Velagapudi Ramakrishna Siddhartha Engineering College

About: Velagapudi Ramakrishna Siddhartha Engineering College is a based out in . It is known for research contribution in the topics: Computer science & Antenna (radio). The organization has 1307 authors who have published 1155 publications receiving 6163 citations.

Classification of Hyperspectral Images using Edge Preserving Filter and Nonlinear Support Vector Machine (SVM)

Abstract: Hyperspectral image is acquired with a special sensor in which the information is collected continuously. This sensor will provide abundant data from the scene captured. The high voluminous data in this image give rise to the extraction of materials and other valuable items in it. This paper proposes a methodology to extract rich information from the hyperspectral images. As the information collected in a contiguous manner, there is a need to extract spectral bands that are uncorrelated. A factor analysis based dimensionality reduction technique is employed to extract the spectral bands and a weight least square filter is used to get the spatial information from the data. Due to the preservation of edge property in the spatial filter, much information is extracted during the feature extraction phase. Finally, a nonlinear SVM is applied to assign a class label to the pixels in the image. The research work is tested on the standard dataset Indian Pines. The performance of the proposed method on this dataset is assessed through various accuracy measures. These accuracies are 96%, 92.6%, and 95.4%. over the other methods. This methodology can be applied to forestry applications to extract the various metrics in the real world.

Weed Detection in Broad Leaves using Invariant U-Net Model

Abstract: Weeds grow in the fields along with crops lowering the crop yield with 30% more losses. Efficient use of chemical herbicides can inhibit the growth of weeds, but to do that we need the location of weeds to be known. Aerial images given by drones can be used as acquisition system for real time weed detection. Machine learning algorithms are still facing automatic detection challenge. So, we have proposed a deep learning based model to detect the presence of weeds from crops in a crop field taking image as an input through image processing. Convolutional Neural Network (CNN) is used for invariant feature extraction. Augmentation techniques are used to generate additional training images. InceptionV3 is used as feature extractor. U-Net is used for classification. The proposed system is tested on the land drone images. Accuracy of weed detection is more than 90%.

Harmonic analysis of wrist mechanism of robot manipulator

Abstract: Wrist mechanism is a part of robot manipulator which is used to provide the pitch and yaw motions to the end effectors for orienting the loads carried by the end effectors. The wrist mechanism is subjected to different types of vibrations because of the various working conditions. Due to these vibrations wrist mechanism experience higher deformations and stresses; this causes failure of wrist mechanism. It is important to study the dynamic behaviour of the wrist mechanism under different loads before adopting in the application. The structure of the wrist mechanism is modelled in the ANSYS Workbench software and analysed for harmonic loads. Proper boundary conditions, mesh and connections between links& pins are assigned to the wrist mechanism assembly. From the present work, peak deformations of links and pins are occurred at 569.83Hz. Further, the link are analysed with 3D composites those are carbon epoxy and E-glass epoxy. It is observed that carbon epoxy shows better stiffness than E-Glass epoxy and it has weight reduction of 13.76% compared with metals.

Indian Date Leaf FRP Composites: Mechanical and Dielectric Properties

Abstract: Natural fibers and their composites play a vital role in the fabrication of various components in automobile and structural components because of their superior specific performance. In order to satisfy day-to-day requirements in various sectors, new eco-friendly materials are introduced which are reinforced with renewable, cheap, and easily available natural fibers. A new leaf fiber, i.e., Indian date leaf (IDL), is introduced in this work and extracted by “pure splitting method” (PSM). Initially, the fiber is characterized for its density and tensile behavior. Surface morphology of the fiber is also examined by using JEOL JSM scanning electron microscope (SEM). Using IDL and IDL CT fibers as reinforcement in the polyester matrix, the composites are fabricated by wet lay-up technique. The fabricated composite specimens are tested to determine mechanical and dielectric properties as per ASTM procedures. Chemically treated IDL fiber exhibited 25.69 %, 4.6 % more tensile strength and modulus than untreated ones, and the stress vs. strain curves are drawn for all tested specimens. The specific tensile strength of chemically treated IDL FRP composites is 1.38 times higher than untreated IDL FRP composites whereas specific tensile modulus of IDL FRP composites is 1.04 times higher than treated IDL FRP composites at maximum fiber volume fraction. Chemically treated IDL FRP composites exhibited flexural strength, modulus of 63.47 MPa, 5 GPa under flexural loading, which is higher than untreated FRP composites. IDL FRP composites’ impact strength is 18.94 kJ/m2 at maximum fiber volume fraction. The dielectric strength is clearly decreasing with increase in fiber content, which gives an opportunity for a designer in selecting suitable lightweight material with reasonable insulation. A clear rougher surface at all portions on the surface of chemically treated IDL fibers is visualized from SEM image.