scholarly journals An Automotive Distributed Mobile Sensor Data Collection with Machine Learning Based Data Fusion and Analysis on a Central Backend System

2016 ◽  
Vol 26 ◽  
pp. 570-579 ◽  
Author(s):  
Tim Tiedemann ◽  
Christian Backe ◽  
Thomas Vögele ◽  
Peter Conradi
Keyword(s):  
Machine Learning ◽  
Data Collection ◽  
Data Fusion ◽  
Sensor Data ◽  
Mobile Sensor

scholarly journals LabelSens: enabling real-time sensor data labelling at the point of collection using an artificial intelligence-based approach

2020 ◽  
Vol 24 (5) ◽  
pp. 709-722
Author(s):  
Kieran Woodward ◽  
Eiman Kanjo ◽  
Andreas Oikonomou ◽  
Alan Chamberlain
Keyword(s):  
Machine Learning ◽  
Data Collection ◽  
Real Time ◽  
High Performance ◽  
Poor Performance ◽  
Limited Range ◽  
Performance Comparison ◽  
Mobile App ◽  
Sensor Data ◽  
New Techniques

Abstract In recent years, machine learning has developed rapidly, enabling the development of applications with high levels of recognition accuracy relating to the use of speech and images. However, other types of data to which these models can be applied have not yet been explored as thoroughly. Labelling is an indispensable stage of data pre-processing that can be particularly challenging, especially when applied to single or multi-model real-time sensor data collection approaches. Currently, real-time sensor data labelling is an unwieldy process, with a limited range of tools available and poor performance characteristics, which can lead to the performance of the machine learning models being compromised. In this paper, we introduce new techniques for labelling at the point of collection coupled with a pilot study and a systematic performance comparison of two popular types of deep neural networks running on five custom built devices and a comparative mobile app (68.5–89% accuracy within-device GRU model, 92.8% highest LSTM model accuracy). These devices are designed to enable real-time labelling with various buttons, slide potentiometer and force sensors. This exploratory work illustrates several key features that inform the design of data collection tools that can help researchers select and apply appropriate labelling techniques to their work. We also identify common bottlenecks in each architecture and provide field tested guidelines to assist in building adaptive, high-performance edge solutions.

scholarly journals Multi-modal mobile sensor data fusion for autonomous robot mapping problem

2016 ◽  
Vol 42 ◽  
pp. 03008 ◽  
Author(s):  
M. H. Kassem ◽  
Omar M. Shehata ◽  
E. I. Imam Morgan
Keyword(s):  
Data Fusion ◽  
Autonomous Robot ◽  
Sensor Data ◽  
Mobile Sensor ◽  
Mapping Problem ◽  
Sensor Data Fusion

scholarly journals Multiple Flights or Single Flight Instrument Fusion of Hyperspectral and ALS Data? A Comparison of their Performance for Vegetation Mapping

2019 ◽  
Vol 11 (8) ◽  
pp. 970 ◽  
Author(s):  
Łukasz Sławik ◽  
Jan Niedzielko ◽  
Adam Kania ◽  
Hubert Piórkowski ◽  
Dominik Kopeć
Keyword(s):  
Data Collection ◽  
Data Fusion ◽  
Laser System ◽  
Remote Sensing Data ◽  
Natura 2000 ◽  
Vegetation Mapping ◽  
Sensor Data ◽  
The Difference ◽  
Using Data ◽  
Instrument Fusion

Fusion of remote sensing data often improves vegetation mapping, compared to using data from only a single source. The effectiveness of this fusion is subject to many factors, including the type of data, collection method, and purpose of the analysis. In this study, we compare the usefulness of hyperspectral (HS) and Airborne Laser System (ALS) data fusion acquired in separate flights, Multiple Flights Data Fusion (MFDF), and during a single flight through Instrument Fusion (IF) for the classification of non-forest vegetation. An area of 6.75 km2 was selected, where hyperspectral and ALS data was collected during two flights in 2015 and one flight in 2017. This data was used to classify three non-forest Natura 2000 habitats i.e., Xeric sand calcareous grasslands (code 6120), alluvial meadows of river valleys of the Cnidion dubii (code 6440), species-rich Nardus grasslands (code 6230) using a Random Forest classifier. Our findings show that it is not possible to determine which sensor, HS, or ALS used independently leads to a higher classification accuracy for investigated Natura 2000 habitats. Concurrently, increased stability and consistency of classification results was confirmed, regardless of the type of fusion used; IF, MFDF and varied information relevance of single sensor data. The research shows that the manner of data collection, using MFDF or IF, does not determine the level of relevance of ALS or HS data. The analysis of fusion effectiveness, gauged as the accuracy of the classification result and time consumed for data collection, has shown a superiority of IF over MFDF. IF delivered classification results that are more accurate compared to MFDF. IF is always cheaper than MFDF and the difference in effectiveness of both methods becomes more pronounced when the area of aerial data collection becomes larger.

Geomorphological hazards assessment using machine learning and data fusion

2020 ◽  
Author(s):  
Mohammad Ahmed ◽  
Hamed Farhadi ◽  
Panagiotis Michalis ◽  
Manousos Valyrakis
Keyword(s):  
Machine Learning ◽  
Data Fusion ◽  
Turbulent Flow ◽  
Turbulent Flows ◽  
Fuzzy Inference ◽  
Data Driven ◽  
Sensor Data ◽  
Machine Learning Techniques ◽  
Flume Experiments ◽  
Motion Data

<p>Turbulent flows may destabilise riverbeds and banks, transporting sediment or underscouring hydraulic infrastructure built near water bodies. For example, scour is a significant challenge that can affect the stability of bridge foundations as the transport of sediment around a bridge pier may cause structural instabilities and catastrophic failures. The aim of this study is to use machine learning techniques & data driven algorithms to predict how energetic turbulent flow events can result in the removal of individual sediment grains, resting on the bed surface or on the protective armour layer around built infrastructure. </p><p>The flume experiments involve flow and particle motion data gathering campaigns [1]. Turbulent flow data are collected upstream the exposed target particle using acoustic Doppler velocimetry. Particle's motion data are gathered using novel micro-electro-mechanical sensors embedded within its waterproof casing, for a range of flow conditions. The obtained data are fed into neural networks having distinct algorithmic complexity (inputs, levels and neutrons). A comparison of the performance of the various model architectures, as well as with past ones [2], is conducted to identify the optimal predictive algorithm for the configuration tested. Sensor data fusion combined with artificial intelligence techniques are shown to provide a unique tool for live and robust data-driven predictions to help tackle significant engineering problems, such as geomorphological activity and scouring of infrastructure (eg bridge piers and embankments) due to turbulent flows, which become increasingly more challenging, under the scope of climate change and intensifying extreme weather hazards.</p><p> </p><p>References</p><p>[1] Valyrakis, M., Farhadi, H. 2017. Investigating coarse sediment particles transport using PTV and “smart-pebbles” instrumented with inertial sensors, EGU General Assembly 2017, Vienna, Austria, 23-28 April 2017, id. 9980.</p><p>[2] Valyrakis, M., Diplas, P., Dancey, C.L. 2011b. Prediction of coarse particle movement with adaptive neuro-fuzzy inference systems, Hydrological Processes, 25 (22). pp. 3513-3524. ISSN 0885-6087, doi:10.1002/hyp.8228.</p>

Sign in / Sign up

Export Citation Format

Share Document