Search Results (22)

This work presents a data-driven framework for early detection of polymer melt instability in industrial injection moulding using Long Short-Term Memory (LSTM) time-series models. The study uses six months of continuous production data comprising approximately 280,000 injection cycles collected from a fully operational thermoplastic injection line. Because melt behaviour evolves gradually and conventional threshold-based monitoring often fails to capture these transitions, the proposed approach models temporal patterns in torque, pressure, temperature, and rheology to identify drift conditions that precede quality degradation. A physically informed labelling strategy enables supervised learning even with sparse defect annotations by defining volatile zones as short time windows preceding operator-identified non-conforming parts, allowing the model to recognise instability windows minutes before defects emerge. The framework is designed for deployment on standard machine signals without requiring additional sensors, supporting proactive process adjustments, improved stability, and reduced scrap in injection moulding environments. These findings demonstrate the potential of temporal deep-learning models to enhance real-time monitoring and contribute to more robust and adaptive manufacturing operations. Full article

A personalized framework for smart home automation is introduced, utilizing machine learning to predict user activities and allow for the context-aware control of living spaces. Predicting user activities, such as ‘Watch_TV’, ‘Sleep’, ‘Work_On_Computer’, and ‘Cook_Dinner’, is essential for improving occupant comfort, optimizing energy consumption, and offering proactive support in smart home settings. The Edge Light Human Activity Recognition Predictor, or EL-HARP, is the main prediction model used in this framework to predict user behavior. The system combines open-source software for real-time sensing, facial recognition, and appliance control with affordable hardware, including the Raspberry Pi 5, ESP32-CAM, Tuya smart switches, NFC (Near Field Communication), and ultrasonic sensors. In order to predict daily user activities, three gradient-boosting models—XGBoost, CatBoost, and LightGBM (Gradient Boosting Models)—are trained for each household using engineered features and past behaviour patterns. Using extended temporal features, LightGBM in particular achieves strong predictive performance within EL-HARP. The framework is optimized for edge deployment with efficient training, regularization, and class imbalance handling. A fully functional prototype demonstrates real-time performance and adaptability to individual behavior patterns. This work contributes a scalable, privacy-preserving, and user-centric approach to intelligent home automation. Full article

Polypharmacy is prevalent in older people residing in care homes. Deprescribing, reducing or stopping harmful or unnecessary medicines, leads to improvements in patient- and health-system-orientated outcomes. This study identified the barriers and enablers to pharmacists proactively deprescribing in United Kingdon care homes. It draws on methods from behavioural science. Twenty-nine participants who had previously taken part in a deprescribing randomised control trial (sixteen pharmacists, six primary care doctors, and seven care home managers) were interviewed. Data were mapped to the Theoretical Domains Framework to understand pharmacists’ deprescribing behaviour. Barriers were deprescribing seen as risky and perceived resistance to deprescribing by residents, their families, and care home staff. Enablers were seeing benefits from deprescribing, part of a pharmacists’ role, and endorsement from a doctor. Ways to change pharmacist behaviour were identified from a suite of behaviour change techniques (BCT). Using a modified Nominal Group Technique, 15 staff (six pharmacists, five primary care doctors, and four care home managers) naïve to deprescribing interventions completed an online survey to assess the feasibility and acceptability of implementing the 27 BCTs. Seven BCTs achieved a more that 80% consensus on all implementation criteria. In a consensus workshop, the staff group discussed practical ways the BCTs might work in primary care practice. Fourteen UK policy and practice leaders worked with the researchers to develop recommendations from the consensus workshop into a policy briefing. In conclusion, this study provides detail on using a theory-informed approach to translate research into policy to inform deprescribing practices. Full article

In multi-agent systems, the Dynamic Distributed Constraint Optimisation Problem (D-DCOP) framework is pivotal, allowing for the decomposition of global objectives into agent constraints. Proactive agent behaviour is crucial in such systems, enabling agents to anticipate future changes and adapt accordingly. Existing approaches, like Proactive Dynamic DCOP (PD-DCOP) algorithms, often necessitate a predefined environment model. We address the problem of enabling proactive agent behaviour in D-DCOPs where the dynamics model of the environment is unknown. Specifically, we propose an approach where agents learn local autoregressive models from observations, predicting future states to inform decision-making. To achieve this, we present a temporal experience-sharing message-passing algorithm that leverages dynamic agent connections and a distance metric to collate training data. Our approach outperformed baseline methods in a search-and-extinguish task using the RoboCup Rescue Simulator, achieving better total building damage. The experimental results align with prior work on the significance of decision-switching costs and demonstrate improved performance when the switching cost is combined with a learned model. Full article

The Single Site Order (SSO)—a policy restricting staff from working at multiple long-term care (LTC) homes—was mandated by the Public Health Agency of Canada to control the spread of COVID-19 in LTC homes, where nearly 70% of COVID-19-related deaths in Canada occurred. This mixed methods study assesses the impact of the SSO on LTC residents in British Columbia. Interviews were conducted (residents (n = 6), family members (n = 9), staff (n = 18), and leadership (n = 10) from long-term care homes (n = 4)) and analyzed using thematic analysis. Administrative data were collected between April 2019 and March 2020 and between April 2020 and March 2021 and analyzed using descriptive statistics and data visualization. Qualitative and quantitative data were triangulated and demonstrated that staffing challenges became worse during the implementation of the SSO, resulting in the mental and physical health deterioration of LTC residents. Qualitative data demonstrated decreased time for personalized and proactive care, increased communication challenges, and increased loneliness and isolation. Quantitative data showed a decline in activities of daily living, increased antipsychotic medication use, pressure ulcers, behavioural symptoms, and an increase in falls. Addressing staff workload and staffing shortages during SSO-related policy implementation is essential to avoid resident health deterioration. Full article

Media discourse surrounding fashion and sustainability tends to be negative, emphasising the problems that exist across the various stages of the lifecycle of a garment. Although consumers are increasingly aware of at least some of the issues surrounding fashion and the environment, research suggests that the scale and complexity of the problem causes them to feel detached and uncertain about how to adapt their own behaviour in response. This research positions Instagram as a digital media platform through which sustainable fashion is communicated and experienced through augmented fashion content. Instagram is recognised for its significant impact on visual culture, particularly within aesthetic sectors such as fashion. Recent research reveals that users have begun engaging in more serious subjects and debates on Instagram, including political, social, and environmental issues. This has brought about opportunities for new voices who are championing sustainable fashion in its variety of manifestations. An open qualitative analysis was carried out using the hashtag #SustainableFashion to uncover themes relating to the types of content, stakeholders, and mechanisms that are being used to augment sustainable fashion on Instagram. The findings reveal a positive community of content creators—including vintage enthusiasts, designers, makers and brands—who are using the hashtag regularly to share proactive content in the form of specific, targeted messages around sustainable fashion solutions. The aim was to uncover the discussions that are taking place right now and provide grounding for future work in this area. Full article

Several vaccines have been developed for COVID-19 since the pandemic began. This study aimed to evaluate the factors associated with COVID-19 vaccination intention. A global survey was conducted across 26 countries from October, 2020 to December, 2021 using an online self-administered questionnaire. Demographic information, socio-economic status, and clinical information were collected. A logistic regression examined the associations between vaccine intention and factors such as perceptions and the presence of chronic physical and mental conditions. The sample included 2459 participants, with 384 participants (15.7%) expressing lower COVID-19 vaccination intent. Individuals who identified as female; belonged to an older age group; had a higher level of education; were students; had full health insurance coverage; or had a previous history of influenza vaccination were more willing to receive vaccination. Conversely, those who were working part-time, were self-employed, or were receiving social welfare were less likely to report an intention to get vaccinated. Participants with mental or physical health conditions were more unwilling to receive vaccination, especially those with sickle cell disease, cancer history within the past five years, or mental illness. Stronger vaccination intent was associated with recommendations from the government or family doctors. The presence of chronic conditions was associated with lower vaccine intention. Individuals with health conditions are especially vulnerable to health complications and may experience an increased severity of COVID-19 symptoms. Future research should evaluate the effectiveness of interventions targeting the vaccine perceptions and behaviours of at-risk groups. As such, public awareness campaigns conducted by the government and proactive endorsement from health physicians may help improve COVID-19 vaccination intention. Full article

Background: Many home-dwelling older adults present abnormal behaviours related to dementia or to non-dementia cognitive impairment (e.g., agitation, anxiety, apathy, etc.). Because many older adults live at home alone or are able to hide any signs of abnormal behaviours from others, the non-healthcare workers who interact with older adults on a daily basis are key actors in detecting those behaviours and orienting older adults towards appropriate support services. To the best of our knowledge, no studies to date have explored the daily interactions experienced between older adults and the various non-healthcare workers whom they regularly encounter in the community. This work aimed to identify the non-healthcare workers who are regularly in direct contact with older adults during their day-to-day activities and then develop specific training for these workers on the subject of abnormal behaviours among the elderly. Methods: This qualitative and ethnographic study asked 21 home-dwelling older adults aged 65 years old or more to answer open-ended questions. Sixteen had no self-reported cognitive impairments, and five had a probable or diagnosed slight cognitive impairment or mild-to-moderate dementia. A thematic analysis of the data was carried out. Results: The non-healthcare workers who spent the most time with older adults with and without reported cognitive impairments were those working in cafés or tea rooms and leisure or activity centres. Conclusions: In view of the significant amounts of contact between home-dwelling older adults and non-healthcare workers, it seems necessary and sensible to increase non-healthcare workers’ knowledge about abnormal behaviours, especially by offering them training. The proactive detection and identification of older adults’ abnormal behaviours by non-healthcare workers will ensure earlier care and reduce avoidable hospitalisations, institutionalisations and costs linked to geriatric healthcare. Full article

Due to the dynamic nature of the food supply chain system, food supply management could suffer because of, and be interrupted by, unforeseen events. Considering the perishable nature of fresh food products and their short life cycle, fresh food companies feel immense pressure to adopt an efficient and proactive risk management system. The risk management aspects within the food supply chains have been addressed in several studies. However, only a few studies focus on the complex interactions between the various types of risks impacting food supply chain functionality and dynamic feedback effects, which can generate a reliable risk management system. This paper strives to contribute to this evident research gap by adopting a system dynamics modelling approach to generate a systemic risk management model. The system dynamics model serves as the basis for the simulation of risk index values and can be explored in future work to further analyse the dynamic risk’s effect on the food supply chain system’s behaviour. According to a literature review of published research from 2017 to 2021, nine different risks across the food supply chain were identified as a subsection of the major risk categories: macro-level and operational risks. Following this stage, two of the risk groups identified first were integrated with a developed system dynamics model to conduct this research and to evaluate the interaction between the risks and the functionality of the three main dairy supply chain processes: production, logistics, and retailing. The key findings drawn from this paper can be beneficial for enhancing managerial discernment regarding the critical role of system dynamics models for analysing various types of risks across the food supply chain process and improving its efficiency. Full article

The circular economy (CE) in construction literature engages with individual CE concepts, mostly at the ‘macro’/‘meso’ levels, and lacks holistic frameworks of indicators for circularity assessments (CAs) to inform decision-making at the ‘micro’ (project) level. This article presents a model using the Analytic Hierarchy Process (AHP) for circular proposal selection in building projects based on a previously validated conceptual framework. The model involves twelve circularity indicators (CIs) classed under five themes relevant to building lifecycle stages. A questionnaire survey was used to establish the final weight vector of CIs. Participants acknowledged the immediate and prolonged effects of design on circularity and viewed waste as ‘design flaws’ but focused on aspirational design indicators relevant to achieving future circularity and missed opportunities for embedding circular materials in design. Moreover, UK participants showed distinctive behaviours towards CAs (proactive/reactive) based on work experience. ‘UK-Experts’ focused on ‘front-end’ design indicators, while ‘UK-Non-experts’ focused on ‘back-end’ waste management indicators. The findings indicate a partial transition to CE better described as a ‘recycle/reuse economy’. CAs and multiple-criteria decision-making (MCDM) techniques facilitate automated decision-making, which provides a new pathway to digital transformation within built environment. Future research will develop a decision-making tool and apply the proposed model in real-life projects. Full article

The objective of the study was to examine the perceptions of business students on their employability skills at the point of graduation. The study was partially driven by past research which identified lack of soft skills as one of the main contributing factors in younger workers’ dismissal from work, and the need to understand the level of employability skills younger graduates have at graduation. An exploratory descriptive research methodology was used for the study. A survey was administered to 189 fourth-year business students. In total, 90 students filled-in the questionnaire, representing a 47.6% response rate. Based on a structured survey questionnaire administered to final-year undergraduate business students, the four most important employability skills for recruitment to entry-level positions are communication skills, learning skills, positive attitudes and behaviours, and problem-solving skills. The main prominent result was that ‘learning skills’ were ranked the second most important employability skills. In today’s fast-paced, rapidly changing work environments that are characterised by rapid knowledge obsolescence and an unknown future, willingness to learn and proactive lifelong learning are key to sustaining long-term graduate employability. Students seem to be satisfied with their perceived level of academic, personal management, and teamwork skills they possessed at the point of graduation. However, there are possible areas for further improvement regarding creativity and innovative skills, and ability to ‘resolve and management conflicts’ in teamwork. The study found that students used a combination of traditional and student-centred learning methods and pedagogies to acquire employability skills. As business students approach graduation, it is important to focus on areas they can improve and emphasise self-directed lifelong learning throughout their careers. The study confirms the role of external factors—labour market demand—in influencing perceived employability. The perceptions of students need to be systematically included in HEIs’ employability policy and discourse. Full article

The demanding work context of physicians challenges their employability (i.e., their ability and willingness to continue to work). This requires them to proactively manage their working life and employability, for instance, through job crafting behaviour. This randomized controlled intervention study aimed to examine the effects of a personalized feedback report on physicians’ employability and job crafting behaviour. A total of 165 physicians from two hospitals in a large Dutch city were randomly assigned to a waitlist control or intervention group in May 2019. Physicians in the intervention group received access to a personalized feedback report with their employability scores, suggestions to improve these and to engage in job crafting. Participants completed a pre-test and eight weeks later a post-test. RM MANOVAs and RM ANOVAs showed that the intervention enhanced participants’ perceptions of their mental (F (1,130) = 4.57, p < 0.05) and physical (F (1,135) = 16.05, p < 0.001) ability to continue working. There was no effect on their willingness to continue to work. Furthermore, while job crafting behaviour significantly increased over time, the personalized feedback report did not account for this change. This low-investment intervention is relevant for organizations to stimulate employees’ proactivity and create positive perceptions of their ability to continue to work. Moreover, this study contributes to the literature by examining a novel approach of a job crafting intervention that does not require many resources to implement. Full article

Sustainable mental health and wellbeing (MHW), as addressed under SDG3, is crucial for achieving sustainable development, notably for sustainable SMEs growth. MWH is specifically interlinked with SDGs 8, 9 and 11: Economic growth and prosperity, sustainable communities, innovation, and jobs. Studies show over 200 million workdays are lost due to poor MHW each year, referring to the global cost of $1 trillion/year in lost productivity and it is increasing every year. Poor workplace MWH is almost an epidemic after COVID-19. It will be a significant challenge for a long time, in particular for SMEs which are hit hardest by the pandemic, as MHW problems have been shown to be a COVID side effect among 1:5 people. Despite the multifactorial aetiology of MHW (individual, social, environmental, and organizational), interventions for workplace MHW mostly refer to ‘one size fits all’ and top-down solutions, primarily asking for the commitment and behaviour change of employees; that has shown to be ineffective. The main assumption underlying the present work is the need for a proactive and tailored MHW frameworks that can be blended to organizational policies. The objective which corresponds to the main purpose of the paper is to provide a 5-staged MWH model, stemming from our evidence-based studies, that may speak for the identified need. We also discuss how the Model can provide a route map on how SMEs can implement and measure SDGs relevant to their business in synergistic interaction with SDG3. Full article

The Swedish equine sector is considered a high-risk work environment, with relatively high injury rates and high severity of injuries. General safety research has identified a correlation between the safety performance and safety culture, but little is known about the intricacies of the safety culture in the Swedish equine sector, especially concerning managers’ and employees’ perceptions of their work environment. The safety climate assessment is recognised as an effective tool for identifying potential problems in the workplace, thus enhancing safety behaviour and decreasing the frequency and severity of injuries. The aim was to evaluate the safety climate at riding schools and trotting stables through the Nordic Safety Climate Questionnaire (NOSACQ-50) diagnostic tool, and to get a better understanding of the workers’ perceptions regarding safety and safety management at their workplace through complementary interviews. The results showed that the safety climate was generally positive and that employees were aware of the risks relating to their work. Riding schools commonly had routines in place for risk assessment and work environment management, but such routines were often lacking at trotting stables, indicating inadequate prioritisation of safety by the management. The main area that should be targeted to improve safety in the sector is employees’ prioritisation and non-acceptance of risks. Proactive instead of reactive safety management should be promoted, where safety is an integral part of daily work and all employees are encouraged to identify factors contributing to occupational injuries and develop strategies for injury prevention. Full article

The uptake of maternal influenza and pertussis vaccinations is often suboptimal. This study explores the factors influencing pregnant women’s and health care professionals’ (HCPs) behaviour regarding maternal vaccinations (MVs). Pregnant/recently pregnant women, midwives, pharmacists and general practice staff in Waikato, New Zealand, were interviewed. The analysis used the behaviour change wheel model. Interviews of 18 women and 35 HCPs revealed knowledge about MVs varied with knowledge deficiencies hindering the uptake, particularly for influenza vaccination. HCPs, especially midwives, were key in raising women’s awareness of MVs. Experience with vaccinating, hospital work (for midwives) and training increased HCPs’ knowledge and proactivity about MVs. A “woman’s choice” philosophy saw midwives typically encouraging women to seek information and make their own decision. Women’s decisions were generally based on knowledge, beliefs, HCPs’ emphasis and their perceived risk, with little apparent influence from friends, family, or online or promotional material. General practice’s concentration on children’s vaccination and minimal antenatal contact limited proactivity with MVs. Busyness and prioritisation appeared to affect HCPs’ proactivity. Multi-pronged interventions targeting HCPs and pregnant women and increasing MV access are needed. All HCPs seeing pregnant women should be well-informed about MVs, including how to identify and address women’s questions or concerns about MVs to optimise uptake. Full article