scholarly journals Video Image Enhancement and Machine Learning Pipeline for Underwater Animal Detection and Classification at Cabled Observatories

Sensors ◽  
2020 ◽  
Vol 20 (3) ◽  
pp. 726 ◽  
Author(s):  
Vanesa Lopez-Vazquez ◽  
Jose Manuel Lopez-Guede ◽  
Simone Marini ◽  
Emanuela Fanelli ◽  
Espen Johnsen ◽  
...  
Keyword(s):  
Image Enhancement ◽  
Barents Sea ◽  
Temporal Dynamics ◽  
Image Annotation ◽  
Sustainable Use ◽  
Area Under The Curve ◽  
Video Image ◽  
Learning Approaches ◽  
Monitoring Networks ◽  
Goods And Services

An understanding of marine ecosystems and their biodiversity is relevant to sustainable use of the goods and services they offer. Since marine areas host complex ecosystems, it is important to develop spatially widespread monitoring networks capable of providing large amounts of multiparametric information, encompassing both biotic and abiotic variables, and describing the ecological dynamics of the observed species. In this context, imaging devices are valuable tools that complement other biological and oceanographic monitoring devices. Nevertheless, large amounts of images or movies cannot all be manually processed, and autonomous routines for recognizing the relevant content, classification, and tagging are urgently needed. In this work, we propose a pipeline for the analysis of visual data that integrates video/image annotation tools for defining, training, and validation of datasets with video/image enhancement and machine and deep learning approaches. Such a pipeline is required to achieve good performance in the recognition and classification tasks of mobile and sessile megafauna, in order to obtain integrated information on spatial distribution and temporal dynamics. A prototype implementation of the analysis pipeline is provided in the context of deep-sea videos taken by one of the fixed cameras at the LoVe Ocean Observatory network of Lofoten Islands (Norway) at 260 m depth, in the Barents Sea, which has shown good classification results on an independent test dataset with an accuracy value of 76.18% and an area under the curve (AUC) value of 87.59%.

scholarly journals GroningenNet: Deep Learning for Low-Magnitude Earthquake Detection on a Multi-Level Sensor Network

Sensors ◽  
2021 ◽  
Vol 21 (23) ◽  
pp. 8080
Author(s):  
Ahmed Shaheen ◽  
Umair bin Waheed ◽  
Michael Fehler ◽  
Lubos Sokol ◽  
Sherif Hanafy
Keyword(s):  
Deep Learning ◽  
Template Matching ◽  
Carbon Capture And Storage ◽  
Microseismic Monitoring ◽  
Seismic Events ◽  
Learning Approaches ◽  
Monitoring Networks ◽  
Level Sensor ◽  
Multi Level ◽  
Low Magnitude

Automatic detection of low-magnitude earthquakes has become an increasingly important research topic in recent years due to a sharp increase in induced seismicity around the globe. The detection of low-magnitude seismic events is essential for microseismic monitoring of hydraulic fracturing, carbon capture and storage, and geothermal operations for hazard detection and mitigation. Moreover, the detection of micro-earthquakes is crucial to understanding the underlying mechanisms of larger earthquakes. Various algorithms, including deep learning methods, have been proposed over the years to detect such low-magnitude events. However, there is still a need for improving the robustness of these methods in discriminating between local sources of noise and weak seismic events. In this study, we propose a convolutional neural network (CNN) to detect seismic events from shallow borehole stations in Groningen, the Netherlands. We train a CNN model to detect low-magnitude earthquakes, harnessing the multi-level sensor configuration of the G-network in Groningen. Each G-network station consists of four geophones at depths of 50, 100, 150, and 200 m. Unlike prior deep learning approaches that use 3-component seismic records only at a single sensor level, we use records from the entire borehole as one training example. This allows us to train the CNN model using moveout patterns of the energy traveling across the borehole sensors to discriminate between events originating in the subsurface and local noise arriving from the surface. We compare the prediction accuracy of our trained CNN model to that of the STA/LTA and template matching algorithms on a two-month continuous record. We demonstrate that the CNN model shows significantly better performance than STA/LTA and template matching in detecting new events missing from the catalog and minimizing false detections. Moreover, we find that using the moveout feature allows us to effectively train our CNN model using only a fraction of the data that would be needed otherwise, saving plenty of manual labor in preparing training labels. The proposed approach can be easily applied to other microseismic monitoring networks with multi-level sensors.

scholarly journals Sustainable use of an extractivist reserve: a spatial-temporal analysis of environmental dynamics

2017 ◽  
Vol 4 (7) ◽  
pp. 195-201
Author(s):  
Joélia Natália Bezerra da Silva ◽  
Janaína Vital de Albuquerque ◽  
Luana de Oliveira Rodrigues
Keyword(s):  
Remote Sensing ◽  
Temporal Dynamics ◽  
Vegetation Indices ◽  
Sustainable Use ◽  
Temporal Analysis ◽  
Conservation Unit ◽  
Climatic Regions ◽  
Cardisoma Guanhumi ◽  
Surrounding Areas ◽  
Spatial Temporal Analysis

Due to its large territory, Brazil has different climatic regions, which determines biome variations and equally diverse ecosystems, of this variety of vegetal landscapes, accompanies the diversity of climates. In this context, results of studies carried out locally, which guide measures, decision-making laws and regulations that reach large scales in the territory, need to be carefully planned, because there is a high risk of disregarding environmental specificities of the studied areas. Therefore, this study aimed to analyze the environmental dynamics resulting from the impacts of the last decades that have affected the habitat of the guaiamum (Cardisoma guanhumi) in the Acaú-Goiana Extractivist Reserve (RESEX) and surrounding areas. The analysis of the spatial-temporal dynamics, in the RESEX and adjacent areas, was made from the vegetation indices (SAVI) through remote sensing. In this way, three images of the RESEX were analyzed, two from the year 2010 and one from 2015, in which the RESEX was already in full legal operation. It is noticeable that there are some areas within the Conservation Unit with small plots of exposed soil, which can demonstrate the occurrence of fires.

scholarly journals A Review on Deep Image Contrast Enhancement

2020 ◽  
Vol 6 (1) ◽  
pp. 4
Author(s):  
Puspad Kumar Sharma ◽  
Nitesh Gupta ◽  
Anurag Shrivastava
Keyword(s):  
Image Processing ◽  
Deep Learning ◽  
Image Enhancement ◽  
Research Work ◽  
Atmospheric Condition ◽  
Input Image ◽  
Learning Approaches ◽  
Sensing Applications ◽  
Image Contrast Enhancement

In image processing applications, one of the main preprocessing phases is image enhancement that is used to produce high quality image or enhanced image than the original input image. These enhanced images can be used in many applications such as remote sensing applications, geo-satellite images, etc. The quality of an image is affected due to several conditions such as by poor illumination, atmospheric condition, wrong lens aperture setting of the camera, noise, etc [2]. So, such degraded/low exposure images are needed to be enhanced by increasing the brightness as well as its contrast and this can be possible by the method of image enhancement. In this research work different image enhancement techniques are discussed and reviewed with their results. The aim of this study is to determine the application of deep learning approaches that have been used for image enhancement. Deep learning is a machine learning approach which is currently revolutionizing a number of disciplines including image processing and computer vision. This paper will attempt to apply deep learning to image filtering, specifically low-light image enhancement. The review given in this paper is quite efficient for future researchers to overcome problems that helps in designing efficient algorithm which enhances quality of the image.

scholarly journals Computational prediction of implantation outcome after embryo transfer

2019 ◽  
Vol 26 (3) ◽  
pp. 1810-1826 ◽  
Author(s):  
Behnaz Raef ◽  
Masoud Maleki ◽  
Reza Ferdousi
Keyword(s):  
Machine Learning ◽  
Feature Selection ◽  
Prediction Model ◽  
Embryo Transfer ◽  
Area Under The Curve ◽  
Computational Prediction ◽  
Support Vector ◽  
Human Menopausal Gonadotropin ◽  
Optimum Number ◽  
Learning Approaches

The aim of this study is to develop a computational prediction model for implantation outcome after an embryo transfer cycle. In this study, information of 500 patients and 1360 transferred embryos, including cleavage and blastocyst stages and fresh or frozen embryos, from April 2016 to February 2018, were collected. The dataset containing 82 attributes and a target label (indicating positive and negative implantation outcomes) was constructed. Six dominant machine learning approaches were examined based on their performance to predict embryo transfer outcomes. Also, feature selection procedures were used to identify effective predictive factors and recruited to determine the optimum number of features based on classifiers performance. The results revealed that random forest was the best classifier (accuracy = 90.40% and area under the curve = 93.74%) with optimum features based on a 10-fold cross-validation test. According to the Support Vector Machine-Feature Selection algorithm, the ideal numbers of features are 78. Follicle stimulating hormone/human menopausal gonadotropin dosage for ovarian stimulation was the most important predictive factor across all examined embryo transfer features. The proposed machine learning-based prediction model could predict embryo transfer outcome and implantation of embryos with high accuracy, before the start of an embryo transfer cycle.

scholarly journals Which PHQ-9 Items Can Effectively Screen for Suicide? Machine Learning Approaches

2021 ◽  
Vol 18 (7) ◽  
pp. 3339
Author(s):  
Sunhae Kim ◽  
Hye-Kyung Lee ◽  
Kounseok Lee
Keyword(s):  
Machine Learning ◽  
Primary Care ◽  
Suicidal Ideation ◽  
Random Forest ◽  
Suicide Ideation ◽  
Area Under The Curve ◽  
Learning Approaches ◽  
K Nearest Neighbors ◽  
Predictive Values ◽  
Linear Discriminant

(1) Background: The Patient Health Questionnaire-9 (PHQ-9) is a tool that screens patients for depression in primary care settings. In this study, we evaluated the efficacy of PHQ-9 in evaluating suicidal ideation (2) Methods: A total of 8760 completed questionnaires collected from college students were analyzed. The PHQ-9 was scored in combination with and evaluated against four categories (PHQ-2, PHQ-8, PHQ-9, and PHQ-10). Suicidal ideations were evaluated using the Mini-International Neuropsychiatric Interview suicidality module. Analyses used suicide ideation as the dependent variable, and machine learning (ML) algorithms, k-nearest neighbors, linear discriminant analysis (LDA), and random forest. (3) Results: Random forest application using the nine items of the PHQ-9 revealed an excellent area under the curve with a value of 0.841, with 94.3% accuracy. The positive and negative predictive values were 84.95% (95% CI = 76.03–91.52) and 95.54% (95% CI = 94.42–96.48), respectively. (4) Conclusion: This study confirmed that ML algorithms using PHQ-9 in the primary care field are reliably accurate in screening individuals with suicidal ideation.

Multi-method approach combining isotopic tracers, anthropogenic contaminants and mapping to retrace socio-environmental trajectories of groundwater-dependent coastal hydrosystems

2020 ◽  
Author(s):  
Melanie Erostate ◽  
Frederic Huneau ◽  
Emilie Garel ◽  
Vanina Pasqualini
Keyword(s):  
Water Resources ◽  
Temporal Dynamics ◽  
Coastal Lagoons ◽  
Management Strategies ◽  
Current Status ◽  
Fresh Groundwater ◽  
Isotopic Tracers ◽  
Goods And Services ◽  
Wide Range ◽  
Multi Method Approach

<p>Coastal lagoons are unique and complex ecosystems. Resulting from both terrestrial (fresh groundwater and surface water) and marine water influences, these ecosystems are often maintained by direct or indirect groundwater supplies and collectively known as groundwater dependent ecosystems (GDEs). Because they provide a wide range of ecosystem goods and services on which a large part of the human population depends, coastal GDEs are considered as complex socio-economic and ecological component worldwide. The increasing human development in coastal areas induces yet a strong pressure on water resources and the expected effects of climate change could exacerbate the pressures on these environments. To limit the risks of degradation and to ensure the sustainability of ecosystem services, the implementation of proper water resources management strategies is essential. This requires a strong knowledge of the environmental and socio-economic trajectories of hydrosystems, and particularly of the behavior and role of groundwater.</p><p>To this end, only the combined use of several tools allows a global understanding of the spatial and temporal dynamics of the system. The correlation between isotopic tracers (<sup>18</sup>O, <sup>2</sup>H, <sup>3</sup>H, <sup>15</sup>N, <sup>11</sup>B), anthropogenic contaminants (organic micro pollutants) and mapping approaches (land-use and vulnerability) allows a historical analyze of the hydrosystem. In addition, to better constraint the hydrosystem hydrological behavior, it is also possible to highlight the current status of water resources, the historical legacy of pollutants and the consequences of past developments and practices, which continue to jeopardize the current quality of the water resource. This methodology was applied to a Mediterranean hydrosystem, in connection with a coastal lagoon (Corsica Island, France). The identification of degradation processes and their chronology could then be traced back in time.</p><p>It appears that the current deterioration is mainly due to a legacy pollution resulting from the development of policies implemented 60 years earlier. In the case of coastal GDEs that are highly anthropized and subject to ever-increasing development, this methodology proposes new key elements for the establishment of relevant management strategies to ensure the future sustainability of water resources.</p>

GENERATIONAL DEMATERIALISATION OF ENERGY IN THE WORLD ECONOMY: EVALUATION APPROACH FOR SUSTAINABLE MANAGEMENT POLICY

2010 ◽  
Vol 12 (03) ◽  
pp. 291-309 ◽  
Author(s):  
JADWIGA ZIOLKOWSKA ◽  
BOZYDAR ZIOLKOWSKI
Keyword(s):  
Environmental Economics ◽  
Sustainable Management ◽  
Sustainable Use ◽  
Management Policy ◽  
New Approach ◽  
Goods And Services ◽  
Evaluation Approach ◽  
World Energy ◽  
The World ◽  
Management Policies

Several methods and ecological indicators are used in environmental economics to analyse the process of sustainable use of natural resources. These approaches are helpful in measuring and assessing the intensity (efficiency) of products' use and their impact on the environment. However, they do not sufficiently reflect the dynamics and improvements in the achieved outcomes as compared to the population (generation) growth. Moreover, they do not allow always analysing product changes on the world level. Referring to this existing gap, we conceptualise a new approach — product generational dematerialisation (PGD) indicator, measuring product efficiency and population changes in relative values, and use it for investigating the dematerialisation for the world energy sector in the last 35 years. The indicator can be used as a new methodical tool to support and evaluate sustainable management policies on the enterprise, regional, national, and international level as well as for different resources, goods, and services.

scholarly journals Impact of COVID-19 on SMEs and the Role of Digitalization

2021 ◽  
pp. 10-17
Author(s):  
Ileana Hamburg
Keyword(s):  
Lifelong Learning ◽  
Formal Education ◽  
Rapid Change ◽  
Learning Approaches ◽  
Goods And Services ◽  
Recovery Processes ◽  
Skill Gaps ◽  
National Economies ◽  
The Impact

Small and medium sized companies (SMEs) should be drivers for national economies, also providing opportunities for socio-economic participation and mobility. But SMEs, more than bigger companies, have experienced difficulties during Covid-19 due to less customer demand for goods and services, limited resources and problems with digitalization. All these facts require rapid change in SME strategies. Based on literature research and on work with SMEs undertaken by the author during European projects, the goal of this communication paper is to illustrate some difficulties experienced by SMEs due to COVID-19 and problems they have with digitalization and skill gaps, as well as measures which could help them. First, the impact of Covid-19 on SMEs and the role of digitalization in their recovery and further developments are presented. Second, certain structures required within SMEs and necessary skills and competences are described in this context. Proposals are then made for reskilling processes within workplace learning and other learning approaches to improve the skills and competences necessary for SME recovery processes. Lifelong learning (LLL) plays an important role in addressing the skills gap between what students have traditionally learned in formal education and the needs of employers and the labor market. LLL should be more connected with other forms of training/learning, digitally supported, interdisciplinary and practically oriented in order to contribute towards achieving the new skills and competences necessary during and after the COVID-19 pandemic and to promote digitalization as a driver to success. The paper also presents examples of the work of the Study Group Lifelong Learning of the IAT, coordinated by the author, and conclusions.

scholarly journals Distinguishing pure histopathological growth patterns of colorectal liver metastases on CT using deep learning and radiomics: a pilot study

2021 ◽  
Vol 38 (5) ◽  
pp. 483-494
Author(s):  
Martijn P. A. Starmans ◽  
Florian E. Buisman ◽  
Michel Renckens ◽  
François E. J. A. Willemssen ◽  
Sebastian R. van der Voort ◽  
...  
Keyword(s):  
Liver Metastases ◽  
Colorectal Liver Metastases ◽  
Cross Validation ◽  
Area Under The Curve ◽  
Growth Patterns ◽  
Learning Approaches ◽  
Intra Class Correlation ◽  
Preoperative Prediction ◽  
Intra Class Correlation Coefficient ◽  
Histopathological Growth Patterns

AbstractHistopathological growth patterns (HGPs) are independent prognosticators for colorectal liver metastases (CRLM). Currently, HGPs are determined postoperatively. In this study, we evaluated radiomics for preoperative prediction of HGPs on computed tomography (CT), and its robustness to segmentation and acquisition variations. Patients with pure HGPs [i.e. 100% desmoplastic (dHGP) or 100% replacement (rHGP)] and a CT-scan who were surgically treated at the Erasmus MC between 2003–2015 were included retrospectively. Each lesion was segmented by three clinicians and a convolutional neural network (CNN). A prediction model was created using 564 radiomics features and a combination of machine learning approaches by training on the clinician’s and testing on the unseen CNN segmentations. The intra-class correlation coefficient (ICC) was used to select features robust to segmentation variations; ComBat was used to harmonize for acquisition variations. Evaluation was performed through a 100 × random-split cross-validation. The study included 93 CRLM in 76 patients (48% dHGP; 52% rHGP). Despite substantial differences between the segmentations of the three clinicians and the CNN, the radiomics model had a mean area under the curve of 0.69. ICC-based feature selection or ComBat yielded no improvement. Concluding, the combination of a CNN for segmentation and radiomics for classification has potential for automatically distinguishing dHGPs from rHGP, and is robust to segmentation and acquisition variations. Pending further optimization, including extension to mixed HGPs, our model may serve as a preoperative addition to postoperative HGP assessment, enabling further exploitation of HGPs as a biomarker.

scholarly journals THE BRAZILIAN ‘ECOLOGICAL-ICMS’: A PES SCHEME BASED ON DISTRIBUTION OF TAX REVENUE

2018 ◽  
Vol 3 (3-4) ◽  
pp. 421-439
Author(s):  
Matheus Linck Bassani
Keyword(s):  
Environmental Protection ◽  
Sustainable Use ◽  
Value Added ◽  
Tax Revenue ◽  
Ecological State ◽  
Payment For Ecosystem Services ◽  
Protection Measures ◽  
Goods And Services ◽  
Brazilian Legislation ◽  
Deductive Method

The scope of this legal brief is to analyze the Brazilian legislation concerning the ‘Ecological-ICMS’, the ‘ecological’ State value-added tax imposed on the circulation of goods and services – ICMS. Using a deductive method, it was identified this tax mechanism operates as a type of ‘payment for ecosystem services’ (PES) scheme in practice, offering the possibility to stimulate environmental protection by distributing revenue from ICMS collected by States to Municipalities that promote conservation of ecosystems and biodiversity. This type of measure was motivated by the need to address challenges in providing economic compensation for Municipalities that undertook environmental protection measures in Brazil, and can serve as a form of positive incentive for the conservation and sustainable use of biodiversity. 

Sign in / Sign up

Export Citation Format

Share Document