• Journal of Information Technology and Architecture
• /
• v.9 no.1
• /
• pp.57-66
• /
• 2012

Recently, with a rapidly growing of the mobile content market, a variety of mobile-based applications are being launched. But mobile devices, compared to the average computer, take a lot of effort and time to get the final contents you want to use due to the restrictions such as screen size and input methods. To solve this inconvenience, a recommender system is required, which provides customized information that users prefer by filtering and forecasting the information.In this study, an tailored multi-information recommendation system utilizing a Personalized information recommendation system on smartphone is proposed. Filtering of information is to predict and recommend the information the individual would prefer to by using the user-based collaborative filtering. At this time, the degree of similarity used for the user-based collaborative filtering process is Euclidean distance method using the Pearson's correlation coefficient as weight value.As a real applying case to evaluate the performance of the recommender system, the scenarios showing the usefulness of recommendation service for the actual restaurant is shown. Through the comparison experiment the augmented reality based multi-recommendation services to the existing single recommendation service, the usefulness of the recommendation services in this study is verified.

• Journal of Information Management
• /
• v.43 no.1
• /
• pp.109-134
• /
• 2012

This study, focusing on process of online Word-of-Mouth(oWOM) adoption in applications market which is a major issue of recent mobile industry, tried to empirically analyze how main characteristics of oWOM affect trust and process of oWOM adoption. To do this, based on understanding about applications market and precedent studies on online communication and Elaboration Likelihood Model(ELM), I developed the research model and proposed seven hypotheses. The subjects were smart phone users who ever used review in mobile applications market. The study method was questionnaire survey. As a result, trust in review was suggested as prerequisite for consumers to accept on-line review in mobile applications market. And it was empirically proved that for the customers to feel trust, these are necessary - positive assessment on argument quality, vividness of delivered explanation, and neutrality of message. The theoretical implications of this study are that based on studies on oWOM, factors affecting trust in review were explored in the environment of mobile applications market with less judgement clues for decision making compared to other on-line media and then, these factors were conceptualized. From the practical view, this study suggested implication on what attributes companies or developers can strategically utilize while investigating prerequisites of oWOM adoption.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.21 no.2
• /
• pp.461-467
• /
• 2017

As the number of smart devices increases, e-book contents and services are proliferating. However, the text based e-book is difficult for a hearing-impairment person to understand. In this paper, we developed an android based application in which we can choose an e-book text file and each sentence is translated to sign-language elements which are shown in videos that are retrieved from the sign-language contents server. We used the korean sentence to sign-language translation algorithm based on the morpheme analysis. The proposed translation algorithm consists of 3 stages. Firstly, some elements in a sentence are removed for typical sign-language usages. Secondly, the tense of the sentence and the expression alteration are applied. Finally, the honorific forms are considered and word positions in the sentence are revised. We also proposed a new method to evaluate the performance of the translation algorithm and demonstrated the superiority of the algorithm through the translation results of 100 reference sentences.

• 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.

• The Journal of the Korea Contents Association
• /
• v.11 no.9
• /
• pp.85-95
• /
• 2011

Recently, sudden interests of mobile cloud computing as well as conventional internet environment are rapidly increased as cloud computing spread out in our web society. Mobile devices including smart phone are rapidly changing in a wholesale way that covers hardwares, applications, and services. However, the Internet access using mobile device is not quite smooth in this local mobile internet environment which suffers from lack of understanding and observance of Web Standards. Although most of domestic web sites are developed focusing on various functions and eye-catching designs, this should became one of the main factors that make the usability and accessability decrease when accessing web with smart phones or table PCs. Therefore, this paper suggested a web interface that considered usability and accessability under mobile cloud environment and we tried to prove it via usability test. It could be found that there was an improvement of usability of interface of the main page that has been optimized to the mobile device environment suggested from the previous research we present, but this paper aimed to prove a usability improvement of total website as a whole by performing the usability test on the entire website. Selecting a special website optimized for mobile cloud computing, we prove an improvement of usability and accessibility. Therefore, we offer a guideline about user interface design applications to developers or companies who want to construct mobile website.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.11
• /
• pp.157-163
• /
• 2022

In this paper, we propose to develop a Bluetooth Health Device Profile (HDP)-based smartphone system to utilize it for early detection of urinary tracts diseases that occur a lot in cats. Therefore, based on Bluetooth HDP, we developed a device and mobile application system (Mycatner®) that can monitor cat activity, toilet usage, urinary disease, and health status, and evaluated its availability to monitor cat health status. The specific feature of this system is that it can measure the number of cat urination frequencies to identify abnormal conditions suspected of urinary tract diseases early, and second, it can be tested with urine test paper and shared with animal hospitals, reducing time and cost. As a result, it is evaluated that the developed device capable of wireless monitoring the urinary system health status of cats is the first in our knowledge.

• Journal of the Institute of Electronics and Information Engineers
• /
• v.54 no.7
• /
• pp.93-102
• /
• 2017

Recently increasing usage of smartphones makes the Internet of Things (IoT) a leading technology that can collect and share data through sensor networks and wireless communication such as low-power Bluetooth (BLE). BLE-based application can provide operators more precise information on Automatic Door system by remotely diagnosing the system faults through wireless sensor networks and sensors around the Automatic Door. In this paper, a smart device with extended BLE module is implemented which can monitor and Control the system states and faults remotely without on-site diagnostic. while maintaining system integrity so that increase efficiency of time and costs for system management. We can use the results of this research as a basis in evaluating reliability of data between devices, extending communication module in Controller of obsolete Door systems, and establishing centralized monitoring systems in near future with multi-channel Door Controls.

• Journal of Digital Contents Society
• /
• v.18 no.4
• /
• pp.761-768
• /
• 2017

As the loss prevention system using bluetooth has a short communication range, it has a problem which its location is not known if it is strayed out of a certain distance. To overcome shortcoming of such an existing loss prevention system, this paper proposes a GPS-based wireless loss prevention system without communication fee using the LoRa Communication with a long distance. The proposed system performs a remote control application on the smart-phone and then is able to get a long-distance GPS coordinates about the location of the loss prevention system on the google map. For performance evaluation of the implemented proposed system, the experiments for transmitting and receiving data are done in open terrain, indoor and outdoor areas and the experiment results identified the superiority of the proposed system in the long-distance.

• Journal of Digital Convergence
• /
• v.15 no.2
• /
• pp.347-353
• /
• 2017

The aim of this paper is to improve the usability of Mobile Maps by allowing more people to use. To figure out better UX/UI, I evaluated usability for Mobile Applications from various materials such as literatures and blogs for qualitative methods and interviews and questionnaires about satisfaction of Naver and Daum for quantitative methods. So, We know that a map app is important and it is affected by force and profile on the portal site than its own features, because, not often in everyday life. Even though people do not use Mobile Map Applications frequently, we need to improve usability to make anybody use them easily by minimizing depth and button designs.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.11 no.2
• /
• pp.48-56
• /
• 2012

One kind of crowdsourcing techniques which allow drivers to collect and provide traffic information using smartphones and applications is being introduced to ITS system as well. The introduction of crowdsourcing techniques requires changes in the existing ITS based on Insourcing which provide traffic information generated by detectors through VMS. ITS Information have had two problems, one is the high cost and the other is an interrupted service. Experts expect crowdsourcing technique which is created SNS, will overcome problems of ITS. But, there are not many examples and research results. Crowdsourcing technique was utilized in Jeju ATMS project to install ITS on the coastal round roads around Jeju since ITS to install point detectors turned out to be non-economic method in case of the coastal round roads with low traffic volume. However, there existed links in which traffic information cannot be generated as there were no smartphone users (crowds) even in the cost-effective crowdsourcing techniques, which indicates the fact that the crowdsourcing method is suitable for urban roads with many smartphone users, but not for local minor roads. On the contrary, insourcing-based ITS is considered to be non-economic method in applying to all roads in the city, but it can be effectively utilized in the local minor roads. Accordingly, Inter-sourcing based ITS operating system in which insourcing is connected with crowdsourcing was suggested in this study.