Refine

Claim type

Research area

Polarity

Statistics

More filters

Method / resourceobservedoriginal resultnegativemeasured

Claim · model-written summary

Attention based models reduced classification speed.

Outcome
classification speede0

Not reportedComparatorValue

Verbatim

e0

“While attention-based models improved accuracy, they also caused reduced classification speed.”

✓ located verbatim in the source · abstract, characters 1939–2033

Title

Lightweight vision transformer and ResNet-9 models for real-time plant disease detection and pest classification with SHAP explainability

Wasswa Shafik; Ali Tufail; Liyanage Chandratilak De Silva; et al. BMC Plant Biology 2026. doi:10.1186/s12870-026-08667-8

Other claims from this paper (8)
Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Clustering increased classification speed.

Taxon
Fruitt0
Outcome
speed with which classification operation is performede0
Direction
increasese0

Not reportedComparator

Verbatim

e0

“Clustering operation increases the speed with which classification operation is performed”

✓ located verbatim in the source · abstract, characters 708–797
t0

“Fruit Disease Detection”

✓ located verbatim in the source · title, characters 0–23

Title

Fruit Disease Detection Using Convolution Neural Network Approach

Shivani .; Sharanjit Singh Asian Journal of Computer Science and Technology 2018. doi:10.51983/ajcst-2018.7.2.1871

Other claims from this paper (3)
Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

The system outperformed traditional CNN classification systems in speed and reliability.

Taxon
Coffee Beanst0
Outcome
speed and reliabilitye0
Direction
outperforminge0
Comparator
traditional CNN classification systemse0

Verbatim

e0

“outperforming traditional CNN classification systems in speed and reliability”

✓ located verbatim in the source · abstract, characters 750–827
t0

“Coffee Beans”

✓ located verbatim in the source · title, characters 50–62

Title

High-Accuracy Real-Time Defect Classification for Coffee Beans Using Deep Learning

Archana N; Mahalaksmi; C G Yashasraj; et al. Iconic Research and Engineering Journals 2025. doi:10.64388/irev9i6-1712938

Other claims from this paper (2)
Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

The MobileNet-based model excelled in classification speed (2556 seconds) for rice grains.

Outcome
speed of classificatione2
Direction
excellede2
Value
2556 secondse2

Verbatim

t0

“rice grain classification”

✓ located verbatim in the source · title, characters 72–97
e2

“the MobileNet-based model excelled in the speed of classification (2556 seconds)”

✓ located verbatim in the source · abstract, characters 1125–1205

Title

A comparative study of state-of-the-art deep learning architectures for rice grain classification

Farshad Farahnakian; Farshad Farahnakian; Javad Sheikh; et al. Journal of Agriculture and Food Research 2023. doi:10.1016/j.jafr.2023.100890

Other claims from this paper (2)
Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Multi-feature fusion classification was relatively higher in speed and accuracy than single-feature classification.

Outcome
speed and accuracye0
Direction
relatively highe0
Comparator
single feature classificatione0

Verbatim

e0

“Compared with the single feature classification, it is found that the multi-feature fusion classification is relatively high in speed and accuracy”

✓ located verbatim in the source · abstract, characters 1023–1169
t0

“Tomato”

✓ located verbatim in the source · title, characters 0–6

Title

Tomato grading based on Machine vision D-S multi-feature fusion algorithm

Yanzhi Bi; Chao Zhang; Peisi Zhong; et al. International Conference on Algorithms Software Engineering and Network Security 2024. doi:10.1145/3677182.3677220

Other claims from this paper (3)
Method / resourceauthor interpretationoriginal resultpositivemeasured

Claim · model-written summary

The methods were judged competitive in computational speed and classification accuracy.

Outcome
computational speed and classification accuracye0
Direction
highly competitivee0

Not reportedComparatorValue

Verbatim

e0

“the new methods are highly competitive in terms of computational speed and classification accuracy of future observation.”

✓ located verbatim in the source · abstract, characters 814–935

Title

METODE KLASIFIKASI BERSTRUKTUR POHON DENGAN ALGORITMA CRUISE

Yasmin Erika F.; Andriansyah Andriansyah DOAJ (DOAJ: Directory of Open Access Journals) 2014

Other claims from this paper (3)
Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Mean spectra classification outperformed textural features except for three-class classification at higher speed.

Taxon
Pickling Cucumberst0
Outcome
classificatione0
Direction
bettere0
Qualifier
except in the three-class classification for the higher conveyor speede0
Comparator
textural feature-based classificatione0

Verbatim

e0

“The mean spectra-based classification achieved better results than the textural feature-based classification except in the three-class classification for the higher conveyor speed”

✓ located verbatim in the source · abstract, characters 1811–1990
t0

“Pickling Cucumbers”

✓ located verbatim in the source · title, characters 100–118

Title

Hyperspectral Imaging-based Classification and Wavebands Selection for Internal Defect Detection of Pickling Cucumbers

Haiyan Cen; Renfu Lu; Diwan Ariana; et al. 2013 Kansas City, Missouri, July 21 - July 24, 2013 2013. doi:10.13031/aim.20131671220

Other claims from this paper (7)
Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

The classifier reached a maximum speed of 97fps for tomato ripeness classification.

Outcome
computation speede0
Direction
maximume0
Value
97fpse0

Verbatim

e0

“The ripeness classification was performed was performed at a maximum computation speed of 97fps”

✓ located verbatim in the source · abstract, characters 656–751
t0

“Tomato Ripeness”

✓ located verbatim in the source · title, characters 10–25

Title

Real-Time Tomato Ripeness Classification System based on Deep Learning Model for Object Detection

KwangEun Ko; Seung-Hwan Yang; Inhoon Jang Journal of Institute of Control Robotics and Systems 2018. doi:10.5302/j.icros.2018.18.0166

Other claims from this paper (2)
Method / resourceobservedoriginal resultpositivemeasured

Claim · model-written summary

Classification accuracy was slightly higher at low than high conveyor speed.

Taxon
Pickling Cucumberst0
Outcome
overall classification accuraciese0
Direction
slightly highere0
Comparator
higher conveyor speede0

Verbatim

e0

“The overall classification accuracies for all selected waveband ratios at the low conveyor speed were slightly higher than those at the higher conveyor speed”

✓ located verbatim in the source · abstract, characters 1992–2149
t0

“Pickling Cucumbers”

✓ located verbatim in the source · title, characters 100–118

Title

Hyperspectral Imaging-based Classification and Wavebands Selection for Internal Defect Detection of Pickling Cucumbers

Haiyan Cen; Renfu Lu; Diwan Ariana; et al. 2013 Kansas City, Missouri, July 21 - July 24, 2013 2013. doi:10.13031/aim.20131671220

Other claims from this paper (7)
Intervention effectobservedoriginal resultno effectmeasured

Claim · model-written summary

Thickness classification did not affect seed vigor and viability after sowing across speed variation.

Taxon
sunflowerHelianthus annuust0
Treatment
seeds classificatione0
Outcome
seed vigor and viabilitye0
Direction
does not affecte0

Not reportedComparator

Verbatim

t0

“sunflower”

✓ located verbatim in the source · title, characters 11–20
e0

“seeds classification does not affect seed vigor and viability after sowing under speed variation”

✓ located verbatim in the source · abstract, characters 828–924

Title

Quality of sunflower seeds in function of thickness classification and sowing under speed variation of the seeder-fertilizer

Dryelle Sifuentes Pallaoro; Pedro Silvério Xavier Pereira; Antônio Renan Berchol da Silva; et al. Revista CERES 2022. doi:10.1590/0034-737x202269060015

Other claims from this paper (4)

Lexical search (BM25). All words must match; if nothing does, any word. Organism names also match every spelling of the same organism. No semantic search yet.