• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.4
• /
• pp.169-178
• /
• 2022

Morphemes are most primitive units in a language that lose their original meaning when segmented into smaller parts. In Korean, a sentence is a sequence of eojeols (words) separated by spaces. Each eojeol comprises one or more morphemes. Korean morphological analysis (KMA) is to divide eojeols in a given Korean sentence into morpheme units. It also includes assigning appropriate part-of-speech(POS) tags to the resulting morphemes. KMA is one of the most important tasks in Korean natural language processing (NLP). Improving the performance of KMA is closely related to increasing performance of Korean NLP tasks. Recent research on KMA has begun to adopt the approach of machine translation (MT) models. MT is to convert a sequence (sentence) of units of one domain into a sequence (sentence) of units of another domain. Neural machine translation (NMT) stands for the approaches of MT that exploit neural network models. From a perspective of MT, KMA is to transform an input sequence of units belonging to the eojeol domain into a sequence of units in the morpheme domain. In this paper, we propose a deep learning model for KMA. The backbone of our model is based on the BERT-fused model which was shown to achieve high performance on NMT. The BERT-fused model utilizes Transformer, a representative model employed by NMT, and BERT which is a language representation model that has enabled a significant advance in NLP. The experimental results show that our model achieves 98.24 F1-Score.

• Journal of the Korea Society of Computer and Information
• /
• v.27 no.3
• /
• pp.33-43
• /
• 2022

In this paper, we propose an ensemble model facilitated by multi-channel palm images with attention U-Net models and pretrained convolutional neural networks (CNNs) for establishing a contactless palm-based user identification system using conventional inexpensive camera sensors. Attention U-Net models are used to extract the areas of interest including hands (i.e., with fingers), palms (i.e., without fingers) and palm lines, which are combined to generate three channels being ped into the ensemble classifier. Then, the proposed palm information-based user identification system predicts the class using the classifier ensemble with three outperforming pre-trained CNN models. The proposed model demonstrates that the proposed model could achieve the classification accuracy, precision, recall, F1-score of 98.60%, 98.61%, 98.61%, 98.61% respectively, which indicate that the proposed model is effective even though we are using very cheap and inexpensive image sensors. We believe that in this COVID-19 pandemic circumstances, the proposed palm-based contactless user identification system can be an alternative, with high safety and reliability, compared with currently overwhelming contact-based systems.

• Journal of the Korean Society of Marine Environment & Safety
• /
• v.28 no.4
• /
• pp.601-609
• /
• 2022

Jack-up drilling rigs are mobile offshore platforms widely used in the offshore oil and gas exploration industry. These are independent, three-legged, self-elevating units with a cantilevered drilling facility for drilling and production. A typical jack-up rig includes a triangular hull, a tower derrick, a cantilever, a jackcase, living quarters and legs which comprise three-chord, open-truss, X-braced structure with a spudcan. Generally, jack-up rigs can only operate in water depths ranging from 130m to 170m. Recently, there has been an increasing demand for jack-up rigs for operating at deeper water levels and harsher environmental conditions such as waves, currents and wind loads. All static and dynamic loads are supported through legs in the jack-up mode. The most important issue by society is to secure the safety of the leg structure against collision that causes large instantaneous impact energy. In this study, nonlinear FE -analysis and verification of the requirement against collision for 35MJ recommended by DNV was performed using LS-Dyna software. The colliding ship used a 7,500ton of shore supply vessel, and five scenarios of collisions were selected. From the results, all conditions do not satisfy the class requirement of 35MJ. The loading conditions associated with chord collision are reasonable collision energy of 15M and brace collisions are 6MJ. Therefore, it can be confirmed that the identical collision criteria by DNV need to be modified based on collision scenarios and colliding members.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.291-298
• /
• 2022

In this paper, we present a method for dependency parsing with chunking in Korean. Dependency parsing is a task of determining a governor of every word in a sentence. In general, we used to determine the syntactic governor in Korean and should transform the syntactic structure into semantic structure for further processing like semantic analysis in natural language processing. There is a notorious problem to determine whether syntactic or semantic governor. For example, the syntactic governor of the word "먹고 (eat)" in the sentence "밥을 먹고 싶다 (would like to eat)" is "싶다 (would like to)", which is an auxiliary verb and therefore can not be a semantic governor. In order to mitigate this somewhat, we propose a Korean dependency parsing after chunking, which is a process of segmenting a sentence into constituents. A constituent is a word or a group of words that function as a single unit within a dependency structure and is called a chunk in this paper. Compared to traditional dependency parsing, there are some advantage of the proposed method: (1) The number of input units in parsing can be reduced and then the parsing speed could be faster. (2) The effectiveness of parsing can be improved by considering the relation between two head words in chunks. Through experiments for Sejong dependency corpus, we have shown that the USA and LAS of the proposed method are 86.48% and 84.56%, respectively and the number of input units is reduced by about 22%p.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.7
• /
• pp.299-306
• /
• 2022

In recent, sensors embedded in robots, equipment, and circuits have become common, and research for diagnosing device failures by learning measured sensor data is being actively conducted. This failure diagnosis study is divided into a classification model for predicting failure situations or types and a regression model for numerically predicting failure conditions. In the case of a classification model, it simply checks the presence or absence of a failure or defect (Class), whereas a regression model has a higher learning difficulty because it has to predict one value among countless numbers. So, the reason that regression modeling is more difficult is that there are many irregular situations in which it is difficult to determine one output from a similar input when predicting by matching input and output. Therefore, in this paper, we focus on input and output data with periodicity, analyze the input/output relationship, and secure regularity between input and output data by performing sliding window-based input data patterning. In order to apply the proposed method, in this study, current and temperature data with periodicity were collected from MMC(Modular Multilevel Converter) circuit system and learning was carried out using ANN. As a result of the experiment, it was confirmed that when a window of 2% or more of one cycle was applied, performance of 97% or more of fit could be secured.

• Journal of Internet Computing and Services
• /
• v.23 no.5
• /
• pp.79-85
• /
• 2022

Anomaly detection is a method to detect and block abnormal data flows in general users' data sets. The previously known method is a method of detecting and defending an attack based on a signature using the signature of an already known attack. This has the advantage of a low false positive rate, but the problem is that it is very vulnerable to a zero-day vulnerability attack or a modified attack. However, in the case of anomaly detection, there is a disadvantage that the false positive rate is high, but it has the advantage of being able to identify, detect, and block zero-day vulnerability attacks or modified attacks, so related studies are being actively conducted. In this study, we want to deal with these anomaly detection mechanisms, and we propose a new mechanism that performs both anomaly detection and classification while supplementing the high false positive rate mentioned above. In this study, the experiment was conducted with five configurations considering the characteristics of various algorithms. As a result, the model showing the best accuracy was proposed as the result of this study. After detecting an attack by applying the Extra Tree and Three-layer ANN at the same time, the attack type is classified using the Extra Tree for the classified attack data. In this study, verification was performed on the NSL-KDD data set, and the accuracy was 99.8%, 99.1%, 98.9%, 98.7%, and 97.9% for Normal, Dos, Probe, U2R, and R2L, respectively. This configuration showed superior performance compared to other models.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.51-58
• /
• 2022

Drivable area detection, one of the main functions of advanced driver assistance systems, means detecting an area where a vehicle can safely drive. The drivable area detection is closely related to the safety of the driver and it requires high accuracy with real-time operation. To satisfy these conditions, V-disparity-based method is widely used to detect a drivable area by calculating the road disparity value in each row of an image. However, the V-disparity-based method can falsely detect a non-road area as a road when the disparity value is not accurate or the disparity value of the object is equal to the disparity value of the road. In a road environment including vegetation, such as a highway and a country road, the vegetation area may be falsely detected as the drivable area because the disparity characteristics of the vegetation are similar to those of the road. Therefore, this paper proposes a drivable area detection method and hardware architecture with a high accuracy in road environments including vegetation areas by reducing the number of false detections caused by V-disparity characteristic. When 289 images provided by KITTI road dataset are used to evaluate the road detection performance of the proposed method, it shows an accuracy of 90.12% and a recall of 97.96%. In addition, when the proposed hardware architecture is implemented on the FPGA platform, it uses 8925 slice registers and 7066 slice LUTs.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.1
• /
• pp.1-10
• /
• 2022

Deep neural networks are widely used to solve various problems. In a fully connected neural network, the nonlinear activation function is a function that nonlinearly transforms the input value and outputs it. The nonlinear activation function plays an important role in solving the nonlinear problem, and various nonlinear activation functions have been studied. In this study, we propose a combined parametric activation function that can improve the performance of a fully connected neural network. Combined parametric activation functions can be created by simply adding parametric activation functions. The parametric activation function is a function that can be optimized in the direction of minimizing the loss function by applying a parameter that converts the scale and location of the activation function according to the input data. By combining the parametric activation functions, more diverse nonlinear intervals can be created, and the parameters of the parametric activation functions can be optimized in the direction of minimizing the loss function. The performance of the combined parametric activation function was tested through the MNIST classification problem and the Fashion MNIST classification problem, and as a result, it was confirmed that it has better performance than the existing nonlinear activation function and parametric activation function.

• Journal of Digital Convergence
• /
• v.19 no.11
• /
• pp.351-357
• /
• 2021

IoT devices, which are used in various ways in distributed environments, are becoming more important in data transmitted and received from IoT devices as fields of use such as medical, environment, transportation, bio, and public places are diversified. In this paper, as a method to ensure the reliability of IoT data, an autoencoder-based IoT-linked processing technique is proposed to classify and process numerous data by various important attributes. The proposed technique uses correlation indices for each IoT data so that IoT data is grouped and processed by blockchain by characteristics for IoT linkage processing based on autoencoder. The proposed technique expands and operates into a blockchain-based n-layer structure applied to the correlation index to ensure the reliability of IoT data. In addition, the proposed technique can not only select IoT data by applying weights to IoT collection data according to the correlation index of IoT data, but also reduce the cost of verifying the integrity of IoT data in real time. The proposed technique maintains the processing cost of IoT data so that IoT data can be expanded to an n-layer structure.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.11
• /
• pp.439-448
• /
• 2021

Driver negligence accounts for the largest proportion of the causes of traffic accidents, and research to detect them is continuously being conducted. This paper proposes a method to accurately detect a distracted driver and localize the most characteristic parts of the driver. The proposed method hierarchically constructs a CNN basic model that classifies 10 classes based on CAM in order to detect driver distration and 4 subclass models for detailed classification of classes having a confusing or common feature area in this model. The classification result output from each model can be considered as a new feature indicating the degree of matching with the CNN feature maps, and the accuracy of classification is improved by horizontally combining and learning them. In addition, by combining the heat map results reflecting the classification results of the basic and detailed classification models, the characteristic areas of attention in the image are found. The proposed method obtained an accuracy of 95.14% in an experiment using the State Farm data set, which is 2.94% higher than the 92.2%, which is the highest accuracy among the results using this data set. Also, it was confirmed by the experiment that more meaningful and accurate attention areas were found than the results of the attention area found when only the basic model was used.