Knowledge-Intensive Business Processes: Proceedings of the 1st International Workshop on Knowledge-intensive Business Processes [CEUR Workshop Proceedings, Volume 861]

Nowadays, Workflow Management Systems (WfMSs) and, more generally, Process Management Systems (PMPs) are process-aware Information Systems (PAISs), are widely used to support many human organizational activities, ranging from well-understood, relatively stable and structures processes (supply chain management, postal delivery tracking, etc.) to processes that are more complicated, less structured and may exhibit a high degree of variation (health-care, emergency management, etc.). Every aspect of a business process involves a certain amount of knowledge which may be complex depending on the domain of interest. The adequate representation of this knowledge is determined by the modeling language used. Some processes behave in a way that is well understood, predictable and repeatable: the tasks are clearly delineated and the control flow is straightforward. Recent discussions, however, illustrate the increasing demand for solutions for knowledge-intensive processes, where these characteristics are less applicable. The actors involved in the conduct of a knowledge-intensive process have to deal with a high degree of uncertainty. Tasks may be hard to perform and the order in which they need to be performed may be highly variable. Modeling knowledge-intensive processes can be complex as it may be hard to capture at design-time what knowledge is available at run-time. In realistic environments, for example, actors lack important knowledge at execution time or this knowledge can become obsolete as the process progresses. Even if each actor (at some point) has perfect knowledge of the world, it may not be certain of its beliefs at later points in time, since tasks by other actors may change the world without those changes being perceived. Typically, a knowledge-intensive process cannot be adequately modeled by classical, state of the art process/workflow modeling approaches. In some respect there is a lack of maturity when it comes to capturing the semantic aspects involved, both in terms of reasoning about them. The main focus of the 1st International Workshop on Knowledge-intensive Business processes (KiBP 2012) was investigating how techniques from different fields, such as Artificial Intelligence (AI), Knowledge Representation (KR), Business Process Management (BPM), Service Oriented Computing (SOC), etc., can be combined with the aim of improving the modeling and the enactment phases of a knowledge-intensive process. The 1st International Workshop on Knowledge-intensive Business process (KiBP 2012) was held as part of the program of the 2012 Knowledge Representation & Reasoning International Conference (KR 2012) in Rome, Italy, in June 2012. The workshop was hosted by the Dipartimento di Ingegneria Informatica, Automatica e Gestionale Antonio Ruberti of Sapienza Universita di Roma, with financial support of the University, through grant 2010-C26A107CN9 TESTMED, and the EU Commission through the projects FP7-25888 Greener Buildings and FP7-257899 Smart Vortex. This volume contains the 5 papers accepted and presented at the workshop. Each paper was reviewed by three members of the internationally renowned Program Committee. In addition, a further paper was invted for inclusion in the workshop proceedings and for presentation at the workshop. There were two keynote talks, one by Marlon Dumas (Institute of Computer Science, University of Tartu, Estonia) on "Integrated Data and Process Management: Finally?" and the other by Yves Lesperance (Department of Computer Science and Engineering, York University, Canada) on "A Logic-Based Approach to Business Processes Customization" completed the scientific program. We would like to thank all the Program Committee members for the valuable work in selecting the papers, Andrea Marrella for his valuable work as publication and publicity chair of the workshop, and Carola Aiello and the consulting agency Consulta Umbria for the organization of this successful event.

Inferencing design styles using Baysian Networks

Reasoning with uncertain knowledge and belief has long been recognized as an important research issue in Artificial Intelligence (AI). Several methodologies have been proposed in the past, including knowledge-based systems, fuzzy sets, and probability theory. The probabilistic approach became popular mainly due to a knowledge representation framework called Bayesian networks. Bayesian networks have earned reputation of being powerful tools for modeling complex problem involving uncertain knowledge. Uncertain knowledge exists in domains such as medicine, law, geographical information systems and design as it is difficult to retrieve all knowledge and experience from experts. In design domain, experts believe that design style is an intangible concept and that its knowledge is difficult to be presented in a formal way. The aim of the research is to find ways to represent design style knowledge in Bayesian net works. We showed that these networks can be used for diagnosis (inferences) and classification of design style. The furniture design style is selected as an example domain, however the method can be used for any other domain.

Achieving intention-centric BPM through automated planning

As a result of the more distributed nature of organisations and the inherently increasing complexity of their business processes, a significant effort is required for the specification and verification of those processes. The composition of the activities into a business process that accomplishes a specific organisational goal has primarily been a manual task. Automated planning is a branch of artificial intelligence (AI) in which activities are selected and organised by anticipating their expected outcomes with the aim of achieving some goal. As such, automated planning would seem to be a natural fit to the BPM domain to automate the specification of control flow. A number of attempts have been made to apply automated planning to the business process and service composition domain in different stages of the BPM lifecycle. However, a unified adoption of these techniques throughout the BPM lifecycle is missing. As such, we propose a new intention-centric BPM paradigm, which aims on minimising the specification effort by exploiting automated planning techniques to achieve a pre-stated goal. This paper provides a vision on the future possibilities of enhancing BPM using automated planning. A research agenda is presented, which provides an overview of the opportunities and challenges for the exploitation of automated planning in BPM.

Analysing student programs in the PHP intelligent tutoring system

Programming is a subject that many beginning students find difficult. The PHP Intelligent Tutoring System (PHP ITS) has been designed with the aim of making it easier for novices to learn the PHP language in order to develop dynamic web pages. Programming requires practice. This makes it necessary to include practical exercises in any ITS that supports students learning to program. The PHP ITS works by providing exercises for students to solve and then providing feedback based on their solutions. The major challenge here is to be able to identify many semantically equivalent solutions to a single exercise. The PHP ITS achieves this by using theories of Artificial Intelligence (AI) including first-order predicate logic and classical and hierarchical planning to model the subject matter taught by the system. This paper highlights the approach taken by the PHP ITS to analyse students’ programs that include a number of program constructs that are used by beginners of web development. The PHP ITS was built using this model and evaluated in a unit at the Queensland University of Technology. The results showed that it was capable of correctly analysing over 96 % of the solutions to exercises supplied by students.

Turning gaming EEG peripherals into trainable brain computer interfaces

Companies such as NeuroSky and Emotiv Systems are selling non-medical EEG devices for human computer interaction. These devices are significantly more affordable than their medical counterparts, and are mainly used to measure levels of engagement, focus, relaxation and stress. This information is sought after for marketing research and games. However, these EEG devices have the potential to enable users to interact with their surrounding environment using thoughts only, without activating any muscles. In this paper, we present preliminary results that demonstrate that despite reduced voltage and time sensitivity compared to medical-grade EEG systems, the quality of the signals of the Emotiv EPOC neuroheadset is sufficiently good in allowing discrimina tion between imaging events. We collected streams of EEG raw data and trained different types of classifiers to discriminate between three states (rest and two imaging events). We achieved a generalisation error of less than 2% for two types of non-linear classifiers.

Automating marine mammal detection in aerial images captured during wildlife surveys: A deep learning approach

Aerial surveys conducted using manned or unmanned aircraft with customized camera payloads can generate a large number of images. Manual review of these images to extract data is prohibitive in terms of time and financial resources, thus providing strong incentive to automate this process using computer vision systems. There are potential applications for these automated systems in areas such as surveillance and monitoring, precision agriculture, law enforcement, asset inspection, and wildlife assessment. In this paper, we present an efficient machine learning system for automating the detection of marine species in aerial imagery. The effectiveness of our approach can be credited to the combination of a well-suited region proposal method and the use of Deep Convolutional Neural Networks (DCNNs). In comparison to previous algorithms designed for the same purpose, we have been able to dramatically improve recall to more than 80% and improve precision to 27% by using DCNNs as the core approach.

Monte Carlo analysis of a puzzle game

When a puzzle game is created, its design parameters must be chosen to allow solvable and interesting challenges to be created for the player. We investigate the use of random sampling as a computationally inexpensive means of automated game analysis, to evaluate the BoxOff family of puzzle games. This analysis reveals useful insights into the game, such as the surprising fact that almost 100% of randomly generated challenges have a solution, but less than 10% will be solved using strictly random play, validating the inventor’s design choices. We show the 1D game to be trivial and the 3D game to be viable.

Finding within-organisation spatial information on the web

Information available on company websites can help people navigate to the offices of groups and individuals within the company. Automatically retrieving this within-organisation spatial information is a challenging AI problem This paper introduces a novel unsupervised pattern-based method to extract within-organisation spatial information by taking advantage of HTML structure patterns, together with a novel Conditional Random Fields (CRF) based method to identify different categories of within-organisation spatial information. The results show that the proposed method can achieve a high performance in terms of F-Score, indicating that this purely syntactic method based on web search and an analysis of HTML structure is well-suited for retrieving within-organisation spatial information.

ThreatBot: A new model for improving FPS experiences with bots

This work is focused on the player experience and the design of artificial intelligence (AI) to meet player expectations in a competitive video game context. The original contribution of this research is a new approach to designing games and AI opponents that are more enjoyable for players to interact with, particularly in First Person Shooter (FPS) video games. This approach is modeled in detail and implemented in a prototype game AI called ThreatBot. The results show that the new AI design is more enjoyable to compete against, particularly with regards to player's perceived levels of competence.

Special Issue: Engineering applications of representations of function, Part 1

In engineering design, the end goal is the creation of an artifact, product, system, or process that fulfills some functional requirements at some desired level of performance. As such, knowledge of functionality is essential in a wide variety of tasks in engineering activities, including modeling, generation, modification, visualization, explanation, evaluation, diagnosis, and repair of these artifacts and processes. A formal representation of functionality is essential for supporting any of these activities on computers. The goal of Parts 1 and 2 of this Special Issue is to bring together the state of knowledge of representing functionality in engineering applications from both the engineering and the artificial intelligence (AI) research communities.

Advanced Monte Carlo Simulation and Machine Learning for Frequency Domain Optical Coherence Tomography

Optical Coherence Tomography(OCT) is a popular, rapidly growing imaging technique with an increasing number of bio-medical applications due to its noninvasive nature. However, there are three major challenges in understanding and improving an OCT system: (1) Obtaining an OCT image is not easy. It either takes a real medical experiment or requires days of computer simulation. Without much data, it is difficult to study the physical processes underlying OCT imaging of different objects simply because there aren't many imaged objects. (2) Interpretation of an OCT image is also hard. This challenge is more profound than it appears. For instance, it would require a trained expert to tell from an OCT image of human skin whether there is a lesion or not. This is expensive in its own right, but even the expert cannot be sure about the exact size of the lesion or the width of the various skin layers. The take-away message is that analyzing an OCT image even from a high level would usually require a trained expert, and pixel-level interpretation is simply unrealistic. The reason is simple: we have OCT images but not their underlying ground-truth structure, so there is nothing to learn from. (3) The imaging depth of OCT is very limited (millimeter or sub-millimeter on human tissues). While OCT utilizes infrared light for illumination to stay noninvasive, the downside of this is that photons at such long wavelengths can only penetrate a limited depth into the tissue before getting back-scattered. To image a particular region of a tissue, photons first need to reach that region. As a result, OCT signals from deeper regions of the tissue are both weak (since few photons reached there) and distorted (due to multiple scatterings of the contributing photons). This fact alone makes OCT images very hard to interpret.

This thesis addresses the above challenges by successfully developing an advanced Monte Carlo simulation platform which is 10000 times faster than the state-of-the-art simulator in the literature, bringing down the simulation time from 360 hours to a single minute. This powerful simulation tool not only enables us to efficiently generate as many OCT images of objects with arbitrary structure and shape as we want on a common desktop computer, but it also provides us the underlying ground-truth of the simulated images at the same time because we dictate them at the beginning of the simulation. This is one of the key contributions of this thesis. What allows us to build such a powerful simulation tool includes a thorough understanding of the signal formation process, clever implementation of the importance sampling/photon splitting procedure, efficient use of a voxel-based mesh system in determining photon-mesh interception, and a parallel computation of different A-scans that consist a full OCT image, among other programming and mathematical tricks, which will be explained in detail later in the thesis.

Next we aim at the inverse problem: given an OCT image, predict/reconstruct its ground-truth structure on a pixel level. By solving this problem we would be able to interpret an OCT image completely and precisely without the help from a trained expert. It turns out that we can do much better. For simple structures we are able to reconstruct the ground-truth of an OCT image more than 98% correctly, and for more complicated structures (e.g., a multi-layered brain structure) we are looking at 93%. We achieved this through extensive uses of Machine Learning. The success of the Monte Carlo simulation already puts us in a great position by providing us with a great deal of data (effectively unlimited), in the form of (image, truth) pairs. Through a transformation of the high-dimensional response variable, we convert the learning task into a multi-output multi-class classification problem and a multi-output regression problem. We then build a hierarchy architecture of machine learning models (committee of experts) and train different parts of the architecture with specifically designed data sets. In prediction, an unseen OCT image first goes through a classification model to determine its structure (e.g., the number and the types of layers present in the image); then the image is handed to a regression model that is trained specifically for that particular structure to predict the length of the different layers and by doing so reconstruct the ground-truth of the image. We also demonstrate that ideas from Deep Learning can be useful to further improve the performance.

It is worth pointing out that solving the inverse problem automatically improves the imaging depth, since previously the lower half of an OCT image (i.e., greater depth) can be hardly seen but now becomes fully resolved. Interestingly, although OCT signals consisting the lower half of the image are weak, messy, and uninterpretable to human eyes, they still carry enough information which when fed into a well-trained machine learning model spits out precisely the true structure of the object being imaged. This is just another case where Artificial Intelligence (AI) outperforms human. To the best knowledge of the author, this thesis is not only a success but also the first attempt to reconstruct an OCT image at a pixel level. To even give a try on this kind of task, it would require fully annotated OCT images and a lot of them (hundreds or even thousands). This is clearly impossible without a powerful simulation tool like the one developed in this thesis.

Differences and commonalities between connectionism and symbolicism

The differences between connectionism and symbolicism in artificial intelligence (AI) are illustrated on several aspects in details firstly; then after conceptually decision factors of connectionism are proposed, the commonalities between connectionism and symbolicism are tested to make sure, by some quite typical logic mathematics operation examples such as "parity"; At last, neuron structures are expanded by modifying neuron weights and thresholds in artificial neural networks through adopting high dimensional space geometry cognition, which give more overall development space, and embodied further both commonalities.

The use of fault detection and diagnostics to reduce air handling unit energy consumption

The contribution of buildings towards total worldwide energy consumption in developed countries is between 20% and 40%. Heating Ventilation and Air Conditioning (HVAC), and more specifically Air Handling Units (AHUs) energy consumption accounts on average for 40% of a typical medical device manufacturing or pharmaceutical facility’s energy consumption. Studies have indicated that 20 – 30% energy savings are achievable by recommissioning HVAC systems, and more specifically AHU operations, to rectify faulty operation. Automated Fault Detection and Diagnosis (AFDD) is a process concerned with potentially partially or fully automating the commissioning process through the detection of faults. An expert system is a knowledge-based system, which employs Artificial Intelligence (AI) methods to replicate the knowledge of a human subject matter expert, in a particular field, such as engineering, medicine, finance and marketing, to name a few. This thesis details the research and development work undertaken in the development and testing of a new AFDD expert system for AHUs which can be installed in minimal set up time on a large cross section of AHU types in a building management system vendor neutral manner. Both simulated and extensive field testing was undertaken against a widely available and industry known expert set of rules known as the Air Handling Unit Performance Assessment Rules (APAR) (and a later more developed version known as APAR_extended) in order to prove its effectiveness. Specifically, in tests against a dataset of 52 simulated faults, this new AFDD expert system identified all 52 derived issues whereas the APAR ruleset identified just 10. In tests using actual field data from 5 operating AHUs in 4 manufacturing facilities, the newly developed AFDD expert system for AHUs was shown to identify four individual fault case categories that the APAR method did not, as well as showing improvements made in the area of fault diagnosis.

The Jama legal narrative part I: The JAMA Model and narrative interpretation patterns

For the purposes of starting to tackle, within artificial intelligence (AI), the narrative aspects of legal narratives in a criminal evidence perspective, traditional AI models of narrative understanding can arguably supplement extant models of legal narratives from the scholarly literature of law, jury studies, or the semiotics of law. Not only: the literary (or cinematic) models prominent in a given culture impinge, with their poetic conventions, on the way members of the culture make sense of the world. This shows glaringly in the sample narrative from the Continent-the Jama murder, the inquiry, and the public outcry-we analyse in this paper. Apparently in the same racist crime category as the case of Stephen Lawrence's murder (in Greenwich on 22 April 1993) with the ensuing still current controversy in the UK, the Jama case (some 20 years ago) stood apart because of a very unusual element: the eyewitnesses identifying the suspects were a group of football referees and linesmen eating together at a restaurant, and seeing the sleeping man as he was set ablaze in a public park nearby. Professional background as witnesses-cum-factfinders in a mass sport, and public perceptions of their required characteristics, couldn't but feature prominently in the public perception of the case, even more so as the suspects were released by the magistrate conducting the inquiry. There are sides to this case that involve different expected effects in an inquisitorial criminal procedure system from the Continent, where an investigating magistrate leads the inquiry and prepares the prosecution case, as opposed to trial by jury under the Anglo-American adversarial system. In the JAMA prototype, we tried to approach the given case from the coign of vantage of narrative models from AI.