Search

Purpose Limitations encountered with the models developed in the previous studies had occurrences of global minima; due to which this study developed a new intelligent ubiquitous computational model that learns with gradient descent learning rule and operates with auto-encoders and decoders to attain better energy optimization. Ubiquitous machine learning computational model process performs training in a better way than regular supervised learning or unsupervised learning computational models with deep learning techniques, resulting in better learning and optimization for the considered problem domain of cloud-based internet-of-things (IOTs). This study aims to improve the network quality and improve the data accuracy rate during the network transmission process using the developed ubiquitous deep learning computational model. Design/methodology/approach In this research study, a novel intelligent ubiquitous machine learning computational model is designed and modelled to maintain the optimal energy level of cloud IOTs in sensor network domains. A new intelligent ubiquitous computational model that learns with gradient descent learning rule and operates with auto-encoders and decoders to attain better energy optimization is developed. A new unified deterministic sine-cosine algorithm has been developed in this study for parameter optimization of weight factors in the ubiquitous machine learning model. Findings The newly developed ubiquitous model is used for finding network energy and performing its optimization in the considered sensor network model. At the time of progressive simulation, residual energy, network overhead, end-to-end delay, network lifetime and a number of live nodes are evaluated. It is elucidated from the results attained, that the ubiquitous deep learning model resulted in better metrics based on its appropriate cluster selection and minimized route selection mechanism. Research limitations/implications In this research study, a novel ubiquitous computing model derived from a new optimization algorithm called a unified deterministic sine-cosine algorithm and deep learning technique was derived and applied for maintaining the optimal energy level of cloud IOTs in sensor networks. The deterministic levy flight concept is applied for developing the new optimization technique and this tends to determine the parametric weight values for the deep learning model. The ubiquitous deep learning model is designed with auto-encoders and decoders and their corresponding layers weights are determined for optimal values with the optimization algorithm. The modelled ubiquitous deep learning approach was applied in this study to determine the network energy consumption rate and thereby optimize the energy level by increasing the lifetime of the sensor network model considered. For all the considered network metrics, the ubiquitous computing model has proved to be effective and versatile than previous approaches from early research studies. Practical implications The developed ubiquitous computing model with deep learning techniques can be applied for any type of cloud-assisted IOTs in respect of wireless sensor networks, ad hoc networks, radio access technology networks, heterogeneous networks, etc. Practically, the developed model facilitates computing the optimal energy level of the cloud IOTs for any considered network models and this helps in maintaining a better network lifetime and reducing the end-to-end delay of the networks. Social implications The social implication of the proposed research study is that it helps in reducing energy consumption and increases the network lifetime of the cloud IOT based sensor network models. This approach helps the people in large to have a better transmission rate with minimized energy consumption and also reduces the delay in transmission. Originality/value In this research study, the network optimization of cloud-assisted IOTs of sensor network models is modelled and analysed using machine learning models as a kind of ubiquitous computing system. Ubiquitous computing models with machine learning techniques develop intelligent systems and enhances the users to make better and faster decisions. In the communication domain, the use of predictive and optimization models created with machine learning accelerates new ways to determine solutions to problems. Considering the importance of learning techniques, the ubiquitous computing model is designed based on a deep learning strategy and the learning mechanism adapts itself to attain a better network optimization model.

Recent technological advancements in information and communication technologies introduced smart ways of handling various aspects of life. Smart devices and applications are now an integral part of our daily life; however, the use of smart devices also introduced various physical and psychological health issues in modern societies. One of the most common health care issues prevalent among almost all age groups is diabetes mellitus. This work aims to propose an Artificial Intelligence (AI) – based intelligent system for earlier prediction of the disease using Ridge Adaline Stochastic Gradient Descent Classifier (RASGD). The proposed scheme RASGD improves the regularization of the classification model by using weight decay methods, namely Least Absolute Shrinkage and Selection Operator(LASSO) and Ridge Regression methods. To minimize the cost function of the classifier, the RASGD adopts an unconstrained optimization model. Further, to increase the convergence speed of the classifier, the Adaline Stochastic Gradient Descent classifier is integrated with Ridge Regression. Finally, to validate the effectiveness of the intelligent system, the results of the proposed scheme have been compared with state-of-art machine learning algorithms such as Support Vector Machine and Logistic Regression methods. The RASGD intelligent system attains an accuracy of 92%, which is better than the other selected classifiers.

The growth of swarm intelligence approaches and machine learning models in the field of medical image processing is extravagant, and the applicability of these approaches for various types of cancer classification has as well grown in the recent years. Considering the growth of these machine learning models, in this work attempt is taken to develop an optimized deep learning neural network classifier for classifying the nodule tissues in the lung cancer images which is an important application in biomedical area. The optimized model developed is the hybrid version of adaptive multi-swarm particle swarm optimizer with the new improved firefly algorithm resulting in better exploration and exploitation mechanism to determine near-optimal solutions. Multi-swarm particle swarm optimizer (MSPSO) possesses strong exploration capability due to its regrouping schedule nature, and the improved firefly algorithm (ImFFA) possesses better exploitation mechanism due to its inherit attractiveness and intensity feature. At this juncture, the new adaptive MSPSO–ImFFA is applied to the deep learning neural classifier to overcome the local and global minima occurrences and premature convergence by tuning its weight values. As a result, in this work the new adaptive MSPSO–ImFFA-based deep learning neural network classifier is employed to classify the lung cancer tissues of the considered lung computed tomography images. Results obtained prove the effectiveness of the deep learning classifier for the considered lung image sample datasets in comparison with the other methods compared from the previous literature works.

Mahalanobis taguchi system (MTS) is a multi-variate statistical method extensively used for feature selection and binary classification problems. The calculation of orthogonal array and signal-to-noise ratio in MTS makes the algorithm complicated when more number of factors are involved in the classification problem. Also the decision is based on the accuracy of normal and abnormal observations of the dataset. In this paper, a multiclass model using Improved Mahalanobis Taguchi System (IMTS) is proposed based on normal observations and Mahalanobis distance for agriculture development. Twenty-six input factors relevant to crop cultivation have been identified and clustered into six main factors for the development of the model. The multiclass model is developed with the consideration of the relative importance of the factors. An objective function is defined for the classification of three crops, namely paddy, sugarcane and groundnut. The classification results are verified against the results obtained from the agriculture experts working in the field. The proposed classifier provides 100% accuracy, recall, precision and 0% error rate when compared with other traditional classifier models., Comment: in IEEE Access

Design of controller for a doubly fed induction generator driven by a variable speed wind turbine employing deep learning neural networks whose weights are tuned by grey artificial bee colony algorithm is developed and simulated in this work. This paper presents the mathematical modelling of the doubly fed induction generator (DFIG) and the controller design is implemented using the third generation deep learning neural network (DLNN). In the proposed work, the variable speed wind turbine generator torque is regulated employing a proportional–integral–derivative (PID) controller. The gains of the PID controller are tuned using DLNN model. The proposed density-based grey artificial bee colony (D-GABC) algorithm provides the optimal dataset required for training DLNN model. As well, the weights of the developed neural network controller are also optimized by D-GABC algorithm to avoid premature convergence and to reduce the incurred computational time of the network model. The effectiveness of the proposed DLNN-based controller for DFIG in wind energy conversion is proved and observed to be better than that of the other methods proposed in the previous literature works in respect of the simulated results obtained.

Diabetes Mellitus (DM) is a serious health problem that affects majority of peoples worldwide, the conventional diagnosis procedure estimates the amount of glucose level in blood and the treatment is to regulate the blood glucose to desired level. As an alternative, an ancient therapy that has been followed for more than two millennium period is the Traditional Chinese Medicine (TCM). Tongue feature analysis is the main strategy followed by the TCM experts as the diagnosing procedure to identify and locate diabetes. In this research article, a computer aided intelligent decision support model is developed, the CNN Dense Net framework is employed to identify the necessary features of the tongue image such as its color, texture, the fur coating, tooth markings, and the red spots. To perform classification Support Vector Machines (SVM) is employed to enhance its performance the SVM parameters are tuned by Particle Swarm Optimization (PSO) technique. The model is validated by the real-time dataset and the performance is compared with state of art methods to establish its efficiency and effectiveness. Simulation is carried out in MATLAB environment and evaluated in terms of performance metrics such as Accuracy, Sensitivity, and Specificity, Precision, F1 Score and Error rate. The proposed model attained an accuracy of 97.82%, precision of 98.18%, sensitivity of 98.44%, and specificity of 96.68%, F1 Score of 98.31% and Error rate of 0.02185 proving its superiority over previous approaches. The developed intelligent decision support model has proven its efficacy over the state-of-the-art techniques for diagnosing and classifying diabetes mellitus. The proposed approach ensures a better healthcare monitoring model for identifying diabetes mellitus and performs treatment to the humans at an early stage.

Sentimental analysis, a most opinion analyzer which takes a process of mathematical calculation for fixing the exact emotion, object or user expected reviews, etc. In the modern generation everything comes in a digital way where sales and buyers are increased in a rapid manner through the internet only. Not only commercial access but also education in this pandemic situation 2021, takes a major part in worldwide internet. In this way sentimental analysis has accounted for its NLP framework in the feedback process also. Detection through many algorithms using machine learning, computer vision and deep learning are in trend now. In such views, a Novel intervention aspect-based (NIAB) sentimental analysis is proposed to classify the emotion from twitter dataset. By using an activation function, the output of each node is identified accurately. Neural network has many input and output nodes that are interconnected through n-number of hidden layers. These nodes are determined through mapping the dependent variable. For a clear direction of slope an non-linear activation function is introduced called an Exponential Linear Unit (ELU) that has the highest scale with positive value. The exact range between the input and output value is 0.1 and 0.3 which has better output compared to Rectified linear unit (RELU).

Hypertensive retinopathy (HR)is one of the severe damages caused in retinal vascular due to the hectic and abnormal upset in a human life. These damages are taken in a clinical sample by monitoring the presence and importance of all parameters that shows the increasing rate. Retina as main features for finding the variation which takes a longer duration to fix the diseases and impact in arteriolar construction and optic disk edema. In this work, a enhanced transfer learning-convolutional neural network (E-TLCNN) model is proposed for diagnosing HR using high quality images from fundus images. Therefore for understanding the results in an accurate manner transfer learning is used for classifying its stages. Also a new model using CNN architecture as DenseNet has been proposed for classifying the features to focus on the severity such as reading the diabetic retinopathy and AVR that can be utilized to spot the diseases. Dataset from Kaggle shows a 96% of accuracy in classifying the sensitivity along with its training and testing data whereas the comparison of image classification fetched less compared with K-nearest neighbor algorithm (KNN). Also based on the accuracy achieved validation process also done using the remaining images from the dataset.

In both developing and developed nations, glaucoma is the primary cause of vision loss. Identifying and classifying glaucoma in the early stage will provide the patients with sufficient care and an effective way to support the eye surgeon. This is the opinion of an initiative to identify and classify glaucoma early with the use of a comprehensive learning system using fundus images. Three pre-trained convolution neural network (ConvNet) architectures are being used for the classification of glaucoma in the proposed framework: the Residual Network (ResNet), the Visual geometry group network (VGGNet), and GoogLeNet. The tests are performed in private and standard benchmark data sets to verify the performance of the proposed system. In terms of accuracy, precision, specificity, sensitivity, and F1, the proposed algorithm is compared to three various ConvNets. The findings obtained are encouraging, and the dominance in performance measurements to detect and diagnose glaucoma using fundus images in the proposed ensemble of deep learning architectures will be verified.

The global demand for electricity has visualized high growth with the rapid growth in population and economy. It thus becomes necessary to efficiently distribute electricity to households and industries in order to reduce power loss. Smart Grids (SG) have the potential to reduce such power losses during power distribution. Machine learning and artificial intelligence techniques have been successfully implemented on SGs to achieve enhanced accuracy in customer demand prediction. There exists a dire need to analyze and evaluate the various machine learning algorithms, thereby identify the most suitable one to be applied to SGs. In the present work, several state-of-the-art machine learning algorithms, namely Support Vector Machines (SVM), K-Nearest Neighbor (KNN), Logistic Regression, Naive Bayes, Neural Networks, and Decision Tree classifier, have been deployed for predicting the stability of the SG. The SG dataset used in the study is publicly available collected from UC Irvine (UCI) machine learning repository. The experimentation results highlighted the superiority of the Decision Tree classification algorithm, which outperformed the other state of the art algorithms yielding 100% precision, 99.9% recall, 100% F1 score, and 99.96% accuracy.

Deep Learning shows a drastic growth in many fields such as medical, voice recognitions, Siri Alexa and computer vision, so on. Even though machine learning and deep learning are developing point in data science the back bone for all these platforms are Big data Analytics. A massive data and information’s from all the website, social media and other networks produced so called Big data are focused in day to day life. When these information are collected from the various chat history such as Whatsapp, Facebook, Twitter and other for generating numerous development such as privacy policy, investing, stock markets, business, study process and many more. Professional involvement deals the deep learning concept to focus on the stock market procedure in particular to develop the Business enterprise, individual profits, product strategies and other decision making process also. However the main gap to be filled in this prediction was to look around the internet sources as well as real time population for stock market varies its accuracy due to the lack of hidden layer interaction. Here we propose a deep learning accuracy prediction named as sentimental analysis to perform an accuracy in a best way by applying Bi-directional long-short term memory (Bi-LSTM) and Deep belief network to overcome the issues and less accuracy given by doc2vec, longshort term memory (LSTM) and provides a good model for our sentimental Bi-LSTM model to find the best stock market analysis.

The most promising of all cancers that are prevailing among and the primary source of women’s deaths worldwide is the cancerous breast cells. Accurate discovery of this type of cancer cells is essential in its early stages, which can be attained via. various data mining and machine learning techniques. Therefore, a comparative analysis among different machine learning techniques such as Random Forest, Support Vector Machine, Naive Bayes, Decision Tree, Neural Networks and Logistic Regression is conducted. It is determined using the WEKA tool. Also, the selected machine learning algorithms are evaluated based on accuracy in prediction results and performance comparison of each classifier with a ROC curve on multiple classifiers is performed.

In this paper, rough, fuzzy and soft set approaches have been integrated to develop a multi-class classification model to assist the farmers in taking decision on crop cultivation for a given agriculture land. The model is divided into three major sections, namely weight calculation of variables, conversion of continuous data to fuzzified values and classification rule generation. Dominance-based rough set approach is used for the calculation of relative weights of variables. Fuzzy proximity relation is applied to convert the continuous data into fuzzified values. Bijective soft set approach is used to generate classification rules for five agriculture crops, namely paddy, groundnut, sugarcane, cumbu and ragi. The developed model has been tested with agriculture dataset which showed 92% accuracy for the validation dataset and proved to be confident and robust for agriculture development. Further, the performance of the proposed model is compared with three popular classifiers such as naive Bayes, support vector machine and J48. The obtained experimental results showed high predictive performance, and the potential of the proposed model is compared with the other classifiers.

In this paper, a predictive mathematical model is proposed to identify the best alternatives from the given set of alternatives characterized by multiple criteria. An objective function is developed to find the ranking index of the alternatives. A new Comprehensive-Technique for Order Preference by Similarity to Ideal Solution (C-TOPSIS) method is proposed which combines the comprehensive weights of the criteria with TOPSIS method. The proposed predictive mathematical model generates a ranking of the alternatives. An experimental study has been carried out by taking agricultural data set of rice paddy crop to demonstrate and validate the developed model. The results show significant correlation between the ranks obtained by the proposed model and the ranks obtained from the average yield per hectare. Also the results of the proposed method outperform the results of the other ranking methods, namely VIKOR and ELECTRE, particularly in the real world example. Thus, the developed predictive mathematical model seems to provide better results for the given alternatives and can also be used for other decision-making problems.

The focus is made to develop predictor models for wind speed prediction employing the support vector machine neural models. Basically, support vector machines (SVM) is employed as classifiers, but this contribution models variant of SVM to act as predictors. A developed model of linear support vector machine (LSVM) and proximal support vector machine (PSVM) is proposed to carry out the wind speed prediction using the available real time wind farm data. In developed PSVM predictor, it is modeled for both linear PSVM predictor and non-linear PSVM predictor. The difference between the developed linear and non-linear PSVM predictor models lies in their applicability of kernel functions to perform effective wind speed prediction. The prediction application is implemented for the set of wind farm data with a wind mill height of 50 m in a manner to minimize the mean square error. The training process of the neural network algorithmic flow is done with the developed LSVM, L-PSVM (Linear PSVM) and N-PSVM (nonlinear PSVM) for predicting the wind speed in renewable energy systems. Results computed are compared with the other types of predictors to prove the effectiveness of the proposed variants of SVM predictors. The simulated results presents the effectiveness of the proposed predictors for the real time wind farm data and the applicability of the predictors for the considered datasets.

In the present competitive environment, a farmer needs better education, business expertise and good knowledge of technologies and tools to be successful in agriculture. Farmers usually select crop for cultivation according to their traditional knowledge and past experience in farming, but a farmer’s predictions may go wrong due to natural disaster. Thus, decision-making tool need to be developed to help farmers to take decision on crop cultivation. In this paper, decision-making tool was developed for selecting the suitable crop that can be cultivated in a given agricultural land. In the present study, 26 input variables were identified and categorized into six broad heads of main variables such as soil, water, season, input, support and infrastructure. Each main variable has several sub-variables. The priority weights for the variables were determined using the dominance-based rough set approach. In order to convert sub-variable sequences to main variable sequences, evaluation scores of each main variable were calculated by applying the weights of sub-variables and by using simple additive method. Finally, the evaluation scores were applied to Johnson’s reduct algorithm and classification rules were generated. The developed tool predicts each site in the datasets into one of the three crops such as paddy, groundnut and sugarcane. In order to validate the performance of the tool, the same datasets were predicted again by agriculture experts. The results obtained from the tool showed 92% agreement with the results obtained from the experts. Thus, the tool is a feasible tool for cultivating the suitable crops in the agricultural sites.

Machine-to-machine communication is now enabled and will rule the world in the future. This is achieved through the Internet and this is called the Internet of Things (IoT) as it enables all the things in the real world to communicate with each other. IoT achieves this by bridging various other software technologies and hardware devices. IoT has flourished in all domains starting with simple home automation to businesses. As everything in this real world is business, enabling IoT in business will be of great help to the enterprises and the decision makers in the field. So here this chapter portrays what an enterprise Internet of Things deals with, its issues, and its applications. Also the importance of business forecast for an enterprise and how it is achieved via various techniques for the business forecast are discussed. For better forecasting results, the advanced machine learning algorithms that can be employed in a different perspective of enterprise IoT and their applications are presented here. This would be a great help for the researchers and practitioners in the field of enterprise IoT.

A hybrid soft decision model has been developed in this paper to take decision on agriculture crop that can be cultivated in a given experimental land by integrating few soft computing techniques. The proposed model comprises of three parts, namely weight calculation, classification and prediction. Twenty-seven input criteria were categorized into seven broad criteria, namely soil (11 sub-criteria), water (2 sub-criteria), season (no sub-criterion), input (6 sub-criteria), support (2 sub-criteria), facilities (3 sub-criteria) and risk (2 sub-criteria). In the proposed model, relative weights of main criteria were calculated using Shannon’s Entropy method and relative weights of sub-criteria in each main criterion were calculated using rough set approach. As VIKOR method is effective in sorting the alternatives, it is used to determine the ranking index of main criteria in this study. A soft decision system was constructed from the results of rough set method, VIKOR method and Shannon’s Entropy method. Classification rules were generated for five agriculture crops, namely paddy, groundnut, sugarcane, cumbu and ragi based on the soft decision system using bijective soft set approach. The developed model predicts each site in the validation dataset into one of the five crops. The performance of the proposed model has been sanity checked by agriculture experts.

In this paper methodologies are proposed to estimate the number of hidden neurons that are to be placed numbers in the hidden layer of artificial neural networks (ANN) and certain new criteria are evolved for fixing this hidden neuron in multilayer perceptron neural networks. On the computation of the number of hidden neurons, the developed neural network model is applied for wind speed forecasting application. There is a possibility of over fitting or under fitting occurrence due to the random selection of hidden neurons in ANN model and this is addressed in this paper. Contribution is done in developing various 151 different criteria and the evolved criteria are tested for their validity employing various statistical error means. Simulation results prove that the proposed methodology minimized the computational error and enhanced the prediction accuracy. Convergence theorem is employed over the developed criterion to validate its applicability for fixing the number of hidden neurons. To evaluate the effectiveness of the proposed approach simulations were carried out on collected real-time wind data. Simulated results confirm that with minimum errors the presented approach can be utilized for wind speed forecasting. Comparative analysis has been performed for the estimation of the number of hidden neurons in multilayer perceptron neural networks. The presented approach is compact, enhances the accuracy rate with reduced error and faster convergence.

The scope of this paper is to forecast wind speed. Wind speed, temperature, wind direction, relative humidity, precipitation of water content and air pressure are the main factors make the wind speed forecasting as a complex problem and neural network performance is mainly influenced by proper hidden layer neuron units. This paper proposes new criteria for appropriate hidden layer neuron unit’s determination and attempts a novel hybrid method in order to achieve enhanced wind speed forecasting. This paper proposes the following two main innovative contributions 1) both either over fitting or under fitting issues are avoided by means of the proposed new criteria based hidden layer neuron unit’s estimation. 2) ELMAN neural network is optimized through Modified Grey Wolf Optimizer (MGWO). The proposed hybrid method (ELMAN-MGWO) performance, effectiveness is confirmed by means of the comparison between Grey Wolf Optimizer (GWO), Adaptive Gbest-guided Gravitational Search Algorithm (GGSA), Artificial Bee Colony (ABC), Ant Colony Optimization (ACO), Cuckoo Search (CS), Particle Swarm Optimization (PSO), Evolution Strategy (ES), Genetic Algorithm (GA) algorithms, meanwhile proposed new criteria effectiveness and precise are verified comparison with other existing selection criteria. Three real-time wind data sets are utilized in order to analysis the performance of the proposed approach. Simulation results demonstrate that the proposed hybrid method (ELMAN-MGWO) achieve the mean square error AVG ± STD of 4.1379e-11 ± 1.0567e-15, 6.3073e-11 ± 3.5708e-15 and 7.5840e-11 ± 1.1613e-14 respectively for evaluation on three real-time data sets. Hence, the proposed hybrid method is superior, precise, enhance wind speed forecasting than that of other existing methods and robust.

This paper analyzes various earlier approaches for selection of hidden neuron numbers in artificial neural networks and proposes a novel criterion to select the hidden neuron numbers in improved back propagation networks for wind speed forecasting application. Either over fitting or under fitting problem is caused because of the random selection of hidden neuron numbers in artificial neural networks. This paper presents the solution of either over fitting or under fitting problems. In order to select the hidden neuron numbers, 151 different criteria are tested by means of the statistical errors. The simulation is performed on collected real-time wind data and simulation results prove that proposed approach reduces the error to a minimal value and enhances forecasting accuracy The perfect building of improved back propagation networks employing the fixation criterion is substantiated based on the convergence theorem. Comparative analyses performed prove the selection of hidden neuron numbers in improved back propagation networks is highly effective in nature.

A model of multi criteria decision making based on extended ANP has been provided and the existing AHP scale method is replaced by another method, in which the user has to provide fewer inputs. To check the validity of the proposed method, a sample data has been taken and an enhanced method is applied on it.

In recent times, the application of enabling technologies such as digital shearography combined with deep learning approaches in the smart quality assessment of tires, which leads to intelligent tire manufacturing practices with automated defects detection. Digital shearography is a prominent approach that can be employed for identifying the defects in tires, usually not visible to human eyes. In this research, the bubble defects in tire shearography images are detected using a unique ensemble hybrid amalgamation of the convolutional neural networks/ConvNets with high-performance Faster Region-based convolutional neural networks. It can be noticed that the routine of region-proposal generation along with object detection is accomplished using the ConvNets. Primarily, the sliding window based ConvNets are utilized in the proposed model for dividing the input shearography images into regions, in order to identify the bubble defects. Subsequently, this is followed by implementing the Faster Region-based ConvNets for identifying the bubble defects in the tire shearography images and further, it also helps to minimize the false-positive ratio (sometimes referred to as the false alarm ratio). Moreover, it is evident from the experimental results that the proposed hybrid model offers a cent percent detection of bubble defects in the tire shearography images. Also, it can be witnessed that the false-positive ratio gets minimized to 18 percent.

Medical diagnostics, a technique used for visualizing the internal structures and functions of human body, serves as a scientific tool to assist physicians and involves direct use of digital imaging system analysis. In this scenario, identification of brain tumors is complex in the diagnostic process. Magnetic resonance imaging (MRI) technique is noted to best assist tissue contrast for anatomical details and also carries out mechanisms for investigating the brain by functional imaging in tumor predictions. Considering 3D MRI model, analyzing the anatomy features and tissue characteristics of brain tumor is complex in nature. Henceforth, in this work, feature extraction is carried out by computing 3D gray-level cooccurence matrix (3D GLCM) and run-length matrix (RLM) and feature subselection for dimensionality reduction is performed with basic differential evolution (DE) algorithm. Classification is performed using proposed extreme learning machine (ELM), with refined group search optimizer (RGSO) technique, to select the best parameters for better simplification and training of the classifier for brain tissue and tumor characterization as white matter (WM), gray matter (GM), cerebrospinal fluid (CSF), and tumor. Extreme learning machine outperforms the standard binary linear SVM and BPN for medical image classifier and proves better in classifying healthy and tumor tissues. The comparison between the algorithms proves that the mean and standard deviation produced by volumetric feature extraction analysis are higher than the other approaches. The proposed work is designed for pathological brain tumor classification and for 3D MRI tumor image segmentation. The proposed approaches are applied for real time datasets and benchmark datasets taken from dataset repositories.

This paper proposes a Neural Network based hybrid computing model for wind speed prediction in renewable energy systems. Wind energy is one of the renewable energy sources which lower the cost of electricity production. Due to the fluctuation and nonlinearity of wind, the accurate wind speed prediction plays a major role in renewable energy systems. To increase the accuracy of wind speed prediction, a hybrid computing model is proposed. The proposed model is tested on real time wind data. The objective is to predict accurate wind speed based on proposed hybrid computing model which integrates Self Organizing feature Maps and Multilayer Perceptron network. The key advantages include higher accuracy, precision and minimal error. The results are computed by the training and testing methodologies. The experimental result shows that as compared to the conventional neural network models, the proposed hybrid model performs better in terms of minimization of errors.

This paper proposes an Enhanced Particle Swarm Optimization (EPSO) for extracting optimal rule set and tuning membership function for fuzzy logic based classifier model. The standard PSO is more sensitive to premature convergence due to lack of diversity in the swarm and can easily get trapped into local minima when it is used for data classification. To overcome this issue, BLX-α crossover and Non-uniform mutation from Genetic Algorithm (GA) are incorporated in addition to standard velocity and position updating of PSO. The performance of the proposed approach is evaluated using ten publicly available bench mark data sets. From the simulation study, it is found that the proposed approach enhances the convergence and generates a comprehensible fuzzy classifier system with high classification accuracy for all the data sets. Statistical analysis of the test result shows the suitability of the proposed method over other approaches reported in the literature.

This paper reviews methods to fix a number of hidden neurons in neural networks for the past 20 years. And it also proposes a new method to fix the hidden neurons in Elman networks for wind speed prediction in renewable energy systems. The random selection of a number of hidden neurons might cause either overfitting or underfitting problems. This paper proposes the solution of these problems. To fix hidden neurons, 101 various criteria are tested based on the statistical errors. The results show that proposed model improves the accuracy and minimal error. The perfect design of the neural network based on the selection criteria is substantiated using convergence theorem. To verify the effectiveness of the model, simulations were conducted on real-time wind data. The experimental results show that with minimum errors the proposed approach can be used for wind speed prediction. The survey has been made for the fixation of hidden neurons in neural networks. The proposed model is simple, with minimal error, and efficient for fixation of hidden neurons in Elman networks.

This work presents and investigates the discriminatory capability of contourlet coefficient co- occurrence matrix features in the analysis of mammogram images and its classification. It has been revealed that contourlet transform has a remarkable potential for analysis of images representing smooth contours and fine geometrical structures, thus suitable for textural details. Initially the ROI (Region of Interest) is cropped from the original image and its contrast is enhanced using histogram equalization. The ROI is decomposed using contourlet transform and the co-occurrence matrices are generated for four different directions (θ=0°, 45°, 90° and 135°) and distance (d= 1 pixel). For each co-occurrence matrix a variety of second order statistical texture features are extracted and the dimensionality of the features is reduced using Sequential Floating Forward Selection (SFFS) algorithm. A PNN is used for the purpose of classification. For experimental evaluation, 200 images are taken from mini MIAS (Mammographic Image Analysis Society) database. Experimental results show that the proposed methodology is more efficient and maximum classification accuracy of 92.5% is achieved. The results prove that contourlet coefficient co-occurrence matrix texture features can be successfully applied for the classification of mammogram images. Keywords-Contourlet Transform, Mammogram, SFFS, PNN, ROI, MIAS

Magnetic Resonance Imaging (MRI) technique is one of the most useful diagnostic tools for human soft tissue analysis. Moreover, the brain anatomy features and internal tissue architecture of brain tumor are a complex task in case of 3-D anatomy. The additional spatial relationship in transverse, longitudinal planes and the coronal plane information has been proved to be helpful for clinical applications. This study extends the computation of gray level co- occurrence matrix (GLCM) and Run length matrix (RLM) to a three- dimensional form for feature extraction. The sub-selection of rich optimal bank of features to model a classifler is achieved with custom Genetic Algorithm design. An improved Extreme Learning Machine (ELM) classifler algorithm is explored, for training single hidden layer artiflcial neural network, integrating an enhanced swarm-based method in optimization of the best parameters (input-weights, bias, norm and hidden neurons), enhancing generalization and conditioning of the algorithm. The method is modeled for automatic brain tissue and pathological tumor classiflcation and segmentation of 3D MRI tumor images. The method proposed demonstrates good generalization capability from the best individuals obtained in the learning phase to handle sparse image data on publically available benchmark dataset and real time data sets.

In this paper we have proposed two co mparative approaches for the contrast enhancement of dark sports images. The contrast of any image is a very important characteristic wh ich decides the quality of image. Lo w contrast images occur often due to poor or non uniform lighting conditions and sometimes due to the non linearity or small dynamic range of the imaging system. Enhancing the contrast of sports images is of importance since it is difficult to analyze the performance of the team or player with a poor quality image. Though several methods are proposed for gray scale images, enhancing the contrast of color images is a comp licated process. In this paper we have proposed two comparative approaches for the contrast enhancement of color images and have compared their perfo rmance against the standard histogram equalization method. First method is contrast enhancement of color images using fuzzy rule based method and the second method is using modified sigmo id function. Color images cannot be processed directly hence a suitable color model is chosen for processing and the proposed methods are imp lemented. Fo r both the approaches the color images are split into RGB p lanes and the proposed operation is performed on each plane and finally the planes are concatenated to obtain the enhanced image. Performance of the proposed methods is measured using a factor known as Measure of Contrast and the comparison is represented graphically. Experimental results prove that of the two methods proposed, contrast enhancement using modified sigmoid function provides the highest measure of contrast and can be effectively used for further analysis of sports color images.

In this paper, a survey has been made on the applications of intelligent computing techniques for diagnostic sciences in biomedical image classification. Several state-of-the-art Artificial Intelligence (AI) techniques for automation of biomedical image classification are investigated. This study gathers representative works that exhibit how AI is applied to the solution of very different problems related to different diagnostic science analysis. It also detects the methods of artificial intelligence that are used frequently together to solve the special problems of medicine. SVM neural network is used in almost all imaging modalities of medical image classification. Similarly fuzzy C means and improvements to it are important tool in segmentation of brain images. Various diagnostic studies like mammogram analysis, MRI brain analysis, bone and retinal analysis etc., using neural network approach result in use of back propagation network, probabilistic neural network, and extreme learning machine recurrently. Hybrid approach of GA and PSO are also commonly used for feature extraction and feature selection.

One of the important issues in the design of fuzzy classifiers is the formation of fuzzy if-then rules and the membership functions. This paper presents a hybrid Particle Swarm Optimization based approach for fuzzy classifier design which incorporates the concept of mutation from evolutionary computations. The proposed MutPSO develops the fuzzy classifier system by encoding and evolving both the membership functions and rule set as particles simultaneously. Non-uniform mutation is applied to the membership functions which are represented as real numbers. Uniform mutation is applied to the rule set which is represented as discrete numbers. In the classification problem under consideration, the objective is to maximize the correctly classified data and minimize the number of rules. This objective is formulated as a fitness function to guide the search procedure to select an appropriate fuzzy classification system so that the number of fuzzy rules and the number of incorrectly classified patterns are simultaneously minimized. The performance of the proposed MutPSO approach is demonstrated through development of fuzzy classifiers for iris data available in UCI machine learning repository. Simulation results show the suitability of the proposed approach for developing the fuzzy system.

A proposed real coded genetic algorithm based radial basis function neural network classifier is employed to perform effective classification of healthy and cancer affected lung images. Real Coded Genetic Algorithm (RCGA) is proposed to overcome the Hamming Cliff problem encountered with the Binary Coded Genetic Algorithm (BCGA). Radial Basis Function Neural Network (RBFNN) classifier is chosen as a classifier model because of its Gaussian Kernel function and its effective learning process to avoid local and global minima problem and enable faster convergence. This paper specifically focused on tuning the weights and bias of RBFNN classifier employing the proposed RCGA. The operators used in RCGA enable the algorithm flow to compute weights and bias value so that minimum Mean Square Error (MSE) is obtained. With both the lung healthy and cancer images from Lung Image Database Consortium (LIDC) database and Real time database, it is noted that the proposed RCGA based RBFNN classifier has performed effective classification of the healthy lung tissues and that of the cancer affected lung nodules. The classification accuracy computed using the proposed approach is noted to be higher in comparison with that of the classifiers proposed earlier in the literatures.

Medical data classification is a prime data mining problem being discussed about for a decade that has attracted several researchers around the world. Most classifiers are designed so as to learn from the data itself using a training process, because complete expert knowledge to determine classifier parameters is impracticable. This paper proposes a hybrid methodology based on machine learning paradigm. This paradigm integrates the successful exploration mechanism called self-regulated learning capability of the particle swarm optimization (PSO) algorithm with the extreme learning machine (ELM) classifier. As a recent off-line learning method, ELM is a single-hidden layer feedforward neural network (FFNN), proved to be an excellent classifier with large number of hidden layer neurons. In this research, PSO is used to determine the optimum set of parameters for the ELM, thus reducing the number of hidden layer neurons, and it further improves the network generalization performance. The proposed method is experimented on five benchmarked datasets of the UCI Machine Learning Repository for handling medical dataset classification. Simulation results show that the proposed approach is able to achieve good generalization performance, compared to the results of other classifiers.

Text extraction in real images taken in unconstrained environments remains surprisingly challenging in Computer Vision due to language characteristics, complex backgrounds and the text color. Extraction of text and caption from images and videos is important and in great demand for video retrieval, annotation, indexing and content analysis. In this paper we propose a weighted hybrid thresholding approach. It is demonstrated that the proposed method achieved reasonable accuracy of the text extraction for moderately difficult examples.

Mammography is the most widely used and the most efficient method for detection of breast cancer. Computer Aided Diagnostic (CADx) systems are used to aid the radiologists in interpreting the mammograms. In this paper we propose an efficient CADx system for classifying the digital mammograms as benign (Non Cancerous) or Malignant (Cancerous). Dual Tree Complex Wavelet Transform (DT-CWT) has shown a good performance in applications that involve medical image processing due to more data phase information, shift invariance and directionality than other wavelet transforms. The ROI (Region Of Interest) image is decomposed using DTCWT and statistical features are extracted and the images are classified using nonlinear Support Vector Machines (SVM). Experiments are carried out on digital mammogram images derived from MIAS (Mammographic Image Analysis Society) mini mammographic database. Classification accuracy of 93.34% is achieved using the proposed method and the results prove that the proposed method can be used as an efficient tool to assist the radiologist in classifying the large number of mammograms generated during widespread screening.

This paper experiments a recently developed, simple and efficient learning algorithm for Single hidden Layer Feed forward Neural networks (SLFNs) called Extreme Learning Machine (ELM) for two category data classification problems evaluated on the Stat log-Heart dataset. ELM randomly chooses hidden nodes and analytically determines the output weights of SLFNs. A detailed analysis of different activation functions with varying number of hidden neurons is carried out using Stat log-Heart dataset. The evaluation results indicate that ELM produces better classification accuracy with reduced training time. Its performance has been compared with other methods such as the Naive Bayes, AWAIS, C4.5, and Logistic Regression algorithms sited in the previous literature.

This paper presents a hybrid neural network approach to predict wind speed automatically in renewable energy systems. Wind energy is one of the renewable energy systems with lowest cost of production of electricity with largest resources available. By the reason of the fluctuation and volatility in wind, the wind speed prediction provides the challenges in the stability of renewable energy system. The aim is to compute predicted wind speed based on hybrid model which integrates a Self Organizing Map (SOM) and Radial basis Function (RBF) neural network. The simulation result shows that the proposed approach provides better result of wind speed prediction with less error rates.

In this system, we exploit the capability of Back propagation neural network (BPN) and Radial Basis Function Neural network (RBFN) to classify brain MRI images to either cancerous or noncancerous tumour automatically. It is classified with respective to symmetry of brain image, exhibited in the axial and coronal images. The initial objective of this study was not to discover which algorithm is superior in classification tasks, but to examine the advantages and downfalls of each algorithm under varying conditions. Using the optimal texture features extracted from normal and tumor regions of MRI by using statistical features, BPN and RBF classifiers are used to classify and segment the tumor portion in abnormal images. Both the testing and training phase gives the percentage of accuracy on each parameter in neural networks, which gives the idea to choose the best one to be used in further works. The results showed outperformance of RBFN algorithm when compared to BPN with classification accuracy of 85.71% which works as promising tool for classification and requires extension in brain tumour analysis.

In this model, we exploit the use of Sequential Minimal Optimization (SMO) to automatically classify brain MRI images either normal or abnormal for tumour. Based on symmetry of brain image, exhibited in the axial and coronal images, it is classified. Using the optimal texture features extracted from normal and tumor regions of MRI by using gray level co-occurrence matrix, SMO classifiers are used to classify and segment the tumor portion in abnormal images. Both the testing and training phase gives the percentage of accuracy on each parameter in SMO, which gives the idea to choose the best one to be used in further works. The results showed outperformance of SMO algorithm when compared to back propagation network with classification accuracy of 88.33% using radial basis function for better convergence and classification.

India is a multilingual and multi-script country where a line of a bilingual document page may contain text words both in regional language and in English. Recognition of documents containing multi-scripts is really a challenging task, which needs more effort of the OCR designers for improving the accuracy rate. This paper presents a Bilingual OCR system for printed Malayalam and English text. Here we propose an algorithm which can accept scanned image of printed characters as input and produce editable Malayalam and English characters in a predefined format as output. The image acquired is segmented into line and character-wise using pixel by pixel approach by scanning from top-left of the image to bottom-right. The character image obtained after segmentation is resized to 16 × 16 bitmap which is used for comparison. The database contains characters in various fonts of both the languages. This database is used for comparison with the resized character image. The comparison is done using pixel-match algorithm. The matched character is displayed in the notepad. An efficiency of 87.25% is obtained using this approach.

The study proposes a modified RBF with better network learning, convergence, error rates and classification results which involves spatial information data points using Gaussian Mixture Model (GMM) and Expectation Maximization (EM) algorithm for automatic biomedical brain tumour detection. The model was used to predict the brain tumour type (benign or malignant). The results showed outperformance of GMM-EM model with spatial points than the standard RBF model.A classification with a success of 85% and 90.3% has been obtained by the classifiers for RBF and RBF-GMM model.

Current video and image systems are typically of limited use in poor visibility conditions such as in poor illumination, rain, fog, smoke, and haze. These conditions severely limit the range and effectiveness of imaging systems because of the severe reduction in contrast. The contrast of any image is a very important characteristic which decides the quality of image. Our chief goal in this paper is to develop a contrast enhancement technique to recover a sports image shot with poor illumination to improve its quality. In our method contrast enhancement is done based on a modified sigmoid mapping function. Several methods are proposed for gray scale images wherein while dealing with color images the procedure becomes complicated. In this method processing is done on RGB color planes and the results are found to be satisfactory. We provide simulation results of our technique applied to real images, which are hard to be contrasted by other conventional techniques.