• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.3
• /
• pp.364-370
• /
• 2020

This paper is related to detection and classification for micro-sized aircraft that flies at low-altitude. The deep-learning based method using sounds coming from the micro-sized aircraft is proposed to detect and identify them efficiently. We use MFCC as sound features and CNN as a detector and classifier. We've proved that each micro-drones have their own distinguishable MFCC feature and confirmed that we can apply CNN as a detector and classifier even though drone sound has time-related sequence. Typically many papers deal with RNN for time-related features, but we prove that if the number of frame in the MFCC features are enough to contain the time-related information, we can classify those features with CNN. With this approach, we've achieved high detection and classification ratio with low-computation power at the same time using the data set which consists of four different drone sounds. So, this paper presents the simple and effecive method of detection and classification method for micro-sized aircraft.

• Journal of the Korean Association of Geographic Information Studies
• /
• v.26 no.4
• /
• pp.27-39
• /
• 2023

Detecting greenhouses from the remote sensing datasets is useful in identifying the illegal agricultural facilities and predicting the agricultural output of the greenhouses. This research proposed a methodology for automatically detecting greenhouses from a given Planetscope satellite imagery acquired in the areas of Gimje City using the deep learning technique through a series of steps. First, multiple training images with a fixed size that contain the greenhouse features were generated from the five training Planetscope satellite imagery. Next, the YOLO(You Only Look Once) model was trained using the generated training images. Finally, the greenhouse features were detected from the input Planetscope satellite image. Statistical results showed that the 76.4% of the greenhouse features were detected from the input Planetscope satellite imagery by using the trained YOLO model. In future research, the high-resolution satellite imagery with a spatial resolution less than 1m should be used to detect more greenhouse features.

• 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 Computer Information Conference
• /
• 2019.01a
• /
• pp.123-124
• /
• 2019

This paper proposes an improved deep learning method based on small data sets for animal image classification. Firstly, we use a CNN to build a training model for small data sets, and use data augmentation to expand the data samples of the training set. Secondly, using the pre-trained network on large-scale datasets, such as VGG16, the bottleneck features in the small dataset are extracted and to be stored in two NumPy files as new training datasets and test datasets. Finally, training a fully connected network with the new datasets. In this paper, we use Kaggle famous Dogs vs Cats dataset as the experimental dataset, which is a two-category classification dataset.

• 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.

• Korean Journal of Fisheries and Aquatic Sciences
• /
• v.55 no.5
• /
• pp.638-644
• /
• 2022

The measurement of morphological features is essential in aquaculture, fish industry and the management of fishery resources. The measurement of fish requires a large investment of manpower and time. To save time and labor for fish measurement, automated and reliable measurement methods have been developed. Automation was achieved by applying computer vision and machine learning techniques. Recently, machine learning methods based on deep learning have been used for most automatic fish measurement studies. Here, we review the current status of automatic fish measurement with traditional computer vision methods and deep learning-based methods.

• The Transactions of the Korean Institute of Power Electronics
• /
• v.27 no.1
• /
• pp.48-55
• /
• 2022

This paper proposes a battery remaining useful life (RUL) prediction method using a deep learning-based EMD-CNN-LSTM hybrid method. The proposed method pre-processes capacity data by applying empirical mode decomposition (EMD) and predicts the remaining useful life using CNN-LSTM. CNN-LSTM is a hybrid method that combines convolution neural network (CNN), which analyzes spatial features, and long short term memory (LSTM), which is a deep learning technique that processes time series data analysis. The performance of the proposed remaining useful life prediction method is verified using the battery aging experiment data provided by the NASA Ames Prognostics Center of Excellence and shows higher accuracy than does the conventional method.

• Structural Engineering and Mechanics
• /
• v.81 no.5
• /
• pp.647-664
• /
• 2022

The powerful data mapping capability of computational deep learning methods has been recently explored in academic works to develop strategies for structural health monitoring through appropriate characterization of dynamic responses. In many cases, these studies concern laboratory prototypes and finite element models to validate the proposed methodologies. Therefore, the present work aims to investigate the capability of a deep learning algorithm called Sparse Autoencoder (SAE) specifically focused on detecting structural alterations in real-case studies. The idea is to characterize the dynamic responses via SAE models and, subsequently, to detect the onset of abnormal behavior through the Shewhart T control chart, calculated with SAE extracted features. The anomaly detection approach is exemplified using data from the Z24 bridge, a classical benchmark, and data from the continuous monitoring of the San Vittore bell-tower, Italy. In both cases, the influence of temperature is also evaluated. The proposed approach achieved good performance, detecting structural changes even under temperature variations.

• Journal of IKEEE
• /
• v.27 no.1
• /
• pp.59-64
• /
• 2023

Deep learning can solve various computer vision problems, but it requires a large dataset. Data augmentation technique based on image binarization for constructing large-scale datasets is proposed in this paper. By extracting features using image binarization and randomly placing the remaining pixels, new images are generated. The generated images showed similar quality to the original images and demonstrated excellent performance in deep learning models.

• Annual Conference of KIPS
• /
• 2023.11a
• /
• pp.605-607
• /
• 2023

Recent research has highlighted the effectiveness of Deep Learning (DL) techniques in automating the detection of lung sound anomalies. However, the available lung sound datasets often suffer from limitations in both size and balance, prompting DL methods to employ data preprocessing such as augmentation and transfer learning techniques. These strategies, while valuable, contribute to the increased complexity of DL models and necessitate substantial training memory. In this study, we proposed a streamlined and lightweight DL method but effectively detects lung sound anomalies from small and imbalanced dataset. The utilization of 1D dilated convolutional neural networks enhances sensitivity to lung sound anomalies by efficiently capturing deep temporal features and small variations. We conducted a comprehensive evaluation of the ICBHI dataset and achieved a notable improvement over state-of-the-art results, increasing the average score of sensitivity and specificity metrics by 2.7%.