• PNF and Movement
• /
• 제22권1호
• /
• pp.43-54
• /
• 2024

Purpose: Falls among persons older than 65 years are a significant concern due to their frequency and severity. This study aimed to develop a vest-type embedded artificial intelligence (AI) system capable of detecting and predicting falls in various scenarios. Methods: In this study, we established and developed a vest-type embedded AI system to judge and predict falls in various directions and situations. To train the AI, we collected data using acceleration and gyroscope values from a six-axis sensor attached to the seventh cervical and the second sacral vertebrae of the user, considering accurate motion analysis of the human body. The model was constructed using a neural network-based AI prediction algorithm to anticipate the direction of falls using the collected pedestrian data. Results: We focused on developing a lightweight and efficient fall prediction model for integration into an embedded AI algorithm system, ensuring real-time network optimization. Our results showed that the accuracy of fall occurrence and direction prediction using the trained fall prediction model was 89.0% and 78.8%, respectively. Furthermore, the fall occurrence and direction prediction accuracy of the model quantized for embedded porting was 87.0 % and 75.5 %, respectively. Conclusion: The developed fall detection and prediction system, designed as a vest-type with an embedded AI algorithm, offers the potential to provide real-time feedback to pedestrians in clinical settings and proactively prepare for accidents.

• 경영정보학연구
• /
• 제22권4호
• /
• pp.21-39
• /
• 2020

딥러닝(Deep learning) 기법은 패턴분석, 이미지분류 등 다양한 분야에서 높은 성과를 나타내고 있다. 특히, 주식시장 분석문제는 머신러닝 연구분야에서도 어려운 분야이므로 딥러닝이 많이 활용되는 영역이다. 본 연구에서는 패턴분석과 분류능력이 높은 딥러닝의 일종인 합성곱신경망(Convolutional Neural Network) 모델을 활용하여 주가방향 예측방법을 제안한다. 추가적으로 합성곱신경망 모델을 효율적으로 학습시키기 위한 속성선택(Feature Selection, FS)방법이 적용된다. 합성곱신경망 모델의 성과는 머신러닝 단일 분류기와 앙상블 분류기를 벤치마킹하여 객관적으로 검증된다. 본 연구에서 벤치마킹한 분류기는 로지스틱 회귀분석(Logistic Regression), 의사결정나무(Decision Tree), 인공신경망(Neural Network), 서포트 벡터머신(Support Vector Machine), 아다부스트(Adaboost), 배깅(Bagging), 랜덤포레스트(Random Forest)이다. 실증분석 결과, 속성선택을 적용한 합성곱신경망이 다른 벤치마킹 분류기보다 분류 성능이 상대적으로 높게 나타났다. 이러한 결과는 합성곱신경망 모델과 속성선택방법을 적용한 예측방법이 기업의 재무자료에 내포된 가치를 보다 정교하게 분석할 수 있는 가능성이 있음을 실증적으로 확인할 수 있었다.

• 대한임베디드공학회논문지
• /
• 제11권3호
• /
• pp.163-171
• /
• 2016

Lane detection is a widely researched topic. Although simple road detection is easily achieved by previous methods, lane detection becomes very difficult in several complex cases involving noisy edges. To address this, we use a Convolution neural network (CNN) for image enhancement. CNN is a deep learning method that has been very successfully applied in object detection and recognition. In this paper, we introduce a robust lane detection method based on a CNN combined with random sample consensus (RANSAC) algorithm. Initially, we calculate edges in an image using a hat shaped kernel, then we detect lanes using the CNN combined with the RANSAC. In the training process of the CNN, input data consists of edge images and target data is images that have real white color lanes on an otherwise black background. The CNN structure consists of 8 layers with 3 convolutional layers, 2 subsampling layers and multi-layer perceptron (MLP) of 3 fully-connected layers. Convolutional and subsampling layers are hierarchically arranged to form a deep structure. Our proposed lane detection algorithm successfully eliminates noise lines and was found to perform better than other formal line detection algorithms such as RANSAC

• 대한임베디드공학회논문지
• /
• 제13권6호
• /
• pp.289-296
• /
• 2018

Drone detection in FMCW radar system needs complex techniques because a drone beat frequency is highly dynamic and unpredictable. Therefore, the current static signal processing algorithms cannot show appropriate detection accuracy. With dynamic signal fluctuation and environmental clutters, it can fail to detect a drone or make false detection. It affects to the radar system integrity and safety. Constant false alarm rate (CFAR), one of famous static signal process algorithm is effective for static environment. But for drone detection, it shows low detection accuracy. In this paper, we suggest neural network based FMCW radar system for detecting a drone. We use recurrent neural network (RNN) because it is the effective neural network for signal processing. In our FMCW radar system, one transmitter emits FMCW signal and four-way fixed receivers detect reflected drone beat frequency. The coordinate of the drone can be calculated with four receivers information by triangulation. Therefore, RNN only learns and inferences reflected drone beat frequency. It helps higher learning and detection accuracy. With several drone flight experiments, RNN shows false detection rate and detection accuracy as 21.1% and 96.4%, respectively.

• Journal of Electrical Engineering and Technology
• /
• 제10권1호
• /
• pp.401-407
• /
• 2015

The increase of image spam, a kind of spam in which the text message is embedded into attached image to defeat spam filtering technique, is a major problem of the current e-mail system. For nearly a decade, content based filtering using text classification or machine learning has been a major trend of anti-spam filtering system. Recently, spammers try to defeat anti-spam filter by many techniques. Text embedding into attached image is one of them. We proposed an ontology spam filters. However, the proposed system handles only text e-mail and the percentage of attached images is increasing sharply. The contribution of the paper is that we add image e-mail handling capability into the anti-spam filtering system keeping the advantages of the previous text based spam e-mail filtering system. Also, the proposed system gives a low false negative value, which means that user's valuable e-mail is rarely regarded as a spam e-mail.

• 대한임베디드공학회논문지
• /
• 제16권6호
• /
• pp.277-283
• /
• 2021

This paper addresses the problem of vision-based mask filter inspection for mask production systems. Machine learning-based approaches can be considered to solve the problem, but they may not be applicable to mask filter inspection if normal and anomaly mask filter data are not sufficient. In such cases, handcrafted image processing methods have to be considered to solve the problem. In this paper, we propose a hierarchical correlation-based approach that combines handcrafted image processing methods to detect anomaly mask filters. The proposed approach combines image rotation, cropping and resizing, edge detection of mask filter parts, average blurring, and correlation-based decision. The proposed approach was tested and analyzed with real mask filters. The results showed that the proposed approach was able to successfully detect anomalies in mask filters.

• 전자통신동향분석
• /
• 제36권2호
• /
• pp.56-64
• /
• 2021

Many computer vision algorithms are computationally expensive and require a lot of computing resources. Recently, owing to machine learning technology and high-performance embedded systems, vision processing applications, such as object detection, face recognition, and visual inspection, are widely used. However, on-devices need to use their resources to handle powerful vision works with low power consumption in heterogeneous environments. Consequently, global manufacturers are trying to lock many developers into their ecosystem, providing integrated low-power chips and dedicated vision libraries. Khronos Group-an international standard organization-has released the OpenVX standard for high-performance/low-power vision processing in heterogeneous on-device systems. This paper describes vision libraries for the embedded systems and presents the OpenVX standard along with related trends for on-device vision system.

• 대한임베디드공학회논문지
• /
• 제18권1호
• /
• pp.1-7
• /
• 2023

In this paper, we implement a lossless compression technique for time-series data generated by IoT (Internet of Things) devices to reduce the disk spaces. The proposed compression technique reduces the size of the encoded data by selectively applying CNN (Convolutional Neural Networks) or Delta encoding depending on the situation in the Forecasting algorithm that performs prediction on time series data. In addition, the proposed technique sequentially performs zigzag encoding, splitting, and bit packing to increase the compression ratio. We showed that the proposed compression method has a compression ratio of up to 1.60 for the original data.

• 대한임베디드공학회논문지
• /
• 제18권6호
• /
• pp.293-301
• /
• 2023

With the advancement of artificial intelligence and its various use cases, accessing it through edge computing environments is gaining traction. However, due to the nature of edge computing environments, efficient management and optimization of clusters distributed in different geographical locations is considered a major challenge. To address these issues, this paper proposes a centralization and automation tool called KubEVC-Agent based on Kubernetes. KubEVC-Agent centralizes the deployment, operation, and management of edge clusters and presents a use case of the data transformation for optimizing intra-cluster communication. This paper describes the components of KubEVC-Agent, its working principle, and experimental results to verify its effectiveness.

• Smart Structures and Systems
• /
• 제22권2호
• /
• pp.175-183
• /
• 2018

Time-series data often contain one of the most valuable pieces of information in many fields including manufacturing. Because time-series data are relatively cheap to acquire, they (e.g., vibration signals) have become a crucial part of big data even in manufacturing shop floors. Recently, deep-learning models have shown state-of-art performance for analyzing big data because of their sophisticated structures and considerable computational power. Traditional models for a machinery-monitoring system have highly relied on features selected by human experts. In addition, the representational power of such models fails as the data distribution becomes complicated. On the other hand, deep-learning models automatically select highly abstracted features during the optimization process, and their representational power is better than that of traditional neural network models. However, the applicability of deep-learning models to the field of prognostics and health management (PHM) has not been well investigated yet. This study integrates the "residual fitting" mechanism inherently embedded in the wavelet transform into the convolutional neural network deep-learning structure. As a result, the architecture combines a signal smoother and classification procedures into a single model. Validation results from rotor vibration data demonstrate that our model outperforms all other off-the-shelf feature-based models.