Fisheries acoustics in Norway—Wide band data, autonomous platforms and deep learning

2021 ◽  
Vol 150 (4) ◽  
pp. A254-A254
Author(s):  
Nils Olav Handegard ◽  
Forland N. Tonje ◽  
Espen Johnsen ◽  
Geir Pedersen ◽  
Maria Tenningen ◽  
...  
Keyword(s):  
Deep Learning ◽  
Wide Band ◽  
Fisheries Acoustics

scholarly journals UWB Indoor Localization Using Deep Learning LSTM Networks

2020 ◽  
Vol 10 (18) ◽  
pp. 6290 ◽  
Author(s):  
Alwin Poulose ◽  
Dong Seog Han
Keyword(s):  
Deep Learning ◽  
Short Term Memory ◽  
Indoor Localization ◽  
Distance Estimation ◽  
Wide Band ◽  
Batch Size ◽  
Estimation Accuracy ◽  
Time Of Arrival ◽  
Localization Error ◽  
Localization Accuracy

Localization using ultra-wide band (UWB) signals gives accurate position results for indoor localization. The penetrating characteristics of UWB pulses reduce the multipath effects and identify the user position with precise accuracy. In UWB-based localization, the localization accuracy depends on the distance estimation between anchor nodes (ANs) and the UWB tag based on the time of arrival (TOA) of UWB pulses. The TOA errors in the UWB system, reduce the distance estimation accuracy from ANs to the UWB tag and adds the localization error to the system. The position accuracy of a UWB system also depends on the line of sight (LOS) conditions between the UWB anchors and tag, and the computational complexity of localization algorithms used in the UWB system. To overcome these UWB system challenges for indoor localization, we propose a deep learning approach for UWB localization. The proposed deep learning model uses a long short-term memory (LSTM) network for predicting the user position. The proposed LSTM model receives the distance values from TOA-distance model of the UWB system and predicts the current user position. The performance of the proposed LSTM model-based UWB localization system is analyzed in terms of learning rate, optimizer, loss function, batch size, number of hidden nodes, timesteps, and we also compared the mean localization accuracy of the system with different deep learning models and conventional UWB localization approaches. The simulation results show that the proposed UWB localization approach achieved a 7 cm mean localization error as compared to conventional UWB localization approaches.

scholarly journals Complex data labeling with deep learning methods: Lessons from fisheries acoustics

2020 ◽  
Author(s):  
Jean-Michel A. Sarr ◽  
Timothée Brochier ◽  
P. Brehmer ◽  
Y. Perrot ◽  
A. Bah ◽  
...  
Keyword(s):  
Deep Learning ◽  
Complex Data ◽  
Learning Methods ◽  
Fisheries Acoustics

Seven-colour photometry at the Geneva Observatory

1966 ◽  
Vol 24 ◽  
pp. 262-266 ◽  
Author(s):  
M. Golay
Keyword(s):  
Wide Band ◽  
Electric System ◽  
Band Type

During the last 5 years, we have developed a seven-colour photometry at the Geneva Observatory. Our multicolour photo-electric system is of a wide-band type; the bandwidth being about 500Å for four filters. The three others are similar to theUBVsystem. In Table 1 we give the filter combinations used in our photometry (1).

TEM and cathodoluminescence of precipitates in II-VI semiconductors

1988 ◽  
Vol 46 ◽  
pp. 488-489
Author(s):  
Joanna L. Batstone
Keyword(s):  
Crystal Growth ◽  
Band Gap ◽  
Local Strain ◽  
Wide Band ◽  
Optoelectronic Device ◽  
Wide Band Gap ◽  
Bulk Crystal Growth ◽  
Transmission Electron ◽  
Device Applications ◽  
Stoichiometry Control

Interest in II-VI semiconductors centres around optoelectronic device applications. The wide band gap II-VI semiconductors such as ZnS, ZnSe and ZnTe have been used in lasers and electroluminescent displays yielding room temperature blue luminescence. The narrow gap II-VI semiconductors such as CdTe and HgxCd1-x Te are currently used for infrared detectors, where the band gap can be varied continuously by changing the alloy composition x.Two major sources of precipitation can be identified in II-VI materials; (i) dopant introduction leading to local variations in concentration and subsequent precipitation and (ii) Te precipitation in ZnTe, CdTe and HgCdTe due to native point defects which arise from problems associated with stoichiometry control during crystal growth. Precipitation is observed in both bulk crystal growth and epitaxial growth and is frequently associated with segregation and precipitation at dislocations and grain boundaries. Precipitation has been observed using transmission electron microscopy (TEM) which is sensitive to local strain fields around inclusions.

Electron microscopic characterization of diamond thin films and substrates for diamond heteroepitaxial growth

1989 ◽  
Vol 47 ◽  
pp. 592-593
Author(s):  
J.B. Posthill ◽  
R.P. Burns ◽  
R.A. Rudder ◽  
Y.H. Lee ◽  
R.J. Markunas ◽  
...  
Keyword(s):  
Thin Films ◽  
Wide Band ◽  
Deposition Process ◽  
Heteroepitaxial Growth ◽  
Electron Microscopic ◽  
Wide Band Gap ◽  
Lattice Matching ◽  
Different Types ◽  
Diamond Thin Films

Because of diamond’s wide band gap, high thermal conductivity, high breakdown voltage and high radiation resistance, there is a growing interest in developing diamond-based devices for several new and demanding electronic applications. In developing this technology, there are several new challenges to be overcome. Much of our effort has been directed at developing a diamond deposition process that will permit controlled, epitaxial growth. Also, because of cost and size considerations, it is mandatory that a non-native substrate be developed for heteroepitaxial nucleation and growth of diamond thin films. To this end, we are currently investigating the use of Ni single crystals on which different types of epitaxial metals are grown by molecular beam epitaxy (MBE) for lattice matching to diamond as well as surface chemistry modification. This contribution reports briefly on our microscopic observations that are integral to these endeavors.

Deep Learning

2009 ◽  
Author(s):  
Stellan Ohlsson
Keyword(s):  
Deep Learning

Intelligence artificielle : le futur de l’Orthodontie ?

2019 ◽  
Vol 53 (3) ◽  
pp. 281-294
Author(s):  
Jean-Michel Foucart ◽  
Augustin Chavanne ◽  
Jérôme Bourriau
Keyword(s):  
Big Data ◽  
Deep Learning ◽  
Intelligence Artificielle ◽  
Set Up

Nombreux sont les apports envisagés de l’Intelligence Artificielle (IA) en médecine. En orthodontie, plusieurs solutions automatisées sont disponibles depuis quelques années en imagerie par rayons X (analyse céphalométrique automatisée, analyse automatisée des voies aériennes) ou depuis quelques mois (analyse automatique des modèles numériques, set-up automatisé; CS Model +, Carestream Dental™). L’objectif de cette étude, en deux parties, est d’évaluer la fiabilité de l’analyse automatisée des modèles tant au niveau de leur numérisation que de leur segmentation. La comparaison des résultats d’analyse des modèles obtenus automatiquement et par l’intermédiaire de plusieurs orthodontistes démontre la fiabilité de l’analyse automatique; l’erreur de mesure oscillant, in fine, entre 0,08 et 1,04 mm, ce qui est non significatif et comparable avec les erreurs de mesures inter-observateurs rapportées dans la littérature. Ces résultats ouvrent ainsi de nouvelles perspectives quand à l’apport de l’IA en Orthodontie qui, basée sur le deep learning et le big data, devrait permettre, à moyen terme, d’évoluer vers une orthodontie plus préventive et plus prédictive.

Sign in / Sign up

Export Citation Format

Share Document