Intelligent Computational Systems

This paper presents the STAR system, a system for automated narrative comprehension, developed on top of an argumentation-theoretic formulation of defeasible reasoning, and strongly following guidelines from the psychology of comprehension. We discuss the system’s use in psychological experiments on story comprehension, and our plans for its broader use in empirical studies concerning wider issues of commonsense reasoning.

This study generally aimed to develop a model that can predict carbon footprint emissions based on the datasets obtained. The parameters that the researchers utilized were population and energy production from 1990 to 2019. The data were all chosen from the vital drivers of CO2 emissions identified through the literature review and had been collected using the open-sourced program WEKA. The three algorithms used in this study are Linear Regression (LR), Multilayer Perceptron (MLP), and Sequential Minimal Optimization Regression (SMOreg) to test which among these most-used algorithms in time series data mining prediction delivers outstanding results. These were participated in the trials given to the researchers to gather sufficient data to draw conclusions. The researchers determined that the MLP model is able to estimate greenhouse gas emissions at error levels that are acceptable in comparison to the actual values and test results. If the Philippines maintains its current trajectory, the carbon footprint emissions will eventually rise and probably reach 255,595.03 kt in the year 2030. There is a powerful correlation between population and energy production that contributes to the carbon footprint emissions within the Philippines.

This research aims to predict PV output power by using different neuro-evolutionary methods. The proposed approach was evaluated by a data set, which was collected at 5-minute intervals in the photovoltaic laboratory of Niroo Research Institute of Iran (Tehran). The data has been divided into three intervals based on the amount of solar irradiation, and different neural networks were used for predicting each interval. NSGA II, a multi-objective optimization algorithm, has been applied to search an appropriate set of weights, which optimized the neural network with two or more conflicting objectives. The MLP-NSGA II algorithm provides better results with the Mean Square Error (MSE) and correlation coefficient (R2) of 0.01 and 0.98, respectively, in comparison with Linear Regression, MLP, and MLP-GA. By the way, obtained results show that the precision of prediction models would be improved by reducing input parameters’ time intervals.

This paper presents the STAR system, a system for automated narrative comprehension, developed on top of an argumentation-theoretic formulation of defeasible reasoning, and strongly following guidelines from the psychology of comprehension. We discuss the system’s use in psychological experiments on story comprehension, and our plans for its broader use in empirical studies concerning wider issues of commonsense reasoning.

We report on an ongoing research program to develop a formal framework for automated narrative text comprehension, bringing together know-how from research in Artificial Intelligence and the Psychology of Reading and Comprehension. It uses argumentation to capture appropriate solutions to the frame, ramification, and qualification problems, and their generalizations as required for text comprehension. In this first part of the study we concentrate on the central problem of integration of the explicit information from the text narrative with the reader's implicit commonsense world knowledge, and the associated tasks of elaboration and revision.

This paper reports on how work in psychology can inform research into automated narrative text comprehension. Specifically, we describe the psychology's view of how human readers combine information from text with their own commonsense world knowledge to build a single coherent model of a narrative. We present a framework that formalizes, using a suitable form of preference-based argumentation, this notion of comprehension and outline how this might form the basis for partially mechanizing the process of comprehension.

This paper develops a Reasoning about Actions and Change framework integrated with Default Reasoning, suitable as a Knowledge Representation and Reasoning framework for Story Comprehension. The proposed framework, which is guided strongly by existing knowhow from the Psychology of Reading and Comprehension, is based on the theory of argumentation from AI. It uses argumentation to capture appropriate solutions to the frame, ramification and qualification problems and generalizations of these problems required for text comprehension. In this first part of the study the work concentrates on the central problem of integration (or elaboration) of the explicit information from the narrative in the text with the implicit (in the reader's mind) common sense world knowledge pertaining to the topic(s) of the story given in the text. We also report on our empirical efforts to gather background common sense world knowledge used by humans when reading a story and to evaluate, through a prototype system, the ability of our approach to capture both the majority and the variability of understanding of a story by the human readers in the experiments.

Machine learning (ML) is penetrating in all walks of life and is one of the major driving forces behind the fourth industrial revolution, typically known as Industry 4.0. This study reviews the state-of-the-art ML applications in the biofuels’ life cycle stages, i.e., soil, feedstock, production, consumption, and emissions. A keyword search is performed to retrieve relevant articles from the databases of the Web of Science and Google Scholar. ML applications in the soil stage were mostly based on the use of satellite images of land for estimation of biofuels yield or suitability analysis of agricultural land. In the second stage of the life cycle, assessment of rheological properties of the feedstocks and their effect on the quality of biofuels were dominant studies reported in the literature. The production stage included estimation and optimization of quality, quantity, and process conditions. The fuel consumption and emissions stage included analysis of engine performance and est...

Green hydrogen is considered to be one of the best candidates for fossil fuels in the near future. Bio-hydrogen production from the dark fermentation of organic materials, including organic wastes, is one of the most cost-effective and promising methods for hydrogen production. One of the main challenges posed by this method is the low production rate. Therefore, optimizing the operating parameters, such as the initial pH value, operating temperature, N/C ratio, and organic concentration (xylose), plays a significant role in determining the hydrogen production rate. The experimental optimization of such parameters is complex, expensive, and lengthy. The present research used an experimental data asset, adaptive network fuzzy inference system (ANFIS) modeling, and particle swarm optimization to model and optimize hydrogen production. The coupling between ANFIS and PSO demonstrated a robust effect, which was evident through the improvement in the hydrogen production based on the four ...

This study presents the use of a machine learning method from the artificial intelligence area, such as the support vector machines, applied to the construction of data-based classification models for diagnosing undesired scenarios in the hydrogen production process by photo-fermentation, which was carried out by an immobilized photo-bacteria consortium. The diagnosis models were constructed with data obtained from simulations run with a mechanistic model of the process and assessed on both modelled and experimental batches. The results revealed a 100% diagnosis performance in those batches where light intensity was below and above an optimum operation range. Nevertheless, 55% diagnosis performance was obtained in modelled batches where pH was away from its optimum operation range, showing that diagnosis model predictions during the first observations of those batches were classified as normal operation and revealing diagnosis delay in pH oscillations. In general, results demonstrat...

This paper presents the STAR system, a system for automated narrative comprehension, developed on top of an argumentation-theoretic formulation of defeasible reasoning, and strongly following guidelines from the psychology of comprehension. We discuss the system’s use in psychological experiments on story comprehension, and our plans for its broader use in empirical studies concerning wider issues of commonsense reasoning.

The widespread access to computing-enabled devices and the World Wide Web has, in a sense, liberated the ordinary user from reliance on technically-savvy experts. To complete this emancipation, a new way of interacting with, and controlling the behavior of, computing-enabled devices is needed. This position paper argues for the adoption of cognitive programming as the paradigm for this user-machine interaction, whereby the machine is no longer viewed as a tool at the disposal of the user, but as an assistant capable of being supervised and guided by the user in a natural and continual manner, and able to acquire and employ common sense to help the user in the completion of everyday tasks. We argue that despite the many challenges that the proposed paradigm presents, recent advances in several key areas of Artificial Intelligence, along with lessons learned from work in Psychology, give reasons for optimism. 1 An Emerging Need and The Overall Challenge Today’s huge market pressure fo...

We report on an ongoing research program to develop a formal framework for automated narrative text comprehension, bringing together know-how from research in Artificial Intelligence and the Psychology of Reading and Comprehension. It uses argumentation to capture appropriate solutions to the frame, ramification, and qualification problems, and their generalizations as required for text comprehension. In this first part of the study we concentrate on the central problem of integration of the explicit information from the text narrative with the reader's implicit commonsense world knowledge, and the associated tasks of elaboration and revision.

Adaptive neuro-fuzzy inference system (ANFIS) and artificial neural network (ANN) were applied in modeling of methane mixed reforming in a packed bed catalytic reactor. These methods were developed by use of data collected from a methane reforming pilot plant using CO2 and steam and in process conditions near to MIDREX reforming plant in sponge Iron production. Different reaction temperatures from 700 to 1100 C with different values of carbon dioxide, steam, hydrogen, methane and carbon monoxide, were randomly selected and used to generate around 5000 data set of input-output data. Both networks achieve quite satisfying scientific results with acceptable deviations. However, it is hard to say which one is better as they have close output values but ANN marginally outperformed ANFIS in predicting the reaction outputs by varying the inputs. The prediction performances of these models are compared. The accuracies of the two models were evaluated in terms of square correlation coefficient (R 2) and mean square error (MSE).

This paper studies how logic-based reasoning about actions and change (RAC) with its problems of temporal projection and qualification can be formalised in terms of argumentation. In particular, we extend earlier work of translating the language E for RAC into a logic-based argumentation framework, by introducing new types of arguments for (i) backward persistence and (ii) persistence from observations. This forms a conservative extension of the language E that gives a semantic meaning to domains that cannot be interpreted under E thus addressing further the frame and (exogenous) qualification problems. As such the paper strengthens the link between argumentation theory and RAC in artificial intelligence.

This paper presents the STAR system, a system for automated narrative comprehension, developed on top of an argumentation-theoretic formulation of defeasible reasoning, and strongly following guidelines from the psychology of comprehension. We discuss the system’s use in psychological experiments on story comprehension, and our plans for its broader use in empirical studies concerning wider issues of commonsense reasoning.

This paper develops a Reasoning about Actions and Change framework integrated with Default Reasoning, suitable as a Knowledge Representation and Reasoning framework for Story Comprehension. The proposed framework, which is guided strongly by existing knowhow from the Psychology of Reading and Comprehension, is based on the theory of argumentation from AI. It uses argumentation to capture appropriate solutions to the frame, ramification and qualification problems and generalizations of these problems required for text comprehension. In this first part of the study the work concentrates on the central problem of integration (or elaboration) of the explicit information from the narrative in the text with the implicit (in the reader's mind) common sense world knowledge pertaining to the topic(s) of the story given in the text. We also report on our empirical efforts to gather background common sense world knowledge used by humans when reading a story and to evaluate, through a prototype system, the ability of our approach to capture both the majority and the variability of understanding of a story by the human readers in the experiments.

This paper develops a Reasoning about Actions and Change framework integrated with Default Reasoning, suitable as a Knowledge Representation and Reasoning framework for Story Comprehension. The proposed framework, which is guided strongly by existing knowhow from the Psychology of Reading and Comprehension, is based on the theory of argumentation from AI. It uses argumentation to capture appropriate solutions to the frame, ramification and qualification problems and generalizations of these problems required for text comprehension. In this first part of the study the work concentrates on the central problem of integration (or elaboration) of the explicit information from the narrative in the text with the implicit (in the reader's mind) common sense world knowledge pertaining to the topic(s) of the story given in the text. We also report on our empirical efforts to gather background common sense world knowledge used by humans when reading a story and to evaluate, through a prototype system, the ability of our approach to capture both the majority and the variability of understanding of a story by the human readers in the experiments.

This paper presents the STAR system, a system for automated narrative comprehension, developed on top of an argumentation-theoretic formulation of defeasible reasoning, and strongly following guidelines from the psychology of comprehension. We discuss the system’s use in psychological experiments on story comprehension, and our plans for its broader use in empirical studies concerning wider issues of commonsense reasoning.

We report on an ongoing research program to develop a formal framework for automated narrative text comprehension, bringing together know-how from research in Artificial Intelligence and the Psychology of Reading and Comprehension. It uses argumentation to capture appropriate solutions to the frame, ramification, and qualification problems, and their generalizations as required for text comprehension. In this first part of the study we concentrate on the central problem of integration of the explicit information from the text narrative with the reader's implicit commonsense world knowledge, and the associated tasks of elaboration and revision.

Fossil fuels (i.e., petroleum, natural gas and coal), which meet most of the world's energy demand today, are being depleted fast. Also, their combustion products are causing the global problems, such as the global warming, climate change, ozone layer depletion, acid rains, oxygen depletion and pollution, which are posing great danger for our environment and eventually for the life in our planet. Many engineers and scientists agree that the solution to these global problems would be replacing the existing fossil fuel system by the Hydrogen Energy System. Hydrogen is the lightest, most efficient and cleanest fuel. Its use will produce no greenhouse gases, no ozone layer depleting chemicals, little or no acid rain ingredients, no oxygen depletion and pollution. Around the world, there is extensive r&d work on Hydrogen Energy. Internal combustion engines are being modified for hydrogen fuel. Many types of fuel cells-to convert hydrogen efficiently to electricity-are being developed. Vehicle manufacturers have built several experimental cars and buses. Hyundai, Toyota, Honda and Mercedes companies started selling hydrogen fueled cars. Many bus companies are selling hydrogen fueled buses. Siemens Company is selling hydrogen fuel cells powered submarines. Hydrogen fueled appliances based on catalytic combustion have been built. There is research and development work on hydrogen hydride refrigeration and air conditioning systems. Aircraft manufacturers are working on hydrogen fueled subsonic and supersonic transport planes. Scientists and Engineers from many countries of the world will gather at the IHTEC2017 Conference to present their papers covering the recent advances in hydrogen energy and in hydrogen technologies. All these will no doubt speed up the conversion to hydrogen economy, eliminate global environmental problems, and provide the humankind with higher living standards. I congratulate the organizers of this Congress and wish all the participants a very fruitful meeting and pleasant days in beautiful Adana, Turkey.

The success of anaerobic digestion (AD) process for biogas production is contingent upon complex mix of operating factors, process conditions, and feedstock types, which could be affected by inadequate understanding of microbial, kinetic, and physicochemical processes. To address these limitations, efforts have been directed toward developing mathematical and intelligent models. Although mathematical models provide near-optimal solutions, they are time consuming, highly expensive, and demanding. Intelligent standalone models are also limited by their low predictive capability and inability to guarantee global optimal solution for the prediction of cumulative biogas yield for FFV waste. However, hyperparameter optimization of such models is essential to improve the prediction performance for cumulative biogas yield for FFV waste. Therefore, this study applies a genetic algorithm (GA) to optimize an adaptive neuro-fuzzy inference system (ANFIS) for the prediction of cumulative biogas ...

Machine learning (ML) is penetrating in all walks of life and is one of the major driving forces behind the fourth industrial revolution, typically known as Industry 4.0. This study reviews the state-of-the-art ML applications in the biofuels’ life cycle stages, i.e., soil, feedstock, production, consumption, and emissions. A keyword search is performed to retrieve relevant articles from the databases of the Web of Science and Google Scholar. ML applications in the soil stage were mostly based on the use of satellite images of land for estimation of biofuels yield or suitability analysis of agricultural land. In the second stage of the life cycle, assessment of rheological properties of the feedstocks and their effect on the quality of biofuels were dominant studies reported in the literature. The production stage included estimation and optimization of quality, quantity, and process conditions. The fuel consumption and emissions stage included analysis of engine performance and est...

We report on an ongoing research program to develop a formal framework for automated narrative text comprehension, bringing together know-how from research in Artificial Intelligence and the Psychology of Reading and Comprehension. It uses argumentation to capture appropriate solutions to the frame, ramification, and qualification problems, and their generalizations as required for text comprehension. In this first part of the study we concentrate on the central problem of integration of the explicit information from the text narrative with the reader's implicit commonsense world knowledge, and the associated tasks of elaboration and revision.

We report on an ongoing research program to develop a formal framework for automated narrative text comprehension, bringing together know-how from research in Artificial Intelligence and the Psychology of Reading and Comprehension. It uses argumentation to capture appropriate solutions to the frame, ramification, and qualification problems, and their generalizations as required for text comprehension. In this first part of the study we concentrate on the central problem of integration of the explicit information from the text narrative with the reader's implicit commonsense world knowledge, and the associated tasks of elaboration and revision.

This paper presents the STAR system, a system for automated narrative comprehension, developed on top of an argumentation-theoretic formulation of defeasible reasoning, and strongly following guidelines from the psychology of comprehension. We discuss the system's use in psychological experiments on story comprehension, and our plans for its broader use in empirical studies concerning wider issues of commonsense reasoning.

This paper reports on how work in psychology can inform research into automated narrative text comprehension. Specifically, we describe the psychology's view of how human readers combine information from text with their own commonsense world knowledge to build a single coherent model of a narrative. We present a framework that formalizes, using a suitable form of preference-based argumentation, this notion of comprehension and outline how this might form the basis for partially mechanizing the process of comprehension.

Nuclear hybrid energy systems (NHES) have potential to capitalize on (1) producing multiple commodities, i.e. electricity and hydrogen as well as (2) allowing for electricity grid load following, with hydrogen production during low electricity prices. Using nuclear thermal energy and electricity (from the reactor itself) makes hydrogen production an economically attractive option. The reactor can continuously operate at full capacity, sending excess heat and electricity towards hydrogen production, which could either be sold or converted back to electricity using fuel cells at high price times. Several hydrogen production technologies exist, but in this study the focus is on processes that require heat and electricity. These candidates include alkaline water electrolysis, proton exchange membrane (PEM) electrolysis, solid oxide electrolysis cells (SOEC), thermochemical sulfur-iodine (S-I), calcium-bromide (Ca-Br) cycles, hybrid sulfur (HyS) and copper-chlorine (Cu-Cl) cycles. Each have different minimum temperature requirements which can be coupled to Generation III and IV reactor outlet temperatures: low (<300 • C), medium (<750 • C), and high (<950 • C). Energy input and material process flow diagrams were created for all technologies at compatible reactor temperatures and compared to the most common commercially operating hydrogen production method: steam methane reforming (SMR). Technology readiness levels (TRLs) and costs were also compared. The TRL of most systems is still below commercial development, and hydrogen productions costs are still too high to be economic without additional policy and/or other developments.

This study presents the use of a machine learning method from the artificial intelligence area, such as the support vector machines, applied to the construction of data-based classification models for diagnosing undesired scenarios in the hydrogen production process by photo-fermentation, which was carried out by an immobilized photo-bacteria consortium. The diagnosis models were constructed with data obtained from simulations run with a mechanistic model of the process and assessed on both modelled and experimental batches. The results revealed a 100% diagnosis performance in those batches where light intensity was below and above an optimum operation range. Nevertheless, 55% diagnosis performance was obtained in modelled batches where pH was away from its optimum operation range, showing that diagnosis model predictions during the first observations of those batches were classified as normal operation and revealing diagnosis delay in pH oscillations. In general, results demonstrat...

Machine learning (ML) is penetrating in all walks of life and is one of the major driving forces behind the fourth industrial revolution, typically known as Industry 4.0. This study reviews the state-of-the-art ML applications in the biofuels’ life cycle stages, i.e., soil, feedstock, production, consumption, and emissions. A keyword search is performed to retrieve relevant articles from the databases of the Web of Science and Google Scholar. ML applications in the soil stage were mostly based on the use of satellite images of land for estimation of biofuels yield or suitability analysis of agricultural land. In the second stage of the life cycle, assessment of rheological properties of the feedstocks and their effect on the quality of biofuels were dominant studies reported in the literature. The production stage included estimation and optimization of quality, quantity, and process conditions. The fuel consumption and emissions stage included analysis of engine performance and est...

Machine learning (ML) is penetrating in all walks of life and is one of the major driving forces behind the fourth industrial revolution, typically known as Industry 4.0. This study reviews the state-of-the-art ML applications in the biofuels’ life cycle stages, i.e., soil, feedstock, production, consumption, and emissions. A keyword search is performed to retrieve relevant articles from the databases of the Web of Science and Google Scholar. ML applications in the soil stage were mostly based on the use of satellite images of land for estimation of biofuels yield or suitability analysis of agricultural land. In the second stage of the life cycle, assessment of rheological properties of the feedstocks and their effect on the quality of biofuels were dominant studies reported in the literature. The production stage included estimation and optimization of quality, quantity, and process conditions. The fuel consumption and emissions stage included analysis of engine performance and est...

Machine learning (ML) is penetrating in all walks of life and is one of the major driving forces behind the fourth industrial revolution, typically known as Industry 4.0. This study reviews the state-of-the-art ML applications in the biofuels’ life cycle stages, i.e., soil, feedstock, production, consumption, and emissions. A keyword search is performed to retrieve relevant articles from the databases of the Web of Science and Google Scholar. ML applications in the soil stage were mostly based on the use of satellite images of land for estimation of biofuels yield or suitability analysis of agricultural land. In the second stage of the life cycle, assessment of rheological properties of the feedstocks and their effect on the quality of biofuels were dominant studies reported in the literature. The production stage included estimation and optimization of quality, quantity, and process conditions. The fuel consumption and emissions stage included analysis of engine performance and est...

This paper develops a Reasoning about Actions and Change framework integrated with Default Reasoning, suitable as a Knowledge Representation and Reasoning framework for Story Comprehension. The proposed framework, which is guided strongly by existing knowhow from the Psychology of Reading and Comprehension, is based on the theory of argumentation from AI. It uses argumentation to capture appropriate solutions to the frame, ramification and qualification problems and generalizations of these problems required for text comprehension. In this first part of the study the work concentrates on the central problem of integration (or elaboration) of the explicit information from the narrative in the text with the implicit (in the reader's mind) common sense world knowledge pertaining to the topic(s) of the story given in the text. We also report on our empirical efforts to gather background common sense world knowledge used by humans when reading a story and to evaluate, through a prototype system, the ability of our approach to capture both the majority and the variability of understanding of a story by the human readers in the experiments.

World fossil fuel reserve is expected to be exhausted in coming few decades. Therefore, the decentralization of energy production requires the design and integration of different energy sources and conversion technologies to meet the power demand for single remote housing applications in a sustainable way under various weather conditions. This work focuses on the integration of photovoltaic (PV) system, micro-wind turbine (WT), Polymeric Exchange Membrane Fuel Cell (PEM-FC) stack and PEM water electrolyzer (PEM-WE), for a sustained power generation system (2.5 kW). The main contribution of this work is the hybridization of alternate energy sources with the hydrogen conversion systems using mid-term and short-term storage models based in artificial intelligence techniques built from experimental data (measurements obtained from the site of interest), this models allow to obtain better accuracy in performance prediction (PV MSE ¼ 8.4%, PEM-FC MSE ¼ 2.4%, PEM-WE MSE ¼ 1.96%, GSR MSE ¼ 7.9%, WT MSE ¼ 14%) with a practical design and dynamic under intelligent control strategies to build an autonomous system.

Forecasting the performance and energy yield of photovoltaic (PV) farms is crucial for establishing the economic sustainability of a newly installed system. The present study aims to develop a prediction model to forecast an installed PV system’s annual power generation yield and performance ratio (PR) using three environmental input parameters: solar irradiance, wind speed, and ambient air temperature. Three data-based artificial intelligence (AI) techniques, namely, adaptive neuro-fuzzy inference system (ANFIS), response surface methodology (RSM), and artificial neural network (ANN), were employed. The models were developed using three years of data from an operational 2MWp Solar PV Project at Kuzhalmannam, Kerala state, India. Statistical indices such as Pearson’s R, coefficient of determination (R2), root-mean-squared error (RMSE), Nash-Sutcliffe efficiency (NSCE), mean absolute-percentage error (MAPE), Kling-Gupta efficiency (KGE), Taylor’s diagram, and correlation matrix were ...

Texas A&M University at Qatar, Chemical Engineering Department, Sustainable Energy & Clean Air Research Laboratory (SECAReLab), PO Box 23874, Doha, Qatar Aristotle University of Thessaloniki, Department of Chemical Engineering, P.O. Box 1517, 54006 Thessaloniki, Greece Texas A&M University, Department of Mechanical Engineering, College Station, TX 77843-3123, USA Florida Solar Energy Center, University of Central Florida, Cocoa, FL 32922, USA k.kakosimos@qatar.tamu.edu

Intelligent Computational Optimization has been successfully applied to several control approaches. For instance, Planning Control uses information regarding a problem and its environment to decide whether a plan is the most suitable to achieve a required control objective or not. Such algorithm is commonly embedded into a conveniently located model inside a control loop. Planning provides a general and easy methodology widely used by a number of approaches such as receding horizon control (RHC) and model predictive control (MPC). Actually, MPC is the planning approach that has recently acknowledged a wide acceptance for industrial applications despite being highly constrained by |its computational complexity. For MPC, the evaluation of the overall plan is based upon time-consuming approaches such as dynamic programming and gradient-like methods. This chapter explores the usefulness of planning in order to improve the performance of feedback-based control schemes considering one probabilistic approach known as the Learning Automata (LA). Standard gradient methods develop a plan evaluation scheme whose solution lies on a neighbourhood distance from the previous point, forcing to explore the space extensively. Remarkably, LA algorithms are based on stochastic principles considering newer points for optimization as being determined by a probability function with no constraints whatsoever on how close they lie from previous optimization points. The proposed LA approach is considered as a planning system to select the plan holding the highest probability of yielding the best closed-loop results. The system's performance is tested through a nonlinear benchmark plant, comparing its results to the Levenberg-Marquardt (LM) algorithm and some other Genetic algorithms (GA).

Intelligent Computational Optimization has been successfully applied to several control approaches. For instance, Planning Control uses information regarding a problem and its environment to decide whether a plan is the most suitable to achieve a required control objective or not. Such algorithm is commonly embedded into a conveniently located model inside a control loop. Planning provides a general and easy methodology widely used by a number of approaches such as receding horizon control (RHC) and model predictive control (MPC). Actually, MPC is the planning approach that has recently acknowledged a wide acceptance for industrial applications despite being highly constrained by |its computational complexity. For MPC, the evaluation of the overall plan is based upon time-consuming approaches such as dynamic programming and gradient-like methods. This chapter explores the usefulness of planning in order to improve the performance of feedback-based control schemes considering one probabilistic approach known as the Learning Automata (LA). Standard gradient methods develop a plan evaluation scheme whose solution lies on a neighbourhood distance from the previous point, forcing to explore the space extensively. Remarkably, LA algorithms are based on stochastic principles considering newer points for optimization as being determined by a probability function with no constraints whatsoever on how close they lie from previous optimization points. The proposed LA approach is considered as a planning system to select the plan holding the highest probability of yielding the best closed-loop results. The system's performance is tested through a nonlinear benchmark plant, comparing its results to the Levenberg-Marquardt (LM) algorithm and some other Genetic algorithms (GA).

In the recent years, the energy issue is known as one of the main entries for economic and social development of human. So the biomass fuels as one of the approaches for supplying energy become the attractive topic for investigation. The higher heating value (HHV) is a key parameter for evaluation of energy of biomasses; so in the present study, a novel work was done to predict HHV as a function of ultimate analysis by utilization of multi-layer perceptron artificial neural network (MLP-ANN). To this end, a total number of 78 actual data were extracted from reliable references for training and validation of the model. The predicted HHVs were compared with the experimental data graphically and statistically, and the obtained results expressed that the MLP-ANN has a great potential for estimation of HHV of biomasses; so this approach can be used as a simple and accurate tool for forecasting HHV in terms of ultimate analysis. Based on the obtained results, this approach becomes one of the applicable softwares in industries.

This paper develops a Reasoning about Actions and Change framework integrated with Default Reasoning, suitable as a Knowledge Representation and Reasoning framework for Story Comprehension. The proposed framework, which is guided strongly by existing knowhow from the Psychology of Reading and Comprehension, is based on the theory of argumentation from AI. It uses argumentation to capture appropriate solutions to the frame, ramification and qualification problems and generalizations of these problems required for text comprehension. In this first part of the study the work concentrates on the central problem of integration (or elaboration) of the explicit information from the narrative in the text with the implicit (in the reader's mind) common sense world knowledge pertaining to the topic(s) of the story given in the text. We also report on our empirical efforts to gather background common sense world knowledge used by humans when reading a story and to evaluate, through a prototype system, the ability of our approach to capture both the majority and the variability of understanding of a story by the human readers in the experiments.

As conflict, the environment, and politics cause changes around the world, the United States Air Force is pursuing a diversification of drop-in and alternative fuel sources. Hydrogen fuel cells for vehicles are gaining popularity worldwide. Yet, how to best produce hydrogen gas still remains a question. This thesis will provide an overview of various hydrogen production methods and their respective environmental impacts, costs, efficiencies, and viability; and will perform sensitivity analysis to determine an optimal solution. The optimal production method is Thermolysis followed by Steam Reformation of Landfill or Natural Gas, Coal Gasification, and PEM Electrolysis. Based on varying requirements the recommended options for U.S. Air Force consideration are Thermolysis if nuclear power is available, Steam Reformation of Landfill Gas, and PEM Electrolysis. Steam Reformation of Natural Gas is only recommended for use in non-contested environments. PEM Electrolysis is extremely promisi...

Accurate forecasting of streamflow is desired in many water resources planning and management, flood prevention and design development. In this study, the accuracy of two hybrid model, support vector machine - particle swarm optimization (SVM-PSO) and bat algorithm – backpropagation neural network (BA-BPNN) for monthly streamflow forecasting at Kuantan River located in Peninsular Malaysia are investigated and compared to regular SVM and BPNN model. Heuristic optimization namely PSO and BA are introduced to find the optimum SVM and BPNN parameters. The input parameters to the forecasting models are antecedent streamflow, historical rainfall and meteorological parameters namely evaporation, temperature, relative humidity and mean wind speed. Two performance evaluation measure, root mean square error (RMSE) and coefficient of determination (R2) were employed to evaluate the performance of developed forecasting model. It is found that, RMSE and R2 for hybrid SVM-PSO are 24.8267 m3/s and...

This research aims to predict PV output power by using different neuro-evolutionary methods. The proposed approach was evaluated by a data set, which was collected at 5-minute intervals in the photovoltaic laboratory of Niroo Research Institute of Iran (Tehran). The data has been divided into three intervals based on the amount of solar irradiation, and different neural networks were used for predicting each interval. NSGA II, a multi-objective optimization algorithm, has been applied to search an appropriate set of weights, which optimized the neural network with two or more conflicting objectives. The MLP-NSGA II algorithm provides better results with the Mean Square Error (MSE) and correlation coefficient (R2) of 0.01 and 0.98, respectively, in comparison with Linear Regression, MLP, and MLP-GA. By the way, obtained results show that the precision of prediction models would be improved by reducing input parameters’ time intervals.

Due to the important role of ammonia as a fertilizer in the agricultural industry and its promising prospects as an energy carrier, many studies have recently attempted to find the most environmentally benign, energy efficient, and economically viable production process for ammonia synthesis. The most commonly utilized ammonia production method is the Haber-Bosch process. The downside to this technology is the high greenhouse gas emissions, surpassing 2.16 kgCO2-eq/kg NH3 and high amounts of energy usage of over 30 GJ/tonne NH3 mainly due to the strict operational conditions at high temperature and pressure. The most widely adopted technology for sustainable hydrogen production used for ammonia synthesis is water electrolysis coupled with renewable technologies such as wind and solar. In general, a water electrolyzer requires a continuous supply of pretreated water with high purity levels for its operation. Moreover, for production of 1 tonne of hydrogen, 9 tonnes of water is requir...

Agents learning to act autonomously in realworld domains must acquire a model of the dynamics of the domain in which they operate. Learning domain dynamics can be challenging, especially where an agent only has partial access to the world state, and/or noisy external sensors. Even in standard STRIPS domains, existing approaches cannot learn from noisy, incomplete observations typical of real-world domains. We propose a method which learns STRIPS action models in such domains, by decomposing the problem into first learning a transition function between states in the form of a set of classifiers, and then deriving explicit STRIPS rules from the classifiers' parameters. We evaluate our approach on simulated standard planning domains from the International Planning Competition, and show that it learns useful domain descriptions from noisy, incomplete observations.

This paper develops a Reasoning about Actions and Change framework integrated with Default Reasoning, suitable as a Knowledge Representation and Reasoning framework for Story Comprehension. The proposed framework, which is guided strongly by existing knowhow from the Psychology of Reading and Comprehension, is based on the theory of argumentation from AI. It uses argumentation to capture appropriate solutions to the frame, ramification and qualification problems and generalizations of these problems required for text comprehension. In this first part of the study the work concentrates on the central problem of integration (or elaboration) of the explicit information from the narrative in the text with the implicit (in the reader's mind) common sense world knowledge pertaining to the topic(s) of the story given in the text. We also report on our empirical efforts to gather background common sense world knowledge used by humans when reading a story and to evaluate, through a prototype system, the ability of our approach to capture both the majority and the variability of understanding of a story by the human readers in the experiments.

This paper reports on how work in psychology can inform research into automated narrative text comprehension. Specifically, we describe the psychology's view of how human readers combine information from text with their own commonsense world knowledge to build a single coherent model of a narrative. We present a framework that formalizes, using a suitable form of preference-based argumentation, this notion of comprehension and outline how this might form the basis for partially mechanizing the process of comprehension.

Accurate simulation of evaporation plays an important role in the efficient management of water Resources. Generally, evaporation is measured using the direct method where Class A panevaporimeter is used, and an indirect method that includes empirical equations. However, despite its widespread usage, Class A pan-evaporimeter method can be affected by human and instrumentation errors. Empirical equations, on the other hand, are generally linked to the different climatic factors that should provide initial or boundary conditions in the mathematical equations that affect the rate of evaporation. Considering these challenging, heuristic soft computing approaches that do not need key information about the physics of evaporation. In this study, a Quantum-behaved Particle Swarm Optimization algorithm, embedded into a multi-layer perceptron technique, is developed to estimate the evaporation rates over a daily forecast horizon. The measured evaporation data from 2012-2014 for Talesh meteorological station located in Northern Iran are employed. The predictive accuracy of the MLP-QPSO model is evaluated with existing methods: i.e. a hybrid MLP-PSO and a standalone MLP model. The results are evaluated in respect to statistical performance criterion: the mean absolute error, root mean square error (RMSE), Willmott's Index and the Nash-Sutcliffe coefficient. In conjunction with these metrics, Taylor diagrams are also utilized to assess the level of agreement between the forecasted and observed evaporation data. Evidently, the hybrid MLP-QPSO model is confirmed to be an optimal forecasting tool applied for estimating daily pan evaporation, outperforming both the hybrid MLP-PSO and the standalone model.In light of these results, the present study justifies the potential utility of the hybrid MLP-QPSO model to be applied for estimating daily evaporation rates in North of Iran.

Sedimentation in open channels occurs frequently and is relative to system inflow. The long-term retention of sediments on channel beds can increase the possibility of variations in deposits and their eventual consolidation. This study compares three hybrid artificial intelligence methods in estimating sediment transport without sedimentation (STWS). We employed the Particle Swarm Optimization (PSO), Imperialist Competitive Algorithm (ICA) and Genetic Algorithm (GA) methods in combination with the Artificial Neural Network (ANN) to overcome the weakness of ANN training with conventional algorithms. We used the ICA, GA and PSO methods to optimize the weights of the ANN layers. Using dimensional analysis, we placed the effective parameters in predicting sediment transport into five non-dimensional groups. Six models are proposed and run using three hybrid methods (18 models in total). As the comparisons demonstrate, the proposed combined models are more accurate than ANN and existing ...

Artificial intelligence (AI) models have been successfully applied in modeling engineering problems, including civil, water resources, electrical, and structure. The originality of the presented chapter is to investigate a non-tuned machine learning algorithm, called self-adaptive evolutionary extreme learning machine (SaE-ELM), to formulate an expert prediction model. The targeted application of the SaE-ELM is the prediction of river water level. Developing such water level prediction and monitoring models are crucial optimization tasks in water resources management and flood prediction. The aims of this chapter are (1) to conduct a comprehensive survey for AI models in water level modeling, (2) to apply a relatively new ML algorithm (i.e., SaE-ELM) for modeling water level, (3) to examine two different time scales (e.g., daily and monthly), and (4) to compare the inspected model with the extreme learning machine (ELM) model for validation. In conclusion, the contribution of the current chapter produced an expert and highly optimized predictive model that can yield a high-performance accuracy.