scholarly journals Deep learning identification for citizen science surveillance of tiger mosquitoes

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Balint Armin Pataki ◽  
Joan Garriga ◽  
Roger Eritja ◽  
John R. B. Palmer ◽  
Frederic Bartumeus ◽  
...  
Keyword(s):  
Deep Learning ◽  
Data Collection ◽  
Citizen Science ◽  
Large Scale ◽  
Mosquito Species ◽  
Characteristic Curve ◽  
Science System ◽  
Public Health Agencies ◽  
Manual Inspection ◽  
Long Run

AbstractGlobal monitoring of disease vectors is undoubtedly becoming an urgent need as the human population rises and becomes increasingly mobile, international commercial exchanges increase, and climate change expands the habitats of many vector species. Traditional surveillance of mosquitoes, vectors of many diseases, relies on catches, which requires regular manual inspection and reporting, and dedicated personnel, making large-scale monitoring difficult and expensive. New approaches are solving the problem of scalability by relying on smartphones and the Internet to enable novel community-based and digital observatories, where people can upload pictures of mosquitoes whenever they encounter them. An example is the Mosquito Alert citizen science system, which includes a dedicated mobile phone app through which geotagged images are collected. This system provides a viable option for monitoring the spread of various mosquito species across the globe, although it is partly limited by the quality of the citizen scientists’ photos. To make the system useful for public health agencies, and to give feedback to the volunteering citizens, the submitted images are inspected and labeled by entomology experts. Although citizen-based data collection can greatly broaden disease-vector monitoring scales, manual inspection of each image is not an easily scalable option in the long run, and the system could be improved through automation. Based on Mosquito Alert’s curated database of expert-validated mosquito photos, we trained a deep learning model to find tiger mosquitoes (Aedes albopictus), a species that is responsible for spreading chikungunya, dengue, and Zika among other diseases. The highly accurate 0.96 area under the receiver operating characteristic curve score promises not only a helpful pre-selector for the expert validation process but also an automated classifier giving quick feedback to the app participants, which may help to keep them motivated. In the paper, we also explored the possibilities of using the model to improve future data collection quality as a feedback loop.

scholarly journals Validating the validation: reanalyzing a large-scale comparison of deep learning and machine learning models for bioactivity prediction

2020 ◽  
Vol 34 (7) ◽  
pp. 717-730 ◽  
Author(s):  
Matthew C. Robinson ◽  
Robert C. Glen ◽  
Alpha A. Lee
Keyword(s):  
Machine Learning ◽  
Deep Learning ◽  
Numerical Experiments ◽  
Large Scale ◽  
Operating Characteristic ◽  
Characteristic Curve ◽  
Learning Models ◽  
Bioactivity Prediction ◽  
Operating Characteristic Curve ◽  
Machine Learning Models

Abstract Machine learning methods may have the potential to significantly accelerate drug discovery. However, the increasing rate of new methodological approaches being published in the literature raises the fundamental question of how models should be benchmarked and validated. We reanalyze the data generated by a recently published large-scale comparison of machine learning models for bioactivity prediction and arrive at a somewhat different conclusion. We show that the performance of support vector machines is competitive with that of deep learning methods. Additionally, using a series of numerical experiments, we question the relevance of area under the receiver operating characteristic curve as a metric in virtual screening. We further suggest that area under the precision–recall curve should be used in conjunction with the receiver operating characteristic curve. Our numerical experiments also highlight challenges in estimating the uncertainty in model performance via scaffold-split nested cross validation.

Design of Microplastics Citizen Science Kit

2020 ◽  
Author(s):  
Rachael Hughson-Gill
Keyword(s):  
Data Collection ◽  
Citizen Science ◽  
Large Scale ◽  
Positive Impact ◽  
Research Process ◽  
Freshwater Ecosystems ◽  
Freshwater Systems ◽  
The Public ◽  
Plastic Bags ◽  
The Impact

<p>Microplastics are an ever-increasing problem. Every river that was tested in a recent study found the presence of microplastics, with 80% of all plastic in the ocean coming from upstream. Despite this, there is little understanding into the abundance of plastic, its characteristics and the full impact that is it having on marine, freshwater ecosystems and wider ecological systems.</p><p> </p><p>Current fresh water monitoring does not consider the fluid dynamics of rivers, is difficult to use and is inaccessible to the wider public. My project will focus on creating a product that allows for the large-scale data collection of microplastic through citizen science. Allowing groups of people to analyse their local natural environment for the presence and abundance of microplastics within the water. This method of data collection could provide information on a scale that is not possible with traditional methods and would allow for the comparison between freshwater systems. This comparison is fundamental to begin to fill the knowledge gaps around the understanding of microplastics.</p><p> </p><p>Inaccessibility of monitoring to the public is not just through tools but also through the current communication of data with research rarely breaking into the public domain. Citizen science offers not just an improvement in understanding but also offers an opportunity for engagement with the public body. Increasing awareness of the impact of habits round plastic through the sharing of monitoring data can generate the much-needed change on both an individual and policy level to address the problem from the source. This method of change through public opinion can be seen to have an effect on freshwater systems through microbeads ban, plastic bags, plastic straws and industrial pollution regulation.</p><p> </p><p>Through the creation of this product a multidisciplinary approach that blends engineering and design practices is implemented. The wholistic approach to creation is something that is fundamental in the success of tools and therefore the success of the research that is implemented through them. A tool such as this whose function is within the public engagement of its use - increased awareness, as well as the outcome of its use - microplastics data, is required to have an engaging user experience as well as data integrity implemented through engineering design.</p><p> </p><p>This project offers an opportunity to show the importance of the design process within research tools to aid the research process and the positive impact that can come from it.</p>

scholarly journals Estimating disease vector population size from citizen science data

2021 ◽  
Vol 18 (184) ◽  
Author(s):  
Tam Tran ◽  
W. Tanner Porter ◽  
Daniel J. Salkeld ◽  
Melissa A. Prusinski ◽  
Shane T. Jensen ◽  
...  
Keyword(s):  
Data Collection ◽  
Citizen Science ◽  
Large Scale ◽  
Species Abundance ◽  
Natural World ◽  
Tick Population ◽  
Science Data ◽  
Tick Abundance ◽  
Vector Population ◽  
Public Datasets

Citizen science projects have the potential to address hypotheses requiring extremely large datasets that cannot be collected with the financial and labour constraints of most scientific projects. Data collection by the general public could expand the scope of scientific enquiry if these data accurately capture the system under study. However, data collection inconsistencies by the untrained public may result in biased datasets that do not accurately represent the natural world. In this paper, we harness the availability of scientific and public datasets of the Lyme disease tick vector to identify and account for biases in citizen science tick collections. Estimates of tick abundance from the citizen science dataset correspond moderately with estimates from direct surveillance but exhibit consistent biases. These biases can be mitigated by including factors that may impact collector participation or effort in statistical models, which, in turn, result in more accurate estimates of tick population sizes. Accounting for collection biases within large-scale, public participation datasets could update species abundance maps and facilitate using the wealth of citizen science data to answer scientific questions at scales that are not feasible with traditional datasets.

scholarly journals Deep learning is combined with massive-scale citizen science to improve large-scale image classification

2018 ◽  
Vol 36 (9) ◽  
pp. 820-828 ◽  
Author(s):  
Devin P Sullivan ◽  
Casper F Winsnes ◽  
Lovisa Åkesson ◽  
Martin Hjelmare ◽  
Mikaela Wiking ◽  
...  
Keyword(s):  
Deep Learning ◽  
Image Classification ◽  
Citizen Science ◽  
Large Scale ◽  
Massive Scale

scholarly journals Deep learning approaches for challenging species and gender identification of mosquito vectors

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Veerayuth Kittichai ◽  
Theerakamol Pengsakul ◽  
Kemmapon Chumchuen ◽  
Yudthana Samung ◽  
Patchara Sriwichai ◽  
...  
Keyword(s):  
Deep Learning ◽  
High Performance ◽  
Mosquito Species ◽  
Characteristic Curve ◽  
Confusion Matrix ◽  
Morphological Identification ◽  
Learning Approaches ◽  
Mosquito Vectors ◽  
Detection Rates ◽  
Proposed Model

AbstractMicroscopic observation of mosquito species, which is the basis of morphological identification, is a time-consuming and challenging process, particularly owing to the different skills and experience of public health personnel. We present deep learning models based on the well-known you-only-look-once (YOLO) algorithm. This model can be used to simultaneously classify and localize the images to identify the species of the gender of field-caught mosquitoes. The results indicated that the concatenated two YOLO v3 model exhibited the optimal performance in identifying the mosquitoes, as the mosquitoes were relatively small objects compared with the large proportional environment image. The robustness testing of the proposed model yielded a mean average precision and sensitivity of 99% and 92.4%, respectively. The model exhibited high performance in terms of the specificity and accuracy, with an extremely low rate of misclassification. The area under the receiver operating characteristic curve (AUC) was 0.958 ± 0.011, which further demonstrated the model accuracy. Thirteen classes were detected with an accuracy of 100% based on a confusion matrix. Nevertheless, the relatively low detection rates for the two species were likely a result of the limited number of wild-caught biological samples available. The proposed model can help establish the population densities of mosquito vectors in remote areas to predict disease outbreaks in advance.

Combining citizen science and deep learning for large-scale estimation of outdoor nitrogen dioxide concentrations

2020 ◽  
pp. 110389
Author(s):  
Scott Weichenthal ◽  
Evi Dons ◽  
Kris Y. Hong ◽  
Pedro O. Pinheiro ◽  
Filip J.R. Meysman
Keyword(s):  
Deep Learning ◽  
Nitrogen Dioxide ◽  
Citizen Science ◽  
Large Scale ◽  
Scale Estimation

scholarly journals Combining citizen science and deep learning to amplify expertise in neuroimaging

2018 ◽  
Author(s):  
Anisha Keshavan ◽  
Jason D. Yeatman ◽  
Ariel Rokem
Keyword(s):  
Decision Making ◽  
Quality Control ◽  
Big Data ◽  
Deep Learning ◽  
Citizen Science ◽  
Large Scale ◽  
Learning Algorithm ◽  
Area Under The Curve ◽  
Magnetic Resonance Images ◽  
Complex Datasets

AbstractResearch in many fields has become increasingly reliant on large and complex datasets. “Big Data” holds untold promise to rapidly advance science by tackling new questions that cannot be answered with smaller datasets. While powerful, research with Big Data poses unique challenges, as many standard lab protocols rely on experts examining each one of the samples. This is not feasible for large-scale datasets because manual approaches are time-consuming and hence difficult to scale. Meanwhile, automated approaches lack the accuracy of examination by highly trained scientists and this may introduce major errors, sources of noise, and unforeseen biases into these large and complex datasets. Our proposed solution is to 1) start with a small, expertly labelled dataset, 2) amplify labels through web-based tools that engage citizen scientists, and 3) train machine learning on amplified labels to emulate expert decision making. As a proof of concept, we developed a system to quality control a large dataset of three-dimensional magnetic resonance images (MRI) of human brains. An initial dataset of 200 brain images labeled by experts were amplified by citizen scientists to label 722 brains, with over 80,000 ratings done through a simple web interface. A deep learning algorithm was then trained to predict data quality, based on a combination of the citizen scientist labels that accounts for differences in the quality of classification by different citizen scientists. In an ROC analysis (on left out test data), the deep learning network performed as well as a state-of-the-art, specialized algorithm (MRIQC) for quality control of T1-weighted images, each with an area under the curve of 0.99. Finally, as a specific practical application of the method, we explore how brain image quality relates to the replicability of a well established relationship between brain volume and age over development. Combining citizen science and deep learning can generalize and scale expert decision making; this is particularly important in emerging disciplines where specialized, automated tools do not already exist.

scholarly journals Ciencia ciudadana como emprendimiento de la ciencia abierta: el riesgo del espectáculo de la producción y el acceso al dato. Hacia otra ciencia ciudadana | Ciência cidadã como empreendimento de ciência aberta: o risco da espetacularização da produção e o acesso ao dado. Para uma outra ciência cidadã | Citizen Science as an open science enterprise: the risk of a spectacle of production and the access to data. Towards another citizen science

2017 ◽  
Vol 13 (1) ◽  
Author(s):  
Julieta Piña Romero
Keyword(s):  
Data Collection ◽  
Citizen Science ◽  
Open Science ◽  
Democratic Values ◽  
Science System ◽  
Access To Data ◽  
The Way

RESUMEN En este trabajo se analiza la forma en que la ciencia ciudadana que hoy conocemos configura sus principales aspiraciones y dinámicas como parte de un sistema de ciencia abierta centrado en la producción y el acceso al dato. Como tal, se advierte del riesgo que existe de que la ciencia ciudadana derive en una práctica de sofisticación de la recolección y clasificación de datos y, con ello, que los valores democráticos que subyacen a la concepción de apertura científica se tornen más que genuinos, espectaculares. Al final del trabajo y como alternativa, se sugiere a través de Alan Irwin (1993) revisar una concepción de ciencia ciudadana ligada a la idea de crítica, demanda y confrontación ciudadana.Palabras clave: Ciencia Ciudadana; Ciencia Abierta; Democratización de la Ciencia; Alan Irwin.RESUMO Este artigo analisa a forma como a ciência cidadã tal como a conhecemos hoje configura suas principais aspirações e dinâmicas como parte de um sistema de ciência aberta centrado na produção do e acesso ao dado. Assim, adverte-se do risco de a ciência cidadã derivar para uma prática de sofisticação da coleta e classificação de dados e que, assim, os valores democráticos que subjazem o conceito de abertura científica se tornem, mais que do que genuínos, espetaculares. Propõe-se ao final, como alternativa, revisar com Alan Irwin (1993) um concepção de ciência cidadã ligada à idéia de crítica, demanda e confrontação cidadã.Palavras-chave: Ciência Cidadã; Ciência Aberta; Democratização da Ciência; Alan Irwin.ABSTRACTThis article analyses the way citizen science as we know it today configures its main aspirations and dynamics as part of an open science system centered on production of and access to data. Seen in this light, we call attention to the risk of citizen science being diverted to a practice of sophisticating data collection and classification and, thus, that the democratic values which underlie the idea of open science become, more than genuine, spectacular. As an alternative, the suggestion proposed – with Alan Irwin (1993) – is to revise the understanding of citizen science as linked to the idea of citizen critique, demand, and confrontation.Keywords: Citizen Science; Open Science; Democratization of Science; Alan Irwin.

scholarly journals Análise do atual cenário da pesquisa científica sobre a ciência cidadã no campo da ciência da informação

2020 ◽  
pp. 26-32
Author(s):  
Erika Rayanne Silva de Carvalho ◽  
Fernando César Lima Leite
Keyword(s):  
Data Collection ◽  
Citizen Science ◽  
Citizen Participation ◽  
Large Scale ◽  
Information Science ◽  
Library And Information Science ◽  
Scientific Training ◽  
Large Scale Data ◽  
Science Projects ◽  
Disciplinary Diversity

This article aimed to analyze studies that constitute the current research scenario on Citizen Science in the field of the Information Science, as presented in the scientific literature. This is a bibliographic research in which the Library and Information Science Abstracts (LISA) database was used for data collection. After careful evaluation, eleven papers were selected to compose the study. The results achieved point out that there is disciplinary diversity in Citizen Science projects, there is an opportune context for libraries to conduct scientific training practices, several factors influence the participation of citizens in scientific projects, the domain of citizens over digital resources is highly relevant in Citizen Science projects and the citizen participation in scientific projects seems to turn around large-scale data collection, which does not necessarily reflect the collaborative potential of these citizens.

scholarly journals Next-generation ultrasonic recorders facilitate effective bat activity and distribution monitoring by citizen scientists

2021 ◽  
Author(s):  
Piia Lundberg ◽  
Melissa Meierhofer ◽  
Ville Vasko ◽  
Miina Suutari ◽  
Ann Ojala ◽  
...  
Keyword(s):  
High School Students ◽  
Data Collection ◽  
Citizen Science ◽  
Scientific Literacy ◽  
Large Scale ◽  
Limiting Factor ◽  
Quality Of Data ◽  
Ecological Data ◽  
Bat Activity ◽  
Science Projects

Time and budgetary resources are often a limiting factor in the collection of large-scale ecological data. If data collected by citizen scientists were comparable to data collected by researchers, it would allow for more efficient data collection over a broad geographic area. Here, we compare the quality of data on bat activity collected by citizens (high school students and teachers) and researchers. Both researchers and citizen scientists used the same comprehensive instructions when choosing study sites. We found no differences in total bat activity minutes recorded by citizens and researchers. Instead, citizen scientists collected data from a wider variety of habitats than researchers. Involvement of citizens also increased the geographical coverage of data collection, resulting in the northernmost documentation of the Nathusius pipistrelle so far in Finland. Therefore, bat research can benefit from the use of citizen science when participants are given precise instructions and calibrated data collection equipment. Citizen science projects also have other far-reaching benefits, increasing, for example, the scientific literacy and interest in natural sciences of citizens. Involving citizens in science projects also has the potential to enhance their willingness to conserve nature.

Sign in / Sign up

Export Citation Format

Share Document