Recently, directed by Prof. Song Yan, Dr. Li Ming, who majors in Control Science and Engineering from School of Optical-electrical and Computer Engineering, won the best paper in the 23rd IEEE International Conference on Industrial Technology, IEEE IES ICIT 2022. The first author is Dr. Li Ming, USST is the first unit and Prof. Song Yan is the corresponding author.
With the rapid development of information technology, geographical information collection and location sensing internet have become widespread. While wireless sensor networks are composed of a large number of wireless sensor devices, as these wireless sensors are located underground, undersea or blocks crowded with tall buildings, the wireless signal can become declined and inaccessible. Distance information of a large number of modes in wireless sensor seems like a high-dimensional, aimless and sparse network, so it is necessary to accurately estimate much unknown information by mining limited information in the network to achieve the precise positioning of measured objects.
Hence, they put forward an idea of latent factor model under multiple rating patterns in the paper. By constructing auxiliary level matrix, coupled with the data information in multiple contexts, the latent information can be mined through transfer laerning. With the learning method of alternating updates, the training speed of the model is accelerated, and the precise prediction of the model for missing information is improved. Finally, simulation experiments were carried out on the real data set for seabed positioning. The results show that the model proposed in this paper significantly appears better than the existing model, and the estimated data is more close to the real one. This research discovery will provide a great help for computer to accurately draw the earth map, which can be used in many fields such as industry, military affairs, agriculture, biology, medical treatment, economy and solution to issues like UAV formation, commodity recommendation, medical system health management.
