• Proceedings of the Korean Society of Computer Information Conference
• /
• 2019.01a
• /
• pp.53-56
• /
• 2019

본 논문에서는 화력을 이용하는 대형 파워 플랜트 설비의 미세먼지 발생량을 저감시키고 능동적으로 제어 할 수 있는 효율적인 시스템을 제안한다. 이 시스템은 기존의 고정형으로 설계된 집진기 방식의 고정부하량 한계점과 극복하고 초미세먼지 PM2.5, 미세먼지 PM10의 발생량에 따라 IoT센서 감지에 의해 지능형 알고리즘으로 효율적으로 저감 제어 처리량을 극대화하고, 미세먼지 발생량을 최소화한다. 또한 이 시스템의 차별성은 기존의 집진기에서 잡혀지지 않는 초미세먼지를 새로운 형태의 물질인 FAA(Fine-dust Adsorption Agent)를 통해 연료 연소 시 발생되는 초미세먼지 미세입자 자체를 크게 만들어 기존 설비 집진기 필터에 포집되게 하는 혁신적인 방식이다. 이번 연구를 통해 350도~1000도 열원에서 작용할 수 있는 화학물질 FAA 용액(Agent)을 개발 하였으며 지능형 AI 분사장치를 통해 연료에 첨가되어 연소 시 미세먼지를 20배~50배까지 볼륨을 확대시켜 기존 집진필터에 포집될 수 있게 동작된다. 이때, 기존 설계된 집진기의 한계(부하)용량에 상관없이 미세먼지 발생량을 상황인식 반응형 알고리즘(AI제어) 통해 분사량을 능동적으로 조절하여 미세먼지 발생량을 저감하는 진보적 혁신성을 지닌다.

• Journal of Sensor Science and Technology
• /
• v.29 no.1
• /
• pp.19-26
• /
• 2020

Electrocardiogram (ECG) classification has become an essential task of modern day wearable devices, and can be used to detect cardiovascular diseases. State-of-the-art Artificial Intelligence (AI)-based ECG classifiers have been designed using various artificial neural networks (ANNs). Despite their high accuracy, ANNs require significant computational resources and power. Herein, three different ANNs have been compared: multilayer perceptron (MLP), convolutional neural network (CNN), and spiking neural network (SNN) only for the ECG classification. The ANN model has been developed in Python and Theano, trained on a central processing unit (CPU) platform, and deployed on a PYNQ-Z2 FPGA board to validate the model using a Jupyter notebook. Meanwhile, the hardware accelerator is designed with Overlay, which is a hardware library on PYNQ. For classification, the MIT-BIH dataset obtained from the Physionet library is used. The resulting ANN system can accurately classify four ECG types: normal, atrial premature contraction, left bundle branch block, and premature ventricular contraction. The performance of the ECG classifier models is evaluated based on accuracy and power. Among the three AI algorithms, the SNN requires the lowest power consumption of 0.226 W on-chip, followed by MLP (1.677 W), and CNN (2.266 W). However, the highest accuracy is achieved by the CNN (95%), followed by MLP (76%) and SNN (90%).

• KSCE Journal of Civil and Environmental Engineering Research
• /
• v.44 no.2
• /
• pp.173-182
• /
• 2024

In recent, there has been a trend toward primarily utilizing data-driven models employing artificial intelligence technologies, such as machine learning, for flood prediction. These data-driven models offer the advantage of utilizing pre-training results, significantly reducing the required simulation time. However, it remains that a considerable amount of flood data is necessary for the pre-training in data-driven models, while the available observed data for application is often insufficient. As an alternative, validated simulation results from physically-based models are being employed as pre-training data alongside observed data. In this context, we developed a flood mapping accelerator to generate flood maps for pre-training. The proposed accelerator automates the entire process of flood mapping, i.e., estimating flood discharge using HEC-1, calculating water surface levels using HEC-RAS, simulating channel overflow and generating flood maps using RAS Mapper. With the accelerator, users can easily prepare a database for pre-training of data-driven models from hundreds to tens of thousands of rainfall scenarios. It includes various convenient menus containing a Graphic User Interface(GUI), and its practical applicability has been validated across 26 test-beds.

• International Journal of Computer Science & Network Security
• /
• v.23 no.1
• /
• pp.103-111
• /
• 2023

Implementing conventional DFT solution for arrays of DNN accelerators having large number of processing elements (PEs), without considering architectural characteristics of PEs may incur overwhelming test overheads. Recent DFT based techniques have utilized the homogeneity and dataflow of arrays at PE-level and Core-level for obtaining reduction in; test pattern volume, test time, test power and ATPG runtime. This paper reviews these contemporary test solutions for ASIC based DNN accelerators. Mainly, the proposed test architectures, pattern application method with their objectives are reviewed. It is observed that exploitation of architectural characteristic such as homogeneity and dataflow of PEs/ arrays results in reduced test overheads.

• Journal of the Korea Institute of Information and Communication Engineering
• /
• v.24 no.10
• /
• pp.1331-1340
• /
• 2020

Object detection in maritime means that the captain detects floating objects that has a risk of colliding with the ship using the computer automatically and as accurately as human eyes. In conventional ships, the presence and distance of objects are determined through radar waves. However, it cannot identify the shape and type. In contrast, with the development of AI, cameras help accurately identify obstacles on the sea route with excellent performance in detecting or recognizing objects. The computer must calculate high-volume pixels to analyze digital images. However, the CPU is specialized for sequential processing; the processing speed is very slow, and smooth service support or security is not guaranteed. Accordingly, this study developed maritime object detection software and implemented it with FPGA to accelerate the processing of large-scale computations. Additionally, the system implementation was improved through embedded boards and FPGA interface, achieving 30 times faster performance than the existing algorithm and a three-times faster entire system.

• Journal of IKEEE
• /
• v.23 no.4
• /
• pp.1314-1320
• /
• 2019

In this paper, we propose a new method for optimizing bit operations and applying them to DNN(Deep Neural Network) in software environment. As a method for this, we propose a packing function for bitwise optimization and a masking matrix multiplication operation for application to DNN. The packing function converts 32-bit real value to 2-bit quantization value through threshold comparison operation. When this sequence is over, four 32-bit real values are changed to one 8-bit value. The masking matrix multiplication operation consists of a special operation for multiplying the packed weight value with the normal input value. And each operation was then processed in parallel using a GPU accelerator. As a result of this experiment, memory saved about 16 times than 32-bit DNN Model. Nevertheless, the accuracy was within 1%, similar to the 32-bit model.

• Journal of Advanced Navigation Technology
• /
• v.28 no.5
• /
• pp.601-609
• /
• 2024

In this paper, we present the design and implementation results of a system that classifies drones from other objects using an FMCW (frequency-modulated continuous wave) radar sensor. The proposed system detects various objects through a four-stage signal processing procedure, consisting of FFT, CFAR, clustering, and tracking, using signals received from the radar sensor. Subsequently, a deep learning process is conducted to classify the detected objects as either drones or other objects. To mitigate the high computational demands and extensive memory requirements of deep learning, a BNN (binary neural network) structure was applied, binarizing the CNN (convolutional neural network) operations. The performance evaluation and verification results demonstrated a drone classification accuracy of 89.33%, with a total execution time of 4 ms, confirming the feasibility of real-time operation.

• Journal of Venture Innovation
• /
• v.5 no.1
• /
• pp.107-127
• /
• 2022

Global challenges such as the corona pandemic, climate change and the war-on-tech ensure that the demand who the technologies of the future develops and monitors prominently for will be on the agenda. Development of, and applications in, agrifood, biotech, high-tech, medtech, quantum, AI and photonics are the basis of the future earning capacity of the Netherlands and contribute to solving societal challenges, close to home and worldwide. To be like the Netherlands and Europe a strategic position in the to obtain knowledge and innovation chain, and with it our autonomy in relation to from China and the United States insurance, clear choices are needed. Brainport Eindhoven: Building on Philips' knowledge base, there is create an innovative ecosystem where more than 7,000 companies in the High-tech Systems & Materials (HTSM) collaborate on new technologies, future earning potential and international value chains. Nearly 20,000 private R&D employees work in 5 regional high-end campuses and for companies such as ASML, NXP, DAF, Prodrive Technologies, Lightyear and many others. Brainport Eindhoven has a internationally leading position in the field of system engineering, semicon, micro and nanoelectronics, AI, integrated photonics and additive manufacturing. What is being developed in Brainport leads to the growth of the manufacturing industry far beyond the region thanks to chain cooperation between large companies and SMEs. South-Holland: The South Holland ecosystem includes companies as KPN, Shell, DSM and Janssen Pharmaceutical, large and innovative SMEs and leading educational and knowledge institutions that have more than Invest €3.3 billion in R&D. Bearing Cores are formed by the top campuses of Leiden and Delft, good for more than 40,000 innovative jobs, the port-industrial complex (logistics & energy), the manufacturing industry cluster on maritime and aerospace and the horticultural cluster in the Westland. South Holland trains thematically key technologies such as biotech, quantum technology and AI. Twente: The green, technological top region of Twente has a long tradition of collaboration in triple helix bandage. Technological innovations from Twente offer worldwide solutions for the large social issues. Work is in progress to key technologies such as AI, photonics, robotics and nanotechnology. New technology is applied in sectors such as medtech, the manufacturing industry, agriculture and circular value chains, such as textiles and construction. Being for Twente start-ups and SMEs of great importance to the jobs of tomorrow. Connect these companies technology from Twente with knowledge regions and OEMs, at home and abroad. Wageningen in FoodValley: Wageningen Campus is a global agri-food magnet for startups and corporates by the national accelerator StartLife and student incubator StartHub. FoodvalleyNL also connects with an ambitious 2030 programme, the versatile ecosystem regional, national and international - including through the WEF European food innovation hub. The campus offers guests and the 3,000 private R&D put in an interesting programming science, innovation and social dialogue around the challenges in agro production, food processing, biobased/circular, climate and biodiversity. The Netherlands succeeded in industrializing in logistics countries, but it is striving for sustainable growth by creating an innovative ecosystem through a regional industry-academic research model. In particular, the Brainport Cluster, centered on the high-tech industry, pursues regional innovation and is opening a new horizon for existing industry-academic models. Brainport is a state-of-the-art forward base that leads the innovation ecosystem of Dutch manufacturing. The history of ports in the Netherlands is transforming from a logistics-oriented port symbolized by Rotterdam into a "port of digital knowledge" centered on Brainport. On the basis of this, it can be seen that the industry-academic cluster model linking the central government's vision to create an innovative ecosystem and the specialized industry in the region serves as the biggest stepping stone. The Netherlands' innovation policy is expected to be more faithful to its role as Europe's "digital gateway" through regional development centered on the innovation cluster ecosystem and investment in job creation and new industries.

• Radiation Oncology Journal
• /
• v.13 no.3
• /
• pp.277-283
• /
• 1995

Purpose : This study was performed to measure dose alteration at the air-tissue interface resulting from rebuild-up to the loss of charged particle equilibrium in the tissues around the air-tissue interfaces. Materials and Methods : The 6 and 10-MV photon beam in dual energy linear accelerator were used to measure the surface dose at the air-tissue interface The polystyrene phantom sized $25{\times}25{\times}5\;cm^3$ and a water phantom sized $29{\times}29{\times}48\;cm^3$ which incorporates a parallel-plate ionization chamber in the distal side of air gap were used in this study. The treatment field sizes were $5{\times}5\;cm^2,\;10{\times}10\;cm^2\;and\;20{\times}20\;cm^2$. Air cavity thickness was variable from 10 mm to 50 mm. The observed-expected ratio (OER) was defined as the ratio of dose measured at the distal junction that is air-tissue interface to the dose measured at the same point in a homogeneous phantom. Results : In this experiment, the result of OER was close or slightly over than 1.0 for the large field size but much less (about 0.565) than 1.0 for the small field size in both photon energy. The factors to affect the dose distribution at the air-tissue interface were the field size, the thickness of air cavity. and the photon energy. Conclusion : Thus, the radiation oncologist should take into account dose reduction at the air-tissue interface when planning the head and neck cancer especially pharynx and laryngeal lesions, because the dose can be less nearly $29{\%}$ than predicted value.