scholarly journals Deep Learning Models for Automatic Makeup Detection

AI ◽  
2021 ◽  
Vol 2 (4) ◽  
pp. 497-511
Author(s):  
Theiab Alzahrani ◽  
Baidaa Al-Bander ◽  
Waleed Al-Nuaimy
Keyword(s):  
Deep Learning ◽  
Supervised Learning ◽  
Learning Strategies ◽  
Learning Strategy ◽  
Real Life ◽  
Estimation Methods ◽  
Learning Models ◽  
Unlabelled Data ◽  
Area Under Roc Curve ◽  
Computational Intelligence Methods

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 directly 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 comparative 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.

scholarly journals Detection and Recognition of Ultrasound Breast Nodules Based on Semi-supervised deep learning

2020 ◽  
Author(s):  
Yanhua Gao ◽  
Bo Liu ◽  
Yuan Zhu ◽  
Lin Chen ◽  
Miao Tan ◽  
...  
Keyword(s):  
Deep Learning ◽  
Supervised Learning ◽  
Learning Strategies ◽  
Learning Strategy ◽  
Medical Images ◽  
Ultrasound Image ◽  
Ultrasound Images ◽  
Training Strategy ◽  
Supervised Training ◽  
Malignant Breast

AbstractBackgroundThe successful application of deep learning in medical images requires a large amount of annotation data for supervised training. However, massive labeling of medical data is expensive and time consuming. This paper proposes a semi-supervised deep learning method for the detection and classification of benign and malignant breast nodules in ultrasound images, which include two phases.MethodsThe nodule position in the ultrasound image is firstly detected using the faster RCNN network. Second, the recognition network is used to identify the benign and malignant types of nodules. The method in this paper uses a semi-supervised learning strategy, using 800 labeled nodules and 4396 unlabeled nodules.ResultsBased on mean teacher training strategy, the proposed semi-supervised network has obtained excellent results, which is similar to currently used with supervised training networks. On the two test data sets, the AUC of semi-supervised learning and supervised learning were: 93.7% vs 94.2% and 92% vs 92.3%.ConclusionsThe paper proves that semi-supervised learning strategies have good application potential in medical images. Based on a special learning strategy, the result of semi-supervised learning is expected to achieve close or even achieve similar result of supervised deep learning, which only need a small number of labeled samples and a large number of unlabeled samples. It means deep learning analysis of breast lesion will be more feasible and more efficient.

scholarly journals MODEL PEMBELAJARAN TEMATIK INTEGRATIF BERBASIS KURIKULUM 2013 DI MADRASAH IBTIDAIYAH

2020 ◽  
Vol 4 (1) ◽  
pp. 100
Author(s):  
Jefryadi Jefryadi
Keyword(s):  
Learning Strategies ◽  
Learning Strategy ◽  
Field Research ◽  
Learning Model ◽  
Research Field ◽  
Learning Material ◽  
Learning Models ◽  
The Media ◽  
Meaningful Experiences ◽  
Thematic Learning

The 2013 curriculum-based integrative thematic learning model is a learning strategy that involves several subjects into a learning theme that uses an interdisciplinary approach to provide meaningful experiences to students in the learning process. The application of this learning model requires adequate infrastructure and mature teacher understanding concepts. Integration and success in this learning model can be seen from the aspect of understanding of the learning model, aspects of the learning strategy, and aspects of the use of media in learning. Because every teacher has their own characteristics in conveying learning to students, in order to achieve learning objectives. Therefore the writer wants to examine more deeply how the application of the 2013 curriculum-based integrative thematic learning model in MIN Yogyakarta II and MI Ma'had Islamy Kotagede Yogyakarta?. This study aims to determine the mastery of integrative thematic learning models, the strategies applied and the media used by teachers in the application of integrative thematic learning models. This research is categorized in the type of field research (Field Research) which is descriptive with qualitative research methods using theories about integrative thematic learning models then proceed to drawing conclusions. The results showed that in general these two institutions had applied the integrative thematic learning model well. The teacher's mastery of the learning model and the methods used by the teacher in linking learning material are already good so that learning becomes a unified and meaningful whole for students. Then the strategies used by the teacher in planning learning activities, preliminary activities, core activities and closing activities are quite diverse and adjusted to the needs and interests of students. The media used have their respective characteristics and are always adapted to the learning material to be taught. Although they have differences in learning strategies and the media used in teaching, however, they have the same goal of achieving success in teaching so that the expected goals can be achieved and provide meaningful experiences to students.

scholarly journals Qualitative Analysis of Christian Religious Education Teacher Learning Strategies in Online Learning

2021 ◽  
Vol 2 (2) ◽  
pp. 145
Author(s):  
Dian Paskarina ◽  
Ludwig Beethoven Jones Noya ◽  
Pratiwi Eunike ◽  
Bobby Kurnia Putrawan
Keyword(s):  
Online Learning ◽  
Learning Strategies ◽  
Religious Education ◽  
Learning Strategy ◽  
Relevant Literature ◽  
Real Life ◽  
Contextual Learning ◽  
Efficient Manner ◽  
Education Teacher ◽  
The Government

In the era of the Covid-19 pandemic, distance or online learning has become the primary method used by the government, in this case the Ministry of Education and Culture, to prevent the increasing number of Covid-19 viruses and the emergence of clusters in schools. In online learning, PAK teachers in their multifunctional role need to apply contextual learning strategies so that teaching and learning activities can take place in a systematic, directed, unobstructed, effective and efficient manner and can achieve educational targets. Contextual learning is a learning strategy that emphasizes the process of student involvement to achieve goals associated with real-life situations. The method used in this research is descriptive qualitative and data collection is done by interview and documentation as well as relevant literature. The results of the study on some high achieving students' motivation and interest in learning increased with the online learning method after the Christian Religious Education teacher carried out the role optimally by using contextual learning strategies. AbstrakDi era pandemi covid 19 pembelajaran jarak jauh atau daring merupakan metode yang digunakan pemerintah dalam hal ini Kemendikbud sebagai upaya untuk mencegah semakin meningkatnya pandemi covid 19 dan munculnya klaster di sekolah sehingga metode daring menjadi satu-satunya pilihan untuk pembelajaran yang harus dilakukan di era pandemi covid 19. Strategi pembelajaran merupakan garis-garis besar haluan untuk mencapai tujuan pembelajaran. Pada pembelajaran daring maka guru PAK dalam peran multifungsinya perlu menerapkan strategi pembelajaran kontekstual agar kegiatan belajar mengajar dapat berlangsung secara sistematis, terarah, tidak terhambat, efektif dan efisien serta dapat mencapai sasaran. Pembelajaran kontekstual merupakan strategi pembelajaran yang menekankan pada proses keterlibatan siswa untuk mencapai sasaran dihubungkan dengan kondisi situasi kehidupan yang nyata. Metode yang digunakan pada penelitian ini adalah kualitatif deskriptif dengan pendekatan studi kasus. Pengumpulan data dilakukan dengan wawancara serta dokumentasi juga literatur-literatur yang relevan. Hasil penelitian pada beberapa siswa berprestasi motivasi dan minat belajar meningkat dengan metode belajar daring setelah guru Pendidikan Agama Kristen menjalankan peran secara maksimal dengan menggunakan strategi pembelajaran kontekstual.

scholarly journals Stochastic Mechanical Characterization of Polysilicon MEMS: A Deep Learning Approach

Proceedings ◽  
2019 ◽  
Vol 42 (1) ◽  
pp. 8
Author(s):  
José Pablo Quesada Molina ◽  
Luca Rosafalco ◽  
Stefano Mariani
Keyword(s):  
Deep Learning ◽  
Learning Strategies ◽  
Mechanical Response ◽  
Learning Strategy ◽  
Monte Carlo Analysis ◽  
Small Samples ◽  
Micro Electro Mechanical Systems ◽  
Polysilicon Film ◽  
Polysilicon Films

Deep Learning strategies recently emerged as powerful tools for the characterization of heterogeneous materials. In this work, we discuss an approach for the characterization of the mechanical response of polysilicon films that typically constitute the movable structures of micro-electro-mechanical systems (MEMS). A dataset of microstructures is digitally generated and a neural network is trained to provide the appropriate scattering in the values of the overall stiffness (in terms of the Young’s modulus) of the grain aggregate. Since results are framed within a stochastic procedure, the aim of the learning strategy is not to accurately reproduce the microstructure-informed response of the polysilicon film, but instead to provide a fast tool to be used at the device level for Monte Carlo analysis of the relevant performance indices. Accuracy of the proposed approach is assessed for very small samples of the polycrystalline aggregate to check if size effects are correctly captured.

scholarly journals An Investigation of Deep Learning Models for EEG-Based Emotion Recognition

2020 ◽  
Vol 14 ◽  
Author(s):  
Yaqing Zhang ◽  
Jinling Chen ◽  
Jen Hong Tan ◽  
Yuxuan Chen ◽  
Yunyi Chen ◽  
...  
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Deep Learning ◽  
Emotion Recognition ◽  
Real Life ◽  
Learning Rate ◽  
Learning Models ◽  
Learning Methods ◽  
Time Frequency ◽  
Comparison Results

Emotion is the human brain reacting to objective things. In real life, human emotions are complex and changeable, so research into emotion recognition is of great significance in real life applications. Recently, many deep learning and machine learning methods have been widely applied in emotion recognition based on EEG signals. However, the traditional machine learning method has a major disadvantage in that the feature extraction process is usually cumbersome, which relies heavily on human experts. Then, end-to-end deep learning methods emerged as an effective method to address this disadvantage with the help of raw signal features and time-frequency spectrums. Here, we investigated the application of several deep learning models to the research field of EEG-based emotion recognition, including deep neural networks (DNN), convolutional neural networks (CNN), long short-term memory (LSTM), and a hybrid model of CNN and LSTM (CNN-LSTM). The experiments were carried on the well-known DEAP dataset. Experimental results show that the CNN and CNN-LSTM models had high classification performance in EEG-based emotion recognition, and their accurate extraction rate of RAW data reached 90.12 and 94.17%, respectively. The performance of the DNN model was not as accurate as other models, but the training speed was fast. The LSTM model was not as stable as the CNN and CNN-LSTM models. Moreover, with the same number of parameters, the training speed of the LSTM was much slower and it was difficult to achieve convergence. Additional parameter comparison experiments with other models, including epoch, learning rate, and dropout probability, were also conducted in the paper. Comparison results prove that the DNN model converged to optimal with fewer epochs and a higher learning rate. In contrast, the CNN model needed more epochs to learn. As for dropout probability, reducing the parameters by ~50% each time was appropriate.

scholarly journals A Deep Learning Algorithm for the Max-Cut Problem Based on Pointer Network Structure with Supervised Learning and Reinforcement Learning Strategies

Mathematics ◽  
2020 ◽  
Vol 8 (2) ◽  
pp. 298 ◽  
Author(s):  
Shenshen Gu ◽  
Yue Yang
Keyword(s):  
Neural Network ◽  
Deep Learning ◽  
Reinforcement Learning ◽  
Combinatorial Optimization ◽  
Supervised Learning ◽  
Learning Strategies ◽  
Large Scale ◽  
Deep Neural Network ◽  
Max Cut Problem ◽  
Cut Problems

The Max-cut problem is a well-known combinatorial optimization problem, which has many real-world applications. However, the problem has been proven to be non-deterministic polynomial-hard (NP-hard), which means that exact solution algorithms are not suitable for large-scale situations, as it is too time-consuming to obtain a solution. Therefore, designing heuristic algorithms is a promising but challenging direction to effectively solve large-scale Max-cut problems. For this reason, we propose a unique method which combines a pointer network and two deep learning strategies (supervised learning and reinforcement learning) in this paper, in order to address this challenge. A pointer network is a sequence-to-sequence deep neural network, which can extract data features in a purely data-driven way to discover the hidden laws behind data. Combining the characteristics of the Max-cut problem, we designed the input and output mechanisms of the pointer network model, and we used supervised learning and reinforcement learning to train the model to evaluate the model performance. Through experiments, we illustrated that our model can be well applied to solve large-scale Max-cut problems. Our experimental results also revealed that the new method will further encourage broader exploration of deep neural network for large-scale combinatorial optimization problems.

MODIFIKASI MODEL PEMBELAJARAN MIND MAPPING DENGAN STRATEGI PEMBELAJARAN TUGAS DAN PAKSA

2019 ◽  
Vol 2 ◽  
Author(s):  
Dini Yuliani ◽  
Mutiara Bhayangkari ◽  
Maria Ulfah
Keyword(s):  
Learning Strategies ◽  
Learning Process ◽  
Intellectual Development ◽  
Learning Strategy ◽  
Student Discipline ◽  
Learning Models ◽  
Mind Mapping ◽  
The Right ◽  
Selection Of

This writing aims to improve students' understanding by modifying learning models with appropriate learning strategies that are considered based on the characteristics and intellectual development of students to improve learning outcomes. The learning process in Indonesia is currently still centered on teachers which causes students' memory and understanding to be still low. This is the background for the purpose of mind mapping learning models, namely making patterned visual and graphical subject matter that can help strengthen and recall information that has been studied. The selection of the right learning strategy can improve the results that will be obtained from the application of learning models in the classroom. Forced and forced learning strategies are chosen to complement and perfect the implementation of mind mapping learning models in the classroom. This strategy aims to train students' independence and discipline in learning through assignments given with clear time limits and strict penalties if there are students not completing their assignments properly. The combination of mind mapping learning models with forced and task learning strategies can be an alternative to improve the quality of learning in schools. With the increase in thinking power accompanied by student discipline in learning, the learning process in the classroom will run well and get maximum results so that the objectives of the learning can be achieved. For educators it is recommended to implement mind mapping learning models with forced and forced learning strategies in schools, so that learning objectives can be achieved optimally.

KNN Loss and Deep KNN

2021 ◽  
Vol 182 (2) ◽  
pp. 95-110
Author(s):  
Linh Le ◽  
Ying Xie ◽  
Vijay V. Raghavan
Keyword(s):  
Deep Learning ◽  
Supervised Learning ◽  
Nearest Neighbor ◽  
Learning Strategy ◽  
Feature Space ◽  
Kernel Functions ◽  
Training Data ◽  
K Nearest Neighbor ◽  
Map Data

The k Nearest Neighbor (KNN) algorithm has been widely applied in various supervised learning tasks due to its simplicity and effectiveness. However, the quality of KNN decision making is directly affected by the quality of the neighborhoods in the modeling space. Efforts have been made to map data to a better feature space either implicitly with kernel functions, or explicitly through learning linear or nonlinear transformations. However, all these methods use pre-determined distance or similarity functions, which may limit their learning capacity. In this paper, we present two loss functions, namely KNN Loss and Fuzzy KNN Loss, to quantify the quality of neighborhoods formed by KNN with respect to supervised learning, such that minimizing the loss function on the training data leads to maximizing KNN decision accuracy on the training data. We further present a deep learning strategy that is able to learn, by minimizing KNN loss, pairwise similarities of data that implicitly maps data to a feature space where the quality of KNN neighborhoods is optimized. Experimental results show that this deep learning strategy (denoted as Deep KNN) outperforms state-of-the-art supervised learning methods on multiple benchmark data sets.

scholarly journals Generalization of spatio-temporal deep learning for vision-based force estimation

2020 ◽  
Vol 6 (1) ◽  
Author(s):  
Finn Behrendt ◽  
Nils Gessert ◽  
Alexander Schlaefer
Keyword(s):  
Deep Learning ◽  
Force Feedback ◽  
Haptic Feedback ◽  
Absolute Error ◽  
Estimation Methods ◽  
Temporal Data ◽  
Learning Models ◽  
Force Estimation ◽  
Tissue Samples ◽  
Spatio Temporal

AbstractRobot-assisted minimally-invasive surgery is increasingly used in clinical practice. Force feedback offers potential to develop haptic feedback for surgery systems. Forces can be estimated in a vision-based way by capturing deformation observed in 2D-image sequences with deep learning models. Variations in tissue appearance and mechanical properties likely influence force estimation methods’ generalization. In this work, we study the generalization capabilities of different spatial and spatio-temporal deep learning methods across different tissue samples. We acquire several data-sets using a clinical laparoscope and use both purely spatial and also spatio-temporal deep learning models. The results of this work show that generalization across different tissues is challenging. Nevertheless, we demonstrate that using spatio-temporal data instead of individual frames is valuable for force estimation. In particular, processing spatial and temporal data separately by a combination of a ResNet and GRU architecture shows promising results with a mean absolute error of 15.450 compared to 19.744 mN of a purely spatial CNN.

Sign in / Sign up

Export Citation Format

Share Document