STUDY COMPARISON OF SVM-, K-NN- AND BACKPROPAGATION-BASED CLASSIFIER FOR IMAGE RETRIEVAL
Abstract: Classification is a
method for compiling data systematically according to the rules that have been
set previously. In recent years classification method has been proven to help
many people’s work, such as image classification, medical biology, traffic
light, text classification etc. There are many methods to solve classification
problem. This variation method makes the researchers find it difficult to
determine which method is best for a problem. This framework is aimed to
compare the ability of classification methods, such as Support Vector Machine
(SVM), K-Nearest Neighbor (K-NN), and Backpropagation, especially in study
cases of image retrieval with five category of image dataset. The result shows
that K-NN has the best average result in accuracy with 82%. It is also the
fastest in average computation time with 17,99 second during retrieve session
for all categories class. The Backpropagation, however, is the slowest among
three of them. In average it needed 883 second for training session and 41,7
second for retrieve session.
Penulis: Muhammad Athoillah,
M. Isa Irawan, Elly Matul Imah
Journal Code: jptkomputergg150003
Artikel Terkait :
Jp Teknik Komputer gg 2015
- Current Ripple Analysis of New Double-Stator AC Drive Systems
- Comparing Performances of Evolutionary Algorithms on the Emission Dispatch and Economic Dispatch Problem
- A Polynomial-based Pairwise Key Pre-distribution and Node Authentication Protocol for Wireless Sensor Networks
- Power Characteristics of Wireless Charging for Sensor Networks in Tunnels
- Influence of Sensor Nodes on the Invulnerability of Tree Network
- An Automatic Calibration Method for Near-infrared Camera in Optical Surgical Navigation
- Optimal Economic Ordering Policy with Trade Credit and Discount Cash-Flow Approach
- Design and Implementation of Network Public Opinion Analysis System
- Evaluation of the Modernization of Hydraulic Projects Management Compact-Center-Point Triangular Whitenization Weight Function
- Transmission of Real-time Video Signal with Interference Density and Human Traffic
- Correlation of Student’s Precursor Emotion towards Learning Science Interest using EEG
- The Analysis of Rank Fusion Techniques to Improve Query Relevance
- Recognition of Emotions in Video Clips: The Self-Assessment Manikin Validation
- Automatically generation and evaluation of Stop words list for Chinese Patents
- Service Engineering Based on Service Oriented Architecture Methodology
- Modelling on Tracking Test Condition of Polymer Nanocomposite using Finite Element Simulation
- A Novel Approach to Optimize Cognitive Radio Network Utilization using Cascading Technique
- Classification of Non-Functional Requirements Using Semantic-FSKNN Based ISO/IEC 9126
- Poisson Clustering Process on Hotspot in Peatland Area in Sumatera
- Computing Game and Learning State in Serious Game for Learning
- Double Difference Motion Detection and Its Application for Madura Batik Virtual Fitting Room
- Alternative Technique Reducing Complexity of Maximum Attribute Relation
- High Performance Computing on Cluster and Multicore Architecture
- Control System for Nutrient Solution of Nutrient Film Technique Using Fuzzy Logic
- Measurement of Ultra Wideband Channel Sounding Using Vector Network Analyzer