In the automatic detection of epileptic seizures, the monitoring of critically ill patients with time varying EEG signals is an essential procedure in intensive care units. There is an increasing interest in using EEG analysis to detect seizure, and in this study we aim to get a better understanding of how to visualize the information in the EEG time-frequency feature, and design and train a novel random forest algorithm for EEG decoding, especially for multiple-levels of illness. Here, we propose an automatic detection framework for epileptic seizure based on multiple time-frequency analysis approaches; it involves a novel random forest model combined with grid search optimization. The short-time Fourier transformation visualizes seizure features after normalization. The dimensionality of features is reduced through principal component analysis before feeding them into the classification model. The training parameters are optimized using grid search optimization to improve detection performance and diagnostic accuracy by in the recognition of three different levels epileptic of conditions (healthy subjects, seizure-free intervals, seizure activity). Our proposed model was used to classify 500 samples of raw EEG data, and multiple cross-validations were adopted to boost the modeling accuracy. Experimental results were evaluated by an accuracy, a confusion matrix, a receiver operating characteristic curve, and an area under the curve. The evaluations indicated that our model achieved the more effective classification than some previous typical methods. Such a scheme for computer-assisted clinical diagnosis of seizures has a potential guiding significance, which not only relieves the suffering of patient with epilepsy to improve quality of life, but also helps neurologists reduce their workload.

Automatic recognition methods for non-stationary electroencephalogram (EEG) data collected from EEG sensors play an essential role in neurological detection. The integrated approaches proposed in this study consist of Symlet wavelet processing, a gradient boosting machine, and a grid search optimizer for a three-class classification scheme for normal subjects, intermittent epilepsy, and continuous epilepsy. Fourth-order Symlet wavelets are adopted to decompose the EEG data into five frequencies sub-bands, such as gamma, beta, alpha, theta, and delta, whose statistical features were computed and used as classification features. The grid search optimizer is used to automatically find the optimal parameters for training the classifier. The classification accuracy of the gradient boosting machine was compared with that of a conventional support vector machine and a random forest classifier constructed according to previous descriptions. Multiple performance indices were used to evaluate the proposed classification scheme, which provided better classification accuracy and detection effectiveness than has been recently reported in other studies on three-class classification of EEG data.

Due to the rapid development of deep learning and artificial intelligence techniques, denoising via neural networks has drawn great attention due to their flexibility and excellent performances. However, for most convolutional network denoising methods, the convolution kernel is only one layer deep, and features of distinct scales are neglected. Moreover, in the convolution operation, all channels are treated equally; the relationships of channels are not considered. In this paper, we propose a multi-scale feature extraction-based normalized attention neural network (MFENANN) for image denoising. In MFENANN, we define a multi-scale feature extraction block to extract and combine features at distinct scales of the noisy image. In addition, we propose a normalized attention network (NAN) to learn the relationships between channels, which smooths the optimization landscape and speeds up the convergence process for training an attention model. Moreover, we introduce the NAN to convolutional network denoising, in which each channel gets gain; channels can play different roles in the subsequent convolution. To testify the effectiveness of the proposed MFENANN, we used both grayscale and color image sets whose noise levels ranged from 0 to 75 to do the experiments. The experimental results show that compared with some state-of-the-art denoising methods, the restored images of MFENANN have larger peak signal-to-noise ratios (PSNR) and structural similarity index measure (SSIM) values and get better overall appearance.

Designing a complex product such as an aircraft usually requires both qualitative and quantitative data and reasoning. To assist the design process, a critical issue is how to represent qualitative data and utilise it in the optimisation. In this study, a new method is proposed for the optimal design of complex products: to make the full use of available data, information and knowledge, qualitative reasoning is integrated into the optimisation process. The transformation and fusion of qualitative and qualitative data are achieved via the fuzzy sets theory and a cloud model. To shorten the design process, parallel computing is implemented to solve the formulated optimisation problems. A parallel adaptive hybrid algorithm (PAHA) has been proposed. The performance of the new algorithm has been verified by a comparison with the results from PAHA and two other existing algorithms. Further, PAHA has been applied to determine the shape parameters of an aircraft model for aerodynamic optimisation purpose.

Heavy computation load and vast memory requirements are major bottlenecks of computer-generated holograms (CGHs), which are promising and challenging in three-dimensional displays. To solve these problems, an improved look-up table (LUT) method suitable for arbitrarily sampled object points is proposed and implemented on a graphics processing unit (GPU) whose reconstructed object quality is consistent with that of the coherent ray-trace (CRT) method. The concept of distance factor is defined, and the distance factors are pre-computed off-line and stored in a look-up table. The results show that while reconstruction quality close to that of the CRT method is obtained, the on-line computation time is dramatically reduced compared with the LUT method on the GPU and the memory usage is lower than that of the novel-LUT considerably. Optical experiments are carried out to validate the effectiveness of the proposed method.