This paper tackles the complex issue of detecting and classifying epileptic seizures whilst maintaining the total calculations at a minimum. Where many systems depend on the coupling between multiple sources, leading to hundreds of combinations of electrodes, our method calculates the instantaneous phase between non-identical upper and lower envelopes of a single-electroencephalography channel reducing the workload to the total number of electrode points. From over 600 h of simulations, our method shows a sensitivity and specificity of $100\%$ for high false-positive rates and $83\%$ and $75\%$, respectively, for moderate to low false positive rates, which compares well to both single- and multi-channel-based methods. Furthermore, pre-ictal variations in synchronisation were detected in over $90\%$ of patients implying a possible prediction system.

This paper presents an integer-based digital processor for the calculation of phase synchronization between two neural signals. It is based on the measurement of time periods between two consecutive minima. The simplicity of the approach allows for the use of elementary digital blocks, such as registers, counters and adders. The processor, fabricated in a 0.18μm CMOS process, only occupies $0.05 \text{mm}^2$ and consumes 15nW from a 0.5V supply voltage at a signal input rate of 1024S/s. These low-area and low-power features make the proposed processor a valuable computing element in closed-loop neural prosthesis for the treatment of neural disorders, such as epilepsy, or for assessing the patterns of correlated activity in neural assemblies through the evaluation of functional connectivity maps.

Given the need for effective crop monitoring while reducing human intervention and workload, it is necessary to implement devices that operate autonomously and are durable. These devices must be capable of operating over long distances, operate with low energy requirements, and resist climatic adversities and external factors such as dust and water to function effectively in rural areas. In this work, we introduce a low-cost autonomous IP67 IoT vision device designed and implemented in a real-world scenario. The device is used for automatic detection of wheat characteristics in order to optimise human resources when monitoring the growth and health of crops. Equipped with algorithms capable of capturing and processing images, the device has been designed to be computationally efficient, cost effective and power efficient. The device utilises the LoRaWAN communication protocol and requires 2.878W and has 3.5 months of autonomy. Furthermore, it leverages specific low computational algorithms that can operate with low-resolution images making them more effective. To test the device in a real-world scenario, an algorithm that measures the height of wheat was introduced using classical vision techniques, with 97% accuracy. Furthermore, the device incorporates an ad-hoc trained YOLOv8 and YOLOV10 object detection machine learning algorithm for the detection of spikes and stubble areas, which achieves a recall of 71.1% and a precision of 79.5% for the YOLOv8. In the case of the YOLOv10, it achieves a recall of 70% and a precision of 77%. The results are validated by expert agronomists annotations and data collected via a custom created web platform for remote visualisation and decision making tasks.

Optimising vegetable production systems is crucial for maintaining and enhancing agricultural productivity, particularly for crops like lettuce. Separating the crop from the background poses a significant challenge when using automated tools. To address this, a novel technique has been developed to automatically detect the vegetative area of lettuces, optimising time and eliminating subjectivity during crop inspections. The proposed deep learning model integrates the YOLOv10 object detector, the K-means classifier, and a segmentation method known as superpixel. This combination enables lettuce area identification using bounding box labels instead of contour labels during training, improving efficiency compared to other methods like YOLOv8 and Detectron2. Additionally, the combination of the YKMS method with YOLOv8 (YKMSV8) is evaluated, where YKMS serves as a label assistant. These methods are also used as benchmarks to compare the proposed approach. For the training of each methods, a custom database has been created using a low-cost, low-power custom IoT node deployed on a real farm to provide the most accurate data. Throughout the comparison, a custom metric is used to evaluate performance both in training and inference, balancing computational cost and area error, making it applicable in agriculture. Performance metric is associated with computational cost factor and accuracy factor whose value are respectively 65% and 35%, ensuring applicability for autonomous agricultural devices. Computational cost is prioritised to maintain battery life during extended campaigns. The custom metric results during inference were YOLOv8: 81.9%, Detectron2: 84%, YKMS: 70.26%, and YKMSV8: 87.3%. Mean error values were YOLOv8: 3.3%, Detectron2: 3.9%, YKMS: 5.2%, and YKMSV8: 5.2%, while mean time values were YOLOv8: 1.01 s, Detectron2: 4.12 s, YKMS: 4.07 s, and YKMSV8: 0.46 s.

In this manuscript the authors, design new hardware efficient combinational building blocks for a Multi Layer Perceptron (MLP) unit which eliminates the need for hardware generic Digital Signal Processing (DSP) units and also eliminates the need for on-chip block RAMs (BRAMs). The components were designed to minimise power and area consumption without sacrificing throughput. All designs were validated in a Field Programmable Gate Array (FPGA) and compared against unrestricted CPU-MATLAB implementations. Furthermore, a (2,2,2,2) MLP with back propagation was implemented and tested in a FPGA showing a total hardware utilisation of just 3782 LUTs, and no DSP or BRAMs. The MLP was also built in a Application Specific Integrated Circuit (ASIC) using a 130 nm technology by Skywater 130A . The results show that the area occupation was just $0.12~mm^{2}$ and consumed just 100 mW at 100 MHz input stimulus.