scholarly journals A low-cost, long-term underwater camera trap network coupled with deep residual learning image analysis

2021 ◽  
Author(s):  
Stephanie M. Bilodeau ◽  
Austin W. H. Schwartz ◽  
Binfeng Xu ◽  
V. Paúl Pauca ◽  
Miles R. Silman
Keyword(s):  
Machine Learning ◽  
Spatial Scales ◽  
Low Cost ◽  
Camera Trap ◽  
Marine Animal ◽  
List Type ◽  
Machine Learning Classification ◽  
Underwater Camera

AbstractUnderstanding long-term trends in marine ecosystems requires accurate and repeatable counts of fishes and other aquatic organisms on spatial and temporal scales that are difficult or impossible to achieve with diver-based surveys. Long-term, spatially distributed cameras, like those used in terrestrial camera trapping, have not been successfully applied in marine systems due to limitations of the aquatic environment.Here, we develop methodology for a system of low-cost, long-term camera traps (Dispersed Environment Aquatic Cameras), deployable over large spatial scales in remote marine environments. We use machine learning to classify the large volume of images collected by the cameras. We present a case study of these combined techniques’ use by addressing fish movement and feeding behavior related to grazing halos, a well-documented benthic pattern in shallow tropical reefscapes.Cameras proved able to function continuously underwater at deployed depths (up to 7 m, with later versions deployed to 40 m) with no maintenance or monitoring for over five months, and collected time-lapse images during daylight hours for a total of over 100,000 images. Our ResNet-50-based deep learning model achieved 92.5% overall accuracy in sorting images with and without fish, and diver surveys revealed that the camera images accurately represented local fish communities.The cameras and machine learning classification represent the first successful method for broad-scale underwater camera trap deployment, and our case study demonstrates the cameras’ potential for addressing questions of marine animal behavior, distributions, and large-scale spatial patterns.

scholarly journals Low-cost monitoring buoys network tracking biogeochemical changes in lakes and marine environments – a regional case study

2018 ◽  
Vol 90 (10) ◽  
pp. 1631-1646 ◽  
Author(s):  
Alejandro J. Vitale ◽  
Gerardo M.E. Perillo ◽  
Sibila A. Genchi ◽  
Andrés H. Arias ◽  
María Cintia Piccolo
Keyword(s):  
High Frequency ◽  
Low Cost ◽  
Decision Makers ◽  
Shallow Waters ◽  
Global Level ◽  
Temperate Region ◽  
Coastal Marine ◽  
The Cost

AbstractLakes, rivers, estuaries and ocean waters control many important natural functions at the regional-global level. Hence, integrative and frequent long-term water monitoring is required globally. This paper describes the main features and innovations of a low-cost monitoring buoys network (MBN) deployed in a temperate region of Argentina. The MBN was designed to record extended time series at high-frequency, which is of great value for the scientific community, as well as for decision-makers. In addition, two innovative designs belonging to two versions of moored buoys (i.e. shallow waters and coastal marine waters) were presented. It was shown that the cost of either of two versions of the buoy is low, which can be considered as the main advantage.

scholarly journals User Identity Protection in Automatic Emotion Recognition through Disguised Speech

AI ◽  
2021 ◽  
Vol 2 (4) ◽  
pp. 636-649
Author(s):  
Fasih Haider ◽  
Pierre Albert ◽  
Saturnino Luz
Keyword(s):  
Machine Learning ◽  
Transfer Learning ◽  
Assisted Living ◽  
Speech Signal ◽  
Low Cost ◽  
Ambient Assisted Living ◽  
Recognition Task ◽  
Affect Recognition ◽  
Acoustic Features ◽  
Machine Learning Classification

Ambient Assisted Living (AAL) technologies are being developed which could assist elderly people to live healthy and active lives. These technologies have been used to monitor people’s daily exercises, consumption of calories and sleep patterns, and to provide coaching interventions to foster positive behaviour. Speech and audio processing can be used to complement such AAL technologies to inform interventions for healthy ageing by analyzing speech data captured in the user’s home. However, collection of data in home settings presents challenges. One of the most pressing challenges concerns how to manage privacy and data protection. To address this issue, we proposed a low cost system for recording disguised speech signals which can protect user identity by using pitch shifting. The disguised speech so recorded can then be used for training machine learning models for affective behaviour monitoring. Affective behaviour could provide an indicator of the onset of mental health issues such as depression and cognitive impairment, and help develop clinical tools for automatically detecting and monitoring disease progression. In this article, acoustic features extracted from the non-disguised and disguised speech are evaluated in an affect recognition task using six different machine learning classification methods. The results of transfer learning from non-disguised to disguised speech are also demonstrated. We have identified sets of acoustic features which are not affected by the pitch shifting algorithm and also evaluated them in affect recognition. We found that, while the non-disguised speech signal gives the best Unweighted Average Recall (UAR) of 80.01%, the disguised speech signal only causes a slight degradation of performance, reaching 76.29%. The transfer learning from non-disguised to disguised speech results in a reduction of UAR (65.13%). However, feature selection improves the UAR (68.32%). This approach forms part of a large project which includes health and wellbeing monitoring and coaching.

scholarly journals EVALUATION OF INLET MANAGEMENT PRACTICES AT NAVIGATION INLETS IN SOUTHWEST FLORIDA, USA

2011 ◽  
Vol 1 (32) ◽  
pp. 89 ◽  
Author(s):  
Mohamed A Dabees ◽  
Brett D Moore
Keyword(s):  
Management Practices ◽  
Spatial Scales ◽  
Natural Conditions ◽  
Central Florida ◽  
Southwest Florida ◽  
Term Evolution ◽  
Morphologic Response ◽  
Temporal And Spatial

This paper describes numerical modeling of long-term evolution of inlet systems in southwest and central Florida. The paper discusses a general methodology developed following four case studies and application to the case study of Gordon Pass in southwest Florida. The case study of Gordon Pass demonstrates the importance of considering large temporal and spatial scales in evaluating morphologic response to inlet management practices. The results describe the evolution of Gordon Pass from 1930 to present. The analysis begins with natural conditions that existed before dredging or inlet modifications and investigates how inlet evolution can be influenced by navigation improvements and provide tools to evaluate alternatives.

scholarly journals COMPARISON OF MACHINE LEARNING CLASSIFICATION ALGORITHM ON HOTEL REVIEW SENTIMENT ANALYSIS (CASE STUDY: LUMINOR HOTEL PECENONGAN)

2020 ◽  
Vol 16 (1) ◽  
pp. 59-64
Author(s):  
Jaja Miharja ◽  
Jordy Lasmana Putra ◽  
Nur Hadianto
Keyword(s):  
Machine Learning ◽  
Nearest Neighbor ◽  
Classification Algorithm ◽  
K Nearest Neighbor ◽  
Business Decisions ◽  
Machine Learning Classification ◽  
Business People ◽  
Auc Value ◽  
The Right

Analysis of hotel review sentiment is very helpful to be used as a benchmark or reference for making hotel business decisions today. However, all the review information obtained must be processed first by using an algorithm. The purpose of this study is to compare the Classification Algorithm of Machine Learning to obtain information that has a better level of accuracy in the analysis of hotel reviews. The algorithm that will be used is k-NN (k-Nearest Neighbor) and NB (Naive Bayes). After doing the calculation, the following accuracy level is obtained: k-NN of 60,50% with an AUC value of 0.632 and NB of 85,25% with an AUC value of 0.658. These results can be determined by the right algorithm to assist in making accurate decisions by business people in the analysis of hotel reviews using the NB Algorithm.

Machine Learning on Low-Power Low-Cost Platforms: An Application Case Study

2019 ◽  
pp. 191-220
Author(s):  
A. Scionti ◽  
O. Terzo ◽  
C. D'Amico ◽  
B. Montrucchio ◽  
R. Ferrero
Keyword(s):  
Machine Learning ◽  
Low Power ◽  
Low Cost

CASE STUDY: STABILISATION OF A RAPIDLY ERODING POINT USING AN INSITU-FILLED GEOTEXTILE CONTAINER GROYNE FIELD

2017 ◽  
pp. 36
Author(s):  
Bobbie Corbett ◽  
Nicholas Wellwood ◽  
David Shing ◽  
Leslie Angus Jackson
Keyword(s):  
Low Cost ◽  
Low Risk ◽  
Recreational Beach ◽  
High Level

Munna Point is a premiere recreational beach in the Noosa River which has been maintained by regular nourishment for over 20 years. As longevity of each nourishment was less than 6 months, the long-term costs were high and efforts were eventually suspended resulting in loss of the beach. In an effort to reinstate the amenity and provide a more stable beach, a groyne field accompanied by nourishment was proposed. To provide a low-impact, low-risk and low-cost solution, the groynes were designed with a low crest using sand-filled geotextile containers. To achieve the design, containers and scour mattresses were filled in-situ using a dredge, which was an innovative application of a methodology typically adopted for much larger containers. The first 3 groynes have successfully been installed as part of the first stage and 12 months of monitoring subsequently undertaken. The groynes have clearly been effective at extending the longevity of the nourishment and the wider intertidal profile has remained very stable. The beach is now successfully enhancing the amenity of the community and experiencing a high level of usage.

scholarly journals Brain Asymmetry Detection and Machine Learning Classification for Diagnosis of Early Dementia

Sensors ◽  
2021 ◽  
Vol 21 (3) ◽  
pp. 778
Author(s):  
Nitsa J. Herzog ◽  
George D. Magoulas
Keyword(s):  
Machine Learning ◽  
Alzheimer’S Disease ◽  
Alzheimer's Disease ◽  
Structural Changes ◽  
Low Cost ◽  
Machine Learning Algorithms ◽  
Supervised Machine Learning ◽  
Progressive Dementia ◽  
Machine Learning Classification

Early identification of degenerative processes in the human brain is considered essential for providing proper care and treatment. This may involve detecting structural and functional cerebral changes such as changes in the degree of asymmetry between the left and right hemispheres. Changes can be detected by computational algorithms and used for the early diagnosis of dementia and its stages (amnestic early mild cognitive impairment (EMCI), Alzheimer’s Disease (AD)), and can help to monitor the progress of the disease. In this vein, the paper proposes a data processing pipeline that can be implemented on commodity hardware. It uses features of brain asymmetries, extracted from MRI of the Alzheimer’s Disease Neuroimaging Initiative (ADNI) database, for the analysis of structural changes, and machine learning classification of the pathology. The experiments provide promising results, distinguishing between subjects with normal cognition (NC) and patients with early or progressive dementia. Supervised machine learning algorithms and convolutional neural networks tested are reaching an accuracy of 92.5% and 75.0% for NC vs. EMCI, and 93.0% and 90.5% for NC vs. AD, respectively. The proposed pipeline offers a promising low-cost alternative for the classification of dementia and can be potentially useful to other brain degenerative disorders that are accompanied by changes in the brain asymmetries.

scholarly journals The Ecology of Sustainable Implementation

2014 ◽  
Vol 222 (1) ◽  
pp. 58-66 ◽  
Author(s):  
Tormod Rimehaug
Keyword(s):  
Low Cost ◽  
Service Evaluation ◽  
Training Methods ◽  
Prevention Services ◽  
Manualized Intervention ◽  
Sustainable Implementation ◽  
Implementation Effort ◽  
Evaluation Staff

The primary aim of this paper is to illustrate the strategic and ecological nature of implementation. The ultimate aim of implementation is not dissemination but sustainability beyond the implementation effort. A case study is utilized to illustrate these broad and long-term perspectives of sustainable implementation based on qualitative analyses of a 10-year implementation effort. The purveyors aimed to develop selective community prevention services for children in families burdened by parental psychiatric or addictive problems. Services were gradually disseminated to 23 sites serving 40 municipalities by 2013. Up to 2013, only one site terminated services after initial implementation. Although many sites suspended services for shorter periods, services are still offered at 22 sites. This case analysis is based on project reports, user evaluations, practitioner interviews, and service statistics. The paper focuses on the analyses and strategies utilized to cope with quality decay and setbacks as well as progress and success in disseminating and sustaining the services and their quality. Low-cost multilevel strategies to implement services at the community level were organized by a prevention unit in child psychiatry, supervised by a university department (purveyors). The purveyors were also involved in national and international collaboration and development. Multilevel strategies included manualized intervention, in-practice training methods, organizational responsibility, media strategies, service evaluation, staff motivation maintenance, quality assurance, and proposals for new law regulations. These case history aspects will be discussed in relation to the implementation literature, focusing on possible applicability across settings.

Sign in / Sign up

Export Citation Format

Share Document