The growing impact of pandemics and infectious disease outbreaks has highlighted the need for vaccine allocation strategies that balance risk-profile protection, equity, and operational feasibility under limited healthcare resources. However, many existing approaches rely on predefined population groups and do not sufficiently integrate data-driven risk-profile information into constrained allocation planning. To address this issue, this study proposes an equity-aware decision-support framework that combines machine learning-based risk-profile stratification with multi-objective vaccine allocation. Publicly available French COVID-19 hospital-surveillance data are reorganized into analytical records to construct operational risk-profile classes for allocation-scenario analysis. A Light Gradient Boosting Machine model classifies these records into ordered risk-profile groups, which are then incorporated into a constrained allocation model. The model aims to maximize protection of higher-priority risk profiles, promote equity across predicted risk-profile groups, and minimize vaccination delays under supply and capacity constraints. The resulting optimization problem is solved using a binary Particle Swarm Optimization algorithm with constraint-handling mechanisms. Computational experiments assess algorithmic performance under a common objective-evaluation budget and examine the repair strategy, policy-weight configurations, Pareto-based compromises, classification uncertainty, scalability, and resource-capacity sensitivity. Overall, the framework supports the exploration of risk-profile-based vaccine allocation policies under constrained pandemic-response settings.

In this paper, we introduce a global framework integrating predictive analytics and multi-objective optimization for the purpose of home healthcare logistics optimization. First, several machine learning approaches such as Multinomial Logistic Regression, Support Vector Machines, Random Forest, AdaBoost, and Gradient Boosting are implemented to predict and classify patients' care requirements. This categorization not only separates professional-grade nurses from primary-grade nurses but also decides whether one caregiver or two caregivers are to be deployed depending on the condition of the patient (bedridden or semi-dependent). Secondly, we create a Multi-Objective Vehicle Routing Problem with Time Windows (MOVRPTW) to schedule the caregivers efficiently and reduce transport costs. Since the corresponding optimization problem is NP-hard, we take two advanced genetic algorithms Non-dominated Sorting Genetic Algorithm II (NSGA-II) and Strength Pareto Evolutionary Algorithm 2 (SPEA2) to find good-quality solutions. To solve the problems of bedridden patient care with multiple visits per day, our model incorporates synchronization constraints to ensure continuity of care and coordination among single-caregiver teams in case dedicated double teams are not possible. By combining predictive analytics with strong optimization techniques, our framework not only improves resource allocation effectiveness and facilitates timely service delivery but also decreases operating expenses, thus providing a holistic solution to the changing needs of home healthcare logistics.

As the need for emergency care services increases, healthcare facilities are recognizing the importance of tailored layout designs to improve patient care efficiency. Strategic layout planning is vital for managing variable productivity and meeting fluctuating demand effectively. The primary aim of tackling the emergency department layout (EDL) problem is to identify a facility configuration that satisfies both internal organizational needs and global healthcare certification standards. A novel mathematical model presented in the article offers a fresh approach to Emergency Department Layout (EDL) optimization, considering patient movement and process flow simultaneously. Our contribution lies in the development of a tailored solution to enhance the efficiency of healthcare facility layouts, setting our work apart from existing methods. The Particle Swarm Optimization (PSO) technique is proposed as a solution to the EDL problem, using a constructive heuristic to provide practical options. The technique's practical applicability is demonstrated through a real-world case study at Roanne Hospital in France, offering insights for improved healthcare delivery.

The promotion of e-commerce platforms has changed the lifestyle of several people from traditional marketing to digital marketing where businesses are made online and the concurrence reached high levels. These platforms have helped the ease of purchases while providing more advantages to the customers such as benefiting from a wide range of high-quality products, low prices, buying at any time, and more importantly supplying information and reviews about the products, and so on. Unfortunately, a plethora of companies mislead the customers to buy their products or demote the competitors' by using deceptive opinion spams which has a negative impact on the decision and the behavior of the purchasers. Deceptive opinion spams are written deliberately to seem legitimate and authentic so that to misguide or delude the customer's purchases. Consequently, the detection of these opinions is a hard task due to their nature for both humans and machines. Most of the studies are based on traditional machine learning and sparse feature engineering. However, these models do not capture the semantic aspect of reviews. According to many researchers, it is the key to the detection of deceptive opinion spam. Besides, only a few studies consider using contextual information by adopting neural networks in comparison with plenty of traditional machine learning classifiers. These models face numerous shortcomings as long as their representations are obtained while mining each review considering only words, sentences, reviews, or a combination of them, thereby classifying them based on their representations. In fact, deceptive opinions are written by the same deceivers belonging to the same companies with similar aims to promote or demolish a product. In other words, Deceptive opinion spams tend to be semantically coherent with each other. To the best of our knowledge, no model tries to obtain a representation based on the contextual relationships between opinions. This article proposes to use a capsule neural network, bidirectional long short-term memory, attention mechanism, and paragraph vector distributed bag of words to detect deceptive opinion spam. Our model provides a powerful representation of the opinions since it centers on the preservation of their contexts and the relationships between them. The results show that our model significantly outperforms the existing state-of-the-art models.

Image registration plays a crucial role in several areas, yet iconic registration methods are more efficient than those in geometrical registration, but they require great execution time. Regarding reduction in the execution time of iconic registration, the authors have proposed a new method based on mutual information while exploiting adaptive multiresolution decomposition, bidimensional empirical mode decomposition (BEMD) in its fast and adaptive version fast and adaptive BEMD (FABEMD). The idea is that instead of registering two images, the authors proceed to registration of the bidimensional intrinsic mode functions (BIMFs) that results from the FABEMD decomposition. The BIMF selected by the authors’ algorithm is characterised by preservation of the general form of the image, and it contains a tone of grey levels lower than that of the original image, thus the number of combinations of the grey levels, used while calculating entropy is reduced, which in turn reduces execution time of the registration.