SVM Classifiers – Concepts and Applications to Character Recognition

Thome, Antonio

doi:10.5772/52009

Cited by 15 publications

(15 citation statements)

References 11 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Typically, a convex quadratic programming (QP) [30] is solved to determine the SVM model, but in this paper, a least squares (LS) SVM [31] method was also used. Moreover, an alternative algorithm to solve the optimization problem in SVM, called sequential minimal optimization (SMO), has been applied [32].…”

Section: Methodsmentioning

confidence: 99%

Evaluating Classifiers to Detect Arm Movement Intention from EEG Signals

Planelles

Hortal

Costa

et al. 2014

Sensors

View full text Add to dashboard Cite

This paper presents a methodology to detect the intention to make a reaching movement with the arm in healthy subjects before the movement actually starts. This is done by measuring brain activity through electroencephalographic (EEG) signals that are registered by electrodes placed over the scalp. The preparation and performance of an arm movement generate a phenomenon called event-related desynchronization (ERD) in the mu and beta frequency bands. A novel methodology to characterize this cognitive process based on three sums of power spectral frequencies involved in ERD is presented. The main objective of this paper is to set the benchmark for classifiers and to choose the most convenient. The best results are obtained using an SVM classifier with around 72% accuracy. This classifier will be used in further research to generate the control commands to move a robotic exoskeleton that helps people suffering from motor disabilities to perform the movement. The final aim is that this brain-controlled robotic exoskeleton improves the current rehabilitation processes of disabled people.

show abstract

Section: Methodsmentioning

confidence: 99%

Evaluating Classifiers to Detect Arm Movement Intention from EEG Signals

Planelles

Hortal

Costa

et al. 2014

Sensors

View full text Add to dashboard Cite

show abstract

“…Metode klasifikasi Support Vector Machine (SVM) merupakan algoritma yang bekerja menggunakan pemetaan nonlinear untuk mengubah data pelatihan asli ke dimensi yang lebih tinggi (Thome, 2012). Dimensi baru akan mencari hyperplane untuk memisahkan secara linear dan pemetaaan nonlinear yang tepat ke dimensi yang cukup tinggi.…”

Section: Support Vector Machine (Svm)unclassified

“…Konsep dari SVM yaitu bekerja dengan baik pada kumpulan data dengan dimensi tinggi. SVM juga menggunakan teknik kernel yang memetakan data asli dari dimensi asalnya menjadi dimensi lain yang relatif lebih tinggi (Thome, 2012 Support Vector Machine adalah algoritma komputasi yang membangun hyperplane atau set hyperplanes dalam ruang dimensi tinggi atau tak terbatas. SVM banyak digunakan untuk klasifikasi, regresi, dan lainnya.…”

Section: Support Vector Machine (Svm)unclassified

Sistem Pengenalan Wajah 3D Menggunakan ICP dan SVM

Lima¹,

Novamizanti²,

Susatio³

2019

JTIIK

View full text Add to dashboard Cite

Pengenalan wajah merupakan salah satu teknologi biometrik yang banyak diaplikasikan terutama pada sistem keamanan. Sistem absensi dengan wajah, mengenali pelaku tindak kriminal dengan CCTV adalah beberapa aplikasi dari pengenalan wajah. Efisiensi dan akurasi menjadi faktor utama pengenalan wajah banyak diaplikasikan. Pada penelitian ini, sistem identifikasi diimplementasikan dalam bentuk pengenalan wajah 3 dimensi berbasis template matching menggunakan metode Iterative Closest Point (ICP) dan klasifikasi Support Vector Machine (SVM). Iterative Closest Point (ICP) memberikan informasi dimensi dengan meminimalisasi kesalahan antara titik-titik dalam satu tampilan dan titik terdekatnya agar template wajah 3D yang dibuat sesuai dengan citra referensi. Sedangkan SVM adalah adalah metode klasifikasi dengan menentukan kelas citra berdasarkan informasi yang diperoleh dari proses ektraksi ciri. Hasil akhir dari penelitian ini adalah suatu aplikasi yang mampu melakukan identifikasi pengenalan pola wajah 3D. Berdasarkan confusion matrix, diperoleh bahwa sistem ini bekerja dengan precision 97,30%, recall 100,00%, accuracy 97,56% pada pengambilan frame citra sebanyak 48, iterasi ke 49, partisi 12, dan menggunakan SVM tipe OAA.AbstractFace recognition is a biometric technology that is widely applied especially in the security system. Attendance systems with faces, recognizing criminals with CCTV are some of the applications of face recognition. Efficiency and accuracy are the main factors that face recognition is widely applied. In this study, the identification system was implemented in the form of 3-dimensional face recognition based on template matching using the Iterative Closest Point (ICP) method and Support Vector Machine (SVM) classification. Iterative Closest Point (ICP) provides dimensional information by minimizing errors between points in one view and the closest point so that 3D face templates are made in accordance with the reference image. Whereas SVM is a classification method by determining the image class based on information obtained from the extraction of features. The final result of this study is an application that is able to identify 3D face pattern recognition. Based on the confusion matrix, found that this system works with 97.30% precision, recall 100.00%, 97.56% accuracy in image frame capture as much as 48 iterations to 49, the partition 12, and using the SVM-type OAA.

show abstract

“…SVM approach has some advantages compared to others classifiers. It is robust, accurate and very effective even in cases where the number of training samples is small [15].…”

Section: Voltage Data and Measurementmentioning

confidence: 99%

Cluster analysis for primary feeder identification using metering data

Khumchoo

Kongprawechnon

2015

2015 6th International Conference of Information and Communication Technology for Embedded Systems (IC-ICTES)

View full text Add to dashboard Cite

This paper presents a methodology to identify the connected feeder of high-usage customers in a primary distribution network. The proposed methodology considers voltage characteristics of radial distribution and actual measurements. Based on 15-minute intervals metering, cluster analysis is applied to categorize customer patterns on the basis of voltage correlation. Afterwards, support vector classification is also introduced for outlier assigning and cluster separation. The feasibility of this method is demonstrated on a practical distribution network of industrial estate area. The result indicates that all of the customers is correctly identified, and its correctness percentage is also better than the existent network representation. Additionally, wavelet reduction offers the same performance as the original time-domain feature but more efficient use of time.

show abstract

SVM Classifiers – Concepts and Applications to Character Recognition

Cited by 15 publications

References 11 publications

Evaluating Classifiers to Detect Arm Movement Intention from EEG Signals

Evaluating Classifiers to Detect Arm Movement Intention from EEG Signals

Sistem Pengenalan Wajah 3D Menggunakan ICP dan SVM

Cluster analysis for primary feeder identification using metering data

Contact Info

Product

Resources

About