1,721,100 research outputs found
Innovative Technologies and Signal Processing in Perinatal Medicine - Volume 2
No full textThe perinatal period ranges from the third trimester of pregnancy up to one month
after birth. It is a critical phase, as some problems arising during this period can
affect the entire life of the newborn. Even if this represents a quite broad field from
the medical perspective, involving several specializations, for biomedical engineers
this is a quite tight research niche characterized by high barriers. From a purely
technical perspective, this issue is due to the intrinsic problems with the measurand
accessibility and the disproportion between the small fetal signals and the stronger
maternal interferences. From a broader bioengineering perspective, this is also due
to both the peculiarities of fetal physiopathology, which evolves and changes during
gestation, and the lack of knowledge of the underpinnings behind some clinical
outcomes, particularly in labor. All these challenges require biomedical engineers
to provide support in developing a deep understanding of medical and physiological
aspects, and to sharpen signal processing, artificial intelligence, and data mining
weapons, in order to conceive innovative solutions for the open issues.
Baring this in mind, in 2018 I ignited a series of educational events, realized
thanks to the collaboration and the financial contribution of the Autonomous Region
of Sardinia and Sardegna Ricerche, in the wonderful framework of Sardinia, with
the aim to present both the fundamentals needed to start moving some steps
in the field, and the advanced (applied) techniques. The International Summer
School on Technologies and Signal Processing in Perinatal Medicine (TSPPM2018)
and then the second edition in 2021 (TSPPM2021) were conceived to create
a multidisciplinary environment with both clinical and engineering outlines, for
young researchers approaching this research niche or already active in it. This
successful event also contributed to establishing a strong network of researchers
from all over the world, including world-recognized top scientists and research
groups. A first book collecting several book chapters inspired by the lectures
presented during the TSPPM2018 was already published by Springer Nature with a
positive impact. Following the success of the first volume, Innovative Technologies
and Signal Processing in Perinatal Medicine – Volume 2 covers other important
topics presented at TSPPM2021, and more.
vii
viii Preface
Although many excellent books exist in the field of biomedical signal processing,
machine learning, medicine, etc., no one expressly targets this specific area in
a way that the aforementioned barriers could be reduced, if not destroyed. For
this purpose, all the experts and scientists who participated in the production of
this unique collection were asked to consider an engineering target, either new
to this exciting topic, or with some previous experience, up to really advanced
skills. The result is a stimulating reading with a rich bibliography and a clear
didactic intention, including medical, legal, and engineering chapters. In particular,
the first three chapters are dedicated to the presentation of the gynecologist’s,
neonatologist’s, and coroner’s perspective of perinatal medicine, with an inspiring
representation of the potentialities and opportunities for technological innovation in
the field. A profound chapter on the legal issues associated with medical liability
tackles the double-edged sword of technology in medicine, not only in terms
of sensible data protection but also in terms of potentialities and criticalities of
artificial intelligence and telemedicine systems. Then, three technical chapters cover
methods and technologies for fetal monitoring and diagnosis, i.e., non-invasive
techniques for neurodevelopment assessment, study of myocardial performance by
Doppler ultrasound, and principles and technologies for fetal electrocardiography.
A deep dive into the information processing for the solution of specific problems
is then presented, with further four chapters dealing with non-linear time-frequency
techniques for non-invasive fetal electrocardiography, fundamentals of information
theory for the analysis of fetal heart rate variability, its analysis with Gaussian
processes, and the estimation of the fetal state by signal processing and machine
learning from such signals. In the end, as data availability is an important barrier for
producing relevant research in the field, and considering the difficulty in obtaining
fetal monitoring data, the closing chapter reviews the most important datasets for
fetal electrocardiography, providing some hints also for phonocardiography and
cardiotocography.
Starting the International Summer School on Technologies and Signal Processing
in Perinatal Medicine series, and collecting the chapters in this second volume, was
difficult but I think the result deserved the lavished efforts. I sincerely thank all the
authors for their excellent work and for being part of this adventure. It is a great
honor for me to present to you the Innovative Technologies and Signal Processing
in Perinatal Medicine book, Volume 2
An on-line algorithm and its DSP implementation for real-time separation of the foetal ECG
No full text
Stigmergic approaches applied to flexible fault-tolerant digital VLSI architectures
No full textParallel implementations are widely used in digital architectures to enhance computational performances, exploiting the number of involved processing units. Cooperative behaviors typical of swarm intelligence can enhance the performances of such systems introducing an amplification effect due to the collective effort of a set of interacting hardware agents. Cooperation can also be exploited like a new weapon to achieve the fault-tolerance goal, with no need for expressly inserted redundant hardware resources. In this paper we present a novel architecture able to address these issues exploiting all the potentiality exposed by this bioinspired approach. A first implementation on CMOS 0.13 μ m technology shows the feasibility of such a design style, allowing preliminary simulations and discussion
Real-time blind audio source separation: performance assessment on an advanced digital signal processor
No full textMany on-line blind audio source separation (BASS) algorithms have been presented so far to the scientific community, but only a few of them have been evaluated in terms of their real-time performance. In this paper we consider a well-established BASS method (oriented to voices separation) evaluating its performance in terms of separation quality allowed by a real-time embedded computing implementation, also considering novel and state-of-the-art improvements to the it. To this aim, the algorithm has been implemented and ported for real-time execution onto an advanced low-power digital signal processor targeted for complex-domain applications. The optimized embedded implementation is able to perform up to five iterations of the gradient for any input frame of data, achieving good separation levels (up to 11.8 dB of signal to interference ratio on custom recording in real environments). The proposed solution doubles the performance of a C-optimized version running on a traditional PC processor, achieving a better separation result with lower power requirement
Identification of fetal QRS complexes in low density non-invasive biopotential recordings
No full textNon-invasive fetal Electrocardiogram (ECG) is currently a missing diagnostic tool. Despite the technology advancements and the improvements of the signal processing techniques, the possibility of extracting this signal from recordings of biopotentials gathered on the maternal abdomen is still unexploited in the clinical practice. The 2013 Physionet/Computing in Cardiology Challenge proposes to address this specific problem, making available a dateset of annotated abdominal signals, with a reduced number of channels, taken with different instruments and protocols. In this paper a novel algorithm based on template matching for maternal QRS subtraction and fetal ECG detection is presented and evaluated on the available dataset. The algorithm achieves a score of 639.465 and 23.821 on dataset B and of 684.158 and 47.990 on dataset C
Reconfigurable Coprocessor for Multimedia Application Domain
No full textA new reconfigurable architectural template is presented. Such a template is composed of coarse-grained and fine-grained reconfigurable datapath and control to obtain performances at custom designed chip level. To show the adaptability/performance of such architectural template, the architecture has been customized (i.e. datapath and control features of the template have been properly sized) for multimedia application domain. To evaluate complexity and maximum clock frequency of the proposed architecture, it has been synthesized using Synopsys Design Compiler on a standard-cell 0.18 μ m technology. Estimated number of transistors is 335 K, while maximum allowable frequency is 460 MHz. Performances have been evaluated comparing the number of clock cycles and the processing time required to process application domain dominant kernels with commercial devices: we obtained up to 95% reduction with respect to ARM and up to 94% reduction with respect to TMS320C5510 in terms of clock cycles
Estimation of FECG power for effective electrodes placement in real-time non-invasive FECG extraction with OL-JADE
No full text- …
