Learning-based text classifiers using the Mahalanobis distance for correlated datasets

Srivastava, Noopur; Rao, Shrisha

doi:10.1504/ijbdi.2016.073901

Cited by 10 publications

(5 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Using the labeled areas, a supervised classification algorithm like Mahalanobis distance was applied in ENVI software to produce a detailed land cover map for each date (Figure 10). Based on the correlations within a dataset as well as the distribution of the data, Mahalanobis distance algorithm determines the similarity between an unknown data element to a known dataset by using a covariance matrix [36]. Consequently, a GIS-based spatial analysis was conducted on pairs of these maps identifying areas of change or no change for the periods 1999-2009 and 2009-2019.…”

Section: Accuracy Assessmentmentioning

confidence: 99%

“…The total of identified information as reference data was finally compared with the change magnitude and direction outputs of CVA in confusion matrices to calculate the statistics of kappa index and overall accuracy ( Table 2). dataset as well as the distribution of the data, Mahalanobis distance algorithm determines the similarity between an unknown data element to a known dataset by using a covariance matrix [36]. Consequently, a GIS-based spatial analysis was conducted on pairs of these maps identifying areas of change or no change for the periods 1999-2009 and 2009-2019.…”

Section: Accuracy Assessmentmentioning

confidence: 99%

See 1 more Smart Citation

Exploring the Impact of Various Spectral Indices on Land Cover Change Detection Using Change Vector Analysis: A Case Study of Crete Island, Greece

2020

View full text Add to dashboard Cite

The main objective of this study was to explore the impact of various spectral indices on the performance of change vector analysis (CVA) for detecting the land cover changes on the island of Crete, Greece, between the last two decades (1999–2009 and 2009–2019). A set of such indices, namely, normalized difference vegetation index (NDVI), soil adjusted vegetation index (SAVI), albedo, bare soil index (BSI), tasseled cap greenness (TCG), and tasseled cap brightness (TCB), representing both the vegetation and soil conditions of the study area, were estimated on Landsat satellite images captured in 1999, 2009, and 2019. Change vector analysis was then applied for five different index combinations resulting to the relative change outputs. The evaluation of these outputs was performed towards detailed land cover maps produced by supervised classification of the aforementioned images. The results from the two examined periods revealed that the five index combinations provided promising performance results in terms of kappa index (with a range of 0.60–0.69) and overall accuracy (with a range of 0.86–0.96). Moreover, among the different combinations, the use of NDVI and albedo were found to provide superior results against the other combinations.

show abstract

Section: Accuracy Assessmentmentioning

confidence: 99%

Section: Accuracy Assessmentmentioning

confidence: 99%

Exploring the Impact of Various Spectral Indices on Land Cover Change Detection Using Change Vector Analysis: A Case Study of Crete Island, Greece

2020

View full text Add to dashboard Cite

show abstract

“…A random sample of 246 areas was then collected and labeled as specific land cover types by visual interpretation. Using this sample, a supervised classification algorithm like Mahalanobis distance (Srivastava & Rao, 2016) was performed to produce a detailed land cover map. C-factor values were assigned to the relative land cover types of the resultant map, according to Sujatha and Sridhar (2018).…”

Section: Soil Erosion Assessmentmentioning

confidence: 99%

Assessment of water-induced soil erosion as a threat to cultural heritage sites: the case of Chania prefecture, Crete Island, Greece

et al. 2021

View full text Add to dashboard Cite

Among the environmental threats, the intensification of natural hazards, such as soil erosion may threaten the integrity and value of cultural heritage sites. In this framework, the present study's main objective was to identify archaeological sites susceptible by soil erosion, taking the case study of Chania prefecture in Crete Island. Remotely sensed and other available geospatial datasets were analyzed in a GIS-based empirical model, namely Unit Stream Power Erosion and Deposition (USPED), to estimate the average annual soil loss and deposition rates due to waterinduced erosion in the study area. The resultant erosion map was then intersected with the locations and surrounding zones of the known archaeological sites for identifying the sites and the portions of their vicinity being at risk. The results revealed that Chania prefecture and its cultural heritage are significantly affected by both soil loss and deposition processes. Between the two processes, soil loss was found to be more intensive, influencing a larger part of the prefecture (especially to the west) as well as a higher amount of archaeological sites. The extreme and high soil loss classes were also detected to cover the most considerable portion of the sites' surrounding area. The identification of the archaeological sites being most exposed to soil erosion hazard can constitute a basis for cultural heritage managers in order to take preventive preservation measures and develop specific risk mitigation strategies.

show abstract

“…Working in this direction, Oliveira et al (2016) have developed an approach which compared four different artificial neural network techniques including deep learning network for forecasting the traffic. Similarly, Srivastava and Rao (2016) have proposed a technique for text categorisation using Mahalanobis distance for correlated dataset. To test it on a large dataset, they first reduce the dataset using principle component analysis (PCA) and then used k-nearest neighbours (kNN) for classification.…”

Section: Literature Surveymentioning

confidence: 99%

Detecting spam web pages using multilayer extreme learning machine

Roul

2018

IJBDI

View full text Add to dashboard Cite

Web spamming generally increases the ranking of some unimportant pages higher in the search results. Detecting and eliminating such spam pages are the need of the day, which mislead the search engine to obtain high-quality information. Aiming in this direction, this study focuses on two important aspects of machine learning. First, it proposes a new content-based spam detection technique which identifies nine important features that help to detect a page is either spam or non-spam. Each feature has an associated value which is calculated by parsing the documents and then performing the require techniques i.e. necessary steps to compute its score. These nine important features along with the class label (spam or non-spam) generate a feature vector for training the classifiers in order to detect the spam pages. Secondly, it highlights the importance of deep learning using multilayer extreme learning machine in the field of spam page detection. For experimental work, two benchmark datasets (WEBSPAM-UK2002 and WEBSPAM-UK2006) have been used and the results using multilayer ELM are found to be more promising compared to other established classifiers.

show abstract

Learning-based text classifiers using the Mahalanobis distance for correlated datasets

Cited by 10 publications

References 0 publications

Exploring the Impact of Various Spectral Indices on Land Cover Change Detection Using Change Vector Analysis: A Case Study of Crete Island, Greece

Exploring the Impact of Various Spectral Indices on Land Cover Change Detection Using Change Vector Analysis: A Case Study of Crete Island, Greece

Assessment of water-induced soil erosion as a threat to cultural heritage sites: the case of Chania prefecture, Crete Island, Greece

Detecting spam web pages using multilayer extreme learning machine

Contact Info

Product

Resources

About