context learning
Recently Published Documents


TOTAL DOCUMENTS

269
(FIVE YEARS 97)

H-INDEX

22
(FIVE YEARS 4)

2022 ◽  
Vol 16 (4) ◽  
pp. 1-22
Author(s):  
Zhe Fu ◽  
Li Yu ◽  
Xi Niu

As the popularity of online travel platforms increases, users tend to make ad-hoc decisions on places to visit rather than preparing the detailed tour plans in advance. Under the situation of timeliness and uncertainty of users’ demand, how to integrate real-time context into dynamic and personalized recommendations have become a key issue in travel recommender system. In this article, by integrating the users’ historical preferences and real-time context, a location-aware recommender system called TRACE ( T ravel R einforcement Recommendations Based on Location- A ware C ontext E xtraction) is proposed. It captures users’ features based on location-aware context learning model, and makes dynamic recommendations based on reinforcement learning. Specifically, this research: (1) designs a travel reinforcing recommender system based on an Actor-Critic framework, which can dynamically track the user preference shifts and optimize the recommender system performance; (2) proposes a location-aware context learning model, which aims at extracting user context from real-time location and then calculating the impacts of nearby attractions on users’ preferences; and (3) conducts both offline and online experiments. Our proposed model achieves the best performance in both of the two experiments, which demonstrates that tracking the users’ preference shifts based on real-time location is valuable for improving the recommendation results.


2021 ◽  
Vol 20 (2) ◽  
pp. 27
Author(s):  
Ráisa Mendes Fernandes de Souza

A explosão informacional e a ubiquidade das tecnologias de informação e comunicação, aspectos inerentes à Sociedade da Informação, remodelaram a dinâmica social de forma irreversível. Nesse contexto, surgiram os objetos de aprendizagem, ferramentas tecnológicas utilizadas para o ensino, seja ele remoto ou presencial. Porém, é preciso que a Ciência da Informação discuta de forma mais lúcida o uso desses instrumentos na atualidade, apontando seus benefícios e limitações. O objetivo geral buscou analisar as vantagens e desvantagens do uso de objetos de aprendizagem como ferramentas de ensino sob o prisma da Ciência da Informação. Os objetivos específicos são: identificar aspectos negativos e positivos das tecnologias de informação e comunicação na atualidade, utilizando principalmente o embasamento teórico da Ciência da Informação; apontar o conceito de objeto de aprendizagem, bem como seu uso no ensino; detectar as potencialidades e limitações dos objetos de aprendizagem e sugerir os contextos em que eles devem ser ou não utilizados como ferramenta de ensino considerando o âmbito da Sociedade da Informação. Por meio de um levantamento bibliográfico, foi possível apontar até que ponto os objetos de aprendizagem possuem limitações que devem ser seriamente consideradas, evitando-se sempre a adoção de discursos tecnocráticos que elegem essa tecnologia como a solução para todos os problemas educacionais existentes. As considerações finais relatam que o uso dos objetos de aprendizagem precisa refletir os contextos educacionais, culturais e as limitações físicas dos sujeitos, além de possibilitar a capacidade de reflexão do aluno.AbstractThe informational explosion and the ubiquity of information and communicationtechnologies, inherent aspects of the Information Society, have irreversibly reshaped the social dynamics. In this context, learning objects emerged, technological tools used for teaching, whether remote or in person. However, it is necessary that Information Science discuss more lucidly the use of these instruments today, pointing out their benefits and limitations. The general objective sought to analyze the advantages and disadvantages of using learning objects as teaching tools from the perspective of Information Science. The specific objectives are: to identify negative and positive aspects of information and communication technologies today, using mainly the theoretical foundation of Information Science; point out the concept of learning object, as well as its use in teaching; detect the potential and limitations of learning objects and suggest the contexts in which they should or should not be used as a teaching tool considering the scope of the Information Society. Through a bibliographic survey, it was possible to point out the extent to which learning objectshave limitations that must be seriously considered, always avoiding the adoption of technocratic speeches that elect this technology as the solution to all existingeducational problems. The final considerations report that the use of learning objects needs to reflect the educational and cultural contexts and the physical limitations of the subjects, in addition to enabling the student's capacity for reflection.


2021 ◽  
Vol 20 (6) ◽  
pp. 969-982
Author(s):  
King-Dow Su

The presented research focuses on verifying the confluent application of concept mapping (CM) and socio-scientific issues (SSI) according to the value-laden and moral dilemma orientation to construct problem-solving performance. This research sets up some perspectives for all 146 participants, including 139 students and 7 experts. All findings reveal that the design of SSICM contexts includes a rebuttal process and incense claim to improve students' argument response (16.4%), to increase content knowledge and illuminate their science learning by argumentations. To develop an assessment tool with high validity and reliability (Cronbach's α > .9) and find positive presentations of all learning attitudes in the SSICM context, learning environment and results will concern the best argumentation process. Students’ interview responses and SWOT analysis of teachers indicate that SSICM's use of argument in the classroom is a real benefit. The research provided a better paradigm of attempts to combine analytical and academic hypotheses to explain literature sources by teachers, researchers, textbook developers, and editors. Keywords: concept mapping (CM), problem-solving, socio-scientific issues (SSI), SSICM contexts


Sensors ◽  
2021 ◽  
Vol 21 (21) ◽  
pp. 7316
Author(s):  
Bo Zhong ◽  
Jiang Du ◽  
Minghao Liu ◽  
Aixia Yang ◽  
Junjun Wu

Semantic segmentation for high-resolution remote-sensing imagery (HRRSI) has become increasingly popular in machine vision in recent years. Most of the state-of-the-art methods for semantic segmentation of HRRSI usually emphasize the strong learning ability of deep convolutional neural network to model the contextual relationship in the image, which takes too much consideration on every pixel in images and subsequently causes the problem of overlearning. Annotation errors and easily confused features can also lead to the confusion problem while using the pixel-based methods. Therefore, we propose a new semantic segmentation network—the region-enhancing network (RE-Net)—to emphasize the regional information instead of pixels to solve the above problems. RE-Net introduces the regional information into the base network, to enhance the regional integrity of images and thus reduce misclassification. Specifically, the regional context learning procedure (RCLP) can learn the context relationship from the perspective of regions. The region correcting procedure (RCP) uses the pixel aggregation feature to recalibrate the pixel features in each region. In addition, another simple intra-network multi-scale attention module is introduced to select features at different scales by the size of the region. A large number of comparative experiments on four different public datasets demonstrate that the proposed RE-Net performs better than most of the state-of-the-art ones.


2021 ◽  
Author(s):  
Pufen Zhang ◽  
Hong Lan

Abstract In recently years, some visual question answering (VQA) methods that emphasize the simultaneous understanding of both the context of image and question have been proposed. Despite the effectiveness of these methods, they fail to explore a more comprehensive and generalized context learning tactics. To address this issue, we propose a novel Multiple Context Learning Networks (MCLN) to model the multiple contexts for VQA. Three kinds of contexts are investigated, namely visual context, textual context and a special visual-textual context that ignored by previous methods. Moreover, three corresponding context learning modules are proposed. These modules endow image and text representations with context-aware information based on a uniform context learning strategy. And they work together to form a multiple context learning layer (MCL). Such MCL can be stacked in depth and which describe high-level context information by associating intra-modal contexts with inter-modal context. On the VQA v2.0 datasets, the proposed model achieves 71.05% and 71.48% on test-dev set and test-std set respectively, and gains better performance than the previous state-of-the-art methods. In addition, extensive ablation studies have been carried out to examine the effectiveness of the proposed method.


2021 ◽  
Author(s):  
Ia Kurnia

Kajian dalam buku ini bertujuan untuk untuk mengetahui relasi antara emotional intelligence, learning context, learning approaches, reflective thinking, dan academic performance. Dalam kajian ini dikembangkan relasi antara lima variabel atau konsep, yaitu variabel academic performance (pestasi akademik), emotional intelligence (kecerdasan emosional), reflective thinking (berpikir reflektif), learning approaches (pendekatan belajar), dan learning context (konteks belajar). Hasil kajian terhadap relasi kelima variabel tersebut diharapkan dapat memberikan kontribusi positif baik secara praktis ataupun teori, juga untuk penelitian-penelitian selanjutnya. Secara praktis kegunaan kajian tentang academic performance akan memberikan komparasi data perkembangan capaian prestasi akademik mahasiswa yang sangat berguna bagi pelaku pendidikan tinggi (pengambil kebijakan akademik dan dosen).


2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Victoria L. Murphy ◽  
Allison Littlejohn ◽  
Bart Rienties

Purpose Learning from incidents (LFI) is an organisational process that high-risk industries use following an accident or near-miss to prevent similar events. Literature on the topic has presented a fragmented conceptualisation of learning in this context. This paper aims to present a holistic taxonomy of the different aspects of LFI from the perspective of front-line staff. Design/methodology/approach The 3-P model of workplace learning was used to guide a thematic analysis of interview data from 45 participants, exploring learner factors, learning context, learning processes and learning products. Findings The analysis was used to create a taxonomy of 21 aspects of learning, grouped into themes using the 3-P model of workplace learning. Many of the aspects of learning reflected previous literature, such as the importance of open communication. The analysis additionally demonstrated the interconnected nature of organisational and individual level learning, as well as how formal resources are needed to support informal learning in this context. Originality/value This study presents a holistic taxonomy of LFI from the perspective of front-line staff, addressing a known challenge of LFI literature being fragmented. Additionally, it provides examples of how aspects of organisational learning would influence individual-level learning and vice versa, adding to the relatively sparse number of studies that have explored this aspect. Finally, the paper highlights how informal learning in contexts where workers continually need to make sense of unseen hazards depends on formal learning activities and resources.


Sign in / Sign up

Export Citation Format

Share Document