Pressure Loss in Ducts by Dissipative Splitter Silencers: Comparative Study of Standardized, Numerical and Experimental Results

Dissipative splitter silencers are widely used in industry for the reduction of propagated sound waves in ducts. Even though these systems are effective from the acoustics point of view when they are properly designed, they also introduce a pressure loss in the system, due to the modification of the properties of the flow circulating inside the duct. This effect is not desired in some industrial applications, so it is necessary to be able to predict the pressure loss as precisely as possible to design silencers according to the needs. Nevertheless, the prediction made by standards are usually limited to given geometries or flow speed. In this work, we present a comparative study on the results obtained for the pressure loss by means of the standards ISO 14163 and VDI 1801-1, numerical simulations with the finite element method, and experimental measurements. Additionally, two different profile shapes and four input face velocities are tested in order to know the influence of these parameters in the variations of the flow and the accuracy of the prediction of the different methods.

Research on dynamic load sharing characteristics of double input face gear split-parallel transmission system

The face gear power-split system has huge superiorities over the traditional transmission form in the application of modern rotorcraft, and it has become the research trend of the industry in recent years. Thus this paper took the double input face gear split-parallel transmission system used in the rotorcraft as the research target, and established its dynamics model through the lumped parameter theory. Based on the Newtonian second law, the dynamics equations were built and solved to gain the meshing forces and load sharing coefficients of the transmission system. Simultaneously, the impacts of the eccentric errors, support stiffness, and torsional stiffness on the load sharing characteristics were studied. The results show that the meshing forces and load sharing coefficients of each gear pair have periodic changes; the eccentric errors of each drive stage gear have only a significant effect on the corresponding drive stage. Moreover, the changes in the support stiffness of the split-torque shafts and double gear shafts mainly affect the load distribution of the parallel stage, and the shaft torsional stiffness is less sensitively to maintain load balance. In addition, the increment of the shaft stiffness increases the load sharing coefficients of the corresponding gear pairs.

Music Recommendation Based on Face Emotion Recognition

We propose a new approach for playing music automatically using facial emotion. Most of the existing approaches involve playing music manually, using wearable computing devices, or classifying based on audio features. Instead, we propose to change the manual sorting and playing. We have used a Convolutional Neural Network for emotion detection. For music recommendations, Pygame & Tkinter are used. Our proposed system tends to reduce the computational time involved in obtaining the results and the overall cost of the designed system, thereby increasing the system’s overall accuracy. Testing of the system is done on the FER2013 dataset. Facial expressions are captured using an inbuilt camera. Feature extraction is performed on input face images to detect emotions such as happy, angry, sad, surprise, and neutral. Automatically music playlist is generated by identifying the current emotion of the user. It yields better performance in terms of computational time, as compared to the algorithm in the existing literature.

Cascade Regression-Based Face Frontalization for Dynamic Facial Expression Analysis

Facial expression recognition has seen rapid development in recent years due to its wide range of applications such as human–computer interaction, health care, and social robots. Although significant progress has been made in this field, it is still challenging to recognize facial expressions with occlusions and large head-poses. To address these issues, this paper presents a cascade regression-based face frontalization (CRFF) method, which aims to immediately reconstruct a clean, frontal and expression-aware face given an in-the-wild facial image. In the first stage, a frontal facial shape is predicted by developing a cascade regression model to learn the pairwise spatial relation between non-frontal face-shape and its frontal counterpart. Unlike most existing shape prediction methods that used single-step regression, the cascade model is a multi-step regressor that gradually aligns non-frontal shape to its frontal view. We employ several different regressors and make a ensemble decision to boost prediction performance. For facial texture reconstruction, active appearance model instantiation is employed to warp the input face to the predicted frontal shape and generate a clean face. To remove occlusions, we train this generative model on manually selected clean-face sets, which ensures generating a clean face as output regardless of whether the input face involves occlusions or not. Unlike the existing face reconstruction methods that are computational expensive, the proposed method works in real time, so it is suitable for dynamic analysis of facial expression. The experimental validation shows that the ensembling cascade model has improved frontal shape prediction accuracy for an average of 5% and the proposed method has achieved superior performance on both static and dynamic recognition of facial expressions over the state-of-the-art approaches. The experimental results demonstrate that the proposed method has achieved expression-preserving frontalization, de-occlusion and has improved performance of facial expression recognition.

Patch Attention Layer of Embedding Handcrafted Features in CNN for Facial Expression Recognition

Recognizing facial expression has attracted much more attention due to its broad range of applications in human–computer interaction systems. Although facial representation is crucial to final recognition accuracy, traditional handcrafted representations only reflect shallow characteristics and it is uncertain whether the convolutional layer can extract better ones. In addition, the policy that weights are shared across a whole image is improper for structured face images. To overcome such limitations, a novel method based on patches of interest, the Patch Attention Layer (PAL) of embedding handcrafted features, is proposed to learn the local shallow facial features of each patch on face images. Firstly, a handcrafted feature, Gabor surface feature (GSF), is extracted by convolving the input face image with a set of predefined Gabor filters. Secondly, the generated feature is segmented as nonoverlapped patches that can capture local shallow features by the strategy of using different local patches with different filters. Then, the weighted shallow features are fed into the remaining convolutional layers to capture high-level features. Our method can be carried out directly on a static image without facial landmark information, and the preprocessing step is very simple. Experiments on four databases show that our method achieved very competitive performance (Extended Cohn–Kanade database (CK+): 98.93%; Oulu-CASIA: 97.57%; Japanese Female Facial Expressions database (JAFFE): 93.38%; and RAF-DB: 86.8%) compared to other state-of-the-art methods.

Improvements on Learning Kernel Extended Dictionary for Face Recognition

Kernel extended dictionary learning model (KED) is a new type of Sparse Representation for Classification (SRC), which represents the input face image as a linear combination of dictionary set and extended dictionary set to determine the input face image class label. Extended dictionary is created based on the differences between the occluded images and non-occluded training images. There are four defaults to make about KED: (1) Similar weights are assigned to the principle components of occlusion variations in KED model, while the principle components of the occlusion variations have different weights, which are proportional to the principle components Eigen-values. (2) Reconstruction of an occluded image is not possible by combining only non-occluded images and the principle components (or the directions) of occlusion variations, but it requires the mean of occlusion variations. (3) The importance and capability of main dictionary and extended dictionary in reconstructing the input face image is not the same, necessarily. (4) KED Runtime is high. To address these problems or challenges, a novel mathematical model is proposed in this paper. In the proposed model, different weights are assigned to the principle components of occlusion variations; different weights are assigned to the main dictionary and extended dictionary; an occluded image is reconstructed by non-occluded images and the principle components of occlusion variations, and also the mean of occlusion variations; and collaborative representation is used instead of sparse representation to enhance the runtime. Experimental results on CAS-PEAL subsets showed that the runtime and accuracy of the proposed model is about 1% better than that of KED.

Optical Trajectory Manipulations Using the Self-Written Waveguide Technique

This study is novel for several reasons: We used a thin drop cast layer of dry photosensitive materials to study the behaviors of wet photopolymer media using microscopic distances during the Self-Written Waveguide (SWW) process; then, we examined the self-trajectories formed inside the solid material. The results provide a framework for theoretical and experimental examinations by handling the effects of manipulating the alignment of fibers. The other main advantage of these techniques is their lightweight, easy to process, highly flexible, and ultimately low-cost nature. First, the SWW process in wet photopolymer media (liquid solutions) was examined under three cases: single-, counter-, and co-fiber exposure. Then, the SWWs formed inside the solid material were examined along with the effects of manipulating the alignment of the fibers. In all cases, high precision measurements were used to position the fiber optic cables (FOCs) before exposure using a microscope. The self-writing process was indirectly monitored by observing (imaging) the light emerging from the side of the material sample during SWW formation. In this way, we examined the optical waveguide trajectories formed in Acrylamide/Polyvinyl Alcohol (AA/PVA), a photopolymer material (sensitized at 532 nm). First, the transmission of light by this material is characterized. Then, the bending and merging of the waveguides that occur are investigated. The predictions of our model are shown to qualitatively agree with the observed trajectories. The largest index changes taking place at any time during exposure, i.e., during SWW formation, are shown to take place at the positions where the largest exposure light intensity is present. Typically, such maxima exist close to the input face. The first maximum is referred to as the location of the Primary Eye. Other local maxima also appear further along the SWW and are referred to as Secondary Eyes, i.e., eyes deeper within the material.

Integarted Minimum Cost Sub-Block Matching Distance based Face Recognition using Internet of Things

Now a days one of the critical factors that affects the recognition performance of any face recognition system is partial occlusion. The paper addresses face recognition in the presence of sunglasses and scarf occlusion. The face recognition approach that we proposed, detects the face region that is not occluded and then uses this region to obtain the face recognition. To segment the occluded and non-occluded parts, adaptive Fuzzy C-Means Clustering is used and for recognition Minimum Cost Sub-Block Matching Distance(MCSBMD) are used. The input face image is divided in to number of sub blocks and each block is checked if occlusion present or not and only from non-occluded blocks MWLBP features are extracted and are used for classification. Experiment results shows our method is giving promising results when compared to the other conventional techniques.

Optical Trajectory Manipulations Using the Self-Written Waveguides Technique

In this paper, first the Self-Written Waveguide (SWW) process in wet photopolymer media (liquid solutions), are examined for three examples: single-, counter-, and co-fibers exposure. Then the SWWs formed inside solid material are examined including the effects of manipulating the alignment of the fibers. In all cases high precision measurements are used to position the fiber optic cables (FOCs) before exposure using a microscope. The self-writing process is indirectly monitored by observing (imaging) the light emerging from the side of the material sample during SWW formation. In this way the optical waveguide trajectories formed in an Acrylamide/Polyvinyl Alcohol (AA/PVA) a photopolymer material (sensitized at 532 nm) are examined. First the transmission of light by this material is characterized. Then the bending and merging of the waveguides which occur are investigated. The predictions of our model are shown to qualitatively agree with the observed trajectories. The largest index changes taking place at any time during the exposure, i.e. during SWW formation, are shown to take place at the positions where the largest exposure light intensity is present. Typically, such maxima exist close to the input face and the first maximum is referred to as the location of the Primary Eye. Other local maxima also appear further along the SWW and are referred to as Secondary Eyes, i.e. deeper within the material.

Eigenfaces Technique, an Improved Face Recognition Approach Using Neural Network

Image analysis and understanding, stands tall amongst all the technologies and face recognition is an eminent part of it. A face database is maintained as a logbook to identify an input face. This is accomplished by mere comparison amongst the face database. There are several face recognition techniques, of which, symmetry, Elastic Bunch Graph Matching (EBGM), and analytic-to-holistic recognition have been explored in this research paper. Other peculiar approaches like image based face recognition techniques like MLP, convolutional neural network, eigenfaces, associative neural networks, recirculation neural network and independent component analysis have been thoroughly discussed. Two vibrant face recognition databases, UMIST and ORL have proved to be extremely important in analyzing the results of face recognition. Eigen Face value approach has been anticipated with the associated analysis of results of face recognition. Another approach in face recognition is optimized multiperceptron, which will be acting as the reference to the optimized eigenfaces approach in this research paper, hence making this study more efficient through comparison.