Abstract Multi-swarm systems base their search on multiple sub-swarms instead of one standard swa... more Abstract Multi-swarm systems base their search on multiple sub-swarms instead of one standard swarm. The use of diverse sub-swarms increases performance when optimizing multi-modal functions. However, new design decisions arise when implementing multi-swarm systems such as how to select the initial positions and initial velocities, and how to coordinate the different sub-swarms.
Recognizing the detrimental impact of information overload on user participation, in this paper w... more Recognizing the detrimental impact of information overload on user participation, in this paper we design and evaluate several algorithms to filter and rank the information on Social Networking Sites (SNS). As a first step we identify the factors that impact user evaluations of information shared through these networks in a set of regression analyses. Second, we use a Neural Network algorithm to predict three dimensions of user evaluations: affective, cognitive and instrumental value of information shared. Moreover, we design algorithms that allow not only to filter out the irrelevant information, but also rank the information on SNS in order of its relevance. As a result, the filtering algorithm accurately predicts in 73% of the cases, whereas for more than 70% of the users the individual ranking accuracy lies over 70%. The designed algorithms can be implemented by SNS providers in order to present users with more relevant and better structured information.
Matheuristic algorithms have begun to demonstrate that they can be the state of the art for some ... more Matheuristic algorithms have begun to demonstrate that they can be the state of the art for some optimization problems. This paper puts forth that they can represent a viable option also in an applicative context. The possibility to get a solution quality validation or a model grounded construction may become a significant competitive advantage against alternative approaches. This view is substantiated in this work by an application on the problem of determining the best set of locations for a constrained number of traffic counters, to the end of estimating a traffic origin / destination matrix. We implemented a Lagrangean heuristic and tested it on instances of different size. A real world use case is also reported.
AI 2011: Advances in Artificial Intelligence, Jan 1, 2011
Particle swarm optimization cannot guarantee convergence to the global optimum on multi-modal fun... more Particle swarm optimization cannot guarantee convergence to the global optimum on multi-modal functions, so multiple swarms can be useful. One means to coordinate these swarms is to use a separate search mechanism to identify different regions of the solution space for each swarm to explore. The expectation is that these independent subswarms can each perform an effective search around the region where it is initialized. This regional focus means that sub-swarms will have different goals and features when compared to standard (single) swarms. A comprehensive study of these differences leads to a new set of general guidelines for the configuration of sub-swarms in multi-swarm systems.
Abstract Multi-swarm systems base their search on multiple sub-swarms instead of one standard swa... more Abstract Multi-swarm systems base their search on multiple sub-swarms instead of one standard swarm. The use of diverse sub-swarms increases performance when optimizing multi-modal functions. However, new design decisions arise when implementing multi-swarm systems such as how to select the initial positions and initial velocities, and how to coordinate the different sub-swarms.
Recognizing the detrimental impact of information overload on user participation, in this paper w... more Recognizing the detrimental impact of information overload on user participation, in this paper we design and evaluate several algorithms to filter and rank the information on Social Networking Sites (SNS). As a first step we identify the factors that impact user evaluations of information shared through these networks in a set of regression analyses. Second, we use a Neural Network algorithm to predict three dimensions of user evaluations: affective, cognitive and instrumental value of information shared. Moreover, we design algorithms that allow not only to filter out the irrelevant information, but also rank the information on SNS in order of its relevance. As a result, the filtering algorithm accurately predicts in 73% of the cases, whereas for more than 70% of the users the individual ranking accuracy lies over 70%. The designed algorithms can be implemented by SNS providers in order to present users with more relevant and better structured information.
Matheuristic algorithms have begun to demonstrate that they can be the state of the art for some ... more Matheuristic algorithms have begun to demonstrate that they can be the state of the art for some optimization problems. This paper puts forth that they can represent a viable option also in an applicative context. The possibility to get a solution quality validation or a model grounded construction may become a significant competitive advantage against alternative approaches. This view is substantiated in this work by an application on the problem of determining the best set of locations for a constrained number of traffic counters, to the end of estimating a traffic origin / destination matrix. We implemented a Lagrangean heuristic and tested it on instances of different size. A real world use case is also reported.
AI 2011: Advances in Artificial Intelligence, Jan 1, 2011
Particle swarm optimization cannot guarantee convergence to the global optimum on multi-modal fun... more Particle swarm optimization cannot guarantee convergence to the global optimum on multi-modal functions, so multiple swarms can be useful. One means to coordinate these swarms is to use a separate search mechanism to identify different regions of the solution space for each swarm to explore. The expectation is that these independent subswarms can each perform an effective search around the region where it is initialized. This regional focus means that sub-swarms will have different goals and features when compared to standard (single) swarms. A comprehensive study of these differences leads to a new set of general guidelines for the configuration of sub-swarms in multi-swarm systems.
Uploads
Papers by Antonio Bolufé