Data of the diabetes mellitus patients is essential in the study of diabetes management, especially when employing the data-driven machine learning methods into the management. To promote and facilitate the research in diabetes management, we have developed the ShanghaiT1DM and ShanghaiT2DM Datasets and made them publicly available for research purposes. This paper describes the datasets, which was acquired on Type 1 (n = 12) and Type 2 (n = 100) diabetic patients in Shanghai, China. The acquisition has been made in real-life conditions. The datasets contain the clinical characteristics, laboratory measurements and medications of the patients. Moreover, the continuous glucose monitoring readings with 3 to 14 days as a period together with the daily dietary information are also provided. The datasets can contribute to the development of data-driven algorithms/models and diabetes monitoring/managing technologies.

This study addresses the current lack of research on the effectiveness assessment of Artificial Intelligence (AI) technology in architectural education. Our aim is to evaluate the impact of AI-assisted architectural teaching on student learning. To achieve this, we developed an AI-embedded teaching model. A total of 24 students from different countries participated in this 9-week course, completing a comprehensive analysis of architectural programming and design using AI technologies. This study conducted questionnaire surveys with students at both midterm and final stages of the course, followed by structured interviews after the course completion, to explore the effectiveness and application status of the teaching model. The results indicate that the AI-embedded teaching model positively and effectively influenced student learning. The “innovative capability” and “work efficiency” of AI technologies were identified as key factors affecting the effectiveness of the teaching model. Furthermore, the study revealed a close integration of AI technologies with architectural programming but identified challenges in the uncontrollable expression of architectural design outcomes. Student utilization of AI technologies appeared fragmented, lacking a systematic approach. Lastly, the study provides targeted optimization suggestions based on the current application status of AI technologies among students. This research offers theoretical and practical support for the further integration of AI technologies in architectural education.

The intelligent monitoring of tool wear status and wear prediction are important factors affecting the intelligent development of the modern machinery industry. Many scholars have used deep learning methods to achieve certain results in tool wear prediction. However, due to the instability and variability of the signal data, some neural network models may have gradient decay between layers. Most methods mainly focus on feature selection of the input data but ignore the influence degree of different features to tool wear. In order to solve these problems, this paper proposes a dual-stage attention model for tool wear prediction. A CNN-BiGRU-attention network model is designed, which introduces the self-attention to extract deep features and embody more important features. The IndyLSTM is used to construct a stable network to solve the gradient decay problem between layers. Moreover, the attention mechanism is added to the network to obtain the important information of output sequence, which can improve the accuracy of the prediction. Experimental study is carried out for tool wear prediction in a dry milling operation to demonstrate the viability of this method. Through the experimental comparison and analysis with regression prediction evaluation indexes, it proves the proposed method can effectively characterize the degree of tool wear, reduce the prediction errors, and achieve good prediction results.

Internet users are benefiting from technologies of abstractive summarization enabling them to view articles on the internet by reading article summaries only instead of an entire article. However, there are disadvantages to technologies for analyzing articles with texts and images due to the semantic gap between vision and language. These technologies focus more on aggregating features and neglect the heterogeneity of each modality. At the same time, the lack of consideration of intrinsic data properties within each modality and semantic information from cross-modal correlations result in the poor quality of learned representations. Therefore, we propose a novel Inter- and Intra-modal Contrastive Hybrid learning framework which learns to automatically align the multimodal information and maintains the semantic consistency of input/output flows. Moreover, ITCH can be taken as a component to make the model suitable for both supervised and unsupervised learning approaches. Experiments on two public datasets, MMS and MSMO, show that the ITCH performances are better than the current baselines.

Blockchain-based mobile edge computing (BMEC) solves the problem of limited computing resources of devices in the Internet of Things (IoT). However, there are some security threats in the blockchain environment, among which the attacks against consensus algorithms are particularly serious, such as double-spending attacks and long-range attacks. These attacks target the block proposal or validation process, which compromise the integrity of the BMEC by overwriting the correct block record with the wrong block record. In this article,we propose a scheme to solve the above problem by using the cooperative threshold signature and group management scheme to protect the block validity. The blockchain process of a single node is controlled in a group cooperative way, and each new block is regarded as a valid block only if it has a valid threshold signature for the group to which it belongs. Concretely, the system is initialized by a cooperative distributed key generation protocol, the device management protocol uses a resident node to ensure the security and efficiency of device join and leave, and the signature issuing protocol can tolerate a certain degree of exceptions of nodes within the group. We analyze the resistance ability of the scheme against consensus attacks, prove the security of the scheme, and analyze the computing and communication efficiency. Experimental evaluations on the protocols of the proposed scheme have been conducted on cloud virtual machines and embedded boards, including Raspberry Pi and UP2 Grove, which indicated that the scheme is efficient in practical scenarios.

Video highlights are welcomed by audiences, and are composed of interesting or meaningful shots, such as funny shots. However, video shots of highlights are currently edited manually by video editors, which is inconvenient and consumes an enormous amount of time. A way to help video editors locate video highlights more efficiently is essential. Since interesting or meaningful highlights in videos usually imply strong sentiments, a sentiment analysis model is proposed to automatically recognize sentiments of video highlights by time-sync comments. As the comments are synchronized with video playback time, the model detects sentiment information in time series of user comments. Moreover, in the model, a sentimental intensity calculation method is designed to compute sentiments of shots quantitatively. The experiments show that our approach improves the F1 score by 12.8% and overlapped number by 8.0% compared with the best existing method in extracting sentiments of highlights and obtaining sentimental intensities, which provides assistance for video editors in editing video highlights efficiently.