Point cloud analysis, arising from computer graphics, remains a fundamental but challenging problem, mainly due to the non-Euclidean property of point cloud data modality. With the snap increase in the amount and breadth of related research in deep learning for graphs, many important works come in the form of graphs representing the point clouds. In this paper, we present a sampling adaptive graph convolutional network that combines the powerful representation ability of random walk subgraph searching and the essential success of the Fisher vector. Extending from those existing graph representation learning or embedding methods with multi-hop neighbor random searching, we sample multi-scale walk fields by using asteerableexploration-exploitationsecond order random walk, which endows our model with the most flexibility compared with the original first order random walk. To encode each-scale walk field consisting of several walk paths, specifically, we characterize these paths of walk field by Gaussian mixture models (GMMs) so as to better analogize the standard CNNs on Euclidean modality. Each Gaussian component implicitly defines a direction and all of them properly encode thespatial layoutof walk fields after the gradient projecting to the space of Gaussian parameters, i.e. the Fisher vectors. Thereby, we introduce and name our deep graph convolutional network asPointFisher. Comprehensive evaluations on several public datasets well demonstrate the superiority of our proposed learning method over other state-of-the-arts for point cloud classification and segmentation.

Aiming at improving collaborative learning, the current study builds and tests an LLM-empowered agent to enhance student engagement in group discussion. We introduce a four-module conversational system, providing a user-friendly chat website integrated with an LLM agent, where students can discuss on and learn a specific topic in an online classroom. The LLM agent can continuously monitor the dialogue process and give constructive and reflective responses as a knowledgeable learning peer to engage students in the computer-supported collaborative learning (CSCL) environment. To evaluate the pedagogical performance of the system, three LLMs were tested by prompting. The results showed that LLMs with only prompting were unable to accurately process multi-user dialogue information and lacked pedagogical strategies in their responses.

This study aimed to identify effective teacher-student dialogues in online one-on-one tutoring sessions for primary mathematics. A total of 35 online videos of one-on-one tutoring sessions focused on the topic of fractions were collected and transcribed into textual data. Two key methods were employed to analyze the data. First, a hybrid coding scheme combining the Initiation-Response-Feedback (IRF) model with scaffolding techniques was used to code teacher-student dialogues from each tutoring session to categorize the session into one of two groups: the more effective tutoring and the less effective tutoring group, based on the presence of indicators suggested by the literature. Second, lag sequential analysis (LSA) was applied to compare dialogue patterns between the more and less effective tutoring groups at a more fine-grained level. Our results indicate that tutors who employed a variety of strategies, including modeling and diverse scaffolding techniques, were more effective in engaging students and addressing their learning needs. This study suggests that adaptive tutoring strategies are crucial for enhancing student understanding in primary mathematics. Future research could further refine these approaches with inputs from human experts and explore their application in different educational contexts, such as developing AI-powered chatbots capable of providing adaptive scaffolding to students beyond the classroom.

With the fast progress in information technologies and artificial intelligence (AI), smart healthcare has gained considerable momentum. By using advanced technologies like AI, smart healthcare aims to promote human beings’ health and well-being throughout their life. As smart healthcare develops, big healthcare data are produced by various sensors, devices, and communication technologies constantly. To deal with these big multi-source data, automatic information fusion becomes crucial. Information fusion refers to the integration of multiple information sources for obtaining more reliable, effective, and precise information to support optimal decision-making. The close study of information fusion for healthcare with the adoption of advanced AI technologies has become an increasingly important and active field of research. The aim of this is to present a systematic description and state-of-the-art understanding of research about information fusion for healthcare with AI. Structural topic modeling was implemented to detect major research topics covered within 351 relevant articles. Annual trends and correlations of the identified topics were also investigated to identify potential future research directions. In addition, the primary research concerns of top countries/regions, institutions, and authors were shown and compared. The findings based on our analyses provide scientific and technological perspectives of research on information fusion for smart health with AI and offer useful insights and implications for its future development. We also provide valuable guidance for researchers and project managers to allocate research resources and promote effective international collaborations.

Automated detecting lung infections from computed tomography (CT) data plays an important role for combating coronavirus 2019 (COVID-19). However, there are still some challenges for developing AI system: 1) most current COVID-19 infection segmentation methods mainly relied on 2-D CT images, which lack 3-D sequential constraint; 2) existing 3-D CT segmentation methods focus on single-scale representations, which do not achieve the multiple level receptive field sizes on 3-D volume; and 3) the emergent breaking out of COVID-19 makes it hard to annotate sufficient CT volumes for training deep model. To address these issues, we first build a multiple dimensional-attention convolutional neural network (MDA-CNN) to aggregate multiscale information along different dimension of input feature maps and impose supervision on multiple predictions from different convolutional neural networks (CNNs) layers. Second, we assign this MDA-CNN as a basic network into a novel dual multiscale mean teacher network (DM [Formula: see text]-Net) for semi-supervised COVID-19 lung infection segmentation on CT volumes by leveraging unlabeled data and exploring the multiscale information. Our DM [Formula: see text]-Net encourages multiple predictions at different CNN layers from the student and teacher networks to be consistent for computing a multiscale consistency loss on unlabeled data, which is then added to the supervised loss on the labeled data from multiple predictions of MDA-CNN. Third, we collect two COVID-19 segmentation datasets to evaluate our method. The experimental results show that our network consistently outperforms the compared state-of-the-art methods.

Abstract Real‐world rain is a mixture of rain streaks and rainy haze. However, current efforts formulate image rain streaks removal and rainy haze removal as separated models, worsening the loss of image details. This paper attempts to solve the mixture of rain removal problem in a single model by estimating the scene depths of images. To this end, we propose a novel SEMI‐ supervised M ixture O f rain RE moval G enerative A dversarial N etwork (Semi‐MoreGAN). Unlike most of existing methods, Semi‐MoreGAN is a joint learning paradigm of mixture of rain removal and depth estimation; and it effectively integrates the image features with the depth information for better rain removal. Furthermore, it leverages unpaired real‐world rainy and clean images to bridge the gap between synthetic and real‐world rain. Extensive experiments show clear improvements of our approach over twenty representative state‐of‐the‐arts on both synthetic and real‐world rainy images. Source code is available at https://github.com/syy-whu/Semi-MoreGAN .

Artificial intelligence (AI) for personalized learning has attracted increasing attention in various educational contexts and domains, including language learning. This study systematically reviewed academic studies on AI-assisted personalized language learning (PLL) from the perspectives of article trends, top journals, countries/regions and institutions, AI technology types, learning outcomes and supports, participants, scientific collaborations, and co-citation relations. Results indicated Taiwanese institutions' predominance in the field and the prevalent use of intelligent tutoring systems, natural language processing, and artificial neural network in facilitating personalized diagnosis and learning path and material recommendations in language learning. Furthermore, students' improved language outcomes and positive perception, satisfaction, or motivation towards language learning and AI technologies were commonly reported. The co-authorship analysis results indicated the close inter-regional collaborations, while the cross-regional collaborations are expected to be enhanced. The co-citation network analysis results highlighted the significance of fuzzy systems and item response theory. Additionally, learner profiling mining and learning resource adaptation were important directions to realize mobile- and web-based PLL.

Abstract Exploiting hand-crafted lexicon knowledge to enhance emotional or sentimental features at word-level has become a widely adopted method in emotion-relevant classification studies. However, few attempts have been made to explore the emotion construction in the classification task, which provides insights to how a sentence’s emotion is constructed. The major challenge of exploring emotion construction is that the current studies assume the dataset labels as relatively independent emotions, which overlooks the connections among different emotions. This work aims to understand the coarse-grained emotion construction and their dependency by incorporating fine-grained emotions from domain knowledge. Incorporating domain knowledge and dimensional sentiment lexicons, our previous work proposes a novel method namedEmoChannelto capture the intensity variation of a particular emotion in time series. We utilize the resultant knowledge of 151 available fine-grained emotions to comprise the representation of sentence-level emotion construction. Furthermore, this work explicitly employs a self-attention module to extract the dependency relationship within all emotions and proposeEmoChannel-SANetwork to enhance emotion classification performance. We conducted experiments to demonstrate that the proposed method produces competitive performances against the state-of-the-art baselines on both multi-class datasets and sentiment analysis datasets.

This paper reports and discusses on a project about designing a digital tool to support Chinese undergraduate students in reflecting on their English language (L2) learning experience. The tool namely ACTIVE was developed primarily based on a classification framework called A-S-E-R and Latent Semantic Analysis. It can automatically classify reflective L2 learning skills into four elements with each divided into four hierarchical levels. This paper begins by presenting the background of the study, followed by the details of methods of automatic classification and performance evaluation. The results of the project indicate that the computer-generated ratings for students' reflection are comparable to human ratings.

In this paper, we report on the findings with regard to classroom activities and their time use in a number of mobile technology-mediated classrooms at Hong Kong. The data was collected from a mobile learning project specifically designed to promote students’ group and independent learning across a range of subject disciplines through using mobile devices within school environment. A total of 30 lessons in 10 primary and secondary schools were videotaped and analyzed. Results indicate that mobile devices can support establishing a well-balanced structure of classroom activities controlled by both teachers and students, where about 40% of the total class time was allocated to direct teaching and 40% was assigned to students’ learning in independent and/or collaborative ways.