Search

The rapid growth of the global population and technological progress has significantly increased the world's total power generation.Electric energy consumption forecasts play an essential role in power system dispatch and power generation management.Aim at the complex characteristics of time series of energy consumption data,and to improve the prediction accuracy of power consumption,a novel sandwich structure is proposed,in which an Attention mechanism is placed in the double layer long short-term memory artificial neural network,namely A-DLSTM.This network structure uses the attention mechanism in the mezzanine to adaptively focus on different features in each single time unit and uses the two-layer LSTM network to capture the time information in the sequence to predict the sequence data.The experimental data comes from the UCI machine learning data set,and it is the electricity consumption of a family in the past five years.The parameters of the experiment are adjusting by the grid search method.The experiment compares the prediction performance of A-DLSTM and the existing model on energy consumption data.The network of this article reaches the state-of-the-art in terms of mean square error,root mean square error,average absolute error,and average absolute percentage error.By analyzing the heat map's attention layer,the factor that has the most significant impact on electricity consumption forecasting is determined.

Nemaline myopathy (NEM) is a congenital myopathy that typically presents with proximal muscle weakness and hypotonia. To date, 13 genes have been associated with NEM. The Kelch repeat and BTB domain‐containing protein 13 (KBTBD13) gene (KBTBD13)‐related NEM is a rarely reported condition, and not a single case has been reported in Asia. Here, we report the case of a mother and daughter in China with NEM caused by a mutation (c.1222C>T) in KBTBD13. Their shared clinical phenotype is symmetrical muscle weakness in the arms and legs with childhood onset. Muscle magnetic resonance imaging showed the unique replacement mode of muscle with fibro‐fatty tissue. Histopathological examination revealed the presence of fibers containing rod‐shaped structures in the cytoplasm or under the sarcolemma. DNA sequencing analysis detected a heterozygous mutation (c.1222C>T) in KBTBD13 in this family. A founder effect for the variant may exist in the Low Countries of Belgium and the Netherlands, and the mutation may be a hotspot mutation in Europe, as it has not been reported in Asia. Our case study expands the spectrum of KBTBD13‐related NEM. [ABSTRACT FROM AUTHOR]

Sarcotubular myopathy (STM) is a rare autosomal recessive myopathy caused by TRIM32 gene mutations. It is predominantly characterized by the weakness of the proximal limb and mild to moderate elevation of creatine kinase (CK) levels. In this study, we describe a 50-year-old Chinese man who exhibited a proximal-to-distal weakness in the muscles of the lower limbs and who had difficulty standing up from a squat position. The symptoms gradually became more severe. He denied a history of cognitive or cardiological problems. The patient's parents and children were healthy. Histopathological examination revealed dystrophic changes and irregular slit-shaped vacuoles containing amorphous materials. Whole-exome sequencing consisting of protein-encoding regions of 19,396 genes was performed, the results of which identified one novel homozygous 2kb deletion chr9.hg19: g.119460021_119461983del (exon2) in the TRIM32 gene. This was confirmed at the homozygous state with quantitative real-time PCR. Here, we present a Chinese case of STM with one novel mutation in TRIM32 and provide a brief summary of all known pathogenic mutations in TRIM32.