Image classification using boosted local features with random orientation and location selection

Zhang, Chunjie; Cheng, Jian; Zhang, Yifan; Liu, Jing; Liang, Chao; Pang, Junbiao; Huang, Qingming

doi:10.1016/j.ins.2015.03.011

Cited by 13 publications

(2 citation statements)

References 47 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is unclear whether NT parameter should simply be set to the largest computationally manageable value or whether a smaller NT parameter may be sufficient or in some cases even better [37], [38]. RFO classifiers have been used for account classification in online social networks [39], image classification [40] or feature extraction [41].…”

Section: A Machine Learning Classifiersmentioning

confidence: 99%

Automatic Learning Framework for Pharmaceutical Record Matching

et al. 2020

View full text Add to dashboard Cite

Pharmaceutical manufacturers need to analyse a vast number of products in their daily activities. Many times, the same product can be registered several times by different systems using different attributes, and these companies require accurate and quality information regarding their products since these products are drugs. The central hypothesis of this research work is that machine learning can be applied to this domain to efficiently merge different data sources and match the records related to the same product. No human is able to do this in a reasonable way because the number of records to be matched is extremely high. This paper presents a framework for pharmaceutical record matching based on machine learning techniques in a big data environment. The proposed framework aims to explode the well-known rules for the matching of records from different databases for training machine learning models. Then the trained models are evaluated by predicting matches with records that do not follow these known rules. Finally, the production environment is simulated by generating a huge amount of combinations of records and predicting the matches. The obtained results show that, despite the good results obtained with the training datasets, in the production environment, the average accuracy of the best model is around 85%. That shows that matches which do not follow the known rules can be predicted and, considering that there is not a human way to process this amount of data, the results are promising.

show abstract

Section: A Machine Learning Classifiersmentioning

confidence: 99%

Automatic Learning Framework for Pharmaceutical Record Matching

et al. 2020

View full text Add to dashboard Cite

show abstract

“…Recently, research into drug taste masking has been highlighted in the popular press (2)(3)(4)(5) with taste masking using bitterness suppressants (BSs) as an important topic. (6)(7)(8)(9)(10) BSs compensate for the bitter substance by blocking bitter taste receptors, truncating the bitterness signal transmission or by offering an even greater signal to the sweet receptors. BSs have different mechanisms.…”

Section: Introductionmentioning

confidence: 99%

Traditional Human Taste Panel and Taste Sensors Methods for Bitter Taste Masking Research on Combined Bitterness Suppressants of Berberine Hydrochloride

2017

Sensors and Materials

View full text Add to dashboard Cite

Bitterness suppressants (BSs) can improve the taste of bitter medicines and mask the taste of bitter foodstuffs. Our goal here was to establish a method of analyzing bitterness using both a traditional human taste panel method (THTPM) and a taste sensors method. Sucralose (SL), sodium ferulate (SF), and β-cyclodextrin (β-CD), and their combinations were tested for their abilities to mask the bitter taste of berberine hydrochloride (BBR). SF showed a weak effect in masking the bitter taste of BBR, whereas SL and β-CD showed stronger effects. The effect of SL on bitter taste masking was linear with the logarithm of concentration, while the effect of β-CD was linear with its concentration. When β-CD and SL were used in combination, β-CD played a major role in taste masking. For this combination, a good correlation was found between the indices of THTPM and the taste sensors method. The taste sensors method can accurately predict the intensity of bitterness of BBR. Thus, it can be an effective tool for the screening of BS of BBR and the study of the taste-masking characteristics of BS combinations.

show abstract