The artificial intelligence calculation method can effectively solve various nonlinear mapping relationships. The strength of these nonlinear solvers is exploited for the evaluation of power grid investment risk using back propagation (BP) neural network optimized by genetic algorithm. The mathematical model of the problem is constructed by selecting the transfer function of the neural network and defining the fitness function of genetic algorithm. BP neural network has good ability of self-learning, self-adaptation and generalization, which can overcome the drawbacks of traditional evaluation methods relying on experts' experience. For the characteristics of genetic algorithm global optimization, the genetic algorithm is used to optimize the weight and threshold of BP neural network, and BP neural network is trained to obtain the optimal evaluation model. The model fully exploits the local search ability of BP neural network and the global search ability of genetic algorithm. It has obtained good evaluation accuracy for the processing of multi-dimensional influence factor problem. And the model can be adapted to different power grids by changing the training data. However, the method cannot describe the specific relationship between each impact factor and the investment risk of the grid. The case study shows that the method can accurately and effectively evaluate power grid investment risk and improve the fault tolerance of the power grid investment risk evaluation.INDEX TERMS Power grid investment risk, risk evaluation, BP neural network, genetic algorithm.

No abstract

Purpose Previous studies have demonstrated abnormal local spontaneous brain activity in the conventional frequency bands (0.01–0.08 Hz) in obstructive sleep apnea (OSA). However, it is not clear whether these abnormalities are associated with the specific frequency band of low-frequency oscillations or whether it can be improved with a continuous positive airway pressure (CPAP) treatment. This study aimed to investigate the regional homogeneity (ReHo) in specific frequency at baseline (pre-CPAP) and after one month of CPAP adherence treatment (post-CPAP) in OSA patients. Methods Twenty-one patients with moderate-to-severe OSA and 21 age- and sex-matched healthy controls (HCs) were included in the final analysis. ReHo was calculated in three different frequency bands (typical frequency band: 0.01–0.1 Hz; slow-5 band: 0.01–0.027 Hz; slow-4 band: 0.027–0.073 Hz), respectively. A partial correlational analysis was performed to assess the relationship between altered ReHo and clinical evaluation. Results OSA patients revealed increased ReHo in the brainstem, bilateral inferior temporal gyrus (ITG)/fusiform, and right-cerebellum posterior lobe (CPL), and decreased ReHo in the bilateral inferior parietal lobule (IPL), right superior temporal gyrus (STG), and left precentral gyrus (PG) compared to HC groups in different frequency bands. Significantly changed ReHo in the bilateral middle temporal gyrus (MTG), PG, medial frontal gyrus (MFG), supplementary motor area (SMA), CPL, IPL, left superior frontal gyrus (SFG), ITG, MTG, and right STG were observed between post-CPAP and pre-CPAP OSA patients, which was associated with specific frequency bands. The altered ReHo in specific frequency bands was correlated with Montreal cognitive assessment score, Epworth sleepiness scale, and apnea hypopnea index in pre-CPAP OSA patients. Conclusion These findings indicate that OSA has frequency-related abnormalities of spontaneous neural activity before and after short-term CPAP treatment, which might contribute to a better understanding of local neural psychopathology and may serve as potential biomarkers for clinical CPAP treatment.

In this paper, we propose an improved rotation invariant uniform local binary pattern (RIU-LBP) operator for segmenting high-resolution sensing image which can effectively describe the texture features of a high-resolution remote sensing image. The improved RIU-LBP is based on RIU-LBP. It introduces a threshold in binarization of region pixels. The new LBP operator can better tolerate small texture variation and better distinguish the plain and rough texture than the original RIU-LBP does. Then, a merging criterion of texture regions is proposed, which is based on regional LBP value distribution and Bhattacharyya distance. Finally, the texture merging criterion and spectral merging criterion are combined in the statistical region merging (SRM)-based remote sensing image segmentation method to improve segmentation results, taking full advantage of rich spectral and texture information in high-resolution remote sensing images. This algorithm can be adjusted to the number of segmented regions, and experiments indicate better segmentation results than ENVI 5.0 and the SRM method.

Sealing characteristics of commonly used water well annular space grouts were investigated using a large‐scale laboratory model. The investigation was carried out in two phases. In the first phase, a bentonite drilling mud, often used as a well sealant, was investigated both in the laboratory well model and in the field. For this purpose, Quik‐Gel® mud with different amounts of formation material (in this case sand) entrained in it was used as a sealant. In the second phase, an evaluation of four grouts: neat cement, bentonite‐cement, powder bentonite (Volclay®), and granular bentonite (Benseal® and bentonite slurry mixed according to the “Ohio” recipe) was undertaken with respect to their effectiveness in sealing the annular space. A well model consisting of a sand‐filled plexiglass container was constructed in this investigation. Four metal well casings were installed in boreholes formed in the sand. The annular space between the well casings and the boreholes formed in the sand were filled with various grouts. The effectiveness of these materials in sealing the annular space was evaluated by observation of their structural stability, infiltration of water placed on top of the sealants, and inspection of the sealants dissected during disassembling of the models. A finite‐element computer program modeling the seepage in these well experiments was used to assist in the interpretation of the experimental results. The results indicate that the final success of a sealant depends on its structural stability as much as its permeability. Benseal®‐bentonite slurry grout behaved best; neat cement and bentonite‐cement grouts also provided good seals. Volclay® and various Quik‐Gel® slurries formed poorer seals compared to these. Among the Quik‐Gel® slurries, best results were obtained in the laboratory when a Marsh Funnel Viscosity of about 70 sec/qt was achieved and a mud weight of about 10 to 11 Ib/gal resulted from mixing of formation soils. However, field observations of drilling mud slurries with entrained cuttings exhibited problems of excessive settling even when the slurries had heavy mud weight, greater than 11 Ib/gal. The extent of settling appears to be positively correlated with the relative permeability of the native formation. This limits the types of well construction where these slurries may be used as annular space seal.