Search

In order to improve energy-saving operation ability of single-effect lithium bromide absorption chiller and to reduce unnecessary energy consumption, a new set-point optimization strategy of refrigeration system based on BP neural network and genetic algorithm (ANN-GA) is proposed in this paper. Firstly, according to the experimental data, the set-point optimization model of BP neural network with structure of 7–7-2 is established. Secondly, we take the coefficient of performance (COP) and cooling pump power consumption as the optimization goal. ANN-GA algorithm is used to find the best set point of refrigeration system at varying load conditions. Finally, through analysis of the experiment and simulation, it can effectively improve energy efficiency ratio of refrigeration system and make the system run in high efficient area by adjusting set point of control loop according to the varying actual condition of refrigeration system. Experiment results of the strategy in this paper are presented to demonstrate its feasibility.

This paper firstly introduces elementary knowledge of bio-electromagnetic dose, and then elaborates on the method and steps of theoretical bio-electromagnetic dose used to compute the electromagnetic dose absorbed by human body at the frequency 300MHz and 3GHz. Afterwards, the finite-difference time-domain (FDTD) method is utilized to analyze the dielectric property and calculate the specific absorption rate (SAR) in several biological organizations of human body and the results produced from this calculating process are compared with proven conclusions. The method and implementation steps used in this article suits for computing dielectric property of multi-layered biological tissue under the irradiation of arbitrary frequency electromagnetic wave. Therefore, the analysis method can lay quantitative foundation of research on the bio-effects of electromagnetic waves, on the mechanism of the bio-effect, on application of the bio-effects, and on the formulation for safety standard of electromagnetic wave radiation.

In this paper, we present a dynamic adaptation framework to adapt the game scenarios for a multi-agent training game. We consider the problem where a trainee has to practice along multiple objectives during the training, and each objective is assigned with a desired difficulty level. The proposed dynamic adaptation approach takes into account of individual player's playing ability as well as the dynamic game circumstance to determine how to adapt the game scenario. We utilize artificial neural networks to construct a data-driven prediction model to estimate the effect of taking certain adaptation to the game. Based on the prediction model, our adaptation framework can determine both the direction and quantity of the adaptation. The performance of the proposed framework is testified in a food distribution training game and the results demonstrate the effectiveness of our adaptation framework.

Dynamic adaptation of games with the objective of catering to the individual players' level of standard is an emerging and challenging research area of artificial intelligence in digital game. In this paper, we propose a data-driven approach for dynamic adaptation of game scenario difficulties. The goal is to fit the performance of the player to the desired conditions set by the designer. To this end, the data on player's in-game performance and dynamic game states are utilized for making adaptation decisions. Trained artificial neural networks are used to capture the relationship between dynamic game state, player performance, adaptation decision and the resultant game difficulty. Based on the predicted difficulty, adaptation of both direction and magnitude can be performed more effectively. Experimental study on a training game application is presented to demonstrate the efficiency and stability of the proposed approach.

Moving objects detection plays a critical role in computer vision application, since it usually is the first phase in video processing. Most traditional methods are used in static scenes, however not perform well in dynamic situations, or they can only overcome limited perturbation. In this paper, we propose a stereo local binary pattern based on appearance and motion (SLBP-AM) descriptor for back-ground modeling and objects detection. We regard the motion of pixels as dynamic texture in ellipsoidal domain, and combine texture histograms in the XY, XT, YT planes in the ellipsoid as the new descriptor for background subtraction. Compared with traditional local binary pattern (LBP) descriptor, experiment results show that the new proposed method can not only be robust to slight disturbance, but also adapt quickly to the large-scale and sudden changes.

We propose a dual hash tables algorithm which can realize the durable top-k search. Two hash tables are constructed to keep the core information, such as score and time in the inverted lists. We use the key-value relationships between the two hash tables to calculate the scores which measure the correlations between a keyword and documents, and search the versioned objects that are consistent in the top-k results throughout a given query interval. Finally, we use data from Wikipedia to demonstrate the efficiency and performance of our algorithm.

Auto Rack Girder Detection System based on image mosaicing technique for aerial images were studied. Phase correlation method is used to complete Rack Girder image mosaicing. With Fast Fourier Transform of images, the phase information in frequency domain is used to realize image mosaicing. Considering a lot of Sequence Images having features need to be real-time stitched, improved Fourier field stitching algorithm is put forward in the paper. At first large region is restricted within overlapped areas of image, and then two-dimension pulsing signal is gotten after cross-power spectrum is counted. Registration parameters are gained through maximum of pulsing signal. To bundle image, a new weighting image smoothing algorithm based on Canny is put forward. To the extent, the algorithm has general adaptability to some factors such as lamination variation and noise and so on. The algorithm suits a lot Sequence Images fast stitching as the fast speed of stitching because of fast speed of stitching. The analytic conclusions indicate that the algorithm is adopted to fast stitch a lot of sequence images, and it has general adaptability to some factors such as lamination variation, noise and so on.