• Journal of KIISE:Software and Applications
• /
• v.31 no.9
• /
• pp.1150-1160
• /
• 2004

In this paper, we propose a new 3D video coding method for heterogeneous display systems and network infrastructure over enhanced Access Grid (e-AG) using spatio-temporal scalability defined in MPEG-2. The proposed encoder produces several bit-streams for providing temporally and spatially scalable 3D video service. The generated bit-streams can be nelivered with proper spatio-temporal resolution according to network bandwidths and processing speeds, visualization capabilities of client systems. The functionality of proposed spatio-temporal scalability can be exploited for construction of highly scalable 3D video service in heterogeneous distributed environments.

• The Journal of Korea Robotics Society
• /
• v.18 no.3
• /
• pp.346-351
• /
• 2023

With the release of numerous open driving datasets, the demand for domain adaptation in perception tasks has increased, particularly when transferring knowledge from rich datasets to novel domains. However, it is difficult to solve the change 1) in the sensor domain caused by heterogeneous LiDAR sensors and 2) in the environmental domain caused by different environmental factors. We overcome domain differences in the semi-supervised setting with 3-stage model parameter training. First, we pre-train the model with the source dataset with object scaling based on statistics of the object size. Then we fine-tine the partially frozen model weights with copy-and-paste augmentation. The 3D points in the box labels are copied from one scene and pasted to the other scenes. Finally, we use the knowledge distillation method to update the student network with a moving average from the teacher network along with a self-training method with pseudo labels. Test-Time Augmentation with varying z values is employed to predict the final results. Our method achieved 3rd place in ECCV 2022 workshop on the 3D Perception for Autonomous Driving challenge.

• International Journal of Computer Science & Network Security
• /
• v.22 no.7
• /
• pp.443-450
• /
• 2022

The method of studying 3D-technologies abroad and in Ukraine is considered. The analysis of educational resources and experience of use of the equipment in branch is carried out. The didactic principles of the educational process for 3D-printing specialists are determined. The use of FDM technology and the ability to minimize the occurrence of defects in the future have been studied. An analysis of the international experience of the educational process of relevant specialists in the field. The content of training for 3D printing specialists has been developed. The experience of using 3D-technologies is described and the list of recommendations for elimination of defects during production of products by means of additive technologies is made. The recommendations will be useful not only for beginners, but also for experienced professionals in additive technologies. The need to study such experience is the main condition for the development of enterprises in Ukraine that plan to automate their own production. A 3D printing engineer must know the basics of economics and marketing, because his responsibilities include optimizing workflows to reduce the cost and speed up printing. Therefore, the knowledge gained from practical experience presented and in building for learning 3D printing engineers by the authors will be important.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.3
• /
• pp.85-90
• /
• 2021

In this paper, fall detection using individual wearable devices for older people is considered. To design a low-cost wearable device for reliable fall detection, we present a comprehensive analysis of two representative models. One is a machine learning model composed of a decision tree, random forest, and Support Vector Machine(SVM). The other is a deep learning model relying on a one-dimensional(1D) Convolutional Neural Network(CNN). By considering data segmentation, preprocessing, and feature extraction methods applied to the input data, we also evaluate the considered models' validity. Simulation results verify the efficacy of the deep learning model showing improved overall performance.

• Journal of KIISE:Software and Applications
• /
• v.34 no.7
• /
• pp.585-594
• /
• 2007

The back propagation algorithm took a long time to learn the input patterns and was difficult to train the additional or repeated learning patterns. So Aleksander proposed the binary neural network which could overcome the disadvantages of BP Network. But it had the limitation of repeated learning and was impossible to extract a generalized pattern. In this paper, we proposed a dynamic 3 dimensional Neuro System which was consisted of a learning network which was based on weightless neural network and a feedback module which could accumulate the characteristic. The proposed system was enable to train additional and repeated patterns. Also it could be produced a generalized pattern by putting a proper threshold into each learning-net's discriminator which was resulted from learning procedures. And then we reused the generalized pattern to elevate the recognition rate. In the last processing step to decide right category, we used maximum response detector. We experimented using the MNIST database of NIST and got 99.3% of right recognition rate for training data.

• The Transactions of The Korean Institute of Electrical Engineers
• /
• v.64 no.6
• /
• pp.900-911
• /
• 2015

In this paper, 3D face recognition model is designed by using Polynomial based RBFNN(Radial Basis Function Neural Network) and PNN(Polynomial Neural Network). Also recognition rate is performed by this model. In existing 2D face recognition model, the degradation of recognition rate may occur in external environments such as face features using a brightness of the video. So 3D face recognition is performed by using 3D scanner for improving disadvantage of 2D face recognition. In the preprocessing part, obtained 3D face images for the variation of each pose are changed as front image by using pose compensation. The depth data of face image shape is extracted by using Multiple point signature. And whole area of face depth information is obtained by using the tip of a nose as a reference point. Parameter optimization is carried out with the aid of both ABC(Artificial Bee Colony) and PSO(Particle Swarm Optimization) for effective training and recognition. Experimental data for face recognition is built up by the face images of students and researchers in IC&CI Lab of Suwon University. By using the images of 3D face extracted in IC&CI Lab. the performance of 3D face recognition is evaluated and compared according to two types of models as well as point signature method based on two kinds of depth data information.

• Journal of IKEEE
• /
• v.28 no.2
• /
• pp.234-238
• /
• 2024

This paper presents a study on the integration of 3D-stacked dual-tip RRAM with a CNN accelerator architecture, leveraging its low drive current characteristics and scalability in a 3D stacked configuration. The dual-tip structure is utilized in a parallel connection format in a synaptic array to implement multi-level capabilities. It is configured within a Network-on-chip style accelerator along with various hardware blocks such as DAC, ADC, buffers, registers, and shift & add circuits, and simulations were performed for the CNN accelerator. The quantization of synaptic weights and activation functions was assumed to be 16-bit. Simulation results of CNN operations through a parallel pipeline for this accelerator architecture achieved an operational efficiency of approximately 370 GOPs/W, with accuracy degradation due to quantization kept within 3%.

• Journal of the Korea Institute of Military Science and Technology
• /
• v.23 no.3
• /
• pp.246-256
• /
• 2020

In the future Network Centric Warfare(NCW), changing to IPv6 based network environment is required to enable various future technologies such as the Internet of Things(IoT) and cloud technology which are expected to be introduced to the tactical network evolution. With the change to the IPv6 network, an ID/LOC(Identifier/Location) separation protocol that decomposes context of the IP address to location and identifier can enhance network capacity of increasing number of device and provide efficient mobility management in the tactical network that changes topology dynamically. In this paper, we choose ILNP(Identifier-Locator Network Protocol) as an ID/LOC separation for tactical network environment. In addition to ILNP-based tactical network design, this paper proposes a network-based mobility management scheme for providing efficient mobility management. Through numerical performance analysis, we show that the proposed scheme can reduce network loads more effectively than the conventional IP-based mobility management scheme and common handover procedure in ILNP.

• Proceedings of the Korean Institute of Information and Commucation Sciences Conference
• /
• 2015.05a
• /
• pp.126-129
• /
• 2015

Device-to-device (D2D) communications, a subset of Proximity-based Services that enables direct communication between LTE network subscribers, is gaining popularity. It is well underway to be adopted in cellular communication systems for pedestrian and connected-vehicles alike. In this paper, we briefly present our model of an Evolved Packet Core Network-assisted device discovery simulator and show the applicability of Proximity-based Services for Vehicular Ad-hoc Networks. Through the performance evaluation based on the developed simulation environment, it is shown that in case when users gather in the same vicinity, as in public transportation, LTE network data can be efficiently offloaded and multicasted through Wi-Fi for e.g. delivering traffic-related information and for the benefit of infotainment service consumers.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.15 no.1
• /
• pp.69-74
• /
• 2005

In this paper, we suggested user assistant soft computing method for 3D effect optimization. In order to maximize 3D effect of image, intervals among cameras have to be set up properly according to distance between cameras and an object. Two data such as interval and distance was obtained to use in neural network as the data for learning. However, if the data for learning was obtained by only human's subjective views, it could be that the obtained data was not optimal for learning because the data had an accidental ewer To obtain optimal data lot learning, we added candidature data to obtained data through data analysis, and then selected the most proper data between the candidature data and the obtained data for learning in neural network. Usually, 3D effect of image was affected by both distance from an object to cameras and an object size. Therefore, we suggested fuzzy inference model which was able to represent two factors like distance and size. Candidature data was added by fuzzy model. In the simulation result, we verified that the mote the obtained data was affected by human's subjective views, the more effective the suggested system was.