Pub Date : 2018-12-01DOI: 10.1109/IICSPI.2018.8690428
Xiaofeng Lu, Caidi Xu
Moving object detection is the focus of research and application in the field of computer vision. Background subtraction method is one of the most commonly used methods for moving object detection, in which moving objects in image sequences are detected by comparison of the background model with the current frame. In the process of moving object detection, there are many challenges, such as the interference of clutter background, the influence of illumination, noise and shadow. In this paper, a novel Gaussian mixture model background subtraction method based on wavelet blocks is proposed for the challenge of object detection. This method can not only reduce the influence of illumination, noise and shadow, but also adapt to the dynamic change of natural scene. The contribution lies in the following aspects: (1) A Gaussian background modeling method with less running time is proposed in the background modeling stage. The background is reconstructed based on Gaussian mixture model (GMM) of the mean images of image blocks, aiming to simplify the calculations so as to improve the speed of the corresponding operations. (2) In the foreground detection stage, a wavelet-based de-noising method with the semi-soft threshold function is applied to de-noise the object images of the foreground. Experimental results show that the computational complexity is reduced, while the adaptability and performance are improved by using the proposed method. It was more efficient and robust than traditional approaches.
{"title":"Novel Gaussian mixture model background subtraction method for detecting moving objects","authors":"Xiaofeng Lu, Caidi Xu","doi":"10.1109/IICSPI.2018.8690428","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690428","url":null,"abstract":"Moving object detection is the focus of research and application in the field of computer vision. Background subtraction method is one of the most commonly used methods for moving object detection, in which moving objects in image sequences are detected by comparison of the background model with the current frame. In the process of moving object detection, there are many challenges, such as the interference of clutter background, the influence of illumination, noise and shadow. In this paper, a novel Gaussian mixture model background subtraction method based on wavelet blocks is proposed for the challenge of object detection. This method can not only reduce the influence of illumination, noise and shadow, but also adapt to the dynamic change of natural scene. The contribution lies in the following aspects: (1) A Gaussian background modeling method with less running time is proposed in the background modeling stage. The background is reconstructed based on Gaussian mixture model (GMM) of the mean images of image blocks, aiming to simplify the calculations so as to improve the speed of the corresponding operations. (2) In the foreground detection stage, a wavelet-based de-noising method with the semi-soft threshold function is applied to de-noise the object images of the foreground. Experimental results show that the computational complexity is reduced, while the adaptability and performance are improved by using the proposed method. It was more efficient and robust than traditional approaches.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":"1 1","pages":"6-10"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91526482","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}
Pub Date : 2018-12-01DOI: 10.1109/IICSPI.2018.8690516
Y. Yong
When the heart sounds reach the chest wall surface through mediated tissue, it is prone to generate noise, which can reduce the accuracy of pathological diagnosis. A new denoising method for heart sound signal based on wavelet transform is proposed. First of all, the information signal is transformed by multi-scale wavelet. The wavelet coefficients of each scale indicate a distribution sequence of probability according to the corresponding wavelet entropy threshold to find the maximum entropy of wavelet on certain interval, and the interval is recognized as the leading range of noise. And then, a fixed threshold denoising method is used to adaptively enhance the judgment about absolute value with larger attenuation wavelet coefficients, which can reduce the high frequency sound signal loss and improve the heart sound signal to noise ratio. The denoising simulation experiment is carried out to test the performance. The result shows that the proposed method can improve the output signal to noise ratio of heart sound signal, reducing the influence of noise on the extraction of heart sound signal, and therefore, the noise elimination algorithm has stronger anti-interference ability and superior performance.
{"title":"Denoising Processing of Heart Sound Signal Based on Wavelet Transform","authors":"Y. Yong","doi":"10.1109/IICSPI.2018.8690516","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690516","url":null,"abstract":"When the heart sounds reach the chest wall surface through mediated tissue, it is prone to generate noise, which can reduce the accuracy of pathological diagnosis. A new denoising method for heart sound signal based on wavelet transform is proposed. First of all, the information signal is transformed by multi-scale wavelet. The wavelet coefficients of each scale indicate a distribution sequence of probability according to the corresponding wavelet entropy threshold to find the maximum entropy of wavelet on certain interval, and the interval is recognized as the leading range of noise. And then, a fixed threshold denoising method is used to adaptively enhance the judgment about absolute value with larger attenuation wavelet coefficients, which can reduce the high frequency sound signal loss and improve the heart sound signal to noise ratio. The denoising simulation experiment is carried out to test the performance. The result shows that the proposed method can improve the output signal to noise ratio of heart sound signal, reducing the influence of noise on the extraction of heart sound signal, and therefore, the noise elimination algorithm has stronger anti-interference ability and superior performance.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":"20 1","pages":"251-255"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90535078","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}
Pub Date : 2018-12-01DOI: 10.1109/IICSPI.2018.8690519
Huang Youjun, Wu Haiyang, Yu Ran, Li Chao
With the continuous development of information technology, applying automatic learning and self-learning methods such as machine learning and neural networks to the knowledge acquisition process of the knowledge base, becomes the trend and direction of the current knowledge base development. This paper describes the development of the self-learning knowledge base and technical methods, and practices the whole process of the database construction, neural network construction, neural network training process, experimental application of self-learning knowledge base, achieves the desired goal. It lays the foundation for the construction and practice of the self learning knowledge base in the broader knowledge field.
{"title":"Application of Power Grid Communication Operation and Maintenance Knowledge Base Based on Self-learning Technology","authors":"Huang Youjun, Wu Haiyang, Yu Ran, Li Chao","doi":"10.1109/IICSPI.2018.8690519","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690519","url":null,"abstract":"With the continuous development of information technology, applying automatic learning and self-learning methods such as machine learning and neural networks to the knowledge acquisition process of the knowledge base, becomes the trend and direction of the current knowledge base development. This paper describes the development of the self-learning knowledge base and technical methods, and practices the whole process of the database construction, neural network construction, neural network training process, experimental application of self-learning knowledge base, achieves the desired goal. It lays the foundation for the construction and practice of the self learning knowledge base in the broader knowledge field.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":"40 1","pages":"396-402"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80654941","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}
Pub Date : 2018-12-01DOI: 10.1109/IICSPI.2018.8690356
L. Li, Ge Chen
A self-adaptive Sigma-Delta modulator, which offers opportunity to simplify the process of tuning parameters and further improve the noise performance, is presented in this paper. Traditional Sigma-Delta modulator mainly focused on using a 2nd order sensing element to improve the SNR, whereas this paper presents a 5th order Sigma-Delta modulator to obtain higher SNR. Specifically, an additional 3rd order digital loop integrator is inserted between the AFE and the quantizer, which increases overall loop order to produce much higher SNR for Sigma-Delta modulator and the parameters of the 3rd order digital loop integrator are optimized by swarm intelligent algorithm. Simulation results with respect to the proposed 5th order Sigma-Delta modulator, SNR >122 dB and the noise floor under -170dB are obtained in frequency range of [5-150Hz]. In further simulation, the robustness of the proposed 5th order Sigma-Delta modulator is analyzed.
{"title":"Designing and Optimizing of Sigma-Delta Modulator Using PSO Algorithm","authors":"L. Li, Ge Chen","doi":"10.1109/IICSPI.2018.8690356","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690356","url":null,"abstract":"A self-adaptive Sigma-Delta modulator, which offers opportunity to simplify the process of tuning parameters and further improve the noise performance, is presented in this paper. Traditional Sigma-Delta modulator mainly focused on using a 2nd order sensing element to improve the SNR, whereas this paper presents a 5th order Sigma-Delta modulator to obtain higher SNR. Specifically, an additional 3rd order digital loop integrator is inserted between the AFE and the quantizer, which increases overall loop order to produce much higher SNR for Sigma-Delta modulator and the parameters of the 3rd order digital loop integrator are optimized by swarm intelligent algorithm. Simulation results with respect to the proposed 5th order Sigma-Delta modulator, SNR >122 dB and the noise floor under -170dB are obtained in frequency range of [5-150Hz]. In further simulation, the robustness of the proposed 5th order Sigma-Delta modulator is analyzed.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":"53 1","pages":"642-644"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78183489","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}
Pub Date : 2018-12-01DOI: 10.1109/IICSPI.2018.8690518
Fu Zou, Chuanchang Liu, Zhiyuan Su
This paper presents a method for the realization of hidden Wi-Fi auto-connect system based on android ROM-Level. Under this system, two Android devices can establish a Wi-Fi connection at a specific time, and do not display a Wi-Fi icon when the connection is successfully established. Among them, write the program of BroadcastReceiver in the Android framework layer to realize the control and management of Wi-Fi module, modify Android native calculator program to achieve user configuration function, and modify system application of SystemUI to realize the function of shielding Wi-Fi icon. Since the code is written based on the ROM-Level and the entire process is user-insensitive, the system maintains a high security and can provide new application scenarios.
{"title":"Hidden Wi-Fi Auto-connecting System Based on Android ROM-Level","authors":"Fu Zou, Chuanchang Liu, Zhiyuan Su","doi":"10.1109/IICSPI.2018.8690518","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690518","url":null,"abstract":"This paper presents a method for the realization of hidden Wi-Fi auto-connect system based on android ROM-Level. Under this system, two Android devices can establish a Wi-Fi connection at a specific time, and do not display a Wi-Fi icon when the connection is successfully established. Among them, write the program of BroadcastReceiver in the Android framework layer to realize the control and management of Wi-Fi module, modify Android native calculator program to achieve user configuration function, and modify system application of SystemUI to realize the function of shielding Wi-Fi icon. Since the code is written based on the ROM-Level and the entire process is user-insensitive, the system maintains a high security and can provide new application scenarios.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":"52 1","pages":"711-714"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"88804513","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}
Pub Date : 2018-12-01DOI: 10.1109/IICSPI.2018.8690387
Lirong Yao, Yazhuo Guan
Natural language processing technology is widely used in artificial intelligence fields such as machine translation, human-computer interaction and speech recognition. Natural language processing is a daunting task due to the variability, ambiguity and context-dependent interpretation of human language. The current deep learning technology has made great progress in NLP technology. However, many NLP systems still have practical problems, such as high training complexity, computational difficulties in large-scale content scenarios, high retrieval complexity and lack of probabilistic significance. This paper proposes an improved NLP method based on long short-term memory (LSTM) structure, whose parameters are randomly discarded when they are passed backwards in the recursive projection layer. Compared with baseline and other LSTM, the improved method has better F1 score results on the Wall Street Journal dataset, including the word2vec word vector and the one-hot word vector, which indicates that our method is more suitable for NLP in limited computing resources and high amount of data.
{"title":"An Improved LSTM Structure for Natural Language Processing","authors":"Lirong Yao, Yazhuo Guan","doi":"10.1109/IICSPI.2018.8690387","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690387","url":null,"abstract":"Natural language processing technology is widely used in artificial intelligence fields such as machine translation, human-computer interaction and speech recognition. Natural language processing is a daunting task due to the variability, ambiguity and context-dependent interpretation of human language. The current deep learning technology has made great progress in NLP technology. However, many NLP systems still have practical problems, such as high training complexity, computational difficulties in large-scale content scenarios, high retrieval complexity and lack of probabilistic significance. This paper proposes an improved NLP method based on long short-term memory (LSTM) structure, whose parameters are randomly discarded when they are passed backwards in the recursive projection layer. Compared with baseline and other LSTM, the improved method has better F1 score results on the Wall Street Journal dataset, including the word2vec word vector and the one-hot word vector, which indicates that our method is more suitable for NLP in limited computing resources and high amount of data.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":"20 1","pages":"565-569"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80885029","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}
Pub Date : 2018-12-01DOI: 10.1109/IICSPI.2018.8690495
Junhui Lai, Guorong Chen
With the rapid development of China’s economy, innovation and interconnection of all things are widely mentioned, and family intelligence has begun to develop. However, due to the high cost, the promotion of family intelligence is limited. Considering the single function of traditional alarm clock and the depressed market, this paper proposes to design a multi-function early morning wake-up system, which can make the alarm clock multi-functional and low-cost. In this way, ordinary families can experience intelligent products, which is conducive to the promotion of family intelligence. The multi-function wake-up system sets the wake-up time through the mobile phone APP, thus triggering the alarm clock of the lower Computer to open and the pressure sensor to collect the pressure value. When the pressure is kept within a certain range for a period of time, the alarm clock can be switched off. At the same time, it can also remotely control the opening and closing of curtains, the opening and closing of lights and so on, which is more convenient for people’s life, but also increases the family “intelligence”. The system is divided into software module and hardware module. The hardware module mainly includes pressure sensor module, stepper motor module and WiFi module, with STM32 development board to control each hardware module; the software module is based on the Android platform development of mobile APP, and users can login through the mobile APP, connect to the server, send instructions to the lower Computer, set the wake-up time, etc. The terminal code is written in C language, compiled on Keil uVision platform, and the mobile terminal is compiled on Eclipse platform in Java language. The system test meets the requirements of the system, which is scientific and feasible.
{"title":"Multi-function Morning Wake-up System","authors":"Junhui Lai, Guorong Chen","doi":"10.1109/IICSPI.2018.8690495","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690495","url":null,"abstract":"With the rapid development of China’s economy, innovation and interconnection of all things are widely mentioned, and family intelligence has begun to develop. However, due to the high cost, the promotion of family intelligence is limited. Considering the single function of traditional alarm clock and the depressed market, this paper proposes to design a multi-function early morning wake-up system, which can make the alarm clock multi-functional and low-cost. In this way, ordinary families can experience intelligent products, which is conducive to the promotion of family intelligence. The multi-function wake-up system sets the wake-up time through the mobile phone APP, thus triggering the alarm clock of the lower Computer to open and the pressure sensor to collect the pressure value. When the pressure is kept within a certain range for a period of time, the alarm clock can be switched off. At the same time, it can also remotely control the opening and closing of curtains, the opening and closing of lights and so on, which is more convenient for people’s life, but also increases the family “intelligence”. The system is divided into software module and hardware module. The hardware module mainly includes pressure sensor module, stepper motor module and WiFi module, with STM32 development board to control each hardware module; the software module is based on the Android platform development of mobile APP, and users can login through the mobile APP, connect to the server, send instructions to the lower Computer, set the wake-up time, etc. The terminal code is written in C language, compiled on Keil uVision platform, and the mobile terminal is compiled on Eclipse platform in Java language. The system test meets the requirements of the system, which is scientific and feasible.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":"1 1","pages":"108-112"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"90752573","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}
Pub Date : 2018-12-01DOI: 10.1109/IICSPI.2018.8690361
Kulyakwave P.D, Shiwei Xu, Wen Yu
This study was conducted to develop econometric models for weather variables for Shinyanga region of Tanzania. The developed models used to predict missing weather variables such as sunshine, maximum, and minimum temperatures from 1981 to 1987. The authors used weather time series data including rainfall, sunshine, maximum, and minimum temperatures from 1981 to 2017 to establish statistical relationship among variables from Mbeya and Shinyanga regions. Various statistical methods used include Ordinary Least Square regression, Augmented Dickey-Fuller test for Unit root test of time series stationarity, Johansen Cointegration test and error correction to establish relationship among variables. We developed three econometric models for missing sunshine, maximum and minimum variables for Shinyanga region. Sunshine model shows that for each unit rainfall (mm) increase in Mbeya region increased the sunshine for Shinyanga by 3.8%, while for each increase in lmm rainfall in Shinyanga region the sunshine decreases by 1%. Maximum temperature model reveals that increase in rainfall in Mbeya by lmm decreases the maximum temperature by 0.5 % while for each increase by lmm rainfall in Shinyanga leads to a decrease of maximum temperature by 0.7%. For the minimum temperature model, 1 mm increase in both Mbeya and Shinyanga rainfall decreases the minimum temperature for Shinyanga by 0.4 % while increase in 1°C minimum temperature for Mbeya region increases Shinyanga minimum temperature by 43%. Accordingly, we estimated the missing variables by the use of the respective constructed models.
本研究的目的是建立坦桑尼亚辛扬加地区天气变量的计量经济模型。开发的模式用于预测1981年至1987年缺少的天气变量，如日照、最高和最低温度。作者利用1981年至2017年的降雨、日照、最高气温和最低气温等天气时间序列数据，建立了Mbeya和Shinyanga地区变量之间的统计关系。使用的统计方法有:普通最小二乘回归、增强型Dickey-Fuller检验时间序列平稳性的单位根检验、Johansen协整检验和误差修正来建立变量之间的关系。我们建立了新阳加地区缺失日照、最大和最小变量的三个计量模型。日照模式表明，Mbeya地区每增加单位降雨量(mm)，新阳加地区的日照增加3.8%，而新阳加地区每增加单位降雨量(mm)，日照减少1%。最高温度模型表明，Mbeya降雨量每增加1mm，最高温度降低0.5%，而Shinyanga降雨量每增加1mm，最高温度降低0.7%。对于最低温度模型，Mbeya和Shinyanga地区的降雨量每增加1 mm, Shinyanga地区的最低温度降低0.4%，而Mbeya地区的最低温度每增加1°C, Shinyanga地区的最低温度升高43%。因此，我们通过使用各自构建的模型来估计缺失变量。
{"title":"Econometric Modelling for Missing Weather Variables Estimation: Shinyanga Region of Tanzania","authors":"Kulyakwave P.D, Shiwei Xu, Wen Yu","doi":"10.1109/IICSPI.2018.8690361","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690361","url":null,"abstract":"This study was conducted to develop econometric models for weather variables for Shinyanga region of Tanzania. The developed models used to predict missing weather variables such as sunshine, maximum, and minimum temperatures from 1981 to 1987. The authors used weather time series data including rainfall, sunshine, maximum, and minimum temperatures from 1981 to 2017 to establish statistical relationship among variables from Mbeya and Shinyanga regions. Various statistical methods used include Ordinary Least Square regression, Augmented Dickey-Fuller test for Unit root test of time series stationarity, Johansen Cointegration test and error correction to establish relationship among variables. We developed three econometric models for missing sunshine, maximum and minimum variables for Shinyanga region. Sunshine model shows that for each unit rainfall (mm) increase in Mbeya region increased the sunshine for Shinyanga by 3.8%, while for each increase in lmm rainfall in Shinyanga region the sunshine decreases by 1%. Maximum temperature model reveals that increase in rainfall in Mbeya by lmm decreases the maximum temperature by 0.5 % while for each increase by lmm rainfall in Shinyanga leads to a decrease of maximum temperature by 0.7%. For the minimum temperature model, 1 mm increase in both Mbeya and Shinyanga rainfall decreases the minimum temperature for Shinyanga by 0.4 % while increase in 1°C minimum temperature for Mbeya region increases Shinyanga minimum temperature by 43%. Accordingly, we estimated the missing variables by the use of the respective constructed models.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":"1 1","pages":"411-415"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"85917089","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}
Pub Date : 2018-12-01DOI: 10.1109/IICSPI.2018.8690416
Liao Jidong, Zhang Ran
Tree boosting is a highly effective and widely used machine learning method. A dynamic weighting multi-factor stock selection strategy based on XGBoost model is constructed. XGboost machine learning method is used to predict the IC coefficients of factors. The results of back testing show that the performance of dynamic weighting strategy is superior to the equal weighting strategy and IC weighting strategy. The empirical results prove that XGBoost model is effective in predicting IC coefficients and the dynamic weighting based on XGBoost model can improve the performance of multi-factor stock selection strategy.
{"title":"Dynamic Weighting Multi Factor Stock Selection Strategy Based on XGboost Machine Learning Algorithm","authors":"Liao Jidong, Zhang Ran","doi":"10.1109/IICSPI.2018.8690416","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690416","url":null,"abstract":"Tree boosting is a highly effective and widely used machine learning method. A dynamic weighting multi-factor stock selection strategy based on XGBoost model is constructed. XGboost machine learning method is used to predict the IC coefficients of factors. The results of back testing show that the performance of dynamic weighting strategy is superior to the equal weighting strategy and IC weighting strategy. The empirical results prove that XGBoost model is effective in predicting IC coefficients and the dynamic weighting based on XGBoost model can improve the performance of multi-factor stock selection strategy.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":"70 1","pages":"868-872"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"86301072","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}
Pub Date : 2018-12-01DOI: 10.1109/IICSPI.2018.8690445
Song Luqing, Hu Wenjin, Liu Kaishu, W. Xiaogang, Song Lepeng
Aiming at the characteristics of large lag, strong interference, nonlinearity and difficult pressure control in pressure controlled drilling, this paper designs an automatic control system for pressure controlled drilling without model adaptive control. The automatic control system consists of signal input device, pressure controlled drilling electronic control unit, actuator and other devices. In order to improve the speed and stability of pressure control in pressure drilling, a model-free adaptive control scheme is proposed. The control scheme only needs on-line I/O data of the controlled system to complete the design of the controller, which has strong resistance to nonlinearity and is suitable for more complicated control projects. The system is modeled and simulated in MATLAB. The experimental results show that compared with cascade PID control, the pressure regulating time of the automatic control system of pressure controlled drilling using model-free adaptive control scheme is shorter and the pressure change curve is smoother, which can better meet the control requirements of the automatic control system of pressure controlled drilling.
{"title":"Application of Model -Free Adaptive Control in Managed Pressure Drilling","authors":"Song Luqing, Hu Wenjin, Liu Kaishu, W. Xiaogang, Song Lepeng","doi":"10.1109/IICSPI.2018.8690445","DOIUrl":"https://doi.org/10.1109/IICSPI.2018.8690445","url":null,"abstract":"Aiming at the characteristics of large lag, strong interference, nonlinearity and difficult pressure control in pressure controlled drilling, this paper designs an automatic control system for pressure controlled drilling without model adaptive control. The automatic control system consists of signal input device, pressure controlled drilling electronic control unit, actuator and other devices. In order to improve the speed and stability of pressure control in pressure drilling, a model-free adaptive control scheme is proposed. The control scheme only needs on-line I/O data of the controlled system to complete the design of the controller, which has strong resistance to nonlinearity and is suitable for more complicated control projects. The system is modeled and simulated in MATLAB. The experimental results show that compared with cascade PID control, the pressure regulating time of the automatic control system of pressure controlled drilling using model-free adaptive control scheme is shorter and the pressure change curve is smoother, which can better meet the control requirements of the automatic control system of pressure controlled drilling.","PeriodicalId":6673,"journal":{"name":"2018 IEEE International Conference of Safety Produce Informatization (IICSPI)","volume":"52 1","pages":"102-107"},"PeriodicalIF":0.0,"publicationDate":"2018-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"84486150","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：