• ETRI Journal
• /
• 제43권4호
• /
• pp.603-616
• /
• 2021

Over the last few years, autonomous vehicles have progressed very rapidly. The odometry technique that estimates displacement from consecutive sensor inputs is an essential technique for autonomous driving. In this article, we propose a fast, robust, and accurate odometry technique. The proposed technique is light detection and ranging (LiDAR)-based direct odometry, which uses a spherical range image (SRI) that projects a three-dimensional point cloud onto a two-dimensional spherical image plane. Direct odometry is developed in a vision-based method, and a fast execution speed can be expected. However, applying LiDAR data is difficult because of the sparsity. To solve this problem, we propose an SRI generation method and mathematical analysis, two key point sampling methods using SRI to increase precision and robustness, and a fast optimization method. The proposed technique was tested with the KITTI dataset and real environments. Evaluation results yielded a translation error of 0.69%, a rotation error of 0.0031°/m in the KITTI training dataset, and an execution time of 17 ms. The results demonstrated high precision comparable with state-of-the-art and remarkably higher speed than conventional techniques.

• 디지털융복합연구
• /
• 제16권1호
• /
• pp.231-242
• /
• 2018

병원 재원일수의 효율적 관리는 병원의 수익과 환자의 진료비 절감을 위해 매우 중요한 요소이다. 이러한 재원일수의 효율적 관리를 위해서는 병원들이 재원일수에 대해서 벤치마킹을 할 수 있도록 지원이 필요하고 재원일수 절감의 구체적인 방향을 제시해 줄 수 있는 재원일수 예측모형의 개발이 필요하다. 본 연구에서는 2013년과 2014년도 퇴원손상환자자료 중 급성뇌졸중 환자를 추출하여 분석용 자료를 만들고 인공지능을 이용하여 급성뇌졸중 환자의 재원일수 예측모형을 개발하였다. 분석용 자료는 훈련용 60%, 평가용 40%로 분류하였다. 모형개발은 전통적 통계기법인 다중회귀분석기법과 인공지능기법인 대화식 의사결정나무기법, 신경망 기법, 그리고 이들을 모두 통합한 앙상블기법을 이용하였다. 모형평가는 Root ASE(Absolute error) 지표를 이용하였는데, 다중회귀분석은 23.7, 대화식결정나무 23.7, 신경망 분석은 22.7, 앙상블은 22.7로 나타났고 이를 통하여 재원일수 예측모형 개발에 인공지능기법의 유용성이 입증되었다. 앞으로 재원일수 예측모형개발에 인공지능 기법을 보다 효율적으로 활용할 수 있는 방안에 대해서 계속적인 연구가 이루어 질 필요가 있다.

• ETRI Journal
• /
• 제41권6호
• /
• pp.760-770
• /
• 2019

Based on the growing demand for neural network technologies, various neural network inference engines are being developed. However, each inference engine has its own neural network storage format. There is a growing demand for standardization to solve this problem. This study presents interworking techniques for ensuring the compatibility of neural networks and data among the various deep learning frameworks. The proposed technique standardizes the graphic expression grammar and learning data storage format using the Neural Network Exchange Format (NNEF) of Khronos. The proposed converter includes a lexical, syntax, and parser. This NNEF parser converts neural network information into a parsing tree and quantizes data. To validate the proposed system, we verified that MNIST is immediately executed by importing AlexNet's neural network and learned data. Therefore, this study contributes an efficient design technique for a converter that can execute a neural network and learned data in various frameworks regardless of the storage format of each framework.

• 디지털융복합연구
• /
• 제19권11호
• /
• pp.359-364
• /
• 2021

최근 인공지능의 딥러닝과 머신러닝을 이용한 예측시스템에 관한 연구가 활발히 진행되고 있다. 인공지능의 발전으로 인해 투자관리자의 역할을 인공지능을 대신하고 있으며, 투자관리자보다 높은 수익률로 인해 점차 인공지능으로 거래를 하는 알고리즘 거래가 보편화하고 있다. 알고리즘 매매는 인간의 감정을 배제하고 조건에 따라 기계적으로 매매를 진행하기 때문에 장기적으로 접근했을 때 인간의 매매 수익률보다 높게 나온다. 인공지능의 딥러닝 기법은 과거의 시계열 데이터를 학습하고 미래를 예측하여 인간처럼 학습하게 되고, 변화하는 전략에 대응할 수 있어 활용도가 증가하고 있다. 특히 LSTM기법은 과거의 데이터 일부를 기억하거나 잊어버리는 형태로 최근의 데이터의 비중으로 높여 미래 예측에 사용하고 있다. 최근 facebook에서 개발한 인공지능 알고리즘인 fbprophet은 높은 예측 정확도를 자랑하며 주가나 암호화폐 시세 예측에 사용되고 있다. 따라서 본 연구는 fbprophet을 활용하여 실제 값과 차이를 분석하고 정확한 예측을 위한 조건들을 제시하여 암호화폐 자동매매를 하기 위한 새로운 알고리즘을 제공하여 건전한 투자 문화를 정착시키는 데 이바지하고자 한다.

• Nuclear Engineering and Technology
• /
• 제54권10호
• /
• pp.3943-3948
• /
• 2022

Single-photon emission computed tomography is one of the reliable pin-by-pin verification techniques for spent-fuel assemblies. One of the challenges with this technique is to increase the total fuel assembly verification speed while maintaining high verification accuracy. The aim of the present study, therefore, was to develop an artificial intelligence (AI) algorithm-based tomographic image analysis technique for partial-defect verification of fuel assemblies. With the Monte Carlo (MC) simulation technique, a tomographic image dataset consisting of 511 fuel-rod patterns of a 3 × 3 fuel assembly was generated, and with these images, the VGG16, GoogLeNet, and ResNet models were trained. According to an evaluation of these models for different training dataset sizes, the ResNet model showed 100% pattern estimation accuracy. And, based on the different tomographic image qualities, all of the models showed almost 100% pattern estimation accuracy, even for low-quality images with unrecognizable fuel patterns. This study verified that an AI model can be effectively employed for accurate and fast partial-defect verification of fuel assemblies.

• 한국건축시공학회:학술대회논문집
• /
• 한국건축시공학회 2021년도 가을 학술논문 발표대회
• /
• pp.217-218
• /
• 2021

The development of artificial intelligence in the field of construction and construction is revitalizing. The performance and development techniques of artificial intelligence are changing rapidly, but if you look at the cases of domestic construction sites, they are using technologies from 5 to 7 years ago. It is right to follow a stable method in consideration of commercialization, but the previous AI development method requires more manpower and time to develop than the current technology. In addition, in order to actively utilize artificial intelligence technology, customized artificial intelligence is required to be applied to ever-changing changes in construction sites. it is the reality As a result, even if good AI technology is secured at the construction site, it is reluctant to introduce it because there is no advantage in terms of time and cost compared to the existing method to apply it only to some processes. Currently, an AI technique with a faster development process and accurate recognition has been developed to cope with a fluid situation, so it will be important to understand and introduce the rapidly changing AI development method.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제18권6호
• /
• pp.1518-1539
• /
• 2024

Artificial intelligence-enabled business models aim to improve decision-making, operational efficiency, innovation, and productivity. The presented systematic literature review is conducted to highlight elucidating the utilization of artificial intelligence (AI) methods and techniques within AI-enabled businesses, the significance and functions of AI-enabled organizational models and frameworks, and the design parameters employed in academic research studies within the AI-enabled business domain. We reviewed 39 empirical studies that were published between 2010 and 2023. The studies that were chosen are classified based on the artificial intelligence business technique, empirical research design, and SLR search protocol criteria. According to the findings, machine learning and artificial intelligence were reported as popular methods used for business process modelling in 19% of the studies. Healthcare was the most experimented business domain used for empirical evaluation in 28% of the primary research. The most common reason for using artificial intelligence in businesses was to improve business intelligence. 51% of main studies claimed to have been carried out as experiments. 53% of the research followed experimental guidelines and were repeatable. For the design of business process modelling, eighteen AI mythology were discovered, as well as seven types of AI modelling goals and principles for organisations. For AI-enabled business models, safety, security, and privacy are key concerns in society. The growth of AI is influencing novel forms of business.

• 디지털산업정보학회논문지
• /
• 제15권3호
• /
• pp.15-28
• /
• 2019

Artificial intelligence is evolving rapidly in the ICT field, smart convergence media system and content industry through the fourth industrial revolution, and it is evolving very rapidly through Big Data. In this paper, we propose a face recognition method based on object recognition based on object recognition through artificial intelligence. In this method, Were experimented and studied through the object recognition technique of artificial intelligence. In the conventional 3D image field, general research on object recognition has been carried out variously, and researches have been conducted on the side effects of visual fatigue and dizziness through 3D image. However, in this study, we tried to solve the problem caused by the quantitative difference between object recognition and object recognition for human factor algorithm that measure visual fatigue through cognitive function, morphological analysis and object recognition. Especially, The new method of computer interaction is presented and the results are shown through experiments.

• International Journal of Computer Science & Network Security
• /
• 제24권2호
• /
• pp.1-14
• /
• 2024

While text-to-image models have made remarkable progress in image synthesis, certain models, particularly generative diffusion models, have exhibited a noticeable bias to- wards generating images related to the culture of some developing countries. This paper introduces an empirical investigation aimed at mitigating the bias of image generative model. We achieve this by incorporating symbols representing Saudi culture into a stable diffusion model using the Dreambooth technique. CLIP score metric is used to assess the outcomes in this study. This paper also explores the impact of varying parameters for instance the quantity of training images and the learning rate. The findings reveal a substantial reduction in bias-related concerns and propose an innovative metric for evaluating cultural relevance.

• ETRI Journal
• /
• 제45권2호
• /
• pp.318-328
• /
• 2023

Recently, embedded systems, such as mobile platforms, have multiple processing units that can operate in parallel, such as centralized processing units (CPUs) and neural processing units (NPUs). We can use deep-learning compilers to generate machine code optimized for these embedded systems from a deep neural network (DNN). However, the deep-learning compilers proposed so far generate codes that sequentially execute DNN operators on a single processing unit or parallel codes for graphic processing units (GPUs). In this study, we propose PartitionTuner, an operator scheduler for deep-learning compilers that supports multiple heterogeneous PUs including CPUs and NPUs. PartitionTuner can generate an operator-scheduling plan that uses all available PUs simultaneously to minimize overall DNN inference time. Operator scheduling is based on the analysis of DNN architecture and the performance profiles of individual and group operators measured on heterogeneous processing units. By the experiments for seven DNNs, PartitionTuner generates scheduling plans that perform 5.03% better than a static type-based operator-scheduling technique for SqueezeNet. In addition, PartitionTuner outperforms recent profiling-based operator-scheduling techniques for ResNet50, ResNet18, and SqueezeNet by 7.18%, 5.36%, and 2.73%, respectively.