Holoentropy enabled-decision tree for automatic classification of diabetic retinopathy using retinal fundus images

Mane, Vijay; Jadhav, Dattatray V.

doi:10.1515/bmt-2016-0112

Cited by 53 publications

(35 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this section, the proposed classifier, FHDT, developed for the classification of bacilli in the image that helps in the diagnosis of TB, is explained. The DT [28] is a tool used for classification taking a tree structure form through the rules obtained from the input feature vector and results in a tree with decision and leaf nodes. The proposed FHDT classifier segregates into few-bacilli, non-bacilli and overlapping bacilli.…”

Section: Proposed Fuzzy and Hyco-entropy-based Decision Tree For The mentioning

confidence: 99%

See 1 more Smart Citation

FHDT: Fuzzy and Hyco-entropy-based Decision Tree Classifier for Tuberculosis Diagnosis from Sputum Images

Mithra

Emmanuel

2018

Sādhanā

View full text Add to dashboard Cite

Tuberculosis (TB) is one of the infectious diseases spread by the infectious agent Mycobacterium tuberculosis. Sputum smear microscopy is the primary tool used for the diagnosis of pulmonary TB, but has its limitations such as low sensitivity and large observation time. Hence, an automated technique is preferred for the diagnosis of TB. This paper develops a technique for TB diagnosis based on the bacilli count by proposing Fuzzy and Hyco-entropy-based Decision Tree (FHDT) classifier using sputum smear microscopic images. The proposed technique involves three steps: segmentation, feature extraction and classification. Initially, the input sputum smear microscopic image is subjected to a colour space transformation, for which a thresholding is applied to obtain the segmented result. Important features such as length, density, area and few histogram features are extracted for FHDT-based classification that classifies the segments into few-bacilli, non-bacilli and overlapping bacilli. An entropy function, called hyco-entropy, is designed for the optimal selection of feature. For further analysis of classification, that is, to count the number in the overlapping bacilli, the fuzzy classifier is adopted. FHDT classifier is evaluated in terms of Segmentation Accuracy (SA), Mean Squared Error (MSE) and Missing Count (MC) using microscopic images taken from ZNSM-iDB, where it can attain maximum mean SA of 0.954 and mean MC of 2.4.

show abstract

Section: Proposed Fuzzy and Hyco-entropy-based Decision Tree For The mentioning

confidence: 99%

“…where cosh : ð Þ is the hyperbolic cosine function employed rather than the exponential function used in paper [28]. The hyperbolic cosine function is usually used for defining complex calculations to simplify the results.…”

Section: Proposed Fuzzy and Hyco-entropy-based Decision Tree For The mentioning

confidence: 99%

FHDT: Fuzzy and Hyco-entropy-based Decision Tree Classifier for Tuberculosis Diagnosis from Sputum Images

Mithra

Emmanuel

2018

Sādhanā

View full text Add to dashboard Cite

show abstract

“…The keyword is selected from the extracted features based on the holoentropy process [25]. The best keywords are selected using the holoentropy, and for each attribute the holoentropy is calculated as,…”

Section: Abstractelectionmentioning

confidence: 99%

Document Retrieval and Cluster Based Indexing using Rider Spider Monkey Optimization Algorithm

Yarlagadda,

Rao,

Srikrishna

2020

IJRTE

View full text Add to dashboard Cite

Document retrieval process is more significant in the field of research community for retrieving the highly-relevant documents that fit for the user query. Even though various document retrieval methods are introduced, retrieving the exact document based on the indexing is a quite challenging task in the document retrieval framework. Thus, an effective document retrieval algorithm named Rider Spider Monkey Optimization Algorithm (RSOA) is proposed in this research. Initially, the documents are pre-processed by the stop word elimination and the stemming process, and the features are extracted to find the key words of the documents by applying the Term FrequencyInverse Document Frequency (TF-IDF). The selected keywords are passed into the cluster-based indexing phase, where the cluster centroids are identified by using the proposed Rider Spider Monkey Optimization Algorithm. Moreover the query matching is carried out at two levels, at first, the query is forwarded and is matched to the entire cluster centroid to find the appropriate centroid. At the second level; the user query is matched based on the records present inside the matched centroid. Moreover, the query matching is progressed using the distance measure by the Bhattacharya distance to retrieve the documents. The performance is analyzed using the metrics, namely precision, F-measure, and recall and accuracy with the values of 90.141%, 91.876%, 91.178%, and 91.202%, respectively using 20 news group dataset .

show abstract

“…The holoentropy has been calculated for each feature from the feature vector. The feature having highest holoentropy is chosen as the best feature to construct the decision tree [18]. The holoentropy HLE (ai) is calculated as given in Eq.…”

Section: Classification Using Hdtmentioning

confidence: 99%

An efficient method for early stage detection of diabetic retinopathy

Shirbahadurkar¹,

Mané²,

Jadhav³

2017

IJET

View full text Add to dashboard Cite

Diabetic Retinopathy (DR) is one of the leading causes of blindness. The early detection and treatment of DR is significant to save the human vision. The presence of microaneurysms (MAs) is the first sign of the disease. The correct identification of MAs is an essential for finding of DR at the early stages. In this paper, we propose a three phase system for efficient recognition of MAs. The tentative MA lesions are recovered from the fundus image in the first stage. To accurately classify an extracted candidate region into MA or non-MA, the second stage prepares an attribute vector for each tentative MA lesion based on shape, intensity and statistical properties. The third stage is a classification step to classify as MAs and Non-MAs for early stage detection of DR. We present a holoentropy enabled decision tree classifier which combines entropy and total correlation. The best feature for decision tree is selected based on holoentropy to enhance the correctness of the classification. The implemented system is experimented using fundus image database DIARETDB1. The proposed method achieved an overall accuracy of 97.67%. The proposed system has detected the MAs with higher performance using simple features and holoentropy based decision tree classifier. The proposed system is suitable for early stage detection of DR through the accurate identification of MAs.

show abstract

Holoentropy enabled-decision tree for automatic classification of diabetic retinopathy using retinal fundus images

Cited by 53 publications

References 32 publications

FHDT: Fuzzy and Hyco-entropy-based Decision Tree Classifier for Tuberculosis Diagnosis from Sputum Images

FHDT: Fuzzy and Hyco-entropy-based Decision Tree Classifier for Tuberculosis Diagnosis from Sputum Images

Document Retrieval and Cluster Based Indexing using Rider Spider Monkey Optimization Algorithm

An efficient method for early stage detection of diabetic retinopathy

Contact Info

Product

Resources

About