Search

Makeup can disguise facial features, which results in degradation in the performance of many facial-related analysis systems, including face recognition, facial landmark characterisation, aesthetic quantification and automated age estimation methods. Thus, facial makeup is likely to di- rectly affect several real-life applications such as cosmetology and virtual cosmetics recommendation systems, security and access control, and social interaction. In this work, we conduct a compar- ative study and design automated facial makeup detection systems leveraging multiple learning schemes from a single unconstrained photograph. We have investigated and studied the efficacy of deep learning models for makeup detection incorporating the use of transfer learning strategy with semi-supervised learning using labelled and unlabelled data. First, during the supervised learning, the VGG16 convolution neural network, pre-trained on a large dataset, is fine-tuned on makeup labelled data. Secondly, two unsupervised learning methods, which are self-learning and convolutional auto-encoder, are trained on unlabelled data and then incorporated with supervised learning during semi-supervised learning. Comprehensive experiments and comparative analysis have been conducted on 2479 labelled images and 446 unlabelled images collected from six challenging makeup datasets. The obtained results reveal that the convolutional auto-encoder merged with supervised learning gives the best makeup detection performance achieving an accuracy of 88.33% and area under ROC curve of 95.15%. The promising results obtained from conducted experiments reveal and reflect the efficiency of combining different learning strategies by harnessing labelled and unlabelled data. It would also be advantageous to the beauty industry to develop such computational intelligence methods. [ABSTRACT FROM AUTHOR]

Skin cancer is one of the most common cancers worldwide caused by excessive development of skin cells. Considering the rapid growth of the use of deep learning algorithms for skin cancer detection, selecting the optimal algorithm has become crucial to determining the efficiency of computer-aided diagnosis (CAD) systems developed for the healthcare sector. However, a sufficient number of criteria and parameters must be considered when selecting an ideal deep learning algorithm. A generally accepted method for benchmarking deep learning models for skin cancer classification is unavailable in the current literature. This paper presents a multi-criteria decision-making framework for evaluating and benchmarking deep learning models for skin cancer detection based on hybridisation of entropy and VIseKriterijumska Optimizacija I Kompromisno Resenje (VIKOR) methods. Twelve well-known convolution networks are evaluated and tested on eleven publicly available image datasets to achieve the target of the study. Several criteria related to deep convolutional neural networks (CNNs) architectures, including optimisation technique, transfer learning, class balancing, transfer learning, data augmentation, and network complexity, have been considered in the multi-criteria evaluation. The decision matrix (DM) is designed based on a crossover of the five evaluation criteria and twelve (CNNs) classification models on different datasets. Subsequently, in the benchmarking and ranking of deep learning classification models, multi-criteria decision making (MCDM) techniques are used. The MCDM uses a scheme that involves the integration of entropy with VIKOR approaches. For the weight calculations of evaluation criteria, entropy is applied, while VIKOR is used to benchmark and rank the models. The obtained results reveal that the InceptionResNetV2 model gained the first rank and is selected as the optimal architecture for skin cancer detection considering the five criteria investigated in our study. The presented framework achieves a significant performance in selecting the best algorithm, which could provide substantial guidance to the researcher working in the field. [ABSTRACT FROM AUTHOR]

Coronavirus disease (COVID-19), which is caused by SARS-CoV-2, has been announced as a global pandemic by the World Health Organization (WHO), which results in the collapsing of the healthcare systems in several countries around the globe. Machine learning (ML) methods are one of the most utilized approaches in artificial intelligence (AI) to classify COVID-19 images. However, there are many machine-learning methods used to classify COVID-19. The question is: which machine learning method is best over multi-criteria evaluation? Therefore, this research presents benchmarking of COVID-19 machine learning methods, which is recognized as a multi-criteria decision-making (MCDM) problem. In the recent century, the trend of developing different MCDM approaches has been raised based on different perspectives; however, the latest one, namely, the fuzzy decision by opinion score method that was produced in 2020, has efficiently been able to solve some existing issues that other methods could not manage to solve. because of the multiple criteria decision-making problem and because some criteria have a conflict problem. The methodology of this research was divided into two main stages. The first stage related to identifying the decision matrix used eight different ML methods on chest X-ray (CXR) images and extracted a new decision matrix so as to assess the ML methods. The second stage related to FDOSM was utilized to solve the multiple criteria decision-making problems. The results of this research are as follows: (1) The individual benchmarking results of three decision makers are nearly identical; however, among all the used ML methods, neural networks (NN) achieved the best results. (2) The results of the benchmarking group are comparable, and the neural network machine learning method is the best among the used methods. (3) The final rank is more logical and closest to the decision-makers' opinion. (4) Significant differences among groups' scores are shown by our validation results, which indicate the authenticity of our results. Finally, this research presents many benefits, especially for hospitals and medical clinics, with a view to speeding up the diagnosis of patients suffering from COVID-19 using the best machine learning method. [ABSTRACT FROM AUTHOR]

Simple Summary: Melanoma is the most dangerous type of skin cancer. It grows quickly and has the ability to spread to any organ. This study aims to evaluate and benchmark deep learning models for automatic melanoma diagnosis considering nineteen convolutional neural networks and ten criteria. Multi-Criteria Decision Making methods (MCDMs) are exploited to conduct the benchmarking and subsequently selecting the optimal model considering the predefined criteria. The study findings would help in the model selection, designing quick and reliable diagnostic tools based on image data, and contributing to the development of more accurate and efficient point-of-care diagnostic and detection systems. Melanoma is the most invasive skin cancer with the highest risk of death. While it is a serious skin cancer, it is highly curable if detected early. Melanoma diagnosis is difficult, even for experienced dermatologists, due to the wide range of morphologies in skin lesions. Given the rapid development of deep learning algorithms for melanoma diagnosis, it is crucial to validate and benchmark these models, which is the main challenge of this work. This research presents a new benchmarking and selection approach based on the multi-criteria analysis method (MCDM), which integrates entropy and the preference ranking organization method for enrichment of evaluations (PROMETHEE) methods. The experimental study is carried out in four phases. Firstly, 19 convolution neural networks (CNNs) are trained and evaluated on a public dataset of 991 dermoscopic images. Secondly, to obtain the decision matrix, 10 criteria, including accuracy, classification error, precision, sensitivity, specificity, F1-score, false-positive rate, false-negative rate, Matthews correlation coefficient (MCC), and the number of parameters are established. Third, entropy and PROMETHEE methods are integrated to determine the weights of criteria and rank the models. Fourth, the proposed benchmarking framework is validated using the VIKOR method. The obtained results reveal that the ResNet101 model is selected as the optimal diagnosis model for melanoma in our case study data. Thus, the presented benchmarking framework is proven to be useful at exposing the optimal melanoma diagnosis model targeting to ease the selection process of the proper convolutional neural network architecture. [ABSTRACT FROM AUTHOR]

Glaucoma is a group of eye diseases which can cause vision loss by damaging the optic nerve. Early glaucoma detection is key to preventing vision loss yet there is a lack of noticeable early symptoms. Colour fundus photography allows the optic disc (OD) to be examined to diagnose glaucoma. Typically, this is done by measuring the vertical cup-to-disc ratio (CDR); however, glaucoma is characterised by thinning of the rim asymmetrically in the inferior-superior-temporal-nasal regions in increasing order. Automatic delineation of the OD features has potential to improve glaucoma management by allowing for this asymmetry to be considered in the measurements. Here, we propose a new deep-learning-based method to segment the OD and optic cup (OC). The core of the proposed method is DenseNet with a fully-convolutional network, whose symmetric U-shaped architecture allows pixel-wise classification. The predicted OD and OC boundaries are then used to estimate the CDR on two axes for glaucoma diagnosis. We assess the proposed method’s performance using a large retinal colour fundus dataset, outperforming state-of-the-art segmentation methods. Furthermore, we generalise our method to segment four fundus datasets from different devices without further training, outperforming the state-of-the-art on two and achieving comparable results on the remaining two. [ABSTRACT FROM AUTHOR]

This research paper focuses on utilizing Artificial Neural Networks (ANN), Multi-Objective Genetic Algorithm Evolutionary Polynomial Regression (MOGA-EPR), and Gene Expression Programming (GEP) to predict the punching shear strength of Steel Fibre-Reinforced Concrete (SFRC) slabs. In order to formulate predictions, research and analysis were carried out making use of a dataset, this dataset included several parameters that impact on punching shear strength, including SFRC slabs longitudinally and transversely, using ANN, GEP, and MOGA-EPR methods. The developed models exhibited very good performance, as the soft computing techniques (GEP and MOGA-EPR) achieved R ² values of 0.91 to 0.93, while the ANN technique was higher at 0.95. Furthermore, two case studies were incorporated to carry out cost analyses of the models in real-world applications. It was shown that the efficiency of the Machine Learning (ML) models in reducing the costs of materials is relatively high, as they were capable of better predictions than the standard methods employed by the codes. • The proposed system combines soft computing techniques with Machine learning protocols to generate practical punching shear design models. • The three new models offer designers powerful, more precise, straightforward tools for design. • Provide access to accurate predictions of the punching shear strength of SFRC for different design scenarios so engineers can make informed decisions and optimise their designs. [ABSTRACT FROM AUTHOR]

Background: Glaucoma is the leading cause of irreversible blindness worldwide. It is a heterogeneous group of conditions with a common optic neuropathy and associated loss of peripheral vision. Both over and under-diagnosis carry high costs in terms of healthcare spending and preventable blindness. The characteristic clinical feature of glaucoma is asymmetrical optic nerve rim narrowing, which is difficult for humans to quantify reliably. Strategies to improve and automate optic disc assessment are therefore needed to prevent sight loss. Methods: We developed a novel glaucoma detection algorithm that segments and analyses colour photographs to quantify optic nerve rim consistency around the whole disc at 15-degree intervals. This provides a profile of the cup/disc ratio, in contrast to the vertical cup/disc ratio in common use. We introduce a spatial probabilistic model, to account for the optic nerve shape, we then use this model to derive a disc deformation index and a decision rule for glaucoma. We tested our algorithm on two separate image datasets (ORIGA and RIM-ONE). Results: The spatial algorithm accurately distinguished glaucomatous and healthy discs on internal and external validation (AUROC 99.6% and 91.0% respectively). It achieves this using a dataset 100-times smaller than that required for deep learning algorithms, is flexible to the type of cup and disc segmentation (automated or semi-automated), utilises images with missing data, and is correlated with the disc size (p = 0.02) and the rim-to-disc at the narrowest rim (p<0.001, in external validation). Discussion: The spatial probabilistic algorithm is highly accurate, highly data efficient and it extends to any imaging hardware in which the boundaries of cup and disc can be segmented, thus making the algorithm particularly applicable to research into disease mechanisms, and also glaucoma screening in low resource settings. [ABSTRACT FROM AUTHOR]