• 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.

• 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.

• IMMUNE NETWORK
• /
• v.5 no.4
• /
• pp.252-257
• /
• 2005

Background: This study was designed to investigate the effect of exercise training on defense mechanism of chronic degenerative disease, aging, and memory impairments of senescence-accelerated mouse (SAM)P8 under the hypothesis that "Senile dementia may be prevented by regular exercises". Methods: To evaluate the effects of exercise training on the defense mechanism of aging and memory impairment, SAMP8 were divided into two groups, the control group and exercise training groups. the exercise training group were performed with low $(\dot{V}O_2max\;25{\sim}33%)$, middle ($\dot{V}O_2max$ 50%) and high $(\dot{V}O_2max\;66{\sim}75%)$ intensity exercise. All SAMP8 mice were fed experimental diet ad libitum until 4, 8 months, and dead period. Results: Median lifespan in middle exercise group resulted in a significantly increased (23.5% and 18.7%, respectively), whereas these lifespan in high exercise group resulted in an unexpectedly decreased (13.5% and 12.1%, respectively) compared with control group. Body fat levels in 4 and 8 months of age were significantly decreased 43% to 51% in middle exercise group, whereas were remarkably deceased to 57% in high exercise group compared with control group. It is believed that extended median and maximum lifespan may be effected by calory restriction through the exercise training. Acetylcholine (ACh) levels were significantly increased 6.7% and 8.5% in middle and high exercise groups, and also choline acetyltransfease (ChAT) activities were significantly increased 10.3% and 11.9% in middle and high exercise groups. Conclusion: These results suggest that proper and regular exercises such as middle group ($\dot{V}O_2max$ 50%) may play an effective role in attenuating an oxygen radicals and may play an important role in improving a learning and memory impairments of senile dementia.

• KIPS Transactions on Computer and Communication Systems
• /
• v.10 no.10
• /
• pp.269-276
• /
• 2021

Recently, smart sensors are used in various environments, and the implementation of ad-hoc sensor networks (ASNs) is a hot research topic. Unfortunately, traditional sensor network routing algorithms focus on specific control issues, and they can't be directly applied to the ASN operation. In this paper, we propose a new routing protocol by using the Q-learning technology, Main challenge of proposed approach is to extend the life of ASNs through efficient energy allocation while obtaining the balanced system performance. The proposed method enhances the Q-learning effect by considering various environmental factors. When a transmission fails, node penalty is accumulated to increase the successful communication probability. Especially, each node stores the Q value of the adjacent node in its own Q table. Every time a data transfer is executed, the Q values are updated and accumulated to learn to select the optimal routing route. Simulation results confirm that the proposed method can choose an energy-efficient routing path, and gets an excellent network performance compared with the existing ASN routing protocols.

• Journal of Korea Society of Digital Industry and Information Management
• /
• v.15 no.1
• /
• pp.133-155
• /
• 2019

The economic growth has made our lives more prosperous than the past, and the development of science fueled the era of 100-year lifespan. It is now distinct to us that preparation for life after retirement is not a choice but an imperative. In the meantime, outplacement programs have driven many to challenge and start a new chapter in life. This paper measures the characteristics of outplacement programs based on the self-determination factors; empirically examines how those characteristics influence on learning performance through self-efficacy and psychological well-being; concludes by proposing effective and productive ways for young adults and senior employees who are in search for new jobs. To test the research hypothesis, a survey was conducted among job searchers who have been previously provided with outplacement programs. The results are as follows: First, self-perceived autonomy has significant influences on self-efficacy and psychological well-being. Second, self-perceived competency has significant influences on self-efficacy and psychological well-being. Third, perceived relationship has no significant influence on self-efficacy and psychological well-being. Fourth, self-efficacy showed significant influences on psychological well-being, while not showing on learning performance. Fifth, psychological well-being has no significant influence on learning performance. This paper finds its academic significance in its theory-based approach to outplacement service program; research variables and examination are not based on researcher's arbitrary choice. This paper is also practically significant in that it discovered that outplacement service alleviates psychological stress caused by job relocation, and guarantees stable life after retirement.

• Journal of the Korea Safety Management & Science
• /
• v.24 no.4
• /
• pp.1-8
• /
• 2022

Elevators are the main means of transport in buildings. A malfunction of an elevator in operation may cause in convenience to users. Furthermore, fatal accidents, such as injuries and death, may occur to the passengers also. Therefore, it is important to prevent failure before accidents happen. In related studies, preventive measures are proposed through analyzing failures, and the lifespan of elevator components. However, these methods are limited to existing an elevator model and its surroundings, including operating conditions and installed environments. Vibration occurs when the elevator is operated. Experts have classified types of faults, which are symptoms for malfunctions (failures), via analyzing vibration. This study proposes an artificial intelligent model for classifying faults automatically with deep learning algorithms through elevator vibration data, hereby preventing failures before they occur. In this study, the vibration data of six elevators are collected. The proposed methodology in this paper removes "the measurement error data" with incorrect measurements and extracts operating sections from the input datasets for proceeding deep learning models. As a result of comparing the performance of training five deep learning models, the maximum performance indicates Accuracy 97% and F1 Score 97%, respectively. This paper presents an artificial intelligent model for detecting elevator fault automatically. The users' safety and convenience may increase by detecting fault prior to the fatal malfunctions. In addition, it is possible to reduce manpower and time by assisting experts who have previously classified faults.

• Proceedings of the Korean Society of Computer Information Conference
• /
• 2022.01a
• /
• pp.345-348
• /
• 2022

본 논문에서는 유체 시뮬레이션(Fluid simulation)중 화염에서 표현되는 불똥 입자(Fire-flake particle)의 생성, 움직임과 삭제를 효율적으로 학습하고 표현할 수 있는 인공지능 기법에 대해 소개한다. 유체 시뮬레이션을 계산하기 위해서는 일반적으로 수치해석학과 같은 학문의 이해가 필요하며 불똥이나 거품과 같은 유체의 2차 효과(Secondary effect)는 기반유체(Underlying fluids)를 통해 추출되기 때문에 복잡하고 계산양이 많아진다. 이러한 문제를 완화하고자 본 논문에서는 인공신경망을 이용한 분류 모델 학습을 통해 격자 내에서 표현되어야 하는 불똥 입자의 생성을 학습하고, 다항 회귀 모델 학습을 통해 불똥 입자의 움직임을 예측한다. 또한, 불똥 입자가 삭제되어야하는 상태를 네트워크 학습을 통해 얻어내며, 수명(Lifespan) 임계값 조절하여 다양한 장면에서 불똥을 제어할 수 있다. 결과적으로 화염의 움직임을 기반으로 불똥의 움직임을 복잡한 수학식이나 디자이너에게 의존하지 않고 인공지능 학습을 통해 쉽게 제어하고 예측하는 결과를 보여준다.

• Korean Chemical Engineering Research
• /
• v.58 no.2
• /
• pp.224-229
• /
• 2020

We propose a machine learning-based method for proactively detecting faults in LDPE processes and predicting equipment lifespan. It is important to detect and prevent unexpected faults in chemical processes in order to maximize safety and productivity. Since LDPE process is a high-pressure process up to 3,000 kg/㎠g or more, once ESD occurs, it can result in productivity loss due to increased maintenance periods. By collecting key variables operation data of the process and using unsupervised machine leaning methods, we developed a fault detection model which detected 4 ESDs 2.4 days prior to the occurrence. In addition, it was confirmed that the life expectancy of a hyper compressor can be predicted by using the physically significant key variables.

• Journal of the Korean Institute of Gas
• /
• v.24 no.6
• /
• pp.91-97
• /
• 2020

Lithium-ion batteries (LIBs) have a longer lifespan, higher energy density, and lower self-discharge rates than other batteries, therefore, they are preferred as an Energy Storage System (ESS). However, during years 2017-2019, 28 ESS fire accidents occurred in Korea, and accurate capacity estimation of LIB is essential to ensure safety and reliability during operations. In this study, data-driven modeling that predicts capacity changes according to the charging cycle of LIB was conducted, and developed models were compared their performance for the selection of the optimal machine learning model, which includes the Decision Tree, Ensemble Learning Method, Support Vector Regression, and Gaussian Process Regression (GPR). For model training, lithium battery test data provided by NASA was used, and GPR showed the best prediction performance. Based on this study, we will develop an enhanced LIB capacity prediction and remaining useful life estimation model through additional data training, and improve the performance of anomaly detection and monitoring during operations, enabling safe and stable ESS operations.

• Design & Manufacturing
• /
• v.16 no.4
• /
• pp.1-6
• /
• 2022

Fine blanking is a press processing technology that can process most of the product thickness into a smooth surface with a single stroke. In this fine blanking process, shear is an essential step. The punches and dies used in the shear are subjected to impacts of tens to hundreds of gravitational accelerations, depending on the type and thickness of the material. Therefore, among the components of the fine blanking mold (dies), punches and dies are the parts with the shortest lifespan. In the actual production site, various types of tool damage occur such as wear of the tool as well as sudden punch breakage. In this study, machine learning algorithms were used to predict these problems in advance. The dataset used in this paper consisted of the signal of the vibration sensor installed in the tool and the measured burr size (tool wear). Various features were extracted so that artificial intelligence can learn effectively from signals. It was trained with 5 features with excellent distinguishing performance, and the SVM algorithm performance was the best among 33 learning models. As a result of the research, the vibration signal at the time of imminent tool replacement was matched with an accuracy of more than 85%. It is expected that the results of this research will solve problems such as tool damage due to accidental punch breakage at the production site, and increase in maintenance costs due to prediction errors in punch exchange cycles due to wear.