• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.11 no.1
• /
• pp.78-101
• /
• 2017

High-quality industrial control is critical to ensuring production quality, reducing production costs, improving management levels and stabilizing equipment and long-term operations. WiFi-based Long Distance (WiLD) networks have been used as remote industrial control networks. Real-time performance is essential to industrial control. However, the original mechanism of WiLD networks does not minimize end-to-end delay and restricts improvement of real-time performance. In this paper, we propose two algorithms to obtain the transmitting/receiving phase cycle length for each node such that real time constraints can be satisfied and phase switching overhead can be minimized. The first algorithm is based on the branch and bound method, which identifies an optimal solution. The second is a fast heuristic algorithm. The experimental results show that the execution time of the algorithm based on branch and bound is less than that of the heuristic algorithm when the network is complex and that the performance of the heuristic algorithm is close to the optimal solution.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2011.10a
• /
• pp.255-258
• /
• 2011

Wi-Fi is a rapidly spreading communications network with Smart phone's publication, the technology has become Ubiquitous-based core network which is connected to personal computers, laptops, and tablet PC. Wi-Fi can send currently a variety of data standard due to developed wireless LAN communications network. One of Wi-Fi standard protocols, which is IEEE 802.11n, use 2.4GHz and 5GHz band. 2.4GHz band is used for 802.11b/g protocol because wavelength is long, diffraction and receiving distance is enough to connect other device. 5GHz band has more available channels to use than 2.4GHz band, so there is no frequency interference of other wireless device such as Bluetooth, RFID. Moreover, there is low interference between channels due to small users in each bandwidth level. In the thesis, we are going to analyze 802.11a/b/g protocol which has used since the beginning of Wi-Fi protocol and 802.11n protocol which is used lately. Furthermore, we look into development and direction for standardization of the next generation wireless LANs which are 802.11ac and 802.11ad. In addition, we will consider for the security, vulnerabilities and its countermeasure in Wireless LAN.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.1
• /
• pp.53-60
• /
• 2017

This paper is to design and implement the drone that supports a wideband multimedia communication and a long-range to save people in maritime. The drone is an Unnamed Aerial Vehicle (UAV) that is controlled by a radio wave not by people boarding the machine. We use the drone to respond quickly to the boating accident. To develop a smart drone for the high speed seamless video streaming in a long-range maritime, a necessary techniques are hardware design techniques that design structure of a drone, controlling techniques that operate a drone and communication techniques that control a drone in a long distance. In this paper, the limitations and techniques to design and implement the structure of drone supporting wideband multimedia communication for long-range maritime are explained. By expanding this communication drone network, it is aimed at improving utility of a drone.

• 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.