PhD Candidate Edward Guillen

Committee: International Scientific Committee of Electronics and Communication Engineering
University: Military University Nueva Granada
Department: Telecommunications
Research Fields: network intrusion detection, machine learning, artificial neural network,anomaly detection module,

Publications

5 Anomaly Detection with ANN and SVM for Telemedicine Networks

Authors: Edward Guillen, Jeisson Sánchez, Carlos Omar Ramos

Abstract:

In recent years, a wide variety of applications are developed with Support Vector Machines -SVM- methods and Artificial Neural Networks -ANN-. In general, these methods depend on intrusion knowledge databases such as KDD99, ISCX, and CAIDA among others. New classes of detectors are generated by machine learning techniques, trained and tested over network databases. Thereafter, detectors are employed to detect anomalies in network communication scenarios according to user’s connections behavior. The first detector based on training dataset is deployed in different real-world networks with mobile and non-mobile devices to analyze the performance and accuracy over static detection. The vulnerabilities are based on previous work in telemedicine apps that were developed on the research group. This paper presents the differences on detections results between some network scenarios by applying traditional detectors deployed with artificial neural networks and support vector machines.

Keywords: Support Vector Machines, Anomaly Detection, back-propagation neural networks, network intrusion detection systems

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1434
4 Evaluating Performance of an Anomaly Detection Module with Artificial Neural Network Implementation

Authors: Edward Guillen, Jhordany Rodríguez, Rafael Páez

Abstract:

Anomaly detection techniques have been focused on two main components: data extraction and selection and the second one is the analysis performed over the obtained data. The goal of this paper is to analyze the influence that each of these components has over the system performance by evaluating detection over network scenarios with different setups. The independent variables are as follows: the number of system inputs, the way the inputs are codified and the complexity of the analysis techniques. For the analysis, some approaches of artificial neural networks are implemented with different number of layers. The obtained results show the influence that each of these variables has in the system performance.

Keywords: Machine Learning, Artificial Neural Network, network intrusion detection

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1677
3 Throughput Optimization on Wireless Networks by Increasing the Maximum Transmission Unit

Authors: Edward Guillen, Stephanne Rodríguez, Jhordany Rodríguez

Abstract:

Throughput enhancement can be achieved with two main approaches. The first one is by the increase of transmission rate and the second one is reducing the control traffic. This paper focuses on how the throughput can be enhanced by increasing Maximum Transmission Unit -MTU. Transmission of larger packets can cause a throughput improvement by reducing IP overhead. Analysis results are obtained by a mathematical model and simulation tools with a main focus on wireless channels.

Keywords: Wireless Networks, throughput enhancement, Maximum Transfer Unit

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3182
2 Weaknesses and Strengths Analysis over Wireless Network Security Standards

Authors: Edward Guillen, Daniel Padilla

Abstract:

Several wireless networks security standards have been proposed and widely implemented in both business and home environments in order to protect the network from unauthorized access. However, the implementation of such standards is usually achieved by network administrators without even knowing the standards- weaknesses and strengths. The intention of this paper is to evaluate and analyze the impact over the network-s security due to the implementation of the wireless networks security standards WEP, WPA and WLAN 802.1X.

Keywords: Wireless Security, WPA, vulnerabilities analysis, WEP

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1779
1 Gait Recognition System: Bundle Rectangle Approach

Authors: Edward Guillen, Daniel Padilla, Adriana Hernandez, Kenneth Barner

Abstract:

Biometrics methods include recognition techniques such as fingerprint, iris, hand geometry, voice, face, ears and gait. The gait recognition approach has some advantages, for example it does not need the prior concern of the observed subject and it can record many biometric features in order to make deeper analysis, but most of the research proposals use high computational cost. This paper shows a gait recognition system with feature subtraction on a bundle rectangle drawn over the observed person. Statistical results within a database of 500 videos are shown.

Keywords: Security, Biometrics, Human identification, gait recognition, Autentication

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1530

Abstracts

2 Anomaly Detection with ANN and SVM for Telemedicine Networks

Authors: Edward Guillen, Jeisson Sánchez, Carlos Omar Ramos

Abstract:

In recent years, a wide variety of applications are developed with Support Vector Machines -SVM- methods and Artificial Neural Networks -ANN-. In general, these methods depend on intrusion knowledge databases such as KDD99, ISCX, and CAIDA among others. New classes of detectors are generated by machine learning techniques, trained and tested over network databases. Thereafter, detectors are employed to detect anomalies in network communication scenarios according to user’s connections behavior. The first detector based on training dataset is deployed in different real-world networks with mobile and non-mobile devices to analyze the performance and accuracy over static detection. The vulnerabilities are based on previous work in telemedicine apps that were developed on the research group. This paper presents the differences on detections results between some network scenarios by applying traditional detectors deployed with artificial neural networks and support vector machines.

Keywords: Support Vector Machines, Anomaly Detection, back-propagation neural networks, network intrusion detection systems

Procedia PDF Downloads 195
1 Evaluating Performance of an Anomaly Detection Module with Artificial Neural Network Implementation

Authors: Edward Guillen, Jhordany Rodríguez, Rafael Páez

Abstract:

Anomaly detection techniques have been focused on two main components: data extraction and selection and the second one is the analysis performed over the obtained data. The goal of this paper is to analyze the influence that each of these components has over the system performance by evaluating detection over network scenarios with different setups. The independent variables are as follows: the number of system inputs, the way the inputs are codified and the complexity of the analysis techniques. For the analysis, some approaches of artificial neural networks are implemented with different number of layers. The obtained results show the influence that each of these variables has in the system performance.

Keywords: Machine Learning, Artificial Neural Network, network intrusion detection, anomaly detection module

Procedia PDF Downloads 185