• 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.

• Journal of Broadcast Engineering
• /
• v.18 no.6
• /
• pp.895-910
• /
• 2013

Multi-screen service is a service that consumes more than one media in a number of terminals simultaneously or discriminately. This multi-screen service has become useful due to distribute of smart TV and terminals. Also, in case of hybrid broadcasting environment that is convergence of broadcasting and communication environment, it is able to provide various user experience through contents consumed by multiple screens. In hybrid broadcasting environment, scene composition technology can be used as an element technology for multi-screen service. Using scene composition technology, multiple media can be consumed complexly through the specified presentation time and space. Thus, multi-screen service based on the scene composition technology can provide spatial and temporal control and consumption of multiple media by linkage between the terminals. However, existing scene composition technologies are not able to use easily in hybrid broadcasting because of applicable environmental constraints, the difficulty in applying the various terminal and complexity. For this problems, HTML5 can be considered. HTML5 is expected to be applied in various smart terminals commonly, and provides consumption of diverse media. So, in this paper, it proposes the scene composition and multi-screen service technology based on HTML5 that is expected be used in various smart terminals providing hybrid broadcasting environment. For this, it includes the introduction in terms of HTML5 and multi-screen service, the method of providing information related with scene composition and multi-screen service through the extention of elements and attributes in HTML5, media signaling between terminals and the method of synchronization. In addition, the proposed scene composition and multi-screen service technology based on HTML5 was verified through the implementation and experiment.