scholarly journals Using autonomous video to estimate the bottom-contact area of longline trap gear and presence–absence of sensitive benthic habitat

2018 ◽  
Vol 75 (5) ◽  
pp. 797-812 ◽  
Author(s):  
Beau Doherty ◽  
Samuel D.N. Johnson ◽  
Sean P. Cox
Keyword(s):  
Contact Area ◽  
Large Scale ◽  
Marine Protected Area ◽  
Cold Water ◽  
Sensor Data ◽  
Benthic Habitat ◽  
Commercial Fishing ◽  
Depth Sensor ◽  
Quality Of Data ◽  
Bottom Contact

Bottom longline hook and trap fishing gear can potentially damage sensitive benthic areas (SBAs) in the ocean; however, the large-scale risks to these habitats are poorly understood because of the difficulties in mapping SBAs and in measuring the bottom-contact area of longline gear. In this paper, we describe a collaborative academic–industry–government approach to obtaining direct presence–absence data for SBAs and to measuring gear interactions with seafloor habitats via a novel deepwater trap camera and motion-sensing systems on commercial longline traps for sablefish (Anoplopoma fimbria) within SGaan Kinghlas – Bowie Seamount Marine Protected Area. We obtained direct presence–absence observations of cold-water corals (Alcyonacea, Antipatharia, Pennatulacea, Stylasteridae) and sponges (Hexactinellida, Demospongiae) at 92 locations over three commercial fishing trips. Video, accelerometer, and depth sensor data were used to estimate a mean bottom footprint of 53 m2 for a standard sablefish trap, which translates to 3200 m2 (95% CI = 2400–3900 m2) for a 60-trap commercial sablefish longline set. Our successful collaboration demonstrates how research partnerships with commercial fisheries have potential for massive improvements in the quantity and quality of data needed for conducting SBA risk assessments over large spatial and temporal scales.

Measuring patient engagement among cancer patients in eHealth and mHealth interventions on symptom management: an integrated review (Preprint)

2020 ◽  
Author(s):  
Juqing Zhao ◽  
Pei Chen ◽  
Guangming Wan
Keyword(s):  
Cancer Patients ◽  
Patient Engagement ◽  
Symptom Management ◽  
Subjective Experience ◽  
Participation Rate ◽  
Sensor Data ◽  
Quality Of Data ◽  
Mhealth Intervention

BACKGROUND There has been an increase number of eHealth and mHealth interventions aimed to support symptoms among cancer survivors. However, patient engagement has not been guaranteed and standardized in these interventions. OBJECTIVE The objective of this review was to address how patient engagement has been defined and measured in eHealth and mHealth interventions designed to improve symptoms and quality of life for cancer patients. METHODS Searches were performed in MEDLINE, PsychINFO, Web of Science, and Google Scholar to identify eHealth and mHealth interventions designed specifically to improve symptom management for cancer patients. Definition and measurement of engagement and engagement related outcomes of each intervention were synthesized. This integrated review was conducted using Critical Interpretive Synthesis to ensure the quality of data synthesis. RESULTS A total of 792 intervention studies were identified through the searches; 10 research papers met the inclusion criteria. Most of them (6/10) were randomized trial, 2 were one group trail, 1 was qualitative design, and 1 paper used mixed method. Majority of identified papers defined patient engagement as the usage of an eHealth and mHealth intervention by using different variables (e.g., usage time, log in times, participation rate). Engagement has also been described as subjective experience about the interaction with the intervention. The measurement of engagement is in accordance with the definition of engagement and can be categorized as objective and subjective measures. Among identified papers, 5 used system usage data, 2 used self-reported questionnaire, 1 used sensor data and 3 used qualitative method. Almost all studies reported engagement at a moment to moment level, but there is a lack of measurement of engagement for the long term. CONCLUSIONS There have been calls to develop standard definition and measurement of patient engagement in eHealth and mHealth interventions. Besides, it is important to provide cancer patients with more tailored and engaging eHealth and mHealth interventions for long term engagement.

scholarly journals Multi-task learning based Encoder-Decoder: A comprehensive detection and diagnosis system for multi-sensor data

2021 ◽  
Vol 13 (5) ◽  
pp. 168781402110131
Author(s):  
Junfeng Wu ◽  
Li Yao ◽  
Bin Liu ◽  
Zheyuan Ding ◽  
Lei Zhang
Keyword(s):  
Anomaly Detection ◽  
Event Detection ◽  
Large Scale ◽  
Multivariate Time Series ◽  
Sensor Data ◽  
Unified Framework ◽  
Diagnosis System ◽  
Learning Framework ◽  
Task Learning ◽  
Detection And Diagnosis

As more and more sensor data have been collected, automated detection, and diagnosis systems are urgently needed to lessen the increasing monitoring burden and reduce the risk of system faults. A plethora of researches have been done on anomaly detection, event detection, anomaly diagnosis respectively. However, none of current approaches can explore all these respects in one unified framework. In this work, a Multi-Task Learning based Encoder-Decoder (MTLED) which can simultaneously detect anomalies, diagnose anomalies, and detect events is proposed. In MTLED, feature matrix is introduced so that features are extracted for each time point and point-wise anomaly detection can be realized in an end-to-end way. Anomaly diagnosis and event detection share the same feature matrix with anomaly detection in the multi-task learning framework and also provide important information for system monitoring. To train such a comprehensive detection and diagnosis system, a large-scale multivariate time series dataset which contains anomalies of multiple types is generated with simulation tools. Extensive experiments on the synthetic dataset verify the effectiveness of MTLED and its multi-task learning framework, and the evaluation on a real-world dataset demonstrates that MTLED can be used in other application scenarios through transfer learning.

scholarly journals BLAINDER—A Blender AI Add-On for Generation of Semantically Labeled Depth-Sensing Data

Sensors ◽  
2021 ◽  
Vol 21 (6) ◽  
pp. 2144
Author(s):  
Stefan Reitmann ◽  
Lorenzo Neumann ◽  
Bernhard Jung
Keyword(s):  
Point Clouds ◽  
Training Data ◽  
Sensor Data ◽  
Generation Process ◽  
Data Generation ◽  
Depth Sensor ◽  
Depth Sensing ◽  
Depth Sensors ◽  
3D Point Clouds ◽  
Wide Range

Common Machine-Learning (ML) approaches for scene classification require a large amount of training data. However, for classification of depth sensor data, in contrast to image data, relatively few databases are publicly available and manual generation of semantically labeled 3D point clouds is an even more time-consuming task. To simplify the training data generation process for a wide range of domains, we have developed the BLAINDER add-on package for the open-source 3D modeling software Blender, which enables a largely automated generation of semantically annotated point-cloud data in virtual 3D environments. In this paper, we focus on classical depth-sensing techniques Light Detection and Ranging (LiDAR) and Sound Navigation and Ranging (Sonar). Within the BLAINDER add-on, different depth sensors can be loaded from presets, customized sensors can be implemented and different environmental conditions (e.g., influence of rain, dust) can be simulated. The semantically labeled data can be exported to various 2D and 3D formats and are thus optimized for different ML applications and visualizations. In addition, semantically labeled images can be exported using the rendering functionalities of Blender.

Challenges to quantifying glass eel abundance from large and dynamic estuaries

2017 ◽  
Vol 75 (2) ◽  
pp. 727-737 ◽  
Author(s):  
Sarah Walmsley ◽  
Julie Bremner ◽  
Alan Walker ◽  
Jon Barry ◽  
David Maxwell
Keyword(s):  
Large Scale ◽  
Anguilla Anguilla ◽  
Commercial Fishing ◽  
European Eel ◽  
Estuarine System ◽  
Glass Eel ◽  
The North ◽  
Adequate Sampling ◽  
South Shore ◽  
Glass Eels

Abstract European eel Anguilla anguilla recruitment into the rivers of the northeastern Atlantic has declined substantially since the 1980s. Monitoring of recruiting juveniles, or glass eels, is usually undertaken in small estuaries and rivers. Sampling of large-scale estuaries is rare, due to the size of the sampling area and the resources needed to provide adequate sampling levels. Here we describe surveys for glass eels in the UK’s largest estuarine system, the Severn Estuary/Bristol Channel. We sampled across a 20 km-wide stretch of the estuary in 2012 and 2013, using a small-meshed net deployed from a commercial fishing trawler, and the surveys yielded over 2500 glass eels. Eels were more abundant in the surface layer (0–1.4 m depth) than at depth (down to 8.4 m depth), were more abundant close to the south shore than along the north shore or middle of the estuary, and were more abundant in lower salinity water. Numbers were higher in the second year than in the first and eels were more abundant in February than April. The difficulties and logistics of sampling in such a large estuary are discussed, along with the level of resources required to provide robust estimates of glass eel abundance.

Machine-Learning for the Prediction of Lost Circulation Events - Time Series Analysis and Model Evaluation

2021 ◽  
Author(s):  
Arturo Magana-Mora ◽  
Mohammad AlJubran ◽  
Jothibasu Ramasamy ◽  
Mohammed AlBassam ◽  
Chinthaka Gooneratne ◽  
...  
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Real Time ◽  
Large Scale ◽  
Model Comparison ◽  
Drilling Fluid ◽  
Sensor Data ◽  
False Alarms ◽  
Suitable Model ◽  
Lost Circulation

Abstract Objective/Scope. Lost circulation events (LCEs) are among the top causes for drilling nonproductive time (NPT). The presence of natural fractures and vugular formations causes loss of drilling fluid circulation. Drilling depleted zones with incorrect mud weights can also lead to drilling induced losses. LCEs can also develop into additional drilling hazards, such as stuck pipe incidents, kicks, and blowouts. An LCE is traditionally diagnosed only when there is a reduction in mud volume in mud pits in the case of moderate losses or reduction of mud column in the annulus in total losses. Using machine learning (ML) for predicting the presence of a loss zone and the estimation of fracture parameters ahead is very beneficial as it can immediately alert the drilling crew in order for them to take the required actions to mitigate or cure LCEs. Methods, Procedures, Process. Although different computational methods have been proposed for the prediction of LCEs, there is a need to further improve the models and reduce the number of false alarms. Robust and generalizable ML models require a sufficiently large amount of data that captures the different parameters and scenarios representing an LCE. For this, we derived a framework that automatically searches through historical data, locates LCEs, and extracts the surface drilling and rheology parameters surrounding such events. Results, Observations, and Conclusions. We derived different ML models utilizing various algorithms and evaluated them using the data-split technique at the level of wells to find the most suitable model for the prediction of an LCE. From the model comparison, random forest classifier achieved the best results and successfully predicted LCEs before they occurred. The developed LCE model is designed to be implemented in the real-time drilling portal as an aid to the drilling engineers and the rig crew to minimize or avoid NPT. Novel/Additive Information. The main contribution of this study is the analysis of real-time surface drilling parameters and sensor data to predict an LCE from a statistically representative number of wells. The large-scale analysis of several wells that appropriately describe the different conditions before an LCE is critical for avoiding model undertraining or lack of model generalization. Finally, we formulated the prediction of LCEs as a time-series problem and considered parameter trends to accurately determine the early signs of LCEs.

scholarly journals A Hybrid Processing System for Large-Scale Traffic Sensor Data

IEEE Access ◽  
2015 ◽  
Vol 3 ◽  
pp. 2341-2351 ◽  
Author(s):  
Zhuofeng Zhao ◽  
Weilong Ding ◽  
Jianwu Wang ◽  
Yanbo Han
Keyword(s):  
Large Scale ◽  
Processing System ◽  
Sensor Data

scholarly journals Observations of Turbulence in Free Atmosphere by Balloon-Borne Sensors

Sensors ◽  
2018 ◽  
Vol 18 (10) ◽  
pp. 3273
Author(s):  
Lesong Zhou ◽  
Zheng Sheng ◽  
Qixiang Liao
Keyword(s):  
Large Scale ◽  
Turbulent Energy ◽  
Energy Dissipation Rate ◽  
Sensor Data ◽  
Free Atmosphere ◽  
Height Range ◽  
High Latitude Region ◽  
Thorpe Scale ◽  
Scale Turbulence ◽  
Turbulence Parameters

In recent years, Thorpe analysis has been used to retrieve the characteristics of turbulence in free atmosphere from balloon-borne sensor data. However, previous studies have mainly focused on the mid-high latitude region, and this method is still rarely applied at heights above 30 km, especially above 35 km. Therefore, seven sets of upper air (>35 km) sounding data from the Changsha Sounding Station (28°12′ N, 113°05′ E), China are analyzed with Thorpe analysis in this article. It is noted that, in the troposphere, Thorpe analysis can better retrieve the turbulence distribution and the corresponding turbulence parameters. Also, because of the thicker troposphere at low latitudes, the values of the Thorpe scale L T and turbulent energy dissipation rate ε remain greater in a larger height range. In the stratosphere below the height of 35 km, the obtained ε is higher, and Thorpe analysis can only be used to analyze the characteristics of large-scale turbulence. In the stratosphere at a height of 35–40 km, because of the interference of sensor noise, Thorpe analysis can only help to retrieve the rough distribution position of large-scale turbulence, while it can hardly help with the calculation of the turbulence parameters.

scholarly journals From Line to Loop, A Circular 3D Printing Initiative for Upcycling Commercial Fishing Plastics

2021 ◽  
Author(s):  
◽  
Matthew O'Hagan
Keyword(s):  
3D Printing ◽  
Large Scale ◽  
Commercial Fishing ◽  
Fishing Gear ◽  
Fishing Industry ◽  
Distributed Manufacturing ◽  
Research Through Design ◽  
Management Scheme ◽  
The Pacific ◽  
Manufacturing Technologies

<p>The current linear use of plastic products follows a take, make and waste process. Commonly used by large scale industries, including the commercial fishing industry, this process results in approximately 8 million tonnes of plastic entering the ocean every year. While the fishing industry supplies livelihoods, a valuable food source and financial capital to millions of people worldwide, it’s also a significant contributor to the ocean plastics crisis. Without effective recycling schemes, an estimated 640,000 tonnes of plastic fishing gear is abandoned, lost or discarded within the ocean every year. New Zealand is no exception to this problem, as China’s waste import ban, as well as a lack of local recycling infrastructures, has resulted in the country’s commercial fishing gear polluting local coastlines as well as islands in the pacific. With the only other option for the plastic fishing gear being landfill, there is a critical need for circular initiatives that upcycle used plastic fishing gear locally into eco-innovative designs.  This research examines the issue by investigating how used buoys, aquaculture ropes and fishing nets from New Zealand’s fishing company ‘Sanford’ may be upcycled into eco-innovative designs through distributed manufacturing technologies. It introduces the idea of the circular economy, where plastic fishing gear can be reused within a technical cycle and explores how 3D printing could be part of the solution as it provides local initiatives, low material and energy usage and customisation. Overall, the research follows the research through design based on design criteria approach. Where materials, designs and systems are created under the refined research criteria, to ensure the plastic fishing gear samples are upcycled effectively into eco-innovative designs through 3D printing.  The tangible outputs of this research demonstrate how a circular upcycling system that uses distributed manufacturing technologies can create eco-innovative designs and provide a responsible disposal scheme for plastic fishing gear. It provides a new and more sustainable waste management scheme that could be applied to a range of plastic waste streams and diverts materials from entering the environment by continuously reusing them within the economy.</p>

scholarly journals Applying Machine Learning for Improving Performance Classification on Driving Behavior

2021 ◽  
Vol 4 (1) ◽  
pp. 8
Author(s):  
Ahmad Iwan Fadli ◽  
Selo Sulistyo ◽  
Sigit Wibowo
Keyword(s):  
Machine Learning ◽  
Traffic Accident ◽  
Large Scale ◽  
Detection System ◽  
Difficult Problem ◽  
Sensor Data ◽  
Driving Safety ◽  
Support Vector ◽  
Classification Methods ◽  
Machine Learning Classification

Traffic accident is a very difficult problem to handle on a large scale in a country. Indonesia is one of the most populated, developing countries that use vehicles for daily activities as its main transportation.  It is also the country with the largest number of car users in Southeast Asia, so driving safety needs to be considered. Using machine learning classification method to determine whether a driver is driving safely or not can help reduce the risk of driving accidents. We created a detection system to classify whether the driver is driving safely or unsafely using trip sensor data, which include Gyroscope, Acceleration, and GPS. The classification methods used in this study are Random Forest (RF) classification algorithm, Support Vector Machine (SVM), and Multilayer Perceptron (MLP) by improving data preprocessing using feature extraction and oversampling methods. This study shows that RF has the best performance with 98% accuracy, 98% precision, and 97% sensitivity using the proposed preprocessing stages compared to SVM or MLP.

Sign in / Sign up

Export Citation Format

Share Document