No abstract

No abstract

Multimodal medical image fusion plays a vital role in clinical diagnoses and treatment planning. In many image fusion methods-based pulse coupled neural network (PCNN), normalized coefficients are used to motivate the PCNN, and this makes the fused image blur, detail loss, and decreases contrast. Moreover, they are limited in dealing with medical images with different modalities. In this article, we present a new multimodal medical image fusion method based on discrete Tchebichef moments and pulse coupled neural network to overcome the aforementioned problems. First, medical images are divided into equal-size blocks and the Tchebichef moments are calculated to characterize image shape, and energy of blocks is computed as the sum of squared non-DC moment values. Then to retain edges and textures, the energy of Tchebichef moments for blocks is introduced to motivate the PCNN with adaptive linking strength. Finally, large firing times are selected as coefficients of the fused image. Experimental results show that the proposed scheme outperforms state-of-theart methods and it is more effective in processing medical images with different modalities.

Coal seam water injection is widely used to prevent rockbursts in coal mines, and the duration of water injection is an important parameter related to the effectiveness of rockburst prevention, making it of practical importance to optimize the effective water injection duration. This paper presents the test results of the mechanical properties and pore structure of samples with different soaking time, obtained from a working face where rockburst occurred. Soaking time changes the mechanical properties of samples, and this time effect differs with the coal size (from centimeter to nanometer size). Results of numerical simulation and on-site tests in the Changgouyu coal mine demonstrated that water injection can effectively soften coal bodies and release or transfer stresses, and the time effect of water injection on rock prevention and control is apparent.

No abstract

No abstract

Wireless body area networks (WBANs) are essential for monitoring physiological signals of the human body, but the lifetime of WBANs is limited by battery longevity and it is not convenient or feasible for replacing the batteries of the sensors. The newly emerged energy-harvesting technology provides the potential to break the battery limitation of WBANs. However, the radio resource of a WBAN should be carefully scheduled for the wireless power transfer links and wireless information transmission links; otherwise, severely unfair resource allocation could be incurred due to the difference of channel qualities of the sensors. In this paper, we propose a marginal utility theoretic method to allocate the radio resource to the on-/in-body sensors in a fair and efficient manner. Especially, we consider that the sensors are wireless powered by multiple pre-installed radio-frequency energy sources. First, the utility function for a sensor node is proposed, which can map the achievable throughput to a satisfaction level of network QoS. Then, the fairness resource allocation among the sensor nodes is modeled as a sum-utility maximization problem. By using the dual decomposition method, the optimal solution to the proposed problem can finally be solved in the closed form. In comparison with the sum-throughput maximization and common-throughput maximization methods, the simulation results show that the proposed sum-utility maximization method can bring a fair throughput allocation for the sensors with different channel conditions, and the performance loss to the sum-throughput maximization method is small, while the sum-throughput maximization method is extremely unfair. INDEX TERMS Wireless body area networks, wireless power transfer, utility theory, convex optimization.

Fault prognostic is one of the most important problems in equipment health management system. This paper presents a hybrid method of mixture of Gaussian hidden Markov model (MG-HMM) and fixed size least squares support vector regression (FS-LSSVR) for fault prognostic. The system is established based on three parts. The first part trains the MG-HMM and FS-LSSVR model. According to the known samples, several MG-HMM models can be learned based on expectation maximization (EM) algorithm. Then, the forward variables can be calculated based on these MG-HMM models. Based on these forward variables, the corresponding FS-LSSVR models are built. All the MG-HMM models and corresponding FS-LSSVR models are combined into a model library. The second part recognizes the unknown sample based on the model library. This part obtains the MG-HMM model and FS-LSSVR model by maximization likelihood calculation between the unknown sample and MG-HMM models. The third part of the system calculates the forward variables based on the MG-HMM obtained from the second part. These forward variables are inputted into the corresponding FS-LSSVR model to compute the remaining useful life (RUL) of the unknown sample. Finally, we carry out experiments on benchmark data set to verify the proposed method. The results illustrate the effectiveness of the hybrid method.