Preliminary Bulbous Bow Design Tool Applying K Nearest Neighbours Classification and Regression Model

2021 ◽  
Vol 163 (A3) ◽  
Author(s):  
A Grech La Rosa ◽  
E Anderlini ◽  
G Thomas
Keyword(s):  
Machine Learning ◽  
Regression Models ◽  
Longitudinal Section ◽  
Design Tool ◽  
Machine Learning Techniques ◽  
Preliminary Design ◽  
Learning Techniques ◽  
Design Attributes ◽  
Nearest Neighbours ◽  
Bulbous Bow

Designing bulbous bows for ships remains a challenging task.  Their impact on different design attributes as well as their change in performance when operating off their intended design condition renders this as a multidimensional problem.  This paper explores the application of machine learning techniques to a sample of in-service vessel data to develop a preliminary design tool.  The ships' data was analysed together with their bulbous bow data to generate machine learning models using a supervised approach.  The K Nearest Neighbours Classifier and Regression models were used as the basis of the tool.  Together, these models can be used to predict whether to install a bulbous bow and the recommended dimensionless coefficients for new vessels. Generating this preliminary bulbous bow design tool required the introduction of new dimensionless coefficients that discretise the bulbous bow's longitudinal section.  The preliminary design tool gives the designer the ability to determine whether a bulbous bow should be fitted and, if so, to obtain an initial estimate of the bulbous bow required for the vessel being designed, based on key input parameters that relate to the ship and its operation.  The new design tool is demonstrated to provide preliminary design details for bulbous bows through the case studies. 

scholarly journals Machine Classification of Transient Images

2014 ◽  
Vol 10 (S306) ◽  
pp. 288-291
Author(s):  
Lise du Buisson ◽  
Navin Sivanandam ◽  
Bruce A. Bassett ◽  
Mathew Smith
Keyword(s):  
Machine Learning ◽  
Naive Bayes ◽  
Machine Learning Techniques ◽  
Imaging Data ◽  
Transient Detection ◽  
Minimum Error ◽  
Learning Techniques ◽  
Nearest Neighbours ◽  
Transient Imaging

AbstractUsing transient imaging data from the 2nd and 3rd years of the SDSS supernova survey, we apply various machine learning techniques to the problem of classifying transients (e.g. SNe) from artefacts, one of the first steps in any transient detection pipeline, and one that is often still carried out by human scanners. Using features mostly obtained from PCA, we show that we can match human levels of classification success, and find that a K-nearest neighbours algorithm and SkyNet perform best, while the Naive Bayes, SVM and minimum error classifier have performances varying from slightly to significantly worse.

scholarly journals Analysis Of Solar Power Generation Forecasting Using Machine Learning Techniques

2021 ◽  
Vol 309 ◽  
pp. 01163
Author(s):  
K. Anuradha ◽  
Deekshitha Erlapally ◽  
G. Karuna ◽  
V. Srilakshmi ◽  
K. Adilakshmi
Keyword(s):  
Machine Learning ◽  
Power Generation ◽  
Random Forest ◽  
Regression Models ◽  
Solar Power ◽  
Machine Learning Techniques ◽  
Pv Systems ◽  
Solar Power Generation ◽  
Learning Techniques ◽  
Solar Power Forecasting

Solar power is generated using photovoltaic (PV) systems all over the world. Because the output power of PV systems is alternating and highly dependent on environmental circumstances, solar power sources are unpredictable in nature. Irradiance, humidity, PV surface temperature, and wind speed are only a few of these variables. Because of the unpredictability in photovoltaic generating, it’s crucial to plan ahead for solar power generation as in solar power forecasting is required for electric grid. Solar power generation is weather-dependent and unpredictable, this forecast is complex and difficult. The impacts of various environmental conditions on the output of a PV system are discussed. Machine Learning (ML) algorithms have shown great results in time series forecasting and so can be used to anticipate power with weather conditions as model inputs. The use of multiple machine learning, Deep learning and artificial neural network techniques to perform solar power forecasting. Here in this regression models from machine learning techniques like support vector machine regressor, random forest regressor and linear regression model from which random forest regressor beaten the other two regression models with vast accuracy.

Oceanographic data reconstruction using machine learning techniques

2021 ◽  
Author(s):  
Hrvoje Kalinić ◽  
Zvonimir Bilokapić ◽  
Frano Matić
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Linear Regression ◽  
Spatial Resolution ◽  
Adriatic Sea ◽  
Machine Learning Techniques ◽  
Wind Data ◽  
Average Amplitude ◽  
Learning Techniques ◽  
Nearest Neighbours

<p>In certain measurement endeavours spatial resolution of the data is restricted, while in others data have poor temporal resolution. Typical example of these scenarios come from geoscience where measurement stations are fixed and scattered sparsely in space which results in poor spatial resolution of acquired data. Thus, we ask if it is possible to use a portion of data as a proxy to estimate the rest of the data using different machine learning techniques. In this study, four supervised machine learning methods are trained on the wind data from the Adriatic Sea and used to reconstruct the missing data. The vector wind data components at 10m height are taken from ERA5 reanalysis model in range from 1981 to 2017 and sampled every 6 hours. Data taken from the northern part of the Adriatic Sea was used to estimate the wind at the southern part of Adriatic. The machine learning models utilized for this task were linear regression, K-nearest neighbours, decision trees and a neural network. As a measure of quality of reconstruction the difference between the true and estimated values of wind data in the southern part of Adriatic was used. The result shows that all four models reconstruct the data few hundred kilometres away with average amplitude error below 1m/s. Linear regression, K-nearest neighbours, decision trees and a neural network show average amplitude reconstruction error of 0.52, 0.91, 0.76 and 0.73, and standard deviation of 1.00, 1.42, 1.23 and 1.17, respectively. This work has been supported by Croatian Science Foundation under the project UIP-2019-04-1737.</p>

scholarly journals A shell dataset, for shell features extraction and recognition

2019 ◽  
Vol 6 (1) ◽  
Author(s):  
Qi Zhang ◽  
Jianhang Zhou ◽  
Jing He ◽  
Xiaodong Cun ◽  
Shaoning Zeng ◽  
...  
Keyword(s):  
Machine Learning ◽  
Recognition Performance ◽  
Academic Research ◽  
Features Extraction ◽  
Machine Learning Techniques ◽  
New Methods ◽  
Learning Techniques ◽  
Nearest Neighbours ◽  
The World ◽  
New Machine

Abstract Shells are very common objects in the world, often used for decorations, collections, academic research, etc. With tens of thousands of species, shells are not easy to identify manually. Until now, no one has proposed the recognition of shells using machine learning techniques. We initially present a shell dataset, containing 7894 shell species with 29622 samples, where totally 59244 shell images for shell features extraction and recognition are used. Three features of shells, namely colour, shape and texture were generated from 134 shell species with 10 samples, which were then validated by two different classifiers: k-nearest neighbours (k-NN) and random forest. Since the development of conchology is mature, we believe this dataset can represent a valuable resource for automatic shell recognition. The extracted features of shells are also useful in developing and optimizing new machine learning techniques. Furthermore, we hope more researchers can present new methods to extract shell features and develop new classifiers based on this dataset, in order to improve the recognition performance of shell species.

scholarly journals Machine learning techniques to derive bioclimatic classifications for Colombia

2021 ◽  
Author(s):  
Richard Rios ◽  
Elkin A. Noguera-Urbano ◽  
Jairo Espinosa ◽  
Jose Manuael Ochoa
Keyword(s):  
Machine Learning ◽  
Principal Component Analysis ◽  
Logistic Regression ◽  
Regression Models ◽  
Principal Component ◽  
Component Analysis ◽  
Machine Learning Techniques ◽  
Study Region ◽  
Logistic Regression Models ◽  
Learning Techniques

Bioclimatic classifications seek to divide a study region into geographic areas with similar bioclimatic characteristics. In this study we proposed two bioclimatic classifications for Colombia using machine learning techniques. We firstly characterized the precipitation space of Colombia using principal component analysis. Based on Lang classification, we then projected all background sites in the precipitation space with their corresponding categories. We sequentially fit logistic regression models to re-classify all background sites in the precipitation space with six redefined Lang categories. New categories were the used to define a new modified Lang and Caldas-Lang classifications.

scholarly journals Analysed potential of big data and supervised machine learning techniques in effectively forecasting travel times from fused data

2015 ◽  
Vol 27 (6) ◽  
pp. 515-528 ◽  
Author(s):  
Ivana Šemanjski
Keyword(s):  
Machine Learning ◽  
Big Data ◽  
Random Forest ◽  
Data Sources ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Travel Times ◽  
The Road ◽  
Learning Techniques ◽  
Nearest Neighbours

Travel time forecasting is an interesting topic for many ITS services. Increased availability of data collection sensors increases the availability of the predictor variables but also highlights the high processing issues related to this big data availability. In this paper we aimed to analyse the potential of big data and supervised machine learning techniques in effectively forecasting travel times. For this purpose we used fused data from three data sources (Global Positioning System vehicles tracks, road network infrastructure data and meteorological data) and four machine learning techniques (k-nearest neighbours, support vector machines, boosting trees and random forest). To evaluate the forecasting results we compared them in-between different road classes in the context of absolute values, measured in minutes, and the mean squared percentage error. For the road classes with the high average speed and long road segments, machine learning techniques forecasted travel times with small relative error, while for the road classes with the small average speeds and segment lengths this was a more demanding task. All three data sources were proven itself to have a high impact on the travel time forecast accuracy and the best results (taking into account all road classes) were achieved for the k-nearest neighbours and random forest techniques.

Sign in / Sign up

Export Citation Format

Share Document