While BP neural network,classical theory of probability and its derivative on algorithm were used to fire loss prediction,the system structure is complex,the detection data is not stable,and the result is easy to fall into local minimum, etc. To resolve these troubles, a method of reasoning and forecasting the regional fire data was proposed based on adaptive fuzzy Generalized Regression Neural Network (GRNN). The improved fuzzy C-clustering algorithm was used to correct weight for the initial data in network input layer, and it reduced the influence of noise and isolated points on the algorithm, improved the approximation accuracy of the predicted value. The adaptive function optimization of GRNN algorithm was introducd to adjust the expansion speed of the iterative convergence, change the step, and found the global optimal solution. The method was used to resolve the premature convergence problem and improved the search efficiency. While the identified fire loss data is put into the algorithm, the experimental results show that the method can overcome the problem of instable detection data, and has good ability of nonlinear approximation and generalization capability.
In order to deal with the channel fading in Underwater Wireless Sensor Networks (UWSN) changing randomly in time-space-frequency domain, underwater cooperative communication model with relays was proposed in this paper to improve reliability and obtain diversity gain of the communication system. Based on the new model, a relay selection algorithm for UWSN was proposed. The new relay selection algorithm used new evaluation criteria to select the best relay node by considering two indicators: channel gain and long delay. With the selected relay node, source node and relay nodes could adjust their sending power by the power allocation algorithm which was based on the principle of minimizing the bit error rate. In a typical scenario, by comparing with the traditional relay selecting algorithm and equal power allocation algorithm, the new algorithm reduces the delay by 16.7% and lowers bit error rate by 1.81dB.
A motion model of underwater sensor node was analyzed, and a new Medium Access Control (MAC) protocol of underwater mobile sensor networks based on variable-length slots: VS FAMA was proposed. In VS FAMA, the length of time-slot would be adaptive adjusted according to sensor location that measured periodically, which was positively correlated to the distance between nodes. New protocol made better use of the time-slot resource in underwater sensor networks. NS-2 simulation results show that VS FAMA can get about 15% higher network goodput under the circumstance of motion.
Concerning the problem of barrier among passengers and unstable illumination on the bus, a detection and tracking algorithm was proposed based on edge feature and local invariant feature of head-shoulder. Firstly, the algorithm used adaptive threshold background subtraction method to achieve passenger segmentation. Secondly, it used Histogram of Oriented Gradient (HOG) feature of different sample sets to train Support Vector Machine (SVM) classifiers, and combined Adaptive Boosting (AdaBoost) algorithm to extract a strong classifier. And then it scanned the foreground using strong classifier to achieve passenger detection. Lastly, it extracted Speeded-Up Robust Feature (SURF) of target region and current search region, and then matched feature points to achieve passenger tracking. The experimental results show that this algorithm has detection rate and tracking rate of more than 80% in the case of barrier among passengers and unstable illumination, and it can meet the requirement of real-time. It can be used for passenger flow counting.
In view of the problem of environmental sensing in Underwater Cognitive Acoustic Networks (UCAN), a Passive Localization algorithm targeting Marine Mammals (PLM) and Speed Measurement algorithm based on Doppler effect (SMD) were proposed. PLM uses the method of retrieval and screening with received signal power to localize marine mammals based on the source level range of their signals. SMD calculates speed using Doppler effect of the received signals on the basis of PLM localization. The experimental results show that PLM and SMD can achieve high accuracy. The average error of PLM increases with the increase of dolpines speed, and its mean value is about 10m. Success rate of localization using PLM can be 90%. The combination of PLM and SMD can help to estimate the movement area of marine mammals accurately.
Aiming at convex optimization problem of undersampling image reconstruction, a new image reconstruction algorithm based on the second order Total Generalized Variation (TGV) model was proposed. In the new model, the second-order TGV semi-norm of images was used as the regularization term, which could automatically balance the first order and second order derivative. The characteristics of the TGV made the new model recover the image edge information better, smooth noise and avoid the staircasing effect. For computing the new model effectively, the orthogonal projection and the adjustment of weight threshold were presented to adaptively amend the iteration results of each step in order to obtain accurate image reconstruction results. The experimental results show that the proposed model can get better results with large value of Peak Signal-to-Noise Ratio (PSNR) and Structure SIMilarity (SSIM) in image reconstruction compared with Orthogonal Matching Pursuit (OMP) and Total Variation (TV) models.