The pursuit of quality improvements and accountability in the food supply chains, especially how they relate to food-related outcomes, such as hunger, has become increasingly vital, necessitating a comprehensive approach that encompasses product quality and its impact on various stakeholders and their communities. Such an approach offers numerous benefits in increasing product quality and eliminating superfluous measurements while appraising and alleviating the broader societal and environmental repercussions. A traceable impact management model (TIMM) provides an impact structure and a reporting mechanism that identifies each stakeholder's role in the total impact of food production and consumption stages. The model aims to increase traceability's utility in understanding the impact of changes on communities affected by food production and consumption, aligning with current and future government requirements, and addressing the needs of communities and consumers. This holistic approach is further supported by an ontological model that forms the logical foundation and a unified terminology. By proposing a holistic and integrated solution across multiple stakeholders, the model emphasizes quality and the extensive impact of championing accountability, sustainability, and responsible practices with global traceability. With these combined efforts, the food supply chain moves toward a global tracking and tracing process that not only ensures product quality but also addresses its impact on a broader scale, fostering accountability, sustainability, and responsible food production and consumption.

The rapid increase in published datasets has intensified challenges in sourcing and integrating relevant data for analysis. Persistent obstacles include poor metadata, ineffective presentation, and difficulties in locating and integrating datasets. This paper delves into the intricacies of dataset retrieval, emphasising the pivotal role of metadata in aligning datasets with user queries. Through an exploration of existing literature, it highlights prevailing issues, such as identifying valuable metadata and developing tools to maintain and annotate them effectively. The paper proposes a dataset metadata maturity model, inspired by software engineering frameworks, to guide dataset creators from basic to advanced documentation. The model encompasses seven pivotal dimensions, spanning content to quality information, each stratified across five maturity levels to guide the optimal documentation of datasets, ensuring ease of discovery, accurate relevance assessment, and comprehensive understanding of datasets. This paper also incorporates the maturity model into a data cataloguing tool called CKAN through a custom plugin, CKANext-udc. The plugin introduces custom fields based on different maturity levels, allows for user interface customisation, and integrates with a graph database, converting catalogue data into a knowledge graph based on the Maturity Model ontology.

In the current environment of data generation and publication, there is an ever-growing number of datasets available for download. This growth precipitates an existing challenge: sourcing and integrating relevant datasets for analysis is becoming more complex. Despite efforts by open data platforms, obstacles remain, predominantly rooted in inadequate metadata, unsuitable data presentation, complications in pinpointing desired data, and data integration. This paper delves into the intricacies of dataset retrieval, emphasizing the pivotal role of metadata in aligning datasets with user queries. Through an exploration of existing literature, it underscores prevailing issues such as the identification of valuable metadata and the development of tools to maintain and annotate them effectively. The central contribution of this research is the proposition of a dataset metadata maturity model. Deriving inspiration from software engineering maturity models, this framework delineates a progression from rudimentary metadata documentation to advanced levels, aiding dataset creators in their documentation efforts. The model encompasses seven pivotal dimensions, spanning content to quality information, each stratified across six maturity levels to guide the optimal documentation of datasets, ensuring ease of discovery, relevance assessment, and comprehensive dataset understanding. This paper also incorporates the maturity model into a data cataloguing tool called CKAN through a custom plugin, CKANext-udc. The plugin introduces custom fields based on different maturity levels, allows for user interface customisation, and integrates with a graph database, converting catalogue data into a knowledge graph based on the Maturity Model ontology.

In the current environment of data generation and publication, there is an ever-growing number of datasets available for download. This growth precipitates an existing challenge: sourcing and integrating relevant datasets for analysis is becoming more complex. Despite efforts by open data platforms, obstacles remain, predominantly rooted in inadequate metadata, unsuitable data presentation, complications in pinpointing desired data, and data integration. This paper delves into the intricacies of dataset retrieval, emphasizing the pivotal role of metadata in aligning datasets with user queries. Through an exploration of existing literature, it underscores prevailing issues such as the identification of valuable metadata and the development of tools to maintain and annotate them effectively. The central contribution of this research is the proposition of a dataset metadata maturity model. Deriving inspiration from software engineering maturity models, this framework delineates a progression from rudimentary metadata documentation to advanced levels, aiding dataset creators in their documentation efforts. The model encompasses seven pivotal dimensions, spanning content to quality information, each stratified across five maturity levels to guide the optimal documentation of datasets, ensuring ease of discovery, relevance assessment, and comprehensive dataset understanding. This paper also incorporates the maturity model into a data cataloguing tool called CKAN through a custom plugin, CKANext-udc. The plugin introduces custom fields based on different maturity levels, allows for user interface customisation, and integrates with a graph database, converting catalogue data into a knowledge graph based on the Maturity Model ontology.

This paper introduces ontological concepts required to evaluate and manage the coverage of social services in a Smart City context. Here, we focus on the perspective of key stakeholders, namely social purpose organizations and the clients they serve. The Compass ontology presented here extends the Common Impact Data Standard by introducing new concepts related to key dimensions: the who (Stakeholder), the what (Need, Need Satisfier, Outcome), the how (Service, Event), and the contributions (tracking resources). The paper first introduces key stakeholders, services, outcomes, events, needs and need satisfiers, along with their definitions. Second, a subset of competency questions are presented to illustrate the types of questions key stakeholders have posed. Third, the extension's ability to answer questions is evaluated by presenting SPARQL queries executed on a Compass-based knowledge graph and analysing their results.

When working with an agent-based system, it may be desirable to develop an algorithm that can predict future time periods for each individual. One such approach that works to accomplish this is the Markov decision process, which takes as its input available actions, unique agent reward functions, and a model of the overall environment. However, it can be difficult to identify the underlying factors that influence decision making when attempting to simulate the behavior of real-world populations. For example, when modeling the transitions of homeless individuals between states such as street and shelter, it can be a challenging task as the external factors impacting them (e.g., weather) may not be readily apparent. Therefore, this paper proposes and evaluates an approach to capture this information in an explainable way from aggregate, real-life data produced by the At Home/Chez Soi project. The proposed algorithm "BEAUT" is a consolidation of a modified deep q-learning (MDQL) and modified neural fitted q-iteration (MNFQ) algorithm that work together to generate a set of probabilistic transition matrices to describe state transitions. BEAUT is evaluated with experimental results that compare its accuracy against similar methods for time-series forecasting using real-world data. Our tests show that BEAUT provides an explainable forecasting model without a loss of accuracy, and in some instances results in higher accuracy.

Named entity recognition (NER) is an important task in narration extraction. Narration, as a system of stories, provides insights into how events and characters in the stories develop over time. This paper proposes an architecture for NER on a corpus about social purpose organizations. This is the first NER task specifically targeted at social service entities. We show how this approach can be used for the sequencing of services and impacted clients with information extracted from unstructured text. The methodology outlines steps for extracting ontological representation of entities such as needs and satisfiers and generating hypotheses to answer queries about impact models defined by social purpose organizations. We evaluate the model on a corpus of social service descriptions with empirically calculated score.

We present a design pattern aimed at supporting the formal representation of information about needs collected in Social Work settings. The framework is designed to integrate with existing information representation frameworks and allow extensions for documenting client progress during social interventions, as well as extensions to support representing information pertinent to activities such as referring clients to services, scheduling appointments, designing individual support plans and evaluating community level needs and service gaps.

When working with an agent-based system, it may be desirable to develop an algorithm that can predict future time periods for each individual. One such approach that works to accomplish this is the Markov decision process, which takes as its input available actions, unique agent reward functions, and a model of the overall environment. However, it can be difficult to identify the underlying factors that influence decision making when attempting to simulate the behavior of real-world populations. For example, when modeling the transitions of homeless individuals between states such as street and shelter, it can be a challenging task as the external factors impacting them (e.g., weather) may not be readily apparent. Therefore, this paper proposes and evaluates an approach to capture this information in an explainable way from aggregate, real-life data produced by the At Home/Chez Soi project. The proposed algorithm “BEAUT” is a consolidation of a modified deep q-learning (MDQL) and modified neural fitted q-iteration (MNFQ) algorithm that work together to generate a set of probabilistic transition matrices to describe state transitions. BEAUT is evaluated with experimental results that compare its accuracy against similar methods for time-series forecasting using real-world data. Our tests show that BEAUT provides an explainable forecasting model without a loss of accuracy, and in some instances results in higher accuracy.

This paper introduces the Compass ontology and proposes a design pattern aimed at supporting the formal representation of information about clients, services, and events in a social service setting. The framework captures entities required to represent the interaction between clients and services and events that track progress through changes exhibited by these stakeholders. The Compass ontology is an extension of the Common Impact Data Standard. It introduces classes and properties that allow it to answer a set of competency questions posed by subject matter experts in the area of social service provisioning. We evaluate the ontology using sample competency questions implemented in SPARQL.

The popularity of ontologies for representing the semantics behind many real-world domains has created a growing pool of ontologies on various topics. While different ontologists, experts, and organizations create the vast majority of ontologies, often for internal use of for use in a narrow context, their domains frequently overlap in a wider context, specifically for complementary domains. To assist in the reuse of ontologies, this thesis proposes a bottom-up technique for creating concept anchors that are used for ontology matching. Anchors are ontology concepts that have been matched to concepts in an eternal ontology. The matching process is based on inductively derived decision trees rules for an ontology that are compared with rules derived for external ontologies. The matching algorithm is intended to match taxomonies, ontologies which define subsumption relations between concepts, with an associated database used to derive the decision trees. This thesis also introduces several algorithm evolution measures, and presents a set of use cases that demonstrate the strengths and weaknesses of the matching process.

In classical AI planning, replanning strategies are used to re-evaluate a plan during execution. For human-like agents, goal preferences and emotions play an important role in evaluating a plan’s progress. However, most existing systems rely on predefined goal ordering and a static association between an event and its emotion-based utility calculation. During execution, utility of individual actions are used to trigger the replanning process. This approach assumes that a complete sequence of actions can be generated, preferences are known, are transitive, the emotion-based utility of every action’s outcome is known, and a replanning condition is well defined. This paper presents an alternative approach, one that does not make assumptions about the agent’s or observer’s omniscience about factors influencing decision making. Our approach recognizes the bounds that limit the agent and observer equally. To accommodate these limits, first, human-centric goal ranking are grounded in a domain-specific mapping to Maslow’s hierarchy. Second, a new replanning condition is proposed with dynamically changing mood-based utility during plan execution.

In this article, we describe high-fidelity human behaviour emulation model capable of ranking and re-ranking goals during plan execution based on changing emotional modes of an agent. Our model assumes the agent is rational but its reasoning is bounded. The agent's reasoning process incorporates emotions and basic human needs to emulate changes in human behaviour under cognitive limitations. The majority of cognitive systems that incorporate emotions rely on reactive models that elicit predetermined responses to emotional modes. Our model demonstrates how human emotions change during the execution of a plan independent of specific events that may elicit such responses. The initial goals of the agent are grounded in basic human needs outlined by Maslow's Hierarchy. Once a plan is generated under the cognitive limitations of the agent and execution begins, goals are re-ranked based on an emotional re-evaluation of the plan's progress. The result is a high-fidelity, domain-independent, general theory of motivation based on human needs and emotions. We demonstrate the algorithm with a use-case from the social service domain by emulating the behaviour of homeless clients in response to an intervention program.

The Social Services Chain is the network of social services through which clients flow. At an abstract level, this is very much like a job shop in that each client moving through the chain requires a unique set and sequence of services, but that these services often have to be repeated as required by the individual needs of a client. When we consider realistic problems for social services, however, the representations underlying traditional approaches, such as job shops, lack the expressiveness required for high fidelity models. In order to apply industrial and systems engineering techniques to the social services chain, we must first understand and be able to represent/model the characteristics of clients and services that uniquely distinguish social services from other service sectors. This model is to be used in a multi-agent simulation environment to test theories to optimize social service delivery. This paper presents a set of requirements that a social service model must satisfy in order to achieve high fidelity. These requirements combine an industrial/systems engineering perspective with a social sciences perspective in order to capture the unique behavioural characteristics of clients and service providers.

The popularity of ontologies for representing the semantics behind many real-world domains has created a growing pool of ontologies on various topics. Different ontologists, experts, and organizations create a great variety of ontologies, often for narrow application domains. Some of the created ontologies frequently overlap with other ontologies in broader domains if they pertain to the Semantic Web. Sometimes, they model similar or matching theories that may be inconsistent. To assist in the reuse of these ontologies, this paper describes a technique for enriching manually created ontologies by supplementing them with inductively derived rules, and reducing the number of inconsistencies. The derived rules are translated from decision trees with probability measures, created by executing a tree based data mining algorithm over the data being modelled. These rules can be used to revise an ontology in order to extend the ontology with definitions grounded in empirical data, and identify possible similarities between complementary ontologies. We demonstrate the application of our technique by presenting an example, and discuss how various data types may be treated to generalize the semantics of an ontology for a broader application domain.

This work presents an evolutionary algorithm for automatic ontology mapping, which attempts to map similar objects based on their hierarchical structures from an unclassified to a classified ontology. Alignment is performed by swapping branches between the two ontologies and comparing their similarities to find possible missing terms in the unclassified ontology. Our algorithm is a stochastic implementation of the expectation maximization (EM) algorithm, which attempts to find and insert possibly missing terms, and measures the resulting improvements through iterative E-steps and M-steps. Our approach evolves the E-step to find these terms, while the M-step maps the classified ontology onto the unclassified one. Only taxonomic information is evaluated. We extract high-level descriptions of low-level definitions, and create subsections of the search-spaces, and thus obtain a satisfactory representation of the entire search-space to sample.