Improved support vector machine classification algorithm based on adaptive feature weight updating in the Hadoop cluster environment

Cao, Jianfang; Wang, Min; Li, Yanfei; Zhang, Qi

doi:10.1371/journal.pone.0215136

Cited by 25 publications

(16 citation statements)

References 33 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Figure 3 demonstrates the evaluation of the classification effects of two types of classifier algorithms, including back-propagation neural network (BPNN) [ 25 ] and support vector machine (SVM) [ 26 ] by confusion matrix. BP neural networks are the most basic neural networks, with forward propagation of the output and backward propagation of the error.…”

Section: Methodsmentioning

confidence: 99%

Data on the Impact of Epidemic on Nursing Staff’s Mental Health in the Context of Wireless Network

Guo

Guo²,

Xing

2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

The research was aimed to analyze the impact of epidemic pneumonia on nursing personnel’s mental health under wireless network background and to improve the selection of random forest classification (RFC) algorithm parameters by the whale optimization algorithm (WOA). Besides, a total of 148 in-service nursing personnel were selected as the research objects, and 148 questionnaires were recycled effectively. The collected data were analyzed by the improved RFC algorithm. In addition, the research investigated the impacts of demographic factors on nursing personnel’s mental health by the one-way variance method. The results demonstrated that the accuracy of the improved algorithm in training samples and test samples reached 83.3% and 81.6%, respectively, both of which were obviously higher than those of support vector machine (SVM) (80.1% and 79.3%, respectively) and back-propagation neural network (BPNN) (78.23% and 77.9%, respectively), and the differences showed statistical meanings P < 0.05 . The Patient Health Questionnaire-9 (PHQ-9) showed that the depression levels of 9.46% of the included personnel were above moderate. The Generalized Anxiety Disorder (GAD-7) demonstrated that the anxiety levels of 3.38% of the included personnel were above moderate. The insomnia severity index (ISI) indicated that the insomnia levels of 3.38% of the included personnel were above moderate. The average score of male personnel (3.65) was obviously lower than that of female personnel (3.71). Besides, the average scale score of married personnel (3.78) was significantly higher than that of unmarried personnel (3.65). The average scale scores of personnel with bachelor’s (3.66) and master’s degrees (3.62) were obviously lower than those of personnel with junior college (3.77) and technical secondary school (3.75) diplomas. The average scale score of personnel with over 5-year work experience (3.68) was significantly lower than that of personnel working for less than five years (3.72). The average scale score of personnel with experience in responding to public emergencies (3.65) was obviously lower than that of personnel without related experience (3.74). The differences all showed statistical meaning P < 0.05 . The results of this research revealed that the accuracy of the improved RFC algorithm was remarkably higher than that of the SVM and BPNN algorithms. Furthermore, many nursing personnel suffered from mental diseases at different levels with the impact of the epidemic. Gender, marital status, education level, and experience in responding to public emergencies were the main factors affecting nursing personnel’s mental health.

show abstract

Section: Methodsmentioning

confidence: 99%

Data on the Impact of Epidemic on Nursing Staff’s Mental Health in the Context of Wireless Network

Guo

Guo²,

Xing

2022

Journal of Healthcare Engineering

View full text Add to dashboard Cite

show abstract

“…The performance of this approach deals with minimizing the executing time with expected accuracy. Better accuracy is also reported in works which integrates K-means algorithm with improved support vector machine (4) . In theory, a new method called Quantum Artificial Immune System -deep spiking neural network (QAIS-DSNN) was proposed to segment and distinguish brain tumors from MR images (5) .…”

Section: Introductionmentioning

confidence: 82%

Mass Sphering Approach for Three-Dimensional Reconstruction of Brain Tumor using MRI

Radhakrishnan¹,

Vanaja²,

Devi³

et al. 2022

IJST

View full text Add to dashboard Cite

Objective: The objective of the research work is to reconstruct the brain tumor three-dimensionally with high degree of accuracy. Methods: This study describes 3D reconstruction of brain tumor using Mass Sphering Approach (MSA) algorithm. 39 weighted features are extracted from the non-tumor and tumor pixels. These weighted features are used to train the Support Vector Machine (SVM) algorithm. Number of training samples taken to train SVM algorithm are 268 and the testing sample are 64. The complete MR image set of a subject (64 axial slices) are detected for tumor pixels and these slices are concatenated to get volumetric tumor information. Findings: 5-step MSA algorithm is proposed which includes filtering, segmentation, classification, optimization and reconstruction. MR images are subjected to Rician noise which can be removed by a simple correction scheme, initiated to change the bias due to the Rician distribution of the noisy magnitude data. The filtered MR image slices are segmented and classified to detect the tumor areas and the tumor pixels are subjected for 3D reconstruction. The improvement in performance of MSA is depicted by comparing the algorithm with traditional SVM. Novelty: The accuracy achieved in detecting glioma and glioblastoma using MSA are 95.24% and 99% respectively which is highly remarkable.

show abstract

“…The proposed MHNN presented in Figure 1 exploits the fact that features within an image utilize similar pixel geometric correlations [ 56 , 57 ]. Such geometric correlations, therefore, can be used to model and reproduce an enhanced image with better feature representation.…”

Section: Methodsmentioning

confidence: 99%

Geometric Regularized Hopfield Neural Network for Medical Image Enhancement

Alenezi

Santosh

2021

International Journal of Biomedical Imaging

View full text Add to dashboard Cite

One of the major shortcomings of Hopfield neural network (HNN) is that the network may not always converge to a fixed point. HNN, predominantly, is limited to local optimization during training to achieve network stability. In this paper, the convergence problem is addressed using two approaches: (a) by sequencing the activation of a continuous modified HNN (MHNN) based on the geometric correlation of features within various image hyperplanes via pixel gradient vectors and (b) by regulating geometric pixel gradient vectors. These are achieved by regularizing proposed MHNNs under cohomology, which enables them to act as an unconventional filter for pixel spectral sequences. It shifts the focus to both local and global optimizations in order to strengthen feature correlations within each image subspace. As a result, it enhances edges, information content, contrast, and resolution. The proposed algorithm was tested on fifteen different medical images, where evaluations were made based on entropy, visual information fidelity (VIF), weighted peak signal-to-noise ratio (WPSNR), contrast, and homogeneity. Our results confirmed superiority as compared to four existing benchmark enhancement methods.

show abstract

Improved support vector machine classification algorithm based on adaptive feature weight updating in the Hadoop cluster environment

Cited by 25 publications

References 33 publications

Data on the Impact of Epidemic on Nursing Staff’s Mental Health in the Context of Wireless Network

Data on the Impact of Epidemic on Nursing Staff’s Mental Health in the Context of Wireless Network

Mass Sphering Approach for Three-Dimensional Reconstruction of Brain Tumor using MRI

Geometric Regularized Hopfield Neural Network for Medical Image Enhancement

Contact Info

Product

Resources

About