Hybrid lightweight Deep-learning model for Sensor-fusion basketball Shooting-posture recognition

J Fan, S Bi, R Xu, L Wang, L Zhang - Measurement, 2022 - Elsevier
Shooting-posture recognition is an important area in basketball technical movement
recognition domain. This paper proposes the squeeze convolutional gated attention (SCGA) …

Improved multi-plant disease recognition method using deep convolutional neural networks in six diseases of apples and pears

YH Gu, H Yin, D Jin, R Zheng, SJ Yoo - Agriculture, 2022 - mdpi.com
Plant diseases are a major concern in the agricultural sector; accordingly, it is very important
to identify them automatically. In this study, we propose an improved deep learning-based …

Ensembles of data-efficient vision transformers as a new paradigm for automated classification in ecology

SP Kyathanahally, T Hardeman, M Reyes, E Merz… - Scientific Reports, 2022 - nature.com
Monitoring biodiversity is paramount to manage and protect natural resources. Collecting
images of organisms over large temporal or spatial scales is a promising practice to monitor …

YOLO object detection models can locate and classify broad groups of flower-visiting arthropods in images

T Stark, V Ştefan, M Wurm, R Spanier… - Scientific Reports, 2023 - nature.com
Develoment of image recognition AI algorithms for flower-visiting arthropods has the
potential to revolutionize the way we monitor pollinators. Ecologists need light-weight …

Preliminary study on hourly dynamics of a ground-dwelling invertebrate community in a farmland vineyard

M Gao, J Sun, T Lu, Y Zheng, J Liu - Insects, 2024 - mdpi.com
Simple Summary Understanding diel variations in ground-dwelling invertebrates is an
important issue for agricultural ecology, which has been extensively studied at the …

Ensembles of vision transformers as a new paradigm for automated classification in ecology

S Kyathanahally, T Hardeman, M Reyes, E Merz… - arXiv preprint arXiv …, 2022 - arxiv.org
Monitoring biodiversity is paramount to manage and protect natural resources. Collecting
images of organisms over large temporal or spatial scales is a promising practice to monitor …

Comparison of single-shot and two-shot deep neural network models for whitefly detection in IoT Web application

CU Parab, C Mwitta, M Hayes, JM Schmidt, D Riley… - AgriEngineering, 2022 - mdpi.com
In this study, we have compared YOLOv4, a single-shot detector to Faster-RCNN, a two-shot
detector to detect and classify whiteflies on yellow-sticky tape (YST). An IoT remote whitefly …

Coccinellidae beetle specimen detection using convolutional neural networks

M Vega, DS Benítez, N Pérez, D Riofrío… - … on Applications of …, 2021 - ieeexplore.ieee.org
In this work, we propose a ladybird beetle detector based on a deep learning classifier and
the weighted Hausdorff distance as a loss function. The detector was trained and validated …

Weighted Hausdorff Distance Loss as a Function of Different Metrics in Convolutional Neural Networks for Ladybird Beetle Detection

M Vega, DS Benítez, N Pérez, D Riofrío… - … on Applications of …, 2021 - Springer
This work compares five different distance metrics (ie, Euclidean, Chebyshev, Manhattan,
Mahalanobis, and Canberra) implemented in the weighted Hausdorff distance (WHD) as …

Habitat and Morphometric Data Based Identification of Tiger Beetle (Coleoptera, Cicindelinae) Species in Sri Lanka Using Classification Algorithms

L Abeywardhana, A Nugaliyadde… - Available at SSRN … - papers.ssrn.com
Habitat and morphometric information can be used as factors to differentiate species,
primarily for species that are habitat Specific. Using the above concept a predictive model …