• 한국컴퓨터정보학회논문지
• /
• 제23권2호
• /
• pp.63-70
• /
• 2018

Safety management agent manages the risk behavior of the worker with the naked eye, but there is a real difficulty for one the agent to manage all the workers. In this paper, IoT device is attached to a harness safety belt that a worker wears to solve this problem, and behavior data is upload to the cloud in real time. We analyze the upload data through the deep learning and analyze the risk behavior of the worker. When the analysis result is judged to be dangerous behavior, we designed and implemented a system that informs the manager through monitoring application. In order to confirm that the risk behavior analysis through the deep learning is normally performed, the data values of 4 behaviors (walking, running, standing and sitting) were collected from IMU sensor for 60 minutes and learned through Tensorflow, Inception model. In order to verify the accuracy of the proposed system, we conducted inference experiments five times for each of the four behaviors, and confirmed the accuracy of the inference result to be 96.0%.

• Structural Engineering and Mechanics
• /
• 제81권2호
• /
• pp.131-146
• /
• 2022

This study highlights the accuracy of several single strut models to predict the global response of infilled reinforced concrete (R/C) frames. To this aim, six experimental tests are selected to calibrate the numerical modeling. The width of the diagonal strut is calculated using several macro models from the literature. The mechanical properties of the diagonal strut are determined by using two methods: (a) by subtracting the bare frame response from that of the infilled frame, and (b) by calculating the axial strength in the diagonal direction. A combination between the different width and the axial force models is carried out to study the effects of each parameter on global response. Non-linear pushover analyses are conducted using SAP2000. The results indicate the accuracy of the macro-modeling approach to predict the behavior of the infilled frames.

• International Journal of Precision Engineering and Manufacturing
• /
• 제8권2호
• /
• pp.85-89
• /
• 2007

Linear ball guideways have been used recently in precision or ultra-precision positioning devices. However, when the inner balls begin to roll or the moving direction reverses, these guideways are subject to rolling friction or nonlinear spring behavior. An ultra-precision device with a linear motor, referred to as a 'tunnel actuator' (TA), has been constructed to measure these phenomena. The application of a TA is beneficial for two reasons: it mostly cancels the attractive magnetic force between the stator and mover (armature), and its magnetic flux leakage is very low. The influence of the nonlinear spring behavior in ball guideways was investigated in this study using the pure driving force from a TA. The equilibrium between the driving force from the TA and the nonlinear spring force provided great accuracy for a positioning stage using a linear ball guideway.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제9권5호
• /
• pp.1963-1978
• /
• 2015

With the advancement of mobile web environments, identification and analysis of the user behavior play a significant role and remains a challenging task to implement with variations observed in the model. This paper presents an efficient method for mining optimized user behavior prediction model using genetic algorithm on mobile web structure. The framework of optimized user behavior prediction model integrates the temporary and permanent register information and is stored immediately in the form of integrated logs which have higher precision and minimize the time for determining user behavior. Then by applying the temporal characteristics, suitable time interval table is obtained by segmenting the logs. The suitable time interval table that split the huge data logs is obtained using genetic algorithm. Existing cluster based temporal mobile sequential arrangement provide efficiency without bringing down the accuracy but compromise precision during the prediction of user behavior. To efficiently discover the mobile users' behavior, prediction model is associated with region and requested services, a method called optimized user behavior Prediction Model using Genetic Algorithm (PM-GA) on mobile web structure is introduced. This paper also provides a technique called MAA during the increase in the number of models related to the region and requested services are observed. Based on our analysis, we content that PM-GA provides improved performance in terms of precision, number of mobile models generated, execution time and increasing the prediction accuracy. Experiments are conducted with different parameter on real dataset in mobile web environment. Analytical and empirical result offers an efficient and effective mining and prediction of user behavior prediction model on mobile web structure.

• 한국멀티미디어학회논문지
• /
• 제21권8호
• /
• pp.982-990
• /
• 2018

In recent years, many wearable devices and mobile apps related to life care have been developed, and a service for measuring the movement during walking and showing the amount of exercise has been provided. However, they do not measure walking in detail, so there may be errors in the total calorie consumption. If the user's behavior is measured by a multi-axis sensor and learned by a machine learning algorithm to recognize the kind of behavior, the detailed operation of walking can be autonomously distinguished and the total calorie consumption can be calculated more than the conventional method. In order to verify this, we measured activities and created a model using a machine learning algorithm. As a result of the comparison experiment, it was confirmed that the average accuracy was 12.5% or more higher than that of the conventional method. Also, in the measurement of the momentum, the calorie consumption accuracy is more than 49.53% than that of the conventional method. If the activity recognition is performed using the wearable device and the machine learning algorithm, the accuracy can be improved and the energy consumption calculation accuracy can be improved.

• Earthquakes and Structures
• /
• 제14권6호
• /
• pp.525-535
• /
• 2018

This study presents a new beam-column model comprising material nonlinearity and joint flexibility to predict the nonlinear response of reinforced concrete structures. The nonlinear behavior of connections has an outstanding role on the nonlinear response of reinforced concrete structures. In presented research, the joint flexibility is considered applying a rotational spring at each end of the member. To derive the moment-rotation behavior of beam-column connections, the relative rotations produced by the relative slip of flexural reinforcement in the joint and the flexural cracking of the beam end are taken into consideration. Furthermore, the considered spread plasticity model, unlike the previous models that have been developed based on the linear moment distribution subjected to lateral loads includes both lateral and gravity load effects, simultaneously. To confirm the accuracy of the proposed methodology, a simply-supported test beam and three reinforced concrete frames are considered. Pushover and nonlinear dynamic analysis of three numerical examples are performed. In these examples the nonlinear behavior of connections and the material nonlinearity using the proposed methodology and also linear flexibility model with different number of elements for each member and fiber based distributed plasticity model with different number of integration points are simulated. Comparing the results of the proposed methodology with those of the aforementioned models describes that suggested model that only uses one element for each member can appropriately estimate the nonlinear behavior of reinforced concrete structures.

• 한국강구조학회 논문집
• /
• 제17권5호통권78호
• /
• pp.593-604
• /
• 2005

본 논문에서는 개단면 리브를 갖는 보강판에 대하여 직교이방성 강성비를 매개변수로 하여, 집중하중이 작용하는 경우 발생하는 보강판의 국부 처짐 및 국부 모멘트에 대한 연구를 수행하였다. 보강판의 국부 거동을 파악하기 위하여 리브 사이에 위치한 판의 중앙점에 하중이 작용하는 경우를 고려하였으며, 전체적인 거동을 산정하기 위하여, 판의 중앙에 위치한 리브 위에 하중이 작용하는 경우를 해석하였다. 여러 가지 보강판에 대한 국부 거동을 분석한 결과, 국부 모멘트의 증가 비율은 리브 간격과 상관없이 리브 크기에 따라 일정함을 알 수 있었으며, 또한, 보강판의 전체 처짐에 대한 국부 처짐의 비율은 리브 간격과 강성비의 함수로 표현할 수 있음을 알 수 있었다. 이러한 관계식을 예제에 적용한 결과, 실제 국부 처짐이 발생하는 경우와 상당한 정확도를 나타내었으며, 또한 직교이방성 판 해석에 적용한 결과, 상당한 정확도의 증가를 나타내었다. 따라서, 본 연구에서 제안한 함수식을 이용하면, 개단면 리브를 갖는 보강판의 전체 거동으로부터 간편하게 국부 거동 결과를 예측할 수 있을 것으로 판단된다.

• Geomechanics and Engineering
• /
• 제13권5호
• /
• pp.743-756
• /
• 2017

Laboratory investigation reveals that rockfills exhibit significant stress-path-dependent behavior during shearing, therefore realistic prediction of deformation of rockfill structures requires suitable constitutive models to properly reproduce such behavior. This paper evaluates the capability of a strain hardening model proposed by the authors, by comparing simulation results with large-scale triaxial stress-path test results. Despite of its simplicity, the model can simulate essential aspects of the shear behavior of rockfills, including the non-linear stress-strain relationship, the stress-dependence of the stiffness, the non-linear strength behavior, and the shearing contraction and dilatancy. More importantly, the model is shown to predict the markedly different stress-strain and volumetric behavior along various loading paths with fair accuracy. All parameters required for the model can be derived entirely from the results of conventional large triaxial tests with constant confining pressures.

• 한국멀티미디어학회논문지
• /
• 제25권6호
• /
• pp.807-818
• /
• 2022

In order to further improve the accuracy and time efficiency of behavior recognition in intelligent monitoring scenarios, a human behavior recognition algorithm based on YOLO combined with LSTM and CNN is proposed. Using the real-time nature of YOLO target detection, firstly, the specific behavior in the surveillance video is detected in real time, and the depth feature extraction is performed after obtaining the target size, location and other information; Then, remove noise data from irrelevant areas in the image; Finally, combined with LSTM modeling and processing time series, the final behavior discrimination is made for the behavior action sequence in the surveillance video. Experiments in the MSR and KTH datasets show that the average recognition rate of each behavior reaches 98.42% and 96.6%, and the average recognition speed reaches 210ms and 220ms. The method in this paper has a good effect on the intelligence behavior recognition.

• 한국암반공학회:학술대회논문집
• /
• 한국암반공학회 2008년도 국제학술회의
• /
• pp.43-51
• /
• 2008

Currently an increasing number of urban tunnels with small overburden are excavated according to the principle of the New Austrian Tunneling Method (NATM). For rational management of tunnels from planning to construction and maintenance stages, prediction, control and monitoring of displacements of and around the tunnel have to be performed with high accuracy. Computational method tools, such as finite element method, have been and are indispensable tool for tunnel engineers for many years. It is, however, a commonly acknowledged fact that determination of input parameters, especially material properties exhibiting nonlinear stress-strain relationship, is not an easy task even for an experienced engineer. Use and application of the acquired tunnel information is important for prediction accuracy and improvement of tunnel behavior on construction. Artificial Neural Network (ANN) model is a form of artificial intelligence that attempts to mimic behavior of human brain and nervous system. The main objective of this paper is to perform the deformation analysis in NATM tunnel by means of numerical simulation and artificial neural network (ANN) with field database. Developed ANN model can achieve a high level of prediction accuracy.