In this work, we propose and encourage the sending of an IoT-based domestic systems conditions small scale programmable framework for grid-tie matrix converter that can efficiently be executed with low-control equipment plan with quick execution capacity. The proposed framework for matrix grid-tie converter has been performed based on an adaptive fuzzy sliding technique and furthermore monitors the grid status through an IoT server. The adaptive fuzzy sliding method was connected to the framework, and a unity power factor was fulfilled alongside the wanted sinusoidal input and output results. The proposed AFS-based matrix converter has been validated through simulation using MATLAB software. The control clock signals are generated for the positive and negative clock pulses of the sequence. Here the sinusoidal reference signal is compared with the switching frequency of the triangular carrier frequency. The hardware results were also verified to validate the simulation. When diverged from other standard techniques, the proposed AFS technique has achieved 97.23% efficiency in full load conditions.

Facial expression is one form of communication which being non‐verbal in nature precedes verbal communication in both origin and conception. Most of the existing methods for Automatic Facial Expression Recognition (AFER) are mainly focused on global feature extraction assuming that all facial regions contribute equal amount of discriminative information to predict the expression class. The detection and localization of facial regions that have significant contribution to expression recognition and extraction of highly discriminative feature distribution from those regions are not fully explored. The key contributions of the proposed work are developing novel feature distribution upon combining the discriminative power of shape and texture feature; determining the contribution of facial regions and identifying the prominent facial regions that hold abstract and highly discriminative information for expression recognition. The shape and texture features taken into consideration are Local Phase Quantization (LPQ), Local Binary Pattern (LBP), and Histogram of Oriented Gradients (HOG). Multiclass Support Vector Machine (MSVM) is used while one versus one classification. The proposed work is implemented on CK+, KDEF, and JAFFE benchmark facial expression datasets. The recognition rate of the proposed work is 94.2% on CK+ and 93.7% on KDEF, which is significantly more than the existing handcrafted feature‐based methods.

Wireless body sensor networks (WBSNs) monitor the changes within the human body by having continuous interactions within the nodes in the body network. Critical issues with these continuous interactions include the limited energy within the node and the nodes becoming isolated from the network easily when it fails. Moreover, when the node’s burden increases because of the failure of other nodes, the energy utilization as well as the heat dissipated increases much more, causing damage to the network as well as human body. In this paper, we propose a threshold-based fail proof lifetime enhancement algorithm which schedules the nodes in an optimal way depending upon the available energy level. The proposed algorithm is experimented with a real time system setup and the proposed algorithm is compared with different routing mechanisms in terms of various network parameters. It is inferred that the proposed algorithm outperforms the existing routing mechanisms.

In this work, the deep learning (DL)-based fifth-generation (5G) non-orthogonal multiple access (NOMA) detector is investigated over the independent and identically distributed (i.i.d.) Nakagami-m fading channel conditions. The end-to-end system performance comparisons are given between the DL NOMA detector with the existing conventional successive interference cancelation (SIC)-based NOMA detector and from results, it has been proved that the DL NOMA detector performance is better than the convention SIC NOMA detector. In our analysis, the long-short term memory (LSTM) recurrent neural network (RNN) is employed, and the results are compared with the minimum mean square estimation (MMSE) and least square estimation (LS) detector’s performance considering all practical conditions such as multipath fading and nonlinear clipping distortion. It has been shown that with the increase in the relay to destination (RD) channel gain, the bit error rate (BER) improves. Also, with the increase in fading parameter m, the BER performance improves. The simulation curves demonstrate that when the clipping ratio (CR) is unity, the performance of the DL-based detector significantly improves as compared to the MMSE and LS detector for the signal-to-noise ratio (SNR) values greater than 15 dB and it proves that the DL technique is more robust to the nonlinear clipping distortion.

In patients with chronic diseases condition, mobile health monitoring facility proves to play a significant role in providing significant assistance toward personal management. This research examined the use of smartphones by diabetes patients and their intentions to apply them for self-care and monitoring as well as management. This cross-sectional survey-based study was conducted in Jul-Aug 2021 with 200 diabetic patients (especially type 2) who were visiting specialized clinics and hospitals of Gujrat state, India. A validated questionnaire survey was designed to collect data, which included questions about demographics, information pertaining to other, use of cellphones, the Internet, and the intention to implement smartphones for diabetes monitoring, self-care, and self-management. A highest number of studied participants have mobile phone (97.5%) and smartphones (87%) and access the Internet on daily basis (83.5%). Younger participants were more inclined to use smartphone apps and have also shown more interest for continuous use in the future ( ). The majority of participants used apps for nutritional planning (85.5%), to monitor glucose control (76.5%), and for scheduling of diabetes appointments on the calendar (90.5%). Recommendations to use mobile app by doctors or healthcare profession were reported by 20.5% of the participants and attitude and future intention to use mobile apps were reported by the majority of participants. The majority of type 2 diabetes patients choose to use their cellphones and the internet or mobile phone reminder system for medication as well as to plan their diets, monitor their blood sugar levels, and communicate with their doctors. The findings of this research can be used to develop strategies and implement mHealth-based therapies to assist patients with type 2 diabetes to efficiently manage their health and might contribute to reducing patients’ out-of-pocket expenditure as well as reducing disability-adjusted life years (DAILY) attributed by DM.