value prediction
Recently Published Documents


TOTAL DOCUMENTS

359
(FIVE YEARS 90)

H-INDEX

27
(FIVE YEARS 6)

2021 ◽  
Vol 13 ◽  
pp. 229-232
Author(s):  
Meixuan Li

The article crawls the audience comments from some videos on the YouTube platform of "Talk Show Conference Season 3", extracts relevant content about popular champions Wang Mian and Wang Jianguo for sentiment analysis, uses Google Data API to design a crawler to obtain comment content, and to crawl After the received content is preprocessed, Word2vec is used to build a word vector model, and finally an LSTM model is built for training prediction. It can be seen that the popularity of the player Wang Mian is higher than that of Wang Jianguo. The entertainment company where the two are located can adjust the artist's work according to the changes in the public's love for the players.


2021 ◽  
Author(s):  
TianGe (Terence) Chen ◽  
Angel Chang ◽  
Evan Gunnell ◽  
Yu Sun

When people want to buy or sell a personal car, they struggle to know when the timing is best in order to buy their favorite vehicle for the best price or sell for the most profit. We have come up with a program that can predict each car’s future values based on experts’ opinions and reviews. Our program extracts reviews which undergo sentiment analysis to become our data in the form of positive and negative sentiment. The data is then collected and used to train the Machine Learning model, which will in turn predict the car’s retail price.


2021 ◽  
pp. 321-332
Author(s):  
Rachna Yogesh Sable ◽  
Shivani Goel ◽  
Pradeep Chatterjee

2021 ◽  
Vol 12 ◽  
Author(s):  
Agustin Barría ◽  
John A. H. Benzie ◽  
Ross D. Houston ◽  
Dirk-Jan De Koning ◽  
Hugues de Verdal

Nile tilapia is a key aquaculture species with one of the highest production volumes globally. Genetic improvement of feed efficiency via selective breeding is an important goal, and genomic selection may expedite this process. The aims of this study were to 1) dissect the genetic architecture of feed-efficiency traits in a Nile tilapia breeding population, 2) map the genomic regions associated with these traits and identify candidate genes, 3) evaluate the accuracy of breeding value prediction using genomic data, and 4) assess the impact of the genetic marker density on genomic prediction accuracies. Using an experimental video recording trial, feed conversion ratio (FCR), body weight gain (BWG), residual feed intake (RFI) and feed intake (FI) traits were recorded in 40 full-sibling families from the GIFT (Genetically Improved Farmed Tilapia) Nile tilapia breeding population. Fish were genotyped with a ThermoFisher Axiom 65 K Nile tilapia SNP array. Significant heritabilities, ranging from 0.12 to 0.22, were estimated for all the assessed traits using the genomic relationship matrix. A negative but favourable genetic correlation was found between BWG and the feed-efficiency related traits; −0.60 and −0.63 for FCR and RFI, respectively. While the genome-wide association analyses suggested a polygenic genetic architecture for all the measured traits, there were significant QTL identified for BWG and FI on chromosomes seven and five respectively. Candidate genes previously found to be associated with feed-efficiency traits were located in these QTL regions, including ntrk3a, ghrh and eif4e3. The accuracy of breeding value prediction using the genomic data was up to 34% higher than using pedigree records. A SNP density of approximately 5,000 SNPs was sufficient to achieve similar prediction accuracy as the full genotype data set. Our results highlight the potential of genomic selection to improve feed efficiency traits in Nile tilapia breeding programmes.


Author(s):  
Takanori Hasegawa ◽  
Rui Yamaguchi ◽  
Masanori Kakuta ◽  
Masataka Ando ◽  
Jung Songee ◽  
...  

2021 ◽  
Author(s):  
Mingxiang Guo ◽  
Xuejun Pan ◽  
Shifan Song ◽  
Wenjuan Jia ◽  
Xiaodong Liu

2021 ◽  
pp. 1-10
Author(s):  
Ahmet Tezcan Tekin ◽  
Tolga Kaya ◽  
Ferhan Cebi

The use of fuzzy logic in machine learning is becoming widespread. In machine learning problems, the data, which have different characteristics, are trained and predicted together. Training the model consisting of data with different characteristics can increase the rate of error in prediction. In this study, we suggest a new approach to assembling prediction with fuzzy clustering. Our approach aims to cluster the data according to their fuzzy membership value and model it with similar characteristics. This approach allows for efficient clustering of objects with more than one cluster characteristic. On the other hand, our approach will enable us to combine boosting type ensemble algorithms, which are various forms of assemblies that are widely used in machine learning due to their excellent success in the literature. We used a mobile game’s customers’ marketing and gameplay data for predicting their customer lifetime value for testing our approach. Customer lifetime value prediction for users is crucial for determining the marketing cost cap for companies. The findings reveal that using a fuzzy method to ensemble the algorithms outperforms implementing the algorithms individually.


Author(s):  
João Roberto Bertini ◽  
Sérgio Ferreira Batista Filho ◽  
Mei Abe Funcia ◽  
Luis Otávio Mendes da Silva ◽  
Antonio Alberto S. Santos ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document