Active learning has become an increasingly popular method for screening large amounts of data in systematic reviews and meta-analyses. The active learning process continually improves its predictions on the remaining unlabeled records, with the goal of identifying all relevant records as early as possible. However, determining the optimal point at which to stop the active learning process is a challenge. The cost of additional labeling of records by the reviewer must be balanced against the cost of erroneous exclusions. This paper introduces the SAFE procedure, a practical and conservative set of stopping heuristics that offers a clear guideline for determining when to end the active learning process in screening software like ASReview. The eclectic mix of stopping heuristics helps to minimize the risk of missing relevant papers in the screening process. The proposed stopping heuristic balances the costs of continued screening with the risk of missing relevant records, providing a practical solution for reviewers to make informed decisions on when to stop screening. Although active learning can significantly enhance the quality and efficiency of screening, this method may be more applicable to certain types of datasets and problems. Ultimately, the decision to stop the active learning process depends on careful consideration of the trade-off between the costs of additional record labeling against the potential errors of the current model for the specific dataset and context.
MULTIFILE
Injuries and lack of motivation are common reasons for discontinuation of running. Real-time feedback from wearables can reduce discontinuation by reducing injury risk and improving performance and motivation. There are however several limitations and challenges with current real-time feedback approaches. We discuss these limitations and challenges and provide a framework to optimise real-time feedback for reducing injury risk and improving performance and motivation. We first discuss the reasons why individuals run and propose that feedback targeted to these reasons can improve motivation and compliance. Secondly, we review the association of running technique and running workload with injuries and performance and we elaborate how real-time feedback on running technique and workload can be applied to reduce injury risk and improve performance and motivation. We also review different feedback modalities and motor learning feedback strategies and their application to real-time feedback. Briefly, the most effective feedback modality and frequency differ between variables and individuals, but a combination of modalities and mixture of real-time and delayed feedback is most effective. Moreover, feedback promoting perceived competence, autonomy and an external focus can improve motivation, learning and performance. Although the focus is on wearables, the challenges and practical applications are also relevant for laboratory-based gait retraining.
DOCUMENT
Pupils with problem behaviours are challenging teachers as well as they are a challenge to teachers to find a way to teach them what curricula prescribe. Especially middle school teachers and those working in schools for special education are con-fronted with pupils with behavioural problems. There, teachers experience hard classes and find it difficult to fit classroom management with the pupils needs. In this paper we focus on two questions: is pullout an effective treatment to handle problem behaviour? do special classes have advantages for pupils who were pulled out or not? First we present a theoretical framework about pullout and we explicit our expectations. Then we describe the methods of our research in schools for special educa-tion during two months for students (N=759) when pulled out. We examined the reason of pulling out and the interactions during the process outside the classroom and the return. Because teachers noticed date and time of the removal, it was possible to use survival analysis to show the effects of the treatment. We found that pullout occurs under quite different circumstances, so the treatment integrity is a problem because deficiency of the intervention leads to repeated pullout. The data also showed that special classes for pupils who are pulled out seem to trigger and/or in-tensify the process itself. So, we conclude that these classes have a contra-productive effect.
DOCUMENT
Mycelium biocomposites (MBCs) are a fairly new group of materials. MBCs are non-toxic and carbon-neutral cutting-edge circular materials obtained from agricultural residues and fungal mycelium, the vegetative part of fungi. Growing within days without complex processes, they offer versatile and effective solutions for diverse applications thanks to their customizable textures and characteristics achieved through controlled environmental conditions. This project involves a collaboration between MNEXT and First Circular Insulation (FC-I) to tackle challenges in MBC manufacturing, particularly the extended time and energy-intensive nature of the fungal incubation and drying phases. FC-I proposes an innovative deactivation method involving electrical discharges to expedite these processes, currently awaiting patent approval. However, a critical gap in scientific validation prompts the partnership with MNEXT, leveraging their expertise in mycelium research and MBCs. The research project centers on evaluating the efficacy of the innovative mycelium growth deactivation strategy proposed by FC-I. This one-year endeavor permits a thorough investigation, implementation, and validation of potential solutions, specifically targeting issues related to fungal regrowth and the preservation of sustained material properties. The collaboration synergizes academic and industrial expertise, with the dual purpose of achieving immediate project objectives and establishing a foundation for future advancements in mycelium materials.
Foodsecurity, duurzaam gebruik van grondstoffen en water zijn items die zijn terug te vinden in de Grand Challenges in de EU-onderzoekagenda Horizon2020. In de tuinbouw vindt dit zijn plaats door steeds meer op microniveau teelt, groei en oogst te beïnvloeden. De Nederlandse tuinbouw loopt hiermee wereldwijd voorop en de kennis en kunde is een belangrijk exportproduct. Bedrijven hebben niettemin te weinig controle over de gewascondities in de tuinbouwkas met negatieve gevolgen voor de oogstopbrengst en overmatig gebruik van grondstoffen. Het teelt- en oogstproces in een tuinbouwkas kan aanzienlijk worden verbeterd door tot op microniveau een betrouwbaar en integraal beeld te verkrijgen van de verdeling van kritische gewasparameters binnen de kas. Via slimme monitoring kunnen eveneens concentraties van ziektekiemen gedetecteerd worden en 3D-beelden worden gemaakt van het gewas. Met hulp van deze informatie kunnen kwantiteit en kwaliteit van de oogst tot op microniveau worden getraceerd om de relatie tussen genomen maatregelen en verkregen effecten na te gaan. De regel-lus met het monitoringsysteem dient hiervoor te worden gesloten, waardoor men vooraf kan gaan sturen op basis van verkregen kennis en ervaring. Zo kan verkregen informatie worden ingezet b.v. om lokaal efficiënt te draineren en te bewateren en om CO2-gehaltes, hoeveelheid licht en temperatuur optimaal aan te passen aan benodigde kascondities. Ook kunnen effectief maatregelen tegen ziektes op plantniveau worden genomen en kunnen oogstopbrengsten worden gemaximaliseerd. Inzet van slim datamanagement is voor dit alles een must. Ambitie van SCOUT is het ontwikkelen van een integraal monitoringequipment- en methodologieconcept in de kas om gewas- en omgevingsparameters van tomaten op robuuste en betrouwbare wijze te kunnen verzamelen en modelmatig te analyseren. Telers willen deze informatie gebruiken voor het nemen van beheersmaatregelen t.b.v. meer controle op uniformiteit in de vruchtontwikkeling. De ambitie wordt uitgewerkt via opzet van slimme meetmethodieken en data-gebaseerde groeimodellen op plant- en vakniveau, die in de praktijk worden uitgetest met integrale sensorconcepten. Verder wordt een data-infrastructuur ontwikkeld inclusief een data dashboard voor visualisatie van de monitoring resultaten. Zo krijgt de tuinder een real-time beeld van de verdeling van kritische gewasparameters in de kas en kan hij in de toekomst de opbrengst bij de oogst beter voorspellen en beïnvloeden met als doel uniformiteit van de oogst, maximalisering van economische opbrengst en minimalisering van milieu-impact. SCOUT is een samenwerking van kennisinstellingen en bedrijven. Partners zijn de hogescholen: HAS hogeschool, Avans, Fontys , Inholland, Haagse Hogeschool en de NHL. WUR ondersteunt het project met wetenschappelijk advies. Participerende bedrijven zijn telers van met name tomaten of toeleveranciers van technologie aan de glastuinbouw. Tenslotte is de landelijke gewascommissie Tomaat en Paprika van LTO Glaskracht Nederland (onderdeel ZLTO) betrokken. SCOUT maakt bestaande kennis toepasbaar en ontwikkelt nieuwe kennis t.b.v. een slimme en robuuste sensor- en data-infrastructuur en groeimodellering in de kas. Verder vindt verankering van kennis en kunde in onderwijs en lectoraten plaats en een vergroting van de kwaliteit van docenten en afstudeerders. Circa 20 (docent)onderzoekers van de hogescholen en circa 100 studenten worden betrokken, die via stages en afstudeeronderzoeken werken aan interessante vraagstukken direct afkomstig uit de beroepspraktijk.
Prompt and timely response to incoming cyber-attacks and incidents is a core requirement for business continuity and safe operations for organizations operating at all levels (commercial, governmental, military). The effectiveness of these measures is significantly limited (and oftentimes defeated altogether) by the inefficiency of the attack identification and response process which is, effectively, a show-stopper for all attack prevention and reaction activities. The cognitive-intensive, human-driven alarm analysis procedures currently employed by Security Operation Centres are made ineffective (as opposed to only inefficient) by the sheer amount of alarm data produced, and the lack of mechanisms to automatically and soundly evaluate the arriving evidence to build operable risk-based metrics for incident response. This project will build foundational technologies to achieve Security Response Centres (SRC) based on three key components: (1) risk-based systems for alarm prioritization, (2) real-time, human-centric procedures for alarm operationalization, and (3) technology integration in response operations. In doing so, SeReNity will develop new techniques, methods, and systems at the intersection of the Design and Defence domains to deliver operable and accurate procedures for efficient incident response. To achieve this, this project will develop semantically and contextually rich alarm data to inform risk-based metrics on the mounting evidence of incoming cyber-attacks (as opposed to firing an alarm for each match of an IDS signature). SeReNity will achieve this by means of advanced techniques from machine learning and information mining and extraction, to identify attack patterns in the network traffic, and automatically identify threat types. Importantly, SeReNity will develop new mechanisms and interfaces to present the gathered evidence to SRC operators dynamically, and based on the specific threat (type) identified by the underlying technology. To achieve this, this project unifies Dutch excellence in intrusion detection, threat intelligence, and human-computer interaction with an industry-leading partner operating in the market of tailored solutions for Security Monitoring.
