No abstract

IntroductionThe aim of this study is to evaluate the performance of the offline smart phone-based Medios artificial intelligence (AI) algorithm in the diagnosis of diabetic retinopathy (DR) using non-mydriatic (NM) retinal images.MethodsThis cross-sectional study prospectively enrolled 922 individuals with diabetes mellitus. NM retinal images (disc and macula centered) from each eye were captured using the Remidio NM fundus-on-phone (FOP) camera. The images were run offline and the diagnosis of the AI was recorded (DR present or absent). The diagnosis of the AI was compared with the image diagnosis of five retina specialists (majority diagnosis considered as ground truth).ResultsAnalysis included images from 900 individuals (252 had DR). For any DR, the sensitivity and specificity of the AI algorithm was found to be 83.3% (95% CI 80.9% to 85.7%) and 95.5% (95% CI 94.1% to 96.8%). The sensitivity and specificity of the AI algorithm in detecting referable DR (RDR) was 93% (95% CI 91.3% to 94.7%) and 92.5% (95% CI 90.8% to 94.2%).ConclusionThe Medios AI has a high sensitivity and specificity in the detection of RDR using NM retinal images.

Automatic Speech Recognition (ASR) system gives better result in restricted conditions but under noisy conditions it does not perform well. The main aim of ASR research work is that a machine must recognize the entire input raw signal with 100% accuracy in real time. In the presence of noise, audiovisual features play a vital role in ASR systems. This paper summarizes various robust feature extraction techniques to study the performance of raw speech signal in automatic speech recognition. We also overview some recently proposed methods on the speech recognition, illustrating their pros and cons together with their detailed computational steps compared to other well known techniques.

No abstract

No abstract