scholarly journals From Coastal to Montane Forest Ecosystems, Using Drones for Multi-Species Research in the Tropics

Drones ◽  
2021 ◽  
Vol 6 (1) ◽  
pp. 6
Author(s):  
Dede Aulia Rahman ◽  
Andre Bonardo Yonathan Sitorus ◽  
Aryo Adhi Condro
Keyword(s):  
Habitat Complexity ◽  
High Performance ◽  
Forest Ecosystems ◽  
Survey Methods ◽  
Learning Approaches ◽  
Size Estimation ◽  
Biodiversity Monitoring ◽  
Field Surveys ◽  
Ground Survey ◽  
The Tropics

Biodiversity monitoring is crucial in tackling defaunation in the Anthropocene, particularly in tropical ecosystems. However, field surveys are often limited by habitat complexity, logistical constraints, financing and detectability. Hence, leveraging drones technology for species monitoring is required to overcome the caveats of conventional surveys. We investigated prospective methods for wildlife monitoring using drones in four ecosystems. We surveyed waterbird populations in Pulau Rambut, a community of ungulates in Baluran and endemic non-human primates in Gunung Halimun-Salak, Indonesia in 2021 using a DJI Matrice 300 RTK and DJI Mavic 2 Enterprise Dual with additional thermal sensors. We then, consecutively, implemented two survey methods at three sites to compare the efficacy of drones against traditional ground survey methods for each species. The results show that drone surveys provide advantages over ground surveys, including precise size estimation, less disturbance and broader area coverage. Moreover, heat signatures helped to detect species which were not easily spotted in the radiometric imagery, while the detailed radiometric imagery allowed for species identification. Our research also demonstrates that machine learning approaches show a relatively high performance in species detection. Our approaches prove promising for wildlife surveys using drones in different ecosystems in tropical forests.

scholarly journals Environmental Sound Recognition on Embedded Systems: From FPGAs to TPUs

Electronics ◽  
2021 ◽  
Vol 10 (21) ◽  
pp. 2622
Author(s):  
Jurgen Vandendriessche ◽  
Nick Wouters ◽  
Bruno da Silva ◽  
Mimoun Lamrini ◽  
Mohamed Yassin Chkouri ◽  
...  
Keyword(s):  
Machine Learning ◽  
High Performance ◽  
Machine Learning Techniques ◽  
Sound Recognition ◽  
Learning Approaches ◽  
Environmental Sound ◽  
Embedded Devices ◽  
Power Efficient ◽  
Computationally Intensive ◽  
Environmental Sound Recognition

In recent years, Environmental Sound Recognition (ESR) has become a relevant capability for urban monitoring applications. The techniques for automated sound recognition often rely on machine learning approaches, which have increased in complexity in order to achieve higher accuracy. Nonetheless, such machine learning techniques often have to be deployed on resource and power-constrained embedded devices, which has become a challenge with the adoption of deep learning approaches based on Convolutional Neural Networks (CNNs). Field-Programmable Gate Arrays (FPGAs) are power efficient and highly suitable for computationally intensive algorithms like CNNs. By fully exploiting their parallel nature, they have the potential to accelerate the inference time as compared to other embedded devices. Similarly, dedicated architectures to accelerate Artificial Intelligence (AI) such as Tensor Processing Units (TPUs) promise to deliver high accuracy while achieving high performance. In this work, we evaluate existing tool flows to deploy CNN models on FPGAs as well as on TPU platforms. We propose and adjust several CNN-based sound classifiers to be embedded on such hardware accelerators. The results demonstrate the maturity of the existing tools and how FPGAs can be exploited to outperform TPUs.

scholarly journals Intact Detection of Highly Occluded Immature Tomatoes on Plants Using Deep Learning Techniques

Sensors ◽  
2020 ◽  
Vol 20 (10) ◽  
pp. 2984
Author(s):  
Yue Mu ◽  
Tai-Shen Chen ◽  
Seishi Ninomiya ◽  
Wei Guo
Keyword(s):  
Deep Learning ◽  
Low Cost ◽  
Yield Prediction ◽  
Learning Approaches ◽  
Size Estimation ◽  
Detection Model ◽  
Lighting Conditions ◽  
Learning Techniques ◽  
Location Map ◽  
Tomato Detection

Automatic detection of intact tomatoes on plants is highly expected for low-cost and optimal management in tomato farming. Mature tomato detection has been wildly studied, while immature tomato detection, especially when occluded with leaves, is difficult to perform using traditional image analysis, which is more important for long-term yield prediction. Therefore, tomato detection that can generalize well in real tomato cultivation scenes and is robust to issues such as fruit occlusion and variable lighting conditions is highly desired. In this study, we build a tomato detection model to automatically detect intact green tomatoes regardless of occlusions or fruit growth stage using deep learning approaches. The tomato detection model used faster region-based convolutional neural network (R-CNN) with Resnet-101 and transfer learned from the Common Objects in Context (COCO) dataset. The detection on test dataset achieved high average precision of 87.83% (intersection over union ≥ 0.5) and showed a high accuracy of tomato counting (R2 = 0.87). In addition, all the detected boxes were merged into one image to compile the tomato location map and estimate their size along one row in the greenhouse. By tomato detection, counting, location and size estimation, this method shows great potential for ripeness and yield prediction.

scholarly journals Variability in the Effectiveness of Two Ornithological Survey Methods between Tropical Forest Ecosystems

PLoS ONE ◽  
2017 ◽  
Vol 12 (1) ◽  
pp. e0169786 ◽  
Author(s):  
Thomas Edward Martin ◽  
Josh Nightingale ◽  
Jack Baddams ◽  
Joseph Monkhouse ◽  
Aronika Kaban ◽  
...  
Keyword(s):  
Tropical Forest ◽  
Forest Ecosystems ◽  
Survey Methods

scholarly journals Multiple Suboptimal Solutions for Prediction Rules in Gene Expression Data

2013 ◽  
Vol 2013 ◽  
pp. 1-14
Author(s):  
Osamu Komori ◽  
Mari Pritchard ◽  
Shinto Eguchi
Keyword(s):  
Gene Expression ◽  
High Performance ◽  
Published Data ◽  
Learning Approaches ◽  
Statistical Machine Learning ◽  
Mutual Coherence ◽  
Gene Expressions ◽  
Microarray Gene Expression ◽  
Analysis Methods ◽  
Microarray Gene

This paper discusses mathematical and statistical aspects in analysis methods applied to microarray gene expressions. We focus on pattern recognition to extract informative features embedded in the data for prediction of phenotypes. It has been pointed out that there are severely difficult problems due to the unbalance in the number of observed genes compared with the number of observed subjects. We make a reanalysis of microarray gene expression published data to detect many other gene sets with almost the same performance. We conclude in the current stage that it is not possible to extract only informative genes with high performance in the all observed genes. We investigate the reason why this difficulty still exists even though there are actively proposed analysis methods and learning algorithms in statistical machine learning approaches. We focus on the mutual coherence or the absolute value of the Pearson correlations between two genes and describe the distributions of the correlation for the selected set of genes and the total set. We show that the problem of finding informative genes in high dimensional data is ill-posed and that the difficulty is closely related with the mutual coherence.

scholarly journals Deep Learning Approaches to Automated Video Classification of Upper Limb Tension Test

Healthcare ◽  
2021 ◽  
Vol 9 (11) ◽  
pp. 1579
Author(s):  
Wansuk Choi ◽  
Seoyoon Heo
Keyword(s):  
Deep Learning ◽  
Transfer Learning ◽  
High Performance ◽  
Model Fit ◽  
Fine Tuning ◽  
Learning Approaches ◽  
Video Classification ◽  
Video Clips ◽  
Performance Computing

The purpose of this study was to classify ULTT videos through transfer learning with pre-trained deep learning models and compare the performance of the models. We conducted transfer learning by combining a pre-trained convolution neural network (CNN) model into a Python-produced deep learning process. Videos were processed on YouTube and 103,116 frames converted from video clips were analyzed. In the modeling implementation, the process of importing the required modules, performing the necessary data preprocessing for training, defining the model, compiling, model creation, and model fit were applied in sequence. Comparative models were Xception, InceptionV3, DenseNet201, NASNetMobile, DenseNet121, VGG16, VGG19, and ResNet101, and fine tuning was performed. They were trained in a high-performance computing environment, and validation and loss were measured as comparative indicators of performance. Relatively low validation loss and high validation accuracy were obtained from Xception, InceptionV3, and DenseNet201 models, which is evaluated as an excellent model compared with other models. On the other hand, from VGG16, VGG19, and ResNet101, relatively high validation loss and low validation accuracy were obtained compared with other models. There was a narrow range of difference between the validation accuracy and the validation loss of the Xception, InceptionV3, and DensNet201 models. This study suggests that training applied with transfer learning can classify ULTT videos, and that there is a difference in performance between models.

scholarly journals Forest ecosystem services in the tropics: an imperfect assessment of their contribution to welfare, and environmental policy implications

2020 ◽  
Vol 27 (1) ◽  
pp. 89-107
Author(s):  
Martín A. López-Ramírez ◽  
Keyword(s):  
Land Use ◽  
Ecosystem Services ◽  
Forest Ecosystems ◽  
Agricultural Land ◽  
Natural Capital ◽  
Bootstrap Method ◽  
Value Added ◽  
Policy Implications ◽  
Production Scale ◽  
The Tropics

Introduction: The specific relation between ecosystem services (ES), land use systems productivity and welfare is complex and poorly understood.Objective: To analyze the relationship between natural capital and welfare in the Agriculture, Forestry and Other Land Use (AFOLU) sector to assess Ecosystem Services contribution to agriculture, forestry and fishing value added (GDP [Gross Domestic Product]) and analyze policy implications.Materials and methods: Using land use allocation variables, forest transition model and land use GDP for 97 tropical countries, the production function of AFOLU sector was estimated using a linear regression model and a bootstrap method. The properties of the function were analyzed, and the optimal land allocation was calculated.Results and discussion: There is a direct contribution and an indirect contribution from forest ecosystems to GDP. The direct effect is manifested through the partial elasticity of forestland (P < 0.05). The indirect effect is reflected through the production scale (P < 0.05). Partial elasticity of agriculture is significantly higher than partial elasticity of forestland (P < 0.05) and production scale increases as forestland is depleted (P < 0.05). In addition, optimal land use indicates that 75 countries have forest surplus (13.2 Mkm2) and 22 forest deficit (1.5 Mkm2).Conclusions: Forest ecosystems in the AFOLU sector in the tropics produce ecosystem services for society. However, these contributions are dwarfed by agricultural land productivity.

Sign in / Sign up

Export Citation Format

Share Document