Research Progress

• 07/11 -2023-
  SIA Researchers Made Progress in Predictive Modeling of Complex Industrial Data

  In view of the problems of insufficient data and algorithm cold start in the modeling process of complex industries such as metallurgy, big data research group under Digital Factory Department of Shenyang Institute of Automation (SIA), the Chinese Academy of Sciences (CAS) has proposed a prediction method of industrial process time series based on dynamic Transfer learning under limited data volume. This method aims at improving multi-step time series prediction accuracy and reducing calculation costs.
• 07/06 -2023-
  Study on Intelligent Maintenance and Management of Industrial Equipment Achieved Progress

  A research team from Shenyang Institute of Automation (SIA) of the Chinese Academy of Science (CAS) proposed a novel spatiotemporal feature learning-based framework, where the data are first segmented and an augmented matrix is constructed to form the featured information containing spatial dependencies and temporal correlations.
• 06/16 -2023-
  Bubble Detection in Photoresist with Small Samples Based on GAN Augmentations and Modified YOLO

  A research team led by Prof. YANG Zhijia from the Shenyang Institutes of Automation of the Chinese Academy of Sciences has developed image augmentation method based on adversarial generative network (GAN) for the limited number of samples, which was used for detecting bubbles in the photoresist during semiconductor manufacture.
• 05/30 -2023-
  A Geometry-Aware Deep Network for Depth Estimation in Monocular Endoscopy

  A research team led by Professor LIU Hao from the Shenyang Institute of Automation (SIA) of the Chinese Academy of Science (CAS) proposed a novel geometry-aware depth estimation framework, which combined the strengths of the gradient and normal losses and geometry consistency loss. The framework enforced the geometric consistency constraints and boosted the reconstruction performance for stepped edge and frequently fluctuations structures. In addition, Liu's team introduced a synthetic RGB-D dataset tailored for interventional endoscopy.
• 04/07 -2022-
  New Correlative AFM and Scanning Microlens Microscopy for Time-Efficient Multiscale Imaging

  With the rapid evolution of microelectronics and nanofabrication technologies, the critical feature sizes of large-scale integrated circuits continue to move toward the nanoscale. There is a strong need to improve the quality and efficiency of integrated circuit inspection, but it remains a great challenge to provides both rapid imaging and circuit node-level high-resolution images simultaneously using a conventional microscope.
• 03/17 -2022-
  Researchers propose new design perspective for more efficient manufacturing system

  Zeng's team proposed a codesign method that considers the design spaces of architecture, control and scheduling as monolithic, mixed discrete-continuous spaces. They formulate DSE as an optimization problem and propose a generic iterative algorithm scheme involving simulation in the loop to solve the above new problem.
• 01/27 -2022-
  Chinese Scientists Develop Highly-sensitive Mid-infrared Detection via BGSe Crystal

  Experimental studies have been implemented and in case of ns-pulse detection, such a system is at least 100 times more sensitive than the HgCdTe detector. AJ-level pulses have been detected successfully. The dynamic range of the system is over 110 dB and the response is quite uniform over 3-8 μm, both parameters above outperform classical detection methods. Moreover, the performance can be improved further in future.
• 12/31 -2021-
  Research on emergency escape system of underground mine based on mixed reality technology

  With the continuous development of the mining industry and the continuous advancement of science and technology, increasing new technical methods have been applied in the field of mine safety. In order to solve the problems of backwardness and inefficiency in the traditional disaster avoidance methods of mines, a three-dimensional modeling technique was used to establish a mixed reality model of disaster avoidance in Yanqianshan mine.
• 12/31 -2021-
  Multilevel feature fusion dilated convolutional network for semantic segmentation

  Recently, convolutional neural network (CNN) has led to significant improvement in the field of computer vision, especially the improvement of the accuracy and speed of semantic segmentation tasks, which greatly improved robot scene perception. In this article, we propose a multilevel feature fusion dilated convolution network (Refine-DeepLab).
• 12/31 -2021-
  A method for the automatic detection of myopia in Optos fundus images based on deep learning

  Myopia detection is significant for preventing irreversible visual impairment and diagnosing myopic retinopathy. To improve the detection efficiency and accuracy, a Myopia Detection Network (MDNet) that combines the advantages of dense connection and Residual Squeeze-and-Excitation attention is proposed in this paper to automatically detect myopia in Optos fundus images.