This paper presents the inference and reasoning methods in a Bayesian supported knowledge-intensive case-based reasoning (CBR) system called BNCreek. The inference and reasoning process in this system is a combination of three methods. The semantic network inference methods and the CBR method are employed to handle the difficulties of inferencing and reasoning in uncertain domains. The Bayesian network inference methods are employed to make the process more accurate. An experiment from oil well drilling as a complex and uncertain application domain is conducted. The system is evaluated against expert estimations and compared with seven other corresponding systems. The normalized discounted cumulative gain (NDCG) as a rank-based metric, the weighted error (WE), and root-square error (RSE) as the statistical metrics are employed to evaluate different aspects of the system capabilities. The results show the efficiency of the developed inference and reasoning methods.

This paper presents fault diagnosis and problem solving under uncertainty by a Bayesian supported knowledge-intensive case-based reasoning (CBR) system called BNCreek. In this system, the main goal is to diagnose the causal failures behind the symptoms in complex and uncertain domains. The system’s architecture is described in three aspects: the general, structural, and functional architectures. The domain knowledge is represented by formally defined methods. An integration of semantic networks, Bayesian networks, and CBR is employed to deal with the domain uncertainty. An experiment is conducted from the oil well drilling domain, which is a complex and uncertain area as an application domain. The system is evaluated against the expert estimations to find the most efficient solutions for the problems. The obtained results reveal the capability of the system in diagnosing causal failures.

Defining similarity measures is a requirement for some machine learning methods. One such method is case-based reasoning (CBR) where the similarity measure is used to retrieve the stored case or a set of cases most similar to the query case. Describing a similarity measure analytically is challenging, even for domain experts working with CBR experts. However, datasets are typically gathered as part of constructing a CBR or machine learning system. These datasets are assumed to contain the features that correctly identify the solution from the problem features; thus, they may also contain the knowledge to construct or learn such a similarity measure. The main motivation for this work is to automate the construction of similarity measures using machine learning. Additionally, we would like to do this while keeping training time as low as possible. Working toward this, our objective is to investigate how to apply machine learning to effectively learn a similarity measure. Such a learned similarity measure could be used for CBR systems, but also for clustering data in semi-supervised learning, or one-shot learning tasks. Recent work has advanced toward this goal which relies on either very long training times or manually modeling parts of the similarity measure. We created a framework to help us analyze the current methods for learning similarity measures. This analysis resulted in two novel similarity measure designs: The first design uses a pre-trained classifier as basis for a similarity measure, and the second design uses as little modeling as possible while learning the similarity measure from data and keeping training time low. Both similarity measures were evaluated on 14 different datasets. The evaluation shows that using a classifier as basis for a similarity measure gives state-of-the-art performance. Finally, the evaluation shows that our fully data-driven similarity measure design outperforms state-of-the-art methods while keeping training time low.

Frequency of failures occurring during offshore oil-well drilling do not diminish over time, probably due to increased operational complexity. The volume and frequency of information generated during the drilling process are high. Every few seconds around 30 drilling parameters are recorded and stored. There will always be a need for new, smart solutions to drilling challenges. Present approaches to drilling challenges apply various types of knowledge generated by the operation; wellbore geometry, fluid info, lithology of the sediments, time-based drilling parameters, drilling equipment data, etc. In our research said knowledge is generalized into general concepts, and structured to form a knowledge model of the drilling process. This model is referred to as a drilling ontology, and we report how methods of knowledge modeling and ontology engineering have been used in developing the model, and subsequently how the model has been applied to predict downhole failures during drilling. The knowledge model and the drilling data are combined in the following manner: Data agents are surveilling drilling data. Deviatoric behavior of the drilling parameters are being detected and formed into symptoms. Symptoms trigger other concepts embedded in the ontology by means of linked cause-effect relationships. The end concept of the relationship path will always be one or several failure states. Tests show that reasoning within the ontology produces the highest probability of the failure identical with the real failure. The causes behind the failure can be retrieved from the ontology and applied in a useful manner in combatting the failure. The testing process also shows that this program is a potential supplement to warning against threatening failures before they occur.

Recent developments have shown that Deep Learning approaches are well suited for Human Action Recognition. On the other hand, the application of deep learning for action or behaviour recognition in other domains such as animal or livestock is comparatively limited. Action recognition in fish is a particularly challenging task due to specific research challenges such as the lack of distinct poses in fish behavior and the capture of spatio-temporal changes. Action recognition of salmon is valuable in relation to managing and optimizing many aquaculture operations today such as feeding, as one of the most costly operations in aquaculture. Inspired by these application domains and research challenges we introduce a deep video classification network for action recognition of salmon from underwater videos. We propose a Dual-Stream Recurrent Network (DSRN) to automatically capture the spatio-temporal behavior of salmon during swimming. The DSRN combines the spatial and motion-temporal information through the use of a spatial network, a 3D-convolutional motion network and a LSTM recurrent classification network. The DSRN shows an accuracy that is suitable for industrial use in prediction of salmon behavior with a prediction accuracy of 80%, validated on the task of predicting Feeding and NonFeeding behavior in salmon at a real fish farm during production. Our results show that the DSRN architecture has high potential in feeding action recognition for salmon in aquaculture and for applications domains lacking distinct poses and with dynamic spatio-temporal changes.

This paper presents the design of a Clinician Dashboard to promote co-decision making between patients and clinicians. Targeted patients are those with non-specific low back pain, a leading cause of discomfort, disability and absence from work throughout the world. Targeted clinicians are those in primary care, including general practitioners, physiotherapists, and chiropractors. Here, the functional specifications for the Clinical Dashboard are delineated, and wireframes illustrating the system interface and flow of control are shown. Representative scenarios are presented to exemplify how the system could be used for co-decision making by a patient and clinician. Also included are a discussion of potential barriers to implementation and use in clinical practice and a look ahead to future work. This work has been conducted as part of the Horizon 2020 selfBACK project, which is funded by the European Commission.

This study presents a case-based reasoning (CBR) system that makes use of general domain knowledge - referred to as a knowledge-intensive CBR system. The system applies a Bayesian analysis aimed at increasing the accuracy of the similarity assessment. The idea is to employ the Bayesian posterior distribution for each case symptom to modify the case descriptions and the dependencies in the model. To evaluate the system, referred to as BNCreek, two experiment sets are set up from a “food” and an “oil well drilling” application domain. In both of the experiments, the BNCreek is evaluated against two corresponding systems named TrollCreek and myCBR with Normalized Discounted Cumulative Gain (NDCG) and interpolated average Precision-Recall as the evaluation measures. The obtained results reveal the capability of Bayesian analysis to increase the accuracy of the similarity assessment.

Cognitive Systems understand the world through learning and experience. Case Based Reasoning (CBR) systems naturally capture knowledge as experiences in memory and they are able to learn new experiences to retain in their memory. CBR’s retrieve and reuse reasoning is also knowledge-rich because of its nearest neighbour retrieval and analogy-based adaptation of retrieved solutions. CBR is particularly suited to domains where there is no well-defined theory, because they have a memory of experiences of what happened, rather than why/how it happened. CBR’s assumption that ‘similar problems have similar solutions’ enables it to understand the contexts for its experiences and the ‘bigger picture’ from clusters of cases, but also where its similarity assumption is challenged. Here we explore cognition and meta-cognition for CBR through self-reflection and introspection of both memory and retrieve and reuse reasoning. Our idea is to embed and exploit cognitive functionality such as insight, intuition and curiosity within CBR to drive robust, and even explainable, intelligence that will achieve problem-solving in challenging, complex, dynamic domains.

Metareasoning has been widely studied in the literature, with a wide variety of algorithms and partially overlapping methodological approaches. However, these methods are typically either not targeted toward practical machine learning systems or alternatively are focused on achieving the best possible performance for a particular domain, with extensive human tuning and research, and vast computing resources. In this paper, our goal is to create systems that perform sustained autonomous learning, with automatically determined domain-specific optimizations for any given domain, and without requiring human assistance. We present Alma, a metareasoning architecture that creates and selects reasoning methods based on empirically observed performance. This is achieved by using lazy learning at the metalevel, and automatically training and combining reasoning methods at run-time. In experiments across diverse data sets, we demonstrate the ability of Alma to successfully reason about learner performance in different domains and achieve a better overall result than any of the individual reasoning methods, even with limited computing time available.

An initial case base population naturally lacks diversity of solutions. In order to overcome this cold-start problem, we present how genetic algorithms (GA) can be applied. The work presented in this paper is part of the SELFBACKEU project and describes a case-based recommendation system that creates exercise plans for patients with non-specific low back pain (LBP). In SELFBACKCase-Based Reasoning (CBR) is used as its main methodology for generating patient-specific advice for managing non-specific LBP. The sub-module of SELFBACKpresented in this work focuses on the adaptation process of exercise plans: A GA inspired method is created to increase the variation of personalized exercise plans, which today are crafted by medical professionals. Experiments are conducted using real patients' characteristics with expert-crafted solutions and automatically generated solutions. In the evaluation we compare the quality of the GA-generated solutions to null-adaptation solutions.

The work presented is part of the selfBACK EU project and describes a case-based recommendation system that creates exercise plans for patients with non-specific low back pain (LBP). The submodule of selfBACK presented in this work focuses on the adaptation process of exercise plans: An evolutionary inspired method is created to increase the variation of personalized exercise plans, which today are crafted by medical professionals. Experiments are conducted using real patients’ characteristics with expert-crafted solutions and automatically generated solutions. In the evaluation we compare the quality of the solutions generated by Genetic Algorithm to null-adaptation solutions.

In this paper we will introduce the SELFBACK decision support system that facilitates, improves and reinforces self-management of non-specific low back pain. The SELFBACK system is a predictive casebased reasoning system for personalizing recommendations in order to provide relief for patients with non-specific low back pain and increase their physical functionality over time. We present how case-based reasoning is used for capturing experiences from temporal patient data, and evaluate how to carry out a similarity-based retrieval in order to find the best advice for patients. Specifically, we will show how heterogeneous data received at various frequencies can be captured in cases and used for personalized advice.

A majority of the remaining oil and gas reserves are located on continental shelves. Offshore drilling operations are expensive, and the numbers of wells are therefrore held low, and they tend to be long and complex. The number of process failures seen in recent years does not exhibit the intended declining tendency. A failure during drilling operations is defined as the state when non-productive time is occurring. The motivation behind the work presented here is to advance a specific computerized method for helping the petroleum industry in reducing unwanted downtime. More up-time is needed. The ultimate goal of our research is to improve the drilling process quality and efficiency. This is achieved by first detecting process deviations (symptoms) during the drilling process, and produce explanations generated by a general knowledge model (ontology). The symptoms have been translated into formal concepts and related into cause-effect relationships with errors and failures. Our experimental system is able to read data from a drilling process and apply the on-line detected and predefined static symptoms to capture a probalistic understanding of the downhole process. We will demonstrate the tool's ability during selected drilling processes to determine which failure type is the most threatening during problem situations and which errors are causing the failure. The failures revealed by the tool on basis of detected symptoms are compared with the reported failure in the field.

This study proposes a methodology to diagnose the root causes of failures in the domain of oil well drilling. The idea is to combine a Bayesian network, which is generated based on an expert knowledge, with situation-specific knowledge of past failure cases. A causal chain is viewed as a temporal sequence. To test the model’s capability, six failure cases from the study’s application domain (oil well drilling) are considered and one of them has been picked up as the studying case. The model is applied to diagnose the root causes of the chosen failure case. A temporal reasoning approach has been employed to narrow down the determination of the effective concepts, given the observations. The preliminary results show some advantages of the new model in comparison with the model that integrated a multi relational knowledge model with case based reasoning.

A new Horizon 2020 research and innovation project will start the development of the SELFBACK decision support system for self-management of low back pain in January 2016.

Many different artificial intelligence/machine learning concepts are driving mechanisms behind entertainment systems. Further, computational creativity (CC) is an area with increased focus within entertainment computing as well as AI. This workshop provides a forum where AI and creativity can be discussed within the context of entertainment computing and related areas, as described in the main conference call.

The most similar case may not always be the most appropriate one to guide a problem-solving process. It is often important that a retrieved past case can be easily adapted to a target problem. The presented work deals with the retrieval and adaptation in textual case-based reasoning (TCBR) where cases are described textually. In TCBR, it is common to use similarity-based retrieval methods from information retrieval where adaptability of the retrieved cases is not considered. In this paper we introduce a novel case retrieval method called evidence-driven retrieval (EDR). It uses the notion of evidence to determine which parts of the new problem text have been useful in the past solutions and will be used in the adaptation to a new problem. This allows EDR to retrieve cases that are not only similar but also adaptable. We evaluated EDR as part of our TCBR approach that aims to support human experts in root cause analysis of transportation incidents. This approach relies on causal knowledge automatically extracted from incident reports from the Transportation Safety Board of Canada, which are used as textual cases in our experiments. The results for EDR are compared with information retrieval methods traditionally applied in TCBR.

This paper discusses the need to recognize and take advantage of arising opportunities when an agent is autonomously interacting with an environment. We discuss the tasks, methods, model framework, and use it to analyze opportunities across several dimensions: when changing the tasks versus changing the methods, when having a complete knowledge about the methods in the domain versus having partial knowledge, when having a complete model of the domain versus having an incomplete model, when tackling a single task versus multiple tasks and finally we discuss the role of causal explanations in opportunistic case-based decision making.