• Annual Conference of KIPS
• /
• 2019.05a
• /
• pp.419-422
• /
• 2019

The recent increase in single-person households and family income has led to an increase in the number of pet owners. However, due to the owners' difficulty to communicate with them for 24 hours, pets, and especially dogs, tend to display unwanted behavior that can be harmful to themselves and their environment when left alone. Therefore, detecting those behaviors when the owner is absent is necessary to suppress them and prevent any damage. In this paper, we propose a camera-based system that detects a set of normal and unwanted behaviors using deep learning algorithms to monitor dogs when left alone at home. The frames collected from the camera are arranged into sequences of RGB frames and their corresponding optical flow sequences, and then features are extracted from each data flow using pre-trained VGG-16 models. The extracted features from each sequence are concatenated and input to a bi-directional LSTM network that classifies the dog action into one of the targeted classes. The experimental results show that our method achieves a good performance exceeding 0.9 in precision, recall and f-1 score.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.13 no.2
• /
• pp.514-535
• /
• 2019

Information-centric networks operate under the assumption that all network components have built-in caching capabilities. Integrating the caching strategies of information centric networking (ICN) with wireless virtualization improves the gain of virtual infrastructure content caching. In this paper, we propose a framework for software-defined information centric virtualized wireless device-to-device (D2D) networks. Enabling D2D communications in virtualized ICN increases the spectral efficiency due to reuse and proximity gains while the software-defined network (SDN) as a platform also simplifies the computational overhead. In this framework, we propose a joint virtual resource and cache allocation solution for latency-sensitive applications in the next-generation cellular networks. As the formulated problem is NP-hard, we design low-complexity heuristic algorithms which are intuitive and efficient. In our proposed framework, different services can share a pool of infrastructure items. We evaluate our proposed framework and algorithm through extensive simulations. The results demonstrate significant improvements in terms of visiting latency, end user QoE, InP resource utilization and MVNO utility gain.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.10
• /
• pp.3373-3389
• /
• 2022

Exploration of mobile robot without prior data about environments is a fundamental problem during the SLAM processes. In this work, we propose improved version of previous Rmap algorithm by modifying its Exploration submodule. Despite the previous Rmap's performance which significantly reduces the overhead of the grid map, its exploration module costs a lot because of its rectangle following algorithm. To prevent that, we propose a new Rmap+ algorithm for autonomous path planning of mobile robot to explore an unknown environment. The algorithm bases on paired frontiers. To navigate and extend an exploration area of mobile robot, the Rmap+ utilizes the inner and outer frontiers. In each exploration round, the mobile robot using the sensor range determines the frontiers. Then robot periodically changes the range of sensor and generates inner pairs of frontiers. After calculating the length of each frontiers' and its corresponding pairs, the Rmap+ selects the goal point to navigate the robot. The experimental results represent efficiency and applicability on exploration time and distance, i.e., to complete the whole exploration, the path distance decreased from 15% to 69%, as well as the robot decreased the time consumption from 12% to 86% than previous algorithms.

• Journal of Internet Computing and Services
• /
• v.23 no.2
• /
• pp.37-44
• /
• 2022

With the outbreak of COVID-19, non-face-to-face activities such as remote learning and telecommuting have increased rapidly. As a result, the number of people staying at home and the number of hours spent inside the house have also increased since the pandemic. Our team had previously worked on methods for detecting abnormal conditions in a person's health in various circumstances within the house by converging single sensor-based algorithms. In our previous research, we installed IoT sensors indoors to detect people emergency situations requiring aids, the scope of detection was limited to indoor space due to the limitation in sensors. In this study, we have come up with a system that integrates our previous study with a new method for detecting abnormal conditions in outdoor environments using outdoor security cameras and wearable devices. The proposed system enables users to be notified of emergency situations in both indoor and outdoor areas and respond to them as quickly as possible.

• Journal of Digital Contents Society
• /
• v.16 no.4
• /
• pp.545-553
• /
• 2015

While all of the data has a value in itself, most of the data that is collected in the real world is a random and unstructured. In order to extract useful information from the data, it is need to use the data transform and analysis algorithms. Data mining is used for this purpose. Today, there is not only need for a variety of data mining techniques to analyze the data but also need for a computational requirements and rapid analysis time for huge volume of data. The method commonly used to store huge volume of data is to use the hadoop. A method for analyzing data in hadoop is to use the MapReduce framework. In this paper, we developed a tournament-based MapReduce method for high efficiency in developing an algorithm on a single machine to the MapReduce framework. This proposed method can apply many analysis algorithms and we showed the usefulness of proposed tournament based method to apply frequently used data mining algorithms k-means and k-nearest neighbor classification.

• KIPS Transactions on Software and Data Engineering
• /
• v.4 no.8
• /
• pp.321-330
• /
• 2015

In journal manuscript submission and review systems, authors can submit their manuscript at any time and editorial members are struggling to find proper reviewers for the submitted manuscripts and assign them to such reviewers. In order to solve this problem, we propose a greedy algorithm and a genetic algorithm to recommend proper reviewers for the submitted manuscripts. The proposed algorithms evaluate reviewers' speciality for the submitted manuscripts by using the submitted manuscripts' keywords and the reviewers expertises. In addition to that, they take the fairness among the reviewers' speciality and the review frequency for consideration. To verify the proposed algorithms, we apply them to the JIPS manuscript submission and review system that the Korea Information Processing Society has operated, and present the results in this paper. By performing the performance evaluation of the proposed algorithms, we finally show that the genetic algorithm outperforms the greedy algorithm in terms of the recommended reviewers' fitness.

• Journal of the Korean Society for Nondestructive Testing
• /
• v.19 no.2
• /
• pp.118-128
• /
• 1999

There are many ultrasonic measurement methods that are used in nondestructive testing applications. Some typical applications include material property determination, microstructural characterization. and flaw detection. Ultrasonic parameters such as velocity and attenuation are most commonly required in these applications. The accuracy and repeatability of testing results are dependent on both the hardware used to generate and receive the ultrasonic waves and on the analysis software for calculating these parameters. In this study, five analysis algorithms were implemented on a computer for measuring wave speed in a pulse echo. immersion testing configuration. In velocity measurements comparisons were made between the overlap. cross-correlation. Fourier transform. Hilbert transform, wavelet transform algorithms. Velocity measurement was applied to an isotropic steel sample using the five analysis algorithms. Frequency-dependent phase/group velocity and attenuation were also measured using the Fourier transform and wavelet transform algorithms on a composite laminate containing voids.

• Journal of the Korean Society of Propulsion Engineers
• /
• v.25 no.3
• /
• pp.127-137
• /
• 2021

The launch complex(LC) is composed of various facilities. The launch control system that operates remotely those of LC spends much time and labor for developing and verifying its control algorithms. The verification of algorithms is performed by the software developer entering simulated state values based on the test procedure and checking the output result according to the algorithm flow. These verification processes should be performed repeatedly, thus the human errors are easily occurred. In this paper, an efficient automated verification method with a script test procedure is proposed to minimize human errors and shorten the verification duration. We also present the results of the algorithm verification tests for the cases of the compressed gases supply system and the electro pneumatic panel system of LC.

• Journal of KIISE
• /
• v.41 no.12
• /
• pp.1007-1012
• /
• 2014

Software birthmarks are used to detect software plagiarism. For binaries, however, only a few birthmarks have been developed. In this paper, we propose a static approach to generate API sequences along major paths, which are analyzed from control flow graphs of the binaries. Since our API sequences are extracted along the most plausible paths of the binary codes, they can represent actual API sequences produced from binary executions, but in a more concise form. Our similarity measures use the Smith-Waterman algorithm that is one of the popular sequence alignment algorithms for DNA sequence analysis. We evaluate our static path-based API sequence with multiple versions of five applications. Our experiment indicates that our proposed method provides a quite reliable similarity birthmark for binaries.

• Journal of Korean Society of Transportation
• /
• v.22 no.2 s.73
• /
• pp.19-26
• /
• 2004

AllWayS(AWS, Satongpaldal in Korean) is the first comprehensive computer software in Korea that is developed for the transportation demand modeling. The original DOS version software was recently receded for Windows environment. Traditional 4-step transportation demand forecasting process is incorporated in the software under graphical user interface environment. AWS is able to compose or edit graphic transportation networks data by each scenario which could be the subject of an analysis. Besides, it use database structure that can handle every data of a scenario such as networks, O/D, and socio-economic data, etc. We expect this integrated process could provide each analyst with efficient and easy to use tool for their analysis. Each models in this software is based on traditional algorithms and the results were compared to existing software, EMME/2 and it showed similar results.