Age Estimation from Facial Images using Transfer Learning and K-fold Cross-Validation

The animal classification system is a technology to classify the animal class (type) automatically and useful in many applications. There are many types of learning models applied to this technology recently. Nonetheless, it is worth noting that the extraction of the features and the classification of the animal features is non-trivial, particularly in the deep learning approach for a successful animal classification system. The use of Transfer Learning (TL) has been demonstrated to be a powerful tool in the extraction of essential features. However, the employment of such a method towards animal classification applications are somewhat limited. The present study aims to determine a suitable TL-conventional classifier pipeline for animal classification. The VGG16 and VGG19 were used in extracting features and then coupled with either k-Nearest Neighbour (k-NN) or Support Vector Machine (SVM) classifier. Prior to that, a total of 4000 images were gathered consisting of a total of five classes which are cows, goats, buffalos, dogs, and cats. The data was split into the ratio of 80:20 for train and test. The classifiers hyper parameters are tuned by the Grids Search approach that utilises the five-fold cross-validation technique. It was demonstrated from the study that the best TL pipeline identified is the VGG16 along with an optimised SVM, as it was able to yield an average classification accuracy of 0.975. The findings of the present investigation could facilitate animal classification application, i.e. for monitoring animals in wildlife.

Download Full-text

Transfer-to-Transfer Learning Approach for Computer Aided Detection of COVID-19 in Chest Radiographs

AI ◽

10.3390/ai1040032 ◽

2020 ◽

Vol 1 (4) ◽

pp. 539-557 ◽

Cited By ~ 1

Author(s):

Barath Narayanan ◽

Russell Hardie ◽

Vignesh Krishnaraja ◽

Christina Karam ◽

Venkata Davuluru

Keyword(s):

Transfer Learning ◽

Cross Validation ◽

Class Imbalance ◽

Chest Radiographs ◽

Training Dataset ◽

Learning Approach ◽

Computer Aided Detection ◽

Computer Aided ◽

Fold Cross Validation ◽

Validation Experiments

The coronavirus disease 2019 (COVID-19) global pandemic has severely impacted lives across the globe. Respiratory disorders in COVID-19 patients are caused by lung opacities similar to viral pneumonia. A Computer-Aided Detection (CAD) system for the detection of COVID-19 using chest radiographs would provide a second opinion for radiologists. For this research, we utilize publicly available datasets that have been marked by radiologists into two-classes (COVID-19 and non-COVID-19). We address the class imbalance problem associated with the training dataset by proposing a novel transfer-to-transfer learning approach, where we break a highly imbalanced training dataset into a group of balanced mini-sets and apply transfer learning between these. We demonstrate the efficacy of the method using well-established deep convolutional neural networks. Our proposed training mechanism is more robust to limited training data and class imbalance. We study the performance of our algorithm(s) based on 10-fold cross validation and two hold-out validation experiments to demonstrate its efficacy. We achieved an overall sensitivity of 0.94 for the hold-out validation experiments containing 2265 and 2139 marked as COVID-19 chest radiographs, respectively. For the 10-fold cross validation experiment, we achieve an overall Area under the Receiver Operating Characteristic curve (AUC) value of 0.996 for COVID-19 detection. This paper serves as a proof-of-concept that an automated detection approach can be developed with a limited set of COVID-19 images, and in areas with scarcity of trained radiologists.

Download Full-text

Adolescent age estimation using voice features

Biomedical Engineering / Biomedizinische Technik ◽

10.1515/bmt-2018-0082 ◽

2020 ◽

Vol 65 (4) ◽

pp. 429-434

Author(s):

Marcin D. Bugdol ◽

Monika N. Bugdol ◽

Maria J. Bieńkowska ◽

Anna Lipowicz ◽

Agata M. Wijata ◽

...

Keyword(s):

Age Estimation ◽

Cross Validation ◽

Rapid Development ◽

Absolute Error ◽

Regression Method ◽

Chronological Age ◽

Height Measurement ◽

Voice Signal ◽

Selection Operator ◽

Fold Cross Validation

AbstractIn this paper, a method for evaluating the chronological age of adolescents on the basis of their voice signal is presented. For every examined child, the vowels a, e, i, o and u were recorded in extended phonation. Sixty voice parameters were extracted from each recording. Voice recordings were supplemented with height measurement in order to check if it could improve the accuracy of the proposed solution. Predictor selection was performed using the LASSO (least absolute shrinkage and selection operator) algorithm. For age estimation, the random forest (RF) for regression method was employed and it was tested using a 10-fold cross-validation. The lowest absolute error (0.37 year ± 0.28) was obtained for boys only when all selected features were included into prediction. In all cases, the achieved accuracy was higher for boys than for girls, which results from the fact that the change of voice with age is larger for men than for women. The achieved results suggest that the presented approach can be employed for accurate age estimation during rapid development in children.

Download Full-text

Deep Neural Networks with Transfer Learning Model for Brain Tumors Classification

Traitement du signal ◽

10.18280/ts.370407 ◽

2020 ◽

Vol 37 (4) ◽

pp. 593-601

Author(s):

Premamayudu Bulla ◽

Lakshmipathi Anantha ◽

Subbarao Peram

Keyword(s):

Neural Networks ◽

Brain Tumors ◽

Mr Imaging ◽

Transfer Learning ◽

Deep Neural Networks ◽

Cross Validation ◽

Mr Images ◽

Patient Level ◽

Group 10 ◽

Fold Cross Validation

To investigate the effect of deep neural networks with transfer learning on MR images for tumor classification and improve the classification metrics by building image-level, stratified image-level, and patient-level models. Three thousand sixty-four T1-weighted magnetic resonance (MR) imaging from two hundred thirty-three patient cases of three brain tumors types (meningioma, glioma, and pituitary) were collected and it includes coronal, sagittal and axial views. The average number of brain images of each patient in three views is fourteen in the collected dataset. The classification is performed in a model of cross-trained with a pre-trained InceptionV3 model. Three image-level and one patient-level models are built on the MR imaging dataset. The models are evaluated in classification metrics such as accuracy, loss, precision, recall, kappa, and AUC. The proposed models are validated using four approaches: holdout validation, 10-fold cross-validation, stratified 10-fold cross-validation, and group 10-fold cross-validation. The generalization capability and improvement of the network are tested by using cropped and uncropped images of the dataset. The best results for group 10-fold cross-validation (patient-level) are obtained on the used dataset (ACC=99.82). A deep neural network with transfer learning can be used to classify brain tumors from MR images. Our patient-level network model noted the best results in classification to improve accuracy.

Download Full-text

Combination of Support Vector Machine and K-Fold cross-validation for prediction of long-term degradation of the compressive strength of marine concrete

International Journal of Computational Physics Series ◽

10.29167/a1i1p120-130 ◽

2018 ◽

Vol 1 (1) ◽

pp. 120-130 ◽

Cited By ~ 1

Author(s):

Chunxiang Qian ◽

Wence Kang ◽

Hao Ling ◽

Hua Dong ◽

Chengyao Liang ◽

...

Keyword(s):

Support Vector Machine ◽

Environmental Factors ◽

Cross Validation ◽

Concrete Strength ◽

Simulation Method ◽

Support Vector ◽

Svm Model ◽

Artificial Neural Network Ann ◽

Influence Degree ◽

Fold Cross Validation

Support Vector Machine (SVM) model optimized by K-Fold cross-validation was built to predict and evaluate the degradation of concrete strength in a complicated marine environment. Meanwhile, several mathematical models, such as Artificial Neural Network (ANN) and Decision Tree (DT), were also built and compared with SVM to determine which one could make the most accurate predictions. The material factors and environmental factors that influence the results were considered. The materials factors mainly involved the original concrete strength, the amount of cement replaced by fly ash and slag. The environmental factors consisted of the concentration of Mg2+, SO42-, Cl-, temperature and exposing time. It was concluded from the prediction results that the optimized SVM model appeared to perform better than other models in predicting the concrete strength. Based on SVM model, a simulation method of variables limitation was used to determine the sensitivity of various factors and the influence degree of these factors on the degradation of concrete strength.

Download Full-text

Rancang Bangun Sistem Informasi Untuk Menentukan Kapabilitas Konsumen Dalam Mengambil Pinjaman KPR

Jurnal ULTIMA InfoSys ◽

10.31937/si.v7i2.543 ◽

2016 ◽

Vol 7 (2) ◽

pp. 75-80

Author(s):

Adhi Kusnadi ◽

Risyad Ananda Putra

Keyword(s):

Data Mining ◽

Low Income ◽

Cross Validation ◽

Classification Tree ◽

Large Population ◽

Housing Development ◽

Good Precision ◽

Index Terms ◽

The Government ◽

Fold Cross Validation

Indonesia is one country that has a relatively large population . The government in the period of 5 years, annually hold a procurement program 1 million FLPP house units. This program is held in an effort to provide a decent home for low income people. FLPP housing development requires good precision and speed of development on the part of the developer, this is often hampered by the bank process, because it is difficult to predict the results and speed of data processing in the bank. Knowing the ability of consumers to get subsidized credit, has many advantages, among others, developers can plan a better cash flow, and developers can replace consumers who will be rejected before entering the bank process. For that reason built a system that can help developers. There are many methods that can be used to create this application. One of them is data mining with Classification tree. The results of 10-fold-cross-validation applications have an accuracy of 92%. Index Terms-Data Mining, Classification Tree, Housing, FLPP, 10-fold-cross Validation, Consumer Capability

Download Full-text

Klasifikasi Berita Kriminal Menggunakan NaÃ¯ve Bayes Classifier (NBC) dengan Pengujian K-Fold Cross Validation

Jurnal Sains dan Informatika ◽

10.34128/jsi.v5i2.177 ◽

2019 ◽

Vol 5 (2) ◽

pp. 108-117

Author(s):

Herfia Rhomadhona ◽

Jaka Permadi

Keyword(s):

Cross Validation ◽

Online Media ◽

Bayes Classifier ◽

Ve Bayes ◽

Fold Cross Validation

Berita kriminalitas merupakan berita yang selalu menjadi trending topik di setiap media massa, khususnya media massa online. Media massa online terlah menyediakan beberapa fasilitas untuk mempermudah masyarakan dalam mencari sebuah berita berdasarkan topik. Media massa online melabeli suatu berita berdasarkan kategorinya. Namun, media massa online tidak memberikan sub kategori pada berita tersebut. Sebagai contoh jika seorang pengguna membuka kategori kriminal, maka yang ditampilkan adalah semua jenis berita kriminal tanpa memberikan informasi yang spesifik dari jenis kriminalitasnya. Permasalahan tersebut dapat diatasi dengan mengklasifikasikan berita kriminalitas berdasarkan subkategori. Penelitian ini menggunakan metode NaÃ¯ve Bayes Classifier (NBC) untuk mengklasifikasi berita berdasarkan sub kategorinya. Adapun subkategori terbagi kedalam 5 kategori yaitu korupsi, narkoba, pencurian, pemerkosaan dan pembunuhan. Penelitian ini bertujuan untuk mengetahui kemampuan NBC dalam mengklasifikasi berita dengan melakukan pengujian menggunakan teknik K-Fold Cross Validation dengan nilai K dari 3 sampai 10. Hasil pengujian menyatakan bahwa NBC memiliki kemampuan dalam klasifikasi berita kriminal dengan nilai precision sebesar 98,53 %, nilai recall sebesar 98,44 % dan nilai accuracy sebesar 99,38 %.

Download Full-text

Prediction of K562 Cells Functional Inhibitors Based on Machine Learning Approaches

Current Pharmaceutical Design ◽

10.2174/1381612825666191107092214 ◽

2020 ◽

Vol 25 (40) ◽

pp. 4296-4302 ◽

Cited By ~ 2

Author(s):

Yuan Zhang ◽

Zhenyan Han ◽

Qian Gao ◽

Xiaoyi Bai ◽

Chi Zhang ◽

...

Keyword(s):

Machine Learning ◽

Inclusion Bodies ◽

Cross Validation ◽

Independent Set ◽

K562 Cells ◽

Machine Learning Algorithms ◽

Learning Approaches ◽

Validation Test ◽

Excess Number ◽

Fold Cross Validation

Background: β thalassemia is a common monogenic genetic disease that is very harmful to human health. The disease arises is due to the deletion of or defects in β-globin, which reduces synthesis of the β-globin chain, resulting in a relatively excess number of α-chains. The formation of inclusion bodies deposited on the cell membrane causes a decrease in the ability of red blood cells to deform and a group of hereditary haemolytic diseases caused by massive destruction in the spleen. Methods: In this work, machine learning algorithms were employed to build a prediction model for inhibitors against K562 based on 117 inhibitors and 190 non-inhibitors. Results: The overall accuracy (ACC) of a 10-fold cross-validation test and an independent set test using Adaboost were 83.1% and 78.0%, respectively, surpassing Bayes Net, Random Forest, Random Tree, C4.5, SVM, KNN and Bagging. Conclusion: This study indicated that Adaboost could be applied to build a learning model in the prediction of inhibitors against K526 cells.

Download Full-text

Environmental Sensitivity and Awareness as Differentiating Factors in the Purchase Decision-Making Process in the Smartphone Industry—Case of Polish Consumers

Sustainability ◽

10.3390/su13010348 ◽

2021 ◽

Vol 13 (1) ◽

pp. 348

Author(s):

Lukasz Skowron ◽

Monika Sak-Skowron

Keyword(s):

Expectation Maximization ◽

Cross Validation ◽

Expectation Maximization Algorithm ◽

Decision Making Process ◽

Environmental Sensitivity ◽

Significance Level ◽

On Line ◽

Purchase Process ◽

The Impact ◽

Fold Cross Validation

The first of the research objectives discussed in this article was to analyze the differences related to the valuation of particular factors influencing the purchase process in the smartphone industry, expressed by respondents with different sensitivity and environmental awareness, as well as the assessment of their knowledge about the impact of smartphones on the natural environment. The second objective of the research was to determine whether the level of environmental sensitivity, awareness and knowledge about the impact of smartphones on the environment has a statistically significant influence on the respondents’ choice of smartphone brand. The survey was conducted using an on-line questionnaire, distributed by a specialized research agency on a representative sample of over 1000 Polish residents. In order to identify the various customers clusters, the expectation-maximization algorithm and the v-fold cross-validation were used. Additionally, in order to analyze the significance level of differences between clusters the nonparametric Mann-Whitney U-test was carried out. The results show unequivocally that people with a different approach to ecological issues demonstrate statistically significant differences in their purchasing behaviors in the smartphone industry. Furthermore, it was noticed that in the case of comparing some smartphones brands, there is a statistically confirmed difference in the environmental sensitivity and awareness of the customers who use them. Moreover, the research has shown that in Polish customers’ consciousness smartphones are mistakenly considered to be relatively safe and environmentally friendly products.

Download Full-text