Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

This book presents a selection of papers representing current research on using field programmable gate arrays (FPGAs) for realising image processing algorithms. These papers are reprints of papers selected for a Special Issue of the Journal of Imaging on image processing using FPGAs. A diverse range of topics is covered, including parallel soft processors, memory management, image filters, segmentation, clustering, image analysis, and image compression. Applications include traffic sign recognition for autonomous driving, cell detection for histopathology, and video compression. Collectively, they represent the current state-of-the-art on image processing using FPGAs.

nuclei detection --- System-on-Chip --- FPGA --- K-Means --- hardware acceleration --- image analysis --- perceptual coding --- line buffer --- heterogeneous computing --- window filters --- processor architectures --- hardware accelerators --- stream processing --- embedded systems --- image processing pipeline --- image processing --- generalized Laplacian of Gaussian filter --- background estimation --- real-time systems --- FPGA implementation --- hardware architecture --- compression --- image borders --- memory --- zig-zag scan --- histopathology --- just-noticeable difference (JND) --- memory management --- downsampling --- image segmentation --- feature extraction --- design --- mean Shift clustering --- high-throughput --- segmentation --- streaming architecture --- power --- D-SWIM --- hardware/software co-design --- high-level synthesis --- contrast masking --- texture detection --- pipeline --- field programmable gate array (FPGA) --- JPEG-LS --- low-latency --- connected components analysis --- luminance masking --- field programmable gate arrays (FPGA)

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The recent successes of machine learning, especially regarding systems based on deep neural networks, have encouraged further research activities and raised a new set of challenges in understanding and designing complex machine learning algorithms. New applications require learning algorithms to be distributed, have transferable learning results, use computation resources efficiently, convergence quickly on online settings, have performance guarantees, satisfy fairness or privacy constraints, incorporate domain knowledge on model structures, etc. A new wave of developments in statistical learning theory and information theory has set out to address these challenges. This Special Issue, "Machine Learning and Information Theory", aims to collect recent results in this direction reflecting a diverse spectrum of visions and efforts to extend conventional theories and develop analysis tools for these complex machine learning systems.

Technology: general issues --- History of engineering & technology --- supervised classification --- independent and non-identically distributed features --- analytical error probability --- empirical risk --- generalization error --- K-means clustering --- model compression --- population risk --- rate distortion theory --- vector quantization --- overfitting --- information criteria --- entropy --- model-based clustering --- merging mixture components --- component overlap --- interpretability --- time series prediction --- finite state machines --- hidden Markov models --- recurrent neural networks --- reservoir computers --- long short-term memory --- deep neural network --- information theory --- local information geometry --- feature extraction --- spiking neural network --- meta-learning --- information theoretic learning --- minimum error entropy --- artificial general intelligence --- closed-loop transcription --- linear discriminative representation --- rate reduction --- minimax game --- fairness --- HGR maximal correlation --- independence criterion --- separation criterion --- pattern dictionary --- atypicality --- Lempel–Ziv algorithm --- lossless compression --- anomaly detection --- information-theoretic bounds --- distribution and federated learning

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

Recent advances in electronics have led to sensors whose sizes and weights are such that they can be placed on living systems without impairing their natural motion and habits. They may be worn on the body as accessories or as part of the clothing and enable personalized mobile information processing. Wearable sensors open the way for a nonintrusive and continuous monitoring of body orientation, movements, and various physiological parameters during motor activities in real-life settings. Thus, they may become crucial tools not only for researchers, but also for clinicians, as they have the potential to improve diagnosis, better monitor disease development and thereby individualize treatment. Wearable sensors should obviously go unnoticed for the people wearing them and be intuitive in their installation. They should come with wireless connectivity and low-power consumption. Moreover, the electronics system should be self-calibrating and deliver correct information that is easy to interpret. Cross-platform interfaces that provide secure data storage and easy data analysis and visualization are needed.This book contains a selection of research papers presenting new results addressing the above challenges.

Medical equipment & techniques --- inertial measurement unit --- movement analysis --- long-track speed skating --- validity --- IMU --- principal component analysis --- wearable --- scoring --- carving --- balance assessment --- data augmentation --- gated recurrent unit --- human activity recognition --- one-dimensional convolutional neural network --- intermittent claudication --- vascular rehabilitation --- 6 min walking test --- functional walking --- TUG --- kinematics --- fall risk --- logistic regression --- elderly --- inertial sensor --- artificial intelligence --- supervised machine learning --- head rotation test --- neck pain --- cerebral palsy --- dystonia --- choreoathetosis --- machine learning --- home-based --- wearable device --- MLP --- gesture recognition --- flex sensor --- model search --- neural network --- inertial measurement unit—IMU --- movement complexity --- sample entropy --- trunk flexion --- low back pain --- lifting technique --- camera system --- ward clustering method --- K-means clustering method --- ensemble clustering method --- Bayesian neural network --- pain self-efficacy questionnaire --- n/a --- inertial measurement unit-IMU

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

[Cancer is the second most common cause of death worldwide and encompasses highly variable clinical and biological scenarios. Some of the current clinical challenges are (i) early diagnosis of the disease and (ii) precision medicine, which allows for treatments targeted to specific clinical cases. The ultimate goal is to optimize the clinical workflow by combining accurate diagnosis with the most suitable therapies. Toward this, large-scale machine learning research can define associations among clinical, imaging, and multi-omics studies, making it possible to provide reliable diagnostic and prognostic biomarkers for precision oncology. Such reliable computer-assisted methods (i.e., artificial intelligence) together with clinicians’ unique knowledge can be used to properly handle typical issues in evaluation/quantification procedures (i.e., operator dependence and time-consuming tasks). These technical advances can significantly improve result repeatability in disease diagnosis and guide toward appropriate cancer care. Indeed, the need to apply machine learning and computational intelligence techniques has steadily increased to effectively perform image processing operations—such as segmentation, co-registration, classification, and dimensionality reduction—and multi-omics data integration.]

melanoma detection --- deep learning --- transfer learning --- ensemble classification --- 3D-CNN --- immunotherapy --- radiomics --- self-attention --- breast imaging --- microwave imaging --- image reconstruction --- segmentation --- unsupervised machine learning --- k-means clustering --- Kolmogorov-Smirnov hypothesis test --- statistical inference --- performance metrics --- contrast source inversion --- brain tumor segmentation --- magnetic resonance imaging --- survey --- brain MRI image --- tumor region --- skull stripping --- region growing --- U-Net --- BRATS dataset --- incoherent imaging --- clutter rejection --- breast cancer detection --- MRgFUS --- proton resonance frequency shift --- temperature variations --- referenceless thermometry --- RBF neural networks --- interferometric optical fibers --- breast cancer --- risk assessment --- machine learning --- texture --- mammography --- medical imaging --- imaging biomarkers --- bone scintigraphy --- prostate cancer --- semisupervised classification --- false positives reduction --- computer-aided detection --- breast mass --- mass detection --- mass segmentation --- Mask R-CNN --- dataset partition --- brain tumor --- classification --- shallow machine learning --- breast cancer diagnosis --- Wisconsin Breast Cancer Dataset --- feature selection --- dimensionality reduction --- principal component analysis --- ensemble method --- n/a

Choose an application

• Reference Manager
• EndNote
• RefWorks (Direct export to RefWorks)

The vast majority of real-world problems can be expressed as an optimisation task by formulating an objective function, also known as cost or fitness function. The most logical methods to optimise such a function when (1) an analytical expression is not available, (2) mathematical hypotheses do not hold, and (3) the dimensionality of the problem or stringent real-time requirements make it infeasible to find an exact solution mathematically are from the field of Evolutionary Computation (EC) and Swarm Intelligence (SI). The latter are broad and still growing subjects in Computer Science in the study of metaheuristic approaches, i.e., those approaches which do not make any assumptions about the problem function, inspired from natural phenomena such as, in the first place, the evolution process and the collaborative behaviours of groups of animals and communities, respectively. This book contains recent advances in the EC and SI fields, covering most themes currently receiving a great deal of attention such as benchmarking and tunning of optimisation algorithms, their algorithm design process, and their application to solve challenging real-world problems to face large-scale domains.

dynamic stream clustering --- online clustering --- metaheuristics --- optimisation --- population based algorithms --- density based clustering --- k-means centroid --- concept drift --- concept evolution --- imbalanced data --- screening criteria --- DE-MPFSC algorithm --- Markov process --- entanglement degree --- data integration --- PSO --- robot --- manipulator --- analysis --- kinematic parameters --- identification --- approximate matching --- context-triggered piecewise hashing --- edit distance --- fuzzy hashing --- LZJD --- multi-thread programming --- sdhash --- signatures --- similarity detection --- ssdeep --- maximum k-coverage --- redundant representation --- normalization --- genetic algorithm --- hybrid algorithms --- memetic algorithms --- particle swarm --- multi-objective deterministic optimization, derivative-free --- global/local optimization --- simulation-based design optimization --- wireless sensor networks --- routing --- Swarm Intelligence --- Particle Swarm Optimization --- Social Network Optimization --- compact optimization --- discrete optimization --- large-scale optimization --- one billion variables --- evolutionary algorithms --- estimation distribution algorithms --- algorithmic design --- metaheuristic optimisation --- evolutionary computation --- swarm intelligence --- memetic computing --- parameter tuning --- fitness trend --- Wilcoxon rank-sum --- Holm–Bonferroni --- benchmark suite --- data sampling --- feature selection --- instance weighting --- nature-inspired algorithms --- meta-heuristic algorithms