This paper addresses the problem of single-target tracker performance evaluation. We consider the performance measures, the dataset and the evaluation system to be the most important components of ...tracker evaluation and propose requirements for each of them. The requirements are the basis of a new evaluation methodology that aims at a simple and easily interpretable tracker comparison. The ranking-based methodology addresses tracker equivalence in terms of statistical significance and practical differences. A fully-annotated dataset with per-frame annotations with several visual attributes is introduced. The diversity of its visual properties is maximized in a novel way by clustering a large number of videos according to their visual attributes. This makes it the most sophistically constructed and annotated dataset to date. A multi-platform evaluation system allowing easy integration of third-party trackers is presented as well. The proposed evaluation methodology was tested on the VOT2014 challenge on the new dataset and 38 trackers, making it the largest benchmark to date. Most of the tested trackers are indeed state-of-the-art since they outperform the standard baselines, resulting in a highly-challenging benchmark. An exhaustive analysis of the dataset from the perspective of tracking difficulty is carried out. To facilitate tracker comparison a new performance visualization technique is proposed.
PURPOSEConsumer-based physical activity (PA) monitors are popular for individual tracking of PA variables. However, current research has not examined how these monitors track energy expenditure (EE) ...and steps in distinct activities. This study examined the accuracy of the Fitbits One, Zip, and Flex and Jawbone UP24 for estimating EE and steps for specific activities and activity categories.
METHODSThirty subjects completed a structured protocol consisting of three sedentary, four household, and four ambulatory/exercise activities. All subjects began by lying on a bed for 10 min; 10 other activities were performed for 5 min each. Indirect calorimetry (COSMED) and researcher-counted steps were criterion measures for EE and step counts, respectively. The Omron HJ-720IT pedometer was used as a comparison of step count accuracy. EE and steps were compared with criterion measures using the Friedman repeated-measures nonparametric test and mean absolute percent error (MAPE).
RESULTSAll PA monitors predicted EE within 8% of COSMED for sedentary activity but overestimated EE by 16%–40% during ambulatory activity. All monitors except the Fitbit Flex (within 8% of criterion) underestimated EE by 27%–34% during household activity. EE predictions were accompanied with MAPE >10%. For household activity, the Fitbit Flex estimated steps within 10% of researcher-counted steps; all other monitors underestimated steps by 35%–64%. All monitors estimated steps within 4% of researcher-counted steps and displayed MAPE <10% during ambulatory activity. The Omron underestimated household steps by 74% but was within 1% for ambulatory steps. All monitors severely underestimated EE and steps during cycling.
CONCLUSIONConsumer-based PA monitors should be used cautiously for estimating EE, although they provide accurate measures of steps for structured ambulatory activity, similar to validated pedometers.
•Comparative data reveals 5.95–57.4% efficiency range across 14 solar tracker groups.•Encoder-based control systems offer superior reliability and performance in tracking the Sun.•Solar trackers ...increase efficiency by 15% to 67.65% compared to stationary PV systems.•An algorithm for selecting a solar tracker has been developed for designing photovoltaic systems.•Recommendations for improving solar trackers are provided.
Implementing solar tracking systems is a crucial approach to enhance solar panel efficiency amid the energy crisis and renewable energy transition. This article explores diverse solar tracking methods and designs, highlighting variations in efficiency, geographical locations, climatic conditions, complexity, and cost. This article reviews solar trackers based on scientific literature, assessing factors as country of research, designs, tracking methods, and efficiency. Findings indicate that single-axis solar trackers employing astronomical calculations with navigation sensors outperform stationary installations by over 57.4%. Additionally, dual-axis solar trackers utilizing trajectory calculations with navigation sensors yield 67.65% more energy. The study emphasizes the impact of design, location, and climate on tracking efficiency. The article proposes a classification table developed for an objective assessment of the efficiency of various types of solar trackers depending on the available equipment, climatic conditions, energy consumption, and prevalence in world practice. An evaluation analysis was carried out using the developed criteria, which allows researchers and engineers to select the most suitable solar tracker for specific conditions and requirements. In addition, the work presents recommendations for improving solar tracking systems, which contribute to the further development and improvement of solar tracking systems.
Solar energy is the cleanest and most abundant form of energy that can be obtained from the Sun. Solar panels convert this energy to generate solar power, which can be used for various electrical ...purposes, particularly in rural areas. Maximum solar power can be generated only when the Sun is perpendicular to the panel, which can be achieved only for a few hours when using a fixed solar panel system, hence the development of an automatic solar tracking system. Over the years, different solar tracking systems have been proposed and developed, and a few have been reviewed in the literature. However, the existing review works have not adequately provided a comprehensive survey and taxonomies of these solar tracking systems to show the trends and possible further research direction. This paper aims to bridge these gaps by extensively reviewing these time-based solar tracking systems based on axis rotation and drive types. Lessons learned from the comprehensive review have been highlighted and discussed. Finally, critical open research issues are identified and elaborated.
Although designed as a consumer product to help motivate individuals to be physically active, Fitbit activity trackers are becoming increasingly popular as measurement tools in physical activity and ...health promotion research and are also commonly used to inform health care decisions.
The objective of this review was to systematically evaluate and report measurement accuracy for Fitbit activity trackers in controlled and free-living settings.
We conducted electronic searches using PubMed, EMBASE, CINAHL, and SPORTDiscus databases with a supplementary Google Scholar search. We considered original research published in English comparing Fitbit versus a reference- or research-standard criterion in healthy adults and those living with any health condition or disability. We assessed risk of bias using a modification of the Consensus-Based Standards for the Selection of Health Status Measurement Instruments. We explored measurement accuracy for steps, energy expenditure, sleep, time in activity, and distance using group percentage differences as the common rubric for error comparisons. We conducted descriptive analyses for frequency of accuracy comparisons within a ±3% error in controlled and ±10% error in free-living settings and assessed for potential bias of over- or underestimation. We secondarily explored how variations in body placement, ambulation speed, or type of activity influenced accuracy.
We included 67 studies. Consistent evidence indicated that Fitbit devices were likely to meet acceptable accuracy for step count approximately half the time, with a tendency to underestimate steps in controlled testing and overestimate steps in free-living settings. Findings also suggested a greater tendency to provide accurate measures for steps during normal or self-paced walking with torso placement, during jogging with wrist placement, and during slow or very slow walking with ankle placement in adults with no mobility limitations. Consistent evidence indicated that Fitbit devices were unlikely to provide accurate measures for energy expenditure in any testing condition. Evidence from a few studies also suggested that, compared with research-grade accelerometers, Fitbit devices may provide similar measures for time in bed and time sleeping, while likely markedly overestimating time spent in higher-intensity activities and underestimating distance during faster-paced ambulation. However, further accuracy studies are warranted. Our point estimations for mean or median percentage error gave equal weighting to all accuracy comparisons, possibly misrepresenting the true point estimate for measurement bias for some of the testing conditions we examined.
Other than for measures of steps in adults with no limitations in mobility, discretion should be used when considering the use of Fitbit devices as an outcome measurement tool in research or to inform health care decisions, as there are seemingly a limited number of situations where the device is likely to provide accurate measurement.
SARS-CoV-2 has significantly mutated its genome during the past 3 years, leading to the periodic emergence of several variants. Some of the variants possess enhanced fitness advantage, ...transmissibility, and pathogenicity and can also reduce vaccine efficacy. Thus, it is important to track the viral evolution to prevent and protect the mankind from SARS-CoV-2 infection. To this end, an interactive web-GUI platform, namely, CoVe-tracker (SARS-CoV-2 evolution tracker), is developed to track its pan proteome evolutionary dynamics (https://project.iith.ac.in/cove-tracker/). CoVe-tracker provides an opportunity for the user to fetch the country-wise and protein-wise amino acid mutations (currently, 44139) of SARS-CoV-2 and their month-wise distribution. It also provides position-wise evolution observed in the SARS-CoV-2 proteome. Importantly, CoVe-tracker provides month- and country-wise distributions of 2065 phylogenetic assignment of named global outbreak (PANGO) lineages and their 177564 variants. It further provides periodic updates on SARS-CoV-2 variant(s) evolution. CoVe-tracker provides the results in a user-friendly interactive fashion by projecting the results onto the world map (for country-wise distribution) and protein 3D structure (for protein-wise mutation). The application of CoVe-tracker in tracking the closest cousin(s) of a variant is demonstrated by considering BA.4 and BA.5 PANGO lineages as test cases. Thus, CoVe-tracker would be useful in the quick surveillance of newly emerging mutations/variants/lineages to facilitate the understanding of viral evolution, transmission, and disease epidemiology.
The similar distractor problem is one of the most difficult challenges for Siamese-based trackers. Since they formulate the visual tracking task as a similar matching problem, these trackers involve ...an essential problem that they are sensitive to the intra-class and inter-class instances with similar appearance confusion. To solve the problem, we propose an object discriminability re-extraction network (ODR-Net) for distractor-aware visual object tracking. The network first mines similar distractors from existing tracking information with a distractor capture module, and then re-extracts discriminative features to redetect the target from distractors with a discriminative feature re-extraction module. It solves the distractor problem in the decoding phase of a tracker and can be considered as a general block that applied to existing Siamese trackers to tackle the similar distractor problem. To demonstrate the effectiveness of the proposed method, extensive experiments and comparisons with state-of-the-art trackers are conducted on a variety of large-scale benchmark datasets, including GOT-10k, LaSOT, OTB-2015, TrackingNet, VOT2020, VOT2021, and VOT2022. Without bells and whistles, our ODR-Net achieves leading performance with a real-time speed.
•ODR-Net re-extracts features to distinguish targets from distractors.•Integrates seamlessly into existing Siamese trackers without retraining.•Simple yet effective, ODR-Net activates when similar distractors appear.
Solar photovoltaic technology has been adopted by various global PV markets with 227 GW cumulative globally installed PV capacity in 2015 replacing the conventional fossil fuel energy resources. ...However, efficiency is still a big challenge for researchers and PV industry. This paper proposes a solar tracker and modified Perturb and Observe (P&O) algorithm for the standalone solar photo-voltaic system. Proposed algorithm confines the search space of the power curve to 10% area that contains Maximum Power Point (MPP) and starts perturbation and observation within that limited search space. The proposed P&O algorithm was simulated in MATLAB/Simulink. Solar tracker makes sure the availability of uniform and maximum irradiance to the solar module throughout the course of the sun during the day. Confinement of the algorithm’s search space lessened the response time to the changing weather conditions that in return decreases the steady-state oscillations at the MPP. Integration of the solar tracker and improved P&O MPPT algorithm provided the better quality and conditioned electricity to the load. The proposed system was experimentally steered whose results verified the effectiveness of the proposed P&O algorithm.
Children and adolescents do not meet the current recommendations on physical activity (PA), and as such, the health-related benefits of regular PA are not achieved. Nowadays, technology-based ...programs represent an appealing and promising option for children and adolescents to promote PA.
The aim of this review was to systematically evaluate the effects of mobile health (mHealth) and wearable activity trackers on PA-related outcomes in this target group.
Electronic databases such as the Cochrane Central Register of Controlled Trials, PubMed, Scopus, SPORTDiscus, and Web of Science were searched to retrieve English language articles published in peer-reviewed journals from January 2012 to June 2018. Those included were articles that contained descriptions of interventions designed to increase PA among children (aged 6 to 12 years) only, or adolescents (aged 13 to 18 years) only, or articles that include both populations, and also, articles that measured at least 1 PA-related cognitive, psychosocial, or behavioral outcome. The interventions had to be based on mHealth tools (mobile phones, smartphones, tablets, or mobile apps) or wearable activity trackers. Randomized controlled trials (RCTs) and non-RCTs, cohort studies, before-and-after studies, and cross-sectional studies were considered, but only controlled studies with a PA comparison between groups were assessed for methodological quality.
In total, 857 articles were identified. Finally, 7 studies (5 with tools of mHealth and 2 with wearable activity trackers) met the inclusion criteria. All studies with tools of mHealth used an RCT design, and 3 were of high methodological quality. Intervention delivery ranged from 4 weeks to 12 months, whereby mainly smartphone apps were used as a tool. Intervention delivery in studies with wearable activity trackers covered a period from 22 sessions during school recess and 8 weeks. Trackers were used as an intervention and evaluation tool. No evidence was found for the effect of mHealth tools, respectively wearable activity trackers, on PA-related outcomes.
Given the small number of studies, poor compliance with accelerometers as a measuring instrument for PA, risk of bias, missing RCTs in relation to wearable activity trackers, and the heterogeneity of intervention programs, caution is warranted regarding the comparability of the studies and their effects. There is a clear need for future studies to develop PA interventions grounded on intervention mapping with a high methodological study design for specific target groups to achieve meaningful evidence.
PDF
