• Structural Engineering and Mechanics
• /
• v.68 no.6
• /
• pp.691-700
• /
• 2018

Ground granulated blast furnace slag (GGBS) is a by product obtained from iron and steel industries, useful in the design and development of high quality cement paste/mortar and concrete. This paper investigates the applicability of relevance vector machine (RVM) based regression model to predict the compressive strength of various GGBS based concrete mixes. Compressive strength data for various GGBS based concrete mixes has been obtained by considering the effect of water binder ratio and steel fibres. RVM is a machine learning technique which employs Bayesian inference to obtain parsimonious solutions for regression and classification. The RVM is an extension of support vector machine which couples probabilistic classification and regression. RVM is established based on a Bayesian formulation of a linear model with an appropriate prior that results in a sparse representation. Compressive strength model has been developed by using MATLAB software for training and prediction. About 70% of the data has been used for development of RVM model and 30% of the data is used for validation. The predicted compressive strength for GGBS based concrete mixes is found to be in very good agreement with those of the corresponding experimental observations.

• ETRI Journal
• /
• v.43 no.1
• /
• pp.95-108
• /
• 2021

Application (app) ratings are feedback provided voluntarily by users and serve as important evaluation criteria for apps. However, these ratings can often be biased owing to insufficient or missing votes. Additionally, significant differences have been observed between numeric ratings and user reviews. This study aims to predict the numeric ratings of Google apps using machine learning classifiers. It exploits numeric app ratings provided by users as training data and returns authentic mobile app ratings by analyzing user reviews. An ensemble learning model is proposed for this purpose that considers term frequency/inverse document frequency (TF/IDF) features. Three TF/IDF features, including unigrams, bigrams, and trigrams, were used. The dataset was scraped from the Google Play store, extracting data from 14 different app categories. Biased and unbiased user ratings were discriminated using TextBlob analysis to formulate the ground truth, from which the classifier prediction accuracy was then evaluated. The results demonstrate the high potential for machine learning-based classifiers to predict authentic numeric ratings based on actual user reviews.

• Journal of the Korean Society for Aviation and Aeronautics
• /
• v.30 no.2
• /
• pp.44-54
• /
• 2022

An empirical analysis was conducted on the workload of helicopter pilots flying in high-risk flight environments such as ground obstacles and weather effects at low altitudes. To evaluate the workload, an independent sample t-test was performed using the NASA-TLX evaluation method most suitable for the aviation field, and the workload score was calculated by applying the analytical stratification method (AHP) to compare and analyze private and commercial pilots. There is a significant difference in mean between private and commercial pilots and the result of work load was obtained over 70%. This paper studied the 'surprise and startle effect' on the helicopter field for the first time. In the future, it is intended to contribute to the safe operation of helicopters by presenting a method for effective safety management by utilizing it in the field of education and training for helicopter pilots and providing basic data for preventing accidents caused by human error.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.16 no.6
• /
• pp.2044-2059
• /
• 2022

Recent works have shown that the geometric constraint can be harnessed to boost the performance of CNN-based camera localization. However, the existing strategies are limited to imposing image-level constraint between pose pairs, which is weak and coarse-gained. In this paper, we introduce a pixel-level epipolar geometry constraint to vanilla localization framework without the ground-truth 3D information. Dubbed EpiLoc, our method establishes the geometric relationship between pixels in different images by utilizing the epipolar geometry thus forcing the network to regress more accurate poses. We also propose a variant called EpiSingle to cope with non-sequential training images, which can construct the epipolar geometry constraint based on a single image in a self-supervised manner. Extensive experiments on the public indoor 7Scenes and outdoor RobotCar datasets show that the proposed pixel-level constraint is valuable, and helps our EpiLoc achieve state-of-the-art results in the end-to-end camera localization task.

• The Journal of Korean Physical Therapy
• /
• v.34 no.5
• /
• pp.242-247
• /
• 2022

Purpose: This study investigates the effect of 60° semi-squat exercises according to three different types of support surfaces. The effects were examined on joint position sense and balancing ability using stable and unstable surfaces in patients afflicted with post-stroke hemiplegia. Methods: Subjects were instructed to perform three sets of 60° semi-squat exercises according to the characteristics of the support surface conditions. The three ground states were bilateral stable surface (BSS), nonaffected side unstable surface (NUS), and bilateral unstable surface (BUS). The joint position sense, characteristics of body sway, and dynamic balance were analyzed according to floor conditions before and after the experiment. A balance-pad (50 cm W×41 cm L×6 cm H; Alcan Airex AG, Sins, Switzerland) was used for the unstable floor. Results: The 60° semi-squat exercises applied to hemiplegic patients showed the highest statistical significance in joint position sense in the NUS group, and Timed Up and Go test (TUG) in the BUS group (p<0.05). Conclusion: Functional training using an unstable surface can be applied as a meaningful intervention method for improving the balance and joint position sense of stroke patients.

• Safety and Health at Work
• /
• v.13 no.3
• /
• pp.315-325
• /
• 2022

Background: Firefighters are required to carry self-contained breathing apparatus (SCBA), which increases the risk of musculoskeletal disorders. This study assessed the newly recruited firefighters' internal forces and potential musculoskeletal disorders when carrying SCBA. The effects of SCBA strap lengths were also evaluated. Methods: Kinematic parameters of twelve male subjects running in a control condition with no SCBA equipped and three varying-strapped SCBAs were measured using 3D inertial motion capture. Subsequently, motion data and predicted ground reaction force were inputted for subject-specific musculoskeletal modeling to estimate joint and muscle forces. Results: The knee was exposed to the highest internal force when carrying SCBA, followed by the rectus femoris and hip, while the shoulder had the lowest force compared to the no-SCBA condition. Our model also revealed that adjusting SCBA straps length was an efficient strategy to influence the force that occurred at the lumbar spine, hip, and knee regions. Grey relation analysis indicated that the deviation of the center of mass, step length, and knee flexion-extension angle could be used as the predictor of musculoskeletal disorders. Conclusion: The finding suggested that the training of the newly recruits focuses on the coordinated movement of muscle and joints in the lower limb. The strap lengths around 98-105 cm were also recommended. The findings are expected to provide injury interventions to enhance the occupational health and safety of the newly recruited firefighters.

• Journal of the Korean Wood Science and Technology
• /
• v.50 no.6
• /
• pp.490-498
• /
• 2022

The current study aimed to verify the image segmentation ability of rays in tangential thin sections of conifers using artificial intelligence technology. The applied model was Mask region-based convolutional neural network (Mask R-CNN) and softwoods (viz. Picea jezoensis, Larix gmelinii, Abies nephrolepis, Abies koreana, Ginkgo biloba, Taxus cuspidata, Cryptomeria japonica, Cedrus deodara, Pinus koraiensis) were selected for the study. To take digital pictures, thin sections of thickness 10-15 ㎛ were cut using a microtome, and then stained using a 1:1 mixture of 0.5% astra blue and 1% safranin. In the digital images, rays were selected as detection objects, and Computer Vision Annotation Tool was used to annotate the rays in the training images taken from the tangential sections of the woods. The performance of the Mask R-CNN applied to select rays was as high as 0.837 mean average precision and saving the time more than half of that required for Ground Truth. During the image analysis process, however, division of the rays into two or more rays occurred. This caused some errors in the measurement of the ray height. To improve the image processing algorithms, further work on combining the fragments of a ray into one ray segment, and increasing the precision of the boundary between rays and the neighboring tissues is required.

• Smart Structures and Systems
• /
• v.30 no.2
• /
• pp.173-181
• /
• 2022

The current paper presents a technique to detect crack in non-uniform cantilever-type pipe beams, that have step changes in the properties of their cross sections, restrained by a translational and rotational spring with a tip mass at the free end. An equation for estimating the natural frequencies for the non-uniform beams is derived using the boundary and continuity conditions, and an equivalent bending stiffness for cracked beam is applied to calculate the natural frequencies of the cracked beam. An experimental study for a step-changed non-uniform cantilever-type pipe beam restrained by bolts with a tip mass is carried out to verify the proposed method. The translational and rotational spring constants are updated using the neural network technique to the results of the experiment for intact case in order to establish a baseline model for the subsequent crack detection. Then, several numerical simulations for the specimen are carried out using the derived equation for estimating the natural frequencies of the cracked beam to construct a set of training patterns of a neural network. The crack locations and sizes are identified using the trained neural network for the 5 damage cases. It is found that the crack locations and sizes are reasonably well estimated from a practical point of view. And it is considered that the usefulness of the proposed method for structural health monitoring of the step-changed non-uniform cantilever-type pipe beam-like structures elastically restrained in the ground and have a tip mass at the free end could be verified.

• The Journal of Korea Robotics Society
• /
• v.16 no.4
• /
• pp.306-312
• /
• 2021

This paper describes localization of autonomous underwater vehicles(AUV), which can be used when some navigation sensor data are an outlier. In that situation, localization through existing navigation algorithms causes problems in long-range localization. Even if an outlier sensor data occurs once, problems of localization will continue. Also, if outlier sensor data is related to azimuth (direction of AUV), it causes bigger problems. Therefore, a parallel localization module, in which different algorithms are performed in a normal and abnormal situation should be designed. Before designing a parallel localization module, it is necessary to study an effective method in the abnormal situation. So, we propose a localization method through machine learning. For this method, a learning model consists of only Fully-Connected and trains through randomly contaminated real sea data. The ground truth of training is displacement between subsequent GPS data. As a result, average error in localization through the learning model is 0.4 times smaller than the average error in localization through the existing navigation algorithm. Through this result, we conclude that it is suitable for a component of the parallel localization module.

• Journal of Information Processing Systems
• /
• v.19 no.5
• /
• pp.673-687
• /
• 2023

Convolutional neural network-based deep learning technology is the most commonly used in image identification, but it requires large-scale data for training. Therefore, application in specific fields in which data acquisition is limited, such as in the military, may be challenging. In particular, the identification of ground weapon systems is a very important mission, and high identification accuracy is required. Accordingly, various studies have been conducted to achieve high performance using small-scale data. Among them, the ensemble method, which achieves excellent performance through the prediction average of the pre-trained models, is the most representative method; however, it requires considerable time and effort to find the optimal combination of ensemble models. In addition, there is a performance limitation in the prediction results obtained by using an ensemble method. Furthermore, it is difficult to obtain the ensemble effect using models with imbalanced classification accuracies. In this paper, we propose a transfer learning-based feature fusion technique for heterogeneous models that extracts and fuses features of pre-trained heterogeneous models and finally, fine-tunes hyperparameters of the fully connected layer to improve the classification accuracy. The experimental results of this study indicate that it is possible to overcome the limitations of the existing ensemble methods by improving the classification accuracy through feature fusion between heterogeneous models based on transfer learning.