Intelligent Decision Support System for Dementia Care Through Smart Home

We propose a system to recognize objects with a camera network in a smart home. Recognizing objects in a home environment from images is challenging, due to the variation in object appearances such as chairs, as well as the clutters in the scene. Therefore, we propose to recognize objects through user interactions. A hierarchical activity analysis is first performed in the system to recognize fine-grained activities including eating, typing, cutting etc. The object-activity relationship is encoded in the knowledge base of a Markov logic network (MLN). MLN has the advantage of encoding relationships in an intuitive way with first-order logic syntax. It can also deal with both soft and hard constraints by associating weights to the formulas in the knowledge base. With activity observations, the defined MLN is grounded and turned into a dynamic Bayesian network (DBN) to infer object type probabilities. We expedite inference by decomposing the MLN into smaller separate domains that relates to the active activity. Experimental results are presented with our testbed smart home environment.

A DSS approach to managing customer enquiries for SMEs at the customer enquiry stage

A SDSS combines database storage technologies, geographic information systems (GIS) and decision modeling into tools which can be used to address a wide variety of decision support areas (Eklund, Kirkby, and Pollitt, 1996). Recently, various emerging technologies in computer hardware and software such as speedy microprocessors, gigabit network connections, fast internet mapping servers along with Web-based technologies like extensible markup language (XML), Web services, etc provide promising opportunities to take the traditional spatial decision support systems one step further to provide easy-to-use, round-the-clock access to spatial data and decision support over the Web. Traditional DSS and Web-based spatial DSS can be further improved by integrating expert knowledge and utilizing intelligent software components (such as expert systems and intelligent agents) to emulate the human intelligence and decision making. These kinds of decision support systems are classified as intelligent decision support systems. The objective of this chapter is to discuss the development of an intelligent web-based spatial decision support system and demonstrate it with a case study for planning snow removal operations.

Intelligent decision support (IDS) systems leverage artificial intelligence techniques to generate recommendations that guide human users through the decision making phases of a task. However, a key challenge is that IDS systems are not perfect, and in complex real-world scenarios may produce suboptimal output or fail to work altogether. The field of explainable AI (XAI) has sought to develop techniques that improve the interpretability of black-box systems. While most XAI work has focused on single-classification tasks, the subfield of explainable AI planning (XAIP) has sought to develop techniques that make sequential decision making AI systems explainable to domain experts. Critically, prior work in applying XAIP techniques to IDS systems has assumed that the plan being proposed by the planner is always optimal, and therefore the action or plan being recommended as decision support to the user is always optimal. In this work, we examine novice user interactions with a non-robust IDS system – one that occasionally recommends suboptimal actions, and one that may become unavailable after users have become accustomed to its guidance. We introduce a new explanation type, subgoal-based explanations, for plan-based IDS systems, that supplements traditional IDS output with information about the subgoal toward which the recommended action would contribute. We demonstrate that subgoal-based explanations lead to improved user task performance in the presence of IDS recommendations, improve user ability to distinguish optimal and suboptimal IDS recommendations, and are preferred by users. Additionally, we demonstrate that subgoal-based explanations enable more robust user performance in the case of IDS failure, showing the significant benefit of training users for an underlying task with subgoal-based explanations.

We propose using a statistical-relational model, the Markov Logic Network, for knowledge transfer in reinforcement learning. Our goal is to extract relational knowledge from a source task and use it to speed up learning in a related target task. We show that Markov Logic Networks are effective models for capturing both source-task Q-functions and source-task policies. We apply them via demonstration, which involves using them for decision making in an initial stage of the target task before continuing to learn. Through experiments in the RoboCup simulated-soccer domain, we show that transfer via Markov Logic Networks can significantly improve early performance in complex tasks, and that transferring policies is more effective than transferring Q-functions.

Object recognition from images in a home environment is challenging since the object usually has low resolution in the image and the scene is usually cluttered. However, many objects have specific functions to the user and the interactions between the user and the object provides useful contextual information to recognize the object. In this paper, we use Markov logic network (MLN) to model such context information as relationship between the objects and user activities. We demonstrate that Markov logic network provides a flexible way in the syntax of first-order logic to incorporate relational context information. It is also a probabilistic graphical model which handles uncertainty in the knowledge base, observations and decisions. In our experiment, objects in the living room and kitchen in a home are recognized based on only user's activity. The user's activity is analyzed from images of cameras installed in the home. Relationship between user activity and objects is defined in a knowledge base with MLN. Experiments show that objects in the home can be recognized irrespective of their position, size and appearance in the image.

This paper presents the application of Markov Logic Networks(MLN) for the the recognition of Activities of Daily Living (ADL) in a smart home. We describe a procedure that uses raw data from non visual and non wearable sensors in order to create a classification model leveraging logic formal representation and probabilistic inference. SVM and Naive Bayes methods were used as baselines to compare the performance of our implementation, as they have proved to be highly efficient in classification tasks. The evaluation was carried out on a real smart home where 21 participants performed ADLs. Results show not only the appreciable capacities of MLN as a classifier, but also its potential to be easily integrable into a formal knowledge representation framework.

Statistical Relational Models are state-of-the-art representation formalisms at the intersection of logical and statistical machine learning. One of the most promising models is Markov Logic (ML) which combines Markov networks (MNs) and first-order logic by attaching weights to first-order formulas and using these as templates for features of MNs. MAP inference in ML is the task of finding the most likely state of a set of output variables given the state of the input variables and this problem is NP-hard. In this paper we present an algorithm for this inference task based on the Iterated Local Search (ILS) and Robust Tabu Search (RoTS) metaheuristics. The algorithm performs a biased sampling of the set of local optima by using RoTS as a local search procedure and repetitively jumping in the search space through a perturbation operator, focusing the search not on the full space of solutions but on a smaller subspace defined by the solutions that are locally optimal for the optimization engine. We show through extensive experiments in real-world domains that it improves over the state-of-the-art algorithm in terms of solution quality and inference time.

Context-aware decision making under uncertainty for voice-based control of smart home

This paper presents a new approach for Intelligent Decision Support Systems (IDSS) development based on the pseudo-Boolean multicriteria optimization with incomplete information for decision making in the complicated, weakly formalized sphere. This approach uses an interactive procedure to form the learning set W = {W 0 ⋃ W 1}, where W 0 contains only Pareto, and W 1 contains only non-Pareto points. This set W is used for inductive learning to approximate the Pareto set.KeywordsMultiple criteria optimizationpseudo-Boolean functionsmachine learningPareto set approximationdecision support systems

A Decision Support System (DSS) is a supporting tool enhancing a decision-making process. Decision-makers are frequently faced with the problem to take decisions on very complex issues, which requires large data inputs, and a timely decision process. DSSs provide decision makers with a tool to reduce uncertainties, and to simplify and speed-up the decision process as well as to avoid subjectivism induced by the decision-maker and to guarantee transparency of a decision process. The DSS approach has been introduced in the ballast water management (BWM) field and the need primarily arose with the introduction of the selective BWM approach. More precisely, it was recognised that a supporting tool is needed to aid transparency and consistency when deciding on BWM requirements to achieve better environmental protection and lessen burden on vessels. The DSS process starts with communication and data input, continues with risk assessment, BWM decisions, vessel’s action(s), and ends with monitoring and review processes. Throughout the entire decision process information needs to be exchanged with outer (e.g., vessel, other ports) and inner sources (e.g., vessel’s particulars, compliance history), and therefore needs to be supported by adequate communication processes and data management. When required BWM measures were not conducted properly the BWM DSS endpoints range from situations where unmanaged ballast water can be discharged to cases where vessels may be turned away. The chapter provides a detailed step-by-step DSS model which may be used by administrations and other authorities involved in the decision making processes.

The object of the study is intelligent decision support systems. The problem addressed in the research is to improve the accuracy of modeling the functioning process of intelligent decision support systems. A polymodel complex for resource management of intelligent decision support systems has been developed. The originality of the study lies in: – the comprehensive description of the functioning processes of intelligent decision support systems; – the capability to model both an individual process occurring in intelligent decision support systems and to perform comprehensive modeling of the processes taking place within them; – the establishment of conceptual dependencies in the functioning process of intelligent decision support systems. This makes it possible to describe the interaction of individual models at all stages of solving computational tasks; – the description of coordination processes in hybrid intelligent decision support systems, which ensures an increase in the reliability of managerial decision-making; – the modeling of processes for solving complex computational tasks in intelligent decision support systems through the conceptual description of the specified process; – the coordination of computational processes in intelligent decision support systems, which leads to a reduction in the number of computational resources of the systems; – the comprehensive resolution of conflicts through a set of corresponding mathematical models. The proposed polymodel complex is advisable for use in solving the problem of managing intelligent decision support systems characterized by a high degree of complexity

The object of research is intelligent decision making support systems. Processing different types of intelligence from a variety of information sources requires significant computational operations with strict time constraints. It leads to the search for new scientific approaches to the processing of various types of geospatial information to increase the efficiency of special purpose systems. This work solves the problem of developing a methodological approach to processing different data types in decision making support systems. During the research, the authors used the main provisions of the queuing theory, the theory of automation, the theory of complex technical systems and general scientific methods of cognition, namely analysis and synthesis. The proposed methodological approach was developed taking into account the practical experience of the authors of this work during the military conflicts of the last decade. The results of the research will be useful in: – development of new algorithms for processing different types of data; – substantiation of recommendations for improving the efficiency of processing various data types; – analysis of the operational situation during the hostilities (operations); – creating promising technologies to increase the efficiency of processing various data types; – assessment of the adequacy, reliability, sensitivity of the scientific and methodological apparatus of processing various data types; – development of new and improvement of existing simulation models of various processing data types. Areas of further research will be aimed at developing a methodology for processing various data types in intelligent decision making support systems.

Statistical Relational Learning has received much attention this last decade. In the ILP community, several models have emerged for modelling and learning uncertain knowledge, expressed in subset of first order logics. Nevertheless, no deep comparisons have been made among them and, given an application, determining which model must be chosen is difficult. In this paper, we compare two of them, namely Markov Logic Networks and Bayesian Programs, especially with respect to their representation ability and inference methods. The comparison shows that the two models are substantially different, from the point of view of the user, so that choosing one really means choosing a different philosophy to look at the problem. In order to make the comparison more concrete, we have used a running example, which shows most of the interesting points of the approaches, yet remaining exactly tractable.

Feasibility, appropriateness, meaningfulness and effectiveness of nursing interventions on the well-being of people with Parkinsonʼs disease and their caregivers living in the community: a mixed-methods systematic review protocol