Low-light image enhancement is one of the most challenging tasks in computer vision, and it is actively researched and used to solve various problems. Most of the time, image processing achieves significant performance under normal lighting conditions. However, under low-light conditions, an image turns out to be noisy and dark, which makes subsequent computer vision tasks difficult. To make buried details more visible, and reduce blur and noise in a low-light captured image, a low-light image enhancement task is necessary. A lot of research has been applied to many different techniques. However, most of these approaches require much effort or expensive equipment to perform low-light image enhancement. For example, the image has to be captured in a raw camera file in order to be processed, and the addressing method does not perform well under extreme low-light conditions. In this paper, we propose a new convolutional network, Attention U-net (the integration of an attention gate and a U-net network), which is able to work on common file types (.PNG, .JPEG, .JPG, etc.) with primary support from deep learning to solve the problem of surveillance camera security in smart city inducements without requiring the raw image file from the camera, and it can perform under the most extreme low-light conditions.

In this paper, we develop a real-time intelligent transportation system (ITS) to detect vehicles traveling the wrong way on the road. The concept of this wrong-way system is to detect such vehicles as soon as they enter an area covered by a single closed-circuit television (CCTV) camera. After detection, the program alerts the monitoring center and triggers a warning signal to the drivers. The developed system is based on video imaging and covers three aspects: detection, tracking, and validation. To locate a car in a video frame, we use a deep learning method known as you only look once version 3 (YOLOv3). Therefore, we use a custom dataset for training to create a deep learning model. After estimating a car’s position, we implement linear quadratic estimation (also known as Kalman filtering) to track the detected vehicle during a certain period. Lastly, we apply an “entry-exit” algorithm to identify the car’s trajectory, achieving 91.98% accuracy in wrong-way driver detection.

Hypergravity accelerators are a type of large machinery used for gravity training or medical research. A failure of such large equipment can be a serious problem in terms of safety or costs. This paper proposes a prediction model that can proactively prevent failures that may occur in a hypergravity accelerator. An experiment was conducted to evaluate the performance of the method proposed in this paper. A 4-channel accelerometer was attached to the bearing housing, which is a rotor, and time-amplitude data were obtained from the measured values by sampling. The method proposed in this paper was trained with transfer learning, a deep learning model that replaced the VGG19 model with a Fully Connected Layer (FCL) and Global Average Pooling (GAP) by converting the vibration signal into a short-time Fourier transform (STFT) or Mel-Frequency Cepstral Coefficients (MFCC) spectrogram and converting the input into a 2D image. As a result, the model proposed in this paper has seven times decreased trainable parameters of VGG19, and it is possible to quantify the severity while looking at the defect areas that cannot be seen with 1D.

Deep neural networks (DNN) have proven to be efficient in computer vision and data classification with an increasing number of successful applications. Time series classification (TSC) has been one of the challenging problems in data mining in the last decade, and significant research has been proposed with various solutions, including algorithm-based approaches as well as machine and deep learning approaches. This paper focuses on combining the two well-known deep learning techniques, namely the Inception module and the Fully Convolutional Network. The proposed method proved to be more efficient than the previous state-of-the-art InceptionTime method. We tested our model on the univariate TSC benchmark (the UCR/UEA archive), which includes 85 time-series datasets, and proved that our network outperforms the InceptionTime in terms of the training time and overall accuracy on the UCR archive.

This paper deals with a method for removing a ghost target that is not a real object from the output of a multiple object-tracking algorithm. This method uses an artificial neural network (multilayer perceptron) and introduces a structure, learning, verification, and evaluation method for the artificial neural network. The implemented system was tested at an intersection in a city center. Results from a 28-min measurement were 88% accurate when the multilayer perceptron for ghost target classification successfully detected the ghost targets, and 6.7% inaccurate when ghost targets were mistaken for actual targets. This method is expected to contribute to the advancement of intelligent transportation systems if the weaknesses revealed during the evaluation of the system are complemented and refined.

Intelligent fault diagnosis for rotary machinery often suffers performance degradation under domain shifts between training and deployment environments. To address this, we propose a robust fault diagnosis framework incorporating three key components: (1) an order-frequency-based preprocessing method to normalize rotational variations, (2) a U-Net variational autoencoder (U-NetVAE) to enhance adaptation through reconstruction learning, and (3) a test-time training (TTT) strategy enabling unsupervised target domain adaptation without access to source data. Since existing works rarely evaluate under true domain shift conditions, we first construct a unified cross-domain benchmark by integrating four public datasets with consistent class and sensor settings. The experimental results show that our method outperforms conventional machine learning and deep learning models in both F1-score and recall across domains. Notably, our approach maintains an F1-score of 0.47 and recall of 0.51 in the target domain, outperforming others under identical conditions. Ablation studies further confirm the contribution of each component to adaptation performance. This study highlights the effectiveness of combining mechanical priors, self-supervised learning, and lightweight adaptation strategies for robust fault diagnosis in the practical domain.