Nowadays Internet of Things (IoT) and mobile systems use more and more Machine Learning based solutions, which implies a high computation cost with a low energy consumption. This is causing a revival of interest in unconventional hardware computing methods capable of implementing both linear and nonlinear functions with less hardware overhead than conventional fixed point and floating point alternatives. Particularly, this work proposes a novel Radial Basis Function Neural Network (RBF-NN) hardware implementation based on Stochastic Computing (SC), which applies probabilistic laws over conventional digital gates. Several complex functions design to implement RBF-NN are presented and theoretically analyzed, such as the squared Euclidean distance and the stochastic Gaussian kernel similarity function between input samples and prototypes. The efficiency and performance of the methodology is tested over well-known pattern recognition tasks, including the MNIST dataset. The results show a low-cost methodology in terms of logic resources and power, along with an inherent capability to implement complex functions in a simple way. This methodology enables the implementation of massively parallel large scale RBF-NN with relatively low hardware requirements while maintaining 96.20% accuracy, which is nearly the same for the floating point and fixed point models (96.4% and 96.25%, respectively).
Reconfigurable intelligent surfaces (RIS) offer the potential to customize the radio propagation environment for wireless networks, and will be a key element for 6G communications. However, due to the unique constraints in these systems, the optimization problems associated to RIS configuration are challenging to solve. This paper illustrates a new approach to the RIS configuration problem, based on the use of artificial intelligence (AI) and deep learning (DL) algorithms. Concretely, a custom convolutional neural network (CNN) intended for edge computing is presented, and implementations on different representative edge devices are compared, including the use of commercial AI-oriented devices and a field-programmable gate array (FPGA) platform. This FPGA option provides the best performance, with performance increase over the closest FP32, GPU-accelerated option, and almost performance advantage when compared with the INT8-quantized, TPU-accelerated implementation. More noticeably, this is achieved even when high-level synthesis (HLS) tools are used and no custom accelerators are developed. At the same time, the inherent reconfigurability of FPGAs opens a new field for their use as enabler hardware in RIS applications.
Internet of Things (IoT) applications and mobile systems are more and more dependent on Machine Learning based solutions, thus requiring a big computational power with a low cost in terms of power consumption. This fact has revived the interest in nonconventional hardware computing methods capable to implement complex functions in a simple way in contrast with the conventional ones. This work proposes a novel hardware/software hybrid Self-Organizing Map (SOM) implementation using stochastic computing. In turn, to support this development, several stochastic block designs are presented as the squared Euclidian distance, and the Winner-Take-All (WTA) similarity check. The capabilities and performance of the methodology is tested over a well-known classification task as the Iris flower benchmark, archiving the same classification performance than the software solutions. The proposed solution presents a low-cost methodology in terms of hardware resources and power, due to its inherent capacity to implement complex functions in a simple way. This enables the methodology to implement large self-learning classifiers based on SOM with low hardware requirements.
21 November 2025 in IEEE Transactions on AgriFood Electronics
BioVIEW is a solar-powered, dual-camera Internet of Things (IoT) station designed for long-term, nondestructive biodiversity monitoring in remote habitats. Each station is built from wood and aluminum and integrates two 64-MP cameras, temperature and humidity sensors, programmable LED attractants, and a 30-W photovoltaic power system that powers two Raspberry Pi (RPi) controllers, ensuring months of autonomous operation. The BioVIEW station also provides dual communication options: mobile networks for high-bandwidth image uploads to servers, and LoRaWAN for ultra-low-power telemetry. This setup supports remote management and ensures resilient data delivery. Ten stations deployed across the Balearic Islands (Mallorca, Menorca, Ibiza, Formentera, Cabrera, and Dragonera) are generating a fixed-interval image archive to support supervised learning. In a proof-of-concept study, 62 labeled frames of Bactrocera oleae were used to train a support vector machine, achieving an accuracy of 0.86 and tracking cumulative counts within one specimen of ground truth over two weeks. Energy profiling across RPi models showed inference budgets ranging from 7 J (MobileNet on RPi 4) to 12 J (SVM on RPi 3), demonstrating the feasibility of edge-based analytics under strict power constraints. By combining energy-efficient hardware, event-driven capture, and a flexible classification framework, BioVIEW enables scalable, high-resolution biodiversity monitoring without harming either target or nontarget species.