2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)最新文献

Faint Moving Small Target Detection based on Optical Flow Method 基于光流法的微弱运动小目标检测

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778780

Yunfei Dong

引用次数: 1

Application of image enhancement based on Universal-FCMSPCNN 基于通用- fcmspcnn的图像增强应用

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778392

Jiajun Zhang, Jing Lian, Yuan Kang, Zilong Dong

{"title":"Application of image enhancement based on Universal-FCMSPCNN","authors":"Jiajun Zhang, Jing Lian, Yuan Kang, Zilong Dong","doi":"10.1109/ICSP54964.2022.9778392","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778392","url":null,"abstract":"In medical diagnosis, medical imaging technology is a potent clinical diagnosis approach. The focal examination and formation of diagnosis and treatment plans are greatly aided by the details and overall enhancement of medical images. It is critical to increase the amount of image information on the basis of high fidelity while studying image enhancement. This paper introduces a novel picture enhancement method and applies it to image processing using Pulse Coupled Neural Network (PCNN) research. Pulse coupled neural network is an artificial neural network that obtains temporal and spatial information from external stimuli and adjacent neurons. It has many unique excellent characteristics in various fields of image processing. Recently, we proposed an improved UFC-MSPCNN model based on the PCNN model. Firstly, we studied the PCNN model and MSPCNN model derived from PCNN model, and proposed this new model after analyzing its model principle and model complexity. Secondly, in our new algorithm, the synaptic weight matrix adopts a new setting method and redefines the attenuation factor α and the amplitude parameter V in the dynamic threshold. a new adjustment parameter J is defined to fine tune the dynamic threshold. Finally, we applied UFC-MSPCNN model to the image processing of left ventricular and peripheral lung cancer in the experiment. The experiment achieved good results, and the enhanced image accorded with the visual characteristics of human eyes, which proved the effectiveness of this method.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"30 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115720672","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Research on regional personnel monitoring technology based on channel state information 基于通道状态信息的区域人员监控技术研究

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778396

Kaijun Mai, Xinghua Lu, Guohua Luo, Jinglong Cheng

{"title":"Research on regional personnel monitoring technology based on channel state information","authors":"Kaijun Mai, Xinghua Lu, Guohua Luo, Jinglong Cheng","doi":"10.1109/ICSP54964.2022.9778396","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778396","url":null,"abstract":"In view of the shortcomings of traditional camera and sensor type monitoring, such as blind spots, limited recognition distance and sensitive scene limitations, this paper proposes a human activity detection and monitoring method based on channel-state-information (CSI). The CSI information of the WiFi signal in the monitored area. Next, use the Butterworth low-pass filter to detect and remove abnormal data. And then use the principal component analysis (PCA) to extract the features of the human body posture, gait information, and number of people model; Learn to build a number recognition model for CSI data; because everyone is different, gait information can be used as an ID for human identification to identify different identities, and the human gait information based on Dynamic Time Warping (DTW) can be Effective identification, so as to play the effect of regional environmental monitoring. In the experiment, this method can achieve 92% capture performance for human gesture recognition, more than 93% error in indoor area recognition is less than 1, and the correct rate of gait recognition is up to 95.2%.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"92 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123069693","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Image Deblurring Based on Generative Adversarial Networks 基于生成对抗网络的图像去模糊

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778672

Wenling Lu, Zhaohui Meng

{"title":"Image Deblurring Based on Generative Adversarial Networks","authors":"Wenling Lu, Zhaohui Meng","doi":"10.1109/ICSP54964.2022.9778672","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778672","url":null,"abstract":"Image deblurring technology uses deep learning method to solve the blurry problem of single image , which is a challenging problem in the field of computer vision. In recent years, the rapid development of deep learning and computer vision has promoted the performance of blur processing algorithm. From the perspective of deep learning, the article studies on the image deblurring problem, and uses convolution neural network to achieve the purpose of image deblurring. Aiming at the problem that the scale of single deblurring using multi-scale network is huge, and the important feature information is not fully used, this paper proposes a deblurring algorithm based on generative adversarial networks. The model uses feature pyramid network as a framework instead of the multi-scale input, which effectively reduces the size of network and accelerates the training speed. In order to make better use of feature information, the attention mechanism and dual scale discriminator are introduced into the network. In order to make the training process more stable, the algorithm improves the discriminator loss, using the least squares and relativistic combination. The experimental results show that the image deblurring algorithm based on the generative adversarial network achieves better restoration effect than other algorithms.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"100 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121832735","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Application of Risk Assessment Model for Breast Cancer 乳腺癌风险评估模型的应用

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778357

Huaizhou Yang, Tian Luo, Chenzhuo Liu

引用次数: 0

Research on back pressure control system of injection molding machine based on predictive self-learning Optimization PID algorithm 基于预测自学习优化PID算法的注塑机背压控制系统研究

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778744

Guanke Wang, Dongmo Zhang, Chun Li, Jingqi Peng, Xuan Zhang

{"title":"Research on back pressure control system of injection molding machine based on predictive self-learning Optimization PID algorithm","authors":"Guanke Wang, Dongmo Zhang, Chun Li, Jingqi Peng, Xuan Zhang","doi":"10.1109/ICSP54964.2022.9778744","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778744","url":null,"abstract":"Most of the hydraulic injection molding machines are controlled by proportional relief valves or proportional servo valves to control the pre-plastic back pressure, but due to the limitations of the relief valve and the servo valve itself, low back pressure or even zero back pressure control cannot be achieved in practical applications. This paper proposes to use a proportional direction valve instead of a relief valve and a servo valve to control the back pressure, and to control the back pressure by controlling the opening of the proportional direction valve, and a large number of simulation results show that under different back pressure conditions, the back pressure can be established quickly and smoothly. And the use of dual channel mode to connect the proportional directional valve, can achieve high flow and low pressure of the flow capacity. The system uses a pre-judgment self-learning algorithm to optimize the PID control algorithm, which can achieve rapid and subtle pressure adjustment of back pressure Simulation and system testing show that the system has good steady-state performance and dynamic quality.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"24 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121239470","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

One Improved Model of Named Entity Recognition by Combining BERT and BiLSTM-CNN for Domain of Chinese Railway Construction 结合BERT和BiLSTM-CNN的中国铁路建设领域命名实体识别改进模型

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778794

Xiaojun Wu, Tianqi Zhang, Sheng Yuan, Yuanfeng Yan

{"title":"One Improved Model of Named Entity Recognition by Combining BERT and BiLSTM-CNN for Domain of Chinese Railway Construction","authors":"Xiaojun Wu, Tianqi Zhang, Sheng Yuan, Yuanfeng Yan","doi":"10.1109/ICSP54964.2022.9778794","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778794","url":null,"abstract":"There are currently few named entity recognition (NER) models in domain of Chinese railway construction. To mitigate such awkward situation, this paper uses the neural network method to sort out the basic information from Chinese text about Chinese railway construction. Concretely, this paper proposes one improved model of NER by combining bidirectional encoder representation from transformers (BERT) and convolutional long short-term memory (LSTM) network model so as to promote the NER performance of Chinese text about Chinese railway construction. Based on deep understandings of domain knowledge about Chinese railway construction, the proposed model performs targeted processing on the input, and designs a novel masking algorithm based on Chinese placenames and numbers. The proposed model further uses bidirectional LSTM (BiLSTM) network as the encoding layer, which can leverage the feature extraction capability of the convolution neural network (CNN) to improve the NER performance. Experimental results show that the F1 value of the proposed model is 7.28% higher than the traditional conditional random field (CRF) model, and the F1 value of the BERT model with mask of Chinese placenames and numbers is 3.43% higher than the original BERT model.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"120 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127229831","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 4

Automated retinal layer segmentation of OCT images in normal and AMD eyes 正常眼和AMD眼OCT图像视网膜层自动分割

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778321

JinTao He, Wending Gu, Jiange Yin

{"title":"Automated retinal layer segmentation of OCT images in normal and AMD eyes","authors":"JinTao He, Wending Gu, Jiange Yin","doi":"10.1109/ICSP54964.2022.9778321","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778321","url":null,"abstract":"Optical coherence tomography (OCT) is a non-invasive, fast imaging technique that is widely used clinically for the diagnosis of ophthalmic diseases. It is very important to obtain quantitative retinal layer information, however, this approach is time consuming and challenging for ophthalmologists since it requires segmentation of the retinal layer in OCT images. An automated retinal layer segmentation method is proposed by employing N-sigmoid and complex diffusion filtering along with signal-noise ratio balance for pre-processing and fuzzy C-mean for clustering. Pre-processing increases the contrast between the retinal layers which eliminates the influence of speckle noise and blood vessels for later segmentation. The eigenvectors of each extremum were calculated and clustered by fuzzy C-means (FCM). The boundaries of each retinal layer were fitted using RANSAC and then retinal layer segmentation of the retina in the fundus OCT images was achieved. The proposed method can accurately obtain five retinal layers in OCT images affected by spackle noise, low image contrast and irregularly shaped structural features such as blood vessels.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"36 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127267566","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

MFENet: Multi-Feature Extraction Net for Remote Sensing Semantic Segmentation 遥感语义分割的多特征提取网络

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778622

Chao Zhang, Xin Lu, Q. Ye, Chao Wang, Chuan-Sheng Yang, Quanqing Wang

{"title":"MFENet: Multi-Feature Extraction Net for Remote Sensing Semantic Segmentation","authors":"Chao Zhang, Xin Lu, Q. Ye, Chao Wang, Chuan-Sheng Yang, Quanqing Wang","doi":"10.1109/ICSP54964.2022.9778622","DOIUrl":"https://doi.org/10.1109/ICSP54964.2022.9778622","url":null,"abstract":"In this paper, we tackle the remote sensing semantic segmentation task by capturing feature information across multiple scales, all channels, and global locations. Different from previous works that simply use U-net to extract multi-scale features, we further improve U-net and propose a Multi-Feature Extraction Network (MFE-Unet). Specifically, we propose the MFE module, which uses both dilated convolution module and two attention modules. Dilated convolution is used to enhance U-net’s ability to represent multi-scale information. The two attention modules refer to the channel attention module and the pixel attention module. Channel attention maps all channels centrally, assigns weights uniformly, and adaptively adjusts the importance of each channel’s information. Pixel attention treats features at each location as the same individual, and similar features will be associated together to further improve feature representation. We conducted multiple sets of experiments on the \"AI+\" remote sensing image dataset. Experiments show that our network is sufficient against several advanced models.","PeriodicalId":363766,"journal":{"name":"2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP)","volume":"25 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-04-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124991083","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

Parameter tuning of active disturbance rejection control based on improved differential evolution algorithm 基于改进差分进化算法的自抗扰控制参数整定

2022 7th International Conference on Intelligent Computing and Signal Processing (ICSP) Pub Date : 2022-04-15 DOI: 10.1109/ICSP54964.2022.9778308

Like Gao, Xiaofeng Guo, D. Mei, Zhigang Qu

引用次数: 1