• Journal of Broadcast Engineering
• /
• v.27 no.4
• /
• pp.561-568
• /
• 2022

Most deep learning-based video object segmentation methods perform the segmentation with past prediction information stored in external memory. In general, the more past information is stored in the memory, the better results can be obtained by accumulating evidence for various changes in the objects of interest. However, all information cannot be stored in the memory due to hardware limitations, resulting in performance degradation. In this paper, we propose a method of storing new information in the external memory without additional memory allocation. Specifically, after calculating the attention score between the existing memory and the information to be newly stored, new information is added to the corresponding memory according to each score. In this way, the method works robustly because the attention mechanism reflects the object changes well without using additional memory. In addition, the update rate is adaptively determined according to the accumulated number of matches in the memory so that the frequently updated samples store more information to maintain reliable information.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.17 no.10
• /
• pp.2627-2642
• /
• 2023

Parkinson's disease (PD) is a typical, chronic neurodegenerative disease involving the concentration of dopamine, which can disrupt motor activity and cause different degrees of gait disturbance relevant to PD severity in patients. As current clinical PD diagnosis is a complex, time-consuming, and challenging task that relays on physicians' subjective evaluation of visual observations, gait disturbance has been extensively explored to make automatic detection of PD diagnosis and severity rating and provides auxiliary information for physicians' decisions using gait data from various acquisition devices. Among them, wearable sensors have the advantage of flexibility since they do not limit the wearers' activity sphere in this application scenario. In this paper, an attention-based temporal network (ATN) is designed for the time series structure of gait data (vertical ground reaction force signals) from foot sensor systems, to learn the discriminative differences related to PD severity levels hidden in sequential data. The structure of the proposed method is illuminated by Transformer Network for its success in excavating temporal information, containing three modules: a preprocessing module to map intra-moment features, a feature extractor computing complicated gait characteristic of the whole signal sequence in the temporal dimension, and a classifier for the final decision-making about PD severity assessment. The experiment is conducted on the public dataset PDgait of VGRF signals to verify the proposed model's validity and show promising classification performance compared with several existing methods.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.18 no.9
• /
• pp.436-443
• /
• 2017

Recently, the development of new energy technologies has become a hot topic due to problems,such as global warming. Unlike renewable energy technologies, such as solar energy generation, solar power, and wind power, which are optimized to achieve medium or above output power, the output power of energy harvesting technology is very small and has not received much attention. On the other hand, as the mobile industry has been revitalized recently, the utility of energy harvesting technology has been reevaluated. In addition, the technology of tracking the maximum power point has been actively researched. This paper proposes a new MPPT(Maximum Power Point Tracking) control method for a TEM(thermoelectric module) for load resistance. The V-I curve characteristics and internal resistance of TEM were analyzed and the conventional MPPT control methods were compared. The P&O(Perturbation and Observation) control method is more accurate, but it is less economical than the CV (Constant Voltage)control method because it usestwo sensors to measure the voltage and current source. The CV control method is superior to the P&O control method in economic aspects because it uses only one voltage sensor but the MPP is not matched precisely. In this paper, a method wasdesigned to track the MPP of TEM combining the advantages of the two control method. The proposed MPPT control method wasverified by PSIM simulation and H/W implementation.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.29 no.2
• /
• pp.122-129
• /
• 2009

Recently much attention has been paid to a guided wave due to its effective applicability to long range and fast inspection of structures. In guided wave based NDE, the appropriate selection of wave modes is one of important factors since the test performance is highly dependent on which mode of guided waves is employed. As far as plate-like structures are concerned, so far, SH guided wave has not been frequently applied compared to Lamb waves, which is mostly caused by the lack of proper and convenient transducers to generate and measure the SH waves. In this investigation, a new small-sized SH guided wave transducer based on magnetostriction is proposed. The present transducer was designed to be modular and be used with shear couplant to avoid the inconvenience of the existing magnetostrictive patch transducers, which comprises the ferromagnetic patch tightly bonded to a structure. The wave transduction mechanism and the detailed configuration of the present transducer are presented. Experimental verification is also conducted on test specimens and the results confirm the good performance of the present transducer module.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.7
• /
• pp.493-503
• /
• 2018

Recently, as living standards have improved, many people are becoming more interested in health, and self-training is increasing through exercise to prevent and manage pre-illness. In general, an imbalance of muscles causes asymmetry of posture, which can cause various diseases by accompanying an adjustment force, circulation action, displacement of internal organs, etc.. In this study, the development of fitness software that can be self - training among smart wears has attracted considerable attention in recent years. In this study, a technology was proposed for the commercialization of self - trainer fitness wear by a simulation through Android - based applications. Self - trainer fitness software was developed by combining a conductive polymer, fashion design, sewing, and electric and electronic technology to monitor the unbalance of the muscles during exercise and make smart wear that can calibrate the asymmetry by oneself. In particular, a polymer sensor was fabricated by deriving the optimal MWCNT concentration, and the electrode signal was collected by attaching the electrode to the optimal position, where the electrode signal line using the conductive fiber was designed and attached to collect the signal. A signal module that converts the bio-signals collected through electrical signal conversion and transmits them using Bluetooth communication was designed and manufactured. Self-trainer fitness software that can be commercialized was developed by combining noise cancellation with Android-based self-training application using a software algorithm method.

• Transactions of the Korean Society of Mechanical Engineers B
• /
• v.36 no.12
• /
• pp.1185-1192
• /
• 2012

The typical operating temperature of an automotive fuel cell is lower than that of an internal combustion engine, which necessitates a refined strategy for thermal management. In particular, the performance of the cooling module has to be higher for a fuel cell system because the temperature difference between the fuel cell and the surrounding is lower than in the case of the internal combustion engine. Even though the cooling system of an automotive fuel cell determines the operating temperature and temperature distribution of the fuel cell, it has attracted little research attention. This study presents the mathematical model of a cooling system for an automotive fuel cell system using Matlab/$Simulink^{(R)}$. In particular, a radiator model is developed for design optimization from the development stage to the operating stage for an automotive fuel cell. The cooling system model comprises a fan, pump, and radiator. The pump and fan model have an empirical relation, and the dynamics of the pump and fan are only explained by motor dynamics. The basic design study was conducted, and the geometric setup of the radiator was investigated. When the control logic was applied, the pump senses the coolant inlet temperature and the fan senses the coolant out temperature. Additionally, the cooling module is integrated with the fuel cell system model so that the performance of the cooling module can be investigated under realistic operating conditions.

• The Journal of the Acoustical Society of Korea
• /
• v.41 no.3
• /
• pp.359-366
• /
• 2022

In this paper, we present the Korean menu-ordering Sentence Text-to-Speech (TTS) system using conformer-based FastSpeech2. Conformer is the convolution-augmented transformer, which was originally proposed in Speech Recognition. Combining two different structures, the Conformer extracts better local and global features. It comprises two half Feed Forward module at the front and the end, sandwiching the Multi-Head Self-Attention module and Convolution module. We introduce the Conformer in Korean TTS, as we know it works well in Korean Speech Recognition. For comparison between transformer-based TTS model and Conformer-based one, we train FastSpeech2 and Conformer-based FastSpeech2. We collected a phoneme-balanced data set and used this for training our models. This corpus comprises not only general conversation, but also menu-ordering conversation consisting mainly of loanwords. This data set is the solution to the current Korean TTS model's degradation in loanwords. As a result of generating a synthesized sound using ParallelWave Gan, the Conformer-based FastSpeech2 achieved superior performance of MOS 4.04. We confirm that the model performance improved when the same structure was changed from transformer to Conformer in the Korean TTS.

• Journal of the Korea Institute of Information Security & Cryptology
• /
• v.34 no.2
• /
• pp.335-345
• /
• 2024

In the digital era, data security has become an increasingly critical issue, drawing significant attention. Particularly, anti-tampering technology has emerged as a key defense mechanism against indiscriminate hacking and unauthorized access. This paper explores case studies that exemplify the trends in the development and application of TPM (Trusted Platform Module) and software anti-tampering technology in today's digital ecosystem. By analyzing various existing security guides and guidelines, this paper identifies ambiguous areas within them and investigates recent trends in domestic and international research on software anti-tampering. Consequently, while guidelines exist for applying anti-tampering techniques, it was found that there is a lack of methods for evaluating them. Therefore, this paper aims to propose a comprehensive and systematic evaluation framework for assessing both existing and future software anti-tampering techniques. To achieve this, it using various verification methods employed in recent research. The proposed evaluation framework synthesizes these methods, categorizing them into three aspects (functionality, implementation, performance), thereby providing a comprehensive and systematic evaluation approach for assessing software anti-tampering technology in detail.

• Journal of Internet of Things and Convergence
• /
• v.10 no.2
• /
• pp.1-15
• /
• 2024

The construction of smart communities is a new method and important measure to ensure the security of residential areas. In order to solve the problem of low accuracy in face recognition caused by distorting facial features due to monitoring camera angles and other external factors, this paper proposes the following optimization strategies in designing a face recognition network: firstly, a global graph convolution module is designed to encode facial features as graph nodes, and a multi-scale feature enhancement residual module is designed to extract facial keypoint features in conjunction with the global graph convolution module. Secondly, after obtaining facial keypoints, they are constructed as a directed graph structure, and graph attention mechanisms are used to enhance the representation power of graph features. Finally, tensor computations are performed on the graph features of two faces, and the aggregated features are extracted and discriminated by a fully connected layer to determine whether the individuals' identities are the same. Through various experimental tests, the network designed in this paper achieves an AUC index of 85.65% for facial keypoint localization on the 300W public dataset and 88.92% on a self-built dataset. In terms of face recognition accuracy, the proposed network achieves an accuracy of 83.41% on the IBUG public dataset and 96.74% on a self-built dataset. Experimental results demonstrate that the network designed in this paper exhibits high detection and recognition accuracy for faces in surveillance videos.

• Journal of the Microelectronics and Packaging Society
• /
• v.26 no.4
• /
• pp.75-82
• /
• 2019

Flexible solar cells have attracted enormous attention in recent years due to their wide applications such as portable batteries, wearable devices, robotics, drones, and airplanes. In particular, the demands of the flexible silicon and compound semiconductor solar cells with high efficiency and high reliability keep increasing. In this study, we fabricated a flexible InGaP/GaAs double-junction solar module. Then, the effects of the wind speed and ambient temperature on the operating temperature of the solar cell were analyzed with the numerical simulation. The temperature distributions of the solar modules were analyzed for three different wind speeds of 0 m/s, 2.5 m/s, and 5 m/s, and two different ambient temperature conditions of 25℃ and 33℃. The flexibility of the flexible solar module was also evaluated with the bending tests and numerical bending simulation. When the wind speed was 0 m/s at 25 ℃, the maximum temperature of the solar cell was reached to be 149.7℃. When the wind speed was increased to 2.5 m/s, the temperature of the solar cell was reduced to 66.2℃. In case of the wind speed of 5 m/s, the temperature of the solar cell dropped sharply to 48.3℃. Ambient temperature also influenced the operating temperature of the solar cell. When the ambient temperature increased to 33℃ at 2.5 m/s, the temperature of the solar cell slightly increased to 74.2℃ indicating that the most important parameter affecting the temperature of the solar cell was heat dissipation due to wind speed. Since the maximum temperatures of the solar cell are lower than the glass transition temperatures of the materials used, the chances of thermal deformation and degradation of the module will be very low. The flexible solar module can be bent to a bending radius of 7 mm showing relatively good bending capability. Neutral plane analysis was also indicated that the flexibility of the solar module can be further improved by locating the solar cell in the neutral plane.