• Structural Monitoring and Maintenance
• /
• 제9권3호
• /
• pp.289-303
• /
• 2022

In this study, the impact of assigned pixel labels on the accuracy of crack image identification of steel structures is examined by using an atrous separable convolution neural network (ASCNN). Firstly, images containing fatigue cracks collected from steel structures are classified into four datasets by assigning different pixel labels based on image features. Secondly, the DeepLab v3+ algorithm is used to determine optimal parameters of the ASCNN model by maximizing the average mean-intersection-over-union (mIoU) metric of the datasets. Thirdly, the ASCNN model is trained for various image sizes and hyper-parameters, such as the learning rule, learning rate, and epoch. The optimal parameters of the ASCNN model are determined based on the average mIoU metric. Finally, the trained ASCNN model is evaluated by using 10% untrained images. The result shows that the ASCNN model can segment cracks and other objects in the captured images with an average mIoU of 0.716.

• 한국환경복원기술학회지
• /
• 제25권2호
• /
• pp.85-92
• /
• 2022

The amphibian breeding habitat is confirmed by mating call. In some cases, the researcher directly identifies the amphibian individual, but in order to designate the habitat, it is necessary to map the mating call region of the amphibian population. Until now, it has been a popular methodology for researchers to hear mating calls and outline their breeding habitats. To improve this subjective methodology, we developed a technique for mapping mating call regions using Unmanned Aerial Vehicle (UAV). The technology uses a UAV, fitted with a sound recorder to record ground mating calls as it flies over an amphibian habitat. The core technology is to synchronize the recorded sound pressure with the flight log of the UAV and predict the sound pressure in a two-dimensional plane with probability density. For a demonstration study of this technology, artificial mating call was generated by a potable speaker on the ground and recorded by a UAV. Then, the recorded sound data was processed with an algorithm developed by us to map mating calls. As a result of the study, the correlation coefficient between the artificial mating call on the ground and the mating call map measured by the UAV was R=0.77. This correlation coefficient proves that our UAV recording system is sufficiently capable of detecting amphibian mating call regions.

• 로봇학회논문지
• /
• 제16권3호
• /
• pp.179-188
• /
• 2021

Construction monitoring is one of the key modules in smart construction. Unlike structured urban environment, construction site mapping is challenging due to the characteristics of an unstructured environment. For example, irregular feature points and matching prohibit creating a map for management. To tackle this issue, we propose a system for data acquisition in unstructured environment and a framework for Intensity and Ambient Enhanced Lidar Inertial Odometry via Smoothing and Mapping, IA-LIO-SAM, that achieves highly accurate robot trajectories and mapping. IA-LIO-SAM utilizes a factor graph same as Tightly-coupled Lidar Inertial Odometry via Smoothing and Mapping (LIO-SAM). Enhancing the existing LIO-SAM, IA-LIO-SAM leverages point's intensity and ambient value to remove unnecessary feature points. These additional values also perform as a new factor of the K-Nearest Neighbor algorithm (KNN), allowing accurate comparisons between stored points and scanned points. The performance was verified in three different environments and compared with LIO-SAM.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제16권4호
• /
• pp.1209-1223
• /
• 2022

Blood pressure is one of the key physiological parameters for determining human health, and can prove whether human cardiovascular function is healthy or not. In general, what we call blood pressure refers to arterial blood pressure. Blood pressure fluctuates greatly and, due to the influence of various factors, even varies with each heartbeat. Therefore, achievement of continuous blood pressure measurement is particularly important for more accurate diagnosis. It is difficult to achieve long-term continuous blood pressure monitoring with traditional measurement methods due to the continuous wear of measuring instruments. On the other hand, radar technology is not easily affected by environmental factors and is capable of strong penetration. In this study, by using machine learning, tried to develop a linear blood pressure prediction model using data from a public database. The radar sensor evaluates the measured object, obtains the pulse waveform data, calculates the pulse transmission time, and obtains the blood pressure data through linear model regression analysis. Confirm its availability to facilitate follow-up research, such as integrating other sensors, collecting temperature, heartbeat, respiratory pulse and other data, and seeking medical treatment in time in case of abnormalities.

• 한국안전학회지
• /
• 제37권4호
• /
• pp.28-35
• /
• 2022

This study is aimed to develop a safety diagnosis system for fire pumps that detects normal and abnormal signals for the stable operation of the system. Hence, the following activities were carried out: first, a threshold value was identified for the normal operation and six abnormal operations (adherence of impeller, absence of water source, separation of pump and motor, run-stop operation, air inflow into the casing, and reverse-phase loss of the power line) reflecting changes in the current, flow and pressure of fire pumps; secondly, based on the identified signals, an algorithm capable of detecting three abnormal signals was developed and in terms of hardware, a current, pressure and flow sensor suitable for the analogue input values of NI-6009 was designed and installed. This combination of the hardware and software is applicable as a diagnosis system to ensure the stable operation of fire pumps.

• 한국표면공학회지
• /
• 제55권3호
• /
• pp.164-172
• /
• 2022

Hot-dip galvanized steel(GI) is widely used throughout the industry as a corrosion resistance material. Corrosion of steel is a common phenomenon that results in the gradual degradation under various environmental conditions. Corrosion monitoring is to track the degradation progress for a long time. Corrosion on steel plate appears as discoloration and any irregularities on the surface. This study developed a quantitative evaluation method of the rust formed on GI steel plate using a superpixel-based DBSCAN clustering method and k-means clustering from the corroded area in a given image. The superpixel-based DBSCAN clustering method decrease computational costs, reaching automatic segmentation. The image color of the rusty surface was analyzed quantitatively based on HSV(Hue, Saturation, Value) color space. In addition, two segmentation methods are compared for the particular spatial region using their histograms.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제15권12호
• /
• pp.4385-4399
• /
• 2021

The Internet of Things (IoT) eHealth systems composed by Wireless Body Area Network (WBAN) has emerged recently. Sensor nodes are placed around or in the human body to collect physiological data. WBAN has many different applications, for instance health monitoring. Since the limitation of the size of the battery, besides speed, reliability, and accuracy; design of WBAN protocols should consider the energy efficiency and time delay. To solve these problems, this paper adopt the end-edge-cloud orchestrated network architecture and propose a transmission based on reinforcement algorithm. The priority of sensing data is classified according to certain application. System utility function is modeled according to the channel factors, the energy utility, and successful transmission conditions. The optimization problem is mapped to Q-learning model. Following this online power control protocol, the energy level of both the senor to coordinator, and coordinator to edge server can be modified according to the current channel condition. The network performance is evaluated by simulation. The results show that the proposed power control protocol has higher system energy efficiency, delivery ratio, and throughput.

• Archives of Plastic Surgery
• /
• 제49권3호
• /
• pp.427-439
• /
• 2022

Peripheral nerve injuries (PNIs) often present with variable symptoms, making them difficult to diagnose, treat, and monitor. When neurologic compromise is inadequately assessed, suboptimal treatment decisions can result in lasting functional deficits. There are many available tools for evaluating pain and functional status of peripheral nerves. However, the literature lacks a detailed, comprehensive view of the data comparing the clinical utility of these modalities, and there is no consensus on the optimal algorithm for sensory and pain assessment in PNIs. We performed a systematic review of the literature focused on clinical data, evaluating pain and sensory assessment methods in peripheral nerves. We searched through multiple databases, including PubMed/Medline, Embase, and Google Scholar, to identify studies that assessed assessment tools and explored their advantages and disadvantages. A total of 66 studies were selected that assessed various tools used to assess patient's pain and sensory recovery after a PNI. This review may serve as a guide to select the most appropriate assessment tools for monitoring nerve pain and/or sensory function both pre- and postoperatively. As the surgeons work to improve treatments for PNI and dysfunction, identifying the most appropriate existing measures of success and future directions for improved algorithms could lead to improved patient outcomes.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권2호
• /
• pp.295-311
• /
• 2023

Cloud computing has evolved significantly, intending to provide users with fast, dependable, and low-cost services. With its development, malicious users have become increasingly capable of attacking both its internal and external security. To ensure the security of cloud services, encryption, authorization, firewalls, and intrusion detection systems have been employed. However, these single monitoring agents, are complex, time-consuming, and they do not detect ransomware and zero-day vulnerabilities on their own. An innovative Record and Replay-based hybrid Honeynet (R2NET) system has been developed to address this issue. Combining honeynet with Record and Replay (RR) technology, the system allows fine-grained analysis by delaying time-consuming analysis to the replay step. In addition, a machine learning algorithm is utilized to cluster the logs of attackers and store them in a database. So, the accessing time for analyzing the attack may be reduced which in turn increases the efficiency of the proposed framework. The R2NET framework is compared with existing methods such as EEHH net, HoneyDoc, Honeynet system, and AHDS. The proposed system achieves 7.60%, 9.78%%, 18.47%, and 31.52% more accuracy than EEHH net, HoneyDoc, Honeynet system, and AHDS methods.

• 디지털산업정보학회논문지
• /
• 제19권3호
• /
• pp.213-220
• /
• 2023

Face recognition is a very important process in video monitoring and is a type of biometric technology. It is mainly used for identification and security purposes, such as ID cards, licenses, and passports. The recognition process has many variables and is complex, so development has been slow. In this paper, we proposed a face recognition method using CNN, which has been re-examined due to the recent development of computers and algorithms, and compared with the feature comparison method, which is an existing face recognition algorithm, to verify performance. The proposed face search method is divided into a face region extraction step and a learning step. For learning, face images were standardized to 50×50 pixels, and learning was conducted while minimizing unnecessary nodes. In this paper, convolution and polling-based techniques, which are one of the deep learning technologies, were used for learning, and 1,000 face images were randomly selected from among 7,000 images of Caltech, and as a result of inspection, the final recognition rate was 98%.