{"title":"Driver Fatigue State Detection Based on Facial Key Points","authors":"N. Zhang, Hui Zhang, Jun Huang","doi":"10.1109/ICSAI48974.2019.9010478","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010478","url":null,"abstract":"The proportion of drivers causing traffic accidents due to fatigue driving has been increasing year by year, which has become one of the main causes of traffic accidents. Therefore, accurate and effective detection of driver fatigue is a hot research topic at present. In this article, the driver's head posture estimation based on face key points is used to judge fatigue. Firstly, the face image is collected from the camera in real time. The model-based method is used to estimate the head posture of the person. The face key points method based on the Dlib library is used to judge the eye state, the mouth state, the head turning posture of the person. The experimental results show that the head pose estimation method based on face key points can accurately judge the fatigue state, and has good real-time and accuracy.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"56 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129266957","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}
{"title":"Adaptive alternating current transcranial electrical stimulation (tACS)","authors":"Dong Guo, Huiyan Li, Minghui Sun","doi":"10.1109/ICSAI48974.2019.9010378","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010378","url":null,"abstract":"Traditional deep brain stimulation (DBS) has been proven effective in the treatment of neurological diseases, especially Parkinson's disease (PD), but the deep brain stimulation system can be further optimized to maximize therapeutic benefits. This paper proposes a programmable adaptive transcranial electrical stimulation, which consists of LFP acquisition circuit, TACS stimulation circuit and adaptive closed-loop control algorithm. Compared with the traditional deep brain electrical stimulation for Parkinson's disease, adaptive ac transcranial electrical stimulation for Parkinson's disease (PD) has a better effect, and the application of advanced technology and treatment program is expected to achieve better clinical effect, save the time of regulation and avoid side effects.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"38 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116412064","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}
{"title":"Face Attribute Transformation Based On ConStarGAN","authors":"Qi Zhang, Jun Du, Jin Yu","doi":"10.1109/ICSAI48974.2019.9010448","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010448","url":null,"abstract":"Many models are able to transform styles by input images, such as Variational autoencoder (VAEs) and Generative adversarial networks (GANs), which have recently been applied to image style and domain transfer. In this paper, we propose a method based on unified generative adversarial networks for multi-domain image-to-image translation (StarGAN) to solve face attribute transfer problem—ConStarGAN. Given a face image, our model can extract the region of interest and transform multiple attributes in this region while keeping other features unchanged. So as to minimize the impact factor on the generated image and make it look very realistic. In our model, we present new loss function. Then, the image is segmented to avoid the influence of background, illumination and other factors, and spectral normalization is used to improve the quality of generated images. Experimental compared with the stability of relevant GAN models. Results show that we proposed model has achieved good results in face attribute translation. Finally, the effect of the improved model is illustrated through the effect analysis experiment.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115683656","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}
Jinbo Fang, Mingxian Guo, Xusheng Gu, Xiuying Wang, Shoubiao Tan
{"title":"Digital instrument identification based on block feature fusion SSD","authors":"Jinbo Fang, Mingxian Guo, Xusheng Gu, Xiuying Wang, Shoubiao Tan","doi":"10.1109/ICSAI48974.2019.9010235","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010235","url":null,"abstract":"In order to identify digital instrument characters 0∼9 and decimal point in different scenarios, a digital instrument recognition algorithm based on block feature fusion SSD is proposed. Because the identification of small targets is difficult, in order to preserve the spatial information of small targets, the algorithm first divides the low-dimensional feature map into blocks and then fuses with the backbone network during the feature extraction phase. Secondly, in the prediction stage, the high-dimensional feature map is deconvoluted and then merged with the low-dimensional features to obtain the feature map with both spatial information and semantic information. Finally, the prediction result is passed through the character processing module to obtain the final representation. The experimental results show that compared with the original SSD, the algorithm improves the AP (Average Precision) of the decimal point by 30% and the mAP (Mean Average Precision) by 5.8%. It can accurately identify many different instrument representations in different environments and is robust enough to meet practical applications.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"150 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115306766","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}
Wanqing Wu, Lipo Wang, Chunlei Ji, Niansheng Chen, Qiang Sun, Xiaoyong Song, Xin Wang, Junjie Yang, Jie Yang, WenZhan Song, Xiaochun Cheng, S. Hu, Weiming Zeng, Ming Chen, Haijun Wang, Hongrong Wang, Charles Yang
{"title":"2019 6th International Conference on Systems and Informatics","authors":"Wanqing Wu, Lipo Wang, Chunlei Ji, Niansheng Chen, Qiang Sun, Xiaoyong Song, Xin Wang, Junjie Yang, Jie Yang, WenZhan Song, Xiaochun Cheng, S. Hu, Weiming Zeng, Ming Chen, Haijun Wang, Hongrong Wang, Charles Yang","doi":"10.1109/icsai48974.2019.9010230","DOIUrl":"https://doi.org/10.1109/icsai48974.2019.9010230","url":null,"abstract":"","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"5 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116164074","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}
{"title":"Application of Wavelet Soft Threshold Denoising Algorithm Based on EMD Decomposition in Vibration Signals","authors":"Biao Sun, Shaoping Zhou, Congyi Wang","doi":"10.1109/ICSAI48974.2019.9010456","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010456","url":null,"abstract":"This paper proposes the wavelet threshold noise reduction algorithm based on Empirical Mode Decomposition (EMD) to solve the problems of centrifugal pump vibration signal complex, exist various frequency band non-single interference signal and useful signal amplitude is small, etc. The algorithm combines the adaptive characteristics of EMD decomposition and the time-frequency localization characteristics of wavelet threshold denoising algorithm. While simplifying the noise reduction process, it can effectively deal with non-single interference signals in each frequency band. In order to verify the applicability of this algorithm, it is compared with wavelet threshold noise reduction algorithm and spatial-temporal filtering analysis method. Finally, the influence of soft and hard threshold functions on the noise reduction effect is analyzed. The experimental results show that the wavelet soft threshold denoising algorithm based on EMD decomposition has better noise reduction effect when the centrifugal pump vibration signal is used as the noise reduction object.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114111126","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}
{"title":"Fault Analysis of Wind Turbine Gearbox Based on Vague Set and Fault Tree","authors":"Hongyan Zhu, Xiaojin Fu","doi":"10.1109/ICSAI48974.2019.9010177","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010177","url":null,"abstract":"Aiming at the high failure rate of gearbox-main components of wind turbine and the limitation of single diagnosis method, this paper proposes a fault diagnosis method based on the generalized set of the fuzzy set-the vague set, which combines the vague set and the fault tree. It is introduced into the fault tree model. The triangular Vague set defined on [0], [1] is used to describe the normal, failure and abnormal behavior of bottom events. Based on the fault tree model of the vague set, the qualitative and quantitative analysis of system faults is made. The vague fuzzy operator is used to calculate the importance of each bottom event and judge the weak links of the system. Finally, a wind power gearbox fault example is simulated. The simulation results show that the proposed method is more flexible and practical than the fuzzy fault tree model.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"7 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125455676","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}
{"title":"A Method for Human Parsing Based on Deep Learning and Attention Mechanism","authors":"Rui Yang, Chaobing Huang","doi":"10.1109/ICSAI48974.2019.9010094","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010094","url":null,"abstract":"Human parsing is thought as a specific image semantic segmentation task. Most existing methods adopt encoder- decoder framework, and make full use of global context to achieve better image segmentation effect. A model is proposed in this paper which uses Convolutional Block Attention Module to select more discriminate feature and refinement residual learning to learn residual representation between input and output. The experiment results shows that our proposed model can achieve better performance on our dataset than other networks. From the generated human body segmentation images, the model can achieve more details and semantic consistency.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"23 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126628955","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}
Xiangwei Kong, Peng Wang, Xiaoya Li, Wei Liu, Huiyang Hu, Zhongjie Wang, Hong Li
{"title":"Prediction Method of Aeroengine Residual Life Based on Stacked Sparse Automatic Encoder","authors":"Xiangwei Kong, Peng Wang, Xiaoya Li, Wei Liu, Huiyang Hu, Zhongjie Wang, Hong Li","doi":"10.1109/ICSAI48974.2019.9010091","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010091","url":null,"abstract":"In order to ensure the safe and reliable operation of the aircraft, improve the efficiency of aviation engine maintenance and improve the prediction accuracy of the remaining life of the aeroengine, a prediction method of the remaining life of the aeroengine based on the stacked sparse self- coding neural network is proposed. The method firstly constructs a plurality of self-encoding networks to form a deep stack self- encoding network, selects the state data of the engine as the training input of the network, and enables the network to extract the distributed rules between the data layer by layer intelligently, thereby constructing the engine degraded stack self-encoding learning. model. The BP residual neural network is used to classify the remaining life of the engine as a result of engine residual life prediction. Finally, the algorithm is validated by the PHM2008 aeroengine degradation data. The results show that the method can effectively predict the remaining life of the aeroengine.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128196569","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}
{"title":"Regionalization Intelligent Garbage Sorting Machine for Municipal Solid Waste Treatment","authors":"Hongyi Luo, J. Sa, Ruibin Li, Jin Li","doi":"10.1109/ICSAI48974.2019.9010575","DOIUrl":"https://doi.org/10.1109/ICSAI48974.2019.9010575","url":null,"abstract":"The rapid development of China's economy brings increasing garbage and ensuring contamination, raising worries about citizens' welfare and local biodiversity. In an attempt to solve the problem, we designed an intelligent garbage classifier with accurate garbage identification method, efficient separation system and intelligent control system. This device can effectively help identify recyclable waste and then reduce toxic gases produced by burning garbage.","PeriodicalId":270809,"journal":{"name":"2019 6th International Conference on Systems and Informatics (ICSAI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-11-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125814184","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}