• Electronics and Telecommunications Trends
• /
• v.33 no.5
• /
• pp.121-134
• /
• 2018

The Von Neumann based architecture of the modern computer has dominated the computing industry for the past 50 years, sparking the digital revolution and propelling us into today's information age. Recent research focus and market trends have shown significant effort toward the advancement and application of artificial intelligence technologies. Although artificial intelligence has been studied for decades since the Turing machine was first introduced, the field has recently emerged into the spotlight thanks to remarkable milestones such as AlexNet-CNN and Alpha-Go, whose neural-network based deep learning methods have achieved a ground-breaking performance superior to existing recognition, classification, and decision algorithms. Unprecedented results in a wide variety of applications (drones, autonomous driving, robots, stock markets, computer vision, voice, and so on) have signaled the beginning of a golden age for artificial intelligence after 40 years of relative dormancy. Algorithmic research continues to progress at a breath-taking pace as evidenced by the rate of new neural networks being announced. However, traditional Von Neumann based architectures have proven to be inadequate in terms of computation power, and inherently inefficient in their processing of vastly parallel computations, which is a characteristic of deep neural networks. Consequently, global conglomerates such as Intel, Huawei, and Google, as well as large domestic corporations and fabless companies are developing dedicated semiconductor chips customized for artificial intelligence computations. The AI Processor Research Laboratory at ETRI is focusing on the research and development of super low-power AI processor chips. In this article, we present the current trends in computation platform, parallel processing, AI processor, and super-threaded AI processor research being conducted at ETRI.

• Journal of the Korean Institute of Electrical and Electronic Material Engineers
• /
• v.35 no.3
• /
• pp.215-222
• /
• 2022

Artificial neuromorphic devices are considered the key component in realizing energy-efficient and brain-inspired computing systems. For the artificial neuromorphic devices, various material candidates and device architectures have been reported, including two-dimensional materials, metal-oxide semiconductors, organic semiconductors, and halide perovskite materials. In addition to conventional electrical neuromorphic devices, optoelectronic neuromorphic devices, which operate under a light stimulus, have received significant interest due to their potential advantages such as low power consumption, parallel processing, and high bandwidth. This article reviews the recent progress in optoelectronic neuromorphic devices using various active materials such as two-dimensional materials, metal-oxide semiconductors, organic semiconductors, and halide perovskites

• The Transactions of the Korea Information Processing Society
• /
• v.7 no.12
• /
• pp.3910-3922
• /
• 2000

Current power systems are distributed geographically and operated in the form of Energy Management System(EMS)/ Supervision Control and Data Acquisition(SCADA) with the aid of computers and communications. Recently a variety of utilities have had interests in using inforrration technology to bring the efficiency and low operational costs. There is also a trend to integrdte the production, transmission, distribution and management/control of power into one and unified distributed system. To this end, Electric Power Hesearch Institute(EPRI) announced a new standard communication protocol called Inter-Control Center Protocol(ICCP).ICCP specifies the use of Manufacturing Message Specification(MMS) for services required by rccr in application layer and supports the communications between heterogeneous control centers. This paper presents the characteristics of MMS,ICCP and their relationship. Futherrnore, we implement the basic functional blocks of ICCP using MMS services under TCI/IP environments. Finally, we model a simple power system and apply the rccp protocol to this system in a window-based scheme, and finally show the operation and validation of this protocol.

• ETRI Journal
• /
• v.42 no.1
• /
• pp.54-66
• /
• 2020

Nowadays, the broad availability of cameras and embedded systems makes the application of computer vision very promising as a supporting technology for intelligent transportation systems, particularly in the field of vehicle tracking. Although there are several existing trackers, the limitation of using low-cost cameras, besides the relatively low processing power in embedded systems, makes most of these trackers useless. For the tracker to work under those conditions, the video frame rate must be reduced to decrease the burden on computation. However, doing this will make the vehicle seem to move faster on the observer's side. This phenomenon is called the fast motion challenge. This paper proposes a tracker called dynamic swarm particle (DSP), which solves the challenge. The term particle refers to the particle filter, while the term swarm refers to particle swarm optimization (PSO). The fundamental concept of our method is to exploit the continuity of vehicle dynamic motions by creating dynamic models based on PSO. Based on the experiments, DSP achieves a precision of 0.896 and success rate of 0.755. These results are better than those obtained by several other benchmark trackers.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.15 no.11
• /
• pp.4065-4083
• /
• 2021

Super-resolution can improve the clarity of low-resolution (LR) images, which can increase the accuracy of high-level compute vision tasks. Portable devices have low computing power and storage performance. Large-scale neural network super-resolution methods are not suitable for portable devices. In order to save the computational cost and the number of parameters, Lightweight image processing method can improve the processing speed of portable devices. Therefore, we propose the Enhanced Information Multiple Distillation Network (EIMDN) to adapt lower delay and cost. The EIMDN takes feedback mechanism as the framework and obtains low level features through high level features. Further, we replace the feature extraction convolution operation in Information Multiple Distillation Block (IMDB), with Ghost module, and propose the Enhanced Information Multiple Distillation Block (EIMDB) to reduce the amount of calculation and the number of parameters. Finally, coordinate attention (CA) is used at the end of IMDB and EIMDB to enhance the important information extraction from Spaces and channels. Experimental results show that our proposed can achieve convergence faster with fewer parameters and computation, compared with other lightweight super-resolution methods. Under the condition of higher peak signal-to-noise ratio (PSNR) and higher structural similarity (SSIM), the performance of network reconstruction image texture and target contour is significantly improved.

• International Journal of Fluid Machinery and Systems
• /
• v.4 no.1
• /
• pp.179-190
• /
• 2011

The swirling flow developing in Francis turbine draft tube under part load operation leads to pressure fluctuations usually in the range of 0.2 to 0.4 times the runner rotational frequency resulting from the so-called vortex breakdown. For low cavitation number, the flow features a cavitation vortex rope animated with precession motion. Under given conditions, these pressure fluctuations may lead to undesirable pressure fluctuations in the entire hydraulic system and also produce active power oscillations. For the upper part load range, between 0.7 and 0.85 times the best efficiency discharge, pressure fluctuations may appear in a higher frequency range of 2 to 4 times the runner rotational speed and feature modulations with vortex rope precession. It has been pointed out that for this particular operating point, the vortex rope features elliptical cross section and is animated of a self-rotation. This paper presents an experimental investigation focusing on this peculiar phenomenon, defined as the upper part load vortex rope. The experimental investigation is carried out on a high specific speed Francis turbine scale model installed on a test rig of the EPFL Laboratory for Hydraulic Machines. The selected operating point corresponds to a discharge of 0.83 times the best efficiency discharge. Observations of the cavitation vortex carried out with high speed camera have been recorded and synchronized with pressure fluctuations measurements at the draft tube cone. First, the vortex rope self rotation frequency is evidenced and the related frequency is deduced. Then, the influence of the sigma cavitation number on vortex rope shape and pressure fluctuations is presented. The waterfall diagram of the pressure fluctuations evidences resonance effects with the hydraulic circuit. The influence of outlet bubble cavitation and air injection is also investigated for low cavitation number. The time evolution of the vortex rope volume is compared with pressure fluctuations time evolution using image processing. Finally, the influence of the Froude number on the vortex rope shape and the associated pressure fluctuations is analyzed by varying the rotational speed.

• Electronics and Telecommunications Trends
• /
• v.33 no.5
• /
• pp.103-110
• /
• 2018

Studies on artificial intelligence have been developed for the past couple of decades. After a few periods of prosperity and recession, a new machine learning method, so-called Deep Learning, has been introduced. This is the result of high-quality big- data, an increase in computing power, and the development of new algorithms. The main targets for deep learning are 1D audio and 2D images. The application domain is being extended from a discriminative model, such as classification/segmentation, to a generative model. Currently, deep learning is used for processing 3D data. However, unlike 2D, it is not easy to acquire 3D learning data. Although low-cost 3D data acquisition sensors have become more popular owing to advances in 3D vision technology, the generation/acquisition of 3D data remains a very difficult problem. Moreover, it is not easy to directly apply an existing network model, such as a convolution network, owing to the variety of 3D data representations. In this paper, we summarize the 3D deep learning technology that have started to be developed within the last 2 years.

• Journal of Intelligence and Information Systems
• /
• v.17 no.1
• /
• pp.53-69
• /
• 2011

Vision and voice-based technologies are commonly utilized for human-robot interaction. But it is widely recognized that the performance of vision and voice-based interaction systems is deteriorated by a large margin in the real-world situations due to environmental and user variances. Human users need to be very cooperative to get reasonable performance, which significantly limits the usability of the vision and voice-based human-robot interaction technologies. As a result, touch screens are still the major medium of human-robot interaction for the real-world applications. To empower the usability of robots for various services, alternative interaction technologies should be developed to complement the problems of vision and voice-based technologies. In this paper, we propose the use of accelerometer-based gesture interface as one of the alternative technologies, because accelerometers are effective in detecting the movements of human body, while their performance is not limited by environmental contexts such as lighting conditions or camera's field-of-view. Moreover, accelerometers are widely available nowadays in many mobile devices. We tackle the problem of classifying acceleration signal patterns of 26 English alphabets, which is one of the essential repertoires for the realization of education services based on robots. Recognizing 26 English handwriting patterns based on accelerometers is a very difficult task to take over because of its large scale of pattern classes and the complexity of each pattern. The most difficult problem that has been undertaken which is similar to our problem was recognizing acceleration signal patterns of 10 handwritten digits. Most previous studies dealt with pattern sets of 8~10 simple and easily distinguishable gestures that are useful for controlling home appliances, computer applications, robots etc. Good features are essential for the success of pattern recognition. To promote the discriminative power upon complex English alphabet patterns, we extracted 'motion trajectories' out of input acceleration signal and used them as the main feature. Investigative experiments showed that classifiers based on trajectory performed 3%~5% better than those with raw features e.g. acceleration signal itself or statistical figures. To minimize the distortion of trajectories, we applied a simple but effective set of smoothing filters and band-pass filters. It is well known that acceleration patterns for the same gesture is very different among different performers. To tackle the problem, online incremental learning is applied for our system to make it adaptive to the users' distinctive motion properties. Our system is based on instance-based learning (IBL) where each training sample is memorized as a reference pattern. Brute-force incremental learning in IBL continuously accumulates reference patterns, which is a problem because it not only slows down the classification but also downgrades the recall performance. Regarding the latter phenomenon, we observed a tendency that as the number of reference patterns grows, some reference patterns contribute more to the false positive classification. Thus, we devised an algorithm for optimizing the reference pattern set based on the positive and negative contribution of each reference pattern. The algorithm is performed periodically to remove reference patterns that have a very low positive contribution or a high negative contribution. Experiments were performed on 6500 gesture patterns collected from 50 adults of 30~50 years old. Each alphabet was performed 5 times per participant using $Nintendo{(R)}$ $Wii^{TM}$ remote. Acceleration signal was sampled in 100hz on 3 axes. Mean recall rate for all the alphabets was 95.48%. Some alphabets recorded very low recall rate and exhibited very high pairwise confusion rate. Major confusion pairs are D(88%) and P(74%), I(81%) and U(75%), N(88%) and W(100%). Though W was recalled perfectly, it contributed much to the false positive classification of N. By comparison with major previous results from VTT (96% for 8 control gestures), CMU (97% for 10 control gestures) and Samsung Electronics(97% for 10 digits and a control gesture), we could find that the performance of our system is superior regarding the number of pattern classes and the complexity of patterns. Using our gesture interaction system, we conducted 2 case studies of robot-based edutainment services. The services were implemented on various robot platforms and mobile devices including $iPhone^{TM}$. The participating children exhibited improved concentration and active reaction on the service with our gesture interface. To prove the effectiveness of our gesture interface, a test was taken by the children after experiencing an English teaching service. The test result showed that those who played with the gesture interface-based robot content marked 10% better score than those with conventional teaching. We conclude that the accelerometer-based gesture interface is a promising technology for flourishing real-world robot-based services and content by complementing the limits of today's conventional interfaces e.g. touch screen, vision and voice.