A patent quality classification model based on an artificial immune system

Tsao, Cheng-Chin; Chang, Pei‐Chann; Fan, Chin-Yuan; Chang, Shu-Hao; Phillips, Fred

doi:10.1007/s00500-016-2212-0

Cited by 10 publications

(4 citation statements)

References 32 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Bian Yali (2013) focused on the nano industry and found that the quantity and quality of patent science citations and patent quality are positively related through empirical research [26]. Aiming at the defects of the traditional patent analysis system, Wu et al (2016) and Tsao et al (2017) developed an automatic patent quality analysis system based on the evaluation indicators of patent quality. Compared with the traditional manual analysis method, the new system can effectively and accurately analyze the patent quality while saving time and manpower [27][28].…”

Section: Correlational Researchmentioning

confidence: 99%

“…Aiming at the defects of the traditional patent analysis system, Wu et al (2016) and Tsao et al (2017) developed an automatic patent quality analysis system based on the evaluation indicators of patent quality. Compared with the traditional manual analysis method, the new system can effectively and accurately analyze the patent quality while saving time and manpower [27][28]. Boeing and Mueller (2016) pointed out that although the number of patent applications in China has increased significantly in recent years, the quality of patents has declined [29].…”

Section: Correlational Researchmentioning

confidence: 99%

See 1 more Smart Citation

Patent Quality Literature Review

Wang¹

2023

FBEM

View full text Add to dashboard Cite

Patent quality is an early concept. At present, many researches on patent quality have been carried out. This paper combs the research on patent quality, and analyzes the views of relevant research to promote the research on patent quality. In this paper, the concept, measurement index and related research of patent quality are reviewed by literature analysis. Compared with defining patent quality, existing researches prefer to analyze the evaluation indicators of patent quality. The measurement of patent quality can be roughly divided into two categories: using a single indicator and using multiple indicators to build a comprehensive evaluation index. At present, there are more and more researches on patent quality in China, but they are obviously behind other countries. It has become the trend of patent quality research in China to study the evaluation indicators of patent quality and use them in empirical analysis.

show abstract

Section: Correlational Researchmentioning

confidence: 99%

Section: Correlational Researchmentioning

confidence: 99%

Patent Quality Literature Review

Wang¹

2023

FBEM

View full text Add to dashboard Cite

show abstract

“…Immune network algorithms have been used in clustering, data visualization, control, optimization domains, and share properties with arti icial neural networks [31]. AIN has also been used in collaborating iltering [32], [33], [34] and patent quality classi ication model [35].…”

Section: B Arti Icial Immune Networkmentioning

confidence: 99%

An artificial immune network based novel approach to predict short term load forecasting

2017

J. adv. ethnol. eng. res.

View full text Add to dashboard Cite

Recent trends of Short-Term Load Forecasting (STLF) is a key issue to regulate power in the electricity market. Many researchers have performed research in this area but it still needs an accurate and robust load forecast method. In this paper, we propose a novel Arti icial Immune Network (AIN)-based approach to predict forecast load depending on last three days' mean actual load. The approach creates an immune memory using time series to forecast one-day ahead hourly loads. The method takes hourly loads separately as an individual daily time series and considers it as an antigen, an af inity is calculated between an antigen and antibody in Immune Networks (INs). A cross-reactivity threshold is used to ind the appropriate cluster for an antigen in an immune network. The historical dataset of Poland is trained and tested by this method which predicts more accurately compared to the most recently existing STLF methods, such as simple Nearest Neighbor (NN), Multilayer Perceptron (MLP), Fuzzy Estimators (FE), and Arti icial Immune System (AIS).

show abstract

“…5. ¿Qué variable fue determinante a considerar y resultó ajena a la observación empírica, si los programas estadísticos son incapaces de analizar cientos de miles o millones de datos y esto carece de sentido al reconocer las decisiones desde una muestra probabilística aleatoria y, por el contrario, si no se considera tampoco pudiera hacerse inferencias a la población (Tsao et al, 2016)?…”

Section: Resumen Introducciónunclassified

Decisión Formativa Como Elemento De La Investigación Científica Desde La Conceptualización Estadística Y Ciencia De Datos: Lo Obvio, No Tan Obvio

Pérez¹,

Argota-Pérez

Becerra

et al. 2023

Paideia XXI

View full text Add to dashboard Cite

El propósito del estudio fue describir la necesidad en la toma de decisiones desde la formación conceptualizada entre la Estadística y Ciencia de Datos. Cuatro elementos son claves en la ciencia: teoría, datos, metodología y problema, por cuanto, si los datos forman parte de la ciencia entonces, parece erróneo que exista una Ciencia de Datos, pues ninguna metodología desde la Ciencia de Datos puede decidir, el patrón “ideal o correcto” dado que existen múltiples patrones a comprenderse. Por su parte, si los programas estadísticos son incapaces de analizar cientos de miles de datos (carece de sentido al reconocerse las decisiones desde una muestra probabilística aleatoria y, por el contrario, no considerarse imposibilita hacer inferencias), entonces la posibilidad de representar la diversidad desde la Estadística es limitada, ya que existe una centralización en minimizar las sumas de las desviaciones al cuadrado medio y no comprender la diversidad que realiza la Ciencia de Datos. Se concluye, que la Estadística suma a la confiabilidad y validez, mientras que la Ciencia de Datos permite el desarrollo de metodologías que condicionan a la incorporación de tecnologías donde resulta difícil desmarcar la barrera entre la Estadística y la Ciencia de Datos, pues en algunas ocasiones son indistintas entre sí y en otros casos se comparte una asociación. Por tanto, el dominio del tratamiento de los datos desde la Estadística y el aprendizaje automático que facilita la Ciencia de Datos se requiere para la decisión, pero debe existir la formación en ambos campos de estudio. Palabras clave: ciencia de datos – competencia profesional – decisiones – estadística

show abstract

A patent quality classification model based on an artificial immune system

Cited by 10 publications

References 32 publications

Patent Quality Literature Review

Patent Quality Literature Review

An artificial immune network based novel approach to predict short term load forecasting

Decisión Formativa Como Elemento De La Investigación Científica Desde La Conceptualización Estadística Y Ciencia De Datos: Lo Obvio, No Tan Obvio

Contact Info

Product

Resources

About