International Journal of Computer and Applications

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.

/pdf/review-on-methods-to-fix-number-of-hidden-neurons-in-neural-22240krax1.pdf

Review on Methods to Fix Number of Hidden Neurons in Neural Networks

https://scholarcommons.sc.edu/cgi/viewcontent.cgi?article=1007&context=aii_fac_pub

Machine Learning for Internet of Things Data Analysis: A Survey

THE FUTURE OF COMPETITION: CO-CREATING UNIQUE VALUE WITH CUSTOMERSC.K. Prahalad & Venkat RamaswamyThe authors - C.K. Prahlad and Venkat Ramaswamy, are known for their non-traditional approach and that has made possible to bring out this path breaking book. Unlearning age old management practices and understanding the changes that is sweeping the business world and giving a framework to the still evolving concept of co-creation of value where customer is at the centre stage is indeed a tough task. And authors have accomplished that with aplomb.Our industrial system is generating more goods and services than before but customer satisfaction remains low in spite of having overwhelming choices, profit level of companies is shrinking though many more decision making tools are at its disposal. What is going wrong and how to set this right? Companies are grappling with these issues and trying to fathom these problems. With the emerging technologies, customers are well informed, well connected with their peer groups and very active in their domain. Now customers have started playing dominant role in the value chain through co-creation of experience which enhances the value.The book can be divided into three distinct parts covering twelve chapters, highlighting future of competition and the role to be played by consumers, markets and companies. First six chapters develop the framework of consumers' role in the changing scenario. Early chapters give a brief account of the change that is taking place; how autonomy of companies in creating product value and satisfying consumers, is slowly and surely giving way to consumer-centric approach? How consumer and firm interact and co-create value, and how the cocreation experience becomes the very basis of value? The authors develop the co-creation experience framework in the subsequent chapters very cogently and lucidly. It goes like this, the co-creation experience depends highly on individuals. Each person's uniqueness affects co-creation process as well as co-creation experience. Dialogue, access, risk assessment and transparency (DART) are the building blocks of value co-creation process and companies use this to engage customer effectively as collaborator. In the domain of competition, co-creation experience plays the most important role in decision making. This process further gains momentum in the later chapters of first part as co-creation experience is shaped by dimensions such as choice of channels, options made available, quality of transaction and price-experience relationship. This experience will vary from consumer to consumer due to the different traits of individual. To ensure that the transaction between the consumer and the firm produces positive co-creation experience, the presence of an appropriate environment is imperative, authors develop this concept very carefully. This environments accommodate the heterogeneity of consumer and facilitate a variety of co-creation experience. In the present day world, emerging technology acts as an experience enabler, facilitating innovation in experience environment. With intense competition, sky high consumer expectation; consumer looks for uniqueness which is possible only through personalized co-creation experience. …

The Future of Competition: Co-Creating Unique Value with Customers

The learning process of artificial neural networks is considered as one of the most difficult challenges in machine learning and has attracted many researchers recently. The main difficulty of training a neural network is the nonlinear nature and the unknown best set of main controlling parameters (weights and biases). The main disadvantages of the conventional training algorithms are local optima stagnation and slow convergence speed. This makes stochastic optimization algorithm reliable alternative to alleviate these drawbacks. This work proposes a new training algorithm based on the recently proposed whale optimization algorithm (WOA). It has been proved that this algorithm is able to solve a wide range of optimization problems and outperform the current algorithms. This motivated our attempts to benchmark its performance in training feedforward neural networks. For the first time in the literature, a set of 20 datasets with different levels of difficulty are chosen to test the proposed WOA-based trainer. The results are verified by comparisons with back-propagation algorithm and six evolutionary techniques. The qualitative and quantitative results prove that the proposed trainer is able to outperform the current algorithms on the majority of datasets in terms of both local optima avoidance and convergence speed.

Optimizing connection weights in neural networks using the whale optimization algorithm

The terms "Neural Network" (NN) and "Artificial Neural Network" (ANN) usually refer to a Multilayer Perceptron Network. It process the records one at a time, and "learn" by comparing their prediction of the record with the known actual record. The problem of model selection is considerably important for acquiring higher levels of generalization capability in supervised learning. This paper discussed behavioral analysis of different number of hidden layers and different number of hidden neurons. It's very difficult to select number of hidden layers and hidden neurons. There are different methods like Akaike's Information Criterion, Inverse test method and some traditional methods are used to find Neural Network architecture. What to do while neural network is not getting train or errors are not getting reduced. To reduce Neural Network errors, what we have to do with Neural Network architecture. These types of techniques are discussed and also discussed experiment and result. To solve different problems a neural network should be trained to perform correct classification..

/pdf/behaviour-analysis-of-multilayer-perceptrons-with-multiple-4dts016e2z.pdf

Behaviour Analysis of Multilayer Perceptrons with Multiple Hidden Neurons and Hidden Layers

The problem of model selection is considerably important for acquiring higher levels of generalization capability in supervised learning. Neural networks are commonly used networks in many engineering applications due to its better generalization property. An ensemble neural network algorithm is proposed based on the Akaike information criterion (AIC). Ecologists have long relied on hypothesis testing to include or exclude variables in models, although the conclusions often depend on the approach used. The advent of methods based on information theory, also known as information-theoretic approaches, has changed the way we look at model selection The Akaike information criterion (AIC) has been successfully used in model selection. It is not easy to decide the optimal size of the neural network because of its strong nonlinearity. We discuss problems with well used information and propose a model selection method.

/pdf/searching-most-efficient-neural-network-architecture-using-30hon5109q.pdf

Searching Most Efficient Neural Network Architecture Using Akaike's Information Criterion (AIC)

an Artificial Neural Network classifier is a nonparametric classifier. It does not need any priori knowledge regarding the statistical distribution of the class in a giver selected data Source. While, neural network can be trained to distinguish the criteria used to classify easily in a generalized manner that allows successful classification the newly arrived inputs not used during training. Through this paper it is eastliblished that back propagation neural network works successfully for the purpose of classification. Back propagation suffers from getting stuck into Local Minima. Weight optimization in Back propagation can be optimized using the Genetic Algorithm (GA). The back propagation algorithm is improved by invoking Genetic algorithm, to improve the overall performance of the classifier. The performance of a fitness algorithm using the approach suggested by us is a Hybrid System that is being analyzed in this paper. In this paper the issue of improving the fitness (weight adjustment) of Back propagation algorithm is addressed. Some of the Advantages of Hybrid algorithms are: convergence speed will be increased and the local minima problem can be overcome. The proposed Hybrid Algorithm is to perform learning as a back propagation and optimize weights using GA for classification.

/pdf/initial-classification-through-back-propagation-in-a-neural-4z6ae8bs2i.pdf

Initial Classification Through Back Propagation In a Neural Network Following Optimization Through GA to Evaluate the Fitness of an Algorithm

In this paper, the authors have presented a reduced size metamaterial loaded circular microstrip patch antenna. In the present work, complementary split ring resonator is loaded in the ground plane of circular microstrip patch antenna is. The unloaded circular microstrip patch antenna resonates at 6.11 GHz, whereas after loading it with complementary split ring resonator, the same antenna resonates near 6.11 GHz with reduced size. The effective footprint of the antenna is reduced by nearly 64% compared to the conventional patch antenna. The gain of the metamaterial loaded antenna structure is 5.04 dB.

Reduced size patch antenna using complementary split ring resonator as defected ground plane

We present microstrip patch antenna loaded with multiple split ring resonator substrate and superstrate. We analyze how the loading of split ring resonator superstrate and substrate can improve the bandwidth compared to the simple microstrip patch antenna and microstrip patch antenna loaded with split ring resonator superstrate. Another important observation is made for multiple split ring resonator loading in superstrate and substrate of microstrip patch antenna. The design is compared for two, three, and four-ring split ring resonator loading. The designs are also compared for different gap spacing between the rings. All three designs are compared for small gap and large gap between the rings. The design results in the form of reflection coefficient and bandwidth is presented in this manuscript. The design results are also compared with previously published designs.

/pdf/broadband-compact-microstrip-patch-antenna-design-loaded-by-579cwnxc7r.pdf

Yogeshwar P. Kosta

Papers

Behaviour Analysis of Multilayer Perceptrons with Multiple Hidden Neurons and Hidden Layers

Searching Most Efficient Neural Network Architecture Using Akaike's Information Criterion (AIC)

Initial Classification Through Back Propagation In a Neural Network Following Optimization Through GA to Evaluate the Fitness of an Algorithm

Reduced size patch antenna using complementary split ring resonator as defected ground plane

Broadband compact microstrip patch antenna design loaded by multiple split ring resonator superstrate and substrate