Vehicle steering control method based on machine learning

In this paper, the effectiveness of the genetic algorithm-based back propagation (GABP) neural network model and its application to the breakout prediction in the continuous casting process are investigated. The formation of the sticking-type breakouts and the prediction principle of thermocouple thermometry method are analysed firstly. Then the genetic algorithm-based back propagation neural network model is proposed by fusing genetic algorithm (GA), and error back propagation neural network to offset the demerits of one paradigm by the merits of another. Finally, the GABP neural network model is applied to the breakout prediction in the continuous casting process; and the feasibility of the model is verified by the testing result with the accuracy rate of 97.56% and the prediction rate of 100%.

In view of emerging applications of alpha+beta titanium alloys in aerospace and defense, we have aimed to develop a Back propagation neural network (BPNN) model capable of predicting the properties of these alloys as functions of alloy composition and/or thermomechanical processing parameters. The optimized BPNN model architecture was based on the sigmoid transfer function and has one hidden layer with ten nodes. The BPNN model showed excellent predictability of five properties: Tensile strength (r: 0.96), yield strength (r: 0.93), beta transus (r: 0.96), specific heat capacity (r: 1.00) and density (r: 0.99). The developed BPNN model was in agreement with the experimental data in demonstrating the individual effects of alloying elements in modulating the above properties. This model can serve as the platform for the design and development of new alpha+beta titanium alloys in order to attain desired strength, density and specific heat capacity.

Aiming at the shortcomings of the low efficiency optimization algorithm and the tendency to fall into the local optimal solution in the existing shallow sea geoacoustic parameters inversion research, a shallow sea geoacoustic parameters inversion method based on the Back Propagation (BP) neural network model is proposed. First, the theoretical prediction value of the shallow sea sound pressure field is obtained through the Fast Field Method (FFM). Then the mapping relationship between the predicted sound pressure field and the geoacoustic parameters value to be inverted is established according to the BP neural network model. Finally, the measured sound pressure field data is brought into the neural network to obtain the inversion results. The experimental results show that, compared with the classic simulated annealing (Simulated Annealing, SA) algorithm, the BP neural network model converts the data matching process of the optimization algorithm into the construction of a relational model, avoiding multiple matching optimization processes for the inversion results, and the inversion results can be output directly, accurately, and efficiently. Under the premise of setting the same accuracy, the calculation time of the BP neural network model for the inversion result is shortened, and the number of iterations is reduced to 5% of the SA algorithm.

PDF HTML阅读 XML下载 导出引用 引用提醒 1988-2013年基于BP神经网络的植被叶面积指数遥感定量反演 DOI: 10.5846/stxb201703290547 作者: 作者单位: 南京林业大学,南京林业大学,南京林业大学,南京林业大学,南京林业大学,南京林业大学 作者简介: 通讯作者: 中图分类号: 基金项目: 国家重点研发计划资助项目（2017YFC0505505）；国家自然科学基金项目（31200534）；江苏高校优势学科建设工程资助项目；2014年江苏省普通高校学术学位研究生科研创新计划项目 Quantitative inversion of long sequential leaf area index using remote sensing based on BP neural network from 1988 to 2013 Author: Affiliation: Key Laboratory of Soil and Water Conservation and Ecological Restoration in Jiangsu Province,Collaborative Innovation Center of Sustainable Forestry in Southern China of Jiangsu Province,Nanjing Forestry University,Nanjing,Key Laboratory of Soil and Water Conservation and Ecological Restoration in Jiangsu Province,Collaborative Innovation Center of Sustainable Forestry in Southern China of Jiangsu Province,Nanjing Forestry University,Nanjing,Key Laboratory of Soil and Water Conservation and Ecological Restoration in Jiangsu Province,Collaborative Innovation Center of Sustainable Forestry in Southern China of Jiangsu Province,Nanjing Forestry University,Nanjing,Key Laboratory of Soil and Water Conservation and Ecological Restoration in Jiangsu Province,Collaborative Innovation Center of Sustainable Forestry in Southern China of Jiangsu Province,Nanjing Forestry University,Nanjing,Key Laboratory of Soil and Water Conservation and Ecological Restoration in Jiangsu Province,Collaborative Innovation Center of Sustainable Forestry in Southern China of Jiangsu Province,Nanjing Forestry University,Nanjing,Key Laboratory of Soil and Water Conservation and Ecological Restoration in Jiangsu Province,Collaborative Innovation Center of Sustainable Forestry in Southern China of Jiangsu Province,Nanjing Forestry University,Nanjing Fund Project: 摘要 | 图/表 | 访问统计 | 参考文献 | 相似文献 | 引证文献 | 资源附件 | 文章评论 摘要:叶面积指数（Leaf Area Index，LAI）高度综合了植被水平覆盖状况和垂直结构，以及枯枝落叶层厚薄和地下生物量多少，是植被影响土壤侵蚀的主要方面。区域尺度的时间序列叶面积指数揭示了区域土壤侵蚀的演化过程。因此，及时准确地掌握区域尺度上长时间序列的植被LAI，对研究土壤侵蚀动态变化与植被的关系至关重要。选择南京市1988-2013年10期遥感影像，基于反向传播（Back Propagation，BP）神经网络构建LAI反演模型，进行了长时间序列的叶面积指数反演。结合2009和2010年LAI实测值，验证与探讨了该模型的评价精度与适应性。结果表明：（1）该模型拟合度较高，2009和2010年平均相对误差、均方根误差、相关系数分别是0.2395和0.2174，0.2962和0.2581，0.7713和0.6844，各项精度评价指标均较好；（2）统计分析去除耕地后全市LAI变化，低植被覆盖（LAI<2）面积不断增加，高植被覆盖区（LAI>3）面积先减少后增加，耕地面积不断减少，符合南京市的发展变化规律；（3）主城区LAI年际变化与其他学者得到的南京市植被盖度变化趋势一致，反演结果的时序性较高。本文提出的基于反向传播神经网络模型反演长时间序列LAI是可行的，为区域尺度土壤侵蚀定量遥感监测提供新途径。 Abstract:Leaf Area Index(LAI) can reflect the horizontal coverage, vertical structure of vegetation, the thickness of the litter layer and the amount of underground biomass, which is the main aspect of vegetation affecting soil erosion. It is very important to monitor the changes in the amount of soil erosion, for useful information to guide the planning of soil and water conservation, protect the soil and water resources and control the soil erosion. Therefore, the method by which we obtain high quality and long sequential LAI at a regional scale is very important for analyzing the relationship between the dynamic changes in soil erosion and vegetation. Previous studies showed that the neural network had an incomparable superiority in terms of complex, nonlinear data fitting and pattern recognition, and had been successfully applied to inverse the LAI in Nanjing based on the multi-spectral remote sensing data derived from the Landsat 8 Operational Land Imager(OLI), four types of vegetation indices(Normalized Difference Vegetation Index, NDVI; Ratio Vegetation Index, RVI; Soil-adjusted Vegetation Index, SAVI; Modified Soil adjusted Vegetation Index, MSAVI), and measured LAI data. The results showed that the accuracy of retrieval was good. In this paper, we used the Back Propagation(BP) neural network model to inverse the LAI in Nanjing during 1988-2013 based on the data derived from Landsat 8 OLI and Landsat 5 Thematic Mapper(TM). Based on the measured values of LAI in 2009 and 2010, the evaluation accuracy and adaptability of the model were verified and discussed. The results showed that:(1) The model had a fitting of higher degree, and average relative errors(MAPE), root mean square errors(RMSE), and correlation coefficients(R) in 2009 and 2010 of 0.2395 and 0.2174, 0.2962 and 0.2581, and 0.7713 and 0.6844, respectively. Each accuracy evaluation index was good.(2) Following statistical analysis, we found that the low vegetation coverage area(LAI < 2) exhibited an increasing trend, the high vegetation coverage area(LAI > 3) presented a first decreasing and then increasing trend, while the cultivated land area decreased with the rapid development in Nanjing.(3) To analyze accurately the LAI, we extracted the LAI in the main urban area, and found that there was a relatively high inversion value, and the inter-annual change in LAI was consistent with the change in vegetation coverage in Nanjing reported by other studies. Therefore, we could see that the BP neural network model had a high accuracy for the time series LAI inversion. It provides a new way for quantitative remote sensing monitoring of regional soil erosion. Moreover, because of other potential limiting factors, such as the errors produced by the BP neural network model, the large area of the inversion area, the complexity of vegetation types and community structure, etc., the inversion accuracy of LAI through remote sensing still needs to be explored, and the inversion method improved. We will try to establish a multi-angle LAI inversion method to construct the coupling model of LAI and soil erosion or quantitative fusion of multi-source remote sensing images in the future study. 参考文献 相似文献 引证文献

This paper presents two space detected Global Positioning System (GPS)signals reflected off sea ice and compares the returned power profiles with independent estimates of ice concentration provided by the Advanced Microwave Scanning Radiometer (AMSR-E) and sea ice charts from the National Ice Center. The results of the analysis show significantly different signals received for each of the GPS reflections. For the first collection,comparisons with ice concentration estimates from AMSR-E and the National Ice Centers reveal a very strong GPS signal return off high concentration sea ice. The second GPS data collection occurs over a region of changing sea ice concentration, and the GPS signal level responds at roughly the same point that the AMSR-E data and National Ice Center charts indicate a change in ice concentration. However, the very strong signal of the first GPS collection is not consistent in magnitude with similar ice concentrations during the secondGPS data collection. This demonstration shows the potential and the difficulties of this new technique as a valuable low-cost compliment to existing sea ice monitoring instruments. Additionally, a general method for calculating the location of the specular reflection point on the Earth’s surface and the received Doppler frequencies and code phase delays is presented as part of an on-board open-loop signal tracking technique.

Improving the resilience of enterprise safety production is one of the important ways to deal with the frequency of safety accidents. Based on the definition of enterprise safety production resilience, we fully consider the impacts of recovery resilience, self-organizing resilience, and learning resilience as the three dimensions of enterprise safety production resilience. We build a back propagation (BP) neural network model that analyzes the main factors of enterprise safety production resilience using the results of gray relational analysis as an input that can assess the resilience of enterprise safety production and provide a valuable reference for the improvement of an enterprise’s safety production level. The results show that the resilience of production safety obviously increased after the Chinese enterprises with low resilience (as predicted by the model) adopted the corresponding early warning methods. The gray relational degree analysis method can incorporate well the variables for the establishment of the BP neural network prediction model.

To study drivers’ driving behaviour in dilemma zones at signalized intersections, dilemma zones at signalized intersections are taken as the research objects. Based on analyzing the driving characteristics of motor vehicles. And collect the driving behavior parameters of video observations and road parameters of field observations, take these parameters as the factors which influence the drivers’ decision, conduct the significance analysis with SPSS(Statistical Product Service Solutions) for significant influencing factors, and then take these factors as the input value of BP(Back Propagation) neural network model, BP neural network model is set up and tested based on TensorFlow in Python. The prediction model of drivers’ decision-making in dilemma zone of signalized intersections under different speed limits is obtained, the research shows that the lower the speed limit, the better the accuracy of the intersection prediction. Further verified by comparison with the prediction model of drivers’ decision-making based on binary logistic, the accuracy of different prediction models is analyzed based on actual driver decisions.

: Software GPS receiver development has been undertaken. We are particularly interested in improving the GPS signal-to-noise/interference ratio using beam forming techniques. The phase relationship among the antenna array elements requires careful calibration. In this study, we will report a phase calibration technique for a 2 by 2 GPS antenna array using both simulated and real GPS signals. This technique is based on the GPS signal-processing algorithm developed for the software GPS receiver. A four-channel digital data collecting system was used in the experiment. For a simulated GPS signal, the experiment was conducted in an anechoic chamber in which a GPS simulation system was facilitated. For real GPS signals, we conducted the experiment on a rooftop to receive the signal from GPS satellites. The calibration verified the coherent nature of the signals among the elements. The results also allowed the source's direction to be determined.

The global positioning system (GPS) signal that is transmitted from satellite to receiver will be disturbed and degraded in the atmosphere layers due to many factors affecting the signal quality, especially in the ionosphere layer which is an ionised layer in upper atmosphere. Ionospheric scintillation and Total Electron Content (TEC) depletions are the most famous factors that can cause serious effects on GPS signal. This research investigates and analyses the measurement of the ionospheric amplitude scintillation and TEC depletions at quiet and disturbed day. The other parameters involved on this study are the carrier-to-noise (C/No) ratio, and rate of change of TEC (ROT). Data from GISTM receiver at UKM station for minimum solar cycle event were analysed on 5 April 2010 (quiet day) and 7 January 2010 (disturbed day); whereas, data from GISTM for maximum solar cycle event were analysed on 7 October 2015 (quiet day) and 2 June 2015 (disturbed day). The solar cycle event affected on the GPS signal especially when this event increased, so the analysis of ionospheric scintillation during maximum solar cycle event was compared with minimum solar cycle event to investigate the differences between these solar cycle events. The ionospheric scintillation and TEC variations are affected by solar cycle. Results showed that the ionospheric scintillation and TEC variations increased during maximum solar cycle event.

Food flavor analysis 4.0: A cross-domain application of machine learning

The car navigation service has opened through the global positioning system (GPS). People's lives have changed through car navigation services, and this service is indispensable nowadays. GPS provides reliable location accuracy in open space, but its location accuracy is degraded where multipath and other error factors are present. In particular, since GPS signals must be received in order to calculate the position, the navigation system cannot calculate the position in an indoor space such as underground parking lot, subway or tunnel where GPS signals are cut off. When car navigation is performed in an indoor parking lot where GPS signals are not transmitted, the user cannot calculate the current location, so the user has to go out by relying on the traffic sign because he does not know the current location. Also, when the user leave the parking lot, the car navigation system has problems. In an urban canyon, it is difficult to calculate accurate current position due to multipath. Because the route is calculated through the current location and route, the car navigation system provides the wrong route to the user. In addition, when entering a tunnel while using car navigation, the car navigation system calculates the position using the initial tunnel entry velocity estimated by the GPS. As the speed of the user increases or decreases, the position error also increases. Then the position suddenly changes when passing through the tunnel. And it is difficult to provide a proper guidance at the branch road or exit in the tunnel because of the positioning error. People are demanding a complete car navigation service, but the current navigation service provides the wrong route and position information to the user where the GPS signal quality is poor. In order to solve the above problem, in this paper, we have studied to improve the user's position accuracy by using LTE signal and mobile phone internal sensor. In general, observed time difference of arrival (OTDOA) technique is applied for the LTE based positioning. Because this method gives tens of meters of error, it is difficult to be used for the car navigation service. In our research, we estimate the position using the LTE signal strength. The difference from conventional fingerprinting method is that instead of using only current signal strength, the signal strength pattern accumulated while moving is utilized to estimate the user position. The signal strength increases as the user approach the access point (AP), and decreases as the user move away from the AP. Therefore, when a user moves and stores signal strength with respect to a specific AP, a pattern that could occur only in the corresponding region is saved. There are many similar candidates in the database when using only the current signal strength. However, when using a pattern, similar candidates exist only around the true position. And, when using several LTE signals, the positioning accuracy could be increased. Since the user receives multiple LTE signals, the pattern becomes surface. The surface is compared with the database, and the position with the highest correlation value is estimated as the current position. We call this method surface correlation (SC). In order to verify the performance of the proposed method, experiments were conducted in the Gangnam beltway tunnel in Seoul. The testbed consisted of three tunnel and total distance is almost 11.8 Km. In the tunnel, repeater and several antennas are installed to widen the area of the LTE signal. When an LTE signal is received by the vehicle, the largest signal strength is received every time when the vehicle passes the nearest antenna. As a result, for a specific LTE signal, when the vehicle has passed through the LTE signal region, a unique pattern with multiple peaks is generated. In order to estimate the position, we first estimate the position with the SC technique. Then, the estimated position is corrected by comparing the peak of the currently received pattern with the peak of the database. Through this method, the position was estimated with an error of less than 50meter in the tunnel. Conclusion In this research, the LTE signal strength based positioning technology is presented. Especially, this technology, SC, provides the positioning performance that could be used for the car navigation in the tunnel where GPS signal is blocked. We expected that user would be use the accurate car navigation service through this technology in the GPS challenging environment.

Modeling UF fouling and backwash in seawater RO feedwater treatment using neural networks with evolutionary algorithm and Bayesian binary classification

India is ranked 120th among 122 countries globally in WaterAid&amp;#8217;s water quality index. Regular water quality monitoring is essential to determine which inland water bodies are experiencing depreciating water quality. Long-term trends have been obtained using satellite remote sensing, necessitating multiple image analysis. The computational burden of processing numerous satellite images can be reduced using Google Earth Engine&amp;#8217;s (GEE) cloud computing capabilities. Thorough research was conducted to determine the global spatio-temporal and biochemical factors impacting surface water quality (WQ). The public availability of geospatial datasets and free access to cloud-based geo-computing platforms such as GEE are widely used for spatio-temporal mapping, global surface water monitoring, water quality parametric variation, and real-time forecasting. Many researchers have recently focused on improving data mining and machine learning algorithms to accurately deal with image classification and predictive problems for crop identification and monitoring. In the present study, we propose to define band spectral ratios, spectral band equations, and empirical models for water quality parameters. A few neural network models will be used to (i) query and pre-process satellite earth observations that coincide with the study area, (ii) extract the spectra, and (iii) use spectral band wavelength charts, time-series charts, spatial-distribution maps, and the development of an online dashboard application to visualize the results graphically upon using integrated Landsat (8,9), Sentinel-2A/B and PlanetScope satellite data for the pre-monsoon and post-monsoon seasons in 2023 in the pan-India region. MODIS-TERRA provides LST spatial-temporal monitoring. In this, we have assessed and compared the performance of CART, SVM, and RF ML algorithms. We found that RF outperforms CART and SVM algorithms in the GEE platform with PlanetScope data (80.71% overall accuracy (OA) with Kappa 0.89) and also with the integration of PlanetScope and Sentinel-2A/B data (OA = 85.53%, Kappa 0.91). But CART outperforms RF and SVM algorithms with Sentiel-2A/B data (OA = 81.59%, Kappa 0.85). The SAM technique, spectral feature fitting, continuum band removal, and other band-spectral ratio techniques are employed for quantitative hyperspectral data analysis. Specifically, the performance metrics of XGBoost and SGD for both Chl-a (R^2 = 0.818) and Turbidity (R^2 = 0.815) models exhibited robust accuracy. We have also developed a Google API-based JavaScript code that can be tested under complex coastal shores, challenging inundation and variable climatic conditions. Our method provides the end-to-end cloud computing workflow shown in this research, considering cost and computational efficiency for timely information delivery.Keywords: Classification and Regression Trees (CART), Chlorophyll-a (conc), Color dissolved organic matter (CDOM), Composite water management index (CWMI), Environmental Mapping and Analysis Program (EnMAP), Land Surface Temperature (LST), Machine Learning (ML), Random Forest (RF), Spectral Angle Mapper (SAM), Stochastic Gradient Descent (SGD), Support Vector Machine (SVM), Total Suspended Solids (TSS), Water Quality (WQ), XGBoost (Extreme Gradient Boosting).

Autonomous driving is essential for the automation of agricultural systems, and current research primarily relies on using global positioning system (GPS) signals. However, in environments where GPS signals are unstable or denied, such as canopies and smart farms, GPS-based autonomous driving systems face limitations. Therefore, this study proposes an unmanned aerial vehicle autonomous driving system using three-dimensional light detection and ranging simultaneous localization and mapping (3D LiDAR SLAM). The proposed algorithm follows three steps: (1) A map is generated using 3D LiDAR. Because it targets an environment with height restrictions, lightweight and ground-optimized LiDAR odometry and mapping (LeGO-LOAM), which has the characteristic of extracting the ground, is used as a 3D LiDAR SLAM algorithm. (2) Noise is removed through post-processing. (3) A path is generated using the A* algorithm. To evaluate the performance of the proposed system, field evaluations were conducted in an outdoor canopy orchard using GPS and real time kinematic (RTK) GPS data as references. The experimental results verified the limitations of existing GPS- and RTK GPS-based methods and demonstrated the good performance and effectiveness of autonomous driving using 3D LiDAR SLAM. These findings suggest the feasibility of automated operations in environments where GPS is unstable or denied, and efficient agricultural automation may be achieved in conjunction with future harvesting and pollination operations.

Global Positioning System (GPS) signals adopt spreading spectrum technology, which could effectively reduce the consumption of signal transmitting power. Nevertheless, the GPS signals may be blocked unexpectedly in complicated environments. In this case, the stronger signals transmitted from Low-Earth-Orbital (LEO) communication satellite systems could be considered to aid in GPS service provision. However, the dynamic of an LEO satellite is relatively high, which causes difficulties with its integration into the general GPS receiver design. Doppler positioning algorithms can benefit from this high dynamic characteristic. In this paper, considering Doppler shifts as measurements, a Doppler Positioning algorithm is introduced. Since no navigation message can be decoded from the signals, satellite orbit prediction using the two-line orbital element set (TLE) will be involved. One commercial LEO communication satellite system is selected as well as the configurable frontend Universal Software Radio Peripheral (USRP) for the LEO signal collection and processing. A static experiment in an open field is conducted in this research. The experimental results for the open field test indicate that the positioning performance might not gain improvement from the use of an LEO signal because of orbit prediction errors or the quality of its measurement is not as good as that of GPS; but the important thing is that the LEO signal can extend positioning service in situations where the number of GPS satellites in-view are less than four due to signal obstructions. This paper presents the results of the enhanced navigation service provided by GPS with the aid of the LEO satellite.