• Journal of Internet of Things and Convergence
• /
• 제9권6호
• /
• pp.17-22
• /
• 2023

Brain-Machine Interfaces(BMI) are interfaces that control machines by decoding brainwaves, which are electrical signals generated from neural activities. Although BMIs can be applied in various fields, their widespread usage is hindered by the low portability of the hardware required for brainwave measurement and decoding. To address this issue, previous research proposed a brain-machine interface system based on the Internet of Things (IoT) using cloud computing. In this study, we developed and tested an application that uses brainwaves to control the Pong game, demonstrating the real-time usability of the system. The results showed that users of the proposed BMI achieved scores comparable to optimal control artificial intelligence in real-time Pong game matches. Thus, this research suggests that IoT-based brain-machine interfaces can be utilized in a variety of real-time applications in everyday life.

• Journal of IKEEE
• /
• 제28권2호
• /
• pp.168-173
• /
• 2024

Speaker recognition refers to a technology that analyzes voice frequencies that are different for each individual and compares them with pre-stored voices to determine the identity of the person. Deep learning-based speaker recognition is being applied to many fields, and pet robots are one of them. However, the hardware performance of pet robots is very limited in terms of the large memory space and calculations of deep learning technology. This is an important problem that pet robots must solve in real-time interaction with users. Lightening deep learning models has become an important way to solve the above problems, and a lot of research is being done recently. In this paper, we describe the results of research on lightweight speaker recognition for pet robots by constructing a voice data set for pet robots, which is a specific command type, and comparing the results of models using residuals. In the conclusion, we present the results of the proposed method and Future research plans are described.

• Proceedings of the KIEE Conference
• /
• 대한전기학회 2002년도 하계학술대회 논문집 B
• /
• pp.1283-1285
• /
• 2002

This study is developed vehicle information detector using loop and piezo sensors. This study would analyze the over all problems concerning our road conditions, environmental matters and unique features of our traffic matters; moreover, with these it would develope the hardware, software, car classification algorithm applied by artificial intelligence and traffic monitoring program which can be easily fixed. This can be divided into traffic detecting algorithm and car classification algorithm. Especially, we have developed the car classification algorithm used by C-means Fuzzy Clustering method.

• Journal of Korea Multimedia Society
• /
• 제23권3호
• /
• pp.476-482
• /
• 2020

In this paper, we propose a block-based modularity architecture design method for distributed machine learning. The proposed architecture is a block-type module structure with various machine learning algorithms. It allows free expansion between block-type modules and allows multiple machine learning algorithms to be organically interlocked according to the situation. The architecture enables open data communication using the metadata query protocol. Also, the architecture makes it easy to implement an application service combining various edge computing devices by designing a communication method suitable for surrounding applications. To confirm the interlocking between the proposed block-type modules, we implemented a hardware-based modularity application system.

• Journal of Institute of Control, Robotics and Systems
• /
• 제10권9호
• /
• pp.771-778
• /
• 2004

Recently, various applications of robot system become more popular in accordance with rapid development of computer hardware/software, artificial intelligence, and automatic control technology. Formerly robots mainly have been used in industrial field, however, nowadays it is said that the robot will do an important role in the home service application. To make the robot more useful, we require further researches on implementation of natural communication method between the human and the robot system, and autonomous behavior generation. The gesture recognition technique is one of the most convenient methods for natural human-robot interaction, so it is to be solved for implementation of intelligent robot system. In this paper, we describe the state-of-the-art of advanced gesture recognition technologies for intelligent robots according to three methods; sensor based method, feature based method, appearance based method, and 3D model based method. And we also discuss some problems and real applications in the research field.

• International Journal of Fuzzy Logic and Intelligent Systems
• /
• 제3권2호
• /
• pp.251-257
• /
• 2003

In this paper, we wish to construct a optimal traffic cycle using wire remote control. if police vehicle or ambulance suddenly enter the traffic Intersection, it will increase the traffic accident. In this paper, wireless traffic light use the radio traffic control signal and research about the hardware manufacture to check special detectors on urgency vehicles may safety and rapidly enter traffic intersection. Also, this paper present a traffic signal control conditions that analyzes different traffic intersection flows in cases of saturated flows, where the real traffic volume demand is large and the capacity constraints of bottlenecks have significant effects on the flow patterns. Through computer simulation this wireless traffic light has been proven to be much more safety and efficient than fixed traffic signal light which does not consider emergency vehicles for safety escort.

• Journal of the Korea Society of Computer and Information
• /
• 제24권4호
• /
• pp.19-26
• /
• 2019

In this study, we study the development and control of motion of 3D character animation and discuss the development direction of technology. Character animation has been developed as a data-based method and a physics-based method. The animation generation technique based on the keyframe method has been made possible by the development of the hardware technology, and the motion capture device has been used. Various techniques for effectively editing the motion data have appeared. At the same time, animation techniques based on physics have emerged, which realistically generate the motion of the character by physically optimized numerical computation. Recently, animation techniques using machine learning have shown new possibilities for creating characters that can be controlled by the user in real time and are expected to be developed in the future.

• Journal of Korea Multimedia Society
• /
• 제24권4호
• /
• pp.528-537
• /
• 2021

Face recognition has gained significant notice because of its application in many businesses: security, healthcare, and marketing. In this paper, we will present the recognition method using the combination of correlation filters (CF) and Support Vector Machine (SVM). Firstly, we evaluate the performance and compared four different correlation filters: minimum average correlation energy (MACE), maximum average correlation height (MACH), unconstrained minimum average correlation energy (UMACE), and optimal-tradeoff (OT). Secondly, we propose the machine learning approach by using the OT correlation filter for features extraction and SVM for classification. The numerical results on National Cheng Kung University (NCKU) and Pointing'04 face database show that the proposed method OT-SVM gets higher accuracy in face recognition compared to other machine learning methods. Our approach doesn't require graphics card to train the image. As a result, it could run well on a low hardware system like an embedded system.

• Journal of Korea Multimedia Society
• /
• 제24권12호
• /
• pp.1606-1613
• /
• 2021

Recently various attempts to control hardware through integration of sensors and artificial intelligence have been made. This paper proposes a smart hazardous sound detection at home. Previous sound recognition methods have problems due to the processing of background sounds and the low recognition accuracy of high-frequency sounds. To get around these problems, a new MFCC(Mel-Frequency Cepstral Coefficient) algorithm using Wiener filter, modified filterbank is proposed. Experiments for comparing the performance of the proposed method and the original MFCC were conducted. For the classification of feature vectors extracted using the proposed MFCC, DNN(Deep Neural Network) was used. Experimental results showed the superiority of the modified MFCC in comparison to the conventional MFCC in terms of 1% higher training accuracy and 6.6% higher recognition rate.

• IEMEK Journal of Embedded Systems and Applications
• /
• 제18권3호
• /
• pp.101-108
• /
• 2023

Optimizing the performance of deep neural networks on embedded systems is a challenging task that requires efficient compilers and runtime systems. We propose a TVM-based approach that consists of three steps: quantization, auto-scheduling, and ahead-of-time compilation. Our approach reduces the computational complexity of models without significant loss of accuracy, and generates optimized code for various hardware platforms. We evaluate our approach on three representative CNNs using ImageNet Dataset on the NVIDIA Jetson AGX Xavier board and show that it outperforms baseline methods in terms of processing speed.