Improvement of satellite image classification: Approach based on Hadoop/MapReduce

Chebbi, Imen; Boulila, ‪Wadii; Farah, Imed Riadh

doi:10.1109/atsip.2016.7523046

Cited by 21 publications

(14 citation statements)

References 4 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Hadoopframework andMapReduce paradigm are the supported technologies. Map Reduce [13] is dominant technique among the other techniques for managing huge data in the cloud environment; it provides an environment for large datasets which are stored in the cluster to get processed. The foundation of cloud framework can act as a suitable environment for executing big data analysis by contending the required data storage [14].…”

Section: Introductionmentioning

confidence: 99%

“…Thepretension of Hadoop was the space utilization. [13] Hadoop is a frameworkthat is open source and is developed by using JAVA platform. Hadoop utilizes a DFS to store and contend the bulky data by providing the faulttolerance environment.…”

Section: Introductionmentioning

confidence: 99%

“…MapReduce is consociated with dealing bulky data sets on a cluster by using different algorithms. The analyzing process of sizeable datasets that get accumulate in HDFS is braced by technologies like Hive using hql.Constituents of HDFS Are: NameNode: Name node is the principal node that encloses apprehensions about file system of Hadoop [13]. It is the sovereign node that perpetuates, instructs and governs the blocks that reside on data nodes.…”

Section: Introductionmentioning

confidence: 99%

“…MapReduce: It is a programming standard utilized for refining, processing and engendering enormous datasets [13]. The datasets to be inputted are gathered in a cluster of segregations in a DFSredistributed on each lump in the cluster.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations

Analysis and Visualization of Data Assimilating Hive and COGNOS Insight 10.2.2

Virk¹,

Chauhan²,

Mittal³

2018

IJET

View full text Add to dashboard Cite

Data analysis is the most grueling tasks in the coinciding world. The size of data is increasing at a very high rate because of the procreation of peripatetic gadgets and sensors attached. To make that data readable is another challenging task. Effectual visualization provides users with better analysis capabilities and helps in deriving evidence about data. Many techniques and tools have been invented to deal with such problems but to make these tools amendable is the main mystification. It is the big data that originated as a technology which is proficient in assembling and transforming the colossal and divergent figures of data, providing organizations with meaningful insights for derivingimprovedresults. Big data is accustomed to delineate technologies and techniques which are used to store, manage, distribute and analyze huge data sheets. The existent of administrating this research is to make the data readable in a more suitable form with less comprehend. Mainly the research emphasizes on the fabrication of using COGNOS insight 10.2.2 for visualizing data and implementing the analyzed results derived from the hive. The assimilation between tools has also been reformed in this research.

show abstract

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Analysis and Visualization of Data Assimilating Hive and COGNOS Insight 10.2.2

Virk¹,

Chauhan²,

Mittal³

2018

IJET

View full text Add to dashboard Cite

show abstract

“…These can be used for detecting objects like landmines [10], classifying [8] [9] & clustering areas, creating maps, discovering pollution areas, monitoring the climate change, and so forth. Classification, supervised or unsupervised, is the most used operation for analyzing remotely-sensed images [8]. The proposed system will segment satellite GeoTIFF files using K-means algorithm on Hadoop and HIPI.…”

Section: Introductionmentioning

confidence: 99%

Image Processing in Hadoop Distributed Environment

Shaheen¹,

Potdar²

Kalpa Publications in Computing

View full text Add to dashboard Cite

Satellite images are a growing resource of information and have many applications. In this research, the multispectral satellite images have been subjected to unsupervised classification based on K-Means clustering using Hadoop Framework, which is designed for big data processing, along with Hadoop Image Processing Interface (HIPI). We developed support for the GeoTIFF format, which is usually used for satellite images, and we will show that our methodology enhances the performance.

show abstract

Global outliers detection in wireless sensor networks: A novel approach integrating time‐series analysis, entropy, and random forest‐based classification.

et al. 2021

View full text Add to dashboard Cite

Wireless sensor networks (WSNs) have recently attracted greater attention worldwide due to their practicality in monitoring, communicating, and reporting specific physical phenomena. The data collected by WSNs is often inaccurate as a result of unavoidable environmental factors, which may include noise, signal weakness, or intrusion attacks depending on the specific situation. Sending high-noise data has negative effects not just on data accuracy and network reliability, but also regarding the decision-making processes in the base station.Anomaly detection, or outlier detection, is the process of detecting noisy data amidst the contexts thus described. The literature contains relatively few noise detection techniques in the context of WSNs, particularly for outlier-detection algorithms applying time series analysis, which considers the effective neighbors to ensure a global-collaborative detection. Hence, the research presented in this article is intended to design and implement a global outlier-detection approach, which allows us to find and select appropriate neighbors to ensure an adaptive collaborative detection based on time-series analysis and entropy techniques. The proposed approach applies a random forest algorithm for identifying the best results. To measure the effectiveness and efficiency of the proposed approach, a comprehensive and real scenario provided by the Intel Berkeley Research Laboratory has been simulated. Noisy data have been injected into the collected data randomly. The results obtained from the experiment then conducted experimentation demonstrate that our approach can detect anomalies with up to 99% accuracy.

show abstract

Improvement of satellite image classification: Approach based on Hadoop/MapReduce

Cited by 21 publications

References 4 publications

Analysis and Visualization of Data Assimilating Hive and COGNOS Insight 10.2.2

Analysis and Visualization of Data Assimilating Hive and COGNOS Insight 10.2.2

Image Processing in Hadoop Distributed Environment

Global outliers detection in wireless sensor networks: A novel approach integrating time‐series analysis, entropy, and random forest‐based classification.

Contact Info

Product

Resources

About