In recent years, deep learning has been applied in the field of clinical medicine to process large-scale medical images, for large-scale data screening, and in the diagnosis and efficacy evaluation of various major diseases. Multi-modal medical data fusion based on deep learning can effectively extract and integrate characteristic information of different modes, improve clinical applicability in diagnosis and medical evaluation, and provide quantitative analysis, real-time monitoring, and treatment planning. This study investigates the performance of existing multi-modal fusion pre-training algorithms and medical multi-modal fusion methods and compares their key characteristics, such as supported medical data, diseases, target samples, and implementation performance. Additionally, we present the main challenges and goals of the latest trends in multi-modal medical convergence. To provide a clearer perspective on new trends, we also analyzed relevant papers on the Web of Science. We obtain some meaningful results based on the annual development trends, country, institution, and journal-level research, highly cited papers, and research directions. Finally, we perform co-authorship analysis, co-citation analysis, co-occurrence analysis, and bibliographic coupling analysis using the VOSviewer software.

Aiming at the high reliability demand of increasingly large and complex supercomputing systems, this paper proposes a multidimensional fusion CBA-net (CNN-BiLSTAM-Attention) fault prediction model based on HDBSCAN clustering preprocessing classification data, which can effectively extract and learn the spatial and temporal features in the predecessor fault log. The model can effectively extract and learn the spatial and temporal features from the predecessor fault logs, and has the advantages of high sensitivity to time series features and sufficient extraction of local features, etc. The RMSE of the model for fault occurrence time prediction is 0.031, and the prediction accuracy of node location for fault occurrence is 93% on average, as demonstrated by experiments. The model can achieve fast convergence and improve the fine-grained and accurate fault prediction of large supercomputers.

This paper presents a Quadrature Charge-Sampling Phase Detector PLL(QCSPLL) with low jitter and low reference spur. To address the issues of phase detection gain ambiguity and prolonged re-lock time in sub-sampling PLL, this paper employs a quadrature signal charge sampling gain compensation technique. A phase detector design that utilizes charge sampling and master-slave sampling is adopted, which achieves low reference spur while maintaining low in-band noise. QCSPLL uses a divider to provide four-phase signals. The divider also replaces the VCO buffer while generating the four-phase signal. QCSPLL is realized using a 28nm CMOS process. Simulation results show that the proposed QCSPLL has advantages in re-lock time. The re-lock time is improved by 63%. The prototype achieves 123-fs RMS jitter(10K-100M), -62.4dBc reference spur (without VCO buffer) and -255.2 dB FoM.

High baud rate optical transceiver based on time division multiplexing technology is proposed. A communication channel at 80GBoud with 4 bit streams at 20Gbps is realized by 4-stage cascaded high speed switches with synchronous drivers.