Identifying Important Tweets by Considering the Potentiality of Neurons

Information Engineering Express

Sakai

2021

Self Cite

Management policies are important guidelines for companies; they describe the founding spirit, company motto, and other objectives. Therefore, we consider that management policy may affect a company's profitability. This study examined management policies from manufacturing companies and extracted keywords that influence profitability.Management policies and profitability [measured by the return on assets (ROA)] data were collected from annual securities reports, because the report descriptions are accurate, and the reports are easy to obtain. The management policies were written in natural language, and the analysis data were complex; therefore, we used a neural computational method known as "potential learning," which can interpret internal representations. To extract keywords that influence profitability, we designed a classification model of profitability with the management policy as input, and a model with an accuracy of 0.6115 was created. The results suggest that the management policies of highly profitable companies are diverse in using the word "improvement," which may influence the ROA.

Section: Methodsmentioning

confidence: 99%

Relationship Between Management Policies and Profitability of Manufacturing Companies Listed in the First Section of the Tokyo Stock Exchange (2016 Results)

Information Engineering Express

Sakai

2021

Self Cite

“…They determined that the model based on PL performed better than the conventional method and succeeded to extract an important variable. In addition, PL has been applied to data in various fields, such as the messages displayed in Twitter at the time of a disaster (Kitajima et al 2016b) and the words involved in the president messages of the Japanese companies (Kitajima et al 2019). Since PL has been used for data analysis in various fields, we aim to identify the most significant parameters that disturb the magnetosphere based on PL.…”

Section: Introductionmentioning

confidence: 99%

Investigation of the relationship between geomagnetic activity and solar wind parameters based on a novel neural network (potential learning)

Nowada

2022

Earth Planets Space

Predicting geomagnetic conditions based on in-situ solar wind observations allows us to evade disasters caused by large electromagnetic disturbances originating from the Sun to save lives and protect economic activity. In this study, we aimed to examine the relationship between the Kp index, representing global magnetospheric activity level, and solar wind conditions using an interpretable neural network known as potential learning (PL). Data analyses based on neural networks are often difficult to interpret; however, PL learns by focusing on the “potentiality of input neurons” and can identify which inputs are significantly utilized by the network. Using the full advantage of PL, we extracted the influential solar wind parameters that disturb the magnetosphere under southward Interplanetary magnetic field (IMF) conditions. The input parameters of PL were the three components of the IMF (Bx, By, Bz), solar wind flow speed (Vx), and proton number density (Np) in geocentric solar magnetospheric (GSM) coordinates obtained from the OMNI solar wind database between 1998 and 2019. Furthermore, we classified these input parameters into two groups (targets), depending on the Kp level: Kp = 6–9 (positive target) and Kp = 0 to 1 + (negative target). Negative target samples were randomly selected to ensure that numbers of positive and negative targets were equal. The PL results revealed that solar wind flow speed is an influential parameter for increasing Kp under southward IMF conditions, which was in good agreement with previous reports on the statistical relationship between the Kp index and solar wind velocity, and the Kp formulation based on the IMF and solar wind plasma parameters. Based on this new neural network, we aim to construct a more correct and parameter-dependent space weather forecasting model. Graphical Abstract

“…to data in various fields, such as Tweet data at the time of a disaster (Kitajima et al 2016b) and data on president messages of the companies (Kitajima et al 2019). Since PL has been used for data analysis in various fields, we aim to identify the most significant parameters that disturb the magnetosphere based on PL.…”

Section: Introductionmentioning

confidence: 99%

Investigation of the Relationship between Geomagnetic Activity and Solar Wind Parameters Based on A Novel Neural Network (Potential Learning)

Nowada

2022

Preprint

Self Cite

Predicting geomagnetic conditions based on in-situ solar wind observations allows us to evade disasters caused by large electromagnetic disturbances originating from the Sun to save lives and protect economic activity. In this study, we aimed to examine the relationship between the Kp index, representing global magnetospheric activity level, and solar wind conditions using an interpretable neural network known as potential learning (PL). Data analyses based on neural networks are difficult to interpret; however, PL learns by focusing on the "potentiality of input neurons" and can identify which inputs are significantly utilized by the network. Using the full advantage of PL, we extracted the influential solar wind parameters that disturb the magnetosphere under southward Interplanetary magnetic field (IMF) conditions. The input parameters of PL were the three components of the IMF (Bx, By, -Bz(Bs)), solar wind flow speed (Vx), and proton number density (Np) in geocentric solar ecliptic (GSE) coordinates obtained from the OMNI solar wind database between 1998 and 2019. Furthermore, we classified these input parameters into two groups (targets), depending on the Kp level: Kp = 6-to 9 (positive target) and Kp = 0 to 1+ (negative target). Negative target samples were randomly selected to ensure that numbers of positive and negative targets were equal. The PL results revealed that solar wind flow speed is an influential parameter for increasing Kp under southward IMF conditions, which was in good agreement with previous reports on the statistical relationship between the Kp index and solar wind velocity, and the Kp formulation based on the IMF and solar wind plasma parameters. Based on this new neural network, we aim to construct a more correct and parameter-dependent space weather forecasting model.