Emotion recognition has important applications in human-computer interaction. Various sources such as facial expressions and speech have been considered for interpreting human emotions. The aim of this paper is to develop an emotion recognition system from facial expressions and speech using a hybrid of machine-learning algorithms in order to enhance the overall performance of human computer communication. For facial emotion recognition, a deep convolutional neural network is used for feature extraction and classification, whereas for speech emotion recognition, the zero-crossing rate, mean, standard deviation and mel frequency cepstral coefficient features are extracted. The extracted features are then fed to a random forest classifier. In addition, a bi-modal system for recognising emotions from facial expressions and speech signals is presented. This is important since one modality may not provide sufficient information or may not be available for any reason beyond operator control. To perform this, decision-level fusion is performed using a novel way for weighting according to the proportions of facial and speech impressions. The results show an average accuracy of 93.22 %.
The deployment of UAVs is one of the key challenges in UAV-based communications while using UAVs for IoT applications. In this article, a new scheme for energy efficient data collection with a deadline time for the Internet of things (IoT) using the Unmanned Aerial Vehicles (UAV) is presented. We provided a new data collection method, which was set to collect IoT node data by providing an efficient deployment and mobility of multiple UAV, used to collect data from ground internet of things devices in a given deadline time. In the proposed method, data collection was done with minimum energy consumption of IoTs as well as UAVs. In order to find an optimal solution to this problem, we will first provide a mixed integer linear programming m
... Show MoreVideo copyright protection is the most generally acknowledged method of preventing data piracy. This paper proposes a blind video copyright protection technique based on the Fast Walsh Hadamard Transform (FWHT), Discrete Wavelet Transform (DWT), and Arnold Map. The proposed method chooses only frames with maximum and minimum energy features to host the watermark. It also exploits the advantages of both the fast Walsh Hadamard transform (FWHT) and discrete wavelet transforms (DWT) for watermark embedding. The Arnold map encrypts watermarks before the embedding process and decrypts watermarks after extraction. The results show that the proposed method can achieve a fast embedding time, good transparency, and robustness against various
... Show MoreObjective(s): The study aims to evaluating the quality of nursing care provided to children under five years to compare between quality related to type of health sectors; to determine the quality of nursing care and to compare between such care in Baquba Health Care Sector I and II.
Methodology: A descriptive study is carried out for the period from December 15th 2019 to May 1st 2020. A purposive "non- probability" sample, of (60) staff nurse and (60) children is selected. An adopted questionnaire has been selected for the study which consists of three parts. The first part is nurses’ socio-demographic characteristic; the second part is ch
... Show MoreThe research aims to identify the importance of using the style of the cost on the basis of activity -oriented in time TDABC and its role in determining the cost of products more equitably and thus its impact on the policy of allocation of resources through the reverse of the changes that occur on an ongoing basis in the specification of the products and thus the change in the nature and type of operations . The research was conducted at the General Company for Textile Industries Wasit / knitting socks factory was based on research into the hypothesis main of that ( possible to calculate the cost of activities that cause the production through the time it takes to run these activities can then be re- distributed product cost
... Show MoreRehabilitation robots are widely recognized as vital for restoring motor function in patients with lower-limb impairments. A Modified Fractional-Order Proportional-Integral-Derivative (MFOPID) controller is proposed to improve trajectory tracking of a 2-DoF Lower Limb Rehabilitation Exoskeleton Robot (LLRER). The classical FOPID is augmented with a modified control formulation by which steady-state error is reduced and the transient response is sharpened. Controller gains and fractional orders were tuned offline using a hybrid metaheuristic Improved Elk Herd Optimization hybridized with Grey Wolf and Multi-Verse Optimization algorithms (IElk-GM) so that exploration and exploitation are balanced. Superiority over the classical FOPID
... Show MoreIn this paper, the theoretical cross section in pre-equilibrium nuclear reaction has been studied for the reaction at energy 22.4 MeV. Ericson’s formula of partial level density PLD and their corrections (William’s correction and spin correction) have been substituted in the theoretical cross section and compared with the experimental data for nucleus. It has been found that the theoretical cross section with one-component PLD from Ericson’s formula when doesn’t agree with the experimental value and when . There is little agreement only at the high value of energy range with the experimental cross section. The theoretical cross section that depends on the one-component William's formula and on-component corrected to spi
... Show MoreIn this work, a new development of predictive voltage-tracking control algorithm for Proton Exchange Membrane Fuel Cell (PEMFCs) model, using a neural network technique based on-line auto-tuning intelligent algorithm was proposed. The aim of proposed robust feedback nonlinear neural predictive voltage controller is to find precisely and quickly the optimal hydrogen partial pressure action to control the stack terminal voltage of the (PEMFC) model for N-step ahead prediction. The Chaotic Particle Swarm Optimization (CPSO) implemented as a stable and robust on-line auto-tune algorithm to find the optimal weights for the proposed predictive neural network controller to improve system performance in terms of fast-tracking de
... Show More