Across the globe, women suffer from breast cancer fatal disease. It is arising surprisingly due to a lack of awareness among them and the inconvenient reach of diagnostic systems. Many computer-aided diagnostic systems have been developed for the detection of cancer. These systems have quite lower performance, so more accurate diagnosis is the need of the time to save the life of human beings. For large and imbalanced image datasets, efficient learning of the network is very important to detect and classify breast cancer more accurately. In this paper, a graph based adaptive regularized learning of deep network (GARL-Net) is proposed for more accurate breast cancer classification. Transfer learning is used for training the bakebone network DenseNet121. furthermore, fine tuning of bakebone network is followed by the estimated improved loss function. The improved loss function is actually graph based adaptively regularized complement cross entropy loss. The SoftMax cross entropy in itself is not sufficient to classify image samples accurately, complement entropy technique is incorporated to overcome the misclassification issue with the cross-entropy loss. Further, by adaptive scaling of regularization term with spatial graph Laplacian basis used to adaptively penalize the complement cross entropy loss for improving the learning of the network. The performance of the proposed method is evaluated using BreakHis and BACH 2018 histopathology image datasets and outperforms the existing state-of-the-art methods and achieved 99.00% of precision, 99.40% of recall, 99.20 % of F-1score, and 99.49% of accuracy for binary classification of breast cancer image samples of BreakHis dataset.

The present era of advances in desalination plants revolves around the involvement of artificial intelligence techniques in ameliorating their modeling and operational performance. Among the two objectives, an accurate modeling of the plant’s behavior may certainly help the design engineers to operate the plant in more stable and controlled operating conditions so as to achieve higher plant efficiency. Furthermore, this helps eliminate the risk to the operator’s life and reduces production time, energy, and money. From the literature, it is observed that Artificial Neural Network (ANN) has been the most extensively used approach for modeling and simulation of the desalination plant. However, ANN has the concept of biases and weights updation for better prediction and accuracy of the predicted model, but the conventional methods do not yield desirable results. So, the updation of biases and weights using optimization algorithms is preferred in the literature. Therefore, this paper presents the Grey Wolf Optimizer based ANN (GWO-ANN) approach for desirable prediction and accuracy of models. Further, six models (GWO-ANN Model-1 to Model-6) are proposed to more accurately predict the Reverse Osmosis (RO) desalination plant’s performance. For this investigation, we have considered four experimental inputs (feed water salt concentration, condenser inlet temperatures, evaporator inlet temperatures, and feed flow rate) and one output (permeate flux). The simulation results predict output performance in quite proximity to the experimental datasets. The simulated hybrid GWO-ANN models (best of best results of GWO-ANN Model-2: $\text{R}^{2} \,\,=98.9$ %, Error = 0.007) show superior results than the reported results from the existing Response Surface Methodology (RSM) ( $\text{R}^{2} \,\,=98.5$ %, Error = 0.100) and ANN models ( $\text{R}^{2} =98.8$ %, Error = 0.060) and other PSO-ANN Model ( $\text{R}^{2} \,\,=96.3$ %, Error = 0.025) and GA-ANN model ( $\text{R}^{2} =98.7$ %, Error = 0.008). This research exemplifies the involvement of superior nature-inspired intelligent techniques in this modern era to further enhance the savings in production time, energy, and investment of desalination plants.

Desalination plants have an important concern regarding controlling the permeate flow rate and pH during operability. This paper proposes the proportional integral derivative (PID) control design using modified Particle Swarm Optimization (PSO) techniques called autonomous groups PSO (AGPSO) in the two-input two-output (TITO) RO desalination plant to control the permeate flow rate and pH . Here, three different versions (AGPSO1, AGPSO2, and AGPSO3) of the AGPSO algorithm are utilized to design PID control for the same TITO plant. In addition, an integral time absolute error ( J _ITAE ) based objective function is utilized to design a PID controller. The simulation results suggest that the proposed controller designs are flexible, self-tuning, and have stable characteristics, while the AGPSO3-PID control design attained a robust design for optimum tuning compared to existing improved grey wolf optimization PID (IGWO-PID) and other versions of AGPSO based PIDs (AGPSO1-PID, AGPSO2-PID). The design of AGPSO-PID achieved a minimum objective function than existing IGWO-PID and other versions of AGPSO based PIDs {AGPSO1-PID, AGPSO2-PID}. Finally, the proposed controller designs outperform the existing IGWO-PID design in literature in terms of control performance, demonstrating a precise control for and the improvement of plant performance.

This paper evaluates the performance of six different machine learning (ML) algorithms for classifying power quality disturbances (PQDs), with statistical features extracted using discrete wavelet transform (DWT) as feature input. The statistical features have been extracted from coefficients of multi-resolution analysis (MRA) using four different mother wavelets: Daubechies 4 (‘db4’), ‘haar’, Discrete Meyer (‘dmey’), Coiflets 4 (‘coif4’). The performance analysis has been carried out with 5,500 synthetic signals pertaining to eleven different PQDs generated in accordance with IEEE 1159-2019. Moreover, the performance of the classifiers trained with synthetic signals has been investigated under the influence of unseen noisy signals, hardware PQD signals obtained from the experimental setup, and real PQD events. The analysis indicates that the performance of the extra tree (ET) classifier with the features extracted using ‘haar’ as a mother wavelet is superior and robust in comparison to other classifiers, viz k-nearest neighbor (kNN), random forest (RF), decision tree (DT), logistic regression model (LRM), and gaussian naïve bayes (GNB) with features extracted using different mother wavelets. Furthermore, the ‘haar-ET’ based technique demonstrated remarkable performance in classifying PQDs, showing strong generalization to both unseen hardware and noisy signals, and achieving consistent results when tested with real PQD events.

An accurate prediction of the performance of water treatment desalination plants could directly improve the global socio-economic balance. In this regard, many researchers have been engaged in the various artificial intelligence applied soft computing techniques to predict actual process outcomes. Inspired by the significance of such techniques, an optimized Particle Swarm Optimization based Artificial Neural Network (PSO-ANN) technique has been proposed herewith to predict an accurate performance of the reverse osmosis (RO) based water treatment desalination plants. Literature suggests that the improvements of the soft computing models depend on their modeling parameters. Therefore, we have included an extended list of nine modeling parameters with a systematic indepth investigation to explore their optimal values. Finally, the model's simulations results (R2 = 99.1%, Error = 0.006) were found superior to the existing ANN models (R2 = 98.8%, Error = 0.060), with the same experimental datasets. Additionally, the simulation results recommend that among many parameters considered, the number of hidden layer nodes (n), swarm sizes (SS), and the weight of inertia (ω) play a major role in the model optimization. This study for a more accurate prediction of the plant's performance shall pave the way for the process design and control engineers to improve the plant efficiency further.

The authentication of digital images poses a significant challenge due to the wide range of image forgery techniques employed, with one notable example being a copy-move forgery. This form of forgery involves duplicating and relocating segments of an image within the same image, often accompanied by geometric transformations to deceive viewers into perceiving the forged image as authentic. Furthermore, additional processing techniques like scaling, rotation, JPEG compression, and the application of Additive White Gaussian Noise (AWGN) are frequently employed to further obscure any traces of forgery, making the detection and verification process even more complex. This paper presents a novel approach for detecting copy-move forgery in digital images using the self-supervised image keypoint detector, SuperPoint. Our approach leverages the advanced capabilities of SuperPoint, which combines keypoint detection and descriptor extraction, to identify and localize copy-move forgery accurately. One important aspect of our approach is its ability to handle images with different textures, including smooth and self-similar structural images. The proposed approach is able to produce stable results in images with various attacks, making it a functional and reliable tool for detecting copy-move forgery in a diverse range of forged images. Comparative analysis with existing forgery detection methods shows the superior performance of our proposed approach. Furthermore, the computational efficiency of our algorithm enables real-time forgery detection. Our approach using SuperPoint offers an effective solution for detecting copy-move forgery in digital images, making it valuable for image forensics and authenticity.