1,720,958 research outputs found
Classification Rules Explain Machine Learning
No full textWe introduce a general model for explainable Artificial Intelligence that identifies an explanation of a Machine Learning method by classification rules. We define a notion of distance between two Machine Learning methods, and provide a method that computes a set of classification rules that, in turn, approximates another black box method to a given extent. We further build upon this method an anytime algorithm that returns the best approximation it can compute within a given interval of time. This anytime method returns the minimum and maximum difference in terms of approximation provided by the algorithm and uses it to determine whether the obtained approximation is acceptable. We then illustrate the results of a few experiments on three different datasets that show certain properties of the approximations that should be considered while modelling such systems. On top of this, we design a methodology for constructing approximations for ML, that we compare to the no-methods approach typically used in current studies on the explainable artificial intelligence topic
Revising non-monotonic theories with sufficient and necessary conditions: the case of Defeasible Logic
No full textIn the setting of Defeasible Logic, we deal with the problem of revising and contracting a non-monotonic theory while minimizing the number of rules to be removed from the theory itself. The process is based on the notions of a set of rules being necessary and sufficient in order to prove a claim. The substantial difference among classical and non-monotonic reasoning processes makes this issue significant in order to achieve the correct revision processes. We show that the process is however computationally hard, and can be solved in polynomial time on non-deterministic machines
Impact Measures for Business Process Compliance: Analyzing Impact Compliance and Declarative Specifications
Get PDFAbstract
A business is an organization that engages in commercial, industrial, or professional activity in a systematic and predefined manner. Key aspects of the business include profit motive, exchange of goods and services, organization and management, and risk.
A business’s objective is typically to supply goods or services to consumers or to other businesses in order to make a profit or to achieve a given non-profit purpose. Businesses can range from small-scale enterprises like neighborhood shops to massive multinational corporations, but they are distinguished from occasional or unorganized endeavors for Their scope is to organize their own activities in a specified way, in many cases formally defined, a priori with respect to the activities. In other terms, businesses have their own predefined processes, or workflows.
A process is a set of events, procedures, or operations that are performed in admissible systematic orders to reach a specified conclusion or purpose. In industrial and agricultural production, for instance, a process is the activity of converting inputs (such as raw materials, data, or resources) into outputs (finished goods, results, or solutions) using a set of structured procedures. Key elements of a process include sequence, inputs and outputs, transformation, repetition, and control.
A business process is a comprehensive formal model that represents the behavior of complex systems, both existing and newly designed ones. These models capture the interactions and synchronizations between humans and machines, making them crucial for understanding and optimizing the dynamic interplay within business operations. Compliance refers to adherence to laws, regulations, guidelines, and specifications relevant to an organization's operations. It ensures that businesses operate within a given normative background and meet the standards set by regulatory bodies, industry best practices, and internal policies. Ensuring compliance means that business processes are aligned with regulatory requirements, organizational goals, and both soft and hard
rules imposed on the processes themselves. Compliance is essential for maintaining legal and ethical integrity, minimizing risks, and enhancing the organization's reputation. Without compliance with warranties, a business may incur penalties from regulatory bodies or have adverse effects in the future, whether economically, socially, or environmentally.
Business processes must adhere to various forms of compliance, in the realm of practical business life including:
A) General Regulatory Compliance: This ensures business processes conform to external authorities’ laws, regulations, and standards. It involves adhering to legal requirements that govern the industry or sector in which the organization operates.
B) Goal Compliance: This aligns business processes with predefined organizational
goals and objectives. It ensures that the processes support the strategic aims and targets of the organization.
C) Impact Compliance: This ensures that the impacts of business processes remain within acceptable thresholds, thereby minimizing negative effects of the execution of the process. It involves assessing and managing the potential effects of processes on various aspects of the business.
D) Environmental Compliance: This ensures that the impacts of business processes
do not exceed constraints set from an environmental perspective. It involves adherence to environmental regulations and practices that mitigate adverse environmental effects. Adhering to these compliance requirements helps ensure that business processes operate effectively within legal and ethical boundaries while supporting organizational objectives and minimizing negative impacts on society and the environment.
This dissertation primarily focuses on impact compliance and environmental compliance, that I shall show are analogous in technical terms. The purpose, on a generic viewpoint, is to minimize the emission of Carbon dioxide (CO2) but can also be used to regulate other pollutant substances. It delves into the definition of impact compliance, its integration with existing compliance concepts, and its evaluation from multiple perspectives.
When we discuss Compliance, there are three perspectives of compliance i.e. corrective, detective, and preventive. All these three-perspective base themselves on the detective dimension, for no correction or prevention can be performed without leaning out the detection of (potential) uncompliances.
Corrective measures are intended to limit the extent of any consequences caused by non-compliant situations. They are reactive and aim to address and mitigate issues after they have occurred. Examples include manual audits, which are periodic reviews conducted by individuals to identify and rectify compliance issues, and automated detections, which are systems and tools that automatically detect deviations from compliance standards.
Detective measures aim to identify non-compliant situations “after-the-fact”. They are essential for recognizing and addressing issues that have already impacted the business process. These measures also include manual audits and automated detections, similar to
corrective measures. Preventive measures embed compliance into the business processes from the outset, a concept known as “Compliance by Design”. The objective is to proactively prevent noncompliance by designing processes that adhere to compliance requirements.
The dissertation explores the synthesis of business processes through declarative specifications, which provide a structured framework for defining and enforcing compliance.
It investigates how impact compliance can be effectively integrated with regulatory and goal compliance, ensuring a holistic approach to business process management. Business Process Compliance (BPC) is a collection of methodologies used to evaluate business processes to ensure they adhere to specified constraints. These constraints,which may be imposed due to regulatory requirements or organizational goals, are essential for maintaining the integrity and reliability of business operations. Business Process
Compliance (BPC) methods assess whether an execution trace exists—a sequence of actions within the process—that violates any of the imposed constraints. Conversely, this evaluation can also involve superimposing a set of constraints on the process and then assess all possible executions for compliance. This dual approach to Business Process Compliance (BPC) is highly relevant in real-world applications, particularly in the realm of regulatory compliance. Businesses must verify their processes against a normative framework, which includes not only stringent regulations but also softer guidelines, product specifications and standards. This verification ensures that processes meet the expectations set by regulatory bodies and the business owners themselves.In this dissertation, I introduce a novel type of compliance, termed impact compliance. This concept is designed to evaluate whether a business process adheres to a set of constraints by ensuring that the undesirable effects of executing tasks within the process are maintained below specified limits. Impact compliance is shown to be usable for minimizing negative outcomes associated with business operations such as for regulating the emission of pollutant substances including carbon dioxide (CO2), thereby optimizing overall process performance. I demonstrate that under certain structural conditions, the problems associated with checking for compliance are polynomially solvable on deterministic machines. Specifically, the task of determining whether any execution trace violates the constraints is generally NP-complete. However, verifying that all possible executions adhere to the constraints is polynomially solvable, provided the structural conditions are met. This dissertation also delves into the synthesis of business processes through declarative specifications and examines the significant role of compliance, discussing impact compliance by design. I also design a method to compare business processes as a whole in terms of impact, and therefore obtain a notion of impact similarity that is in turn shown to be useful for process mining. By introducing and detailing the concept of impact compliance, I provide a framework for ensuring that business processes not only comply with regulatory and organizational standards but also minimize undesired effects, thereby enhancing operational efficiency and time Complexity. This research contributes to the field by offering a detailed exploration of impact compliance, proposing innovative methods for integrating impact compliance into business process models, and demonstrating the application of these methods through various case studies and theoretical analyses
Business Process Compliance with impact constraints
No full textBusiness Process Compliance is a family of methods to evaluate Business Processes in terms of the existence of one execution (one trace) that does not violate constraints superimposed on the process itself. The dual version is formulated as the superimposition of a set of constraints and consequent evaluation of the process for all the executions. These problems are relevant to a large part of actual applications, especially those in the context of regulatory compliance where we aim at verifying the process against a normative background (including, for instance, soft ones, such as guidelines, product specification, and product standards) or goals fixed by the owner of the process. In this paper we discuss one new type of compliance, that is impact compliance, devised to verify when a process respects a set of constraints, to establish that certain amounts, measuring the undesired effects of the tasks executed to implement the process, are below given limits. In the current literature on Business Process Management, Business Process Analysis, and Business Process Compliance, this type of compliance checking process has not yet been addressed. As we demonstrate in this paper, this problem is significant and complex to address. In particular, we show that the checking problems described above are, under certain structural conditions, polynomially solvable on deterministic machines. In general, however, the first problem is NP-complete whilst the second is polynomially solvable on deterministic machines
Going Beyond Counting First Authors in Author Co-citation Analysis
Get PDFThe present study examines one of the fundamental aspects of author co-citation analysis (ACA) - the way co-citation
counts are defined. Co-citation counting provides the data on which all subsequent statistical analyses and mappings
are based, and we compare ACA results based on two different types of co-citation counting - the traditional type that
only counts the first one among a cited work's authors on the one hand and a non-traditional type that takes into
account the first 5 authors of a cited work on the other hand. Results indicate that the picture produced through this non-traditional author co-citation counting contains more coherent author groups and is therefore considerably clearer. However, this picture represents fewer specialties in the research field being studied than that produced through the traditional first-author co-citation counting when the same number of top-ranked authors is selected and analyzed. Reasons for these effects are discussed
Variations on the Author
Get PDF“Variations on the Author” discusses two of Eduardo Coutinho’s recent films (Um Dia na Vida, from 2010, and Últimas Conversas, posthumously released in 2015) and their contribution to the general question of documentary authorship. The director’s filmography is characterized by a consistent yet self-effacing form of authorial self-inscription: Coutinho often features as an interviewer that rather than express opinions propels discourses; an interviewer that is good at listening. This mode of self-inscription characterizes him as an author who is not expressive but who is nonetheless markedly present on the screen. In Um Dia na Vida, however, Coutinho is completely absent form the image, while Últimas Conversas, on the contrary, includes a confessional prologue that moves the director from the margins to the center of his films. This article examines the ways in which these works stand out in the filmography of a director who offers new insights into the notion of cinematic authorship
Appropriate Similarity Measures for Author Cocitation Analysis
Get PDFWe provide a number of new insights into the methodological discussion about author cocitation analysis. We first argue that the use of the Pearson correlation for measuring the similarity between authors’ cocitation profiles is not very satisfactory. We then discuss what kind of similarity measures may be used as an alternative to the Pearson correlation. We consider three similarity measures in particular. One is the well-known cosine. The other two similarity measures have not been used before in the bibliometric literature. Finally, we show by means of an example that our findings have a high practical relevance.information science;Pearson correlation;cosine;similarity measure;author cocitation analysis
Towards Posture and Gait Evaluation through Wearable-Based Biofeedback Technologies
Get PDFIn medicine and sport science, postural evaluation is an essential part of gait and posture correction. There are various instruments for quantifying the postural system’s efficiency and determining postural stability which are considered state-of-the-art. However, such systems present many limitations related to accessibility, economic cost, size, intrusiveness, usability, and time-consuming set-up. To mitigate these limitations, this project aims to verify how wearable devices can be assembled and employed to provide feedback to human subjects for gait and posture improvement, which could be applied for sports performance or motor impairment rehabilitation (from neurodegenerative diseases, aging, or injuries). The project is divided into three parts: the first part provides experimental protocols for studying action anticipation and related processes involved in controlling posture and gait based on state-of-the-art instrumentation. The second part provides a biofeedback strategy for these measures concerning the design of a low-cost wearable system. Finally, the third provides algorithmic processing of the biofeedback to customize the feedback based on performance conditions, including individual variability. Here, we provide a detailed experimental design that distinguishes significant postural indicators through a conjunct architecture that integrates state-of-the-art postural and gait control instrumentation and a data collection and analysis framework based on low-cost devices and freely accessible machine learning techniques. Preliminary results on 12 subjects showed that the proposed methodology accurately recognized the phases of the defined motor tasks (i.e., rotate, in position, APAs, drop, and recover) with overall F1-scores of 89.6% and 92.4%, respectively, concerning subject-independent and subject-dependent testing setups
Dispelling the Myths Behind First-author Citation Counts
Get PDFWe conducted a full-scale evaluative citation analysis study of scholars in the XML research field to explore just how different from each other author rankings resulting from different citation counting methods actually are, and to demonstrate the capability of emerging data and tools on the Web in supporting more realistic citation counting methods. Our results contest some common arguments for the continued
use of first-author citation counts in the evaluation of scholars, such as high correlations between author rankings by first-author citation counts and other citation
counting methods, and high costs of using more realistic citation counting methods that are not well-supported by the ISI databases. It is argued that increasingly available digital full text research papers make it possible for citation analysis studies to go beyond what the ISI databases have directly supported and to employ more
sophisticated methods
- …
