Saad Rehman

Texture Classification Using Rotation- and Scale-Invariant Gabor Texture Features

This letter introduces a novel approach to rotation and scale invariant texture classification. The proposed approach is based on Gabor filters that have the capability to collapse the filter responses according to the scale and orientation of the textures. These characteristics are exploited to first calculate the homogeneous texture of images followed by the rearrangement of features as a two-dimensional matrix (scale and orientation), where scaling and rotation of images correspond to shifting in this matrix. The shift invariance property of discrete fourier transform is used to propose rotation and scale invariant image features. The performance of the proposed feature set is evaluated on Brodatz texture album. Experimental results demonstrate the superiority of the proposed descriptor as compared to other methods considered in this letter.

EMD-Based Temporal and Spectral Features for the Classification of EEG Signals Using Supervised Learning

This paper presents a novel method for feature extraction from electroencephalogram (EEG) signals using empirical mode decomposition (EMD). Its use is motivated by the fact that the EMD gives an effective time-frequency analysis of nonstationary signals. The intrinsic mode functions (IMF) obtained as a result of EMD give the decomposition of a signal according to its frequency components. We present the usage of upto third order temporal moments, and spectral features including spectral centroid, coefficient of variation and the spectral skew of the IMFs for feature extraction from EEG signals. These features are physiologically relevant given that the normal EEG signals have different temporal and spectral centroids, dispersions and symmetries when compared with the pathological EEG signals. The calculated features are fed into the standard support vector machine (SVM) for classification purposes. The performance of the proposed method is studied on a publicly available dataset which is designed to handle various classification problems including the identification of epilepsy patients and detection of seizures. Experiments show that good classification results are obtained using the proposed methodology for the classification of EEG signals. Our proposed method also compares favorably to other state-of-the-art feature extraction methods.

A survey of multicast routing protocols for vehicular ad hoc networks

Vehicular Ad Hoc Networks (VANETs) are autonomous and self-configurable wireless ad hoc networks and considered as a subset of Mobile Ad Hoc Networks (MANETs). MANET is composed of self-organizing mobile nodes which communicate through a wireless link without any network infrastructure. A VANET uses vehicles as mobile nodes for creating a network within a range of 100 to 1000 meters. VANET is developed for improving road safety and for providing the latest services of intelligent transport system (ITS). The development and designing of efficient, self-organizing, and reliable VANET are a challenge because the nodes mobility is highly dynamic which results in frequent network disconnections and partitioning. VANET protocols reduce the power consumption, transmission overhead, and network partitioning successfully by using multicast routing schemes. In multicasting, the messages are sent to multiple specified nodes from a single source. The novel aspect of this paper is that it categorizes all VANET multicast routing protocols into geocast and cluster-based routing. Moreover, the performance of all protocols is analyzed by comparing their routing techniques and approaches.

A Novel Real Time Framework for Cluster Based Multicast Communication in Vehicular Ad Hoc Networks

In a vehicular ad hoc network (VANET), the vehicles communicate with each other to develop an intelligent transport system (ITS) which provides safety and convenience while driving. The major challenge of VANET is that the topology changes dynamically due to the high speed and unpredictable mobility of vehicles resulting in an inefficient real time message dissemination, especially in emergency scenarios such as in the accident event where it can cause high level of destruction. To the best of our knowledge, there is no such mechanism in existing literature which can handle real time multicast communication in VANET for both urban and highway scenarios. In this paper, we propose a novel real time vehicular communication (RTVC) framework which consists of a VANET cluster scheme (VCS) and VANET multicast routing (VMR) to achieve efficient vehicle communication within both urban and highway scenarios. The RTVC framework develops stable communication links and achieves high throughput with low overhead despite high mobility by combining the multicast routing with a unique cluster based scheme. In VCS, the cluster head (CH) is elected upon cluster threshold value (CTV) to disseminate the messages within the cluster members (CMs) and to other cluster heads by intercluster communication, which reduces the network overhead. In addition, the vehicles cluster head election (VCHE) procedure is proposed to reduce the number of CHs and CMs switches which results in lower overhead of maintaining the clusters. Moreover, another novelty of the framework is that the CTV of VCHE can be adjusted by speed adjustment factor (SAF) to achieve the desired cluster stability depending upon the required VANET application. The simulation results illustrate that the proposed framework has achieved the goal of stable, efficient, and real time communication despite highly dynamic environment of VANET.

AMVR: A multicast routing protocol for autonomous military vehicles communication in VANET

Unmanned military vehicles (UMVs) and autonomous robots became part of modern warfare strategy to perform military combat missions and dangerous war field operations. The military vehicles (MVs) need to communicate with each other to achieve several required military tasks collectively. It has been achieved by proposing an autonomous military vehicles routing (AMVR) protocol to develop a vehicular ad hoc network (VANET) among all military manned and unmanned vehicles to meet the challenges of modern warfare. AMVR protocol performs multicast communication among unmanned and manned military vehicles in combination to develop strong coordination among them. The proposed protocol performs the message dissemination among MVs in two tier structure i.e. T1 and T2 which reduces the network overhead by distributing it among the two tiers. The UMVs are grouped in to T1 because these vehicles have the capability to arrange them at front autonomously with uniform distance by sharing speed and direction which avoids the occurrence of network fragmentation also. Hence, the UMVs maintain the stable radio links of VANET within dynamic environment of war field. The event detection messages (EDMs) are disseminated from unmanned vehicles to manned military vehicles (MMVs) of T2. The proposed protocol performs multicast communication to achieve high throughput and efficient dissemination of EDMs among all or specific group of military vehicles. The store and carry approach is adopted to inform incoming MVs about the current situation of war field. The simulation results illustrate that the proposed protocol has achieved the goal of EDMs dissemination among all UMVs and MMVs efficiently despite of dynamic battlefield environment.

Self-Organizing Hierarchical Particle Swarm Optimization of Correlation Filters for Object Recognition

Advanced correlation filters are an effective tool for target detection within a particular class. Most correlation filters are derived from a complex filter equation leading to a closed form filter solution. The response of the correlation filter depends upon the selected values of the optimal trade-off (OT) parameters. In this paper, the OT parameters are optimized using particle swarm optimization with respect to two different cost functions. The optimization has been made generic and is applied to each target separately in order to achieve the best possible result for each scenario. The filters obtained using standard particle swarm optimization (PSO) and hierarchal particle swarm optimization algorithms have been compared for various test images with the filter solutions available in the literature. It has been shown that optimization improves the performance of the filters significantly.

A cluster based multicast routing protocol for Autonomous Unmanned Military Vehicles (AUMVs) communication in VANET

Autonomous Unmanned Military Vehicles (AUMVs) became part of numerous military combat operations to meet the challenges of modern warfare techniques and strategies. Hence, there is a need to develop an ad hoc network among AUMVs to perform the military tasks collectively within a war field where infrastructure installation is not possible. Therefore, in this paper a novel AUMVs protocol is proposed to develop a Vehicular Ad Hoc Network (VANET) among unmanned Military Vehicles (MVs). The proposed protocol performs cluster based multicast communication among AUMVs by considering real time and dynamic war field scenario. The AUMVs protocol develops stable clusters and becomes adaptable according to the military environment by using a proposed Priority Based Cluster Head Election Scheme (PCHE) during cluster formation which reduces the network overhead and delay. Additionally, the AUMVs protocol achieves high throughput by combining the multicast approach with a cluster based scheme. The simulation results illustrate that the proposed protocol has achieved the goal of stable and efficient communication among unmanned MVs.

Improved maximum average correlation height filter with adaptive log base selection for object recognition

Sensitivity to the variations in the reference image is a major concern when recognizing target objects. A combinational framework of correlation filters and logarithmic transformation has been previously reported to resolve this issue alongside catering for scale and rotation changes of the object in the presence of distortion and noise. In this paper, we have extended the work to include the influence of different logarithmic bases on the resultant correlation plane. The meaningful changes in correlation parameters along with contraction/expansion in the correlation plane peak have been identified under different scenarios. Based on our research, we propose some specific log bases to be used in logarithmically transformed correlation filters for achieving suitable tolerance to different variations. The study is based upon testing a range of logarithmic bases for different situations and finding an optimal logarithmic base for each particular set of distortions. Our results show improved correlation and target detection accuracies.

Using a Portable Device for Online Single-Trial MRCP Detection and Classification

In the past decade, the use of movement-related cortical potentials (MRCPs) for brain computer interface-based rehabilitation protocols has increased manifolds. Such systems suffer severely from high frequency colored noise making it extremely difficult to recognize these signals with high accuracy on a single-trial basis. All previous work in this domain has mainly focused on offline systems using computing power of lab computers in which the detection of the MRCPs is done independent to the classification of the type of movement. The main focus of this work is to test the detection of the presence of the MRCP signal as well as its classification into different types of movements in a single online system (portable Raspberry Pi II) where the classification system takes over only after the presence of MRCP signal has been detected. To achieve this, the MRCP signal was first spatially (Laplacian) and later band pass filtered to improve the signal to noise ratio, then a matched filter was applied to detect the signal. This was obtained with a detection latency of −458 ± 97 ms before the movement execution. Then six temporal features were extracted from 400 ms data after the point of detection to be classified by a standard linear support vector machine. The overall accuracy of 73 % was achieved for the online detection and classification for four different types of movements which is very close to the base line accuracy of 74 % using the offline system. The whole system was tested on Matlab and verified on a Raspberry Pi II as a portable device. The results show that the online implementation of such a system is feasible and can be adapted for stroke patient rehabilitation.

Prioritized Fair Round Robin Algorithm with Variable Time Quantum

The performance of the time sharing systems and multiprocessor systems is greatly dependent on CPU scheduling algorithms. Some of the famous algorithms are Shortest Job First (SJF), First Come First Served (FCFS), Priority Scheduling and Round Robin (RR). Round Robin is the preferable choice for time shared systems. The main aim of this paper is to formulate a new methodology for RR algorithm that enhances the performance of the time sharing systems by reducing the waiting time, turnaround time and number of context switches. The proposed algorithm Prioritized Fair Round Robin (PFRR) with variable time quantum is a combination of SJF, Priority Scheduling, and RR with variable time quantum. The idea is to set the time quantum value according to the priority and burst times of the processes in the ready queue. The algorithm is designed for both equal priority processes and different priority processes.