Mei-Hsin Chen

Images captured in rainy weather conditions often suffer from contamination, resulting in blurred or obscured objects, which can significantly impact detection performance due to the loss of identifiable texture and color information. Moreover, the quality of the detection model plays a pivotal role in determining detection outcomes. This study adopts a dual perspective, considering both pre-trained models and training data. It employs 15 image augmentation techniques, combined with neural style transfer (NST), CycleGAN, and an analytical method, to synthesize images under rainy conditions. The Real-Time Detection Transformer (RTDETR) and YOLOv8 pre-trained models are utilized to establish object detection frameworks tailored for rainy weather conditions. Testing is carried out using the DAWN (Detection in Adverse Weather Nature) dataset. The findings suggest compatibility between the pre-trained detection models and various data synthesis methods. Notably, YOLOv8 exhibits better compatibility with CycleGAN data synthesis, while RTDETR demonstrates a stronger alignment with the NST and analytical approaches. Upon the integration of synthesized rainy images into model training, RTDETR demonstrates significantly enhanced detection accuracy compared to YOLOv8, indicating a more pronounced improvement in performance. The proposed approach of combining RTDETR with NST in this study shows a significant improvement in Recall (R) and mAP50-95 by 16.35% and 15.50%, respectively, demonstrating the robust rainy weather resilience of this method. Additionally, RTDETR outperforms YOLOv8 in terms of inference speed and hardware requirements, making it easier to use and deploy in real-time applications.

Latent Low-Rank Representation (LatLRR) has emerged as a prominent approach for fusing visible and infrared images. In this approach, images are decomposed into three fundamental components: the base part, salient part, and sparse part. The aim is to blend the base and salient features to reconstruct images accurately. However, existing methods often focus more on combining the base and salient parts, neglecting the importance of the sparse component, whereas we advocate for the comprehensive inclusion of all three parts generated from LatLRR image decomposition into the image fusion process, a novel proposition introduced in this study. Moreover, the effective integration of Convolutional Neural Network (CNN) technology with LatLRR remains challenging, particularly after the inclusion of sparse parts. This study utilizes fusion strategies involving weighted average, summation, VGG19, and ResNet50 in various combinations to analyze the fusion performance following the introduction of sparse parts. The research findings show a significant enhancement in fusion performance achieved through the inclusion of sparse parts in the fusion process. The suggested fusion strategy involves employing deep learning techniques for fusing both base parts and sparse parts while utilizing a summation strategy for the fusion of salient parts. The findings improve the performance of LatLRR-based methods and offer valuable insights for enhancement, leading to advancements in the field of image fusion.

Although many machine learning methods have been widely used to predict PM2.5 concentrations, these single or hybrid methods still have some shortcomings. This study integrated the advantages of convolutional neural network (CNN) feature extraction and the regression ability of random forest (RF) to propose a novel CNN-RF ensemble framework for PM2.5 concentration modeling. The observational data from 13 monitoring stations in Kaohsiung in 2021 were selected for model training and testing. First, CNN was implemented to extract key meteorological and pollution data. Subsequently, the RF algorithm was employed to train the model with five input factors, namely the extracted features from the CNN and spatiotemporal factors, including the day of the year, the hour of the day, latitude, and longitude. Independent observations from two stations were used to evaluate the models. The findings demonstrated that the proposed CNN–RF model had better modeling capability compared with the independent CNN and RF models: the average improvements in root mean square error (RMSE) and mean absolute error (MAE) ranged from 8.10% to 11.11%, respectively. In addition, the proposed CNN–RF hybrid model has fewer excess residuals at thresholds of 10 μg/m³, 20 μg/m³, and 30 μg/m³. The results revealed that the proposed CNN–RF ensemble framework is a stable, reliable, and accurate method that can generate superior results compared with the single CNN and RF methods. The proposed method could be a valuable reference for readers and may inspire researchers to develop even more effective methods for air pollution modeling. This research has important implications for air pollution research, data analysis, model estimation, and machine learning.

With the continual advancement of positioning technology, people′s use of mobile devices has increased substantially. The global navigation satellite system (GNSS) has improved outdoor positioning performance. However, it cannot effectively locate indoor users owing to signal masking effects. Common indoor positioning technologies include radio frequencies, image visions, and pedestrian dead reckoning. However, the advantages and disadvantages of each technology prevent a single indoor positioning technology from solving problems related to various environmental factors. In this study, a hybrid method was proposed to improve the accuracy of indoor positioning by combining visual simultaneous localization and mapping (VSLAM) with a magnetic fingerprint map. A smartphone was used as an experimental device, and a built-in camera and magnetic sensor were used to collect data on the characteristics of the indoor environment and to determine the effect of the magnetic field on the building structure. First, through the use of a preestablished indoor magnetic fingerprint map, the initial position was obtained using the weighted k-nearest neighbor matching method. Subsequently, combined with the VSLAM, the Oriented FAST and Rotated BRIEF (ORB) feature was used to calculate the indoor coordinates of a user. Finally, the optimal user’s position was determined by employing loose coupling and coordinate constraints from a magnetic fingerprint map. The findings indicated that the indoor positioning accuracy could reach 0.5 to 0.7 m and that different brands and models of mobile devices could achieve the same accuracy.

Traffic speed forecasting in the short term is one of the most critical parts of any intelligent transportation system (ITS). Accurate speed forecasting can support travelers’ route choices, traffic guidance, and traffic control. This study proposes a deep learning approach using long short-term memory (LSTM) network with tuning hyper-parameters to forecast short-term traffic speed on an arterial parallel multi-lane road in a developing country such as Vietnam. The challenge of mishandling the location data of vehicles on small and adjacent multi-lane roads will be addressed in this study. To test the accuracy of the proposed forecasting model, its application is illustrated using historical voyage GPS-monitored data on the Le Hong Phong urban arterial road in Haiphong city of Vietnam. The results indicate that in comparison with other models (e.g., traditional models and convolutional neural network), the best performance in terms of root mean square error (RMSE), mean absolute error (MAE), and median absolute error (MDAE) is obtained by using the proposed model.

Spatial information technology has been widely used for vehicles in general and for fleet management. Many studies have focused on improving vehicle positioning accuracy, although few studies have focused on efficiency improvements for managing large truck fleets in the context of the current complex network of roads. Therefore, this paper proposes a multilayer-based map matching algorithm with different spatial data structures to deal rapidly with large amounts of coordinate data. Using the dimension reduction technique, the geodesic coordinates can be transformed into plane coordinates. This study provides multiple layer grouping combinations to deal with complex road networks. We integrated these techniques and employed a puncture method to process the geometric computation with spatial data-mining approaches. We constructed a spatial division index and combined this with the puncture method, which improves the efficiency of the system and can enhance data retrieval efficiency for large truck fleet dispatching. This paper also used a multilayer-based map matching algorithm with raster data structures. Comparing the results revealed that the look-up table method offers the best outcome. The proposed multilayer-based map matching algorithm using the look-up table method is suited to obtaining competitive performance in identifying efficiency improvements for large truck fleet dispatching.