A novel online incremental and decremental learning algorithm based on variable support vector machine

Chen, Yuantao; Xiong, Jie; Wang, Xu; Zuo, Jiakuo

doi:10.1007/s10586-018-1772-4

Cited by 133 publications

(63 citation statements)

References 17 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Especially, support vector machine (SVM), one kind of learning algorithm performs ideally in classification. Therefore, we chose this algorithm in this paper because of relatively few sample requirements, nonlinear and high dimensional pattern recognition [5][6][7].…”

Section: Methodsmentioning

confidence: 99%

Wearable Resistive-based Gesture-Sensing Interface Bracelet

Chen

Liang

Assaad

et al. 2019

2019 UK/ China Emerging Technologies (UCET)

View full text Add to dashboard Cite

This paper presents a gesture recognition system based on the pressure changes produced by wrist tendon movements for wearable devices. The data of the pressure variations are captured by means of flexible and ultrathin force resistive sensors. A learning algorithm, Support Vector Machine, helps the system to distinguish various hand gestures through developed programming on MATLAB after extracting the key features of data. In order to achieve rapid gesture recognition with a shorter computational time, higher precision and less space complexity, genetic optimization algorithm is used to find the optimal parameter c (cost factor) and g (kernel function parameters) in SVM algorithm. The SVM parameter optimization improves the classification accuracy and the performance of the classifier. Finally, developed wearable resistive-based wrist-worn gesture sensing system classifies the hand gesture with high accuracy (>70%) and the results are displayed on the GUIDE user interface.

show abstract

Section: Methodsmentioning

confidence: 99%

Wearable Resistive-based Gesture-Sensing Interface Bracelet

Chen

Liang

Assaad

et al. 2019

2019 UK/ China Emerging Technologies (UCET)

View full text Add to dashboard Cite

show abstract

“…Academic research works done in Qian et al are based on SVM to deal with QoE prediction. Some relevant research works done in Paudel et al, Menkovski et al, and Rodr'ıguez et al to make QoE estimation are based on SVM, discriminate analysis, decision tree, neural network, Bayesian, and random neural networks (RNN), while Machado et al based their study on artificial neural network (ANN) to estimate QoE metrics in WiMAX networks or on KNN in Kang et al…”

Section: Related Work On Big Data Tools and Machine Learning Algorithmsmentioning

confidence: 99%

“…The objective of past network techniques was to control the metrics of network QoS. This previous work described the architecture of the proposed approach and especially the monitoring module based on ML algorithms.…”

Section: Web Qoe Monitoring Systemmentioning

confidence: 99%

“…At first, we distinguish the relationship between QoS and QoE like it was studied in Fiedler et al and Khan et al 23,24 Several research works discussed different approaches based on ML for predicting QoE. 25 So, Le Callet et al 26 [33][34][35] to make QoE estimation are based on SVM, discriminate analysis, [36][37][38][39] decision tree, neural network, 36,40,[43][44][45][46] Bayesian, and random neural networks (RNN), while Machado et al 41 based their study on artificial neural network (ANN) to estimate QoE metrics in WiMAX networks or on KNN in Kang et al 42 ML algorithms help to deduce knowledge from stocked data and enable automation in the area of QoS and QoE management for operators and services providers. Different learning paradigms and ML techniques are applied to solve prediction problem in the QoE context by predicting MOS or estimating the user expectation before serving them (video or web pages).…”

Section: • K-nearest Neighbormentioning

confidence: 99%

See 1 more Smart Citation

WBQoEMS: Web browsing QoE monitoring system based on prediction algorithms

Letaïfa

2019

Int J Communication

View full text Add to dashboard Cite

Summary These years, researchers are interested in the web users perceived Quality of Experience called web QoE. Monitoring web browsing QoE can help service providers to determine if network conditions are contributing to user satisfaction. Making a relationship between web QoE and network parameters helps them to evaluate potential solutions in order to increase user satisfaction. Recent literature use metrics such as page load, wait time, or SpeedIndex to estimate the QoE of web users. However, QoE is a measure that remains subjective, and its evaluation is expensive and tedious because it requires a high human participation. Using Big Data Analytics, web service providers can anticipate user's behavior and take necessary actions which lead to better QoS/QoE. In this work, we have shown that we can make a relationship between QoS and QoE and predict QoE thanks to machine learning (ML) algorithms or deep learning approach. In fact, these new prediction solutions can help in prediction of the web QoE. Yet, this work focuses on some key performance indicators in the field of web browsing where Big Data Analytics are used. It gives a predictive solution based on Big Data tools to monitor and work toward enhancing QoS and QoE for the web users. Therefore, the design of a tool that can objectively measure this QoE with reasonable accuracy and in real time has become a primary need which is an interesting challenge to solve. As a first contribution, we analyzed the impact of network behavior on the quality of web services, then described some relevant research works done in ML field to predict QoE. We finally give the proposed tool based on prediction algorithms from ML and deep learning both used to monitor web QoE.

show abstract

“…Then, using the man-machine interactive method for the image segmentation process, the algorithm achieved artificial image segmentation. Then, another work [8] designed and optimized this algorithm. Further designs of the proposed algorithm were then presented in the literature [9,10].…”

Section: Introductionmentioning

confidence: 99%

A study of a clothing image segmentation method in complex conditions using a features fusion model

Zhang

Liu

2019

Automatika

View full text Add to dashboard Cite

According to a priori knowledge in complex conditions, this paper proposes an unsupervised image segmentation algorithm to be used for clothing images that combines colour and texture features. First, block truncation encoding is used to divide the traditional three-dimensional colour space into a six-dimensional colour space so that more fine colour features can be obtained. Then, a texture feature based on the improved local binary pattern (LBP) algorithm is designed and used to describe the clothing image with the colour features. After that, according to the statistical appearance law of the object region and background information in the clothing image, a bisection method is proposed for the segmentation operation. Since the image is divided into several subimage blocks, bisection image segmentation will be accomplished more efficiently. The experimental results show that the proposed algorithm can quickly and effectively extract effective clothing regions from complex circumstances without any artificial parameters. The proposed clothing image segmentation method will play an important role in computer vision, machine learning applications, pattern recognition and intelligent systems.

show abstract

A novel online incremental and decremental learning algorithm based on variable support vector machine

Cited by 133 publications

References 17 publications

Wearable Resistive-based Gesture-Sensing Interface Bracelet

Wearable Resistive-based Gesture-Sensing Interface Bracelet

WBQoEMS: Web browsing QoE monitoring system based on prediction algorithms

A study of a clothing image segmentation method in complex conditions using a features fusion model

Contact Info

Product

Resources

About