• 전기전자학회논문지
• /
• 제26권3호
• /
• pp.341-348
• /
• 2022

Wi-Fi가 거의 모든 곳에서 사용이 가능한 환경이 도래하면서 Wi-Fi 기반의 센싱 시스템의 활용가능성에 대한 학계의 주목과 함께 활발한 연구가 진행되고 있다. 최근에는 채널 상태 정보(CSI)를 활용한 딥러닝 기술의 비약적 발달로 높은 감지 성능을 달성하고 있다. 하지만, 새로운 대상 도메인에 적용하기 위해서는 명시적인 데이터 수집 및 모델 재학습 과정의 값비싼 적응 노력 없이는 여전히 실질적으로는 사용하기가 어렵다. 본 연구에서는 딥러닝 기반의 Wi-Fi 센싱 시스템을 위한 훈련데이터 수집 및 레이블링을 자동으로 진행하는 CSI 자동 레이블링 시스템(CALS)를 제안한다. 제안 시스템은 CSI 데이터 수집 과정에서 컴퓨터 비전 기술을 함께 활용하여, 지도학습용으로 수집된 CSI 데이터에 대한 레이블링을 자동으로 수행토록 하였다. CALS의 효율성을 보이기 위해 라즈베리파이를 이용하여 프로토타입 시스템을 구현하고, 실내 환경에서의 사람 존재 감지를 수행하는 3가지 모델에 대해 학습과 평가를 진행하였다. 자동 수집된 데이터를 진행하여 학습을 활용하는 방식으로 실시간 데이터에 대해 평가를 진행했을 때 90% 이상의 높은 정확도를 달성하였다.

• 문화기술의 융합
• /
• 제8권6호
• /
• pp.405-411
• /
• 2022

2008년에 시작된 한국의 노인 장기요양보험은 그보다 8년 먼저 시작된 일본의 개호보험을 원용한 것이다. 양국은 노인의 생활을 지원하기 위하여 지적 정신적으로 약화된 노인의 삶을 지원하기 위한 복지용구 급여제도를 가지고 있다. 본 연구에서는 한국의 복지용품 품목과 일본의 복지용품 품목을 비교·검토하여 한국과 일본의 품목별 특성을 알아보았다. 한국은 배회감지기, 자세변환용구, 요실금팬티 등이 일본보다 앞서서 복지용구로 등록되었으며 일본은 자동소변처리기, 휠체어 전동보조장치, 체위변환기, 이동용 리프트 등이 한국보다 먼저 복지용구로 지정되었다. 또한 일본 후생노동성은 배설예측지원기기의 복지용구 지정을 예고한 상태이다. 한국과 일본이 복지용구 품목들을 발전 시키기 위하여 협력한다면 초고령사회에 양국의 노인의 삶의 질을 향상시키는데 많은 도움이 될 것이다.

• Journal of Animal Science and Technology
• /
• 제64권3호
• /
• pp.531-538
• /
• 2022

In Italy, buffalo mozzarella is a largely sold and consumed dairy product. The fraudulent adulteration of buffalo milk with cheaper and more available milk of other species is very frequent. In the present study, Fourier transform infrared spectroscopy (FTIR), in combination with multivariate analysis by partial least square (PLS) regression, was applied to quantitatively detect the adulteration of buffalo milk with cow milk by using a fully automatic equipment dedicated to the routine analysis of the milk composition. To enhance the heterogeneity, cow and buffalo bulk milk was collected for a period of over three years from different dairy farms. A total of 119 samples were used for the analysis to generate 17 different concentrations of buffalo-cow milk mixtures. This procedure was used to enhance variability and to properly randomize the trials. The obtained calibration model showed an R² ≥ 0.99 (R² cal. = 0.99861; root mean square error of cross-validation [RMSEC] = 2.04; R² val. = 0.99803; root mean square error of prediction [RMSEP] = 2.84; root mean square error of cross-validation [RMSECV] = 2.44) suggesting that this method could be successfully applied in the routine analysis of buffalo milk composition, providing rapid screening for possible adulteration with cow's milk at no additional cost.

• Imaging Science in Dentistry
• /
• 제52권4호
• /
• pp.383-391
• /
• 2022

Purpose: Periodontitis, the most prevalent chronic inflammatory condition affecting teeth-supporting tissues, is diagnosed and classified through clinical and radiographic examinations. The staging of periodontitis using panoramic radiographs provides information for designing computer-assisted diagnostic systems. Performing image segmentation in periodontitis is required for image processing in diagnostic applications. This study evaluated image segmentation for periodontitis staging based on deep learning approaches. Materials and Methods: Multi-Label U-Net and Mask R-CNN models were compared for image segmentation to detect periodontitis using 100 digital panoramic radiographs. Normal conditions and 4 stages of periodontitis were annotated on these panoramic radiographs. A total of 1100 original and augmented images were then randomly divided into a training (75%) dataset to produce segmentation models and a testing (25%) dataset to determine the evaluation metrics of the segmentation models. Results: The performance of the segmentation models against the radiographic diagnosis of periodontitis conducted by a dentist was described by evaluation metrics(i.e., dice coefficient and intersection-over-union [IoU] score). MultiLabel U-Net achieved a dice coefficient of 0.96 and an IoU score of 0.97. Meanwhile, Mask R-CNN attained a dice coefficient of 0.87 and an IoU score of 0.74. U-Net showed the characteristic of semantic segmentation, and Mask R-CNN performed instance segmentation with accuracy, precision, recall, and F1-score values of 95%, 85.6%, 88.2%, and 86.6%, respectively. Conclusion: Multi-Label U-Net produced superior image segmentation to that of Mask R-CNN. The authors recommend integrating it with other techniques to develop hybrid models for automatic periodontitis detection.

• 한국정보통신학회:학술대회논문집
• /
• 한국정보통신학회 2022년도 추계학술대회
• /
• pp.225-228
• /
• 2022

한국건축정책학회의 건축 설계 대가 산정 방법은 설계 기간 중 투입된 시간을 고려한다. 그래서 설계 시간을 단축하면 설계 비용을 절감할 수 있다. 실제 건축학과 전공 학생들을 대상으로 설문 조사한 결과, 반복되는 도면 작성으로 인한 피로감과 도면 작성 시 고려할 사항이 많다는 점에서 어려움을 느끼고 있었다. 본 논문에서는 건축 설계 과정 중 도면화 단계에서 스케치를 규격화된 평면도로 자동 변환할 수 있는 프로그램과 사용자의 편리를 위한 웹앱을 구현한다. 제안하는 방법에서는 사용자가 스케치 이미지를 웹앱을 통해 등록하게 되면 프로그램은 도형 검출을 통해 도면 내 공간을 분리한다. 스케치에 표기된 치수와 공간 정보를 기반으로 외벽과 내벽을 표시하고 공간에 적절한 인테리어를 배치한다. 제안하는 방법을 통해 건축 설계 단계 중 도면화 과정의 시간을 줄여 설계 비용 절감을 기대할 수 있으며, 실제 건축 전공자 학생들 중 95.2%는 본 프로그램을 사용하고 싶다는 의향을 밝혔다.

• International Journal of Computer Science & Network Security
• /
• 제23권5호
• /
• pp.135-147
• /
• 2023

Internet of things has revolutionaries every field of life due to the use of artificial intelligence within Machine Learning. It is successfully being used for the study of Radiation monitoring, prediction of Ultraviolet and Electromagnetic rays. However, there is no particular system available that can monitor and detect waves. Therefore, the present study designed in which IOT enables intelligence system based on machine learning was developed for the prediction of the radiation and their effects of human beings. Moreover, a sensor based system was installed in order to detect harmful radiation present in the environment and this system has the ability to alert the humans within the range of danger zone with a buzz, so that humans can move to a safer place. Along with this automatic sensor system; a self-created dataset was also created in which sensor values were recorded. Furthermore, in order to study the outcomes of the effect of these rays researchers used Support Vector Machine, Gaussian Naïve Bayes, Decision Trees, Extra Trees, Bagging Classifier, Random Forests, Logistic Regression and Adaptive Boosting Classifier were used. To sum up the whole discussion it is stated the results give high accuracy and prove that the proposed system is reliable and accurate for the detection and monitoring of waves. Furthermore, for the prediction of outcome, Adaptive Boosting Classifier has shown the best accuracy of 81.77% as compared with other classifiers.

• 드라이브 ㆍ 컨트롤
• /
• 제20권2호
• /
• pp.15-23
• /
• 2023

In this study, two-dimensional location of crops for auto weeding was detected using deep learning. To construct a dataset for soybean detection, an image-capturing system was developed using a mono camera and single-board computer and the system was mounted on a weeding robot to collect soybean images. A dataset was constructed by extracting RoI (region of interest) from the raw image and each sample was labeled with soybean and the background for classification learning. The deep learning model consisted of four convolutional layers and was trained with a weakly supervised learning method that can provide object localization only using image-level labeling. Localization of the soybean area can be visualized via CAM and the two-dimensional position of the soybean was estimated by clustering the pixels associated with the soybean area and transforming the pixel coordinates to world coordinates. The actual position, which is determined manually as pixel coordinates in the image was evaluated and performances were 6.6(X-axis), 5.1(Y-axis) and 1.2(X-axis), 2.2(Y-axis) for MSE and RMSE about world coordinates, respectively. From the results, we confirmed that the center position of the soybean area derived through deep learning was sufficient for use in automatic weeding systems.

• 국제학술발표논문집
• /
• The 8th International Conference on Construction Engineering and Project Management
• /
• pp.87-95
• /
• 2020

Generally, occupational safety and particularly construction safety is an intricate phenomenon. Industry professionals have devoted vital attention to enforcing Occupational Safety and Health (OHS) from the last three decades to enhance safety management in construction. Despite the efforts of the safety professionals and government agencies, current safety management still relies on manual inspections which are infrequent, time-consuming and prone to error. Extensive research has been carried out to deal with high fatality rates confronting by the construction industry. Sensor systems, visualization-based technologies, and tracking techniques have been deployed by researchers in the last decade. Recently in the construction industry, computer vision has attracted significant attention worldwide. However, the literature revealed the narrow scope of the computer vision technology for safety management, hence, broad scope research for safety monitoring is desired to attain a complete automatic job site monitoring. With this regard, the development of a broader scope computer vision-based risk recognition system for correlation detection between the construction entities is inevitable. For this purpose, a detailed analysis has been conducted and related rules which depict the correlations (positive and negative) between the construction entities were extracted. Deep learning supported Mask R-CNN algorithm is applied to train the model. As proof of concept, a prototype is developed based on real scenarios. The proposed approach is expected to enhance the effectiveness of safety inspection and reduce the encountered burden on safety managers. It is anticipated that this approach may enable a reduction in injuries and fatalities by implementing the exact relevant safety rules and will contribute to enhance the overall safety management and monitoring performance.

• 한국작물학회:학술대회논문집
• /
• 한국작물학회 2022년도 추계학술대회
• /
• pp.81-81
• /
• 2022

Recently, many studies on big data based smart farming have been conducted. Research to quantify morphological characteristics using image data from various crops in smart farming is underway. Rice is one of the most important food crops in the world. Much research has been done to predict and model rice crop yield production. The number of productive tillers per plant is one of the important agronomic traits associated with the grain yield of rice crop. However, modeling the basic growth characteristics of rice requires accurate data measurements. The existing method of measurement by humans is not only labor intensive but also prone to human error. Therefore, conversion to digital data is necessary to obtain accurate and phenotyping quickly. In this study, we present an image-based method to predict leaf number and evaluate tiller number of individual rice crop using YOLOv5 deep learning network. We performed using various network of the YOLOv5 model and compared them to determine higher prediction accuracy. We ako performed data augmentation, a method we use to complement small datasets. Based on the number of leaves and tiller actually measured in rice crop, the number of leaves predicted by the model from the image data and the existing regression equation were used to evaluate the number of tillers using the image data.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• 제17권10호
• /
• pp.2627-2642
• /
• 2023

Parkinson's disease (PD) is a typical, chronic neurodegenerative disease involving the concentration of dopamine, which can disrupt motor activity and cause different degrees of gait disturbance relevant to PD severity in patients. As current clinical PD diagnosis is a complex, time-consuming, and challenging task that relays on physicians' subjective evaluation of visual observations, gait disturbance has been extensively explored to make automatic detection of PD diagnosis and severity rating and provides auxiliary information for physicians' decisions using gait data from various acquisition devices. Among them, wearable sensors have the advantage of flexibility since they do not limit the wearers' activity sphere in this application scenario. In this paper, an attention-based temporal network (ATN) is designed for the time series structure of gait data (vertical ground reaction force signals) from foot sensor systems, to learn the discriminative differences related to PD severity levels hidden in sequential data. The structure of the proposed method is illuminated by Transformer Network for its success in excavating temporal information, containing three modules: a preprocessing module to map intra-moment features, a feature extractor computing complicated gait characteristic of the whole signal sequence in the temporal dimension, and a classifier for the final decision-making about PD severity assessment. The experiment is conducted on the public dataset PDgait of VGRF signals to verify the proposed model's validity and show promising classification performance compared with several existing methods.