Search results

In autonomous driving, the inherent sparsity of point clouds often limits the performance of object detection, while existing multimodal architectures struggle to meet the real-time requirements for 3D object detection. Therefore, the main purpose of this paper is to significantly enhance the detection performance of objects, especially the recognition capability for small-sized objects and to address the issue of slow inference speed. This will improve the safety of autonomous driving systems and provide feasibility for devices with limited computing power to achieve autonomous driving.

BRTPillar first adopts an element-based method to fuse image and point cloud features. Secondly, a local-global feature interaction method based on an efficient additive attention mechanism was designed to extract multi-scale contextual information. Finally, an enhanced multi-scale feature fusion method was proposed by introducing adaptive spatial and channel interaction attention mechanisms, thereby improving the learning of fine-grained features.

Extensive experiments were conducted on the KITTI dataset. The results showed that compared with the benchmark model, the accuracy of cars, pedestrians and cyclists on the 3D object box improved by 3.05, 9.01 and 22.65%, respectively; the accuracy in the bird’s-eye view has increased by 2.98, 10.77 and 21.14%, respectively. Meanwhile, the running speed of BRTPillar can reach 40.27 Hz, meeting the real-time detection needs of autonomous driving.

This paper proposes a boosting multimodal real-time 3D object detection method called BRTPillar, which achieves accurate location in many scenarios, especially for complex scenes with many small objects, while also achieving real-time inference speed.

High-speed turnouts are more complex in structure and thus may cause abnormal vibration of high-speed train car body, affecting driving safety and passenger riding experience. Therefore, it is necessary to analyze the data characteristics of continuous hunting of high-speed trains passing through turnouts and propose a diagnostic method for engineering applications.

First, Complete Ensemble Empirical Mode Decomposition with Adaptive Noise (CEEMDAN) is performed to determine the first characteristic component of the car body’s lateral acceleration. Then, the Short-Time Fourier Transform (STFT) is performed to calculate the marginal spectra. Finally, the presence of a continuous hunting problem is determined based on the results of the comparison calculations and diagnostic thresholds. To improve computational efficiency, permutation entropy (PE) is used as a fast indicator to identify turnouts with potential problems.

Under continuous hunting conditions, the PE is less than 0.90; the ratio of the maximum peak value of the signal component to the original signal peak value exceeded 0.7, and there is an energy band in the STFT time-frequency map, which corresponds to a frequency distribution range of 1–2 Hz.

The research results have revealed the lateral vibration characteristics of the high-speed train’s car body during continuous hunting when passing through turnouts. On this basis, an effective diagnostic method has been proposed. With a focus on practical engineering applications, a rapid screening index for identifying potential issues has been proposed, significantly enhancing the efficiency of diagnostic processes.

This study aims to investigate the optimal pricing decisions and shared channel strategy selection of battery manufacturers considering heterogeneous consumers' range anxiety.

Amidst the rapid growth of the electric vehicle sector, countries are promoting upgrades in the automotive industry. However, insufficient driving range causes consumer range anxiety. The study utilizes the Stackelberg game model to assess how range anxiety influences battery manufacturers' pricing and channel strategy decisions across three strategies.

We find that electric vehicle battery manufacturers' decisions to cooperate with third-party sharing platforms (TPSPs) are primarily influenced by fixed costs and consumer range anxiety levels. As range anxiety increases, the cost threshold for joining shared channels rises, reducing cooperation likelihood. However, considering diverse consumer needs, especially a higher proportion of leisure-oriented consumers, increases the likelihood of cooperation. Furthermore, higher battery quality makes direct participation in shared channels more probable.

In the electric vehicle industry, range anxiety is a significant concern. While existing literature focuses on its impact on consumer behavior and charging infrastructure, this study delves into battery manufacturers' strategic responses, offering insights into channel options and pricing strategies amidst diverse consumer segments.

Agriculture commodity price forecasts have long been important for a variety of market players. The study we conducted aims to address this difficulty by examining the weekly wholesale price index of green grams in the Chinese market. The index covers a ten-year period, from January 1, 2010, to January 3, 2020, and has significant economic implications.

In order to address the nonlinear patterns present in the price time series, we investigate the nonlinear auto-regressive neural network as the forecast model. This modeling technique is able to combine a variety of basic nonlinear functions to approximate more complex nonlinear characteristics. Specifically, we examine prediction performance that corresponds to several configurations across data splitting ratios, hidden neuron and delay counts, and model estimation approaches.

Our model turns out to be rather simple and yields forecasts with good stability and accuracy. Relative root mean square errors throughout training, validation and testing are specifically 4.34, 4.71 and 3.98%, respectively. The results of benchmark research show that the neural network produces statistically considerably better performance when compared to other machine learning models and classic time-series econometric methods.

Utilizing our findings as independent technical price forecasts would be one use. Alternatively, policy research and fresh insights into price patterns might be achieved by combining them with other (basic) prediction outputs.

This study aims to streamline and enhance the assembly defect inspection process in diesel engine production. Traditional manual inspection methods are labor-intensive and time-consuming because of the complex structures of the engines and the noisy workshop environment. This study’s robotic system aims to alleviate these challenges by automating the inspection process and enabling easy remote inspection, thereby freeing workers from heavy fieldwork.

This study’s system uses a robotic arm to traverse and capture images of key components of the engine. This study uses anomaly detection algorithms to automatically identify defects in the captured images. Additionally, this system is enhanced by digital twin technology, which provides inspectors with various tools to designate components of interest in the engine and assist in defect checking and annotation. This integration facilitates smooth transitions from manual to automatic inspection within a short period.

Through evaluations and user studies conducted over a relatively long period, the authors found that the system accelerates and improves the accuracy of engine inspections. The results indicate that the system significantly enhances the efficiency of production processes for manufacturers.

The system represents a novel approach to engine inspection, leveraging robotic technology and digital twin enhancements to address the limitations of traditional manual inspection methods. By automating and enhancing the inspection process, the system offers manufacturers the opportunity to improve production efficiency and ensure the quality of diesel engines.

Enhancing total factor productivity through digital transformation is a crucial pathway for the high-quality development of manufacturing enterprises. This research aims to investigate the impact mechanisms of manufacturing enterprises’ total factor productivity in the context of digital transformation.

Using the data from 536 Chinese listed manufacturing enterprises from 2018 to 2021, this research divides digital transformation into two dimensions (i.e. digital transformation breadth and digital transformation depth) and examines their impacts on total factor productivity as well as the mediation effects of innovation capability and reconfiguration capacity.

It is found that digital transformation breadth, digital transformation depth and their interaction can positively affect manufacturing enterprises’ total factor productivity. The innovation capability and reconfiguration capacity of manufacturing enterprises act as mediators between digital transformation breadth and total factor productivity, as well as between digital transformation depth and total factor productivity.

This study is one of the first attempts to investigate the impact mechanisms of manufacturing enterprises’ total factor productivity from the perspective of digital transformation breadth and depth.

Using the theoretical framework of social comparison theory (SCT), this study investigates the effects of employee envy on service sabotage behaviors in the hospitality industry. It further examines the complex dynamics of self-performance and job dissatisfaction in this context. Notably, this paper seeks to determine the potential moderating role of perceived employability in the interactions between service sabotage, employee envy, job dissatisfaction and self-performance.

Our research structure was divided into four distinct models. The findings of Model 1 highlight the significant impact of employee envy on service sabotage. The analysis in Model 2a shows that job dissatisfaction acts as a partial mediator in the employee envy and service sabotage linkage. On the other hand, Model 2b reveals self-performance as yet another partial mediator between envy-service sabotage relationships. In turn, Model 3 demonstrates that job dissatisfaction and self-performance play a serial mediation role in the envy-service sabotage relationship. In addition, our research shows that perceived employability effectively moderates the three proposed paths within these relationships.

Our research structure was divided into four distinct models. The findings of Model 1 highlight the significant impact of employee envy on service sabotage. The analysis in Model 2a shows that job dissatisfaction acts as a partial mediator in the employee envy and service sabotage linkage. On the other hand, Model 2b reveals self-performance as yet another partial mediator between envy-service sabotage relationships. In turn, Model 3 demonstrates that job dissatisfaction and self-performance play a serial mediation role in the envy-service sabotage relationship. In addition, our research shows that perceived employability effectively moderates the three proposed paths within these relationships.

Hotel managers must keep a close eye on their front-of-house staff to avoid any unintentional or direct interactions with customers. Equally important is the consistent and impartial treatment of all employees, which is an important consideration for managers to consider because it can help mitigate employee envy and job dissatisfaction.

This study seeks to enhance understanding of SCT by emphasizing perceived employability as a boundary influencing the relationships between these factors and desired outcomes in the hotel industry, such as job dissatisfaction, self-performance and service sabotage. This paper is an initial attempt to investigate the underlying mechanisms in the relationship between envy and service sabotage.

Hospital heating, ventilation and air conditioning (HVAC) systems are essential to patient safety and wellness. System malfunctions, however, may result in energy waste and even pose health dangers. This project aims to provide a fault detection and diagnostics framework designed primarily for HVAC systems in hospitals.

In order to identify problems in hospital air handling units, the study uses a data-driven methodology that makes use of Long Short-Term Memory (LSTM) and Gated Recurrent Units (GRU) models. To address the problem of uneven data, the dataset is balanced. Other machine learning classifiers, such as Logistic Regression, Multilayer Perceptron, Support Vector Machine, Random Forest, Gradient Boosting and eXtreme Gradient Boosting, are compared to see how well the LSTM and GRU models perform.

Regarding defect detection, the LSTM and GRU models outperform traditional classifiers in terms of both accuracy and computation speed, with high accuracy rates surpassing 90%. Due to its simpler design, GRU achieves higher accuracy and performs faster calculations than LSTM. These recurrent models work well to identify temporal relationships in time-series data, which is crucial for detecting HVAC system problems.

This study closes a research gap by concentrating on issue identification in hospital HVAC systems using actual data. It illustrates how deep learning may increase the precision of fault identification and computational efficiency in medical settings by utilizing LSTM and GRU models.

Crack detection of pavement is a critical task in the periodic survey. Efficient, effective and consistent tracking of the road conditions by identifying and locating crack contributes to establishing an appropriate road maintenance and repair strategy from the promptly informed managers but still remaining a significant challenge. This research seeks to propose practical solutions for targeting the automatic crack detection from images with efficient productivity and cost-effectiveness, thereby improving the pavement performance.

This research applies a novel deep learning method named TransUnet for crack detection, which is structured based on Transformer, combined with convolutional neural networks as encoder by leveraging a global self-attention mechanism to better extract features for enhancing automatic identification. Afterward, the detected cracks are used to quantify morphological features from five indicators, such as length, mean width, maximum width, area and ratio. Those analyses can provide valuable information for engineers to assess the pavement condition with efficient productivity.

In the training process, the TransUnet is fed by a crack dataset generated by the data augmentation with a resolution of 224 × 224 pixels. Subsequently, a test set containing 80 new images is used for crack detection task based on the best selected TransUnet with a learning rate of 0.01 and a batch size of 1, achieving an accuracy of 0.8927, a precision of 0.8813, a recall of 0.8904, an F1-measure and dice of 0.8813, and a Mean Intersection over Union of 0.8082, respectively. Comparisons with several state-of-the-art methods indicate that the developed approach in this research outperforms with greater efficiency and higher reliability.

The developed approach combines TransUnet with an integrated quantification algorithm for crack detection and quantification, performing excellently in terms of comparisons and evaluation metrics, which can provide solutions with potentially serving as the basis for an automated, cost-effective pavement condition assessment scheme.

When recommending products to consumers, it is important to be able to accurately predict how consumers will rate them. However, existing collaborative filtering models are difficult to achieve a balance between rating prediction accuracy and complexity. Therefore, the purpose of this paper is to propose an accurate and effective model to predict users’ ratings of products for the accurate recommendation of products to users.

First, we introduce an attention mechanism that dynamically assigns weights to user preferences, highlighting key interaction information and enhancing the model’s understanding of user behavior. Second, a fold embedding strategy is employed to segment user interaction data, increasing the information density of each subset while reducing the complexity of the attention mechanism. Finally, a masking strategy is integrated to mitigate overfitting by concealing portions of user-item interactions, thereby improving the model’s generalization ability.

The experimental results demonstrate that the proposed model significantly minimizes prediction error across five real-world datasets. On average, the evaluation metrics root mean square error (RMSE) and mean absolute error (MAE) are reduced by 9.11 and 13.3%, respectively. Additionally, the Friedman test results confirm that these improvements are statistically significant. Consequently, the proposed model more accurately captures the intrinsic correlation between users and products, leading to a substantial reduction in prediction error.

We propose a novel collaborative filtering model to learn the user-item interaction matrix effectively. Additionally, we introduce a fold embedding strategy to reduce the computational resource consumption of the attention mechanism. Finally, we implement a masking strategy to encourage the model to focus on key features and patterns, thereby mitigating overfitting.