scholarly journals Automatic Task Classification via Support Vector Machine and Crowdsourcing

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Hyungsik Shin ◽  
Jeongyeup Paek
Keyword(s):  
Support Vector Machine ◽  
Mobile Devices ◽  
Prediction Accuracy ◽  
Training Data ◽  
Amazon Mechanical Turk ◽  
Support Vector ◽  
Data Set ◽  
English Sentence ◽  
Task Classification ◽  
Personal Assistant

Automatic task classification is a core part of personal assistant systems that are widely used in mobile devices such as smartphones and tablets. Even though many industry leaders are providing their own personal assistant services, their proprietary internals and implementations are not well known to the public. In this work, we show through real implementation and evaluation that automatic task classification can be implemented for mobile devices by using the support vector machine algorithm and crowdsourcing. To train our task classifier, we collected our training data set via crowdsourcing using the Amazon Mechanical Turk platform. Our classifier can classify a short English sentence into one of the thirty-two predefined tasks that are frequently requested while using personal mobile devices. Evaluation results show high prediction accuracy of our classifier ranging from 82% to 99%. By using large amount of crowdsourced data, we also illustrate the relationship between training data size and the prediction accuracy of our task classifier.

scholarly journals Prediction of Collapsibility of Loess of Construction Sites in Xining Based on Machine Learning Methods

2021 ◽  
Author(s):  
Qifei Zhao ◽  
Xiaojun Li ◽  
Yunning Cao ◽  
Zhikun Li ◽  
Jixin Fan
Keyword(s):  
Machine Learning ◽  
Support Vector Machine ◽  
Training Data ◽  
Support Vector ◽  
Engineering Practice ◽  
Burial Depth ◽  
Learning Methods ◽  
Data Set ◽  
Machine Learning Methods ◽  
North East

Abstract Collapsibility of loess is a significant factor affecting engineering construction in loess area, and testing the collapsibility of loess is costly. In this study, A total of 4,256 loess samples are collected from the north, east, west and middle regions of Xining. 70% of the samples are used to generate training data set, and the rest are used to generate verification data set, so as to construct and validate the machine learning models. The most important six factors are selected from thirteen factors by using Grey Relational analysis and multicollinearity analysis: burial depth、water content、specific gravity of soil particles、void rate、geostatic stress and plasticity limit. In order to predict the collapsibility of loess, four machine learning methods: Support Vector Machine (SVM), Random Subspace Based Support Vector Machine (RSSVM), Random Forest (RF) and Naïve Bayes Tree (NBTree), are studied and compared. The receiver operating characteristic (ROC) curve indicators, standard error (SD) and 95% confidence interval (CI) are used to verify and compare the models in different research areas. The results show that: RF model is the most efficient in predicting the collapsibility of loess in Xining, and its AUC average is above 80%, which can be used in engineering practice.

Application of Support Vector Machine in Determination of Real Estate Price

2012 ◽  
Vol 461 ◽  
pp. 818-821
Author(s):  
Shi Hu Zhang
Keyword(s):  
Support Vector Machine ◽  
Real Estate ◽  
Learning Algorithm ◽  
Predictive Ability ◽  
Training Data ◽  
Small Samples ◽  
Support Vector ◽  
Data Set ◽  
Real Estate Price

The problem of real estate prices are the current focus of the community's concern. Support Vector Machine is a new machine learning algorithm, as its excellent performance of the study, and in small samples to identify many ways, and so has its unique advantages, is now used in many areas. Determination of real estate price is a complicated problem due to its non-linearity and the small quantity of training data. In this study, support vector machine (SVM) is proposed to forecast the price of real estate price in China. The experimental results indicate that the SVM method can achieve greater accuracy than grey model, artificial neural network under the circumstance of small training data. It was also found that the predictive ability of the SVM outperformed those of some traditional pattern recognition methods for the data set used here.

scholarly journals Optimizing the Prediction Accuracy of Friction Capacity of Driven Piles in Cohesive Soil Using a Novel Self-Tuning Least Squares Support Vector Machine

2018 ◽  
Vol 2018 ◽  
pp. 1-9 ◽  
Author(s):  
Doddy Prayogo ◽  
Yudas Tadeus Teddy Susanto
Keyword(s):  
Support Vector Machine ◽  
Least Squares ◽  
Prediction Accuracy ◽  
Hybrid Approach ◽  
Cohesive Soil ◽  
Training Data ◽  
Support Vector ◽  
Driven Piles ◽  
Self Tuning ◽  
Friction Capacity

This research presents a novel hybrid prediction technique, namely, self-tuning least squares support vector machine (ST-LSSVM), to accurately model the friction capacity of driven piles in cohesive soil. The hybrid approach uses LS-SVM as a supervised-learning-based predictor to build an accurate input-output relationship of the dataset and SOS method to optimize the σ and γ parameters of the LS-SVM. Evaluation and investigation of the ST-LSSVM were conducted on 45 training data and 20 testing data of driven pile load tests that were compiled from previous studies. The prediction accuracy of the ST-LSSVM was then compared to other machine learning methods, namely, LS-SVM and BPNN, and was benchmarked with the previous results by neural network (NN) from Goh using coefficient of correlation (R), mean absolute error (MAE), and root mean square error (RMSE). The comparison showed that the ST-LSSVM performed better than LS-SVM, BPNN, and NN in terms of R, RMSE, and MAE. This comprehensive evaluation confirmed the capability of hybrid approach SOS and LS-SVM to modeling the accurate friction capacity of driven piles in clay. It makes for a reliable and robust assistance tool in helping all geotechnical engineers estimate friction pile capacity.

scholarly journals Mitigation of Nonlinear Impairments by Using Support Vector Machine and Nonlinear Volterra Equalizer

2019 ◽  
Vol 9 (18) ◽  
pp. 3800
Author(s):  
Rebekka Weixer ◽  
Jonas Koch ◽  
Patrick Plany ◽  
Simon Ohlendorf ◽  
Stephan Pachnicke
Keyword(s):  
Support Vector Machine ◽  
Phase Noise ◽  
Nonlinear Effects ◽  
Single Mode ◽  
Single Mode Fiber ◽  
Kernel Functions ◽  
Training Data ◽  
Support Vector ◽  
Data Set ◽  
Nonlinear Phase

A support vector machine (SVM) based detection is applied to different equalization schemes for a data center interconnect link using coherent 64 GBd 64-QAM over 100 km standard single mode fiber (SSMF). Without any prior knowledge or heuristic assumptions, the SVM is able to learn and capture the transmission characteristics from only a short training data set. We show that, with the use of suitable kernel functions, the SVM can create nonlinear decision thresholds and reduce the errors caused by nonlinear phase noise (NLPN), laser phase noise, I/Q imbalances and so forth. In order to apply the SVM to 64-QAM we introduce a binary coding SVM, which provides a binary multiclass classification with reduced complexity. We investigate the performance of this SVM and show how it can improve the bit-error rate (BER) of the entire system. After 100 km the fiber-induced nonlinear penalty is reduced by 2 dB at a BER of 3.7 × 10 − 3 . Furthermore, we apply a nonlinear Volterra equalizer (NLVE), which is based on the nonlinear Volterra theory, as another method for mitigating nonlinear effects. The combination of SVM and NLVE reduces the large computational complexity of the NLVE and allows more accurate compensation of nonlinear transmission impairments.

scholarly journals DoS attack detection method on application layer for publish-subscribe networks

2020 ◽  
pp. 50-60
Author(s):  
Dmitrii Dikii
Keyword(s):  
Support Vector Machine ◽  
New Technologies ◽  
Denial Of Service ◽  
Attack Detection ◽  
Training Data ◽  
Polynomial Kernel ◽  
Support Vector ◽  
Cyberphysical Systems ◽  
Dos Attack ◽  
Data Set

Introduction: For the development of cyberphysical systems, new technologies and data transfer protocols are being developed, in order to reduce the energy costs of communication devices. One of the modern approaches to data transmission in cyberphysical systems is the publish-subscribe model, which is subject to a denial-of-service attack. Purpose: Development of a model for detecting a DoS attack implemented at the application level of publish-subscribe networks based on the analysis of their traffic using machine learning methods. Results: A model is developed for detecting a DoS attack, operating with three classifiers depending on the message type: connection, subscription, and publication. This approach makes it possible to identify the source of an attack. That can be a network node, a particular device, or a user account. A multi-layer perceptron, the random forest algorithm, and a support vector machine of various configurations were considered as classifiers. Training and test data sets were generated for the proposed feature vector. The classification quality was evaluated by calculating the F1 score, the Matthews correlation coefficient, and accuracy. The multilayer perceptron model and the support vector machine with a polynomial kernel and SMO optimization method showed the best values of all metrics. However, in the case of the support vector machine, a slight decrease in the prediction quality was detected when the width of the traffic analysis window was close to the longest period of sending legitimate messages from the training data set. Practical relevance: The results of the research can be used in the development of intrusion detection features for cyberphysical systems using the publish-subscribe model, or other systems based on the same approach

scholarly journals Beam-hardening correction by a surface fitting and phase classification by a least square support vector machine approach for tomography images of geological samples

2015 ◽  
Vol 7 (4) ◽  
pp. 3383-3408 ◽  
Author(s):  
F. Khan ◽  
F. Enzmann ◽  
M. Kersten
Keyword(s):  
Support Vector Machine ◽  
Image Data ◽  
Least Square ◽  
Training Data ◽  
Support Vector ◽  
Beam Hardening ◽  
Reconstruction Procedure ◽  
Data Set ◽  
Corrected Image ◽  
Computed Microtomography

Abstract. In X-ray computed microtomography (μXCT) image processing is the most important operation prior to image analysis. Such processing mainly involves artefact reduction and image segmentation. We propose a new two-stage post-reconstruction procedure of an image of a geological rock core obtained by polychromatic cone-beam μXCT technology. In the first stage, the beam-hardening (BH) is removed applying a best-fit quadratic surface algorithm to a given image data set (reconstructed slice), which minimizes the BH offsets of the attenuation data points from that surface. The final BH-corrected image is extracted from the residual data, or the difference between the surface elevation values and the original grey-scale values. For the second stage, we propose using a least square support vector machine (a non-linear classifier algorithm) to segment the BH-corrected data as a pixel-based multi-classification task. A combination of the two approaches was used to classify a complex multi-mineral rock sample. The Matlab code for this approach is provided in the Appendix. A minor drawback is that the proposed segmentation algorithm may become computationally demanding in the case of a high dimensional training data set.

scholarly journals KOMPARASI MODEL SUPPORT VECTOR MACHINES (SVM) DAN NEURAL NETWORK UNTUK MENGETAHUI TINGKAT AKURASI PREDIKSI TERTINGGI HARGA SAHAM

2017 ◽  
Vol 3 (1) ◽  
Author(s):  
R. Hadapiningradja Kusumodestoni ◽  
Sarwido Sarwido
Keyword(s):  
Neural Network ◽  
Support Vector Machine ◽  
Stock Prices ◽  
Prediction Accuracy ◽  
High Accuracy ◽  
Stock Index ◽  
Support Vector ◽  
Accuracy Rate ◽  
Trend Prediction ◽  
Data Set

There are many types of investments to make money, one of which is in the form of shares. Shares is a trading company dealing with securities in the global capital markets. Stock Exchange or also called stock market is actually the activities of private companies in the form of buying and selling investments. To avoid losses in investing, we need a model of predictive analysis with high accuracy and supported by data - lots of data and accurately. The correct techniques in the analysis will be able to reduce the risk for investors in investing. There are many models used in the analysis of stock price movement prediction, in this study the researchers used models of neural networks (NN) and a model of support vector machine (SVM). Based on the background of the problems that have been mentioned in the previous description it can be formulated the problem as follows: need an algorithm that can predict stock prices, and need a high accuracy rate by adding a data set on the prediction, two algorithms will be investigated expected results last researchers can deduce where the algorithm accuracy rate predictions are the highest or accurate, then the purpose of this study was to mengkomparasi or compare between the two algorithms are algorithms Neural Network algorithm and Support Vector Machine which later on the end result has an accuracy rate forecast stock prices highest to see the error value RMSEnya. After doing research using the model of neural network and model of support vector machine (SVM) to predict the stock using the data value of the shares on the stock index hongkong dated July 20, 2016 at 16:26 pm until the date of 15 September 2016 at 17:40 pm as many as 729 data sets within an interval of 5 minute through a process of training, learning, and then continue the process of testing so the result is that by using a neural network model of the prediction accuracy of 0.503 +/- 0.009 (micro 503) while using the model of support vector machine (SVM) accuracy of the predictions for 0477 + / - 0.008 (micro: 0477) so that after a comparison can be concluded that the neural network models have trend prediction accuracy higher than the model of support vector machine (SVM).

scholarly journals Prediksi Risiko Perjalanan Transportasi Online Dari Data Telematik Menggunakan Algoritma Support Vector Machine

2020 ◽  
Vol 6 (2) ◽  
Author(s):  
Christ Memory Sitorus ◽  
Adhi Rizal ◽  
Mohamad Jajuli
Keyword(s):  
Support Vector Machine ◽  
User Satisfaction ◽  
Internet Technology ◽  
Training Data ◽  
Support Vector ◽  
Data Set ◽  
K Value ◽  
Movement Data ◽  
Svm Algorithm ◽  
Rbf Kernel

The ride-hailing service is now booming because it has been helped by internet technology, therefore many call this service online transportation. The magnitude of the potential for growth in online transportation service users also increases the risk of user satisfaction which could have declined therefore the company is increasing in its service. Both in terms of application and services provided by partners/drivers of the company. During each trip, the online transportation application will record device movement data and send it to the server. This data set is usually called telematic data. This telematics data if processed can have enormous benefits. In this study, an analysis will be conducted to predict the risk of online transportation trips using the Support Vector Machine (SVM) algorithm based on the obtained telematic data. The data obtained is telematic data so it must be processed first using feature engineering to obtain 51 features, then trained using the SVM algorithm with RBF kernel and modified C values. Every C value that is changed will be used K-Fold cross-validation first to separate the testing data and training data. The specified k value is 5. The results for each trial obtained accuracy, Receiver Operating Characteristic (ROC) and Area Under the Curves (AUC), for the best that is at C = 100 while the worst at C = 0.001.

scholarly journals Weed Detection and Classification using ICA Based SVM Classifier

2020 ◽  
Vol 8 (5) ◽  
pp. 1557-1560
Keyword(s):  
Support Vector Machine ◽  
Classification Accuracy ◽  
Learning Algorithm ◽  
Feature Weighting ◽  
Training Data ◽  
Support Vector ◽  
Svm Classifier ◽  
Classification Problems ◽  
Weed Detection ◽  
Data Set

Support vector machine (SVM) is a commonly known efficient supervised learning algorithm for classification problems. However, the classification accuracy of the SVM classifier depends on its training parameters and the training data set as well. The main objective of this paper is to optimize its parameters and feature weighting in order to improve the strength of the SVM simultaneously. In this paper, the Imperialist Competitive Algorithm based Support Vector Machine (ICA-SVM) classifier is proposed to classify the efficient weed detection. This enhanced ICA-SVM classifier is able to select the appropriate input features and to optimize the parameters of SVM and is improving the classification accuracy. Experimental results show that the ICA-SVM classification algorithm reduces the computational complexity tremendously and improves classification Accuracy.

A WEIGHTED SUPPORT VECTOR MACHINE FOR DATA CLASSIFICATION

2007 ◽  
Vol 21 (05) ◽  
pp. 961-976 ◽  
Author(s):  
XULEI YANG ◽  
QING SONG ◽  
YUE WANG
Keyword(s):  
Support Vector Machine ◽  
Clustering Algorithm ◽  
Data Classification ◽  
Training Data ◽  
Support Vector ◽  
Classification Rate ◽  
Data Set ◽  
Standard Support Vector Machine ◽  
Data Points ◽  
Sensitivity Problem

This paper presents a weighted support vector machine (WSVM) to improve the outlier sensitivity problem of standard support vector machine (SVM) for two-class data classification. The basic idea is to assign different weights to different data points such that the WSVM training algorithm learns the decision surface according to the relative importance of data points in the training data set. The weights used in WSVM are generated by a robust fuzzy clustering algorithm, kernel-based possibilistic c-means (KPCM) algorithm, whose partition generates relative high values for important data points but low values for outliers. Experimental results indicate that the proposed method reduces the effect of outliers and yields higher classification rate than standard SVM does when outliers exist in the training data set.

Sign in / Sign up

Export Citation Format

Share Document