User Experience (UX) researchers and designers who seek to predict users39; subjective impressions nowadays turn to Machine learning (ML) models trained on marked-up data. Labeling of graphical user interfaces (UIs)...
详细信息
Servo motors, with their strong load capacity, reliable operation, and high efficiency, are widely used in electrical production and daily life. As one of the main power sources in modern industry, a motor failure can...
详细信息
ISBN:
(纸本)9798350375145;9798350375138
Servo motors, with their strong load capacity, reliable operation, and high efficiency, are widely used in electrical production and daily life. As one of the main power sources in modern industry, a motor failure can paralyze operating mechanisms and even threaten life safety. Therefore, this paper conducts intelligent diagnosis research on motor drive systems based on neural networks. Firstly, finite element method simulation is used to obtain fault data of the servo motor and collect sufficient samples. Secondly, addressing the slow convergence speed caused by the deepening of traditional convolutional neural networks (CNN), this paper combines residual learning with convolutional neural networks, proposing a residual learning-based convolutional neural network with Wide Kernel (R-WDCNN) model for fault classification. Finally, compared with traditional convolutional neural networks, the R-WDCNN algorithm achieves higher recognition accuracy and faster convergence speed.
Missing data is a prevalent problem in data science for many fields such as natural, social, and health sciences. Since most regression methods can not handle missing data directly, imputation methods are used in data...
详细信息
ISBN:
(纸本)9783031777301;9783031777318
Missing data is a prevalent problem in data science for many fields such as natural, social, and health sciences. Since most regression methods can not handle missing data directly, imputation methods are used in data pre-processing. Finding the best imputation method is non-trivial, however. Moreover, our results show that an independent choice for a best imputation method does not always result in the best predictive performance in the end;the combination matters. Furthermore, search-based approaches for finding a best-fitting imputer/regressor-pair can be computationally intensive. In this paper, we propose the MetaLIRS (Meta learning Imputation and Regression Selection) framework for developing resource-friendly ML-based recommendation models for method selection. With MetaLIRS, we constructed a proof-of-concept recommendation model based on 12 meta-features that achieves an accuracy of 63% for selecting the best-fitting imputer/regressor-pair. A data scientist can use this model for a quick resource-friendly recommendation on which imputation and regression method to use for their particular data set and task without the need for an expensive grid search among methods.
The abnormal growth of skin cells that are exposed to the sun is identified as skin cancer. Even though skin cancer is curable, late diagnosis and improper treatment can lead to severe effects and death. Melanoma has ...
详细信息
Strong battery management systems (BMS) are required to guarantee the best possible performance, safety, and longevity of battery packs due to the quick development of electric vehicles (EVs). This study introduces an...
详细信息
Alzheimer39;s is one of the progressively debilitating conditions, and it currently affects millions of people worldwide with no definitive medication for treatment. Understanding the nature of this disease is very ...
详细信息
This research study proposes an AI application for a HR interview simulation system to improve candidate assessment. The proposed system is based on the recent AI technologies that generate questions out of the candid...
详细信息
With the rapid development of the global new energy vehicle industry and the growing demand for professional technical talents, this paper introduces an online course and assessment system for new energy vehicles, whi...
详细信息
The high number of sentiment analysis systems and applications developed over the last few years provided companies with very sophisticated analysis tools, allowing them to establish preferences, trends and patterns o...
详细信息
ISBN:
(纸本)9783031777370;9783031777387
The high number of sentiment analysis systems and applications developed over the last few years provided companies with very sophisticated analysis tools, allowing them to establish preferences, trends and patterns of customer behavior. This is quite important for companies intending to change their way of being, promoting work actions aimed at specific customer segments, to obtain business advantages and improve their image and performance in the market in which they work. In this paper, we present and describe a sentiment analysis system that combine techniques based on ontologies and domain lexicons, to provide relevant indicators to support the evaluation of the degree of user satisfaction and know the influence of each ontological element incorporated in opinion texts in sentiment classification.
Coronavirus pandemic caused by a deadly virus that rapidly spread worldwide, necessitated the usage of face mask to minimize the airborne transmission of the virus. An automated face mask recognition system has made i...
详细信息
暂无评论