Search

This paper presents a review of research works from the last several years in automated story generation systems. These systems are categorised into interactive story generation systems and non-Interactive story generation systems. Interactive systems are those that collaborate with a user/author during the process of creating and/or executing the story. The extent of user interaction varies across systems but remains an integral part of the creation and/or the unfolding of the story. Non-Interactive systems concentrate on complete automation of the creative process involved in narrative generation to create diverse and interesting stories. Interactive story generators specifically designed for video game narratives are reviewed as a separate sub-class of interactive story generation systems. Also reviewed are the methods used for evaluation of story generation systems as a way to explore the possibility of having standard methods of evaluation within the research community. The paper includes a discussion of trends and directions of the research discipline. [ABSTRACT FROM AUTHOR]

This paper presents and evaluates a method for automatically generating a narrative that includes initial input from the listener, without forcing him/her to become an actual character in the story. More importantly, the story can be modified by the listener during the course of the story being narrated. This latter feature works without pre-defining alternative paths, thereby permitting the changes to take place at any time throughout the course of the story. This system, called the Campfire Storytelling System, employs a contextual approach to narrative generation called the Cooperating Context Method (CCM). Campfire STS was assessed for its functionality and its user acceptance. Thirty-eight human test subjects evaluated stories generated by Campfire STS. They responded to a survey stating their opinions about the generated stories, their entertainment value for adults, their creativity, and other similar issues. Furthermore, 20 of these subjects who self-reported non-trivial experience with children were additionally asked to evaluate the generated stories with respect to how much children would enjoy them. The results of these evaluations suggest that Campfire STS is able to create interesting and novel stories, as well as change them seamlessly in mid-stream while still maintaining interesting and entertaining stories. [ABSTRACT FROM AUTHOR]

This paper introduces, describes, and evaluates real-time models of affective states of individual learners interacting with Intelligent Tutoring Systems. Computer-based instructors, like human instructors, should use affective information for adapting instruction. This requires an accurate representation of individual learner state during tutoring; however, models described in the literature are generalised and constructed offline. Such total population models have faced validation difficulty with individuals, while individualised models have had difficulties with offline creation and online use. The simultaneous creation and utilisation of an individualised model from sensor-based physiological measurements presents an attractive alternative. We present and evaluate approaches for building affective models during the tutoring session which address the difficulties present in real-time data streams. Additionally, this work examines the impact of occasional direct user query on model quality. The results indicate that individualised real-time model construction is comparable to offline equivalents, yet can be successfully applied in tutoring settings. [ABSTRACT FROM PUBLISHER]

Subject matter experts can sometimes provide incorrect and/or incomplete knowledge in the process of building intelligent systems. Other times, the expert articulates correct knowledge only to be misinterpreted by the knowledge engineer. In yet other cases, changes in the domain can lead to outdated knowledge in the system. This paper describes a technique that improves a flawed tactical agent by revising its knowledge through practice in a simulated version of its operational environment. This form of theory revision repairs agents originally built through interaction with subject matter experts. It is advantageous because such systems can now cease to be completely dependent on human expertise to provide correct and complete domain knowledge. After an agent has been built in consultation with experts, and before it is allowed to become operational, our method permits its improvement by subjecting it to several practice sessions in a simulation of its mission environment. Our method uses reinforcement learning to correct such errors and fill in gaps in the knowledge of a context-based tactical agent. The method was implemented and evaluated by comparing the performance of an agent improved by our method, to the original hand-built agent whose knowledge was purposely seeded with known errors and/or gaps. The results show that the improved agent did in fact correct the seeded errors and did gain the missing knowledge to permit it to perform better than the original, flawed agent. [ABSTRACT FROM AUTHOR]

This article describes a knowledge preservation and re-use tool designed to capture the knowledge of a specific individual at the US National Science Foundation, for later retrieval by successors after his retirement. The system is designed in a Q&A format, where it is sufficiently intelligent to ask for clarifying questions. The primary objective was to create a system that would result in acceptance of the system by the users. The domain of interest to be preserved and re-used was programmatic knowledge about the NSF Industry/University Collaborative Research Centers (I/UCRC) Program, and more specifically, the knowledge of its long-time director, Dr. Alex Schwarzkopf. The system is called AskAlex and it uses a trio of techniques to accomplish its objectives. Contextual graphs (CxG) are used as the basic knowledge representation structure. CxG's are assisted by a search engine and an ontology of terms to help find the proper contextual graph that can best answer the question being asked. Evaluations with users and potential users generally confirm our selection and provided some guidance for improvements in the system. [ABSTRACT FROM AUTHOR]

Highlights: [•] We train a team of autonomous agents to duplicate the behavior of other agents within a simulation. [•] We use a context-based multi-agent system known as Collaborative Context-based Reasoning. [•] We use an off-line machine learning technique to train agents via observation of the original agents. [ABSTRACT FROM AUTHOR]

• Showed the feasibility of identifying health condition in drivers by monitoring their actions. • Built model of driver behavior through machine learning from observation. • Falconet system employs Neuroevolution and Particle Swarm Optimization to build model. This paper describes our investigation to determine whether undesirable health conditions of an automobile driver can be identified in real time solely by monitoring and assessing his/her driving behavior. The concept has great potential to reduce the accident rate on roadways, especially for young inexperienced drivers who may be suffering from chronic health conditions that when uncontrolled, can result in dangerous driving actions. Our approach involves building models of "normal" and "abnormal" driving by an individual through machine learning from observation (MLfO, or simply LfO). Conceptually, discrepancies between actual driving actions taken by a driver in real time and the actions prescribed by a model of her/his normal driving, and/or similarities to a model of his/her abnormal driving, could indicate a dangerous medical condition. If appropriate, the system could alert the driver and/or the appropriate authorities (e.g., EMTs, police, or parents if a minor) of the potential for danger. More specifically, our research created models of human driving through the use of an LfO system developed previously in our laboratory called Force-feedback Approach to Learning from Coaching and Observation with Natural and Experiential Training (Falconet). Time-stamped traces of actions taken by 12 human test subjects in a driving simulator were collected and used to create the models of human driving behavior through Falconet. Then the overall actions prescribed by the models (called the agents) were compared to the original traces to ascertain whether similarities and/or differences between the human test subject behaviors and the agent behaviors could be indicative of the target conditions. In our use case presented here, the target condition was Attention Deficit/Hyperactivity Disorder (ADHD), a condition that afflicts many driving age teenagers and which can be detrimental to safe driving when not under control through medication. The work described in this paper is exploratory in nature, with the objective of showing scientific feasibility. The results of extensive testing indicate that the agents created with the Falconet system produced promising results, being able to correctly characterize traces in up to nearly 82% of the test cases presented. Nevertheless, as is typical in such exploratory works, we found that much further work remains to be done before this concept becomes ready for commercial application. In this paper we describe the approach taken, the agents created and the extensive quantitative experiments conducted, as well as any insights learned. Areas of further research are also identified and discussed. [ABSTRACT FROM AUTHOR]

This paper describes a two-phase approach for automating the agent-building process when the agent is to perform tactical tasks. The research is inspired by how humans learn—first by observation of a teacher's performance and then by practicing the performance themselves. The objectives of this approach are to produce a high-performing agent that 1) approaches or exceeds the proficiency of a human and 2) does so in a human-like manner. We accomplish these objectives by combining observational learning with experiential learning. These processes are executed sequentially, with the former creating a competent but somewhat limited human-like model from scratch, and the latter improving its performance without significantly eroding its human-like qualities. The process is described in detail, and test results confirming our hypothesis are described. [ABSTRACT FROM PUBLISHER]

This article describes an investigation into the feasibility of using contextual reasoning to monitor and supervise the collaborative work of several knowledge workers working together on a project. Managing large and complex projects is a difficult task that requires situational awareness by the project manager to be able to be proactive when possible and to react correctly in the presence of events. In complex projects, effective oversight of the project personnel and the progress of the project are essential in ensuring that project objectives are met. This is especially true of projects that require contributions from various experts, whose interaction may be limited to a Web-based collaborative tool. Such oversight is typically the job of a project manager who is tasked with avoiding cost overruns, shipment delays, and ensuring product effectiveness. We utilize context-based reasoning and contextual graphs as the tools of choice for implementing an agent that emulates the function of a competent project manager. We use rocket design and manufacture as the domain to evaluate our technique. We use a public domain rocket design software package developed by the National Aeronautics and Space Administration as a guide to the domain. The article describes the investigation, its results, and the related works in a collaborative design project. [ABSTRACT FROM AUTHOR]

This paper explores the issues faced in creating a system that can learn tactical human behavior merely by observing a human perform the behavior in a simulation. More specifically, this paper describes a technique based on fuzzy ARTMAP (FAM) neural networks to discover the criteria that cause a transition between contexts during a strategic game simulation. The approach depends on existing context templates that can identify the high-level action of the human, given a description of the situation along with his action. The learning task then becomes the identification and representation of the context sequence executed by the human. In this paper, we present the FAM/Template-based Interpretation Learning Engine (FAMTILE). This system seeks to achieve this learning task by constructing rules that govern the context transitions made by the human. To evaluate FAMTILE, six test scenarios were developed to achieve three distinct evaluation goals: 1) to assess the learning capabilities of FAM; 2) to evaluate the ability of FAMTILE to correctly predict human and context selections, given an observation; and 3) more fundamentally, to create a model of the human's behavior that can perform the high-level task at a comparable level of proficiency. [ABSTRACT FROM AUTHOR]

Abstract: To gain a clearer understanding of conditions conducive to the development of coffee rust and improve disease control, we monitored the development of rust epidemics in 73 plots in Honduras, over 1–3 years depending on the case, focusing on coffee tree characteristics, crop management patterns, and the environment. A simple correspondence analysis was used to show that a link could be found between certain production situations and the intensity of coffee rust epidemics. Local characteristics specific to each plantation were particularly well linked to the intensity of coffee rust epidemics, whereas regional factors such as rainfall appeared to be of secondary importance. The yield and the number of leaves of the coffee trees were positively linked to epidemic development. Soil pH and fertilisation were negatively associated with epidemic development. Shade, when it did not limit yield, probably affected the microclimate in such a way that coffee rust incidence increased. Altitude was a serious constraint in disease development. These links were illustrated by a segmentation tree, which helped to define risk domains and rationalise coffee rust control. It also provided an understanding of how intensifying Arabica cultivation, through its effects on yield and soil acidification, increased the risk of a serious coffee rust epidemic occurring. [Copyright &y& Elsevier]

It is widely accepted that the difficulty and expense involved in acquiring the knowledge behind tactical behaviors has been one limiting factor in the development of simulated agents representing adversaries and teammates in military and game simulations. Several researchers have addressed this problem with varying degrees of success. The problem mostly lies in the fact that tactical knowledge is difficult to elicit and represent through interactive sessions between the model developer and the subject matter expert. This paper describes a novel approach that employs genetic programming in conjunction with context-based reasoning to evolve tactical agents based upon automatic observation of a human performing a mission on a simulator. In this paper, we describe the process used to carry out the learning. A prototype was built to demonstrate feasibility and it is described herein. The prototype was rigorously and extensively tested. The evolved agents exhibited good fidelity to the observed human performance, as well as the capacity to generalize from it. [ABSTRACT FROM AUTHOR]

The effects of crop management patterns on coffee rust epidemics, caused byHemileia vastatrix, are not well documented despite large amounts of data acquired in the field on epidemics, and much modelling work done on this disease. One main reason for this gap between epidemiological knowledge and understanding for management resides in the lack of links between many studies and actual production situations in the field. Coffee rust epidemics are based on a seemingly simple infection cycle, but develop polycyclic epidemics in a season and polyetic epidemics over successive seasons. These higher-level processes involve a very large number of environmental variables and, as in any system involving a perennial crop, the physiology of the coffee crop and how it affects crop yield. Crop management is therefore expected to have large effects on coffee rust epidemics because of its immediate effect on the infection cycle, but also because of its cumulative effect on ongoing and successive epidemics. Quantitative examples taken from a survey conducted in Honduras illustrate how crop management, different combinations of shade, coffee tree density, fertilization and pruning may strongly influence coffee rust epidemics through effects on microclimate and plant physiology which, in turn, influence the life cycle of the fungus. We suggest there is a need for novel coffee rust management systems which fully integrate crop management patterns in order to manage the disease in a sustainable way. [ABSTRACT FROM AUTHOR]

BSTRACT: To better know the cup quality of Honduran coffee, a study was carried out on samples from 52 Arabica coffee plots spread throughout 6 producing regions in Honduras. The aim was to identify environmental and agronomic factors that affect coffee quality. Biochemical and physical characteristics of coffees after roasting were used to link quality descriptors to these variables by means of multiple factor analyses. Coffees of superior quality came from the Olancho and El Paraíso regions. High altitudes and annual rainfall of under 1500 mm were favorable factors for the sensory quality. An optimum roasting time must be sought for each type of coffee, hence for each terroir. [ABSTRACT FROM AUTHOR]

Presents a study that developed a methodology for the validation of rule-based expert intelligent systems. Generation of test cases; Details on the development of a validity statement based on a Turing test; Refinement of intelligent systems; Evaluation of the methodology.

Researchers and practitioners in the field of expert systems all generally agree that to be useful, any fielded intelligent system must be adequately verified and validated. But what does this mean in concrete terms? What exactly is verification? What exactly is validation? How are they different? Many authors have attempted to define these terms and, as a result, several interpretations have surfaced. It is our opinion that there is great confusion as to what these terms mean, how they are different, and how they are implemented. This paper, therefore, has two aims-to clarify the meaning of the terms validation and verification as they apply to intelligent systems, and to describe how several researchers are implementing these. The second part of the paper, therefore, details some techniques that can be used to perform the verification and validation of systems. Also discussed is the role of testing as part of the above-mentioned processes. [ABSTRACT FROM AUTHOR]

Presents information on issues which arise when a diagnostic problem solver is equipped with the means of reasoning with multiple models of a system. Information on the representation of the knowledge used in the construction and execution control strategies; What is required for the effective diagnosis of complex systems.

Presents a validation technique which uses a case library system to validate a case-based reasoning (CBR) system. Description of case-based reasoning; Presence of test cases in the CBR system; Functioning of the validation technique; Phases of the validation technique.

Describes an alternative knowledge-based approach to automated control of electrical power systems. Background on the study; Intelligent power controller (IPC); Verification testing of IPC prototype; IPC performance evaluation.

This paper presents robust weighted variants of batch and online standard Gaussian processes (GPs) to effectively reduce the negative impact of outliers in the corresponding GP models. This is done by introducing robust data weighers that rely on robust and quasi-robust weight functions that come from robust M-estimators. Our robust GPs are compared to various GP models on four datasets. It is shown that our batch and online robust weighted GPs are indeed robust to outliers, significantly outperforming the corresponding standard GPs and the recently proposed heteroscedastic GP method GPz. Our experiments also show that our methods are comparable to and sometimes better than a state-of-the-art robust GP that uses a Student-t likelihood. [ABSTRACT FROM AUTHOR]

Pests and diseases are the main yield-reducing factors in simplified agricultural systems. Their role in complex, diverse, agricultural systems may, however, be less apparent because of the many interactions in which they are involved. However, it is essential to understand the relationships between pests and diseases, on the one hand, and ecosystem services (including crop production), on the other, to develop sustainable agroecosystems. Our study aims to illustrate these complex relationships based on the example of coffee agroecosystems in Costa Rica. We analysed a dataset consisting of 107 coffee plots characterized for their topoclimates, soils, coffee plant production characteristics, cropping practices, and pest and disease injuries. Meta-variables were created through cluster analyses to account for these different broad attributes of coffee-based agroecosystems. In particular, coffee injury profiles were determined on the basis of injury levels incurred by pathogens, nematodes, and insects over the course of one growing season. We used correspondence analysis to assess the levels of linkage between injury profiles and other agroecosystem meta-variables. Indicators of biodiversity based on shade diversity and of attainable yield were incorporated in the analysis as additional variables. Four groups of coffee-based agrosystems were identified, ranging from extensive (low-input, perennial polyculture) to intensive (unshaded high-input monoculture). Each group of coffee-based agroecosystem corresponds to varying levels of pest and disease injuries, crop yield, and ecosystem service provision, excluding coffee production. In each group of coffee-based agrosystem, we discussed the drivers of coffee production and explored potential avenues to improve sustainability based on ecosystem services provision. We highlighted that the physical characteristics of the environment, topoclimate and soil characteristics, are the main drivers of injury profiles and of resulting yield losses. Cropping practices and pest and disease management first need to be adapted to these physical characteristics. Where topoclimate and soils favour pest and disease development, potentially leading to heavy yield losses, system diversification can enhance ecosystem service provision, including production of other crops, thus helping to offset low coffee production. Where physical environmental characteristics hamper pests and diseases, increasing ecosystem service provision by incorporating shade trees may be considered, provided that coffee production is not significantly reduced. We conclude that there is an acute need to quantify losses caused by pests and diseases in agroforestry systems, in order to provide a rational basis for growers’ decisions and to better determine the value of economic incentives needed for ecosystem service provision. [ABSTRACT FROM AUTHOR]

Highlights: [•] We present a unified framework for learning from observation (LfO). [•] We present a Dynamic Bayesian Network (DBN) model of LfO. [•] We present a novel set of evaluation metrics for LfO algorithms. [•] We show evidence that our metrics better capture LfO algorithm performance than metrics used in previous LfO work. [Copyright &y& Elsevier]

This paper presents an integrated research and teaching model that has resulted from an NSF-funded effort to introduce results of current Machine Learning research into the engineering and computer science curriculum at the University of Central Florida (UCF). While in-depth exposure to current topics in Machine Learning has traditionally occurred at the graduate level, the model developed affords an innovative and feasible approach to expanding the depth of coverage in research topics to undergraduate students. The model has been self-sustaining as evidenced by its continued operation during the years after the NSF grant's expiration, and is transferable to other institutions due to its use of modular and faculty-specific technical content. This model offers a tightly coupled teaching and research approach to introducing current topics in Machine Learning research to undergraduates, while also involving them in the research process itself. The approach has provided new mechanisms to increase faculty participation in undergraduate research, has exposed approximately 15 undergraduates annually to research at UCF, and has effectively prepared a number of these students for graduate study through active involvement in the research process and coauthoring of publications. [ABSTRACT FROM AUTHOR]

Human experts employed in validation exercises for knowledge-based systems (KBSs) often have limited time and availability. Furthermore, they often have different opinions from each other as well as from themselves over time. We address this situation by introducing the use of validation knowledge used in prior validation exercises for the same KBS. We present a validation knowledge base (VKB) that is the collective best experience of several human experts. The VKB is constructed and maintained across various validation exercises, and its primary benefits are given as follows: 1) more reliable validation results by incorporating external knowledge and 2) decrease of the experts' workload. We also present the concept of validation expert software agents (VESAs), which represent a particular expert's knowledge. VESA is a software agent corresponding to a specific human expert. It models the validation knowledge and behavior of its human counterpart by analyzing similarities with the responses of other experts. After a learning period, it can be used to temporarily substitute for its corresponding human expert. We also describe experiments with a small prototype system to evaluate the usefulness of these concepts. [ABSTRACT FROM AUTHOR]

A methodology for the validation of rule-based expert systems is presented as a multi-step process that has three central themes: (1) creation of a useful set of test inputs that cover the domain; (2) a methodology that evaluates the system's responses to the test inputs and compares it to the responses of a panel of human experts; and (3) use of the validation results for system refinement. The presented methodology is performed in a loop. The starting point is a rule base and the loop ends up in a (hopefully) better rule base. The first three steps of this process have been published as separate issues in earlier papers by the authors. Here, these issues are just outlined and references are provided for detailed information. This paper gives an overview of the entire process and describes the relation between its steps. The last step, system refinement, is the new scientific issue here and thus, presented in more detail. Here, the rules are modified according to the results of evaluating the test cases. The base of this rule base reconstruction is both a 'rule-associated validity' and the existence of a 'better rated' human solution. [ABSTRACT FROM AUTHOR]

Imagine an agent that performs tasks according to different strategies. The goal of Behavioral Recognition (BR) is to identify which of the available strategies is the one being used by the agent, by simply observing the agent’s actions and the environmental conditions during a certain period of time. The goal of Behavioral Cloning (BC) is more ambitious. In this last case, the learner must be able to build a model of the behavior of the agent. In both settings, the only assumption is that the learner has access to a training set that contains instances of observed behavioral traces for each available strategy. This paper studies a machine learning approach based on Probabilistic Finite Automata (PFAs), capable of achieving both the recognition and cloning tasks. We evaluate the performance of PFAs in the context of a simulated learning environment (in this case, a virtual Roomba vacuum cleaner robot), and compare it with a collection of other machine learning approaches. [ABSTRACT FROM AUTHOR]

Stomoxys calcitrans control is primarily based on the use of chemical products; however, new methods for control have been investigated. Biological control has been proposed as a promising alternative to traditional chemicals. The current study evaluated three methods in vitro to treat S. calcitrans eggs with the fungus Metarhizium anisopliae and assessed the virulence of this fungus to immature stages of this fly. In the first method of egg exposure, eggs were immersed in conidial suspensions and transferred to Petri plates with high humidity. A high mortality was observed in both treated and control groups. In the second method, the eggs were transferred to rearing medium right after immersion in conidial suspensions; the suspensions with highest conidial concentrations, 107 and 108 conidia mL−1, caused 96.25% and 100% mortality, respectively. In the third method, the eggs were sprayed with conidial suspensions on the rearing medium. A high mortality was observed at 107 and 108 conidia mL−1, 78.3% and 100%, respectively. The second method had the lowest mortality in the control group and was considered the most useful method for evaluating the effect of entomopathogenic fungi on S. calcitrans eggs. While eggs were very susceptible to M. anisopliae infection, larvae and pupae were not. [ABSTRACT FROM AUTHOR]