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.
High density Wi-Fi networks require load balancing in order to ensure quality of service (QoS). In the traditional Wi-Fi networks, the wireless stations learn the access points (APs) load and make the association decisions themselves leading to uneven load distribution among the APs. The new paradigm, software defined networking (SDN), has a centralized architecture, which allows to manage, measure and control high density Wi-Fi networks easily. In this paper we propose a QoS-aware load balancing strategy (QALB) for software defined Wi-Fi networks (SD-Wi-Fi), as a solution to address the problem of Wi-Fi congestion among the OpenFlow enabled APs (OAPs). The SDN controller selects a load level up to which the association decisions are made by the OAPs without consulting the controller. The wireless stations from an overloaded OAP are handed to an underloaded OAP by considering multi-metrics such as the packet loss rate, received signal strength indicator (RSSI) and throughput. An emulation platform and a large-scalelow-cost testbed with the same settings are constructed to evaluate the performance of our load balancing strategy. The results show that in comparison to four non-static schemes such as, channel measurement based access selection scheme (CMAS), (DL-SINR) downlink-signal to interference plus noise ratio AP selection scheme (DASA), mean probe delay scheme (MPD) and RSSI scheme, the proposed QALB, optimizes the throughput up to 16%, reduces the average frame delay up to 19%, minimizes the number of re-transmissions by 49%, reduces the number of handoffs by 15%, improves the degree of load balancing by 22% and minimizes the re-association times by 38%, in high density SD-Wi-Fi. INDEX TERMS Emulation, high density, load balancing, QoS, Wi-Fi, SDN, testbed.
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.
Demographic estimation of human face images involves estimation of age group, gender, and race, which finds many applications, such as access control, forensics, and surveillance. Demographic estimation can help in designing such algorithms which lead to better understanding of the facial aging process and face recognition. Such a study has two parts-demographic estimation and subsequent face recognition and retrieval. In this paper, first we extract facial-asymmetry-based demographic informative features to estimate the age group, gender, and race of a given face image. The demographic features are then used to recognize and retrieve face images. Comparison of the demographic estimates from a state-of-the-art algorithm and the proposed approach is also presented. Experimental results on two longitudinal face datasets, the MORPH II and FERET, show that the proposed approach can compete the existing methods to recognize face images across aging variations.
In IEEE 802.11 wireless local area networks (WLANs), an important technique for medium access control (MAC) is the distributed coordination function (DCF). Two access mechanisms are provided by DCF, the default basic access mechanism and the optional request-to-send/clear-to-send (RTS/CTS) mechanism. The performance of IEEE 802.11 DCF networks has been predicted recently by NS-2 simulator based on a unified analytical model presenting the delay, throughput and stability [1]. NS-3 and OMNeT++ provide an essential platform to model IEEE 802.11 physical (PHY) and MAC layers, nevertheless the accuracy of which is yet not investigated. In this paper we present two studies, first is a comparative simulation study of the unified IEEE 802.11 DCF analytical model [1], by considering distinct network conditions, various topologies, different access modes and discrete system parameters in NS-3 and OMNeT++. A Linux based testbed is setup to validate the mathematical model and the simulation results. The second is the optimization study to adaptively tune the RTS threshold, so that the network operates in an access mode which steers to the maximum network throughput performance. An explicit expression of RTS threshold, verified by the simulations in NS-3 and OMNeT++, is obtained in contrast to previous studies based on channel estimation and numerical calculations. Performance evaluation is done by comparing the simulation, testbed and theoretical results. This study not only proves the credibility of the theoretical model of IEEE 802.11 DCF, but also assures that the results obtained from NS-3 and OMNeT++ are persuasive and provides a foundation for RTS threshold analysis in IEEE 802.11 WLANs for practical network design considerations.
In recent years, power companies have shown increasing interest in making strategic decisions to maintain profitable energy systems. Economic Load Dispatch (ELD) is a complex decisionmaking process where the output power of the entire power generating units must be set in a way that results in the overall economic operation of the power system. Moreover, it is a constrained multi-objective optimization problem. Now a days, there is a tendency to use metaheuristic methods to deal with the complexity of the ELD problem. Particle swarm optimization (PSO) is a subclass of metaheuristic methods inspired by fish schooling and bird flocking behaviors. However, the optimization performance of the PSO is highly dependent on fitness landscapes and can lead to local optima stagnation and premature convergence. Therefore, in the proposed study, two new variants of the PSO called global particle swarm optimizer with inertia weights (GPSO-w) and quasi-oppositional population based global particle swarm optimizer with inertia weights (QPGPSO-w) are proposed to address the complexity of the ELD problem. The ELD problem is formulated as an optimization problem and validation of the proposed methods is performed on IEEE standards (3 , 6, 13, 15, 40 & 140) unit Korean grid ELD test systems under numerous constraints and the obtained results are compared with the several recent techniques presented in the literature. The results obtained with convex systems showed excellent cost-effectiveness, while for non-convex systems sequential quadratic programming (SQP) optimizer was added to discover global minima even more efficiently. The proposed techniques were successful in solving the ELD problem and yielded better results compared to the reported results in the selected cases. It is further inferred that the proposed techniques with less algorithmic parameters reflected improved exploration and convergence characteristics.
Bit-level and pixel-level methods are two classifications for image encryption, which describe the smallest processing elements manipulated in diffusion and permutation respectively. Most pixel-level permutation methods merely alter the positions of pixels, resulting in similar histograms for the original and permuted images. Bit-level permutation methods, however, have the ability to change the histogram of the image, but are usually not preferred due to their time-consuming nature, which is owed to bit-level computation, unlike that of other permutation techniques. In this paper, we introduce a new image encryption algorithm which uses binary bit-plane scrambling and an SPD diffusion technique for the bit-planes of a plain image, based on a card game trick. Integer values of the hexadecimal key SHA-512 are also used, along with the adaptive block-based modular addition of pixels to encrypt the images. To prove the first-rate encryption performance of our proposed algorithm, security analyses are provided in this paper. Simulations and other results confirmed the robustness of the proposed image encryption algorithm against many well-known attacks; in particular, brute-force attacks, known/chosen plain text attacks, occlusion attacks, differential attacks, and gray value difference attacks, among others.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.