12560 research outputs found
Sort by
Weak relation enforcement for kinematic-informed long-term stock prediction with artificial neural networks
No full textWe propose loss function week enforcement of the velocity relations between time-series points in the Kinematic-Informed artificial Neural Networks (KINN) for long-term stock prediction. Problems of the series volatility, Out-of-Distribution (OOD) test data, and outliers in training data are addressed by (Artificial Neural Networks) ANN’s learning not only future points prediction but also by learning velocity relations between the points, such a way as avoiding unrealistic spurious predictions. The presented loss function penalizes not only errors between predictions and supervised label data, but also errors between the next point prediction and the previous point plus velocity prediction. The loss function is tested on the multiple popular and exotic AR ANN architectures, and around fifteen years of Dow Jones function demonstrated statistically meaningful improvement across the normalization-sensitive activation functions prone to spurious behaviour in the OOD data conditions. Results show that such architecture addresses the issue of the normalization in the auto-regressive models that break the data topology by weakly enforcing the data neighbourhood proximity (relation) preservation during the ANN transformation.</p
High-quality AFM image acquisition of living cells by modified residual encoder-decoder network
No full textAtomic force microscope enables ultra-precision imaging of living cells. However, atomic force microscope imaging is a complex and time-consuming process. The obtained images of living cells usually have low resolution and are easily influenced by noise leading to unsatisfactory imaging quality, obstructing the research and analysis based on cell images. Herein, an adaptive attention image reconstruction network based on residual encoder-decoder was proposed, through the combination of deep learning technology and atomic force microscope imaging supporting high-quality cell image acquisition. Compared with other learning-based methods, the proposed network showed higher peak signal-to-noise ratio, higher structural similarity and better image reconstruction performances. In addition, the cell images reconstructed by each method were used for cell recognition, and the cell images reconstructed by the proposed network had the highest cell recognition rate. The proposed network has brought insights into the atomic force microscope-based imaging of living cells and cell image reconstruction, which is of great significance in biological and medical research.</p
A multidisciplinary hyper-modeling scheme in personalized in silico oncology:coupling cell kinetics with metabolism, signaling networks, and biomechanics as plug-in component models of a cancer digital twin
Get PDFThe massive amount of human biological, imaging, and clinical data produced by multiple and diverse sources necessitates integrative modeling approaches able to summarize all this information into answers to specific clinical questions. In this paper, we present a hypermodeling scheme able to combine models of diverse cancer aspects regardless of their underlying method or scale. Describing tissue-scale cancer cell proliferation, biomechanical tumor growth, nutrient transport, genomic-scale aberrant cancer cell metabolism, and cell-signaling pathways that regulate the cellular response to therapy, the hypermodel integrates mutation, miRNA expression, imaging, and clinical data. The constituting hypomodels, as well as their orchestration and links, are described. Two specific cancer types, Wilms tumor (nephroblastoma) and non-small cell lung cancer, are addressed as proof-of-concept study cases. Personalized simulations of the actual anatomy of a patient have been conducted. The hypermodel has also been applied to predict tumor control after radiotherapy and the relationship between tumor proliferative activity and response to neoadjuvant chemotherapy. Our innovative hypermodel holds promise as a digital twin-based clinical decision support system and as the core of future in silico trial platforms, although additional retrospective adaptation and validation are necessary.</p
Energy efficiency and interoperability through O-RAN Rapid Transition Protocol (ORTP)
No full textMobile network traffic is increasing accompanied by increased energy consumption. Traditional Radio Access Networks (RANs) have been used for decades as the foundation of mobile communications, providing mobile customers with reliable voice and data services. However, they encounter obstacles in terms of scalability, adaptability, and cost-effectiveness. Next-generation wireless networks need efficient Radio Access Network (RAN) solutions to achieve low latency and high throughput. The Open RAN (O-RAN) architecture is a potential solution for 5G and beyond networks due to its open interfaces, disaggregated network entities and services, network hardware and software virtualization, and intelligent control. Traditionally standard RAN accounts for the bulk of mobile network energy consumption, leading towards higher Operational expenditure (OPEX) costs. In the context of cellular networks. Handover strategies need careful development to cater for efficient resource usage as well as overall system energy efficiency. O-RAN Rapid Transition Protocol (ORTP) presented in this paper employs minimum value of handover margin (HOM) and is aimed at increased energy efficiency. 5G based System level simulations have been performed to investigate the efficacy of ORTP for key performance indicators including handover probability, Radio Link Failure, connection density, ping pong effect and dynamic power consumption. It is found that the usage of lower HOM values provide noticeable achievement in terms of power consumption, thereby rendering ORTP around 20 % more efficient compared to 5G networks, while keeping it interoperable.<br/
Landscape of practice learning
No full textThis opening chapter attempts to introduce the reader to the nature of practice learning as a living landscape of key features that determine supervisors’ and learners’ engagement with learning, including the nature of knowledge, boundaries and terrains that characterise the learning journey. It is argued that practice and work-based learning need to be understood as similar but distinct fields by supervisors, assessors and educators who need to be committed to the wellbeing of students and apprentices through the provision of a compassionate practice learning environment.</p
Data-driven decision support systems in e-governance:leveraging AI for policymaking
No full textData-driven decision support systems have been used more and more in e-governance as a result of the digital revolution. In order to improve the efficacy and efficiency of policymaking, this research article investigates the integration of artificial intelligence (AI) approaches into e-governance systems. Governments can access enormous volumes of data, and AI algorithms are used to analyze and extract insightful data that enables decision-making based on facts. The article emphasizes the advantages of using AI in the e-governance space while formulating policy. Decision support systems can analyze and understand complicated information by utilizing cutting-edge machine learning and data analytics approaches, revealing trends, patterns, and correlations that would be challenging for human analysts to manually find. As a result, decision-makers in government may make well-informed choices based on impartial research and data. The paper also examines the difficulties and factors to be considered when implementing AI in decision support systems for e-governance. With an emphasis on the significance of responsible AI governance frameworks, ethical issues, including algorithmic bias, transparency, and accountability are addressed. The article also explores the effects of incorporating AI into decision-making processes, including potential sociopolitical effects and the requirement for stakeholder participation and public confidence. The results of this study show how data-driven decision support systems may revolutionize e-governance policies when equipped with AI technology. Governments may enhance their decision-making processes and the outcomes of governance by using the power of big data and sophisticated analytics. This will lead to better public service delivery
A study on the imobilization method of E. coli for AFM detection under physiological conditions
No full textThe micro-nano manipulation techniques based on Atomic Force Microscopy (AFM) is an important tool for studying the morphology and mechanical properties of bacteria under physiological conditions. However, immobilizing the bacteria on the substrate is the key obstacle for AFM detection in liquid condition. In this study, the methods of embedding and adsorption were combined to improve the immobilization efficiency. Compared to E. coli on a non-structured base surface, E. coli on a structured base surface appears more stretched out and is less likely to aggregate. It grown along the structure of the substrate, achieving nanomanipulation to a certain extent. This study will provide a new immobilization method for microorganism as well as E. coli.</p
Ten tips when instigating an assessment transformation programme
No full textHigher education is facing pressure to reform assessment. But how to get started? Steve Briggs offers 10 tip
Exploring justice tensions in the Barnahus model
Get PDFBarnahus is to support children and their families during the justice and recovery process from experiencing abuse or violence. Yet, many perspectives of justice exist in the multi-disciplinary systems involved in Barnahus. The intersection of these systems can cause tension, which affects service delivery and, ultimately, the experience of the justice and recovery journey. The purpose of this chapter is to outline the needs, rights, and responsibilities of those involved in Barnahus as key stakeholders, including children, their families, criminal justice professionals, social and health care professionals, and professionals working in non-governmental organisations (NGOs) that support children and families. We also discuss the justice-related tensions that arise in the Barnahus model and how Barnahus can situate and advance a child-friendly justice model.<br/
Data sources:
Access Repository Dashboard
Do you manage University of Bedfordshire Repository? Access insider analytics, issue reports and manage access to outputs from your repository in the CORE Repository Dashboard!