Siamak Layeghy

Pushing SDN to the end-host, network load balancing using OpenFlow

The concept of Software Defined Networking (SDN) has been successfully applied to efficiently configure and manage network infrastructure, e.g. in the context of data centres or WANs, and increasingly for ubiquitous communication. In this paper, we explore the idea of pushing SDN to the end-host. In particular, we consider the scenario of load balancing across multiple host network interfaces. We have explored and implemented different SDN-based load balancing approaches based on OpenFlow software switches, and have demonstrated the feasibility and potential of this approach.

Time-frequency characterization of tri-axial accelerometer data for fetal movement detection

Monitoring fetal wellbeing is a significant problem in modern obstetrics. Clinicians have become increasingly aware of the link between fetal activity and its well-being. Using data acquired by accelerometry sensors, we use TFDs such as the spectrogram and modified B distribution (MBD) to characterize fetal movements in the time-frequency (TF) domain. This paper reports a fetal activity detection method based on the root-mean-square (RMS) of time series and evaluates its performance against real-time ultrasound imaging, taken as the gold standard. The evaluation showed better performance with the RMS-based detector as compared to maternal perception. The evaluation also showed that the detector performance is age-dependent and that fetal movement is characterized by different TF morphology. Time-frequency distributions (TFDs) with better resolution such as MBD are investigated for TF-based techniques for the detection of fetal movements.

A passive DSP approach to fetal movement detection for monitoring fetal health

Fetal movement can help clinicians understand fetal functional development. Active methods for fetal monitoring such as ultrasound are expensive and there are objections to their long term usage. This paper presents a passive approach for fetal monitoring which uses solid state accelerometers placed on the mothers abdomen for the collection of fetal movements. The proposed fetal movement detection is based on the root-mean-square (RMS) of time series. The detection performance is evaluated against real-time ultrasound imaging. A good detection rate of 80% and a positive predictive value of 77% were achieved based on the analysis of 4 subjects. Time-frequency (TF) analysis of fetal movement signals, using a number of quadratic TF distributions, has shown that some fetal movements are spectrally characterized by nonstationary and nonlinear behavior and that fetal activity is generally below 20 Hz. More data are needed for further TF analysis and future detections will depend on the outcome of this analysis.

Non-invasivemonitoring of fetal movements using time-frequency features of accelerometry

This paper presents a time-frequency approach for fetal movement monitoring which is based on the instantaneous amplitude (IA) and instantaneous frequency (IF) of signals collected using 3axial accelerometers placed over the maternal abdomen. Results of a feature selection method based on receiver operating characteristic analysis shows that the mean of the IAs and deviation of the Ifs outperform other features. A support vector machine based classifier which uses these 2 features exhibits a total accuracy of 96.6% with reasonably high sensitivity and specificity.

Link capacity estimation in SDN-based end-hosts

Software Defined Networking (SDN) is a new paradigm that facilitates network management and control. In our work, we explore the use of SDN for the control of network traffic on end-hosts. In particular, we use an OpenFlow software switch (OVS) to load balance application traffic across the multiple available network interfaces. A typical example is the simultaneous use of Wifi and 4G interfaces on a mobile device. In order to achieve optimal load balancing, it is critical to know the capacity of the last-hop links associated with the different interfaces. In this paper, we explore and adapt active packet probing mechanisms to the scenario of SDN-based end-host traffic control, in order to estimate the link capacity. In particular, we investigate the use of Variable Packet Size (VPS) probing, and demonstrate its viability via experiments.

Classification of fetal movement accelerometry through time-frequency features

This paper presents a time-frequency approach for fetal movement monitoring which is based on classification of accelerometry signals collected from pregnant womens abdomen. Features extracted from time-frequency distribution of these signals were supplied into statistical analysis to generate feature-measure mixtures. Four various classes subjectively are recognized in accelerometry data by means of objective tools such as ultrasound sonography. These include strong and weak fetal movement, artefact, and background. Receiver operating characteristic analysis utilized to compute the performance of feature-measures for the comparison between various classes. Next, a feature selection applied to reduce the feature space dimension by means of principal component analysis. The selected feature-measures then employed in support vector machine classifiers to classify artefact and fetal movement in different subsets of available classes. The results indicate the fetal movement events are identified with an accuracy of 92.19%.

Evaluation of Mininet-WiFi integration via ns-3

Mininet is a Linux-based network emulator that is particularly widely used for Software Defined Network experiments, due to its in-built support for OpenFlow switches. However, Mininet currently lacks support for wireless links. A recent work has addressed this limitation by using the real-time feature of ns-3 to integrate the IEEE 802.11 channel emulation feature with Mininet, which we refer to as Mininet-ns3-WiFi. While this approach has great potential to serve as an experimental platform, in particular for Software Defined Wireless Networks, it has not been extensively evaluated in terms of experiment result accuracy and fidelity. This is critical for any system that integrates simulation with real-time components. In this paper, we present a detailed evaluation of the fidelity of experimental results of Mininet-ns3-WiFi. We further present a reliable and low cost method that gives an experimenter an indicator about the fidelity and trustworthiness of the results.

SCOR: Constraint Programming-based Northbound Interface for SDN

In this paper, we introduce SCOR (Software-defined Constrained Optimal Routing), a new SDN Northbound Interface for QoS routing and traffic engineering. SCOR is based on constraint programming techniques and is implemented in the MiniZinc modelling language. It provides a powerful, high level abstraction, consisting of 9 basic constraint programming predicates. A key feature of SCOR is that it is declarative, where only the constraints and utility function of the routing problem need to be expressed, and the complexity of solving the problem is hidden from the user, and handled by a powerful generic solver. We show that the interface (set of predicates) of SCOR is sufficiently expressive to handle all the known and relevant QoS routing problems. We further demonstrate the practicality and scalability of the approach via a number of example scenarios, with varying network topologies, network sizes and number of flows.

A time frequency approach to CFAR detection

Simultaneous analysis of signals in time and frequency domains is a standard approach in many signal processing applications including some detection. Parameters of clutter, noise and interference, and in some cases Doppler specifications, are the basis for most of current CFAR target detection techniques. When these parameters are unknown, most of current detection methods do not perform well. In this paper, a detection approach is introduced using time-frequency (TF) signal analysis. The method is non-parametric and by analysis of the spectrogram of the input, the presence of target signal is localized in time domain. Then, the signal detection is achieved using an adaptive thresholding.