Differential evolution (DE) is one of the highly acknowledged population-based optimization algorithms due to its simplicity, user-friendliness, resilience, and capacity to solve problems. DE has grown steadily since its beginnings due to its ability to solve various issues in academics and industry. Different mutation techniques and parameter choices influence DE's exploration and exploitation capabilities, motivating academics to continue working on DE. This survey aims to depict DE's recent developments concerning parameter adaptations, parameter settings and mutation strategies, hybridizations, and multi-objective variants in the last twelve years. It also summarizes the problems solved in image processing by DE and its variants.
Deep learning (DL) models are becoming pervasive and applicable to computer vision, image processing, and synthesis problems. The performance of these models is often improved through architectural configuration, tweaks, the use of enormous training data, and skillful selection of hyperparameters. The application of deep learning models to medical image processing has yielded interesting performance, capable of correctly detecting abnormalities in medical digital images, making them surpass human physicians. However, advancing research in this domain largely relies on the availability of training datasets. These datasets are sometimes not publicly accessible, insufficient for training, and may also be characterized by a class imbalance among samples. As a result, inadequate training samples and difficulty in accessing new datasets for training deep learning models limit performance and research into new domains. Hence, generative adversarial networks (GANs) have been proposed to mediate this gap by synthesizing data similar to real sample images. However, we observed that benchmark datasets with regions of interest (ROIs) for characterizing abnormalities in breast cancer using digital mammography do not contain sufficient data with a fair distribution of all cases of abnormalities. For instance, the architectural distortion and breast asymmetry in digital mammograms are sparsely distributed across most publicly available datasets. This paper proposes a GAN model, named ROImammoGAN, which synthesizes ROI-based digital mammograms. Our approach involves the design of a GAN model consisting of both a generator and a discriminator to learn a hierarchy of representations for abnormalities in digital mammograms. Attention is given to architectural distortion, asymmetry, mass, and microcalcification abnormalities so that training distinctively learns the features of each abnormality and generates sufficient images for each category. The proposed GAN model was applied to MIAS datasets, and the performance evaluation yielded a competitive accuracy for the synthesized samples. In addition, the quality of the images generated was also evaluated using PSNR, SSIM, FSIM, BRISQUE, PQUE, NIQUE, FID, and geometry scores. The results showed that ROImammoGAN performed competitively with state-of-the-art GANs. The outcome of this study is a model for augmenting CNN models with ROI-centric image samples for the characterization of abnormalities in breast images.
Shigella-infected bacillary dysentery or commonly known as Shigellosis is a leading cause of morbidity and mortality worldwide. The gradual emergence of multidrug resistant Shigella spp. has triggered the search for alternatives to conventional antibiotics. Phage therapy could be one such suitable alternative, given its proven long term safety profile as well as the rapid expansion of phage therapy research. To be successful, phage therapy will need an adequate regulatory framework, effective strategies, the proper selection of appropriate phages, early solutions to overcome phage therapy limitations, the implementation of safety protocols, and finally improved public awareness. To achieve all these criteria and successfully apply phage therapy against multidrug resistant shigellosis, a comprehensive study is required. In fact, a variety of phage-based approaches and products including single phages, phage cocktails, mutated phages, genetically engineered phages, and combinations of phages with antibiotics have already been carried out to test the applications of phage therapy against multidrug resistant Shigella. This review provides a broad survey of phage treatments from past to present, focusing on the history, applications, limitations and effective solutions related to, as well as the prospects for, the use of phage therapy against multidrug resistant Shigella spp. and other multidrug resistant bacterial pathogens.
Globally, water pollution from the textile industries is an alarming issue. Malachite Green dye of the triphenylmethane group is an extensively used dye in the fabric industries that is emitted through textile wastewater. This study aimed to isolate and characterize potential Malachite Green (MG) dye degrading bacteria from textile effluents. Different growth and culture parameters such as temperature, pH and dye concentration were optimized to perform the dye-degradation assay using different concentrations of MG dye in the mineral salt medium. A photo-electric-colorimeter was used to measure the decolorizing activity of bacteria at different time intervals after aerobic incubation. Two potential bacterial strains of Enterobacter spp. CV-S1 (accession no: MH450229) and Enterobacter spp. CM-S1 (accession no: MH447289) were isolated from textile effluents exhibiting potential MG dye decoloring efficiency. Further, the RAPD analysis and 16S rRNA sequencing confirmed the genetic differences of the isolated strains. Enterobacter sp CV-S1 and Enterobacter sp CM-S1 can completely decolor MG dye up to 15 mg/L under shaking condition without any requirement of sole carbon source. Thus, these two bacteria have the potency to be utilized in the textile wastewater treatment plant.
Industrial effluent containing textile dyes is regarded as a major environmental concern in the present world. Crystal Violet is one of the vital textile dyes of the triphenylmethane group; it is widely used in textile industry and known for its mutagenic and mitotic poisoning nature. Bioremediation, especially through bacteria, is becoming an emerging and important sector in effluent treatment. This study aimed to isolate and identify Crystal Violet degrading bacteria from industrial effluents with potential use in bioremediation. The decolorizing activity of the bacteria was measured using a photo electric colorimeter after aerobic incubation in different time intervals of the isolates. Environmental parameters such as pH, temperature, initial dye concentration and inoculum size were optimized using mineral salt medium containing different concentration of Crystal Violet dye. Complete decolorizing efficiency was observed in a mineral salt medium containing up to 150 mg/l of Crystal Violet dye by 10% (v/v) inoculums of Enterobacter sp. CV-S1 tested under 72 h of shaking incubation at temperature 35 °C and pH 6.5. Newly identified bacteria Enterobacter sp. CV-S1, confirmed by 16S ribosomal RNA sequencing, was found as a potential bioremediation biocatalyst in the aerobic degradation/de-colorization of Crystal Violet dye. The efficiency of degrading triphenylmethane dye by this isolate, minus the supply of extra carbon or nitrogen sources in the media, highlights the significance of larger-scale treatment of textile effluent.