Experiment Improvement of Restricted Boltzmann Machine Methods for Image Classification

Dewi, Christine; Chen, Rung-Ching; Hendry, .; Hung, Hsiu-Te

doi:10.1142/s2196888821500184

Cited by 10 publications

(3 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…SVM has several hyperparameters that must be set before training the model. One important hyperparameter is the choice of kernel function, which determines the mapping of the input data into a highdimensional feature space (Dewi et al, 2021). Other hyperparameters include the regularization parameter (C), which controls the trade-off between minimizing the training error and maximizing the margin, and the kernel coefficient (gamma), which controls the shape of the decision boundary (Wang et al, 2015;Ardhianto et al, 2022).…”

Section: Hyperparameter Of Svmmentioning

confidence: 99%

Spam classification problems using support vector machine and grid search

Dewi,

Indriawan,

Christanto

2023

Int. J. Appl. Sci. Eng.

View full text Add to dashboard Cite

Spam classification is an important task in identifying unwanted and potentially harmful emails for internet users. The increasing number of internet users highlights the growing importance of handling spam effectively. In this paper, we propose an approach for spam classification using Support Vector Machines (SVM) with grid search hyperparameter optimization. Our research differs from existing studies by specifically focusing on the integration of SVM with grid search to achieve optimal hyperparameter tuning. Additionally, we provide a unique dataset comprising diverse samples of spam emails for evaluation purposes. We also employ pre-processing techniques, including the removal of unnecessary words such as stop words and punctuation marks, as well as word stemming to convert words into their base forms. To optimize the performance of the SVM model, we use Grid Search to determine the optimal values for hyperparameters, including C, gamma, and the kernel. The results of the first experiment using SVM with the first dataset show that grid search yields the optimal parameters {'C': 100, 'gamma': 0.01, 'kernel': 'rbf'}, resulting in an accuracy improvement from 98.02% to 98.47%. In the second experiment using the second dataset, the accuracy obtained is 99.1%, compared to the previous non-optimized parameters which achieved 98.8%. These results indicate a significant improvement in spam classification accuracy. The experimental results demonstrate that our approach outperforms existing methods in terms of accuracy, precision, and recall. The findings of our research have significant implications for improving spam detection systems and enhancing the overall effectiveness of email communication.

show abstract

Section: Hyperparameter Of Svmmentioning

confidence: 99%

Spam classification problems using support vector machine and grid search

Dewi,

Indriawan,

Christanto

2023

Int. J. Appl. Sci. Eng.

View full text Add to dashboard Cite

show abstract

“…The gradient ascent method is the most efficient way to maximise the log-likelihood function and it uses an iterative approach to update the parameters as shown in equation ( 11) [20].…”

Section:  mentioning

confidence: 99%

A Deep Learning-based Model for Evaluating the Sustainability Performance of Accounting Firms

Chen¹

2022

IJACSA

View full text Add to dashboard Cite

The harmonious and stable development of society is strongly related to the sustainable development of enterprises. In order to better face the challenges of environmental resources, sustainable development must be included in the development focus of accounting enterprises. The research proposes a performance evaluation model based on deep learning, improves RBMs model on the basis of deep belief network (DBN), improves the accuracy of the model through reverse fine-tuning technology, and effectively combines multiple restricted Boltzmann machines (RBMs) and Softmax classifiers to build a modular multi classification model to complete the sustainable development performance evaluation of accounting enterprises. The performance of RBM fine tuning classifier is higher than that of RBM expression and PCA (Principal Component Analysis) expression, which mainly shows the effectiveness and stability of feature extraction. The network output results of test samples are converted into prediction performance evaluation. The model is evaluated by average precision (AP), average recall (AR), and prediction accuracy. The AP, AR, and prediction accuracy of the proposed method are 86.95%, 89.74%, and 88.29% respectively, which are higher than Softmax classifiers, Back Propagation (BP) neural networks, and DBN based Softmax methods, It shows that this method is superior to other algorithms in the application of performance evaluation model for sustainable development of accounting enterprises, and it is feasible and effective, which is of great significance to the establishment of performance evaluation model for the accounting industry.

show abstract

“…RBM is a probabilistic and generative model comprising well-connected visible and hidden layers. Recent developments have highlighted the capacity of RBM in feature extraction procedures 87 . An RBM model has been proposed for image compression and image reconstruction.…”

Section: Restricted Boltzmann Machinementioning

confidence: 99%

Multimodal Classification on PET/CT Image Fusion for Lung Cancer: A Comprehensive Survey

Das

Chandra

2022

ECS Trans.

View full text Add to dashboard Cite

Medical image fusion has become essential for accurate diagnosis. For example, a lung cancer diagnosis is currently conducted with the help of multimodality image fusion to find anatomical and functional information about the tumor and metabolic measurements to identify the lung cancer stage and metastatic information of the disease. Generally, the success of multimodality imaging for lung cancer diagnosis is due to the combination of PET and CT imaging advantages while minimizing their respective limitations. However, medical image fusion involves the registration of two different modalities, which is time-consuming and technically challenging, and it is a cause of concern in a clinical setting. Therefore, the paper's main objective is to identify the most efficient medical image fusion techniques and the recent advances by conducting a collective survey. In addition, the study delves into the impact of deep learning techniques for image fusion and their effectiveness in automating the image fusion procedure with better image quality while preserving essential clinical information.

show abstract

Experiment Improvement of Restricted Boltzmann Machine Methods for Image Classification

Cited by 10 publications

References 20 publications

Spam classification problems using support vector machine and grid search

Spam classification problems using support vector machine and grid search

A Deep Learning-based Model for Evaluating the Sustainability Performance of Accounting Firms

Multimodal Classification on PET/CT Image Fusion for Lung Cancer: A Comprehensive Survey

Contact Info

Product

Resources

About