Search results for "image processing"
showing 10 items of 3285 documents
Performance and energy optimisation in CPUs through fuzzy knowledge representation
2019
Abstract This paper presents an automatic design space exploration using processor design knowledge for the multi-objective optimisation of a superscalar microarchitecture enhanced with selective load value prediction (SLVP). We introduced new important SLVP parameters and determined their influence regarding performance, energy consumption, and thermal dissipation. We significantly enlarged initial processor design knowledge expressed through fuzzy rules and we analysed its role in the process of automatic design space exploration. The proposed fuzzy rules improve the diversity and quality of solutions, and the convergence speed of the design space exploration process. Experiments show tha…
An overview of incremental feature extraction methods based on linear subspaces
2018
Abstract With the massive explosion of machine learning in our day-to-day life, incremental and adaptive learning has become a major topic, crucial to keep up-to-date and improve classification models and their corresponding feature extraction processes. This paper presents a categorized overview of incremental feature extraction based on linear subspace methods which aim at incorporating new information to the already acquired knowledge without accessing previous data. Specifically, this paper focuses on those linear dimensionality reduction methods with orthogonal matrix constraints based on global loss function, due to the extensive use of their batch approaches versus other linear alter…
A formal model based on Game Theory for the analysis of cooperation in distributed service discovery
2016
New systems can be designed, developed, and managed as societies of agents that interact with each other by offering and providing services. These systems can be viewed as complex networks where nodes are bounded rational agents. In order to deal with complex goals, they require cooperation of the other agents to be able to locate the required services. The aim of this paper is formally and empirically analyze under which circumstances cooperation emerges in decentralized search of services. We propose a repeated game model that formalizes the interactions among agents in a search process where agents are free to choose between cooperate or not in the process. Agents make decisions based on…
Towards safe reinforcement-learning in industrial grid-warehousing
2020
Abstract Reinforcement learning has shown to be profoundly successful at learning optimal policies for simulated environments using distributed training with extensive compute capacity. Model-free reinforcement learning uses the notion of trial and error, where the error is a vital part of learning the agent to behave optimally. In mission-critical, real-world environments, there is little tolerance for failure and can cause damaging effects on humans and equipment. In these environments, current state-of-the-art reinforcement learning approaches are not sufficient to learn optimal control policies safely. On the other hand, model-based reinforcement learning tries to encode environment tra…
Using PageRank for non-personalized default rankings in dynamic markets
2017
Abstract Default ranking algorithms are used to generate non-personalized product rankings for standard consumers, for example, on landing pages of online stores. Default rankings are created without any information about the consumers’ preferences. This paper proposes using the product centrality ranking algorithm (PCRA), which solves some problems of existing default ranking algorithms: Existing approaches either have low accuracy, because they rely on only one product attribute, or they are unable to estimate ranks for new or updated products, because they use past consumer behavior, such as previous sales or ratings. The PCRA uses the PageRank centrality of products in a product dominat…
Probabilistic quantum clustering
2020
Abstract Quantum Clustering is a powerful method to detect clusters with complex shapes. However, it is very sensitive to a length parameter that controls the shape of the Gaussian kernel associated with a wave function, which is employed in the Schrodinger equation with the role of a density estimator. In addition, linking data points into clusters requires local estimates of covariance which requires further parameters. This paper proposes a Bayesian framework that provides an objective measure of goodness-of-fit to the data, to optimise the adjustable parameters. This also quantifies the probabilities of cluster membership, thus partitioning the data into a specific number of clusters, w…
Evaluating security and privacy issues of social networks based information systems in Industry 4.0
2022
[EN] The present study aimed to analyse the main risks related to security and privacy of social networks based information systems in Industry 4.0. The methodology we used is an innovative exploratory data-driven process divided into three steps. First, we performed sentiment analysis to divide the database composed of 67, 206 tweets into feelings. Second, we applied a topic-modelling algorithm to extract topics. Third, we applied textual analysis to collect insights. A total of 10 topics related to security and privacy issues were identified as results. The paper concludes with a discussion of the challenges and main concerns related to the identified topics.
An efficient method for clustered multi-metric learning
2019
Abstract Distance metric learning, which aims at finding a distance metric that separates examples of one class from examples of the other classes, is the key to the success of many machine learning tasks. Although there has been an increasing interest in this field, learning a global distance metric is insufficient to obtain satisfactory results when dealing with heterogeneously distributed data. A simple solution to tackle this kind of data is based on kernel embedding methods. However, it quickly becomes computationally intractable as the number of examples increases. In this paper, we propose an efficient method that learns multiple local distance metrics instead of a single global one.…
Adaptive memory programming for the dynamic bipartite drawing problem
2020
Abstract The bipartite drawing problem is a well-known NP-hard combinatorial optimization problem with numerous applications. The aim is to minimize the number of edge crossings in a two-layer graph, in which the edges are drawn as straight lines. We consider the dynamic variant of this problem, called the dynamic bipartite drawing problem (DBDP), which consists of adding (resp. or removing) vertices and edges to (resp. or from) a given bipartite drawing, thereby obtaining a new drawing with a layout similar to that of the original drawing. To solve this problem, we propose a tabu search method that incorporates adaptive memory to search the solution space efficiently. In this study, we com…
Towards the Design of Respond Action in Disaster Management Using Knowledge Modeling
2017
This position paper highlights current problems linked to the aspects of the multi-agency collaboration during disaster response. The coordination and cooperation depend on the information sharing and use which must face up to interoperability, access rights, and quality problems. The research project aims at providing an assessment of information impact on the disaster response in order to support the decision-making about what information shared or what quality of data used to improve the response efficiency. Our research approach propose to combine an information system able to integrate heterogeneous data and a simulation system to assess different strategies of information sharing, dis…