Feature selection (FS) is a machine learning process commonly used to reduce the high dimensionality problems of datasets This task permits to extract the most representative information of high sized pools of data, reducing the computational effort in other tasks as classification This article presents a hybrid optimization method for the FS problem; it combines the slap swarm algorithm (SSA) with the particle swarm optimization The hybridization between both approaches creates an algorithm called SSAPSO, in which the efficacy of the exploration and the exploitation steps is improved To verify the performance of the proposed algorithm, it is tested over two experimental series, in the first one, it is compared with other similar approaches using benchmark functions Meanwhile, in the second set of experiments, the SSAPSO is used to determine the best set of features using different UCI datasets Where the redundant or the confusing features are removed from the original dataset while keeping or yielding a better accuracy The experimental results provide the evidence of the enhancement in the SSAPSO regarding the performance and the accuracy without affecting the computational effort

Improved salp swarm algorithm based on particle swarm optimization for feature selection

Review of swarm intelligence-based feature selection methods

Image segmentation is the method of partitioning an image into a group of pixels that are homogenous in some manner. The homogeneity dependents on some attributes like intensity, color etc. Segmentation being a pre-processing step in image processing have been used in the number of applications like identification of objects to medical images, satellite images and much more. The taxonomy of an image segmentation methods collectively can be divided among two categories Traditional methods and Soft Computing (SC) methods. Unlike Traditional methods, SC methods have the ability to simulate human thinking and are flexible to work with their ownership function, have been predominantly applied to the task of image segmentation. SC techniques are tolerant of partial truth, imprecision, uncertainty, and approximations. Soft Computing approaches also having advantages of providing cost-effective, high performance and steadfast solutions. In this survey paper, our emphasis is on core SC approaches like Fuzzy logic, Artificial Neural Network, and Genetic Algorithm used for image segmentation. The contribution lies in the fact to present this paper to the researchers that explore state-of-the-art elaboration of almost all dimensions associated with the image segmentation. The idea is to encapsulate various aspects like emerging topics, methods, evaluation parameters, the problem associated with different type of images, databases, segmentation applications, and other resources so that, it could be advantageous for researchers to make effort in developing new methods for segmentation. The paper accomplishes with findings and concluding remarks.

Soft computing approaches for image segmentation: a survey

Multimodal medical image fusion review: Theoretical background and recent advances

The number of deaths caused by melanoma has increased remarkably in the last few years which are the carcinogenic type of skin cancer. Lately, computer based methods are introduced which are intelligent enough to support dermatologist in initial judgment of skin lesion. However, there still exists a gap for an optimal solution; therefore, machine learning community is still considering it a great challenge. The primary objective of this article is to efficiently detect and classify skin lesion with the utilization of an improved segmentation and feature selection criteria. Presented contribution is threefold; First, ternary color spaces are exploited to separate foreground from the background—utilizing multilevel approach of contrast stretching. Second, a weighting criterion is designed which is able to select the best solution based on extended texture feature analysis, related labels, boundary connections and central distance. Third, an improved feature extraction and dimensionality reduction criteria is proposed which combines conventional as well as recent feature extraction techniques. The proposed method is tested on PH2, ISBI 2016 and ISIC benchmark data sets and evaluated on the basis of multiple parameters including FPR, sensitivity, specificity, FNR and accuracy. From the statistics, it is quite clear that the proposed method outperforms numerous existing techniques with considerable margin.

Skin lesion segmentation and recognition using multichannel saliency estimation and M-SVM on selected serially fused features

One of the leading causes of cancer death for both men and women is the lung cancer. The best way to improve the patient’s chances for survival is the early detection of potentially cancerous cells. But, the conventional systems fails to segment the cancerous cells of various types namely, well-circumscribed, juxta-pleural, juxta-vascular and pleural-tail at its early stage (i.e., less than 3 mm) that leads to less classification accuracy. It is also noted that none of the existing systems achieved accuracy more than 98%. In this paper, we propose an optimal diagnosis system not only for early detection of lung cancer nodules and also to improve the accuracy in Fog computing environment. The Fog environment is used for storage of the high volume CT scanned images to achieve high privacy, low latency and mobility support. In our approach, for the accurate segmentation of Region of Interest (ROI), the hybrid technique namely Fuzzy C-Means (FCM) and region growing segmentation algorithms are used. Then, the important features of the nodule of interest such as geometric, texture and statistical or intensity features are extracted. From the above extracted features, the optimal features used for the classification of lung cancer are identified using the Cuckoo search optimization algorithm. Finally, the SVM classifier is trained using these optimal features, which in turn helps us to classify the lung cancer as either of type benign or malignant. The accuracy of the proposed system is tested using Early Lung Cancer Action Program (ELCAP) public database CT lung images. The total sensitivity and specificity attained in our system for the above said database are 98.13 and 98.79% respectively. This results in a mean accuracy of 98.51% for training and testing in a sample of 103 nodules occurring in 50 exams. The rate of false positives per exam was 0.109. Also, a high receiver operating characteristic (ROC) of 0.9962 has been achieved.

An intelligent lung cancer diagnosis system using cuckoo search optimization and support vector machine classifier

The advancements in network technologies and processing of multimedia contents have provided the way for the distribution and sharing of multimedia contents through networks. This in turn has increased the demand for protecting the multimedia contents in terms of authentication, proof of ownership, copy control etc., which can be achieved by means of what is called digital watermarking. The challenges in watermarking techniques are how to achieve the imperceptibility, robustness and payload simultaneously. This paper presents a new bit plane sliced, scrambled color image watermark embedded on the color cover video using hybrid transforms such as Contourlet Transform (CT), Discrete Wavelet Transform (DWT) and Singular Value Decomposition (SVD) transformations with good imperceptibility, high robustness and at an information rate of (N ź number of motion frames) / 24 images per second of the video, where N is the total number of frames in the video. In order to achieve a good level of imperceptibility, we perform the following: First, we slice the color watermark image into 24 slices using the bit plane slicing mechanism. Subsequently, the so called Arnold transformation key is used to scramble those slices, to achieve first-level of security. Thus, an authenticated receiver with an appropriate key alone can descramble the received slices. Second, we embed those scrambled slices on one of the DWT mid-frequency coefficients (LH band) of successive 1-level CT non-motion frames of color cover video. The non-motion frames are identified using the histogram difference based shot boundary detection algorithm. Third, in order to the provide second-level of security, we generate a random eigen vector from the color watermark image, using co-variance matrix and maximum eigen value and then embed it on another DWT mid-frequency coefficients (HL band). Thus, embedding only the slices (not an entire image) will improve the level of imperceptibility. The mid-frequency embedding location can withstand against all low pass and high pass filtering attacks; thereby it increases the level of robustness. Thus, the proposed system is suitable for authentication. Finally, as far as payload is concerned, we need only 24 non-motion frames for embedding our watermark on to the cover video. Hence the remaining frames can be utilized for embedding other color images. Our simulation results prove that the proposed system provides trustworthy performance against various notable image processing attacks, multiple attacks, geometrical attacks, and temporal attacks.

A robust color video watermarking scheme based on hybrid embedding techniques

Research in the field of remote sensing attracts attention among researchers all over the world. From different remote sensing applications, the problem on Land Use/ Land Cover change analysis has been considered as the critical research for more than four decades. The researchers had discovered the new innovative ways of finding the solution to analyze the Land Use/ Land Cover change over a particular region. The multispectral and hyperspectral satellite images play a considerable part in analyzing environmental changes. Many algorithms developed and used by researchers for analyzing the Land Use/ Land Cover change are discussed in this paper. This review article aims to provide detailed analyses of performing Land Use/ Land Cover changes in the field of remote sensing. The main motive is to make the future researchers know about the flow of the Land Use/ Land Cover change analysis process and provide a clear presentation about every method. The results of this Land Use/ Land Cover problem mainly assist the land resource management, urban planners, and other government officials across the world in protecting the land resource and its nature for future needs.

Multispectral and hyperspectral images based land use / land cover change prediction analysis: an extensive review

The hyperspectral remote sensor acquires hundreds of contiguous spectral images, resulting in large data that contain a significant amount of redundant information. This high-dimensional and redundant data always influence the efficiency of the data processing. Therefore, feature extraction becomes one of the critical tasks in hyperspectral image classification. A transform-domain-based feature extraction technique, three-dimensional discrete cosine transform (3-D DCT), is proposed. The reason behind the transform domains is that, generally, an invertible linear transform reconstructs the image data to provide the independent information about the spectra or more separable transformation coefficients. Moreover, DCT has excellent energy compaction properties for highly correlated images, such as hyperspectral images, which reduces the complexity of the separation significantly. Unlike the discrete wavelet transform that requires sequential transform to obtain the approximation and detailed coefficients, DCT extracts all coefficients simultaneously. As a result, computation time in the feature extraction can be reduced. The experimental results on three benchmark datasets (Indian Pines, Pavia University, and Salinas) show that the proposed approach produces a good classification in terms of overall accuracy, average accuracy as well as Cohen’s kappa coefficient (κ) when compared with some traditional as well as transform-based feature extraction algorithms. Experimental result also shows that the proposed method requires less computational time than the transform-based feature extraction method.

/pdf/three-dimensional-discrete-cosine-transform-based-feature-4dq6rz9f7b.pdf

Three-dimensional discrete cosine transform-based feature extraction for hyperspectral image classification

Telemedicine is a rapidly developing application of clinical medicine where medical information is transferred through the internet and other networks for the purpose of consulting, and remote medical procedures or examinations. This paper presents a novel neural network inspired watermarking technique, to enhance the authentication of the transmitted sensitive medical images over telemedicine network. In order to examine the medical images, the multiple scan images of same type or different types can be considered as watermarks and the same are trained using Bidirectional Associative Memory (BAM) neural network. The resultant weight matrix is embedded in the less correlated Principal Component Analysis (PCA) components of the wavelet coefficients of the cover video frames using additive embedding type of watermark. At the receiver end, the same BAM neural network is used with the randomly generated target matrix and the extracted weight matrix as input. As a result of this, the input matrix will be obtained. From the input matrix, the physician can extract their own information or scan images using their private or secret key. The proposed watermarking technique is validated with the existing systems in terms of imperceptibility, robustness and watermark capacity using the metrics such as Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Normalized Cross Correlation (NCC), Bit Correction Rate (BCR), Detection rate, Receiver Operating Characteristics (ROC) and payload. The performance of the proposed system is evaluated by introducing various notable image processing attacks, geometrical attacks and video processing attacks on watermarked video. The experimental results demonstrate that the proposed technique has good perceptual quality of 50.6292 dB in terms of PSNR value, robustness of about nearly 1.0000 in terms of NCC value and payload of 1000 watermarks.

L. Agilandeeswari

Papers

An intelligent lung cancer diagnosis system using cuckoo search optimization and support vector machine classifier

A robust color video watermarking scheme based on hybrid embedding techniques

Multispectral and hyperspectral images based land use / land cover change prediction analysis: an extensive review

Three-dimensional discrete cosine transform-based feature extraction for hyperspectral image classification

A bi-directional associative memory based multiple image watermarking on cover video