Data-Driven Method for Predicting Remaining Useful Life of Bearings Based on Multi-Layer Perception Neural Network and Bidirectional Long Short-Term Memory Network

The remaining useful life prediction of rolling bearing is vital in safety and reliability guarantee.In engineering scenarios,only a small amount of bearing performance degradation data can be obtained through accelerated life testing.In the absence of lifetime data,the hidden long-term correlation between performance degradation data is challenging to mine effectively,which is the main factor that restricts the prediction precision and engineering application of the residual life prediction method.To address this problem,a novel method based on the multi-layer perception neural network and bidirectional long short-term memory network is proposed.Firstly,a nonlinear health indicator(HI)calculation method based on kernel principal component analysis(KPCA)and exponential weighted moving average(EWMA)is designed.Then,using the raw vibration data and HI,a multi-layer perceptron(MLP)neural network is trained to further calculate the HI of the online bearing in real time.Furthermore,The bidirectional long short-term memory model(BiLSTM)optimized by particle swarm optimization(PSO)is used to mine the time series features of HI and predict the remaining service life.Performance verification experiments and comparative experiments are carried out on the XJTU-SY bearing open dataset.The research results indicate that this method has an excellent ability to predict future HI and remaining life.

Cell Wall Fixation,Translocation,and Vacuolar Detoxification of Cadmium Contribute to Differential Grain Cadmium Accumulation in Two Rice Cultivars

Cadmium(Cd)toxicity in rice is a major concern for human health and the environment,as it can accumulate in rice grains when grown in Cd-contaminated soils.To mitigate the risk of Cd toxicity,it is crucial to cultivate rice varieties with low grain Cd accumulation.In the summers of 2021 and 2022,we conducted Cd analysis on two rice cultivars,Tianyouhuazhan(TYHZ)and Xiushui 14,grown in fields with varying Cd pollution levels.These cultivars were also subjected to hydroponic treatment with or without 1μmol/L Cd for 7 d to assess Cd accumulation,nitric oxide(NO)production。

Predictive value of red blood cell distribution width and hematocrit for short-term outcomes and prognosis in colorectal cancer patients undergoing radical surgery

BACKGROUND Previous studies have reported that low hematocrit levels indicate poor survival in patients with ovarian cancer and cervical cancer,the prognostic value of hematocrit for colorectal cancer(CRC)patients has not been determined.The prognostic value of red blood cell distribution width(RDW)for CRC patients was controversial.AIM To investigate the impact of RDW and hematocrit on the short-term outcomes and long-term prognosis of CRC patients who underwent radical surgery.METHODS Patients who were diagnosed with CRC and underwent radical CRC resection between January 2011 and January 2020 at a single clinical center were included.The short-term outcomes,overall survival(OS)and disease-free survival(DFS)were compared among the different groups.Cox analysis was also conducted to identify independent risk factors for OS and DFS.RESULTS There were 4258 CRC patients who underwent radical surgery included in our study.A total of 1573 patients were in the lower RDW group and 2685 patients were in the higher RDW group.There were 2166 and 2092 patients in the higher hematocrit group and lower hematocrit group,respectively.Patients in the higher RDW group had more intraoperative blood loss(P<0.01)and more overall complications(P<0.01)than did those in the lower RDW group.Similarly,patients in the lower hematocrit group had more intraoperative blood loss(P=0.012),longer hospital stay(P=0.016)and overall complications(P<0.01)than did those in the higher hematocrit group.The higher RDW group had a worse OS and DFS than did the lower RDW group for tumor node metastasis(TNM)stage I(OS,P<0.05;DFS,P=0.001)and stage II(OS,P=0.004;DFS,P=0.01)than the lower RDW group;the lower hematocrit group had worse OS and DFS for TNM stage II(OS,P<0.05;DFS,P=0.001)and stage III(OS,P=0.001;DFS,P=0.001)than did the higher hematocrit group.Preoperative hematocrit was an independent risk factor for OS[P=0.017,hazard ratio(HR)=1.256,95%confidence interval(CI):1.041-1.515]and DFS(P=0.035,HR=1.194,95%CI:1.013-1.408).CONCLUSION A higher preoperative RDW and lower hematocrit were associated with more postoperative complications.However,only hematocrit was an independent risk factor for OS and DFS in CRC patients who underwent radical surgery,while RDW was not.

A modified stochastic model for LS+AR hybrid method and its application in polar motion short-term prediction

Short-term(up to 30 days)predictions of Earth Rotation Parameters(ERPs)such as Polar Motion(PM:PMX and PMY)play an essential role in real-time applications related to high-precision reference frame conversion.Currently,least squares(LS)+auto-regressive(AR)hybrid method is one of the main techniques of PM prediction.Besides,the weighted LS+AR hybrid method performs well for PM short-term prediction.However,the corresponding covariance information of LS fitting residuals deserves further exploration in the AR model.In this study,we have derived a modified stochastic model for the LS+AR hybrid method,namely the weighted LS+weighted AR hybrid method.By using the PM data products of IERS EOP 14 C04,the numerical results indicate that for PM short-term forecasting,the proposed weighted LS+weighted AR hybrid method shows an advantage over both the LS+AR hybrid method and the weighted LS+AR hybrid method.Compared to the mean absolute errors(MAEs)of PMX/PMY sho rt-term prediction of the LS+AR hybrid method and the weighted LS+AR hybrid method,the weighted LS+weighted AR hybrid method shows average improvements of 6.61%/12.08%and 0.24%/11.65%,respectively.Besides,for the slopes of the linear regression lines fitted to the errors of each method,the growth of the prediction error of the proposed method is slower than that of the other two methods.

Yield and Nutritive Values of Semi- and Non-Fall Dormant Alfalfa Cultivars under Late-Cutting Schedule in California’s Central Valley

California is one of the major alfalfa (Medicago sativa L) forage-producing states in the U.S, but its production area has decreased significantly in the last couple of decades. Selection of cultivars with high yield and nutritive value under late-cutting schedule strategy may help identify cultivars that growers can use to maximize yield while maintaining area for sustainable alfalfa production, but there is little information on this strategy. A field study was conducted to determine cumulative dry matter (DM) and nutritive values of 20 semi- and non-fall dormant (FD) ratings (FD 7 and FD 8 - 10, respectively) cultivars under 35-day cut in California’s Central Valley in 2020-2022. Seasonal cumulative DM yields ranged from 6.8 in 2020 to 37.0 Mg·ha−1 in 2021. Four FD 8 - 9 cultivars were the highest yielding with 3-yrs avg. DM greater than the lowest yielding lines by 46%. FD 7 cultivar “715RR” produced the highest crude protein (CP: 240 g·Kg−1) while FD 8 cultivar “HVX840RR” resulted in the highest neutral detergent fiber digestibility (NDFD: 484 g·Kg−1, 7% greater than the top yielding cultivars) but with DM yield intermediate. Yields and NDFD correlated positively but weakly indicating some semi- and non-FD cultivars performing similarly. These results suggest that selecting high yielding cultivars under 35-day cutting schedule strategy can be used as a tool to help growers to maximize yield while achieving good quality forages for sustainable alfalfa production in California’s Central Valley.

Effect of rice cultivar on greenhouse-gas emissions from rice-fish co-culture

In aquaculture,co-culturing rice with fish may mitigate greenhouse-gas emissions.In this study,co-culture of four rice cultivars in a laboratory-scale rice–fish system reduced CH_(4)and N_(2)O emissions relative to fish monoculture.Differences in CH_(4)and N_(2)O emissions among rice cultivars primarily stem from the differential effects of rice plants on plant-mediated CH_(4)transport,CH_(4)oxidation and nitrogen absorption.

Increasing root-lower characteristics improves drought tolerance in cotton cultivars at the seedling stage

Drought is an important abiotic stress factor in cotton production.The root system architecture(RSA)of cotton shows high plasticity which can alleviate drought-related stress under drought stress(DS)conditions;however,this alleviation is cultivar dependent.Therefore,this study estimated the genetic variability of RSA in cotton under DS.Using the paper-based growth system,we assessed the RSA variability in 80 cotton cultivars at the seedling stage,with 0 and10%polyethylene glycol 6000(PEG6000)as the control(CK)and DS treatment,respectively.An analysis of 23 aboveground and root traits in the 80 cotton cultivars revealed different responses to DS.On the 10th day after DS treatment,the degree of variation in the RSA traits under DS(5–55%)was greater than that of CK(5–49%).The 80 cultivars were divided into drought-tolerant cultivars(group 1),intermediate drought-tolerant cultivars(group 2),and drought-sensitive cultivars(group 3)based on their comprehensive evaluation values of drought resistance.Under DS,the root lengthlower,root area-lower,root volume-lower,and root length density-lower were significantly reduced by 63,71,76,and 4%in the drought-sensitive cultivars compared to CK.Notably,the drought-tolerant cultivars maintained their root lengthlower,root area-lower,root volume-lower,and root length density–lower attributes.Compared to CK,the root diameter(0–2 mm)-lower increased by 21%in group 1 but decreased by 3 and 64%in groups 2 and 3,respectively,under DS.Additionally,the drought-tolerant cultivars displayed a plastic response under DS that was characterized by an increase in the root-lower characteristics.Drought resistance was positively correlated with the root area-lower and root length density-lower.Overall,the RSA of the different cotton cultivars varied greatly under DS.Therefore,important root traits,such as the root-lower traits,provide great insights for exploring whether drought-tolerant cotton cultivars can effectively withstand adverse environments.

A telomere-to-telomere genome assembly of Hongyingzi,a sorghum cultivar used for Chinese Baijiu production

Sorghum(Sorghum bicolor(L.)Moench)is a world cereal crop used in China for producing Baijiu,a distilled spirit.We report a telomere-to-telomere genome assembly of the Baijiu cultivar Hongyingzi,HYZ-T2T,using ultralong reads.The 10 chromosome pairs contained 33,462 genes,of which 93%were functionally annotated.The 20 telomeres and 10 centromeric regions on the HYZ-T2T chromosomes were predicted and two consecutive large inversions on chromosome 2 were characterized.A 65-gene reconstruction of the metabolic pathway of tannins,the flavor substances in Baijiu,was performed and may advance the breeding of sorghum cultivars for Baijiu production.

Towards cultivar-oriented gene discovery for better crops

The continued expansion of the world population,increasingly inconsistent climate and shrinking agricultural resources present major challenges to crop breeding.Fortunately,the increasing ability to discover and manipulate genes creates new opportunities to develop more productive and resilient cultivars.Many genes have been described in papers as being beneficial for yield increase.However,few of them have been translated into increased yield on farms.In contrast,commercial breeders are facing gene decidophobia,i.e.,puzzled about which gene to choose for breeding among the many identified,a huge chasm between gene discovery and cultivar innovation.The purpose of this paper is to draw attention to the shortfalls in current gene discovery research and to emphasise the need to align with cultivar innovation.The methodology dictates that genetic studies not only focus on gene discovery but also pay good attention to the genetic backgrounds,experimental validation in relevant environments,appropriate crop management,and data reusability.The close of the gaps should accelerate the application of molecular study in breeding and contribute to future global food security.

Short-Term Household Load Forecasting Based on Attention Mechanism and CNN-ICPSO-LSTM

Accurate load forecasting forms a crucial foundation for implementing household demand response plans andoptimizing load scheduling. When dealing with short-term load data characterized by substantial fluctuations,a single prediction model is hard to capture temporal features effectively, resulting in diminished predictionaccuracy. In this study, a hybrid deep learning framework that integrates attention mechanism, convolution neuralnetwork (CNN), improved chaotic particle swarm optimization (ICPSO), and long short-term memory (LSTM), isproposed for short-term household load forecasting. Firstly, the CNN model is employed to extract features fromthe original data, enhancing the quality of data features. Subsequently, the moving average method is used for datapreprocessing, followed by the application of the LSTM network to predict the processed data. Moreover, the ICPSOalgorithm is introduced to optimize the parameters of LSTM, aimed at boosting the model’s running speed andaccuracy. Finally, the attention mechanism is employed to optimize the output value of LSTM, effectively addressinginformation loss in LSTM induced by lengthy sequences and further elevating prediction accuracy. According tothe numerical analysis, the accuracy and effectiveness of the proposed hybrid model have been verified. It canexplore data features adeptly, achieving superior prediction accuracy compared to other forecasting methods forthe household load exhibiting significant fluctuations across different seasons.

Modeling injection-induced fault slip using long short-term memory networks

Stress changes due to changes in fluid pressure and temperature in a faulted formation may lead to the opening/shearing of the fault.This can be due to subsurface(geo)engineering activities such as fluid injections and geologic disposal of nuclear waste.Such activities are expected to rise in the future making it necessary to assess their short-and long-term safety.Here,a new machine learning(ML)approach to model pore pressure and fault displacements in response to high-pressure fluid injection cycles is developed.The focus is on fault behavior near the injection borehole.To capture the temporal dependencies in the data,long short-term memory(LSTM)networks are utilized.To prevent error accumulation within the forecast window,four critical measures to train a robust LSTM model for predicting fault response are highlighted:(i)setting an appropriate value of LSTM lag,(ii)calibrating the LSTM cell dimension,(iii)learning rate reduction during weight optimization,and(iv)not adopting an independent injection cycle as a validation set.Several numerical experiments were conducted,which demonstrated that the ML model can capture peaks in pressure and associated fault displacement that accompany an increase in fluid injection.The model also captured the decay in pressure and displacement during the injection shut-in period.Further,the ability of an ML model to highlight key changes in fault hydromechanical activation processes was investigated,which shows that ML can be used to monitor risk of fault activation and leakage during high pressure fluid injections.

A Time Series Short-Term Prediction Method Based on Multi-Granularity Event Matching and Alignment

Accurate forecasting of time series is crucial across various domains.Many prediction tasks rely on effectively segmenting,matching,and time series data alignment.For instance,regardless of time series with the same granularity,segmenting them into different granularity events can effectively mitigate the impact of varying time scales on prediction accuracy.However,these events of varying granularity frequently intersect with each other,which may possess unequal durations.Even minor differences can result in significant errors when matching time series with future trends.Besides,directly using matched events but unaligned events as state vectors in machine learning-based prediction models can lead to insufficient prediction accuracy.Therefore,this paper proposes a short-term forecasting method for time series based on a multi-granularity event,MGE-SP(multi-granularity event-based short-termprediction).First,amethodological framework for MGE-SP established guides the implementation steps.The framework consists of three key steps,including multi-granularity event matching based on the LTF(latest time first)strategy,multi-granularity event alignment using a piecewise aggregate approximation based on the compression ratio,and a short-term prediction model based on XGBoost.The data from a nationwide online car-hailing service in China ensures the method’s reliability.The average RMSE(root mean square error)and MAE(mean absolute error)of the proposed method are 3.204 and 2.360,lower than the respective values of 4.056 and 3.101 obtained using theARIMA(autoregressive integratedmoving average)method,as well as the values of 4.278 and 2.994 obtained using k-means-SVR(support vector regression)method.The other experiment is conducted on stock data froma public data set.The proposed method achieved an average RMSE and MAE of 0.836 and 0.696,lower than the respective values of 1.019 and 0.844 obtained using the ARIMA method,as well as the values of 1.350 and 1.172 obtained using the k-means-SVR method.

Analysis on Genetic Diversity of 40 Flowering Cherry Cultivars and Construction of Molecular ID Based on SSR Markers

Studying on the genetic diversity and genetic relationship of flowering cherry cultivars is extremely important for germplasm conservation, cultivar identification and breeding. Flowering cherry is widely cultivated as an important woody ornamental plant in worldwide, especially Japan, China. However, owning to the morphological similarity, many cultivars are distinguished hardly in non-flowering season. Here, we evaluated the genetic diversity and genetic relationship of 40 flowering cherry cultivars, which are mainly cultivated in China. We selected 13 polymorphicprimers to amplify to allele fragments with fluorescent-labeled capillary electrophoresis technology. The population structure analysis results show that these cultivars could be divided into 4 subpopulations. At the population level, Na and Ne were 6.062, 4.326, respectively. Ho and He were 0.458 and 0.670, respectively. The Shannon’s information index (I) was 1.417. The Pop3, which originated from P. serrulata, had the highest Ho, He, and I among the 4 subpopulations. AMOVA showed that only 4% of genetic variation came from populations, the 39% variation came from individuals and 57% (p < 0.05) came from intra-individuals. 5 polymorphic SSR primers were selected to construct molecular ID code system of these cultivars. This analysis on the genetic diversity and relationship of the 40 flowering cherry cultivars will help to insight into the genetic background, relationship of these flowering cherry cultivars and promote to identify similar cultivars.

Effect of Different Mulch Materials on Yield and Nutrition Profile of Common Capsicum (Capsicum annuum) Cultivars in Bangladesh

Capsicum is a nutritious vegetable and its cultivation in farms is getting popular in Bangladesh. Although many efforts have lain to explore better yielding and nutritionally rich cultivars with suitable modern cultivation techniques but still have to find the desired outcome. Thus, it’s necessary to conduct further research to identify the high-yielding and nutritious capsicum cultivars in Bangladesh. An experiment was conducted from July 2021 to June 2022 at the Bangladesh Institute of Research and Training on Applied Nutrition (BIRTAN) research field with three cultivars of capsicum: B0 = California Wonder, B1 = BARI Misti Morich-1 and B2 = BARI Misti Morich-2 and three mulching: T0 = No mulching, T1 = Water hyacinth, T2 = Poly Mulching in randomized complete block design with three replications to identify better quality capsicum cultivar and suitable mulching material. Among cultivars the BARI Misti Morich-2 (B2) showed increased agronomic parameters like number of branches and effective branches per plant, leaves length and width, consequently yield and yield contributing traits were also enhanced like fruits per plant, fruit length, fruit diameter and yield per plant (25.97%, 4.54%, 3.64% and 21.43%, respectively). Poly Mulching (T2) increased agronomic traits, yield traits and yield (0.61 kg) than BARI Misti Morich-1 (T1). The combined effect of B2T2 increased the number of branches per plant, effective branches per plant, leaves length and breadth by 40%, 90%, 15.57% and 26.22%, respectively, hence resulting in an increased yield of 20%. BARI Misti Morich-2 cultivar showed an increase in Fe, Zn and Vitamin-C content of 26.24% and 23.10%, 8.82% and 5.14%, and 6.03% and 5.74% than B0 and B1 cultivars, respectively. Therefore, BARI Misti Morich-2 exhibited the improved agronomic, yield and nutritional traits of capsicum under poly mulching among other cultivars in Bangladesh.

Physics Guided Deep Learning-Based Model for Short-Term Origin–Destination Demand Prediction in Urban Rail Transit Systems Under Pandemic

Accurate origin–destination(OD)demand prediction is crucial for the efficient operation and management of urban rail transit(URT)systems,particularly during a pandemic.However,this task faces several limitations,including real-time availability,sparsity,and high-dimensionality issues,and the impact of the pandemic.Consequently,this study proposes a unified framework called the physics-guided adaptive graph spatial–temporal attention network(PAG-STAN)for metro OD demand prediction under pandemic conditions.Specifically,PAG-STAN introduces a real-time OD estimation module to estimate real-time complete OD demand matrices.Subsequently,a novel dynamic OD demand matrix compression module is proposed to generate dense real-time OD demand matrices.Thereafter,PAG-STAN leverages various heterogeneous data to learn the evolutionary trend of future OD ridership during the pandemic.Finally,a masked physics-guided loss function(MPG-loss function)incorporates the physical quantity information between the OD demand and inbound flow into the loss function to enhance model interpretability.PAG-STAN demonstrated favorable performance on two real-world metro OD demand datasets under the pandemic and conventional scenarios,highlighting its robustness and sensitivity for metro OD demand prediction.A series of ablation studies were conducted to verify the indispensability of each module in PAG-STAN.

New insights into the combined effects of geographical origin,cultivar and crop season on the physicochemical characteristics of Moroccan olive oils produced in northern Morocco.A comparative study

The Tangier-Tetouan-Al Hoceima(TTA)region is one of the main olive oil producing regions in Morocco.Little is devoted to characterize olive oil physicochemical traits from TTA hence the originality of this study.It aimed at investigating variation in olive oil quality produced from three Moroccan cultivars‘Moroccan Picholine’,‘Menara’,and‘Haouzia’and their blends.Sampling was performed in five provinces fromTTA(Northern Morocco)during four consecutive crop-seasons(2018-2021)considering three extraction technologies(ET):traditional discontinuous press system(SP)and continuous extraction systems including decanter of three outlets(3O)and decanter of two outlets(2O).Physicochemical measurements consisted of routinely quality parameters namely free acidity(FA),peroxide value(PV),UV absorption parameters(K232,K270,andΔK),chlorophylls(Chl)and carotenoids(Car)contents,total phenolic compounds(TPC)and oxidative stability(OS).Crop season showed its superiority impacts on K232,OS,TPC,Chl,and OS.While cultivar was the main variability source in both PV and K270,and FA was mainly determined by ET.Important variations(p<0.05)were reported among crop seasons and locations due to pedoclimatic differences.‘Menara’and‘Haouzia’had higher pigments content,TPC,and OS,and the blends displayed low pigments concentration,TPC,and OS.Expectedly,continuous ET(2O and 3O)had the greatest values of pigments content,TPC,and OS as revealed by principal component analysis.Strong correlations were highlighted among basic quality parameters,TPC,pigments,and OS.Simple linear regression was used to describe the relationships between OS and TPC(R^(2)=0.856)and OS regressed against Chl(R^(2)=0.690)and Car(R^(2)=0.760),while TPC were regressed on Chl(R^(2)=0.670)and Car(R^(2)=0.680)and finally Chl against Car(R^(2)=0.931).In conclusion,compared to technological,genotypic,and geographic effects,climatic conditions were the main factor driving olive oil stability and associated phenolics and pigments;oil cultivar blend seems to have negative effects on pigments concentration and total phenolic compounds as well as oxidative stability.

Short-term efficacy of microwave ablation in the treatment of liver cancer and its effect on immune function

BACKGROUND Hepatectomy is the first choice for treating liver cancer.However,inflammatory factors,released in response to pain stimulation,may suppress perioperative immune function and affect the prognosis of patients undergoing hepatectomies.AIM To determine the short-term efficacy of microwave ablation in the treatment of liver cancer and its effect on immune function.METHODS Clinical data from patients with liver cancer admitted to Suzhou Ninth People’s Hospital from January 2020 to December 2023 were retrospectively analyzed.Thirty-five patients underwent laparoscopic hepatectomy for liver cancer(liver cancer resection group)and 35 patients underwent medical image-guided microwave ablation(liver cancer ablation group).The short-term efficacy,complications,liver function,and immune function indices before and after treatment were compared between the two groups.RESULTS One month after treatment,19 patients experienced complete remission(CR),8 patients experienced partial remission(PR),6 patients experienced stable disease(SD),and 2 patients experienced disease progression(PD)in the liver cancer resection group.In the liver cancer ablation group,21 patients experienced CR,9 patients experienced PR,3 patients experienced SD,and 2 patients experienced PD.No significant differences in efficacy and complications were detected between the liver cancer ablation and liver cancer resection groups(P>0.05).After treatment,total bilirubin(41.24±7.35 vs 49.18±8.64μmol/L,P<0.001),alanine aminotransferase(30.85±6.23 vs 42.32±7.56 U/L,P<0.001),CD4+(43.95±5.72 vs 35.27±5.56,P<0.001),CD8+(20.38±3.91 vs 22.75±4.62,P<0.001),and CD4+/CD8+(2.16±0.39 vs 1.55±0.32,P<0.001)were significantly different between the liver cancer ablation and liver cancer resection groups.CONCLUSION The short-term efficacy and safety of microwave ablation and laparoscopic surgery for the treatment of liver cancer are similar,but liver function recovers quickly after microwave ablation,and microwave ablation may enhance immune function.

Study on Germplasm Resources of Peach Cultivars

[Objectives]To study the germplasm resources of excellent peach cultivars.[Methods]Five peach cultivars were introduced,in-cluding‘Jinxiu’peach,‘Jinxiang’peach,‘Chunxiao’peach,‘Hujingmilu’peach and‘018 nectarine’peach.Then,these five cultivars were used to study the biological characteristics of peach trees,namely,as phenology,fruit quality,heat resistance,cold resistance and other resistance.[Results]Five cultivars of peach plants grew fast and robust,among which‘018 nectarine’had very crisp fruit,‘Jinxiu’,‘Jinxiang’,‘Chunxiao’and‘Hujingmilu’had very sweet fruitꎻthe peach trees of these five cultivars have good water resistance,heat resist-ance and cold resistance.[Conclusions]The results of this study can not only provide a reference for the introduction of peach trees,but also provide a practical basis for the large-scale planting of peach trees.

Study of A Hybrid Deep Learning Method for Forecasting the Short-Term Motion Responses of A Semi-Submersible

Accurately predicting motion responses is a crucial component of the design process for floating offshore structures.This study introduces a hybrid model that integrates a convolutional neural network(CNN),a bidirectional long short-term memory(BiLSTM)neural network,and an attention mechanism for forecasting the short-term motion responses of a semisubmersible.First,the motions are processed through the CNN for feature extraction.The extracted features are subsequently utilized by the BiLSTM network to forecast future motions.To enhance the predictive capability of the neural networks,an attention mechanism is integrated.In addition to the hybrid model,the BiLSTM is independently employed to forecast the motion responses of the semi-submersible,serving as benchmark results for comparison.Furthermore,both the 1D and 2D convolutions are conducted to check the influence of the convolutional dimensionality on the predicted results.The results demonstrate that the hybrid 1D CNN-BiLSTM network with an attention mechanism outperforms all other models in accurately predicting motion responses.

Transformer-based correction scheme for short-term bus load prediction in holidays

To tackle the problem of inaccurate short-term bus load prediction,especially during holidays,a Transformer-based scheme with tailored architectural enhancements is proposed.First,the input data are clustered to reduce complexity and capture inherent characteristics more effectively.Gated residual connections are then employed to selectively propagate salient features across layers,while an attention mechanism focuses on identifying prominent patterns in multivariate time-series data.Ultimately,a pre-trained structure is incorporated to reduce computational complexity.Experimental results based on extensive data show that the proposed scheme achieves improved prediction accuracy over comparative algorithms by at least 32.00%consistently across all buses evaluated,and the fitting effect of holiday load curves is outstanding.Meanwhile,the pre-trained structure drastically reduces the training time of the proposed algorithm by more than 65.75%.The proposed scheme can efficiently predict bus load results while enhancing robustness for holiday predictions,making it better adapted to real-world prediction scenarios.