• Journal of the Korea Society of Computer and Information
• /
• v.26 no.3
• /
• pp.19-28
• /
• 2021

Esophagogastroduodenoscopy is a method commonly used for early diagnosis of upper gastrointestinal lesions. However, 10-20 percent of the gastric lesions are reported to be missed, due to human error. And countries including the US, the UK, and Japan, the World Endoscopy Organization (WEO) suggested guidelines about essential gastrointestinal parts to take pictures of so that all gastric lesions are observed. In this paper, we propose deep learning techniques for classification of anatomical sites, aiming for the system that informs practitioners whether they successfully did the gastroscopy without blind spots. The proposed model uses pre-processing modules and data augmentation techniques suitable for gastroscopy images. Not only does the experiment result with a maximum F1 score of 99.6%, but it also shows a error rate of less than 4% based on the actual data. Given the performance results, we found the model to be explainable with the potential to be utilized in the clinical area.

• Nuclear Engineering and Technology
• /
• v.55 no.9
• /
• pp.3409-3416
• /
• 2023

Licensing the next-generation of nuclear reactor designs requires extensive use of Modeling and Simulation (M&S) to investigate system response to many operational conditions, identify possible accidental scenarios and predict their evolution to undesirable consequences that are to be prevented or mitigated via the deployment of adequate safety barriers. Deep Learning (DL) and Artificial Intelligence (AI) can support M&S computationally by providing surrogates of the complex multi-physics high-fidelity models used for design. However, DL and AI are, generally, low-fidelity 'black-box' models that do not assure any structure based on physical laws and constraints, and may, thus, lack interpretability and accuracy of the results. This poses limitations on their credibility and doubts about their adoption for the safety assessment and licensing of novel reactor designs. In this regard, Physics Informed Neural Networks (PINNs) are receiving growing attention for their ability to integrate fundamental physics laws and domain knowledge in the neural networks, thus assuring credible generalization capabilities and credible predictions. This paper presents the use of PINNs as surrogate models for accidental scenarios simulation in Nuclear Power Plants (NPPs). A case study of a Loss of Heat Sink (LOHS) accidental scenario in a Nuclear Battery (NB), a unique class of transportable, plug-and-play microreactors, is considered. A PINN is developed and compared with a Deep Neural Network (DNN). The results show the advantages of PINNs in providing accurate solutions, avoiding overfitting, underfitting and intrinsically ensuring physics-consistent results.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.5
• /
• pp.1310-1338
• /
• 2023

As Internet of Things (IoT) applications and devices rapidly grow, cyber-attacks on IoT networks/systems also have an increasing trend, thus increasing the threat to security and privacy. Botnet is one of the threats that dominate the attacks as it can easily compromise devices attached to an IoT networks/systems. The compromised devices will behave like the normal ones, thus it is difficult to recognize them. Several intelligent approaches have been introduced to improve the detection accuracy of this type of cyber-attack, including deep learning and machine learning techniques. Moreover, dimensionality reduction methods are implemented during the preprocessing stage. This research work proposes deep Autoencoder dimensionality reduction method combined with Artificial Neural Network (ANN) classifier as botnet detection system for IoT networks/systems. Experiments were carried out using 3- layer, 4-layer and 5-layer pre-processing data from the MedBIoT dataset. Experimental results show that using a 5-layer Autoencoder has better results, with details of accuracy value of 99.72%, Precision of 99.82%, Sensitivity of 99.82%, Specificity of 99.31%, and F1-score value of 99.82%. On the other hand, the 5-layer Autoencoder model succeeded in reducing the dataset size from 152 MB to 12.6 MB (equivalent to a reduction of 91.2%). Besides that, experiments on the N_BaIoT dataset also have a very high level of accuracy, up to 99.99%.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.16 no.4
• /
• pp.1-7
• /
• 2020

Over the past few years, Wi-Fi signal based indoor positioning system (IPS) has been researched extensively because of its low expenses of infrastructure deployment. There are two major aspects of location-related information contained in Wi-Fi signals. One is channel state information (CSI), and one is received signal strength indicator (RSSI). Compared to the RSSI, the CSI has been widely utilized because it is able to reveal fine-grained information related to locations. However, the conventional IPS that employs a single access point (AP) does not exhibit decent performance especially in the environment of non-line-of-sight (NLOS) situations due to the reliability degeneration of signals caused by multipath fading effect. In order to address this problem, in this paper, we propose a novel method that utilizes multiple APs instead of a single AP to enhance the robustness of the IPS. In our proposed method, a hybrid neural network is applied to the CSIs collected from multiple APs. By relying more on the fingerprint constructed by the CSI collected from an AP that is less affected by the NLOS, we find that the performance of the IPS is significantly improved.

• Journal of Digital Convergence
• /
• v.18 no.11
• /
• pp.241-246
• /
• 2020

In this paper, we propose a neural network model to converge the marine electric propulsion system and deep learning algorithm to predict the DC/DC converter output current in the electric propulsion regeneration system and to predict the battery charge during regeneration. In order to experiment with the proposed neural network, the input voltage and current of the PCM were measured and the data set was secured on the prototype PCM board. In addition, in order to improve the learning results in the insufficient data set, the scale of the data set was increased through data fitting and its learning was executed further. After learning, the difference between the data prediction result of the neural network model and the actual measurement data was compared. The proposed neural network model effectively showed the prediction of battery charge according to changes in input voltage and current. In addition, by predicting the characteristic change of the analog circuit constituting the DC/DC converter through a neural network, it is determined that the characteristics of the analog circuit should be considered when designing the regeneration system.

• Korean Medical Education Review
• /
• v.17 no.1
• /
• pp.5-9
• /
• 2015

A teaching hospital is a place where both patient care and learning occur together. To identify the role of the teaching hospital in an effective clerkship, we first determined the features of workplace learning and the factors that affect learning in the workplace, and then we proposed a role for the teaching hospital in the clinical clerkship. Features of learning in a clerkship include learning in context, and learning from patients, supervising doctors, others in the team, and colleagues. During the clerkship, medical students learn in three-way learner-patient-teacher relationships, and students' participation in the tasks of patient care is crucial for learning. Factors that influence learning in the workplace are associated with tasks, context, and learner. Tying the three factors together, we proposed a role for the teaching hospital in the three categories: involvement in the tasks of patient care, engagement in the medical team, and engagement in the learning environment and system. Supervising doctors and team members in a teaching hospital support students' deep participation in patient care, while improving the learning environment through organizational guidelines and systems. Gathering both qualitative and quantitative data for the evaluation of a teaching hospital is important.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.11
• /
• pp.499-506
• /
• 2017

Chatter bots are normally used in task-oriented dialogue systems to support free conversations. However, there is not much research on how chatter bots as auxiliary system should be different from independent ones. In this paper, we have developed a chatter bot for a dialogue-based computer assisted language learning (DB-CALL) system. We compared the chatter bot in two different cases: as an independent bot, and as an auxiliary system. The results showed that, the chatter bot as an auxiliary system showed much lower satisfaction than the independent one. A discussion is held about the difference between an auxiliary chatter bot and an independent bot. In addition, we evaluated a search-based chatter bot and a deep learning based chatter bot. The advantages and disadvantages of both methods are discussed.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.12 no.2
• /
• pp.331-336
• /
• 2017

The need for early fire detection technology is increasing in order to prevent fire disasters. Sensor device detection for heat, smoke and fire is widely used to detect flame and smoke, but this system is limited by the factors of the sensor environment. To solve these problems, many image-based fire detection systems are being developed. In this paper, we implemented a system to detect fire and smoke from camera input images using a convolution neural network. Through the implemented system using the convolution neural network, a feature map is generated for the smoke image and the fire image, and learning for classifying the smoke and fire is performed on the generated feature map. Experimental results on various images show excellent effects for classifying smoke and fire.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.7 no.7
• /
• pp.1449-1455
• /
• 2003

This paper describes the development of an effective celestial learning system using virtual reality technology. Our system support a deep immersion and comfortable navigation by using HMD(Head Mounted Display) and 3 dimensional mouse. We make three dimensional celestial image dynamically with OpenGL and display the rendered image to HMD. Students can feel that they are on the space ship and navigate through the celestial body. During the navigation, students can get the information of each planet and solve given problems. Our system shows that virtual reality can be used as an effective tool for training and education.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.8
• /
• pp.2993-3010
• /
• 2021

The job shop scheduling problem (JSSP) plays a critical role in smart manufacturing, an effective JSSP scheduler could save time cost and increase productivity. Conventional methods are very time-consumption and cannot deal with complicated JSSP instances as it uses one optimal algorithm to solve JSSP. This paper proposes an effective scheduler based on deep learning technology named self-supervised long-short term memory (SS-LSTM) to handle complex JSSP accurately. First, using the optimal method to generate sufficient training samples in small-scale JSSP. SS-LSTM is then applied to extract rich feature representations from generated training samples and decide the next action. In the proposed SS-LSTM, two channels are employed to reflect the full production statues. Specifically, the detailed-level channel records 18 detailed product information while the system-level channel reflects the type of whole system states identified by the k-means algorithm. Moreover, adopting a self-supervised mechanism with LSTM autoencoder to keep high feature extraction capacity simultaneously ensuring the reliable feature representative ability. The authors implemented, trained, and compared the proposed method with the other leading learning-based methods on some complicated JSSP instances. The experimental results have confirmed the effectiveness and priority of the proposed method for solving complex JSSP instances in terms of make-span.