scholarly journals Photo Identification of Individual Salmo trutta Based on Deep Learning

2021 ◽  
Vol 11 (19) ◽  
pp. 9039
Author(s):  
Marius Pedersen ◽  
Ahmed Mohammed
Keyword(s):  
Salmo Trutta ◽  
Video Sequence ◽  
Space Representation ◽  
Shape Variation ◽  
Photo Identification ◽  
Identification Method ◽  
Tag Loss ◽  
Video Recordings ◽  
Individual Fish ◽  
High Level

Individual fish identification and recognition is an important step in the conservation and management of fisheries. One of most frequently used methods involves capturing and tagging fish. However, these processes have been reported to cause tissue damage, premature tag loss, and decreased swimming capacity. More recently, marine video recordings have been extensively used for monitoring fish populations. However, these require visual inspection to identify individual fish. In this work, we proposed an automatic method for the identification of individual brown trouts, Salmo trutta. We developed a deep convolutional architecture for this purpose. Specifically, given two fish images, multi-scale convolutional features were extracted to capture low-level features and high-level semantic components for embedding space representation. The extracted features were compared at each scale for capturing representation for individual fish identification. The method was evaluated on a dataset called NINA204 based on 204 videos of brown trout and on a dataset TROUT39 containing 39 brown trouts in 288 frames. The identification method distinguished individual fish with 94.6% precision and 74.3% recall on a NINA204 video sequence with significant appearance and shape variation. The identification method takes individual fish and is able to distinguish them with precision and recall percentages of 94.6% and 74.3% on NINA204 for a video sequence with significant appearance and shape variation.

scholarly journals Associations Between Music Training and the Dynamics of Writing Music by Hand

2020 ◽  
pp. 102986492097214
Author(s):  
Aurélien Bertiaux ◽  
François Gabrielli ◽  
Mathieu Giraud ◽  
Florence Levé
Keyword(s):  
Classical Music ◽  
Music Notation ◽  
Musical Score ◽  
Music Training ◽  
Video Recordings ◽  
Musical Structures ◽  
Music Recognition ◽  
High Level ◽  
Bottom To Top ◽  
Western Classical Music

Learning to write music in the staff notation used in Western classical music is part of a musician’s training. However, writing music by hand is rarely taught formally, and many musicians are not aware of the characteristics of their musical handwriting. As with any symbolic expression, musical handwriting is related to the underlying cognition of the musical structures being depicted. Trained musicians read, think, and play music with high-level structures in mind. It seems natural that they would also write music by hand with these structures in mind. Moreover, improving our understanding of handwriting may help to improve both optical music recognition and music notation and composition interfaces. We investigated associations between music training and experience, and the way people write music by hand. We made video recordings of participants’ hands while they were copying or freely writing music, and analysed the sequence in which they wrote the elements contained in the musical score. The results confirmed experienced musicians wrote faster than beginners, were more likely to write chords from bottom to top, and they tended to write the note heads first, in a flowing fashion, and only afterwards use stems and beams to emphasize grouping, and add expressive markings.

Intraspecific variation and structuring of phenotype in a lake-dwelling species are driven by lake size and elevation

2020 ◽  
Vol 131 (3) ◽  
pp. 585-599
Author(s):  
J Peter Koene ◽  
Kathryn R Elmer ◽  
Colin E Adams
Keyword(s):  
Brown Trout ◽  
Salmo Trutta ◽  
Geographic Area ◽  
Geographic Region ◽  
Shape Variation ◽  
Multivariate Statistical ◽  
Geometric Morphometric ◽  
Medium Scale ◽  
Natural Lakes ◽  
Almost All

Abstract The fragmented, heterogeneous and relatively depauperate ecosystems of recently glaciated lakes present contrasting ecological opportunities for resident fish. Across a species, local adaptation may induce diverse and distinct phenotypic responses to various selection pressures. We tested for intraspecific phenotypic structuring by population in a common native lake-dwelling fish species across a medium-scale geographic region with considerable variation in lake types. We investigated potential lake-characteristic drivers of trophic morphology. Using geometric morphometric techniques, we quantified the head shapes of 759 adult brown trout (Salmo trutta L.) from 28 lakes and reservoirs across Scotland. Multivariate statistical analyses showed that almost all populations differed from one another. Trout from larger and deeper lakes had deeper, but shorter heads, and smaller eyes. Higher elevation lakes were associated with fish with shorter heads and jaws. Within-population shape variation also differed by population, and was positively correlated with lake surface area and depth. Trout within reservoirs differed subtly from those in natural lakes, having larger eyes, shorter jaws and greater variability. This study documents an extraordinary morphological variation between and within populations of brown trout, and demonstrates the role of the extrinsic environment in driving phenotypic structuring over a medium-scale and varied geographic area.

Speed Adaptation in Learning from Demonstration through Latent Space Formulation

Robotica ◽  
2019 ◽  
Vol 38 (10) ◽  
pp. 1867-1879 ◽  
Author(s):  
Maria Koskinopoulou ◽  
Michail Maniadakis ◽  
Panos Trahanias
Keyword(s):  
Human Robot Interaction ◽  
Space Representation ◽  
Learning From Demonstration ◽  
Level Control ◽  
Physical Constraints ◽  
Spatial Features ◽  
Spatial Consistency ◽  
Latent Space ◽  
Space Formulation ◽  
High Level

SUMMARYPerforming actions in a timely manner is an indispensable aspect in everyday human activities. Accordingly, it has to be present in robotic systems if they are going to seamlessly interact with humans. The current work addresses the problem of learning both the spatial and temporal characteristics of human motions from observation. We formulate learning as a mapping between two worlds (the observed and the action ones). This mapping is realized via an abstract intermediate representation termed “Latent Space.” Learned actions can be subsequently invoked in the context of more complex human–robot interaction (HRI) scenarios. Unlike previous learning from demonstration (LfD) methods that cope only with the spatial features of an action, the formulated scheme effectively encompasses spatial and temporal aspects. Learned actions are reproduced under the high-level control of a time-informed task planner. During the implementation of the studied scenarios, temporal and physical constraints may impose speed adaptations in the reproduced actions. The employed latent space representation readily supports such variations, giving rise to novel actions in the temporal domain. Experimental results demonstrate the effectiveness of the proposed scheme in the implementation of HRI scenarios. Finally, a set of well-defined evaluation metrics are introduced to assess the validity of the proposed approach considering the temporal and spatial consistency of the reproduced behaviors.

Repeat Homing of Brown Trout (Salmo trutta) in Lake Eucumbene, New South Wales, Australia

1977 ◽  
Vol 34 (8) ◽  
pp. 1085-1094 ◽  
Author(s):  
R. D. J. Tilzey
Keyword(s):  
Rainbow Trout ◽  
Brown Trout ◽  
Salmo Trutta ◽  
New South ◽  
Tag Loss ◽  
Trout Population ◽  
South Wales ◽  
High Incidence ◽  
Brown Trout Salmo Trutta ◽  
External Form

Spawning runs of lentic-dwelling brown trout (Salmo trutta) and rainbow trout (S. gairdneri) in Swamp Creek, an inlet of Lake Eucumbene, were studied for 4 consecutive yr, and 3517 browns and 415 rainbows were tagged during 1968–70. A further 240 browns and 229 rainbows were marked in other inlets. Recaptures of marked browns in 1969 and 1970 showed a high incidence of repeat homing, up to 25.7 and 10.6% returning after 12 and 24 mo, respectively. Few rainbow trout homed. Tag loss and the mortality and maturation of marked browns were estimated and percentage homing and straying in 1969, 1970 and 1971 was calculated. High percentage homing [Formula: see text] in 1969–70 and the variance in external form in the lentic population suggested some genetic isolation within the brown trout population. Homing ability was not influenced by fish age. Percentage homing fell markedly in 1971 after the removal of nearly all resident brown trout from Swamp Creek and suggested racially distinct stream trout populations to be an important navigational cue to homing brown trout. Key words: repeat homing, Salmo trutta, homing frequency, navigation, racial cue, Australia

scholarly journals Automatized analysis of children’s exposure to child-directed speech in reschool settings: Validation and application

PLoS ONE ◽  
2020 ◽  
Vol 15 (11) ◽  
pp. e0242511
Author(s):  
Hugo Gonzalez Villasanti ◽  
Laura M. Justice ◽  
Leidy Johana Chaparro-Moreno ◽  
Tzu-Jung Lin ◽  
Kelly Purtell
Keyword(s):  
Speech Recognition ◽  
Automatic Speech Recognition ◽  
Error Rates ◽  
Preschool Classrooms ◽  
Video Recordings ◽  
Supervised Classifiers ◽  
Time Fall ◽  
High Level ◽  
Early Childhood Settings ◽  
Children’S Exposure

The present study explored whether a tool for automatic detection and recognition of interactions and child-directed speech (CDS) in preschool classrooms could be developed, validated, and applied to non-coded video recordings representing children’s classroom experiences. Using first-person video recordings collected by 13 preschool children during a morning in their classrooms, we extracted high-level audiovisual features from recordings using automatic speech recognition and computer vision services from a cloud computing provider. Using manual coding for interactions and transcriptions of CDS as reference, we trained and tested supervised classifiers and linear mappings to measure five variables of interest. We show that the supervised classifiers trained with speech activity, proximity, and high-level facial features achieve adequate accuracy in detecting interactions. Furthermore, in combination with an automatic speech recognition service, the supervised classifier achieved error rates for CDS measures that are in line with other open-source automatic decoding tools in early childhood settings. Finally, we demonstrate our tool’s applicability by using it to automatically code and transcribe children’s interactions and CDS exposure vertically within a classroom day (morning to afternoon) and horizontally over time (fall to winter). Developing and scaling tools for automatized capture of children’s interactions with others in the preschool classroom, as well as exposure to CDS, may revolutionize scientific efforts to identify precise mechanisms that foster young children’s language development.

Studies on Crepidostomum metoecus (Braun) and C. farionis (Müller), parasitic in Salmo trutta L. and S. salar L. in Britain

Parasitology ◽  
1958 ◽  
Vol 48 (3-4) ◽  
pp. 336-352 ◽  
Author(s):  
J. D. Thomas
Keyword(s):  
Salmo Trutta ◽  
Anguilla Anguilla ◽  
Habitat Isolation ◽  
Acquired Immunity ◽  
Host Fish ◽  
Individual Fish ◽  
Large Numbers ◽  
Accidental Host ◽  
Fish Hosts ◽  
First Time

1. Crepidostomum farionis (Müller, 1784) and C. metoecus (Braun, 1900) were found to occur together in the same host fish, Salmo trutta L., S. salar L. and Anguilla anguilla (L.) in mid-Wales. It is believed that the latter species constituted an accidental host.2. C. metoecus is recorded in Britain for the first time.3. There was some evidence of a habitat isolation in individual fish as C. metoecus occurred predominantly within the pyloric caeca, while C. farionis usually occupied a more posterior station in the intestine.4. A detailed description is given of G. metoecus and the salient features of this species are compared with those of C. farionis.5. The two species of Crepidostomum commonly occurred in large numbers in their fish hosts, individual fish harbouring up to 157 worms. No lesions attributable to Crepidostomum were, however, detected and there was no evidence of pathogenicity.6. It would appear that the eel is physiologically immune to both species of Crepidostomum and that the salmon parr is partially resistant.7. The degree of infestation of trout and parr with both the Crepidostomum species is at a maximum during the winter months and at a minimum in the summer months. This seasonal variation can be attributed to a periodicity in the swarming of the cercariae.8. There is no evidence of age resistance or acquired immunity of the trout to infestation by Crepidostomum species.

Model Predictive Control for Lateral Position of Endless Metal Belts

2013 ◽  
Vol 198 ◽  
pp. 525-532
Author(s):  
Stefan Grosswindhager ◽  
Klemens Schulmeister ◽  
Martin Kozek
Keyword(s):  
Model Predictive Control ◽  
Predictive Control ◽  
Research Work ◽  
Lateral Position ◽  
Operating Conditions ◽  
Space Representation ◽  
Control Approach ◽  
State Space Representation ◽  
Lateral Disturbance ◽  
High Level

Endless metal belts play an important role in advanced processing lines or belt machines for many production processes. In contrast to standard conveyor lines metal belts must be run over cylindrical return drums due to the high elastic modulus of the belts material and the usually high level of pre-stress. Since cylindrical return drums do not provide passive lateral guidance (self-centering) they have to be actively adjusted by swiveling drum axes. In this work a suitable control scheme is presented to guarantee a set lateral position at the return drums even in the presence of a lateral disturbance force. Since the lateral dynamics of the endless belt show strong coupling between all inputs and all outputs a multivariate control approach with inherent decoupling capabilities is needed. Moreover, a number of technological constraints must be fulfilled for all operating conditions such as limited swivel angles and the maximum allowable tensile stress in the belt. In this research work a constrained model predictive control (MPC) is therefore designed to overcome the aforementioned problems. The model is based on a description in the spatial domain (belt travel) which renders the model independent of operating speed. Using this model a multi-input multi-output (MIMO) MPC-scheme is derived also in state-space representation. Moreover, the control explicitly considers constraints on the control inputs and on the maximum allowable belt stress.

scholarly journals Non-linearity matters: a deep learning solution to generalization of hidden brain patterns across population cohorts

2021 ◽  
Author(s):  
Mariam Zabihi ◽  
Seyed Mostafa Kia ◽  
Thomas Wolfers ◽  
Richard Dinga ◽  
Alberto Llera ◽  
...  
Keyword(s):  
Deep Learning ◽  
Fmri Data ◽  
Space Representation ◽  
Model Parameters ◽  
Independent Dataset ◽  
Latent Space ◽  
Human Connectome Project ◽  
Nonlinear Features ◽  
Latent Representations ◽  
High Level

AbstractThe increasing number of neuroimaging scans in recent years has facilitated the use of complex nonlinear approaches to analyzing such data. More specifically, deep learning, which has been previously hindered by the curse of dimensionality is now feasible. However, it remains challenging to use these techniques develop reliable biomarkers and find an optimal representation of data that explains the biological underpinnings of the mental disorders Here, we employed a 3-dimensional autoencoder with an architecture designed from the ground up for task-fMRI data. Our study presented a coherent strategy for optimizing model parameters and architecture and a method for visualizing and interpreting the latent space representation. We trained our model with multi-task fMRI data derived from the Human Connectome Project (HCP) that provides whole-brain coverage across a range of cognitive tasks. Next, in a transfer learning setting, we tested the generalization of our latent space on UK Biobank data as an independent dataset. We showed that the model did not only learn salient features such as age but also high-level behavioral characteristics and that this representation was highly generic and generalizable to an independent dataset. Furthermore, we demonstrated that the projection of latent space back into the original space is meaningful and interpretable. Finally, our results show that with careful implementation, nonlinear features can provide complementary information that accessible to purely linear methods. Our results provide an important step toward learning interpretable and generalizable latent representations that link cognition with underlying brain systems.

Sign in / Sign up

Export Citation Format

Share Document