Case-Based Reasoning

Nearest-neighbor missing visuals revealed


The unsupervised K- Nearest Neighbour (KNN) algorithm is perhaps the most straightforward machine learning algorithm. However, a simple algorithm does not mean that analyzing the results is equally simple. As per my research, there are not many documented approaches to analyzing the results of the KNN algorithm. In this article, I will show you how to analyze and understand the results of the unsupervised KNN algorithm. I will be using a dataset on cars.

The Historical Case for a Gay Bridgerton


It's simple math, really: In a family with eight children, it stands to reason, surely one of them must be queer. Bridgerton has defied other expectations of a Regency-era love story: It is set in an alternate universe where the upper class is fully integrated and race is not an issue. The show's first two seasons focus on interracial romances, and the second season at least obliquely references the history of British colonialism in India. There's one obvious candidate for such a storyline: On the show, Eloise is the most outspoken, most feminist Bridgerton sibling. She is not interested in becoming a debutante, delaying her appearance to pursue another year of studies. She often dismisses marriage, questioning why a husband and children are all that are waiting in store for women.

Case-based reasoning for rare events prediction on strategic sites Machine Learning

Satellite imagery is now widely used in the defense sector for monitoring locations of interest. Although the increasing amount of data enables pattern identification and therefore prediction, carrying this task manually is hardly feasible. We hereby propose a cased-based reasoning approach for automatic prediction of rare events on strategic sites. This method allows direct incorporation of expert knowledge, and is adapted to irregular time series and small-size datasets. Experiments are carried out on two use-cases using real satellite images: the prediction of submarines arrivals and departures from a naval base, and the forecasting of imminent rocket launches on two space bases. The proposed method significantly outperforms a random selection of reference cases on these challenging applications, showing its strong potential. Keywords: Predictive analysis · Case-based reasoning · Earth observation · Submarine activity · Space launch.


AAAI Conferences

We investigate case-based reasoning (CBR) problems where cases are represented by abstract factors and (positive or negative) outcomes, and an outcome for a new case, represented by abstract factors, needs to be established. To this end, we employ abstract argumentation (AA) and propose a novel methodology for CBR, called AA-CBR. The argumentative formulation naturally allows to characterise the computation of an outcome as a dialogical process between a proponent and an opponent, and can also be used to extract explanations for why an outcome for a new case is (not) computed.


AAAI Conferences

The addition of a robot to a team can be difficult if the human teammates do not trust the robot. This can result in underutilization or disuse of the robot, even if the robot has skills or abilities that are necessary to achieve team goals or reduce risk. To help a robot integrate itself with a human team, we present an agent algorithm that allows a robot to estimate its trustworthiness and adapt its behavior accordingly. As behavior adaptation is performed, using case-based reasoning (CBR), information about the adaptation process is stored and used to improve the efficiency of future adaptations.


AAAI Conferences

We present a case-based approach to character identification in natural language text in the context of our Voz system. Voz first extracts entities from the text, and for each one of them, computes a feature-vector using both linguistic information and external knowledge. We propose a new similarity measure called Continuous Jaccard that exploits those feature-vectors to compute the similarity between a given entity and those in the case-base, and thus determine which entities are characters or not. We evaluate our approach by comparing it with different similarity measures and feature sets. Results show an identification accuracy of up to 93.49%, significantly higher than recent related work.


AAAI Conferences

This paper presents a case-based reasoning (CBR) application for discovering similar patients with non-specific musculoskeletal disorders (MSDs) and recommending treatment plans using previous experiences. From a medical perspective, MSD is a complex disorder as its cause is often bounded to a combination of physiological and psychological factors. Likewise, the features describing the condition and outcome measures vary throughout studies. However, healthcare professionals in the field work in an experience-based way, therefore we chose CBR as the core methodology for developing a decision support system for physiotherapists which would assist them in the process of their co-decision making and treatment planning. In this paper, we focus on case representation and similarity modeling for the non-specific MSD patient data as well as we conducted initial experiments on comparing patient profiles.


AAAI Conferences

The similarity assumption in Case-Based Reasoning (similar problems have similar solutions) has been questioned by several researchers. If knowledge about the adaptability of solutions is available, it can be exploited in order to guide retrieval. Several approaches have been proposed in this context, often assuming a similarity or cost measure defined over the solution space. In this paper, we propose a novel approach where the adaptability of the solutions is captured inside a metric Markov Random Field (MRF). Each case is represented as a node in the MRF, and edges connect cases whose solutions are close in the solution space. States of the nodes represent the adaptability effort with respect to the query. Potentals are defined to enforce connected nodes to share the same state; this models the fact that cases having similar solutions should have the same adaptability effort with respect to the query. The main goal is to enlarge the set of potentially adaptable cases that are retrieved (the recall) without significantly sacrificing the precision of retrieval. We will report on some experiments concerning a retrieval architecture where a simple kNN retrieval is followed by a further retrieval step based on MRF inference.


AAAI Conferences

Case-Based Reasoning relies on the underlying hypothesis that similar problems have similar solutions. The extent to which this hypothesis holds good in the case base has been used by CBR designers as a measure of case base complexity, which in turn gives insights on the generalization ability of the reasoner. Several local and global complexity measures have been proposed in the literature. However, the existing measures rely only on the similarity knowledge to compute complexity. We propose a new complexity measure called Reachability-Based Complexity Measure (RBCM) that goes beyond the similarity knowledge to include the effects of all knowledge containers in the reasoner. The proposed measure is evaluated on several real-world datasets and results suggest that RBCM corroborates well with the generalization accuracy of the reasoner.


AAAI Conferences

This paper presents the first results of the research into AI-based support of the room configuration process during the early design phases in architecture. Room configuration (also: room layout or space layout) is an essential stage of the initial design phase: its results are crucial for user-friendliness and success of the planned utilization of the architectural object. Our approach takes into account different possible actions of the configuration process, such as adding, removing, or (re)assigning of the room type. Its mode of operation is based on specific process chain clusters, where each cluster represents a contextual subset of previous configuration steps and provides a recurrent neural network trained on this cluster data only to suggest the next step, and a case base that is used to determine if the current process chain belongs to this cluster. The most similar cluster then tries to suggest the next step of the process. The approach is implemented in a distributed CBR framework for support of early conceptual design in architecture and was evaluated with a high number of process chain queries to prove its general suitability.