In modern society, air pollution is an important topic as this pollution exerts a critically bad influence on human health and the environment. Among air pollutants, Particulate Matter (PM2.5) consists of suspended particles with a diameter equal to or less than 2.5 μm. Sources of PM2.5 can be coal-fired power generation, smoke, or dusts. These suspended particles in the air can damage the respiratory and cardiovascular systems of the human body, which may further lead to other diseases such as asthma, lung cancer, or cardiovascular diseases. To monitor and estimate the PM2.5 concentration, Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) are combined and applied to the PM2.5 forecasting system. To compare the overall performance of each algorithm, four measurement indexes, Mean Absolute Error (MAE), Root Mean Square Error (RMSE) Pearson correlation coefficient and Index of Agreement (IA) are applied to the experiments in this paper. Compared with other machine learning methods, the experimental results showed that the forecasting accuracy of the proposed CNN-LSTM model (APNet) is verified to be the highest in this paper. For the CNN-LSTM model, its feasibility and practicability to forecast the PM2.5 concentration are also verified in this paper. The main contribution of this paper is to develop a deep neural network model that integrates the CNN and LSTM architectures, and through historical data such as cumulated hours of rain, cumulated wind speed and PM2.5 concentration. In the future, this study can also be applied to the prevention and control of PM2.5.
Abstract:One of the most important research topics in smart grid technology is load forecasting, because accuracy of load forecasting highly influences reliability of the smart grid systems. In the past, load forecasting was obtained by traditional analysis techniques such as time series analysis and linear regression. Since the load forecast focuses on aggregated electricity consumption patterns, researchers have recently integrated deep learning approaches with machine learning techniques. In this study, an accurate deep neural network algorithm for short-term load forecasting (STLF) is introduced. The forecasting performance of proposed algorithm is compared with performances of five artificial intelligence algorithms that are commonly used in load forecasting. The Mean Absolute Percentage Error (MAPE) and Cumulative Variation of Root Mean Square Error (CV-RMSE) are used as accuracy evaluation indexes. The experiment results show that MAPE and CV-RMSE of proposed algorithm are 9.77% and 11.66%, respectively, displaying very high forecasting accuracy.
The deep population history of East Asia remains poorly understood due to a lack of ancient DNA data and sparse sampling of present-day people. We report genome-wide data from 191 individuals from Mongolia, northern China, Taiwan, the Amur River Basin and Japan dating to 6000 BCE – 1000 CE, many from contexts never previously analyzed with ancient DNA. We also report 383 present-day individuals from 46 groups mostly from the Tibetan Plateau and southern China. We document how 6000-3600 BCE people of Mongolia and the Amur River Basin were from populations that expanded over Northeast Asia, likely dispersing the ancestors of Mongolic and Tungusic languages. In a time transect of 89 Mongolians, we reveal how Yamnaya steppe pastoralist spread from the west by 3300-2900 BCE in association with the Afanasievo culture, although we also document a boy buried in an Afanasievo barrow with ancestry entirely from local Mongolian hunter-gatherers, representing a unique case of someone of entirely non-Yamnaya ancestry interred in this way. The second spread of Yamnaya-derived ancestry came via groups that harbored about a third of their ancestry from European farmers, which nearly completely displaced unmixed Yamnaya-related lineages in Mongolia in the second millennium BCE, but did not replace Afanasievo lineages in western China where Afanasievo ancestry persisted, plausibly acting as the source of the early-splitting Tocharian branch of Indo-European languages. Analyzing 20 Yellow River Basin farmers dating to ∼3000 BCE, we document a population that was a plausible vector for the spread of Sino-Tibetan languages both to the Tibetan Plateau and to the central plain where they mixed with southern agriculturalists to form the ancestors of Han Chinese. We show that the individuals in a time transect of 52 ancient Taiwan individuals spanning at least 1400 BCE to 600 CE were consistent with being nearly direct descendants of Yangtze Valley first farmers who likely spread Austronesian, Tai-Kadai and Austroasiatic languages across Southeast and South Asia and mixing with the people they encountered, contributing to a four-fold reduction of genetic differentiation during the emergence of complex societies. We finally report data from Jomon hunter-gatherers from Japan who harbored one of the earliest splitting branches of East Eurasian variation, and show an affinity among Jomon, Amur River Basin, ancient Taiwan, and Austronesian-speakers, as expected for ancestry if they all had contributions from a Late Pleistocene coastal route migration to East Asia.
With the fast expansion of renewable energy system installed capacity in recent years, the availability, stability, and quality of smart grids have become increasingly important. The renewable energy output forecasting applications have also been developing rapidly in recent years, and such techniques have particularly been applied in the fields of wind and solar photovoltaic (PV). In the case of solar PV output forecasting, many applications have been performed with machine learning and hybrid techniques. In this paper, we propose a high-precision deep neural network model named PVPNet to forecast PV system output power. The methodology behind the proposed model is based on deep neural networks, and the model is able to generate a 24-h probabilistic and deterministic forecasting of PV power output based on meteorological information, such as temperature, solar radiation, and historical PV system output data. The forecasting accuracy of PVPNet is determined by the mean absolute error (MAE) and root mean square error (RMSE) values. The results from the experiments show that the MAE and RMSE of the proposed algorithm are 109.4845 and 163.1513, respectively. The results prove that the prediction accuracy of the PVPNet outperforms other benchmark models, and the algorithm also effectively predicts complex time series with a high degree of volatility and irregularity. INDEX TERMS Deep neural network, photovoltaic output power forecasting, photovoltaic system, renewable energy sources.
Electricity price is a key influencer in the electricity market. Electricity market trades by each participant are based on electricity price. The electricity price adjusted with the change in supply and demand relationship can reflect the real value of electricity in the transaction process. However, for the power generating party, bidding strategy determines the level of profit, and the accurate prediction of electricity price could make it possible to determine a more accurate bidding price. This cannot only reduce transaction risk, but also seize opportunities in the electricity market. In order to effectively estimate electricity price, this paper proposes an electricity price forecasting system based on the combination of 2 deep neural networks, the Convolutional Neural Network (CNN) and the Long Short Term Memory (LSTM). In order to compare the overall performance of each algorithm, the Mean Absolute Error (MAE) and Root-Mean-Square error (RMSE) evaluating measures were applied in the experiments of this paper. Experiment results show that compared with other traditional machine learning methods, the prediction performance of the estimating model proposed in this paper is proven to be the best. By combining the CNN and LSTM models, the feasibility and practicality of electricity price prediction is also confirmed in this paper.
The first 57 bp upstream of the transcription initiation site of the human CYP17 (hCYP17) gene are essential for both basal and cAMP-dependent transcription. EMSA carried out by incubating H295R adrenocortical cell nuclear extracts with radiolabeled -57/-38 probe from the hCYP17 promoter showed the formation of three DNA-protein complexes. The fastest complex contained steroidogenic factor (SF-1) and p54(nrb)/NonO, the intermediate complex contained p54(nrb)/NonO and polypyrimidine tract-binding protein-associated splicing factor (PSF), and the slowest complex contained an SF-1/PSF/p54(nrb)/NonO complex. (Bu)(2)cAMP treatment resulted in a cAMP-inducible increase in the binding intensity of only the upper complex and also activated hCYP17 gene transcription. SF-1 coimmunoprecipitated with p54(nrb)/NonO, indicating direct interaction between these proteins. Functional assays revealed that PSF represses basal transcription. Further, the repression of hCYP17 promoter-reporter construct luciferase activity resulted from PSF interacting with the corepressor mSin3A. Trichostatin A attenuated the inhibition of basal transcription, suggesting that a histone deacetylase interacts with the SF-1/PSF/p54(nrb)/NonO/mSin3A complex. Our studies lend support to the idea that the balance between transcriptional activation and repression is essential in the control of adrenocortical steroid hormone biosynthesis.
Summary A Ubiquitous Power Internet of Things is fundamentally an Internet of Things, but focused upon power systems. Being able to predict these prices accurately may help with the identification of customer needs and the effective regulation of the power grid by power producers. It may also help electric power traders to manage risks, make correct decisions, and obtain more benefits. In this paper, a novel hybrid model is proposed for short‐term electricity price prediction. The model consists of three algorithms: Variational Mode Decomposition (VMD); a Convolutional Neural Network (CNN); and Gated Recurrent Unit (GRU). This is called SEPNet for convenience. The annual electricity price data is divided into seasons because of seasonal differences in the time series of electricity prices. The VMD algorithm is used to decompose the complex time series of electricity prices into intrinsic mode functions (IMFs) with different center frequencies. The CNN is used to further extract the time‐domain features for all the intrinsic model functions in the VMD domain. The GRU is then employed to process and learn the time‐domain features extracted by the CNN, leading to the final prediction. A comparison is made with five models, such as LSTM, CNN, VMD‐CNN, BP, VMD‐ELMAN. The results showed that the proposed model had the best performance, and it was found that using VMD can improve the Mean Absolute Percentage Error (MAPE) and Root Mean Square Error (RMSE) for the four seasons by 84% and 81%, respectively. The addition of GRU in the SEPNet model further improved the MAPE and RMSE by 19% and 25%, respectively. Including CNN and VMD‐CNN, that shows that the proposed model has the best performance. The MAPE and RMSE for the four seasonal averages are 0.730% and 0.453, respectively. This confirms that the SEPNet model has the feasibility and high accuracy to predict short‐term electricity prices.
This study examined the association between pressure pain sensitivity and various single nucleotide polymorphisms (SNPs) of human l-, j-, and d-opioid receptor (i.e. OPRM1, OPRK1, and OPRD1) genes in 72 healthy adult Taiwanese women of Han Chinese race. Pressure pain threshold and tolerance were measured by an algometer and polymorphisms of the opioid receptor genes determined from blood samples. Our data revealed that pressure pain threshold, but not tolerance, in subjects with the minor allele (termed 'GA') genotype of the IVS2+31G>A polymorphism of the OPRM1 gene was significantly higher than those with major allele (termed 'GG') genotype. Neither pressure pain threshold nor tolerance between major and minor alleles of other SNPs of the OPRM1, OPRK1, and OPRD1 genes were significantly different. These data suggest an association between the IVS2+31G>A SNP of the OPRM1 gene and pressure pain sensitivity in healthy adult females. We have previously shown that pre-operative pressure pain sensitivity, especially pressure pain tolerance, predicts postoperative pain and analgesic consumption in female patients [1]. However, the mechanisms that underlie the substantial inter-individual variability in pressure pain sensitivity in females remain to be elucidated.The human l-opioid receptor mediates the analgesic effects of endogenous opioid peptides and exogenous opioid agents [2]. The function of the l-receptor is under the influence of single nucleotide polymorphisms (SNPs) of the human l-opioid receptor (OPRM1) gene [3]. With an incidence of 10-15%, the 118A>G SNP is one of the most widely studied SNPs of the OPRM1 gene [4]. In the terminology, '118' refers to the position of this SNP in the genome (i.e. position 118 in the exon) and 'A>G' represents a possible substitution of the nucleotide adenine, A, by guanine, G [4]. The genotype of individuals in relation to this SNP can therefore be homozygous GG, or -where a substitution occurshomozygous AA, or heterozygous AG. As the incidence of AA is significantly higher than that of GG, the genotype AA is referred to as the 'major homozygous genotype' and the genotype GG is referred to as the 'minor homozygous genotype' of this SNP [4].Fillingim et al. reported that the 118A>G SNP of the OPRM1 gene was associated with pressure pain sensitivity in healthy adults: individuals with heterozygous (AG) and minor homozygous (GG) genotypes of this SNP were found to have higher pressure pain threshold than individuals with major homozygous (AA) genotype [5]. However, when data from men and women were analysed separately this association of genotype with response was only significant in men [5]. Since substantial inter-individual variability in pressure pain sensitivity also exists in females, these data suggest that the 118A>G SNP of the OPRM1 gene may not be the mechanism that
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.