The use of computational methods is fundamental in cancer research. One of the possibilities is the use of Artificial Intelligence techniques. Several of these techniques have been used to analyze expression arrays. However, the new Exon arrays which work with a large amount of data require novel solutions. This paper presents a Case-based reasoning (CBR) system for automatic classification of leukemia patients from Exon array data. The proposed CBR system incorporates novel algorithms for data filtering and classification. The system has been tested and the results obtained are presented in this paper.
Short, less than one second, residence time non-catalytic hydropyrolysis is conducted by rapid heating at more than 600 DEG C. per second of a solid mixture of aldehydo-, carboxy-, keto- and carboxy-, and aldehydo- and carboxy- substituted benzene and toluene and such solid also containing cobalt and/or manganese salts of organic acids and organic and/or inorganic bromides obtained from the manufacture of benzene di- and tricarboxylic acids up to a temperature of at least 700 DEG C. Such short residence hydropyrolysis produces attractive amounts of readily recoverable benzene and toluene as well as lower alkanes and alkenes and a solid carbonaceous char which can be burned to provide heat for the hydropyrolysis. The short residence hydropyrolysis is not subject to short activity and frequent periods of off-stream time as are the catalytic pyrolysis conducted at lower temperatures of from 300 DEG up to 500 DEG C.
An electrical insulator having opposed jaws with at least one of the jaws being adjustable in relation to the other jaw for clamping an electrical conductor therebetween. The jaws are part of plastic pieces which are molded at elevated temperatures and which undergo thermal contraction when cooled subsequent to the molding process. Opposed grooves are provided in the confronting surfaces of the jaws. Liner members consisting of a material different from that of the jaws are received in the grooves. The liner members are sized for ready insertion into the grooves while the interior groove dimensions are expanded as a result of the elevated molding temperatures. The subsequent thermal contraction of the internal groove dimensions during cooling results in the liner members being firmly anchored within the grooves.
The main goal of a Case-Based Reasoning (CBR) system is to provide criteria for evaluating the internal behavior and task efficiency of a particular system for a given initial case base and sequence of a solved problems. The choice of Case Base Maintenance (CBM) strategies is driven by the maintainer's performance goals for the system and by constraints on the system's design and the task environment. This paper gives an overview of CBM works and proposes a case deletion strategy based on a competence criterion using a novel approach. The proposed method combines an algorithm with a Competence Metric (CM). Series of tests are conducted using four standard data-sets as well as a locally constructed one, on which, three case base maintenance approaches will be tested and evaluated by competence and performance criteria. Thereafter competence and performance experimental study shows how this method compares favorably to more traditional methods.
This paper presents how a distributed multi-agent architecture facilitates the integration of services and applications to optimize the performance of a Case-Based Planning mechanism. This mechanism has been modelled as a service and is part of a multi-agent system aimed at enhancing health care for Alzheimer patients in geriatric residences. Several tests have been done to demonstrate that this approach is adequate to build complex systems with distributed functionalities.
A marine wave power plant includes interconnected, swingable, floating basic units with anchoring means. Each unit consists of bearing displacement tubes, a stationary member and a displacement body movably joined thereto and moving with the waves. The wave movements are converted to electrical energy via a hydraulic-electrical system. The rear surface of the movable member is curved with its center of curvature at the journalling axis on the stationary member to avoid pumping between the two members, while a journalling arm is length-adjustable for different wave characteristics. To control the various parameters dependent on incoming waves, a sensor measures the water level in front of the displacement body. The movements of this body, the radian volume of the hydraulic motor and the electrical power output is controlled via a process computer.
In this paper we propose an approach to address the old problem of identifying the feature conditions under which a gaming strategy can be effective. For doing this, we will build on previous work on CBRetaliate, a system that combines case-based reasoning and reinforcement learning to play team-based First Person Shooter Games. In CBRetaliate, cases are pairs (features, Q-table), where the Q-table associates a utility with each state-action pair, which is used to select an appropriate action in a given state. CBRetaliate learns cases as it plays against opponents. We propose to cluster cases in the case-base using a novel definition of similarity between their Q-tables; cases will be grouped in the same cluster if they have similar Q-tables. We propose to use standard information gain formulas and use the clusters as the classification to assign feature weights. We expect that this approach would lead to identifying features that are crucial to select which Q-table to reuse in a given situation. In addition, we propose to use the same notions of Qtable similarity to find substrategies that are common to every or nearly every case in the case base.
In this paper we present ColibriCook: a CBR system for ontology-based cooking recipe retrieval and adaptation. The system’s purpose is to participate in the 1st Computer Cooking Contest, organized by the European Conference on Case-Based Reasoning (ECCBR’08), at the University of Trier, Germany. CBR is based on a best-adaptation likeness paradigm between ingredient sets, with a domain ontology providing one-on-one fuzzy ingredient similarity. A number of other machine learning techniques are used to calculate, propagate, compare and adapt other recipe properties.
This paper presents how the Taaable project addresses the textual case-based reasoning challenge of the CCC, thanks to a combination of principles, methods, and technologies of various fields of knowledge-based system technologies, namely CBR, ontology engineering manual and semi-automatic), data and text-mining using textual resources of the Web, text annotation (used as an indexing technique), knowledge representation, and hierarchical classification. Indeed, to be able to reason on textual cases, indexing them by a formal representation language using a formal vocabulary has proven to be useful.
Biofeedback is a method gaining increased interest and showing good results for a number of physical and psychological problems. Biofeedback training is mostly guided by an experienced clinician and the results largely rely on the clinician's competence. In this paper we propose a three phase computer assisted sensor-based biofeedback decision support system assisting less experienced clinicians, acting as second opinion for experienced clinicians. The three phase CBR framework is deployed to classify a patient, estimate initial parameters and to make recommendations for biofeedback training by retrieving and comparing with previous similar cases in terms of features extracted. The three phases work independently from each other. Moreover, fuzzy techniques are incorporated into our CBR system to better accommodate uncertainty in clinicians reasoning as well as decision analysis. All parts in the proposed framework have been implemented and primarily validated in a prototypical system. The initial result shows how the three phases functioned with CBR technique to assist biofeedback training. Eventually the system enables the clinicians to allow a patient to train himself/herself unsupervised.
In the context of case-based reasoning (CBR) methodology, better understanding of the conditions under which CBR systems are used has the potential to increase our understanding of how uncertainty affects the overall quality of these systems. Our ultimate goal is to determine what properties exist and how these properties may be used to improve the utility of a CBR system, as well as methods of maintenance and evaluation. With this purpose, we start by investigating how properties of case bases can be demonstrated and applied.
The domain of cookery has been of interest for Case-Based Reasoning (CBR) research for many years since the CHEF case-based planning system in the mid 1980s. This paper returns to look at this domain, emphasising a knowledge-light approach. Our approach focuses on; the design of a structured case representation which encapsulates the details of a recipe, on leveraging WordNet for identifying food items and the relationships between them, and on using Active Learning to assist in labelling recipes with meal and cuisine types. Users can search for recipes by specifying the ingredients they wish to include in, or exclude from, the recipe and optionally specifying the type of meal and/or cuisine they are interested in. Recipes are retrieved based on a weighted similarity of the ingredients, the meal and/or cuisine types (if specified) and the textual similarity between the query and specific fields of the recipe text. The system includes substitution adaptation where a recipe can be recommended with a replacement ingredient, where appropriate.
This paper presents a case-based reasoning system applied to the mastery of cooking. JadaCook has been developed to participate in the Computer Cooking Contest to be held at the European Conference on Case Based Reasoning 2008. The system is also the final evaluation assignment for a graduate course in Machine Learning at the Computer Science Faculty (Complutense University of Madrid). In this paper we present a brief review of the technical characteristics of the system, describing the knowledge acquisition and reasoning processes, and some experimental results.
