Search results for "Machine"
showing 10 items of 2592 documents
Predicting Heuristic Search Performance with PageRank Centrality in Local Optima Networks
2015
Previous studies have used statistical analysis of fitness landscapes such as ruggedness and deceptiveness in order to predict the expected quality of heuristic search methods. Novel approaches for predicting the performance of heuristic search are based on the analysis of local optima networks (LONs). A LON is a compressed stochastic model of a fitness landscape's basin transitions. Recent literature has suggested using various LON network measurements as predictors for local search performance.In this study, we suggest PageRank centrality as a new measure for predicting the performance of heuristic search methods using local search. PageRank centrality is a variant of Eigenvector centrali…
Replacing radiative transfer models by surrogate approximations through machine learning
2015
Physically-based radiative transfer models (RTMs) help in understanding the processes occurring on the Earth's surface and their interactions with vegetation and atmosphere. However, advanced RTMs can take a long computational time, which makes them unfeasible in many real applications. To overcome this problem, it has been proposed to substitute RTMs through so-called emulators. Emulators are statistical models that approximate the functioning of RTMs. They are advantageous in real practice because of the computational efficiency and excellent accuracy and flexibility for extrapolation. We here present an ‘Emulator toolbox’ that enables analyzing three multi-output machine learning regress…
Process mechanics analysis in single point incremental forming
2004
The request of highly differentiated products and the need of process flexibility have brought the researchers to focus the attention on innovative sheet forming processes. Industrial application of conventional processes is, in fact, economically convenient just for large scale productions; furthermore conventional processes do not allow to fully satisfy the mentioned demand of flexibility. In this contest, single point incremental forming (SPIF) is an innovative and flexible answer to market requests. The process is characterized by a peculiar process mechanics, being the sheet plastically deformed only through a localised stretching mechanism. Some recent experimental studies have shown …
Control of hysteretic instability in rotating machinery by elastic suspension systems subject to dry and viscous friction
2010
Abstract Most of the undesired whirling motions of rotating machines can be efficiently reduced by supporting journal boxes elastically and controlling their movement by viscous dampers or by dry friction surfaces normal to the shaft axis, which rub against the frame. In the case of dry dampers, resonance ranges of the floating support configuration can be easily cut off by planning a motionless adhesive state of the friction surfaces. On the contrary, the dry friction contact must change automatically into sliding conditions when the fixed support resonances are to be feared. Moreover, the whirl amplitude can be restrained throughout the speed range by a proper choice of the suspension-to-…
Virtual Synchronous Machine Control of RES Plants in Isolated Power Systems
2022
Because of the increase in renewable energy sources (RESs) share, new control strategies of isolated power systems have been developed to improve the frequency and voltage stability of inverter-interfaced RESs. A voltage source converter (VSC) with a virtual synchronous machine (VSM) is among the most promising control schemes. This paper demonstrates how VSM control of inverter-interfaced RES can be efficiently used to improve the dynamic stability in small isolated power systems. In the proposed analysis, the RESs of a Mediterranean island are assumed interfaced to the grid by VSCs with a swing controller and a vector-current controller (VCC) with two different options for the reference c…
On Unsupervised Methods for Medical Image Segmentation: Investigating Classic Approaches in Breast Cancer DCE-MRI
2021
Unsupervised segmentation techniques, which do not require labeled data for training and can be more easily integrated into the clinical routine, represent a valid solution especially from a clinical feasibility perspective. Indeed, large-scale annotated datasets are not always available, undermining their immediate implementation and use in the clinic. Breast cancer is the most common cause of cancer death in women worldwide. In this study, breast lesion delineation in Dynamic Contrast Enhanced MRI (DCE-MRI) series was addressed by means of four popular unsupervised segmentation approaches: Split-and-Merge combined with Region Growing (SMRG), k-means, Fuzzy C-Means (FCM), and spatial FCM (…
Robustness, Stability, and Fidelity of Explanations for a Deep Skin Cancer Classification Model
2022
Skin cancer is one of the most prevalent of all cancers. Because of its being widespread and externally observable, there is a potential that machine learning models integrated into artificial intelligence systems will allow self-screening and automatic analysis in the future. Especially, the recent success of various deep machine learning models shows promise that, in the future, patients could self-analyse their external signs of skin cancer by uploading pictures of these signs to an artificial intelligence system, which runs such a deep learning model and returns the classification results. However, both patients and dermatologists, who might use such a system to aid their work, need to …
DNA Computing: Concepts for Medical Applications
2022
The branch of informatics that deals with construction and operation of computers built of DNA, is one of the research directions which investigates issues related to the use of DNA as hardware and software. This concept assumes the use of DNA computers due to their biological origin mainly for intelligent, personalized and targeted diagnostics frequently related to therapy. Important elements of this concept are (1) the retrieval of unique DNA sequences using machine learning methods and, based on the results of this process, (2) the construction/design of smart diagnostic biochip projects. The authors of this paper propose a new concept of designing diagnostic biochips, the key elements o…
Context-Aware Visual Exploration of Molecular Datab
2006
Facilitating the visual exploration of scientific data has received increasing attention in the past decade or so. Especially in life science related application areas the amount of available data has grown at a breath taking pace. In this paper we describe an approach that allows for visual inspection of large collections of molecular compounds. In contrast to classical visualizations of such spaces we incorporate a specific focus of analysis, for example the outcome of a biological experiment such as high throughout screening results. The presented method uses this experimental data to select molecular fragments of the underlying molecules that have interesting properties and uses the res…
Optimization of Cultural Heritage Virtual Environments for Gaming Applications
2020
Serious games are games with a purpose beyond entertainment and are widely acknowledged as fruitful tools for learning and developing skills across multiple domains, including educational enhancement. In the last few years, the world of serious games has widely increased. The use of these types of games can aid in classrooms to not only help the students learn concepts but also to improve their motivation to do so. However, designing games necessitates very specialized personnel and the process can often be costly and slow. The adaptions of the design to the implantation phase are also difficult and the process needs more focus. The challenge of this study was to create a game within the co…