In this paper, we present a new method for object tracking. We use an efficient local search scheme based on the probability product kernel using particle filter PPKPF to find the image region with a histogram most similar to the histogram of the tracked target. Experimental results verify the effectiveness of this proposed algorithm.

The air traffic management operations are considered as complex problems. In practice, they can formulate as a constrained optimisation problem that needs to be solved in a real-time environment, also they are non-regular problems, so we can use the expert system to schedule the air traffic management operations. Expert systems using extracted cognitive data, inspiring from the human expertise and its best practices. They are based on the machine performance and its ability to carry out a very large number of complex iterations. Almost all air traffic management operations are classified as scheduling operations. The goal of this paper is to present a new intelligent system with an evolving knowledge base and a creative inference engine. This system allows choosing the optimal way based on real time algorithms to schedule all air traffic management operations such as aircrafts' landing scheduling.

This work proposes a new framework for multichannel speech extraction (MCSE) of one target speaker from mixtures of multiple speakers. In this framework, a beamforming technique that is based on a prior knowledge of the desired speaker's position is used. The car environment is a good example of an application where the position of the desired speaker (the driver) is known in advance. The proposed method is an optimum spatial filter with a structure inspired by the minimum variance distortionless response (MVDR) beamformer and its practical realisation through generalised side lobe canceller (GSC). The performance of the proposed method through different experiments form the 'multichannel in-car speech and noise database' must be tested and evaluated. Simulative experiments include one desired speaker (driver) and one interferer speaker (co-driver) who talked simultaneously in car environment. The experimental results show that the proposed method provides satisfactory performance.

In this paper, an attempt is made to apply few conventional methods of EEG feature extraction and classification methods and compare their performance for a specific task. Two different feature extraction and classification methods are implemented to classify the mental tasks of EEG signals from a known dataset. For this purpose, the auto regression model and the wavelet transform is used as feature extraction. A combined EEG feature vector is also evaluated on the classification accuracy. The features extracted from these methods are applied to the k-nearest neighbour and support vector machine classifiers separately. Each subject has ten trials of each mental task, in which five trials of each task is used for training the system. The remaining five tasks are used for testing the system. Four different trial combinations of each task are made. The results are evaluated using the confusion matrix. Experimental results specify that each method has specific advantages and disadvantages and is suitable for EEG signal analysis for a specific application.

Mahalanobis Taguchi system MTS is a classification technique which is used to group objects into dichotomous or binary categories based on numerical predictor variables. MTS uses threshold values based on Mahalanobis distance to group objects into binary classes. An important step in MTS is feature selection whereby a subset of the original set of predictor variables is selected based on maximisation of signal-to-noise S/N ratio. Application of S/N ratio for feature selection in MTS has been criticised for its limitations in handling large number of predictor variables. This research explores the application of artificial bee colony ABC optimisation to select features in MTS. The problem of feature selection is formulated as minimisation of total weighted misclassification and solved as a binary integer programme. The optimal subset of features is obtained via the stochastic search mechanism of binary ABC. The methodology is applied for five case studies. Results are compared with those obtained from two other meta-heuristic techniques namely genetic algorithm and particle swarm optimisation.

This paper proposes two techniques for multiple image watermarking based on discrete wavelet transform (DWT) and dual-tree complex wavelet transform (DT-CWT) using spread transform. The proposed scheme embed two watermarks by spreading the orthogonal projection vectors into the cover vectors extracted from the first level decomposition discrete wavelet coefficients in first technique and dual tree CWT coefficients of the host image in the second technique. The spread transform disperse the watermark over a large number of frequencies providing robustness to geometric attacks like rotation, scaling, cropping, etc., as well as compression like JPEG. The multiple watermark signals are embedded in different orientations of projection vectors which increase the embedding capacity as compared to the single watermark embedding techniques. The experimental results show that the watermarked image by both the techniques has good visual quality in terms of PSNR. Thus the proposed scheme provides the balanced trade off between important parameters of watermarking, i.e., capacity, robustness and imperceptibility.

Security and privacy issues of the transmitted data have become an important concern in multimedia technology. In this paper, we propose two computationally efficient and secure video in-compression encryption models. Both models use adaptive lossy image compression (ALIC) technique (El-said et al., 2010) for video compression and optimised multiple Huffman tables (OMHT) technique (El-said et al., 2011) for video encryption. We achieve computational efficiency by using the proposed ALIC technique that exploits the frequently occurring patterns in the DCT coefficients of the video data. Computational complexity of the encryption is made proportional to the number of DCT transmitted coefficients in each video frame. The proposed video encryption models produce an encrypted coded sequence with an improved quality for the high compression ratios when compared to the existing techniques. The performances of the proposed models are compared with those of the existing techniques with respect not only to their compression performance but also their security level. The simulation study for the two models over mobile communication system proves that the proposed models perform well in the presence of transmission errors.

In critical communication infrastructures, hardware accelerators are often used to speed up cryptographic calculations. Their resistance to physical attacks determines how secure the overall infrastructure is. In this paper, we describe the implementation and characterisation of an AES accelerator embedding security features against physical attacks. This AES chip is implemented in HCMOS9gp 130 nm STM technology. The countermeasure is based on duplication and works on complemented values in parallel. The chip was tested against side channel attacks showing the efficiency of the proposed countermeasure against such attacks. Fault injection tests based on the use of local laser shoots showed that the fault detection mechanism did indeed react as expected. However, using clock set-up time violations, 80% of the secret key were retrieved in less than 40 hours, thus illustrating the limits of the duplication countermeasure against a global fault attack which was published after the chip was designed.

Recently, it has been proved that the resolution of methods based on optimising the modularity Q is limited. In order to improve this limit, a novel local quantitative measure called normalised modularity density NMD is proposed and optimised by simulated annealing technique. Both theoretical certifications on some schematic examples and numerical results on a suit of computer-generated and real-world networks show that optimising NMD can detect communities with different scales, especially small dense communities that optimising Q cannot detect, which provides meaningful evidence that optimising NMD can improve the resolution limit in optimising modularity Q.