Diabetic Retinopathy (DR) is one of the leading causes of blindness for people who have diabetes in the world. However, early detection of this disease can essentially decrease its effects on the patient. The recent breakthroughs in technologies, including the use of smart health systems based on Artificial intelligence, IoT and Blockchain are trying to improve the early diagnosis and treatment of diabetic retinopathy. In this study, we presented an AI-based smart teleopthalmology application for diagnosis of diabetic retinopathy. The app has the ability to facilitate the analyses of eye fundus images via deep learning from the Kaggle database using Tensor Flow mathematical library. The app would be useful in promoting mHealth and timely treatment of diabetic retinopathy by clinicians. With the AI-based application presented in this paper, patients can easily get supports and physicians and researchers can also mine or predict data on diabetic retinopathy and reports generated could assist doctors to determine the level of severity of the disease among the people.

Recently, a new transmission method has been proposed for power-efficient wireless communication systems called Orthogonal Frequency Division Multiplexing with Index Modulation (OFDM-IM). This method offers high spectral efficiency with good error performance. The greedy detection (GD) scheme of subcarrier indices is often used to reduce the complexity of the OFDM-IM system in comparison to other relevant detectors. In this letter, an optimized greedy detection (OGD) scheme is proposed. The received subblock is divided into mini-subblocks to decrease the risk of error. The Total Symbol Error Probability (TSEP) is derived using a closed-form expression to evaluate the performance. Simulation and analytic results demonstrate the superiority of the proposed detector.