ABSTRACT Multimodal optimization problems (MMOPs) are critical in fields like game theory and robotics, where identifying multiple optimal solutions simultaneously is essential, yet challenging due to the need for effective global exploration and precise localization of optima. This study introduces the multimodal lotus effect algorithm (M‐LEA), a novel extension of our previously published lotus effect optimization algorithm (LEA), which was designed for single‐modal optimization and thus struggled to maintain multiple optima in complex multimodal spaces. M‐LEA addresses this limitation by incorporating a roaming technique with independently evolving subpopulations, enabling it to navigate multimodal spaces without requiring parameters such as radius or prior information about the number or distribution of optima. Its robustness is demonstrated through comparisons with five algorithms on the IEEE CEC2013‐2015 challenge, where M‐LEA consistently outperformed competitors. The algorithm's practical utility is further validated in two applications: identifying Nash equilibrium points in game theory and localizing resources via robotic systems. Results show that M‐LEA achieves superior performance and stability, making it well‐suited for scenarios demanding high efficiency and precision. These findings highlight M‐LEA's potential for diverse domains, paving the way for its application in game theory, robotics, and other fields requiring advanced multimodal optimization techniques.

Contrastive learning has arisen as a potent method in self-supervised learning (SSL), seeking to acquire rich and significant representations from unlabeled data by differentiating between positive and negative samples. However, the efficacy of contrastive learning is heavily contingent upon many aspects, including feature representation, hyperparameters, and data augmentation techniques, which are often manually tuned and suboptimal. To address these challenges, this research presents a unique framework named HOCLGA that uses Genetic Algorithms (GAs) to automate and optimize these critical components for contrastive learning. In fact, by combining GA with contrastive learning, we provide a systematic method for optimizing feature representations, improving the quality of learned representations, adjusting hyperparameters, investigating data augmentation techniques, and formulating SSL challenges. This study examines the use of self-supervised learning to enhance the precision of identifying damaged regions in medical imaging using High-Intensity Focused Ultrasound (HIFU). The framework is pretrained on large-scale datasets (ImageNet, DeepLesion, Breast Ultrasound) and fine-tuned for ultrasound image analysis. Experimental findings indicate that the proposed method may improve representation learning efficacy and provide substantial progress in medical picture interpretation. Specifically, it achieves the highest accuracy of 94.3

The injection of viscoelastic fluids into the oil-bearing formations to push the bypassed and entrapped oil toward the producers is a widely accepted technique known for creating a stable displacement front and piston-like displacement, leading to Enhanced Oil Recovery (EOR). However, the sweep efficiency of such complex fluids in stratified formations is still a topic of debate in the literature and is problematic, particularly in harsh reservoir conditions. This research concerns how the inclusion of nanoparticles into the polymer solution could affect the porous media flow of polymeric fluids in multilayered reservoirs. Accordingly, validated core-scale numerical models for polymer flood and polymer nanohybrid flood were upscaled to develop a reservoir-scale model. Through numerical simulations using a compositional reservoir simulator, the simultaneous flow of crude oil and polymer nanohybrids in both low and high-permeable layers of the reservoir were scrutinized. The numerical outputs showed that, compared with polymer flood, the flow dynamics of the polymer nanohybrids in different layers of the reservoir are more favorable, which resulted in improved oil recovery of over 20% of Residual Oil In Place (ROIP). Additionally, our numerical findings indicated that the polymer nanohybrids could exhibit lower polymer adsorption and acceptable salt tolerance in porous media.

Lack of diversity in synthetic data and inaccurate approximations of the minority class distribution are two main challenges with most oversampling techniques. This paper proposes a multi-manifold guided dictionary learning (M2GDL) approach for minority class oversampling. The proposed approach checks whether synthetic data points are useful and whether minority-class samples are important for data generation. The approach utilizes a linear combination of multiple manifolds by leveraging the inherent substructures of the data. Different data manifolds are constructed from the minority class training data and evaluated using a novel criterion. The importance of each sample is calculated within each manifold and then weighted according to the manifolds’ scores. Samples with the highest scores are identified as significant, and their K nearest neighbors are used to form a data dictionary for generating artificial data. The proposed sample generation method is achieved through the iterative solution of an optimization problem. Synthetic samples are then validated based on their proximity to the minority-class combinatorial manifold. Empirical evaluations across 22 datasets with varying degrees of class imbalance demonstrate that the proposed method outperforms recent oversampling approaches, particularly in scenarios with high imbalance.

Artificial intelligence-based models and robust computational methods have expedited the data-to-knowledge trajectory in precision medicine. Although machine learning models have been widely applied in medical data analysis, some barriers are yet to be challenging, such as available biosample shortage, prohibitive costs, rare diseases, and ethical considerations. Transcriptomics, an omics approach that studies gene activities and provides gene expression data such as microarray and RNA-Sequences faces the difficulties of biospecimen collection, particularly for mental disorders, as some psychiatric patients avoid medical care. Microarray data suffers from the low number of available samples, making it challenging to apply machine learning models. However, adversarial generative network (GAN), the hottest paradigm in deep learning, has created unprecedented momentum in data augmentation and efficiently expands datasets. This paper proposes a novel model termed MS-ACGAN, where the generator feeds on a bordered Gaussian distribution. In machine learning, calibration is of utmost importance, which gives insight into model uncertainty and is considered a crucial step toward improving the robustness and reliability of models. Therefore, we apply calibration techniques to classifiers and focus on estimating their probabilities as accurately as possible. Additionally, we present our trustworthy outputs by harnessing confidence intervals that confine the point estimate limitations and report a range of expected values for performance metrics. Both concepts statistically describe the implemented model's reliability in this study. Furthermore, we employ two quantitative measures, GAN-train and GAN-test, to demonstrate that the artificial data generated by our robust approach remarkably resembles the original data characteristics.

Abstract The adoption of Deep Neural Networks has surged due to their ability to automatically extract features and employ diverse approaches in data analysis. This research proposes a novel feature extraction method that doesn't rely on labeled training data, particularly considering the utilization of hard negatives. Given the remarkable success of DNN-based models in analyzing various medical images, including disease diagnosis and detection, this paper delves into diagnosing the lesion area against the normal area, particularly in the context of the non-invasive treatment of HIFU. Monitoring and analyzing inputs related to the lesion area are crucial to prevent damage to normal tissue during the heating process. However, several challenges exist in ultrasound medical imaging, including small sample sizes, data lacking labels, and the time-intensive nature of deep supervised training. These challenges have motivated the introduction of a new self-supervised deep learning method. While supervised learning excels in accuracy, unlabeled data holds valuable information discarded in supervised approaches. Conversely, ultrasonic data's nature lies in the RF signal, offering a detailed acoustic structure of tissue. Acknowledging the limitations and advantages of each method, an effective approach leveraging both signal and image simultaneously is presented. This integrated method enhances diagnostic capabilities and contributes to improve monitoring of HIFU procedures. The proposed methodology for classifying HIFU lesion areas attained high performance metrics: 95% accuracy, 94% precision, 96% recall, and a 95% F1-score. These outcomes underscore the efficacy of the proposed method in accurately classifying HIFU lesion areas.

Under-sampling is a technique to overcome imbalanced class problem, however, selecting the instances to be dropped and measuring their informativeness is an important concern. This paper tries to bring up a new point of view in this regard and exploit the structure of data to decide on the importance of the data points. For this purpose, a multi-manifold learning approach is proposed. Manifolds represent the underlying structures of data and can help extract the latent space for data distribution. However, there is no evidence that we can rely on a single manifold to extract the local neighborhood of the dataset. Therefore, this paper proposes an ensemble of manifold learning approaches and evaluates each manifold based on an information loss-based heuristic. Having computed the optimality score of each manifold, the centrality and marginality degrees of samples are computed on the manifolds and weighted by the corresponding score. A gradual elimination approach is proposed, which tries to balance the classes while avoiding a drop in the F measure on the validation dataset. The proposed method is evaluated on 22 imbalanced datasets from the KEEL and UCI repositories with different classification measures. The results of the experiments demonstrate that the proposed approach is more effective than other similar approaches and is far better than the previous approaches, especially when the imbalance ratio is very high.

Omics data are multidimensional, heterogeneous, and high throughput. Robust computational methods and machine learning (ML)-based models offer new prospects to accelerate the data-to-knowledge trajectory. Deep learning (DL) is a powerful subset of ML inspired by brain structure and has created unprecedented momentum in bioinformatics and computational biology research. This article provides an overview of the current DL models applied to multi-omics data for both the beginner and the expert user. Additionally, COVID-19 will continue to impact planetary health as a pandemic and an endemic disease, with genomic and multi-omic pathophysiology. DL offers, therefore, new ways of harnessing systems biology research on COVID-19 diagnostics and therapeutics. Herein, we discuss, first, the statistical ML algorithms and essential deep architectures. Then, we review DL applications in multi-omics data analysis and their intersection with COVID-19. Finally, challenges and several promising directions are highlighted going forward in the current era of COVID-19.

Here we introduce a new evolutionary algorithm called the Lotus Effect Algorithm, which combines efficient operators from the dragonfly algorithm, such as the movement of dragonflies in flower pollination for exploration, with the self-cleaning feature of water on flower leaves known as the lotus effect, for extraction and local search operations. The authors compared this method to other improved versions of the dragonfly algorithm using standard benchmark functions, and it outperformed all other methods according to Fredman's test on 29 benchmark functions. The article also highlights the practical application of LEA in reducing energy consumption in IoT nodes through clustering, resulting in increased packet delivery ratio and network lifetime. Additionally, the performance of the proposed method was tested on real-world problems with multiple constraints, such as the welded beam design optimization problem and the speed-reducer problem applied in a gearbox, and the results showed that LEA performs better than other methods in terms of accuracy.

Polymer nanohybrids have displayed great potential in remobilizing oil droplets through porous media. This research aims at providing some insights into how the hydrolyzed polyacrylamide (HPAM) polymer and Al2O3 nanoparticles’ (NPs) hybrid can push crude oil toward the producers. An understanding of what the hybrid viscosity is when flowing through porous rocks was acquired by the rheological tests. Using the Du Noüy ring method, the interfacial tension (IFT) between the polymer nanohybrid and crude oil was studied. Contact angle experiments were employed to assess the ability of hybrid in reversing surface wettability. The results show that the hybrid can yield a 12% higher shear viscosity than the HPAM solution and the viscosity improvement dramatically depends on NPs’ concentration and temperature. With more than a 23% drop in the contact angle value, the results of contact angle experiments reveal the capability of the Al2O3 NPs in altering surface wettability. The measured IFT between hybrid and crude oil at different temperatures demonstrates that the adsorption of NPs on the oil–aqueous phase interface can significantly improve the capillary number. This article not only presents the underlying mechanisms of oil recovery during hybrid flooding but also provides a new reference for formulating a novel hybrid agent.

Atrial fibrillation (AF) is the most prevalent cardiac arrhythmia and it is considered as one of the most important risk factor for death, stroke, hospitalization, and heart failure. It is possible to detect AF by analyzing electrocardiogram (ECG) of patients. To work on clean signals and reduce errors resulted from noise, we have used Butterworth filter. The short‐term Fourier transform was used to analyze ECG segments to obtain ECG spectrogram images. Convolutional neural network (CNN) models have been proposed for improving automatic detection of AF. The number of convolutional layers varies in different CNN models, and as the model become deeper, more hyper parameters are added. So in this article, variable length genetic algorithm was used in order to optimize hyper parameters of CNN. The results of experiments that performed on the MIT‐BIH AF database showed that the proposed method achieved 100%, 98.90%, and 99.95% for the sensitivity, specificity, and accuracy, respectively, so the proposed method outperforms the deep CNNs. Hence, the proposed method is an accurate and efficient method for detection of AF.

Improvement in information retrieval performance relates to the method of knowledge extraction from large amounts of text information on web. Text classification is one of application of knowledge extraction with supervised machine learning methods. This paper proposed Kullback-Leibler divergence KNN for classifying extracted features based on term weighting with Latent Dirichlet Allocation Algorithm. LDA is Non Negative matrix factorization method proposed for topic modelling and dimension reduction of high dimensional feature space .In traditional LDA, each component value is assigned using the information retrieval TF measure, While this weighting method seems very appropriate for IR, it is not clear that it is the best choice for TC problems. Actually, this weighting method does not leverage the information implicitly contained in the categorization task to represent documents. In this paper, we introduce a new weighting method based on Point wise Mutual Information for accessing the importance of a word for a specific latent concept, then each document classified based on probability distribution over the latent topics. Experimental result investigated when we used PMI measure for term Weighing and KNN with Kullback-Leibler distance, accuracy has been 82.5%, with lower complexity and same accuracy versus complex deep learning methods.

Massive amounts of data in social networks have made researchers look for ways to display a summary of the information provided and extract knowledge from them.Basic methods in the field used the criteria coming from graph theory, but new approaches are trying to take advantage of the realm of traditional data exploration and linked data.One of these new approaches is the approach called conceptual link approach, which was introduced to describe the social networks.In this approach, using the concept of contextual links, knowledge of the social network through a conceptual view of the dramatic structure is summarized as means of social networking.Conceptual perspective provides a summary of existing knowledge on a social network.In order to build this display, it is first needed to extract conceptual links from the intended network.However, extracting these links for networks with larger scale is very time consuming.In this paper, a new method for extracting frequent conceptual link from social networking is provided where by using the concept of dependency, it is tried to accelerate the process of extracting conceptual links.The proposed method will be able to accelerate this process if there are dependencies between data

Due to the dynamics of the power of resources in non-dedicated computing environments such as Grid, and on the other hand, the autonomy of these environments and, consequently, the impossibility of repeating the operating scenarios to compare the algorithms created in this context, creating an environment by providing such conditions is necessary. In this paper, a framework for evaluating workflow-scheduling algorithms has been created, focusing on the dynamics of the power of resources in distributed environments. This framework based on a switching model that is capable of considering the change in the processing power of resources with high precision. Using the ability of this framework, the effectiveness of several different workflow scheduling algorithms has been evaluated.

The first step in the process of detection a license plate is to determine the location of the plate. The output of this stage should be accurate enough and calculations will be completed within a short time. The reason for this is that the output of this stage is as input in the next steps. If the step to determine the location is encountered error. then the operation of the next steps will also be interrupted. In this paper, a new method is used to improve the contrast of the image, delete non-numeric characters, analysis and clustering of plain characters in order to determine the location of an Iranian car license plate with dark characters. a clear background is provided. The proposed method reduces the overall complexity of the algorithm and in addition to its ease of implementation, the system's speed and efficiency improve the location of the plate. The proposed algorithm is independent of the number of vehicle plates in the image, image size, complete unread plate and in contrast to brightness variations, it is largely resistant. The results of the test on two different data sets with 67 and 492 images, to an accuracy of 100 and 99.59 percent with an error rate of 1.5 and 1.63 and the runtime of 109 and 17.5 milliseconds averaged. were achieved.

Massive amounts of data in social networks have made researchers look for ways to display a summary of the information provided and extract knowledge from them. One of the new approaches to describe knowledge of the social network is through a concise structure called conceptual view. In order to build this view, it is first needed to extract conceptual links from the intended network. However, extracting these links for large scale networks is very time consuming. In this paper, a new algorithm for extracting frequent conceptual link from social networks is provided where by introducing the concept of dependency, it is tried to accelerate the process of extracting conceptual links. Although the proposed algorithm will be able to accelerate this process if there are dependencies between data, but the tests carried out on Pokec social network, which lacks dependency between its data, revealed that absence of dependency, increases execution time of extracting conceptual links only up to 15 percent.

ABSTRACTPolymer flooding is an attractive branch of chemical enhanced oil recovery techniques. Regrettably, chemical and mechanical degradation reduces the effectiveness of polymer flooding. This paper explores the effects of silica nanoparticles on flow behavior of polymer solution in porous media by employing both rheological experiments and numerical simulations. Experimental results indicate that dispersed silica nanoparticles in polymer solution are responsible for polymer adsorption reduction and the solution viscosity improvement. Simulation results revealed that if the injectant has some dispersed silica nanoparticles, the cumulative heavy oil recovery and breakthrough time will be bettered compared to the conventional polymer flood.

The hypertension is one of the most dangerous diseases that seriously threat the health of people and communities in the worldwide. This kind of disease often leads to fatal outcomes such as heart attack, stroke and renal failure. One of the most dangerous aspects of the hypertension is that you may not know that you have it. In fact, nearly one-third of people who have high blood pressure don't know it. The only way to know if your blood pressure is high is through the regular checkups. Therefore, an intelligent and accurate system in order to diagnosis this disease is needed. In this study, we’ve used two methods for the diagnosis of the hypertension. Firstly, a Fuzzy Expert system (FEs) is introduced for the diagnosis of the hypertension in adults. The input parameters include Systolic Blood Pressure (SBP) and Body Mass Index (BMI). Secondly, the multilayer neural network (MNN) with 5 inputs, 5 hidden layers and 1 output is employed for the diagnosis of the hypertension. The inputs include SBP, smoking, age, weight and BMI. Finally the results of two systems (FEs and MNN) are compared individually.

Voltage drop, multiple power outages, load imbalance and high losses are major problems appeared in distribution networks. Reconfiguration is the easiest and least costly solution to overcome the aforementioned challenges without any need to install additional equipment in the network. Reconfiguration can be defined as imposing changes to the topology of the distribution network by appropriate closing and opening of the network switches. Minimization of losses in a distribution network can be identified as the main objective of the reconfiguration. In this paper, a new evolutionary approach based on a hybrid fuzzyparticle swarm optimization (PSO) hybrid algorithm is proposed to solve the problem of the distribution networks reconfiguration. In this paper, results obtained using the proposed method, are compared with other methods. The obtained results indicate that use of the fuzzy system to adjust PSO parameters (i.e. C1, C2, W) enhances the performance of the reconfiguration algorithm, in terms of selection of the appropriate switches, and faster convergence of the PSO algorithm.