• Korean Journal of Social Welfare Studies
• /
• v.44 no.3
• /
• pp.323-346
• /
• 2013

The main purpose of this study is to analyze job sequences according to poverty profiles that the working poor have had. For the stated purpose, this study examines characteristics and patterns of job sequences by diving the subgroups, using the 10 year data of KLIPS and the sequence analysis. Major findings are as follows. The working-transient poor have different characteristics, such as longer working term, less job change, less number of gap and length, and relatively higher monthly income, from the working-recurrent poor and the working-persistent poor. However, there are no different characteristics between the working-recurrent poor and working-persistent poor, except for monthly income. Job sequences are divided into 5 clusters and job sequences types according to the working poor subgroups are quite different. Such analysis results would contribute to planning poverty policies based on job sequences differently seen in subgroups and finding specific policy alternatives to relieve the working poor.

• Proceedings of the Korea Water Resources Association Conference
• /
• 2023.05a
• /
• pp.246-246
• /
• 2023

Multi-purpose dams are operated accounting for both physical and socioeconomic factors. This study aims to evaluate the utility of a deep learning algorithm-based model for three multi-purpose dam operation (Seomjin River dam, Juam dam, and Juam Control dam) in Seomjin River. In this study, the Gated Recurrent Unit (GRU) algorithm is applied to predict hourly water level of the dam reservoirs over 2002-2021. The hyper-parameters are optimized by the Bayesian optimization algorithm to enhance the prediction skill of the GRU model. The GRU models are set by the following cases: single dam input - single dam output (S-S), multi-dam input - single dam output (M-S), and multi-dam input - multi-dam output (M-M). Results show that the S-S cases with the local dam information have the highest accuracy above 0.8 of NSE. Results from the M-S and M-M model cases confirm that upstream dam information can bring important information for downstream dam operation prediction. The S-S models are simulated with altered outflows (-40% to +40%) to generate the simulated water level of the dam reservoir as alternative dam operational scenarios. The alternative S-S model simulations show physically inconsistent results, indicating that our deep learning algorithm-based model is not explainable for multi-purpose dam operation patterns. To better understand this limitation, we further analyze the relationship between observed water level and outflow of each dam. Results show that complexity in outflow-water level relationship causes the limited predictability of the GRU algorithm-based model. This study highlights the importance of socioeconomic factors from hidden multi-purpose dam operation processes on not only physical processes-based modeling but also aritificial intelligence modeling.

• KIPS Transactions on Software and Data Engineering
• /
• v.12 no.8
• /
• pp.355-364
• /
• 2023

As advanced cyber threats continue to increase in recent years, it is difficult to detect new types of cyber attacks with existing pattern or signature-based intrusion detection method. Therefore, research on anomaly detection methods using data learning-based artificial intelligence technology is increasing. In addition, supervised learning-based anomaly detection methods are difficult to use in real environments because they require sufficient labeled data for learning. Research on an unsupervised learning-based method that learns from normal data and detects an anomaly by finding a pattern in the data itself has been actively conducted. Therefore, this study aims to extract a latent vector that preserves useful sequence information from sequence log data and develop an anomaly detection learning model using the extracted latent vector. Word2Vec was used to create a dense vector representation corresponding to the characteristics of each sequence, and an unsupervised autoencoder was developed to extract latent vectors from sequence data expressed as dense vectors. The developed autoencoder model is a recurrent neural network GRU (Gated Recurrent Unit) based denoising autoencoder suitable for sequence data, a one-dimensional convolutional neural network-based autoencoder to solve the limited short-term memory problem that GRU can have, and an autoencoder combining GRU and one-dimensional convolution was used. The data used in the experiment is time-series-based NGIDS (Next Generation IDS Dataset) data, and as a result of the experiment, an autoencoder that combines GRU and one-dimensional convolution is better than a model using a GRU-based autoencoder or a one-dimensional convolution-based autoencoder. It was efficient in terms of learning time for extracting useful latent patterns from training data, and showed stable performance with smaller fluctuations in anomaly detection performance.

• Asian Pacific Journal of Cancer Prevention
• /
• v.13 no.6
• /
• pp.2639-2642
• /
• 2012

Background: The patterns of gastric cancer recurrence vary across societies. We designed the current study in an attempt to evaluate and reveal the outbreak of the recurrence patterns of gastric cancer and also prediction of time to recurrence and its effected factors in Iran. Materials and Methods: This research was performed from March 2003 to February 2007. Demographic characteristics, clinical and pathological diagnosis and classification including pathologic stage, tumor grade, tumor site and tumor size in of patients with GC recurrent were collected from patients' data files. To evaluate of factors affected on the relapse of the GC patients, gender, age at diagnosis, treatment type and Hgb were included in the research. Data were analyzed using Kaplan-Meier and logistic regression models. Results: After treatment, 82 patients suffered recurrence, 42, 33 and 17 by the ends of first, second and third years. The mean ( SD) and median ( IQR) time to recurrence in patients with GC were 25.5 (20.6-30.1) and 21.5 (15.6-27.1) months, respectively. The results of multivariate analysis logistic regression showed that only pathologic stage, tumor grade and tumor site significantly affected the recurrence. Conclusions: We found that pathologic stage, tumor grade and tumor site significantly affect on the recurrence of GC which has a high positive prognostic value and might be functional for better follow-up and selecting the patients at risk. We also showed time to recurrence to be an important factor for follow-up of patients.

• Journal of Korean Society of Industrial and Systems Engineering
• /
• v.46 no.3
• /
• pp.123-138
• /
• 2023

The Fourth Industrial Revolution and sensor technology have led to increased utilization of sensor data. In our modern society, data complexity is rising, and the extraction of valuable information has become crucial with the rapid changes in information technology (IT). Recurrent neural networks (RNN) and long short-term memory (LSTM) models have shown remarkable performance in natural language processing (NLP) and time series prediction. Consequently, there is a strong expectation that models excelling in NLP will also excel in time series prediction. However, current research on Transformer models for time series prediction remains limited. Traditional RNN and LSTM models have demonstrated superior performance compared to Transformers in big data analysis. Nevertheless, with continuous advancements in Transformer models, such as GPT-2 (Generative Pre-trained Transformer 2) and ProphetNet, they have gained attention in the field of time series prediction. This study aims to evaluate the classification performance and interval prediction of remaining useful life (RUL) using an advanced Transformer model. The performance of each model will be utilized to establish a health index (HI) for cutting blades, enabling real-time monitoring of machine health. The results are expected to provide valuable insights for machine monitoring, evaluation, and management, confirming the effectiveness of advanced Transformer models in time series analysis when applied in industrial settings.

• KIPS Transactions on Software and Data Engineering
• /
• v.6 no.9
• /
• pp.457-464
• /
• 2017

Indoor air quality analysis is conducted to understand abnormal atmospheric phenomena and the external factor affecting indoor air quality. By recording indoor air quality measurements periodically, we are able to observe patterns in air quality. However, it difficult to predict the number of potential parameters, set parameters for a given observation and find the coefficients. Moreover, the results are time-dependent. Thus to address these issues, we introduce a microchip capable of periodically recording indoor air quality and a model that estimates atmospheric changes based on time series data.

• Korean Journal of Head & Neck Oncology
• /
• v.33 no.1
• /
• pp.31-34
• /
• 2017

First branchial cleft anomaly is a very rare disease and exhibits various clinical presentations. Therefore, the diagnosis of first branchial cleft anomaly may be difficult; the condition is often misdiagnosed and mismanaged. Accurate diagnosis is very important, because if not diagnosed correctly, patients with first branchial cleft anomaly would be treated with local incision and drainage repeatedly. We report two cases of first branchial cleft anomaly. The first patient visited for recurrent swell and discharge in the infra-auricular area with a history of previous incision and drainage. The other patient showed a cystic mass in the infra-auricular area and all of them were misdiagnosed initially by their treating specialists elsewhere. The objective of this study is to share our experiences of first branchial cleft anomaly, and emphasize its various clinical patterns and the significance of accurate diagnosis.

• Animal Systematics, Evolution and Diversity
• /
• v.32 no.2
• /
• pp.105-111
• /
• 2016

The genetic structure of marine animals that inhabit the seashore is affected by numerous factors. Of these, gene flow and natural selection during recruitment have strong influences on the genetic structure of seashore-dwelling species that have larval periods. Relative contributions of these two factors to the genetic structure of marine species would be determined mainly by the duration of larval stage. The relationship between larval period and genetic structure of population has been rarely studied in Korea. In this study, genetic variations of cytochrome oxidase subunit I (COI) were analyzed in two dominant species on rocky shore habitats in the Korean peninsula: periwinkle Littorina brevicula and acorn barnacle Fistulobalanus albicostatus. Both species are not strongly structured and may have experienced recent population expansion. Unlike periwinkle, however, barnacle populations have considerable genetic variation, and show a bimodal pattern of mismatch distribution. These results suggest that barnacle populations are more affected by local adaptation rather than gene flow via larval migration. The bimodal patterns of barnacle populations observed in mismatch distribution plots imply that they may have experienced secondary contact. Further studies on seashore-dwelling species are expected to be useful in understanding the evolution of the coastal ecosystem around Korean waters.

• BMB Reports
• /
• v.51 no.1
• /
• pp.1-2
• /
• 2018

Positive selection on a new beneficial mutation generates a characteristic pattern of DNA sequence polymorphism when it reaches an intermediate allele frequency. On genome sequences of African Drosophila melanogaster, we detected such signatures of selection at 37 candidate loci and identified "sweeping haplotypes (SHs)" that are increasing or have increased rapidly in frequency due to hitchhiking. Based on geographic distribution of SH frequencies, we could infer whether selective sweeps occurred starting from de novo beneficial mutants under simple constant selective pressure. Single SHs were identified at more than half of loci. However, at many other loci, we observed multiple independent SHs, implying soft selective sweeps due to a high beneficial mutation rate or parallel evolution across space. Interestingly, SH frequencies were intermediate across multiple populations at about a quarter of the loci despite relatively low migration rates inferred between African populations. This invokes a certain form of frequency-dependent selection such as heterozygote advantage. At one locus, we observed a complex pattern of multiple independent that was compatible with recurrent frequency-dependent positive selection on new variants. In conclusion, genomic patterns of positive selection are very diverse, with equal contributions of hard and soft sweeps and a surprisingly large proportion of frequency-dependent selection in D. melanogaster populations.

• Advances in robotics research
• /
• v.1 no.1
• /
• pp.101-126
• /
• 2014

In this article we present modular neural control for a leg-wheel hybrid robot consisting of three legs with omnidirectional wheels. This neural control has four main modules having their functional origin in biological neural systems. A minimal recurrent control (MRC) module is for sensory signal processing and state memorization. Its outputs drive two front wheels while the rear wheel is controlled through a velocity regulating network (VRN) module. In parallel, a neural oscillator network module serves as a central pattern generator (CPG) controls leg movements for sidestepping. Stepping directions are achieved by a phase switching network (PSN) module. The combination of these modules generates various locomotion patterns and a reactive obstacle avoidance behavior. The behavior is driven by sensor inputs, to which additional neural preprocessing networks are applied. The complete neural circuitry is developed and tested using a physics simulation environment. This study verifies that the neural modules can serve a general purpose regardless of the robot's specific embodiment. We also believe that our neural modules can be important components for locomotion generation in other complex robotic systems or they can serve as useful modules for other module-based neural control applications.