A5075803496- Network Security and Intrusion Detection
- Anomaly Detection Techniques and Applications
- Internet Traffic Analysis and Secure E-voting
- Remote Sensing in Agriculture
- Network Packet Processing and Optimization
- Advanced Manufacturing and Logistics Optimization
- Remote Sensing and Land Use
- IoT and GPS-based Vehicle Safety Systems
- Autonomous Vehicle Technology and Safety
- Vehicle License Plate Recognition
- Time Series Analysis and Forecasting
- Industrial Automation and Control Systems
- Robotic Path Planning Algorithms
- Statistical Mechanics and Entropy
- Video Surveillance and Tracking Methods
- Remote-Sensing Image Classification
- Opinion Dynamics and Social Influence
Center for Research and Advanced Studies of the National Polytechnic Institute
2012-2019
Instituto Politécnico Nacional
2014-2015
This paper presents a high performance vision-based system with single static camera for traffic surveillance, moving vehicle detection occlusion handling, tracking, counting, and One Class Support Vector Machine (OC-SVM) classification. In this approach, objects are first segmented from the background using adaptive Gaussian Mixture Model (GMM). After that, several geometric features extracted, such as area, height, width, centroid, bounding box. As is present, an algorithm was implemented...
Network anomaly detection and classification is an important open issue in network security. Several approaches systems based on different mathematical tools have been studied developed, among them, the Anomaly-Network Intrusion Detection System (A-NIDS), which monitors traffic compares it against established baseline of a “normal” profile. Then, necessary to characterize Internet traffic. This paper presents approach for Shannon, Rényi Tsallis entropies selected features, construction...
This paper proposes an Entropy-Mahalanobis-based methodology to detect certain anomalies in IP traffic. The balanced estimator II is used model the normal behavior of two intrinsic traffic features: source and destination addresses. Mahalanobis distance allows describe ellipse that characterizes network entropy, which determine whether a given actual traffic-slot or anomalous. Experimental tests were conducted evaluate performance detection portscan worm attacks deployed campus network,...
Different systems have been continuously developed in order to ensure integrity, availability, and confidentiality of networks. An important approach is the anomaly-based network intrusion detection system (A-NIDS). In this paper, we provide a structured comprehensive overview research on entropy-based A-NIDS with intention providing researchers quick introduction essential aspects topic. As help point, general architecture based Entropy described their main components are discussed. We also...
This paper presents an algorithm based on entropy and Mahalanobis distance to characterize the behavior of worms attack. For this, is built a matrix with estimates different intrinsic features network traffic, this four parameters {μ, γ, λ, d <sup xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">2</sup> } are obtained. These values determine ellipsoidal region that characterizes worm within space defined by traffic features. Tests were conducted two...
Lane detection for traffic surveillance in intelligent transportation systems is a challenge vision-based systems. In this paper, novel pixel-entropy based algorithm the automatic of number lanes and their centers, as well formation division lines proposed. Using input video from static camera, each pixel behavior gray color space modeled by time series; then, period τ , its histogram followed entropy are calculated. Three different types theoretical behaviors can be distinguished: (1) at...
El objetivo de esta investigación es presentar el diseño y la implementación un robot seguidor línea basado en visión artificial con sistema operativo para robots (ROS) biblioteca código abierto (OpenCV). La razón usar ROS OpenCV crear una plataforma robusta que pueda ser base más complejos como los vehículos guiado automatizado (AGVs). Una cámara sensor le permite al obtener imágenes ruta, se procesan algoritmo detectar error retroalimentación del controlador Proporcional Integral...
Network anomaly detection and classification is an important open issue of network security. Several approaches systems based on different mathematical tools have been studied developed. Among them, the Anomaly-Network Intrusion Detection System (A-NIDS), this monitors traffic compares it against established baseline "normal" profile. Then, necessary to characterize Internet traffic. This paper presents approach for on: The entropy selected features (including Shannon, Renyi Tsallis...
Floodings in Mexico generated economic and human losses recent years, so it is necessary to use all possible tools that can help the government reduce these disasters, especially losses. Therefore, a Graphical User Interface (GUI) was developed Matlab for segmentation classification of vegetation, water city multispectral images obtained from Landsat 8 satellite with intention detecting floods vulnerable zones flooding. The interface performs feature extraction, segmentation, classification,...