1,720,963 research outputs found
Deep Neural Oracles for Short-Window Optimized Compressed Sensing of Biosignals
Get PDFThe recovery of sparse signals given their linear mapping on lower-dimensional spaces can be partitioned into a support estimation phase and a coefficient estimation phase. We propose to estimate the support with an oracle based on a deep neural network trained jointly with the linear mapping at the encoder. The divination of the oracle is then used to estimate the coefficients by pseudo-inversion. This architecture allows the definition of an encoding-decoding scheme with state-of-the-art recovery capabilities when applied to biological signals such as ECG and EEG, thus allowing extremely low-complex encoders. As an additional feature, oracle-based recovery is able to self-assess, by indicating with remarkable accuracy chunks of signals that may have been reconstructed with a non-satisfactory quality. This self-assessment capability is unique in the CS literature and paves the way for further improvements depending on the requirements of the specific application. As an example, our scheme is able to satisfyingly compress by a factor of 2.67 an ECG or EEG signal with a complexity equivalent to only 24 signed sums per processed sample
Deep Neural Oracle with Support Identification in the Compressed Domain
Get PDFWe investigate the advantage of a two-step approach in the recovery of Compressed Sensing (CS) encoded signals in a realistic environment. First, the support of the signal is computed from the compressed measurements exploiting a Deep Neural Network (DNN). Once the support is known, the input signal can be easily recovered by a pseudoinverse operation. We consider a case study involving realistic biomedical signals and a processing architecture based on a limited precision fixed-point arithmetic unit for the implementation of the DNN and the pseudoinverse operation. In this setting, we show that the proposed approach results in a performance improvement of more than 5 dB in terms of average reconstructed signal to noise ratio (ARSNR) compared to CS state-of-the-art approach. This has been possible thanks to two main contributions reported in this paper. The first one is a theoretical investigation of the relationship between the definition of support and both the properties of the input signal and the adopted compression technique. The second one relies on replacing the pseudoinverse operation with a least mean square filter, whose small sensitivity to numerical errors grants advantages in architectures relying on limited precision fixed-point arithmetic units
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe 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
Low-power ECG acquisition by Compressed Sensing with Deep Neural Oracles
Get PDFThe recovery of sparse signals from their linear mapping on a lower-dimensional space is traditionally performed by finding the sparsest solution compatible with such solutions. This task can be partitioned in two phases: support estimation and coefficient estimation. We propose to perform the former with a deep neural network jointly trained with the encoder that divines a support that is used in the latter phase to estimate the coefficients by pseudo-inversion. Numerical evidence demonstrates that the proposed encoder-decoder architecture outperforms state-of-the-art Compressed Sensing (CS) approaches in the recovery of synthetic ECG signals for a compression ratio higher than 2.5. Further tests on real ECG prove the applicability in real-world scenarios
A passive and low-complexity Compressed Sensing architecture based on a charge-redistribution SAR ADC
Get PDFAn innovative analog-to-digital converter (ADC) architecture is proposed, with the aim of acquiring an input signal according to the Compressed Sensing (CS) paradigm and without the need for dedicated active analog blocks. Its core is the capacitive array employed in traditional successive-approximation-register (SAR) ADCs. Introducing only a few additional switches, the array can compute the linear combination of consecutive signal samples, as required by the CS encoding. To manage the presence of leakage currents, which may impair signal reconstruction, a compensation circuit is considered, allowing close-to-ideal performance of the system when properly designed. A neural network-based decoding strategy is also analyzed, with up to 20 dB of additional reconstruction quality with respect to standard algorithms. Synthetic electrocardiogram signals are used to validate optimizations both at the hardware level in the encoding block and at the software level in the decoder
Optimizing Vision Transformers: Leveraging Max and Min Operations for Efficient Pruning
Get PDFThe research on Deep Neural Networks (DNNs) continues to enhance the performance of these models over a wide spectrum of tasks, increasing their adoption in many fields. This leads to the need of extending their usage also on edge devices with limited resources, even though, with the advent of Transformer-based models, this has become an increasingly complex task because of their size. In this context, pruning emerges as a crucial tool to reduce the number of weights in the memory-hungry Fully Connected (FC) layers. This paper explores the usage of neurons based on the Multiply-And-Max/min (MAM) operation, an alternative to the conventional Multiply-and-Accumulate (MAC), in a Vision Transformer (ViT). This enhances the model prunability thanks to the usage of Max and Min operations. For the first time, many MAM-based FC layers are used in a large state-of-the-art DNN model and compressed with various pruning techniques available in the literature. Experiments show that MAM-based layers achieve the same accuracy of traditional layers using up to 12 times less weights. In particular, when using Global Magnitude Pruning (GMP), the FC layers following the Multi-head Attention block of a ViT-B/16 model, fine-tuned on CIFAR-100, count only 560000 weights if MAM neurons are used, compared to the 31.4 million that remain when using traditional MAC neurons
Variations on the Author
Get PDF“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
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Event-based Classification with Recurrent Spiking Neural Networks on Low-end Micro-Controller Units
Get PDFDue to its intrinsic sparsity both in time and space, event-based data is optimally suited for edge-computing applications that require low power and low latency. Time varying signals encoded with this data representation are best processed with Spiking Neural Networks (SNN). In particular, recurrent SNNs (RSNNs) can solve temporal tasks using a relatively low number of parameters, and therefore support their hardware implementation in resource-constrained computing architectures. These premises propel the need of exploring the properties of these kinds of structures on low-power processing systems to test their limits both in terms of computational accuracy and resource consumption, without having to resort to full-custom implementations. In this work, we implemented an RSNN model on a low-end, resource-constrained ARM-Cortex-M4-based Micro Controller Unit (MCU). We trained it on a down-sampled version of the N-MNIST event-based dataset for digit recognition as an example to assess its performance in the inference phase. With an accuracy of 97.2%, the implementation has an average energy consumption as low as 4.1μJ and a worst-case computational time of 150.4μs per time-step with an operating frequency of 180 MHz, so the deployment of RSNNs on MCU devices is a feasible option for small image vision real-time tasks
- …
