Plane wave imaging (PWI) has significantly advanced ultrasound diagnostics by enabling high frame rates and real-time capabilities critical for applications such as cardiac imaging and elastography. However, its clinical utility remains constrained by inherent trade-offs between spatial resolution, contrast, and frame rate, particularly when using a limited number of transmissions. Existing solutions, such as pixel-level apodization or angle-dependent transmit apodization (ADTA), either impose prohibitive computational costs or restrict adaptability to small fields of view (FOV). To address these limitations, we propose a genetic algorithm (GA)-based framework for depth-dependent transmit apodization optimization in PWI. Our approach models the spatial contribution of each plane-wave transmission via a continuous parametric function, reducing the optimization dimensionality. The multi-objective GA simultaneously minimizes the full width at half maximum (FWHM) and peak sidelobe level (PSL), achieving resolution enhancement and artifact suppression across the entire FOV. Experimental validation using a Verasonics Vantage 256 system and an L74 linear probe on a tissue-mimicking phantom demonstrates the feasibility of the approach using only seven steered transmissions.

Divergent wave imaging (DWI) achieves high-framerate ultrasound with a broad field of view incomparable to conventional line-by-line ultrasound techniques. However, unlike traditional focused ultrasound, which applies apodization in both transmit and receive modes, DWI restricts beamforming adjustments to the receive phase, inherently limiting its ability to suppress off-axis clutter and noise. To address this, we propose a multi-objective optimization framework using genetic algorithms to derive spatial weights for DWI transmissions. Each virtual source's contribution is modeled as a depth-dependent Gaussian function, with optimized parameters-lateral spread, axial coverage, and amplitude-to enhance resolution and contrast. The approach was validated through in silico data using convex probe, demonstrating a 25 % reduction in full-width-at-half-maximum (FWHM) and a 44 % improvement in contrast ratio (CR) compared to conventional compounding with only ten virtual sources.

An energy harvester based on the electromagnetic induction effect exploiting the pitch oscillation of a sensor buoy is presented. An experimental prototype has been tested to extract the main parameters of the system.

A fully synthesizable rail-to-rail dynamic voltage comparator referring to different technology nodes and supply voltages down to 0.3V is presented in this paper. The analyzed circuit is composed of standard cells only so that the design flow can be automated, and based on its digital nature, it enables a supply voltage scaling down to deep sub-threshold. The specifications of the same topology are investigated with post-layout simulations under different technology nodes such as 180nm, 130nm, and 40nm and across scaled supply voltage ranging from 0.9 down to 0.3 V. Delay versus common and differential mode of the input and power and offset versus common mode. On this basis, pros and contras across technology and voltage scaling are highlighted to suit integration into sensor nodes for the Internet of Things and related applications.

This paper presents an ultra-low-power, low-voltage universal multi-mode Gm-C filter, designed in CMOS technology. The proposed filter uses only three transconductance operational amplifiers (OTAs) operating in a sub-threshold region: this leads to a significant reduction in energy consumption compared to previous solutions reported in the literature. Furthermore, the proposed filter can operate in four different functional modes, namely voltage, current, transconductance, and trans-resistance, without requiring extra active elements. Finally, the proposed filter for the band-pass responses features a power consumption of 32nW with a voltage supply of 0.5V, with a center frequency of 462Hz which can be considered for biomedical applications.

In recent years, opportunistic rainfall sensing exploiting Commercial Microwave Links (CML) has become popular for real-time monitoring of rainfall events. Among such systems, Satellite-to-earth Microwave Links (SML) are gaining great interest. An important information to extract from the collected data is whether or not an SML observation corresponds to a rain condition. This letter proposes an online training procedure to keep the algorithms that classify this condition up to date, overcoming the problem of data seasonality. Specifically, we propose to retrain the algorithms after one day of observations by applying a forgetting mechanism, where the oldest data are removed from the training dataset. Data were collected by the Smart Rainfall System (SRS) SML-type sensors located in the city of Genoa (Italy). We compare three classification algorithms: one based on an anomaly detection method and two based on Machine Learning (ML) algorithms. The outcomes of this analysis pave the way for implementing artificial intelligence models on embedded systems with limited resources such as the electronic units of SML sensors, hence reducing the data flow from the peripheral sensor network to the central data acquisition and integration server.

In this article, a new microwave-radar-based technique for short-range detection and classification of multiple human and vehicle targets crossing a monitored area is proposed. This approach, which can find applications in both security and infrastructure surveillance, relies upon the processing of the scattered-field data acquired by low-cost off-the-shelf components, i.e., a 24 GHz frequency-modulated continuous wave (FMCW) radar module and a Raspberry Pi mini-PC. The developed method is based on anad hocprocessing chain to accomplish the automatic target recognition (ATR) task, which consists of blocks performing clutter and leakage removal with an infinite impulse response (IIR) filter, clustering with a density-based spatial clustering of applications with noise (DBSCAN) approach, tracking using a Benedict-Bordner$\alpha $-$\beta $filter, features extraction, and finally classification of targets by means of a$k$-nearest neighbor ($k$-NN) algorithm. The approach is validated in real experimental scenarios, showing its capabilities in correctly detecting multiple targets belonging to different classes (i.e., pedestrians, cars, motorcycles, and trucks).

This article compares different rainfall observing techniques available in the City of Genoa (Italy): the Ligurian regional tipping-bucket rain gauge (TBRG) network and the Monte Settepani long-range weather radar (WR) operated by the Ligurian Regional Environmental Protection Agency (ARPAL) and Smart Rainfall System (SRS), a network of microwave sensors for satellite down-links developed by the University of Genoa and Artys Srl. SRS and WR are the two indirect monitoring systems considered in this analysis. The respective performance of the rainfall measurements was assessed by comparison with the reference observations made in situ by seven TBRG stations selected within the boundary of the City of Genoa. The analysis was performed by considering the main precipitation events that occurred between January 2017 and December 2018. The results show an agreement between the precision of the 10-min rainfall intensity (RI) measurements, quantified by the root mean square errors (RMSEs), made by the WR and the SRS system for the seven sites. Similar performance has been also observed when comparing the peak of RI and the total rain accumulation with the reference TBRG values for the selected precipitation events. An assessment of the WR and SRS accuracy in providing the 2-D RI fields was also performed by computing the map of the RMSE differences over the City of Genoa territory. It is shown that the SRS RI maps are generally associated with a lower level of RMSE with respect to the WR in the areas that are characterized by a higher density of sensors.

This paper describes the results obtained by the application of an innovative environmental monitoring technique able to estimate rainfall intensity in real time by processing the attenuation of microwave satellite link signal measured by low cost sensors. The satellite that has been used during our work, Turksat 42° E, belongs to the plethora of satellites operating for television and radio channel broadcasting. Each sensor exploits off the shelf components, is equipped with a radio frequency power-measuring unit, and provides connectivity to the server over a wide area network. A validation of the approach with a field comparison experiment at the urban scale, comprising three measurement sites equipped with such sensors, was established since autumn 2016 in the municipality of Genoa, Italy. Point-scale rainfall intensity measurements made by two calibrated tipping-bucket rain gauges constitute the reference for the comparative analysis of the microwave sensors performance. The dynamic calibration of the rain gauges was carried out by using an automatic calibration rig and the measurements have been processed with advanced algorithms to reduce counting errors. The experimental setup allowed a full characterization of the microwave signal trends as a function of different precipitation. The results showed a strong correlation between the microwave signal attenuation and the reference rainfall observations and demonstrated the possibility to retrieve ten-minute rain accumulations from the microwave links by adopting a proper electromagnetic model. The comparison between the different measuring systems is performed by computing the time series statistics and the frequency of the rain conditions for each precipitation event.

Biological systems live and grow. Many aspects are inherent to the concept of living, such as the adaptation, the interaction with the environment, and the ability to deal with limited resources. Living systems present multiple levels of organization, with elements at one level interacting and aggregating to create more complex behavior at a higher level. In recent years, many new techniques used to investigate the spatio-temporal activity in living being have demonstrated the presence of features common to the behavior of self organizing dynamical systems. Thus a question arises: Is this chaos useful to model living beings? The answer is very difficult to find. Many experimental data support the dynamic chaotic modelling of living systems. Complex behaviors such as perceiving, intending, acting, learning, and remembering arise as metastable spatio-temporal patterns of brain activity that are themselves produced by the cooperative interactions among neural clusters. In this article we present and discuss that question, and we try to give indication for a possible answer, with the aim of defining the basic features of a behavioral kernel for living artefacts.

We present and discuss the major results of our research activity aimed to the analog VLSI implementation of on-chip learning neural networks. In particular we present the SLANP (self learning neural processor) chip results. The SLANP architecture implements an on-chip learning multilayer perceptron network. The learning algorithm is based on the back propagation but it exhibits increased capabilities due to the local learning rate management. A prototype chip has been designed and fabricated in a CMOS 0.7 /spl mu/m minimum channel length technology. The experimental results confirm the functionality of the chip and the soundness of the approach. The SLANP performance compares favorably with that reported in the literature.

In this paper we present the analog on-chip learning architecture of a gradient descent learning algorithm: the weight perturbation learning algorithm. From the circuit implementation point of view our approach is based on current mode and translinear operated circuits. The proposed architecture is very efficient in terms of speed, size, precision and power consumption; moreover it exhibits also high scalability and modularity.

Gradient descent learning algorithms (namely backpropagation and weight perturbation) can significantly increase their classification performances by adopting a local and adaptive learning rate management approach. We present the results of the comparison of the classification performance of the two algorithms in a tough application: quality control analysis in the steel industry. The feedforward network is hierarchically organized (i.e. tree of multilayer perceptrons). The comparison has been performed starting from the same operating conditions (i.e. network topology, stopping criterion, etc.): the results show that the probability of correct classification is significantly better for the weight perturbation algorithm.

In this paper we present the analog on-chip learning architecture of a gradient descent learning algorithm: the Weight Perturbation learning algorithm. From the circuit implementation point of view our approach is based on current mode and translinear operated circuits. The proposed architecture is very efficient in terms of speed, size, precision and power consumption; moreover it exhibits also high scalability and modularity.

The CMOS circuit implementation of the feedforward neural primitives of a generic Multi Layer Perceptron network is presented. Basically our approach is based on current mode computation and is aimed at a low power/low voltage circuit implementation; moreover, it is easily scalable to implement networks of any size. Experimental results are reported.

A symbolic cell generator (SYC) that can generate the symbolic layout of a generic CMOS logic cell is presented. It accepts as input a SPICE-like netlist describing circuit components, connectivity, and the list of the I/O pins. Using this generator, the user can specify topological constraints on pin and transistor positions, the maximum lengths of polysilicon and diffusion wires, and a preferred layer for each electrical node. Cells are generated according to optimization criteria that take into account not only geometric factors, such as cell area, aspect ratio, and wirelength, but also electrical features, namely capacitance to the substrate and contact and via minimization. The generator's placement strategy includes transistor clustering into regions, global region placement by linear ordering, and two-dimensional local transistor placement. The routing combines Steiner trees and Lee algorithms. Object-oriented programming paradigms were used in the implementation of the program, written in C++ language. Experimental results for small and medium-sized cells are presented.>

An architectural configuration for the back-propagation (BP) algorithm is illustrated. The circuit solution for the basic blocks is presented, and the effect of weight discretization on the BP algorithm is analyzed. It is demonstrated, through simulations, how the BP algorithm can be operated successfully with discretized weights. In particular, better performances can be achieved with an exponential discretization, i.e. the strength of weights varies exponentially with the controlling variable (voltage). The discretized voltage values differ by a quantity high enough that the neural network can be backed up with a refresh technique in combination with a multilevel dynamic memory that entails a particularly low wiring cost. A quasi-analog adaptive architecture is devised, properly matching the BP algorithm, and its CMOS circuit implementation is detailed. The mechanism controlling weight changes is simple enough to be reproduced locally at each synapsis site, thus meeting one of the requirements for an efficient storage technology for analog VLSI

The problem of the efficient simulation of neural networks on parallel machines is addressed. First, the computationally most efficient neural algorithms capturing the functionality of the network are searched for. Then their implementations on a given concurrent machine (a transputer array programmed in Occam) is presented and discussed. Single-layer networks, described by the additive, or Hopfield, model are considered. Results of the solution of optimization problems (analog/digital conversion and the traveling salesman problem) are given.>