Now showing items 21-40 of 9706

    • Biomaterials for breast reconstruction: Promises, advances, and challenges

      Abdul-Al, Mohamed; Zaernia, Amir; Sefat, Farshid (2020-11)
      Breast reconstruction is the opportunity that provides the chance of having breast after undergoing surgical removal of the breast tissue due to cancer-related surgery. However, this varies on the stage of the cancer diagnosis and the procedure undertaken. There are many regenerative medicine methods that provide several initiatives and direct solutions to problems such as the development of “bioactive tissue,” which can regenerate adipose tissues with similar normal functions and structures. There have been several studies which have previously explored for the improvement of breast reconstruction including different variations of biomaterials, different fabrication and processing techniques, cells as well as growth factors which enable bioengineers and tissue engineers to reconstruct a suitable breast for patients with breast cancer. Many factors such as shape, proper volume, mechanical properties have been studies but very scattered with not adequate solutions for existing patients worldwide. This review article aims to cover recent advances in biomaterials, which can be used for reconstruction of breasts as well as looking at the various factors that might lead to individuals needing reconstruction and the materials that are available. The focus would be to look at the various biomaterials that are available to use for reconstruction, their properties, and their structural integrity.
    • The feasibility of patient reported outcome measures for the care of penile cancer

      Branney, Peter; Walters, Elizabeth R.; Bryant, Eleanor J.; Hollyhead, Cyan; Njoku, K.; Vyas, L.; Modica, C.; Kayes, O.; Eardley, I.; Henry, A. (Wiley, 2022)
      When used in routine clinical practice, Patient Reported Outcomes Measures (PROMS) can give patients tacit approval to discuss embarrassing topics, which could be particularly useful for urological nursing. The aim of this study was to assess whether it would be feasible to use two such measures for penile cancer; one for body image (the Male Genital Self-Image Scale; MGSIS-5) and another for lymphedema (the Groin and Lower Limb Lymphedema questionnaire; G3L-20). Study packs were posted to penile cancer patients who had received (i) sentinel node biopsy only, (ii) inguinal node dissection only, and (iii) inguinal node dissection with post-operative radiotherapy with or without chemotherapy. The two measures (MGSIS-5 and G3L-20) were complemented with those specific to sexual function (IIEF) and cancer (EORTC-QLQ-C30 version 3) and a modified Lymphoedema Genitourinary Cancer Questionnaire (mLGUCQ). Twenty patients returned questionnaires. Validity and reliability analyses are presented but low participant numbers mean that results need treating with caution. Results show sufficient feasibility for the MGSIS-5 and the G3L-20 to warrant another study to attract larger numbers of participants, either over a longer time frame or at multiple sites. In these further studies, we would recommend adding (1) more Likert responses, (2) the timeframe to the MGIS and (3) exploring either the use of sexual desire psychometric measures or the addition of sexual desire items to the MGSIS for this patient group.
    • A prospective evaluation of the clinical safety and effectiveness of COVID-19 Urgent Eyecare Services across 5 areas in England

      Swystun, A.G.; Davey, Christopher J. (2022-01)
      Purpose: Although urgent primary eye care schemes exist in some areas of England, their current safety is unknown. Accordingly, the aim of the present study was to quantify the clinical safety and effectiveness of a COVID-19 Urgent Eyecare Service (CUES) across Luton, Bedford, Hull, East Riding of Yorkshire and Harrogate. Methods: Consenting patients with acute onset eye problems who had accessed the service were contacted to ascertain what the optometrist’s recommendation was, whether this worked, if they had to present elsewhere and how satisfied they were with the CUES. Results: 27% (170/629) and 6.3% (28/445) of patients managed virtually and in person, respectively, did not have their acute eye problem resolved. Regression analysis revealed that patients who attended a face-to-face consultation were 4.66 times more likely to be correctly managed (Exp (β) = 5.66), relative to those managed solely virtually. Optometrists phone consultations failed to detect conditions such as stroke, intracranial hypertension, suspected space occupying lesions, orbital cellulitis, scleritis, corneal ulcer, wet macular degeneration, uveitis with macular oedema and retinal detachment. Of referrals to hospital ophthalmology departments, in total, 19% were false-positives. Patients, however, were typically very satisfied with the service. Uptake was associated with socio-economic status. Conclusion: The present study found that a virtual assessment service providing optometrist teleconsultations was not effective at resolving patient’s acute-onset eye problems. The range and number of pathologies missed by teleconsultations suggests that the service model in the present study was detrimental to patient safety. To improve this, optometrists should follow evidence based guidance when attempting to manage patients virtually, or in person. For example, patients presenting with acute-onset symptoms of flashing lights and/or floaters require an urgent dilated fundus examination. Robust data collection on service safety is required on an ongoing basis.
    • Teachers' Perspectives on the Acceptability and Feasibility of Wearable Technology to Inform School-Based Physical Activity Practices

      Wort, G.K.; Wiltshire, G.; Peacock, O.; Sebire, S.; Daly-Smith, Andrew; Thompson, D. (2021-11-18)
      Background: Many children are not engaging in sufficient physical activity and there are substantial between-children physical activity inequalities. In addition to their primary role as educators, teachers are often regarded as being well-placed to make vital contributions to inclusive visions of physical activity promotion. With the dramatic increase in popularity of wearable technologies for physical activity promotion in recent years, there is a need to better understand teachers' perspectives about using such devices, and the data they produce, to support physical activity promotion in schools. Method: Semi-structured interviews were conducted with 26 UK-based primary school teachers, exploring their responses to children's physical activity data and their views about using wearable technologies during the school day. Interview discussions were facilitated by an elicitation technique whereby participants were presented with graphs illustrating children's in-school physical activity obtained from secondary wearable technology data. Interview transcripts were thematically analyzed. Results: Most teachers spoke positively about the use of wearable technologies specifically designed for school use, highlighting potential benefits and considerations. Many teachers were able to understand and critically interpret data showing unequal physical activity patterns both within-and between-schools. Being presented with the data prompted teachers to provide explanations about observable patterns, emotional reactions-particularly about inequalities-and express motivations to change the current situations in schools. Conclusion: These findings suggest that primary school teachers in the UK are open to integrating wearable technology for measuring children's physical activity into their practices and can interpret the data produced by such devices. Visual representations of physical activity elicited strong responses and thus could be used when working with teachers as an effective trigger to inform school practices and policies seeking to address in-school physical inactivity and inequalities.
    • A whole system approach to increasing children's physical activity in a multi-ethnic UK city: a process evaluation protocol

      Hall, Jennifer; Bingham, Daniel D.; Seims, Amanda; Dogra, Sufyan A.; Burkhardt, Jan; Nobles, J.; McKenna, J.; Bryant, M.; Barber, Sally E.; Daly-Smith, Andrew (2021-12-18)
      Engaging in regular physical activity requires continued complex decision-making in varied and dynamic individual, social and structural contexts. Widespread shortfalls of physical activity interventions suggests the complex underlying mechanisms of change are not yet fully understood. More insightful process evaluations are needed to design and implement more effective approaches. This paper describes the protocol for a process evaluation of the JU:MP programme, a whole systems approach to increasing physical activity in children and young people aged 5-14 years in North Bradford, UK. This process evaluation, underpinned by realist philosophy, aims to understand the development and implementation of the JU:MP programme and the mechanisms by which JU:MP influences physical activity in children and young people. It also aims to explore behaviour change across wider policy, strategy and neighbourhood systems. A mixed method data collection approach will include semi-structured interview, observation, documentary analysis, surveys, and participatory evaluation methods including reflections and ripple effect mapping. This protocol offers an innovative approach on the use of process evaluation feeding into an iterative programme intended to generate evidence-based practice and deliver practice-based evidence. This paper advances knowledge regarding the development of process evaluations for evaluating systems interventions, and emphasises the importance of process evaluation.
    • The Conforming, The Innovating and The Connecting Teacher: A qualitative study of why teachers in lower secondary school adopt physically active learning

      Øystein, L.; Tjomsland, H.E.; Leirhaug, P.E.; McKenna, J.; Quaramby, T.; Bartholomew, J.; Jenssen, E.S.; Daly-Smith, Andrew; Resaland, G.K. (2021-09)
      This paper explores why teachers adopt physically active learning (PAL). Data were collected through ‘go-alongs’ supplemented by individual interviews with 13 teachers in seven Norwegian lower secondary schools. Data were then analysed thematically. Results indicated that as well as to enhance their teaching and pupils' learning, teachers adopt PAL to adhere to school policy (The Conforming Teacher), to be an innovative educator (The Innovating Teacher), and, because it matches past positive personal experiences (The Connecting Teacher). The findings can be used to shape PAL teacher training programs to increase the likelihood of adoption.
    • Sedimentation and Consolidation of cohesive and non-cohesive soils formed under turbulent flows

      Mohamed, Mostafa H.A.; Pu, Jaan H.; Almabruk, Adam (University of BradfordFaculty of Engineering and Informatics, 2018)
      Settling and consolidation of suspended clay particles are significant issue in many fields such as geotechnical engineering, coastal and hydraulic engineering, and environmental engineering. A comprehensive literature review was conducted on the settling, consolidation and erosion of mixed soil material (cohesive and non-cohesive). Soil beds formed by sedimentation process of loose particles will be either show a segregated or homogeneous in structure, depending on the depositional environment. These sediments initially undergo self-weight consolidation and may be eroded under high flow rate. A number of studies have recently investigated the characteristic of consolidated clay bed in stagnant water. Hence, consolidation parameters were determined using a well-known vertical settling column consolidation test setup. However, limited research studies are available for deposition and consolidation of a mixture of sediment (clay, silt and sand) under flow conditions which are more representative of what happens in nature. A long flume and pump were used to create different turbulent conditions and simulate the natural process... The results for deposition and consolidation of different mixtures under stagnant and turbulence conditions were analyzed and compered in term of compressibility, permeability as well as shear strength. The results of this experimental research program indicated that the flow rate, initial concentration, height of settling and composition of sediment are all important factors that could affect the final bed dry unit weight. Two non-intrusive techniques were applied for measuring the dry unit weight at settling and consolidation stages. Impact echo technique has never been applied to measure the dry unit weight of self-weight consolidation along the vertical stratification of cohesive and non-cohesive particles. Also, a novel conductance sensor has been developed to improve the efficiency of this technique. The limitations of using these techniques will be highlighted in this study.
    • Effects of Graphene Oxide in vitro on DNA Damage in Human Whole Blood and Peripheral Blood Lymphocytes from Healthy individuals and Pulmonary Disease Patients: Asthma, COPD, and Lung Cancer

      Anderson, Diana; Najafzadeh, Mojgan; Amadi, Emmanuel E. (University of BradfordFaculty of Life Sciences, 2019)
      For the past few decades, the popularity of graphene oxide (GO) nanomaterials (NMs) has increased exceedingly due to their biomedical applications in drug delivery of anti-cancer drugs. Their unique physicochemical properties such as high surface area and good surface chemistry with unbound surface functional groups (e.g. hydroxyl - OH, carboxyl /ketone C=O, epoxy/alkoxy C-O, aromatic group C=C, etc) which enable covalent bonding with organic molecules (e.g. RNA, DNA) make GO NMs as excellent candidates in drug delivery nanocarriers. Despite the overwhelming biomedical applications, there are concerns about their genotoxicity on human DNA. Published genotoxicity studies on GO NMs were performed using non-commercial GO with 2-3 layers of GO sheets, synthesized in various laboratories with the potential for inter-laboratory variabilities. However, what has not been studied before is the effects of the commercial GO (15-20 sheets; 4-10% edge-oxidized; 1 mg/mL) in vitro on DNA damage in human whole blood and peripheral blood lymphocytes (PBL) from real-life patients diagnosed with chronic pulmonary diseases [asthma, chronic obstructive pulmonary disease (COPD), and lung cancer], and genotoxic endpoints compared with those from healthy control individuals to determine whether there are any differences in GO sensitivity. Thus, in the present study, we had characterized GO NMs using Zetasizer Nano for Dynamic Light Scattering (DLS) and zeta potential (ZP) in the aqueous solution, and electron microscopy using the Scanning Electron Microscope (SEM) and Transmission Electron Microscope (TEM) in the dry state, respectively. Cytotoxicity studies were conducted on human PBL from healthy individuals and patients (asthma, COPD, and lung cancer) using the Methylthiazolyldiphenyl-tetrazolium bromide (MTT) and Neutral Red Uptake (NRU) assays, respectively. The genotoxicity (DNA damage) and cytogenetic effects (chromosome aberration parameters) induced by GO NMs on human whole blood from healthy individuals and patients were studied using the Alkaline Comet Assay and Cytokinesis-blocked Micronucleus (CBMN) assay, respectively. Our results showed concentration-dependent increases in cytotoxicity, genotoxicity, and chromosome aberrations, with blood samples from COPD and lung cancer patients being more sensitive to DNA damage insults compared with asthma patients and healthy control individuals. Furthermore, the relative gene and protein expressions of TP53, CDKN1A/p21, and BCL-2 relative to GAPDH on human PBL were studied using the Reverse Transcription Quantitative Polymerase Chain Reaction (RT-qPCR) and Western Blot techniques, respectively. Our results have shown altered gene and protein expression levels. Specifically, GO-induced cytotoxicity, genotoxicity, and micronuclei aberrations were associated with TP53 upregulation - a biomarker of DNA damage - in both patients and healthy individuals. These effects show that GO NMs have promising roles in drug delivery applications when formulated to deliver drug payload to COPD and cancer cells. However, the fact that cytotoxicity, genotoxicity, chromosome instability, and gene/protein expressions - biomarkers of cancer risk - were observed in healthy individuals are of concern to public health, especially in occupational exposures at micro levels at the workplace.
    • Performance of Multimodal Biometric Systems Using Face and Fingerprint (Short Survey)

      Abdul-Al, Mohamed; Kyeremeh, George K.; Parchin, Naser O.; Abd-Alhameed, Raed A.; Qahwaji, Rami S.R.; Rodriguez, J. (2021-10-27)
      Biometric authentication is the science and engineering of assessing and evaluating bioinformatics from the human body in order to increase system security by providing reliable and accurate behaviors and classifiers for personal identification and authentication. Its solutions are widely used in industries, governments, and the military. This paper reviews the multimodal biometric systems that integrated both faces and fingerprints as well as shows which one has the best accuracy and hardware complexity with the methods and databases. Several methods have been used in multimodal biometric systems such as KNN (K-Nearest Neighbor), CNN (Convolutional Neural Network), PCA (Principal Component Analysis), and so on. A multimodal biometric system for face and fingerprints that uses an FoM (Figure of Merit) to compare and show between the articles the best accuracy that have used multimodal biometric system face and fingerprints methods. The best performance has been found is 99.43% by using the cascade multimodal method.
    • Strategic Decision-Making and Implementation in Public Organizations in the Gulf Cooperation Council: The Role of Procedural Rationality

      Al-Hashimi, K.; Weerakkody, Vishanth J.P.; Elbanna, S.; Schwarz, G. (Wiley, 2022)
      Based on Herbert Simon's conceptualization of bounded rationality, this study develops and tests an integrative model of the strategic decision-making process (SDMP) and outcomes in public organizations. The model integrates different SDMP dimensions—procedural rationality, intuition, participation, and constructive politics—and examines their impacts on the successful implementation of strategic decisions. Additionally, it analyzes the influence of implementation on the overall outcomes of strategic decisions. The model was tested with multi-source data on 170 strategic decisions collected from senior executives working in 38 public organizations in Qatar—a context in which studies on decision-making are rare. With the exception of intuition, this study shows a positive impact of all SDMP dimensions on the successful implementation and outcomes of strategic decisions. Successful implementation fully mediates the relationships between procedural rationality, participation, and constructive politics and the outcomes of strategic decision.
    • Demystifying Corporate Inertia Towards Transition to Circular Economy: A Management Frame of Reference

      Yamoah, F.A.; Sivarajah, Uthayasankar; Mahroof, Kamran; González Peña, I. (2022-02)
      We examine corporate inertia towards circularity transition using organisational case studies, observations, and qualitative interviews with business executives. The study explores how the values and beliefs of business leaders and managers promote or inhibit internal and external stakeholder engagement to enable transition to circular business models. We focus on four large UK food companies, conducting interviews with 11 senior managers. Rather than a lack of awareness of the circular economy (CE), the results demonstrate that business leaders are not persuaded by the short-to medium-term business case for a CE. There is misalignment between values and beliefs of business executives and the circularity values and goals of their organisations. The misaligned values and beliefs inhibit relevant stakeholder engagement for transitions to a CE with responsibility shifted to civil society and public institutions. Management commitment to circularity transitions are at best a sophisticated form of circularity greenwashing. The study further suggests a general lack of collective disposition to foster collaborations with sectoral and supply chain partners to engender circularity transitions due to the absence of any standard systems for CE performance indicators. Circularity education and training play a positive mediatory role in changing negative assumptions, including the promotion of managers' engagement with other relevant stakeholders to build synergies and strategies for CE systems. The findings contribute to understanding the dynamics of corporate inertia regarding transitions to CE and highlight the relevance of aligning the personal values and beliefs of top management with organisational, sectoral, and supply chain partners’ values and goals.
    • The Impact of Institutions on Innovation: Three Empirical Studies

      Wang, Chengang; Trivedi, Rohitkumar; Sharma, Abhijit; Abdin, Joynal (University of BradfordAccounting, Finance and Economics Research Centre, Faculty of Management, Law and Social Sciences, 2020)
      This thesis carries out empirical investigations of the possible impacts of institutions relating to different aspects of innovation, namely incremental innovation activities, collaborative research and development (R&D) activities and radical innovation outcomes. It comprises three studies. The first empirical study focuses on examining the impact of financial constraints and intellectual property rights (IPR) protection on incremental innovation. Using firm-level data from transition countries and employing a two-step probit model with endogenous regressors, this study provides evidence that both financing constraints and strong IPR protection are negatively associated with the incremental innovation activities of firms. Results also confirm that financing constraints faced by firms are significantly influenced by the overall levels of development of financial institutions within a country. The second empirical study looks at the effects of contracting institutions and intellectual property institutions on firms’ collaborative research and development (R&D) activities in developing and transition countries. By employing the Cragg double-hurdle model, this study finds that efficient contract enforcement has a positive effect on the likelihood of firms engaging in R&D partnership and the intensity of firms' expenditures on collaborative R&D. On the other hand, the decision of firms to participate in R&D partnerships and their level of expenditure on collaborative R&D are adversely affected by the strength of IPR protection. The third empirical study investigates the influences of a set of institutions on producing new-to-the-world technologies, as measured by patents. This study is conducted by using a large panel dataset of 98 developed and developing countries over a period of 23 years. Building on the idea production framework, the unconditional quantile regression (UQR) estimates of this study show that along with key research inputs (i.e., existing knowledge stock and resources devoted to R&D), the strength of IPR protection, quality of governance and functioning of financial institutions are also significant determinants of the patent output of a country. The UQR methodology also demonstrates that the effects of institutions on patent production are heterogeneous throughout the various quantiles of patent output distribution. This thesis, therefore, offers an example of how the new institutional economics (NIE) theory is applicable in analysing innovation performances. The findings of this thesis propose useful policy directions that can assist policymakers and managers in accelerating innovation and technological development.
    • Comparative Techno-Economic Analysis of Carbon Capture Processes: Pre-Combustion, Post-Combustion, and Oxy-Fuel Combustion Operations

      Kheirinik, M.; Ahmed, Shaab; Rahmanian, Nejat (MDPI, 2021-12-08)
      Evaluation of economic aspects is one of the main milestones that affect taking rapid actions in dealing with GHGs mitigation; in particular, avoiding CO2 emissions from large source points, such as power plants. In the present study, three kinds of capturing solutions for coal power plants as the most common source of electricity generation have been studied from technical and economic standpoints. Aspen HYSYS (ver.11) has been used to simulate the overall processes, calculate the battery limit, and assess required equipment. The Taylor scoring method has been utilized to calculate the costliness indexes, assessing the capital and investment costs of a 230 MW power plant using anthracite coal with and without post-combustion, pre-combustion, and oxy-fuel combustion CO2 capture technologies. Comparing the costs and the levelized cost of electricity, it was found that pre-combustion is more costly, to the extent that the total investment for it is approximately 1.6 times higher than the oxy-fuel process. Finally, post-combustion, in terms of maturity and cost-effectiveness, seems to be more attractive, since the capital cost and indirect costs are less. Most importantly, this can be applied to the existing plants without major disruption to the current operation of the plants.
    • Psychological processes in adapting to dementia: illness representations among the IDEAL cohort

      Clare, L.; Gamble, L.D.; Martyr, A.; Quinn, Catherine; Litherland, R.; Morris, R.G.; Jones, I.R.; Matthews, F.E. (2022)
      How people understand and adapt to living with dementia may influence well-being. Leventhal’s Common Sense Model (CSM) of Self-Regulation provides a theoretical basis for exploring this process. We used cross-sectional and longitudinal data from 1,109 people with mild-to-moderate dementia in the Improving the experience of Dementia and Enhancing Active Life (IDEAL) cohort. We elicited dementia representations (DRs) using the Representations and Adjustment to Dementia Index (RADIX), a validated measure based on the CSM, identified groups sharing distinct DR profiles, and explored predictors of group membership and associations with well-being, and whether problem-focused coping played a mediating role in these associations. We identified four DR classes: people who see the condition as a disease and adopt a diagnostic label; people who see the condition as a disease but refer to symptoms rather than a diagnostic label; those who see the condition as part of aging; and those who are unsure how to make sense of the condition. A fifth group did not acknowledge any difficulties. “Disease” representations were associated with better cognition and younger age, while “aging” and “no problem” representations were associated with better mood and well-being. The association with well-being remained stable over 24 months. There was limited partial support for a mediating role of problem-focused coping. Variations in DRs may reflect individual differences in the psychological processes involved in adjusting to dementia. DRs provide a framework for personalizing and tailoring both communications about dementia and interventions aimed at supporting people in coping with dementia. There is a need to debate what constitutes a positive DR and how its development might be encouraged.
    • Functional Modelling of Systems with Multiple Operation Modes: Case Study on an Active Spoiler System

      Yildirim, Unal; Campean, I. Felician (SAE International, 2021-11)
      This article presents the application of the Enhanced Sequence Diagram (ESD) for the analysis of the functionality of a system with shape-changing aspects in the context of its multiple operational modes, considering an active rear spoiler as a case study. The article provides new insights on the ESD support for model-based capture and articulation of functional requirements across multiple operation modes of the same system, with appropriate detail on attributes and metrics, and the alignment of these attributes and metrics in line with the concept of time through scope lines. The article also provides a comprehensive argument and discussion, exemplified based on the case study, for the support that the ESD provides for early systems functional and architecture analysis, within the context of a broader model-based Failure Mode Analysis methodology.
    • Towards a resilience assurance model for robotic autonomous systems

      Campean, I. Felician; Kabir, Sohag; Dao, Cuong D.; Zhang, Qichun; Eckert, C. (2021-01)
      Applications of autonomous systems are becoming increasingly common across the field of engineered systems from cars, drones, manufacturing systems and medical devices, addressing prevailing societal changes, and, increasingly, consumer demand. Autonomous systems are expected to self-manage and self-certify against risks affecting the mission, safety and asset integrity. While significant progress has been achieved in relation to the modelling of safety and safety assurance of autonomous systems, no similar approach is available for resilience that integrates coherently across the cyber and physical parts. This paper presents a comprehensive discussion of resilience in the context of robotic autonomous systems, covering both resilience by design and resilience by reaction, and proposes a conceptual model of a system of learning for resilience assurance in a continuous product development framework. The resilience assurance model is proposed as a composable digital artefact, underpinned by a rigorous model-based resilience analysis at the system design stage, and dynamically monitored and continuously updated at run time in the system operation stage, with machine learning based knowledge extraction and validation.
    • A reliability inspired strategy for intelligent performance management with predictive driver behaviour: A case study for a diesel particulate filter

      Doikin, Aleksandr; Campean, I. Felician; Priest, Martin; Lin, C.; Angiolini, E. (2021-08)
      The increase availability of operational data from the fleets of cars in the field offers opportunities to deploy machine learning to identify patterns of driver behaviour. This provides contextual intelligence insight that can be used to design strategies for online optimisation of the vehicle performance, including compliance with stringent legislation. This paper illustrates this approach with a case study for a Diesel Particulate Filter, where machine learning deployed to real world automotive data is used in conjunction with a reliability inspired performance modelling paradigm to design a strategy to enhance operational performance based on predictive driver behaviour. The model-in-the-loop simulation of the proposed strategy on a fleet of vehicles showed significant improvement compared to the base strategy, demonstrating the value of the approach.
    • A Framework to Handle Uncertainties of Machine Learning Models in Compliance with ISO 26262

      Vasudevan, Vinod; Abdullatif, Amr; Kabir, Sohag; Campean, I. Felician (2022)
      Assuring safety and thereby certifying is a key challenge of many kinds of Machine Learning (ML) Models. ML is one of the most widely used technological solutions to automate complex tasks such as autonomous driving, traffic sign recognition, lane keep assist etc. The application of ML is making a significant contributions in the automotive industry, it introduces concerns related to the safety and security of these systems. ML models should be robust and reliable throughout and prove their trustworthiness in all use cases associated with vehicle operation. Proving confidence in the safety and security of ML-based systems and there by giving assurance to regulators, the certification authorities, and other stakeholders is an important task. This paper proposes a framework to handle uncertainties of ML model to improve the safety level and thereby certify the ML Models in the automotive industry.
    • A Model-Based Reliability Analysis Method Using Bayesian Network

      Kabir, Sohag; Campean, I. Felician (Springer, 2022)
      Bayesian Network (BN)-based methods are increasingly used in system reliability analysis. While BNs enable to perform multiple analyses based on a single model, the construction of robust BN models relies either on the conversion from other intermediate system model structures or direct analyst-led development based on experts input, both requiring significant human effort. This article proposes an architecture model-based approach for the direct generation of a BN model. Given the architectural model of a system, a systematic bottom-up approach is suggested, underpinned by failure behaviour models of components composed based on interaction models to create a system-level failure behaviour model. Interoperability and reusability of models are supported by a library of component failure models. The approach was illustrated with application to a case study of a steam boiler system.
    • Driver Behaviour Clustering Using Discrete PDFs and Modified Markov Algorithm

      Kartashev, K.; Doikin, A.; Campean, I. Felician; Uglanov, A.; Abdullatif, A.; Zhang, Q.; Angiolini, E.; aiR-FORCE project, funded as Proof of Concept by the Institute of Digital Engineering. (Springer, 2022)
      This paper presents a novel approach for probabilistic clustering, motivated by a real-world problem of modelling driving behaviour. The main aim is to establish clusters of drivers with similar journey behaviour, based on a large sample of historic journeys data. The proposed approach is to establish similarity between driving behaviours by using the Kullback-Leibler and Jensen-Shannon divergence metrics based on empirical multi-dimensional probability density functions. A graph-clustering algorithm is proposed based on modifications of the Markov Cluster algorithm. The paper provides a complete mathematical formulation, details of the algorithms and their implementation in Python, and case study validation based on real-world data.