Search

This paper proposed a method for the residency of the RT-Thread real-time operating system based on the general embedded computer(GEC) architecture to address the issues of slow compilation speed and poor reusability caused by the complexity of the real-time operating system kernel in embedded applications. On the basis of reasonable storage space allocation, the method achieved the sharing of interrupt service routines, providing users with function call services for both low-level drivers and software application layers. Finally, the residency method was tested using the D1-H application processor as an example. And the results demonstrate that it achieves physical isolation between the system kernel and application programs, resulting in shorter compilation time and higher development efficiency. This method provides a foundation for the timeliness, convenience, and simplicity of embedded program development. [ABSTRACT FROM AUTHOR]

Considering the existing spinal Computer Tomography（CT） and Magnetic Resonance（MR） image segmentation models have limitations in segmentation performance, this paper proposes a spinal segmentation method MAU-Net based on U-shaped network. Frist, this paper introduces coordinate attention module into the encoder of Ushaped network, which enables the network accurately capture the spatial position information and embed it into the channel attention. Second, this paper proposes dual-branch channel cross fusion module based on Transformer, it can replace the skip connection for multi-scale feature fusion. Finally, this paper proposes a feature fusion attention module to better fuse the semantic differences between Transformer and convolution network. On scoliosis CT dataset, Dice reached 0.9296, IoU reached 0.8597. On the public MR dataset SpineSagT2 Wdataset3, compared with FCN, Dice improved by 14.46%. Experimental results show that this method can effectively reduce the false segmentation area of vertebrae. [ABSTRACT FROM AUTHOR]

Aiming at computer resources was limited and the total overhead of the system processing tasks was too high, this paper proposed an offloading strategy based on dynamic perception-hybrid artificial fish swarm（DP-HAFS） algorithm. First, it constructed a "local-edge-cloud" three-layer network architecture and adopted a fine-grained partial offloading mode; then, for the scenario where a terminal device covered by multiple base stations, this paper proposed a base station selection strategy to select the optimal base station; finally, it used the DP-HAFS algorithm to dynamically modify the unloading decision and got the best uninstall strategy. The simulation results show that the proposed offloading strategy can effectively reduce the total system overhead in a scenario with a large number of tasks. [ABSTRACT FROM AUTHOR]

Ternary optical computer（TOC） is a new architecture computer with a large number of processor bits and the characteristics of easily scaling, reconfigurable bit functions, and groupable bits. It has great potential for fast processing of massive or complex data. However, it is still in the early stage of application development exploration. To expand its application, this paper proposed a TOCSim design scheme for a simulator based on a ternary optical computer architecture. It simulates the TOC operation process in the form of software and implements its prototype on an ordinary PC. These operation processes mainly include the TOC processor reconfiguration strategy, processor bit allocation strategy, intermediate result decoding, and computing effect simulation. A comparison of the simulation effect graphs derived from the simulator proposed in this paper between the light graphs of the operation results on the TOC prototype shows that the design scheme of the simulator is correct and feasible. [ABSTRACT FROM AUTHOR]

Intelligent question answering based on reading comprehension refers to letting computers read and comprehend texts like humans, extracts the text information and answers corresponding questions. The pre-training model RoBERTa-wwm-ext uses the extracted original fragments as the answers to the questions, but this method can’t solve the two situations that the answer fragments don’t exist in the original text or need to reply to the original text after summarizing. The pre-training model is used for generative model training, which can solve the problems that need to summarize the original text to a certain extent. Therefore, this paper improved the method of only using RoBERTa-wwm-ext model to extract answers. On this basis, it integrated the generative question answering model based on RAG model to answer questions that could not be handled by Roberta-wwm-ext and other extraction models. At the same time, this paper absorbed the advantages of PGN model, improved RAG model, and obtained RPGN sub model, which could make better use of reading and understanding articles to generate reasonable answers. Therefore, this paper proposed a fusion model of RPR（RAG, PGN, RoBERTa-wwm-ext）,which could be used to deal with both extractive question task and generative question answering task at the same time. [ABSTRACT FROM AUTHOR]

Object tracking is an important topic in computer visual directions, where scale changes, deformation and rotation are difficult to resolve in the field. For the challenging problems faced in the above track, based on existing Siamese network algorithms, this paper proposed multi-layer feature fusion and parallel self-attention Siamese networks (MPSiamRPN) for visual tracking. Firstly, MPSiamRPN used the modified ResNet50 to extract features from the template image and the search image. In order to deal with the loss of some features caused by the deep network, it proposed a multi-layer feature fusion module to fuse the features of the last three layers of ResNet. Secondly, it introduced the parallel self-attention module, which was composed of channel self-attention and spatial self-attention. The channel self-attention could selectively emphasize the beneficial channel features for tracking, and the spatial self-attention could learn the rich spatial information of the target. Finally, it proposed the region proposal network ( RPN) to perform classification and regression operations to determine the location and shape of the target. Experiments show that the MPSiamRPN can achieve competitive results on OTBlOO and VOT2018 test datasets. [ABSTRACT FROM AUTHOR]

Perturbation of chaotic system can effectively solve the degradation of chaotic system dynamic characteristics caused by computer finite precision effect. This paper proposed parameter perturbation scheme for digital chaotic system based on the construction method of Cantor set in interval mapping. This scheme spread the sequence values obtained from each iteration of chaotic system proportionally to the compressed interval of chaotic state parameters, so as to achieve the purpose of disturbing chaotic sequence. The experimental simulation and analysis show that the chaotic system with disturbance has better chaotic characteristics, larger parameter range and higher complexity. [ABSTRACT FROM AUTHOR]

Based on the theory of conceptual metaphor, this paper discusses the formation and characteristics of conceptual metaphor in the computer field and its influence on human thinking. The functions of the human brain and the expressions and related concepts used to describe these functions are applied to the computer, thus conceptual metaphor concerning the computer come into being. Conceptual metaphor in the field of computer, which is not only of universality but also of systematization, reflects human’s cognition of the computer and also influences human’s thinking mode to cognize the world. The study of this kind of conceptual metaphor can deepen our understanding of computer science and widen the research field of metaphor cognitive function as well. [ABSTRACT FROM AUTHOR]

In order to achieve an accurate description of the urban road network morphology, the morphological characteristics of the road network are divided into two categories: geometric shape and topological structure for analysis. For each type of structural characteristics, corresponding quantitative description indicators and calculation methods are proposed, combined with the computer aided analysis techniques such as Origin and DepthMapX, this paper quantitatively analyzes and compares 8 samples of 4 types of road networks which are common in modem cities and displayed in different development stages. The results show that: (1) compared with the traditional or single - type indicator research, the two types of indicators further show the difference between the internal relationship and composition of the road network. The effect is particularly significant when distinguishing the road network in the historical old city and the road network in the peripheral area. (2) There is a mutual feedback effect between the two types of morphological characteristics : the cell rate, integration and intelligibility show a certain positive correlation. (3) The naturally formed road network appears to have a structure complex, but easier to understand after topological deformation. [ABSTRACT FROM AUTHOR]

Recently,researchers pay more and more attentions for automatic or semi-automatic music generation based on computer algorithm.With the further development of deep learning,researchers start to focus on producing high-quality and multifarious-style music with neural network and priori knowledge of music theory.Furthermore,several works introduced generative adversarial network(GAN) to try to improve the quality of the results.To summarize the important results in this area is meaningful and with guiding significance for the following works.This paper firstly reviewed the history of intelligent music,then listed related GAN model that are commonly applied in music creation,after that it analyzed some important works in this area.Finally,it presented some observations,and prospected future work direction. [ABSTRACT FROM AUTHOR]

As for the drivers' eye open degree changing due to fatigue, this paper proposed a finite state machine based on PERCLOS algorithm and applied to pre-warning system of fatigue driving according to the original PERCLOS standards. Firstly, it used infrared camera to capture drivers' face in real time and detected face by ASM algorithm. To avoid the influence of the distance between man and camera, it normalized eye open degree when it was calculated. Then it obtained PERCLOS value by the proposed finite state machine based method. Finally, the eye open degree based system pre-warns the fatigue according to the established pre-warning mechanism. The experiment results show that this method can monitor drivers' fatigue status in real time and it is insensitive to light and drivers' accessories. [ABSTRACT FROM AUTHOR]