Facial palsy caused by nerve damage results in loss of facial symmetry and expression. A reliable palsy grading system for large-scale applications is still missing in the literature. Although numerous approaches have been reported on facial palsy quantification and grading, most employ hand-crafted features on relatively smaller datasets which limit the classification accuracy due to non-optimal face representation. In contrast, convolutional neural networks (CNNs) automatically learn the discriminative features facilitating the accurate classification of underlying tasks. In this paper, we propose to apply a typical deep network on a large dataset to extract palsy-specific features from face images. To prevent the inherent limitation of overfitting frequently occurring in CNNs, a generative adversial network (GAN) is applied to augment the training dataset. The deeply learned features are then used to classify the palsy disease into five benchmarked grades. The experimental results show that the proposed approach offers superior palsy grading performance compared to some existing methods. Such an approach is useful for palsy grading at large scale, such as primary health care.

A huge increase in the percentage of the world’s urban population poses resource management especially energy management challenges in smart cities. In this paper, the growing challenges of energy management in smart cities have been explored and significance of elimination of energy holes in converge cast communication has been discussed. The impact of mitigation of energy holes on the network lifetime and energy efficiency has been thoroughly covered. The particular focus of this work has been on energy-efficient practices in two major key enablers of smart cities namely, the Internet of Things (IoT) and Wireless Sensor Networks (WSNs). In addition, this paper presents a robust survey of state-of-the-art energy-efficient routing and clustering methods in WSNs. A niche energy efficiency issue in WSNs routing has been identified as energy holes and a detailed survey and evaluation of various techniques that mitigate the formation of energy holes and achieve balanced energy-efficient routing has been covered.

Bilateral facial asymmetry is frequently exhibited by humans but its combined evaluation across demographic traits including gender and ethnicity is still an open research problem. In this study we measure and evaluate facial asymmetry across gender and different ethnic groups and investigate the differences in asymmetric facial dimensions among the subjects from two public face datasets, the MORPH and FERET. To this end, we detect 28 facial asymmetric dimensions from each face image using an anthropometric technique. An exploratory analysis is then performed via a multiple linear regression model to determine the impact of gender and ethnicity on facial asymmetry. Post-hoc Tukey test has been used to validate the results of the proposed method. The results show that out of 28 asymmetric dimensions, females differ in 25 dimensions from males. African, Asian, Hispanic and other ethnic groups have asymmetric dimensions that differ significantly from those of Europeans. These findings could be important to certain applications like the design of facial fits, as well as guidelines for facial cosmetic surgeons. Lastly, we train a neural network classifier that employs asymmetric dimensions for gender and race classification. The experimental results show that our trained classifier outperforms the support vector machine (SVM) and k-nearest neighbors (kNN) classifiers.

Due to the technological advancements in wireless communication and their continuously increasing applications in collaborative and cooperative smart infrastructures, energy efficient data collection using wireless devices, has gained significant importance recently. Modern wireless sensor networks refer to network of low-powered and energy-constrained Internet of Things (IoT) devices. Although data collection using hierarchical routing with clustered network improves energy efficiency but introduces energy holes in the region closer to the data gathering center due to heavy relaying load on cluster heads. In this paper, first an improved data gathering center deployment technique for heterogeneous networks has been proposed. Technique for Order of Preference by Similarity to Ideal Solutions (TOPSIS), a multi-criteria decision-making technique, is used to determine the optimal location for the deployment of data gathering center. The proposed technique is adaptive to various shaped networks as required by IoT and increases energy efficiency. Secondly, an unequal clustering based on transmission distances has been proposed. Moreover, cubical, and spherical segmentation schemes for 3D heterogeneous networks have been proposed that assist the formation of unequal clusters. Finally, a shape independent data rate-based segmentation has been proposed that further extends the adaptability and scalability of the proposed unequal clustering. The results demonstrate that the proposed data traffic-based shape independent adaptive clustering scheme increases network lifetime up to 14.2% and 18.8% as compared to Fuzzy Logic based unequal clustering and IUCR respectively. It also reduces the overall network energy consumption up to 61.4% as compared to the state-of-the art unequal clustering methods.

The emergence of Internet of Things (IoT)-based heterogeneous wireless sensor network (HWSN) technology has become widespread, playing a significant role in the development of diverse human-centric applications. The role of efficient resource utilisation, particularly energy, becomes further critical in IoT-based HWSNs than it was in WSNs. Researchers have proposed numerous approaches to either increase the provisioned resources on network devices or to achieve efficient utilisation of these resources during network operations. The application of a vast proportion of such methods is either limited to homogeneous networks or to a single parameter and limited-level heterogeneity. In this work, we propose a multi-parameter and multi-level heterogeneity model along with a cluster-head rotation method that balances energy and maximizes lifetime. This method achieves up to a 57% increase in throughput to the base station, owing to improved intra-cluster communication in the IoT-based HWSN. Furthermore, for inter-cluster communication, a mathematical framework is proposed that first assesses whether the single-hop or multi-hop inter-cluster communication is more energy efficient, and then computes the region where the next energy-efficient hop should occur. Finally, a relay-role rotation method is proposed among the potential next-hop nodes. Results confirm that the proposed methods achieve 57.44%, 51.75%, and 17.63% increase in throughput of the IoT-based HWSN as compared to RLEACH, CRPFCM, and EERPMS, respectively.