1,721,046 research outputs found
Explainable deep learning for medical image processing: computer-aided diagnosis and robot-assisted surgery.
Full text linkThe recent advancements in the surging field of Deep Learning (DL) have revolutionized every sphere of life, and the healthcare domain is no exception. The enormous success of DL models, particularly with image data, has led to the development of several computeraided diagnosis and clinical support systems. These intelligent imaging systems can help physicians in numerous medical tasks including classification and staging of the various diseases, image-guided surgical procedures, and many more. Additionally, the proliferation of medical datasets has further facilitated the applications of DL techniques in healthcare realm. Moreover, all the perks DL offers are remarkable, however, DL architectures are typically blackbox, i.e. they hide the decision making mechanism, therefore, interpreting how the model arrived at a particular decision is hidden. Additionally, Convolutional Neural Networks (CNNs), which are most widely used DL techniques, are prone to adversarial examples, where small, imperceptible perturbations to the input data can cause the model to make incorrect predictions. These facts question the applicability of DL in healthcare sector where explainability holds paramount significance to build a trust on surging field of machine learning. The concept of eXplainable Artificial Intelligence (XAI) brings forward the possibility of explaining the results of DL models and reveals how the models produce results. These techniques aim to improve the transparency and interpretability of AI models, which can enhance trust in their results and facilitate their adoption in clinical practice. XAI approaches have the potential to advance the understanding of complex medical image analysis tasks and improve the reliability of AI-based diagnosis and treatment planning. The story does not end here, the XAI methods in the context of medical imaging generally produce saliency maps and compute feature importance to explain the results of DL models. The sensitive nature of healthcare industry, because of having the direct correlation with human life, questions the authenticity of XAI outcomes, and demands a qualitative and quantitative measure to evaluate these evaluation methods. Furthermore, heatmap visualizations alone are often insufficient for achieving transparency and interpretability of DL models in medical imaging to foster the AI and biomedical synergy. Inspired by the latest trends and contributions in light of the aforementioned concerns, this thesis designs, develops, and validates an interpretable and transparent intelligent clinical decision support system based on traditional machine and DL architectures, whose outcomes can be qualitatively and quantitatively explained with XAI methods. The thesis also comprises a segmentation and detection pipeline for image-driven surgical applications. These novel intelligent systems aims to assist the physicians and clinicians in image-guided diagnostic and treatment systems. The developed interpretable diagnostic frameworks offer wide range of applications and can be extended to several clinical scenarios. Concerning the XAI, transparency and interpretability of CNN architectures are achieved through two families of XAI methods, i.e. perceptive and mathematical XAI. Furthermore, within each of these XAI families, two explanation frameworks are employed. These methods facilitated to investigate the reliability of features and learning process, to critically analyse various CNN architectures and XAI methods, and to compare the outcomes of both XAI pipelines. To further highlight the applications of DL in the image-guided surgical domain, a case study has been performed on image-guided surgical procedures and interventions. The case study also encompasses a detailed investigative study of public datasets and presents the legal and ethical issues of DL-driven image-guided surgery. The study additionally underlines the risks and limitations towards the autonomous systems and provides the future perspective. Finally, the second case study investigates the qualitative and quantitative evaluation of the XAI techniques in regards to the medical images. The case study also sheds light on the evaluation measures, metrics for XAI, quality of explanation, types of explanation, and few more. The clinical efficacy of the developed solutions is evaluated through comparison with existing state-of-the-art methods, and is further validated through consultation with physicians where feasible. The datasets incorporated during the study are either obtained from the online open source platforms or collected from local health institutions
Dynamic Behaviour and Magneto-Mechanical Efficiency of a Contactless Magnetic Transmission
No full textThis paper addresses the analysis of torsional dynamic behaviour in a magnetic transmission, where the torque is transferred in a contactless way between two coaxial rotors with permanent magnets through the interaction with a modulator element holding ferromagnetic poles. This transmission device is called planetary magnetic gear (PMG), due to its topological and functional similarity with a planetary mechanical gearing device, from which the same working principles are derived.
A test bench for testing the magneto-mechanical efficiency of the PMG prototype has been designed and realised. The PMG planetary arrangement allows the possibility to test different configurations, as regards the input/output power, and the prototype dynamic behaviour has been tested as a torque multiplier or as a speed multiplier. No-load tests have been performed, evaluating the torque losses due to bearing dissipations inside the transmission, proving that the efficiency is practically independent from the power direction, in contrast with the traditional mechanical transmissions.
The results here presented can be considered as an overview of a wider activity since, a design of experiment (DOE) with different loads, different speeds at the two sides of transmission and different transmission gear ratios will be further investigated, to assess the independency of efficiency from external conditions
A proposal of dynamic behaviour design based on mode shape tracing: numerical application to a motorbike frame
No full textFinite Element Model Updating Applied to a Lower Limb Prosthesis Through the Optimisation of Its Mechanical Properties
No full textIn the context of elite sports for lower limb amputees, the use of advanced materials and pioneering designs has enhanced athletes’ performance by improving the energy storage and return capability of prosthesis feet. The knowledge of the behaviour of these components is crucial to meet athletes’ requirements and needs. Given their inherent anisotropic nature, the modelling of these components entails fine-tuning several parameters, i.e., Young moduli, Poisson ratios and shear moduli along three directions. This research aims to develop an automated algorithm, implemented in Matlab, for the automated fitting of the material properties. An experimental modal analysis in free-free conditions has been conducted on the blade prosthetic to extract natural frequencies and mode shapes. Subsequently, in the optimisation code, modal simulations are performed on a finite element model, using Nastran. The optimisation procedure is based on the comparison to the experimental data previously evaluated. The optimisation outcomes, in terms of material properties, enable the development of a numerical model capable of predicting the experimental dynamic behaviour up to 400 Hz
Energy Management Strategy for Hybrid Multimode Powertrains: Influence of Inertial Properties and Road Inclination
Full text linkMultimode hybrid powertrains have captured the attention of automotive OEMs for their flexible nature and ability to provide better and optimized efficiency levels. However, the presence of multiple actuators, with different efficiency and dynamic characteristics, increases the problem complexity for minimizing the overall power losses in each powertrain operating condition. The paper aims at providing a methodology to select the powertrain mode and set the reference torques and angular speeds for each actuator, based on the power-weighted efficiency concept. The power-weighted efficiency is formulated to normalize the efficiency contribution from each power source and to include the inertial properties of the powertrain components as well as the vehicle motion resistance forces. The approach, valid for a wide category of multimode powertrain architectures, is then applied to the specific case of a two-mode hybrid system where the engagement of one of the two clutches enables an Input Split or Compound Split operative mode. The simulation results obtained with the procedure prove to be promising in avoiding excessive accelerations, drift of powertrain components, and in managing the power flow for uphill and downhill vehicle conditions
Path Planning and Tracking Algorithms for Autonomous Off-Road Vehicles
No full textThe increasingly diffusion of autonomous driving has transformed the mobility framework, sparking heightened interest among both academic and industrial researchers in the field of autonomous vehicles. The main goal of this paper is the implementation and integration of path planning (PP) and path tracking (PT) algorithms to enable the vehicle to fully cross an obstacle-filled map. This technique can be adopted both in case of on-road mobility and off-road scenarios, where road natural unevenness are treated as equivalent virtual obstacles. The adopted path planning algorithm has been optimized for the generation of the shortest and best feasible trajectory based on the vehicle dynamics constraints. The resulting path is then input to the path tracking logic, configured as a Linear Quadratic Regulator controller whose design is based on a linearized vehicle model. A speed controller is also designed and implemented to improve the vehicle roll dynamic and safety. The controller is then applied to a higher fidelity vehicle model developed in IPG-CarMaker environment, thus validating the methodology through a simulation assessment approach. Optimal results confirm the efficacy of the proposed path planning and tracking strategies
Going Beyond Counting First Authors in Author Co-citation Analysis
Full text linkThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Assessment of Track Chain Tensioning on the Vertical Dynamic Behaviour of a High-Speed Tracked Vehicle
No full textIn this paper, the influence of tensioning force of the track chain on the dynamics of a high-speed tracked vehicle is investigated, through a sensitivity analysis. The tensioning force is responsible of two different effects: the variation of the track chain geometry, since the tensioner acts on the position of idle gear, and the variation of the stiffness of the connections between two different track assemblies. In this paperwork only the second aspect is modelled, connecting two adjacent track assemblies with beam elements, including a constant pre-tensioning, depending on the tensioner force. The vehicle model, comprising sprung and unsprung masses, torsional bars and the two track chains is realised in an in-house developed open-source FEM code. The performed analyses include the evaluation of natural frequencies and mode shapes, and the vehicle vertical dynamics, considering a condensed model to reduce computational efforts. The impact of tensioning is examined within the frequency domain, focusing on several critical acceleration frequency response functions of the vehicle under synchronous excitation caused by road profile input. The presented outcomes have proven a substantial effect of chain tensioning on the vibrations of the above-ground track assemblies, with a minimal influence on the vehicle sprung mass dynamics
Variations on the Author
Full text link“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
- …
