• The KIPS Transactions:PartB
• /
• v.10B no.3
• /
• pp.347-358
• /
• 2003

VSField-associated term is a single or compound word whose terms occur in any document, and which makes it possible to recognize a field of text by using common knowledge of human. For example, human recognizes the field of document such as or , a field name of text, when she encounters a word 'Pitcher' or 'election', respectively We Proposes an efficient construction method of field-associated terms (FTs) for specializing field to decide a field of text. We could fix document classification scheme from well-classified document database or corpus. Considering focus field we discuss levels and stability ranks of field-associated terms. To construct a balanced FT collection, we construct a single FTs. From the collections we could automatically construct FT's levels, and stability ranks. We propose a new extraction algorithms of FT's for document classification by using FT's concentration rate, its occurrence frequencies.

• KIPS Transactions on Software and Data Engineering
• /
• v.11 no.11
• /
• pp.473-478
• /
• 2022

Evaluation learning based on code testing is becoming a popular solution in programming education via Online judge(OJ). In the recent past, many papers have been published on how to detect plagiarism through source code similarity analysis to support OJ. However, deep learning-based research to support automated tutoring is insufficient. In this paper, we propose Input & Output side FiLM models to predict whether the input code will pass or fail. By applying Feature-wise Linear Modulation(FiLM) technique to GRU, our model can learn combined information of Java byte codes and problem information that it tries to solve. On experimental design, a balanced sampling technique was applied to evenly distribute the data due to the occurrence of asymmetry in data collected by OJ. Among the proposed models, the Input Side FiLM model showed the highest performance of 73.63%. Based on result, it has been shown that students can check whether their codes will pass or fail before receiving the OJ evaluation which could provide basic feedback for improvements.

• The Journal of Korean Institute of Communications and Information Sciences
• /
• v.39C no.1
• /
• pp.28-35
• /
• 2014

Surveillance cameras in national border and coastline area often occur the video distortion because of rapidly changing weather and light environments. It is positively necessary to enhance the distorted video quality for keeping surveillance. In this paper, we propose an adaptive video enhancement algorithm in the various environment changes. To solve an unstable performance problem of the existing method, the proposed method is based on Retinex algorithm and uses enhanced curves which is adapted in foggy and low-light conditions. In addition, we mixture the weighted HSV color model to keep color constancy and reduce noise to obtain clear images. As a results, the proposed algorithm improves the performance of well-balanced contrast enhancement and effective color restoration without any quality loss compared with the existing algorithm. We expect that this method will be used in surveillance camera systems and offer help of national defence with reliability.

• Proceedings of the Korea Information Processing Society Conference
• /
• 2011.04a
• /
• pp.576-579
• /
• 2011

Wireless sensor network are widely all over different fields. Because of its distinguished characteristics, we must take account of the factor of energy consumed when designing routing protocol. Wireless sensor networks consist of small battery powered devices with limited energy resources. Once deployed, the small sensor nodes are usually inaccessible to the user, and thus replacement of the energy source is not feasible. Hence, energy efficiency is a key design issue that needs to be enhanced in order to improve the life span of the network. In BCDCP, all sensors sends data from the CH (Cluster Head) and then to the BS (Base Station). BCDCP works well in a smallscale network however is not preferred in a large scale network since it uses much energy for long distance wireless communication. TBRP can be used for large scale network, but it weakness lies on the fact that the nodedry out of energy easily since it uses multi-hops transmission data to the Base Station. Here, we proposed a routing protocol. A Cluster Based Energy Efficient Tree Routing Protocol (CETRP) in Wireless Sensor Networks (WSNs) to prolong network life time through the balanced energy consumption. CETRP selects Cluster Head of cluster tree shape and uses maximum two hops data transmission to the Cluster Head in every level. We show CETRP outperforms BCDCP and TBRP with several experiments.

• Journal of Intelligence and Information Systems
• /
• v.29 no.1
• /
• pp.121-142
• /
• 2023

As the number and weight of imported food are steadily increasing, safety management of imported food to prevent food safety accidents is becoming more important. The Ministry of Food and Drug Safety conducts on-site inspections of foreign food facilities before customs clearance as well as import inspection at the customs clearance stage. However, a data-based safety management plan for imported food is needed due to time, cost, and limited resources. In this study, we tried to increase the efficiency of the on-site inspection by preparing a machine learning prediction model that pre-selects the companies that are expected to fail before the on-site inspection. Basic information of 303,272 foreign food facilities and processing businesses collected in the Integrated Food Safety Information Network and 1,689 cases of on-site inspection information data collected from 2019 to April 2022 were collected. After preprocessing the data of foreign food facilities, only the data subject to on-site inspection were extracted using the foreign food facility_code. As a result, it consisted of a total of 1,689 data and 103 variables. For 103 variables, variables that were '0' were removed based on the Theil-U index, and after reducing by applying Multiple Correspondence Analysis, 49 characteristic variables were finally derived. We build eight different models and perform hyperparameter tuning through 5-fold cross validation. Then, the performance of the generated models are evaluated. The research purpose of selecting companies subject to on-site inspection is to maximize the recall, which is the probability of judging nonconforming companies as nonconforming. As a result of applying various algorithms of machine learning, the Random Forest model with the highest Recall_macro, AUROC, Average PR, F1-score, and Balanced Accuracy was evaluated as the best model. Finally, we apply Kernal SHAP (SHapley Additive exPlanations) to present the selection reason for nonconforming facilities of individual instances, and discuss applicability to the on-site inspection facility selection system. Based on the results of this study, it is expected that it will contribute to the efficient operation of limited resources such as manpower and budget by establishing an imported food management system through a data-based scientific risk management model.

• The KIPS Transactions:PartC
• /
• v.15C no.4
• /
• pp.303-310
• /
• 2008

To increase the lifetime of ad-hoc networks, a ratio of energy consumption for each node should be kept constant by equally distributing network traffic loads into all of the nodes. In this paper, we propose a modified AODV routing protocol to determine a possible route by considering a remaining battery capacity of a node and the degree of its usage. In addition, to reduce the amount of energy consumption during the path rediscovery process due to the huge amount of the AODV control messages the limited number of possible routes are stored into a routing table of a source node. When some links of a route fail, another possible path can be looked up in the table before the route discovery process should be initiated. We have tested our proposed method with a conventional AODV and a MMBCR method which is one of the power-efficient energy routing protocols based on the three performance metrics, i.e., the total remaining battery capacity, network lifetime and the ratio of data packets received by the destination node to compare their performance.

• KIPS Transactions on Computer and Communication Systems
• /
• v.1 no.2
• /
• pp.99-102
• /
• 2012

The performance of P2P application services may be improved by reducing unnecessary inter-network traffic through intelligent peer selection. However, since a logical link between peers in a P2P overlay network is composed of a set of physical links in an underlay network, the traffic pattern determined by the sending rates of selected peers imposes loads on each underlay links. Thus, if the sending rates are not determined carefully, the loads between underlay links may not be balanced, which means some links are underloaded while the other links are congested. In this paper, we take an optimization approach to determine the sending rates of peers strategically to avoid the inefficient use of underlay links. The proposed scheme also guarantee the minimum receiving rates of peers while minimizing the maximum link utilization of underlay links, which is beneficial both to P2P applications and an underlay network.

• KIPS Transactions on Computer and Communication Systems
• /
• v.12 no.8
• /
• pp.235-242
• /
• 2023

In recent years, as online counseling for infants and adolescents has increased, CNN-based deep learning models are widely used as assistance tools for emotion recognition. However, since most emotion recognition models are trained on mainly adult data, there are performance restrictions to apply the model to infants and adolescents. In this paper, in order to analyze the performance constraints, the characteristics of facial expressions for emotional recognition of infants and adolescents compared to adults are analyzed through LIME method, one of the XAI techniques. In addition, the experiments are performed on the male and female groups to analyze the characteristics of gender-specific facial expressions. As a result, we describe age-specific and gender-specific experimental results based on the data distribution of the pre-training dataset of CNN models and highlight the importance of balanced learning data.

• Journal of the Institute of Electronics Engineers of Korea SP
• /
• v.41 no.3
• /
• pp.73-81
• /
• 2004

To extract the creditable features in fingerprint image, many people use the thinning algorithm that has a very important position in the preprocessing. In this paper, we propose the robust parallel thinning algorithm that can preserve the connectivity of the binarized fingerprint image, make the thinnest skeleton with 1-pixel width and get near to the medial axis extremely. The proposed thinning method repeats three sub-iterations. The first sub-iteration takes off only the outer boundary pixel by using the interior points. To extract the one side skeletons, the second sub-iteration finds the skeletons with 2-pixel width. The third sub-iteration prunes the needless pixels with 2-pixel width existing in the obtained skeletons and then the proposed thinning algorithm has the robustness against the rotation and noise and can make the balanced medial axis. To evaluate the performance of the proposed thinning algorithm we compare with and analyze the previous algorithms.

• KIPS Transactions on Software and Data Engineering
• /
• v.10 no.5
• /
• pp.169-178
• /
• 2021

Recently, a bike-sharing system (BSS) has become popular as a convenient "last mile" transportation. Rebalancing of bikes is a critical issue to manage BSS because the rents and returns of bikes are not balanced by stations and periods. For efficient and effective rebalancing, accurate traffic prediction is important. Recently, cluster-based traffic prediction has been utilized to enhance the accuracy of prediction at the station-level and the clustering step is very important in this approach. In this paper, we propose a k-means based clustering algorithm that overcomes the drawbacks of the existing clustering methods for BSS; indeterministic and hardly converged. By employing the centroid initialization and using the temporal proportion of the rents and returns of stations as an input for clustering, the proposed algorithm can be deterministic and fast.