• Smart Media Journal
• /
• v.12 no.3
• /
• pp.120-128
• /
• 2023

There are various ICT technologies continuously being developed to reduce damage by industrial accidents. And research is being conducted to minimize damage in case of industrial accidents by utilizing sensors, IoT, big data, machine learning and artificial intelligence. In this paper, we propose a design method for a smart device capable of multilateral communication between devices and smart repeater in the communication shaded Areas such as closed areas of industrial sites, mountains, oceans, and coal mines. The proposed device collects worker's information such as worker location and movement speed, and environmental information such as terrain, wind direction, temperature, and humidity, and secures a safe distance between workers to warn in case of a dangerous situation and is designed to be attached to a helmet. For this, we proposed functional requirements for smart devices and design methods for implementing each requirement using sensors and modules in smart device. And we derived evaluation items for performance evaluation of the smart device and proposed an evaluation environment for performance evaluation in mountainous area.

• Transactions of the Korean Society of Machine Tool Engineers
• /
• v.14 no.3
• /
• pp.32-37
• /
• 2005

Several types of smart materials and control scheme are available to adjust the structure actively in various external disturbances. A control scheme was introduced for a specific material. But the effectiveness of the control scheme has some limitation according to the choice of the smart materials and the response of the structure. The ER(Electrorheological) fluid is adequate for a large control force, and the PZT(lead zirconate titanate) patches are suitable for small but arbitrary control force at any point of the structure. It can be used for active control of structure by changing the dynamic characteristics of the structure. But it has some difficulty in suppressing the excited vibration in broad band. To compensate this resonance of the controlled structure, a hybrid controller was constructed using PPF(Positive position feedback) control with PZT and ER fluid control.

• Land and Housing Review
• /
• v.11 no.1
• /
• pp.103-108
• /
• 2020

Autonomous things system is a technology that judges and acts based on using surrounding information by itself, and it is evaluated as a future technology that can replace the current IoT technology. The current IoT technology is widely used from facility monitoring to machine control but it is shown weakness as a evaluation and prediction technique despite of smart city important technology. In this study, in order to confirm the application of the autonomous things technology, a monitoring system was installed on a real reservoir dam facility and long-term monitoring was performed that the measuring device itself judges and control as a facility monitoring technology. The autonomous things technology was confirmed during 19 months and it is possible to continuous measurement in the same way as current automated instrumentation. In addition, it was confirmed that the ICT device itself could to control autonomously measurement cycle according to the rainfall by itself.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2013.11a
• /
• pp.1064-1067
• /
• 2013

정보검색 기술의 발달과 더불어 검색에 대한 사용자의 요구사항이 다양해지고 있다. 특히, 스마트TV와 같은 장치에서 동영상 콘텐츠를 검색하는데 있어서 콘텐츠의 타이틀과 같은 정형 메타데이터를 이용한 검색뿐만 아니라, 콘텐츠 주제와 같은 비정형 메타데이터를 이용한 검색도 요구되고 있다. 이러한 검색 요구사항을 수용하기 위해서는 주제와 같은 비정형 메타데이터가 구축되어 있어야만 가능하다. 콘텐츠의 주제는 사람의 이해와 분석을 통해서 수작업으로 구축 가능하다. 본 논문에서는 수작업만으로 구축 가능한 콘텐츠의 주제를 기계학습을 기반으로 자동화 할 수 있는 기법을 제안하고, 제안한 기법의 실험을 통하여 타당성을 검증한다.

• Journal of Sensor Science and Technology
• /
• v.31 no.2
• /
• pp.79-84
• /
• 2022

Self-powered sensors play an important role in everyday life, and they cover a wide range of topics. These sensors are meant to measure the amount of relevant motion and transform the biomechanical activities into electrical signals using triboelectric nanogenerators (TENGs) since they are sensitive to external stimuli such as pressure, temperature, wetness, and motion. The present advancement of TENGs-based self-powered wearable, implantable, and patchable sensors for healthcare monitoring, human body motion, and medication delivery systems was carefully emphasized in this study. The use of TENG technology to generate electrical energy in real-time using self-powered sensors has been the topic of considerable research among various leading scholars. TENGs have been used in a variety of applications, including biomedical and healthcare physical sensors, wearable devices, biomedical, human-machine interface, chemical and environmental monitoring, smart traffic, smart cities, robotics, and fiber and fabric sensors, among others, as efficient mechanical-to-electric energy conversion technologies. In this evaluation, the progress accomplished by TENG in several areas is extensively reviewed. There will be a discussion on the future of self-powered sensors.

• IEIE Transactions on Smart Processing and Computing
• /
• v.2 no.6
• /
• pp.323-331
• /
• 2013

An extreme learning machine (ELM) is an efficient learning algorithm that is based on the generalized single, hidden-layer feed-forward networks (SLFNs), which perform well in classification applications. Many studies have demonstrated its superiority over the existing classical algorithms: support vector machine (SVM) and BP neural network. This paper presents a novel face recognition approach based on a multi-class project extreme learning machine (MPELM) classifier and 2D Gabor transform. First, all face image features were extracted using 2D Gabor filters, and the MPELM classifier was used to determine the final face classification. Two well-known face databases (CMU-PIE and ORL) were used to evaluate the performance. The experimental results showed that the MPELM-based method outperformed the ELM-based method as well as other methods.

• Smart Structures and Systems
• /
• v.8 no.1
• /
• pp.53-67
• /
• 2011

Human state in human-machine systems highly affects the overall system performance, and should be detected and monitored. Physiological cues are essential indicators of human state and useful for the purpose of monitoring. The study presented in this paper was focused on developing a bio-inspired sensing system, i.e., Nano-Skin, to non-intrusively measure physiological cues on human-machine contact surfaces to detect human state. The paper is presented in three parts. The first part is to analyze the relationship between human state and physiological cues, and to introduce the conceptual design of Nano-Skin. Generally, heart rate, skin conductance, skin temperature, operating force, blood alcohol concentration, sweat rate, and electromyography are closely related with human state. They can be measured through human-machine contact surfaces using Nano-Skin. The second part is to discuss the technologies for skin temperature measurement. The third part is to introduce the design and manufacture of the Nano-Skin for skin temperature measurement. Experiments were performed to verify the performance of the Nano-Skin in temperature measurement. Overall, the study concludes that Nano-Skin is a promising product for measuring physiological cues on human-machine contact surfaces to detect human state.

• International journal of advanced smart convergence
• /
• v.12 no.2
• /
• pp.47-55
• /
• 2023

The automotive industry is undergoing a paradigm shift due to the convergence of IT and rapid digital transformation. Various components, including embedded structures and systems with complex architectures that incorporate IC semiconductors, are being integrated and modularized. As a result, there has been a significant increase in vehicle defects, raising expectations for the quality of automotive parts. As more and more data is being accumulated, there is an active effort to go beyond traditional reliability analysis methods and apply machine learning models based on the accumulated big data. However, there are still not many cases where machine learning is used in product development to identify factors of defects in performance and durability of products and incorporate feedback into the design to improve product quality. In this paper, we applied a prediction algorithm to the defects of automotive door devices equipped with automatic responsive sensors, which are commonly installed in recent electric and hydrogen vehicles. To do so, we selected test items, built a measurement emulation system for data acquisition, and conducted comparative evaluations by applying different machine learning algorithms to the measured data. The results in terms of R² score were as follows: Ordinary multiple regression 0.96, Ridge regression 0.95, Lasso regression 0.89, Elastic regression 0.91.

• Korea Trade Review
• /
• v.47 no.2
• /
• pp.69-88
• /
• 2022

This paper aims to predict Busan's regional product and employment using the logistic regression models and machine learning models. The following are the main findings of the empirical analysis. First, the OLS regression model shows that the main industries such as electricity and electronics, machine and transport, and finance and insurance affect the Busan's income positively. Second, the binomial logistic regression models show that the Busan's strategic industries such as the future transport machinery, life-care, and smart marine industries contribute on the Busan's income in large order. Third, the multinomial logistic regression models show that the Korea's main industries such as the precise machinery, transport equipment, and machinery influence the Busan's economy positively. And Korea's exports and the depreciation can affect Busan's economy more positively at the higher employment level. Fourth, the voting ensemble model show the higher predictive power than artificial neural network model and support vector machine models. Furthermore, the gradient boosting model and the random forest show the higher predictive power than the voting model in large order.

• IEIE Transactions on Smart Processing and Computing
• /
• v.1 no.1
• /
• pp.1-7
• /
• 2012

This paper presents a system used to automatically recognize the road traffic control gestures of police officers. In this approach,the control gestures of traffic police officers are captured in the form of depth images.A human skeleton is then constructed using a kinematic model. The feature vector describing a traffic control gesture is built from the relative angles found amongst the joints of the constructed human skeleton. We utilize Support Vector Machines (SVMs) to perform the gesture recognition. Experiments show that our proposed method is robust and efficient and is suitable for real-time application. We also present a testbed system based on the SVMs trained data for real-time traffic gesture recognition.