In this article, a comprehensive overview of the Crow Search Algorithm (CSA) is introduced with detailed discussions, which is intended to keep researchers interested in swarm intelligence algorithms and optimization problems. CSA is a new swarm intelligence algorithm recently developed, which simulates crow behavior in storing excess food and retrieving it when needed. In the optimization theory, the crow is the searcher, the surrounding environment is the search space, and randomly storing the location of food is a feasible solution. Among all food locations, the location where the most food is stored is considered to be the global optimal solution, and the objective function is the amount of food. By simulating the intelligent behavior of crows, CSA tries to find optimal solutions to various optimization problems. It has gained a considerable interest worldwide since its advantages like simple implementation, a few numbers of parameters, flexibility, etc. This survey introduces a comprehensive variant of CSA, including hybrid, modified, and multi-objective versions. Furthermore, based on the analyzed papers published in the literature by some publishers such as IEEE, Elsevier, and Springer, the comprehensive application scenarios of CSA such as power, computer science, machine learning, civil engineering have also been reviewed. Finally, the advantages and disadvantages of CSA have been discussed by conducting some comparative experiments with other similar published peers.

/pdf/crow-search-algorithm-theory-recent-advances-and-20yq33540d.pdf

Crow Search Algorithm: Theory, Recent Advances, and Applications

Crow Search Algorithm (CSA) is a recent swarm intelligence optimization algorithm inspired by the social intelligent behavior of crows for hiding food. It has been widely used to solve a large variety of optimization problems in several fields and areas of research and has proved its efficiency compared to several state-of-the-art optimization algorithms available in the literature. This paper presents a comprehensive overview of Crow Search Algorithm and its new variants categorized into modified and hybridized versions. It also describes the several applications of CSA in various domains such as feature selection, image processing, scheduling, economic dispatch, distributed generation, and other engineering problems. In addition, the paper suggests some interesting research areas related to CSA enhancement, CSA hybridization, and possible new applications.

A comprehensive survey of Crow Search Algorithm and its applications

Enhanced salp swarm algorithm based on firefly algorithm for unrelated parallel machine scheduling with setup times

In computer vision, traditional machine learning (TML) and deep learning (DL) methods have significantly contributed to the advancements of medical image analysis (MIA) by enhancing prediction accuracy, leading to appropriate planning and diagnosis. These methods substantially improved the diagnoses of automatic brain tumor and leukemia/blood cancer detection and can assist the hematologist and doctors by providing a second opinion. This review provides an in-depth analysis of available TML and DL techniques for MIA with a significant focus on leukocytes classification in blood smear images and other medical imaging domains, i.e., magnetic resonance imaging (MRI), CT images, X-ray, and ultrasounds. The proposed review’s main impact is to find the most suitable TML and DL techniques in MIA, especially for leukocyte classification in blood smear images. The advanced DL techniques, particularly the evolving convolutional neural networks-based models in the MIA domain, are deeply investigated in this review article. The related literature study reveals that mainstream TML methods are vastly applied to microscopic blood smear images for white blood cells (WBC) analysis. They provide valuable information to medical specialists and help diagnose various hematic diseases such as AIDS and blood cancer (Leukaemia). Based on WBC related literature study and its extensive analysis presented in this study, we derive future research directions for scientists and practitioners working in the MIA domain.

/pdf/a-review-on-traditional-machine-learning-and-deep-learning-4d74zo8iit.pdf

A Review on Traditional Machine Learning and Deep Learning Models for WBCs Classification in Blood Smear Images

The recent advancements in science, engineering, and technology have facilitated huge generation of datasets. These huge datasets contain noisy, redundant, and irrelevant features which negatively affects the performance of classification techniques in machine learning and data mining process. Feature selection is a pre-processing stage for reducing the dimensionality of datasets by selecting the most important attributes while increasing the accuracy of classification at the same time. In this paper, we present a novel hybrid binary version of enhanced chaotic crow search and particle swarm optimization algorithm (ECCSPSOA) to solve feature selection problems. In the proposed ECCSPSOA, in order to navigate the feature space, we hybridized the enhanced version of the CSA algorithm which has a better search strategy and particle swarm optimization (PSO) which is capable of converging into the best global solution in the search field. We further embed opposition-based learning technique in the local search of the hybrid algorithm. The ECCSPSOA was compared using 15 datasets from the UCI repository with four well-known optimization algorithms, such as particle swarm optimization (PSO), binary particle swarm optimization (BPSO), crow search algorithm (CSA), and chaotic crow search algorithm (CCSA). In the experiments with k-Nearest Neighbour (KNN) as a classifier, six different performance metrics were used. To tackle the over-fitting problem, each dataset is divided into training and testing data using K-fold cross-validation. The computational findings demonstrate that the proposed algorithm obtains an average accuracy rate of 89.67 % over 15 datasets, indicating that our technique exceeds state-of-the-art findings in 12 of the 15 datasets studied. Furthermore, the suggested approach outperforms state-of-the-art methods in terms of fitness value and standard deviation, obtaining the lowest value in 13 and 8 of the datasets studied respectively.

An hybrid particle swarm optimization with crow search algorithm for feature selection

Fuzzy C Means (FCM) clustering technique is widely used in medical image segmentation. The classical FCM is sensitive to noise and the objective function often gets trapped in local optima. In this work, we have combined FCM with various optimization techniques to find the optimum cluster centres. The Artificial Bee Colony (ABC), Firefly, Cuckoo and Simulated Annealing (SA) are the widely used optimization techniques in segmentation as well as for classification problems. Here we are proposing the Crow Search (CS) Optimization for the image segmentation using FCM. The CS optimization was found to produce satisfactory and promising results when compared with ABC, Firefly, Cuckoo and SA algorithm in the segmentation of abdomen CT images using FCM. In addition, a thorough investigation has been made in choosing the appropriate validation functions for the clustering techniques. The algorithms have been developed in Matlab 2015a and tested on CT abdomen datasets. Finally, the hardware implementation of FCM-CS algorithm was done in Raspberry Pi B+ model embedded board.

Fuzzy-Crow Search Optimization for Medical Image Segmentation

Image segmentation plays a vital role in medical image processing for the delineation of anatomical organs and analysis of anomalies. The evaluation of segmentation algorithms is vital to select the appropriate algorithm and parameters for optimum performance. In this paper, we are describing various metrics for evaluating the quality of segmentation algorithms with respect to ground truth images. The analysis of metrics has been carried out on real-time data sets of abdomen and retina. The variants of active contour algorithms are employed for the abdomen CT images, Kirsch and Wavelet algorithm were used for the retinal fundus images. This paper presents performance evaluation parameters that can be used to analyze efficiency of segmentation algorithms.

Performance Metric Evaluation of Segmentation Algorithms for Gold Standard Medical Images

Health care sector is entirely different from other industrial sector owing to the value of human life and people gives the highest priority. Medical image processing is a research domain where advance computer-aided algorithms are used for disease prognosis and treatment planning. Machine learning comprises of neural networks and fuzzy logic algorithms that have immense applications in the automation of a process. The deep learning algorithm is a machine learning technique that does not relies on feature extraction unlike classical neural network algorithms. Computer-aided automatic processing is in high demand in the medical field due to the improved accuracy and precision. The coupling of machine learning algorithms with high-performance computing gives promising results in medical image analysis like fusion, segmentation, registration and classification. This chapter proposes the applications of deep learning algorithms in cancer diagnosis specifically in the CT/MR brain and abdomen images, mammogram images, histopathological images and also in the detection of diabetic retinopathy. The overview of deep learning algorithms in cancer diagnosis, challenges and future scope is also highlighted in this work. The pros and cons of various types of deep learning neural network architectures are also stated in this work. The intelligent machines in future will be using the deep learning algorithms for the disease diagnosis, treatment planning and surgery.

Deep Learning Algorithms in Medical Image Processing for Cancer Diagnosis: Overview, Challenges and Future

The role of compression is inevitable in the storage and transmission of medical images. The polynomial based image compression is proposed in this work for the compression of abdomen CT medical images. The input images are preprocessed by min–max normalization; the pixels are scanned and subjected to polynomial approximation. The polynomial approximated coefficients are subjected to llyods quantization and encoded by arithmetic coder. The medical image compression using Gaussian Hermite polynomial gives superior results when compared with the legendre polynomial based image compression and JPEG lossless compression techniques in terms of Peak to signal noise ratio (PSNR), Mean square Error (MSE) and other picture quality metrics. The algorithms are tested on real-time DICOM abdomen CT image and can be used for data transfer in teleradiology application.

Gaussian Hermite polynomial based lossless medical image compression

The segmentation is the process of extraction of the desired region of interest. In medical images, the anatomical organs and anomalies like a tumor, cysts, etc. are of importance for the diagnosis of diseases by physicians for telemedicine applications. The thresholding, region growing, and edge detection are termed as classical segmentation algorithms. Clustering is an unsupervised learning technique to group similar data points and fuzzy partitioning merges similar pixels based on the fuzzy membership value. The classical FCM algorithm lacks sensitivity in the cluster centroid initialization and often gets trapped in local minima. The optimization algorithm gains its importance in cluster centroids initialization, thereby improving the efficiency of FCM algorithm. In this work, firefly optimization is coupled with FCM algorithm for CT/MR medical image segmentation. Fireflies are insects having a natural capacity to illumine in dark with glowing and flickering lights and firefly optimization algorithm was modeled based on its biological traits. The preprocessing stage comprises of artifacts removal and denoising by Nonlinear Tensor Diffusion (NLTD) filter. The computation time was minimized by reducing the total pixels count for the processing. The Firefly optimization, when coupled with FCM, generates satisfactory results inconsistent with FCM when coupled with Cuckoo, Artificial Bee Colony, and Simulated annealing algorithms. The cluster validity performance metrics are used for the determination of optimum number of clusters. The algorithms are developed in Matlab 2010a and tested on real-time abdomen datasets.

H. Ajay Kumar

Papers

Fuzzy-Crow Search Optimization for Medical Image Segmentation

Performance Metric Evaluation of Segmentation Algorithms for Gold Standard Medical Images

Deep Learning Algorithms in Medical Image Processing for Cancer Diagnosis: Overview, Challenges and Future

Gaussian Hermite polynomial based lossless medical image compression

Firefly Optimization Based Improved Fuzzy Clustering for CT/MR Image Segmentation