Intrusion Detection Method Based on Sparse Expression for SVM

Although Support Vector Machines (SVM) are widely used for classifying human motion patterns, their application in the automatic recognition of dynamic and static activities of daily life in the healthy older adults is limited. Using a body mounted wireless inertial measurement unit (IMU), this paper explores the use of SVM approach for classifying dynamic (walking) and static (sitting, standing and lying) activities of the older adults. Specifically, data formatting and feature extraction methods associated with IMU signals are discussed. To evaluate the performance of the SVM algorithm, the effects of two parameters involved in SVM algorithm—the soft margin constant C and the kernel function parameter γ—are investigated. The changes associated with adding white-noise and pink-noise on these two parameters along with adding different sources of movement variations (i.e., localized muscle fatigue and mixed activities) are further discussed. The results indicate that the SVM algorithm is capable of keeping high overall accuracy by adjusting the two parameters for dynamic as well as static activities, and may be applied as a tool for automatically identifying dynamic and static activities of daily life in the older adults.

Download Full-text

An Image Hided-Data Detection Method Combining Markov Chain and Support Vector Machines

Applied Mechanics and Materials ◽

10.4028/www.scientific.net/amm.128-129.520 ◽

2011 ◽

Vol 128-129 ◽

pp. 520-524

Author(s):

Hui Min Zhao ◽

Li Zhu

Keyword(s):

Markov Chain ◽

Support Vector Machines ◽

Spread Spectrum ◽

Detection Method ◽

Markov Chain Model ◽

Support Vector ◽

Data Detection ◽

Chain Model ◽

Detection Rates ◽

Vector Machines

An image hided-data detection method is proposed combining 2-D Markov chain model and Support Vector Machines (SVM) by the paper, in which image pixels are predicted with their neighboring pixels, and the prediction-error image is generated by subtracting the prediction value from the pixel value. Support vector machines are utilized as classifier. As embedding data rate being 0.1 bpp, experimental investigation utilizing spread spectrum (SS) and a Quantization Index Modulation (QIM) method data hiding method respectively , correction detection rates are all above 90% . For optimum LSB method ,the method achieves a detection rate from 50% to 90% above with 0.01bpp-0.3bpp various embedding data rates.

Download Full-text

Automatic Detection of Dynamic and Static Activities of the Older Adults Using a Wearable Sensor and Support Vector Machines

Sci ◽

10.3390/sci2030060 ◽

2020 ◽

Vol 2 (3) ◽

pp. 60

Author(s):

Jian Zhang ◽

Rahul Soangra ◽

Thurmon E. Lockhart

Keyword(s):

Older Adults ◽

Support Vector Machines ◽

Daily Life ◽

Human Motion ◽

Function Parameter ◽

Support Vector ◽

Activities Of Daily Life ◽

Svm Algorithm ◽

Vector Machines ◽

Two Parameters

Although Support Vector Machines (SVM) are widely used for classifying human motion patterns, their application in the automatic recognition of dynamic and static activities of daily life in the healthy older adults is limited. Using a body mounted wireless inertial measurement unit (IMU), this paper explores the use of SVM approach for classifying dynamic (walking) and static (sitting, standing and lying) activities of the older adults. Specifically, data formatting and feature extraction methods associated with IMU signals are discussed. To evaluate the performance of the SVM algorithm, the effects of two parameters involved in SVM algorithm—the soft margin constant C and the kernel function parameter γ—are investigated. The changes associated with adding white-noise and pink-noise on these two parameters along with adding different sources of movement variations (i.e., localized muscle fatigue and mixed activities) are further discussed. The results indicate that the SVM algorithm is capable of keeping high overall accuracy by adjusting the two parameters for dynamic as well as static activities, and may be applied as a tool for automatically identifying dynamic and static activities of daily life in the older adults.

Download Full-text