Rough-Fuzzy Clustering for Grouping Functionally Similar Genes from Microarray Data

Maji, Pradipta; Paul, Sushmita

doi:10.1109/tcbb.2012.103

Cited by 77 publications

(31 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This hybrid combination of rough fuzzy [15][16][17][18][19] clustering had applied to many of the research application areas like brain MRI [15,19], Micro gene expression data [16][17][18] and various other datasets like Synthetic dataset, Iris dataset [19]. This hybrid technique gave most significant results in almost every datasets.…”

Section: Related Workmentioning

confidence: 99%

Probabilistic mutual information based extraction of malignant brain tumors in MR images

Vidyarthi

Mittal

2014

2014 9th International Conference on Industrial and Information Systems (ICIIS)

View full text Add to dashboard Cite

Extraction of the malignant tumor region from the brain magnetic resonance (MR) image is a critical task. As the soft tissues of the brain neoplasm has a lot of variation thus the proper extraction of the malignant tumor and segmenting the affected part from brain MR image is the major part of concern. Malignant brain tumors like Central Neuro Cytoma (CNC), Glioblastoma Multiforme (GBM), Gliomas, Intra Ventricular Malignant Mass and Metastasis are concerned as one of the critical brain tumors of medical science therefore the extraction and appropriate segmentation of such tumor from the brain MR image in their early phase of generation is required. In the past innumerable approaches had applied on brain MR imaging system to figure out the proper abnormality region inside the brain image. The literature gives an idea about various clustering and segmentation approaches that help to identify the abnormal region inside imaging systems based on predefined threshold values. While the selection of proper threshold is again a mind blundering. In this paper a new image segmentation algorithm is proposed which clusters the maximum possible abnormality region based on the probabilistic mutual information. Proposed algorithm is free from any initial selection of threshold value and gives significant results in extraction of the malignant tumor region inside brain MR image.

show abstract

Section: Related Workmentioning

confidence: 99%

Probabilistic mutual information based extraction of malignant brain tumors in MR images

Vidyarthi

Mittal

2014

2014 9th International Conference on Industrial and Information Systems (ICIIS)

View full text Add to dashboard Cite

show abstract

“…In recent years, the theory of rough sets has gained popularity in handling uncertainties associated with incomplete class definitions. The rough-fuzzy clustering, presented in (Maji and Pal (2007); Maji and Paul (2013)), judiciously integrates the merits of fuzzy set and rough set theory. The rough-fuzzy clustering based segmentation methods (Maji and Roy (2015a,b); Maji and Pal (2007)) have shown their effectiveness in image segmentation by capturing different uncertainties that cannot be handled by traditional clustering algorithms, such as hard c-means (HCM), FCM and so on.…”

Section: Introductionmentioning

confidence: 99%

Rough-fuzzy segmentation of HEp-2 cell indirect immunofluorescence images

Roy

Maji

2017

IJDMB

Self Cite

View full text Add to dashboard Cite

Human epithelial type-2 (HEp-2) cell is currently the most recommended substrate in indirect immunofluorescence (IIF) tests to diagnose various connective tissue disorders. The IIF test identifies the presence of antinuclear antibody (ANA) in patient serum. However, the proper detection of HEp-2 cells from the IIF images is an important prerequisite for the recognition of staining patterns of ANAs. The characteristics of HEp-2 cell images, due to fluorescence intensity, make the segmentation process more challenging.Recently, rough-fuzzy clustering algorithms have been shown to provide significant results for image segmentation by handling different uncertainties present in the images. But, the neighborhood information is completely ignored in these algorithms. However, the spatial information is useful when the image is distorted by different imaging artifacts. In this regard, the paper presents a segmentation algorithm by incorporating the neighborhood information into rough-fuzzy clustering algorithm. In the current study, the class label of a pixel is influenced by its neighboring pixels, depending on their local spatial constraint and local gray level constraint. The performance of the proposed method is evaluated on several HEp-2 cell IIF images and compared with that of existing algorithms, both qualitatively and quantitatively.

show abstract

“…Aside from the above mentioned three aspects of literature, there exists a plenty of other work regarding soft-partition clustering. For example, Miyamoto and Umayahara [3,29] regarded FCM as a regularization of crisp c -means, and then via the quadratic regularization function of memberships they designed another regularization method named fuzzy clustering by quadratic regularization (FC-QR); Yu [30] devised the general c -means model by extending the definition of the mean from a statistical point of view; Gan and Wu [31] proposed a classic fuzzy subspace clustering model and further analyzed its convergence; Wang et al [32] proposed another fuzzy subspace clustering method for handling high-dimensional, sparse data; and in addition, some application studies with respect to soft-partition clustering were also conducted, such as image compression [33,34], image segmentation [35-37], real-time target tracking [38,39], and gene expression data analysis [40]. …”

Section: Introductionmentioning

confidence: 99%

Cross-domain, soft-partition clustering with diversity measure and knowledge reference

Qian

Sun

Jiang

et al. 2016

Pattern Recognition

View full text Add to dashboard Cite

Conventional, soft-partition clustering approaches, such as fuzzy c-means (FCM), maximum entropy clustering (MEC) and fuzzy clustering by quadratic regularization (FC-QR), are usually incompetent in those situations where the data are quite insufficient or much polluted by underlying noise or outliers. In order to address this challenge, the quadratic weights and Gini-Simpson diversity based fuzzy clustering model (QWGSD-FC), is first proposed as a basis of our work. Based on QWGSD-FC and inspired by transfer learning, two types of cross-domain, soft-partition clustering frameworks and their corresponding algorithms, referred to as type-I/type-II knowledge-transfer-oriented c-means (TI-KT-CM and TII-KT-CM), are subsequently presented, respectively. The primary contributions of our work are four-fold: (1) The delicate QWGSD-FC model inherits the most merits of FCM, MEC and FC-QR. With the weight factors in the form of quadratic memberships, similar to FCM, it can more effectively calculate the total intra-cluster deviation than the linear form recruited in MEC and FC-QR. Meanwhile, via Gini-Simpson diversity index, like Shannon entropy in MEC, and equivalent to the quadratic regularization in FC-QR, QWGSD-FC is prone to achieving the unbiased probability assignments, (2) owing to the reference knowledge from the source domain, both TI-KT-CM and TII-KT-CM demonstrate high clustering effectiveness as well as strong parameter robustness in the target domain, (3) TI-KT-CM refers merely to the historical cluster centroids, whereas TII-KT-CM simultaneously uses the historical cluster centroids and their associated fuzzy memberships as the reference. This indicates that TII-KT-CM features more comprehensive knowledge learning capability than TI-KT-CM and TII-KT-CM consequently exhibits more perfect cross-domain clustering performance and (4) neither the historical cluster centroids nor the historical cluster centroid based fuzzy memberships involved in TI-KT-CM or TII-KT-CM can be inversely mapped into the raw data. This means that both TI-KT-CM and TII-KT-CM can work without disclosing the original data in the source domain, i.e. they are of good privacy protection for the source domain. In addition, the convergence analyses regarding both TI-KT-CM and TII-KT-CM are conducted in our research. The experimental studies thoroughly evaluated and demonstrated our contributions on both synthetic and real-life data scenarios.

show abstract

Rough-Fuzzy Clustering for Grouping Functionally Similar Genes from Microarray Data

Cited by 77 publications

References 38 publications

Probabilistic mutual information based extraction of malignant brain tumors in MR images

Probabilistic mutual information based extraction of malignant brain tumors in MR images

Rough-fuzzy segmentation of HEp-2 cell indirect immunofluorescence images

Cross-domain, soft-partition clustering with diversity measure and knowledge reference

Contact Info

Product

Resources

About