The rapid growth of online financial transactions has made fraud detection a critical priority, especially with evolving fraud strategies that evade traditional systems. This paper presents a novel and secure fraud detection framework integrating Deep Learning (DL), Federated Learning (FL), and Quantum Encryption Communication (QEC). Our approach ensures high fraud detection accuracy while maintaining user data privacy and secure communication. We implemented a 3-layer GRU model using the MOON algorithm under the FL paradigm and achieved a global accuracy of 97.47%, outperforming traditional models like LSTM, 1D-CNN and XGBoost. To secure model parameter exchange between clients and server, we evaluated two entanglement-based Quantum Key Distribution (QKD) protocols — BBM92 and MDI-QKD. Experimental results revealed BBM92 to be more stable and suitable for integration with FL, demonstrating superior average secret key rate (SKR) and lower quantum bit error rate (QBER). The proposed system effectively combines accuracy, privacy, and quantum security, making it a scalable solution for real-world fraud detection.

Software Defect Prediction (SDP) empowers the creators to diagnose and unscramble defects in the introductory legs of the software evolution process to reduce the effort and cost invested in creating high-quality software. Feature Selection (FS) is critical to pinpoint the most pertinent features for defect prediction. This paper intends to employ a peculiar wrapper-based FS mode, dubbed DAOAFS, rooted on the dynamic arithmetic optimization algorithm (DAOA). Subsequently, this work evaluates the competence of the proposed FS mode using ten benchmark NASA datasets on four supervised learning classifiers, namely NB, DT, SVM, and KNN using accuracy and error curve as the standard performance measure metrics. This paper also correlates the proposed FS mode's conduct with existing FS techniques based on widely utilized meta-heuristic approaches such as GA, PSO, DE, ACO, FA, and SWO. This work employed Friedman and Holm test to ratify the proposed FS mode's statistical connotation. The investigatory outcomes supported the assertion that the recommended DAOAFS mode was effective in enhancing the efficacy of the defect forecasting model by achieving the highest mean accuracy of 94.76%. The findings also revealed that the proposed approach established its supremacy over the other studied FS techniques with bettered veracity in most instances.

In many diagnostic imaging settings, including positron emission tomography (PET), images are typically used for multiple tasks such as detecting disease and quantifying disease. Unlike conventional image reconstruction that optimizes a single objective, this work proposes a multi-objective optimization algorithm for PET image reconstruction to identify a set of images that are optimal for more than one task. This work is reliant on a genetic algorithm to evolve a set of solutions that satisfies two distinct objectives. In this paper, we defined the objectives as the commonly used Poisson log-likelihood function, typically reflective of quantitative accuracy, and a variant of the generalized scan-statistic model, to reflect detection performance. The genetic algorithm uses new mutation and crossover operations at each iteration. After each iteration, the child population is selected with non-dominated sorting to identify the set of solutions along the dominant front or fronts. After multiple iterations, these fronts approach a single non-dominated optimal front, defined as the set of PET images for which none the objective function values can be improved without reducing the opposing objective function. This method was applied to simulated 2D PET data of the heart and liver with hot features. We compared this approach to conventional, single-objective approaches for trading off performance: maximum likelihood estimation with increasing explicit regularization and maximum a posteriori estimation with varying penalty strength. Results demonstrate that the proposed method generates solutions with comparable to improved objective function values compared to the conventional approaches for trading off performance amongst different tasks. In addition, this approach identifies a diverse set of solutions in the multi-objective function space which can be challenging to estimate with single-objective formulations.

In multiobjective optimization, defining a good solution is a multifactored process. Most existing evolutionary multi- or many-objective optimization (EMO) algorithms have utilized two factors: 1) domination and 2) crowding levels of each solution. Although these two coarse-grained factors are found to be adequate in many EMO algorithms, their relative importance in an algorithm has been a matter of great concern to many current studies. We argue that beside these issues, other more fine-grained factors are of importance. For example, since extreme objective-wise solutions are important in establishing a noise-free and stable normalization process, reaching extreme solutions is more crucial than finding other solutions. In this paper, we propose an integrated algorithm, B-NSGA-III, that produces much better convergence and diversity preservation. For this purpose, in addition to emphasizing extreme objective-wise solutions, B-NSGA-III tries to find solutions near intermediate undiscovered regions of the front. B-NSGA-III addresses critical algorithmic issues of convergence and diversity-preservation directly through recent progresses in literature and integrates all these critical fine-grained factors seamlessly in an alternating phases scheme. The proposed algorithm is shown to perform better than a number of commonly used existing methods.

A measure for estimating the convergence characteristics of a set of non-dominated points obtained by a multi-objective optimization algorithm was developed recently. The idea of the measure was developed based on the Karush-Kuhn-Tucker (KKT) optimality conditions which require the gradients of objective and constraint functions. In this paper, we extend the scope of the proposed KKT proximity measure by computing gradients numerically and evaluating the accuracy of the numerically computed KKT proximity measure with the same computed using the exact gradient computation. The results are encouraging and open up the possibility of using the proposed KKTPM to non-differentiable problems as well.

Set-based multiobjective optimization methods, such as evolutionary multiobjective optimization (EMO) methods, attempt to find a set of Pareto-optimal solutions, instead of a single optimal solution. To evaluate these algorithms for their convergence to the efficient set in multiobjective optimization problems, the current performance metrics require the knowledge of the true Pareto-optimal solutions. In this paper, we develop a theoretically motivated Karush-Kuhn-Tucker proximity measure (KKTPM) that can provide an estimate of the proximity of a set of tradeoff solutions from the true Pareto-optimal solutions without any prior knowledge. Besides theoretical development of the proposed metric, the proposed KKTPM is computed for iteration-wise tradeoff solutions obtained from specific EMO algorithms on two-, three-, five-, and ten-objective optimization problems. Results amply indicate the usefulness of the proposed KKTPM as a metric for evaluating different sets of tradeoff solutions and also as a possible termination criterion for an EMO algorithm. Other possible uses of the proposed metric are also highlighted.