A cooperating metaheuristic approach for MR image segmentation

Cuckoo search optimization (CSO) algorithm, a recently proposed metaheuristic, has shown promising results in various problem domains. Results from recent studies show that engineering and tuning discrete cuckoo search optimization’ parameters is a daunting task. In this paper, an attempt to enhance the performance of the CSO algorithm in solving discrete combinatorial optimization problems is presented. Performance of the discrete modified CSO algorithm is compared with genetic algorithm (GA), particle swarm optimization (PSO), hybrid of GA/PSO, and simulated annealing. In addition, a memetic algorithm (MA) that combines discrete modified CSO and tabu search is proposed. Results show that the proposed improvements help in enhancing the performance of the original algorithm. As a test case, the NP-hard problem of buffer minimization in CMOL (CMOS[Formula: see text]+[Formula: see text]nanowire[Formula: see text]+[Formula: see text]MOLecules) circuits is addressed. The performance of the proposed implementation of CSO algorithm is compared with other heuristics.

In order to overcome the poor anti-noise performance of traditional fuzzy C-Means (FCM) algorithm in image segmentation, a novel improved FCM algorithm was proposed in this paper based on Particle Swarm Optimization (PSO) algorithm and Markov Random Field (MRF) model, which can make full use of the global searching ability of PSO and the spatial information integrating ability of MRF for image segmentation. In this algorithm, the image segmentation is converted to a PSO optimization problem, in which the fitness function is set up to containing the spatial information based on the spectral value and the neighboring pixels modeled by MRFs. And segmentation results can be iteratively obtained during the PSO iterations according to the newly designed membership function of FCM in which the spatial information is integrated. The experiments herein reported in this paper illustrate the better performance of this algorithm than the traditional FCM algorithm and the PSO algorithm for image segmentation.

In this paper, Cuckoo Search Optimization (CSO) algorithm is presented for robust tuning of Power System Stabilizer (PSS) parameters in multimachine power system. In this work, a conventional speed-based lead-lag PSS is used. A damping ratio based objective function is formulated to optimize the damping of all electromechanical modes. The parameters of the CSO based PSS (CSOPSS) are optimized to shift the unstable or poorly damped eigenvalues associated with all electromechanical modes to a wedge-shape zone in left half of the s-plane. The eigenvalue analysis, time domain simulation results and performance indices show the effectives of CSOPSS by exhibiting better damping ratio than Genetic Algorithm based PSS (GAPSS) and Particle Swarm Optimization based PSO (PSOPSS). It is observed that CSOPSS exhibits improved damping performance compared to GAPSS and PSOPSS. The performance of proposed PSS is tested on Kundur 2-area 4-machine power system for wide range of operating conditions and severe disturbances.

In this chapter, we present an illustration of basic cuckoo search optimization (CSO) algorithm. Generally, the parameters of CSO are kept constant. We also explore some of its modified variants from existing literature to improve its performance, i.e. modified cuckoo search by varying step size only, and an improved cuckoo search by varying both step size and probability index. The application of CSO algorithm to solve complex combinatorial optimization problems is also demonstrated. A real-life engineering optimization problem for designing the power system stabilizer parameters of multi-machine power system to enhance small-signal stability is solved by using CSO algorithm.

Medical-image segmentation is of primary importance in the development of computer assisted detection (CAD) of mammographic masses. Image segmentation is used for finding regions of interest (ROI) within mammograms that are further processed to estimate their likelihood of being a potential lesion or mass. This task can be stated as follows: €œA gray-scale image is represented as a 1D array X = (x1, x2,...,xN), where xn is an input feature for pixel n and N is the total number of pixels in the image. The input feature vector xn may be a D dimensional vector or simply the gray-scale value of the pixel n. Let the underlying true segmentation of the image be denoted as Y = (y1, y2,..., yN). It is assumed that the number of classes is predetermined as a set of known class labels I‰l, where l Iµ {1,..., L{ and therefore the class label of pixel n is indicated as y n ∈{I‰ l } L l=1 . The task is to predict the A·n estimate of the segmentation for each pixel. In an automated system, such likelihood estimates are generated using a classifier that takes as input some features that describe region properties, e.g., image texture. The segmentation of digital mammograms is a difficult task. A number of different approaches have been adopted in this area with varying success. Broadly speaking, image segmentation can be carried out either as: (1) image preprocessing step with the main objective of identifying regions of interest (spatially coherent collection of pixels within the image) and a subsequent feature extraction and classification step is required to characterize a given region of interest as either €œnormal€ or €œsuspicious€; or (2) part of the overall classification scheme, where the likelihood of each pixel being €œsuspicious is calculated to generate a probability image using pixel-based features as input to a classifier. The probability image is thereafter thresholded to give both the segmentation and classification output. The main difference between (1) and (2) is that in the first case, image segmentation is needed before classification can be performed; whereas in the second case, classification and segmentation are both based on thresholding probability estimates of pixels and are achieved at the same time. The image segmentation approaches, with the aim of finding regions of interest, were first attempted in digital mammography with varying techniques, including global thresholding, region growing, region clustering, template matching, edge operators and filtering, and edge-based hybrid methods. Image segmentation is developed from pixel-based probability estimation is underpinned by modeling features using parametric methods, Gaussian mixture modeling, Markov random fields, and other methods. A detailed discussion on mammogram-based image segmentation with their algorithms is available in Singh and Bovis. Experience shows that it is quite difficult to select an outright winning image-segmentation method, since different approaches have been shown to be suitable for different data sets and show varied performance under different experimental conditions. However, there is a consensus that image segmentation in medical imaging is most successful when explicitly using a priori information about the problem to be studied.

A wavelet-based Markov random field segmentation model in segmenting microarray experiments

Vehicle ad hoc network is the key technology for a future Internet of vehicles and intelligent transport system. However, involvement of vast number of vehicles in Internet of vehicles limits the performance of vehicle ad hoc network. To tackle this problem, a novel vehicle ad hoc network architecture with two different technologies such as software-defined networking and named-data networking is proposed in this article. In the proposed software-defined networking controlled vehicular named-data networking, IP addressing issue is resolved by named-data networking and global view of the network is attained by software-defined networking. Emergency data dissemination is initiated with packet classification. For packet classification, policy-based bifold classifier is proposed in roadside unit and supported by evolved interest packet. Subsequently, best disseminator selection is carried out by trustworthy weighted graph scheme based on novel weight value, which is computed by considering significant metrics. Content retrieval is accomplished by roadside unit and assisted by a controller. Location of content producer is obtained from a controller and optimal route is selected by roadside unit. Optimal route selection is performed by roadside unit for both content retrieval and vehicle-to-vehicle communication using novel region-based hybrid cuckoo search algorithm. Hybrid algorithm combines cuckoo search and particle swarm optimization algorithm to perform efficient route selection. Involvement of software-defined networking controller supports numerous users by providing a global view of the network, which includes network status and traffic information. Extensive simulation in NS-3 assures better interest satisfaction rate, interest satisfaction delay, forwarder interest packets, average hop count, and gain of scalability in software-defined networking controlled vehicular named-data networking than traditional vehicle ad hoc network.

Automatic cytoplasm and nuclei segmentation for color cervical smear image using an efficient gap-search MRF

Particle Swarm Optimization (PSO) is population based stochastic algorithm to form clusters with the help of fitness functions. PSO clustering algorithm is widely used in pattern recognition methods such as image segmentation where PSO defines less number of clusters compared to conventional clustering approaches. Level Sets image segmentation aided with the clustering gives fast convergence towards the desired boundaries of the object to be segmented. Here in this paper a novel approach of image segmentation using PSO clustering applied to Level sets is been presented where PSO performs better than KFCM by generating more compact clusters and larger inter cluster separation. The proposed method is successfully implemented on the images and results obtained show the effectiveness of the approach.

Segmentation is a low-level processing aimed at the partition of an image in disjoint regions, each one homogeneous with respect to some properties like intensity, texture, shape, etc. Such a task is needed in many high-level processing and applications in such diverse fields as remote-sensing, medical imaging, video coding, and industrial automation, just to name a few. In this work of thesis, we first deal with the problem of color based image segmentation, that is based on some form of homogeneity in the color/spectral properties of the image, and then move to the more complex task of texture based segmentation, where the aim is to recognize complex structures in the image which are typically non homogeneous in terms of spectral properties. Concerning color based segmentation, we focus on a specific class of Markov Random Field (MRF) probability models, namely the Tree-Structured Markov Random Fields (TS-MRF), recently proposed to provide a hierarchical multiscale description of images. Based on such a model, the unsupervised image segmentation is carried out by means of a sequence of nested class splits, where each class is modeled as a local binary MRF. As a first contribution, we first extend the model to generic tree structures removing the unnecessary binary constraint, and then devise a new TS-MRF unsupervised segmentation technique which improves upon the original algorithm by selecting a better tree structure and eliminating spurious classes. Such results are obtained by using the Mean-Shift procedure to estimate the number of pdf modes at each node, and to obtain a more reliable initial clustering for subsequent MRF optimization. To this end, we devise a new reliable and fast clustering algorithm based on the Mean-Shift technique, which makes use of a variable-bandwidth strategy based on the k-Nearest Neighbors (k-NN) technique, and is implemented with a speed-up strategy that cuts significantly the computational complexity. Experimental results on synthetic data and real life images from the remote sensing domain prove the potential of the proposed method. Turning to texture based segmentation, we present a novel multiscale texture model, and a related algorithm for the unsupervised segmentation of color images. Elementary textures are characterized by their spatial interactions with neighboring regions along selected directions. Such interactions are modeled in turn by means of a set of Markov chains, one for each direction, whose parameters are collected in a feature vector that synthetically describes the texture. Based on the feature vectors, the texture are then recursively merged, giving rise to larger and more complex textures, which appear at different scales of observation: accordingly, the model is named Hierarchical Multiple Markov Chain (H-MMC). The Texture Fragmentation and Reconstruction (TFR) algorithm, addresses the unsupervised segmentation problem based on the H-MMC model. The ``fragmentation'' step allows one to find the elementary textures of the model, while the ``reconstruction'' step defines the hierarchical image segmentation based on a probabilistic measure (texture score) which takes into account both region scale and inter-region interactions. The performance of the proposed method was assessed through the Prague segmentation benchmark, based on mosaics of real natural textures, and also tested on real-world natural images from the Berkeley dataset. Finally, an application of the TFR algorithm for the unsupervised segmentation of multiresolution remotely sensed images is proposed, based on the significant presence of textural content in last generation high-resolution satellite images. The obtained results further assess the potential of the proposed method for such real life applications.

Maximum power point tracking (MPPT) control is one of the essential requirements in harnessing wind power of wind energy conversion systems (WECS). The more precise the maximum power point (MPP) is determined, the more optimal the WECS is operated. Amongst MPPT algorithms, a hill-climb search (HCS) algorithm is preferred because of its simplicity however it also has few drawbacks such as the difficulty of selecting an appropriate step size, the premature convergence phenomenon and the speed-efficiency trade-off. A cuckoo search (CS) algorithm is proposed in this paper for finding out a MPP of a WECS driven by a doubly-fed induction generator (DFIG) under various wind speeds which mostly overcomes the above disadvantages. Then, the DFIG-WECS is controlled to track the MPP. This ensures that the DFIG-WECS is always operated at MPPs regardless of various wind speeds. It is realized that the proposed CS algorithm is also a population-based algorithm inspired from the breeding behavior of cuckoos but it is quite simple, powerful and especially requires less parameters to define optimal solutions than a genetic algorithm (GA) and a particle swarm optimization (PSO) algorithm. Though numerical results, the CS algorithm shows its effectiveness in finding out MPPs in the DFIG-WECS. Furthermore, the obtained results using the CS algorithm are also compared with those using the HCS and PSO algorithms. The comparison demonstrates that the convergence value and speed of the CS algorithm are always better than those of the HCS and PSO algorithms in the MPPT application in the DFIG-WECS.

Breast DCE-MRI segmentation for lesion detection by multi-level thresholding using student psychological based optimization

Image segmentation has key influence in numerous medical imaging uses. In this paper, we present a new algorithm for spatial fuzzy segmentation using modified particle swarm optimization of medical & multimedia data. The algorithm is realized by modifying the scaling parameters in the conventional fuzzy C-means (FCM) algorithm using Modified Particle Swarm Optimization (MPSO). Spatial coordinates depend on filter radius, weight, gradient & threshold. Firstly, the initial parameters in the FCM are replaced by optimized parameters, & thus the corresponding algorithm is derived & called as the SFCM-MPSO. Outcomes of the experiment on both real MR images & Multimedia images demonstrate that the proposed algorithms have better performance when noise & other artefacts are present than the standard algorithms. Voxel based error method shows Positive Predictive Value (PPV), Sensitivity (Sens), & Dice Similarity Coefficient (DSC) between existing methodology.

Cuckoo search (CS) is widely used to solve many optimisation problem, which is a biologically inspired the brood parasitic behaviour of a type of cuckoos and the Levy flights behaviour of some animals. However, it has been demonstrated to easily get trapped into local optimal solutions and slow convergence speed. Therefore, an improved adaptive cuckoo search (IACS) optimisation algorithm is proposed in this article. Two adaptive strategies based on the population feature and iteration information feedback which are integrated into the CS algorithm to adjust the parameters pa and α0. We compared the proposed algorithm to CS and five variants on the 30 benchmark functions proposed in CEC 2014. In addition, the proposed algorithm and CS are integrated into support vector machine (SVM) for classification. Experimental results certify that the modified algorithm is superior to the CS for most optimisation problems and has better performance than the other variants of CS algorithm.

The cuckoo search (CS) algorithm, which is a new meta-heuristic optimization algorithm, is an efficient approach to solve continuous function optimization problems. Normally, the parameters of the CS are fixed constants. This may result in affecting the algorithm efficiency. To cope with this issue, we properly tune the parameters of the CS and propose an adaptive cuckoo search (ACS) algorithm to enhance the convergence rate and accuracy of the CS. Then, we validate the proposed ACS against test functions and compare its performance with those of particle swarm optimization (PSO), improved cuckoo search algorithm (ICS) and CS by simulation. The simulation results demonstrate that the ACS obtains some solutions better than those obtained by PSO, ICS and CS.