• Korean Journal of Plant Resources
• /
• v.35 no.2
• /
• pp.192-200
• /
• 2022

Nitrogen is the most essential macronutrient for the growth of fruit trees and is important factor determining the fruit yield. In order to produce high-quality fruits, it is necessary to supply the appropriate nitrogen fertilizer at the right time. For this, it is a prerequisite to accurately diagnose the nitrogen status of fruit trees. The fastest and most accurate way to determine the nitrogen deficiency of fruit trees is to measure the nitrogen concentration in leaves. However, it is not easy for citrus growers to measure nitrogen concentration through leaf analysis. In this study, several machine learning models were developed to classify the nitrogen deficiency based on the concentration measurement of mineral nutrients in the leaves of tangor Shiranuhi (Citrus unshiu × C. sinensis). The data analyzed from the leaves were increased to about 1,000 training dataset through the bootstrapping method and used to train the models. As a result of testing each model, gradient boosting model showed the best classification performance with an accuracy of 0.971.

• Tunnel and Underground Space
• /
• v.31 no.6
• /
• pp.508-519
• /
• 2021

In this study, a model was developed to predict the peak particle velocity (PPV) that affects people and the surrounding environment during blasting. Four machine learning models using the k-nearest neighbors (kNN), classification and regression tree (CART), support vector regression (SVR), and particle swarm optimization (PSO)-SVR algorithms were developed and compared with each other to predict the PPV. Mt. Yogmang located in Changwon-si, Gyeongsangnam-do was selected as a study area, and 1048 blasting data were acquired to train the machine learning models. The blasting data consisted of hole length, burden, spacing, maximum charge per delay, powder factor, number of holes, ratio of emulsion, monitoring distance and PPV. To evaluate the performance of the trained models, the mean absolute error (MAE), mean square error (MSE), and root mean square error (RMSE) were used. The PSO-SVR model showed superior performance with MAE, MSE and RMSE of 0.0348, 0.0021 and 0.0458, respectively. Finally, a method was proposed to predict the degree of influence on the surrounding environment using the developed machine learning models.

• Journal of Internet of Things and Convergence
• /
• v.8 no.5
• /
• pp.17-25
• /
• 2022

Recently the massive amount of data has been generated because of the number of edge devices increases. And especially, the number of raw unstructured HTML documents has been increased. Therefore, MRC(Machine Reading Comprehension) in which a natural language processing model finds the important information within an HTML document is becoming more important. In this paper, we propose HTDE(HTML Tag Depth Embedding Method), which allows the BERT to train the depth of the HTML document structure. HTDE makes a tag stack from the HTML document for each input token in the BERT and then extracts the depth information. After that, we add a HTML embedding layer that takes the depth of the token as input to the step of input embedding of BERT. Since tokenization using HTDE identifies the HTML document structures through the relationship of surrounding tokens, HTDE improves the accuracy of BERT for HTML documents. Finally, we demonstrated that the proposed idea showing the higher accuracy compared than the accuracy using the conventional embedding of BERT.

• Smart Media Journal
• /
• v.12 no.7
• /
• pp.59-67
• /
• 2023

Recently, research on behavior analysis tracking human posture and movement has been actively conducted. In particular, OpenPose, an open-source software developed by CMU in 2017, is a representative method for estimating human appearance and behavior. OpenPose can detect and estimate various body parts of a person, such as height, face, and hands in real-time, making it applicable to various fields such as smart healthcare, exercise training, security systems, and medical fields. In this paper, we propose a method for classifying four exercise movements - Squat, Walk, Wave, and Fall-down - which are most commonly performed by users in the gym, using OpenPose-based deep learning models, DNN and CNN. The training data is collected by capturing the user's movements through recorded videos and real-time camera captures. The collected dataset undergoes preprocessing using OpenPose. The preprocessed dataset is then used to train the proposed DNN and CNN models for exercise movement classification. The performance errors of the proposed models are evaluated using MSE, RMSE, and MAE. The performance evaluation results showed that the proposed DNN model outperformed the proposed CNN model.

• Nuclear Engineering and Technology
• /
• v.55 no.8
• /
• pp.3030-3038
• /
• 2023

Nowadays, mobile robots have been used to search for uncontrolled radioactive source in indoor environments to avoid radiation exposure for technicians. However, in the indoor environments, especially in the presence of obstacles, how to make the robots with limited sensing capabilities automatically search for the radioactive source remains a major challenge. Also, the source search efficiency of robots needs to be further improved to meet practical scenarios such as limited exploration time. This paper proposes an automatic source search strategy, abbreviated as ACA: the location of source is estimated by a convolutional neural network (CNN), and the path is planned by the A-star algorithm. First, the search area is represented as an occupancy grid map. Then, the radiation dose distribution of the radioactive source in the occupancy grid map is obtained by Monte Carlo (MC) method simulation, and multiple sets of radiation data are collected through the eight neighborhood self-avoiding random walk (ENSAW) algorithm as the radiation data set. Further, the radiation data set is fed into the designed CNN architecture to train the network model in advance. When the searcher enters the search area where the radioactive source exists, the location of source is estimated by the network model and the search path is planned by the A-star algorithm, and this process is iterated continuously until the searcher reaches the location of radioactive source. The experimental results show that the average number of radiometric measurements and the average number of moving steps of the ACA algorithm are only 2.1% and 33.2% of those of the gradient search (GS) algorithm in the indoor environment without obstacles. In the indoor environment shielded by concrete walls, the GS algorithm fails to search for the source, while the ACA algorithm successfully searches for the source with fewer moving steps and sparse radiometric data.

• Convergence Security Journal
• /
• v.23 no.1
• /
• pp.117-123
• /
• 2023

To detect advanced ransomware attacks with machine learning-based models, the classification model must train learning data with high-dimensional feature space. And in this case, a 'curse of dimension' phenomenon is likely to occur. Therefore, dimensionality reduction of features must be preceded in order to increase the accuracy of the learning model and improve the execution speed while avoiding the 'curse of dimension' phenomenon. In this paper, we conducted classification of ransomware by applying three machine learning models and two feature extraction techniques to two datasets with extremely different dimensions of feature space. As a result of the experiment, the feature dimensionality reduction techniques did not significantly affect the performance improvement in binary classification, and it was the same even when the dimension of featurespace was small in multi-class clasification. However, when the dataset had high-dimensional feature space, LDA(Linear Discriminant Analysis) showed quite excellent performance.

• International Journal of Computer Science & Network Security
• /
• v.23 no.4
• /
• pp.95-102
• /
• 2023

The emergence of Internet of Things (IoT) into our daily lives has grown rapidly. It's been integrated to our homes, cars, and cities, increasing the intelligence of devices involved in communications. Enormous amount of data is exchanged over smart devices through the internet, which raises security concerns in regards of privacy evasion. This paper is focused on the forensics and intrusion detection on one of the most common protocols in IoT environments, especially smart home environments, which is the Message Queuing Telemetry Transport (MQTT) protocol. The paper covers general IoT infrastructure, MQTT protocol and attacks conducted on it, and multiple network forensics frameworks in smart homes. Furthermore, a machine learning model is developed and tested to detect several types of attacks in an IoT network. A forensics tool (MQTTracker) is proposed to contribute to the investigation of MQTT protocol in order to provide a safer technological future in the warmth of people's homes. The MQTT-IOT-IDS2020 dataset is used to train the machine learning model. In addition, different attack detection algorithms are compared to ensure the suitable algorithm is chosen to perform accurate classification of attacks within MQTT traffic.

• Smart Structures and Systems
• /
• v.32 no.3
• /
• pp.153-166
• /
• 2023

Health monitoring of civil infrastructures, in particular, old bridges that are still in service, has become more than necessary, given the risk that a possible degradation or failure of these infrastructures can induce on the safety of users in addition to the resulting commercial and economic impact. Bridge integrity assessment has attracted significant research efforts over the past forty years with the aim of developing new damage identification methods applicable to real structures. The bridge of Ouled Mimoun (Tlemcen, Algeria) is one of the oldest railway structure in the country. It was built in 1889. This bridge, which is too low with respect to the level of the road, has suffered multiple shocks from various machines that caused considerable damage to its central part. The present work aims to analyze the stability of this bridge by identifying damages and evaluating the damage rate in different parts of the structure on the basis of a finite element model. The applied method is based on an inverse analysis of the normal stress responses that were calculated from the corresponding recorded strains, during the passage of a real train, by means of a set of strain gauges placed on certain elements of the bridge. The results obtained from the inverse analysis made it possible to successfully locate areas that were really damaged and to estimate the damage rate. These results were also used to detect an excessive rigidity in certain elements due to the presence of plates, which were neglected in the numerical reference model. In the case of the continuous bridge monitoring, this developed method will be a very powerful tool as a smart health monitoring system, allowing engineers to take in time decisions in the event of bridge damage.

• Korean Medical Education Review
• /
• v.25 no.3
• /
• pp.192-197
• /
• 2023

Physicians should be able to address health-related issues of patients and populations from a multidimensional perspective. Therefore, medical schools have a social responsibility to develop and implement curricula that enable trainees to acquire the competencies needed to improve all aspects of patient care and healthcare delivery. This study explored the concept of health systems science concept as the third pillar of medical education (the other two are basic science and clinical medicine) in the Korean context, as well as related educational needs. The theoretical foundation of health systems science is the biopsychosocial conceptual model, which emphasizes the biological, psychological, and social factors surrounding patients. We concluded that the three domains (core functional, foundational, linking) and 12 subcategories of health systems science proposed by the Association of American Medical Colleges could be applied to Korean medical education. Health systems science education must be emphasized to solve the various healthcare problems facing Korea today and to train physicians to provide medical services in line with society's needs. Introducing a health systems science curriculum will be challenging in the Korean medical environment, which has traditionally emphasized basic science and clinical medical education. Health systems science education should begin in the basic medical education phase, where physicians' professional identity is formed, and continue through graduate medical education. It is essential to understand related educational needs, develop curricular content, conduct faculty development programs, and provide financial resources for the development of an integrated curriculum.

• KSII Transactions on Internet and Information Systems (TIIS)
• /
• v.18 no.2
• /
• pp.263-283
• /
• 2024

Users' comments after online shopping are critical to product reputation and business improvement. These comments, sometimes known as e-commerce reviews, influence other customers' purchasing decisions. To confront large amounts of e-commerce reviews, automatic analysis based on machine learning and deep learning draws more and more attention. A core task therein is sentiment analysis. However, the e-commerce reviews exhibit the following characteristics: (1) inconsistency between comment content and the star rating; (2) a large number of unlabeled data, i.e., comments without a star rating, and (3) the data imbalance caused by the sparse negative comments. This paper employs Bidirectional Encoder Representation from Transformers (BERT), one of the best natural language processing models, as the base model. According to the above data characteristics, we propose the F_MixBERT framework, to more effectively use inconsistently low-quality and unlabeled data and resolve the problem of data imbalance. In the framework, the proposed MixBERT incorporates the MixMatch approach into BERT's high-dimensional vectors to train the unlabeled and low-quality data with generated pseudo labels. Meanwhile, data imbalance is resolved by Focal loss, which penalizes the contribution of large-scale data and easily-identifiable data to total loss. Comparative experiments demonstrate that the proposed framework outperforms BERT and MixBERT for sentiment analysis of e-commerce comments.