Blindness is a global health problem that affects billions of lives. Recent advancements in Artificial Intelligence (AI), (Deep Learning (DL)) has the intervention potential to address the blindness issue, particularly as an accurate and non-invasive technique for early detection and treatment of Diabetic Retinopathy (DR). DL-based techniques rely on extensive examples to be robust and accurate in capturing the features responsible for representing the data. However, the number of samples required is tremendous for the DL classifier to learn properly. This presents an issue in collecting and categorizing many samples. Therefore, in this paper, we present a lightweight Generative Neural Network (GAN) to synthesize fundus samples to train AI-based systems. The GAN was trained using samples collected from publicly available datasets. The GAN follows the structure of the recent Lightweight GAN (LGAN) architecture. The implementation and results of the LGAN training and image generation are described. Results indicate that the trained network was able to generate realistic high-resolution samples of normal and diseased fundus images accurately as the generated results managed to realistically represent key structures and their placements inside the generated samples, such as the optic disc, blood vessels, exudates, and others. Successful and unsuccessful generation samples were sorted manually, yielding 56.66% realistic results relative to the total generated samples. Rejected generated samples appear to be due to inconsistencies in shape, key structures, placements, and color.

No abstract

No abstract

In this study, modeling approach for interpretation of data logged from chemically field-effect transistor (CHEMFET) sensor is described. Firstly, backpropagation algorithm is used to train the proposed network by optimizing the parameters of the network. Then, by applying the optimized parameters obtained from the trained network, the feed forward neural network algorithm is implemented using C language for compatibility with 16-bit microcontroller board and the output is compared with the simulation output which has been simulated using MATLAB software. Initial findings showed that the neural the proposed method is able to provide excellence estimation of main ion concentration in mixed solution as well as capable to interpret and estimate the ion concentration in mixed solution. Index Terms-CHEMFET sensor, backpropagation algorithm, 16bit microcontroller board

No abstract