NPrSVM: Nonparallel sparse projection support vector machine with efficient algorithm

Chen, Wei-Jie; Shao, Yuan‐Hai; Li, Chun‐Na; Wang, Yuqing; Liu, Ming-Zeng; Wang, Zhen

doi:10.1016/j.asoc.2020.106142

Cited by 12 publications

(8 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To derive the model of MPMSVC, firstly, we enhance MPMSVC in least squares sense via replacing the equality constraints with inequality in TPMSVM, which enjoys an effective learning procedure. Besides, to reduce the impact of outliers, L 1 -norm metric [31,[39][40][41] is further considered for MPMSVC, which can also improve the flexibility of model. For this purpose, our MPMSVC considers the following linear L 1 -norm loss function for each cluster plane-center…”

Section: A Model Formulationmentioning

confidence: 99%

“…Similar to linear case, we optimize problem (40) via solving series of convex unconstrained quadratic problem (41) iteratively until converges. That is, the iteration solution u t+1 k is updated by…”

Section: Nonlinear Extensionmentioning

confidence: 99%

“…e k is the i-th element of the slack vector ξ t k and H φ k,i is the i-th row of H φ k . Then, we can derive the solution of problem (41) in each iteration by Proposition 2 without proof.…”

Section: Nonlinear Extensionmentioning

confidence: 99%

See 2 more Smart Citations

MPMSVC: Multiple Parametric-Margin Support Vector Clustering

et al. 2021

Self Cite

View full text Add to dashboard Cite

Under the nonparallel plane-based clustering paradigm, in this work, we propose an unsupervised multiple parametric-margin support vector clustering (MPMSVC) for noisy clustering tasks. The main idea of MPMSVC is to find a parametric-margin center hyperplane for each cluster in a manner that gathers the within-cluster instances around the corresponding center hyperplane, and keeps the betweencluster instances far away. Specifically, our MPMSVC owns the following attractive merits: i) The primal of MPMSVC is enhanced in the least squares sense, which enjoys an effective learning procedure. ii) The utilization of the linear L 1-norm loss makes MPMSVC be more robust to noisy clustering tasks. iii) An efficient iterative algorithm is presented to optimize the non-smooth problem of MPMSVC, which only involves a set of linear equations. Also, the convergence of the proposed algorithm is guaranteed theoretically. iv) The nonlinear extension is further derived via kernel technique to deal with more complex clustering tasks. Finally, the feasibility and effectiveness of MPMSVC are validated by extensive experiments on both synthetic and real-world datasets. INDEX TERMS Plane-based clustering, Nonparallel support vector clustering, L 1-norm, Robustness.

show abstract

Section: A Model Formulationmentioning

confidence: 99%

Section: Nonlinear Extensionmentioning

confidence: 99%

See 1 more Smart Citation

MPMSVC: Multiple Parametric-Margin Support Vector Clustering

et al. 2021

Self Cite

View full text Add to dashboard Cite

show abstract

“…It has been widely used in many different studies in the literature with high precision. SVM is a learning approach based on maximum margin [24]. It tries to find optimal decision boundary through maximizing the margin between parallel support hyperplanes.…”

Section: Support Vector Machinesmentioning

confidence: 99%

“…It tries to find optimal decision boundary through maximizing the margin between parallel support hyperplanes. It finds the global optimum because its objective function is quadratic and all constraints are linear [24]. Non-linear classifications are successfully handled through kernel functions used in the algorithm.…”

Section: Support Vector Machinesmentioning

confidence: 99%

A Machine Learning Based Early Diagnosis System for Mesothelioma Disease

Şentürk

Çekiç

2020

Düzce Üniversitesi Bilim Ve Teknoloji Dergisi

View full text Add to dashboard Cite

Mesothelioma is pleura cancer that cause death in about one year after diagnosis. The disease causes pain and shortness of breath. Patients have a CT (Computed Tomography)-scan and lung x-ray traditionally, but the exact method is biopsy. There are also different biopsy methods for its diagnosis. Its prevalence is one or two in a million around the world, but for Turkey it is disastrous. Five hundred people are diagnosed as mesothelioma every year in Turkey. This serious rate makes early diagnosis systems crucial for mesothelioma. In this paper, a machine learning based early detection system has been proposed for this fatal disease. An open database is used for the experiments and different methods have been applied to the problem of diagnosing mesothelioma disease. Accuracy and sensitivity performance metrics were used for the evaluation of the methods. The results show the diagnostic performance of different machine learning methods and present a successful early diagnosis system.

show abstract