Diabetes is a long-term illness caused by the inefficient use of insulin generated by the pancreas. If diabetes is detected at an early stage, patients can live their lives healthier. Unlike previously used analytical approaches, deep learning does not need feature extraction. In order to support this viewpoint, we developed a real-time monitoring hybrid deep learning-based model to detect and predict Type 2 diabetes mellitus using the publicly available PIMA Indian diabetes database. This study contributes in four ways. First, we perform a comparative study of different deep learning models. Based on experimental findings, we next suggested merging two models, CNN-Bi-LSTM, to detect (and predict) Type 2 diabetes. These findings demonstrate that CNN-Bi-LSTM surpasses the other deep learning methods in terms of accuracy (98%), sensitivity (97%), and specificity (98%), and it is 1.1% better compared to other existing state-of-the-art algorithms. Hence, our proposed model helps clinicians obtain complete information about their patients using real-time monitoring and can check real-time statistics about their vitals.

Deep learning-based machine learning models have shown significant results in speech recognition and numerous vision-related tasks. The performance of the present speech-to-text model relies upon the hyperparameters used in this research work. In this research work, it is shown that convolutional neural networks (CNNs) can model raw and tonal speech signals. Their performance is on par with existing recognition systems. This study extends the role of the CNN-based approach to robust and uncommon speech signals (tonal) using its own designed database for target research. The main objective of this research work was to develop a speech-to-text recognition system to recognize the tonal speech signals of Gurbani hymns using a CNN. Further, the CNN model, with six layers of 2DConv, 2DMax Pooling, and 256 dense layer units (Google’s TensorFlow service) was also used in this work, as well as Praat for speech segmentation. Feature extraction was enforced using the MFCC feature extraction technique, which extracts standard speech features and features of background music as well. Our study reveals that the CNN-based method for identifying tonal speech sentences and adding instrumental knowledge performs better than the existing and conventional approaches. The experimental results demonstrate the significant performance of the present CNN architecture by providing an 89.15% accuracy rate and a 10.56% WER for continuous and extensive vocabulary sentences of speech signals with different tones.

Recently, the Internet of Things (IoT) has attracted the interest of network researchers all over the world. Multimedia transmission through IoT presents an important challenge owing to nodes diversity. In this paper, adaptive versions of the real-time transport protocol (RTP) and real-time control protocol (RTCP), i.e., IoT-RTP and IoT-RTCP, are proposed. In these versions, the nature of IoT environments, such as transmission channels heterogeneity, sudden change in session size, and different multimedia sources, is considered. The basic idea of the proposed adaptive versions is to divide the large multimedia sessions into simple sessions with awareness of network status. To achieve this target, additional fields are added to the RTP and RTCP headers. These fields work under certain conditions to decrease the network overload. Finally, to test the performance of the proposed IoT-RTP and IoT-RTCP, a simulation environment is constructed using the network simulation package (NS2).The results of intensive simulations proved that the proposed adaptive versions of the multimedia protocols outperform the basic ones in terms of end-to-end delay, delay jitter, number of receiver reports, packet loss, throughput, and energy consumption.

A new tapering window is proposed for the uniform concentric circular arrays (UCCA) in order to reduce the sidelobe level at lower cost of wider beams and more practical feasibility and stability. ...