Natural organic memristors exhibit promising synaptic behavior, thereby being potential candidates for synaptic devices in neuromorphic systems. This paper details the fabrication and evaluation of a neuromorphic system based on natural organic 16- and 32-level fructose memristors. The manufacturing process of fructose memristors is outlined comprehensively. The nonlinear characteristics of fructose memristors are examined, and a mapping method is employed to mitigate the nonlinear effects. The performance of the fructose memristor-based neuromorphic system on MNIST using a multi-layer perceptron is evaluated and reported with and without nonlinearity mapping. Without nonlinearity mapping, simulation results on MNIST indicate that fructose memristor-based neuromorphic systems achieve average accuracies of 65% for 16-level and 76% for 32-level devices. Applying the nonlinearity mapping technique has increased the average accuracies to 70% in 16-level and 81% in 32-level devices. This paper presents results that illustrate the potential and viability of the fructose memristor-based neuromorphic systems. The fructose memristor is a promising addition to sustainable alternatives for neuromorphic systems, encouraging further exploration into natural organic materials. © 2025 IEEE.

Although traditional human image recognition suggests that higher resolution images will yield better results than lower resolution images because they hold more details, the results of this study prove that low-resolution images may have their own niche in the training of Artificial Intelligence (AI) models for more accurate and reliable image recognition. The purpose of this study is to investigate the impact of image resolution on the performance of an Artificial Neural Network (ANN), by case study on budgie gender identification. This study will be an important reference for the training of color-oriented models by encouraging low-power and small-size data storage due to low-resolution images, decreasing cost and resources of AI applications. In the study, multiple data sets of images of budgie ceres with varying image resolutions, ranging from 22×22 to 256×256 pixels, are used to train and validate neural networks and test the reliability. It finds that the peak and end accuracy of the models are both right skewed with respect to the pixel size distribution and high accuracy. High reliability can be associated with a low image resolution, 22×22, 25×25, and 32×32 pixels image data set. The highest accuracy is obtained with an optimized ratio of a number of pixels to a number of images in a training dataset to create a stable learning rate and prevent overfitting or underfitting too rapidly. © 2025 IEEE.

Unlike traditional cloud-based Artificial Intelligence (AI) which sends data to remote servers for processing, Edge AI keeps data locally on the device or nearby servers [1]. This approach significantly reduces time for data transfer and makes it possible to react instantly, which is important in situations where even a small delay can cause problems, such as self-driving cars or industrial machinery. In addition, Edge AI significantly reduces power consumption and eases privacy concerns, demonstrating advantages of AI processing on edge devices. However, deploying machine learning (ML) models on edge devices also presents significant challenges, including limited computational resources and power constraints [2]. This study investigates these challenges by evaluating edge computing platforms - specifically, the Google Coral Accelerator and the Raspberry Pi are employed due to their low power consumption and compact form [3]. © 2025 Copyright held by the owner/author(s).