摘要 :
The dilution ratio of the Ni60A coating prepared by the laser cladding under the assistance of the follow-up feeding pulsed current was optimized by combining back propagation (BP) neural network and genetic algorithm. The model w...
展开
The dilution ratio of the Ni60A coating prepared by the laser cladding under the assistance of the follow-up feeding pulsed current was optimized by combining back propagation (BP) neural network and genetic algorithm. The model was trained according to the results of the 6-factor 3-level orthogonal experiments. A BP genetic neural network forecast model between cladding parameters (laser power, scanning speed, powder feeding rate, pulsed current, pulse frequency and pulse width) and dilution ratio of coating was constructed. On this basis, technological parameters under the target dilution ratio of the coating were optimized by a genetic algorithm. Results demonstrated that the predicted results of the model are very close to the experimental results in term of dilution ratio of the coating, with a relative error no higher than 2.63%. This demonstrates that the model is reliable and effective. The optimal technological parameters are gained when the dilution ratio of the coating is 17.5%, including laser power=1926.3 W, laser scanning speed =4.7 mm-s~(-1), powder feeding rate= 26.9 g-min~(-1), average pulsed current =53.1 A, pulse frequency=445.6 Hz, pulse width= 108.4 μs.
收起
摘要 :
There is an increasing need to understand pattern and growth of impervious surfaces in rural regions. However, studies using remote sensing of impervious surfaces have often focused on mapping impervious surfaces in urban regions ...
展开
There is an increasing need to understand pattern and growth of impervious surfaces in rural regions. However, studies using remote sensing of impervious surfaces have often focused on mapping impervious surfaces in urban regions with less emphasis placed on the rural impervious surfaces. In this paper, we proposed a new index, Rural Impervious Surface Index (RISI) by taking advantage of narrow spectral bands of Landsat 8 OLI for estimating impervious surfaces within rural land covers. This index is based on the combination of Normalized Difference Built-up Index (NDBI), Soil Adjusted Vegetation Index (SAVI) and Soil Index (SI). Respectively, these represent the three major rural land covers components: impervious surfaces, vegetation, and soil. The index was further used for estimating fraction of impervious surfaces using fuzzy KNN classifier. The performance of this technique was also compared with Linear Spectral Mixture Analysis (LSMA). Our results showed that RISI could accurately detect spatial pattern of rural impervious surfaces due to the suppressing background noise and minimizing spectral confusion. Accuracy assessment revealed that incorporation of RISI with fuzzy KNN classification generates higher correlation coefficient, lower root mean square and systematic error compared to the LSMA technique.
收起
摘要 :
There is an increasing need to understand pattern and growth of impervious surfaces in rural regions. However, studies using remote sensing of impervious surfaces have often focused on mapping impervious surfaces in urban regions ...
展开
There is an increasing need to understand pattern and growth of impervious surfaces in rural regions. However, studies using remote sensing of impervious surfaces have often focused on mapping impervious surfaces in urban regions with less emphasis placed on the rural impervious surfaces. In this paper, we proposed a new index, Rural Impervious Surface Index (RISI) by taking advantage of narrow spectral bands of Landsat 8 OLI for estimating impervious surfaces within rural land covers. This index is based on the combination of Normalized Difference Built-up Index (NDBI), Soil Adjusted Vegetation Index (SAVI) and Soil Index (SI). Respectively, these represent the three major rural land covers components: impervious surfaces, vegetation, and soil. The index was further used for estimating fraction of impervious surfaces using fuzzy KNN classifier. The performance of this technique was also compared with Linear Spectral Mixture Analysis (LSMA). Our results showed that RISI could accurately detect spatial pattern of rural impervious surfaces due to the suppressing background noise and minimizing spectral confusion. Accuracy assessment revealed that incorporation of RISI with fuzzy KNN classification generates higher correlation coefficient, lower root mean square and systematic error compared to the LSMA technique.
收起
摘要 :
In complex indoor environments, the non-line-of-sight (NLOS) error severely affects the accuracy and reliability of the position estimation. The combined Chan/Newton method uses Chan algorithm to estimate the initial value, then s...
展开
In complex indoor environments, the non-line-of-sight (NLOS) error severely affects the accuracy and reliability of the position estimation. The combined Chan/Newton method uses Chan algorithm to estimate the initial value, then searches for the position accurately by Newton's method. However, in the environment with many NLOS base stations, the accuracy and convergence of the positioning algorithm will decrease sharply. This paper proposes an improved Chan/Newton combined position estimate algorithm. Firstly, we take weighting method based on minimum residual principle for Chan's position estimate values produced by different base stations combination, the results of which are utilized in our improved Newton's method as initial values. Next, an amendment factor to modify the range measurement and a damping factor are adopted for constructing accurate objective function and stabling iteration convergence respectively. Finally, weighting the initial values and iteration results to obtain the final location information. Experimental evaluations show that the proposed algorithm has a better performance in terms of location accuracy and convergence in NLOS conditions.
收起
摘要 :
In complex indoor environments, the non-line-of-sight (NLOS) error severely affects the accuracy and reliability of the position estimation. The combined Chan/Newton method uses Chan algorithm to estimate the initial value, then s...
展开
In complex indoor environments, the non-line-of-sight (NLOS) error severely affects the accuracy and reliability of the position estimation. The combined Chan/Newton method uses Chan algorithm to estimate the initial value, then searches for the position accurately by Newton's method. However, in the environment with many NLOS base stations, the accuracy and convergence of the positioning algorithm will decrease sharply. This paper proposes an improved Chan/Newton combined position estimate algorithm. Firstly, we take weighting method based on minimum residual principle for Chan's position estimate values produced by different base stations combination, the results of which are utilized in our improved Newton's method as initial values. Next, an amendment factor to modify the range measurement and a damping factor are adopted for constructing accurate objective function and stabling iteration convergence respectively. Finally, weighting the initial values and iteration results to obtain the final location information. Experimental evaluations show that the proposed algorithm has a better performance in terms of location accuracy and convergence in NLOS conditions.
收起
摘要 :
In recent years, indoor location services have gradually become a new research direction in addition to outdoor location services. Traditionally, WiFi-based indoor location technologies are divided into two categories: (ⅰ) using ...
展开
In recent years, indoor location services have gradually become a new research direction in addition to outdoor location services. Traditionally, WiFi-based indoor location technologies are divided into two categories: (ⅰ) using WiFi channel propagation model based on RSSI values for ranging, whose localization error can reach 10~20 m; (ⅱ) using RSSI to establish fingerprint library for fingerprint matching and machine learning algorithms for matching, whose localization error can reach 3~20 m. Existing WiFi-based location technologies are usually applied to position coordinate solving, but the accuracy is not high enough. However, using WiFi-RSSI for indoor room switching pattern recognition will effectively improve the accuracy of map matching. In this paper, we use the gate recurrent unit (GRU) algorithm to determine the user's indoor room switching model from the WiFi RSSI timing data set of the mobile terminal in the indoor room switching scenario, which can effectively correct the traditional Hidden Markov Model (HMM) indoor map matching algorithm and significantly improve the accuracy and stability of the indoor map matching algorithm. This algorithm improves the matching accuracy by up to 25.1% compared with the traditional HMM indoor map matching algorithm under the limited accuracy of the original solution coordinates provided by the indoor positioning system.
收起
摘要 :
In recent years, indoor location services have gradually become a new research direction in addition to outdoor location services. Traditionally, WiFi-based indoor location technologies are divided into two categories: (ⅰ) using ...
展开
In recent years, indoor location services have gradually become a new research direction in addition to outdoor location services. Traditionally, WiFi-based indoor location technologies are divided into two categories: (ⅰ) using WiFi channel propagation model based on RSSI values for ranging, whose localization error can reach 10~20 m; (ⅱ) using RSSI to establish fingerprint library for fingerprint matching and machine learning algorithms for matching, whose localization error can reach 3~20 m. Existing WiFi-based location technologies are usually applied to position coordinate solving, but the accuracy is not high enough. However, using WiFi-RSSI for indoor room switching pattern recognition will effectively improve the accuracy of map matching. In this paper, we use the gate recurrent unit (GRU) algorithm to determine the user's indoor room switching model from the WiFi RSSI timing data set of the mobile terminal in the indoor room switching scenario, which can effectively correct the traditional Hidden Markov Model (HMM) indoor map matching algorithm and significantly improve the accuracy and stability of the indoor map matching algorithm. This algorithm improves the matching accuracy by up to 25.1% compared with the traditional HMM indoor map matching algorithm under the limited accuracy of the original solution coordinates provided by the indoor positioning system.
收起
摘要 :
Mobile communication network could provide time-difference-of-arrival (TDOA) and time-of-arrival (TOA) for hybrid positioning in indoor environment. However, the existing research lacks the analysis of the geometric influence on t...
展开
Mobile communication network could provide time-difference-of-arrival (TDOA) and time-of-arrival (TOA) for hybrid positioning in indoor environment. However, the existing research lacks the analysis of the geometric influence on the hybrid TDOA and TOA positioning accuracy. This paper defines and derives the dilution of precision (DOP) of the hybrid positioning. In the simulation, the DOP distribution of the hybrid positioning is calculated and compared with that of the TDOA-only positioning. The results show that, in the edge of network coverage area, the hybrid TDOA and TOA positioning has a smaller DOP than the TDOA-only positioning, which proves that the method has the potential to achieve higher positioning accuracy.
收起
摘要 :
Mobile communication network could provide time-difference-of-arrival (TDOA) and time-of-arrival (TOA) for hybrid positioning in indoor environment. However, the existing research lacks the analysis of the geometric influence on t...
展开
Mobile communication network could provide time-difference-of-arrival (TDOA) and time-of-arrival (TOA) for hybrid positioning in indoor environment. However, the existing research lacks the analysis of the geometric influence on the hybrid TDOA and TOA positioning accuracy. This paper defines and derives the dilution of precision (DOP) of the hybrid positioning. In the simulation, the DOP distribution of the hybrid positioning is calculated and compared with that of the TDOA-only positioning. The results show that, in the edge of network coverage area, the hybrid TDOA and TOA positioning has a smaller DOP than the TDOA-only positioning, which proves that the method has the potential to achieve higher positioning accuracy.
收起
摘要 :
Electronically controllable magnetorheological brakes (MRB) can be used in haptic devices to apply forces/torques to the user in a virtual reality (VR) simulation to improve realism. Precise control of the braking torque is possib...
展开
Electronically controllable magnetorheological brakes (MRB) can be used in haptic devices to apply forces/torques to the user in a virtual reality (VR) simulation to improve realism. Precise control of the braking torque is possible with a control system using a Hall sensor which measures the magnetic field. Machine learning models can be used to predict the output torque using the input from the Hall sensor. However, over time the fluid leaks out of the MRB due to failure of rubber seals, which degrades the haptic device performance and presents challenges in torque prediction. In this paper, we present our efforts in developing machine learning based approaches that can capture the dynamic behavior of an MRB and its changing torque output as the fluid leaks out. Extensive experiments have been carried out using data collected from the device, and results show that our 2-Step-RN approach can accurately predict the output torque. Notably, it even outperforms the baseline models which are trained for and operate at a stable fluid level, indicating its great potential for enabling torque control of MRB devices with high fidelity.
收起