Innovations in Intelligent Machines, Volume 3: Contemporary Achievements in Intelligent Systems (Studies in Computational Intelligence, Volume 442)
Language: English
Pages: 161
ISBN: 2:00351522
Format: PDF / Kindle (mobi) / ePub
This book aims to promote a sample of current theoretical and application oriented intelligent systems research specifically in the field of neural networks computing. It presents examples of experimental and real-world investigations that demonstrate contemporary achievements and advances in the area of intelligent systems.
This book will prove as a valuable source of up-to-date theoretical and application oriented research in intelligent systems for researchers and postgraduate students.
................................................................................................... 15 2 Introduction ...................................................................................................... 16 3 Market Power ................................................................................................... 17 4 FNN Approach for Open Electricity Market .................................................... 19 5 Hybrid Fuzzy Neural Network Based Power Market Assessment
weight to the least severe class (class I). Full AC, OPF solution were run for all load scenarios to obtain LI,RMP and NC for each trading period of an IEEE 14 bus system. The normalized LI, RMP and NC values were fuzzified using data given in Tables 1, 2 and 3 respectively. The graphical representation is given in figs 2, 3 and 4 respectively. The value of FCMI of individual generator for each trading period was computed using membership values of the indices LI, RMP and NC. Table 4 presents the
Class1 (NMP) GENCOS do not use market power Class2 (NMP) GENCOS do not use market power Class3 (PMP) GENCOS partially utilize the market power Class4 (LMP) GENCOS create the local market Class5 (FMP) GENCOS Fully utilize the market power 1.2 1.2 Target value1 ANN output1 1 0.8 0.8 0.6 Output Output 0.6 0.4 0.4 0.2 0.2 0 0 -0.2 Target value2 ANN output2 1 -0.2 0 10 20 30 40 50 60 Pattern number 70 80 90 100 0 Fig. 6. Testing performance of FNN for Membership value
human-to-human skill transfer process, it is intuitive for human trainers, and we define this framework as Coaching a robot, opposed to Teaching a robot. The biggest difference between Teaching and Coaching is: conventional Teaching methodologies require adequate evaluation function in advance, while Coaching, as indicated in Fig. 1, allows the agent to learn not only the desired behavior but also the adequate evaluation function as an internal model of human trainer, simultaneously. In this
Multiplicative Neuron (SMN) Model for Software Reliability Prediction S. Chatterjee*, J.B. Singh, S. Nigam, and L.N. Upadhyaya Dept. of Applied Mathematics, ISM, Dhanbad-826004, India chatterjee_subhashis@rediffmail.com Abstract. This chapter presents a single multiplicative neuron model for predicting software failure has been proposed. Standard back propagation and real coded genetic algorithm with mean squarer error as a fitness function are used for optimizing the parameters. The performance