The huge number of images shared on the Web makes effective cataloguing methods for efficient storage and retrieval procedures specifically tailored on the end-user needs a very demanding and crucial issue. In this paper, we investigate the applicability of Automatic Image Annotation (AIA) for image tagging with a focus on the needs of database expansion for a news broadcasting company. First, we determine the feasibility of using AIA in such a context with the aim of minimizing an extensive retraining whenever a new tag needs to be incorporated in the tag set population. Then, an image annotation tool integrating a Convolutional Neural Network model (AlexNet) for feature extraction and a K-Nearest-Neighbours classifier for tag assignment to images is introduced and tested. The obtained performances are very promising addressing the proposed approach as valuable to tackle the problem of image tagging in the framework of a broadcasting company, whilst not yet optimal for integration in the business process.
DOCUMENT
Background Wheelchair tennis, a globally popular sport, features a professional tour spanning 40 countries and over 160 tournaments. Despite its widespread appeal, information about the physical demands of wheelchair tennis is scattered across various studies, necessitating a comprehensive systematic review to synthesise available data. Objective The aim was to provide a detailed synthesis of the physical demands associated with wheelchair tennis, encompassing diverse factors such as court surfaces, performance levels, sport classes, and sexes. Methods We conducted comprehensive searches in the PubMed, Embase, CINAHL, and SPORTDiscus databases, covering articles from inception to March 1, 2023. Forward and backward citation tracking from the included articles was carried out using Scopus, and we established eligibility criteria following the Population, Exposure, Comparison, Outcome, and Study design (PECOS) framework. Our study focused on wheelchair tennis players participating at regional, national, or international levels, including both juniors and adults, and open and quad players. We analysed singles and doubles matches and considered sex (male, female), sport class (open, quad), and court surface type (hard, clay, grass) as key comparative points. The outcomes of interest encompassed play duration, on-court movement, stroke performance, and physiological match variables. The selected study designs included observational cross-sectional, longitudinal, and intervention studies (baseline data only). We calculated pooled means or mean differences with 95% confidence intervals (CIs) and employed a random-effects meta-analysis with robust variance estimation. We assessed heterogeneity using Cochrane Q and 95% prediction intervals. Results Our literature search retrieved 643 records, with 24 articles meeting our inclusion criteria. Most available information focused on international male wheelchair tennis players in the open division, primarily competing in singles on hard courts. Key findings (mean [95% CI]) for these players on hard courts were match duration 65.9 min [55.0–78.8], set duration 35.0 min [28.2–43.5], game duration 4.6 min [0.92–23.3], rally duration 6.1 s [3.7–10.2], effective playing time 19.8% [18.9–20.7], and work-to-rest ratio 1:4.1 [1:3.7–1:4.4]. Insufficient data were available to analyse play duration for female players. However, for the available data on hard court matches, the average set duration was 34.8 min [32.5–37.2]. International male players on hard court covered an average distance per match of 3859 m [1917–7768], with mean and peak average forward speeds of 1.06 m/s [0.85–1.32] and 3.55 m/s [2.92–4.31], respectively. These players executed an average of 365.9 [317.2–422.1] strokes per match, 200.6 [134.7–299.0] per set, 25.4 [16.7–38.7] per game, and 3.4 [2.6–4.6] per rally. Insufficient data were available for a meta-analysis of female players’ on-court movement and stroke performance. The average and peak heart rates of international male players on hard court were 134.3 [124.2–145.1] and 166.0 [132.7–207.6] beats per minute, and the average match heart rate expressed as a percentage of peak heart rate was 74.7% [46.4–100]. We found no studies concerning regional players or juniors, and only one study on doubles match play. Conclusions While we present a comprehensive overview of the physical demands of wheelchair tennis, our understanding predominantly centres around international male players competing on hard courts in the open division. To attain a more comprehensive insight into the sport’s physical requirements, future research should prioritise the inclusion of data on female and quad players, juniors, doubles, and matches played on clay and grass court surfaces. Such endeavours will facilitate the development of more tailored and effective training programmes for wheelchair tennis players and coaches.
DOCUMENT
A formal description of a database consists of the description of the relations (tables) of the database together with the constraints that must hold on the database. Furthermore the contents of a database can be retrieved using queries. These constraints and queries for databases can very well be formalized. A formal description of a constraint or a query is necessary to describe the constraint or query unambiguously. In other words, a formal description leads to one and only one meaning of the constraint or query. To describe constraints and queries in a formal way we use predicate logic, set theory and tuple relational calculus. The tuple relational calculus is a calculus based on the use of tuple variables. A tuple variable is a variable that ranges over a named relation (i.e. a set of tuples of a relation). This paper describes the use of the relational calculus for databases. A description of the formal notation is given as well as a mapping of these expressions to SQL.
DOCUMENT
Substitution is an essential tool for a coach to influence the match. Factors like the injury of a player, required tactical changes, or underperformance of a player initiates substitutions. This study aims to predict the physical performance of individual players in an early phase of the match to provide additional information to the coach for his decision on substitutions. Tracking data of individual players, except for goalkeepers, from 302 elite soccer matches of the Dutch ‘Eredivisie’ 2018–2019 season were used to enable the prediction of the individual physical performance. The players’ physical performance is expressed in the variables distance covered, distance in speed category, and energy expenditure in power category. The individualized normalized variables were used to build machine learning models that predict whether players will achieve 100%, 95%, or 90% of their average physical performance in a match. The tree-based algorithms Random Forest and Decision Tree were applied to build the models. A simple Naïve Bayes algorithm was used as the baseline model to support the superiority of the tree-based algorithms. The machine learning technique Random Forest combined with the variable energy expenditure in the power category was the most precise. The combination of Random Forest and energy expenditure in the power category resulted in precision in predicting performance and underperformance after 15 min in a match, and the values were 0.91, 0.88, and 0.92 for the thresholds 100%, 95%, and 90%, respectively. To conclude, it is possible to predict the physical performance of individual players in an early phase of the match. These findings offer opportunities to support coaches in making more informed decisions on player substitutions in elite soccer.
DOCUMENT
New technologies will allow Crime Scene Investigators (CSIs) in the near future to analyse traces at the crime scene and receive identification information while still conducting the investigation. These developments could have considerable effects on the way an investigation is conducted. CSIs may start reasoning based on possible database-matches which could influence scenario formation (i.e. the construction of narratives that explain the observed traces) during very early phases of the investigation. The goal of this study is to gain more insight into the influence of the rapid identification information on the reconstruction of the crime and the evaluation of traces by addressing two questions, namely 1) is scenario formation influenced from the moment that ID information is provided and 2) do database matches influence the evaluation of traces and the reconstruction of the crime. We asked 48 CSIs from England to investigate a potential murder crime scene on a computer. Our findings show that the interpretation of the crime scene by CSIs is affected by the moment identification information is provided. This information has a higher influence on scenario formation when provided after an initial scenario has been formed. Also, CSIs seem to attach great value to traces that produce matches with databases and hence yield a name of a known person. Similar traces that did not provide matches were considered less important. We question whether this kind of selective attention is desirable as it may cause ignorance of other relevant information at the crime scene.
DOCUMENT
Mobiele identificatietechnieken maken het in de nabije toekomst mogelijk DNA- en vingersporen tijdens een lopend forensisch sporenonderzoek snel te analyseren, te vergelijken met referentiemonsters, en de resultaten hiervan te gebruiken in het verdere onderzoek. In dit experimentele onderzoek werd de invloed onderzocht van deze snelle analyseresultaten op de scenariovorming, en van de databankidentificaties in deze resultaten op de interpretatie van sporen door forensisch rechercheurs in Nederland. Forensisch rechercheurs (N = 65) voerden een gesimuleerd plaats delict onderzoek uit. Hierbij werden zowel de analyseresultaten als het moment waarop deze werden verstrekt gemanipuleerd. De resultaten laten zien dat snelle analyseresultaten de scenariovorming van rechercheurs beïnvloeden, en dat deze invloed afhankelijk is van het moment van de informatieverstrekking. Oordelen van rechercheurs over het belang van de sporen blijken niet door databankidentificaties te worden beïnvloed.
DOCUMENT
In recent years, there has been an exponential increase in the use of health and sports-related smartphone applications (apps). This is also reflected in App-stores, which are stacked with thousands of health- and sports-apps, with new apps launched each day. These apps have great potential to monitor and support people’s physical activity and health. For users, however, it is difficult to know which app suits their needs. In this paper, we present an online tool that supports the decision-making process for choosing an appropriate app. We constructed and validated a screening instrument to assess app content quality, together with the assessment of users’ needs. Both served as input for building the tool through various iterations with prototypes and user tests. This resulted in an online tool which relies on app content quality scores to match the users’ needs with apps that score high in the screening instrument on those particular needs. Users can add new apps to the database via the screening instrument, making the tool self-supportive and future proof. A feedback loop allows users to give feedback on the recommended app and how well it meets their needs. This feedback is added to the database and used in future filtering and recommendations. The principles used can be applied to other areas of sports, physical activity and health to help users to select an app that suits their needs. Potentially increasing the long-term use of apps to monitor and to support physical activity and health.
DOCUMENT
Background: Due to demographic transitions and budget restraints, it is now necessary to search for comprehensive new strategies, in order to constitute a sustainable healthcare system. Recently, various online care platforms for community-dwelling older adults were introduced in several European countries. These platforms have aimed at solidifying social cohesion in the community, so as to support the older adults in coordinating or managing their care and to enhance the self-reliance of these older adults. Consequently, these platforms might contribute to a more sustainable healthcare system. The main research question of this study was twofold: Which online care platforms for older adults are available in the Netherlands and what are their characteristics? Methods: The researchers have performed a scoping review of the online care platforms in the Netherlands, according to the six steps of Arksey & O’Malley (2005), which were as follows: (1) Identifying the research question; (2) Identifying any relevant studies; (3) Selecting the studies; (4) Charting the data; (5) Collating, summarising and reporting on the results; together with (6) consultations with the relevant stakeholders. The study searched for evidence in online scientific databases (Phase 1) and on the Internet (Phase 2). The relevant studies that were published between February 2012 and October 2017 were included. Results: The review resulted in an overview of 21 care platforms, for which 3 types were identified: (1) Community Care Platforms; (2) Care Network Platforms; and (3) System Integrator Platforms. Conclusion: This typology of platforms can guide users – for instance, older adults, care professionals, informal caregivers and municipalities, in choosing a suitable care platform, i.e. the typology gives users insight into the functionalities, goals and target groups which allows them to choose a platform that matches their needs. As far as the authors know, no studies have previously reported on the effects of the online care platforms for older adults in the Netherlands, so further research is required on their impacts and on their benefits.
DOCUMENT
The aim of the study was to evaluate whether multiple sclerosis (MS) is associated with risk of cataract or glaucoma. We conducted a population-based cohort study utilizing the UK General Practice Research Database (1987–2009) linked to the national hospital registry of England (1997–2008). Incident MS patients (5576 cases) were identified and each was matched to six patients without MS (controls) by age, gender, and practice. Cox proportional hazard models were used to estimate hazard ratios (HRs) of incident cataract and glaucoma in MS. Time-dependent adjustments were made for age, history of diseases and drug use.
DOCUMENT
The aim of this study was to assess the association between prescription changes frequency (PCF) and hospital admissions and to compare the PCF to the Chronic Disease Score (CDS). The CDS measures comorbidity on the basis of the 1-year pharmacy dispensing data. In contrast, the PCF is based on prescriptionchanges over a 3-month period. A retrospective matched case–control design was conducted. 10.000 patients were selected randomly from the Dutch PHARMO database, who had been hospitalized (index date) between July 1, 1998 and June 30, 2000. The primary study outcome was the number of prescription changes during several three-month time periods starting 18, 12, 9, 6, and 3 months before the index date. For each hospitalized patient, one nonhospitalized patient was matched for age, sex, and geographic area, and was assigned the same index date as the corresponding hospitalized patient.We classified four mutually exclusive types of prescription changes: change in dosage, switch, stop and start.
DOCUMENT
