Narrow Results

Diabetic Retinopathy (DR) is a common retinal vascular disease to injure the retinal blood vessels. DR causes the vision-related disorder without showing any symptoms. As the condition becomes more severe, it can result the partial or complete vision loss. Numerous clinical approaches were developed for treating DR; still, the processing cost and processing period are high. For solving such difficulties, the Deep Spiking Neural Principle Component Analysis Network (DSNPCANet) is proposed for DR detection. The input retinal fundus images are employed for detecting the DR. Pre-processing is the initial process, where the Wiener filter is utilized for eliminating the noise. The optic disc segmentation is used to segment the optic disc, where the active contour model is employed, moreover, the Artery/Vein Classification Network (AVNet) is employed for segmenting the blood vessel using the preprocessed images. Furthermore, the significant features are extracted from the preprocessed, optic disc-segmented, and blood vessel-segmented images. At last, the DSNPCANet is employed for DR detection. Moreover, the accuracy, sensitivity, specificity, precision, and $F$1-score are utilized to validate the DSNPCANet, which yields the finest values of 90.67%, 91.26%, 89.86%, 90.19%, and 90.14%.

The appearance of the inside of a running pressure flow pipe, when viewed through a photo-lens, is often blurred and deformed by the influence of fluid pressure, temperature and type. This study proposes an image pre-processing method based on self-scoring restoration and self-calibration to solve the problems and make it adaptable to the complicated environments inside the pipe. The method consists of two stages, in the first stage, a restoration method based on Wiener filter is used to work with the defined merit functions to deal with the degenerated images, in the second stage, two images taken from different depths inside the pipe are used to calculate the distortion parameters according to the matching points obtained from those two pictures. The experiment results show the proposed method performs well in clarity and contrast and removes the distortion effectively.

Narrowband jammer excision is formulated as an optimization problem in this paper. Optimal filter weights are calculated/searched for by the computational intelligence techniques. We compare the error rate performance, complexity, and implementation issues of various computational intelligence techniques like Particle Swarm Optimization (PSO), Genetic Algorithm, and Least Mean Square (LMS). These techniques update the excision filter weights iteratively till the convergence criteria has been achieved. Bit Error Rate performance shows these techniques effectively suppress the Narrow Band Interference. It has been observed that PSO-based algorithm with tuned parameters outperforms other schemes of PSO and the other algorithms. It approaches the optimum performance in fewer iterations with ease in implementation.

This work describes a new scheme for denoising noisy electrocardiogram (ECG) signals. In the first step, the noise variance is estimated using the well-known DONOHO’s estimator followed by the wavelet-based baseline wander removing. In the second step, the estimated variance is employed in the adaptive 1D Wiener filter to reduce the additive noise. Next, a Low Pass filter, based on the FFT, is applied on the resulting denoised signal. Furthermore, a cascaded Savitzky–Golay (SG) smoother filter is applied to refine the restoration process. The final step consists in the recovering of the $R$-peaks and the surrounding areas. It can be reported that the suggested algorithm is optimal for the additive Gaussian noise and is useful for other types of noises. Both qualitative and quantitative results, achieved from several experimental tests, establish high-quality restoration ability and the efficiency of the proposed method. Thus, when compared to some powerful techniques recently published, the designed algorithm demonstrates very competitive performances.

In today’s scientific epoch, speech is an important means of communication. Speech enhancement is necessary for increasing the quality of speech. However, the presence of noise signals can corrupt speech signals. Thereby, this work intends to propose a new speech enhancement framework that includes (a) training phase and (b) testing phase. The input signal is first given to STFT-based noise estimate and NMF-based spectra estimate during the training phase in order to compute the noise spectra and signal spectra, respectively. The obtained signal spectra and noise spectra are then Wiener-filtered, then empirical mean decomposition (EMD) is used. Because the tuning factor of Wiener filters is so important, it should be computed for each signal by coaching in a fuzzy wavelet neural network (FW-NN). Subsequently, a bark frequency is computed from the denoised signal, which is then subjected to FW-NN to identify the suitable tuning factor for all input signals in the Wiener filter. For optimal tuning of $\eta$, this work deploys the fitness-oriented elephant herding optimization (FO-EHO) algorithm. Additionally, an adaptive Wiener filter is used to supply EMD with the ideal tuning factor from FW-NN, producing an improved speech signal. At last, the presented approach’s supremacy is proved with varied metrics.

This paper proposes the use of a modified Wiener digital restoration technique for multi-frame image sequences that are degraded by both blur and noise. The proposed multi-channel Wiener restoration filter accounts for both intra-frame (spatial) and inter-frame (temporal) correlation. A modified cross-correlation formula between consecutive frames, which directly utilizes the motion vectors in the calculation of correlation among frames is derived and implemented in a multi-frame Wiener filter. Our modification estimates the motion vectors (horizontal and vertical) between consecutive frames using the three-step method, and then uses the estimated motion vectors to modify the cross-correlation terms in the formula for restoration. The performed simulations verified that the multi-frame restoration algorithm, that uses the motion information among different frames in restoration, gives improved results than both of the single frame independent restoration and the multi-channel restoration without considering the motion vectors.

The gravity recovery and climate experiment (GRACE) satellite mission has been providing near-continuous measurements of Earth's mass variations at regional spatial scales since early 2003, with applications to hydrologic, oceanographic, and cryospheric research. Motivated by recent regional land ice solutions, we analyze an array of simulated GRACE-like signals and seek optimal procedures to denoise the time series and accurately determine the seasonal timing and the corresponding seasonal and net mass balances. For the purpose of signal denoising we consider Gaussian smoothing, wavelet thresholding, the ensemble empirical mode decomposition (EEMD), the complete EEMD with adaptive noise (CEEMDAN), and a Wiener filter. We achieve the best denoising performance with a Wiener filter where the signal and noise spectra are estimated with Gaussian smoothing and the highest frequency wavelet coefficients, respectively. For the purpose of estimating seasonal timing we consider wavelet multiresolution analysis, EEMD, CEEMDAN, and a new cluster analysis of the ensemble of seasonal intrinsic mode functions that result from executing the EEMD and CEEMDAN. We select CEEMDAN cluster analysis as the best approach due to its consistent performance and ability to provide reliable uncertainties. Lastly, we investigate the effect of signal noise, high-frequency signal power, and data gaps, on the accuracy of the estimated parameters.

Back Ground: Liver tumors are a type of growth found in the liver which can be categorized as malignant or benign. It is also called as hepatic tumors. Early stage detection of tumor could be treated at a faster phase; if it is left undiagnosed it may lead to several complications. Traditional method adopted for diagnosis can be time consuming, error-prone and also requires an experts study. Hence a non invasive diagnostic method is required which overcomes the flaws of conventional method. Liver segmentation from CT images in post processing techniques not only is an essential prerequisite, but, by playing an important role in confirming liver function, pathological, and anatomical studies, is also a key technique for diagnosis of liver disease. Hence in the proposed study Fast greedy snakes algorithm in abdominal CT images were used for segmenting tumor portion.

Aim & Objectives: The aim and objectives of study is: (i) to segment tumor region in the liver image using Fast Greedy Snakes Algorithm (FGSA); (ii) to extract the GLCM features from the segmented region; (iii) to classify the normal and abnormal liver image using neural network classifier.

Methodology: The study involved a total of 30 normal and 30 abnormal Images from database. In the proposed study automated segmentation was performed using Fast Greedy Snakes (FGS) Algorithm and the features were extracted using GLCM method. Classification of normal and abnormal images was carried out using Back propagation Neural Network classifier.

Result: The proposed FGS algorithm provides accurate segmentation in liver images. Statistical features like mean, kurtosis, correlation and Entropy showed a higher value for the normal image than liver tumor image. On the other hand, features like Skewness, Homogeneity, contrast, Energy and standard deviation showed a comparatively higher value for a liver tumor image than the normal. Statistical features such as Mean, Contrast, Homogeneity and standard deviation are statistically significant at $p<0.01$. Features like correlation, entropy and energy exhibits significance at $p<0.05$. The feature extracted values provided significant difference between the normal and abnormal liver images. The neural network classifier yields the sensitivity of 95.8%, sensitivity of 81.4% and achieved the overall accuracy of 92%.

Conclusion: A most accurate, reliable and fast automated method was implemented to segment the liver tumor image using Fast Greedy snakes algorithm. Hence the proposed algorithm resulted in effective segmentation and the classifier could classify the normal and abnormal images with greater accuracy.

According to WHO, 2.6 million babies die during pregnancy. Good monitoring during the prenatal period could provide a significant reduction of this mortality rate. This is possible by detection and extraction of the fetal electrocardiogram (FECG). Extraction of that information is complex due to other noise coming from the mother and within the fetus that drowns out the fetal heart signal. However, new technology and improved filtering technique have provided ways to more accurately and efficiently gather various electrical components regarding fetal heart condition. In this paper, we propose a new source separation filtering method exploiting linear and nonlinear filtering techniques. Our method is a non-invasive extraction technique, where the source signal is the cardiac electrical signal acquired by non-invasive electrodes to facilitate the collection of signals and reduce the cost of the acquisition system; it differs from other existing methods in minimizing the number of input signals and the simplicity of its implementation. The fetal heart signal is drowned out by the maternal electrocardiogram (MECG). The problem that arises is the exact knowledge of the MECG signal affecting the chosen measuring electrode, since the MECG is dependent on the position of the electrode and the type of tissue that goes through. Therefore, its knowledge can be made only by a mathematical estimation. A DWT decomposition with adaptive thresholding based on an LMS filter is applied to extract the fetal signal. So first we extract the QRS complex of the FECG and detect the fetal heart rate (FHR).

This paper proposes an algorithm for restoring the motion blurred images. The restored images are then used for registering the template image. Restoration and registration of blurred images is very important problem from its application point of view. For restoration of motion blurred images, a modified Weiner filter based technique has been developed. An algorithm to register the restored image with given template image has also been proposed. The experimental results demonstrate that the images can successfully be registered in images with substantial amount of artificial and natural motion blur.