Multilingual BERT (mBERT) has demonstrated considerable cross-lingual syntactic ability, whereby it enables effective zero-shot cross-lingual transfer of syntactic knowledge.The transfer is more successful between some languages, but it is not well understood what leads to this variation and whether it fairly reflects difference between languages.In this work, we investigate the distributions of grammatical relations induced from mBERT in the context of 24 typologically different languages.We demonstrate that the distance between the distributions of different languages is highly consistent with the syntactic difference in terms of linguistic formalisms.Such difference learnt via self-supervision plays a crucial role in the zero-shot transfer performance and can be predicted by variation in morphosyntactic properties between languages.These results suggest that mBERT properly encodes languages in a way consistent with linguistic diversity and provide insights into the mechanism of crosslingual transfer.

Brain disease gene identification is critical for revealing the biological mechanism and developing drugs for brain diseases. To enhance the identification of brain disease genes, similarity-based computational methods, especially network-based methods, have been adopted for narrowing down the searching space. However, these network-based methods only use molecular networks, ignoring brain connectome data, which have been widely used in many brain-related studies. In our study, we propose a novel framework, named brainMI, for integrating brain connectome data and molecular-based gene association networks to predict brain disease genes. For the consistent representation of molecular-based network data and brain connectome data, brainMI first constructs a novel gene network, called brain functional connectivity (BFC)-based gene network, based on resting-state functional magnetic resonance imaging data and brain region-specific gene expression data. Then, a multiple network integration method is proposed to learn low-dimensional features of genes by integrating the BFC-based gene network and existing protein-protein interaction networks. Finally, these features are utilized to predict brain disease genes based on a support vector machine-based model. We evaluate brainMI on four brain diseases, including Alzheimer's disease, Parkinson's disease, major depressive disorder and autism. brainMI achieves of 0.761, 0.729, 0.728 and 0.744 using the BFC-based gene network alone and enhances the molecular network-based performance by 6.3% on average. In addition, the results show that brainMI achieves higher performance in predicting brain disease genes compared to the existing three state-of-the-art methods.

The purpose is to cope with mobile educational game users' low continuous utilization rate. This thesis innovatively introduces the deep learning technology to study and the relationship between the mobile educational game and learners' learning behavior. It is found that learners' game experience is significantly correlated with game satisfaction. The estimation algorithm is designed based on the convolutional neural network (CNN), and the questionnaire method is adopted. The design tool of the estimation algorithm is a computer system, and the social software is used for the questionnaire. The dataset source used in the estimation algorithm design is “World Sudoku Championship.” The game satisfaction questionnaire and learning behavior questionnaire subjects are 60 primary school students and 300 college students, respectively.

For iris recognition in non-cooperative environments, iris segmentation has been regarded as the first most important challenge still open to the biometric community, affecting all downstream tasks from normalization to recognition. In recent years, deep learning technologies have gained significant popularity among various computer vision tasks and also been introduced in iris biometrics, especially iris segmentation. To investigate recent developments and attract more interest of researchers in the iris segmentation method, we organized the 2021 NIR Iris Challenge Evaluation in Non-cooperative Environments: Segmentation and Localization (NIR-ISL 2021) at the 2021 International Joint Conference on Biometrics (IJCB 2021). The challenge was used as a public platform to assess the performance of iris segmentation and localization methods on Asian and African NIR iris images captured in non-cooperative environments. The three best-performing entries achieved solid and satisfactory iris segmentation and localization results in most cases, and their code and models have been made publicly available for reproducibility research.

RoboSim is a tool-independent notation for modeling software simulations of robots, and it can be verified by a variety of techniques and tools, including model checking and theorem proving. RoboSim has a formal tock-CSP (Communicating Sequential Processes) semantics, and so refinement checkers, such as FDR, can be used for verification of models. In this paper, we explore the use of UPPAAL, as a well-established tool for verification of time-dependent properties. We propose a model-transformation strategy to translate RoboSim models into NTA (Network of Timed Automata) based on some patterns and mapping rules. We implement our strategy as a plug-in for the RoboSim modeling and verification tool. Using examples, we compare the verification results of UPPAAL and FDR for a series of safety, reachability, and liveness properties. Moreover, we use a robotic platform model of swarm robots in an uncertain environment, to illustrate how our approach can be extended to the verification of stochastic and hybrid systems using UPPAAL SMC. Such an extension cannot be easily conceived for The original tock-CSP semantics of RoboSim.