Soft computing refers to a collection of imprecision-tolerant techniques which can fairly deal with uncertainty, partial truth,
and approximation. The basic constituents of soft computing are fuzzy logic, neural computing, evolutionary computation, and
machine learning. Soft computing may be viewed as a foundation component for the emerging field of conceptual intelligence
to generate human-type intelligence in computers. Most of the current research works are focused on one or the other methods
encouraged by these concepts and therefore, attracting students. Soft computing is having a especially important role in science
and engineering in many ways and becoming a backbone of almost all the upcoming technologies. This special issue contains
research contributions from leading scholars from all over the world with comprehensive coverage of each specific topic, highlighting
recent and future trends and describing the latest advances.
Highlighting theoretical perspectives and empirical research, we hope that this special issue will prove to be a comprehensive
reference source for researchers, practitioners, students, and professionals interested in the current advancements and efficient
use of Soft Computing methods.
This issue is a catalogue of ten quality papers presented by various authors across the globe. All the issues related to soft
computing and its applications are covered in the following papers:
A Comprehensive Review on Nature Inspired Neural Network-based Adaptive Filter for Eliminating Noise in Medical
Images:
In this comprehensive review article, more than 65 research articles are investigated to illustrate the applications of Artificial
Neural Networks (ANN) in the field of biomedical image denoising. The objective is to highlight the hybridized filtering
model using nature-inspired algorithms and artificial neural networks for suppression of noise. Various other techniques, such
as fixed filter, linear adaptive filters and gradient descent learning-based neural network filters, are also included. This article
envisages how to train ANN using derivative-free nature-inspired algorithms, and its performance in various medical images
modalities and noise conditions [1].
Computational Intelligence Techniques for Assessing Anthropometric Indices Changes in Female Athletes:
This research proposes a novel approach for determining the slimming effect of a herbal composition as a natural medicine
for weight loss. To build an effective prediction model, a modern hybrid approach, merging Adaptive Network-based Fuzzy
Inference System and Particle Swarm Optimization (ANFIS-PSO) was designed for prediction of changes in anthropometric
indices including waist circumference, waist to hip ratio, thigh circumference and mid-upper arm circumference, on female
athletes after the consumption of caraway extract during ninety days clinical trial. The outcomes showed that caraway extract
intake was effective in lowering all anthropometric indices in female athletes after ninety days trial. The results by ANFIS-PSO
was more accurate compared to SPSS [2].
An Improved B-hill Climbing Optimization Technique for Solving the Text Documents Clustering Problem:
This paper presents a novel local clustering technique, namely, β-hill-climbing, to solve the problem of the text document
clustering through modeling the β-hill-climbing technique for dividing the similar documents into the same cluster. The β parameter
is the primary innovation in β-hill climbing technique. Experiments were conducted on eight benchmark standard text
datasets with different characteristics taken from the Laboratory of Computational Intelligence (LABIC). The results proved
that the proposed β-hill-climbing achieved better results in comparison with the original hill-climbing technique in solving the
text clustering problem [3].
Modified Cuckoo Search Algorithm Using a New Selection Scheme for Unconstrained Optimization Problems:
In this paper, the modified cuckoo search algorithm (MCSA) is proposed to enhance the performance of CSA for unconstrained
optimization problems. MCSA is focused on the default selection scheme of CSA (i.e. random selection), which is
replaced with tournament selection. The experimental results showed that the performance of MCSA outperformed standard
CSA and the existing literature methods [4].
An Intuitionistic Fuzzy Based Novel Approach to CPU Scheduler:
This paper introduces a novel approach to design an intuitionistic fuzzy inference system for CPU scheduler. The proposed
inference system is implemented with a priority scheduler. The proposed scheduler has the ability to dynamically handle the
impreciseness of both priority and estimated execution time. Simulation results prove the effectiveness and efficiency of intuitionistic
fuzzy-based priority scheduler [5].
Cat Swarm Optimization based Functional Link Multilayer Perceptron for Suppression of Gaussian and Impulse Noise
from Computed Tomography Images:
This paper discusses the Gaussian and impulse noise that corrupts the Computed Tomography (CT) images either individually
or collectively, and the conventional fixed filters that do not have the potential to suppress these noises. These spurious noises affect the inherent features of the CT image. Hence, to handle such a situation, an adaptive Cat Swarm Optimization
based Functional Link Multilayer Perceptron (CSO-FLMLP) has been proposed in this paper to get rid of unwanted noise from
the CT images. In this work, the cost function considered for CSO highlights the error between noisy and contextual pixels of
reference images. For examining the efficiency of the CSO-FLMLP filter, it is compared with the other six competitive adaptive
filters [6].
Implementation and Analysis of Classification Algorithms for Diabetes:
This paper presents a novel classification technique for the detection of diabetes in a timely and effective manner. In this
study, a comparative analysis of outcomes obtained by with and without the use of GA for the same set of classification technique.
It has been conclusively inferred that GA is helpful in removing insignificant attributes, reducing the cost and computation
time while enhancing ROC and accuracy. The utilized strategy may likewise be executed for other medical issues [7].
Multi-Objective Evolutionary Approach for the Performance Improvement of Learners Using Ensembling Feature selection
and Discretization Technique on Medical Data: This paper proposes a novel multi-objective based dimensionality
reduction framework, which incorporates both discretization and feature reduction as an ensemble model for performing feature
selection and discretization. The selection of optimal features and categorization of discretized and nondiscretized features from
the feature subset are governed by the multi-objective genetic algorithm (NSGA-II). An extensive experiment was conducted
on the dataset, to prove that the proposed model improves the classification rate and outperforms the base learner [8].
Design of Patient-Specific Spinal Implant (Pedicle Screw Fixation) using FE Analysis and Soft Computing Techniques:
This work uses the Genetic Algorithm (GA) for optimum design of patient-specific spinal implants (pedicle screw) with
varying implant diameter and bone condition. The optimum pedicle screw fixation in terms of implant diameter works on the
basis of minimum strain difference from the intact bones (natural) to implantation at the peri-prosthetic bone for the considered
six different peri-implant positions. This design problem is expressed as an optimization problem using the desirability function,
where the data generated by finite element analysis is converted into an Artificial Neural Network (ANN) model [9].
Half Difference Expansion Based Reversible Data Hiding Scheme for Medical Image Forensics:
Medical image authentication is an important area which attempts to establish ownership authentication and data authentication
of medical images. In this paper, the authors proposed a new reversible watermarking scheme based on a novel half difference
expansion technique for medical image forensics. Experimental study of the proposed scheme on the standard medical
images from the Osrix medical image data set showed that the proposed watermarking scheme outperforms the existing
schemes in terms of the visual quality of the watermarked image and embedding rate [10].
We express our heartfelt gratitude to all the authors, reviewers and Bentham Science personnel, especially Aqsa Hassan, for
endless motivation and patience. Special thanks to Ms. Ambreen Irshad and Romasa Azhar Mahaser for their constant support.
We hope that this issue will be beneficial to all the concerned readers.