TY - GEN
T1 - Optimized Convolutional Gabor Using Particle Swarm Optimization
T2 - 29th International Symposium on Micro-NanoMechatronics and Human Science, MHS 2018
AU - Abdillah, Bariqi
AU - Jati, Grafika
AU - Alhamidi, Machmud R.
AU - Jatmiko, Wisnu
PY - 2018/12
Y1 - 2018/12
N2 - The increase of data is becoming faster, so the amount of data becomes very large, which in the end creates a big data problem. Three aspects that are often identified as problems faced with big data are volume, velocity, and variety. In this paper, the big data problem that will be solved is the problem of volume, which is quantity/ amount of data. Several common methods for solving the problem are compressing the data, reducing the dimensionality feature, and managing the workflow storage. This paper applies the Particle Swarm optimization, an evolutionary algorithm, in dimensionality feature reduction. The case study used in this paper is image data with classification task. We exhibit the framework by applying particle swarm optimization algorithm in the reduction feature. In practice, such frameworks can not only be done for data images but can be used for other data with classification task. This paper compares the performance with and without feature selection. From the results of the comparison, feature selection achieves a better accuracy and a faster computation time.
AB - The increase of data is becoming faster, so the amount of data becomes very large, which in the end creates a big data problem. Three aspects that are often identified as problems faced with big data are volume, velocity, and variety. In this paper, the big data problem that will be solved is the problem of volume, which is quantity/ amount of data. Several common methods for solving the problem are compressing the data, reducing the dimensionality feature, and managing the workflow storage. This paper applies the Particle Swarm optimization, an evolutionary algorithm, in dimensionality feature reduction. The case study used in this paper is image data with classification task. We exhibit the framework by applying particle swarm optimization algorithm in the reduction feature. In practice, such frameworks can not only be done for data images but can be used for other data with classification task. This paper compares the performance with and without feature selection. From the results of the comparison, feature selection achieves a better accuracy and a faster computation time.
KW - Big Data
KW - classification
KW - dimensionality reduction
KW - feature selection
KW - Particle Swarm optimization
KW - Vehicle classification
UR - http://www.scopus.com/inward/record.url?scp=85075003920&partnerID=8YFLogxK
U2 - 10.1109/MHS.2018.8886933
DO - 10.1109/MHS.2018.8886933
M3 - Conference contribution
T3 - MHS 2018 - 2018 29th International Symposium on Micro-NanoMechatronics and Human Science
BT - MHS 2018 - 2018 29th International Symposium on Micro-NanoMechatronics and Human Science
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 10 December 2018 through 12 December 2018
ER -