• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.2
• /
• pp.109-117
• /
• 2022

This paper proposes a method for detecting flight anomalies of drones through the difference between the command of flight controller (FC) and the navigation solution. If the drones make a flight normally, control errors generated by the difference between the desired control command of FC and the navigation solution should converge to zero. However, there is a risk of sudden change or divergence of control errors when the FC control feedback loop preset for the normal flight encounters interferences such as strong winds or navigation sensor abnormalities. In this paper, we propose the method with a deep neural network model that predicts the control error in the normal flight so that the abnormal flight state can be detected. The performance of proposed method was evaluated using the real-world flight data. The results showed that the method effectively detects anomalies in various situation.

• ETRI Journal
• /
• v.44 no.2
• /
• pp.194-207
• /
• 2022

In the last decade, substantial progress has been achieved in intelligent traffic control technologies to overcome consistent difficulties of traffic congestion and its adverse effect on smart cities. Edge computing is one such advanced progress facilitating real-time data transmission among vehicles and roadside units to mitigate congestion. An edge computing-based deep reinforcement learning system is demonstrated in this study that appropriately designs a multiobjective reward function for optimizing different objectives. The system seeks to overcome the challenge of evaluating actions with a simple numerical reward. The selection of reward functions has a significant impact on agents' ability to acquire the ideal behavior for managing multiple traffic signals in a large-scale road network. To ascertain effective reward functions, the agent is trained withusing the proximal policy optimization method in several deep neural network models, including the state-of-the-art transformer network. The system is verified using both hypothetical scenarios and real-world traffic maps. The comprehensive simulation outcomes demonstrate the potency of the suggested reward functions.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.12
• /
• pp.3855-3867
• /
• 2022

Name separation (splitting full names into surnames and given names) is not a tedious task in a multiethnic country because the procedure for splitting surnames and given names is ethnicity-specific. Malaysia has multiple main ethnic groups; therefore, separating Malaysian full names into surnames and given names proves a challenge. In this study, we develop a two-phase framework for Malaysian name separation using deep learning. In the initial phase, we predict the ethnicity of full names. We propose a recurrent neural network with long short-term memory network-based model with character embeddings for prediction. Based on the predicted ethnicity, we use a rule-based algorithm for splitting full names into surnames and given names in the second phase. We evaluate the performance of the proposed model against various machine learning models and demonstrate that it outperforms them by an average of 9%. Moreover, transfer learning and fine-tuning of the proposed model with an additional dataset results in an improvement of up to 7% on average.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.448-449
• /
• 2022

In the image upscaling field, the method using deep learning is showing better results than using the interpolation method. And for hologram upscaling, using deep learning is showing better results than general interpolation. In this paper, the network structure and learning results are analyzed. The learning results are compared by adjusting the depth of the network and the number of channels at the same weight.

• Computers and Concrete
• /
• v.32 no.6
• /
• pp.615-623
• /
• 2023

Crack detection is an essential method to ensure the safety of dam concrete structures. Low-quality crack images of dam concrete structures limit the application of neural network methods in crack detection. This research proposes a modified attentional mechanism model to reduce the disturbance caused by uneven light, shadow, and water spots in crack images. Also, the focal loss function solves the small ratio of crack information. The dataset collects from the network, laboratory and actual inspection dataset of dam concrete structures. This research proposes a novel method for crack detection of dam concrete structures based on the U-Net neural network, namely AF-UNet. A mutual comparison of OTSU, Canny, region growing, DeepLab V3+, SegFormer, U-Net, and AF-UNet (proposed) verified the detection accuracy. A binocular camera detects cracks in the experimental scene. The smallest measurement width of the system is 0.27 mm. The potential goal is to achieve real-time detection and localization of cracks in dam concrete structures.

• Journal of Drive and Control
• /
• v.20 no.4
• /
• pp.54-63
• /
• 2023

High and intermittent loading cycles induce fatigue damage to transmission components, resulting in premature gearbox failure. To identify gearbox defects, numerous vibration-based diagnostics techniques, using several artificial intelligence (AI) algorithms, have recently been presented. In this paper, an optimized deep belief network (DBN) model for gearbox problem diagnosis was designed based on time-frequency visual pattern identification. To optimize the hyperparameters of the model, a particle swarm optimization (PSO) approach was integrated into the DBN. The proposed model was tested on two gearbox datasets: a wind turbine gearbox and an experimental gearbox. The optimized DBN model demonstrated strong and robust performance in classification accuracy. In addition, the accuracy of the generated datasets was compared using traditional ML and DL algorithms. Furthermore, the proposed model was evaluated on different partitions of the dataset. The results showed that, even with a small amount of sample data, the optimized DBN model achieved high accuracy in diagnosis.

• International Journal of Computer Science & Network Security
• /
• v.24 no.9
• /
• pp.119-126
• /
• 2024

Diabetes is a chronic condition that happens when the pancreas fails to produce enough insulin or when the body's insulin is ineffectively used. Uncontrolled diabetes causes hyperglycaemia, or high blood sugar, which causes catastrophic damage to many of the body's systems, including the neurons and blood vessels, over time. The burden of disease on the global healthcare system is enormous. As a result, early diabetes diagnosis is critical in saving many lives. Current methods for determining whether a person has diabetes or is at risk of acquiring diabetes, on the other hand, rely heavily on clinical biomarkers. This research presents a unique deep learning architecture for predicting whether or not a person has diabetes and the severity levels of diabetes from the person's retinal image. This study incorporates datasets such as EyePACS and IDRID, which comprise Diabetic Retinopathy (DR) images and uses Dense-121 as the base due to its improved performance.

• Journal of Korea Multimedia Society
• /
• v.22 no.12
• /
• pp.1447-1456
• /
• 2019

As artificial intelligence technology is actively used in image processing, it is possible to generate high-quality fake images based on deep learning. Fake images generated using GAN(Generative Adversarial Network), one of unsupervised learning algorithms, have reached levels that are hard to discriminate from the naked eye. Detecting these fake images is required as they can be abused for crimes such as illegal content production, identity fraud and defamation. In this paper, we develop a deep-learning model based on CNN(Convolutional Neural Network) for the detection of StyleGAN fake images. StyleGAN is one of GAN algorithms and has an excellent performance in generating face images. We experiment with 48 number of experimental scenarios developed by combining parameters of the proposed model. We train and test each scenario with 300,000 number of real and fake face images in order to present a model parameter that improves performance in the detection of fake faces.

• International Journal of Internet, Broadcasting and Communication
• /
• v.12 no.2
• /
• pp.113-119
• /
• 2020

Numerous tourist-related data produced on the Internet contain not only simple tourist information but also diverse ideas and opinions from users. In order to derive meaningful information about tourist sites from such big data, the social network analysis of tourist keywords can identify the frequency of keywords and the relationship between keywords. Thus, it is possible to make recommendations more suitable for users by utilizing the clear recommendation criteria of tourist attractions and the relationship between tourist attractions. In this paper, a recommendation system was designed based on tourist site information through big data social network analysis. Based on user personality information, the types of tourism suitable for users are classified through deep learning and the network analysis among tourist keywords is conducted to identify the relationship between tourist attractions belonging to the type of tourism. Tour information for related tourist attractions shown on SNS and blogs will be recommended through tagging.

• International Journal of Internet, Broadcasting and Communication
• /
• v.14 no.4
• /
• pp.58-63
• /
• 2022

Recently, the improvement of computational processing ability due to the rapid development of computing technology has greatly advanced the field of artificial intelligence, and research to apply it in various domains is active. In particular, in the national defense field, attention is paid to intelligent recognition among machine learning techniques, and efforts are being made to develop object identification and monitoring systems using artificial intelligence. To this end, various image processing technologies and object identification algorithms are applied to create a model that can identify friendly and enemy weapon systems and personnel in real-time. In this paper, we conducted image processing and object identification focused on tanks among various weapon systems. We initially conducted processing the tanks' image using a convolutional neural network, a deep learning technique. The feature map was examined and the important characteristics of the tanks crucial for learning were derived. Then, using YOLOv5 Network, a CNN-based object detection network, a model trained by labeling the entire tank and a model trained by labeling only the turret of the tank were created and the results were compared. The model and labeling technique we proposed in this paper can more accurately identify the type of tank and contribute to the intelligent recognition system to be developed in the future.