6664 research outputs found
Sort by
An Ensemble Learning Method for Emotion Charting Using Multimodal Physiological Signals
Get PDFEmotion charting using multimodal signals has gained great demand for stroke-affected patients, for psychiatrists while examining patients, and for neuromarketing applications. Multimodal signals for emotion charting include electrocardiogram (ECG) signals, electroencephalogram (EEG) signals, and galvanic skin response (GSR) signals. EEG, ECG, and GSR are also known as physiological signals, which can be used for identification of human emotions. Due to the unbiased nature of physiological signals, this field has become a great motivation in recent research as physiological signals are generated autonomously from human central nervous system. Researchers have developed multiple methods for the classification of these signals for emotion detection. However, due to the non-linear nature of these signals and the inclusion of noise, while recording, accurate classification of physiological signals is a challenge for emotion charting. Valence and arousal are two important states for emotion detection; therefore, this paper presents a novel ensemble learning method based on deep learning for the classification of four different emotional states including high valence and high arousal (HVHA), low valence and low arousal (LVLA), high valence and low arousal (HVLA) and low valence high arousal (LVHA). In the proposed method, multimodal signals (EEG, ECG, and GSR) are preprocessed using bandpass filtering and independent components analysis (ICA) for noise removal in EEG signals followed by discrete wavelet transform for time domain to frequency domain conversion. Discrete wavelet transform results in spectrograms of the physiological signal and then features are extracted using stacked autoencoders from those spectrograms. A feature vector is obtained from the bottleneck layer of the autoencoder and is fed to three classifiers SVM (support vector machine), RF (random forest), and LSTM (long short-term memory) followed by majority voting as ensemble classification. The proposed system is trained and tested on the AMIGOS dataset with k-fold cross-validation. The proposed system obtained the highest accuracy of 94.5% and shows improved results of the proposed method compared with other state-of-the-art methods
Malware Detection in Internet of Things (IoT) Devices Using Deep Learning
Get PDFInternet of Things (IoT) devices usage is increasing exponentially with the spread of the internet. With the increasing capacity of data on IoT devices, these devices are becoming venerable to malware attacks; therefore, malware detection becomes an important issue in IoT devices. An effective, reliable, and time-efficient mechanism is required for the identification of sophisticated malware. Researchers have proposed multiple methods for malware detection in recent years, however, accurate detection remains a challenge. We propose a deep learning-based ensemble classification method for the detection of malware in IoT devices. It uses a three steps approach; in the first step, data is preprocessed using scaling, normalization, and de-noising, whereas in the second step, features are selected and one hot encoding is applied followed by the ensemble classifier based on CNN and LSTM outputs for detection of malware. We have compared results with the state-of-the-art methods and our proposed method outperforms the existing methods on standard datasets with an average accuracy of 99.5%
Comparing abuse profiles, contexts and outcomes of help-seeking heterosexual male and female victims of domestic violence: part II – exit from specialist services
Get PDFThe present study represents the second part of a two-part project that has sought to explore the demographic characteristics, assessment of abuse risks, and provision needs of service users of specialist Domestic Violence and Abuse (DVA) services in the United Kingdom (UK; see Hine et al., in press for Part 1). The current study utilised a large-scale quantitative data set of 27,876 clients (734 men and 27,142 women) exiting from specialist DVA services within the UK between 2007 and 2017. Across the sample there were significant reductions in abuse upon discharge from services, with most participants no longer living with their abusive partner. There were some significant differences between male and female clients, but most had small or negligible effect sizes. For example, men were more likely to be still living with their abuser (twice as many men as women), and for those not living together men were more likely to report ongoing contact. Women were found to have significantly higher reported rates of improved quality of life and overall safety. The findings are discussed in line with recommendations for future research and practice, including the more widespread commissioning of “gender inclusive” provision which acknowledges differential risks associated with male and female clients
Factors affecting dementia care practitioners’ decision‐making on moves to a care home for persons living with dementia: a factorial survey
Get PDFDeciding if and when might be the ‘optimal’ time for a person living with dementia to move to a care home is often difficult for the individual, family and practitioners. In this study, we describe the outcome of a factorial survey conducted with 100 dementia care practitioners (a frontline health or social care worker who works with people living with dementia) in England, which investigated factors used in deciding when a person living with dementia moves to a care home. Using findings from qualitative interviews with older people living with dementia, family carers, care home managers and social workers, we identified four factors that appeared to influence the decision to move to a care home: (1) Family carers’ ability to support the person with daily activities, (2) amount of support provided by home care workers, (3) level of risk of harm and (4) the person living with dementia's wishes. These factors were then randomised within skeleton vignettes that told the story of a fictitious woman (Jane) living with dementia at home with her husband. Fifty-four variations of the vignettes were produced and randomly assigned to 100 surveys. A total of 100 volunteer dementia care practitioners (78% female, 54% over 50 years of age) received their own personalised online survey link via email and were asked to read each vignette and decide whether to suggest Jane (a) move to a care home or (b) continue living at home. Results indicated that Jane's wishes principally drove most dementia care practitioners’ decision on whether to suggest a move to a care home or stay living at home (odds ratio = 6.5–19.5). Findings will inform a better understanding of the factors that contribute toward a decision to move to a care home and be of relevance to policy, practice, training and support
Reviewing the impacts of climate change on air transport operations
Get PDFClimate change is increasing global-mean tropospheric temperatures, but the localised trends are uneven, including cooling the lower stratosphere and lifting the tropopause. The wind speeds are also being modified, both at the surface and aloft. A further effect, additional to wind and temperature alone, is of increasing fluctuations and severity of extreme weather. These are impacting air transport, and this will continue. The effects are known to include increased take-off distances where excess runway lengths exist and reduced payloads where they do not, increased en-route flight times, increased frequency and severity of encounters with clear air turbulence in some regions, changed patterns of wildlife — particularly bird — activity in some regions (potentially also for other anthropogenic reasons) are shifting locations of flight safety hazards, and increased burdens upon airport and associated infrastructure. There is increasing understanding and acknowledgment by companies and authorities of these effects and the importance of mitigating them, although this is not universal and there are as yet no universally understood best practices for air transport climate change mitigation
The effect of occupant behaviour on the performance gap: UK residential case studies
Get PDFStudies have shown that the assumptions used to create dynamic thermal models of buildings do not reflect their actual energy use. This is known as the energy performance gap. Bridging the energy performance gap is vital in ensuring that a designed or retrofitted building meets the energy performance targets that are set at the beginning of a project. Using thermal analysis simulation software Tas, this paper presents a simulation model of seven different UK single family houses. The results from the various models are validated by comparing the actual energy consumption (as obtained from energy bills) against the simulated consumption. The simulation results show that the heating set point has the greatest impact on the simulated energy consumption out of the other investigated factors. The results also demonstrate that the energy consumption of the dwellings can be reduced by appropriately applying window opening schemes and by controlling the heating setpoint temperature and schedule. Plug load consumption is also considered within this study by using plug load data of real UK households as obtained from a longitudinal study and calibrating the model based on average plug load contributions for the various households. The results showed that by increasing the heating set point and heating and window opening schedules by 10% from self-reported data and by also considering an additional 12% for plug loads the energy performance gap is reduced to less than >15% for all examined houses
Analysis of the binding selectivity and inhibiting mechanism of chlorogenic acid isomers and their interaction with grass carp endogenous lipase using multi-spectroscopic, inhibition kinetics and modeling methods
Get PDFPolyphenols are inhibitors for lipase, but the binding selectivity and mechanism of polyphenol isomers and how they interact with lipase are not clear. Here, chlorogenic acid (CGA) isomers, neochlorogenic acid (NCGA) and cryptochlorogenic acid (CCGA) were used to explore the binding selectivity and mechanism of lipase. An inhibition assay indicated that both CGA isomers had dose-dependent inhibitory effects on lipase; however, the inhibitory effect of NCGA was better (IC50: 0.647 mg/mL) than that of CCGA (IC50: 0.677 mg/mL). NCGA and CCGA formed complexes with lipase at a molar ratio of 1:1, and the electrostatic interaction force plays a major role in the lipase–CCGA system. Molecular dynamics studies demonstrated that NCGA had a greater impact on the structure of lipase. The multi-spectroscopic and modeling results explained the effects of micro-structural changes on the binding site, the interaction force and the inhibition rate of the isomers when they combined with lipase
Assessing the failures in water distribution networks using a combination of geographic information system, EPANET 2, and descriptive statistical analysis: a case study
Get PDFNowadays, issues related water are considered one of the most significant and vital problems in human societies. One of the fundamental branches of the water crisis is the distribution network-related problems. The present study attempted to extract, classify and verify the failure data obtained from the Preventive Maintenance database of Birjand Water Distribution Network (WDN). The WDN was meshed in terms of the rate of failures using a combination of Geographic Information Systems (GIS) and EPANET 2. Then it was assessed by using the descriptive statistical analysis method. Investigations revealed that the middle sections of WDN involved the highest rate of failures. Furthermore, the investigations demonstrated that from 2011 to 2016 the highest rate of failures per kilometer per year ranged in range of 0.6 to 1.8 which involved the highest aggregation for all cells. In this regard, the highest intensity aggregation of occurrence rate in 2011 was estimated as 1.4 to 1.8, while in 2012, 2013, and 2016 it was estimated as 1-1.4 and finally in 2014 and 2015, estimations showed an interval of 0.6-1
Systematic use of transport infrastructure non-destructive assessment and remote sensing
Get PDFFor decades, remote sensing technologies and the non-destructive testing (NDT) methods have been used for the assessment of transport infrastructure, highways, railways and airfields. The existence of provisions of multi-source, multi-scale and multi-temporal based information on infrastructure conditions on one hand and the developments of hardware and software technologies in the other, have provided opportunities for the growth of the applications of NDT techniques. The outcome lends itself to be incorporated into existing infrastructure management models. This paper presents an overview of the latest developments in ground-based (Ground Penetrating Radar (GPR) and interferometric radar systems) and satellite (space-borne Synthetic Aperture Radar (SAR) interferometry) remote sensing that applied to transport infrastructures. The applications of GPR to pavements, e.g. multi-layered pavement structure and asphalt concrete (AC) density, and rail-tracks, e.g. ballast assessment are discussed. In addition, the applicability of ground-based radar interferometry and SAR for the bridge structural health monitoring and horizontal transport infrastructure is presented. A novel integrated approach is introduced to form the base of a novel intelligent transport infrastructure management system. The approach is aimed utilizing the structure condition assessment-based information collected using SAR and NDT techniques to prioritize maintenance/rehabilitation activities of transportation assets. For example, analyses of multi-temporal SAR data are used to identify areas of concern at the network level (e.g. differential settlements at bridge approaches or rail track-beds, and excessive deformation rate of pavement surface). The identified locations would be further assessed using ground-based techniques to collect more accurate data. This approach would provide an effective, efficient, and sustainable state of good repair over the life cycle of the transportation infrastructure system
Optimising exome prenatal sequencing services (EXPRESS): a study protocol to evaluate rapid prenatal exome sequencing in the NHS genomic medicine service
Get PDFBackground: Prenatal exome sequencing (ES) for the diagnosis of fetal anomalies has been implemented nationally in England through the NHS Genomic Medicine Service that is based around seven regional Genomic Laboratory Hubs (GLHs). Prenatal ES has the potential to significantly improve NHS prenatal diagnostic services by increasing genetic diagnoses and informing prenatal decision-making. Prenatal ES has not previously been offered routinely in a national healthcare system and there are gaps in knowledge and guidance.
Methods: We are conducting a mixed-methods evaluation of the NHS prenatal ES service. Study design draws on a framework developed in previous studies of major system innovation and Normalisation Process Theory. There are five interrelated workstreams. Workstream-1 will use interviews and surveys with professionals, non-participant observations and documentary analysis to produce in-depth case studies at all GLHs. Data collection at multiple time points will track changes over time. In Workstream-2 qualitative interviews with parents offered prenatal ES or with previous experience of fetal anomalies will explore experiences and establish information and support needs. Workstream-3 will analyse data from all prenatal ES tests for nine-months to establish service outcomes (e.g. diagnostic yield, referral rates, referral sources). Comparisons between GLHs will identify factors (individual or service-related) associated with any variation in outcomes. Workstream-4 will identify and analyse practical ethical problems. Requirements for an effective ethics framework for an optimal and equitable service will be determined. Workstream-5 will assess costs and cost-effectiveness of prenatal ES versus standard tests and evaluate costs of implementing an optimal prenatal ES care pathway. Integration of findings will determine key features of an optimal care pathway from a service delivery, parent and professional perspective.
Discussion: The proposed formative and summative evaluation will inform the evolving prenatal ES service to ensure equity of access, high standards of care and benefits for parents across England