HomeCoursesPublicationsEventsPresentationsContactProjectsLinks|
Publications
Updated list of Publications Edited volumes
Dissertation & Thesis
Journal
Journal articles, conference and refereed workshop papers by yearPublications in the areas of Knowledge management, Lessons-learned systems, Case-based reasoning and Textual case-based reasoning; Soft CBR (Fuzzy Set Theory); Artificial Intelligence Research and Applications in the areas of Law, Nutrition, Medicine, Software Engineering, Corporate Finance, and Fuzzy Decision Making2006
Weber, R.O. (2006).
Fuzzy Set Theory and Uncertainty in Case-Based Reasoning.
Engineering Intelligent Systems. To appear.
Abstract:
Case-based reasoning (CBR) is a reasoning methodology that relies on previous experiences, making it well suited to various real world application domains. When we use CBR to solve real world problems, its inherent uncertainty tends to propagate and may be detrimental to the system's quality. Consequently, the quality of a CBR system's outcome tends to increase as we address its uncertainty. This article examines approaches based on fuzzy set theory that manage the uncertainty originated in CBR systems and describes in detail a method based to address the uncertainty originated in the CBR assumption that similar problems have similar solutions.
Weber, R.O., Ashley, K., Bruninghaus, S. (2006)
Textual Case-based reasoning.
Knowledge Engineering Review, Special Issue: Readings on Case-based reasoning. To appear.
Althoff, K. D. and Weber, R.O. (2006).
Knowledge Management in Case-Based Reasoning.
Knowledge Engineering Review, Special Issue: Readings on Case-based reasoning. To appear.
Cheetham, W., Shiu, S. and Weber, R.O. (2006).
Soft Case-Based Reasoning.
Knowledge Engineering Review, Special Issue: Readings on Case-based reasoning. To appear.
Fowler, Caleb and Weber, Rosina (2006).
Information technology incorporating emotion in dialogues.
Accepted for the i-Society 2006 conference in Miami, Florida, USA.
2005
Rosina Weber, Jason M. Proctor, Ilya Waldstein, Andres Kriete. (2005)
CBR for Modeling Complex Systems.
Accepted for oral presentation to the Sixth International Conference on Case-Based Reasoning. To be published in Munoz, H. and Ricci, F. (eds.) Lecture Notes in Artificial Intelligence. Springer, Berlin.
Abstract:
This paper describes how CBR can be used to compare, reuse, and adapt inductive models that represent complex systems. Complex systems are not well understood and therefore require models for their manipulation and understanding. We propose an approach to address the challenges for using CBR in this context, which relate to finding similar inductive models (solutions) to represent similar complex systems (problems). The purpose is to improve the modeling task by considering the quality of different models to represent a system based on the similarity to a system that was successfully modeled. The revised and confirmed suitability of a model can become additional evidence of similarity between two complex systems, resulting in an increased understanding of a domain. This use of CBR supports tasks (e.g., diagnosis, prediction) that inductive or mathematical models alone cannot perform. We validate our approach by modeling software systems, and illustrate its potential significance for biological systems.
Jason M. Proctor, Rosina Weber (2005)
Systematically Evolving Configuration Parameters for Computational Intelligence Methods.
In S.K. Pal et al. (Eds.): PReMI 2005, LNCS 3776, pp. 376-381, 2005. Springer-Verlag, Berlin Heidelberg.
Abstract:
The configuration of a computational intelligence (CI) method is
responsible for its intelligence (e.g. tolerance, flexibility) as well as its
accuracy. In this paper, we investigate how to automatically improve the
performance of a CI method by finding alternate configuration parameter values
that produce more accurate results. We explore this by using a genetic
algorithm (GA) to find suitable configurations for the CI methods in an
integrated CI system, given several different input data sets. This paper
describes the implementation and validation of our approach in the domain of
software testing, but ultimately we believe it can be applied in many situations
where a CI method must produce accurate results for a wide variety of
problems.
Maria Cleci Martins and Rosina Weber (2005).
Modeling Preferences Online.
Accepted for oral presentation to the 1st International Conference on Web Information Systems and Technologies.
Abstract:
The search for an online product that matches e-shoppers' needs and preferences can be frustrating and time-consuming. Browsing large lists arranged in tree-like structures demands focused attention from e-shoppers. Keyword search often results in either too many useless items (low precision) or few or none useful ones (low recall). This can cause potential buyers to seek another seller or choose to go in person to a store. This paper introduces the SPOT (Stated Preference Ontology Targeted) methodology to model e-shoppers' decision-making processes and use them to refine a search and show products and services that meet their preferences. SPOT combines probabilistic theory on discrete choices, the theory of stated preferences, and knowledge modeling (i.e. ontologies). The probabilistic theory on discrete choices coupled with e-shoppers' stated preferences data allow us to unveil parameters e-shoppers would employ to reach a decision of choice related to a given product or service. Those parameters are used to rebuild the decision process and evaluate alternatives to select candidate products that are more likely to match e-shoppers' choices. We use a synthetic example to demonstrate how our approach distinguishes from currently used methods for e-commerce.
Weber, R.; Waldstein, I.; Deshpande, A.; Proctor, J. M. (2005).
Integrated Approach to Detect Inconspicuous Contents. IIn Klaus-Dieter Althoff, Andreas Dengel, Ralph Bergmann, Markus Nick and Thomas Roth-Berghofer (Eds.): WM2005, Professional Knowledge Management (LNAI 3782) pp. 304 - 315. Springer-Verlag, Berlin Heidelberg.
Abstract:
This paper describes an integrated approach for detecting
inconspicuous contents in text. Inconspicuous contents can be an opinion or
goal that may be disguised in some way to mislead automated methods but
keeps a clear message for humans (e.g., terrorist sites). Our methodology
hypothesizes that patterns that convey inconspicuous contents can be extracted,
represented, generalized, and matched in unknown text. The proposed approach
is meant to complement data-intensive methods (e.g. clustering). Data-intensive
methods are fast but are susceptible to variations in frequency, do not discern
meaning, and require a large corpus for training. Our approach relies on manual
engineering for natural language interpretation and pattern extraction using no
more than ten examples, but is sufficiently fast to complement a real-time
application.
Proctor, J., Waldstein, I. & Weber, R. 2005
Identifying Facts for TCBR
In Weber, R. & Branting, L. K. eds. Proceedings of the Textual Case-Based Reasoning Workshop, Chicago, IL, pp. 150-159.
Abstract:
This paper explores a method to algorithmically distinguish case-specific
facts from potentially reusable or adaptable elements of cases in a textual case-based
reasoning (TCBR) system. In the legal domain, documents often contain casespecific
facts mixed with case-neutral details of law, precedent, conclusions the
attorneys reach by applying their interpretation of the law to the case facts, and other
aspects of argumentation that attorneys could potentially apply to similar situations.
The automated distinction of these two categories, namely facts and other elements,
has the potential to improve quality of automated textual case acquisition. The goal
is ultimately to distinguish case problem from solution. To separate fact from other
elements, we use an information gain (IG) algorithm to identify words that serve as
efficient markers of one or the other. We demonstrate that this technique can
successfully distinguish case-specific fact paragraphs from others, and propose
future work to overcome some of the limitations of this pilot project.
Weber, Rosina; Waldstein, Ilya; Deshpande, Amit; Proctor, Jason M. (2005).
Integrated Approach to Detect Inconspicuous Content. In Althoff, KD et al. (eds.) WM2005: Professional Knowledge Management Experiences and Visions.Deutches Forschungszentrum fur Kunstliche Intelligenz DFKI GmbH, Kaiserslautern (281-286).
Abstract:
This paper describes a methodology for detecting inconspicuous content in text. Inconspicuous content may be an intent, opinion, or goal that may be disguised in some way to mislead automated methods but keeps a clear message for humans (e.g., terrorist sites). This methodology hypothesizes that patterns that convey inconspicuous content can be extracted, represented, generalized, and matched in unknown text. Our approach combines information extraction, case-based reasoning, and computational linguistics and is meant to complement methods based on term-frequencies. Statistical methods are fast but are susceptible to variations in frequency, do not discern meaning, and require a large corpus for training. Our approach relies on manual engineering for natural language interpretation and pattern extraction using no more than ten examples, but is sufficiently fast to complement a real-time application.
2004
Cunningham, Colleen; Weber, Rosina; Proctor, Jason M.; Fowler, Caleb; Murphy, Michael (2004).
Investigating Graphs in Textual Case-Based Reasoning..
In Funk, Peter; González Calero, Pedro A. (Eds.), Advanced in Case-Based Reasoning, 573-587. (Lecture Notes in Artificial Intelligence, Vol. 3155) Berlin, Springer-Verlag.
A poster about this work presented by Colleen Cunningham received an Honorable Mention at 2004 Drexel Research Day.
Allendoerfer, Kenneth R. and Weber, Rosina (2004).
PlayMaker: An Application of Case-Based Reasoning to Air Traffic Control Plays. .
In P. A. Gonzalez Calero and P. Funk (Eds.), Case-Based Reasoning Research and Development (LNAI): Springer-Verlag. (7th European Conference in Case-Based Reasoning: 30th August through 2nd September 2004, Madrid, Spain).
A poster about this work presented by Ken Allendoefer won the category of emerging technologies at 2005 Drexel Research Day.
Wu, D. Weber, R., Abramson, F. (2004).
A Case-Based Framework for Leveraging NutriGenomics
Knowledge and Personal Nutrition Counseling. . CASE-BASED REASONING
in Health Sciences Workshop. 7th European Conference in Case-Based Reasoning:
30th August through 2nd September 2004, Madrid, Spain.
Abstract:NutriGenomics is the bioscience that links the way nutrients and other dietary
components shape genetic activity. It builds on the success of Human Genome Project by applying
systems biology methods to explain how the molecular components of food, supplements and pharmaceuticals
dynamically influence and shape the activity of genomic subsystems, which in turn define how a person
can stay healthy or become ill. Applying NutriGenomics knowledge is done through Directive Genomics,
which develops purposeful dietary strategies that influence gene expression at the individual level
with the goal of better ge-netic function and health. This paper proposes a case-based framework for leveraging nutrigenomics knowledge and Directive Genomics applications. The unique features of the proposed system include a self-maintained distributed case base structure and a CBR-based nutrition counseling module that can learn, adapt, and maintain its case base via the integrated distributed case bases as well as external resources.
Weber, R., Evanco, W., Waller, M., Verner, J. (2004).
Identifying Critical Factors in Case-Based Prediction..
In Valerie Barr and Zdravko Markov (eds.) Proceedings of the Seventeenth Annual Conference of the
International Florida Artificial Intelligence Research Society, 207-212. Menlo Park,
CA: AAAI Press.
Abstract:
A reversible outcome is one that can be changed. For example, the failure of an ongoing project may be avoided
if certain actions are taken, while an outcome such as the path of a hurricane cannot be changed under current
knowledge. The major benefit of predicting reversible outcomes resides in the possibility to avoid unwanted
results. For this purpose, it is necessary to identify contributing factors responsible for the outcome, which
once modified, can steer the result to a desired outcome. Consequently, the incorporation of a method into
a case-based reasoning system to identify contributing factors affecting an outcome can improve its usefulness.
This paper compares different approaches, particularly the use of domain knowledge, with respect to their ability to identify sets of factors that reverse software development projects predicted to fail into a prediction of success.
Weber, R., Wu, D. (2004).
Knowledge Management for Computational Intelligence Systems..
Eighth IEEE International Symposium on High Assurance Systems Engineering (HASE 2004), 116-125. IEEE Computer Society: :Los Alamitos, CA.
Abstract:
Computer systems do not learn from previous experiences unless they are designed for this purpose. Computational intelligence systems (CIS) are inherently capable of dealing with imprecise contexts, creating a new solution in each new execution. Therefore, every execution of a CIS is valuable to be learned. We describe an architecture for designing CIS that includes a knowledge management (KM) framework, allowing the system to learn from its own experiences, and those learned in external contexts. This framework makes the system flexible and adaptable so it evolves, guaranteeing high levels of reliability when performing in a dynamic world. This KM framework is being incorporated into the computational intelligence tool for software testing at National Institute for Systems Test and Productivity. This paper introduces the framework describing the two underlying methodologies it uses, i.e. case-based reasoning and monitored distribution; it also details the motivation and requirements for incorporating the framework into CIS.
2003
Weber, R. & Kaplan, R. (2003).
Knowledge-based knowledge management.
In Innovations in Knowledge Engineering, Editors: Ravi Jain, Ajith Abraham, Colette Faucher and Berend
Jan van der Zwaag. International Series on Advanced Intelligence, Volume 4. July 2003. Advanced Knowledge
International Pty Ltd.
Abstract:
Knowledge-based knowledge management (KBKM) focuses on applications of knowledge-based systems (KBS) tailored to knowledge management (KM) problems. KM practitioners and research scientists have been implementing various frameworks to address pragmatic KM problems reusing decades of technology developed for knowledge-based systems. Therefore, when we talk about knowledge-based knowledge management, we talk about the overlap of knowledge-based systems and knowledge management.
Weber, R., Waller, M., Verner, J., Evanco, B. (2003).
Predicting Software Development Project Outcomes
In D. Bridge and K. Ashley (eds.) Case-Based Reasoning Research and Development. LNAI 2689, 595-609.
Berlin Heidelberg:Springer-Verlag. .
Abstract:
Case-based reasoning is a flexible methodology to manage software
development related tasks. However, when the reasoner’s task is prediction,
there are a number of different CBR techniques that could be chosen to address
the characteristics of a dataset. We examine several of these techniques to
assess their accuracy in predicting software development project outcomes (i.e.,
whether the project is a success or failure) and identify critical success factors
within our data. We collected the data from software developers who answered
a questionnaire targeting a software development project they had recently
worked on. The questionnaire addresses both technical and managerial features
of software development projects. The results of these evaluations are compared
with results from logistic regression analysis, which serves as a comparative
baseline. The research in this paper can guide design decisions in future CBR
implementations to predict the outcome of projects described with managerial
factors.
Weber, R. & Aha, D.W. (2003).
Intelligent delivery of
military lessons learned. Decision support systems 34, 3, Feb. 287-304.
Abstract:
Lessons learned systems are a common knowledge management initiative among the American
government (e.g., Department of Defense, Department of Energy, NASA). An effective lessons learned
process can substantially improve decision processes, thus representing an essential chapter
in a knowledge sharing digital government. Unfortunately, these systems typically fail to deliver lessons when and where they are needed. In this paper, we introduce, describe, and empirically evaluate the monitored distribution approach for the active delivery of lessons learned. Our results show that this just-in-time information delivery approach, embedded in a decision support system for plan authoring, significantly improved plan execution performance measures.
Weber, R. (2003).
Proactive Knowledge Distribution for Agile Processes
1st Workshop on Knowledge Management for Distributed Agile Processes: Models, Techniques, and Infrastructure in the IEEE
International Workshops on Enabling Technologies: Infrastructure for Collaborative
Enterprises (WETICE-2003)
Abstract:
Monitored distribution (MD) is a case-based approach for proactive knowledge distribution. MD allows the dissemination of knowledge artifacts in a just-in-time fashion in the context of its applicable targeted processes. In MD, knowledge artifacts are retrieved when they are applicable to the task in which a user is currently engaged. We define MD's requirements and argue that it can be applied to agile processes because the targeted processes are collected as an attribute of knowledge artifacts.
2002
Weber, R. & Aha, D.W. (2002).
Intelligent Elicitation of Military Lessons. In
Proceedings of the Sixth International Conference on Intelligent User Interfaces, San Francisco,
CA, January 14-17, 2002.
Abstract:
We introduce LET (Lesson Elicitation Tool), which uses domain and linguistic knowledge to guide users during their submission of lessons learned. LET can detect a user's need for instructions and disambiguates expressions while collecting taxonomic domain knowledge.
2001
Aha, D.W., Weber, R., Muñoz, H., Breslow, L.A. & Gupta, K. (2001).
Bridging the Lesson Distribution Gap. Proceedings of
IJCAI'01 (Seattle, WA, Aug 2001), Morgan Kaufmann Publishers, Inc., 987-992.
Abstract:
Many organizations employ lessons learned (LL) processes to collect,
analyze, store, and distribute, validated experiential knowledge (lessons)
of their members that, when reused, can substantially improve organizational
decision processes. Unfortunately, deployed LL systems do not facilitate
lesson reuse and fail to bring lessons to the attention of the users when
and where they are needed and applicable (i.e., they fail to bridge the
lesson distribution gap). Our approach for solving this problem, named
monitored distribution, tightly integrates lesson distribution with these
decision processes. We describe a case-based implementation of monitored
distribution (ALDS) in a plan authoring tool suite (HICAP). We evaluate
its utility in a simulated military planning domain. Our results show that
monitored distribution can significantly improve plan evaluation measures
for this domain.
Weber, R., Aha, D.W., & Becerra-Fernandez, I. (2001).
Intelligent lessons learned systems. Expert Systems with Applications, Vol. 20, No. 1., 17-34.
Abstract:
Lessons learned processes have been deployed in commercial, government, and military organizations since the late 1980s to capture, store, disseminate, and share experiential working knowledge. However, recent studies have shown that software systems for supporting lesson dissemination do not effectively promote knowledge sharing. We found that the problems with these systems are related to their textual representation for lessons and that they are not incorporated into the processes they are intended to support. In this article, we survey lessons learned processes and systems, detail their capabilities and
limitations, examine lessons learned system design issues, and identify how artificial intelligence technologies can contribute to knowledge management solutions for these systems.
Download a preliminary work that categorizes lessons learned systems.
Weber, R., Aha, D.W., Sandhu, N., & Muñoz-Avila, H. (2001).
A Textual Case-Based Reasoning Framework for Knowledge Management Applications.
Professionelles Wissenmanagement Erfahrungen und Visionen. Knowledge Management
by Case-Based Reasoning: Experience Management as Reuse of Knowledge, 244-253.
Aachen:Shaker Verlag.
Abstract:
Abstract. Knowledge management (KM) systems manipulate organizational
knowledge by storing and redistributing corporate memories that are
acquired from the organization's members. In this paper, we introduce
a textual case-based reasoning (TCBR) framework for KM systems that
manipulates organizational knowledge embedded in artifacts (e.g., best
practices, alerts, lessons learned). The TCBR approach acquires
knowledge from human users (via knowledge elicitation) and from text
documents (via knowledge extraction) using template-based information
extraction methods, a subset of natural language, and a domain ontology.
Organizational knowledge is stored in a case base and is distributed
in the context of targeted processes (i.e., within external distribution
systems). The knowledge artifacts in the case base have to be translated
into the format of the external distribution systems. A domain ontology
supports knowledge elicitation and extraction, storage of knowledge
artifacts in a case base, and artifact translation.
Weber, R., Breslow, L., Sandhu, N. (2001). On the Technological,
Human, and Managerial Issues in Sharing Organizational Lessons. In
Proceedings of the Fourteenth Annual Conference of the International
Florida Artificial Intelligence Research Society, 334-338.
Menlo Park, CA: AAAI Press.
Abstract:
Lessons learned systems (LLS) are systems that support a lessons
learned process (LLP) to collect, verify, store, disseminate, and
reuse organizational lessons. In this paper we examine technological,
human, and managerial problems that contribute to the limited reuse of
lessons in deployed LLS. This analysis results in the identification
of a set of requirements that when met tend to improve the reuse of
lessons. These requirements are mainly related to the identification
and representation of a lesson's reuse components, i.e., what in a
lesson is essential to promote reuse. We present and demonstrate a
standardized format for lessons and a lesson elicitation tool (LET)
that uses this format to collect lessons from human users and
addresses some of the requirements while contributing to the
satisfaction of other requirements. This tool illustrates how
technological solutions can impact human and managerial problems.
2000
Weber, R., Aha, D.W., Branting, L.K., Lucas, J.R., & Becerra-Fernandez,
I. (2000). Active case-based reasoning for lessons delivery systems. In
Proceedings of the Thirteenth Annual Conference of the International Florida
Artificial Intelligence Research Society, 170-174. Menlo Park, FL: AAAI Press.
Abstract:
Exploiting lessons learned is a key knowledge management (KM) task. Currently, most lessons learned systems
are passive, stand-alone systems. In contrast, practical KM solutions should be active, interjecting relevant
information during decision-making. We introduce an architecture for active lessons delivery systems,
an instantiation of it that serves as a monitor, and illustrate it in the context of the conversational
case-based plan authoring system HICAP (Muñoz-Avila et al., 1999). When users interact with HICAP, updating
its domain objects, this monitor accesses a repository of lessons learned and alerts the user to the
ramifications of the most relevant past experiences. We demonstrate this in the context of planning
noncombatant evacuation operations.
Weber, R., Aha, D.W., Munoz, H., & Breslow, L.A. (2000). An intelligent
lessons learned process. Z.W. Rás & S. Ohsuga (Eds.):ISMIS,
LNAI 1932, pp. 358-367. Berlin Heidelberg:Springer-Verlag.
Abstract:
A learned lesson, in the context of a pre-defined organizational process, summarizes an experience that should be used to modify that process, under the conditions for which that lesson applies. To promote lesson reuse, many organizations employ lessons learned processes, which define how to collect, validate, store, and disseminate lessons among their personnel, typically by using a standalone retrieval tool. However, these processes are problematic: they do not address lesson reuse effectively. We demonstrate how reuse can be facilitated through a representation that highlights reuse conditions (and other features) in the context of lessons learned systems embedded in targeted decision-making processes. We describe a case-based reasoning implementation of this concept for a decision support tool and detail an example.
This paper introduces an indexing structure for 'military' lessons and illustrates
lessons in the context of NEOs.
Weber, R., Aha, D.W., Munoz, H., & Breslow, L.A. (2000). Active
Delivery for Lessons Learned Systems. In E. Blanzieri and L. portinale (Eds.) Advances in Case-Based Reasoning, pp. 322-334., 5th European Workshop, EWCBR2K.
Trento, Italy:Springer-Verlag.
Abstract:Lessons learned processes, and software systems that support them, have been developed by many organizations (e.g., all USA military branches, NASA, several Department of Energy organizations, the Construction Industry Institute). Their purpose is to promote the dissemination of knowledge gained from the experiences of an organization's employees. Unfortunately, lessons learned systems are usually ineffective because they invariably introduce new processes when, instead, they should be embedded into the processes that they are meant to improve. We developed an embedded case-based approach for lesson dissemination and reuse that brings lessons to the attention of users rather than requiring them to fetch lessons from a standalone software tool. We demonstrate this active lessons delivery architecture in the context of HICAP, a decision support tool for plan authoring. We also show the potential of active lessons delivery to increase plan quality for a new travel domain.
Weber, R., Aha, D.W., & Becerra-Fernandez, I. (2000). Categorizing
Intelligent Lessons Learned Systems. In D.W.Aha & R. Weber (Eds.) (2000).
Intelligent Lessons Learned Systems: Papers
from the AAAI 2000 Workshop , 63-67. (Technical Report WS-00-008).
Menlo Park, CA:AAAI Press.
Abstract:
Lessons learned systems are knowledge management
solutions that serve the purpose of capturing, storing,
disseminating and sharing an organization’s verified
lessons. In this paper we propose a two-step categorization
method to support the design of intelligent lessons learned
systems. The first step refers to the categories of the lessons
learned processes the system is designed to support. The
second step refers to the categories of the system itself.
These categories are based on systems available online and
described in the literature. We conclude by summarizing
representational and other important issues that need to be
addressed when designing intelligent lessons learned
systems.
1999
Weber, R. 1999. Intelligent jurisprudence research. In Proceedings of
the Seventh International Conference on Artificial Intelligence and Law
(ICAIL-99), 164-172. Oslo, Norway: ACM.
Abstract:
Intelligent Jurisprudence Research (IJR) is a concept that
consists in performing jurisprudence research with a
computational tool that employs Artificial Intelligence
(AI) techniques. Jurisprudence research is the search
employed by judicial professionals when seeking for past
legal situations that may be useful to a legal activity.
When humans perform jurisprudence research, they
employ analogical reasoning in comparing a given actual
situation with past decisions, noting the affinities between
them. In the process of remembering a similar situation
when faced to a new one, Case-Based Reasoning (CBR)
systems simulate analogical reasoning. Therefore, CBR is
an appropriate technology to deal with the chosen
problem.
The, M. Alice L.; Bell, R.C.; Camargo, K. G.; Weber, R.; Martins, A.;
Barcia, R. (1999). Case-Based Reasoning for Nutritional Consulting. The
FASEB Journal: A Multidisciplinary Resource for the Life Sciences Experimental
Biology, v. 13, n. 4. Washington, D.C., USA. April, 1999. 465.17.
1998
Weber, R., Martins, A., and Barcia, R. (1998). On legal texts and cases.
In M. Lenz and K. Ashley eds. Textual Case-Based Reasoning: Papers from
the AAAI-98 Workshop, 40-50. Technical Report, WS-98-12. Menlo Park, CA:
AAAI Press.
Weber, R. (1998) Intelligent Jurisprudence Research. Doctoral dissertation,
Department of Production Engineering, Federal University of Santa Catarina,
Brazil. Download here.
Weber, R.; Martins, A.; Mattos, E.; Bueno, T.; Hoeschl, H.; Pacheco,
R.; Barcia, R. (1998). Reusing Cases to the Automatic Index Assignment
from Textual Documents. 6th German Workshop on Case-Based Reasoning - Foundations,
Systems, and Applications. Berlin, March 6-8, 1998.
Abstract:
This paper describes one solution developed to convert textual documents
into formlike representations of cases. The experiences described by cases are textual
descriptions of legal decisions. Indexing vocabulary and assignment theory contributed
in gathering expert knowledge to define attributes and values as well as the required
elements to employ template mining. Most index values are automatically extracted by
the use of template mining. The multi-purpose index Theme is automatically assigned
by reusing cases through an elaboration process. Seed cases are used to indicate values
if the new case is a partial match to one in the case base.
Heinisch, R.; Weber, R.; Martins, A.; Barcia, R. (1998) Representing
Medical Decision Making Strategies in a CBR System. 6th German Workshop
on Case-Based Reasoning - Foundations, Systems, and Applications. Berlin,
March 6-8, 1998.
Abstract:
This paper describes and compares the development of two
organizational structures to represent medical decision making strategies. We
generate the solution to a new problem by applying a previous solution from a
medical record in a CBR system that performs decision-making about hypertension
drug therapy. The case libraries are structured in accordance with the approaches of
flat memory and discrimination network. Cases are originated by a retrospective
knowledge acquisition about 47 patients who underwent ambulatory care of a
university hospital. The similarity-based retrieval employed in the flat structure
resembles what physicians do when handling their routine cases of arterial
hypertension. Physicians identify a similar case in memory by recognizing the
content embedded in the new situation, like a script. The hypothetico-deductive
method for searching the case solution follows a similar strategy to the one
represented in the prioritized discrimination network. The inclusion of cases in the
case library of the discrimination network required more complex procedures than in
the case library of the flat memory. These two decision support systems could
contribute significantly to patient care. The system we are researching on has
educational purposes as well.
Wangenheim, C.; Ramos, A.; Althoff, K. D.; Weber, R.; Martins, A.; Barcia,
R. (1998) Case-Based Reasoning Approach to Reuse of Experiential Knowledge
in Software Measurement Programs. 6th German Workshop on Case-Based Reasoning
- Foundations, Systems, and Applications. Berlin, March 6-8, 1998.
Abstract:
For the successful application of innovative software engineering technologies in industry, the
technologies have to evolve incrementally based on continuous feedback from practice.
Experiences about their practical application have to be systematically collected and stored in
corporate memories and reused in future software projects. This promotes the sharing of
experiences across individuals and projects, the formulation of best practices and facilitates the
successful application of tailored technologies in practice. This paper presents a case-based
reasoning approach for capturing and reusing experiential knowledge on software measurement
programs in industry. A representation structure for experiential measurement knowledge is
described in detail and knowledge retrieval and acquisition techniques are presented..
Camargo, K.; Thé, M. A.; Weber, R.; Martins, A.; Barcia, R. (1998) Designing Nutritional Programs with Case-Based Reasoning. 6th German Workshop on Case-Based Reasoning
- Foundations, Systems, and Applications, 141-147. Berlin, March 6-8, 1998.
Abstract:
This paper describes a system aimed at prescribing nutritional
programs using Case-Based Reasoning (CBR). A nutritional program is a
balanced dietetic plan aimed at better health conditions of the individuals. The
nutritional task refers to prescribing a nutritional program as a therapy for a given
nutritional disorder, in accordance to the patient’s characteristics that act as
constraints, functions and goals. The main reason to use a case-based reasoning
system in designing nutritional programs lies in the nature of the nutritional expert
task, which is carried out by reusing past experiences. Nutritional professionals
usually express their knowledge with generalizations, even when pointing specific
instances as examples. This has motivated us to model the starting case base with
a prototypical memory. Our approach to perform the nutritional task in a casebased
reasoning system can be viewed as a two-fold process. First, the
characteristics, symptoms, goals and restrictions are used to classify the new
patient in a group associated to a diagnostic category. Second, the hypothetical
case corresponding to the category that classifies the new case provides the design
that represents the solution to be adapted to solve the new case. The system we
are describing contemplates the nutritional task from the collection of patient's
characteristics performing the diagnosis task implicitly, and prescribing the
nutritional program (meal plan) to treat the respective nutritional disorder..
1997
Weber-Lee, R.; Barcia, R.; Costa, M.; Rodrigues Filho, I.; Hoeschl,
H.; Bueno, T.; Martins, A.; Pacheco, R. (1997). A Large Case-Based Reasoner
for Legal Cases. In Proceedings of the Second International Conference
on Case Based Reasoning, 190-199. David Leake, Enric Plaza (eds.), Providence,
RI, Berlin: Springer.
Abstract:
In this paper we propose a large case-based reasoner for the legal domain.
Analyzing legal texts for indexing purposes makes the implementation of large case
bases a complex task. We present a methodology to automatically convert legal texts
into legal cases guided by domain expert knowledge in a rule-based system with
Natural Language Processing (NLP) techniques. This methodology can be generalized
to be applied in different domains making Case-Based Reasoning (CBR) paradigm a
powerful technology to solve real world problems with large knowledge sources.
Weber-Lee, R.; Barcia, R.; Pacheco, R.; Martins, A.; Hoeschl, Hugo;
Bueno, Tania; Costa, Marcio; Rodrigues Filho, Ilson. (1997). Representing
Cases From Texts in Case-Based Reasoning. III Congresso Internacional de
Engenharia Industrial e XVII ENEGEP, 6 a 9 de Outubro de 1997, Canela,
RS, Brasil.
1996
Weber-Lee, R.; Pacheco, R.; Martins, A.; Barcia, R. (1996). Using
Typicality Theory to Select the Best Match. Ian Smith; Boi Faltings (eds.)
Advances in Case-Based Reasoning (LNAI 1168), pp. 445-459. Berlin: Springer.
Abstract:
This paper focuses on the problem of choosing the best match among a set of retrieved cases. The Select step is subtask of case retrieval that produces the case that suggests the solution for the input case. There are many different ways to accomplish this task and we propose an automatic means for it. Following the original motivation of paralleling the human similarity heuristic we argue that the selection of the best match is performed by humans choosing the solution that best represents the set of candidate solutions retrieved. The solution that best represent a given data set is the "most typical" solution. Therefore, we describe an application in a Case-Based Reasoning system using the Theory of Typicality to calculate the Most Typical Value of a given set to automatically perform the Select task. An example illustrates the application.
Weber-Lee, R.; Martins, A.; Pacheco, R.; Barcia, R.. (1996). Design of Fuzzy Cash Flows Applying Most Typical Values to a Case-Based Reasoner Outcome. Third Congress of the International Association for Fuzzy-Set
Management and Economics, November 11-13, Buenos Aires, Argentina, 1996.
Weber-Lee, R.; Martins, A.; Pacheco, R.; Barcia, R.. (1996). The Integration
of an Expert System and a Case-Based Reasoner in the Financial Environment.
2nd International Congress of Industrial Engineering and 16th National
Congress of Production Engineering- ENEGEP , October, 7 - 10, Piracicaba,
São Paulo, Brasil, 1996.
1995
Weber-Lee, R.; Barcia, R.; Khator, Suresh. (1995). Case-Based Reasoning
for Cash Flow Forecasting using Fuzzy Retrieval. In Proceedings of the
First International Conference on Case-Based Reasoning, 510-519.
Manuela Veloso & Agnar Aamodt (eds.), Sesimbra, Portugal:Springer.
Abstract:
Case-Based Reasoning (CBR) simulates human way of solving problems as it solves a new problem using a successful past experience applied to a similar problem. In this paper we describe a CBR system that performs forecasts for cash flow accounts. Forecasting cash flows to a certain degree of accuracy, is an important aspect of a Working Capital decision support system. Working Capital (WC) management decisions reflect a choice among different options on how to arrange the cash flow. The decision establishes an actual event in the cash flow and that means that one needs to envision the consequences of such a decision. Hence, forecasting cash flows accurately can minimize losses caused by usually unpredictable events. Cash flows are usually forecasted by a combination of different techniques enhanced by human experts' feelings about the future, which are grounded in past experience. That is what makes the use of the CBR paradigm the proper choice. Advantages of a CBR system over other Artificial Intelligence techniques are associated to knowledge acquisition, knowledge representation, reuse, updating and justification. An important step in developing a CBR system is the retrieval of similar cases. The proposed system makes use of fuzzy integrals to calculate the synthetic evaluations of similarities between cases instead of the usual weighted mean.
Weber-Lee, R.; Barcia, R.; Gauthier, F.; Tcholakian, A. (1995). Sistema
Experto Difuso para Analisis de Credito. Información Tecnológica,
6, 6, 65-70.
Abstract:
El Sistema Experto (SE) aquí presentado fue desarrollado para análisis de crédito. El proceso de desarrollo del prototipo (adquisición y representación del conocimiento, estructura del motor de inferencia, etc.) es presentado y discutido. La adquisición del conocimiento fue hecha através de entrevistas estructuradas realizadas con los expertos de la institución financiera. El prototipo utiliza una forma híbrida de representación del conocimiento, combinando reglas de produción y "frames". El sistema usa el conocimiento de los expertos, incluido en las reglas, para llegar a una conclusión sobre los hechos referentes a los clientes representados por "frames". La manipulación del conocimiento sigue el comportamiento y raciocinio de los expertos entrevistados.
Weber-Lee, R.; Viali, L.; Pacheco, R.; Martins, A.; Barcia, R.; Khator,
S. (1995). Object Oriented Analysis and Programming for a Working Capital
Management System. CIFEr IEEE/IAFE Computational Intelligence on Financial
Engineering, Manhattan, New York City, 9 a 11 de abril, 1995.
Abstract:
The main purpose of this paper is to present an Object Oriented Analysis (OOA) of a firm and its accounting and financial environments for the implementation of a working capital management system. The object oriented analysis has been designed so that it can be (re)used by different types and sizes of companies, (e.g., industrial, commercial or service). This versatility is a consequence of an important feature of the object oriented paradigm: the reusability of code. This OOA includes firm's regular operations as well as tools and reports used in the management of working capital such as cash flows and estimated balance sheets. In order to demonstrate the functionality of the OOA, we discuss parts of the analysis that we have implemented successfully in the C++ object oriented programming language.
1993
Weber, R.; Gauthier, Fernando; Barcia, R.. (1993) Expert System for
Credit Analysis: a Prototype. XIII National Meeting of Industrial Engineering
and I Latin American Congress of Industrial Engineering. Brazil, October,
1993.
Weber, R. (1993) Sistema Especialista Difuso para Analise de Credito (Fuzzy Expert System for Credit Analysis. Master's thesis,
Department of Production Engineering, Federal University of Santa Catarina,
Brazil. In Portuguese.
|
