scholarly journals Re-identification of individuals from images using spot constellations: a case study in Arctic charr ( Salvelinus alpinus )

2021 ◽  
Vol 8 (7) ◽  
pp. 201768
Author(s):  
Ignacy T. De¸bicki ◽  
Elizabeth A. Mittell ◽  
Bjarni K. Kristjánsson ◽  
Camille A. Leblanc ◽  
Michael B. Morrissey ◽  
...  
Keyword(s):  
Salvelinus Alpinus ◽  
Arctic Charr ◽  
Wild Populations ◽  
Learning Techniques ◽  
Small Set ◽  
Set Up ◽  
The Individual ◽  
Classical Computer ◽  
Better Than

The ability to re-identify individuals is fundamental to the individual-based studies that are required to estimate many important ecological and evolutionary parameters in wild populations. Traditional methods of marking individuals and tracking them through time can be invasive and imperfect, which can affect these estimates and create uncertainties for population management. Here we present a photographic re-identification method that uses spot constellations in images to match specimens through time. Photographs of Arctic charr ( Salvelinus alpinus ) were used as a case study. Classical computer vision techniques were compared with new deep-learning techniques for masks and spot extraction. We found that a U-Net approach trained on a small set of human-annotated photographs performed substantially better than a baseline feature engineering approach. For matching the spot constellations, two algorithms were adapted, and, depending on whether a fully or semi-automated set-up is preferred, we show how either one or a combination of these algorithms can be implemented. Within our case study, our pipeline both successfully identified unmarked individuals from photographs alone and re-identified individuals that had lost tags, resulting in an approximately 4% increase in our estimate of survival rate. Overall, our multi-step pipeline involves little human supervision and could be applied to many organisms.

Thermal stress in Arctic charr Salvelinus alpinus broodstock: a 28 year case study

2015 ◽  
Vol 86 (3) ◽  
pp. 1139-1152 ◽  
Author(s):  
H. Jeuthe ◽  
E. Brännäs ◽  
J Nilsson
Keyword(s):  
Thermal Stress ◽  
Salvelinus Alpinus ◽  
Arctic Charr

Comparison of the growth performance of offspring from cultured versus wild populations of arctic charr,Salvelinus alpinus(L.), kept at three different temperatures

2012 ◽  
Vol 44 (6) ◽  
pp. 995-1001 ◽  
Author(s):  
Sten Ivar Siikavuopio ◽  
Atle Foss ◽  
Bjørn-Steinar Saether ◽  
Snorri Gunnarsson ◽  
Albert K Imsland
Keyword(s):  
Growth Performance ◽  
Salvelinus Alpinus ◽  
Arctic Charr ◽  
Wild Populations ◽  
Different Temperatures

Relational capital and knowledge transfer in universities

2019 ◽  
Vol 25 (1) ◽  
pp. 185-201 ◽  
Author(s):  
Paola Paoloni ◽  
Francesca Maria Cesaroni ◽  
Paola Demartini
Keyword(s):  
Research Approach ◽  
Relational Capital ◽  
Content Type ◽  
Action Research Approach ◽  
Relevant Topic ◽  
Set Up ◽  
The Individual ◽  
New Research ◽  
The University

PurposeThe importance of relational capital for the university has grown enormously in recent years. In fact, relational capital allows universities to promote and emphasize the effectiveness of the third mission. The purpose of this paper is to propose a case study involving an Italian university that recently set up a new research observatory, and, thanks to its success, succeeded in enhancing its relational capital.Design/methodology/approachThe authors adopted an action research approach to analyze the case study. Consistently, the authors followed the analysis, diagnosis, and intervention phases. First, the authors focused on the identification of the strengths and weaknesses of the process through which the university created relational capital, and finally, the authors proposed solutions to improve the process.FindingsThis case study shows that the creation of relation capital for the host university was the result of a process of transfer and transformation of the individual relationships of the observatory’s promoters.Originality/valueThis paper contributes to filling a significant gap in the literature on relational capital and universities and provides useful insights into how these organizations can encourage its creation. It also allows scholars, managers, and politicians involved in higher education to gain a greater understanding of this relevant topic.

Cerebral and gaze data fusion for wheelchair navigation enhancement: case of distracted users

Robotica ◽  
2018 ◽  
Vol 37 (2) ◽  
pp. 246-263 ◽  
Author(s):  
Hachem A. Lamti ◽  
Mohamed Moncef Ben Khelifa ◽  
Vincent Hugel
Keyword(s):  
Neural Network ◽  
Steady State ◽  
Brain Regions ◽  
Experimental Protocol ◽  
Powered Wheelchair ◽  
Set Up ◽  
Individual Use ◽  
The Individual ◽  
New Framework ◽  
Better Than

SUMMARYThe goal of this paper is to present a new hybrid system based on the fusion of gaze data and Steady State Visual Evoked Potentials (SSVEP) not only to command a powered wheelchair, but also to account for users distraction levels (concentrated or distracted). For this purpose, a multi-layer perception neural network was set up in order to combine relevant gazing and blinking features from gaze sequence and brainwave features from occipital and parietal brain regions. The motivation behind this work is the shortages raised from the individual use of gaze-based and SSVEP-based wheelchair command techniques. The proposed framework is based on three main modules: a gaze module to select command and activate the flashing stimuli. An SSVEP module to validate the selected command. In parallel, a distraction level module estimates the intention of the user by mean of behavioral entropy and validates/inhibits the command accordingly. An experimental protocol was set up and the prototype was tested on five paraplegic subjects and compared with standard SSVEP and gaze-based systems. The results showed that the new framework performed better than conventional gaze-based and SSVEP-based systems. Navigation performance was assessed based on navigation time and obstacles collisions.

scholarly journals E‐books from MyiLibrary at the University of Worcester: a case study

2007 ◽  
Vol 41 (3) ◽  
pp. 217-226 ◽  
Author(s):  
Alison Taylor
Keyword(s):  
Technical Problems ◽  
Content Type ◽  
Library Users ◽  
User Access ◽  
Set Up ◽  
The Individual ◽  
The University ◽  
Practical Implications ◽  
Selection Of

PurposeThe purpose of this paper is to describe how an e‐books project was set up at the University of Worcester Information and Learning Services with the aim of improving user access to the range of textbook materials available.Design/methodology/approachDetails of the background and circumstances of the University and the effect of these on the process undertaken by the e‐books project group are described. The selection of an e‐books provider, MyiLibrary, and subsequent ordering, cataloguing and promotion activities are outlined.FindingsThis paper outlines the importance of tailoring the approach to e‐books acquisition to the individual institution. It is found that authentication is a major issue and that for e‐books packages to be successful, technical problems need to be kept to a minimum.Practical implicationsExamples to assist others in setting up e‐books provision are given. Technical difficulties and the range of titles available are both impediments to providing a full e‐books service.Originality/valueE‐books appear to provide greater access and flexibility to library users. Information and Learning Services fully intends to extend the range of e‐books available to students. This paper looks at the practicalities of setting up and expanding such a service.

scholarly journals EMG BASED DIAGNOSIS OF MYOPATHY AND NEUROPATHY USING MACHINE LEARNING TECHNIQUES

2020 ◽  
Vol 4 (4) ◽  
pp. 38-45
Author(s):  
Anisha C. D ◽  
Arulanand N
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Time Domain ◽  
Neuromuscular Disorders ◽  
Bayesian Optimization ◽  
Machine Learning Techniques ◽  
Diagnostic Model ◽  
Learning Techniques ◽  
The Individual ◽  
Better Than

Myopathy and Neuropathy are non-progressive and progressive neuromuscular disorders which weakens the muscles and nerves respectively. Electromyography (EMG) signals are bio signals obtained from the individual muscle cells. EMG based diagnosis for neuromuscular disorders is a safe and reliable method. Integrating the EMG signals with machine learning techniques improves the diagnostic accuracy. The proposed system performs analysis on the clinical raw EMG dataset which is obtained from the publicly available PhysioNet database. The two-channel raw EMG dataset of healthy, myopathy and neuropathy subjects are divided into samples. The Time Domain (TD) features are extracted from divided samples of each subject. The extracted features are annotated with the class label representing the state of the individual. The annotated features split into training and testing set in the standard ratio 70: 30. The comparative classification analysis on the complete annotated features set and prominent features set procured using Pearson correlation technique is performed. The features are scaled using standard scaler technique. The analysis on scaled annotated features set and scaled prominent features set is also implemented. The hyperparameter space of the classifiers are given by trial and error method. The hyperparameters of the classifiers are tuned using Bayesian optimization technique and the optimal parameters are obtained. and are fed to the tuned classifier. The classification algorithms considered in the analysis are Random Forest and Multi-Layer Perceptron Neural Network (MLPNN). The performance evaluation of the classifiers on the test data is computed using the Accuracy, Confusion Matrix, F1 Score, Precision and Recall metrics. The evaluation results of the classifiers states that Random Forest performs better than MLPNN wherein it provides an accuracy of 96 % with non-scaled Time Domain (TD) features and MLPNN outperforms better than Random Forest with an accuracy of 97% on scaled Time Domain (TD) features which is higher than the existing systems. The inferences from the evaluation results is that Bayesian optimization tuned classifiers improves the accuracy which provides a robust diagnostic model for neuromuscular disorder diagnosis.

scholarly journals Evaluation of Ensemble Machines in Breast Cancer Prediction

2020 ◽  
Author(s):  
LeenaNesamani S ◽  
NirmalaSugirthaRajini S
Keyword(s):  
Breast Cancer ◽  
Ensemble Methods ◽  
Machine Learning Techniques ◽  
Prediction System ◽  
Weighted Voting ◽  
Cancer Prediction ◽  
Learning Techniques ◽  
Deadly Disease ◽  
The Individual ◽  
Better Than

Breast cancer is one of the most deadly diseases encountered among women for which the cause is not clearly defined yet. Early diagnosis may help the physicians in the treatment of this deadly disease which could turn out fatal otherwise. Machine Learning techniques are employed in the process of detecting breast cancer with greater accuracy. Individual classifiers employed in this process, predicted the disease with less accuracy when compared with ensemble models. Ensemble methods employ a group of classifiers to individually classify the data. It then combines the result of the individual classifiers using weighted voting of their predictions. Ensemble machines perform better than individual models and show improved levels in the accuracy of the prediction system. This paper examines and evaluates different ensemble machines that are used in the prediction of breast cancer and tries to identify the combinations that prove to be better than the existing ones.

scholarly journals Participatory budgeting as a form of dialogic accounting in Russia

2018 ◽  
Vol 31 (4) ◽  
pp. 1098-1123 ◽  
Author(s):  
Evgenii Aleksandrov ◽  
Anatoli Bourmistrov ◽  
Giuseppe Grossi
Keyword(s):  
Democratic Governance ◽  
Participatory Budgeting ◽  
Structured Interviews ◽  
Institutional Work ◽  
Content Type ◽  
Documentary Analysis ◽  
Set Up ◽  
The Individual ◽  
The Way

Purpose The purpose of this paper is to investigate how participatory budgeting (PB), as a form of dialogic accounting, is produced in practice. Design/methodology/approach This is a qualitative case study of PB development for the period 2013-2016 in one Russian municipality. Based on triangulation of in-depth semi-structured interviews, documentary analysis, videotape data and netnographic observation, the authors employ ideas of dialogic accounting and institutional work. Findings The study shows that the PB experiment, which began with dialogic rhetoric, in reality, had very limited dialogic effects. However, the authors also observed that the PB dynamics over time made the practice neither inherently monologic nor dialogic. The authors explained such transformations by the way in which the individual reflexivity of actors altered when carrying out institutional work. Curiosity reflexivity was the most essential, triggering different patterns of institutional work to set up the PB experiment. However, further, the authors demonstrated that, over the course of the experiment’s development, the institutional work was trapped by various actors’ individual reflexivity forms and in this way limited PB’s dialogic potential. Originality/value The study shows the importance of understanding and managing individuals’ reflexivity, as it shapes the institutional work performed by different actors and, therefore, influences the direction of both the design and materialization of dialogic accounting experiments such as PB. In a broader sense, this also influences the way in which democratic governance is developed, losing democratization potential.

Sign in / Sign up

Export Citation Format

Share Document