2021 IEEE International Conference on Big Data (Big Data)
Interpretability in machine learning projects and one of its aspects - causal inference - have re... more Interpretability in machine learning projects and one of its aspects - causal inference - have recently gained significant interest and focus. Due to the recent rapid appearance of frameworks, methods, algorithms and software most of which are in early stages of their development, it can be confusing for practitioners and researchers involved in a machine learning project to choose the best approach and set of techniques that would efficiently deliver valid insights while minimising the known risks of failure of data-related projects. CRISP-ML process methodology minimises this confusion by outlining a clear step-by-step process that explicitly treats of interpretability issues through every stage. The paper presents an update of CRISP-ML, which incorporates causality in a similar way and supports formalisation, design and implementation of specific instances of CRISP-ML process, subject to required levels of interpretability and causality of results. The approach is demonstrated on examples from the domains of credit risk, public health and healthcare.
Communications in Computer and Information Science, 2019
The broad application of machine learning (ML) methods and algorithms in diverse range of organis... more The broad application of machine learning (ML) methods and algorithms in diverse range of organisational settings led to the adoption of legislation, like European Union’s General Data Protection Regulation, which require firm capabilities to explain algorithmic decisions. Currently in the ML literature there does not seem to be a consensus on the definition of interpretability of a ML solution. Moreover, there is no agreement about the necessary level of interpretability of such solution and on how this level can be determined, measured and achieved. In this article, we provide such definitions based on research as well as our extensive experience of building ML solutions for various organisations across industries. We present CRISP-ML, a detailed step-by-step methodology, that provides guidance on creating the necessary level of interpretability at each stage of the solution building process and is consistent with the best practices of project management in the ML settings. We illustrate the versatility and effortless applicability of CRISP-ML with examples across a variety of industries and types of ML projects.
Federal Research Center *Computer Science and Control* of the Russian Academy of Sciences, Moscow; Plekhanov Russian University of Economics, Moscow, 2019
Industry, government and various professional organisations emphasize the need for the ICT gradua... more Industry, government and various professional organisations emphasize the need for the ICT graduates to be able to communicate in the global work environment. The elegant injection of ‘soft skills’ in the ICT curriculum is what differentiates good contemporary ICT programmes. This paper presents a joint pilot work in this area between the New Bulgarian University (NBU) and the University of Western Sydney (UWS). This blended learning approach aims to develop broad social intelligence knowledge and skills in the IT graduates, applicable by future IT specialists working in companies, ranging from small and medium enterprises to corporate global players.
This paper presents a novel 3D point cloud gesture recognition system, based on an existing low-c... more This paper presents a novel 3D point cloud gesture recognition system, based on an existing low-cost, accurate and easy to implement 2D point cloud gesture recognition system called $P. Our work improves recognition rates and lowers algorithmic complexity. We develop new 3D gestures, such as the GUN gesture and the SHAKE gesture, while also developing 3D poses like the L pose, OK pose, ROCK pose and PEACE pose for the LeapMotion Device. We demonstrate proposed gesture and pose methods on various 3D environments including a Monsoon mini-game, a cave painting interaction and a target practice scene. The average recognition rates for 3D gestures and poses were compared against the 2D, 3D and 3D+ recognition systems. The results indicate that most gestures in the proposed system were improved in comparison to the existing ones.
In the last decade students of the so-called App generation committed a “positive disruption” on ... more In the last decade students of the so-called App generation committed a “positive disruption” on existing practices of cognitive experience and the ways to access knowledge. Developing a natural feeling of reality through a permanent online presence they are using a variety of web tools and mobile apps in a NETWORK SOCIETY (under construction). In the introduction we show how a paradigm shift from INSTRUCTOR-CENTERED TEACHING to a STUDENT-BASED PARTICIPATORY LEARNING occurs within a variety of “disruptive practices” imposed by the requirements of global market interaction on education models. In this paper we focus especially on how DISRUPTIVE EXPERIENCE of so-called DIGITAL NATIVES could be followed within dynamic in-class scenarios. A social and cognitive phenomenon of “disrupting ourselves” will be approached here in the following ways. On the one side it highlights radical changes of natural communication of the App generation and their impact on educational models. On the other...
Public healthcare has a history of cautious adoption for artificial intelligence (AI) systems. Th... more Public healthcare has a history of cautious adoption for artificial intelligence (AI) systems. The rapid growth of data collection and linking capabilities combined with the increasing diversity of the data-driven AI techniques, including machine learning (ML), has brought both ubiquitous opportunities for data analytics projects and increased demands for the regulation and accountability of the outcomes of these projects. As a result, the area of interpretability and explainability of ML is gaining significant research momentum. While there has been some progress in the development of ML methods, the methodological side has shown limited progress. This limits the practicality of using ML in the health domain: the issues with explaining the outcomes of ML algorithms to medical practitioners and policy makers in public health has been a recognized obstacle to the broader adoption of data science approaches in this domain. This study builds on the earlier work which introduced CRISP-M...
In this paper we introduce a negotiation mediator in a multiagent context. When negotiation fails... more In this paper we introduce a negotiation mediator in a multiagent context. When negotiation fails, a mediator can interact with the parties, find out about their goals, ontologies, and arguments for and against negotiation outcome, and suggest solutions based on previous experience. An algorithmic schema to be instantiated with particular argumentation, semantic alignment and case-base reasoning techniques is presented. The proposal is neutral with respect to which particular technique is selected. An example illustrates the approach that is framed in the existing body of literature on argumentation and mediation.
2021 IEEE International Conference on Big Data (Big Data)
Interpretability in machine learning projects and one of its aspects - causal inference - have re... more Interpretability in machine learning projects and one of its aspects - causal inference - have recently gained significant interest and focus. Due to the recent rapid appearance of frameworks, methods, algorithms and software most of which are in early stages of their development, it can be confusing for practitioners and researchers involved in a machine learning project to choose the best approach and set of techniques that would efficiently deliver valid insights while minimising the known risks of failure of data-related projects. CRISP-ML process methodology minimises this confusion by outlining a clear step-by-step process that explicitly treats of interpretability issues through every stage. The paper presents an update of CRISP-ML, which incorporates causality in a similar way and supports formalisation, design and implementation of specific instances of CRISP-ML process, subject to required levels of interpretability and causality of results. The approach is demonstrated on examples from the domains of credit risk, public health and healthcare.
Communications in Computer and Information Science, 2019
The broad application of machine learning (ML) methods and algorithms in diverse range of organis... more The broad application of machine learning (ML) methods and algorithms in diverse range of organisational settings led to the adoption of legislation, like European Union’s General Data Protection Regulation, which require firm capabilities to explain algorithmic decisions. Currently in the ML literature there does not seem to be a consensus on the definition of interpretability of a ML solution. Moreover, there is no agreement about the necessary level of interpretability of such solution and on how this level can be determined, measured and achieved. In this article, we provide such definitions based on research as well as our extensive experience of building ML solutions for various organisations across industries. We present CRISP-ML, a detailed step-by-step methodology, that provides guidance on creating the necessary level of interpretability at each stage of the solution building process and is consistent with the best practices of project management in the ML settings. We illustrate the versatility and effortless applicability of CRISP-ML with examples across a variety of industries and types of ML projects.
Federal Research Center *Computer Science and Control* of the Russian Academy of Sciences, Moscow; Plekhanov Russian University of Economics, Moscow, 2019
Industry, government and various professional organisations emphasize the need for the ICT gradua... more Industry, government and various professional organisations emphasize the need for the ICT graduates to be able to communicate in the global work environment. The elegant injection of ‘soft skills’ in the ICT curriculum is what differentiates good contemporary ICT programmes. This paper presents a joint pilot work in this area between the New Bulgarian University (NBU) and the University of Western Sydney (UWS). This blended learning approach aims to develop broad social intelligence knowledge and skills in the IT graduates, applicable by future IT specialists working in companies, ranging from small and medium enterprises to corporate global players.
This paper presents a novel 3D point cloud gesture recognition system, based on an existing low-c... more This paper presents a novel 3D point cloud gesture recognition system, based on an existing low-cost, accurate and easy to implement 2D point cloud gesture recognition system called $P. Our work improves recognition rates and lowers algorithmic complexity. We develop new 3D gestures, such as the GUN gesture and the SHAKE gesture, while also developing 3D poses like the L pose, OK pose, ROCK pose and PEACE pose for the LeapMotion Device. We demonstrate proposed gesture and pose methods on various 3D environments including a Monsoon mini-game, a cave painting interaction and a target practice scene. The average recognition rates for 3D gestures and poses were compared against the 2D, 3D and 3D+ recognition systems. The results indicate that most gestures in the proposed system were improved in comparison to the existing ones.
In the last decade students of the so-called App generation committed a “positive disruption” on ... more In the last decade students of the so-called App generation committed a “positive disruption” on existing practices of cognitive experience and the ways to access knowledge. Developing a natural feeling of reality through a permanent online presence they are using a variety of web tools and mobile apps in a NETWORK SOCIETY (under construction). In the introduction we show how a paradigm shift from INSTRUCTOR-CENTERED TEACHING to a STUDENT-BASED PARTICIPATORY LEARNING occurs within a variety of “disruptive practices” imposed by the requirements of global market interaction on education models. In this paper we focus especially on how DISRUPTIVE EXPERIENCE of so-called DIGITAL NATIVES could be followed within dynamic in-class scenarios. A social and cognitive phenomenon of “disrupting ourselves” will be approached here in the following ways. On the one side it highlights radical changes of natural communication of the App generation and their impact on educational models. On the other...
Public healthcare has a history of cautious adoption for artificial intelligence (AI) systems. Th... more Public healthcare has a history of cautious adoption for artificial intelligence (AI) systems. The rapid growth of data collection and linking capabilities combined with the increasing diversity of the data-driven AI techniques, including machine learning (ML), has brought both ubiquitous opportunities for data analytics projects and increased demands for the regulation and accountability of the outcomes of these projects. As a result, the area of interpretability and explainability of ML is gaining significant research momentum. While there has been some progress in the development of ML methods, the methodological side has shown limited progress. This limits the practicality of using ML in the health domain: the issues with explaining the outcomes of ML algorithms to medical practitioners and policy makers in public health has been a recognized obstacle to the broader adoption of data science approaches in this domain. This study builds on the earlier work which introduced CRISP-M...
In this paper we introduce a negotiation mediator in a multiagent context. When negotiation fails... more In this paper we introduce a negotiation mediator in a multiagent context. When negotiation fails, a mediator can interact with the parties, find out about their goals, ontologies, and arguments for and against negotiation outcome, and suggest solutions based on previous experience. An algorithmic schema to be instantiated with particular argumentation, semantic alignment and case-base reasoning techniques is presented. The proposal is neutral with respect to which particular technique is selected. An example illustrates the approach that is framed in the existing body of literature on argumentation and mediation.
Uploads
Papers by Simeon SIMOFF