• International journal of advanced smart convergence
• /
• v.6 no.3
• /
• pp.29-37
• /
• 2017

The current behavior recognition system don't match data formats between sensor data measured by user's sensor module or device. Therefore, it is necessary to support data processing, sharing and collaboration services between users and behavior recognition system in order to process sensor data of a large capacity, which is another formats. It is also necessary for real time interaction with users and behavior recognition system. To solve this problem, we propose fog cloud based behavior recognition system for human body sensor data processing. Fog cloud based behavior recognition system solve data standard formats in DbaaS (Database as a System) cloud by servicing fog cloud to solve heterogeneity of sensor data measured in user's sensor module or device. In addition, by placing fog cloud between users and cloud, proximity between users and servers is increased, allowing for real time interaction. Based on this, we propose behavior recognition system for user's behavior recognition and service to observers in collaborative environment. Based on the proposed system, it solves the problem of servers overload due to large sensor data and the inability of real time interaction due to non-proximity between users and servers. This shows the process of delivering behavior recognition services that are consistent and capable of real time interaction.

• Journal of the Korean Institute of Landscape Architecture
• /
• v.25 no.4
• /
• pp.18-29
• /
• 1998

This study was carried out to test the theory of planned behavior in recreational choices behavior. Lotte World was chosen as study area, and college students were selected by nonprobability sampling for two waves of data collection. The first wave of data were collected one weeks into the spring semester : intention, attitude, subjective norm, and perceived behavioral control were measured. To collect the data of the second wave, the same resondents were asked their behavior, one week data of the second wave, the same respondents were asked their behavior , one week prior to the final examination : whether they visited the Lotte World or not. Polychoric correlation among variables were calculated by the PRELIS because behavior was nominal variable. Then, weighted least square method was utilized to calibrate structural equation model by the LISREL version 7.2. Structural link effect on intention among three determinants : the direct effect on intention was 0.421 and the indirect effect via intention on behavior was 0.145, respectively. However, its effect on behavior was insignificant because actual control over 'visiting of Lotte World' was relatively high. A few comments were sugested on data collection, and inclusion of new variables was discussed for the sufficiency f the theory of planned behavior.

• Journal of Information Processing Systems
• /
• v.20 no.2
• /
• pp.159-172
• /
• 2024

The number of healthcare products available for pets has increased in recent times, which has prompted active research into wearable devices for pets. However, the data collected through such devices are limited by outliers and missing values owing to the anomalous and irregular characteristics of pets. Hence, we propose pet behavior recognition based on a hybrid one-dimensional convolutional neural network (CNN) and long short- term memory (LSTM) model using pet wearable devices. An Arduino-based pet wearable device was first fabricated to collect data for behavior recognition, where gyroscope and accelerometer values were collected using the device. Then, data augmentation was performed after replacing any missing values and outliers via preprocessing. At this time, the behaviors were classified into five types. To prevent bias from specific actions in the data augmentation, the number of datasets was compared and balanced, and CNN-LSTM-based deep learning was performed. The five subdivided behaviors and overall performance were then evaluated, and the overall accuracy of behavior recognition was found to be about 88.76%.

• Steel and Composite Structures
• /
• v.36 no.5
• /
• pp.521-531
• /
• 2020

The behavior variation of concrete dam is investigated, based on a new method for analyzing the data model of concrete dam in service process for the limitation of wavelet transform for solving concrete dam service process model. The study takes into account the time and position of behavior change during the process of concrete dam service. There is no dependence on the effect quantity for overcoming the shortcomings of the traditional identification method. The panel data model is firstly proposed for analyzing the behavior change of composite concrete dam. The change-point theory is used to identify whether the behavior of concrete dams changes during service. The phase space reconstruction technique is used to reconstruct the phase plane of the trend effect component. The time dimension method is used to solve the construction of multi-transformation model of composite panel data. An existing 76.3-m-high dam is used to investigate some key issues on the behavior change. Emphasis is placed on conversion time and location for three time periods consistent with the practical analysis report for evaluating the validity of the analysis method of the behavior variation of concrete dams presented in this paper.

• The Journal of Industrial Distribution & Business
• /
• v.13 no.12
• /
• pp.43-57
• /
• 2022

Purpose: Despite the numerous studies on factors impacting pro-environmental behavior, actual studies analyzing a relationship between pro-environmental behavior and eco-friendly channels (e.g., local food market and farmers' market channel) usage behavior (visit and purchasing frequency) are rare. This study investigated the relationship between consumers with positive pro-environmental behavior and eco-friendly channels usage behavior. Research design, data and methodology: The study investigated the relationship between pro-environmental behavior and eco-friendly channels (local food markets and farmers market) visit behavior by analyzing data from the Korea Consumer Agency's 2021 Korea Consumption Life Index, with a focus on the pro-environmental index. Relationship between pro-environmental behavior and whether eco-friendly channels visit or not were analyzed. Demographic variables also influence eco-friendly oriented channels visit. Data analysis used hierarchical regression, firstly inputted pro-environmental behavior, and then demographic variables inputted, and finally pro-environmental behavior and demographics interactions as moderating variables inputted. Results: Consumer's with positive behavior towards pro-environment were indeed more likely to choose local food market and farmers' market compared to other consumers. Demographic variables also effect local food market visit. Some demographic variables moderate this relationship. The results, however, differed by channel type. Conclusions: Pro-environmental behavior is closely related to eco-friendly channels (local food market and farmers; market) visit.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.6
• /
• pp.3055-3073
• /
• 2019

In this paper, a new user identification method is presented using real environmental human-computer-interaction (HCI) behavior data to improve method usability. User behavior data in this paper are collected continuously without setting experimental scenes such as text length, action number, etc. To illustrate the characteristics of real environmental HCI data, probability density distribution and performance of keyboard and mouse data are analyzed through the random sampling method and Support Vector Machine(SVM) algorithm. Based on the analysis of HCI behavior data in a real environment, the Multiple Kernel Learning (MKL) method is first used for user HCI behavior identification due to the heterogeneity of keyboard and mouse data. All possible kernel methods are compared to determine the MKL algorithm's parameters to ensure the robustness of the algorithm. Data analysis results show that keyboard data have a narrower range of probability density distribution than mouse data. Keyboard data have better performance with a 1-min time window, while that of mouse data is achieved with a 10-min time window. Finally, experiments using the MKL algorithm with three global polynomial kernels and ten local Gaussian kernels achieve a user identification accuracy of 83.03% in a real environmental HCI dataset, which demonstrates that the proposed method achieves an encouraging performance.

• The Journal of Society for e-Business Studies
• /
• v.4 no.1
• /
• pp.21-36
• /
• 1999

Using user monitoring techniques on web, marketing decision makers in cyber shopping malls can gather customer behavior data as well as sales transaction data and customer profiles. In this paper, we present a marketing rule extraction technique for customer behavior analysis in cyber shopping malls, The technique is an application of market basket analysis which is a representative data mining technique for extracting association rules. The market basket analysis technique is applied on a customer behavior log table, which provide association rules about web pages in a cyber shopping mall. The extracted association rules can be used for mall layout design, product packaging, web page link design, and product recommendation. A prototype cyber shopping mall with customer monitoring features and a customer behavior analysis algorithm is implemented using Java Web Server, Servlet, JDBC(Java Database Connectivity), and relational database on windows NT.

• ETRI Journal
• /
• v.44 no.3
• /
• pp.426-437
• /
• 2022

To understand the multilateral characteristics of human behavior and physiological markers related to physical, emotional, and environmental states, extensive lifelog data collection in a real-world environment is essential. Here, we propose a data collection method using multimodal mobile sensing and present a long-term dataset from 22 subjects and 616 days of experimental sessions. The dataset contains over 10 000 hours of data, including physiological, data such as photoplethysmography, electrodermal activity, and skin temperature in addition to the multivariate behavioral data. Furthermore, it consists of 10 372 user labels with emotional states and 590 days of sleep quality data. To demonstrate feasibility, human activity recognition was applied on the sensor data using a convolutional neural network-based deep learning model with 92.78% recognition accuracy. From the activity recognition result, we extracted the daily behavior pattern and discovered five representative models by applying spectral clustering. This demonstrates that the dataset contributed toward understanding human behavior using multimodal data accumulated throughout daily lives under natural conditions.

• Research in Community and Public Health Nursing
• /
• v.30 no.4
• /
• pp.414-425
• /
• 2019

Purpose: The purpose of this study was to examine the effects of psychosocial wellbeing status and self efficacy on health-promoting behavior of nursing students, and to explore the experiences related to health-promoting behavior. Methods: For this study, an explanatory sequential mixed method design approach was used with survey data collected from 148 nursing students. In addition, qualitative data for exploration of health-promoting behavior experience were collected from three focus-group interviews of 17 participants. Quantitative data were analyzed with SPSS/WIN 25.0 and qualitative data were analyzed by making contents analysis with Nvivo 12.0. Results: The results showed that psychosocial wellbeing status, self efficacy, grade, and regularity meal explained 43.0% of the variance in health-promoting behavior. And seven themes from the collected significant statements about experience of health-promoting behavior included the daily life going on without delay; changes in body which is felt; recognizing the necessity of health care; making efforts to increase physical activities; revising eating habit; looking for the way to relieve stress; and attempting to divert my thoughts. Conclusion: Based on the results of this study, it is necessary to develop and verify health program in order to improve nursing students' health-promoting behavior. And university authorities and government should make an effort to improve nursing students' health-promoting behavior.

• Journal of Family Relations
• /
• v.23 no.2
• /
• pp.3-28
• /
• 2018

Objectives: The study examined the mediated role of family functioning in the relation between fathers' and mothers' depression and drinking behaviors, and children's internalizing/externalizing problems and peer-play behavior. Methods: The study utilized data from the Panel Study on Korean Children(PSKC), namely Wave 5 data(N=1,703) for parental depression and drinking behavior, Wave 6 data(N=1,662) for family functioning, and Wave 7 data(N=1,620) for children's internalizing/externalizing problems and peer-play behavior. Results: Mothers' perceived family functioning mediated the relation between parental depression and boys' internalizing/externalizing problems. Second, fathers' perceived family functioning mediated the relation between parental depression and children's peer-play behavior. Third, only when both parents engaged in an above-average level of drinking behavior, did father perceive that their family functioning was low. Conclusions: This study showed the mediated effect of family functioning in the influence of parental depression and drinking behavior on children's developmental outcomes. The study ditermined that fathers and mothers played different roles in children's development, and found different mechanisms related to parental depression and their drinking behavior.