The Experts below are selected from a list of 297 Experts worldwide ranked by ideXlab platform
Bing Zheng - One of the best experts on this subject based on the ideXlab platform.
-
Vision-Based In Situ Monitoring of Plankton Size Spectra Via a Convolutional Neural Network
IEEE Journal of Oceanic Engineering, 2020Co-Authors: Nan Wang, Haiyong Zheng, Jia Yu, Biao Yang, Bing ZhengAbstract:Plankton size spectra monitoring is crucial for managing and conserving aquatic ecosystems. Thus, we develop an in situ size spectra monitoring system to obtain the size spectra of Plankton and the information of their living status underwater. The system consists of an imaging unit and an information processing unit. The imaging part applies a darkfield illumination to enhance the image contrast. Three lenses with different magnifications are alternated by a motor automatically to capture sizes of Plankton from 3 μm to 3 mm. Moreover, the system can analyze the captured images in real time using the proposed multitask size spectra convolutional neural network, obtaining size spectra and density distribution of Plankton simultaneously. Field test confirms that our system performs well both in imaging and information processing. Furthermore, the system can provide the living behavior of Plankton, thereby helping biologists to study the aquatic ecosystem effectively and precisely.
-
Video-Based Real Time Analysis of Plankton Particle Size Spectrum
IEEE Access, 2019Co-Authors: Jia Yu, Zhibin Yu, Haiyong Zheng, Xuewen Yang, Nan Wang, Gavin Tilstone, Elaine Fileman, Min Fu, Bing ZhengAbstract:Plankton is one of the most basic components in the marine ecosystem. The community structure and population change of Plankton are the important ecological information to reflect the environmental situation. As the fundamental parameter of the Plankton community structure, size spectrum is very useful for the evaluation of the marine ecosystem. In this paper, we propose a real-time and adaptive algorithm to calculate the size spectrum of underwater Plankton video, which is captured by the high-resolution and high-speed optical camera. First, this algorithm screens the high-resolution Plankton images to ensure that every Plankton is counted once with the clearest frame. Second, edge detection and morphological methods are performed to get Plankton areas. Furthermore, we perform several simplifications that each particle is handled as ellipses shape to calculate the volume to obtain the size spectrum. Moreover, in order to facilitate the biologists to research Plankton deeply, we record a region of the clear area containing each Plankton to build a Plankton database.
-
Texture and Shape Information Fusion of Convolutional Neural Network for Plankton Image Classification
2018 OCEANS - MTS IEEE Kobe Techno-Oceans (OTO), 2018Co-Authors: Chao Wang, Zhibin Yu, Haiyong Zheng, Bing Zheng, Hua YangAbstract:Plankton is the foundation of marine ecosystem and of great value in environmental protection and fishing industries. As Plankton plays an essential role in maintaining ecosystem balance and economic development, more and more researches are focused on Plankton analysis. Plankton classification is very crucial for Plankton analysis and related ecological study, but it is extremely difficult because of the huge amount and tiny volume of Plankton. In this paper, we propose an effective Plankton feature extraction method followed by an end-to-end hybrid convolutional neural network for Plankton classification. The database we used is from a large scale database named WHOI-Plankton which contains about 3.6 million in situ images labeled into 103 classes. The experimental results show that our method can significantly improve Plankton classification accuracy compared with other commonly used deep neural networks.
-
Deep Pyramidal Residual Networks for Plankton Image Classification
2018 OCEANS - MTS IEEE Kobe Techno-Oceans (OTO), 2018Co-Authors: Angang Du, Chao Wang, Zhibin Yu, Haiyong Zheng, Bing Zheng, Hao ZhangAbstract:In this paper, we explore a new deep learning algorithm called Deep Pyramidal Residual Networks (PyramidNet) to solve Plankton image classification problem. It is well known that Plankton image classification is playing an increasingly important role in the research of Plankton organisms. Nowadays, scientists tend to use image-based technologies to study marine Plankton. However, manual classification of the Plankton images is a time-consuming and labor-intensive work. So it is urgent to find methods that can do automatic classification using few samples labeled by experts and have good performance. In recent years, Deep Convolutional Neural Networks (DCNNs) have shown remarkable performance in image classification tasks. The recently proposed algorithm PyramidNet even performed better than all previous state-of-the-art DCNNs in image classification experiments using some image classification benchmark datasets. So we explore the PyramidNet to solve our Plankton image classification problem and it shows superior generalization ability, gaining higher accuracies. Another meaningful point of our experiment is the improved F1 score compared to other benchmark methods. We use the WHOI-Plankton dataset in our experiment. Although some DCNNs have achieved high accuracies on this dataset, it doesn't mean that the classifiers are really accurate about the minority classes because of the low F1 score which is also another important measurement for image classification. In this paper, we choose the accuracy and F1 score as our evaluating indicators and it ultimately shows that the PyramidNet outperforms the benchmark methods not only on the accuracy but also on the F1 score.
-
automatic Plankton image classification combining multiple view features via multiple kernel learning
BMC Bioinformatics, 2017Co-Authors: Haiyong Zheng, Zhibin Yu, Nan Wang, Ruchen Wang, Zhaorui Gu, Bing ZhengAbstract:Plankton, including phytoPlankton and zooPlankton, are the main source of food for organisms in the ocean and form the base of marine food chain. As the fundamental components of marine ecosystems, Plankton is very sensitive to environment changes, and the study of Plankton abundance and distribution is crucial, in order to understand environment changes and protect marine ecosystems. This study was carried out to develop an extensive applicable Plankton classification system with high accuracy for the increasing number of various imaging devices. Literature shows that most Plankton image classification systems were limited to only one specific imaging device and a relatively narrow taxonomic scope. The real practical system for automatic Plankton classification is even non-existent and this study is partly to fill this gap. Inspired by the analysis of literature and development of technology, we focused on the requirements of practical application and proposed an automatic system for Plankton image classification combining multiple view features via multiple kernel learning (MKL). For one thing, in order to describe the biomorphic characteristics of Plankton more completely and comprehensively, we combined general features with robust features, especially by adding features like Inner-Distance Shape Context for morphological representation. For another, we divided all the features into different types from multiple views and feed them to multiple classifiers instead of only one by combining different kernel matrices computed from different types of features optimally via multiple kernel learning. Moreover, we also applied feature selection method to choose the optimal feature subsets from redundant features for satisfying different datasets from different imaging devices. We implemented our proposed classification system on three different datasets across more than 20 categories from phytoPlankton to zooPlankton. The experimental results validated that our system outperforms state-of-the-art Plankton image classification systems in terms of accuracy and robustness. This study demonstrated automatic Plankton image classification system combining multiple view features using multiple kernel learning. The results indicated that multiple view features combined by NLMKL using three kernel functions (linear, polynomial and Gaussian kernel functions) can describe and use information of features better so that achieve a higher classification accuracy.
Sarah W Davies - One of the best experts on this subject based on the ideXlab platform.
-
Eukaryotic Plankton communities across reef environments in Bocas del Toro Archipelago, Panamá
Coral Reefs, 2020Co-Authors: Andrea M Rodas, Logan K Buie, Hannah E Aichelman, Karl D Castillo, Rachel M Wright, Sarah W DaviesAbstract:Variation in light and temperature can influence the genetic diversity and structure of marine Plankton communities. While open-ocean Plankton communities receive much scientific attention, little is known about how environmental variation affects Plankton communities on tropical coral reefs. Here, we characterize eukaryotic Plankton communities on coral reefs across the Bocas del Toro Archipelago, Panamá. Temperature loggers were deployed, and midday light levels were measured to quantify environmental differences across reefs at four inshore and four offshore sites (Inshore = Punta Donato, Smithsonian Tropical Research Institute (STRI) Point, Cristobal, Punta Laurel and Offshore = Drago Mar, Bastimentos North, Bastimentos South, and Cayo de Agua). Triplicate vertical Plankton tows were collected midday, and high-throughput 18S ribosomal DNA metabarcoding was leveraged to investigate the relationship between eukaryotic Plankton community structure and inshore/offshore reef environments. Plankton communities from STRI Point were additionally characterized in the morning (~ 08:00), midday (~ 12:00), and late-day (~ 16:00) to quantify temporal variation within a single site. We found that inshore reefs experienced higher average seawater temperatures, while offshore sites offered higher light levels, presumably associated with reduced water turbidity on reefs further from shore. These significant environmental differences between inshore and offshore reefs corresponded with overall Plankton community differences. We also found that temporal variation played a structuring role within these Plankton communities, and conclude that time of community sampling is an important consideration for future studies. Follow-up studies focusing on more intensive sampling efforts across space and time, coupled with techniques that can detect more subtle genetic differences between and within communities will more fully capture Plankton dynamics in this region and beyond.
-
eukaryotic Plankton community stability across reef environments in bocas del toro archipelago panama
bioRxiv, 2019Co-Authors: Andrea M Rodas, Logan K Buie, Hannah E Aichelman, Karl D Castillo, Rachel M Wright, Sarah W DaviesAbstract:Variation in light and temperature can influence the genetic diversity and structure of marine Plankton communities. While open ocean Plankton communities receive much scientific attention, little is known about how environmental variation affects tropical coral reef Plankton communities. Here, we characterize eukaryotic Plankton communities on coral reefs across the Bocas del Toro Archipelago in Panama. Temperature loggers were deployed for one year and mid-day light levels were measured to quantify environmental differences across reef zones at four inner and four outer reef sites: Inner: Punta Donato, Smithsonian Tropical Research Institute (STRI) Point, Cristobal, Punta Laurel and Outer: Drago Mar, Bastimentos North, Bastimentos South, and Popa Island. Triplicate vertical Plankton tows were collected mid-day and high-throughput 18S ribosomal DNA metabarcoding was leveraged to investigate the relationship between eukaryotic Plankton community structure and reef zones. Plankton communities from STRI Point were additionally characterized in the morning (~08:00), mid-day (~12:00), and evening (~16:00) to quantify diel variation within a single site. We found that inshore reefs experienced higher average seawater temperatures, while offshore sites offered higher light levels, presumably associated with reduced water turbidity on reefs further from shore. However, these significant reef zone-specific environmental differences did not correlate with overall Plankton community differences or changes in Plankton genetic diversity. Instead, we found that time of day within a site and diel vertical migration played structuring roles within these Plankton communities, and therefore conclude that the time of community sampling is an important consideration for future studies. Overall, Plankton communities in the Bocas del Toro Archipelago appear relatively well mixed across space; however, follow-up studies focusing on more intensive sampling efforts across space and time coupled with techniques that can detect more subtle genetic differences between and within communities will more fully capture Plankton dynamics in this region.
Haiyong Zheng - One of the best experts on this subject based on the ideXlab platform.
-
Vision-Based In Situ Monitoring of Plankton Size Spectra Via a Convolutional Neural Network
IEEE Journal of Oceanic Engineering, 2020Co-Authors: Nan Wang, Haiyong Zheng, Jia Yu, Biao Yang, Bing ZhengAbstract:Plankton size spectra monitoring is crucial for managing and conserving aquatic ecosystems. Thus, we develop an in situ size spectra monitoring system to obtain the size spectra of Plankton and the information of their living status underwater. The system consists of an imaging unit and an information processing unit. The imaging part applies a darkfield illumination to enhance the image contrast. Three lenses with different magnifications are alternated by a motor automatically to capture sizes of Plankton from 3 μm to 3 mm. Moreover, the system can analyze the captured images in real time using the proposed multitask size spectra convolutional neural network, obtaining size spectra and density distribution of Plankton simultaneously. Field test confirms that our system performs well both in imaging and information processing. Furthermore, the system can provide the living behavior of Plankton, thereby helping biologists to study the aquatic ecosystem effectively and precisely.
-
Video-Based Real Time Analysis of Plankton Particle Size Spectrum
IEEE Access, 2019Co-Authors: Jia Yu, Zhibin Yu, Haiyong Zheng, Xuewen Yang, Nan Wang, Gavin Tilstone, Elaine Fileman, Min Fu, Bing ZhengAbstract:Plankton is one of the most basic components in the marine ecosystem. The community structure and population change of Plankton are the important ecological information to reflect the environmental situation. As the fundamental parameter of the Plankton community structure, size spectrum is very useful for the evaluation of the marine ecosystem. In this paper, we propose a real-time and adaptive algorithm to calculate the size spectrum of underwater Plankton video, which is captured by the high-resolution and high-speed optical camera. First, this algorithm screens the high-resolution Plankton images to ensure that every Plankton is counted once with the clearest frame. Second, edge detection and morphological methods are performed to get Plankton areas. Furthermore, we perform several simplifications that each particle is handled as ellipses shape to calculate the volume to obtain the size spectrum. Moreover, in order to facilitate the biologists to research Plankton deeply, we record a region of the clear area containing each Plankton to build a Plankton database.
-
Texture and Shape Information Fusion of Convolutional Neural Network for Plankton Image Classification
2018 OCEANS - MTS IEEE Kobe Techno-Oceans (OTO), 2018Co-Authors: Chao Wang, Zhibin Yu, Haiyong Zheng, Bing Zheng, Hua YangAbstract:Plankton is the foundation of marine ecosystem and of great value in environmental protection and fishing industries. As Plankton plays an essential role in maintaining ecosystem balance and economic development, more and more researches are focused on Plankton analysis. Plankton classification is very crucial for Plankton analysis and related ecological study, but it is extremely difficult because of the huge amount and tiny volume of Plankton. In this paper, we propose an effective Plankton feature extraction method followed by an end-to-end hybrid convolutional neural network for Plankton classification. The database we used is from a large scale database named WHOI-Plankton which contains about 3.6 million in situ images labeled into 103 classes. The experimental results show that our method can significantly improve Plankton classification accuracy compared with other commonly used deep neural networks.
-
Deep Pyramidal Residual Networks for Plankton Image Classification
2018 OCEANS - MTS IEEE Kobe Techno-Oceans (OTO), 2018Co-Authors: Angang Du, Chao Wang, Zhibin Yu, Haiyong Zheng, Bing Zheng, Hao ZhangAbstract:In this paper, we explore a new deep learning algorithm called Deep Pyramidal Residual Networks (PyramidNet) to solve Plankton image classification problem. It is well known that Plankton image classification is playing an increasingly important role in the research of Plankton organisms. Nowadays, scientists tend to use image-based technologies to study marine Plankton. However, manual classification of the Plankton images is a time-consuming and labor-intensive work. So it is urgent to find methods that can do automatic classification using few samples labeled by experts and have good performance. In recent years, Deep Convolutional Neural Networks (DCNNs) have shown remarkable performance in image classification tasks. The recently proposed algorithm PyramidNet even performed better than all previous state-of-the-art DCNNs in image classification experiments using some image classification benchmark datasets. So we explore the PyramidNet to solve our Plankton image classification problem and it shows superior generalization ability, gaining higher accuracies. Another meaningful point of our experiment is the improved F1 score compared to other benchmark methods. We use the WHOI-Plankton dataset in our experiment. Although some DCNNs have achieved high accuracies on this dataset, it doesn't mean that the classifiers are really accurate about the minority classes because of the low F1 score which is also another important measurement for image classification. In this paper, we choose the accuracy and F1 score as our evaluating indicators and it ultimately shows that the PyramidNet outperforms the benchmark methods not only on the accuracy but also on the F1 score.
-
automatic Plankton image classification combining multiple view features via multiple kernel learning
BMC Bioinformatics, 2017Co-Authors: Haiyong Zheng, Zhibin Yu, Nan Wang, Ruchen Wang, Zhaorui Gu, Bing ZhengAbstract:Plankton, including phytoPlankton and zooPlankton, are the main source of food for organisms in the ocean and form the base of marine food chain. As the fundamental components of marine ecosystems, Plankton is very sensitive to environment changes, and the study of Plankton abundance and distribution is crucial, in order to understand environment changes and protect marine ecosystems. This study was carried out to develop an extensive applicable Plankton classification system with high accuracy for the increasing number of various imaging devices. Literature shows that most Plankton image classification systems were limited to only one specific imaging device and a relatively narrow taxonomic scope. The real practical system for automatic Plankton classification is even non-existent and this study is partly to fill this gap. Inspired by the analysis of literature and development of technology, we focused on the requirements of practical application and proposed an automatic system for Plankton image classification combining multiple view features via multiple kernel learning (MKL). For one thing, in order to describe the biomorphic characteristics of Plankton more completely and comprehensively, we combined general features with robust features, especially by adding features like Inner-Distance Shape Context for morphological representation. For another, we divided all the features into different types from multiple views and feed them to multiple classifiers instead of only one by combining different kernel matrices computed from different types of features optimally via multiple kernel learning. Moreover, we also applied feature selection method to choose the optimal feature subsets from redundant features for satisfying different datasets from different imaging devices. We implemented our proposed classification system on three different datasets across more than 20 categories from phytoPlankton to zooPlankton. The experimental results validated that our system outperforms state-of-the-art Plankton image classification systems in terms of accuracy and robustness. This study demonstrated automatic Plankton image classification system combining multiple view features using multiple kernel learning. The results indicated that multiple view features combined by NLMKL using three kernel functions (linear, polynomial and Gaussian kernel functions) can describe and use information of features better so that achieve a higher classification accuracy.
Amanda M Kaltenberg - One of the best experts on this subject based on the ideXlab platform.
-
Biophysical interactions in the Plankton: A cross‐scale review
Limnology and Oceanography, 2012Co-Authors: Jennifer C Prairie, Kelly R Sutherland, Kerry J Nickols, Amanda M KaltenbergAbstract:In Plankton ecology, biological and physical dynamics are coupled, structuring how Plankton interact with their environment and other organisms. This interdisciplinary field has progressed considerably over the recent past, due in large part to advances in technology that have improved our ability to observe Plankton and their fluid environment simultaneously across multiple scales. Recent research has demonstrated that fluid flow interacting with Plankton behavior can drive many Planktonic processes and spatial patterns. Moreover, evidence now suggests that Plankton behavior can significantly affect ocean physics. Biophysical processes relevant to Plankton ecology span a range of scales; for example, microscale turbulence influences Planktonic growth and grazing at millimeter scales, whereas features such as fronts and eddies can shape larger-scale Plankton distributions. Most research in this field focuses on specific processes and thus is limited to a narrow range of spatial scales. However, biophysical interactions are intimately connected across scales, since processes at a given scale can have implications at much larger and smaller scales; thus, a cross-scale perspective on how biological and physical dynamics interact is essential for a comprehensive understanding of the field. Here, we present a review of biophysical interactions in the Plankton across multiple scales, emphasizing new findings over recent decades and highlighting opportunities for cross-scale comparisons. By investigating feedbacks and interactions between processes at different scales, we aim to build cross-scale intuition about biophysical Planktonic processes and provide insights for future directions in the field.
-
biophysical interactions in the Plankton a cross scale review
Limnology and Oceanography, 2012Co-Authors: Jennifer C Prairie, Kelly R Sutherland, Kerry J Nickols, Amanda M KaltenbergAbstract:In Plankton ecology, biological and physical dynamics are coupled, structuring how Plankton interact with their environment and other organisms. This interdisciplinary field has progressed considerably over the recent past, due in large part to advances in technology that have improved our ability to observe Plankton and their fluid environment simultaneously across multiple scales. Recent research has demonstrated that fluid flow interacting with Plankton behavior can drive many Planktonic processes and spatial patterns. Moreover, evidence now suggests that Plankton behavior can significantly affect ocean physics. Biophysical processes relevant to Plankton ecology span a range of scales; for example, microscale turbulence influences Planktonic growth and grazing at millimeter scales, whereas features such as fronts and eddies can shape larger-scale Plankton distributions. Most research in this field focuses on specific processes and thus is limited to a narrow range of spatial scales. However, biophysical interactions are intimately connected across scales, since processes at a given scale can have implications at much larger and smaller scales; thus, a cross-scale perspective on how biological and physical dynamics interact is essential for a comprehensive understanding of the field. Here, we present a review of biophysical interactions in the Plankton across multiple scales, emphasizing new findings over recent decades and highlighting opportunities for cross-scale comparisons. By investigating feedbacks and interactions between processes at different scales, we aim to build cross-scale intuition about biophysical Planktonic processes and provide insights for future directions in the field.
Nan Wang - One of the best experts on this subject based on the ideXlab platform.
-
Vision-Based In Situ Monitoring of Plankton Size Spectra Via a Convolutional Neural Network
IEEE Journal of Oceanic Engineering, 2020Co-Authors: Nan Wang, Haiyong Zheng, Jia Yu, Biao Yang, Bing ZhengAbstract:Plankton size spectra monitoring is crucial for managing and conserving aquatic ecosystems. Thus, we develop an in situ size spectra monitoring system to obtain the size spectra of Plankton and the information of their living status underwater. The system consists of an imaging unit and an information processing unit. The imaging part applies a darkfield illumination to enhance the image contrast. Three lenses with different magnifications are alternated by a motor automatically to capture sizes of Plankton from 3 μm to 3 mm. Moreover, the system can analyze the captured images in real time using the proposed multitask size spectra convolutional neural network, obtaining size spectra and density distribution of Plankton simultaneously. Field test confirms that our system performs well both in imaging and information processing. Furthermore, the system can provide the living behavior of Plankton, thereby helping biologists to study the aquatic ecosystem effectively and precisely.
-
Video-Based Real Time Analysis of Plankton Particle Size Spectrum
IEEE Access, 2019Co-Authors: Jia Yu, Zhibin Yu, Haiyong Zheng, Xuewen Yang, Nan Wang, Gavin Tilstone, Elaine Fileman, Min Fu, Bing ZhengAbstract:Plankton is one of the most basic components in the marine ecosystem. The community structure and population change of Plankton are the important ecological information to reflect the environmental situation. As the fundamental parameter of the Plankton community structure, size spectrum is very useful for the evaluation of the marine ecosystem. In this paper, we propose a real-time and adaptive algorithm to calculate the size spectrum of underwater Plankton video, which is captured by the high-resolution and high-speed optical camera. First, this algorithm screens the high-resolution Plankton images to ensure that every Plankton is counted once with the clearest frame. Second, edge detection and morphological methods are performed to get Plankton areas. Furthermore, we perform several simplifications that each particle is handled as ellipses shape to calculate the volume to obtain the size spectrum. Moreover, in order to facilitate the biologists to research Plankton deeply, we record a region of the clear area containing each Plankton to build a Plankton database.
-
automatic Plankton image classification combining multiple view features via multiple kernel learning
BMC Bioinformatics, 2017Co-Authors: Haiyong Zheng, Zhibin Yu, Nan Wang, Ruchen Wang, Zhaorui Gu, Bing ZhengAbstract:Plankton, including phytoPlankton and zooPlankton, are the main source of food for organisms in the ocean and form the base of marine food chain. As the fundamental components of marine ecosystems, Plankton is very sensitive to environment changes, and the study of Plankton abundance and distribution is crucial, in order to understand environment changes and protect marine ecosystems. This study was carried out to develop an extensive applicable Plankton classification system with high accuracy for the increasing number of various imaging devices. Literature shows that most Plankton image classification systems were limited to only one specific imaging device and a relatively narrow taxonomic scope. The real practical system for automatic Plankton classification is even non-existent and this study is partly to fill this gap. Inspired by the analysis of literature and development of technology, we focused on the requirements of practical application and proposed an automatic system for Plankton image classification combining multiple view features via multiple kernel learning (MKL). For one thing, in order to describe the biomorphic characteristics of Plankton more completely and comprehensively, we combined general features with robust features, especially by adding features like Inner-Distance Shape Context for morphological representation. For another, we divided all the features into different types from multiple views and feed them to multiple classifiers instead of only one by combining different kernel matrices computed from different types of features optimally via multiple kernel learning. Moreover, we also applied feature selection method to choose the optimal feature subsets from redundant features for satisfying different datasets from different imaging devices. We implemented our proposed classification system on three different datasets across more than 20 categories from phytoPlankton to zooPlankton. The experimental results validated that our system outperforms state-of-the-art Plankton image classification systems in terms of accuracy and robustness. This study demonstrated automatic Plankton image classification system combining multiple view features using multiple kernel learning. The results indicated that multiple view features combined by NLMKL using three kernel functions (linear, polynomial and Gaussian kernel functions) can describe and use information of features better so that achieve a higher classification accuracy.
