• Journal of the Korean Society of Environmental Restoration Technology
• /
• v.16 no.6
• /
• pp.77-91
• /
• 2013

The researcher noted the fact that wetland users are more and more diversified while people are more conscious of their ecological importance. Wetlands tend to be very sensitive in ecological terms, and therefore, they can hardly accommodate their users' needs indefinitely. With such basic perception in mind, the purpose of this study was to survey wetland users' eco-consciousness, determine their traits, analyze the corelation between their traits and preferences of wetland amenities, and thereby, provide the data useful to planning of an effective wetland management policy. To this end, the researcher sampled nation's largest wetland, Upo Marsh located in Changnyeong for a questionnaire survey. Wetland users' eco-consciousness was measured, using Dunlap's NEP (New Ecological Paradigm) approved by many researchers. Wetland users' preferences of the wetland amenities were measured, centered around 11 amenity types observed commonly at the domestic wetlands. As a result of the survey conducted in October, 2012, a total of 228 effective samples were acquired. Wetland users' eco-consciousness was higher than normal, scoring 3.45 on the 5-point scale consisting of 5 sub-scales. In particular, users were more conscious of 'the possibility of an eco-crisis,' while being less conscious of 'ejection of exemptionalism.' As a result of classifying the users into 3 sub-groups in reference to their eco-consciousness and analyzing their preferences of amenities comparatively, significant differences were found in all 3 sub-areas. In particular, the sub-group most eco-conscious tended to prefer the learning amenities, but the least eco-conscious sub-group tended to prefer the utilities. As a result of the post-hoc test, it was found that most and normal eco-conscious sub-groups were more or less homogeneous, while the least eco-conscious sub-group was significantly different from the former 2 sub-groups in terms of eco-consciousness. As the wetland users were found to be diversified in terms of their eco-consciousness, it is necessary to plan the wetland management policies in consideration of such differences. However, it is perceived that the wetland amenities need to be built to meet the more eco-conscious users.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.