Noise Reduction Effect Research Articles

MRI tractography-guided PET image reconstruction regularisation using connectome-based nonlocal means filtering

Positron emission tomography (PET) molecular biomarkers and diffusion magnetic resonance imaging (dMRI) derived information show associations and highly complementary information in a number of neurodegenerative conditions, including Alzheimer’s disease. Diffusion MRI provides valuable information about the microstructure and structural connectivity (SC) of the brain which could guide and improve the PET image reconstruction when such associations exist. However, this potental has not been previously explored. In the present study, we propose a CONNectome-based non-local means one-atep late maximum a posteriori (CONN-NLM-OSLMAP) method, which allows diffusion MRI-derived connectivity information to be incorporated into the PET iterative image reconstruction process, thus regularising the estimated PET images. The proposed method was evaluated using a realistic tau-PET/MRI simulated phantom, demonstrating more effective noise reduction and lesion contrast improvement, as well as the lowest overall bias compared with both a median filter applied as an alternative regulariser and CONNectome-based non-local means as a post-reconstruction filter. By adding complementary SC information from diffusion MRI, the proposed regularisation method offers more useful and targeted denoising and regularisation, demonstrating the feasibility and effectiveness of integrating connectivity information into PET image reconstruction.

Acoustic Characteristics of Jute and Coir Non-woven Fabric

Effective noise reduction is essential because it can influence the health and well-being of living organisms significantly, both physically and psychologically. This necessitates the use of appropriate absorbing materials to minimize the negative impact of noise. In recent years, there has been growing interest in using jute, coir and natural fibre-based acoustic materials in architectural and interior applications due to their exceptional acoustic properties, eco-friendliness, cost-effectiveness and widespread availability. The study focuses on analysing the effects of some scrutinised testing parameters of jute, coir and jute-coir blended non-woven fabric samples on noise reduction coefficient through observing sound absorption coefficient. The sound absorption coefficient was measured using the impedance tube method as per the ASTM E-1050 standard. The mean value of the sound absorption coefficient observed at frequencies 250 Hz, 500 Hz, 1000 Hz, and 2500 Hz was used to calculate the noise reduction coefficient. A three-factor & three-level Box–Behnken experimental design was used for designing research and non-woven jute, coir and jute coir blended fabric sample planning. The experimental work showed that with an increase in non-woven jute fabric sample thickness from 15 mm to 45 mm, blending jute 50 % with coir 50% and non-woven fabric samples tested by creating air gaps (15 mm to 30 mm) resulted in higher sound absorption coefficient and improved noise reduction coefficient. The experimental findings and statistical analysis revealed that blending jute with coir and increasing the thickness of non-woven fabric led to a significant improvement in the acoustic performance of the tested samples. However, increasing the air gap resulted in only a marginal improvement in acoustic performance.

Research on improved level set image segmentation method.

Aiming at the shortcomings of the traditional level set model which only has good robustness to the weak boundary and strong noise of the original target image, this paper proposes an improved algorithm based on the no-weight initialization level set model, introducing bilateral filters and using implicit surface level sets to extract and segment the original target image object more accurately, clearly and intuitively in the evolution process. The experimental simulation results show that, compared with the traditional non-reinitialized level set model segmentation method, the improved method can more accurately extract the edge contours of the target image object, and has better edge contour extraction effect, and the original target noise reduction effect of the improved model is better than that of the model before the improvement. The original target image object edge contour takes less time to extract than the conventional non-reinitialized level set model before the improvement.

Distributed Recursive Estimation under Heavy-Tail Communication Noise

We consider distributed recursive estimation of an unknown vector parameter in the presence of impulsive communication noise. That is, we assume that interagent communication is subject to an additive communication noise that may have heavy-tails or is contaminated with outliers. To combat this effect, within the class of consensus+innovations distributed estimators, we introduce for the first time a nonlinearity in the consensus update. We allow for a general class of nonlinearities that subsumes, e.g., the sign function or componentwise saturation function. For the general nonlinear estimator and a general class of additive communication noises—that may have infinite moments of order higher than one—we establish almost sure convergence to the parameter . We further prove asymptotic normality and evaluate the corresponding asymptotic covariance. These results reveal interesting tradeoffs between the negative effect of “loss of information” due to incorporation of the nonlinearity and the positive effect of communication noise reduction. We also demonstrate and quantify benefits of introducing the nonlinearity in high-noise (low signal-to-noise ratio) and heavy-tail communication noise regimes.

Satisfaction Evaluation for Underpass Green Spaces in Mountainous Cities under the Perspective of Environmental Perception

The overpasses and the terrain under them in Chongqing, a mountainous city in China, are complex and diverse, and some spaces under the overpasses are integrated and reconstructed into the underpass green space for citizens to stroll about or have a rest. From the perspective of visitor perception, this paper constructs a perception evaluation system of the environmental characteristics of underpass green space in mountainous cities from the following five environmental perception dimensions: path organization, security, aesthetic value, physical environment, activities and cultural. The IPA-Kano model is used to quantify environmental perception, and the main environmental factors affecting the improvement of recreation satisfaction of underpass green space in three types of terrain are explored, with a view to improving the environment and service functions of underpass green spaces in high-density interchange networks in mountainous cities, and enhancing the attractiveness of underpass green spaces. It can be found from the study that: (1) Among the five environmental perception dimensions, visitors pay more attention to the physical environment quality of the underpass green space and their physical and psychological activity experience, while their demands for visual senses are relatively low. Due to the deficiency or lack of leisure facilities, sports facilities, children’s playgrounds and amusement equipment, the dimension of “activities and cultural perception” of the underpass green space has the lowest scores of all. (2) The existing sites, facilities and landscape resources of the underpass green space, different terrain types and underpass environment are the important reasons that affect the performance of environmental perception factors and their priority ranking results. (3) The improvement of security of the arrival path or sports facilities is beneficial to improve visitor satisfaction of underpass green space of three types of terrain. The number of environmental factors to be optimized of the three types of terrain are ranked as: mountainous green space > flat green space > concave green space. Among them, four environmental factors have a high priority in two kinds of underpass green space, which are the distribution and quantity of leisure facilities, the effect of noise reduction and sound insulation, the adequacy of activity venues and the distribution and quantity of sports facilities. Finally, according to the particularity of the underpass environment and the characteristics of three types of terrain, this paper puts forward some suggestions for optimizing the service function of underpass green space from five perceptual dimensions.

The Acoustic Performance of Natural Composites in Reducing Stress Levels: Textile Industry

The porous characteristics of recycled natural fibres make them suitable for use as acoustic materials. Straw and water hyacinth fibres are natural materials that can potentially be used as composites in damping devices. This study evaluated the acoustic performance of two types of reinforced composites containing natural fibers (water hyacinth and rice straw) and gypsum adhesives in reducing stress levels in the textile industry. The evaluation was carried out through laboratory tests using impedance tubes and direct testing in a textile factory to reduce the stress level of production machine workers and operators. Rice straw and water hyacinth fibres were thoroughly mixed in proven mass ratios of 10% and 30% with water and gypsum plaster as a binder. The mixture was pressed into a mould at a pressure of 3 MPa before being heated in an oven at 900ºC for 5 hours. Perforations measuring 4 to 8 mm in diameter were then made at equal distances on the panels. Acoustic panel performance tests were carried out with impedance tubes according to ISO 10534-2 standards at sound frequencies ranging from 0 to 6400 Hz. Field tests were also conducted at a textile factory, with each machine unit generating a sound source of 100 to 110 dB. Heart rate data was collected, and noise measurements were carried out before and after the panels were installed in the area around the operating machines. The results showed that the rice straw-gypsum composite with four perforations performed the best, achieving an α coefficient of 1.0 at a frequency of 1500 Hz and an NRC of 0.50, indicating effective noise reduction. The installation of acoustic panels around the noise source in the textile industry reduced noise levels by up to 9.8 dB and was found to affect workers' heart rates, indicating reduced stress levels. The questionnaire results also showed a significant effect on the stress levels of workers. The use of natural fibers in composite materials has the potential to be an eco-friendly and sustainable solution for soundproofing applications. Doi: 10.28991/CEJ-2023-09-06-02 Full Text: PDF

A Rolling Bearing Fault Diagnosis Method Based on the WOA-VMD and the GAT.

In complex industrial environments, the vibration signal of the rolling bearing is covered by noise, which makes fault diagnosis inaccurate. In order to overcome the effect of noise on the signal, a rolling bearing fault diagnosis method based on the WOA-VMD (Whale Optimization Algorithm-Variational Mode Decomposition) and the GAT (Graph Attention network) is proposed to deal with end effect and mode mixing issues in signal decomposition. Firstly, the WOA is used to adaptively determine the penalty factor and decomposition layers in the VMD algorithm. Meanwhile, the optimal combination is determined and input into the VMD, which is used to decompose the original signal. Then, the Pearson correlation coefficient method is used to select IMF (Intrinsic Mode Function) components that have a high correlation with the original signal, and selected IMF components are reconstructed to remove the noise in the original signal. Finally, the KNN (K-Nearest Neighbor) method is used to construct the graph structure data. The multi-headed attention mechanism is used to construct the fault diagnosis model of the GAT rolling bearing in order to classify the signal. The results show an obvious noise reduction effect in the high-frequency part of the signal after the application of the proposed method, where a large amount of noise was removed. In the diagnosis of rolling bearing faults, the accuracy of the test set diagnosis in this study was 100%, which is higher than that of the four other compared methods, and the diagnosis accuracy rate of various faults reached 100%.

Edge detection algorithm in complex image text information extraction

With the rapid development of network technology and information technology, the amount of information contained in images has increased significantly. How to effectively extract text information from complex images has become the focus of current research in this field. Firstly, the Canny algorithm in the edge detection algorithm is improved and applied to the edge detection of complex images. Then the K-means algorithm is optimized to achieve better clustering effect of pixels. Finally, the text information in the image is extracted from the two. The results show that under the influence of salt and pepper noise from 0% to 90%, the quality factor obtained by the improved Canny algorithm is at least 0.4, and the detection accuracy is higher; The minimum peak signal-to-noise ratio of the algorithm is 38, and the maximum mean square error is 30, which are both better than the LOG algorithm and the traditional Canny algorithm, and have better noise reduction effect and image fidelity. It is used together in the extraction process of image text information, and the text recognition accuracy rate of the combined algorithm reaches a maximum of 93%, and is stable at more than 90%, indicating that this method has a high text recognition accuracy rate and provides text extraction for complex images. A reference path is available.

Effect of Sub-Surface Damage Layer Removal by Sublimation Etching of 4H-SiC Bulk Wafers on PL Imaging of Crystal Defect Visibility

Improving the visibility of defects in nitrogen-doped 4H-SiC (0001) bare wafers by photoluminescence imaging (PLI) is essential for improving the epitaxial growth process and device yields. This study proposes sub-surface damage (SSD) introduced during the mechanical process of SiC wafers as a new factor in reducing defect visibility in PL images. To verify the effect of SSD, we observed the surface of a SiC wafer, which was thermally etched at about 3 μm. As a result, dramatic defect visibility improvement was observed when the surface roughness was sufficiently flat (Ra < 0.3 nm) after thermal etching. Thus, the results suggest that defect visibility in PL images can be improved by controlling SSD and surface roughness. Using the background noise reduction effect of the SSD removal, not only PLI but also many other wafer surface inspections are expected to be improved.

Effect of Pore Characteristics on Sound Absorption Ability of Permeable Pavement Materials

Permeable pavement materials are attracting great attention due to the superior benefits in fast drainage, driving safety, and noise reduction effectiveness. This study investigated the sound absorption behaviors of permeable pavement materials, including permeable cement concrete (PCC) and open-graded friction course asphalt mixture (OGFC). The sound absorption coefficients (SACs) of dense-graded cement concrete and dense-graded asphalt mixture were also measured for comparison. The sound absorption test was conducted by the impedance tube method according to ASTM E1050-19. Computed tomography (CT) scanning tests were conducted to obtain the pore characteristics of PCC and OGFC, including porosity distribution, pore size, and coordination number (CN). The porosity distribution, pore size distribution, and CN distribution presented a symmetrical trend of decreasing, then increasing, and then decreasing with the increase of specimen height. When OGFC and PCC showed similar porosities, the pore number of PCC was significantly larger than that of OGFC. Comparisons of the peak SAC and the average SAC were made between PCC and OGFC. Correlations were made between the SAC and the pore characteristics. Results indicated that with increasing porosity, the peak SAC and the average SAC both increased significantly for PCC and OGFC. The characteristic pore size, pore number, and CN distribution together affected the SAC. At the same porosity, OGFC mixtures presented larger average SAC compared to PCC, which was ascribed to the fact that more pores with larger size and a better pore connectivity existed in OGFC mixtures.

Noise Reduction Method of Pipeline Infrasonic Leakage Signal Based on Improved Prony Algorithm and Difference Energy Model

To solve the difficult problem of low-frequency noise processing in pipeline infrasonic leakage detection signals, a pipeline infrasonic leakage signal denoising method based on improved Prony algorithm and differential energy model was proposed to reduce the low-frequency interference noise in the signal and to improve the signal denoising effect. First, the frequency window of the effective signal is obtained according to the spectrogram of the infrasound signal. Aiming at the problem that the Prony algorithm is affected by noise, a difference energy model is proposed. The difference energy model is used to filter out the part of the frequency domain signal with large energy fluctuation, and a relatively stable preprocessing signal is obtained. In view of the instability of the traditional Prony algorithm, a Hankel matrix is established in the operation process. The stability is improved by extracting the extremum and residue of the signal instead of directly solving the sampling data points, and the extremum and residue of the effective signal are selected by combining the frequency window of the active ingredient. Finally, the effective signal is reconstructed to obtain a relatively stable infrasound leakage noise reduction signal. Experimental results show that the noise reduction technology based on the improved Prony algorithm and differential energy model can effectively reduce the noise of pipeline leakage signals. Compared with the traditional Prony algorithm, the noise reduction effect of the proposed method is up to 38.01% higher. Compared with the empirical mode decomposition method, the noise reduction effect of this method is improved by 9.25% at least, which opens up a new idea for pipeline leakage signal noise reduction.

Analysis of verification results of protective effects of hearing protectors in different industries

Objective: To get insight into the current practice of noise reduction effect of workers as they wore hearing protectors in different domestic enterprises and the possible affected factors. Methods: From October 2020 to April 2021, using a random sampling method, 1197 workers exposed to noise in petrochemical factories, textile factories, and parts manufacturing factories were selected as the study subjects. The noise reduction effect of hearing protectors worn by workers in daily use was tested using a hearing protector suitability testing system. The personal sound attenuation level (PAR) was compared among workers in three enterprises, Targeted intervention and repetitive testing were conducted for workers who did not meet the noise reduction effect required by the enterprise, and the changes in PAR of workers before and after the intervention were compared. The comparison of baseline PARs between two or more groups was performed using the Mann Whitney test, the comparison of baseline PARs with post intervention PARs was performed using the Wilcoxon signed rank sum test, and the comparison of qualitative data between two or more groups was performed using the Chi square test. Results: The median baseline PAR for all workers was 15 dB. Men, age<30 years old, education level at or above college level, working experience of 5 to 15 years, and those who used hearing protectors for 5 to 15 years had higher PARs, with statistically significant differences (P<0.05). The median difference in baseline PAR among workers from three enterprises was statistically significant (H=175.06, P<0.01). The median PAR of subjects who did not pass the baseline increased from 3 dB to 21 dB after intervention (Z=-27.92, P<0.01) . Conclusion: Some workers wearing hearing protectors do not meet the required PAR, and low PARs may be related to incorrect wearing methods and incorrect selection of hearing protectors. As a tool for testing, training, and assisting in selection, the hearing protector suitability testing system is of great significance for worker hearing protection.

Experiment on Noise Reduction of a Wavy Cylinder with a Large Spanwise Wavelength and Large Aspect Ratio in Aeroacoustic Wind Tunnels

Current research shows that the wavy shape can play an important role in drag reduction. Meanwhile, it also has the potential of noise reduction. In the present study, a kind of wavy shape of periodic cosine profile with a large spanwise wavelength and large aspect ratio was applied to the circular cylinder model. The experiments on the influence of various aspect ratios (ratio of wave wavelength to amplitude) on the far-field noise of the wavy cylinder were carried out in a 0.55 m × 0.4 m aeroacoustic wind tunnel. It is shown that the maximum decrease of the far-field SPL (Sound Pressure Level) between the wavy cylinder and baseline cylinder exceeded 37 dB within the frequency between 200 Hz and 1000 Hz. The noise reduction effect of the wavy cylinder will become better along with the increasing aspect ratio. However, there exists a critical aspect ratio near λ/a = 30. If the aspect ratio continues increasing, the noise reduction effect of the wavy cylinder will decrease instead of increasing. Finally, the computational fluid dynamics method is applied to reveal the noise reduction mechanism of this kind of wavy cylinder with a large spanwise wavelength and large aspect ratio. It is found that the periodic shedding vortex is disturbed and tends to be banded instead of showing alternate oscillation. The turbulence intensity and velocity fluctuation around the wavy cylinder will be also reduced. According to the vortex and sound theory, these changes are beneficial to the noise reduction. The large spanwise wavelength and large aspect ratio play a significant role in controlling the shedding vortex variation and adjusting the local flow field around the crest and trough of the wavy cylinder, which is the key factor to change the flow field and reduce the flow-noise of the wavy cylinder.

Formula omitted]-ToF: A feature-alignment and frequency-division time-of-flight data denoise network

Infrared wave time-of-flight (ToF) imaging is a important method to sense the 3D information of scene for Internet of Things (IoT) and artificial intelligent (AI). Driven by heavy demands from industry and users, ToF imaging has received significant research attention in recent year, but the artifacts of depth image still remain and need to be improved. Removing multiple artifacts of ToF data is usually treated as a multi-stage stitching problem for deep learning methods. However, the multi-stage cascade and cross-domain refinement architecture could increase the difficulty of model fitting and hurt the effect of noise reduction. In this paper, we classify the artifacts of ToF data as temporal-related or modulation frequency-related noise and propose a ToF denoising convolutional neural network (f2-ToF) to reduce multiple artifacts simultaneously. Specifically, a frequency-division structure is designed to reduce the influence of frequency-related noise in different modulation frequencies. For efficient correcting misalignment data and ensuring a one-stage end-to-end training, the feature-wise alignment module is proposed. In experiments, every proposed module effectively performed its designed task, and the whole framework achieved strong performance in ToF image refinement.

Photoplethysmogram Biometric Authentication Using a 1D Siamese Network.

In the head-mounted display environment for experiencing metaverse or virtual reality, conventional input devices cannot be used, so a new type of nonintrusive and continuous biometric authentication technology is required. Since the wrist wearable device is equipped with a photoplethysmogram sensor, it is very suitable for use for nonintrusive and continuous biometric authentication purposes. In this study, we propose a one-dimensional Siamese network biometric identification model using a photoplethysmogram. To maintain the unique characteristics of each person and reduce noise in preprocessing, we adopted a multicycle averaging method without using a bandpass or low-pass filter. In addition, to verify the effectiveness of the multicycle averaging method, the number of cycles was changed and the results were compared. Genuine and impostor data were used to verify the biometric identification. We used the one-dimensional Siamese network to verify the similarity between the classes and found that the method with five overlapping cycles was the most effective. Tests were conducted on the overlapping data of five single-cycle signals and excellent identification results were observed, with an AUC score of 0.988 and an accuracy of 0.9723. Thus, the proposed biometric identification model is time-efficient and shows excellent security performance, even in devices with limited computational capabilities, such as wearable devices. Consequently, our proposed method has the following advantages compared with previous works. First, the effect of noise reduction and information preservation through multicycle averaging was experimentally verified by varying the number of photoplethysmogram cycles. Second, by analyzing authentication performance through genuine and impostor matching analysis based on a one-dimensional Siamese network, the accuracy that is not affected by the number of enrolled subjects was derived.

A Novel ECG Signal Denoising Algorithm Based on Sparrow Search Algorithm for Optimal Variational Modal Decomposition.

ECG signal processing is an important basis for the prevention and diagnosis of cardiovascular diseases; however, the signal is susceptible to noise interference mixed with equipment, environmental influences, and transmission processes. In this paper, an efficient denoising method based on the variational modal decomposition (VMD) algorithm combined with and optimized by the sparrow search algorithm (SSA) and singular value decomposition (SVD) algorithm, named VMD-SSA-SVD, is proposed for the first time and applied to the noise reduction of ECG signals. SSA is used to find the optimal combination of parameters of VMD [K,α], VMD-SSA decomposes the signal to obtain finite modal components, and the components containing baseline drift are eliminated by the mean value criterion. Then, the effective modalities are obtained in the remaining components using the mutual relation number method, and each effective modal is processed by SVD noise reduction and reconstructed separately to finally obtain a clean ECG signal. In order to verify the effectiveness, the methods proposed are compared and analyzed with wavelet packet decomposition, empirical mode decomposition (EMD), ensemble empirical mode decomposition (EEMD), and the complete ensemble empirical mode decomposition with adaptive noise (CEEMDAN) algorithm. The results show that the noise reduction effect of the VMD-SSA-SVD algorithm proposed is the most significant, and that it can suppress the noise and remove the baseline drift interference at the same time, and effectively retain the morphological characteristics of the ECG signals.

A novel plumes treater for solid rocket motors during hot‐firing tests using ice tunnel structure

AbstractAiming at the perniciousness of the exhausted plumes from solid rocket motors during hot‐firing tests, a novel plume treater is proposed using the ice tunnel device. The feasibility and effectiveness of this ice tunnel treater were successfully verified by tests on two solid rocket motors, XX 127 and XX 500, with different fuel charges of about 1.5 and 700 kg, respectively. Results show that the plume temperature could be greatly reduced from around 2000 to below 100°C through the ice tunnel for both motors, and the effect of noise reduction as well as the elimination of gaseous hydrogen chloride was also measured to be available in the test of XX 500, indicating the new ice tunnel treater could quickly achieve the “three reductions” of high temperature, serious noise, and gas pollution of the solid rocket motor emissions. Besides, a numerical model considering the factors of air entrainment, afterburning, convective heat transfer, radiation heat transfer, and phase change was established to investigate the flow and heat transfer behaviors within the ice tunnel. The plume temperature at the outlet of the ice tunnel was in good agreement with the experimental data. The intensity of afterburning is mainly determined by the amount of entrained air and the CO concentration. The cooling capacity of the ice tunnel is mainly contributed by convection, air entrainment, and particle radiation. This work could provide new ideas and references for the technological upgrade of the ground test platforms for solid rocket motors.

Effects of Air Void Content, Crumb Rubber, and Pozzolanic Fillers on OGFC Laboratory Performance

Open-graded friction course (OGFC) is recognized for its ability for rapid stormwater drainage and effective noise reduction. Yet, several state highway agencies have limited its use because of concerns about its durability. The objective of this study was to investigate the impacts of air void (AV) reduction, crumb rubber (CR), and pozzolanic fillers on OGFC durability. Six mixtures were fabricated in the laboratory and their performance was evaluated. A control mix, 9.5-NMAS mix, two mixes incorporating CR, and two mixes prepared with pozzolanic fillers (i.e., Portland cement and fly ash) were evaluated. The test factorial was designed so that each mix would be evaluated at three different stages (i.e., production, construction, and field performance). A suite of laboratory tests was conducted including draindown, prediction of compaction effort, Cantabro abrasion loss, Hamburg wheel-tracking, Texas overlay tester, modified Lottman test, and boiling test to evaluate production, compaction, and OGFC resistance to raveling, permanent deformation, cracking, and moisture damage. Results showed that the reduction in AV and the use of CR and pozzolanic fillers considerably enhanced OGFC durability while maintaining appropriate functional performance (i.e., permeability).

Noise Attenuation by Half Flat tip Serrated Trailing Edge in Rotating Blades

Two rotating blade models with different half-flat tip trailing edge serrations were proposed. The flow characteristics and aerodynamic noise were simulated using the large-eddy simulation model and Ffowcs Williams and Hawking’s acoustic analogy, respectively. The effect of half-flat tip trailing edge serrations in reducing noise was investigated. Results showed that the proposed half-flat tip trailing edge serration designs can effectively reduce broadband noise, and the effectiveness of noise reduction was related to the wavelength-to-amplitude ratio of the half-flat tip trailing edge serrations. The Wide-serrated blade had better noise reduction performance, and the local noise reduction according to the simulations can be as high as 3.3 dBA. Besides, it was found that the aerodynamic performance of the rotating blades was not detrimentally affected by the introduction of half-flat tip serration.

A Hybrid Deep CNN-SVM Approach for Brain Tumor Classification

Background: Feature extraction process is noteworthy in order to categorize brain tumors. Handcrafted feature extraction process consists of profound limitations. Similarly, without appropriate classifier, the promising improved results can’t be obtained. Objective: This paper proposes a hybrid model for classifying brain tumors more accurately and rapidly is a preferable choice for aggravating tasks. The main objective of this research is to classify brain tumors through Deep Convolutional Neural Network (DCNN) and Support Vector Machine (SVM)-based hybrid model. Methods: The MRI images are firstly preprocessed to improve the feature extraction process through the following steps: resize, effective noise reduction, and contrast enhancement. Noise reduction is done by anisotropic diffusion filter, and contrast enhancement is done by adaptive histogram equalization. Secondly, the implementation of augmentation enhances the data number and data variety. Thirdly, custom deep CNN is constructed for meaningful deep feature extraction. Finally, the superior machine learning classifier SVM is integrated for classification tasks. After that, this proposed hybrid model is compared with transfer learning models: AlexNet, GoogLeNet, and VGG16. Results: The proposed method uses the ‘Figshare’ dataset and obtains 96.0% accuracy, 98.0% specificity, and 95.71% sensitivity, higher than other transfer learning models. Also, the proposed model takes less time than others. Conclusion: The effectiveness of the proposed deep CNN-SVM model divulges by the performance, which manifests that it extracts features automatically without overfitting problems and improves the classification performance for hybrid structure, and is less time-consuming. Keywords: Adaptive histogram equalization, Anisotropic diffusion filter, Deep CNN, E-health, Machine learning, SVM, Transfer learning.