Towards Developing the Piece-Wise Linear Neural Network Algorithm for Rule Extraction

This paper discusses development and application of a decomposition neural network rule extraction algorithm for nonlinear regression problems. The algorithm is called the piece-wise linear artificial neural network or PWL-ANN algorithm. The objective of the algorithm is to “open up” the black box of a neural network model so that rules in the form of linear equations are generated by approximating the sigmoid activation functions of the hidden neurons in an artificial neural network (ANN). The preliminary results showed that the algorithm gives high fidelity and satisfactory results on sixteen of the nineteen tested datasets. By analyzing the values of R2 given by the PWL approximation on the hidden neurons and the overall output, it is evident that in addition to accurate approximation of each individual node of a given ANN model, there are more factors affecting the fidelity of the PWL-ANN algorithm Nevertheless, the algorithm shows promising potential for domains when better understanding about the problem is needed.

Software Defect Prediction Using Genetic Programming and Neural Networks

This article describes how classification methods on software defect prediction is widely researched due to the need to increase the software quality and decrease testing efforts. However, findings of past researches done on this issue has not shown any classifier which proves to be superior to the other. Additionally, there is a lack of research that studies the effects and accuracy of genetic programming on software defect prediction. To find solutions for this problem, a comparative software defect prediction experiment between genetic programming and neural networks are performed on four datasets from the NASA Metrics Data repository. Generally, an interesting degree of accuracy is detected, which shows how the metric-based classification is useful. Nevertheless, this article specifies that the application and usage of genetic programming is highly recommended due to the detailed analysis it provides, as well as an important feature in this classification method which allows the viewing of each attributes impact in the dataset.

Deep Learning and Online Education as an Informal Learning Process

Informal learning is a universal current phenomenon of learning via participation, experience, or learning via student-centered knowledge creation. It stands in stark contrast with the traditional view of didactic teacher-centered learning. Online education can be regarded as a positive and self-directed form of informal learning. Whether or not deep learning takes place for the online learner is a controversial topic for many educators. This chapter will discuss the benefits and challenges of the relationship between informal online learning leading to deeper learning. But, what isn't controversial is that in this century more education has been delivered in digital platforms than in any other time in history. For most providers of education to remain highly competitive, they must engage in electronic education of some form by moving beyond the brick and mortar of the traditional classroom. Informal learning has become the impetus resulting in the extensive and intensive application of electronic education.

Comparing Predictive Ability of Classifiers in Forecasting Online Buying Behaviour

With Internet invading geographic boundaries and diverse demographic strata, online shopping is growing at exponential rate. Expected to grow by 45 per cent to $7.69 billion by the end of 2015, India's ecommerce market has emerged as one of the most anticipated destinations for both multinational and domestic retailers. Since their success will depend on their ability to attract shoppers to buy online, it becomes relevant for them to decipher Indian consumers' attitude and behaviour towards online shopping and to predict online buying potential in India. The effectiveness of marketing and promotional strategies and action plans also will have to be pivoted around the potential available in the market. This empirical study explores the accuracy, precision and recall of four different classifying techniques used in predicting online buying. The forecasting ability of logistic regression (LR), artificial neural network (ANN), support vector machines (SVM) and random forest (RF) in the context of willingness of shoppers' to buy online has been compared. Analysis of the data supported most of the predictions albeit with varying level of accuracy. The outcome of the study reflects the superiority of artificial neural network over the other three models in terms of the predicting power. This paper adds to the knowledge body for online retailers in reducing their vulnerability with respect to market demand and improves their preparedness to handle the market response. Managerial implications of the findings and scope for future research have been deliberated.

Classification of Breast Thermograms Using Statistical Moments and Entropy Features with Probabilistic Neural Networks

Breast cancer is considered as one of the life-threatening disease among woman population in developing as well as developed countries. This specific study reports on classification of breast thermograms using probabilistic neural network (PNN) with four statistical moments features mean, standard deviation, skewness and kurtosis and two entropy features, Shannon entropy and Wavelet packet entropy. The CLAHE histogram equalization algorithm with uniform and Rayleigh distributions were considered for contrast enhancement of breast thermal images. The asymmetry detection was performed by applying bilateral ratio. A total of 95 test images (normal = 53, abnormal = 42) was considered. Simulation study shows that CLAHE -RD with wavelet entropy features confirms the existence of symmetry on the right and left breast thermal images. An overall classification accuracy of 92.5% was achieved using the proposed multifeatures with PNN classifier. The proposed technique thus confirms the suitability as a screening tool for asymmetry detection as well as classification of breast thermograms.

Identifying the Antecedents of Children's Market Using Neural Network

Chapter 5 explores the main features contributing towards the formation of living brand among children within the age 10 to 12-year-old by using a fuzzy logic analysis. From this methodological approach, several interesting insights emerge with regard to children's consumer behaviour, especially the factors of future anticipation, ritual, and autobiographical memory in the priming of the development of a living brand. In this chapter, we are going to expand on the discussion by identifying the antecedents of a successful product using Indonesian market segment from the same age group as the research subjects in Chapter 6. Some of the important elements for success in the children's segment that we identify here include brand personality, brand trust, and brand salience, particularly on how each of them affect brand relationship. When combined with autobiographical memory and buying habituation, this emotional bonding results in brand loyalty. Finally, we utilised a neural network topology in order to fully understand the antecedents of brand loyalty construction within the children's market.

A Survey on Supervised Convolutional Neural Network and Its Major Applications

With the advances in the computer science field, various new data science techniques have been emerged. Convolutional Neural Network (CNN) is one of the Deep Learning techniques which have captured lots of attention as far as real world applications are considered. It is nothing but the multilayer architecture with hidden computational power which detects features itself. It doesn't require any handcrafted features. The remarkable increase in the computational power of Convolutional Neural Network is due to the use of Graphics processor units, parallel computing, also the availability of large amount of data in various variety forms. This paper gives the broad view of various supervised Convolutional Neural Network applications with its salient features in the fields, mainly Computer vision for Pattern and Object Detection, Natural Language Processing, Speech Recognition, Medical image analysis.

Resource Scheduling and Load Balancing Fusion Algorithm with Deep Learning Based on Cloud Computing

With the wide application of the cloud computing, the contradiction between high energy cost and low efficiency becomes increasingly prominent. In this article, to solve the problem of energy consumption, a resource scheduling and load balancing fusion algorithm with deep learning strategy is presented. Compared with the corresponding evolutionary algorithms, the proposed algorithm can enhance the diversity of the population, avoid the prematurity to some extent, and have a faster convergence speed. The experimental results show that the proposed algorithm has the most optimal ability of reducing energy consumption of data centers.

Business Applications of Deep Learning

Deep Learning (DL) took Artificial Intelligence (AI) by storm and has infiltrated into business at an unprecedented rate. Access to vast amounts of data extensive computational power and a new wave of efficient learning algorithms, helped Artificial Neural Networks to achieve state-of-the-art results in almost all AI challenges. DL is the cornerstone technology behind products for image recognition and video annotation, voice recognition, personal assistants, automated translation and autonomous vehicles. DL works similarly to the brain by extracting high-level, complex abstractions from data in a hierarchical and discriminative or generative way. The implications of DL supported AI in business is tremendous, shaking to the foundations many industries. In this chapter, I present the most significant algorithms and applications, including Natural Language Processing (NLP), image and video processing and finance.

Meteorological Data Forecast using RNN

Gathering knowledge not only of the current but also the upcoming wind speed is getting more and more important as the experience of operating and maintaining wind turbines is increasing. Not only with regards to operation and maintenance tasks such as gearbox and generator checks but moreover due to the fact that energy providers have to sell the right amount of their converted energy at the European energy markets, the knowledge of the wind and hence electrical power of the next day is of key importance. Selling more energy as has been offered is penalized as well as offering less energy as contractually promised. In addition to that the price per offered kWh decreases in case of a surplus of energy. Achieving a forecast there are various methods in computer science: fuzzy logic, linear prediction or neural networks. This paper presents current results of wind speed forecasts using recurrent neural networks (RNN) and the gradient descent method plus a backpropagation learning algorithm. Data used has been extracted from NASA's Modern Era-Retrospective analysis for Research and Applications (MERRA) which is calculated by a GEOS-5 Earth System Modeling and Data Assimilation system. The presented results show that wind speed data can be forecasted using historical data for training the RNN. Nevertheless, the current set up system lacks robustness and can be improved further with regards to accuracy.