A Systematic Review of Movement Tracking for Real‐Time Monitoring of Physical Exercises in the Gym

ABSTRACTRemote photoplethysmography (rPPG) has emerged as a vital technology for remote healthcare, offering non‐invasive and accessible health monitoring through off‐the‐shelf standard video cameras. rPPG facilitates the assessment of key health indicators like heart rate (HR), respiratory rate (RR), and blood oxygen saturation (SpO2) from video data, providing advantages in early disease diagnosis and routine health assessments. Recognizing its potential, researchers from multiple fields have substantially progressed rPPG by establishing a strong theoretical basis for signal acquisition and developing signal processing and data‐driven algorithms for rPPG extraction. While most rPPG reviews primarily focus on HR signal extraction methods, our research provides an overview of the potential scope of rPPG. We systematically organize research on rPPG signal acquisition and extraction techniques and provide a critical review of recent rPPG advancements in diverse health parameter estimation. Besides providing a thorough HR estimation review, we incorporate the extraction of derivative signals such as RR and SpO2 from rPPG data, including their applications and limitations. We also highlight the adaptation of Machine Learning (ML), Deep Learning (DL), and Computer Vision (CV) techniques with rPPG technologies, and accumulate available critical rPPG resources like datasets, codes, and tutorials. Finally, we identify challenges and research gaps, such as motion artifacts, varying lighting conditions, and differences in skin tone. We aim to uplift advancements in rPPG systems by outlining future research directions. Our comprehensive review aims to support the development of robust and safe applications by advancing the field of contactless health parameter sensing.This article is categorized under: Application Areas > Health Care Technologies > Machine Learning Fundamental Concepts of Data and Knowledge > Human Centricity and User Interaction

Motivation – Healthcare are rapidly replacing manual with computerized artefacts for many reasons, but the impact on users of the technology is often assumed to be neutral. Approach – Three presentations of the increasingly more intensive use of computer technology in healthcare will be discussed by panelists and audience to explore the problem space. A closing presentation will highlight issues in designing technology that is both usable and useful to frontline workers. Originality/Value – There is great pressure to speed up the introduction of technology in healthcare, but a “rush to implementation” risks serious design problems. Take away message – Technological artefacts are introduced to meet many needs, but if users’ needs are not taken into account, the technology may founder or be subverted.

Diabetic foot ulcers (DFUs) present a substantial health risk across diverse age groups, creating challenges for healthcare professionals in the accurate classification and grading. DFU plays a crucial role in automated health monitoring and diagnosis systems, where the integration of medical imaging, computer vision, statistical analysis, and gait information is essential for comprehensive understanding and effective management. Diagnosing DFU is imperative, as it plays a major role in the processes of diagnosis, treatment planning, and neuropathy research within automated health monitoring and diagnosis systems. To address this, various machine learning and deep learning‐based methodologies have emerged in the literature to support healthcare practitioners in achieving improved diagnostic analyses for DFU. This survey paper investigates various diagnostic methodologies for DFU, spanning traditional statistical approaches to cutting‐edge deep learning techniques. It systematically reviews key stages involved in diabetic foot ulcer classification (DFUC) methods, including preprocessing, feature extraction, and classification, explaining their benefits and drawbacks. The investigation extends to exploring state‐of‐the‐art convolutional neural network models tailored for DFUC, involving extensive experiments with data augmentation and transfer learning methods. The overview also outlines datasets commonly employed for evaluating DFUC methodologies. Recognizing that neuropathy and reduced blood flow in the lower limbs might be caused by atherosclerotic blood vessels, this paper provides recommendations to researchers and practitioners involved in routine medical therapy to prevent substantial complications. Apart from reviewing prior literature, this survey aims to influence the future of DFU diagnostics by outlining prospective research directions, particularly in the domains of personalized and intelligent healthcare. Finally, this overview is to contribute to the continual evolution of DFU diagnosis in order to provide more effective and customized medical care.This article is categorized under: Application Areas > Health Care Technologies > Machine Learning Technologies > Artificial Intelligence

With the fast integration of artificial intelligence (AI) technologies in healthcare, several aspects of medical practice have undergone considerable change, assuring major improvements in diagnostic, treatment, and operational efficiencies. This review reflects on the key opportunities presented by AI, especially in improving diagnostic precision, optimizing treatment planning, and facilitating personalized medicine on the basis of ever-improving machine learning and deep learning technologies. Such AI-driven tools have shown promising performance in large medical imaging, predictive analytics, and clinical decision support, making informed decisions more viable for clinicians. However, significant challenges must be faced while integrating AI into healthcare facilities. These challenges do not relate simply to data privacy issues, algorithmic bias, or transparency of the decision-making process of AI-driven intelligence. Furthermore, there are scant regulatory frameworks that deal with the adoption of AI in healthcare, with accountability and ethics of use in the line of fire. Therefore, the review has identified that full policy development, ethical guidelines, and regulation are urgently needed to allow for the safe and effective introduction of AI. The future of AI in health is bright, with the emerging trends being AI-enhanced robotic surgery, telemedicine, and remote patient monitoring that are likely to further revolutionize patient care. While much attention has been given to these technologies’ potential for healthcare, the ethical, legal, and operational challenges inherent in AI systems should first be addressed as a foundation for leveraging the full potential of AI technologies in healthcare.

The use of cutting-edge technology has resulted in a significant enhancement in athletic training. Computer vision and motion tracking are very important for enhancing performance, reducing the risk of accidents, and training in general. Some computer vision algorithms investigate how a sportsperson moves when competing or practising. It is possible that coaches who continuously evaluate their players’ posture, muscle activation, and joint angles would have a better understanding of biomechanical efficiency. It is possible to generate performance measurements from the real-time surveillance of athletes while competing in sports. Through the use of computer vision, it is possible to identify acts that might be hazardous. Notifications are given to coaches if there is a deviation in the form of an athlete, which enables them to address the situation as soon as possible. The three variables that these sensors monitor are the direction, speed, and acceleration. Athletes can encounter realistic environments thanks to the integration of motion tracking with virtual reality. One may use the feedback loop to increase their spatial awareness and decision-making ability. Augmented reality allows for enhancing an athlete’s eyesight by providing them with real-time data while practising. Last but not least, the use of computer vision and motion tracking is bringing about a significant improvement in the sporting training process. Through collaborative efforts, researchers, athletes, and coaches can accelerate humans' performance to levels that have never been seen before.

From machine learning to deep learning: Advances of the recent data-driven paradigm shift in medicine and healthcare

Monitoring system framework design for floating wind turbine using the deep learning technology and tower response identification considering sensor optimization

Physical activity for older adults is an important countermeasure to reduce the risk for chronic disease, falls, osteoporosis, depression and dementia while serving to preserve mobility and independence in activities of daily living. Access to structured physical activity and rehabilitation services is hampered by a deficit of licensed physical and occupational therapists, transportation challenges, and proximity to care services, particularly for older adults with disability and those who live in rural settings. Artificially intelligent SAR have the potential to bridge the care access gap by providing home exercise programs that can be tailored and autonomously delivered to older adults. A learning from demonstration algorithm allows therapists to teach robots exercises without computer programming, and computer vision can be used to recognize, quantify, and assess the quality of the exercises performed by older adults in their home, allowing for the identification of movement deficiencies and tracking of progress over time. We will illustrate the process by which therapists can teach robots exercises using AI, how the exercises are encoded and delivered by the robot, a framework for tracking performance, and results of a survey of 110 licensed therapists who were asked to evaluate the potential for robot-led therapy in home settings. We will discuss the emerging potential of SAR as an in-home adjunct therapy to supplement clinical exercise programs as well as the barriers to implementation including the anatomical structure of current robots, ability to provide real-time, physical, corrective feedback, potential loss of human connection, user acceptance and cost.

The increasing demand for sustainable livestock products necessitates a re-evaluation of animal production and breeding practices. Contemporary breeding programs now integrate animal phenotypic behaviors due to their considerable influence on productivity, health, and welfare, which ultimately impact industry yield and economic outcomes. Monitoring animal behavior manually is challenging and subjective, especially in continuous or large-scale operations, as it is time-consuming and labor-intensive. Consequently, computer vision technology has attracted attention for its objectivity, non-invasiveness, and capacity for continuous monitoring. However, recognizing livestock behavior using computer vision remains difficult due to complex scenes and varying conditions, hindering its widespread adoption in the industry. Deep learning technology has emerged as a promising solution, mitigating some of these challenges and enhancing the recognition of livestock behaviors. This paper reviews recent advancements in computer vision methods for detecting behaviors in livestock such as cattle with an emphasis on behaviors critical for health, welfare, and productivity. It investigates the development of both traditional computer vision and deep learning techniques for image segmentation, identification, and behavior recognition. The review explores the development of research trends in livestock behavior recognition, focusing on improvements in reliable identification algorithms, the analysis of behaviors at different growth stages, the measurement of behavioral data, and the design of systems to evaluate welfare, health, growth, and development.

This paper presents a moving-object segmentation algorithm using edge information as segment. The proposed method is developed to address challenges due to variations in ambient lighting and background contents. We investigated the suitability of the proposed algorithm in comparison with the traditional-intensity-based as well as edge-pixel-based detection methods. In our method, edges are extracted from video frames and are represented as segments using an efficiently designed edge class. This representation helps to obtain the geometric information of edge in the case of edge matching and moving-object segmentation; and facilitates incorporating knowledge into edge segment during background modeling and motion tracking. An efficient approach for background initialization and robust method of edge matching is presented, to effectively reduce the risk of false alarm due to illumination change and camera motion while maintaining the high sensitivity to the presence of moving object. Detected moving edges are utilized along with watershed algorithm for extracting video object plane (VOP) with more accurate boundary. Experiment results with real image sequence reflect that the proposed method is suitable for automated video surveillance applications in various monitoring systems.

Visual tracking is a fundamental technology in computer vision, with wide-ranging applications in fields such as robotics, autonomous driving, augmented reality, and security systems. A key challenge in these domains is ensuring stable object tracking in dynamic and complex environments. Tracking objects in real-world settings presents difficulties like occlusion, lighting changes, and sudden object movements, all of which demand the development of robust algorithms that can handle such variability effectively. This research introduces a novel single object visual tracking technique that leverages the YOLO (You Only Look Once) object detection model, combined with an adaptive particle filter. By integrating YOLO's precise object detection capabilities with the continuous state estimation offered by particle filters, this approach achieves stable object tracking, even in challenging environments. At the heart of the proposed algorithm is a dynamic fusion of YOLO detection results with image feature-based particle weight updates. When YOLO successfully detects an object, the position and size data of the object are used to adjust the state and weights of the particles, resulting in improved tracking accuracy and quick recovery from events such as sudden movements or occlusions. Conversely, in situations where YOLO detection is unavailable, the algorithm seamlessly transitions to a pure particle filter mode. In this fallback mode, visual features, such as image color histograms, are used to update particle weights, ensuring continuous and robust tracking even during temporary detection failures. The object’s dynamic state is modeled using an 8-dimensional vector, which includes information about position, velocity, size, and size-change rate. This comprehensive state representation enables precise tracking of various object motions and size transformations. Additionally, a Bhattacharyya distance-based weight calculation method is employed to assess particle similarity more effectively. Experimental results demonstrate that the proposed method excels in various challenging scenarios, including those with sudden object movements, partial occlusions, and lighting variations. The algorithm consistently delivers stable tracking, underscoring its robustness and adaptability. The contributions of this research have potential applications in fields such as autonomous driving, SLAM (Simultaneous Localization and Mapping), and augmented reality. Specifically, this technique could enhance pedestrian and vehicle tracking in autonomous driving systems and improve the accuracy of dynamic object tracking and environmental mapping in SLAM. It is also likely to play a key role in real-world applications like person tracking in security systems, player motion analysis in sports, and focused tracking in medical imaging. Future research directions include expanding the method to handle multi-object tracking and optimizing its real-time performance, broadening its applicability. Additionally, further improvements in tracking accuracy and robustness may be achieved by incorporating deep learning-based feature extraction and integrating data from various sensors.

Robotic simulators are crucial for academic research and education as well as the development of safety-critical applications. Reinforcement learning environments— simple simulations coupled with a problem specification in the form of a reward function—are also important to standardize the development (and benchmarking) of learning algorithms. Yet, full-scale simulators typically lack portability and paral-lelizability. Vice versa, many reinforcement learning environments trade-off realism for high sample throughputs in toy-like problems. While public data sets have greatly benefited deep learning and computer vision, we still lack the software tools to simultaneously develop—and fairly compare—control theory and reinforcement learning approaches. In this paper, we propose an open-source OpenAI Gym-like environment for multiple quadcopters based on the Bullet physics engine. Its multi-agent and vision-based reinforcement learning interfaces, as well as the support of realistic collisions and aerodynamic effects, make it, to the best of our knowledge, a first of its kind. We demonstrate its use through several examples, either for control (trajectory tracking with PID control, multi-robot flight with downwash, etc.) or reinforcement learning (single and multi-agent stabilization tasks), hoping to inspire future research that combines control theory and machine learning.

Imagine yourself, as an ecologist during field work, deep in the woods. Eerily silent was the forest, when loudly from the tree above a wren started to sing. A quick, skilful use of the binoculars showed it was the male ringed last week, but swiftly the bird disappeared again among the leaves. Similar difficulties in reliably observing the behaviour of the study species will be familiar to many ecologists and can strongly affect the choice of the study species; for example, the ethologist and zoologist Nikolaas Tinbergen mentioned ease of observation as a motivation to study seabirds instead of forest birds (Tinbergen, 1939). While certainly smart choices of the study species are key to successful research, typified by the Krogh principle: "for a large number of problems there will be some animal of choice, or a few such animals, on which it can be most conveniently studied" (Krogh, 1929), most terrestrial, aquatic and aerial species cannot be well observed in the field. Technological solutions to record the movements, behaviour and physiology of animals, and associated methodological advancements for analysing the data collected, have revolutionized research in animal ecology and beyond (Brisson-Curadeau, Patterson, Whelan, Lazarus, & Elliott, 2017; Kenward, 2001; Ropert-Coudert, Beaulieu, Hanuise, & Kato, 2009; Ropert-Coudert & Wilson, 2005; Weimerskirch, 2009). The general term for this technological approach to study animals is called Biologging—'the use of miniaturized animal-attached tags for logging and/or relaying data about an animal's movements, behaviour, physiology, and/or environment' (Rutz & Hays, 2009). It is closely related to and comprises the field of Biotelemetry—the remote measurement of the physiological conditions and activity/behavioural state of animals (Cooke et al., 2004), including biomedical applications in humans. The use of electronic loggers and transmitters offers unprecedented opportunities for uncovering the 'hidden lives' of animals and achieve a more mechanistic understanding of their ecology, and indeed the first 'Virtual Issue' (an online collection of papers published on a specific topic) published by the Journal of Animal Ecology was on 'Biotelemetry and Biologging' (Hays, 2008). Progress in this broad field has been exceptional in the last decade (Baratchi, Meratnia, Havinga, Skidmore, & Toxopeus, 2013; Hussey et al., 2015; Kays, Crofoot, Jetz, & Wikelski, 2015; Wilmers et al., 2015; Brisson-Curadeau et al., 2017; Tibbetts, 2017; Harcourt et al., 2019; Lowerre-Barbieri, Kays, Thorson, & Wikelski, 2019), with exciting ongoing developments often occurring outside the field of animal ecology, including in different disciplines such as engineering, physics or computer science. As such, the Journal of Animal Ecology issued an Open Call in 2018 for a Special Feature on 'Biologging', with the aim to showcase the novel developments in the field and the range of ecological questions which can now be addressed. The call resulted in the largest number of submitted manuscripts to any Special Feature in the Journal so far, which is a further indication of the interest in the topic. In this Editorial for the Special Feature, we discuss the papers and topics covered and conclude with a brief outlook on ongoing and future developments. This Special Feature comprises 18 contributions, of which 13 present novel analyses and approaches, three are reviews, one is a meta-analysis and one is a 'How to' paper. Overall, the papers cover a broad range of biologging technologies used to address a variety of fundamental questions in animal ecology, in aquatic, terrestrial and aerial species. Three papers use light-level geolocator tags—miniature light-weight tags which measure ambient light levels to determine sunrise and sunset times, and hence estimate the approximate location of the animal (Bridge et al., 2011; Wilson, Ducamp, Rees, Culik, & Niekamp, 1992)—to investigate the ontogeny of migratory behaviour in a long-lived seabird species (Campioni, Dias, Granadeiro, & Catry, 2020), quantify effects of biologgers on the survival of tagged birds (Brlík et al., 2020) and provide a practical guide for the effective application of geolocator tags to track animals (Lisovski et al., 2020). Seven papers use GPS loggers (for a review of GPS technology, see Tomkiewicz, Fuller, Kie, & Bates, 2010) often combined with other sensor technologies such as accelerometers (see Shepard et al., 2008 for a review of the technology) and/or complementary methods including stable isotopes (see Hobson & Wassenaar, 2008 for information about the method) and behavioural observations (see Altmann, 1974 about observational methods to study animal behaviour). These GPS-based papers investigate predator–prey spatiotemporal interactions among elk Cervus canadensis and wolf Canis lupus (Cusack et al., 2020), quantify foraging niche overlap between sympatric seabird species (Dehnhard et al., 2020), or assess effects of personality on the consistency and repeatability of foraging trips in black-legged kittiwakes Rissa tridactyla (Harris et al., 2020). Other contributions present novel statistical methods to estimate individual variation in habitat selection (Muff, Signer, & Fieberg, 2020) or to identify different movement modes in movement tracks (Patin, Etienne, Lebarbier, Chamaillé-Jammes, & Benhamou, 2020), whereas other studies use fine-scale movement data to quantify the impact of wind turbines on functional habitat loss of a soaring terrestrial bird, the black kite Milvus migrans (Marques et al., 2020), or identify mating tactics of male African elephants Loxodonta africana (Taylor et al., 2020). Seven papers primarily use other biologging sensors, alone or in combination with GPS tags, including inertial measurement unit sensors (see Baratchi et al., 2013 for information on the technology) such as accelerometers (Shepard et al., 2008) and magnetometers (see Williams et al., 2017 for information on magnetometers), or wet–dry and pressure and depth sensors (for a review see Ropert-Coudert et al., 2009), to markedly enhance the quantity of information on animal behaviour, individual state and performance that can be obtained from the tagged animals. In particular, Wilson et al. (2020) critically assesses the use of metrics derived from accelerometers as a proxy for movement-related metabolic energy expenditure, with Benoit et al. (2020) using such metrics to quantify the cost of dispersal in roe deer Capreolus capreolus, and Corbeau, Prudor, Kato, and Weimerskirch (2020) to quantify and compare average energy expenditure during different flight phases (soaring and flapping flight) in juvenile and adult great frigatebirds Fregata minor during their foraging trips, to study the ontogeny of flight and foraging behaviour. Bonnot et al. (2020) use activity sensors in roe deer to disentangle the contrasting effects of predator density and human disturbance on diel activity patterns, whereas Nuijten, Gerrits, Shamoun-Baranes and Nolet (2020) present a new data compression approach for accelerometer data to overcome limitations in storage and energy capacity of loggers and aid data transmission while preserving the behavioural signal in the data. Barkley et al. (2020) develop a novel multi-sensor biologging package, combined with a new statistical modelling approach, to detect and record sub-surface interactions among aquatic animals and ensuing movement-related behavioural responses, and apply it to Greenland sharks Somniosus microcephalus. More generally, Williams et al. (2020) review a large set of biologging sensors and address the question of how to select the most appropriate type or combination of devices for different biological questions. Finally, Joo et al. (2020) review an astonishing number of 58 different R packages which have become available in the last few years for analysing movement and biologging data, to act as a road map for ecologists and software developers. We now describe in more detail the questions and topics addressed by the papers of this Special Feature. We structure this section around the diverse research questions and themes addressed by these article—ranging from topics in Behavioural Ecology, Community Ecology, Statistical Ecology and Functional Ecology, to methodological approaches, with some papers linking multiple research fields. Understanding how behaviour arises is a key question in behavioural ecology. An adaptive behaviour can be informed by genetically controlled (innate) or learned components, but while some seem to be mostly programmed from birth, such as pecking in young domestic chicks (Dawkins, 1968), others, like the chaffinch song, have an innate basis but require the animal to practise and even learn from others (Thorpe, 1958). The scope for learnt behaviours may be particularly important in long-lived species, whose long lifespan increases the opportunity to practise and learn. In fact, the breeding deferral observed in many long-lived species is thought to be driven by high costs of early breeding (Lack, 1968), which could be caused by an incomplete set of skills (Daunt, Afanasyev, Adam, Croxall, & Wanless, 2007). Thanks to ever smaller loggers which can record an animal's behaviour for ever longer periods of time, biologging is now allowing researchers to study with unprecedented detail how behaviours develop in slow-maturing animals. In this Special Feature, two papers push the boundaries of this emerging field and highlight the potential of biologging to advance our understanding of the ontogeny of animal behaviour. Corbeau et al. (2020) demonstrate how juvenile great frigatebirds progressively improve their flight skills in the first few months following their first flight. Combining GPS and accelerometers to distinguish between different flight behaviours (e.g. flapping, gliding, soaring), they show that juveniles' flight skills, initially inferior, improve gradually until becoming comparable to adults'. Interestingly, juveniles outperformed adults in some aspects, likely due to their morphology, and this may explain their remarkable months-long dispersive flights (Weimerskirch, Bishop, Jeanniard-du-Dot, Prudor, & Sachs, 2016). These findings provide one of the first insights into the development of flight in long-lived birds (Rotics et al., 2016; Yoda, Kohno, & Yasuhiko, 2004), and highlight the importance of early-life learning for the acquisition of physical skills. Campioni et al. (2020) focus on another behaviour whose ontogeny is poorly understood: migration. Some animals learn their migration routes by following older conspecifics (Mueller, O'Hara, Converse, Urbanek, & Fagan, 2013), while others follow an innate migratory distance and direction (Liedvogel, Åkesson, & Bensch, 2011). Campioni et al. (2020) provide the first robust evidence for a third mechanism by which long-lived animals may acquire a migratory strategy. In an impressive long-term study tracking the migration of Cory's shearwaters Calonectris borealis across ages, from immatures to established breeders, they show that young birds follow more exploratory routes, and as they aged they gradually advance their migration timings and shorten their migration route. These findings show that learning, memory and experience can play a key role in the development of migration behaviour in long-lived species, and provide support for the exploration-refinement hypothesis (Guilford et al., 2011) as another mechanism for the development of migration behaviour in long-lived animals (Fayet, accepted). Animal movements are fundamentally characterized by facultative switches between distinct movement modes (Fryxell et al., 2008) and many methods have been developed to identify and segment movement paths into different behavioural sections (Barraquand & Benhamou, 2008; Beyer, Morales, Murray, & Fortin, 2013; Edelhoff, Signer, & Balkenhol, 2016; Gurarie et al., 2015; Leos-Barajas et al., 2017; Michelot & Blackwell, 2019; Wang, 2019), where issues of scale and the difference between stationary and non-stationary movements are of particular importance (Benhamou, 2014). Here, Patin et al. (2020) contribute to this growing literature by extending the K-segmentation approach of Lavielle (2005) to identify breakpoints in time-series of biologging data (or more generally any multivariate time-series) and potentially categorize resulting segments into common groups based on similarities in data characteristics. This provides a viable alternative to established but often statistically complicated methods (e.g. Hidden Markov models, HMMs) for identifying "behavioural states" across time-series data. Indeed, the authors contend that in some circumstances such segmentation can actually outperform these increasingly popular yet more complex methods, and through application to both fine- and broad-scale biologging data (and through simulation) they demonstrate that their approach is scale-insensitive and may be applied to many ecologically relevant questions. An alternative to using statistical segmentation methods to identify different movement modes is to observe the behaviour and state of tagged individuals, annotate the movement paths with the observed behaviour or state time-series, derive from the annotated time-series a set of criteria to distinguish different individual states or behaviour modes from the characteristics of the movement path alone, and use these rules to identify changes in state or movement mode from tagged animals which had not been also visually monitored. To do so, Taylor et al. (2020) employ a novel use of HMMs, to identify different types of sexual behaviour in male African savanna elephants Loxodonta africana as a function of their movement. The study shows that the activity and home range of elephants vary with male reproductive status and age and as such offer an exceptional opportunity to reliably estimate fitness metrics from movement itself. The authors further discuss the implications for the conservation and management of elephants, as well as the opportunities of long-term biologging of individuals for linking movement to life-history trade-offs. While an increasing body of research has shown the impact of consistent individual differences in behavioural phenotypes, called animal personalities or behavioural syndromes (Réale et al., 2010; Sih, Bell, Johnson, & Ziemba, 2004), on foraging behaviour, exploratory movements and other spatial behaviours (Bijleveld et al., 2014; Boon, Réale, & Boutin, 2008; Minderman et al., 2010; van Overveld & Matthysen, 2010; Villegas-Ríos, Réale, Freitas, Moland, & Olsen, 2018; Wilson & McLaughlin, 2007), the important relationship between animal personality and foraging site fidelity has not been studied yet. Here, in Harris et al. (2020) GPS tagged over 100 breeding kittiwakes Rissa tridactyla across four colonies in Svalbard and used a robust type of novel object tests to measure the personality (especially, boldness) of the tagged individuals, HMMs to identify the foraging sites at sea, and also quantified the repeatability of foraging trips. Their results show that individual differences in site fidelity can be driven by differences in individual personality, with bolder birds showing more repeatable foraging trips and a higher degree of site fidelity during the chick incubation stage. This has important implications for studies on individual differences in foraging behaviour and movements, indicating that in addition to age and sex or environmental drivers, also personality differences such as boldness will need to be considered. A key aim of movement ecology research is to quantify and predict habitat/resource selection by animals (Arthur, Manly, McDonald, & Garner, 1996; Christ, Hoef, & Zimmerman, 2008; Johnson, 1980; Matthiopoulos et al., 2015; Moorcroft & Barnett, 2008; Rhodes, McAlpine, Lunney, & individual movements to the of habitat selection and use at & 2008; Johnson, 1980; Moorcroft & and differences in habitat use between individuals may be caused by differences in the individual state (Bijleveld et al., or the et al., 2008). individual differences in behaviour is a key focus of ecological research et al., and for selection have as early as et al. and and occurring more for example, et al. and et al. solutions for these solutions for selection et al., or selection analyses & 2016). et al. (2020) this and present new statistical methods to estimate individual variation in habitat The approach from the between and have been as a which used in to a set of available and the more understanding that selection and are a Johnson, & Morales, The authors on this relationship between and and develop an approach based on to estimate for and habitat selection for individuals and using both and approaches, and the approach using and This methodological advance a new for and habitat selection studies and researchers to estimate individual an unprecedented opportunity to questions of differences in the spatial ecology of habitat and the habitat used by animals is also critically important for applied questions. the growing need for energy and the on will over habitat tracking movement analyses and environmental et al. (2020) showed that soaring black turbines during migration. a loss of to of habitat for these the authors highlight that the of wind turbines is and to that soaring A fundamental of the movement ecology is that the interactions between individual conditions and the characteristics and of the the structure and of movement paths et al., 2008). Thanks to the in biologging technology, there has been a in the movements and behaviour or survival of multiple individuals from species. Here, et al. (2020) use a large tracking GPS and wet–dry sensors, to investigate and niche overlap in three breeding and closely related species of stable to investigate GPS data and to identify foraging in the tracking data. a high degree of and overlap in foraging in both incubation and with niche and individual of foraging location or The study provides novel evidence that foraging may be in even from and a contrasting to niche by by other seabirds et al., 2019; & et al. (2020) combined movement and data from a predator–prey and in the investigate the question how use can a set of data, combined with a the three common in the of of robust and obtained at spatiotemporal authors show an of of to Bonnot et al. (2020) also of predator on the authors use activity sensor and accelerometer data from GPS that to from the on of roe to at changes in activity in to disturbance and predator both by human and deer in by their in to human with the human and this is when with human the in roe deer activity a when to the of a how human may with predator–prey More generally, the is also an of how technological in biologging may also researchers to large through a biologging Finally, biologging provides new opportunities to interactions for and species. Barkley et al. (2020) demonstrate this by and a novel multi-sensor biologging of a combined and a with a accelerometer and a a to the at and on a the Greenland This is to an both and statistical methods to estimate the of animal interactions based on characteristics and of between tagged The authors use these sensors to assess behavioural changes in and depth during and following and they discuss how this may be and applied to many species, with exciting potential for future energy of animals are mostly by the of and obtained from & the and energy of the foraging behaviour and habitat use of animals et al., these research has the to overcome complex to data on and energy in animals et al., 2016). of the in the is the observations to estimate energy Here, Wilson et al. (2020) this by critically the use of metrics derived from accelerometers as a proxy for movement-related metabolic energy biologging Benoit et al. (2020) to quantify energy expenditure, body and distance as a proxy for applied to the costs of To that or to that is a fundamental question in how we animal movement with implications for and mating & 2009). roe Benoit et al. (2020) that the of dispersal is markedly more that these energy costs become more in by and that these costs are primarily at so many behavioural are between energy and energy biologging quantify and these Corbeau et al. (2020) GPS with of and to identify different flight behaviours (e.g. in great frigatebirds and quantify energy expenditure during This to compare the flapping and of soaring or between age and to the hypothesis that juvenile birds have flight skills but that they learn how to improve their skills over (see also above in the Behavioural Ecology is a general that biologging has our understanding of and species & Wilson, 2005; Wilmers et al., It is also that the of biologgers to animals & Wilson, Wilson & for including the location of the devices on the body and their (e.g. and few studies the behavioural to (e.g. & 2019; et al., 2017; et al., Williams et al. (2020) discuss how many of these have not been addressed yet. In particular, the authors highlight the need for more information on physical (e.g. to the and long-term effects for animals. potential this a from et al. (2020) that meta-analysis to review the literature to effects of geolocator on bird species. Their findings that the may to a potential on the survival of tagged Overall, both are consistent with their on the of and to to the application of biologging technologies to ecological research is the management of the devices and of the of data they It is not for a to not of observations on a et al., which storage both the during data collection and in data These are by to animal such that do not affect the animal the of resulting data. are such issues covered in great detail in the ecological and a of this Special Feature is in and for Here, et al. (2020) provide a practical on the effective use of and how resulting data be and for This multiple online in an the complex of linking to the authors also provide data and to of geolocator studies and common data to data and between which may this body of data strongly common data for such to the data storage and transmission of biologgers methods to and the data and the data et al., 2018; & 2019), or the use of to the sensors to record data when the animals the behaviour of interest et al., Here, et al. (2020) present a new data compression approach for accelerometer data to storage capacity and for the data while the data from tagged the authors compare the information from of accelerometer data and from in a in data and energy use while the in behaviour and The in use and storage can hence be used to or to the and a more of the of tagged the use of biologging sensors, a of the characteristics of the many different sensors Interestingly, in the to the on and & the the need to researchers from contrasting development of ever more is among between at some of is this more between and and yet with a it can be years the importance of is as important as ever to of the opportunities by the biologging as Williams et al. (2020) highlight in a review of the field in this Special Feature. the authors identify four sensors, data and and it into an biologging to aid for ecologists to the use of biologging technologies for ecological questions. on the the authors also address in detail the yet question of how to biological questions with the most appropriate type and combination of biologging sensors, as well as how to the and how to and complex biologging data, and conclude with an outlook of the most future developments for the use of Finally, as the and of movement and environmental data has so has the number of statistical and methods to movement data, as well as the number of software packages for movement researchers are not of the number and of software packages available for movement often the to select the most appropriate and software for the question addressed. Here, Joo et al. (2020) provide the first of the field and review a 58 different packages available for analysing movement and biologging data in the R the authors first set a for the of tracking data, identifying three key which they use to the software packages by the package, including the of the available the authors use to assess the between the and development of the and provide a road map for ecologists and software to the most appropriate for a research question and improve the of software the the movements and behaviour of most animal species cannot be studied using or not over technological smaller sensors, smaller novel and methods and their to their be to advance research in animal ecology and will be through These could to insights into a range of research for of in (e.g. et al., 2011; et al., et al., of the and of species & a understanding of the terrestrial and aquatic species in and their (Cooke et al., and the effects of and environmental in habitat foraging behaviour and acquisition in individuals and their et al., ongoing developments the of GPS but also the development of alternative that smaller tracking devices et al., 2009; & 2019; & and biologgers with sensors to measure the impact of devices on tagged animals, and novel for and remote transmission of data et al., 2020). a of the and of movement ecology, combined with methods, will be to of the and complex types and of data now by biologging will be key to achieve future ecologists will also need to to the and to and the and in data and and and and statistical The papers in this Special Feature an exciting set of the and methodological which can be and an of how more may yet be with biologging We hence that by the conservation and management has the capacity to ecology as as and GPS years It is our that this Special Feature the many insights by the application of biologging to animal ecology and the of to for their

IoT is quickly becoming a leading technology in healthcare. Early detection of health problems and preset protocols after patient recovery are all employed to decrease the chance of COVID-19 spreading to others in the event of COVID-19. Such wireless positioning devices can correctly remind individuals to maintain distance by sensing between people and then warning them if the people are close to each other. Motivated by this notion, in this paper we have proposed and implemented a model of the social distance assessment, monitoring, and marker system for prevention. The goal is to minimize the effects of the coronavirus outbreak while generating the least amount of economic harm possible, as well as to enable or even impose social distance. In the Monitoring System, users can easily access a web-based application that is integrated with the detection system by following the integration with the Raspberry Pi 4 and Pi Camera, in which they can monitor the detection of safe and unsafe people. Meanwhile, the marker system that is based on a laser will guide the user to stand in safer locations with the help of a laser marker module to eliminate violations. The proposed system is implemented using OPEN CV and Mobile NET SSD for object detection and uses the Euclidean Distance measurement method for measuring the distance between people. The hardware and software integration is also included in the system with an accuracy level, the system is an effective, low-cost, and user-friendly social spacing tool for preserving distance around people at a large gatherings.

Machine learning in anaesthesia: reactive, proactive… predictive!