scholarly journals Bringing deep learning to the surface

2020 ◽  
Vol 4 (2) ◽  
pp. 25-41
Author(s):  
Øystein Winje ◽  
Knut Løndal

Deep learning is a key term in current educational discourses worldwide and used by researchers, policymakers, stakeholders, politicians, organisations and the media with different definitions and, consequently, much confusion about its meaning and usage. This systematic mapping review attempts to reduce this ambiguity by investigating the definitions of deep learning in 71 research publications on primary and secondary education from 1970 to 2018. The results show two conceptualisations of the term deep learning—1) meaningful learning and 2) transfer of learning—both based on cognitive learning perspectives. The term deep learning is used by researchers worldwide and is mainly investigated in the school subjects of science, languages and mathematics with samples of students between 13 and 16 years of age. Deep learning is also a prevalent term in current international education policy and national curriculum reform, thus deeply affecting the practice of teaching and learning in general education. Our review identifies a lack of studies investigating deep learning through perspectives other than cognitive learning theories and suggests that future research should emphasise applying embodied, affective, and social perspectives on learning in the wide array of school subjects, in lower primary education and in a variety of sociocultural contexts, to support the adaptation of deep learning to a general educational practice.

Author(s):  
Дмитрий Николаевич Быков-Куликовский

Рассматривается возможность использования исторически сложившихся интонационных семантических стереотипов для развития творческой активности учащихся, мотивации познавательной учебной деятельности. Анализируются конкретные варианты использования «мигрирующих интонационных комплексов» для импровизации, сочинения, ансамблевого музицирования на музыкально-теоретических дисциплинах детских музыкальных школ (детских школ искусств), на музыкальных занятиях общеобразовательных школ и различных учреждениях дополнительного образования, включая дошкольное. Именно мотивация способствует достижению важнейшей цели в образовании – экологизации учебного процесса. Это значит максимально вписать учебную деятельность в жизненные потребности учащихся. Положительно переживаемые эмоции в процессе музыкальных занятий способствуют решению очень многих задач. «Пропустить» музыку через себя, «прожить в ней», музицируя, – значит полюбить, понять. Решение весьма сложных вопросов музыкальной педагогики академик Б. В. Асафьев видел в использовании семантического подхода, открывающего и перспективу будущих исследований ученых, и перспективу разработки методики и методологии семантического подхода в музыкально-художественном воспитании и образовании. На основе семантического подхода-анализа исследуются наиболее яркие культурные коды «золотого фонда стандартов» мировой музыки. Представлены некоторые методические подходы-рекомендации и предложения их практического использования в музыкальной педагогике. Сделаны соответствующие выводы по теме исследования. На основе семантического подхода-анализа можно раскрыть феномен музыкального текста, его смысла «не только с позиции фонетики, грамматики и синтаксиса», но и «с точки зрения поэтики, семантики, стилистики». Используя семантический подход в процессе обучения, можно приобрести «навыки устной музыкальной речи» – импровизации, бывшей обязательной когда-то при подготовке музыканта. Необходимо создание «органичной межпредметной связи» между теоретическими дисциплинами и «музицирующей практикой», так как теоретические дисциплины могут и изначально должны быть музицирующими. Вопрос в методике, методологии «погружения» в музыку. Музыкальной педагогике еще предстоит принять и освоить семантический подход, учитывая уровень современной психологии восприятия, выработать методику и методологию учебного процесса, чтобы заинтересовать, увлечь, влюбить в музыку, слушаемую и исполняемую. The article considers the possibility of using historical intonation semantic stereotypes for the development of creative activity of students, motivation of cognitive learning activities. Specific options are being considered for the use of «migratory intonation complexes» for improvisation, composition, ensemble music in the musical-theoretical disciplines of CMS / CSA, in music classes of general education school and various institutions of additional education, including pre-school. It is motivation that contributes to the achievement of the most important goal in education - the greening of the educational process. This means to maximally incorporate educational activities into the life needs of students. Positively experienced emotions in the process of music classes contribute to the solution of many problems. To «pass» music through oneself, «to live in it» while playing music means to love, to understand. Academician B. V. Asafiev saw the solution to very complex issues of musical pedagogy in the use of the semantic approach, which opens up both the prospect of future research of scientists, and the prospect of developing the methods and methodology of the semantic approach in musical and artistic education and training. Based on the semantic approach of analysis the article explores the brightest cultural codes of the «golden fund of standards» of world music. Some methodical approaches-recommendations and proposals for their practical use in music pedagogy are presented. In the effective and final sections of the article, the relevant conclusions are drawn on the topic of the study. On the basis of semantic approach-analysis it is possible to reveal the phenomenon of musical text, its meaning «not only from the position of phonetics, grammar and syntax», but also «from the point of view of poetics, semantics, style». Using a semantic approach in the process of learning you need to acquire «the skills of oral musical speech» – improvisation, which was once obligatory in the training of a musician. It is necessary to create an «organic intersubject communication» between theoretical disciplines and «music-making practice» because theoretical disciplines can and should be musical. The question is the methods of teaching, the methodology of «immersion» in music. Musical pedagogy has yet to be adopted and mastered, taking into account the level of modern psychology of perception, to develop the methods and methodology of the educational process to interest, captivate, to make students fall in love with music heard and performed.


2020 ◽  
Vol 14 ◽  
Author(s):  
Meghna Dhalaria ◽  
Ekta Gandotra

Purpose: This paper provides the basics of Android malware, its evolution and tools and techniques for malware analysis. Its main aim is to present a review of the literature on Android malware detection using machine learning and deep learning and identify the research gaps. It provides the insights obtained through literature and future research directions which could help researchers to come up with robust and accurate techniques for classification of Android malware. Design/Methodology/Approach: This paper provides a review of the basics of Android malware, its evolution timeline and detection techniques. It includes the tools and techniques for analyzing the Android malware statically and dynamically for extracting features and finally classifying these using machine learning and deep learning algorithms. Findings: The number of Android users is expanding very fast due to the popularity of Android devices. As a result, there are more risks to Android users due to the exponential growth of Android malware. On-going research aims to overcome the constraints of earlier approaches for malware detection. As the evolving malware are complex and sophisticated, earlier approaches like signature based and machine learning based are not able to identify these timely and accurately. The findings from the review shows various limitations of earlier techniques i.e. requires more detection time, high false positive and false negative rate, low accuracy in detecting sophisticated malware and less flexible. Originality/value: This paper provides a systematic and comprehensive review on the tools and techniques being employed for analysis, classification and identification of Android malicious applications. It includes the timeline of Android malware evolution, tools and techniques for analyzing these statically and dynamically for the purpose of extracting features and finally using these features for their detection and classification using machine learning and deep learning algorithms. On the basis of the detailed literature review, various research gaps are listed. The paper also provides future research directions and insights which could help researchers to come up with innovative and robust techniques for detecting and classifying the Android malware.


Author(s):  
Matthew L. Hall

Deaf and hard of hearing (DHH) children have been claimed to lag behind their hearing peers in various domains of cognitive development, especially in implicit learning, executive function, and working memory. Two major accounts of these deficits have been proposed: one based on a lack of auditory access, and one based on a lack of language access. This chapter reviews these theories in relation to the available evidence and concludes that there is little evidence of direct effects of diminished auditory access on cognitive development that could not also be explained by diminished language access. Specifically, reports of deficits in implicit learning are not broadly replicable. Some differences in executive function do stem from deafness itself but are not necessarily deficits. Where clinically relevant deficits in executive function are observed, they are inconsistent with the predictions of accounts based on auditory access, but consistent with accounts based on language access. Deaf–hearing differences on verbal working memory tasks may indicate problems with perception and/or language, rather than with working memory. Deaf–hearing differences on nonverbal tasks are more consistent with accounts based on language access, but much more study is needed in this area. The chapter concludes by considering the implications of these findings for psychological theory and for clinical/educational practice and by identifying high-priority targets for future research.


2020 ◽  
Vol 7 (1) ◽  
Author(s):  
Manan Binth Taj Noor ◽  
Nusrat Zerin Zenia ◽  
M Shamim Kaiser ◽  
Shamim Al Mamun ◽  
Mufti Mahmud

Abstract Neuroimaging, in particular magnetic resonance imaging (MRI), has been playing an important role in understanding brain functionalities and its disorders during the last couple of decades. These cutting-edge MRI scans, supported by high-performance computational tools and novel ML techniques, have opened up possibilities to unprecedentedly identify neurological disorders. However, similarities in disease phenotypes make it very difficult to detect such disorders accurately from the acquired neuroimaging data. This article critically examines and compares performances of the existing deep learning (DL)-based methods to detect neurological disorders—focusing on Alzheimer’s disease, Parkinson’s disease and schizophrenia—from MRI data acquired using different modalities including functional and structural MRI. The comparative performance analysis of various DL architectures across different disorders and imaging modalities suggests that the Convolutional Neural Network outperforms other methods in detecting neurological disorders. Towards the end, a number of current research challenges are indicated and some possible future research directions are provided.


2021 ◽  
Vol 22 (15) ◽  
pp. 7911
Author(s):  
Eugene Lin ◽  
Chieh-Hsin Lin ◽  
Hsien-Yuan Lane

A growing body of evidence currently proposes that deep learning approaches can serve as an essential cornerstone for the diagnosis and prediction of Alzheimer’s disease (AD). In light of the latest advancements in neuroimaging and genomics, numerous deep learning models are being exploited to distinguish AD from normal controls and/or to distinguish AD from mild cognitive impairment in recent research studies. In this review, we focus on the latest developments for AD prediction using deep learning techniques in cooperation with the principles of neuroimaging and genomics. First, we narrate various investigations that make use of deep learning algorithms to establish AD prediction using genomics or neuroimaging data. Particularly, we delineate relevant integrative neuroimaging genomics investigations that leverage deep learning methods to forecast AD on the basis of incorporating both neuroimaging and genomics data. Moreover, we outline the limitations as regards to the recent AD investigations of deep learning with neuroimaging and genomics. Finally, we depict a discussion of challenges and directions for future research. The main novelty of this work is that we summarize the major points of these investigations and scrutinize the similarities and differences among these investigations.


Electronics ◽  
2021 ◽  
Vol 10 (4) ◽  
pp. 517
Author(s):  
Seong-heum Kim ◽  
Youngbae Hwang

Owing to recent advancements in deep learning methods and relevant databases, it is becoming increasingly easier to recognize 3D objects using only RGB images from single viewpoints. This study investigates the major breakthroughs and current progress in deep learning-based monocular 3D object detection. For relatively low-cost data acquisition systems without depth sensors or cameras at multiple viewpoints, we first consider existing databases with 2D RGB photos and their relevant attributes. Based on this simple sensor modality for practical applications, deep learning-based monocular 3D object detection methods that overcome significant research challenges are categorized and summarized. We present the key concepts and detailed descriptions of representative single-stage and multiple-stage detection solutions. In addition, we discuss the effectiveness of the detection models on their baseline benchmarks. Finally, we explore several directions for future research on monocular 3D object detection.


Religions ◽  
2021 ◽  
Vol 12 (5) ◽  
pp. 348
Author(s):  
Muhammad Azeem Ashraf ◽  
Samson Maekele Tsegay ◽  
Jin Ning

Pakistan is a Muslim-majority country, and religion plays a great role in the life of society. This study examines how teachers from the religious, national, and international education sectors realize the concept of global citizenship education (GCE) in Pakistan. Based on 24 semi-structured interviews, this study found differences among the teachers’ understandings of the concept of GCE and its characteristics. Teachers from the national and religious curriculum sectors viewed GCE as a threat to Islamic values, whereas those from the international curriculum sector regarded GCE as an opportunity for improving the economic development and image of Pakistan. Moreover, the teachers from the religious sector argued for the cultivation of Islamic identity instead of GCE. However, the teachers from the national curriculum sector noted the economic benefits of GCE and were keen on global citizenship principles that do not conflict with national and Islamic values. The different perceptions held by teachers from the three educational sectors indicate the need for more work on GCE to narrow the conflicting agendas and broaden the understandings within Pakistani society. Creating common ideas within these different sectors of education is significant for developing sustainable peace within the divided society.


2021 ◽  
Vol 13 (10) ◽  
pp. 1953
Author(s):  
Seyed Majid Azimi ◽  
Maximilian Kraus ◽  
Reza Bahmanyar ◽  
Peter Reinartz

In this paper, we address various challenges in multi-pedestrian and vehicle tracking in high-resolution aerial imagery by intensive evaluation of a number of traditional and Deep Learning based Single- and Multi-Object Tracking methods. We also describe our proposed Deep Learning based Multi-Object Tracking method AerialMPTNet that fuses appearance, temporal, and graphical information using a Siamese Neural Network, a Long Short-Term Memory, and a Graph Convolutional Neural Network module for more accurate and stable tracking. Moreover, we investigate the influence of the Squeeze-and-Excitation layers and Online Hard Example Mining on the performance of AerialMPTNet. To the best of our knowledge, we are the first to use these two for regression-based Multi-Object Tracking. Additionally, we studied and compared the L1 and Huber loss functions. In our experiments, we extensively evaluate AerialMPTNet on three aerial Multi-Object Tracking datasets, namely AerialMPT and KIT AIS pedestrian and vehicle datasets. Qualitative and quantitative results show that AerialMPTNet outperforms all previous methods for the pedestrian datasets and achieves competitive results for the vehicle dataset. In addition, Long Short-Term Memory and Graph Convolutional Neural Network modules enhance the tracking performance. Moreover, using Squeeze-and-Excitation and Online Hard Example Mining significantly helps for some cases while degrades the results for other cases. In addition, according to the results, L1 yields better results with respect to Huber loss for most of the scenarios. The presented results provide a deep insight into challenges and opportunities of the aerial Multi-Object Tracking domain, paving the way for future research.


2021 ◽  
Vol 54 (4) ◽  
pp. 1-37
Author(s):  
Azzedine Boukerche ◽  
Xiren Ma

Vision-based Automated Vehicle Recognition (VAVR) has attracted considerable attention recently. Particularly given the reliance on emerging deep learning methods, which have powerful feature extraction and pattern learning abilities, vehicle recognition has made significant progress. VAVR is an essential part of Intelligent Transportation Systems. The VAVR system can fast and accurately locate a target vehicle, which significantly helps improve regional security. A comprehensive VAVR system contains three components: Vehicle Detection (VD), Vehicle Make and Model Recognition (VMMR), and Vehicle Re-identification (VRe-ID). These components perform coarse-to-fine recognition tasks in three steps. In this article, we conduct a thorough review and comparison of the state-of-the-art deep learning--based models proposed for VAVR. We present a detailed introduction to different vehicle recognition datasets used for a comprehensive evaluation of the proposed models. We also critically discuss the major challenges and future research trends involved in each task. Finally, we summarize the characteristics of the methods for each task. Our comprehensive model analysis will help researchers that are interested in VD, VMMR, and VRe-ID and provide them with possible directions to solve current challenges and further improve the performance and robustness of models.


Publications ◽  
2021 ◽  
Vol 9 (3) ◽  
pp. 27
Author(s):  
Yaniasih Yaniasih ◽  
Indra Budi

Classifying citations according to function has many benefits when it comes to information retrieval tasks, scholarly communication studies, and ranking metric developments. Many citation function classification schemes have been proposed, but most of them have not been systematically designed for an extensive literature-based compilation process. Many schemes were also not evaluated properly before being used for classification experiments utilizing large datasets. This paper aimed to build and evaluate new citation function categories based upon sufficient scientific evidence. A total of 2153 citation sentences were collected from Indonesian journal articles for our dataset. To identify the new categories, a literature survey was conducted, analyses and groupings of category meanings were carried out, and then categories were selected based on the dataset’s characteristics and the purpose of the classification. The evaluation used five criteria: coherence, ease, utility, balance, and coverage. Fleiss’ kappa and automatic classification metrics using machine learning and deep learning algorithms were used to assess the criteria. These methods resulted in five citation function categories. The scheme’s coherence and ease of use were quite good, as indicated by an inter-annotator agreement value of 0.659 and a Long Short-Term Memory (LSTM) F1-score of 0.93. According to the balance and coverage criteria, the scheme still needs to be improved. This research data was limited to journals in food science published in Indonesia. Future research will involve classifying the citation function using a massive dataset collected from various scientific fields and published from some representative countries, as well as applying improved annotation schemes and deep learning methods.


Sign in / Sign up

Export Citation Format

Share Document