Driving behavior classification is a critical component of social transportation systems and advanced driver assistance systems, and it has gained increasing attention in recent years. Accurate classification algorithms for driving behavior play a significant role in enhancing traffic safety, energy conservation, and related fields. In this article, we propose a novel driving behavior classification network named feature-attention- embedding-based multimodal-fusion driving-behavior-classification network (FMDNet). FMDNet incorporates eight types of data, including acceleration along the x-axis, y-axis, z-axis, roll angle, pitch angle, yaw angle, roadside image, and vehicle speed, to classify driving behavior. To effectively fuse features extracted from different modalities, taking into account their varying importance, we introduce the feature attention embedding-based fusion module (FAEF) as our fusion strategy. This fusion strategy enhances the network’s capability to capture meaningful features by incorporating two feature attention embedding units that delve deeper into the interplay between different modes. Furthermore, we provide further validation of the effectiveness of our approach through extensive ablation experiments to investigate and analyze the impact of various modal data on the classification of driving behavior. Our proposed FMDNet achieves state-of-the-art performance on the public UAH-DriveSet dataset, demonstrating its effectiveness with an impressive F1-score of 99.0%. Additionally, the robustness of our model is confirmed on distracted dataset, achieving a remarkable F1-score of 99.7%. The model’s outstanding performance on both the UAH-DriveSet dataset and the distracted-dataset highlights its capabilities and potential for real-world applications.

The thermal performance of rural building envelopes is mostly non-standardized in Northern China, resulting in significant heat loss. In this study, we take, as an example, the central area of Liaoning province, with the objective of proposing some low-cost and energy-efficient solutions. Through our investigations, we found that heating energy consumption was reduced by 20% and construction costs increased by less than CNY 8000 (USD 1108), which can be accepted by rural residents. In order to achieve this target, the NSGA-II algorithm integrated with Rhino + Grasshopper and EnergyPlus simulation kernel was used to establish a thermal performance optimization model for the heat transfer of rural building envelopes in this severe cold region. Among the above-calculated Pareto optimal solutions, the recommended thickness of insulation layers for room floors, roofs, and external walls was about 70 mm, 50 mm, and 40 mm, respectively. Furthermore, we tried to reduce the window-to-wall ratio as much as possible. Finally, based on both the lower building renovation cost and energy-saving rate, three technical solutions from which rural residents could select, according to their specific needs, are put forward.

In recent years, researchers have focused on identifying tasks related to driver state, traffic environment, and others to enhance the safety of autonomous driving assistance systems. However, current research on these tasks is conducted independently, neglecting the interconnections between the driver, traffic environment, and vehicle. In this paper, we propose a Unified Multi-task Assistive Driving Network Based on Multimodal Fusion (UMD-Net), the first unified model capable of recognizing four tasks simultaneously by utilizing multimodal data: driver behavior recognition, driver emotion recognition, traffic context recognition, and vehicle behavior recognition. In order to better enhance the synergistic effects between multiple tasks, we designed the position-sensitive multi-directional attention feature extraction subnetwork and recursive dynamic feature fusion module. The former captures the key features of multi-view images by different directions of attention mechanism to improve the generalization of the model across multiple tasks. The latter dynamically adjusts the fusion weight according to the multimodal features to enhance the representation ability of important features in multi-task learning. Our model was evaluated on the public dataset AIDE, achieving the best performance across all four tasks and a high accuracy of 95.31% in the traffic context recognition task, demonstrating the superiority of our approach. The code is available on https://github.com/Wenzhuo-Liu/UMD-Net.

It is challenging to accurately establish the dynamic heat transfer model of the internal thermal mass owing to the irregular shape. In building energy simulation software, the internal thermal mass is described as slabs. However, the parameter setting of the equivalent slabs depends primarily on the user experience, which may lead to uncontrollable errors. Therefore, this paper proposes a method, termed the effective area method (EAM), which specifies the transformation of an irregular internal thermal mass to the slab and can be used as a pre-processing method for building simulation software. This paper describes the methodology and pre-processing logic of the EAM, and the implementation of the approach in EnergyPlus considering an office environment. The root-mean-square errors between the simulation and measured temperatures are less than 0.3°C, which indicates that the EAM can effectively eliminate the errors caused by the unreasonable settings of the internal thermal mass.