Explore chapters and articles related to this topic
Internet of Things with Machine Learning-Based Smart Cardiovascular Disease Classifier for Healthcare in Secure Platform
Published in Ankan Bhattacharya, Bappadittya Roy, Samarendra Nath Sur, Saurav Mallik, Subhasis Dasgupta, Internet of Things and Data Mining for Modern Engineering and Healthcare Applications, 2023
Sima Das, Jaya Das, Subrata Modak, Kaushik Mazumdar
Highlights of work are as follows:It is difficult to store, determine, and predict data manually to overcome this problem. Machine learning techniques are used in our proposed model.Above proposed work overcomes challenges from healthcare organizations, the system is diagnosed heart disease at a reasonable price.To get accurate results, the proposed model removes noise using a bandpass filter and an acceptable signal range between 5 Hz and 50Hz.Stationary wavelet transform is used to remove human motion artefacts so that datasets are cleaner and results more accurately.Feature extraction and selection by using principal component analysis that chooses important features for heart disease prediction.Support vector machine (SVM) is used to detect heart problems, categorized as suffering from cardiovascular disease or not.
Genetic Algorithm and BFOA-Based Iris and Palmprint Multimodal Biometric Digital Watermarking Models
Published in D. P. Acharjya, V. Santhi, Bio-Inspired Computing for Image and Video Processing, 2018
This method fuses two biometric modality images by means of stationary wavelet transform (DSWT or SWT). The stationary wavelet transform is a wavelet transform procedure that is modeled to overcome the absence of translation invariance of the discrete wavelet transform. Translation invariance is accomplished by eliminating the down samplers and the up samplers in the DWT, and up-sampling the filter coefficients by a component of 2(j-1) $ 2(j-1) $ at the jth $ j^{th} $ level of the procedure. In summary, the SWT method can be described as follows:Decompose the two source images utilizing SWT at one level, resulting in three details sub-bands, and one approximation sub-band (HL, LH, HH and LL bands). Further, the approximate parts are averaged.Choose the absolute values of horizontal details of the image and subtract the second part of the image from first. Compute D=H1L2-H2L2≥0 $$ D = \left|H1 L2\right| - \left|H2 L2\right| \ge 0 $$ For the fused horizontal part perform elementwise multiplication of D and horizontal detail of the first image, and then subtract another horizontal detail of the second image multiplied by logical not of D.Find D for vertical and diagonal parts and acquire the fused vertical and details of the image. Further fused image is retrieved by applying ISWT.
Stationary Wavelet-Based Image Watermarking for E-Healthcare Applications
Published in Cybernetics and Systems, 2023
Med Sayah Moad, Narima Zermi, Amine Khaldi, Med Redouane Kafi
Stationary wavelet transform is similar to the discrete wavelet transform, except that the signal is not decimated and at each iteration, different low-pass and high-pass filters are used. For a signal X(n) of length N which must be divisible by 2j with J an integer representing the number of decompositions (Nardecchia, Vitale, and Duponchel 2021), Stationary wavelet transform approximation and detail coefficients for each scale j are given by: