scholarly journals MapReduce Based Parallel Neural Networks in Enabling Large Scale Machine Learning

2015 ◽  
Vol 2015 ◽  
pp. 1-13 ◽  
Author(s):  
Yang Liu ◽  
Jie Yang ◽  
Yuan Huang ◽  
Lixiong Xu ◽  
Siguang Li ◽  
...  
Keyword(s):  
Neural Networks ◽  
Big Data ◽  
Large Scale ◽  
Training Data ◽  
Computer Cluster ◽  
Data Intensive ◽  
Big Data Applications ◽  
The Neural Network ◽  
Computation Process ◽  
Data Intensive Applications

Artificial neural networks (ANNs) have been widely used in pattern recognition and classification applications. However, ANNs are notably slow in computation especially when the size of data is large. Nowadays, big data has received a momentum from both industry and academia. To fulfill the potentials of ANNs for big data applications, the computation process must be speeded up. For this purpose, this paper parallelizes neural networks based on MapReduce, which has become a major computing model to facilitate data intensive applications. Three data intensive scenarios are considered in the parallelization process in terms of the volume of classification data, the size of the training data, and the number of neurons in the neural network. The performance of the parallelized neural networks is evaluated in an experimental MapReduce computer cluster from the aspects of accuracy in classification and efficiency in computation.

scholarly journals Gravity Control-Based Data Augmentation Technique for Improving VR User Activity Recognition

Symmetry ◽  
2021 ◽  
Vol 13 (5) ◽  
pp. 845
Author(s):  
Dongheun Han ◽  
Chulwoo Lee ◽  
Hyeongyeop Kang
Keyword(s):  
Activity Recognition ◽  
Large Scale ◽  
Data Augmentation ◽  
Training Data ◽  
Measurement Unit ◽  
Gravitational Acceleration ◽  
The Neural Network ◽  
Typical Data ◽  
Robust Recognition ◽  
Gravity Acceleration

The neural-network-based human activity recognition (HAR) technique is being increasingly used for activity recognition in virtual reality (VR) users. The major issue of a such technique is the collection large-scale training datasets which are key for deriving a robust recognition model. However, collecting large-scale data is a costly and time-consuming process. Furthermore, increasing the number of activities to be classified will require a much larger number of training datasets. Since training the model with a sparse dataset can only provide limited features to recognition models, it can cause problems such as overfitting and suboptimal results. In this paper, we present a data augmentation technique named gravity control-based augmentation (GCDA) to alleviate the sparse data problem by generating new training data based on the existing data. The benefits of the symmetrical structure of the data are that it increased the number of data while preserving the properties of the data. The core concept of GCDA is two-fold: (1) decomposing the acceleration data obtained from the inertial measurement unit (IMU) into zero-gravity acceleration and gravitational acceleration, and augmenting them separately, and (2) exploiting gravity as a directional feature and controlling it to augment training datasets. Through the comparative evaluations, we validated that the application of GCDA to training datasets showed a larger improvement in classification accuracy (96.39%) compared to the typical data augmentation methods (92.29%) applied and those that did not apply the augmentation method (85.21%).

Large-Scale Sensor Network Analysis

2013 ◽  
pp. 314-347 ◽  
Author(s):  
Joaquin Vanschoren ◽  
Ugo Vespier ◽  
Shengfa Miao ◽  
Marvin Meeng ◽  
Ricardo Cachucho ◽  
...  
Keyword(s):  
Big Data ◽  
Data Analysis ◽  
Large Scale ◽  
Vital Signs ◽  
Sensor Data ◽  
Atmospheric Conditions ◽  
Big Data Applications ◽  
The World ◽  
Sheer Size ◽  
Effective Use

Sensors are increasingly being used to monitor the world around us. They measure movements of structures such as bridges, windmills, and plane wings, human’s vital signs, atmospheric conditions, and fluctuations in power and water networks. In many cases, this results in large networks with different types of sensors, generating impressive amounts of data. As the volume and complexity of data increases, their effective use becomes more challenging, and novel solutions are needed both on a technical as well as a scientific level. Founded on several real-world applications, this chapter discusses the challenges involved in large-scale sensor data analysis and describes practical solutions to address them. Due to the sheer size of the data and the large amount of computation involved, these are clearly “Big Data” applications.

NoSQL Databases

2014 ◽  
pp. 186-215 ◽  
Author(s):  
Ganesh Chandra Deka
Keyword(s):  
Cloud Computing ◽  
Big Data ◽  
Data Processing ◽  
Open Source ◽  
Data Storage ◽  
Big Data Processing ◽  
Nosql Databases ◽  
Data Intensive ◽  
Huge Data ◽  
Data Intensive Applications

NoSQL databases are designed to meet the huge data storage requirements of cloud computing and big data processing. NoSQL databases have lots of advanced features in addition to the conventional RDBMS features. Hence, the “NoSQL” databases are popularly known as “Not only SQL” databases. A variety of NoSQL databases having different features to deal with exponentially growing data-intensive applications are available with open source and proprietary option. This chapter discusses some of the popular NoSQL databases and their features on the light of CAP theorem.

Affordances of Data Science in Agriculture, Manufacturing, and Education

Web Services ◽  
2019 ◽  
pp. 953-978
Author(s):  
Krishnan Umachandran ◽  
Debra Sharon Ferdinand-James
Keyword(s):  
Big Data ◽  
Large Scale ◽  
Data Science ◽  
Data Generation ◽  
Large Scale Data ◽  
Big Data Applications ◽  
Effective Decision ◽  
Effective Decision Making ◽  
Text Images ◽  
Scale Data

Continued technological advancements of the 21st Century afford massive data generation in sectors of our economy to include the domains of agriculture, manufacturing, and education. However, harnessing such large-scale data, using modern technologies for effective decision-making appears to be an evolving science that requires knowledge of Big Data management and analytics. Big data in agriculture, manufacturing, and education are varied such as voluminous text, images, and graphs. Applying Big data science techniques (e.g., functional algorithms) for extracting intelligence data affords decision markers quick response to productivity, market resilience, and student enrollment challenges in today's unpredictable markets. This chapter serves to employ data science for potential solutions to Big Data applications in the sectors of agriculture, manufacturing and education to a lesser extent, using modern technological tools such as Hadoop, Hive, Sqoop, and MongoDB.

Affordances of Data Science in Agriculture, Manufacturing, and Education

2017 ◽  
pp. 14-40 ◽  
Author(s):  
Krishnan Umachandran ◽  
Debra Sharon Ferdinand-James
Keyword(s):  
Big Data ◽  
Large Scale ◽  
Data Science ◽  
Data Generation ◽  
Large Scale Data ◽  
Big Data Applications ◽  
Effective Decision ◽  
Effective Decision Making ◽  
Text Images ◽  
Scale Data

Continued technological advancements of the 21st Century afford massive data generation in sectors of our economy to include the domains of agriculture, manufacturing, and education. However, harnessing such large-scale data, using modern technologies for effective decision-making appears to be an evolving science that requires knowledge of Big Data management and analytics. Big data in agriculture, manufacturing, and education are varied such as voluminous text, images, and graphs. Applying Big data science techniques (e.g., functional algorithms) for extracting intelligence data affords decision markers quick response to productivity, market resilience, and student enrollment challenges in today's unpredictable markets. This chapter serves to employ data science for potential solutions to Big Data applications in the sectors of agriculture, manufacturing and education to a lesser extent, using modern technological tools such as Hadoop, Hive, Sqoop, and MongoDB.

scholarly journals Automatic Gully Detection: Neural Networks and Computer Vision

2020 ◽  
Vol 12 (11) ◽  
pp. 1743
Author(s):  
Artur M. Gafurov ◽  
Oleg P. Yermolayev
Keyword(s):  
Neural Network ◽  
Neural Networks ◽  
Convolutional Neural Networks ◽  
Large Scale ◽  
Satellite Images ◽  
Gully Erosion ◽  
Training Data ◽  
Russian Plain ◽  
Data Set ◽  
High Resolution Satellite Images

Transition from manual (visual) interpretation to fully automated gully detection is an important task for quantitative assessment of modern gully erosion, especially when it comes to large mapping areas. Existing approaches to semi-automated gully detection are based on either object-oriented selection based on multispectral images or gully selection based on a probabilistic model obtained using digital elevation models (DEMs). These approaches cannot be used for the assessment of gully erosion on the territory of the European part of Russia most affected by gully erosion due to the lack of national large-scale DEM and limited resolution of open source multispectral satellite images. An approach based on the use of convolutional neural networks for automated gully detection on the RGB-synthesis of ultra-high resolution satellite images publicly available for the test region of the east of the Russian Plain with intensive basin erosion has been proposed and developed. The Keras library and U-Net architecture of convolutional neural networks were used for training. Preliminary results of application of the trained gully erosion convolutional neural network (GECNN) allow asserting that the algorithm performs well in detecting active gullies, well differentiates gullies from other linear forms of slope erosion — rills and balkas, but so far has errors in detecting complex gully systems. Also, GECNN does not identify a gully in 10% of cases and in another 10% of cases it identifies not a gully. To solve these problems, it is necessary to additionally train the neural network on the enlarged training data set.

scholarly journals Multiactivation Pooling Method in Convolutional Neural Networks for Image Recognition

2018 ◽  
Vol 2018 ◽  
pp. 1-15 ◽  
Author(s):  
Qi Zhao ◽  
Shuchang Lyu ◽  
Boxue Zhang ◽  
Wenquan Feng
Keyword(s):  
Neural Networks ◽  
Image Processing ◽  
Big Data ◽  
Convolutional Neural Networks ◽  
Image Recognition ◽  
Large Scale ◽  
Fog Computing ◽  
Feature Extractor ◽  
Benchmark Datasets ◽  
Classification Tasks

Convolutional neural networks (CNNs) are becoming more and more popular today. CNNs now have become a popular feature extractor applying to image processing, big data processing, fog computing, etc. CNNs usually consist of several basic units like convolutional unit, pooling unit, activation unit, and so on. In CNNs, conventional pooling methods refer to 2×2 max-pooling and average-pooling, which are applied after the convolutional or ReLU layers. In this paper, we propose a Multiactivation Pooling (MAP) Method to make the CNNs more accurate on classification tasks without increasing depth and trainable parameters. We add more convolutional layers before one pooling layer and expand the pooling region to 4×4, 8×8, 16×16, and even larger. When doing large-scale subsampling, we pick top-k activation, sum up them, and constrain them by a hyperparameter σ. We pick VGG, ALL-CNN, and DenseNets as our baseline models and evaluate our proposed MAP method on benchmark datasets: CIFAR-10, CIFAR-100, SVHN, and ImageNet. The classification results are competitive.

scholarly journals Significance of Hierarchical and Markov Clustering in Grouping Aware Data Placement for Data Intensive Applications Having Interest Locality

2018 ◽  
Vol 19 (3) ◽  
pp. 245-258
Author(s):  
Vengadeswaran Shanmugasundaram ◽  
Balasundaram Sadhu Ramakrishnan
Keyword(s):  
Big Data ◽  
Data Placement ◽  
Query Execution ◽  
Access Pattern ◽  
Clustering Techniques ◽  
Data Intensive ◽  
Markov Clustering ◽  
Default Data ◽  
Data Intensive Applications ◽  
Grouping Behavior

In this data era, massive volumes of data are being generated every second in variety of domains such as Geoscience, Social Web, Finance, e-Commerce, Health Care, Climate modelling, Physics, Astronomy, Government sectors etc. Hadoop has been well-recognized as de factobig data processing platform that have been extensively adopted, and is currently widely used, in many application domains processing Big Data. Even though it is considered as an efficient solution for such complex query processing, it has its own limitation when the data to be processed exhibit interest locality. The data required for any query execution follows grouping behavior wherein only a part of the Big-Data is accessed frequently. During such scenarion, the time taken to execute a queryand return results, increases exponentially as the amount of data increases leading to much waiting time for the user. Since Hadoop default data placement strategy (HDDPS) does not consider such grouping behavior, it does not perform efficiently resulting in lacunas such as decreased local map task execution, increased query execution time etc. Hence proposed an Optimal Data Placement Strategy (ODPS) based on grouping semantics. In this paper we experiment the significance oftwo most promising clustering techniques viz. Hierarchical Agglomerative Clustering (HAC) and Markov Clustering (MCL) in grouping aware data placement for data intensive applications having interest locality. Initially user access pattern is identified by dynamically analyzing history log.Then both clustering techniques (HAC & MCL) are separately applied over the access pattern to obtain independent clusters. These clusters are interpreted and validated to extract the Optimal Data Groupings (ODG). Finally proposed strategy reorganizes the default data layouts in HDFSbased on ODG to achieve maximum parallel execution per group subjective to Load Balancer and Rack Awareness. Our proposed strategy is tested in 10 node cluster placed in a multi rack with Hadoop installed in every node deployed in cloud platform. Proposed strategy reduces the query execution time, significantly improves the data locality and has proved to be more efficient for massive datasets processing in heterogeneous distributed environment. Also MCL shows a marginal improved performance over HAC for queries exhibiting interest localities.

Sign in / Sign up

Export Citation Format

Share Document