28579 research outputs found
Sort by
Advancing Skin Cancer Detection through Deep Learning and Fusion of Patient Metadata and Skin Lesion Images
Get PDFThere has been a significant rise in skin cancer incidence during the last three decades and the waiting time for skin lesion assessment in both the National Health Service ( NHS) and private sectors in the UK has increased significantly. Therefore, to reduce waiting time and to make a faster decision, there is a need to develop automated methods that can be used to classify whether a skin lesion is suspicious or non-suspicious during teledermatology triage. In this study, we propose an artificial intelligence ( AI) framework that uses patient metadata together with image data to classify skin lesions into suspicious or
non-suspicious categories. To evaluate our proposed approach, we collected 79,246 skin lesion images along with their 22 meta-features such as lesion size, lesion colour, lesion shape, patient age, and gender from 19,295 patients who attended a network of private skin cancer diagnostic centres across the UK. We developed three separate models for skin lesion classification: 1) an AI model using only metadata that achieved 85.24% sensitivity and 61.12% specificity; 2) an AI model using
only images that achieved 99.72% sensitivity and 63.22% specificity; and 3) a fused model based on both metadata and images that achieved 99.66% sensitivity and 74.45% specificity. The decisions of the developed AI models were then fused through a majority voting technique, which achieved a sensitivity of 99.50% and a specificity of 82.45%, significantly outperforming the state-of-the-art methods that rely solely on image data. Furthermore, we add a post-processing step to explain AI model decisions by implementing a soft-attention module that provides essential explainability and supports healthcare professionals in informed decision-making. The developed AI framework has great potential for the detection of suspicious skin lesions. With a reduction in patient referrals for possible biopsies, waiting times for skin cancer diagnosis and treatment will be shortened, resulting in improved outcomes
MmWave Radar Perception Learning using Pervasive Visual-Inertial Supervision
Get PDFThis paper introduces a radar perception learning framework guided by data collected from commonly equipped visual-inertial (VI) sensor suites on smart vehicles. Unlike existing approaches that rely on dense point clouds from 3D LiDARs, which are costly and not widely deployed, this method leverages the broader availability of VI data. However, visual images alone lack the ability to capture the three-dimensional motion of moving targets, which limits their effectiveness in supervising motion-related tasks. To overcome this limitation, the framework integrates multiple perception tasks such as odometry estimation, motion segmentation, and scene flow prediction into a unified learning process. The first component is an odometry estimation module that combines deterministic ego-motion models with data-driven learning results. This fusion helps accurately infer the scene flow of static background points while minimizing drift. The second component is a supervision signal extraction module that aligns optical and millimeter-wave radar measurements to guide the learning of radar scene flow and rigid transformations. This module improves the reliability of dynamic point supervision through joint constraints across sensing modalities. The third component introduces a feature-selection module designed for cross-modal learning. It enhances the accuracy of motion segmentation and enforces consistency between odometry and scene flow, resulting in more coherent radar perception outputs. Experimental evaluations show that this framework achieves superior performance in challenging conditions such as smoke-obscured environments. It surpasses state-of-the-art (SOTA) methods that depend on high-cost LiDAR systems
Narrow and general intelligence: embodied, self-referential social cognition and novelty production in humans, AI and robots
Get PDFIs Habermas a critical theorist? Continuities and discontinuities in the Frankfurt School
No full textIn this Chapter, I will explore the view that Habermas in his critique of Horkheimer and T.W. Adorno left behind not just their particular version of critical theory as it had emerged in the 1940s, but critical theory in the broad sense of a particularly self-reflective form of theorising that is carried out in the pursuit of social emancipation. Specifically, my suggestion will be that Habermas, in this critique, falls short especially of the self-reflective aspect of such an endeavour, despite sharing a commitment to that aspect
Des pyramides partout
No full textThis article analyzes the central role played today by Ponzi schemes and pump-and-dump mechanism. There’s a fine line between a financial claim and a deluded belief. The whole of Trump’s policy seems to be based on the ability to “pump” hopes of gains invested in vaporous entities (like shit-coins), which are then “dumped” before everyone realizes their inanity—not without having significantly redistributed the credits and debts of the various stakeholders in the process
Artificial intelligence and innovation in educational processes: for what?
Get PDFThe article examines the contradictions of capitalism and the role of Artificial Intelligence (AI) as an instrument for reproducing social inequalities and intensifying labor exploitation. The analysis situates technological hegemony as an expression of the structural crisis of capital and problematizes the advance of technocentrism and technological solutionism in education. It discusses how public policies and the emerging legal framework in Brazil, influenced by neoliberal logic, confront the structural precariousness of schools and deepen historical inequalities. Grounded in historical-dialectical materialism, the study proposes a counter-hegemonic teaching praxis aimed at the critical and collective appropriation of technology by teachers. This movement seeks to overcome alienation and to restore the autonomy and recognition of teaching workers as class subjects
Atlas Unplugged: Re-Imagining the Premises and Prospects of Capitalism for Business and Society
Get PDFAtlas Shrugged, Ayn Rand’s dystopian work of fiction, became a cornerstone of libertarian philosophy and its influence continues as an articulation of contemporary capitalism. In introducing this Special Issue, we revisit its core assumptions and contradictions in order to reimagine capitalism and reflect on the potential of management studies to contribute alternatives. These aspirations are reflected in the contributions. They discuss Indigenous views of capitalism, the ethics of care, insights from self-determination theory, the logic of marketization, and how capitalist institutions foster violence, racism, inequality, and environmental crisis. Building from these insights, we discuss the potential for future research to draw on a combined critical lens of place and intersectionality in developing systemic analyses of capitalism. Place situates action in its meaningful social and geographical spaces, recognizing the specific historical, political, and community relations through which global forces are (re-)produced and experienced. Intersectionality interrogates the capitalist system through various axes of identity to understand its consequences and inequalities. We use this framing to assess key aspects of contemporary capitalism: labour markets, globalization and global value chains, and access to resources. We then reflect on the prospects for alternative imaginings of capitalism and how management research might contribute to these
Cross-view identification based on gait bioinformation using a dynamic densely connected spatial-temporal feature decoupling network
Get PDFExisting cross-view identification methods based on gait bioinformation often overlook the importance of feature reuse and the decoupling of spatial–temporal features in gait data. To address these challenges, we propose a novel approach named the Dynamic Densely connected Spatial-Temporal feature decoupling Network (DDSTFDN). First, the continuous gait sequence data are preprocessed by cropping and normalization before being fed into an initial network module to extract shallow gait features. These shallow features are then processed by the dynamic dense spatial–temporal decoupling network, which includes densely connected spatial–temporal feature decoupling blocks and enhanced convolutional block attention modules (E-CBAM) to obtain decoupled spatial–temporal features. Finally, the resultant gait features are divided into probe features and gallery features for similarity calculation, enabling accurate classification. Our approach achieves recognition accuracies of 97.2 % and 87.6 % for the normal walking (NM) conditions of the CASIA-B and OUMVLP datasets, respectively, as well as 93.4 % and 78.1 % recognition accuracies in the walking with a backpack (BG) and walking with a coat or jacket (CL) walking complex scenarios in the CASIA-B dataset. In addition, our method obtains a recognition accuracy of up to 98.6 % on the CASIA-C dataset. On the CASIA-B dataset, we outperform the current baseline by 3.9 percentage points in accuracy for a batch size of 4 × 8, achieving a level of recognition comparable to that of the state-of-the-art (SOTA) approaches. The above experimental results demonstrate that DDSTFDN can effectively improve recognition accuracy and reduce resource consumption
How to use Generative AI to Assist the Analysis of Qualitative Data [How-to Guide]
Get PDFThis guide discusses the use of Generative Artificial Intelligence (GenAI) tools in qualitative analysis. There is a growing body of research which has used programmes like ChatGPT and other OpenAI software to analyse qualitative data. This has been justified because GenAI can produce summaries of large amounts of data which resemble human-created output. This guide offers an overview of the options available to researchers and discusses some of the implications of their use. There is an active debate about whether such tools are appropriate and if so how to ethically and practically implement them into a qualitative analysis workflow. This guide argues that the human analyst remains central, with GenAI acting as a useful assistant. Technology will shape ‘how to do’ qualitative analysis and it is important for researchers to actively reflect upon the opportunities and challenges of using these tools within their practice
A Metric for the Entropic Purpose of a System
Get PDFPurpose in systems is considered to be beyond the purview of science since it is thought to be intrinsically personal. However, just as Claude Shannon was able to define an impersonal measure of information, so we formally define the (impersonal) ‘entropic purpose’ of an information system (using the theoretical apparatus of Quantitative Geometrical Thermodynamics) as the line integral of an entropic “purposive” Lagrangian defined in hyperbolic space across the complex temporal plane. We verify that this Lagrangian is well-formed: it has the appropriate variational (Euler-Lagrange) behaviour. We also discuss the teleological characteristics of such variational behaviour (featuring both thermodynamically reversible and irreversible temporal measures), so that a “Principle of Least (entropic) Purpose” can be adduced for any information-producing system. We show that entropic purpose is (approximately) identified with the information created by the system: an empirically measurable quantity. Exploiting the relationship between the entropy production of a system and its energy Hamiltonian, we also show how Landauer’s principle also applies to the creation of information; any purposive system that creates information will also dissipate energy. Finally, we discuss how ‘entropic purpose’ might be applied in artificial intelligence contexts (where degrees of system ‘aliveness’ need to be assessed), and in cybersecurity (where this metric for ‘entropic purpose’ might be exploited to help distinguish between people and bots)