• ETRI Journal
• /
• v.36 no.3
• /
• pp.418-428
• /
• 2014

In social network services, such as Facebook, Google+, Twitter, and certain postings attract more people than others. In this paper, we propose a novel method for predicting the lifespan and retweet times of tweets, the latter being a proxy for measuring the popularity of a tweet. We extract information from retweet graphs, such as posting times; and social, local, and content features, so as to construct prediction knowledge bases. Tweets with a similar topic, retweet pattern, and properties are sequentially extracted from the knowledge base and then used to make a prediction. To evaluate the performance of our model, we collected tweets on Twitter from June 2012 to October 2012. We compared our model with conventional models according to the prediction goal. For the lifespan prediction of a tweet, our model can reduce the time tolerance of a tweet lifespan by about four hours, compared with conventional models. In terms of prediction of the retweet times, our model achieved a significantly outstanding precision of about 50%, which is much higher than two of the conventional models showing a precision of around 30% and 20%, respectively.

• The Journal of Advanced Prosthodontics
• /
• v.16 no.3
• /
• pp.151-162
• /
• 2024

PURPOSE. This study aimed to analyze factors influencing the success and failure of implant prostheses and to estimate the lifespan of prostheses using standardized evaluation criteria. An online survey platform was utilized to efficiently gather large samples from multiple institutions. MATERIALS AND METHODS. During the one-year period, patients visiting 16 institutions were assessed using standardized evaluation criteria (KAP criteria). Data from these institutions were collected through an online platform, and various statistical analyses were conducted. Risk factors were assessed using both the Cox proportional hazard model and Cox regression analysis. Survival analysis was conducted using Kaplan-Meier analysis and nomogram, and lifespan prediction was performed using principal component analysis. RESULTS. The number of patients involved in this study was 485, with a total of 841 prostheses evaluated. The median survival was estimated to be 16 years with a 95% confidence interval. Factors found to be significantly associated with implant prosthesis failure, characterized by higher hazard ratios, included the 'type of clinic', 'type of antagonist', and 'plaque index'. The lifespan of implant prostheses that did not fail was estimated to exceed the projected lifespan by approximately 1.34 years. CONCLUSION. To ensure the success of implant prostheses, maintaining good oral hygiene is crucial. The estimated lifespan of implant prostheses is often underestimated by approximately 1.34 years. Furthermore, standardized form, online platform, and visualization tool, such as nomogram, can be effectively utilized in future follow-up studies.

• Corrosion Science and Technology
• /
• v.18 no.3
• /
• pp.86-91
• /
• 2019

Generally, atmospheric corrosion is the electrochemical degradation of metal that can be caused by various corrosion factors of atmospheric components and weather, as well as air pollutants. Specifically, moisture and particles of sea salt and sulfur dioxide are major factors in atmospheric corrosion. Using galvanized steel is one of the most efficient ways to protect iron from corrosion by zinc plating on the surface of the iron. Galvanized steel is widely used in automobiles, building structures, roofing, and other industrial structures due to their high corrosion resistance relative to iron. The atmospheric corrosion of galvanized steel shows complex corrosion behavior, depending on the plating, coating thickness, atmospheric environment, and air pollutants. In addition, corrosion products are produced in different types of environments. The lifespans of galvanized steels may vary depending on the use environment. Therefore, this study investigated the corrosion behavior of galvannealed steel under atmospheric corrosion in two locations in Korea, and the lifespan prediction of galvannealed steel in rural and coastal environments was conducted by means of the potentiostatic dissolution test and the chemical cyclic corrosion test.

• Journal of the Korea Academia-Industrial cooperation Society
• /
• v.19 no.10
• /
• pp.424-429
• /
• 2018

In this study, an expansion joint that is susceptible to waterhammer was tested for its vibration durability. The operation data for the hydraulic actuator was the expansion length of the expansion joint when the waterhammer occurred. In the case of the vibration durability test, the internal temperature status of the expansion joint was assumed to be a stress factor and a lifespan prediction model was assumed to follow the Arrhenius model. A test was carried out by increasing the internal temperature status at $30^{\circ}C$, $50^{\circ}C$, and $65^{\circ}C$. By a linear transformation of the lifespan data for each temperature, a constant value and activation energy coefficient was induced for the Arrhenius equation and verified by comparing the value of a lifetime prediction model with the experimental value at $85^{\circ}C$. The failure modes of the ongoing or finished test were leakage, bellows separation, and internal deformation. In the future, a composite lifespan prediction model, including two more stress factors, will be developed.

• Elastomers and Composites
• /
• v.59 no.2
• /
• pp.73-81
• /
• 2024

In the field of electronic components, the potting material, which is a part of the electronic circuit package, plays a significant role in protecting circuits from the external environment and reducing signal interference among electronic devices during operation. This significantly affects the reliability of the components. Therefore, the accurate prediction and assessment of the lifespan of a material are of paramount importance in the electronics industry. We conducted an accelerated thermal aging evaluation using the Arrhenius technique on elastic potting material developed in-house, focusing on its insulation, waterproofing, and contraction properties. Through a comprehensive analysis of these properties and their interrelations, we confirmed the primary factors influencing molding material failure, as increased hardness is related to aggregation, adhesion, and post-hardening or thermal-aging-induced contraction. Furthermore, when plotting failure times against temperature, we observed that the hardness, adhesive strength, and water absorption rate were the predominant factors up to 120 ℃. Beyond this temperature, the tensile properties were the primary contributing factors. In contrast, the dielectric constant and loss tangent, which are vital for reducing signal interference in electric devices, exhibited positive changes(decreases) with aging and could be excluded as failure factors. Our findings establish valuable correlations between physical properties and techniques for the accurate prediction of failure time, with broad implications for future product lifespans. This study is particularly advantageous for advancing elastic potting materials to satisfy the stringent requirements of reliable environments.

• Journal of the Korean Society of Manufacturing Process Engineers
• /
• v.17 no.5
• /
• pp.58-63
• /
• 2018

Recently in weapon systems development, the importance of reliability has been emphasized due to the increase in complexity and the rapid development of key components and components. Accordingly, the importance of lifespan testing is increased. However, lifespan testing to verify the reliability of a system is costly and takes a lot of time. Therefore in this paper, it was demonstrated that the most critical item of a bladder type accumulator is the bladder. Fatigue life is sensitive to temperature and pressure, with temperature having more impact. The fatigue life of the bladder was estimated to be 18,140 hr through fatigue analysis, which satisfies the required life expectancy of 10,000 hr.

• International Journal of Internet, Broadcasting and Communication
• /
• v.16 no.3
• /
• pp.236-241
• /
• 2024

Due to the recent emphasis on carbon neutrality and environmental regulations, the global electric vehicle (EV) market is experiencing rapid growth. This surge has raised concerns about the recycling and disposal methods for EV batteries. Unlike traditional internal combustion engine vehicles, EVs require unique and safe methods for the recovery and disposal of their batteries. In this process, predicting the lifespan of the battery is essential. Impedance and State of Charge (SOC) analysis are commonly used methods for this purpose. However, predicting the lifespan of batteries with complex chemical characteristics through electrical measurements presents significant challenges. To enhance the accuracy and precision of existing measurement methods, this paper proposes using a Long Short-Term Memory (LSTM) model, a type of deep learning-based recurrent neural network, to diagnose battery performance. The goal is to achieve safe classification through this model. The designed structure was evaluated, yielding results with a Mean Absolute Error (MAE) of 0.8451, a Root Mean Square Error (RMSE) of 1.3448, and an accuracy of 0.984, demonstrating excellent performance.

• Journal of Digital Convergence
• /
• v.19 no.6
• /
• pp.113-132
• /
• 2021

This study is a new evaluation using the Arrhenius equation, which is known as the chemical reaction rate estimation equation, to evaluate the intrinsic and extrinsic value elements of patents as a model. The performance of the evaluation model was superior to the SVM, Logistic reg. and ANN models that were used as patent evaluation models in prior studies. In addition, there was a strong correlation between the predicted lifespan of the patent and the actual lifespan of the patent. These evaluation models may be used for evaluation purposes only, or if an evaluation is required, including a commercialization entity or technical characteristics.

• Journal of Intelligence and Information Systems
• /
• v.28 no.2
• /
• pp.147-170
• /
• 2022

Although the number of patent which is one of the core outputs of technological innovation continues to increase, the number of low-value patents also hugely increased. Therefore, efficient evaluation of patents has become important. Estimation of patent lifespan which represents private value of a patent, has been studied for a long time, but in most cases it relied on a linear model. Even if machine learning methods were used, interpretation or explanation of the relationship between explanatory variables and patent lifespan was insufficient. In this study, patent lifespan (number of renewals) is predicted based on the idea that patent lifespan represents the value of the patent. For the research, 4,033,414 patents applied between 1996 and 2017 and finally granted were collected from USPTO (US Patent and Trademark Office). To predict the patent lifespan, we use variables that can reflect the characteristics of the patent, the patent owner's characteristics, and the inventor's characteristics. We build four different models (Ridge Regression, Random Forest, Feed Forward Neural Network, Gradient Boosting Models) and perform hyperparameter tuning through 5-fold Cross Validation. Then, the performance of the generated models are evaluated, and the relative importance of predictors is also presented. In addition, based on the Gradient Boosting Model which have excellent performance, Accumulated Local Effects Plot is presented to visualize the relationship between predictors and patent lifespan. Finally, we apply Kernal SHAP (SHapley Additive exPlanations) to present the evaluation reason of individual patents, and discuss applicability to the patent evaluation system. This study has academic significance in that it cumulatively contributes to the existing patent life estimation research and supplements the limitations of existing patent life estimation studies based on linearity. It is academically meaningful that this study contributes cumulatively to the existing studies which estimate patent lifespan, and that it supplements the limitations of linear models. Also, it is practically meaningful to suggest a method for deriving the evaluation basis for individual patent value and examine the applicability to patent evaluation systems.

• Journal of Information Processing Systems
• /
• v.18 no.4
• /
• pp.457-469
• /
• 2022

Hydraulic concrete buildings in the northwest of China are often subject to the combined effects of low-temperature frost damage, during drying and wetting cycles, and salt erosion, so the study of concrete deterioration prediction is of major importance. The prediction model of the relative dynamic elastic modulus (RDEM) of four different kinds of modified concrete under the special environment in the northwest of China was established using Grey residual Markov theory. Based on the available test data, modified values of the dynamic elastic modulus were obtained based on the Grey GM(1,1) model and the residual GM(1,1) model, combined with the Markov sign correction, and the dynamic elastic modulus of concrete was predicted. The computational analysis showed that the maximum relative error of the corrected dynamic elastic modulus was significantly reduced, from 1.599% to 0.270% for the BS2 group. The analysis error showed that the model was more adjusted to the concrete mixed with fly ash and mineral powder, and its calculation error was significantly lower than that of the rest of the groups. The analysis of the data for each group proved that the model could predict the loss of dynamic elastic modulus of the deterioration of the concrete effectively, as well as the number of cycles when the concrete reached the damaged state.