• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.123-138
• /
• 2023

The Fourth Industrial Revolution and sensor technology have led to increased utilization of sensor data. In our modern society, data complexity is rising, and the extraction of valuable information has become crucial with the rapid changes in information technology (IT). Recurrent neural networks (RNN) and long short-term memory (LSTM) models have shown remarkable performance in natural language processing (NLP) and time series prediction. Consequently, there is a strong expectation that models excelling in NLP will also excel in time series prediction. However, current research on Transformer models for time series prediction remains limited. Traditional RNN and LSTM models have demonstrated superior performance compared to Transformers in big data analysis. Nevertheless, with continuous advancements in Transformer models, such as GPT-2 (Generative Pre-trained Transformer 2) and ProphetNet, they have gained attention in the field of time series prediction. This study aims to evaluate the classification performance and interval prediction of remaining useful life (RUL) using an advanced Transformer model. The performance of each model will be utilized to establish a health index (HI) for cutting blades, enabling real-time monitoring of machine health. The results are expected to provide valuable insights for machine monitoring, evaluation, and management, confirming the effectiveness of advanced Transformer models in time series analysis when applied in industrial settings.

• Korean Journal of Radiology
• /
• v.24 no.7
• /
• pp.698-714
• /
• 2023

In recent years, artificial intelligence, especially object detection-based deep learning in computer vision, has made significant advancements, driven by the development of computing power and the widespread use of graphic processor units. Object detection-based deep learning techniques have been applied in various fields, including the medical imaging domain, where remarkable achievements have been reported in disease detection. However, the application of deep learning does not always guarantee satisfactory performance, and researchers have been employing trial-and-error to identify the factors contributing to performance degradation and enhance their models. Moreover, due to the black-box problem, the intermediate processes of a deep learning network cannot be comprehended by humans; as a result, identifying problems in a deep learning model that exhibits poor performance can be challenging. This article highlights potential issues that may cause performance degradation at each deep learning step in the medical imaging domain and discusses factors that must be considered to improve the performance of deep learning models. Researchers who wish to begin deep learning research can reduce the required amount of trial-and-error by understanding the issues discussed in this study.

• International Journal of Control, Automation, and Systems
• /
• v.6 no.3
• /
• pp.327-338
• /
• 2008

A fault tolerant control system design technique has been proposed and analyzed for managing performance degradation in the presence of multiple faults in actuators. The method is based on a control structure with a model reference reconfigurable control design in an inner loop and command input adjustment in an outer loop. The reduced dynamic performance requirements in the presence of different actuator faults are accounted for through different performance reduced (degraded) reference models. The degraded steady-state performances are governed by the reduced levels of command input. The reconfigurable controller is designed on-line automatically in an explicit model reference control framework so that the dynamics of the closed-loop system follow that of the performance reduced reference model under each fault condition. The reduced command input level is determined to prevent potential actuator saturation. The proposed method has been evaluated and analyzed using an aircraft example against actuator faults subject to constraints on the magnitude and slew-rate of actuators.

• MALSORI
• /
• no.53
• /
• pp.119-127
• /
• 2005

Speech recognition is one of the user interface technologies in commanding and controlling any terminal such as a TV, PC, cellular phone etc. in a ubiquitous environment. In controlling a terminal, the mismatch between training and testing causes rapid performance degradation. That is, the mismatch decreases not only the performance of the recognition system but also the reliability of that. Therefore, the performance degradation due to the mismatch caused by the change of the environment should be necessarily compensated. Whenever the environment changes, environment adaptation is performed using the user's speech and the background noise of the changed environment and the performance is increased by employing the models appropriately transformed to the changed environment. So far, the research on the environment compensation has been done actively. However, the compensation method for the effect of distant-talking speech has not been developed yet. Thus, in this paper we apply MLLR-based environment adaptation to compensate for the effect of distant-talking speech and the performance is improved.

• Speech Sciences
• /
• v.15 no.4
• /
• pp.85-96
• /
• 2008

Automatic speech recognition has severe performance degradation under noisy environments. To cope with the noise problem, many methods have been proposed. Most of them focused on noise-robust features or model adaptation. However, researchers have overlooked utterance verification (UV) under noisy environments. In this paper we discuss UV problems based on the normalized confidence measure. First, we show that UV performance is also degraded in noisy environments with the experiments of an isolated word recognition. Then we observe how the degradation of UV performances is suffered. Based on the UV experiments we propose a modeling method of the statistics of phone confidences using sigmoid functions. For obtaining the parameters of the sigmoidal models, the particle swarm optimization (PSO) is adopted. The proposed method improves 20% rejection performance. Our experimental results show that the PSO-NCM can apply noise speech recognition successfully.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.43 no.2
• /
• pp.48-55
• /
• 2020

Recently, a study of prognosis and health management (PHM) was conducted to diagnose failure and predict the life of air craft engine parts using sensor data. PHM is a framework that provides individualized solutions for managing system health. This study predicted the remaining useful life (RUL) of aeroengine using degradation data collected by sensors provided by the IEEE 2008 PHM Conference Challenge. There are 218 engine sensor data that has initial wear and production deviations. It was difficult to determine the characteristics of the engine parts since the system and domain-specific information was not provided. Each engine has a different cycle, making it difficult to use time series models. Therefore, this analysis was performed using machine learning algorithms rather than statistical time series models. The machine learning algorithms used were a random forest, gradient boost tree analysis and XG boost. A sliding window was applied to develop RUL predictions. We compared model performance before and after applying the sliding window, and proposed a data preprocessing method to develop RUL predictions. The model was evaluated by R-square scores and root mean squares error (RMSE). It was shown that the XG boost model of the random split method using the sliding window preprocessing approach has the best predictive performance.

• International conference on construction engineering and project management
• /
• 2022.06a
• /
• pp.1252-1252
• /
• 2022

Temporary work that utilizes temporary equipment (e.g., system scaffold and system pipe support) in construction work is one of the most vulnerable work from a safety perspective in South Korea. Typically, temporary equipment is reused at construction sites. The Korea Occupational Safety and Health Agency announced guidelines regarding the performance standards for reusable temporary equipment to prevent the accidental collapse of temporary facilities. Nevertheless, temporary facilities' collapse still occurs, which could be attributed to a degradation in the performance due to the reuse of temporary equipment. Therefore, this study investigated the performance of simple temporary structures assembled with new and reused equipment. To this end, an experimental module was designed based on previous research cases, and two experimental models were constructed, in which one was assembled using new equipment (Model A), and the other was built using reused equipment (Model B). To determine the performance of each model, a load test was conducted to measure the maximum load that each model could withstand. The experimental results revealed that the maximum load of Model B was 15% lower than that of Model A. This indicates that there is a meaningful performance difference between those two models. Based on this result, the authors decided to perform additional tests with more realistic models than previous ones. The new experimental module was designed to ensure compliance with the Korean design guidelines. In this presentation, the authors show details of the first tests and their results and plan for the additional test.

• IEMEK Journal of Embedded Systems and Applications
• /
• v.18 no.3
• /
• pp.89-100
• /
• 2023

Recently, on-device artificial intelligence (AI) solutions using mobile devices and embedded edge devices have emerged in various fields, such as computer vision, to address network traffic burdens, low-energy operations, and security problems. Although vision transformer deep learning models have outperformed conventional convolutional neural network (CNN) models in computer vision, they require more computations and parameters than CNN models. Thus, they are not directly applicable to embedded edge devices with limited hardware resources. Many researchers have proposed various model compression methods or lightweight architectures for vision transformers; however, there are only a few studies evaluating the effects of model compression techniques of vision transformers on performance. Regarding this problem, this paper presents a performance evaluation of vision transformers on embedded platforms. We investigated the behaviors of three vision transformers: DeiT, LeViT, and MobileViT. Each model performance was evaluated by accuracy and inference time on edge devices using the ImageNet dataset. We assessed the effects of the quantization method applied to the models on latency enhancement and accuracy degradation by profiling the proportion of response time occupied by major operations. In addition, we evaluated the performance of each model on GPU and EdgeTPU-based edge devices. In our experimental results, LeViT showed the best performance in CPU-based edge devices, and DeiT-small showed the highest performance improvement in GPU-based edge devices. In addition, only MobileViT models showed performance improvement on EdgeTPU. Summarizing the analysis results through profiling, the degree of performance improvement of each vision transformer model was highly dependent on the proportion of parts that could be optimized in the target edge device. In summary, to apply vision transformers to on-device AI solutions, either proper operation composition and optimizations specific to target edge devices must be considered.

• Journal of the Semiconductor & Display Technology
• /
• v.19 no.3
• /
• pp.82-87
• /
• 2020

The comprehensive and physics-based compact noise models for advanced CMOS devices were presented. The models incorporate important physical effects in nanoscale MOSFETs, such as the low frequency correlation effect between the drain and the gate, the trap-related phenomena, and QM (quantum mechanical) effects in the inversion layer. The drain current noise model was improved by including the tunneling assisted-thermally activated process, the realistic trap distribution, the parasitic resistance, and mobility degradation. The expression of correlation coefficient was analytically described, enabling the overall noise performance to be evaluated. With the consideration of QM effects, the comprehensive low frequency noise performance was simulated over the entire bias range.

• Convergence Security Journal
• /
• v.24 no.2
• /
• pp.201-207
• /
• 2024

Voice is a critical element of human communication, and the development of speech recognition models is one of the significant achievements in artificial intelligence, which has recently been applied in various aspects of human life. The application of speech recognition models in the military field is also inevitable. However, before artificial intelligence models can be applied in the military, it is necessary to research their vulnerabilities. In this study, we evaluates the military applicability of the multilingual speech recognition model "Whisper" by examining its vulnerabilities to battlefield noise, white noise, and adversarial attacks. In experiments involving battlefield noise, Whisper showed significant performance degradation with an average Character Error Rate (CER) of 72.4%, indicating difficulties in military applications. In experiments with white noise, Whisper was robust to low-intensity noise but showed performance degradation under high-intensity noise. Adversarial attack experiments revealed vulnerabilities at specific epsilon values. Therefore, the Whisper model requires improvements through fine-tuning, adversarial training, and other methods.