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 application of the test case prioritization method is a key part of system testing intended to think it through and sort out the issues early in the development stage. Traditional prioritization techniques frequently fail to take into account the complexities of big-scale test suites, growing systems and time constraints, therefore cannot fully fix this problem. The proposed study here will deal with a meta-heuristic hybrid method that focuses on addressing the challenges of the modern time. The strategy utilizes genetic algorithms alongside a black hole as a means to create a smooth tradeoff between exploring numerous possibilities and exploiting the best one. The proposed hybrid algorithm of genetic black hole (HGBH) uses the
... Show MorePreparation of epoxy/MgO and epoxy/SiO2 nanocomposites is
studding. The nano composites were processed by different nano
fillers concentrations (0, 0.01, 0.02, 0.03, 0.04, 0.05, 0.07 and
0.1 wt%). Epoxy resin and nanocomposites containing different
shape nano fillers of (MgO:SiO2 composites), are shear mixing with
ratio 1:1,with different nano hybrid fillers concentrations (0.025,
0.05, 0.1, 0.15, 0.2 and 0.25 wt%) to preparation of epoxy/(MgOSiO2)
hybrid nanocomposites. Experimental tests results indicate that
the composite materials have significantly higher modulus of
elasticity than the matrix material but the hybrid nanocomposites
have lower modulus of elasticity. The wear rate was decreased in
nanoc
This paper presents a cognition path planning with control algorithm design for a nonholonomic wheeled mobile robot based on Particle Swarm Optimization (PSO) algorithm. The aim of this work is to propose the circular roadmap (CRM) method to plan and generate optimal path with free navigation as well as to propose a nonlinear MIMO-PID-MENN controller in order to track the wheeled mobile robot on the reference path. The PSO is used to find an online tune the control parameters of the proposed controller to get the best torques actions for the wheeled mobile robot. The numerical simulation results based on the Matlab package show that the proposed structure has a precise and highly accurate distance of the generated refere
... Show MoreThis research deals with increasing the hardening and insulating the petroleum pipes against the conditions and erosion of different environments. So, basic material of epoxy has been mixed with Ceramic Nano Zirconia reinforcement material 35 nm with the percentages (0,1,2,3,4,5) %, whereas the paint basis of broken petroleum pipes was used to paint on it, then it was cut into dimensions (2 cm. × 2 cm.) and 0.3cm high. After the paint and percentages are completed, the samples were immersed into the paint. Then, the micro-hardness was checked according to Vickers method and thermal inspection of paint, which contained (Thermal conduction, thermal flux and Thermal diffusivity), the density of the painted samples was calculate
... Show MoreAs organizations generate and store more data in the cloud and hybrid infrastructures, their databases’ attack surface area grows. This makes organizational databases a prime target for cyber-attacks. Using only the perimeter security and existing database controls is not enough to protect against APT, insider threat and zero-day attack. A novel Database Cybersecurity System framework is presented to move beyond silos to proactive, smart layered security, in this article. The proposed system provides real-time threat analytics, adaptive encryption, and incident automation all within one management centre. It involves designing a core monitoring agent, analysis engine based on machine learning, and policy enforcement module. Comparison a
... Show More