iosr-JCE   Volume-23 ~ Issue-5 ~ Sep. - Oct. 2021

Abstract: In this paper we have presented a new approach to grid computing for processing video and image using Remote Method Invocation (RMI). Our proposed grid consists of four components: Donor, Server, Client and Service. Donor allows server to use its resources so that server can provide services to the clients using the donors' resources. Donor registers itself to the server as a resource holder. Server receives request along with dataset from a client for a specific service. Server splits the dataset into smaller units and invites the registered donors for processing the smaller units. Each donor sends processed data to the server. Server compiles the processed data received from different donors and performs some basic operations on the processed data and replies the client with the result. Performance of the grid is evaluated in terms of time complexity.

Key Word: Grid computing, RMI, Callback RMI, RMI registry, object registry.

[1] Vladimir Silva, "Grid Computing for Developers", Charles River Media,Inc. ISBN 1-58450-424-2
[2] I. Foster, "What is the Grid? A Three Point Checklist", GRIDToday, July 20, 2002.
[3] M.L.Liu, "Distributed Computing PRINCIPLES and APPLICATIONS",
[4] Rajkumar Kettimuthu, William Allcock, Lee Liming, John-Paul Navarro and Ian Foster,. "GridCopy: Moving Data Fast on the Grid", Proceedings of the Fourth High Performance Grid Computing Workshop to be held in conjunction with International Parallel and Distributed Processing Symposium (IPDPS 2007), March, 2007
[5] I. Foster, C. Kesselman, J. Nick, S. Tuecke, "Grid Services for Distributed System Integration", . Computer, 35(6), 2002

Abstract: Most researches belief that the left and the right retina of an individual are different. However, in this research Legendre moments are used to show that there are some similarities between the left and right retinal images. Some parts of the whole retinal image are used in Legendre moment calculation. Most effective parts are defined and selected for Legendre moment calculation. In this approach Orthogonal Legendre moments are used for feature extraction and dimensionality reduction. Legendre moments can preserve almost all the information of the left and right retinal images in few coefficients. After extracting the Legendre features from different parts of the left and right retinal images, similarity measurement is carried out by calculating the cosine distances between the feature vectors of different parts in a left retina and the feature vectors of different parts in a right retina. Training and evaluation are performed on the publicly available datasets CHASE_DB1 and Messidor-2 respectively. The proposed method provides a high probability of finding similarities between the left and the right retinal images based on different parts.

Key Words: Legendre moments, retina, cosine similarity, biometric, part-based

[1] C. Simon and I. Golstein, "A New Scientific Method of Identification," New York State Journal of Medicine, vol. 35, no. 18, pp. 901–906, 1935.
[2] Jonas JB, Schmidt AM, Müller-Bergh JA, et al: Human optic nerve fiber count and optic disc size, Invest Ophthalmol Vis Sci 33(6):1992, 2012.
[3] Quigley HA, Brown AE, Morrison JD, et al: The size and shape of the optic disc in normal human eyes, Arch Ophthalmol 108(1):51, 1990.
[4] Budenz, Donald L. "Symmetry between the right and left eyes of the normal retinal nerve fiber layer measured with optical coherence tomography (an AOS thesis)." Transactions of the American Ophthalmological Society vol. 106 (2008): 252-75.
[5] Fishman RS. Optic disc asymmetry. Arch Ophthalmol 1970;84:590-594.

Abstract: Currently, we witness the severe spread of the pandemic of the new Corona virus, COVID-19, which causes dangerous symptoms to humans and animals, its complications may lead to death. Although convolutional neural networks (CNNs) is considered the current state of the art image classification technique, it needs massive computational cost for deployment and training. In this paper, we propose an improved hybrid classification approach for COVID-19 images by combining the strengths of CNNs (using a powerful architecture called Inception) to extract features and a swarm based feature selection algorithm (Marine Predators Algorithm) to select the most relevant features. A combination of fractional order and marine predator's algorithm (FO MPA) is considered integration among a robust tool in mathematics named fractional order calculus (FO). The proposed approach was evaluated on two public COVID-19 X-ray datasets which achieves both high performance......

Key Words: Machine Learning, Natural Language Processing, SVM, NB, Sentiment Analysis

[1]. Ge, X.-Y. et al. Isolation and characterization of a bat sars-like coronavirus that uses the ace2 receptor. Nature 503, 535–538 (2013).
[2]. Al-qaness, M. A., Ewees, A. A., Fan, H. & Abd El Aziz, M. Optimization method for forecasting confirmed cases of covid-19 in china. J. Clin. Med. 9, 674 (2020).
[3]. Cauchemez, S. et al. Transmission scenarios for middle east respiratory syndrome coronavirus (mers-cov) and how to tell them apart. Eurosurveillance 18, 20503 (2013).
[4]. Huang, P. et al. Use of chest ct in combination with negative rt-pcr assay for the 2019 novel coronavirus but high clinical suspicion. Radiology 295, 22–23 (2020).
[5]. Zhu, H., He, H., Xu, J., Fang, Q. & Wang, W. Medical image segmentation using fruit fly optimization and density peaks clustering. Comput. Math. Methods Med. https://doi.org/10.1155/2018/3052852 (2018)..