Modelling and improving maintenance decisions:Having foresight with simulation and artificial intelligence

Machine breakdowns are one of the main sources of disruption and throughput fluctuation in highly automated production facilities. One element in reducing this disruption is ensuring that the maintenance team responds correctly to machine failures. It is, however, difficult to determine the current practice employed by the maintenance team, let alone suggest improvements to it. 'Knowledge based improvement' is a methodology that aims to address this issue, by (a) eliciting knowledge on current practice, (b) evaluating that practice and (c) looking for improvements. The methodology, based on visual interactive simulation and artificial intelligence methods, and its application to a Ford engine assembly facility are described. Copyright © 2002 Society of Automotive Engineers, Inc.

Knowledge based improvement:simulation and artificial intelligence for identifying and improving human decision-making in an operations systems

The performance of most operations systems is significantly affected by the interaction of human decision-makers. A methodology, based on the use of visual interactive simulation (VIS) and artificial intelligence (AI), is described that aims to identify and improve human decision-making in operations systems. The methodology, known as 'knowledge-based improvement' (KBI), elicits knowledge from a decision-maker via a VIS and then uses AI methods to represent decision-making. By linking the VIS and AI representation, it is possible to predict the performance of the operations system under different decision-making strategies and to search for improved strategies. The KBI methodology is applied to the decision-making surrounding unplanned maintenance operations at a Ford Motor Company engine assembly plant.

Measurement of intervertebral cervical motion by means of dynamic X-ray image processing and data interpolation

Accurate measurement of intervertebral kinematics of the cervical spine can support the diagnosis of widespread diseases related to neck pain, such as chronic whiplash dysfunction, arthritis, and segmental degeneration. The natural inaccessibility of the spine, its complex anatomy, and the small range of motion only permit concise measurement in vivo. Low dose X-ray fluoroscopy allows time-continuous screening of cervical spine during patient's spontaneous motion. To obtain accurate motion measurements, each vertebra was tracked by means of image processing along a sequence of radiographic images. To obtain a time-continuous representation of motion and to reduce noise in the experimental data, smoothing spline interpolation was used. Estimation of intervertebral motion for cervical segments was obtained by processing patient's fluoroscopic sequence; intervertebral angle and displacement and the instantaneous centre of rotation were computed. The RMS value of fitting errors resulted in about 0.2 degree for rotation and 0.2 mm for displacements. © 2013 Paolo Bifulco et al.

SEQUENTIAL DECISIONS AND PREDICTIONS IN NATURAL LANGUAGE PROCESSING

Natural language processing has achieved great success in a wide range of ap- plications, producing both commercial language services and open-source language tools. However, most methods take a static or batch approach, assuming that the model has all information it needs and makes a one-time prediction. In this disser- tation, we study dynamic problems where the input comes in a sequence instead of all at once, and the output must be produced while the input is arriving. In these problems, predictions are often made based only on partial information. We see this dynamic setting in many real-time, interactive applications. These problems usually involve a trade-off between the amount of input received (cost) and the quality of the output prediction (accuracy). Therefore, the evaluation considers both objectives (e.g., plotting a Pareto curve). Our goal is to develop a formal understanding of sequential prediction and decision-making problems in natural language processing and to propose efficient solutions. Toward this end, we present meta-algorithms that take an existent batch model and produce a dynamic model to handle sequential inputs and outputs. Webuild our framework upon theories of Markov Decision Process (MDP), which allows learning to trade off competing objectives in a principled way. The main machine learning techniques we use are from imitation learning and reinforcement learning, and we advance current techniques to tackle problems arising in our settings. We evaluate our algorithm on a variety of applications, including dependency parsing, machine translation, and question answering. We show that our approach achieves a better cost-accuracy trade-off than the batch approach and heuristic-based decision- making approaches. We first propose a general framework for cost-sensitive prediction, where dif- ferent parts of the input come at different costs. We formulate a decision-making process that selects pieces of the input sequentially, and the selection is adaptive to each instance. Our approach is evaluated on both standard classification tasks and a structured prediction task (dependency parsing). We show that it achieves similar prediction quality to methods that use all input, while inducing a much smaller cost. Next, we extend the framework to problems where the input is revealed incremen- tally in a fixed order. We study two applications: simultaneous machine translation and quiz bowl (incremental text classification). We discuss challenges in this set- ting and show that adding domain knowledge eases the decision-making problem. A central theme throughout the chapters is an MDP formulation of a challenging problem with sequential input/output and trade-off decisions, accompanied by a learning algorithm that solves the MDP.

An Artificial Intelligence Approach to Individuals' Age Assessment

A link between patterns of pelvic growth and human life history is supported by the finding that, cross-culturally, variation in maturation rates of female pelvis are correlated with variation in ages of menarche and first reproduction, i.e., it is well known that the human dimensions of the pelvic bones depend on the gender and vary with the age. Indeed, one feature in which humans appear to be unique is the prolonged growth of the pelvis after the age of sexual maturity. Both the total superoinferior length and mediolateral breadth of the pelvis continues to grow markedly after puberty, and do not reach adult proportions until the late teens years. This continuation of growth is accomplished by relatively late fusion of the separate centers of ossification that form the bones of the pelvis. Hence, in this work we will focus on the development of an intelligent decision support system to predict individual’s age based on a pelvis' dimensions criteria. Some basic image processing techniques were applied in order to extract the relevant features from pelvic X-rays, being the computational framework built on top of a Logic Programming approach to Knowledge Representation and Reasoning that caters for the handling of incomplete, unknown, or even self-contradictory information, complemented with a Case Base approach to computing.

Hybrid Artificial Intelligence to Extract Patterns and Rules from Argumentative and Legal Texts

This Thesis is composed of a collection of works written in the period 2019-2022, whose aim is to find methodologies of Artificial Intelligence (AI) and Machine Learning to detect and classify patterns and rules in argumentative and legal texts. We define our approach “hybrid”, since we aimed at designing hybrid combinations of symbolic and sub-symbolic AI, involving both “top-down” structured knowledge and “bottom-up” data-driven knowledge. A first group of works is dedicated to the classification of argumentative patterns. Following the Waltonian model of argument and the related theory of Argumentation Schemes, these works focused on the detection of argumentative support and opposition, showing that argumentative evidences can be classified at fine-grained levels without resorting to highly engineered features. To show this, our methods involved not only traditional approaches such as TFIDF, but also some novel methods based on Tree Kernel algorithms. After the encouraging results of this first phase, we explored the use of a some emerging methodologies promoted by actors like Google, which have deeply changed NLP since 2018-19 — i.e., Transfer Learning and language models. These new methodologies markedly improved our previous results, providing us with best-performing NLP tools. Using Transfer Learning, we also performed a Sequence Labelling task to recognize the exact span of argumentative components (i.e., claims and premises), thus connecting portions of natural language to portions of arguments (i.e., to the logical-inferential dimension). The last part of our work was finally dedicated to the employment of Transfer Learning methods for the detection of rules and deontic modalities. In this case, we explored a hybrid approach which combines structured knowledge coming from two LegalXML formats (i.e., Akoma Ntoso and LegalRuleML) with sub-symbolic knowledge coming from pre-trained (and then fine-tuned) neural architectures.

Augmented Audiovisual Translation: the Perks and Perils of the Implementation of Artificial Intelligence in Subtitling and Dubbing

This thesis examines the state of audiovisual translation (AVT) in the aftermath of the COVID-19 emergency, highlighting new trends with regards to the implementation of AI technologies as well as their strengths, constraints, and ethical implications. It starts with an overview of the current AVT landscape, focusing on future projections about its evolution and its critical aspects such as the worsening working conditions lamented by AVT professionals – especially freelancers – in recent years and how they might be affected by the advent of AI technologies in the industry. The second chapter delves into the history and development of three AI technologies which are used in combination with neural machine translation in automatic AVT tools: automatic speech recognition, speech synthesis and deepfakes (voice cloning and visual deepfakes for lip syncing), including real examples of start-up companies that utilize them – or are planning to do so – to localize audiovisual content automatically or semi-automatically. The third chapter explores the many ethical concerns around these innovative technologies, which extend far beyond the field of translation; at the same time, it attempts to revindicate their potential to bring about immense progress in terms of accessibility and international cooperation, provided that their use is properly regulated. Lastly, the fourth chapter describes two experiments, testing the efficacy of the currently available tools for automatic subtitling and automatic dubbing respectively, in order to take a closer look at their perks and limitations compared to more traditional approaches. This analysis aims to help discerning legitimate concerns from unfounded speculations with regards to the AI technologies which are entering the field of AVT; the intention behind it is to humbly suggest a constructive and optimistic view of the technological transformations that appear to be underway, whilst also acknowledging their potential risks.

High Performance Multi-Standard Architecture for DCT Computation in H.264/AVC High Profile and HEVC Codecs

A new high performance architecture for the computation of all the DCT operations adopted in the H.264/AVC and HEVC standards is proposed in this paper. Contrasting to other dedicated transform cores, the presented multi-standard transform architecture is supported on a completely configurable, scalable and unified structure, that is able to compute not only the forward and the inverse 8×8 and 4×4 integer DCTs and the 4×4 and 2×2 Hadamard transforms defined in the H.264/AVC standard, but also the 4×4, 8×8, 16×16 and 32×32 integer transforms adopted in HEVC. Experimental results obtained using a Xilinx Virtex-7 FPGA demonstrated the superior performance and hardware efficiency levels provided by the proposed structure, which outperforms its more prominent related designs by at least 1.8 times. When integrated in a multi-core embedded system, this architecture allows the computation, in real-time, of all the transforms mentioned above for resolutions as high as the 8k Ultra High Definition Television (UHDTV) (7680×4320 @ 30fps).

Increasing source to image distance for AP pelvis imaging: impact on radiation dose and image quality

Aim - A quantative primary study to determine whether increasing source to image distance (SID), with and without the use of automatic exposure control (AEC) for antero-posterior (AP) pelvis imaging, reduces dose whilst still producing an image of diagnostic quality. Methods - Using a computed radiography (CR) system, an anthropomorphic pelvic phantom was positioned for an AP examination using the table bucky. SID was initially set at 110 cm, with tube potential set at a constant 75 kVp, with two outer chambers selected and a fine focal spot of 0.6 mm. SID was then varied from 90 cm to 140 cm with two exposures made at each 5 cm interval, one using the AEC and another with a constant 16 mAs derived from the initial exposure. Effective dose (E) and entrance surface dose (ESD) were calculated for each acquisition. Seven experienced observers blindly graded image quality using a 5-point Likert scale and 2 Alternative Forced Choice software. Signal-to-Noise Ratio (SNR) was calculated for comparison. For each acquisition, femoral head diameter was also measured for magnification indication. Results - Results demonstrated that when increasing SID from 110 cm to 140 cm, both E and ESD reduced by 3.7% and 17.3% respectively when using AEC and 50.13% and 41.79% respectively, when the constant mAs was used. No significant statistical (T-test) difference (p = 0.967) between image quality was detected when increasing SID, with an intra-observer correlation of 0.77 (95% confidence level). SNR reduced slightly for both AEC (38%) and no AEC (36%) with increasing SID. Conclusion - For CR, increasing SID significantly reduces both E and ESD for AP pelvis imaging without adversely affecting image quality.

Optimising protocol of acquisition and post-processing procedures in the assessment of coronary artery disease by computed tomography

Coronary artery disease (CAD) is currently one of the most prevalent diseases in the world population and calcium deposits in coronary arteries are one direct risk factor. These can be assessed by the calcium score (CS) application, available via a computed tomography (CT) scan, which gives an accurate indication of the development of the disease. However, the ionising radiation applied to patients is high. This study aimed to optimise the protocol acquisition in order to reduce the radiation dose and explain the flow of procedures to quantify CAD. The main differences in the clinical results, when automated or semiautomated post-processing is used, will be shown, and the epidemiology, imaging, risk factors and prognosis of the disease described. The software steps and the values that allow the risk of developingCADto be predicted will be presented. A64-row multidetector CT scan with dual source and two phantoms (pig hearts) were used to demonstrate the advantages and disadvantages of the Agatston method. The tube energy was balanced. Two measurements were obtained in each of the three experimental protocols (64, 128, 256 mAs). Considerable changes appeared between the values of CS relating to the protocol variation. The predefined standard protocol provided the lowest dose of radiation (0.43 mGy). This study found that the variation in the radiation dose between protocols, taking into consideration the dose control systems attached to the CT equipment and image quality, was not sufficient to justify changing the default protocol provided by the manufacturer.

Logic programming and artificial neural networks in breast cancer detection

About 90% of breast cancers do not cause or are capable of producing death if detected at an early stage and treated properly. Indeed, it is still not known a specific cause for the illness. It may be not only a beginning, but also a set of associations that will determine the onset of the disease. Undeniably, there are some factors that seem to be associated with the boosted risk of the malady. Pondering the present study, different breast cancer risk assessment models where considered. It is our intention to develop a hybrid decision support system under a formal framework based on Logic Programming for knowledge representation and reasoning, complemented with an approach to computing centered on Artificial Neural Networks, to evaluate the risk of developing breast cancer and the respective Degree-of-Confidence that one has on such a happening.

Influence of magnetic field strength and image registration strategy on voxel-based morphometry in a study of Alzheimer's disease.

Multi-centre data repositories like the Alzheimer's Disease Neuroimaging Initiative (ADNI) offer a unique research platform, but pose questions concerning comparability of results when using a range of imaging protocols and data processing algorithms. The variability is mainly due to the non-quantitative character of the widely used structural T1-weighted magnetic resonance (MR) images. Although the stability of the main effect of Alzheimer's disease (AD) on brain structure across platforms and field strength has been addressed in previous studies using multi-site MR images, there are only sparse empirically-based recommendations for processing and analysis of pooled multi-centre structural MR data acquired at different magnetic field strengths (MFS). Aiming to minimise potential systematic bias when using ADNI data we investigate the specific contributions of spatial registration strategies and the impact of MFS on voxel-based morphometry in AD. We perform a whole-brain analysis within the framework of Statistical Parametric Mapping, testing for main effects of various diffeomorphic spatial registration strategies, of MFS and their interaction with disease status. Beyond the confirmation of medial temporal lobe volume loss in AD, we detect a significant impact of spatial registration strategy on estimation of AD related atrophy. Additionally, we report a significant effect of MFS on the assessment of brain anatomy (i) in the cerebellum, (ii) the precentral gyrus and (iii) the thalamus bilaterally, showing no interaction with the disease status. We provide empirical evidence in support of pooling data in multi-centre VBM studies irrespective of disease status or MFS.

Model-based Segmentation and Image Fusion of 3D Computed Tomography and 3D Ultrasound of the Eye for Radiotherapy Planning

For radiotherapy treatment planning of retinoblastoma inchildhood, Computed Tomography (CT) represents thestandard method for tumor volume delineation, despitesome inherent limitations. CT scan is very useful inproviding information on physical density for dosecalculation and morphological volumetric information butpresents a low sensitivity in assessing the tumorviability. On the other hand, 3D ultrasound (US) allows ahigh accurate definition of the tumor volume thanks toits high spatial resolution but it is not currentlyintegrated in the treatment planning but used only fordiagnosis and follow-up. Our ultimate goal is anautomatic segmentation of gross tumor volume (GTV) in the3D US, the segmentation of the organs at risk (OAR) inthe CT and the registration of both. In this paper, wepresent some preliminary results in this direction. Wepresent 3D active contour-based segmentation of the eyeball and the lens in CT images; the presented approachincorporates the prior knowledge of the anatomy by usinga 3D geometrical eye model. The automated segmentationresults are validated by comparing with manualsegmentations. Then, for the fusion of 3D CT and USimages, we present two approaches: (i) landmark-basedtransformation, and (ii) object-based transformation thatmakes use of eye ball contour information on CT and USimages.

Recent advances in remote sensing image processing

Remote sensing image processing is nowadays a mature research area. The techniques developed in the field allow many real-life applications with great societal value. For instance, urban monitoring, fire detection or flood prediction can have a great impact on economical and environmental issues. To attain such objectives, the remote sensing community has turned into a multidisciplinary field of science that embraces physics, signal theory, computer science, electronics, and communications. From a machine learning and signal/image processing point of view, all the applications are tackled under specific formalisms, such as classification and clustering, regression and function approximation, image coding, restoration and enhancement, source unmixing, data fusion or feature selection and extraction. This paper serves as a survey of methods and applications, and reviews the last methodological advances in remote sensing image processing.