Earticle

지하철은 현대 도시의 교통 체계에서 중요한 역할을 하는 대중 교통 수단이다. 하지만, 갑작스런 고장 및 시스템 불통 등의 이유로 혼잡을 야기시키는 경우가 종종 발생하여 불편을 초래하고 있다. 따라서, 본 논문에서는 지하철 시스템의 효율적 운영을 위해 머신러닝을 활용한 고장 예측 및 예방 연구를 진행하였다. UC Irvine의 MetroPT-3 데이터셋을 활용하고, 로지스틱 회귀를 이용하여 지하철 고장 예측 모델을 구축하였다. 모델은 0.991 의 높은 정확도로 비고장 상태를 예측하나, 정밀도와 재현율은 상대적으로 낮아 고장 예측에 있어 오류 가능성을 시사하고 있다. ROC_AUC 값이 0.901로, 모델이 무작위 추측보다 뛰어난 분류를 할 수 있다. 구축한 모델은 지하 철 시스템의 안정적인 운영 운영에 유용하나, 성능 개선을 위한 추가 연구가 필요하다고 생각한다. 따라서 학습 데이터가 많고 데이터의 정제가 잘 이루어진다면 고장 예측을 통해 사전 점검을 하여 예방할 수 있다.

The subway is a means of public transportation that plays an important role in the transportation system of modern cities. However, congestion often occurs due to sudden breakdowns and system outages, causing inconvenience. Therefore, in this paper, we conducted a study on failure prediction and prevention using machine learning to efficiently operate the subway system. Using UC Irvine's MetroPT-3 dataset, we built a subway breakdown prediction model using logistic regression. The model predicted the non-failure state with a high accuracy of 0.991. However, precision and recall are relatively low, suggesting the possibility of error in failure prediction. The ROC_AUC value is 0.901, indicating that the model can classify better than random guessing. The constructed model is useful for stable operation of the subway system, but additional research is needed to improve performance. Therefore, in the future, if there is a lot of learning data and the data is well purified, failure can be prevented by pre-inspection through prediction.

This study aims to analyze the financial soundness of 15 listed international e-sport firms from 2021 to 2023 using three failure prediction models: the Altman revised Z score model, the Springate model, and the Zmijewski model. The results are summarized as follows. First, this study's findings show that most firms are in financial distress over the sample period. Second, the Altman revised Z score model classified results 4 out of the 15 e-sport firms as financially healthy for the entire period. Second, Springate and Zmijewski’s models classified 1 out of the 15 esports firms as financially sound for the entire period. In conclusion, Springate and Zmijewski’s models predicted more e-sport firms as likely to go bankrupt than the Altman Z score model. This result is expected to be useful for investors and lenders in their investment decision-making process regarding e-sport firms.

This study aims to analyze the financial soundness of 15 listed international e-sport firms from 2021 to 2023 using three failure prediction models: the Altman revised Z score model, the Springate model, and the Zmijewski model. The results are summarized as follows. First, this study's findings show that most firms are in financial distress over the sample period. Second, the Altman revised Z score model classified results 4 out of the 15 e-sport firms as financially healthy for the entire period. Second, Springate and Zmijewski’s models classified 1 out of the 15 esports firms as financially sound for the entire period. In conclusion, Springate and Zmijewski’s models predicted more e-sport firms as likely to go bankrupt than the Altman Z score model. This result is expected to be useful for investors and lenders in their investment decision-making process regarding e-sport firms.

Electrical and mechanical failures in electric vehicles (EVs) during passenger operation cause significant operational losses and elevated energy consumption, amplifying range anxiety. To address this issue, we utilized 250,000 rows of real-time data from electric trolleybuses operating in Turkiye to develop a robust artificial intelligence (AI)-based optimization model for failure mitigation. Initially, Tri layered Neural Network (TNN) was employed to create a predictive function for electrical and mechanical failures, followed by comparative analyses across six optimization algorithms widely adopted in failure prediction studies. Among these, the Developed Honey Badger Algorithm with AI Approach (DHBA) emerged as the most effective, achieving a predictive accuracy improvement of 15 % over the standard Honey Badger Algorithm (HBA). The DHBA incorporates a Dynamic Fitness-Distance Balance (DFDB) mechanism and a novel spiral motion feature to enhance search precision, leading to the DHBA-FPM (Developed-Honey Badger Algorithm - Failure Prediction Model). The final DHBA-FPM model was applied to the 10 highest-density bus routes in Turkiye to predict and optimize failures. Results indicate that applying the DHBA-FPM model across these routes yielded a 3.96 % average range increase in EVs, extending the total range by approximately 79,200 km annually. It can be concluded that the model could prevent the release of 238.7 tons/year of CO2, NO, and NO2 emissions through its potential to improve both the operational efficiency and sustainability of EVs in public transit networks.

본 연구의 목적은 전통적인 통계기법인 로짓회귀모형과 인공지능기법인 서퍼트벡터머신모형 (SVM-RBF와 SVM-LIN) 및 랜덤포레스트모형(RF)을 사용하여 남아프리카아공화국 요하네스버그 증권거래소에 상장된 기업의 부도예측모형을 개발하고 이를 모형들의 예측력을 비교분석하는 것이 다. 본 연구는 쌍대표본추출법을 이용하여 2005년부터 2018년까지 부실기업 또는 정리계획 등의 이 유로 요하네스버그 증권거래소에서 상장 폐지된 72개 기업 및 상장폐지 연도, 업종, 총자산규모를 기준으로 건전 기업 72개를 선정하여 총 144개 기업을 분석에 활용하였다. 설명변수로는 34개의 재 무변수와 시장 변수를 대상으로 t-검증을 실시하여 1단계분석을 통해 통계적으로 유의미한 10개 변 수를 선정하였으며, 2단계분석에서는 10개 변수를 단계적선택법을 적용하여 최종적으로 4개의 변 수를 선정하였다. 본 연구 결과는 다음과 같다. 첫째, 1단계분석 결과에서는 부도예측 모형의 추정표본과 예측표본 의 평균예측성과를 비교해보았을 때, SVM-RBF의 추정표본이 83.3% 예측표본이 65.8%를 보여 평균 예측 성과가 가장 높게 나타났다. 둘째, 단계적선택법을 이용하여 선정된 변수의 경우 SVM-RBF가 추정표본의 평균 예측성과가 71%로 가장 높았으며, 예측표본의 평균 예측성과는 SVM-RBF와 SVM-linear가 65%로 가장 높게 나타났다. 따라서 본 연구에서는 SVM 모형과 같은 인공지능기법 관련 모형이 기타 부도예측모형보다 더 높은 예측성과를 가지고 있는 것으로 검증되 었다. 본 연구 결과는 투자자에게 기업의 부도예측을 함에 있어 유용하게 활용될 수 있다는 점에서 의의가 있다.

The aim of this paper is to construct and investigate a superior model that can predict bankruptcy for JSE listed companies using a traditional statistical method (Logistic Regression, LR) and artificial intelligent related models (Support Vector Machines, SVM; Random Forest, RF). This research adopted the paired sample approach for 144 companies. 72 companies that are delisted from JSE due to business failure or scheme of arrangement from 2005 to 2018 are matched with 72 bankrupt counterparts based on year of delisting, industry and asset size. Our results indicate that compared with other models investigated, SVM-RBF outperformed other models for both the training dataset and testing dataset with average accuracies of 83.3% and 65.8% respectively for the t-test selected input variables. For the two-step feature selection (stepwise logistic regression) input variables, SVM-RBF has the highest average accuracy performance of 71% for the training data. For the testing data, SVM-RBF and SVM-linear show the highest average performance of 65%. This paper finds evidence in support of artificial intelligence related techniques such as SVM models having better performance compared with other models examined in this paper. This model can be employed as a tool for predicting failure five years before hand by investors and academics may refer to it as a fundamental reference material.

To better predict and classify failures of information system development projects (ISDPs), this study proposes ISDPs failure prediction models using the traditional statistical methods and artificial intelligence methods, namely multiple discriminant analysis (MDA), logistic regression (LR), multi-layer perceptron (MLP), classification and regression tree (CART), commercial version 5.0 (C5.0), and support vector machine (SVM). We performed the analysis on the audit report data of 446 projects that were conducted by a global information technology (IT) company, to build the IT service systems and relevant service infrastructures needed for a project with South Korea’s mobile telecommunication companies. The research variables, which were confirmed by project performance management system (PPMS) of the company, are composed of thirteen variables. Empirical results indicated that SVM outperforms other models such as MDA, LR, MLP, CART, and C5.0.

The authors previously developed a dynamic Cox hazards model with time-varying covariates to estimate and forecast the events of financial distress for Australian firms (Kim and Partington, 2014). Yet, in common with most prior studies on financial distress, they neglect the potential non-linear relation between individual predictor variables and the event of interest (the risk of financial distress). This paper extends Kim and Partington (2014) by addressing both the effect of non-linearity and the impact of the state of the economy on the financial distress risk. Specifically, each predictor variable is transformed non-parametrically based on the univariate empirical mapping with the observed failure rates. With the use of data on publicly listed companies on the Australian Securities Exchange (ASX) from 1995 to 2006, the models are calibrated using an estimation sample ((1995-2002) and the out-of-sample discriminatory power (based on the ROC curve) and accuracy (based on the Brier Score) are assessed on the holdout sample (2003-2006). It is found that the discriminatory power (but not the accuracy of probabilistic predictions) of the models is substantively improved by catering for the non-linear relations between the risk of financial distress and predictor variables. However, it is shown that variables capturing the state of the economy do not add to the predictive power when timevarying firm-specific variables are already included in the model.

The electrification of modern energy systems relies heavily on lithium-ion batteries, yet their high energy density exacerbates thermal runaway (TR) safety risks. Traditional TR characterization is expensive, time-consuming, and reliant on post-mortem analysis. To enable design-stage safety screening, this study proposes a physics-informed machine learning framework utilizing the open Battery Failure Databank. We curated 309 experiments and used 11 pre-test variables to predict three complementary TR severity metrics: total energy yield, unrecovered mass, and positive-end ejecta energy fraction. Evaluating four tree-based models via 10-fold stratified cross-validation, Random Forest emerged as the best baseline across all targets. Results revealed a clear predictability gradient: total energy yield showed high determinism (R² = 0.93), unrecovered mass moderate predictability (R² = 0.57), and directional ejecta energy remained stochastic (R² = 0.30). This framework can help reduce reliance on destructive testing.

We consider the mean value function for NHPP software reliability model and time series regression model in software failure data. We estimate parameters for the proposed models from two data sets. The values of SSE and MSE is presented from two data sets. We compare the predicted number of faults with the actual two data sets using the mean value function and regression curve.

본 보고에서는 강우에 의한 대규모 노천광산 사면의 붕괴 위험도 평가에 활용 가능한 기술로서 침투-응력 해석에 의한 사면안정 평가기술 뿐만 아니라 이를 보완하기 위한 방안으로 강우량 자료에 근거한 위험도 추정, 사면에서의 계측자료를 이용한 위험도 예측 기법, 수치표고모델(Digital Elevation Model, DEM)을 이용한 위험도 예측 기법 등을 소개하였다. 누적강우량과 강우강도를 이용하여 사면 붕괴 위험도를 예측할 수 있음을 보였으며, 지하수면 상부 모관흡수력의 계측을 통한 표층 붕괴 위험도 예측이 가능함을 알 수 있었다. DEM을 이용한 사면 붕괴 위험도 예측기법은 대규모 노천 사면의 위험지역을 사전에 추출하여 관리하고 채광작업 진행에 따른 위험도 변화 양상을 신속하게 파악하는데 유용할 것으로 판단된다. 또한, 노천광산 사면의 안정성을 향상시키기 위한 보조공법으로 자연배수, 수평배수공, 양수공법, 배수 터널공과 같은 지하수위 하강공법의 종류 및 특징과 사면의 지질학적 및 수리지질학적 특징에 따른 적용성에 대해 기술하였다.

In this study, we have introduced a risk prediction method for the slope failure at large open pit mine. The method includes the risk prediction based on rainfall data, using monitored data, and in terms of digital elevation model (DEM) in addition to a conventional slope stability analysis as a result of a seepage-stress analysis. Cumulative precipitation rate and intensity were useful in predicting slope failure induced by rainfall and monitoring suction pressure above groundwater table was also applicable. Slope failure prediction due to rainfall using DEM was considered to help identify potentially dangerous regions and their evolution during excavation. And mine dewatering technologies such as natural and horizontal drainage, vertical pumping and drainage tunnel method to enhance a open pit mine slope stability were introduced as well together with their applicability, depending on geological and hydrogeological characteristics of the slope.

This paper presents a method for the assesment of thermal and vibration fatigues in integral exhaust manifold/turbine housing system. Most of failures on turbine housing are observed by thermal cyclic loads. In order to predict thermal failures by finite element analysis, we considered the temperature-dependent inelastic materials and transient temperature histories based on the thermal shock test. The results showed that the plastic strains of localized critical regions such as valve seat coincided well with crack locations from an endurance test. But, some failures around neck areas of turbine housing could not predict from thermal stress analysis. These cracks were originated due to the vibration excitations near resonance frequencies within engine operating ranges. The stress results of neck areas, which divided by temperature dependent yield stresses, from harmonic analysis showd a good agreement with experimental results.

본 연구는 코스닥(KOSDAQ) 시장에서 특정기간(2009년 ∼ 2011년)동안 상장폐지된 기업들을 대상으로 재무적 특성을 파악한 후, 재무적 특성 중에서 재무비율을 가지고 로짓분석(Logit Analysis)을 통해 부실예측모형을 제시하였다. 그리고 상장폐지된 기업과 유사한 자산규모를 가지고 있는 정상적인 기업을 1대 1로 대응시켜서 이 두 그룹간 재무비율의 차이를 분석하고 이들에 대한 부실예측모형도 제시하였다. 본 연구는 7개의 재무비율을 이용하여 분석을 실시하였다. 이것들을 가지고 평균의 차이를 검정한 t-test결과, 현금성자산비율(CATA)을 제외한 모든 비율에서 정상적인 기업과 상장폐지된 기업 간에 유의한 차이가 존재하는 것으로 나타났다. 그런데 그 차이는 상장폐지 직전년도로 갈수록 더욱 큰 차이가 나타나고 있음을 확인할 수 있었다. 또한 부실예측을 파악하기 위해 단계적 회귀분석방법을 이용하여 로짓분석을 실시한 결과, 상장폐지 1년 전의 예측력이 83.8%, 2년 전의 예측력이 69.6% 등으로 나타났다. 그리고 선행연구에서 분석하지 않았던 부분인 상장폐지된 기업 중 감사의견의 적정성 여부에 따라 차이가 발생하는 지를 파악하기 위해 두 그룹으로 나누어 분석을 실시한 결과, 비적정감사의견을 받은 기업과 적정감사의견을 받은 기업 간의 재무비율에 있어서 유의적인 차이가 나타나지 않는 것으로 밝혀졌다. 이와 같은 결과를 토대로 적정감사의견을 받은 기업 중 상장폐지된 기업에 대한 감사의견의 적정성에 의문을 갖게 되었다.

We researched the delisting firms’ financial characteristics and the failure prediction model using Logit analysis in KOSDAQ market. This research selected samples that was delisted firms at KOSDAQ market during 3 years from 2009 to 2011. And we matched normal firms with 1:1 matching method. Normal firms were selected with total asset. We analysed the Logit analysis with financial ratios and calculated T-value of mean difference between delisting firms and normal firms. The results shows the significant difference about two groups. Also the difference get become larger. We used the Backward elimination method. The results shows prediction capability is 83.8% before 1 years and 69.6% before 2 years. Also, we researched the suitability of auditors opinion about the delisting firms. The results shows the insignificant difference about two groups. And we got second thoughts about the suitability of auditors opinion of the delisting firms in Korea.

본 논문에서는 수중 펌프에 대한 동작 상태 모니터링, 고장 진단 및 예측 알고리즘에 대하여 연구하였다. 모니터링 유닛은 수중펌프의 센서 값을 모니터링 제어유닛으로 485통신을 통해서 전송되며, 모니터링 제어 유닛은 센서 값을 변환하여 서버 컴퓨터와 임베디드시스템에 송신한다. 서버 및 임베디드시스템은 데이터베이스에 센서 값을 저장하고 화면에 디스플레이 하여 수중 펌프의 동작 상태를 확인 할 수 있다. 임베디드시스템에서는 데이터 베이스에 저장된 센서 값을 읽어 들여, 개별 및 복합진단을 수행하고, 서버 및 모니터링 제어 유닛에게 송신하여 결과를 표시할 수 있게 하였다. 수중펌프의 예측진단은 23개의 개별 센서의 분류별로 나눠서 다층페셉트론을 구현 하였고, 학습 및 테스트를 통해서 가중치를 설정하였으며, 실시간 입력되는 센서 값을 통하여 알고리즘의 성능을 확인 할 수 있었다. 제안된 알고리즘은 수중 펌프 제품 경쟁력에 도움이 될 것으로 판단된다.

In this paper, operation status monitoring, fault diagnosis, and prediction algorithms for submersible pumps were studied. The monitoring unit transmits the sensor value of the submersible pump to the monitoring control unit through 485 communication, and the monitoring control unit converts the sensor value and transmits it to the server computer and embedded system. The server and embedded system store the sensor value in the database and display it on the screen to check the operation status of the submersible pump. In the embedded system, it is possible to read the sensor values stored in the database, perform individual and complex diagnosis, and display the results by sending them to the server and monitoring control unit. . For predictive diagnosis, the multi-layered peceptron was implemented by dividing by classification of 23 individual sensors, and the performance of the algorithm was confirmed through learning and testing. The proposed algorithm is judged to be helpful in the competitiveness of submersible pump products.

최근 모니터링 및 예측 시스템을 이용하여 사전에 결함을 발견하고 이를 경고하는 시스템이 활발히 연구되고 있다. 차량 안전 관리에 있어서도 예측 결함 분석 기술을 적용하여 자동차 휠 베어링의 고장 유무 및 고장 유형을 조기 에 경고하는 시스템이 필요하다. 본 논문에서는 휠 베어링과 결합 된 센서 모듈과 각 센서 모듈에서 차량 가속 정보 및 진동 정보를 수집, 저장 및 분석하는 진단 시스템을 제시하였다. 제안된 센서 모듈은 저비용으로 차량의 휠 베어링 상태를 모니터링하며, 이렇게 수집된 데이터를 활용하여 진단 및 고장 예측 기능을 수행하는 방안을 연구하였다. 개발된 센서 모듈과 예측 분석 시스템은 가진 테스트 장비 및 실제 차량을 이용하여 테스트하고 그 유효성을 평가하였다.

There is a need for a system that provides early warning of presence and type of failure of automobile wheel bearings through the application of predictive fault analysis technologies. In this paper, we presented a sensor module mounted on a wheel bearing and a diagnostic system that collects, stores and analyzes vehicle acceleration information and vibration information from the sensor module. The developed sensor module and predictive analysis system was tested and evaluated thorough excitation test equipment and real automotive vehicle to prove the effectiveness.

The purpose of this article is to study for the situation of small and medium firm and firm's failure. The effect of the situation of small and medium firm is about 99.0% above. The firm's failure are economic failure and financial failure. And, financial failure are technical insolvency and bankruptcy. The factor of the firm failure are inner factor and outer factor. The inner factors are no financial management, unreasonable investment, inferiority technical and production. The outer factors are excessive competition, loss of blood selling, depreciation of foreign exchange, a rising of material price. The effect of firm failure are inner factors is 50.4%, outer factors 49.6%. The further study is empirical study small and medium firm in KOREA.

The policemen are normally supposed to devote themselves wholly for the freedom and security of the national people. Actually, however, they are rather busy dealing with the drunken people who cause a stir at police boxes or regional police units than doing their own task of keeping peace for the citizens. The cost and time spent for such non-authoritative purposes eventually go to the burden of the good citizens who in turn are deprived of chance to get quality security service by the police. The present paper is thus aimed at examining judicial cases concerned with probation for the drunken and drawing out measures for improvements by reducing the burden of the police in the front line caused from probation of the drunken or proteges and by cutting down the social and economic cost arising therefrom.