Search

When identifying the sequence of some species using fewer known gene training data (named target domain), the data of closely related species and unlabeled data of the species (named source domain) could be considered for auxiliary training. However, there are differences in the statistical distribution of the feature space comprising of genetic data of different species. Therefore, this paper proposes a feature and sample jointed transfer (FSJT) method for semi-supervised scenarios, consisting of two modules. In the first module, the distance between the sample probability distribution functions in the feature space is taken as the optimization objective, and a hybrid balanced distribution adaptation method is constructed to transform the feature space of the two domains to increase the similarity between the domains. In the second module, the confidence of the unlabeled data in the target domain is defined and a self-learning sample transfer method is proposed to reduce the impact of samples having large differences in source-domain training data. Simultaneously, to select the suitable source-domain samples and the target domain when the sample size between the fields is very different, the transferred Lasso and the nearest-neighbor (TLR) feature selection method is proposed using FSJT. Then, the whole framework and algorithm flow of the TLR-FSJT model is presented and verified using the transfer learning standard dataset and ribonucleic acid data from GenBank database by comparing it with three machine learning methods and the FSJT model. Results show that the TLR-FSJT model has the highest accuracy in semi-supervised scenarios. [ABSTRACT FROM AUTHOR]

Risky driving behavior (RDB) can cause panic and anger among other drivers. Under the influence of irrational emotions, RDB can reoccur, resulting in a phenomenon known as risky driving behavior propagation (RDBP). RDBP is a dangerous phenomenon, which can easily lead to traffic conflicts and accidents. It is significant to determine the propagation mechanism of RDBP to road safety. Firstly, RDBP can be considered a type of disease because three essential components of RDBP share similarities with an epidemic. A stochastic SIR model for risky driving behavior propagation (SSIR-RDBP) is constructed to quantify the mechanism of RDBP. Additionally, a Lyapunov function is adopted to prove the existence and uniqueness of the model solution. Secondly, based on current moment risk and cumulative risk, a two-stage risk approach is adopted to quantify the risk of RDBP. The Conditional Value at Risk (CVaR) is used to quantify the current moment risk, and the probability of the Markov state transition matrix is introduced to describe the cumulative risk. Finally, sensitivity analysis of the model parameters is carried out to explore the intrinsic variables of the parameters. The results suggest that the risk of RDBP increases rapidly to its peak value within the first 5 s. As traffic saturation increases, the decline rate of sustainable drivers and the rise rate of recovered individuals grows cubically, and the rate of reaching peak infection increases linearly. Furthermore, the fluctuation range of risk and the maximum risk both increase quadratically. The driver's emotional control ability is strongest when the infection rate is set to 4, and the recovery rate increases linearly with road safety education. Improving the driver's emotional control ability, and increasing awareness of road safety education, can help to control the risk in RDBP. • A stochastic SIR model for risky driving behavior propagation is presented. • Two-stage risk quantification approach based CVaR and Markov chain is proposed. • Relationship between model parameters and traffic measures are analyzed. [ABSTRACT FROM AUTHOR]

• Developed mandatory lane change models to various intelligent connected vehicles environments employing game theory. • Model demonstrated exceptional predictive accuracy for both lane changes and waiting events. • Predicted lane change positions varied significantly based on different intelligent connected vehicles environments. • Discrepancies in lane change duration were notably influenced by diverse game strategies. In the environment of intelligent connected vehicles, drivers are capable of making wiser and safer decisions. However, the interaction between drivers and vehicle systems has undergone changes in the intelligent connected vehicles environment, leading to a decrease in the applicability of existing microscopic driving models, such as the mandatory lane change model, which requires reevaluation or improvement. Therefore, to investigate the influence of different intelligent connected vehicles environments on the microscopic mandatory lane-changing model, this study developed three interaction systems to characterize different intelligent connected vehicles environments: the baseline, warning group, and guidance group. The Baseline provides basic information, the warning group adds icons of preceding vehicles and real-time headway information, while the guidance group further includes speed and voice guidance functions. The baseline describes the traditional environment, while the other two groups describe the intelligent connected vehicles environment. Using a self-developed intelligent connected vehicle testing platform, we conducted driving simulation experiments with 43 participants at the interchange merging area of a highway. This study, grounded in game theory, establishes function models for participants, strategies, and payoff functions in the mandatory lane-changing process. Utilizing data from driving simulation experiments, the parameters of the dual-layered planning model are calibrated. Evaluation of the constructed model is conducted through confusion matrices and lane-changing spatiotemporal characteristic indicators. The results demonstrate satisfactory predictive performance of the baseline group model, warning group model, and guidance group model across different intelligent connected vehicles environments. Specifically, compared to existing literature, the baseline group model exhibits improvements of 7 % and 2 % respectively in overall lane-changing detection accuracy by drivers. The warning group model shows improvements of 2.9 % and 1.7 %, while the guidance group model exhibits improvements of 5.1 % and 4.3 %. Additionally, the baseline group model reduces the mean absolute error in predicting different game strategies by 16.7 % and 5.6 % respectively compared to existing literature. Concerning lane-changing position prediction, the warning and guidance group models demonstrate minimal errors, whereas the baseline group model exhibits good consistency in predicting lane-changing duration. Furthermore, both the warning and guidance group models show some delay in predicting lane-changing duration. While intelligent connected vehicles environments significantly influence the prediction of lane-changing positions, they do not significantly affect the prediction of lane-changing duration. However, game strategies significantly impact the prediction of lane-changing duration but do not significantly affect the prediction of lane-changing positions. The study findings offer valuable insights into micro lane-changing behaviors of drivers in intelligent connected vehicles environments, bearing crucial significance for the in-depth investigation of real-time control and guidance strategies for vehicles in merge areas of highways under intelligent connected vehicles conditions. [ABSTRACT FROM AUTHOR]

• A hybrid traffic flow model of micro and macro is proposed. • The Maximum Likelihood Estimation of stop and go coefficients is deduced. • The mechanism of traffic flow oscillation is explored with Brownian noise. To investigate the stop-and-go phenomenon triggered by car-following, a hybrid model of micro and macro is proposed. Firstly, with the stochastic nature of driving behavior, a Brownian noise is added into the velocity difference to give a modification to the car-following model. Then, to combine the macroscopic traffic flow characteristics, the traffic stream model is introduced, and the two models are fused in the context of high traffic flow. Next, the theoretical validity of the fusion model is verified by the existence and uniqueness of the solution. The coefficients of the hybrid model are extracted as the stop coefficient and go coefficient which reflect the micro driving behavior. The Maximum Likelihood Estimations of the two coefficients are also given, as well as the boundedness of traffic oscillation in stop-and-go. Finally, numerical simulations show that the model has good fitting and prediction ability for traffic flow in high flow period. Moreover, the greater the stop coefficient, the stronger the traffic flow oscillation intensity, the larger the upper boundedness of the oscillation, the more severe the stop-and-go. [ABSTRACT FROM AUTHOR]

McKean–Vlasov stochastic differential equation is a class of complicated and special equation since the drift term is a function of stochastic process and its distribution. This paper discusses the maximum likelihood estimation of parameters in the drift term through transforming McKean–Vlasov stochastic process into homogeneous one and estimates parameters of the latter to discuss that of McKean–Vlasov equation. Then we build a McKean–Vlasov stochastic model for ion diffusion since ions moved by liquid viscous force and also by coulomb interaction related with ion charged distribution, and simulate the changing trajectory of the ion motion through numerical calculation. Results manifest that the ion motion shows strong random property and has the same tendency for different time intervals, however, the smaller of time lag, the more distinct of wave trajectory observed. [ABSTRACT FROM AUTHOR]

Myostation (MSTN), which is primarily expressed in muscle, plays an important role in myogenic and adipogenic cells. However, there is little information about whether MSTN displays different roles between adipose-derived stem cells (ADSCs) and muscle satellite cells (MSCs). The two kinds of cells can both exist in the muscle and differentiate into adiposities. In this research, we isolated ADSCs and MSCs from porcine fat tissues and semitendinosus muscle, respectively, to investigate the effect of MSTN on the adipogenesis of those cells. ADSCs and MSCs were treated with recombinant human MSTN during the induction of adipogenesis or before the induction of differentiation. Then, we evaluated adipogenesis by Oil Red O staining and assessed the expression patterns of adipocyte-specific fatty acid binding protein ( aP2) and peroxisome proliferator-activated receptor ( PPAR) γ using real-time polymerase chain reaction methods. Our results indicated that the treatment with MSTN before or during the induction of differentiation in MSCs could both inhibit the adipogenesis. However, the treatment with MSTN only during the induction of differentiation in ADSCs could suppress the adipogenesis. Those results showed that MSTN had different roles in the adipogenesis of ADSCs and MSCs. It can shed new light on the origin of adipocyte located in muscle. Copyright © 2011 John Wiley & Sons, Ltd. [ABSTRACT FROM AUTHOR]

Abstract - This paper chooses scrap steel as research object, firstly we use grey relational analysis between the present phase of steel industry in China and three phases of that in developed countries according to industrial lifecycle. Then we set up GM(l,l) power model, and build objective function of least average comparative error, solve the optimized solution of its whitenization equation by particle swarm optimization algorithm. At last, apply it to forecast the demand of scrap steel for the next several years in China. The forecasted result is consistent with fact, and the demand we forecast gives scientific evidence to the design of reverse logistics networks. [ABSTRACT FROM AUTHOR]

Accurate traffic flow prediction can effectively improve traffic efficiency and safety. This has become a trending topic in intelligent transportation systems. However, the occurrence of traffic accidents will cause great fluctuations of traffic flow in a short time, thus affecting the accuracy of flow prediction. This paper analyses the influence of traffic accident information on traffic flow, and proposes a grey convolutional neural network called G-CNN for traffic flow prediction. First, considering the small sample size of traffic accidents and the incomplete information description, the traffic flow and traffic speed change rate are defined to represent traffic accident grey information, and a grey fixed-weight clustering method for extracting the characteristics of traffic accident grey information is established. Second, the spatiotemporal characteristics of traffic flow are analysed, and a third-order tensor is developed to fuse them with the accident characteristics and serve as the input of the G-CNN. Then the G-CNN model is built to predict traffic flow in a traffic accident environment. The Canadian Whitemud Drive experiment on traffic flow without traffic accident information reveals that the developed G-CNN model has a better ability to predict future traffic flow with better accuracy and stability. Meanwhile, it is verified that the fluctuation of the traffic change rate will cause traffic accidents, and the probability of traffic accidents at a certain time point will be obtained through feature extraction of traffic accidents. Finally, the model is verified for the traffic flow of Hangzhou Viaduct in China, which demonstrates that the G-CNN model outperforms all of the compared models. [ABSTRACT FROM AUTHOR]

Studying the rear-end early warning methods of connected automated vehicles (CAVs) is useful for issuing early warnings and reducing traffic accidents. Establishing a corresponding driving model according to CAV characteristics is necessary when designing intelligent decision and control systems, especially for the safety speed threshold. However, since traffic systems are stochastic, there are random factors that influence car-following behavior. Therefore, this study proposes a rear-end collision warning method for CAVs based on a stochastic local multivehicle optimal speed (SLMOV) car-following model. First, the SLMOV model is proposed to characterize the car-following behavior of CAVs. Simultaneously, a stability analysis and parameter estimation method are discussed. Second, the safety distance between the CAVs changes with time because the speed of the rear vehicles satisfies the SLMOV model, which is used to calculate the safety probability of rear-end CAV collisions through an analysis of the driving process. The speed threshold is assessed by controlling the rear-end collision probability. Third, next-generation simulation (NGSIM) data are used in an empirical analysis of a rear-end collision warning method on the basis of a parameter estimation of the SLMOV model. The results present the speed thresholds of vehicles under different braking deceleration levels. Finally, the merits and demerits of fixed-speed and variable-speed adjustment time intervals are compared by considering driving safety and comfort as evaluation indexes. A reasonable CAV adjustment time interval of 0.4 s is determined. This result can be used to help develop a vehicle loading rear-end collision warning system. [ABSTRACT FROM AUTHOR]

Background: Long-chain non-coding RNA (lncRNA) is closely related to many biological activities. Since its sequence structure is similar to that of messenger RNA (mRNA), it is difficult to distinguish between the two based only on sequence biometrics. Therefore, it is particularly important to construct a model that can effectively identify lncRNA and mRNA. Results: First, the difference in the k-mer frequency distribution between lncRNA and mRNA sequences is considered in this paper, and they are transformed into the k-mer frequency matrix. Moreover, k-mers with more species are screened by relative entropy. The classification model of the lncRNA and mRNA sequences is then proposed by inputting the k-mer frequency matrix and training the convolutional neural network. Finally, the optimal k-mer combination of the classification model is determined and compared with other machine learning methods in humans, mice and chickens. The results indicate that the proposed model has the highest classification accuracy. Furthermore, the recognition ability of this model is verified to a single sequence. Conclusion: We established a classification model for lncRNA and mRNA based on k-mers and the convolutional neural network. The classification accuracy of the model with 1-mers, 2-mers and 3-mers was the highest, with an accuracy of 0.9872 in humans, 0.8797 in mice and 0.9963 in chickens, which is better than those of the random forest, logistic regression, decision tree and support vector machine. [ABSTRACT FROM AUTHOR]

Structural prediction and analysis of sub-industrial energy consumption with economic data across three industrial sectors are an important basis for reflecting the coordinated development relationship between energy consumption and industrial development. Empirically, the sub-industrial energy consumption and economic structure have numerous compositional data. The multivariate compositional data's fractional gray multivariate model on the basis of the Simplex space and its algebraic system is proposed in this study aiming at the multi-dimensional small sample size with high uncertainties. First, the fractional accumulative generation operation sequence of multivariate compositional data is defined according to Aitchison geometry. Then, the novel model with the form of the compositional data vector is obtained. Second, the least square parameter estimation of the model is studied. A derived model is deduced and selected as the time-response expression of the model solution. Moreover, the gray wolf optimizer is introduced and designed to determine the optimal value of the fractional order. Detailed modeling procedures, including the computational steps and the intelligent optimization algorithm, have been clearly presented. Furthermore, 10-year economic structural data of 14 provinces in China are used to validate the effectiveness of the proposed model. The validation presents that the proposed model performs better in fitting, prediction, stability, and applicability, in comparison with the two other models in the Simplex space. Last, from the updated real-time datasets from 2008 to 2018, the proposed model is applied to analyze and forecast the sub-industrial energy consumption structure and industrial structure of Beijing. Results show that the proposed model presents high accuracy and is efficient in addressing the multivariate compositional data in some structural energy and economic issues. [ABSTRACT FROM AUTHOR]

• A novel inertia gray model is proposed based on classic car-following models. • The models reveal the problem of the transformation of the micro model and macro model. • The models use the problem of the mechanical characteristics and inertia process traffic flow data. • The models can predict the flow of a specific period of time evaluating to the state of traffic flow. Real-time and accurate short-term traffic flow prediction results can provide real-time and effective information for traffic information systems. Based on classic car-following models, this paper establishes differential equations according to the traffic state and proposes a car-following inertial gray model based on the information difference of the differential and gray system, in combination with the mechanical characteristics of traffic flow data and the characteristics of an inertial model. Furthermore, analytical methods are used to study the parameter estimation and model solution of the new model, and the important properties, such as the original data, inertia coefficient and simulation accuracy, are studied. The effectiveness of the model is verified in two cases. The performance of the model is better than that of six other prediction models, and the structural design of the new model is more reasonable than that of the existing gray models. Moreover, the new model is applied to short-term traffic flow prediction for three urban roads. The results show that the simulation and prediction effects of the model are better than those of other gray models. In terms of the traffic flow state, an optimal match between short-term traffic flow prediction and the new model is achieved. [ABSTRACT FROM AUTHOR]

Myostatin (MSTN) was previously shown to differentially regulate the adipogenesis of adipose-derived stem cells (ADSCs) and muscle satellite cells (MSCs), both of which can serve as progenitor cells for intramuscular adipocytes. We previously showed that MSTN mediates the differential regulation of MyoD and PPARγ in ADSCs and MSCs. Here, we analyzed the effects of MSTN on whole-transcriptome expression profiles of ADSCs and MSCs, revealing that MSTN differentially regulates ADSCs and MSCs, with MSCs being more responsive to MSTN treatment. More genes and pathways were altered in MSCs than in ADSCs. These changes may be responsible for the differences in the adipogenesis potential of ADSCs and MSCs after MSTN treatment. Analysis of the functions of genes that are differentially expressed in ADSCs and MSCs showed that KLF6 is a positive regulator of adipogenesis. In conclusion, the results provide important molecular insights into the regulatory mechanisms of MSTN in ADSCs and MSCs. • MSTN differentially regulates ADSCs and MSCs adipogenic potential. • More genes and pathways were altered in MSTN treated MSCs than in MSTN treated ADSCs. • KLF6 is a positive regulator of adipogenesis in ADSCs and MSCs. [ABSTRACT FROM AUTHOR]

Considering the variability and complexity of rotating machinery fault diagnosis, the fault diagnosis information carried out by a single model is not comprehensive and the fault identification rate is not high, so it cannot fully reflect the mechanical operation status. In response to this situation, this paper proposes an integrated learning method based on wavelet neural networks as base classifiers for fault diagnosis of rotating machinery, which largely meets the requirements of strong interpretability, high accuracy, and good stability. To start with, the method utilizes empirical mode decomposition (EMD) processing and decision layer fusion on multiple independent sensor signals separately, resulting in interpretative and discriminative extraction of fusion features. Next, a rose diagram classifier based on gray correlation weighting, which integrates the outputs of multiple wavelet neural networks (WNNs), is constructed, which is a more intuitive and reliable method for fusing multiple decision results using graphics. In addition, decision fusion based on rose diagram circularity is performed to realize rotating machinery fault diagnosis. Finally, the method is validated using the gear dataset and the bearing dataset, and the results of the analysis showed that the fault diagnosis accuracies for gears and bearings under two operating conditions are 97.72%, 99.41%, and 99.32%. The new method has a better fault diagnosis stability and higher fault diagnosis accuracy compared to other comparative methods. [ABSTRACT FROM AUTHOR]

• A novel Lotka-Volterra model describes the microbial competition in composting. • Time-varying parameter matrix reflects the variation of microbial interaction. • The influence of biological agents on the microbial competition can be analyzed. Aerobic compost is an effective method for the treatment of livestock manure, which is usually accompanied by complex interspecific competition. Describing these competitive relationships through mathematical models can help understand the interaction of microorganisms and analyze the effect of exogenous additive to regulate the composting process. The common model for analyzing competition problem is the Lotka-Volterra model. However, the fixed parameters of the Lotka-Volterra model are not suitable to reflect the dynamic variations of the competitive relationship when the environmental conditions change during composting process. Therefore, this paper establishes a novel fractional grey unequal-interval time-varying Lotka-Volterra model. Firstly, a fractional grey derivate operator is proposed on the basis of the unequal interval of composting data and historical dependence of microbial growth. Secondly, considering the influence of temperature, a time-varying parameter matrix is defined to reflect the variation of competitive relationship at different composting phases, and it is estimated by forgetting factor recursive least squares. Thirdly, the optimal coefficients are optimized by grey prediction evolution algorithm. Finally, the proposed model is employed to analyze the chicken manure composting experiment. The results show that the proposed model has lower error criteria and more accurate trend of fitting curve than the other five existing models. The parameter matrix describes the dynamical variation of microbial competitive relationship in two taxonomic levels and reveals that effect of the exogenous additive is principally reacted in the thermophilic phase and the competitive advantage is shifted from Bacteroidota to Firmicutes after treatment with the exogenous additive. [ABSTRACT FROM AUTHOR]

Based on the conditional heteroskedasticity of following vehicle acceleration fluctuation in car-following behavior, this paper combines the idea of driving force, Intelligent Driving Model (IDM) and Generalized Autoregressive Conditional Heteroskedasticity (GARCH model) to establish a novel car-following model. First, the concept of safety driving force and efficiency driving force are recommended, and both of them are defined by the idea of IDM, and the dynamic balance of them are the reason for acceleration fluctuation. Then, according to the heteroskedasticity of acceleration sequence, the classic GARCH model is introduced to establish the relationship among the variance of acceleration fluctuation items, driving force items and fluctuating memory items. On this basis, a novel car-following model is established, and the relational properties are studied. Finally, an example is used to verify our model, the results show that the novel car-following model is more accurate than IDM model, and the forward prediction result is close to the actual acceleration change value, which can predict the occurrence of dangerous driving behavior. [ABSTRACT FROM AUTHOR]

Analyzing the drivers of energy demand and predicting energy consumption can help to shape national policies on energy transformation and energy security. This paper estimates the demand for the various forms of energy consumed in China. A least absolute shrinkage and selection operator-random forest (Lasso-RF) two-stage model is first proposed to identify the drivers of the demand in energy. A support vector regression-compositional data second exponential smoothing (SVR-CDSES) model is then established to forecast the demand for coal, oil, natural gas, and primary electricity. The empirical analysis results inform that China's appetite for energy in the next decade will grow at an annualised rate of 2.68%. The demand for coal will rise initially and then fall at a rate of 0.79% per annum. The annual growth rate in the demand for oil will be relatively stable at 3.52%. However, the demand for natural gas and primary electricity will increase rapidly, with the highest annual growth rate at 8.05%, pointing to greater awareness of clean energy. • Study the drivers of China's energy demand and the trend of energy demand. • A new two-stage model is presented to identify the drivers in energy demand. • A new compound Support Vector Regression model is proposed to predict energy demand. • Some managerial insights and policy guidelines for energy demand are provided. [ABSTRACT FROM AUTHOR]

In this work, we consider the nonparametric estimation problem of the drift function of stochastic differential equations driven by the α -stable Lévy process. We first optimize the Kullback–Leibler divergence between the path probabilities of two stochastic differential equations with different drift functions. We then construct the variational formula based on the stationary Fokker–Planck equation using the Lagrangian multiplier. Moreover, we apply the empirical distribution to replace the stationary density, combining it with the data information, and we present the estimator of the drift function from the perspective of the process. In the numerical experiment, we investigate the effect of the different amounts of data and different α values. The experimental results demonstrate that the estimation result of the drift function is related to both and that the exact drift function agrees well with the estimated result. The estimation result will be better when the amount of data increases, and the estimation result is also better when the α value increases. [ABSTRACT FROM AUTHOR]

Myostatin (MSTN) is a secreted protein belonging to the transforming growth factor-β (TGF-β) family that is primarily expressed in skeletal muscle and also functions in adipocyte maturation. Studies have shown that MSTN can inhibit adipogenesis in muscle satellite cells (MSCs) but not in adipose-derived stem cells (ADSCs). However, the mechanism by which MSTN differently regulates adipogenesis in these two cell types remains unknown. Peroxisome proliferator-activated receptor-γ (PPARγ) and myogenic differentiation factor (MyoD) are two key transcription factors in fat and muscle cell development that influence adipogenesis. To investigate whether MSTN differentially regulates PPARγ and MyoD , we analyzed PPARγ and MyoD expression by assessing mRNA, protein and methylation levels in ADSCs and MSCs after treatment with 100 ng/mL MSTN for 0, 24, and 48 h. PPARγ mRNA levels were downregulated after 24 h and upregulated after 48 h of treatment in ADSCs, whereas in MSCs, PPARγ levels were downregulated at both time points. MyoD expression was significantly increased in ADSCs and decreased in MSCs. PPARγ and MyoD protein levels were upregulated in ADSCs and downregulated in MSCs. The CpG methylation levels of the PPARγ and MyoD promoters were decreased in ADSCs and increased in MSCs. Therefore, this study demonstrated that the different regulatory adipogenic roles of MSTN in ADSCs and MSCs act by differentially regulating PPARγ and MyoD expression. [ABSTRACT FROM AUTHOR]

Recently, electric vehicles (EVs) have become an important traffic tool in connected and automated environments due to their own advantages. However, the optimal driving control strategies of EVs and charging modes of wireless charging lanes are complex since wireless charging technology is limited when EVs are moving and traffic conditions are random. This paper constructs a scenario in which wireless charging facilities are deployed in part of a single lane and proposes a cooperative control method of mixed fleets including EVs and fuel vehicles based on the four objectives of driving safety, traffic efficiency, passenger comfort and energy management. Combined with the particle swarm optimization algorithm, the average driving velocity, lane-changing frequency and location of vehicles under different deployment lengths of charging facilities and mixing ratios are compared to discuss the influence of deployment length on the control effect of energy consumption and traffic efficiency. The numerical results indicate that when the lane length is 1500 m, with the increasing proportion of EVs, the optimal deployment lengths are approximately 700 m, 550 m and 400 m in the case of low traffic density and approximately 550 m, 500 m and 450 m in the case of high traffic density. • A multi-objective cooperative control model for hybrid vehicles is proposed. • Relations between wireless-charging arrangement and traffic condition are explored. • Optimal strategies of wireless-charging arrangement are considered. [ABSTRACT FROM AUTHOR]

The Mahalanobis–Taguchi system (MTS) is a multivariate data diagnosis and prediction technology, which is widely used to optimize large sample data or unbalanced data, but it is rarely used for high-dimensional small sample data. In this paper, the optimized MTS for the classification of high-dimensional small sample data is discussed from two aspects, namely, the inverse matrix instability of the covariance matrix and the instability of feature selection. Firstly, based on regularization and smoothing techniques, this paper proposes a modified Mahalanobis metric to calculate the Mahalanobis distance, which is aimed at reducing the influence of the inverse matrix instability under small sample conditions. Secondly, the minimum redundancy-maximum relevance (mRMR) algorithm is introduced into the MTS for the instability problem of feature selection. By using the mRMR algorithm and signal-to-noise ratio (SNR), a two-stage feature selection method is proposed: the mRMR algorithm is first used to remove noise and redundant variables; the orthogonal table and SNR are then used to screen the combination of variables that make great contribution to classification. Then, the feasibility and simplicity of the optimized MTS are shown in five datasets from the UCI database. The Mahalanobis distance based on regularization and smoothing techniques (RS-MD) is more robust than the traditional Mahalanobis distance. The two-stage feature selection method improves the effectiveness of feature selection for MTS. Finally, the optimized MTS is applied to email classification of the Spambase dataset. The results show that the optimized MTS outperforms the classical MTS and the other 3 machine learning algorithms. [ABSTRACT FROM AUTHOR]

Accurate real-time prediction of urban traffic flows is one of the most important problems in traffic management and control optimization research. Short-term traffic flow has complex stochastic and nonlinear characteristics, and it shows a similar seasonality within intraday and weekly trends. Based on these properties, we propose an improved binding cycle truncation accumulated generating operation seasonal grey rolling forecasting model. In the new model, the traffic flow sequence of seasonal fluctuation is converted to a flat sequence using the cycle truncation accumulated generating operation. Then, grey modeling of the cycle truncation accumulated generating operation sequence weakens the stochastic disturbances and highlights the intrinsic grey exponential law after the sequence is accumulated. Finally, rolling forecasts of the limited data reflect the new information priority and timeliness of the grey prediction. Two numerical traffic flow examples from China and Canada, including four groups at different time intervals (1 h, 15 min, 10 min, and 5 min), are used to verify the performance of the new model under different traffic flow conditions. The prediction results show that the model has good adaptability and stability and can effectively predict the seasonal variations in traffic flow. In 15 or 10 min traffic flow forecasts, the proposed model shows better performance than the autoregressive moving average model, wavelet neural network model and seasonal discrete grey forecasting model. [ABSTRACT FROM AUTHOR]

Peroxisome proliferator-activated receptor γ (PPARγ) is a key transcription factor in adipogenesis and can be regulated by adipogenesis-related factors. However, little information is available regarding its regulation by myogenic factors. In this study, we found that over-expression of MyoD enhanced porcine adipocyte differentiation and up-regulated PPARγ expression, whereas small interfering RNA against MyoD significantly attenuated porcine adipocyte differentiation and inhibited PPARγ expression. The MyoD-binding sites in the PPARγ promoter region at −412 to −396 and −155 to −150 were identified by promoter deletion analysis and site-directed mutagenesis. Electrophoretic mobility shift assays and chromatin immunoprecipitation further showed that these two regions are MyoD-binding sites, both in vitro and in vivo, indicating that MyoD directly interacts with the porcine PPARγ promoter. Thus, our results demonstrate that an Enhancer box and a binding site for a cooperative co-activator of MyoD are present in the promoter region of porcine PPARγ; furthermore, MyoD up-regulates PPARγ expression and promotes porcine adipocyte differentiation. [ABSTRACT FROM AUTHOR]