Search results for " image processing."
showing 10 items of 2265 documents
Hybrid chaotic firefly decision making model for Parkinson’s disease diagnosis
2020
Parkinson’s disease is found as a progressive neurodegenerative condition which affects motor circuit by the loss of up to 70% of dopaminergic neurons. Thus, diagnosing the early stages of incidence is of great importance. In this article, a novel chaos-based stochastic model is proposed by combining the characteristics of chaotic firefly algorithm with Kernel-based Naïve Bayes (KNB) algorithm for diagnosis of Parkinson’s disease at an early stage. The efficiency of the model is tested on a voice measurement dataset that is collected from “UC Irvine Machine Learning Repository.” The dynamics of chaos optimization algorithm will enhance the firefly algorithm by introducing six types of chao…
Intelligent Cloud Storage Management for Layered Tiers
2018
Today, the cloud offers a large array of possibilities for storage, with this flexibility comes also complexity. This complexity stems from the variety of storage mediums, such as, blob storage or NoSQL tables, and also from the different cost tiers within these systems. A strategic thinking to navigate this complex cloud storage landscape is important, not only for cost saving but also for prioritizing information, this prioritization has wider implications in other domains such as the Big Data realm, especially for governance and efficiency. In this paper we propose a strategy centered around probabilistic graphical model (PGM), this heuristic oriented management and organizational strate…
Robotic assistance for industrial sanding with a smooth approach to the surface and boundary constraints
2021
[EN] Surface treatment operations, such as sanding, deburring, finishing, grinding, polishing, etc. are progressively becoming more automated using robotic systems. However, previous research in this field used a completely automatic operation of the robot system or considered a low degree of human-robot interaction. Therefore, to overcome this issue, this work develops a truly synergistic cooperation between the human operator and the robot system to get the best from both. In particular, in the application developed in this work the human operator provides flexibility, guiding the tool of the robot system to treat arbitrary regions of the workpiece surface; while the robot system provides…
Towards a Reference Architecture for Model-Driven Business Apps
2016
Model-driven development techniques have been proposed for cross-platform app development. Typically, an individual domain-specific language (DSL) is used. The MD² framework consists of a DSL for business apps and generators, which transform a domain model to native platform code. Prior research on it focused on language and general generator design, this paper accentuates the code generation stage. A reference architecture for the generated apps is proposed to accelerate the development of new generators for which architectural decisions had been made on ad-hoc basis up to now. Moreover, generators are going to expose similar structures that facilitate maintenance. Our proposal takes MD²'s…
A Feature Rich Distance-Based Many-Objective Visualisable Test Problem Generator
2019
In optimiser analysis and design it is informative to visualise how a search point/population moves through the design space over time. Visualisable distance-based many-objective optimisation problems have been developed whose design space is in two-dimensions with arbitrarily many objective dimensions. Previous work has shown how disconnected Pareto sets may be formed, how problems can be projected to and from arbitrarily many design dimensions, and how dominance resistant regions of design space may be defined. Most recently, a test suite has been proposed using distances to lines rather than points. However, active use of visualisable problems has been limited. This may be because the ty…
Blockchain-based DR logic: a trade-off between system operator's and customer's needs
2020
This paper describes a way to include the end users of the electrical network in the Demand Response mechanism using the Blockchain technology and the Smart Contract concepts, thus developing a distributed system where customers can communicate directly with the system operator to provide their flexibility in a transparent, secure and traceable way.The historical data on energy consumption and production of the customers is recorded on the Blockchain, with the Smart Contract evaluating the baseline and the potential support that each customer can provide to fulfill the requested load adaptation communicated by the grid operator. The baseline and the optimal power reduction for a customer (e…
Selecting between CNC turning centers using a combined AHP and fuzzy approach
2019
Abstract CNC turning centers (CNCTC) are designed to perform simple turning operations, for parts having a symmetry axis. However, the flexibility of these machine-tools is increasing rapidly. Supplementary modules, such as Y-axis and driven tools, which allow the user to perform milling operations, are fitted on CNCTC. Selecting the proper CNCTC, out of a great number of commercially available solution has become a very difficult task. A combined approach using Analytic Hierarchy Process (AHP) and fuzzy logic is proposed, to assist the decision-making process of choosing between three variants of CNCTC.
Cloud Computing Vulnerabilities Analysis
2019
Nowadays cloud computing technologies are the most widely used tools due to their great flexibility and also to their lower maintenance costs. Many vendors of cloud computing have appeared on the market for each type of cloud. These solutions still pose certain vulnerabilities and work to improve the security of cloud computing technologies. We analyze the main cloud computing solutions, analyze the vulnerabilities identified for these solutions, and also calculate the impact of these vulnerabilities based on the NVD scores. We average the scores for each solution for each cloud computing model. This way, we can see the impact of the vulnerabilities identified so far for each cloud computin…
Collaborative development of a CPS-based production system
2019
Abstract The paper describes the collaborative processes and technologies used to develop a prototype for a Cyber-Physical Production System of USB sticks. The development of this system follows the model-based approach where co-simulations of different components, detailed at different level of abstractions, serve as a basis for structured dialogue between specialised teams and agreement on shared interactions. The focus is primarily on the co-simulation technology, allowing a gradual increase of fidelity and independent testing and validation of the composing subsystems. This technology may be equally complemented with group decision-making tools to better support the collaboration during…
Improving Serendipity and Accuracy in Cross-Domain Recommender Systems
2017
Cross-domain recommender systems use information from source domains to improve recommendations in a target domain, where the term domain refers to a set of items that share attributes and/or user ratings. Most works on this topic focus on accuracy but disregard other properties of recommender systems. In this paper, we attempt to improve serendipity and accuracy in the target domain with datasets from source domains. Due to the lack of publicly available datasets, we collect datasets from two domains related to music, involving user ratings and item attributes. We then conduct experiments using collaborative filtering and content-based filtering approaches for the purpose of validation. Ac…