A. Murat Ozbayoglu

Estimation of the Burned Area in Forest Fires Using Computational Intelligence Techniques

Abstract Forest fires have environmental impacts that create economic problems as well as ecological damage. Developing a means to predict the possible size of a fire shortly after it first breaks out has the potential to guide proper resource allocation for improved fire control and was the main motivation of this research. In this study, the burned areas resulting from possible forest fires were estimated using historical forest fire records which contained parameters like geographical conditions of the existing environment, date and time when the fire broke out, meteorological data such as temperature, humidity and wind speed, and the type and number of trees in a unit area. The data was from the Department of Forestry in Turkey and contained 7,920 forest fire records from 2000 and 2009. The output from the estimation methods implemented in this work predicted the size of the area lost due to the fire and the corresponding fire size, i.e. big, medium, or small fire. Some of the estimation methods investigated were Multilayer Perceptron (MLP), Radial Basis Function Networks (RBFN), Support Vector Machines (SVM) and fuzzy logic. The results of these estimates are presented and compared to similar studies in literature.

An ontology-based multi-agent virtual enterprise system OMAVE: part 1: domain modelling and rule management

New advancements in computers and information technologies have yielded novel ideas to create more effective virtual collaboration platforms for multiple enterprises. Virtual enterprise (VE) is a collaboration model between multiple independent business partners in a value chain and is particularly suited to small and medium-sized enterprises (SMEs). The most challenging problem in implementing VE systems is ineffcient and inflexible data storage and management techniques for VE systems. In this research, an ontology-based multi-agent virtual enterprise (OMAVE) system is proposed to help SMEs shift from the classical trend of manufacturing part pieces to producing high-value-added, high-tech, innovative products. OMAVE targets improvement in the flexibility of VE business processes in order to enhance integration with available enterprise resource planning (ERP) systems. The architecture of OMAVE supports the requisite flexibility and enhances the reusability of the data and knowledge created in a VE system. In this article, a detailed description of system features along with the rule-based reasoning and decision support capabilities of OMAVE system are presented. To test and verify the functionality and operation of this system, a sample product was manufactured using OMAVE applications and tools with the contribution of three SMEs.

Ontology-centric data modelling and decision support in smart grid applications a distribution service operator perspective

Conventional electricity distribution grids are getting smarter by coupling operation technologies with advanced information and communication technologies (ICT). This provides a better, reliable, cost effective and efficient service to the consumer while requiring an immense two way data transfer between consumer and distribution service operator (DSO). This paper gives a brief summary of the current situation of DSOs in Turkey after the privatization of the market and also the state of operational technologies (OT) in use. The integration of OT with ICT is the first step in building a smart grid, and the decision support systems (DSS) are becoming crucial in this integration and operational effectiveness. A major component in the smart grid integration efforts is a common information model as pointed out in earlier work. We restate the case of ontologies in information modeling towards building a smart grid and present the requirements for using ontologies in smart grid information systems and DSSs.

An extended IoT framework with semantics, big data, and analytics

Many experts claim that data will be the most valuable commodity in the 21st century. At the same time, two of the most influential components of this era, Big Data and IoT are moving very fast, on a collision course with the methodologies that are associated with conventional data processing and database systems. As a result, new approaches like NoSQL databases, distributed architectures, etc. started appearing on the stage. Meanwhile, another technology, ontology and semantic data processing can be a very convenient catalyzer that might assist in smoothly providing this transformation process. In this paper, we propose a combined framework that brings Big Data, IoT, and semantic web together to build an augmented framework for this new era. We not only list the components of such a system and define the necessary bindings that needs to be integrated together, but also provide a realistic use case that demonstrates how the model can implement the desired functionality and achieve the goals of such a model.

Clustering Quality Improvement of k-means Using a Hybrid Evolutionary Model☆

Abstract Choosing good candidates for the initial centroid selection process for compact clustering algorithms, such as k-means, is essential for clustering quality and performance. In this study, a novel hybrid evolutionary model for k-means clustering (HE-kmeans) is proposed. This model uses meta-heuristic methods to identify the “good candidates” for initial centroid selection in k-means clustering method. The results indicate that the clustering quality is improved by approximately 30% compared to the standard random selection of initial centroids. We also experimentally compare our method with the other heuristics proposed for initial centroid selection and the experimental results show that our method performs better in most cases.

TN-RSI: Trend-normalized RSI Indicator for Stock Trading Systems with Evolutionary Computation

Abstract RSI is a commonly used indicator preferred by stock traders. However, even though it works well when the market is trendless, during bull or bear market conditions (when there is a clear trend) its performance degrades. In this study, we developed a trading model using a modified RSI using trend-removed stock data. The model has several parameters including, the trend detection period, RSI buy-sell trigger levels and periods. These parameters are optimized using genetic algorithms; then the trading performance is compared against B&H and standard RSI indicator usage. 9 different ETFs are selected for evaluating trading performance. The results indicate there is a performance improvement both in profit and success rates using this new model. As future work, other indicators might be modelled in a similar fashion in order to see if it is possible to find one indicator that can work under any market condition.

An Artificial Neural Network-based Stock Trading System Using Technical Analysis and Big Data Framework

In this paper, a neural network-based stock price prediction and trading system using technical analysis indicators is presented. The model developed first converts the financial time series data into a series of buy-sell-hold trigger signals using the most commonly preferred technical analysis indicators. Then, a Multilayer Perceptron (MLP) artificial neural network (ANN) model is trained in the learning stage on the daily stock prices between 1997 and 2007 for all of the Dow30 stocks. Apache Spark big data framework is used in the training stage. The trained model is then tested with data from 2007 to 2017. The results indicate that by choosing the most appropriate technical indicators, the neural network model can achieve comparable results against the Buy and Hold strategy in most of the cases. Furthermore, fine tuning the technical indicators and/or optimization strategy can enhance the overall trading performance.

A survey on semantic Web and big data technologies for social network analysis

Social Network Analysis (SNA) has become a very important and increasingly popular topic among researchers in recent years especially after emerging Semantic Web and Big Data technologies. Social networking services such as Facebook, Google+, Twitter, etc. provide large amounts of data that can be used for social network analysis by researchers. Semantic Web technology plays an important role for collecting, merging, and aggregating social network data from heterogeneous sources more easily, robustly and in an interoperable manner. Today, data scientists use several different frameworks for querying, integrating and analyzing datasets located at different sources. Meanwhile, most of the big social data is in unstructured or semi-structured format. Big data architectures allow researchers to analyze unstructured data in a time and cost-efficient way. New approaches for SNA are needed to combine Semantic Web and Big Data technologies in order to utilize and add capabilities to existing solutions. To be able to analyze large scale social networks, algorithms should have scalable designs in order to benefit from the emerging Big Data technologies. This survey focuses on recently developed systems for SNA and summarizes the state-of-the-art technologies used by them and points out to future research directions.

A Two-level Cascade Evolutionary Computation based Covered Call Trading Model☆

Abstract In this study, a two-level cascade stock trading model is proposed. In the first level, the buy/sell signals are created by optimizing the RSI technical indicator parameters with evolutionary computation techniques. Then using the selected parameters, in the second level actual trading is performed using an optimized covered call strategy. Again, the optimization is implemented with evolutionary computation. In this particular study, genetic algorithms (GA) and Particle Swarm Optimization (PSO) are chosen as the soft computing methods for optimization. Historical end-of-day close values and options data for the SP the testing is done with 2009 data. The results indicate that the proposed model outperformed not only the buy and hold strategy, but also buying and selling the ETF alone without the options. In future work different stock/ETF data and different combined options strategies will be included in the model to identify performances of different techniques.

Estimation of Multiphase Flow Properties using Computational Intelligence Models

Abstract Estimation of flow properties is essential in terms of the efficient usage of resources in drilling operations. Meanwhile, hydraulic characteristics of two phase fluids in annular geometries are not studied thoroughly. In this study, the flow patterns and liquid holdup characteristics of liquid-gas flow is analyzed using experimental data obtained from an eccentric pipe configuration. A high speed digital camera is used for recording the flow; in addition liquid holdup values are calculated using digital image processing techniques instead of empirical correlations or mechanistic measurements. At the same time through the acquired images, corresponding flow patterns are observed. Using the acquired images, estimation models are developed for air-water flow in horizontal eccentric annulus. This is conducted by using computational intelligence rather than conventional mechanistic models. The chosen models are nearest neighbor, backpropagation, decision trees and SVM. Input attributes are superficial Reynolds numbers for both liquid and gas phase. The output is the classified flow pattern and the liquid holdup value. SVM model turned out to be the best estimator for flow pattern identification process (%92.49 success rate for classifying 7 different flow patterns) whereas regression decision tree had the best performance for liquid holdup determination (RMSE of 0.0777).