scholarly journals Comparison of Three Individual Identification Algorithms for Sperm Whales (Physeter macrocephalus) after Automated Detection

2021 ◽  
Author(s):  
JASON Holmberg ◽  
Shane Gero ◽  
Andrew Blount ◽  
Jason Parham ◽  
jacob Levenson
Keyword(s):  
High Volume ◽  
Training Data ◽  
Individual Identification ◽  
Physeter Macrocephalus ◽  
Sperm Whales ◽  
Data Set ◽  
Visual Appearance ◽  
Photo Identification ◽  
Edge Matching ◽  
Human Labor

Photo-identification of individual sperm whales (Physeter macrocephalus) is the primary technique for mark-recapture-based population analyses for the species The visual appearance of the fluke - with its distinct nicks and notches - often serves as the primary visual differentiator, allowing humans to make recorded sightings of specific individuals. However, the advent of digital photography and the significant increase in volume of images from multiple projects in combination with pre-existing historical catalogs has made applying the method more challenging.with the required human labor for de-duplication (reduction of Type II errors) and reconciliation of sightings between large datasets too cost- and time- prohibitive. To address this, we trained and evaluated the accuracy of PIE v2 (a triplet loss network) along with two existing fluke trailing edge-matching algorithms, CurvRank v2 and Dynamic Time Warping (DTW), as a mean to speed comparison among a high volume of photographs. Analyzed data were collected from a curated catalog of well-known sperm whales sighted across years (2005-2018) off the island of Dominica. The newly-trained PIE model outperformed the older CurvRank and DTW algorithms, and PIE provided the following top-k individual ID matching accuracy on a standard min-3/max-10 sighting training data set: Rank-1: 87.0%, Rank-5: 90.5%, and Rank-12: 92.5%. An essential aspect of PIE is that it can learn new individuals without network retraining, which can be immediately applied in the presence of (and for the resolution of) duplicate individuals in overlapping catalogs. Overall, our results recommend the use of PIE v2 and CurvRank v2 for ID reconciliation in combination due to their complementary performance.

scholarly journals Underwater photo-identification of marine megafauna: an identity card catalogue of sperm whales (Physeter macrocephalus) off Mauritius Island

2021 ◽  
Author(s):  
Sarano Véronique ◽  
Sarano François ◽  
Girardet Justine ◽  
Preud’homme Axel ◽  
Vitry Hugues ◽  
...  
Keyword(s):  
Skin Pigmentation ◽  
Individual Identification ◽  
Physeter Macrocephalus ◽  
Sperm Whales ◽  
Caudal Fin ◽  
Photo Identification ◽  
Long Term Monitoring ◽  
Marine Megafauna ◽  
Term Monitoring

ABSTRACTThe long-term monitoring of long-lived animal populations often requires individual identification. For cetacean populations, this identification is mostly based on morphological characters observable from a boat such as shape, spots and cuts of the back, caudal and dorsal fins. This is well suited for species easily displaying their caudal fins, such as the humpback whales Megaptera novaeangliae, or those whose skin pigmentation patterns enable individual identification.However, for elusive or shier species such as the sperm whales Physeter macrocephalus, this approach may be more challenging as individuals display a rather uniform skin pigmentation. They also do not show very often their caudal fin that must be photographed perpendicularly to the water surface, vertically and fully emerged, uneasing the individual identification from a boat. Immature sperm whales that usually have a caudal fin without any distinctive marks may sometimes be excluded from photo-identification catalogues.Within the framework of the Maubydick project, focusing on the long-term monitoring of sperm whales in Mauritius, passive underwater observation and video recording were used to identify long-lasting body markers (e.g., sex, ventral white markings, cut outs of fins) to improve individual identification. A catalogue of individual identity cards was developed and 38 individuals were recorded (six adult males, 18 adult females and 14 immatures). This catalogue was used in the field and enabled observers to record some nearly-daily and yearly recaptures. Advantages and disadvantages of this method are presented here.Such catalogues represent a robust baseline for conducting behavioural, genetic and acoustic studies in marine megafauna social species. Benefits of such newly acquired knowledge are of first importance to implement relevant conservation plans in the marine realm.

scholarly journals Long-term associations among male sperm whales (Physeter macrocephalus)

PLoS ONE ◽  
2020 ◽  
Vol 15 (12) ◽  
pp. e0244204
Author(s):  
Hayao Kobayashi ◽  
Hal Whitehead ◽  
Masao Amano
Keyword(s):  
Physeter Macrocephalus ◽  
Sperm Whales ◽  
Association Rate ◽  
Photo Identification ◽  
Male Sperm ◽  
The Social ◽  
Pelagic Habitat ◽  
Best Fitting ◽  
Social Associations

Little is known about the social structure of male sperm whales (Physeter macrocephalus) after they leave their natal units. While previous studies found no evidence for preferred associations among males, the observation of mass-strandings consisting exclusively of males, suggest that they have strong social bonds. To investigate the social associations among male sperm whales, we used half weight index of association, permutation tests and standardized lagged association rate models on a large photo-identification database collected between 2006 and 2017 in Nemuro Strait, Japan. Our results suggest that while male sperm whales are not as social as females, they do form long term associations, have preferred companionship, and forage in social proximity to each other. The best-fitting model to the standardized lagged association rate showed that associations among males last for at least 2.7 years and as most males leave the area after 2 years, associations may last for longer. Twenty dyads were observed associating over more than 2 years, for a maximum 5 years. One dyad was observed associating on 19 different days and clustered on 7 different days. Male associations may function to enhance foraging or to fend off predators. Such relationships seem to be adapted to a pelagic habitat with uncertain resource availability and predation pressure.

Killer whales (Orcinus orca) in Angolan and Gulf of Guinea waters, tropical West Africa

2010 ◽  
Vol 90 (8) ◽  
pp. 1601-1611 ◽  
Author(s):  
Caroline R Weir ◽  
Tim Collins ◽  
Inês Carvalho ◽  
Howard C. Rosenbaum
Keyword(s):  
Group Size ◽  
Orcinus Orca ◽  
Humpback Whales ◽  
Physeter Macrocephalus ◽  
Sperm Whales ◽  
Killer Whales ◽  
External Appearance ◽  
Tropical Waters ◽  
Photo Identification ◽  
Mola Mola

Killer whales Orcinus orca are considered to be relatively uncommon in tropical waters. Few sightings have been reported from the west coast of Africa due to a paucity of survey coverage. We present data on 32 killer sightings from tropical waters off Angola (N = 18), Gabon (N = 7), São Tomé (N = 6) and Cameroon (N = 1), comprising a combination of dedicated survey sightings (N = 21) and reliable anecdotal records (n = 11). Killer whales were reported from coastal waters, the shelf edge and deep, oceanic areas. Sightings indicate a probable year-round occurrence of killer whales within the region. Mean group size was 5.6 animals. There was no difference in group size between sightings in waters >200 m deep and those on the continental shelf. No photo-identification matches were found between Angola, Gabon and São Tomé. Re-sightings of two individuals occurred annually in São Tomé during 2002–2004. Killer whales had external appearance consistent with the Type A nominate species form. Antagonistic encounters were recorded between killer whales and humpback whales Megaptera novaeangliae off Angola, Gabon and Cameroon, and with sperm whales Physeter macrocephalus off Angola. Predation on ocean sunfish Mola mola was recorded in São Tomé, and possible predation on sharks was recorded twice in Gabon.

A link between male sperm whales, Physeter macrocephalus, of the Azores and Norway

2012 ◽  
Vol 92 (8) ◽  
pp. 1751-1756 ◽  
Author(s):  
Lisa Steiner ◽  
Luca Lamoni ◽  
Marta Acosta Plata ◽  
Silje-Kristin Jensen ◽  
Erland Lettevall ◽  
...  
Keyword(s):  
Nova Scotia ◽  
North Atlantic ◽  
Ocean Basin ◽  
Physeter Macrocephalus ◽  
Sperm Whales ◽  
Photo Identification ◽  
The North ◽  
Male Sperm ◽  
Basin Scale ◽  
The North Atlantic

Little is known about the movements of male sperm whales, Physeter macrocephalus, in the North Atlantic. Recoveries of traditional harpoons and tags during commercial whaling indicated movements from Nova Scotia to Spain and from the Azores to Iceland and Spain. We compared collections of photo-identification images from different areas using the North Atlantic and Mediterranean Sperm Whale Catalogue and the Eurphlukes Phlex/Match programs. The largest collections of identified males (number of individuals, start and end date for data collection shown in parentheses) are for the Azores (297, 1987–2008), Andenes (375, 1988–1996 and 2008), Tromsø (84, 2005–2008). There were six matches between Andenes and Tromsø (~25 nm), with three of these re-sighted in multiple years and three photo-identification matches from the Azores to Norway (~2400 nm). In all cases individuals first photographed in the Azores (in 1993, 1999 and 2003) were matched to images collected later in Tromsø (in 2007 and 2008). In 1997 a photo-identification image from Andenes matched a male stranded on the west coast of Ireland. No matches were made to images in smaller collections from Iceland, Nova Scotia, Greenland, Dominica, Guadeloupe, Gulf of Mexico and the Mediterranean. These findings show the value of data collected from whale watching vessels and the importance of collaboration between groups to allow investigation on an ocean basin scale. It is hoped that with the coordinated collection of more images from around the Atlantic, further insight might be gained into the movements of these widely ranging animals.

scholarly journals Research on emitter individual identification technology based on Automatic Dependent Surveillance–Broadcast signal

2021 ◽  
Vol 17 (2) ◽  
pp. 155014772199262
Author(s):  
Shiwen Chen ◽  
Junjian Yuan ◽  
Xiaopeng Xing ◽  
Xin Qin
Keyword(s):  
Individual Recognition ◽  
Evidence Theory ◽  
Field Measurements ◽  
Training Data ◽  
Individual Identification ◽  
Identification System ◽  
Individual Feature ◽  
Data Set ◽  
Theoretical Simulation ◽  
The Individual

Aiming at the shortcomings of the research on individual identification technology of emitters, which is primarily based on theoretical simulation and lack of verification equipment to conduct external field measurements, an emitter individual identification system based on Automatic Dependent Surveillance–Broadcast is designed. On one hand, the system completes the individual feature extraction of the signal preamble. On the other hand, it realizes decoding of the transmitter’s individual identity information and generates an individual recognition training data set, on which we can train the recognition network to achieve individual signal recognition. For the collected signals, six parameters were extracted as individual features. To reduce the feature dimensions, a Bessel curve fitting method is used for four of the features. The spatial distribution of the Bezier curve control points after fitting is taken as an individual feature. The processed features are classified with multiple classifiers, and the classification results are fused using the improved Dempster–Shafer evidence theory. Field measurements show that the average individual recognition accuracy of the system reaches 88.3%, which essentially meets the requirements.

scholarly journals Interaction between sperm whales (Physeter macrocephalus) and northern bottlenose whales (Hyperoodon ampullatus) and deep-water trawlers in the Northwest Atlantic

2021 ◽  
Author(s):  
Usua Oyarbide ◽  
Laura Joan Feyrer ◽  
Jonathan Gordon
Keyword(s):  
The Arctic ◽  
Physeter Macrocephalus ◽  
Sperm Whales ◽  
Greenland Halibut ◽  
Cetacean Species ◽  
Northwest Atlantic ◽  
Grand Banks ◽  
Photo Identification ◽  
Northern Bottlenose Whales

Interactions between various cetacean species and fisheries are geographically widespread and diverse. Foraging in association with fishing activities may increase prey encounter rates and possibly increase the quantity and the quality of the food consumed. This paper describes interactions between benthic trawlers, targeting mainly Greenland halibut, and two whale species: sperm whales and northern bottlenose whales, in the eastern Grand Banks of the northwest Atlantic. Whale behaviors were compared during four trawling-related activities: preparing/ shooting the net, towing, hauling and transiting between fishing sites. Sperm whales and bottlenose whales were more likely to be observed during hauling. We observed probable feeding behavior of both species close to the surface at the end of hauling which suggests they are taking fish escaping from the cod end of the net when it is close to the surface. It is not clear whether feeding attempts are made during other phases of the trawling cycle. Ten sperm whales were photo-identified and six of these individuals were resighted on different days. Resights of individuals indicated that sperm whales could follow trawlers through several sets over of distances up to 234 km. While some individuals were observed to move between fishing grounds others remained within one fishing area for some time. By contrast, even though twenty-three bottlenose whales were photo-identified, there were no resights of individual whales. While northern bottlenose whales have been studied quite extensively in some adjacent areas, particularly off Nova Scotia, their behaviour and distribution within the Grand Banks fishing areas has not been well described. No matches were found between northern bottlenose whales in this study and photo-identification catalogues for the Scotian Shelf or the Arctic. Whether and how northern bottlenose whales found in this area are connected to other subpopulations remains unclear.

Long-Range Longitudinal Movements of Sperm Whales (Physeter macrocephalus) in the North Atlantic Ocean Revealed by Photo-Identification

2022 ◽  
Vol 48 (1) ◽  
pp. 3-8
Author(s):  
Keith D. Mullin ◽  
Lisa Steiner ◽  
Charlotte Dunn ◽  
Diane Claridge ◽  
Laura González García ◽  
...  
Keyword(s):  
Atlantic Ocean ◽  
Long Range ◽  
North Atlantic ◽  
North Atlantic Ocean ◽  
Physeter Macrocephalus ◽  
Sperm Whales ◽  
Photo Identification ◽  
The North ◽  
The North Atlantic

Comparison of Two Computer-Assisted Photo-Identification Methods Applied to Sperm Whales (Physeter macrocephalus)

2005 ◽  
Vol 31 (2) ◽  
pp. 243-247 ◽  
Author(s):  
Bas W. P. M. Beekmans ◽  
Hal Whitehead ◽  
Ruben Huele ◽  
Lisa Steiner ◽  
Adri G. Steenbeek
Keyword(s):  
Computer Assisted ◽  
Physeter Macrocephalus ◽  
Sperm Whales ◽  
Identification Methods ◽  
Photo Identification

Cloning Safe Driving Behavior for Self-Driving Cars using Convolutional Neural Networks

2019 ◽  
Vol 12 (2) ◽  
pp. 120-127 ◽  
Author(s):  
Wael Farag
Keyword(s):  
Gradient Descent ◽  
Autonomous Driving ◽  
Driving Behavior ◽  
Training Data ◽  
Stochastic Gradient Descent ◽  
Data Set ◽  
Safe Driving ◽  
Processing Pipeline ◽  
Self Driving Cars ◽  
And Training

Background: In this paper, a Convolutional Neural Network (CNN) to learn safe driving behavior and smooth steering manoeuvring, is proposed as an empowerment of autonomous driving technologies. The training data is collected from a front-facing camera and the steering commands issued by an experienced driver driving in traffic as well as urban roads. Methods: This data is then used to train the proposed CNN to facilitate what it is called “Behavioral Cloning”. The proposed Behavior Cloning CNN is named as “BCNet”, and its deep seventeen-layer architecture has been selected after extensive trials. The BCNet got trained using Adam’s optimization algorithm as a variant of the Stochastic Gradient Descent (SGD) technique. Results: The paper goes through the development and training process in details and shows the image processing pipeline harnessed in the development. Conclusion: The proposed approach proved successful in cloning the driving behavior embedded in the training data set after extensive simulations.

Comparative Analysis of Machine Learning Techniques Using Predictive Modeling

2020 ◽  
Vol 13 ◽  
Author(s):  
Ritu Khandelwal ◽  
Hemlata Goyal ◽  
Rajveer Singh Shekhawat
Keyword(s):  
Machine Learning ◽  
Comparative Analysis ◽  
Data Science ◽  
Training Data ◽  
Machine Learning Techniques ◽  
Future Trends ◽  
Data Set ◽  
Learning Stage ◽  
Learning Techniques ◽  
Different Types

Introduction: Machine learning is an intelligent technology that works as a bridge between businesses and data science. With the involvement of data science, the business goal focuses on findings to get valuable insights on available data. The large part of Indian Cinema is Bollywood which is a multi-million dollar industry. This paper attempts to predict whether the upcoming Bollywood Movie would be Blockbuster, Superhit, Hit, Average or Flop. For this Machine Learning techniques (classification and prediction) will be applied. To make classifier or prediction model first step is the learning stage in which we need to give the training data set to train the model by applying some technique or algorithm and after that different rules are generated which helps to make a model and predict future trends in different types of organizations. Methods: All the techniques related to classification and Prediction such as Support Vector Machine(SVM), Random Forest, Decision Tree, Naïve Bayes, Logistic Regression, Adaboost, and KNN will be applied and try to find out efficient and effective results. All these functionalities can be applied with GUI Based workflows available with various categories such as data, Visualize, Model, and Evaluate. Result: To make classifier or prediction model first step is learning stage in which we need to give the training data set to train the model by applying some technique or algorithm and after that different rules are generated which helps to make a model and predict future trends in different types of organizations Conclusion: This paper focuses on Comparative Analysis that would be performed based on different parameters such as Accuracy, Confusion Matrix to identify the best possible model for predicting the movie Success. By using Advertisement Propaganda, they can plan for the best time to release the movie according to the predicted success rate to gain higher benefits. Discussion: Data Mining is the process of discovering different patterns from large data sets and from that various relationships are also discovered to solve various problems that come in business and helps to predict the forthcoming trends. This Prediction can help Production Houses for Advertisement Propaganda and also they can plan their costs and by assuring these factors they can make the movie more profitable.

Sign in / Sign up

Export Citation Format

Share Document