Automatic Covid 19 Infected Chest X Ray Image Classification using Support Vector Machine
by Md. Abdul Matin | Abdur Rahman | S M Abdullah Al Shuaeb | Anwar Hossen "Automatic Covid-19 Infected Chest X-Ray Image Classification using Support Vector Machine"
Published in International Journal of Trend in Scientific Research and Development (ijtsrd), ISSN: 2456-6470, Volume-5 | Issue-4 , June 2021,
URL: https://www.ijtsrd.compapers/ijtsrd41283.pdf
Paper URL: https://www.ijtsrd.comcomputer-science/artificial-intelligence/41283/automatic-covid19-infected-chest-xray-image-classification-using-support-vector-machine/md-abdul-matin
The recent coronavirus disease COVID 19 is extending very speedily over the world for the sake of its very infectious nature and is announced nationwide by the world health organization WHO . The COVID 19 is a group of coronavirus that has caused panic all over the world. It enters people through the sneezing and coughing of the infected person and weakens the person and it then slowly infects the affected person’s lungs. In this study, we have classified the chest X Ray images like Covid 19 infected chest images or normal chest images. Classifying the chest X Ray images is hard and time consuming work for human beings. Hence, an automatic Covid 19 infected chest X Ray image or normal chest classification tool is very useful even for experience humans to classify a lot of chest X Ray images. For that, we have proposed a new machine learning technique to automatically classify the chest Covid 19 infected X Ray images or normal chest images. Hence, we have used a Machine learning ML model like Support Vector Machine SVM to classify Covid 19 infected chest images and normal chest images. For this work, at first, we have preprocessed the chest X Ray image. Then we have extracted the distinct features from the chest X Ray images. After that, these features have trained into Machine Learning ML algorithm and finally classify these images into the category. From the experiment, The Support Vector Machine SVM models achieving an accuracy of up to 93.1 .
Android mobile applications become an simple target for the attacker because of its open source background. Also user' lack of knowledge the process of installing and usage of the apps. To categorize fake and malware apps, all the earlier methods listening carefully on getting permission from the user and executing that particular mobile apps. A malware detection structure that discover fraudulent developer, to detect search rank fraud as well as malware in Google Play Store. The fraud application is detected by aggregate the three pieces of proof such as ranking based, co review based and rating based evidence. It combine efficiently for all the evidence for fraud detection. Detect fraud ranking in daily Apps head board. Avoid ranking manipulation. In the proposed system the detecting of normal and harmful application is analyzed by the SVM Algorithm. This system will analyze the uploaded application that are to be classifying the status which is dangerous application or normal application. The client can view the both the normal and harmful apps in ASP.NET. They can download the application after screening the secret manner. After using the apps the client can give the review on that downloaded apps. By the known review post for any application the admin will analyze the ASP.NET application for giving the ranking. The reviews are analyzed by the SVM Algorithm.
Paper URL: https://www.ijtsrd.com/computer-science/multimedia/27992/acoustic-scene-classification-by-using-combination-of-modwpt-and-spectral-features/mie-mie-oo
chemistry journal, high impact factor, call for paper management
Acoustic Scene Classification ASC is classified audio signals to imply about the context of the recorded environment. Audio scene includes a mixture of background sound and a variety of sound events. In this paper, we present the combination of maximal overlap wavelet packet transform MODWPT level 5 and six sets of time domain and frequency domain features are energy entropy, short time energy, spectral roll off, spectral centroid, spectral flux and zero crossing rate over statistic values average and standard deviation. We used DCASE Challenge 2016 dataset to show the properties of machine learning classifiers. There are several classifiers to address the ASC task. We compare the properties of different classifiers K nearest neighbors KNN , Support Vector Machine SVM , and Ensembles Bagged Trees by using combining wavelet and spectral features. The best of classification methodology and feature extraction are essential for ASC task. In this system, we extract at level 5, MODWPT energy 32, relative energy 32 and statistic values 6 from the audio signal and then extracted feature is applied in different classifiers.
Paper URL: https://www.ijtsrd.com/computer-science/database/26660/predition-model-for-stock-price-on-big-data-analytics/thin-thin-swe
engineering journal, open access journal of chemistry, indexed journal
Prediction in the stock market is very challenging in these days. Large datasets available from Twitter micro blogging platform and widely available stock market records. Machine learning was employ to conduct sentiment analysis of data and to estimate for future stock prices. The relation between sentiments and the stock value is to be determined. A comparative study of these algorithms Multiple linear Regression, Support Vector Machine and Artificial Neural Network are done.
Paper URL: https://www.ijtsrd.com/computer-science/other/26609/gait-recognition-for-person-identification-using-statistics-of-surf/khaing-zarchi-htun
medical science journal, best journal, call for paper languages
In recent years, the use of gait for human identification is a new biometric technology intended to play an increasingly important role in visual surveillance applications. Gait is a less unobtrusive biometric recognition that it identifies people from a distance without any interaction or cooperation with the subject. However, the effects of ""covariates factors"" such as changes in viewing angles, shoe styles, walking surfaces, carrying conditions, and elapsed time make gait recognition problems more challenging for research. Therefore, discriminative features extraction process from video frame sequences is challenging. This system proposes statistical gait features on Speeded Up Robust Features SURF to represent the biometric gait feature for human identification. This system chooses the most suitable gait features to diminish the effects of ""covariate factors"" so human identification accuracy is effectiveness. Support Vector Machine SVM classifier evaluated the discriminatory ability of gait pattern classification on CASIA B Multi view Gait Dataset .
