• Geomechanics and Engineering
• /
• v.30 no.6
• /
• pp.489-502
• /
• 2022

In this study, a Gaussian process regression (GPR) model as well as six GPR-based metaheuristic optimization models, including GPR-PSO, GPR-GWO, GPR-MVO, GPR-MFO, GPR-SCA, and GPR-SSO, were developed to predict fly-rock distance in the blasting operation of open pit mines. These models included GPR-SCA, GPR-SSO, GPR-MVO, and GPR. In the models that were obtained from the Soungun copper mine in Iran, a total of 300 datasets were used. These datasets included six input parameters and one output parameter (fly-rock). In order to conduct the assessment of the prediction outcomes, many statistical evaluation indices were used. In the end, it was determined that the performance prediction of the ML models to predict the fly-rock from high to low is GPR-PSO, GPR-GWO, GPR-MVO, GPR-MFO, GPR-SCA, GPR-SSO, and GPR with ranking scores of 66, 60, 54, 46, 43, 38, and 30 (for 5-fold method), respectively. These scores correspond in conclusion, the GPR-PSO model generated the most accurate findings, hence it was suggested that this model be used to forecast the fly-rock. In addition, the mutual information test, also known as MIT, was used in order to investigate the influence that each input parameter had on the fly-rock. In the end, it was determined that the stemming (T) parameter was the most effective of all the parameters on the fly-rock.

• Journal of Positioning, Navigation, and Timing
• /
• v.12 no.2
• /
• pp.91-100
• /
• 2023

The existing indoor localization method using Wi-Fi fingerprinting has a high collection cost and relatively low accuracy, thus requiring integrated correction of convergence with other technologies. This paper proposes a new method that significantly reduces collection costs compared to existing methods using Wi-Fi fingerprinting. Furthermore, it does not require labeling of data at collection and can estimate pedestrian travel paths even in large indoor spaces. The proposed pedestrian movement path estimation process is as follows. Data collection is accomplished by setting up a feature area near an indoor space intersection, moving through the set feature areas, and then collecting data without labels. The collected data are processed using Kernel Linear Discriminant Analysis (KLDA) and the valley point of the Euclidean distance value between two data is obtained within the feature space of the data. We build learning data by labeling data corresponding to valley points and some nearby data by feature area numbers, and labeling data between valley points and other valley points as path data between each corresponding feature area. Finally, for testing, data are collected randomly through indoor space, KLDA is applied as previous data to build test data, the K-Nearest Neighbor (K-NN) algorithm is applied, and the path of movement of test data is estimated by applying a correction algorithm to estimate only routes that can be reached from the most recently estimated location. The estimation results verified the accuracy by comparing the true paths in indoor space with those estimated by the proposed method and achieved approximately 90.8% and 81.4% accuracy in two experimental spaces, respectively.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.137-147
• /
• 2023

LiDAR is used in autonomous driving and various industrial fields to measure the size and distance of an object. In addition, the sensor also provides intensity images based on the amount of reflected light. This has a positive effect on sensor data processing by providing information on the shape of the object. LiDAR guarantees higher performance as the resolution increases but at an increased cost. These conditions also apply to LiDAR intensity images. Expensive equipment is essential to acquire high-resolution LiDAR intensity images. This study developed artificial intelligence to improve low-resolution LiDAR intensity images into high-resolution ones. Therefore, this study performed parameter analysis for the optimal super-resolution neural network model. The super-resolution algorithm was trained and verified using 2,500 LiDAR intensity images. As a result, the resolution of the intensity images were improved. These results can be applied to the autonomous driving field and help improve driving environment recognition and obstacle detection performance

• Journal of the Korea Society of Computer and Information
• /
• v.29 no.1
• /
• pp.77-84
• /
• 2024

In this paper, we propose a method for accurately and rapidly detecting defects in wire harnesses by utilizing computer vision to calculate six crucial measurement values: the length of crimped terminals, the dimensions (width) of terminal ends, and the width of crimped sections (wire and core portions). We employ Harris corner detection to locate object positions from two types of data. Additionally, we generate reference points for extracting measurement values by utilizing features specific to each measurement area and exploiting the contrast in shading between the background and objects, thus reflecting the slope of each sample. Subsequently, we introduce a method using the Euclidean distance and correction coefficients to predict values, allowing for the prediction of measurements regardless of changes in the wire's position. We achieve high accuracy for each measurement type, 99.1%, 98.7%, 92.6%, 92.5%, 99.9%, and 99.7%, achieving outstanding overall average accuracy of 97% across all measurements. This inspection method not only addresses the limitations of conventional visual inspections but also yields excellent results with a small amount of data. Moreover, relying solely on image processing, it is expected to be more cost-effective and applicable with less data compared to deep learning methods.

• Journal of Cadastre & Land InformatiX
• /
• v.48 no.1
• /
• pp.169-186
• /
• 2018

The social influence of the elderly population will accelerate in a rapidly aging society. The purpose of this study is to establish a methodology for extracting vulnerable districts of the welfare of the aged through machine learning(ML), artificial neural network(ANN) and geospatial analysis. In order to establish the direction of analysis, this progressed after an interview with volunteers who over 65-year old people, public officer and the manager of the aged welfare facility. The indicators are the geographic distance capacity, elderly welfare enjoyment, officially assessed land price and mobile communication based on old people activities where 500 m vector areal unit within 15 minutes in Yongin-city, Gyeonggi-do. As a result, the prediction accuracy of 83.2% in the support vector machine(SVM) of ML using the RBF kernel algorithm was obtained in simulation. Furthermore, the correlation result(0.63) was derived from ANN using backpropagation algorithm. A geographically weighted regression(GWR) was also performed to analyze spatial autocorrelation within variables. As a result of this analysis, the coefficient of determination was 70.1%, which showed good explanatory power. Moran's I and Getis-Ord Gi coefficients are analyzed to investigate spatially outlier as well as distribution patterns. This study can be used to solve the welfare imbalance of the aged considering the local conditions of the government recently.

• Korean Journal of Radiology
• /
• v.22 no.11
• /
• pp.1850-1857
• /
• 2021

Objective: The purpose of this study was to assess whether a deep learning (DL) algorithm could enable simultaneous noise reduction and edge sharpening in low-dose lumbar spine CT. Materials and Methods: This retrospective study included 52 patients (26 male and 26 female; median age, 60.5 years) who had undergone CT-guided lumbar bone biopsy between October 2015 and April 2020. Initial 100-mAs survey images and 50-mAs intraprocedural images were reconstructed by filtered back projection. Denoising was performed using a vendor-agnostic DL model (ClariCT.AI^TM, ClariPI) for the 50-mAS images, and the 50-mAs, denoised 50-mAs, and 100-mAs CT images were compared. Noise, signal-to-noise ratio (SNR), and edge rise distance (ERD) for image sharpness were measured. The data were summarized as the mean ± standard deviation for these parameters. Two musculoskeletal radiologists assessed the visibility of the normal anatomical structures. Results: Noise was lower in the denoised 50-mAs images (36.38 ± 7.03 Hounsfield unit [HU]) than the 50-mAs (93.33 ± 25.36 HU) and 100-mAs (63.33 ± 16.09 HU) images (p < 0.001). The SNRs for the images in descending order were as follows: denoised 50-mAs (1.46 ± 0.54), 100-mAs (0.99 ± 0.34), and 50-mAs (0.58 ± 0.18) images (p < 0.001). The denoised 50-mAs images had better edge sharpness than the 100-mAs images at the vertebral body (ERD; 0.94 ± 0.2 mm vs. 1.05 ± 0.24 mm, p = 0.036) and the psoas (ERD; 0.42 ± 0.09 mm vs. 0.50 ± 0.12 mm, p = 0.002). The denoised 50-mAs images significantly improved the visualization of the normal anatomical structures (p < 0.001). Conclusion: DL-based reconstruction may enable simultaneous noise reduction and improvement in image quality with the preservation of edge sharpness on low-dose lumbar spine CT. Investigations on further radiation dose reduction and the clinical applicability of this technique are warranted.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.7
• /
• pp.1216-1221
• /
• 2022

Ships tend to be larger to increase the efficiency of cargo transportation. Larger ships lead to increased travel time for ship workers, increased work intensity, and reduced work efficiency. Problems such as increased work intensity are reducing the influx of young people into labor, along with the phenomenon of avoidance of high intensity labor by the younger generation. In addition, the rapid aging of the population and decrease in the young labor force aggravate the labor shortage problem in the maritime industry. To overcome this, the maritime industry has recently introduced technologies such as an intelligent production design platform and a smart production operation management system, and a smart autonomous logistics system in one of these technologies. The smart autonomous logistics system is a technology that delivers various goods using intelligent mobile robots, and enables the robot to drive itself by using sensors such as lidar and camera. Therefore, in this paper, it was checked whether the mobile robot could autonomously drive to the stop sign by detecting the passage way of the ship deck. The autonomous driving was performed by detecting the passage way of the ship deck through the camera mounted on the mobile robot based on the data learned through Nvidia's End-to-end learning. The mobile robot was stopped by checking the stop sign using SSD MobileNetV2. The experiment was repeated five times in which the mobile robot autonomously drives to the stop sign without deviation from the ship deck passage way at a distance of about 70m. As a result of the experiment, it was confirmed that the mobile robot was driven without deviation from passage way. If the smart autonomous logistics system to which this result is applied is used in the marine industry, it is thought that the stability, reduction of labor force, and work efficiency will be improved when workers work.

• Journal of Intelligence and Information Systems
• /
• v.25 no.1
• /
• pp.163-177
• /
• 2019

As smartphones are getting widely used, human activity recognition (HAR) tasks for recognizing personal activities of smartphone users with multimodal data have been actively studied recently. The research area is expanding from the recognition of the simple body movement of an individual user to the recognition of low-level behavior and high-level behavior. However, HAR tasks for recognizing interaction behavior with other people, such as whether the user is accompanying or communicating with someone else, have gotten less attention so far. And previous research for recognizing interaction behavior has usually depended on audio, Bluetooth, and Wi-Fi sensors, which are vulnerable to privacy issues and require much time to collect enough data. Whereas physical sensors including accelerometer, magnetic field and gyroscope sensors are less vulnerable to privacy issues and can collect a large amount of data within a short time. In this paper, a method for detecting accompanying status based on deep learning model by only using multimodal physical sensor data, such as an accelerometer, magnetic field and gyroscope, was proposed. The accompanying status was defined as a redefinition of a part of the user interaction behavior, including whether the user is accompanying with an acquaintance at a close distance and the user is actively communicating with the acquaintance. A framework based on convolutional neural networks (CNN) and long short-term memory (LSTM) recurrent networks for classifying accompanying and conversation was proposed. First, a data preprocessing method which consists of time synchronization of multimodal data from different physical sensors, data normalization and sequence data generation was introduced. We applied the nearest interpolation to synchronize the time of collected data from different sensors. Normalization was performed for each x, y, z axis value of the sensor data, and the sequence data was generated according to the sliding window method. Then, the sequence data became the input for CNN, where feature maps representing local dependencies of the original sequence are extracted. The CNN consisted of 3 convolutional layers and did not have a pooling layer to maintain the temporal information of the sequence data. Next, LSTM recurrent networks received the feature maps, learned long-term dependencies from them and extracted features. The LSTM recurrent networks consisted of two layers, each with 128 cells. Finally, the extracted features were used for classification by softmax classifier. The loss function of the model was cross entropy function and the weights of the model were randomly initialized on a normal distribution with an average of 0 and a standard deviation of 0.1. The model was trained using adaptive moment estimation (ADAM) optimization algorithm and the mini batch size was set to 128. We applied dropout to input values of the LSTM recurrent networks to prevent overfitting. The initial learning rate was set to 0.001, and it decreased exponentially by 0.99 at the end of each epoch training. An Android smartphone application was developed and released to collect data. We collected smartphone data for a total of 18 subjects. Using the data, the model classified accompanying and conversation by 98.74% and 98.83% accuracy each. Both the F1 score and accuracy of the model were higher than the F1 score and accuracy of the majority vote classifier, support vector machine, and deep recurrent neural network. In the future research, we will focus on more rigorous multimodal sensor data synchronization methods that minimize the time stamp differences. In addition, we will further study transfer learning method that enables transfer of trained models tailored to the training data to the evaluation data that follows a different distribution. It is expected that a model capable of exhibiting robust recognition performance against changes in data that is not considered in the model learning stage will be obtained.

• Journal of the Korean earth science society
• /
• v.32 no.2
• /
• pp.212-224
• /
• 2011

In school science class, actual geological field trips tend to be restricted due to a number of problems including travel distance, cost, safety, and so on. Therefore, alternative way should be sought to provide students with the benefits of actual field trip. The purpose of this study is to develop web-based virtual field trip (VFT) about Jeju island in Korea by using flash panorama, and to explore a variety of ways to utilize the VFT. The characteristics of Jeju VFT are as follows: it provides virtual space for secondary school students to learn about volcanic topography and geology; students can access contents in a non-sequential order by virtue of web-based system, and students can control learning pace according to their ability; it is possible to investigate the same field site repeatedly, not limited by time and space; it presents differentiated worksheets for different school grade; it provides diverse complementary web contents, e. g., closeup features, thin sections, inquiry questions, and explanations of outcrops. We proposed several ways with instructional models to utilize Jeju VFT in science class and extra-school curricular as well.

• Journal of the Korean Institute of Intelligent Systems
• /
• v.19 no.4
• /
• pp.562-567
• /
• 2009

As a key mechanism of the human emotion interaction, Facial Expression is a powerful tools in HRI(Human Robot Interface) such as Human Computer Interface. By using a facial expression, we can bring out various reaction correspond to emotional state of user in HCI(Human Computer Interaction). Also it can infer that suitable services to supply user from service agents such as intelligent robot. In this article, We addresses the issue of expressive face modeling using an advanced active appearance model for facial emotion recognition. We consider the six universal emotional categories that are defined by Ekman. In human face, emotions are most widely represented with eyes and mouth expression. If we want to recognize the human's emotion from this facial image, we need to extract feature points such as Action Unit(AU) of Ekman. Active Appearance Model (AAM) is one of the commonly used methods for facial feature extraction and it can be applied to construct AU. Regarding the traditional AAM depends on the setting of the initial parameters of the model and this paper introduces a facial emotion recognizing method based on which is combined Advanced AAM with Bayesian Network. Firstly, we obtain the reconstructive parameters of the new gray-scale image by sample-based learning and use them to reconstruct the shape and texture of the new image and calculate the initial parameters of the AAM by the reconstructed facial model. Then reduce the distance error between the model and the target contour by adjusting the parameters of the model. Finally get the model which is matched with the facial feature outline after several iterations and use them to recognize the facial emotion by using Bayesian Network.