Yongguo Jiang

Trajectory-User Linking (TUL) is crucial for human mobility modeling by linking different trajectories to users with the exploration of complex mobility patterns. Existing works mainly rely on the recurrent neural framework to encode the temporal dependencies in trajectories, have fall short in capturing spatial-temporal global context for TUL prediction. To fill this gap, this work presents a new hierarchical spatio-temporal attention neural network, calledAttnTUL, to jointly encode the local trajectory transitional patterns and global spatial dependencies for TUL. Specifically, our first model component is built over the graph neural architecture to preserve the local and global context and enhance the representation paradigm of geographical regions and user trajectories. Additionally, a hierarchically structured attention network is designed to simultaneously encode the intra-trajectory and inter-trajectory dependencies, with the integration of the temporal attention mechanism and global elastic attentional encoder. Extensive experiments demonstrate the superiority of our AttnTUL method as compared to state-of-the-art baselines on various trajectory datasets. The source code of our model is available athttps://github.com/Onedean/AttnTUL.

How to implement the construction of hardware course group for complex engineering problems in the context of the New engineering education certification in China, taking the cultivation of Computer System Capability as an example, through a series of courses that connect before and after, with the teaching objective of "one CPU, one OS, one compiler, and one Computer System", highlighting the primary issues; Enhancing students’ capacity to analyze and resolve complex engineering problems from a system perspective, as well as consistently seeking out greater system capabilities. In order to target reform strategies for complex engineering problems, the "student-centered" method continuously researches and evaluates numerous complex engineering challenges that are faced in classroom trials. In maritime universities in China, it is hoped that the practical application of engineering education certification will be useful.

With the rapid development of technology, enterprises are striving to improve production and efficiency by adopting and popularizing new technological methods. However, the teaching in schools still predominantly focuses on traditional technical knowledge. In response to the problem of the mismatch between school education and industry demands, we conducted research on existing training programs and had multiple discussions with enterprises to analyze the main issues. Based on this, we proposed a solution and developed a collaborative model for Industry-Education Integration training programs. Following this model, we designed undergraduate course/practice matrices aligned with the knowledge framework recommended by ACM and IEEE CS, and constructed exemplary courses according to the requirements outlined in the matrices. This approach offers a higher granularity and operability compared to conventional industry-academia integration programs. The practical application of this model has yielded positive learning outcomes. Through our proposed solution and design, we have made significant progress in addressing the gap between schools and enterprises. The collaborative model for Industry-Education Integration training programs establishes a closer cooperation mechanism between schools and enterprises, ensuring the alignment of educational knowledge with industry requirements. The development of exemplary courses provides students with learning content that better meets actual industry needs, enhancing their practical skills and employability. The practical application of this model has demonstrated favorable outcomes, providing robust support for the collaboration between schools and enterprises.

In recent years, with the diversification of people’s modes of transportation, a large amount of traffic data is generated when people travel every day, and this data can help transportation mode detection to be of great use in a variety of applications. Although transportation mode detection has been investigated, there are still challenges in terms of accuracy and robustness. This paper presents a novel transportation mode detection algorithm, DFTrans, which is based on Temporal Block and Attention Block. Low- and high-frequency components of traffic sequences are obtained using discrete wavelet transforms. A two-channel encoder is carefully designed to accurately capture the temporal and spatial correlation between low- and high-frequency components in both long- and short-term patterns. With the Temporal Block, the inductive bias of the CNN is introduced at high frequencies to improve generalization performance. At the same time, the network is generated with the same length as the input, ensuring a long effective history. Low frequencies are passed through Attention Block, which has fewer parameters to capture the global focus and solves the problem that RNNs cannot be computed in parallel. After fusing the output of the feature by Temporal Block and Attention Block, the classification results are output by MLP. Extensive experimental results show that the DFTrans algorithm achieves macro F1 scores of 86.34% on the real-world SHL dataset and 87.64% on the HTC dataset. Our model can better identify eight modes of transportation, including stationary, walking, running, cycling, bus, car, underground, and train, and has better performance in transportation mode detection than other baseline algorithms.

In recent years, with the development of science and technology, people have more and more choices for daily travel. However, assisting with various mobile intelligent services by transportation mode detection has become more urgent for the refinement of human activity identification. Although much work has been done on transportation mode detection, accurate and reliable transportation mode detection remains challenging. In this paper, we propose a novel transportation mode detection algorithm, namely T2Trans, based on a temporal convolutional network (i.e., TCN), which employs multiple lightweight sensors integrated into a phone. The feature representation learning of multiple preprocessed sensor data using temporal convolutional networks can improve transportation mode detection accuracy and enhance learning efficiency. Extensive experimental results demonstrated that our algorithm attains a macro F1-score of 86.42% on the real-world SHL dataset and 88.37% on the HTC dataset, with an average accuracy of 86.37% on the SHL dataset and 89.13% on the HTC dataset. Our model can better identify eight transportation modes, including stationary, walking, running, cycling, car, bus, subway, and train, with better transportation mode detection accuracy, and outperform other benchmark algorithms.

Distributed measurement systems (DMSs) are widely adopted to assist the design and testing of household appliances. Unfortunately, a reference model rarely rules the development of those systems, leading to poor software quality and bringing many troubles in the process of maintenance and integration. Furthermore, the development of measurement systems often suffers from low efficiency due to the complex programming and debugging process. To address the aforementioned issues, we first present a universal reference model serving as a foundation in the design of DMSs, particularly for the household appliance testing industry. The model provides the design criteria and methodologies of DMSs in terms of data collection and management. Then, according to the model, an interactive platform is built to facilitate the software development of DMSs for both local and web-based applications. The platform consists of the reusable component libraries, the client-based assembly subsystem, the web-based assembly subsystem, the data collection subsystem, and the customization subsystem. The software development process for measurement systems is turned into configuring parameters through interactive dialog boxes. The development efficiency and performance of the system generated by the platform are evaluated. Moreover, the model and platform are validated by various development cases for manufacturing enterprises. The results demonstrate that the model is feasible and that the platform remarkably improves the development efficiency and software quality.