• Journal of the Korean Institute of Intelligent Systems
• /
• v.18 no.2
• /
• pp.187-192
• /
• 2008

The Intelligent Space(ISpace) provides challenging research fields for surveillance, human-computer interfacing, networked camera conferencing, industrial monitoring or service and training applications. ISpace is the space where many intelligent devices, such as computers and sensors, are distributed. According to the cooperation of many intelligent devices, the environment, it is very important that the system knows the location information to offer the useful services. In order to achieve these goals, we present a method for representing, tracking and human Jollowing by fusing distributed multiple vision systems in ISpace, with application to pedestrian tracking in a crowd. This paper describes appearance based unknown object tracking with the distributed vision system in intelligent space. First, we discuss how object color information is obtained and how the color appearance based model is constructed from this data. Then, we discuss the global color model based on the local color information. The process of learning within global model and the experimental results are also presented.

• KIPS Transactions on Software and Data Engineering
• /
• v.3 no.2
• /
• pp.81-86
• /
• 2014

In this paper, we present an effective sound classification system for recognizing the real-time context of a smartphone user. Our system avoids unnecessary consumption of limited computational resource by filtering both silence and white noise out of input sound data in the pre-processing step. It also improves the classification performance on low energy-level sounds by amplifying them as pre-processing. Moreover, for efficient learning and application of HMM classification models, our system executes the dimension reduction and discretization on the feature vectors through k-means clustering. We collected a large amount of 8 different type sound data from daily life in a university research building and then conducted experiments using them. Through these experiments, our system showed high classification performance.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.25 no.5
• /
• pp.628-636
• /
• 2021

This paper contains the implementation and performance evaluation results of a system that collects environmental data at the time when the wild animal intrusion occurred at farms and then predicts future wild animal intrusions through a machine learning-based Vector Autoregression(VAR) model. To collect the data for intrusion prediction, an IoT-based hardware prototype was developed, which was installed on a small farm located near the school and simulated over a long period to generate intrusion events. The intrusion prediction service based on the implemented VAR model provides the date and time when intrusion is likely to occur over the next 30 days. In addition, the proposed system includes the function of providing real-time notifications to the farmers mobile device when wild animals intrusion occurs in the farm, and performance evaluation was conducted to confirm that the average response time was 7.89 seconds.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.18 no.5
• /
• pp.927-934
• /
• 2023

With the recent growth of the companion animal market, various social issues related to companion animals have also come to the forefront. Notable problems include incidents of dog bites, the challenge of managing abandoned companion animals, euthanasia, animal abuse, and more. As potential solutions, a variety of training programs such as companion animal-focused broadcasts and educational apps are being offered. However, these options might not be very effective for novice caretakers who are uncertain about what to prioritize in training. While training apps that are relatively easy to access have been widely distributed, apps that allow users to directly engage in training and learn through hands-on experience are still insufficient. In this paper, we propose a more efficient AR-based mobile app for companion animal training, utilizing the Unity engine. The results of usability evaluations indicated increased user engagement due to the inclusion of elements that were previously absent. Moreover, training immersion was enhanced, leading to improved learning outcomes. With further development and subsequent verification and production, we anticipate that this app could become an effective training tool for novice caretakers planning to adopt companion animals, as well as for experienced caretakers.

• Information Systems Review
• /
• v.22 no.3
• /
• pp.15-30
• /
• 2020

In the real estate industry, the latest changes in the Fourth Industrial Revolution, such as big data analytics, machine learning, and VR (virtual reality), combine to bring about industry change. Proptech is a new term combining properties and technology. This study aims to derive and analyze from a comprehensive perspective the quality factors (systems, services, interfaces, information) for mobile real estate brokerage services that are well known and used in the domestic market. The surveys in this study were conducted online and offline and a total of 161 samples were used for statistical analysis. As a result, all hypotheses were approved to except system quality and service quality. The results show that the domestic proptech companies who are mostly focused on real estate brokerage services, peer-to-peer lending, advertising platforms and apartments need to grow in various fields of proptech business of other countries including Europe, USA and China.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.12 no.1
• /
• pp.454-475
• /
• 2018

This paper presents a novel Android malware classification model planned to classify and categorize Android malicious code at Drebin dataset. The amount of malicious mobile application targeting Android based smartphones has increased rapidly. In this paper, Restricted Boltzmann Machine and Deep Belief Network are used to classify malware into families of Android application. A texture-fingerprint based approach is proposed to extract or detect the feature of malware content. A malware has a unique "image texture" in feature spatial relations. The method uses information on texture image extracted from malicious or benign code, which are mapped to uncompressed gray-scale according to the texture image-based approach. By studying and extracting the implicit features of the API call from a large number of training samples, we get the original dynamic activity features sets. In order to improve the accuracy of classification algorithm on the features selection, on the basis of which, it combines the implicit features of the texture image and API call in malicious code, to train Restricted Boltzmann Machine and Back Propagation. In an evaluation with different malware and benign samples, the experimental results suggest that the usability of this method---using Deep Belief Network to classify Android malware by their texture images and API calls, it detects more than 94% of the malware with few false alarms. Which is higher than shallow machine learning algorithm clearly.

• The Journal of Society for e-Business Studies
• /
• v.22 no.2
• /
• pp.1-18
• /
• 2017

Recently, identification of the extremely stressed condition of children is an essential skill for real-time recognition of a dangerous situation because incidents of children have been dramatically increased. In this paper, therefore, we present a model based on machine learning techniques for stress status identification of a child by using bio-signals such as voice and heart rate that are major factors for presenting a child's emotion. In addition, a smart band for collecting such bio-signals and a mobile application for monitoring child's stress status are also suggested. Specifically, the proposed method utilizes stress patterns of children that are obtained in advance for the purpose of training stress status identification model. Then, the model is used to predict the current stress status for a child and is designed based on conventional machine learning algorithms. The experiment results conducted by using a real-world dataset showed that the possibility of automated detection of a child's stress status with a satisfactory level of accuracy. Furthermore, the research results are expected to be used for preventing child's dangerous situations.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.3
• /
• pp.93-102
• /
• 2023

Data processing through the cloud causes many problems, such as latency and increased communication costs in the communication process. Therefore, many researchers study edge computing in the IoT, and autonomous driving is a representative application. In indoor self-driving, unlike outdoor, GPS and traffic information cannot be used, so the surrounding environment must be recognized using sensors. An efficient autonomous driving system is required because it is a mobile environment with resource constraints. This paper proposes a machine-learning method using neural networks for autonomous driving in an indoor environment. The neural network model predicts the most appropriate driving command for the current location based on the distance data measured by the LiDAR sensor. We designed six learning models to evaluate according to the number of input data of the proposed neural networks. In addition, we made an autonomous vehicle based on Raspberry Pi for driving and learning and an indoor driving track produced for collecting data and evaluation. Finally, we compared six neural network models in terms of accuracy, response time, and battery consumption, and the effect of the number of input data on performance was confirmed.

• Journal of Science Education
• /
• v.42 no.2
• /
• pp.95-105
• /
• 2018

The purpose of this study was to develop a digital textbook on 'structure and contraction mechanism of skeletal muscle' with the learning model for biomimicry-based convergence. The unit of 'structure and contraction mechanism of skeletal muscle' is a part of Life Science I in high school. The convergence learning model was designed with three phases of biomimicry-based convergence (Exploration-Design-Implementation) including 3D modeling & printing. The developed digital textbook was composed of 8 sessions which contains the following learning contents : Exploration of skeletal muscle, creative designing of skeletal muscle using sketch application and 3D modeling, convergent implementing of the designed using 3D printing, exploration of muscle contraction, creative designing of muscle contraction using sketch application and 3D modeling, and convergent implementing of the designed using 3D printing. Each session is also involved in the contents of gallery widgets, media widgets, keynote widgets, sketch widgets, the cloud, polling widgets, and review widgets for interactive and mobile learning. After administering the developed digital textbook to 20 high school students, it was shown a positive effectiveness on life science learning for high school students. Moreover, the digital textbook was evaluated as to promote student's abilities on creative designs and implementation related to biomimicry-based convergence. The digital textbook was also shown a favorable response on students' interest and self-directed learning on life science.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.9 no.8
• /
• pp.2894-2909
• /
• 2015

As the number of mobile devices such as smart phones and tablets explodes, the need for new services or applications is also rapidly increasing. Smart class application is one of the emerging applications, in which most of contents are distributed to all members of a class simultaneously. It is highly required to select relay nodes to cover shadow area of radio as well as extend coverage, but existing algorithms in a smart class environment suffer from high control packet overhead and delay for exchanging topology information among all pairs of nodes to select relay nodes. In addition, the relay selection procedure should be repeated in order to adapt to the dynamic topology changes caused by link status changes or device's movement. This paper proposes the learning based relay selection algorithm to overcome aforementioned problems. The key idea is that every node keeps track of its relay quality in a fully distributed manner, where RQI (Relay Quality Indicator) is newly defined to measure both the ability of receiving packets from content source and the ability of successfully relaying them to successors. The RQI of each node is updated whenever it receives or relays broadcast packet, and the node having the higher RQI is selected as a relay node in a distributed and run-time manner. Thus, the proposed algorithm not only removes the overhead for obtaining prior knowledge to select relay nodes, but also provides the adaptability to the dynamic topology changes. The network simulation and experimental results prove that the proposed algorithm provides efficient and reliable content distribution to all members in a smart class as well adaptability against network dynamics.