A comparative study on the swarm intelligence based feature selection approaches for fake and real fingerprint classification

Sasikala, V.; LakshmiPrabha, V.

doi:10.1109/icsns.2015.7292421

Cited by 6 publications

(2 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Similar condition also exists in the ABC method (Karaboga and Basturk, 2007). The convergence rate of conventional ABC is not significant, since inherent constraints may result in premature convergence (Sasikala and Lakshmiprabha, 2015). In basic GA, the premature convergence and weak local searching speed cause a slow convergence speed (Duan et al, 2013).…”

Section: Introductionmentioning

confidence: 74%

A Quantum-behaved Pigeon-Inspired Optimization approach to Explicit Nonlinear Model Predictive Controller for quadrotor

Xian

Chen

2018

IJICC

View full text Add to dashboard Cite

Purpose The purpose of this paper is to simplify the Explicit Nonlinear Model Predictive Controller (ENMPC) by linearizing the trajectory with Quantum-behaved Pigeon-Inspired Optimization (QPIO). Design/methodology/approach The paper deduces the nonlinear model of the quadrotor and uses the ENMPC to track the trajectory. Since the ENMPC has high demand for the state equation, the trajectory needed to be differentiated many times. When the trajectory is complicate or discontinuous, QPIO is proposed to linearize the trajectory. Then the linearized trajectory will be used in the ENMPC. Findings Applying the QPIO algorithm allows the unequal distance sample points to be acquired to linearize the trajectory. Comparing with the equidistant linear interpolation, the linear interpolation error will be smaller. Practical implications Small-sized quadrotors were adopted in this research to simplify the model. The model is supposed to be accurate and differentiable to meet the requirements of ENMPC. Originality/value Traditionally, the quadrotor model was usually linearized in the research. In this paper, the quadrotor model was kept nonlinear and the trajectory will be linearized instead. Unequal distance sample points were utilized to linearize the trajectory. In this way, the authors can get a smaller interpolation error. This method can also be applied to discrete systems to construct the interpolation for trajectory tracking.

show abstract

Section: Introductionmentioning

confidence: 74%

A Quantum-behaved Pigeon-Inspired Optimization approach to Explicit Nonlinear Model Predictive Controller for quadrotor

Xian

Chen

2018

IJICC

View full text Add to dashboard Cite

show abstract

“…T 2 -FS images of each patient were normalized by minimum-maximum normalization in order to convert all pixels into a range of [1,50] integral intensities. 20,21 The hand-crafted feature extraction was implemented with an in-house Matlab code (MATLAB 2013a, MathWorks, Natick, MA). A total of 8715 features were extracted, including 14 first-order statistics features, 14 size and shape-based features, 63 texture features and 8624 wavelet features (Supplementary Material 1).…”

Section: Radiomics Feature Extractionmentioning

confidence: 99%

A preoperative radiomics model for the identification of lymph node metastasis in patients with early-stage cervical squamous cell carcinoma

Yao

Long

et al. 2020

BJR

View full text Add to dashboard Cite

Objectives: To develop and validate a radiomics modelfor preoperative identification of lymph node metastasis (LNM) in patients with early-stage cervical squamous cell carcinoma (CSCC). Methods: Total of 190 eligible patients were randomly divided intotraining(n = 100) andvalidation (n = 90) cohorts. Handcrafted features and deep-learning features were extracted from T2-weighted fat suppressionimages. The minimum redundancy maximum relevancealgorithm and LASSO regression with 10-fold cross-validation were used for key features selection. A radiomics model that incorporated the handcrafted-signature, deep-signature and squamous cell carcinoma antigen (SCC-Ag) levels was developed by logistic regression. The modelperformance was assessed and validatedwith respect to its calibration, discrimination and clinical usefulness. Results: Three handcrafted features and three deep-learning features were selected and used to build handcrafted- and deep-signature. The model, which incorporated the handcrafted-signature, deep-signature and SCC-Ag showed satisfactory calibration and discrimination in the training cohort (AUC: 0.852, 95% CI: 0.761–0.943) and the validation cohort (AUC: 0.815, 95% CI: 0.711–0.919). Decision curve analysis indicated the clinical usefulness of the radiomics model. The radiomics model yielded greater AUCs than either the radiomics signature (AUC = 0.806 and 0.779, respectively) or the SCC-Ag (AUC = 0.735 and 0.688, respectively) alone in both the training andvalidation cohorts. Conclusion: The presented radiomics model can be used for preoperative identification of LNM inpatientswith early-stage CSCC. Its performance outperforms that ofSCC-Ag level analysis alone. Advances in knowledge: A radiomics model incorporated radiomics signature and SCC-Ag levels demonstrated good performance in identifying LNM in patientswithearly-stage CSCC.

show abstract

Fingerprint Classification Models Based on Bioinspired Optimization Algorithm: A Systematic Review

Mustafa¹,

Millham²,

Yang³

2023

Lecture Notes in Networks and Systems

View full text Add to dashboard Cite

A comparative study on the swarm intelligence based feature selection approaches for fake and real fingerprint classification

Cited by 6 publications

References 14 publications

A Quantum-behaved Pigeon-Inspired Optimization approach to Explicit Nonlinear Model Predictive Controller for quadrotor

A Quantum-behaved Pigeon-Inspired Optimization approach to Explicit Nonlinear Model Predictive Controller for quadrotor

A preoperative radiomics model for the identification of lymph node metastasis in patients with early-stage cervical squamous cell carcinoma

Fingerprint Classification Models Based on Bioinspired Optimization Algorithm: A Systematic Review

Contact Info

Product

Resources

About