A traffic sign recognition system is crucial for safely operating an autonomous driving car and efficiently managing road facilities. Recent studies on traffic sign recognition tasks show significant advances in terms of accuracy on several benchmarks. However, they lack performance evaluation in driving cars in diverse road environments. In this study, we develop a traffic sign recognition framework for a vehicle to evaluate and compare deep learning-based object detection and tracking models for practical validation. We collect a large-scale highway image set using a camera-installed vehicle for training models, and evaluate the model inference during a test drive in terms of accuracy and processing time. In addition, we propose a novel categorization method for urban road scenes with possible scenarios. The experimental results show that the YOLOv5 detector and strongSORT tracking model result in better performance than other models in terms of accuracy and processing time. Furthermore, we provide an extensive discussion on possible obstacles in traffic sign recognition tasks to facilitate future research through numerous experiments for each road condition.

In complex urban road conditions, stationary or illegally parked vehicles present a considerable risk to the overall traffic system. In safety-critical applications like autonomous driving, the detection of stopped vehicles is of utmost importance. Previous methods for detecting stopped vehicles have been designed for stationary viewpoints, such as security cameras, which consistently monitor fixed locations. However, these methods for detecting stopped vehicles based on stationary views cannot address blind spots and are not applicable from driving vehicles. To address these limitations, we propose a novel deep learning-based framework for detecting stopped vehicles in dynamic environments, particularly those recorded by dashcams. The proposed framework integrates a deep learning-based object detector and tracker, along with movement estimation using the dense optical flow method. We also introduced additional centerline detection and inter-vehicle distance measurement. The experimental results demonstrate that the proposed framework can effectively identify stopped vehicles under real-world road conditions.

Multivariate time-series forecasting derives key seasonality from past patterns to predict future time-series. Multi-step forecasting is crucial in the industrial sector because a continuous perspective leads to more effective decisions. However, because it depends on previous prediction values, multi-step forecasting is highly unstable. To mitigate this problem, we introduce a novel model, named stacked dual attention neural network (StackDA), based on an encoder-decoder. In dual attention, the initial attention is for the time dependency between the encoder and decoder, and the second attention is for the time dependency in the decoder time steps. We stack dual attention to stabilize the long-term dependency and multi-step forecasting problem. We add an autoregression component to resolve the lack of linear properties because our method is based on a nonlinear neural network model. Unlike the conventional autoregressive model, we propose skip autoregressive to deal with multiple seasonalities. Furthermore, we propose a denoising training method to take advantage of both the teacher forcing and without teacher forcing methods. We adopt multi-head fully connected layers for the variable-specific modeling owing to our multivariate time-series data. We add positional encoding to provide the model with time information to recognize seasonality more accurately. We compare our model performance with that of machine learning and deep learning models to verify our approach. Finally, we conduct various experiments, including an ablation study, a seasonality determination test, and a stack attention test, to demonstrate the performance of StackDA.

The automation of systems and the accelerated digital transformations across various industries have rendered the manual monitoring of systems difficult. Therefore, the automatic detection of system anomalies is essential in diverse industries. Various deep learning-based techniques have been developed for anomaly detection in multivariate time-series data with promising performance. However, there are several challenges: 1) difficulty in understanding the relationships among time-series data due to their complexity and high-dimensionality, 2) limitation in distinguishing anomalies from normal data that exhibit similar distributional patterns, and 3) lack of intuitive interpretation of anomaly detection results. To address these issues, we propose a novel approach referred to as the time-series to image-transformed adversarial autoencoder (T2IAE), which adopts image transformation techniques and convolutional neural network (CNN)-based adversarial learning. Image transformation techniques were used to effectively capture the local features of adjacent time points. Two CNN-based adversarial autoencoders competitively learned to distinguish between normal and abnormal data. We experimentally analyzed five real-world multivariate time-series datasets, wherein the proposed model achieved superior anomaly detection performance compared with state-of-the-art methods. Moreover, the proposed model enables humans to intuitively interpret the detection results, facilitating appropriate explanations of the results and enhancing the model’s usability.