scholarly journals Evaluating classification accuracy for modern learning approaches

2019 ◽  
Vol 38 (13) ◽  
pp. 2477-2503 ◽  
Author(s):  
Jialiang Li ◽  
Ming Gao ◽  
Ralph D'Agostino
Keyword(s):  
Classification Accuracy ◽  
Learning Approaches ◽  
Modern Learning

scholarly journals Insights into few shot learning approaches for image scene classification

2021 ◽  
Vol 7 ◽  
pp. e666
Author(s):  
Mohamed Soudy ◽  
Yasmine Afify ◽  
Nagwa Badr
Keyword(s):  
Classification Accuracy ◽  
Large Data ◽  
Image Understanding ◽  
Research Area ◽  
Optimal Performance ◽  
Learning Approaches ◽  
Learning Models ◽  
Scene Classification ◽  
Training Set ◽  
Machine Learning Models

Image understanding and scene classification are keystone tasks in computer vision. The development of technologies and profusion of existing datasets open a wide room for improvement in the image classification and recognition research area. Notwithstanding the optimal performance of exiting machine learning models in image understanding and scene classification, there are still obstacles to overcome. All models are data-dependent that can only classify samples close to the training set. Moreover, these models require large data for training and learning. The first problem is solved by few-shot learning, which achieves optimal performance in object detection and classification but with a lack of eligible attention in the scene classification task. Motivated by these findings, in this paper, we introduce two models for few-shot learning in scene classification. In order to trace the behavior of those models, we also introduce two datasets (MiniSun; MiniPlaces) for image scene classification. Experimental results show that the proposed models outperform the benchmark approaches in respect of classification accuracy.

scholarly journals Towards an intelligent blended system of learning activities model for New Zealand institutions: an investigative approach

2021 ◽  
Vol 8 (1) ◽  
Author(s):  
Amr Adel ◽  
Joshua Dayan
Keyword(s):  
New Zealand ◽  
Blended Learning ◽  
Teaching Style ◽  
Educational Institution ◽  
Human Interaction ◽  
Learning Activities ◽  
Traditional Learning ◽  
Learning Approaches ◽  
Learning Models ◽  
Modern Learning

AbstractCOVID-19 has accelerated the uptake of blended learning approaches all over the world. The need to restrict human interaction to reduce the possibility of infection has led to a full lockdown of all educational institutions. Blended learning is a new teaching style combining traditional and modern learning models, where the digital methods of teaching students do not completely replace the ways in which the traditional teachers used to interact with and teach the students. However, there are several challenges associated with the understanding of blended learning models and their implementation in an educational institution. With the development of these blended learning models, there have also been several challenges associated with the different ways of accepting the learning models and using them in combination. This is why this paper proposes a design for a system of blended learning activities that would provide students with a total learning model, which has not replaced the traditional learning models but has successfully utilized digital technologies and blended them with traditional learning. Therefore, they can be used along with the old way of teaching a student, evaluating how the student is performing and also how the staff are performing as teachers. This paper focuses on the development of this model for students in New Zealand.

scholarly journals A High-Accuracy Model Average Ensemble of Convolutional Neural Networks for Classification of Cloud Image Patches on Small Datasets

2019 ◽  
Vol 9 (21) ◽  
pp. 4500 ◽  
Author(s):  
Phung ◽  
Rhee
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Classification Accuracy ◽  
Complete Solution ◽  
Large Data ◽  
High Accuracy ◽  
Learning Approaches ◽  
Model Average ◽  
Image Patches

Research on clouds has an enormous influence on sky sciences and related applications, and cloud classification plays an essential role in it. Much research has been conducted which includes both traditional machine learning approaches and deep learning approaches. Compared with traditional machine learning approaches, deep learning approaches achieved better results. However, most deep learning models need large data to train due to the large number of parameters. Therefore, they cannot get high accuracy in case of small datasets. In this paper, we propose a complete solution for high accuracy of classification of cloud image patches on small datasets. Firstly, we designed a suitable convolutional neural network (CNN) model for small datasets. Secondly, we applied regularization techniques to increase generalization and avoid overfitting of the model. Finally, we introduce a model average ensemble to reduce the variance of prediction and increase the classification accuracy. We experiment the proposed solution on the Singapore whole-sky imaging categories (SWIMCAT) dataset, which demonstrates perfect classification accuracy for most classes and confirms the robustness of the proposed model.

scholarly journals Calibrating Wrist-Worn Accelerometers for Physical Activity Assessment in Preschoolers: Machine Learning Approaches (Preprint)

2019 ◽  
Author(s):  
Shiyu Li ◽  
Jeffrey T Howard ◽  
Erica T Sosa ◽  
Alberto Cordova ◽  
Deborah Parra-Medina ◽  
...  
Keyword(s):  
Physical Activity ◽  
Machine Learning ◽  
Cluster Analysis ◽  
Sedentary Behavior ◽  
Classification Accuracy ◽  
Characteristic Curve ◽  
Learning Approaches ◽  
Cut Points ◽  
Activity Intensity ◽  
Vector Magnitude

BACKGROUND Physical activity (PA) level is associated with multiple health benefits during early childhood. However, inconsistency in the methods for quantification of PA levels among preschoolers remains a problem. OBJECTIVE This study aimed to develop PA intensity cut points for wrist-worn accelerometers by using machine learning (ML) approaches to assess PA in preschoolers. METHODS Wrist- and hip-derived acceleration data were collected simultaneously from 34 preschoolers on 3 consecutive preschool days. Two supervised ML models, receiver operating characteristic curve (ROC) and ordinal logistic regression (OLR), and one unsupervised ML model, k-means cluster analysis, were applied to establish wrist-worn accelerometer vector magnitude (VM) cut points to classify accelerometer counts into sedentary behavior, light PA (LPA), moderate PA (MPA), and vigorous PA (VPA). Physical activity intensity levels identified by hip-worn accelerometer VM cut points were used as reference to train the supervised ML models. Vector magnitude counts were classified by intensity based on three newly established wrist methods and the hip reference to examine classification accuracy. Daily estimates of PA were compared to the hip-reference criterion. RESULTS In total, 3600 epochs with matched hip- and wrist-worn accelerometer VM counts were analyzed. All ML approaches performed differently on developing PA intensity cut points for wrist-worn accelerometers. Among the three ML models, k-means cluster analysis derived the following cut points: ≤2556 counts per minute (cpm) for sedentary behavior, 2557-7064 cpm for LPA, 7065-14532 cpm for MPA, and ≥14533 cpm for VPA; in addition, k-means cluster analysis had the highest classification accuracy, with more than 70% of the total epochs being classified into the correct PA categories, as examined by the hip reference. Additionally, k-means cut points exhibited the most accurate estimates on sedentary behavior, LPA, and VPA as the hip reference. None of the three wrist methods were able to accurately assess MPA. CONCLUSIONS This study demonstrates the potential of ML approaches in establishing cut points for wrist-worn accelerometers to assess PA in preschoolers. However, the findings from this study warrant additional validation studies.

scholarly journals Multi-Keyword Classification: A Case Study in Finnish Social Sciences Data Archive

Information ◽  
2021 ◽  
Vol 12 (12) ◽  
pp. 491
Author(s):  
Erjon Skenderi ◽  
Jukka Huhtamäki ◽  
Kostas Stefanidis
Keyword(s):  
Social Science ◽  
Classification Accuracy ◽  
Human Error ◽  
Learning Approaches ◽  
Text Representation ◽  
Nearest Neighbours ◽  
Ranking Performance ◽  
Ranking Score ◽  
Science Domain ◽  
Representation Techniques

In this paper, we consider the task of assigning relevant labels to studies in the social science domain. Manual labelling is an expensive process and prone to human error. Various multi-label text classification machine learning approaches have been proposed to resolve this problem. We introduce a dataset obtained from the Finnish Social Science Archive and comprised of 2968 research studies’ metadata. The metadata of each study includes attributes, such as the “abstract” and the “set of labels”. We used the Bag of Words (BoW), TF-IDF term weighting and pretrained word embeddings obtained from FastText and BERT models to generate the text representations for each study’s abstract field. Our selection of multi-label classification methods includes a Naive approach, Multi-label k Nearest Neighbours (ML-kNN), Multi-Label Random Forest (ML-RF), X-BERT and Parabel. The methods were combined with the text representation techniques and their performance was evaluated on our dataset. We measured the classification accuracy of the combinations using Precision, Recall and F1 metrics. In addition, we used the Normalized Discounted Cumulative Gain to measure the label ranking performance of the selected methods combined with the text representation techniques. The results showed that the ML-RF model achieved a higher classification accuracy with the TF-IDF features and, based on the ranking score, the Parabel model outperformed the other methods.

scholarly journals Artifacts in EEG-Based BCI Therapies: Friend or Foe?

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 96
Author(s):  
Eric James McDermott ◽  
Philipp Raggam ◽  
Sven Kirsch ◽  
Paolo Belardinelli ◽  
Ulf Ziemann ◽  
...  
Keyword(s):  
Classification Accuracy ◽  
Therapeutic Potential ◽  
Brain Activity ◽  
Mental States ◽  
Extraction Methods ◽  
Brain State ◽  
Learning Approaches ◽  
Eeg Signal ◽  
Motor Tasks ◽  
Brain States

EEG-based brain–computer interfaces (BCI) have promising therapeutic potential beyond traditional neurofeedback training, such as enabling personalized and optimized virtual reality (VR) neurorehabilitation paradigms where the timing and parameters of the visual experience is synchronized with specific brain states. While BCI algorithms are often designed to focus on whichever portion of a signal is most informative, in these brain-state-synchronized applications, it is of critical importance that the resulting decoder is sensitive to physiological brain activity representative of various mental states, and not to artifacts, such as those arising from naturalistic movements. In this study, we compare the relative classification accuracy with which different motor tasks can be decoded from both extracted brain activity and artifacts contained in the EEG signal. EEG data were collected from 17 chronic stroke patients while performing six different head, hand, and arm movements in a realistic VR-based neurorehabilitation paradigm. Results show that the artifactual component of the EEG signal is significantly more informative than brain activity with respect to classification accuracy. This finding is consistent across different feature extraction methods and classification pipelines. While informative brain signals can be recovered with suitable cleaning procedures, we recommend that features should not be designed solely to maximize classification accuracy, as this could select for remaining artifactual components. We also propose the use of machine learning approaches that are interpretable to verify that classification is driven by physiological brain states. In summary, whereas informative artifacts are a helpful friend in BCI-based communication applications, they can be a problematic foe in the estimation of physiological brain states.

scholarly journals The flipped classes and educatıon ınformatıon network (EIN)Ters yüz edilmiş sınıflar ve eğitim bilişim ağı (EBA)

2016 ◽  
Vol 13 (2) ◽  
pp. 3373 ◽  
Author(s):  
Yavuz Bolat
Keyword(s):  
Literature Review ◽  
Learning Environment ◽  
Information Network ◽  
Learning Approaches ◽  
Important Place ◽  
Learner Centered ◽  
Modern Learning ◽  
Flipped Classrooms ◽  
Research In Education ◽  
Technological Improvements

Learner centered activities take an important place in modern learning approaches. These activities are both setting the student to work and increasing the teacher’s guiding properties in learning environment. Moreover the classes which have classically learning environment turn into training workshops. Reflection of technological improvements to education have an important place for being this approach is successful. In the reversed classes which have learner centered, there are accessorily used computer, printer, internet and internet based networks for providing students self-access. In Turkey, Education Information Network (EIN) which is developed by MEB contributes high for this issue to educators and students. But, there is a lack of knowledge in educators about filipped classrooms. And therefore, this research is that flipped classrooms and flipped learning on information while Education Information Network (EBA) provides location-based usage. This study is a qualitative research in education based on literature review. In this study was conducted literature review with the help of keywords. Sources achieved by this method was used to support the research and concluded. ÖzetModern öğrenme yaklaşımlarında öğrenen merkezli eğitim faaliyetleri önemli bir yer tutmaktadır. Bu faaliyetler öğrenciyi aktif olarak işe koştuğu gibi öğretmenin öğrenme ortamındaki rehberlik etme özelliklerini artırmaktadır. Ayrıca klasik anlamda öğrenme ortamı olan sınıflar, eğitim atölyesine dönüşmektedir. Bu yaklaşımın başarılı olabilmesinde ise teknolojik gelişmelerin eğitim alanına yansımaları önemli bir yer tutmaktadır. Öğrenen merkezli anlayışa sahip ters yüz edilmiş sınıflarda öğrencinin bireysel öğrenmesini sağlamak için; bilgisayar, yazıcı, internet ve internet tabanlı ağlar yardımcı olarak kullanılmaktadır. Türkiye’de MEB tarafından geliştirilen Eğitim Bilişim Ağı (EBA) bu konuda eğitimcilere ve öğrencilere önemli katkılar sağlamaktadır. Ancak ters yüz edilmiş sınıflar ve ters yüz öğrenme hakkında eğitimcilerde bir bilgi eksikliği bulunmaktadır. Bu nedenle bu araştırma ters yüz öğrenme ve ters yüz sınıflar hakkında bilgi vermeyi amaçlarken ters yüz edilmiş sınıfların Eğitim Bilişim Ağı (EBA) tabanlı kullanımına yer vermektedir.  Literatür taramasına dayanan nitel bir eğitim araştırması olan bu çalışmada anahtar kelime yardımıyla literatür taraması yapılmıştır. Bu yöntemle ulaşılan kaynaklar, araştırmanın desteklenmesi ve sonuca ulaşmasında kullanılmıştır.

scholarly journals Advocacy Learning: Learning through Competition and Class-Conditional Representations

2019 ◽  
Author(s):  
Ian Fox ◽  
Jenna Wiens
Keyword(s):  
Classification Accuracy ◽  
Learning Approaches ◽  
Classification Problems ◽  
Class Label ◽  
Discriminative Performance ◽  
Supervised Training ◽  
Training Scheme ◽  
Classification Tasks ◽  
Standard Learning

We introduce advocacy learning, a novel supervised training scheme for attention-based classification problems. Advocacy learning relies on a framework consisting of two connected networks: 1) N Advocates (one for each class), each of which outputs an argument in the form of an attention map over the input, and 2) a Judge, which predicts the class label based on these arguments. Each Advocate produces a class-conditional representation with the goal of convincing the Judge that the input example belongs to their class, even when the input belongs to a different class. Applied to several different classification tasks, we show that advocacy learning can lead to small improvements in classification accuracy over an identical supervised baseline. Though a series of follow-up experiments, we analyze when and how such class-conditional representations improve discriminative performance. Though somewhat counter-intuitive, a framework in which subnetworks are trained to competitively provide evidence in support of their class shows promise, in many cases performing on par with standard learning approaches. This provides a foundation for further exploration into competition and class-conditional representations in supervised learning.

Sign in / Sign up

Export Citation Format

Share Document