Showing papers by "University of Hertfordshire published in 2022"

Building energy consumption prediction for residential buildings using deep learning and other machine learning techniques

Abstract: The high proportion of energy consumed in buildings has engendered the manifestation of many environmental problems which deploy adverse impacts on the existence of mankind. The prediction of building energy use is essentially proclaimed to be a method for energy conservation and improved decision-making towards decreasing energy usage. Also, the construction of energy efficient buildings will aid the reduction of total energy consumed in newly constructed buildings. Machine Learning (ML) method is recognised as the best suited approach for producing desired outcomes in prediction task. Hence, in several studies, ML has been applied in the field of energy consumption of operational building. However, there are not many studies investigating the suitability of ML methods for forecasting the potential building energy consumption at the early design phase to reduce the construction of more energy inefficient buildings. To address this gap, this paper presents the utilization of several machine learning techniques namely Artificial Neural Network (ANN), Gradient Boosting (GB), Deep Neural Network (DNN), Random Forest (RF), Stacking, K Nearest Neighbour (KNN), Support Vector Machine (SVM), Decision tree (DT) and Linear Regression (LR) for predicting annual building energy consumption using a large dataset of residential buildings. This study also examines the effect of the building clusters on the model performance. The novelty of this paper is to develop a model that enables designers input key features of a building design and forecast the annual average energy consumption at the early stages of development. This result reveals DNN as the most efficient predictive model for energy use at the early design phase and this presents a motivation for building designers to utilize it before construction to make informed decision, manage and optimize design.

Drift in a popular metal oxide sensor dataset reveals limitations for gas classification benchmarks

Abstract: Metal oxide (MOx) gas sensors are a popular choice for many applications, due to their tunable sensitivity, space efficiency and low cost. Publicly available sensor datasets are particularly valuable for the research community as they accelerate the development and evaluation of novel algorithms for gas sensor data analysis. A dataset published in 2013 by Vergara and colleagues contains recordings from MOx gas sensor arrays in a wind tunnel. It has since become a standard benchmark in the field. Here we report a latent property of this dataset that limits its suitability for gas classification studies. Measurement timestamps show that gases were recorded in separate, temporally clustered batches. Sensor baseline response before gas exposure were strongly correlated with the recording batch, to the extent that baseline response was largely sufficient to infer the gas used in a given trial. Zero-offset baseline compensation did not resolve the issue, since residual short-term drift still contained enough information for gas/trial identification using a machine learning classifier. A subset of the data recorded within a short period of time was minimally affected by drift and suitable for gas classification benchmarking after offset-compensation, but with much reduced classification performance compared to the full dataset. We found 18 publications where this dataset was used without precautions against the circumstances we describe, thus potentially overestimating the accuracy of gas classification algorithms. These observations highlight potential pitfalls in using previously recorded gas sensor data, which may have distorted widely reported results.

Common Envelope Jet Supernova r-process Yields Can Reproduce [Eu/Fe] Abundance Evolution in the Galaxy

Abstract: We use a numerical Galactic chemical evolution model and find that the common envelope jets supernova (CEJSN) r-process scenario can account for both the very early average ratio of europium to iron and its evolution at later times in the Milky-Way (MW) Galaxy. In the CEJSN scenario a neutron star (NS) spirals-in inside a red supergiant (RSG) star all the way to the core and destroys it. According to this scenario r-process isotopes are nucleosynthesized inside neutron-rich jets that the accretion disk around the NS launches inside the core. The merger of a NS with an RSG core already takes place in the very young Galaxy. We conclude that CEJSNe can be a major contributor to r-process nucleosynthesis.

MALAT-1/p53/miR-155/miR-146a ceRNA circuit tuned by methoxylated quercitin glycoside alters immunogenic and oncogenic profiles of breast cancer

Abstract: Triple-Negative Breast Cancer (TNBC) is one of the most aggressive and hot BC subtypes. Our research group has recently shed the light on the utility of natural compounds as effective immunotherapeutic agents. The aim of this study is to investigate the role of a methoxylated quercetin glycoside (MQG) isolated from Cleome droserifolia in harnessing TNBC progression and tuning the tumor microenvironment and natural killer cells cytotoxicity. Results showed that MQG showed the highest potency (IC50 = 12 µM) in repressing cellular proliferation, colony-forming ability, migration, and invasion capacities. Mechanistically, MQG was found to modulate a circuit of competing endogenous RNAs where it was found to reduce the oncogenic MALAT-1 lncRNA and induce TP53 and its downstream miRNAs; miR-155 and miR-146a. Accordingly, this leads to alteration in several downstream signaling pathways such as nitric oxide synthesizing machinery, natural killer cells' cytotoxicity through inducing the expression of its activating ligands such as MICA/B, ULBP2, CD155, and ICAM-1 and trimming of the immune-suppressive cytokines such as TNF-α and IL-10. In conclusion, this study shows that MQG act as a compelling anti-cancer agent repressing TNBC hallmarks, activating immune cell recognition, and alleviating the immune-suppressive tumor microenvironment experienced by TNBC patients.

The Dutch Protocol for Juvenile Transsexuals: Origins and Evidence

Abstract: It has been a quarter of a century since Dutch clinicians proposed puberty suppression as an intervention for "juvenile transsexuals," which became the international standard for treating gender dysphoria. This paper reviews the history of this intervention and scrutinizes the evidence adduced to support it. The intervention was justified by claims that it was reversible and that it was a tool for diagnosis, but these claims are increasingly implausible. The main evidence for the Dutch protocol came from a longitudinal study of 70 adolescents who had been subjected to puberty suppression followed by cross-sex hormones and surgery. Their outcomes shortly after surgery appeared positive, except for the one patient who died, but these findings rested on a small number of observations and incommensurable measures of gender dysphoria. A replication study conducted in Britain found no improvement. While some effects of puberty suppression have been carefully studied, such as on bone density, others have been ignored, like on sexual functioning.

Evaluation of tensile strength retention and service life prediction of hydrothermal aged balanced orthotropic carbon/glass and Kevlar/glass fabric reinforced polymer hybrid composites

Abstract: © 2021 Wiley Periodicals LLC. This is the accepted manuscript version of an article which has been published in final form at https://doi.org/10.1002/app.51602

A multidomain decision support tool to prevent falls in older people: the FinCH cluster RCT

Abstract: Falls in care home residents are common, unpleasant, costly and difficult to prevent.The objectives were to evaluate the clinical effectiveness and cost-effectiveness of the Guide to Action for falls prevention in Care Homes (GtACH) programme.A multicentre, cluster, parallel, 1 : 1 randomised controlled trial with embedded process evaluation and economic evaluation. Care homes were randomised on a 1 : 1 basis to the GtACH programme or usual care using a secure web-based randomisation service. Research assistants, participating residents and staff informants were blind to allocation at recruitment; research assistants were blind to allocation at follow-up. NHS Digital data were extracted blindly.Older people's care homes from 10 UK sites.Older care home residents.The GtACH programme, which includes care home staff training, systematic use of a multidomain decision support tool and implementation of falls prevention actions, compared to usual falls prevention care.The primary trial outcome was the rate of falls per participating resident occurring during the 90-day period between 91 and 180 days post randomisation. The primary outcome for the cost-effectiveness analysis was the cost per fall averted, and the primary outcome for the cost-utility analysis was the incremental cost per quality adjusted life-year. Secondary outcomes included the rate of falls over days 0-90 and 181-360 post randomisation, activity levels, dependency and fractures. The number of falls per resident was compared between arms using a negative binomial regression model (generalised estimating equation).A total of 84 care homes were randomised: 39 to the GtACH arm and 45 to the control arm. A total of 1657 residents consented and provided baseline measures (mean age 85 years, 32% men). GtACH programme training was delivered to 1051 staff (71% of eligible staff) over 146 group sessions. Primary outcome data were available for 630 GtACH participants and 712 control participants. The primary outcome result showed an unadjusted incidence rate ratio of 0.57 (95% CI 0.45 to 0.71; p < 0.01) in favour of the GtACH programme. Falls rates were lower in the GtACH arm in the period 0-90 days. There were no other differences between arms in the secondary outcomes. Care home staff valued the training, systematic strategies and specialist peer support, but the incorporation of the GtACH programme documentation into routine care home practice was limited. No adverse events were recorded. The incremental cost was £20,889.42 per Dementia Specific Quality of Life-based quality-adjusted life-year and £4543.69 per quality-adjusted life-year based on the EuroQol-5 dimensions, five-level version. The mean number of falls was 1.889 (standard deviation 3.662) in the GtACH arm and 2.747 (standard deviation 7.414) in the control arm. Therefore, 0.858 falls were averted. The base-case incremental cost per fall averted was £190.62.The GtACH programme significantly reduced the falls rate in the study care homes without restricting residents' activity levels or increasing their dependency, and was cost-effective at current thresholds in the NHS.Future work should include a broad implementation programme, focusing on scale and sustainability of the GtACH programme.A key limitation was the fact that care home staff were not blinded, although risk was small because of the UK statutory requirement to record falls in care homes.This trial is registered as ISRCTN34353836.This project was funded by the National Institute for Health Research (NIHR) Health Technology Assessment programme and will be published in full in Health Technology Assessment; Vol. 26, No. 9. See the NIHR Journals Library website for further project information.Falls in care home residents are common, unpleasant, costly and hard to prevent. We tested whether or not the Guide to Action for falls prevention in Care Homes (GtACH) programme was effective in preventing falls. In this programme, care home staff were systematically trained and supported in the assessment of residents’ risk of falling and the generation of a falls reduction care plan. We undertook a randomised controlled trial comparing the GtACH programme with usual care, which does not involve this systematic attention to falls prevention. We also undertook a process evaluation, observing organisational and care processes, and an economic study to evaluate value for money. A total of 39 care homes were randomly allocated to the GtACH programme and 45 care homes were randomly allocated to usual care, involving a total of 1657 residents. The main comparison between the two arms was the rate of falls during months 4–6 after randomisation, when we expected any effect to be at its peak. We also assessed the falls rates before and 6 months after this period. We measured activity and dependency levels, as it was important to be sure that any reduction in the rate of falls was not achieved through restrictive care practices. We saw a 43% reduction in the falls rates of the GtACH programme participants during months 4–6, without observing any reduction in residents’ activity or dependency. Care home staff and relatives were positive about the GtACH programme. The GtACH programme was good value for money, as it was likely to be cost-effective. The effect of the programme waned over months 6–12, which may be because some staff did not embed the GtACH programme in their usual practice routines, and awareness levels may have dropped.

Restricting the advertising of high fat, salt and sugar foods on the Transport for London estate: Process and implementation study

Abstract: One in five UK children aged 10–11 years live with obesity. They are more likely to continue living with obesity into adulthood and to develop obesity-related chronic health conditions at a younger age. Regulating the marketing of high fat, salt and sugar (HFSS) foods and beverages has been highlighted as a promising approach to obesity prevention. In 2019, Transport for London implemented restrictions on the advertisement of HFSS products across its network. This paper reports on a process evaluation of the design and implementation of this intervention. In 2019–2020, we conducted semi-structured interviews with 23 stakeholders. Interviews with those responsible for implementation (n = 13) explored stakeholder roles, barriers and facilitators to policy development/implementation and unintended consequences. Interviews with food industry stakeholders (n = 10) explored perceptions and acceptability of the policy, changes to business practice and impact on business. Data were analysed using a general inductive approach. Practical challenges included limited time between policy announcement and implementation, translating the concept of ‘junk food’ into operational policy, the legal landscape, and reported uneven impacts across industry stakeholders. Political challenges included designing a policy the public views as appropriate, balancing health and financial impacts, and the perceived influence of political motivations. Consultation during policy development and close communication with industry reportedly facilitated implementation, as did the development of an exceptions process that provided a review pathway for HFSS products that might not contribute to children's HFSS consumption. Findings suggest that restricting the outdoor advertisement of HFSS foods and beverages at scale is feasible within a complex policy and business landscape. We outline practical steps that may further facilitate the development and implementation of similar policies and we report on the importance of ensuring such policies are applied in a way that is perceived as reasonable by industry and the public.

Avoiding Catastrophe: Active Dendrites Enable Multi-Task Learning in Dynamic Environments

Abstract: A key challenge for AI is to build embodied systems that operate in dynamically changing environments. Such systems must adapt to changing task contexts and learn continuously. Although standard deep learning systems achieve state of the art results on static benchmarks, they often struggle in dynamic scenarios. In these settings, error signals from multiple contexts can interfere with one another, ultimately leading to a phenomenon known as catastrophic forgetting. In this article we investigate biologically inspired architectures as solutions to these problems. Specifically, we show that the biophysical properties of dendrites and local inhibitory systems enable networks to dynamically restrict and route information in a context-specific manner. Our key contributions are as follows: first, we propose a novel artificial neural network architecture that incorporates active dendrites and sparse representations into the standard deep learning framework. Next, we study the performance of this architecture on two separate benchmarks requiring task-based adaptation: Meta-World, a multi-task reinforcement learning environment where a robotic agent must learn to solve a variety of manipulation tasks simultaneously; and a continual learning benchmark in which the model's prediction task changes throughout training. Analysis on both benchmarks demonstrates the emergence of overlapping but distinct and sparse subnetworks, allowing the system to fluidly learn multiple tasks with minimal forgetting. Our neural implementation marks the first time a single architecture has achieved competitive results in both multi-task and continual learning settings. Our research sheds light on how biological properties of neurons can inform deep learning systems to address dynamic scenarios that are typically impossible for traditional ANNs to solve.

Patient experience of the diagnosis and management of patellofemoral pain: A qualitative exploration.

Abstract: Background Patellofemoral pain (PFP) is common and long-term treatment outcomes are unsatisfactory. Qualitative exploration of diagnosis and management from the perspective of people with PFP is lacking. Objectives To inform care and improve intervention delivery by exploring the experience of people with patellofemoral pain (PFP) regarding diagnosis and management. Design Qualitative study with semi-structured interviews. Method Online recruiting yielded a convenience sample of participants with PFP for semi-structured interviews. Interviews were recorded, transcribed verbatim and analysed using thematic analysis until theoretical saturation by multiple investigators to determine themes and sub-themes. Results 12 participants were interviewed, with three themes identified; the value of diagnosis, the need for tailored (individualised) care, and the role of education. Participants viewed a diagnosis as essential to guide management, yet this was rarely provided, causing uncertainty about pain mechanisms; “it's nice to be told what it is that's wrong”. Interventions needed to be tailored to the individual as not all participants responded in the same way to treatment(s) or had the same needs; “everyone copes and reacts differently”. Finally, participants viewed education as essential to empower them to understand and manage the condition; “if I'd have been given more information, I think I'd know how to deal with it more”. Conclusions The overarching narrative from three themes was a desire for clearly communicated personalised care that meets individual needs. People with PFP desire a diagnosis to explain their pain, tailored interventions, and appropriate education to optimise their experience and outcomes.

The effect of alterations of schizophrenia-associated genes on gamma band oscillations

Abstract: Abnormalities in the synchronized oscillatory activity of neurons in general and, specifically in the gamma band, might play a crucial role in the pathophysiology of schizophrenia. While these changes in oscillatory activity have traditionally been linked to alterations at the synaptic level, we demonstrate here, using computational modeling, that common genetic variants of ion channels can contribute strongly to this effect. Our model of primary auditory cortex highlights multiple schizophrenia-associated genetic variants that reduce gamma power in an auditory steady-state response task. Furthermore, we show that combinations of several of these schizophrenia-associated variants can produce similar effects as the more traditionally considered synaptic changes. Overall, our study provides a mechanistic link between schizophrenia-associated common genetic variants, as identified by genome-wide association studies, and one of the most robust neurophysiological endophenotypes of schizophrenia.

Edge security for SIP-enabled IoT devices with P4

Abstract: The exponential growth of IoT devices poses security concerns, in part because they provide a fertile breeding ground for botnets . For example, the Mirai botnet infected almost 65,000 devices in its first 20 h. With the prevalence of Session Initiation Protocol (SIP) phones and devices on the networks today, the attacker could easily target and recruit these IoT devices as bots. Conventional network security measures do not provide adequate attack prevention, detection, and mitigation for these widely distributed IoT devices. This paper presents microVNF, a Virtualized Network Function (VNF) that leverages the programmable data plane feature on the edge switch. Based on knowledge gained from the Mirai botnet incident and following the defense-in-depth principle, microVNF protects IoT devices against SIP DDoS attacks in two stages: before and after infection. Prior to infection, it protects against SIP scanning, enumeration, and dictionary attacks. After infection, microVNF blocks botnet registration attempts to the command-and-control (CNC) server, thereby preventing the botnet from receiving commands sent from the CNC server, and detects and mitigates botnet SIP DDoS attacks. We conducted six experiments that involved using popular attack tools against microVNF, and it successfully performed deep-packet inspection of unencrypted SIP packets so as to track anomalies from a typical SIP state-machine. In this use case, besides providing physical connectivity to the IoT devices, the edge switch containing microVNF also provides the first line of defense in stopping malicious packets from propagating upstream to the core network. In addition to securing SIP, the microVNF approach can be adapted to other text-based, application-layer protocols such as HTTP and SMTP. MicroVNF leverages the native capability of programmable data planes without depending on external devices, thereby making this approach practical for securing edge-computing environments against application-layer attacks.

Simulation and field campaign evaluation of an optical particle counter on a fixed-wing UAV

Abstract: Abstract. Unmanned aerial vehicles (UAVs) have great potential to be utilised as an airborne platform for measurement of atmospheric particulates and droplets. In particular, the spatio-temporal resolution of UAV measurements could be of use for the characterisation of aerosol, cloud, and radiation (ACR) interactions, which contribute to the largest uncertainty in the radiative forcing of climate change throughout the industrial era (Zelinka et al., 2014). UAV-instrument combinations must be extensively validated to ensure the data are repeatable and accurate. This paper presents an evaluation of a particular UAV-instrument combination: the FMI-Talon fixed-wing UAV and the UCASS open-path optical particle counter. The performance of the UCASS was previously evaluated on a multi-rotor airframe by Girdwood et al. (2020). However, fixed-wing measurements present certain advantages – namely endurance, platform stability, and maximum altitude. Airflow simulations were utilised to define limiting parameters on UAV sampling – that is, an angle of attack limit of 10∘ and a minimum airspeed of 20 m s−1 – which were then applied retroactively to field campaign data as rejection criteria. The field campaign involved an inter-comparison with reference instrumentation mounted on a research station, which the UAV flew past. Cloud droplets were considered the ideal validation particle; since the underlying Mie assumptions used to compute droplet radius were more valid, future work will focus on the instrument response to aerosol particles. The effective diameter measured by the UAV largely agreed within 2 µm. The droplet number concentration agreed within 15 % on all but five profiles. It was concluded that UCASS would benefit from a mechanical redesign to avoid calibration drifts, and UAV attitude variations during measurement should be kept to a minimum.

Elaboration of Whey Protein-Based Films in Food Products: Emphasis on the Addition of Natural Edible Bio-nanocomposites With Antioxidant and Antimicrobial Activity

Abstract: Food spoilage is one of the major elements of food insecurity that has acquired significant attention over recent decades due to global human population growth. Several studies have investigated increasing shelf life of food products using natural and environmentally friendly compounds. Whey protein (WP) can be an important additive material because it is well-known for its high value of nutrition and well characteristics for the formation of edible films. Furthermore, natural bioactive compounds have been incorporated with WP-based films to confer their antioxidant and antimicrobial activities. Herein, nanotechnology has been effectively potentiated the antimicrobial and antioxidant properties of WP films. A wide range of bioactive agents has been embedded in the WP films, such as essential oils (EOs), TiO2, nano-clay, and even lactic acid bacteria. The current paper reviews the antioxidant and antimicrobial effects of different types of WP films and their applications in food products. This study also discussed the impact of WP films on shelf life, chemical and microbiological quality indices of meats, processed meats, poultry meat products, and fish.

The hypersimplex canonical forms and the momentum amplituhedron-like logarithmic forms

Abstract: In this paper we provide a formula for the canonical differential form of the hypersimplex $\Delta_{k,n}$ for all $n$ and $k$. We also study the generalization of the momentum amplituhedron $\mathcal{M}_{n,k}$ to $m=2$, and we conclude that the existing definition does not possess the desired properties. Nevertheless, we find interesting momentum amplituhedron-like logarithmic differential forms in the $m=2$ version of the spinor helicity space, that have the same singularity structure as the hypersimplex canonical forms.

These six countries are about to go to the Moon — here’s why

Abstract: Japan, South Korea, Russia, India, the United Arab Emirates and the United States aim to send missions to the Moon in the next year. But will they all make it? Japan, South Korea, Russia, India, the United Arab Emirates and the United States aim to send missions to the Moon in the next year. But will they all make it?

Accelerated discharge after aseptic revision knee arthroplasty is not associated with early readmission and reoperation

Abstract: Aims In the last decade, perioperative advancements have expanded the use of outpatient primary total knee arthroplasty (TKA). Despite this, there remains limited data on expedited discharge after revision TKA. This study compared 30-day readmissions and reoperations in patients undergoing revision TKA with a hospital stay greater or less than 24 hours. The authors hypothesized that expedited discharge in select patients would not be associated with increased 30-day readmissions and reoperations. Methods Aseptic revision TKAs in the National Surgical Quality Improvement Program database were reviewed from 2013 to 2020. TKAs were stratified by length of hospital stay (greater or less than 24 hours). Patient demographic details, medical comorbidities, American Society of Anesthesiologists (ASA) grade, operating time, components revised, 30-day readmissions, and reoperations were compared. Multivariate analysis evaluated predictors of discharge prior to 24 hours, 30-day readmission, and reoperation. Results Of 21,610 aseptic revision TKAs evaluated, 530 were discharged within 24 hours. Short-stay patients were younger (63.1 years (49 to 78) vs 65.1 years (18 to 94)), with lower BMI (32.3 kg/m 2 (17 to 47) vs 33.6 kg/m 2 (19 to 54) and lower ASA grades. Diabetes, chronic obstructive pulmonary disease, hypertension, and cancer were all associated with a hospital stay over 24 hours. Single component revisions (56.8% (n = 301) vs 32.4% (n = 6,823)), and shorter mean operating time (89.7 minutes (25 to 275) vs 130.2 minutes (30 to 517)) were associated with accelerated discharge. Accelerated discharge was not associated with 30-day readmission and reoperation. Conclusion Accelerated discharge after revision TKA did not increase short-term complications, readmissions, or reoperations. Further efforts to decrease hospital stays in this setting should be evaluated. Cite this article: Bone Joint J 2022;104-B(12):1323–1328.