• 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 Society for e-Business Studies
• /
• v.21 no.1
• /
• pp.147-163
• /
• 2016

Gender information of a smart device user is essential to provide personalized services, and multi-modal data obtained from the device is useful for predicting the gender of the user. However, the method for utilizing each of the multi-modal data for gender prediction differs according to the characteristics of the data. Therefore, in this study, an ensemble method for predicting the gender of a smart device user by using three classifiers that have text, application, and acceleration data as inputs, respectively, is proposed. To alleviate privacy issues that occur when text data generated in a smart device are sent outside, a classification method which scans smart device text data only on the device and classifies the gender of the user by matching text data with predefined sets of word. An application based classifier assigns gender labels to executed applications and predicts gender of the user by comparing the label ratio. Acceleration data is used with Support Vector Machine to classify user gender. The proposed method was evaluated by using the actual smart device log data collected from an Android application. The experimental results showed that the proposed method outperformed the compared methods.

• The Journal of Society for e-Business Studies
• /
• v.13 no.1
• /
• pp.21-32
• /
• 2008

RFID systems provide technologies of automatic object identification through wireless communications in invisible ranges and adaptability against various circumstances. These advantages make RFID systems to be applied in various fields of industries and individual life. However, it is difficult to use tags with distinction as tags are increasingly used in life because a tag usually stores only one object identifier in common RFID applications. In addition, RFID systems often make serious violation of privacy caused by various attacks because of their weakness of radio frequency communication. Therefore, information sharing methods among applications are necessary for expansive development of RFID systems. In this paper, we propose efficient RFID scheme. At first, we design a new RFID tag structure which supports many object identifiers of different applications in a tag and allows those applications to access them simultaneously. Secondly, we propose an authentication protocol to support the proposed tag structure. The proposed protocol is designed by considering of robustness against various attacks in low cost RFID systems. Especially, the proposed protocol is focused on efficiency of authentication procedure by considering security levels of applications. In the proposed protocol, each application goes through one of different authentication procedures according to their security levels. Finally, we prove efficiency of th proposed scheme compared with the other schemes through experiments and evaluation.

• The Journal of Society for e-Business Studies
• /
• v.22 no.1
• /
• pp.89-106
• /
• 2017

In advanced mobile devices environment, the market share of mobile application has been increased. Among various mobile services, Location-based Service (LBS) is an important feature to increase user motivation related to purchase intention on mobile. However, individual privacy has also increased as an important problem for invasion of privacy and information leakage while too many LBS based applications (App) rapidly launched in the App market. In this study, we focused on perceived values of LBS App users who use Apps related to recommending best restaurants in China and South Korea. The purpose of this study is to identify important factors for perceived value when users provide personal information for LBS service provider. The result of this study is follows: perceived value can increase while LBS customers can more control self-information and information useability. Also information ability of users affected perceived values for LBS Apps. Also users' app user ability and perceived value were effects on privacy revenue. In addtion, perceived weakness of users and perceived value increased privacy threat.

• Journal of Korean Medicine for Obesity Research
• /
• v.17 no.1
• /
• pp.37-45
• /
• 2017

Recently the global epidemic problem of obesity has stimulated intense interest in the study of physiological mechanisms using animal models as a way to gain crucial data required for translation to human studies. Panax ginseng has been reported to have anti-obesity or antidiabetic effects in many animal studies; however, there have been few studies investigating human obesity. Herein, we will assess and examine the evidence supporting the anti-obesity effect of Panax ginseng in animal models with respect to anthropometric and metabolic outcomes. We will include controlled, comparative studies assessing the effect of Panax ginseng in preclinical studies of obesity. Panax ginseng will be administered during or following the induction of experimental obesity. The primary outcome measure will be anthropometric assessment and the secondary outcome measures will include adipose tissue weight, total amount of food consumed and metabolic parameters. We will search MEDLINE, Embase, PubMed, Web of Science, and Scopus without language, publication date, or other restrictions. Ethical approval will not be necessary as the data collected in this study will not be individual patient data, consequently there will be no concerns about violations of privacy. After finishing the whole procedure, the results will be disseminated by publication in a peer-reviewed journal or presented at a relevant conference. This protocol has been registered on the Collaborative Approach to Meta-Analysis and Review of Animal Data from Experimental Studies (CAMARADES) website (http://www.camarades.info).

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.21 no.10
• /
• pp.602-608
• /
• 2020

Development of Internet technology and the spread of various smart devices provide a convenient computing environment for people, which is becoming common thanks to the Internet of Things (IoT). However, attacks by hackers have caused various problems, such as leaking personal information or violating privacy. In the IoT environment, various smart devices are connected, and network attacks that are used in the PC environment are occurring frequently in the IoT. In fact, security incidents such as conducting DDoS attacks by hacking IP cameras, leaking personal information, and monitoring unspecified numbers of personal files without consent are occurring. Although attacks in the existing Internet environment are PC-oriented, we can now confirm that smart devices such as IP cameras and tablets can be targets of network attacks. Through performance evaluation, the proposed protocol shows 11% more energy efficiency on servers than RSA, eight times greater energy efficiency on clients than Kerberos, and increased efficiency as the number of devices increases. In addition, it is possible to respond to a variety of security threats that might occur against the network. It is expected that efficient operations will be possible if the proposed protocol is applied to the IoT environment.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.15 no.3
• /
• pp.1740-1748
• /
• 2014

In this paper, we propose an RBAC based personalized health care service platform in order to provide smart management of personal health record using smart devices. It helps to guide healthful service and provide useful information according to one's individual health record. Personalized health care services platform supports a healthy lifestyle by measuring personal health information in a hospital clinical, imaging, and drug data, as well as that can be obtained from smart devices. Everyone can enter his health related data in everyday life such as food, sleeping time, mood, movement and exercise so that one can manage his personal health information of modern smart features. In addition, if necessary, personal health information can be provided to the hospital information system and staff with the consent of the individual. It can be contributed to simplify the complex process for remote medical. The proposed platform, which applies role based access control model to protect security and privacy, supports a smart health care services for users by providing personalized health care services through the smart applications.

• The Journal of the Korea Contents Association
• /
• v.20 no.1
• /
• pp.356-363
• /
• 2020

As a becoming era of Internet-of-Things, various devices are connected via wire or wirless networks. Although every day life is more convenient, security problems are also increasing such as privacy, information leak, denial of services. Since ECC, a kind of public key cryptosystem, has a smaller key size compared to RSA, it is widely used for environmentally constrained devices. The key of ECC in constrained devices can be exposed to power analysis attacks during scalar multiplication operation. In this paper, a key-randomization method is suggested for scalar multiplication on SECG parameters. It is against differential power analysis and has operational efficiency. In order to increase of operational efficiency, the proposed method uses the property 2^lP=∓cP where the constant c is small compared to the order n of SECG parameters and n=2^l±c. The number of operation for the Coron's key-randomization scalar multiplication algorithm is 21, but the number of operation for the proposed method in this paper is (3/2)l. It has efficiency about 25% compared to the Coron's method using full random numbers.

• Korean Journal of Construction Engineering and Management
• /
• v.19 no.1
• /
• pp.21-31
• /
• 2018

The rapid increase of the elderly living alone is a critical issue in worldwide as it leads to a rapid increase of a social support costs (e.g., medical expenses) for the elderly. In early stages of dementia, the activities of daily living (ADL) including self-care tasks can be affected by abnormal patterns or behaviors and used as an evidence for the early diagnosis. However, extracting activities using non-intrusive approach is still quite challenging and the existing methods are not fully visualized to understand the behavior pattern or routine. To address these issues, this research suggests a model to extract the activities from coarse-grained data (spatio-temporal data log) and visualize the behavioral context information. Our approach shows the process of extracting and visualizing the subject's spaceactivity map presenting the context of each activity (time, room, duration, sequence, frequency). This research contributes to show a possibility of detecting subject's activities and behavioral patterns using coarse-grained data (limited to spatio-temporal information) with little infringement of personal privacy.

• Journal of the Korea Convergence Society
• /
• v.8 no.9
• /
• pp.1-7
• /
• 2017

As the network environment develops and speeds up, a lot of smart devices is developed, and a high-speed smart society can be realized while allowing people to interact with objects. As the number of things Internet has surged, a wide range of new security risks and problems have emerged for devices, platforms and operating systems, communications, and connected systems. Due to the physical characteristics of IoT devices, they are smaller in size than conventional systems, and operate with low power, low cost, and relatively low specifications. Therefore, it is difficult to apply the existing security solution used in the existing system. In addition, IoT devices are connected to the network at all times, it is important to ensure that personal privacy exposure, such as eavesdropping, data tampering, privacy breach, information leakage, unauthorized access, Significant security issues can arise, including confidentiality and threats to facilities. In this paper, we investigate cases of security threats and cases of network of IoT, analyze vulnerabilities, and suggest ways to minimize property damage by Internet of things.