Accurate segmentation of brain tumor plays a key role in the diagnosis of brain tumor. Preset and precise diagnosis of Magnetic Resonance Imaging (MRI) brain tumor is enormously significant for medical analysis. During the last years many methods have been proposed. In this research, a novel fuzzy approach has been proposed to classify a given MRI brain image as normal or cancer label and the intensity of the disease. The applied method first employed feature selection algorithms to extract features from images, and then followed by applying a median filter to reduce the dimensions of features. The brain MRI offers a valuable method to perform pre-and-post surgical evaluations, which are keys to define procedures and to verify their effects. The reduced dimension was submitted to a diagnosis algorithm. We retrospectively investigated a total of 19 treatment plans, each of whom has CT simulation and MRI images acquired during pretreatment. The dose distributions of the same treatment plans were calculated on original CT simulation images as ground truth, as well as on pseudo CT images generated from MRI images. The simulation results demonstrate that the proposed algorithm is promising. Manuscript profile

Deep learning techniques have been concentrated on medical applications in recent years. The proposed methodologies are inadequate while medical applications' evolutionary and complex nature is changing quickly and becoming harder to recognize. This paper presents a systematic and detailed survey of the deep learning techniques in medical pattern analysis applications. In addition, it classifies deep learning techniques into two main categories: advanced machine learning and deep learning techniques. The main contributions of this paper are presenting a systematic and categorized overview of the current approaches to machine learning methodologies and exploring the structure of the effective methods in the medical pattern analysis based on deep learning techniques. At last, the advantages and disadvantages of deep learning techniques and their proficiency were discussed. This state-of-the-art survey helps researchers comprehend the deep learning field and allows specialists in intelligent medical research to do consequent examinations. Manuscript profile

Computational intelligence methods, such as fuzzy logic and deep neural networks, are robust models to solve real-world problems. In many dynamic and complex problems, statistical attributes frequently change over the time. Recurrent neural networks (RNN) are suitable to model dynamic high-dimensional and non-linear state-space systems. Nevertheless, the RNN is incapable of modelling long-term dependencies in temporal data, and its learning using gradient descent is a complex and difficult task. Long Short-Term Memory (LSTM) networks were introduced to overcome the RNN issues, but coping with uncertainty is still a major challenge for the LSTM models. This research presents a Hybrid Type-2 Fuzzy LSTM (HHT2FLSTM) deep approach to learn long-term dependencies in order to obtain a reliable prediction in uncertain time series circumstances. The proposed model was applied to the air quality prediction problem to evaluate the model’s robustness in handling uncertainties in a real-world application. The proposed model has been evaluated on a real dataset that contains the outdoor pollutants from July 2011 to October 2020 in Tehran and Beijing by a 10-fold cv with an average area under the ROC curve of 97 % with a 95% confidence interval [95-97] %. Manuscript profile

Time series consists of a sequence of observations, measured at moments in time, sorted chronologically, and evenly spaced from each other, so the data are usually dependent on each other. Uncertainty is the consequence of imperfection of knowledge about a state or a process. The time series is an important class of time-based data objects and it can be easily obtained from scientific and financial applications. Main carrier of time series forecasting is which constitutes the level of uncertainty human knowledge, with its intrinsic ambiguity and vagueness in complex and non-stationary criteria. In this study, a comprehensive revision on the existing time series pattern analysis research is given. They are generally categorized into representation and indexing, similarity measure, uncertainty modeling, visualization and mining. Various Fuzzy Time Series (FTS) models have been proposed in scientific literature during the past decades or so. Among the most accurate FTS models found in literature are the high order models. However, three fundamental issues need to be resolved with regards to the high order models. The primary objective of this paper is to serve as a glossary for interested researchers to have an overall depiction on the current time series prediction and fuzzy time-series models development. Manuscript profile

Prediction is a very important problem that appears in many disciplines. Better weather forecasts can save lives in the event of a catastrophic hurricane; better financial forecasts can improve the return on an investment. The increasing rate of industrial development and urbanization, especially in developing countries, has led to increased levels of air pollution along with increased concern about air pollution effect on human health. This has taken about a diversity of strategies for air quality management, prediction and pollution control. Today’s applications of fuzzy systems are emerging in uncertain environments such as air quality assessments. A fuzzy system that accounts for all of the uncertainties that are present, namely, rule uncertainties due to training with noisy data and measurement uncertainties due to noisy measurements that are used during actual forecasting. The performance results on real data set show the superiority of the fuzzy-markov model in the prediction process with an average accuracy of 94.79% compared to other related works. These results are promising for early prediction of the natural disasters and prevention of its side effects Manuscript profile

Graph and hypergraph matching are fundamental problems in pattern analysis problems. They are applied to various tasks requiring 2D and 3D feature matching, such as image alignment, 3D reconstruction, and object or action recognition. Graph pattern analysis considers pairwise constraints that usually encode geometric and appearance associations between local features. On the other hand, hypergraph matching incorporates higher-order relations computed over sets of features, which could capture both geometric and appearance information. Therefore, using higher-order constraints enables matching that is more robust (or even invariant) to changes in scale, non-rigid deformations, and outliers. Many objects or other entities such as gesture recognition and human activities in the spatiotemporal domain can be signified by graphs with local information on nodes and more global information on edges or hyperedges. In this research, and essential review have been done on the unsupervised methods to explore and communicate meta-analytic data and results with a large number of novel graphs proposed quite recently. Manuscript profile

High efficient routing is an important issue for the design of wireless sensor network (WSN) protocols to meet the severe hardware and resource constraints. This paper presents an inclusive evolutionary reinforcement method. The proposed approach is a combination of Cellular Automata (CA) and Ant Colony Optimization (ACO) techniques in order to create collision-free trajectories for every agent of a team while their formation is kept unchallengeable. The method reacts with problem distribution changes and therefore can be used in dynamical or unknown environments, without the need of a priori knowledge of the space. The swarm of agents are divided into subgroups and all the desired trails are created with the combined use of a CA path finder and an ACO algorithm. In case of lack of pheromones, paths are created using the CA path finder. Compared to other methods, the proposed method can create accurate clustered, collision-free and reliable paths in real time with low complexity while the implemented system is completely autonomous. Manuscript profile

Convolutional neural networks show outstanding performance in many image processing problems, such as image recognition, object detection and image segmentation. Semantic segmentation is a very challenging task that requires recognizing, understanding what's in the image in pixel level. The goal of this research is to develop on the known mathematical properties of the soft-max function and demonstrate how they can be exploited to conclude the convergence of learning algorithm in a simple application of image recognition in supervised learning. So, we utilize results from convex analysis theory which associated with hierarchical architecture to derive additional properties of the soft-max function not yet covered in the existing literature for Multi-Class Classification problems. The proposed MC-DEEP model represents an average accuracy of 90.25% in different layers setting with 95% confidence interval in best initial settings in deep convolutional layers which applied on MNIST dataset. The results show that the regularized networks not only could provide better segmentation results with regularization effect than the original ones but also have certain robustness to noise. Manuscript profile

Solving medical image diagnosis and image analysis problems has long been thought of in many research types in the last decades. Mostly the interpretations of medical data are being made by a medical expert. In terms of image interpretation by a human expert, it is entirely limited due to its subjectivity, complexity, extensive variations across different interpreters, and fatigue. After the success of deep learning in other real-world applications, it provides exciting solutions with reasonable accuracy for medical imaging and is seen as a critical method for future applications in the health sector. This study proposed the deep learning approach based on soft-max activation function to obtain more reliable medical image diagnosis results properly. The proposed model evaluated a brain tumor (MRI) medical dataset, alongside an assessment in terms of accuracy, MSE, and RMSE, as a qualitative analysis of the learned features and practical commendations. This research should help improve the application and refinement of the evaluated approaches in the future. Manuscript profile

This study presents Interval Type-2 Fuzzy Evolutionary models to manage uncertainty in the process of uncertain time-series prediction. This study presents two type-2 fuzzy evolutionary models for rule extraction that were proposed: 1) Evolutionary Interval Type-2 Fuzzy Rule Learning (EIT2FRL), and 1) Evolutionary Interval Type-2 Fuzzy Rule-Set Learning (EIT2FRLS). A ROC curve analysis was applied for performance evaluation, and the results were validated using a 10-fold cross-validation technique. The results reveal that the proposed methods have an AUC of 0.96 for EIT2FRLS and 0.93 for EIT2FRL proposed methods. The results are promising for knowledge extraction in uncertain circumstances, predicting uncertain patterns prediction, and making suitable strategies and optimal decisions. Manuscript profile

In this research, we first present some background on the sample size estimation for conducting clinical trials, discussing the necessity of a computational enrichment criterion. The Denoising Autoencoder Stacked Deep Learning (DASDL) design and development are directly motivated by the optimal enrichment design. Although there are many types of deep architectures in the literature, we focus our presentation using two of the most widely used models stacked denoising autoencoders and fully-supervised dropout. The ideas presented here are applied to any such architectures used for learning problems in the small-sample regime. In this work, we propose a novel, scalable, deep learning method that is applicable for learning problems in the small sample regime and obtains reliable performance. The results show via extensive analyses using imaging, cognitive, and other clinical data alongside a ROC curve analysis. When used as trial inclusion criteria, the new computational markers result in cost-efficient clinical Alzheimer’s disease trials with moderate sample sizes. Manuscript profile

in computational intelligence area, it is suitable to fulfill the analysis in order to interpret the concept and sources of uncertainty and the conditions of its incidence, and hence pursuit for reliable techniques of dealing with it. Dealing with uncertainties in this case is a challenging and multidisciplinary activity. So, there is a need for a capable tool for modeling, control, and analytics to test and evaluate uncertainties for different configurations of the same IoT system. This article emphasis on the analysis of the uncertainty in one of the most important technology trends, the IOT on case study of green environment, such as smart homes. In this research a Mamdani Fuzzy Inference System has been proposed with a Gaussian MFs to handle the uncertainty in intelligent environments. Taking advantage of the feedback control technology, this scheme deals with the impact of unpredictable changes in traffic load on the QoS of WSANs. It utilizes a fuzzy logic controller inside each source sensor node to adapt sampling period to the deadline miss ratio associated with data transmission from the sensor to the actuator. The deadline miss ratio is maintained at a pre-determined desired level so that the required QoS can be achieved. Manuscript profile

Complex systems and information flow such as command, control, communication, computer intelligence, inference, and expert systems exhibit an increasing dependence on the system's nature and information flow. For this reason, it is both the flow exchange of information in the system and the emergent information properties of the system, which are central to the definition, design and analysis of such systems. Besides, the achievement of human-level machine intelligence has long been one of the principal objectives of Artificial Intelligence (AI). Machine intelligence methods have gained many orders of magnitude in computational capability in the last decade, especially in cognitive science and cognitive informatics. This research discussed the difference between Human IQ and Machine Intelligence Quotient (MIQ). Also, we show that MIQ is an abstract intelligence and soft concept of artificial intelligence. Finally, we conclude that the fuzzy sets can better represent MIQ instead of probabilistic and numerical methods. Manuscript profile

The statistical attributes of the non-stationary problems such as air quality and other natural phenomena frequently changed. Type-2 fuzzy logic is a robust and capable model to cope with high-order uncertainties associated with non-stationary time-dependent features. This research's main objective is to present a novel Fuzzy Deep LSTM (IT2FLSTM) model to predict air quality for Tehran and Beijing in a short and long time series scale. The proposed model has been evaluated on a real dataset that contains the one-decade information about outdoor pollutants from April 2011 to November 2020 in Tehran and Beijing. The IT2FLSTM model was evaluated using a ROC curve analysis and validated using 10-fold cross-validation. The results confirm the IT2FLSTM model's superiority with an average area under the ROC curve (AUC) of 97 % and a 95% confidence interval of [95-98] %. The proposed IT2FLSTM model promises to predict complex problems to make strategic prevention decisions to save more lives. Manuscript profile