Extreme Learning Machine-Based Age-Invariant Face Recognition With Deep Convolutional Descriptors

Boussaad, Leila; Boucetta, Aldjia

doi:10.4018/ijamc.290540

Cited by 3 publications

(2 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Although the proposed DET can reduce the computation and avoid overfitting problems, some parameters in the DET are set randomly and will not change, which also leads to some problems [27]. Poor weight and bias will lead to the decline of model performance [28]. For better classification performance, BA is selected for the optimization of DET.…”

Section: Proposed Ba-guided Optimizationmentioning

confidence: 99%

ODET: Optimized Deep ELM-based Transfer Learning for Breast Cancer Explainable Detection

Zhu¹,

Wang²

2022

EAI Endorsed Scal Inf Syst

View full text Add to dashboard Cite

INTRODUCTION: Breast cancer is one of the most common malignant tumors in women, and the incidence rate is increasing year by year. Women in every country in the world may develop breast cancer at any age after puberty. The cause of breast cancer is not fully understood. At present, the main methods of breast cancer detection are inefficient. Researchers are trying to use computer technology to detect breast cancer. But there are some still limitations. METHODS: We propose a network (ODET) to detect breast cancer based on ultrasound images. In this paper, we use ResNet50 as the backbone model. We make some modifications to the backbone model by deep ELM-based transfer learning. After these modifications, the network is named DET. However, DET still has some shortcomings because the parameters in DET are randomly assigned and will not change in the experiment. In this case, we select BA to optimize DET. The optimized DET is named ODET. RESULTS: The proposed ODET gets the F1-score (F1), precision (PRE), specificity (SPE), sensitivity (SEN), and accuracy (ACC) are 93.16%±1.12%, 93.28%±1.36%, 98.63%±0.31%, 93.96%±1.85%, and 97.84%±0.37%, respectively. CONCLUSION: It proves that the proposed ODET is an effective method for breast cancer detection.

show abstract

Section: Proposed Ba-guided Optimizationmentioning

confidence: 99%

ODET: Optimized Deep ELM-based Transfer Learning for Breast Cancer Explainable Detection

Zhu¹,

Wang²

2022

EAI Endorsed Scal Inf Syst

View full text Add to dashboard Cite

show abstract

“…The third category, reinforcement learning, is somewhere in between, where an intelligent being "tries out" different actions based on the choices it makes in the environment and thus receives different rewards to guide its next behaviour. The aim of this learning is to maximise the cumulative rewards available to the intelligence [15][16].…”

Section: MLmentioning

confidence: 99%

Machine Learning-Based Study on the Identification of Misstatements in Annual Reports of Listed Companies - A Financial Restatement Prediction Perspective

2021

View full text Add to dashboard Cite

The significance and importance of financial reporting as the basis and foundation for relevant decision makers to make judgments cannot be overstated, and both capital market participants and regulators attach great importance to the disclosure of financial reports. Although relevant regulatory authorities such as China's Securities Regulatory Commission and Accounting Standards Board have issued corresponding standards and regulations to strictly regulate the disclosure behaviour of companies' financial reports, due to insufficient supervision or relatively low costs of non-compliance, listed companies have committed FF in violation of relevant laws and regulations in order to preserve their own interests, causing unmeasurable losses to stakeholders. The main objective of this paper is to launch a study on the identification of misstatements in listed companies' annual reports based on ML under the perspective of financial restatement prediction. Based on the research on FF patterns and FFI in the first part, we firstly select the set of primary features based on the theory of FF motive, then perform Mann-Whitney test on the set of primary features to obtain the set of original features, and then use Bortua algorithm to select the final set of FI features from the set of original features. The data of the fraud samples and non-fraud samples were loaded into the four types of financial fraud identification models (FFIM) in the order of the original FI features and the FI features constructed by the BA. The model identification results showed that the combination of the FFI features constructed by the BA and the RFM had a good identification effect, and the overall evaluation indexes of G-mean and F-value were 75.9% and 78.3% respectively.

show abstract

Bald eagle search optimization with deep transfer learning enabled age-invariant face recognition model

Alsubai

Hamdi²,

Abdel‐Khalek³

et al. 2022

Image and Vision Computing

View full text Add to dashboard Cite

Extreme Learning Machine-Based Age-Invariant Face Recognition With Deep Convolutional Descriptors

Cited by 3 publications

References 35 publications

ODET: Optimized Deep ELM-based Transfer Learning for Breast Cancer Explainable Detection

ODET: Optimized Deep ELM-based Transfer Learning for Breast Cancer Explainable Detection

Machine Learning-Based Study on the Identification of Misstatements in Annual Reports of Listed Companies - A Financial Restatement Prediction Perspective

Bald eagle search optimization with deep transfer learning enabled age-invariant face recognition model

Contact Info

Product

Resources

About