are preparation, feature selection, instance reduction, and classification stages. In the instance reduction stage, we try to reduce and remove instances that cause misclassification. We use Fuzzy-Rough Nearest Neighbour to remove mislabelled instances. Experimental results proved the great effectiveness of the proposed technique on Biomedical Big Data to enhance classification accuracy. A classification tree is the most influence classification techniques by applying our model. Our model helps to raise its accuracy to 89.24%.
... Big data investigation system is implemented in a method that it can generate valuable data from a unstructured raw data. Big data techniques are now apply the characteristics in medical science, health informatics, computer science and lots of fields [6]. ...
The evolution of the IoT representatives a new age of technology and administrations that aim to contribute in this new area will have to modify the method they do things to adapt with new data forms and data sources. And these modifications are just the start. As the IoT develops and businesses expand with IoT, they will have many more faces to resolve. The raw IoT data is collected from different sensors, which leads to many problems, such as noisy, heterogeneous, and massive data. Our proposed system aims to solve these problems that face IoT data. The architecture of the proposed system involves of two major stages: data preprocessing and data processing phases. In the preprocessing phase, we used KNN to clean noisy data and replace missing data, which can use the most probable value. The SVD is used to reduce data to save time. The mutual information is implemented to detect the relationship between the data and detect semantic clustering to achieve high accuracy and speed the running time. We compared between many different techniques which are KM, Optics, EM, DBSCAN, and the proposed techniques FCM-DBSCAN and KMeans-DBSCAN. We found that FCM-DBSCAN with its varied approaches for data reduction had the high accuracy value. FCM-DBSCAN with SVD have the highest value of accuracy and retrieve data in a small time. KMeans-DBSCAN has a small time to retrieve data but has less accuracy than FCM-DBSCAN. The proposed FCM-DBSCAN technique is applied to both MapReduce and Spark. The proposed technique consumes smaller time in Spark than in MapReduce.
... The data responds contrastingly relying upon the medicinal information and constant recording of the patients in various conditions. To help these kinds of frameworks, a few methods like data mining (for the presumed present medical condition of a patient), or applying a group algorithm to both current and historic data have been proposed [65,66]. Another approach for simple data mining is introduced as object oriented database system for server and customer [67]. ...
