Mohammad Ghavami

A novel blind watermarking of ECG signals on medical images using EZW algorithm.

In this paper, we present a novel blind watermarking method with secret key by embedding ECG signals in medical images. The embedding is done when the original image is compressed using the embedded zero-tree wavelet (EZW) algorithm. The extraction process is performed at the decompression time of the watermarked image. Our algorithm has been tested on several CT and MRI images and the peak signal to noise ratio (PSNR) between the original and watermarked image is greater than 35 dB for watermarking of 512 to 8192 bytes of the mark signal. The proposed method is able to utilize about 15% of the host image to embed the mark signal. This marking percentage has improved previous works while preserving the image details

Wireless Sensor Networks for Monitoring Physiological Signals of Multiple Patients

This paper presents the design of a novel wireless sensor network structure to monitor patients with chronic diseases in their own homes through a remote monitoring system of physiological signals. Currently, most of the monitoring systems send patients data to a hospital with the aid of personal computers (PC) located in the patients home. Here, we present a new design which eliminates the need for a PC. The proposed remote monitoring system is a wireless sensor network with the nodes of the network installed in the patients homes. These nodes are then connected to a central node located at a hospital through an Internet connection. The nodes of the proposed wireless sensor network are created by using a combination of ECG sensors, MSP430 microcontrollers, a CC2500 low-power wireless radio, and a network protocol called the SimpliciTI protocol. ECG signals are first sampled by a small portable device which each patient carries. The captured signals are then wirelessly transmitted to an access point located within the patients home. This connectivity is based on wireless data transmission at 2.4-GHz frequency. The access point is also a small box attached to the Internet through a home asynchronous digital subscriber line router. Afterwards, the data are sent to the hospital via the Internet in real time for analysis and/or storage. The benefits of this remote monitoring are wide ranging: the patients can continue their normal lives, they do not need a PC all of the time, their risk of infection is reduced, costs significantly decrease for the hospital, and clinicians can check data in a short time.

A semantic-enhanced trajectory visual analytics for digital forensic

With the increasing application of GPS devices, trajectory data have been frequently adopted in digital forensics because it can encompass spatial and temporal aspects of suspects’ movements. However, a lack of semantic information causes difficulty of linking the trajectories with the activities of suspects. Using the situation of a kidnapping, this paper proposes a semantic-enhanced method in trajectory analysis, which categorizes the daily activities of suspects into different semantic types by connecting trajectory data with transaction data. In the meantime, we present an interactive visualization system with four inner-linked views to provide a collaborative visual analytics of trajectory and transaction data in multiple perspectives. In the case study, the kidnapping investigation is used to demonstrate how the system works on the routine pattern analysis of suspects, the detection of abnormal behaviors, and the association exploration among suspects and their abnormal behaviors.Graphical abstract

Median Filter Approach for Removal of Baseline Wander in Photoplethysmography Signals

Removal of baseline wander is a crucial step in the signal conditioning stage of photoplethysmography signals. Hence, a method for removing the baseline wander from photoplethysmography based on two-stages of median filtering is proposed in this paper. Recordings from Physionet database are used to validate the proposed method. In this paper, the two-stage moving average filtering is also applied to remove baseline wander in photoplethysmography signals for comparison with our novel two-stage median filtering method. Our experiment results show that the performance of two-stage median filtering method is more effective in removing baseline wander from photoplethysmography signals. This median filtering method effectively improves the cross correlation with minimal distortion of the signal of interest. Although the method is proposed for baseline wander in photoplethysmography signals, it can be applied to other biomedical signals as well.

Improving time-frequency domain sleep EEG classification via singular spectrum analysis.

BACKGROUNDnManual sleep scoring is deemed to be tedious and time consuming. Even among automatic methods such as time-frequency (T-F) representations, there is still room for more improvement.nnnNEW METHODnTo optimise the efficiency of T-F domain analysis of sleep electroencephalography (EEG) a novel approach for automatically identifying the brain waves, sleep spindles, and K-complexes from the sleep EEG signals is proposed. The proposed method is based on singular spectrum analysis (SSA). The single-channel EEG signal (C3-A2) is initially decomposed and then the desired components are automatically separated. In addition, the noise is removed to enhance the discrimination ability of features. The obtained T-F features after preprocessing stage are classified using a multi-class support vector machines (SVMs) and used for the identification of four sleep stages over three sleep types. Furthermore, to emphasise on the usefulness of the proposed method the automatically-determined spindles are parameterised to discriminate three sleep types.nnnRESULTnThe four sleep stages are classified through SVM twice: with and without preprocessing stage. The mean accuracy, sensitivity, and specificity for before the preprocessing stage are: 71.5±0.11%, 56.1±0.09% and 86.8±0.04% respectively. However, these values increase significantly to 83.6±0.07%, 70.6±0.14% and 90.8±0.03% after applying SSA.nnnCOMPARISON WITH EXISTING METHODnThe new T-F representation has been compared with the existing benchmarks. Our results prove that, the proposed method well outperforms the previous methods in terms of identification and representation of sleep stages.nnnCONCLUSIONnExperimental results confirm the performance improvement in terms of classification rate and also representative T-F domain.

A new approach for event detection using k-means clustering and neural networks

In composite event detection systems such as fire alarms, the two foremost goals are speed and accuracy. One way to achieve these goals is by performing data aggregation at central nodes. This helps reduce energy consumption and redundancy. In this paper we present a new hybrid approach that involves the use of k-means algorithm with neural networks, an efficient supervised learning algorithm that extracts patterns and detects trends that are hidden in complex data. Previous research on event detection concentrates majorly on the use of feed forward neural network and other classifiers such as naive Bayes and decision tree alone for modern fire detection applications. In our approach presented here, we combine k-means with neural networks and other classifiers in order to improve the detection rate of event detection applications. To demonstrate our approach, we perform data aggregation on normalized multi-dimensional fire datasets in order to remove redundant data. The aggregated data forms two clusters which represent the two class labels (actual outputs) with the aid of k-means clustering. The resulting data outputs are trained by the Feed Forward Neural Network, Naive Bayes, and Decision Trees. This approach was found to significantly improve fire detection performance.

Classification of awake, REM, and NREM from EEG via singular spectrum analysis

In this study, a single-channel electroencephalography (EEG) analysis method has been proposed for automated 3-state-sleep classification to discriminate Awake, NREM (non-rapid eye movement) and REM (rapid eye movement). For this purpose, singular spectrum analysis (SSA) is applied to automatically extract four brain rhythms: delta, theta, alpha, and beta. These subbands are then used to generate the appropriate features for sleep classification using a multi class support vector machine (M-SVM). The proposed method provided 0.79 agreement between the manual and automatic scores.

On the Filtering of Photoplethysmography Signals

Recently there has been renewed interest in the application of photoplethysmography signals for cardiovascular disease assessment. Photoplethysmography signals are acquired non-invasively using visible and infrared light passed through the finger pulp. Unfortunately, this method commonly suffers from many forms of interference and distortion such as; baseline wander, mains-line interference and random spikes or other such artifacts. This paper presents a new approach for effective filtering of the photoplethysmography signal. Specifically, a cascaded filtering method for removing the artifacts from photoplethysmography signals based on the median and polynomial filters (MdPF) is proposed. Recordings from the PhysioNet database are used to validate the proposed method. Our experimental results show that the performance of MdPF cascaded filtering method is more effective than other current methods alone in removing artifacts from photoplethysmography signals. Root mean square error measurements are used for comparison purposes. This paper follows from previous work on median based method for baseline wander removal in photoplethysmogram signals.

Ultra-wideband-based multilateration technique for indoor localisation

In this study, the authors present a novel geometrically driven multilateration technique that is based on ultra-wideband (UWB) technology. The authors refer to their proposed solution as time reflection of arrival (TROA). They demonstrate in this study how the position estimation error is improved upon by carefully considering the inherent properties of the UWB technology and the reflection properties of transmitted UWB signals. By a direct comparison between TROA and two widely used multilateration techniques, the authors show that indoor position estimation can be done much more effectively using their proposed solution. They also derive a new Cramer–Rao lower bound for TROA multilateration and use it to show its level of efficiency.

UWB based pre-localization algorithm for aiding target location in a multipath environment

When a UWB signal is transmitted, we expect there to be a number of reflected multipath signals because of reflections due to objects in the environment. As a result of these reflected signals, it is impossible to define the ellipses that would be used for target detection as described by existing elliptical based localization schemes when we consider a highly multipath rich environment such as a typical UWB propagation channel unless we are able to manipulate the multipath propagation scenario and reduce it to a two-path propagation one. To tackle this problem, a pre-localization algorithm is proposed. In our proposed algorithm, we use the reflection properties of UWB signals to extract information from the reflected signals in the multipath environment and ultimately reduce the multipath propagation scenario into a two-path one based on these extracted information. Our process of extraction involves the sampling of the received signals at three receivers during regular intervals, correlating the sampled signals with a predefined database of template reflected signals; and finally using a decision engine to determine the signals that would be used for generating the ellipse for target localization. Consequently, we were able to differentiate multipath signals from one another using the relationship between individual multipath signals and their respective angle of incidences; and ultimately select a set of reflected signals that would be suitable for the localization process described by existing elliptical based localization schemes.