“…In this experiment, we compared our CNN-DO-BN-SP method with traditional AI methods: Multiscale AM-FM (Murray et al, 2010 ), ARF (Nayak et al, 2016 ), BWT-LR (Wang et al, 2016 ), 4-level HWT (Wu and Lopez, 2017 ), and MBD (Zhang et al, 2017 ). The results were presented in Table 10 .…”
Section: Experiments Results and Discussionmentioning
confidence: 99%
“…For instances, Murray et al ( 2010 ) proposed to use multiscale amplitude modulation and frequency modulation (AM-FM) to identify MS. Nayak et al ( 2016 ) presented a novel method, combining AdaBoost with random forest (ARF). Wang et al ( 2016 ) combined biorthogonal wavelet transform (BWT) and logistic regression (LR). Wu and Lopez ( 2017 ) used four-level Haar wavelet transform (HWT).…”
Aim: Multiple sclerosis is a severe brain and/or spinal cord disease. It may lead to a wide range of symptoms. Hence, the early diagnosis and treatment is quite important.Method: This study proposed a 14-layer convolutional neural network, combined with three advanced techniques: batch normalization, dropout, and stochastic pooling. The output of the stochastic pooling was obtained via sampling from a multinomial distribution formed from the activations of each pooling region. In addition, we used data augmentation method to enhance the training set. In total 10 runs were implemented with the hold-out randomly set for each run.Results: The results showed that our 14-layer CNN secured a sensitivity of 98.77 ± 0.35%, a specificity of 98.76 ± 0.58%, and an accuracy of 98.77 ± 0.39%.Conclusion: Our results were compared with CNN using maximum pooling and average pooling. The comparison shows stochastic pooling gives better performance than other two pooling methods. Furthermore, we compared our proposed method with six state-of-the-art approaches, including five traditional artificial intelligence methods and one deep learning method. The comparison shows our method is superior to all other six state-of-the-art approaches.
“…In this experiment, we compared our CNN-DO-BN-SP method with traditional AI methods: Multiscale AM-FM (Murray et al, 2010 ), ARF (Nayak et al, 2016 ), BWT-LR (Wang et al, 2016 ), 4-level HWT (Wu and Lopez, 2017 ), and MBD (Zhang et al, 2017 ). The results were presented in Table 10 .…”
Section: Experiments Results and Discussionmentioning
confidence: 99%
“…For instances, Murray et al ( 2010 ) proposed to use multiscale amplitude modulation and frequency modulation (AM-FM) to identify MS. Nayak et al ( 2016 ) presented a novel method, combining AdaBoost with random forest (ARF). Wang et al ( 2016 ) combined biorthogonal wavelet transform (BWT) and logistic regression (LR). Wu and Lopez ( 2017 ) used four-level Haar wavelet transform (HWT).…”
Aim: Multiple sclerosis is a severe brain and/or spinal cord disease. It may lead to a wide range of symptoms. Hence, the early diagnosis and treatment is quite important.Method: This study proposed a 14-layer convolutional neural network, combined with three advanced techniques: batch normalization, dropout, and stochastic pooling. The output of the stochastic pooling was obtained via sampling from a multinomial distribution formed from the activations of each pooling region. In addition, we used data augmentation method to enhance the training set. In total 10 runs were implemented with the hold-out randomly set for each run.Results: The results showed that our 14-layer CNN secured a sensitivity of 98.77 ± 0.35%, a specificity of 98.76 ± 0.58%, and an accuracy of 98.77 ± 0.39%.Conclusion: Our results were compared with CNN using maximum pooling and average pooling. The comparison shows stochastic pooling gives better performance than other two pooling methods. Furthermore, we compared our proposed method with six state-of-the-art approaches, including five traditional artificial intelligence methods and one deep learning method. The comparison shows our method is superior to all other six state-of-the-art approaches.
“…Artificial Neural Networks (ANN) are currently one of the main techniques applied by the scientific community (FAN et al, 2013). Several techniques can be used, such as Multilayer Perceptron (MLP) (BOUGHRARA et al, 2016), Radial Basis Function (RBF) (WANG et al, 2016), Extreme Learning Machine (ELM) (SA JUNIOR; BACKES, 2016), Fuzzy Logic (KIM; KIM; KIM, 2015), Genetic Algorithms (GA) (MOREIRA et al, 2018). Another efficient method is genetic programming (GP), that generate knowledge base vectors.…”
Inspections in areas of difficult access or hostile to the human, pattern recognition, surveillance and monitoring, are some of the many applications in with Unmanned Aerial Vehicles (UAV), can be a solution, opening up new perspectives for the use of this technology. The navigation and the position of the UAVs can be made by autonomous method through the computational vision, which is a technology of construction of artificial systems capable of read information from images or any multidimensional data and making decisions. This work presents a review of the use of computer vision systems by UAVs, with a focus on its many applications. The main objective is to analyze the latest technologies used for the development of computer vision in UAVs, through the tools of data search, information storage and, mainly, processing and analysis of data. The researches encompasses a publication of recent works, 2011 onwards, from the Science Direct portal. For each work were analyzed the objectives, methodology and results. Based in this analysis, was made a comparison between the techniques and their challenges. From this, future outlook scenarios of UAVs using computational vision are mentioned.
“…The biorthogonal wavelet transform is found to be efficient for transforming the input MRI image. The transformed image can be further efficiently analyzed with the principal component analysis [27]. From the analyzed image, the lesion of the MS [28,29] can be efficiently detected with the regression model.…”
Abstract-Sclerosis is a disease that triggers mainly due to damage of nerve cells in the brain and spinal cord. Various impairments are observed with this disease. Analyzing this type of images is needed for the medical research field for early stage identification. So, the present paper uses Bivariate Gaussian Mixture distribution for analyzing the noisy sclerosis images. For this, the present paper uses neural network for classification. The proposed method is evaluated with various images of brain web repository and the results show the efficiency of the proposed method.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.