An Uncertainty-based Neural Network for Explainable Trajectory Segmentation

As a variant task of time-series segmentation, trajectory segmentation is a key task in the applications of transportation pattern recognition and traffic analysis. However, segmenting trajectory is faced with challenges of implicit patterns and sparse results. Although deep neural networks have tremendous advantages in terms of high-level feature learning performance, deploying as a blackbox seriously limits the real-world applications. Providing explainable segmentations has significance for result evaluation and decision making. Thus, in this article, we address trajectory segmentation by proposing a Bayesian Encoder-Decoder Network (BED-Net) to provide accurate detection with explainability and references for the following active-learning procedures. BED-Net consists of a segmentation module based on Monte Carlo dropout and an explanation module based on uncertainty learning that provides results evaluation and visualization. Experimental results on both benchmark and real-world datasets indicate that BED-Net outperforms the rival methods and offers excellent explainability in the applications of trajectory segmentation.

Evaluating the university professor’s performance in distance education in light of the Corona pandemic

The study aims to identify the difficulties of teaching-learning performance facing teachers, whether in terms of performance or reception by students in light of the Corona pandemic and quarantine. The study relied on the descriptive approach to evaluate the teaching-learning performance with the application of a questionnaire for teachers and another for students. The results revealed several difficulties facing the professor and the student alike, whether in terms of controlling the skills and techniques of distance education and its technological means, or regarding the organization of lessons and pedagogical activities.

Edge Learning for Distributed Big Data Analytics

Discover this multi-disciplinary and insightful work, which integrates machine learning, edge computing, and big data. Presents the basics of training machine learning models, key challenges and issues, as well as comprehensive techniques including edge learning algorithms, and system design issues. Describes architectures, frameworks, and key technologies for learning performance, security, and privacy, as well as incentive issues in training/inference at the network edge. Intended to stimulate fruitful discussions, inspire further research ideas, and inform readers from both academia and industry backgrounds. Essential reading for experienced researchers and developers, or for those who are just entering the field.

Self-relabeling for noise-tolerant retina vessel segmentation through label reliability estimation

Background Retinal vessel segmentation benefits significantly from deep learning. Its performance relies on sufficient training images with accurate ground-truth segmentation, which are usually manually annotated in the form of binary pixel-wise label maps. Manually annotated ground-truth label maps, more or less, contain errors for part of the pixels. Due to the thin structure of retina vessels, such errors are more frequent and serious in manual annotations, which negatively affect deep learning performance. Methods In this paper, we develop a new method to automatically and iteratively identify and correct such noisy segmentation labels in the process of network training. We consider historical predicted label maps of network-in-training from different epochs and jointly use them to self-supervise the predicted labels during training and dynamically correct the supervised labels with noises. Results We conducted experiments on the three datasets of DRIVE, STARE and CHASE-DB1 with synthetic noises, pseudo-labeled noises, and manually labeled noises. For synthetic noise, the proposed method corrects the original noisy label maps to a more accurate label map by 4.0–$$9.8\%$$ 9.8 % on $$F_1$$ F 1 and 10.7–$$16.8\%$$ 16.8 % on PR on three testing datasets. For the other two types of noise, the method could also improve the label map quality. Conclusions Experiment results verified that the proposed method could achieve better retinal image segmentation performance than many existing methods by simultaneously correcting the noise in the initial label map.

Improving machine learning performance on small chemical reaction data with unsupervised contrastive pretraining

Machine learning (ML) methods have great potential to transform chemical discovery by accelerating the exploration of chemical space and drawing scientific insights from data. However, modern chemical reaction ML models, such as those based on graph neural networks (GNNs), must be trained on a large amount of labelled data in order to avoid overfitting the data and thus possessing low accuracy and transferability. In this work, we propose a strategy to leverage unlabelled data to learn accurate ML models for small labelled chemical reaction data. We focus on an old and prominent problem—classifying reactions into distinct families—and build a GNN model for this task. We first pretrain the model on unlabelled reaction data using unsupervised contrastive learning and then fine-tune it on a small number of labelled reactions. The contrastive pretraining learns by making the representations of two augmented versions of a reaction similar to each other but distinct from other reactions. We propose chemically consistent reaction augmentation methods that protect the reaction center and find they are the key for the model to extract relevant information from unlabelled data to aid the reaction classification task. The transfer learned model outperforms a supervised model trained from scratch by a large margin. Further, it consistently performs better than models based on traditional rule-driven reaction fingerprints, which have long been the default choice for small datasets. In addition to reaction classification, the effectiveness of the strategy is tested on regression datasets; the learned GNN-based reaction fingerprints can also be used to navigate the chemical reaction space, which we demonstrate by querying for similar reactions. The strategy can be readily applied to other predictive reaction problems to uncover the power of unlabelled data for learning better models with a limited supply of labels.

The Potential of Blockchain Technology in Higher Education as Perceived by Students in Serbia, Romania, and Portugal

Lifelong learning approaches that include digital, transversal, and practical skills (i.e., critical thinking, communication, collaboration, information literacy, analytical, metacognitive, reflection, and other research skills) are required in order to be equitable and inclusive and stimulate personal development. Realtime interaction between teachers and students and the ability for students to choose courses from curricula are guaranteed by decentralized online learning. Moreover, through blockchain, it is possible to acquire skills regarding the structure and content while also implementing learning tools. Additionally, documentation validation should be equally crucial to speeding up the process and reducing costs and paperwork. Finally, blockchains are open and inclusive processes that include people and cultures from all walks of life. Learning in Higher Education Institutions (HEI) is facilitated by new technologies, connecting blockchain to sustainability, which helps understand the relationship between technologies and sustainability. Besides serving as a secure transaction system, blockchain technology can help decentralize, provide security and integrity, and offer anonymity and encryption, therefore, promoting a transaction rate increase. This study investigates an alternative in which HEI include a blockchain network to provide the best sustainable education system. Students’ opinions were analyzed, and they considered that blockchain technology had a very positive influence on learning performance.

Predicting students’ performance in e-learning using learning process and behaviour data

E-learning is achieved by the deep integration of modern education and information technology, and plays an important role in promoting educational equity. With the continuous expansion of user groups and application areas, it has become increasingly important to effectively ensure the quality of e-learning. Currently, one of the methods to ensure the quality of e-learning is to use mutually independent e-learning behaviour data to build a learning performance predictor to achieve real-time supervision and feedback during the learning process. However, this method ignores the inherent correlation between e-learning behaviours. Therefore, we propose the behaviour classification-based e-learning performance (BCEP) prediction framework, which selects the features of e-learning behaviours, uses feature fusion with behaviour data according to the behaviour classification model to obtain the category feature values of each type of behaviour, and finally builds a learning performance predictor based on machine learning. In addition, because existing e-learning behaviour classification methods do not fully consider the process of learning, we also propose an online behaviour classification model based on the e-learning process called the process-behaviour classification (PBC) model. Experimental results with the Open University Learning Analytics Dataset (OULAD) show that the learning performance predictor based on the BCEP prediction framework has a good prediction effect, and the performance of the PBC model in learning performance prediction is better than traditional classification methods. We construct an e-learning performance predictor from a new perspective and provide a new solution for the quantitative evaluation of e-learning classification methods.

Assessment of Flipped Learning as an Innovative Method of Teaching English: A Case Study

The article aims to assess the efficiency of flipped learning as one of the most up-to-date methods when teaching English for the EFL students in Ukraine. The significance of the study bases on the necessity to implement advanced teaching practices during the COVID-19 pandemic since online learning requires constructive changes in the traditional system of education. It is necessary to shift from the direct knowledge transfer to searching and cognition of new information by students, to change the teacher’s role to being ‘a facilitator’ and organizer of various academic activities. The article outlines the main characteristics of flipped learning, including flexibility, individualization, differentiation, and opportunities for students to learn at any place or time. The contribution of this research is to estimate new experiences of University students due to flipped learning implementation. It was achieved due to analyzing responses to the survey-based questionnaire of 48 learners and 23 teachers of the Department of Foreign Philology and Translation of Vinnytsia Institute of Trade and Economics of Kyiv National University of Trade and Economics, evaluation of students’ performance, attendance, and attitude to the study. In order to verify results of the research, a descriptive statistical and analytical method was applied. The study results reveal that implementation of flipped learning made the educational process more effective and innovative as it improved students’ progress in language learning performance, increased their motivation and involvement, and made them more interested in learning English.

Exploring jump back behavior patterns and reasons in e-book system

With the increasing use of digital learning materials in higher education, the accumulated operational log data provide a unique opportunity to analyzing student learning behaviors and their effects on student learning performance to understand how students learn with e-books. Among the students’ reading behaviors interacting with e-book systems, we find that jump-back is a frequent and informative behavior type. In this paper, we aim to understand the student’s intention for a jump-back using user learning log data on the e-book materials of a course in our university. We at first formally define the “jump-back” behaviors that can be detected from the click event stream of slide reading and then systematically study the behaviors from different perspectives on the e-book event stream data. Finally, by sampling 22 learning materials, we identify six reading activity patterns that can explain jump backs. Our analysis provides an approach to enriching the understanding of e-book learning behaviors and informs design implications for e-book systems.