The rapid rise of many e-commerce platforms for individual consumers has generated a large amount of text-based data, and thus researchers have begun to experiment with text mining techniques to extract information from the large amount of textual data to assist in sales forecasting. The existing literature focuses textual data on product reviews; however, consumer reviews are not something that companies can directly control, here we argue that textual product descriptions are also important determinants of consumer choice. We construct an artificial intelligence (AI) framework that combines text mining, WaveNet neural networks, multiple regression, and SHAP model to explain the impact of product descriptions on sales forecasting. Using data from nearly 200,000 sales records obtained from a cross-border e-commerce firm, an empirical study showed that the product description presented to customers can influence sales forecasting, and about 44% of the key phrases greatly affect sales forecasting results, the sales forecasting models that added key product description phrases had improved forecasting accuracy. This paper provides explainable results of sales forecasting, which can provide guidance for firms to design product descriptions with reference to the market demand reflected by these phrases, and adding these phrases to product descriptions can help win more customers.

We explored carers experiences during the COVID-19 pandemic in England to identify long-term impacts and implications, and to suggest future support for caregivers. Data were collected during COVID-19 rapid response studies (IDEAL-CDI; INCLUDE) from carers participating in a British longitudinal cohort study (IDEAL). Semi-structured interview data were compared to their accounts from previous interviews conducted during the first 18 months of the pandemic. There was indication of some return to pre-pandemic lifestyles but without appropriate support carers risked reaching crisis point. Evidence points to a need for assessment and management of support needs to ensure well-being and sustainable dementia caregiving.

The health and well-being benefits of outdoor nature-based activity are increasingly recognised, but older people with cognitive impairment face significant barriers to access. The ENLIVEN project aims to promote access by gathering evidence and coproducing guidance for activity providers. As part of this project, we conducted a scoping review to characterise the types of outdoor nature-based activity for older people with dementia and other forms of cognitive impairment for which research evidence is available and the range of outcomes is examined. The protocol is available online. We systematically searched relevant databases from 1st January, 2009, to 20th October, 2022, and screened articles against the following criteria: participants were older people aged 65 and above with cognitive impairment arising from dementia or another health condition. The study described the formal provision of outdoor nature-based activity away from the person’s usual place of residence, and at least one outcome of participation in the activity was evaluated. Twenty-eight articles met inclusion criteria, all focused on people with dementia. In most cases, participants were attending day care or living in residential care, and sample sizes ranged from 4 to 136. Activities fell into three groups: green day care (fifteen articles), equine-assisted interventions (seven articles), and community nature-based activities (six articles). Outcome domains explored were connection with nature, activity engagement, impacts on clinical symptoms, functional ability, physical, psychological and social health,, and quality of life. Outdoor nature-based activity can be offered as an opportunity for meaningful occupation to enrich daily life, as a framework for day care provision, or as an intervention to address clinical needs. The evidence base for green day care is relatively established, but the potential for addressing specific clinical needs remains to be explored. The paucity of evidence regarding community provision, especially for those not attending formal care settings, suggests the need for effective knowledge exchange to stimulate initiatives in this area.

Physically active learning (PAL) has emerged as a promising way of eliciting health and education-based outcomes for pupils. Concurrently, research suggests large variability in how PAL is perceived, operationalized, and prioritized in practice across Europe. Therefore, this study aimed to co-develop a framework for action to support the adoption and implementation of PAL. Adopting a design thinking approach, 40 international stakeholders representing 13 countries engaged in an idea generation workshop during a two-day PAL international conference. Participants included professionals from research (n = 20), practice (n = 4) and policy (n = 1) or a combination (n = 15). Their experience with PAL ranged from none to 19 years (with an average of 3.9 years). Participants were allocated into one of six heterogeneous and multidisciplinary groups and led through interactive tasks to identify: the landscape for PAL across Europe, barriers to the adoption and implementation of PAL, and key objectives for research, policy and practice to improve the adoption and implementation of PAL. All discussions were audio recorded and prioritized objectives were transcribed verbatim and analysed using inductive qualitative content analysis. Five interlinked and mutually reinforcing themes were identified: (1) Integration of the health and education paradigms (2) Coherent national policy and decision making (3) Building confident and competent teachers (4) Adopting a whole school approach for PAL (5) Strengthening the evidence base for PAL. The priority action framework identifies five key areas for action to facilitate PAL adoption and implementation across Europe. Central to the success of border uptake of PAL is the integration of the health and education paradigms. To achieve this aim, reframing PAL as movement-centered pedagogy would provide a more holistic and inclusive perspective.

Developing a fast, cost-effective, eco-friendly solution to recycle large amounts of construction and demolition waste (CDW) generated from construction industry-related activities and natural disasters is crucial. The present investigation aims to offer a solution for repurposing CDW into building materials suitable for accelerated construction and housing in developing countries and disaster-prone areas. Feasibility of recycled concrete aggregate (RCA) inclusion in geopolymer mortars constituted entirely from CDW (masonry elements) was investigated via an environmental impact-oriented approach by addressing the composition related key parameters. Mechanical performance was evaluated through compressive strength tests, and scanning electron microscope (SEM) imaging with line mapping analyses were carried out to monitor the interfacial transition zone (ITZ) properties. To investigate the environmental impacts of the geopolymer mortars and highlight the advantages over Portland cement-based mortars, a cradle-to-gate life cycle assessment (LCA) was performed. Findings revealed that roof tile (RT)-based geopolymer mortars mainly exhibited better strength performance due to their finer particle size. Mixtures activated with 15 M NaOH solution and cured at 105 °C achieved an average compressive strength above 55 MPa. RCA size was the most influential parameter on compressive strength, and a smaller maximum RCA size significantly increased the compressive strength. Microstructural analyses showed that the ITZ around smaller RCAs was relatively thinner, resulting in better compressive strength results. LCA proved that CDW-based geopolymer mortars provide the same compressive strength with around 60% less CO2 emissions and similar energy consumption compared to Portland cement-based mortars.

Over the next decade the number of humans venturing beyond Earth is projected to rapidly increase in both quantity and diversity. Humans will regularly fly to the International Space Station until it is decommissioned by 2031, will return to the Moon by 2025 via the Artemis programme, and will fly to space via commercial ventures. Spaceflight presents a hazardous environment for human health. To understand spaceflight-associated health risks further and to increase safety via advanced healthcare approaches, including personalised medicine, more data must be collected. Importantly, this data must be derived from a diverse cohort of participants and a range of mission formats. We propose that the UK should start to consider all citizens venturing into space as potential participants from which health and biological data could be consensually collected. Importantly, we believe that this routine data collection programme should adopt a similar strategy to the UK National Health Service and the UK Biobank, by including "omics" data for scientific and healthcare purposes. We consider how such a world-leading programme, kick-started via a pilot study, might be realised through appropriate policy design, including which measures to collect, when to collect them, and unique ethical considerations pertaining to the spacefaring population.

The application of omics to study Caenorhabditis elegans (C. elegans) in the context of spaceflight is increasing, illuminating the wide-ranging biological impacts of spaceflight on physiology. In this review, we highlight the application of omics, including transcriptomics, genomics, proteomics, multi-omics, and integrated omics in the study of spaceflown C. elegans, and discuss the impact, use, and future direction of this branch of research. We highlight the variety of molecular alterations that occur in response to spaceflight, most notably changes in metabolic and neuromuscular gene regulation. These transcriptional features are reproducible and evident across many spaceflown species (e.g., mice and astronauts), supporting the use of C. elegans as a model organism to study spaceflight physiology with translational capital. Integrating tissue-specific, spatial, and multi-omics approaches, which quantitatively link molecular responses to phenotypic adaptations, will facilitate the identification of candidate regulatory molecules for therapeutic intervention and thus represents the next frontiers in C. elegans space omics research.

The Arg-Gly-Asp (RGD)-binding family of integrin receptors, and notably the β3 subfamily, are key to multiple physiological processes involved in tissue development, cancer proliferation, and metastatic dissemination. While there is compelling preclinical evidence that both αvβ3 and αIIbβ3 are important anticancer targets, most integrin antagonists developed to target the β3 integrins are highly selective for αvβ3 or αIIbβ3. We report the design, synthesis, and biological evaluation of a new structural class of ligand-mimetic β3 integrin antagonist. These new antagonists combine a high activity against αvβ3 with a moderate affinity for αIIbβ3, providing the first evidence for a new approach to integrin targeting in cancer.

The early diagnosis and personalised treatment of diseases are facilitated by machine learning. The quality of data has an impact on diagnosis because medical data are usually sparse, imbalanced, and contain irrelevant attributes, resulting in suboptimal diagnosis. To address the impacts of data challenges, improve resource allocation, and achieve better health outcomes, a novel visual learning approach is proposed. This study contributes to the visual learning approach by determining whether less or more synthetic data are required to improve the quality of a dataset, such as the number of observations and features, according to the intended personalised treatment and early diagnosis. In addition, numerous visualisation experiments are conducted, including using statistical characteristics, cumulative sums, histograms, correlation matrix, root mean square error, and principal component analysis in order to visualise both original and synthetic data to address the data challenges. Real medical datasets for cancer, heart disease, diabetes, cryotherapy and immunotherapy are selected as case studies. As a benchmark and point of classification comparison in terms of such as accuracy, sensitivity, and specificity, several models are implemented such as k-Nearest Neighbours and Random Forest. To simulate algorithm implementation and data, Generative Adversarial Network is used to create and manipulate synthetic data, whilst, Random Forest is implemented to classify the data. An amendable and adaptable system is constructed by combining Generative Adversarial Network and Random Forest models. The system model presents working steps, overview and flowchart. Experiments reveal that the majority of data-enhancement scenarios allow for the application of visual learning in the first stage of data analysis as a novel approach. To achieve meaningful adaptable synergy between appropriate quality data and optimal classification performance while maintaining statistical characteristics, visual learning provides researchers and practitioners with practical human-in-the-loop machine learning visualisation tools. Prior to implementing algorithms, the visual learning approach can be used to actualise early, and personalised diagnosis. For the immunotherapy data, the Random Forest performed best with precision, recall, f-measure, accuracy, sensitivity, and specificity of 81%, 82%, 81%, 88%, 95%, and 60%, as opposed to 91%, 96%, 93%, 93%, 96%, and 73% for synthetic data, respectively. Future studies might examine the optimal strategies to balance the quantity and quality of medical data.

This paper proposes a novel approach for the reliability cost-based optimization of Distribution Systems (DS), considering tie line-based network reconfiguration method with integration of Distributed Energy Resources (DER). An optimal Energy not Supplied (ENS) index is proposed, where the capacity is handled by curtailment devices in the network such as sectionalizers and the energy supplied by DERs which considers Flexibility Services (FS) within a market environment. The decision variables include the investment and operation of tie-lines and buying regulation services from DER such as Distributed Generation (DG) and Battery Energy Storage Systems (BESS). The results validate the cost-effectiveness of the proposed method through implementation of these technologies to improve the reliability of the DS, within a comprehensive set of case-study scenarios for a 16-bus UK generic distribution system (UKGDS). The case study results indicate that significant savings can be achieved through the proposed method, ranging between 36%–71% depending on the level of automation in tie-line operations in combination with the settlement price for the power-balance of FS. This illustrates that the proposed DS reliability cost-based optimization method could have a significant impact for real world DG and BESS applications.