Data Augmentation Technology Driven By Image Style Transfer in Self-Driving Car Based on End-to-End Learning

With the advent of deep learning,self-driving schemes based on deep learning are becoming more and more popular.Robust perception-action models should learn from data with different scenarios and real behaviors,while current end-to-end model learning is generally limited to training of massive data,innovation of deep network architecture,and learning in-situ model in a simulation environment.Therefore,we introduce a new image style transfer method into data augmentation,and improve the diversity of limited data by changing the texture,contrast ratio and color of the image,and then it is extended to the scenarios that the model has been unobserved before.Inspired by rapid style transfer and artistic style neural algorithms,we propose an arbitrary style generation network architecture,including style transfer network,style learning network,style loss network and multivariate Gaussian distribution function.The style embedding vector is randomly sampled from the multivariate Gaussian distribution and linearly interpolated with the embedded vector predicted by the input image on the style learning network,which provides a set of normalization constants for the style transfer network,and finally realizes the diversity of the image style.In order to verify the effectiveness of the method,image classification and simulation experiments were performed separately.Finally,we built a small-sized smart car experiment platform,and apply the data augmentation technology based on image style transfer drive to the experiment of automatic driving for the first time.The experimental results show that:(1)The proposed scheme can improve the prediction accuracy of the end-to-end model and reduce the model’s error accumulation;(2)the method based on image style transfer provides a new scheme for data augmentation technology,and also provides a solution for the high cost that many deep models rely heavily on a large number of label data.

Integrated System of Solar Cells with Hierarchical NiCo2O4 Battery-Supercapacitor Hybrid Devices for Self-Driving Light-Emitting Diodes

An integrated system has been provided with a-Si/H solar cells as energy conversion device,NiCo2O4 battery-supercapacitor hybrid(BSH)as energy storage device,and light emitting diodes(LEDs)as energy utilization device.By designing three-dimensional hierarchical NiCo2O4 arrays as faradic electrode,with capacitive electrode of active carbon(AC),BSHs were assembled with energy density of 16.6 Wh kg-1,power density of 7285 W kg-1,long-term stability with 100% retention after 15,000 cycles,and rather low self-discharge.The NiCo2O4//AC BSH was charged to 1.6 V in 1 s by solar cells and acted as reliable sources for powering LEDs.The integrated system is rational for operation,having an overall efficiency of 8.1% with storage efficiency of 74.24%.The integrated system demonstrates a stable solar power conversion,outstanding energy storage behavior,and reliable light emitting.Our study offers a precious strategy to design a self-driven integrated system for highly efficient energy utilization.

An Optimal Distribution of RSU for Improving Self-Driving Vehicle Connectivity

Self-driving and semi-self-driving cars play an important role in our daily lives.The effectiveness of these cars is based heavily on the use of their surrounding areas to collect sensitive and vital information.However,external infrastructures also play significant roles in the transmission and reception of control data,cooperative awareness messages,and caution notifications.In this case,roadside units are considered one of themost important communication peripherals.Random distribution of these infrastructures will overburden the spread of self-driving vehicles in terms of cost,bandwidth,connectivity,and radio coverage area.In this paper,a new distributed roadside unit is proposed to enhance the performance and connectivity of these cars.Therefore,this approach is based primarily on k-means to find the optimal location of each roadside unit.In addition,this approach supports dynamicmobility with a long period of connectivity for each car.Further,this system can adapt to various locations(e.g.,highways,rural areas,urban environments).The simulation results of the proposed system are reflected in its efficiency and effectively.Thus,the system can achieve a high connectivity rate with a low error rate while reducing costs.

A Co-Point Mapping-Based Approach to Drivable Area Detection for Self-Driving Cars

The randomness and complexity of urban traffic scenes make it a difficult task for self-driving cars to detect drivable areas, Inspired by human driving behaviors, we propose a novel method of drivable area detection for self-driving cars based on fusing pixel information from a monocular camera with spatial information from a light detection and ranging （LIDAR） scanner, Similar to the bijection of collineation, a new concept called co-point mapping, which is a bijection that maps points from the LIDAR scanner to points on the edge of the image segmentation, is introduced in the proposed method, Our method posi- tions candidate drivable areas through self-learning models based on the initial drivable areas that are obtained by fusing obstacle information with superpixels, In addition, a fusion of four features is applied in order to achieve a more robust performance, In particular, a feature called drivable degree （DD） is pro- posed to characterize the drivable degree of the LIDAR points, After the initial drivable area is characterized by the features obtained through self-learning, a Bayesian framework is utilized to calculate the final probability map of the drivable area, Our approach introduces no common hypothesis and requires no training steps; yet it yields a state-of-art performance when tested on the ROAD-KITTI benchmark, Experimental results demonstrate that the proposed method is a general and efficient approach for detecting drivable area,

The Effect of Self-Driving Car on Urban Traffic

Based on the idea of infinitesimal analysis, we establish the basic model of relation between speed and flow. Since putting a certain amount of self-driving car will affect the average speed of mixed traffic flow, we choose the proportion of self-driving car to be a variable, denoted by k. Based on the least square method, we find two critical values of k that are 38.63% and 68.26%. When k 38.63%, the self-driving cars have a negative influence to the traffic. When 38.63% < k < 68.26%, they have a positive influence to the traffic. When k > 68.26%, they have significant improvement to the traffic capacity of the road.

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.

A Driving Strategy Model of Self-Driving Cars

The self-driving cars are highly developed and about to meet the market, but the driving strategies and corresponding behaviors with others still need to be tested. In this paper, based on its characteristics and behaviors of manual-driving vehicles, we propose the driving strategies of manual-driving cars as well as self-driving cars. And we use the cellular automaton to simulate the traffic reality under different conditions, and to evaluate the efficiency of a road when self-driving cars are put into use. This research can be a reference by traffic planning and vehicles performance test, and further research can be designed in a model which can calculate the efficiency of a road when the percentage of self-driving cars are different.

Behavior Analysis of Self-Driving Tourists Based on Content Analysis of Network Travel Notes: A Case Study of the Inner Mongolia Autonomous Region

Self-diiviiig tour is one of the most important wajrs for people to travel, and network travel notes actually reflect the traveling information of self-driving tourists. In this paper, witii the network travel notes of self-driving tourists as the tesearch object^ methods such as text analysis and visualization were adopted to study behavior patterns of self-driving tourists, tourism experience, time-space migration, and distribution of tourism resources in Inner Mongolia, fi：om the multiple dimensions of mobile drivers, perceived, dimensions, and spatial migration. The results showed tiiat ①self-cidviiig tourists had a variety of motivations for traveling, in which love for nature dominated; ②self-driving tour destinations were mainly Hulunbuir, Ordos, and Alxa League; ③spatial migration was characterized by obvious seasonal fluctuations. The fesearch on the behavior of self-driving tourists in Inner Mongolia is an important part of the study of the connection between tourism resources and market connection in Inner Mongolia, and is of significance for guiding the theory, practice and poliqr foimuktion of self-doving tours in Inner Mongolia.

Using discriminant analysis to detect intrusions in external communication for self-driving vehicles

Security systems are a necessity for the deployment of smart vehicles in our society. Security in vehicular ad hoe networks is crucial to the reliable exchange of information and control data. In this paper, we propose an intelligent Intrusion Detection System （IDS） to protect the external communication of self-driving and semi self-driving vehicles. This technology has the ability to detect Denial of Service （DOS） and black hole attacks on vehicular ad hoe networks （VANETs）. The advantage of the proposed IDS over existing security systems is that it detects attacks before they causes significant damage. The intrusion prediction technique is based on Linear Discriminant Analysis （LDA） and Quadratic Diseriminant Analysis （QDA） which are used to predict attacks based on observed vehicle behavior. We perform simulations using Network Simulator 2 to demonstrate that the IDS achieves a low rate of false alarms and high accuracy in detection.

Laws and Ethics Policy of Self-driving Cars in Taiwan

Countries have invested considerable sums of human capital and material resources in the practical application of self-driving cars demonstrating the impressive market opportunity.In light of this trend,Taiwan does not want to fall behind either.As on-road testing and technological development for self-driving cars continue to develop in different countries,the controversial issues of safety,ethics,liability,and the invasion of privacy continue to emerge.In order to resolve these issues,the government of Taiwan seeks to provide a good environment for AI(artificial intelligence)innovation and applications.This article summarizes and highlights relevant content and key points of Unmanned Vehicles Technology Innovative Experimentation Act,which was legislated in Taiwan in 2018.In addition,it points out the fundamental ethics regulation of AI,which has influenced Taiwan legal policy.

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.

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.

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.

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.

Should Self-Driving Vehicles Be Encouraged?

Late this March.China＇s Internet giant Baidu became the first self-driving car developer to obtain temporary license plates to carry out self driving tests on public roads in Beijing.

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.

An Enhanced Ensemble-Based Long Short-Term Memory Approach for Traffic Volume Prediction

With the advancement of artificial intelligence,traffic forecasting is gaining more and more interest in optimizing route planning and enhancing service quality.Traffic volume is an influential parameter for planning and operating traffic structures.This study proposed an improved ensemble-based deep learning method to solve traffic volume prediction problems.A set of optimal hyperparameters is also applied for the suggested approach to improve the performance of the learning process.The fusion of these methodologies aims to harness ensemble empirical mode decomposition’s capacity to discern complex traffic patterns and long short-term memory’s proficiency in learning temporal relationships.Firstly,a dataset for automatic vehicle identification is obtained and utilized in the preprocessing stage of the ensemble empirical mode decomposition model.The second aspect involves predicting traffic volume using the long short-term memory algorithm.Next,the study employs a trial-and-error approach to select a set of optimal hyperparameters,including the lookback window,the number of neurons in the hidden layers,and the gradient descent optimization.Finally,the fusion of the obtained results leads to a final traffic volume prediction.The experimental results show that the proposed method outperforms other benchmarks regarding various evaluation measures,including mean absolute error,root mean squared error,mean absolute percentage error,and R-squared.The achieved R-squared value reaches an impressive 98%,while the other evaluation indices surpass the competing.These findings highlight the accuracy of traffic pattern prediction.Consequently,this offers promising prospects for enhancing transportation management systems and urban infrastructure planning.

Seasonal Short-Term Load Forecasting for Power Systems Based onModal Decomposition and Feature-FusionMulti-Algorithm Hybrid Neural NetworkModel

To enhance the refinement of load decomposition in power systems and fully leverage seasonal change information to further improve prediction performance,this paper proposes a seasonal short-termload combination prediction model based on modal decomposition and a feature-fusion multi-algorithm hybrid neural network model.Specifically,the characteristics of load components are analyzed for different seasons,and the corresponding models are established.First,the improved complete ensemble empirical modal decomposition with adaptive noise(ICEEMDAN)method is employed to decompose the system load for all four seasons,and the new sequence is obtained through reconstruction based on the refined composite multiscale fuzzy entropy of each decomposition component.Second,the correlation between different decomposition components and different features is measured through the max-relevance and min-redundancy method to filter out the subset of features with strong correlation and low redundancy.Finally,different components of the load in different seasons are predicted separately using a bidirectional long-short-term memory network model based on a Bayesian optimization algorithm,with a prediction resolution of 15 min,and the predicted values are accumulated to obtain the final results.According to the experimental findings,the proposed method can successfully balance prediction accuracy and prediction time while offering a higher level of prediction accuracy than the current prediction methods.The results demonstrate that the proposedmethod can effectively address the load power variation induced by seasonal differences in different regions.