Microphysics of E-Learning Tutor: GT Brain™

The choice of computer-based national exams is a choice of a student that must be adjusted to his interests and talents, so in this case the selection of majors is very important for the future of a student who will continue his studies to college. But in reality the decisions taken in choosing majors often cause problems, because the majors taken only follow the choice of friends or on the basis of coercion from parents. Causing the large number of students who feel out of line with expectations or abilities and want to change majors. For this reason, an expert system has been made that can make it easy for students to consult early to determine elective subjects for computer-based national examinations. The method used in making this expert system is the Forward Chaining method to determine conclusions. The process of this application is to receive input in the form of types of problems experienced by students. The result of the application is that it can provide early instructions for subjects that match the talents and interests of students. With the application of the forward chaining method that is applied to the system that is governed by the rule type problem. From the accuracy of 89.29%, the system can be said to be good enough to be implemented.

Reconfigurable computing is emerging as an important area of research in computer architectures and software systems. Many algorithms can be greatly accelerated by placing the computationally intense portions of an algorithm into reconfigurable hardware. Reconfigurable computing combines many benefits of both software and ASIC implementations. Like software, the mapped circuit is flexible, and can be changed over the lifetime of the system. Similar to an ASIC, reconfigurable systems provide a method to map circuits into hardware. Reconfigurable systems therefore have the potential to achieve far greater performance than software as a result of bypassing the fetch-decode-execute operations of traditional processors, and possibly exploiting a greater level of parallelism. Such a field, where there is many different algorithms which can be accelerated, is an artificial intelligence. This paper presents example hardware implementations of Artificial Neural Networks, Genetic Algorithms and Expert Systems.

This chapter deals with expert systems (ES) development as the final product of a software product line (SPL). We take into account software variability management in the ES domain. Two kinds of variability emerge: variability in the behavior as well as in the structure of such systems. Experts’ knowledge is captured using domain conceptual models in order to manage the variability and functionality of the ES. The ES are constructed using our baseline-oriented modeling (BOM) approach. BOM is a framework that automatically generates software applications as PRISMA architectural models by using SPL techniques. We follow the model-driven architecture (MDA) initiative for building domain models, which are automatically transformed into executable applications.

Applications of artificial neural networks in the field of genome research will be reviewed and some more recent developments in neural network research relevant for future applications will be surveyed. The basic definitions for artificial neural networks and neural learning algorithms will be introduced. The applications range from the recognition of translation initiation sites in nucleic acid sequences, the recognition of splice junctions and exons/ introns in mRNA, the detection of uncommon sequences in cDNA, to the prediction of secondary and tertiary structures of proteins from the amino acid sequence, the detection of structural motifs in protein sequences and the classification of protein sequences into functional families. Most applications employ multilayer feedforward networks trained supervised with the backpropagation learning algorithm or self-organising Kohonen maps adapted unsupervised for feature extraction. The most promising developments in neural network research usable in all mentioned applications are new modular network architectures with more problem-tailored connection topologies such as linked receptive fields and recurrent networks with short-term memory capable of modelling any dynamical system using only inductive learning.

An expert system in computer assisted language learning

Improved Salp Swarm Algorithm based on opposition based learning and novel local search algorithm for feature selection

The purpose of this research is to analyze the distribution of countries and territories within the structural elements of the Global Economy, presented both graphically and in tabular form. Using World Bank statistical data on GDP and population from 2005 to 2009, the study applies a previously proposed methodology for identification of the structural elements on the planes of pairs of scaled indices. It examines annual changes in the general appearance and composition of these elements, as well as the overall stability of the Global Economy structure. The scientific novelty of this research lies in the identification and description of the Global Economy's structure during this period. The detailed description of the Global Economy structure provided for 2005-2009 in combination with the previously presented description of the same structure in 2000-2004 may serve, as a result, as a foundational framework for analyzing the Global Economy dynamics over a longer time period from 2000 to the present.

In this paper, a learning algorithm using neuronal networks to improve the roll stability and prevent the rollover in a single unit heavy vehicle is proposed. First, a linear quadratic regulator (LQR) to keep balanced normalised rollovers, between front and rear axles, below the unity, is designed; the data collected from this controller is used to train the artificial neuronal network (ANN), whose inputs are quite selected. The neuronal controller is thereafter applied for linear side force model, with constant and variable friction, which gives satisfactory results. And since the hydraulic actuator has eight order transfer function with uncontrollable states, an effective method to calculate the reduced order model (ROM) of the original high order model (HOM) is elaborated. The actuator has been approximated by a fully controllable second order model, which is suitable for feedback controllers. The control of the hydraulic actuator is based on a polynomial approach controller (R, S, T). This last RST controller is applied to control the roll angle of the actuator and simulations are carried out to show the effectiveness of the procedure.

A review is presented of ATR (automatic target recognition), and some of the highlights of neural network technology developments that have the potential for making a significant impact on ATR are presented. In particular, neural network technology developments in the areas of collective computation, learning algorithms, expert systems, and neurocomputer hardware could provide crucial tools for developing improved algorithms and computational hardware for ATR. The discussion covers previous ATR system efforts. ATR issues and needs, early vision and collective computation, learning and adaptation for ATR, feature extraction, higher vision and expert systems, and neurocomputer hardware.

Iterative learning belief rule-base inference methodology using evidential reasoning for delayed coking unit

As discussed in Chapter , the analytical approach requires a detailed quantitative mathematical model in order to be effective. For large-scale systems, such information may not be available or may be too costly and timeconsuming to obtain. An alternative method for process monitoring is to use knowledge-based methods such as causal analysis, expert systems, and pattern recognition. These techniques are based on qualitative models, which can be obtained through causal modeling of the system, expert knowledge, a detailed description of the system, or fault-symptom examples. Causal analysis techniques are based on the causal modeling of fault-symptom relationships. Qualitative and semi-quantitative relationships in these causal models can be obtained without using first principles. Causal analysis techniques including signed directed graphs and symptom trees are primarily used for diagnosing faults. These techniques are described in Section 12.2.

EXPOSE is an expert system with the objective to provide user interface designers with empirical knowledge about common practice of the application domain, with software-ergonomic (HCI-) knowledge comprised from psychology and ergonomics research findings and with procedural knowledge about a principled approach (design rationale) to user interface design. The system provides the designer with a tool to describe the design decisions for a specific user interface subsequently in four models in order to reduce the design complexity: a conceptual model, a model of the dialog structure, a concretized model of the user interface and the prototype, following the four views of MUSE (Method for User Interface Engineering).

A lot of people nowadays use online education platforms. Most of them run on the free «Open edX» open-source software platform. Using the logs that the platform provides us, we can get psychometrics of students, which can be used to improve the presentation of material or other things, which can increase the quality of online courses. We provide a ready-to-use tool that will help figure out how and for what purpose you can analyze the log files of platforms based on «Open edX».

Smart grids of the future will create and provide huge data volumes, which are subject to FAIR data management solutions when used within the scientific domain and for operation. FAIR digital objects (FDO) provide access to (meta)data, and ontologies explicitly describe metadata as well as application data objects and domains. The present paper proposes a novel approach to integrate FAIR digital objects and ontologies as metadata models in order to support data access for energy researchers, energy research applications, operational applications and energy information systems. As the first example domain to be modeled using an ontology and to get integrated with FAIR digital objects, a photovoltaic system model is selected. For the given purpose, a discussion of existing energy ontologies shows the necessity to develop a new PV ontology. By integration of FDOs, this new PV ontology is introduced in the present paper. Furthermore, the concept of FDOs is integrated with the PV ontology in such a way that it allows for generalization. By this, the present paper contributes to a sustainable data management for smart grid operation, especially for interoperability, by using ontologies and hence unambiguous semantics.

The steady state and transient analysis methods of converter-fed dc series motor reported so far do not take into account the nonlinearity of the magnetic circuit. Furthermore for transient analysis discontinuous conduction has been neglected and only first order model has been reported though series motor is essentially a second order system. Various approximations for the nonlinearity of the magnetic circuit and steady state analysis have been described In Fart I of the paper. The present paper (Part II) describes the methods of transient analysis for fully-controlled and half-controlled converter controlled dc series motor taking the nonlinearity and discontinuous conduction into account. First order as well as second order models have been considered. Calculated performance has been verified experimentally.