• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.411-425
• /
• 2021

In this paper, a vehicle recognition algorithm based on deep convolutional neural network and compression dictionary is proposed. Firstly, the network structure of fine vehicle recognition based on convolutional neural network is introduced. Then, a vehicle recognition system based on multi-scale pyramid convolutional neural network is constructed. The contribution of different networks to the recognition results is adjusted by the adaptive fusion method that adjusts the network according to the recognition accuracy of a single network. The proportion of output in the network output of the entire multiscale network. Then, the compressed dictionary learning and the data dimension reduction are carried out using the effective block structure method combined with very sparse random projection matrix, which solves the computational complexity caused by high-dimensional features and shortens the dictionary learning time. Finally, the sparse representation classification method is used to realize vehicle type recognition. The experimental results show that the detection effect of the proposed algorithm is stable in sunny, cloudy and rainy weather, and it has strong adaptability to typical application scenarios such as occlusion and blurring, with an average recognition rate of more than 95%.

• Journal of Information Processing Systems
• /
• v.17 no.2
• /
• pp.385-398
• /
• 2021

The complexity of deep learning models affects the real-time performance of gesture recognition, thereby limiting the application of gesture recognition algorithms in actual scenarios. Hence, a residual learning neural network based on a deep convolutional neural network is proposed. First, small convolution kernels are used to extract the local details of gesture images. Subsequently, a shallow residual structure is built to share weights, thereby avoiding gradient disappearance or gradient explosion as the network layer deepens; consequently, the difficulty of model optimisation is simplified. Additional convolutional neural networks are used to accelerate the refinement of deep abstract features based on the spatial importance of the gesture feature distribution. Finally, a fully connected cascade softmax classifier is used to complete the gesture recognition. Compared with the dense connection multiplexing feature information network, the proposed algorithm is optimised in feature multiplexing to avoid performance fluctuations caused by feature redundancy. Experimental results from the ISOGD gesture dataset and Gesture dataset prove that the proposed algorithm affords a fast convergence speed and high accuracy.

• Proceedings of the Korean Society of Broadcast Engineers Conference
• /
• 2019.06a
• /
• pp.98-101
• /
• 2019

At present, deep convolutional neural networks have made a very important contribution in single-image super-resolution. Through the learning of the neural networks, the features of input images are transformed and combined to establish a nonlinear mapping of low-resolution images to high-resolution images. Some previous methods are difficult to train and take up a lot of memory. In this paper, we proposed a simple and compact deep recursive residual network learning the features for single image super resolution. Global residual learning and local residual learning are used to reduce the problems of training deep neural networks. And the recursive structure controls the number of parameters to save memory. Experimental results show that the proposed method improved image qualities that occur in previous methods.

• Journal of the Semiconductor & Display Technology
• /
• v.20 no.1
• /
• pp.94-98
• /
• 2021

As the world's population grows, the food industry becomes increasingly important. Among them, agriculture is an industry that produces stocks of people all over the world, which is very important food industry. Despite the growing importance of agriculture, however, a large number of crops are lost every year due to pests and malnutrition. So, we propose a plant anomaly detection system for managing crops incorporating deep learning and drones with various possibilities. In this paper, we develop a system that analyzes images taken by drones and GPS of the drone's movement path and visually displays them on a map. Our system detects plant anomalies with 97% accuracy. The system is expected to enable efficient crop management at low cost.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.68 no.2
• /
• pp.359-363
• /
• 2019

As commercial drones have been widely used, concerns for collision accidents with people and invading secured properties are emerging. The detection of drone is a challenging problem. The deep learning based object detection techniques for detecting drones have been applied, but limited to the specific cases such as detection of drones from bird and/or background. We have tried not only detection of drones, but classification of different drones with an end-to-end model. YOLOv2 is used as an object detection model. In order to supplement insufficient data by shooting drones, data augmentation from collected images is executed. Also transfer learning from ImageNet for YOLOv2 darknet framework is performed. The experimental results for drone detection with average IoU and recall are compared and analysed.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.5
• /
• pp.674-677
• /
• 2020

The cultural background of users utilizing image search engines has a significant impact on the satisfaction of the search results. Therefore, it is important to analyze and understand the cultural context of images for more accurate image search. In this paper, we investigate how the cultural context of images can affect the performance of image classification. To this end, we first collected various types of images (e.g,. food, temple, etc.) with various cultural contexts (e.g., Korea, Japan, etc.) from web search engines. Afterwards, a deep transfer learning approach using VGG19 and MobileNetV2 pre-trained with ImageNet was adopted to learn the cultural features of the collected images. Through various experiments we show the performance of image classification can be differently affected according to the cultural context of images.

• Investigative Magnetic Resonance Imaging
• /
• v.25 no.4
• /
• pp.266-280
• /
• 2021

Advances in radiomics and deep learning (DL) hold great potential to be at the forefront of precision medicine for the treatment of patients with brain metastases. Radiomics and DL can aid clinical decision-making by enabling accurate diagnosis, facilitating the identification of molecular markers, providing accurate prognoses, and monitoring treatment response. In this review, we summarize the clinical background, unmet needs, and current state of research of radiomics and DL for the treatment of brain metastases. The promises, pitfalls, and future roadmap of radiomics and DL in brain metastases are addressed as well.

• KEPCO Journal on Electric Power and Energy
• /
• v.8 no.2
• /
• pp.137-141
• /
• 2022

To inspect the power facility faults using artificial intelligence, it need that improve the accuracy of the diagnostic model are required. Data augmentation skill using generative adversarial network (GAN) is one of the best ways to improve deep learning performance. GAN model can create realistic-looking fake images using two competitive learning networks such as discriminator and generator. In this study, we intend to verify the effectiveness of virtual data generation technology by including the fake image of power facility generated through GAN in the deep learning training set. The GAN-based fake image was created for damage of LP insulator, and ResNet based normal and defect classification model was developed to verify the effect. Through this, we analyzed the model accuracy according to the ratio of normal and defective training data.

• Nuclear Engineering and Technology
• /
• v.54 no.5
• /
• pp.1747-1753
• /
• 2022

Compton imaging is the main method for locating radioactive hot spots emitting high-energy gamma-ray photons. In particular, this imaging method is crucial when the photon energy is too high for coded-mask aperture imaging methods to be effective or when a large field of view is required. Reconstruction of the photon source requires advanced Compton event processing algorithms to determine the exact position of the source. In this study, we introduce a novel method based on a Deep Learning algorithm with a Convolutional Neural Network (CNN) to perform Compton imaging. This algorithm is trained on simulated data and tested on real data acquired with Caliste, a single planar CdTe pixelated detector. We show that performance in terms of source location accuracy is equivalent to state-of-the-art algorithms, while computation time is significantly reduced and sensitivity is improved by a factor of ~5 in the Caliste configuration.

• Journal of Internet Computing and Services
• /
• v.23 no.2
• /
• pp.97-105
• /
• 2022

Web services show a rapid evolution and integration to meet the increased users' requirements. Thus, web services undergo updates and may have performance degradation due to undetected faults in the updated versions. Due to these faults, many performances and regression anomalies in web services may occur in real-world scenarios. This paper proposed applying the deep learning model and innovative explainable framework to detect performance and regression anomalies in web services. This study indicated that upper bound and lower bound values in performance metrics provide us with the simple means to detect the performance and regression anomalies in updated versions of web services. The explainable deep learning method enabled us to decide the precise use of deep learning to detect performance and anomalies in web services. The evaluation results of the proposed approach showed us the detection of unusual behavior of web service. The proposed approach is efficient and straightforward in detecting regression anomalies in web services compared with the existing approaches.