• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.61-68
• /
• 2024

Despite the continuous efforts to mitigate pedestrian accidents at crosswalks, the problem persist. Vulnerable groups, including the elderly and disabled individuals are at a risk of being involved in traffic incidents. This paper proposes the implementation of object detection algorithm using the YOLO v5 model specifically for pedestrians using assistive devices like wheelchairs and crutches. For this research, data was collected and utilized through image crawling, Roboflow, and Mobility Aids datasets, which comprise of wheelchair users, crutch users, and pedestrians. Data augmentation techniques were applied to improve the model's generalization performance. Additionally, ensemble techniques were utilized to mitigate type 2 errors, resulting in 96% recall rate. This demonstrates that employing ensemble methods with a single YOLO model to target transportation-disadvantaged individuals can yield accurate detection performance without overlooking crucial objects.

• Smart Media Journal
• /
• v.12 no.11
• /
• pp.1-9
• /
• 2023

Stress is a significant issue in modern society, often triggered by external or internal factors that are difficult to manage. When high stress persists over a long term, it can develop into a chronic condition, negatively impacting health and overall well-being. However, it is challenging for individuals experiencing chronic stress to recognize their condition, making early detection and management crucial. Using biosignals measured from wearable devices to detect stress could lead to more effective management. However, there are two main problems with using biosignals: first, manually extracting features from these signals can introduce bias, and second, the performance of classification models can vary greatly depending on the subject of the experiment. This paper proposes a model that reduces bias using convo utional autoencoders, which can represent the key features of data, and enhances generalizability by employing soft voting, a method of ensemble learning, to minimize performance variability. To verify the generalization performance of the model, we evaluate it using LOSO cross-validation method. The model proposed in this paper has demonstrated superior accuracy compared to previous studies using the WESAD dataset.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.37 no.4
• /
• pp.420-426
• /
• 2024

This study proposes an innovative methodology for developing flexible printed circuit boards (FPCBs) capable of conforming to three-dimensional shapes, meeting the increasing demand for electronic circuits in diverse and complex product designs. By integrating a traditional flat plate-based fabrication process with a subsequent three-dimensional thermal deformation technique, we have successfully demonstrated an FPCB that maintains stable electrical characteristics despite significant shape deformations. Using a modified polyimide substrate along with Ag flake-based conductive ink, we identified optimized process variables that enable substrate thermal deformation at lower temperatures (~130℃) and enhance the stretchability of the conductive ink (ε ~30%). The application of this novel FPCB in a prototype 3D-shaped sensor device, incorporating photosensors and temperature sensors, illustrates its potential for creating multifunctional, shape-adaptable electronic devices. The sensor can detect external light sources and measure ambient temperature, demonstrating stable operation even after transitioning from a planar to a three-dimensional configuration. This research lays the foundation for next-generation FPCBs that can be seamlessly integrated into various products, ushering in a new era of electronic device design and functionality.

• Advanced Industrial SCIence
• /
• v.3 no.1
• /
• pp.30-36
• /
• 2024

Recently, the Internet of Things (IoT), which has been applied to various industrial fields, is constantly evolving in the process of automation and digitization. However, in the network where IoT devices are built, research on IoT critical information-related data sharing, personal information protection, and data integrity among intermediate nodes is still being actively studied. In this study, we propose a blockchain-based IoT critical information management technique that is easy to implement without burdening the intermediate node in the network environment where IoT is built. The proposed technique allocates a random value of a random size to the IoT critical information arriving at the intermediate node and manages it to become a decentralized P2P blockchain. In addition, the proposed technique makes it easier to manage IoT critical data by creating licenses such as time limit and device limitation according to the weight condition of IoT critical information. Performance evaluation and proposed techniques have improved delay time and processing time by 7.6% and 10.1% on average compared to existing techniques.

• Journal of Advanced Navigation Technology
• /
• v.28 no.4
• /
• pp.566-573
• /
• 2024

Applying autonomous driving technology to construction sites is very difficult due to safety issues. However, the application of various positioning and sensing devices, such as cameras and radars, to construction equipment is very active. Based on these technological trends, the government is making various efforts, including the Serious Accident Punishment Act and support for industrial safety management expenses, to reduce the incidence of accidents caused by construction equipment and industrial vehicles. And, related industries have been developing various safety equipment over the past few years and applying them to the field. In this paper, we investigate the current status of safety equipment-related technologies currently applied to construction equipment and industrial vehicles, and propose a direction for the development of safety technology in construction equipment based on artificial intelligence. Improving the safety and work efficiency of construction equipment based on the technology proposed in this paper should be reviewed through simulation in the future.

• Convergence Security Journal
• /
• v.21 no.4
• /
• pp.49-57
• /
• 2021

The 4th industrial revolution will develop the network environment of future warfare through the increase of IoT devices, individual warrior platforms, the operation of manned and unmanned weapon systems, intelligent command post. They are leading to the weapon system combined with hundreds or thousands of sensors will be used for surveillance and reconnaissance, electronic warfare, and deception operations on the battlefield. This change to the environment brings superiority in operational performance on the battlefield, but if the weapon system is exposed to the outside, it will lead to fatal results. In this paper, we analyze the network environment that is changing in the future warfare environment, focusing on the currently used network. In addition, it considers information security issues that must correspond to the evolving network technology and suggests various security measures to suggest the direction our military should take in the future.

• Asian-Australasian Journal of Animal Sciences
• /
• v.16 no.2
• /
• pp.180-184
• /
• 2003

The intrauterine inseminator (IUI) was developed to provide the method of depositing dog semen into the uterine body instead of the vagina. The IUI consists of a vaginal endoscope, a balloon sheath, and injection catheter. When the endoscope is inserted into the vagina and the balloon expanded with air, the cervical os becomes visible so a injection catheter can be inserted through the cervix for deposition of the frozen-thawed semen. The efficacy of the IUI device was compared to intra-vaginal artificial insemination using semen that had been collected and frozen from pooled sperm-rich fraction of ejaculates collected from two Jindo dog donors. Aliquots of semen were extended with a Tris-egg yolk diluent, centrifuged, the seminal plasma removed, the pellet resuspended with the same diluent, and cooled to $5^{\circ}C$ over a 2 h period. A Tris-egg yolk-glycerol extender was added at $5^{\circ}C$; after 1 h, semen was loaded into 0.5 ml straws, and straws were frozen in LN vapor for 5 min, and immersed in LN for storage. The final sperm concentration for freezing was approximately $100{\times}10^{6}cells/ml$. The straws were thawed at $70^{\circ}C$ for precisely 6 sec, 1.5 ml Tris-egg yolk buffer at $38^{\circ}C$ added, and the 2 ml of thawed semen was used for a single insemination using the IUI device. Each bitch was inseminated at optimal insemination point, which was estimated by vaginal epithelial cells staining and progesterone concentration analysis. Use of the IUI device resulted in 21 of 26 females giving birth to 89 pups ($4.2{\pm}1.6$ pups per litter), while intra-vaginal AI resulted in 6 of 15 females whelping a total of 17 pups ($2.8{\pm}1.2$ pups per litter). We believe the IUI device is easier to use than previously described devices used for intrauterine insemination. In our experience the expansion of the balloon has a calming effect on the bitch that aids the inseminator. These results indicate that the IUI device was able to provide high fertility with 50 million frozen sperm per insemination and two inseminations.

• KIPS Transactions on Computer and Communication Systems
• /
• v.11 no.2
• /
• pp.67-72
• /
• 2022

Recently, various intelligent application services using artificial intelligence are being actively developed. In particular, research on artificial intelligence-based real-time prediction services is being actively conducted in the manufacturing industry, and the demand for artificial intelligence services that can detect and predict fire and odors is very high. However, most of the existing detection and prediction systems do not predict the occurrence of fires and odors, but rather provide detection services after occurrence. This is because AI-based prediction service technology is not applied in existing systems. In addition, fire prediction, odor detection and odor level prediction services are services with ultra-low delay characteristics. Therefore, in order to provide ultra-low-latency prediction service, edge computing technology is combined with artificial intelligence models, so that faster inference results can be applied to the field faster than the cloud is being developed. Therefore, in this paper, we propose an LSTM algorithm-based learning model that can be used for fire prediction and odor detection/prediction, which are most required in the manufacturing industry. In addition, the proposed learning model is designed to be implemented in edge devices, and it is proposed to receive real-time sensor data from the IoT terminal and apply this data to the inference model to predict fire and odor conditions in real time. The proposed model evaluated the prediction accuracy of the learning model through three performance indicators, and the evaluation result showed an average performance of over 90%.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2022.05a
• /
• pp.41-43
• /
• 2022

In order to prevent and block infectious diseases caused by the recent COVID-19 pandemic, non-contact biometric information acquisition and analysis technology is attracting attention. The invasive and attached biometric information acquisition method accurately has the advantage of measuring biometric information, but has a risk of increasing contagious diseases due to the close contact. To solve these problems, the non-contact method of extracting biometric information such as human fingerprints, faces, iris, veins, voice, and signatures with automated devices is increasing in various industries as data processing speed increases and recognition accuracy increases. However, although the accuracy of the non-contact biometric data acquisition technology is improved, the non-contact method is greatly influenced by the surrounding environment of the object to be measured, which is resulting in distortion of measurement information and poor accuracy. In this paper, we propose a context-based bio-signal modeling technique for the interpretation of personalized information (image, signal, etc.) for bio-information analysis. Context-based biometric information modeling techniques present a model that considers contextual and user information in biometric information measurement in order to improve performance. The proposed model analyzes signal information based on the feature probability distribution through context-based signal analysis that can maximize the predicted value probability.

• Journal of the Institute of Convergence Signal Processing
• /
• v.23 no.2
• /
• pp.76-83
• /
• 2022

With the recent development of IT technology, research and interest in various biosignal measuring devices is increasing. As an aging society is in full swing, research on the elderly population using IT-related technologies is continuously developing. This study is about the development of life pattern detection and fall detection algorithm, which is one of the medical service areas for the elderly, who are rapidly developing as they enter a super-aged society. This study consisted of a system using a 3-axis accelerometer and an electrocardiogram sensor, collected data, and then analyzed the data. It was confirmed that behavioral patterns could be classified from the actual research results. In order to evaluate the usefulness of the human activity monitoring system implemented in this study, experiments were performed under various conditions, such as changes in posture and walking speed, and signal magnitude range and signal vector magnitude parameters reflecting the acceleration of gravity of the human body and the degree of human activity. was extracted. And the possibility of discrimination according to the condition of the subject was examined by these parameter values.