The waste in the perishable goods supply-chain has prompted many global organizations (e.g., FAO and WHO), to develop the Hazard Analysis and Critical Control Points (HACCP) protocol that ensures a high degree of food quality, minimizing the losses in all the stages of the farm-to-fork chain. It has been proven that good warehouse management practices improve the average life of perishable goods. The advances in wireless sensors network (WSN) technology offers the possibility of a “smart” storage organization. In this paper, a low cost reprogrammable WSN-based architecture for functional warehouse management is proposed. The management is based on the continuous monitoring of environmental parameters (i.e., temperature, light exposure and relative humidity), and on their combination to extract a spatial real-time prediction of the product shelf life. For each product, the quality decay is computed by using a 1st order kinetic Arrhenius model to the whole storage site area. It strives to identify, in a way compatible with the other products’ shelf lives, the position within the warehouse that maximizes the food expiration date. The shelf life computing and the “first-expired first-out” logistic problem are entrusted to a Raspberry Pi-based central unit, which manages a set of automated pallet transporters for the displacement of products, according to the computed shelf lives. The management unit supports several commercial light/temperature/humidity sensor solutions, implementing ZigBee, Bluetooth and HTTP-request interfaces. A proof of concept of the presented pro-active WSN-based architecture is also shown. Comparing the proposed monitoring system for the storage of e.g., agricultural products, with a typical one, the experimental results show an improvement of the expected expiration date of about 1.2 ± 0.5 days, for each pallet, when placed in a non-refrigerated environment. In order to stress the versatility of the WSN solution, a section is dedicated to the implemented system user interfaces that highlight detecting critical situations and allow timely automatic or human interventions, minimizing the latter.

Abnormal gait and postural instability are common disorders in people affected by Parkinson's disease (PD). This paper proposes an embedded cyber-physical system for the identification and the real-time extraction of highly selective diagnostic indexes for PD patients. A noninvasive wearable and wireless architecture for both gait analysis and postural instability detection has been proposed and implemented on a programmable hardware. The combined analysis of electroencephalography and electromyography allows studying the motor cortex activity through the movement-related potentials, determining a novel set of indexes that could be used for the PD diagnosis and classification. In a future perspective of an application-specific integrated circuit implementation, the real-time data processing has been fully realized on the Altera Cyclone V field-programmable gate array (FPGA), without interactions with embedded processor architecture. Referring to an Altera Cyclone V SE 5CSEMA5F31C6N device, the whole implemented architecture exploits 90% of the available FPGA adaptive logic modules, 74% of the manageable registers, and 10.3% of the total memory, as well as 29.7% wires utilization. Furthermore, the system is able to provide the outputs in about 57 ms with a dynamically power dissipation of 89 mW. The platform has been tested in vivo on two Parkinson's patients and two healthy subjects (control group) covering three typical diagnostic scenarios: PD versus controls, drug treatment evaluation, and involuntary movements detection.

A novel mobile healthcare solution for remotely monitoring neuro-cognitive efficiency is here presented. The method is based on the spatio-temporal characterization of a specific event-related potential, called P300, induced in our brain by a target stimulus. P300 analysis is used as a biomarker: the amplitude and latency of the signal are quality indexes of the brain activity. Up to now, the P300 characterization has been performed in hospital through EEG analysis and it has not been experimented an algorithm that can work remotely and learn from the subject performance. The proposed m-health service allows remote EEG monitoring of P300 through a “plug and play” system based on the video game reaction of the subject under test. The signal processing is achieved by tuned residue iteration decomposition (t-RIDE). The methodology has been tested on the parietal-cortex area (Pz, Fz, and Cz) of 12 subjects involved in three different cognitive tasks with increasing difficulty. For the set of considered subjects, a P300 deviation has been detected: the amplitude ranges around 2.8-8 μV and latency around 300-410 ms. To demonstrate the improvement achieved by the proposed algorithm respect the state of the art, a comparison between t-RIDE, RIDE, independent component analysis (ICA) approaches, and grand average method is here reported. t-RIDE and ICA analyses report the same results (0.1% deviation) using the same data set (game with a detection of 40 targets). Nevertheless, t-RIDE is 1.6 times faster than ICA since converges in 79 iterations (i.e., t-RIDE: 1.95s against ICA: 3.1s). Furthermore, t-RIDE reaches 80% of accuracy after only 13 targets (task time can be reduced to 65s); differently from ICA, t-RIDE can be performed even on a single channel. The procedure shows fast diagnosis capability in cognitive deficit, including mild and heavy cognitive impairment.

In this paper, we propose a breakthrough single-trial P300 detector that maximizes the information translate rate (ITR) of the brain–computer interface (BCI), keeping high recognition accuracy performance. The architecture, designed to improve the portability of the algorithm, demonstrated full implementability on a dedicated embedded platform. The proposed P300 detector is based on the combination of a novel pre-processing stage based on the EEG signals symbolization and an autoencoded convolutional neural network (CNN). The proposed system acquires data from only six EEG channels; thus, it treats them with a low-complexity preprocessing stage including baseline correction, windsorizing and symbolization. The symbolized EEG signals are then sent to an autoencoder model to emphasize those temporal features that can be meaningful for the following CNN stage. This latter consists of a seven-layer CNN, including a 1D convolutional layer and three dense ones. Two datasets have been analyzed to assess the algorithm performance: one from a P300 speller application in BCI competition III data and one from self-collected data during a fluid prototype car driving experiment. Experimental results on the P300 speller dataset showed that the proposed method achieves an average ITR (on two subjects) of 16.83 bits/min, outperforming by +5.75 bits/min the state-of-the-art for this parameter. Jointly with the speed increase, the recognition performance returned disruptive results in terms of the harmonic mean of precision and recall (F1-Score), which achieve 51.78 ± 6.24%. The same method used in the prototype car driving led to an ITR of ~33 bit/min with an F1-Score of 70.00% in a single-trial P300 detection context, allowing fluid usage of the BCI for driving purposes. The realized network has been validated on an STM32L4 microcontroller target, for complexity and implementation assessment. The implementation showed an overall resource occupation of 5.57% of the total available ROM, ~3% of the available RAM, requiring less than 3.5 ms to provide the classification outcome.

This paper proposes a novel mobile healthcare system for remotely monitoring neuro-cognitive functions of impaired subjects and proposing possible treatments. Currently, only hospital centers perform similar analyses through fixed and wired electroencephalography (EEG) inspection. The solution proposed here works wirelessly and improves its accuracy learning by performances of the subject playing a game/test. The system is based on spatio-temporal detection and characterization of a specific brain potential named P300. It includes: i) a wearable wireless EEG device; ii) a gateway (tablet or smartphone) processing gathered data, also providing the test/game to the user. Given the above hardware settings, a new algorithm, named tuned-Residue Iteration Decomposition (t-RIDE), provides spatiotemporal features of P300s and a semantic-based reasoner allows taking into account factors which could modify the test if performed in non-standard conditions. The system has been adopted with 12 subjects involved in three different cognitive tasks with increasing difficulty. Fast diagnosis of cognitive deficits is reached, including mild and heavy impairments cases: t-RIDE processing is performed in 1.95s (after 79 iterations for convergence) whereas semantic matchmaking routine requires 2.5ms in the worst case. A case study for an Alzheimer injured patient is reported to corroborate and clarify the proposed approach.