Side-scan sonar is a widely explored technology for underwater exploration. It has a variety of utilization in research and industry, which facilitates scientific understanding, resource management, and safety of maritime activities. These images can be used in underwater image communication but suffer due to the limited acoustic channel bandwidth. The segmented images may be used instead for communication purposes but the process of segmentation of these images is hindered by influence of a large noise along with low resolution, complicating the segmen-tation process. In this work, an evolutionary dynamic many-objective optimization algorithm, KRR-DNSGA-III is proposed. This algorithm is equipped with KRR-ANOVA predictor for predicting the new solutions closer to the reference points. A modified mutation technique is also introduced for achieving faster convergence. Performance of the proposed algorithm is verified on four benchmark JY problems along with another problem from DF test suite. The algorithm is then used to segment a set of images from Seabed objects KLSG- II dataset.

Dynamic multi-objective TSP (DMTSP) finds extensive applications in scheduling and routing problems. The task is challenging due to the change in problem environment (arrangement and number of cities) after certain time period. To solve this, in this manuscript a new prediction based dynamic multi-objective optimization method termed as Dynamic non-dominated sorting genetic algorithm III (DNSGA-III) is proposed. This approach reuses the information obtained from previous Pareto optimal sets (POS) to train prediction models. The prediction has been carried out with SVR-RBF, SVR-Linear, polynomial interpolation and cubic spline based prediction approaches and to determine new solutions that are closer to the reference points. This significantly promote population diversity, along with desired convergence. Performance of the proposed DNSGA-III approach has been validated on four benchmark JY test problems. Further a sixteen cities DMTSP problem with two objective functions is solved using the proposed algorithm.

Seismicity de-clustering is the technique to isolate the earthquake catalog into aftershock-foreshock (clustered) and background (random) events. These isolated events are widely used in seismology for hazard assessment and to design the model for future earthquake predictions. The key challenge in seismic de-clustering is due to significant overlapping and high correlation between the space-time domain of aftershock-foreshock and background events. In this manuscript, a new model is proposed to de-cluster earthquake catalog based on a binary Non-dominated sorting genetic (B/NSGA)-II algorithm. In the fundamental version of the popular NSGA-II algorithm, one apprehension is that crossover and mutation are performed only on real-valued population. Here binary domain logical crossover and mutation operators are employed to optimally segregate the seismic events. The proposed model is tested on thirty year historical earthquake catalog of Turkey and Chile. Comparative analysis has been demonstrated with five benchmark de-clustering techniques. The simulation results demonstrate the potential of the proposed model efficiently discriminates the aftershocks and background events in the two catalogs.

Automatic cloud detection algorithm based on supervised learning approach has emerged due to its effectiveness in extracting weather information in satellite images. However, algorithm requires field‐expert intervention with huge database of training samples to evaluate its clustering performance. Moreover, lacking in availability of labelled data makes difficult to train the input samples. Therefore, this article puts forward unsupervised many‐objective evolutionary clustering technique to discriminate cloudy regions on varying characteristic of underlying surfaces. The study begins with the modification in search capability of ‐NSGA‐III optimisation algorithm by incorporating penalised vector angle concept in associate operator. The analysis of proposed approach has been carried out on benchmark many‐objective DTLZ test problems, compared against original ‐NSGA‐III and NSGA‐III algorithms. The proposed modified ‐NSGA‐III has been further utilised as clustering technique to solve unsupervised cloud detection problem. Optimal centroid vector for clustering using proposed approach is obtained through modified crossover operator, mutation operator and environmental selection method. Experimental results reveal that proposed approach outperforms comparative many‐objective algorithms, MOEA/D and NSGA‐III for Landsat 8, MODIS and NOAA satellite images with lower classification average error of % in cloud detection for most of the evaluated test cases.

High spectral correlation among bands lead to unsupervised band selection problem in hyper-spectral images. Moreover, the presence of large number of spectral bands increase the classification complexity task. This matter is efficiently handled by non-dominated sorting method in third version of NSGA algorithm (NSGA-III). However, a concern about the NSGA-III algorithm is that it uses crossover operator for real-value initialized population. To overcome with this problem, present study introduces logical crossover and mutation operator to strengthen the performance of NSGA-III to select optimal set of bands. This enhanced algorithm is named as `Binary NSGA-III' which is further implemented in order to separate distinguish spectral classes. Further, the optimized set of bands is used as feature set to provide automated classification system using K-means technique. The experimental results demonstrate the promising discriminant potential when compared against conventional methods.

Physarum optimization becomes popular after Liu et al in 2015 applied it for solving Steiner tree problem in networks. It has been effective in designing complicated road transportation networks, drug similarity networks and node-weighted protein-protein interaction network for cancer. In this paper, a clustering network is proposed based on Physarum optimization to identify the aftershocks (hazardous events) in the seismic catalog. In seismology, the process of identification of aftershocks and backgrounds (events due to regular earth movements) is popularly termed as declustering of earthquake catalog. Therefore the optimized networks obtained for aftershocks is termed as `Earthquake Clustering Network (ECN)'. The simulation studies are carried out on benchmark catalogs of Southern California and Japan. It is observed that the ECNs obtained from both the catalogs contain all the mainshocks and aftershocks occurred for the duration of the catalogs. The lambda plots obtained justify that identified aftershocks with ECN following the pattern of total events whereas the declustered events follow a uniform distribution. Comparative analysis demonstrates the effectiveness of the proposed model over three other benchmark declustering methods.

In this paper, a distributed K-Means algorithm is proposed based on the point symmetry distance measure which is termed as “Point symmetrical based distributed K-Means (PSDK-Means)” algorithm. Conventional distributed K-Means (DK-Means) clustering is able to detect only spherical shape clusters and it is not suitable for identifying the convex and concave (arbitrary shaped) clusters. The proposed method is implemented to detect spherical, convex and non-convex shape clusters which are distributed over the network at different peers. In the proposed method, cluster centers are shared using the diffusion based cooperation to achieve global clustering of the network. The cluster assignment is carried out using minimum point symmetry distance instead of Euclidean distance. Effectiveness of the proposed PSDK-Means algorithm has been validated on four synthetic and two real life datasets where it is observed to outperform conventional DK-Means algorithm.

Denoising of hyperspectral images is an essential step to remove the visual artifacts and improve the quality of an image. There are various sources of noise such as dark current, thermal and read noise produced due to detectors, stochastic error of photo‐counting and so on which leads to variability of noise both in spatial and spectral domains. In this study, author proposes a novel denoising method based on concept of Hilbert vibration decomposition (HVD). Being iterative in nature it segregates initial amplitude composition into various components which are composed of slow varying wavelength. Any hyperspectral image is captured by the sensor over contiguous wavelengths. Thus, variation in intensities over the spectral dimension is less. HVD separates pixels in decreasing order of their intensity and results in denoising of the image. To evaluate method, various noise conditions have been tested on three real datasets: Washington DC mall, Urban and Pavia University. The validation is done both visually and quantitatively. The denoising with almost 100% mean structural similarity index confirms superiority of the designed method. Clustering and spectral analysis of various denoised images have also been reported. Clustering accuracy of 65% is achieved by the HVD as compared to other methods.

From the decades, due to the independent and Poisson nature of background seismicity, they are extensively used for hazard analysis, modelling of prediction phenomenon and also used for earthquake simulations. In this study, a tetra‐stage cluster identification model is proposed for accurate estimation of background seismicity and triggered seismicity. The proposed method considers a seismic event's occurrence time, location, magnitude and depth information available in the given catalogue to classify the event as a background or aftershock. The model has flexible threshold parameters which can be tuned to a proper value according to the specific seismic zone to be analysed. It exploits the current seismic activities of the region by taking care the past samples of the region over last 25 years. The analyses of Japan, Himalaya and Taiwan catalogues are carried out using the proposed model. Superior results with the proposed model are achieved, compared with benchmark models by Nanda et al ., Gardner–Knopoff and Uhrhammer et al . in terms of percentage of background seismicity, lambda plot and cumulative plot. The ergodicity present in the original seismic catalogue and catalogue after de‐clustering are compared using Thirumalai‐Mountain metric to justify the stationary and linearity.

The declustering of an earthquake catalog identify the background events (seismic events generated by regular earth movements), which leads to an unbiased estimation of seismic activities in a region. The ergodicity of a seismic region represents the ensemble average of events in time and space. The ergodicity of a seismic catalog is represented by a Thirumalai-Mountain (TM) metric. If the inverse TM metric becomes linear with time then the catalog is assumed to be declustered (it contains only the background events). But the original catalog normally contains backgrounds as well as seismically triggered events (Foreshocks and Aftershocks). The objective here is to optimally remove the triggered events from the catalog with an optimization algorithm so that the remaining catalog contains only the backgrounds. Here a parallel Grey Wolf Optimization (P-GWO) is introduced to perform the optimization task. Compared to the original GWO here the new updated positions of wolves are computed in parallel which reduces the computational complexity of the algorithm keeping the same accuracy level. The analysis is carried out on Southern California catalog and the results obtained are superior to that achieved by Cho et al. using PSO in 2010. Comparative results also demonstrate better performance over three benchmark statistical de-clustering methods by Gardner-Knopoff, Uhrhammer and Reseanberg.

Combining the good features of particle swarm optimization (PSO) and artificial immune system (AIS) we propose a new Immunized PSO (IPSO) algorithm. This algorithm is used to identify generalized Hammerstein model by employing functional link artificial neural network (FLANN) architecture for the nonlinear static part and an adaptive linear combiners for the linear dynamic part of the model. Simulation study of few benchmark Hammerstein models is carried out through simulation study and the results obtained are compared with those obtained by standard PSO and AIS based method. Comparison of results demonstrate superior performance of the proposed methods over its PSO and AIS counterpart in terms of response matching, accuracy of identification and convergence speed achieved.