This paper develops an unsupervised discriminant projection (UDP) technique for dimensionality reduction of high-dimensional data in small sample size cases. UDP can be seen as a linear approximation of a multimanifolds-based learning framework which takes into account both the local and nonlocal quantities. UDP characterizes the local scatter as well as the nonlocal scatter, seeking to find a projection that simultaneously maximizes the nonlocal scatter and minimizes the local scatter. This characteristic makes UDP more intuitive and more powerful than the most up-to-date method, locality preserving projection (LPP), which considers only the local scatter for clustering or classification tasks. The proposed method is applied to face and palm biometrics and is examined using the Yale, FERET, and AR face image databases and the PolyU palmprint database. The experimental results show that UDP consistently outperforms LPP and PCA and outperforms LDA when the training sample size per class is small. This demonstrates that UDP is a good choice for real-world biometrics applications

The metaverse is swiftly flattering an important player in the e‐commerce domain. It provides innumerable opportunities and indicates a revolutionary paradigm shift in e‐commerce. Online businesses can now create virtual storefronts that enable immersive, lifelike product exploration within the metaverse, in contrast to traditional brick‐and‐mortar stores that cater to local customers. Current research offers a novel conceptual framework based on theories of interactive media effects and the stimulus–organism–response paradigm to understand consumer purchase intentions in the metaverse. Carefully gathered data from 342 survey participants were then examined using the analytical tools of structural equation modelling (SEM) and importance–performance map analysis (IPMA). The results of the study shed light on how much perceived augmentation and interaction affect consumers’ cognitive and emotive reactions, including feelings of realism, immersion, and telepresence. Remarkably, these reactions have a significant influence on how customers behave. The study’s distinctive worth is found in its creative recommendations, which can help tech firms and metaverse developers improve the purchasing experience in this dynamic digital environment.

This research is among the very few studies seeking a focalized examination on the relationship between knowledge sharing within a firm and organizational innovation. This specific study establishes that the knowledge sharing and innovation processes in Islamic banks are integral parts of the survival and progress of business organizations. Knowledge sharing and creativity are essential elements in the development of innovative strategies, but few studies have sought to investigate this relationship. This study proposes a framework with five hypotheses, which predicts the influences of knowledge sharing and organizational innovation on the Pakistani banking sector. This survey scrutinizes the impacts of knowledge sharing and innovation, and its primary objective is to determine how learning in Islamic banks mediates the relationship, and enhances the performance, of Pakistani Islamic banks. The authors distributed a self-administered survey, and randomly selected 554 employees from Mirpur AJ&K, Rawalpindi and Islamabad, Pakistan. We screened and tested the data received using SPSS version 25 for analysis purposes to measure the strength of the relationships which exist among the studied variables. The findings indicate that all of the proposed hypotheses have significant positive relationships, proving that knowledge sharing and organizational innovation have mediating impacts upon organizational learning. The findings can also be used to propose a systematic and holistic framework for attaining an improved performance in Islamic banks through the mediating role of organizational learning. This study offers empirical evidence and original data to examine the connection between knowledge sharing, innovation processes and learning culture in Islamic Banks. The generalizability of these findings is restricted to Islamic banks, and the study delivers valuable insights and suggestions for imminent research studies.

This paper investigates the behaviors at different developmental stages in Escherichia coli (E. coli) lifecycle and developing a new biologically inspired optimization algorithm named bacterial colony optimization (BCO). BCO is based on a lifecycle model that simulates some typical behaviors of E. coli bacteria during their whole lifecycle, including chemotaxis, communication, elimination, reproduction, and migration. A newly created chemotaxis strategy combined with communication mechanism is developed to simplify the bacterial optimization, which is spread over the whole optimization process. However, the other behaviors such as elimination, reproduction, and migration are implemented only when the given conditions are satisfied. Two types of interactive communication schemas: individuals exchange schema and group exchange schema are designed to improve the optimization efficiency. In the simulation studies, a set of 12 benchmark functions belonging to three classes (unimodal, multimodal, and rotated problems) are performed, and the performances of the proposed algorithms are compared with five recent evolutionary algorithms to demonstrate the superiority of BCO.

Metaheuristic algorithms have been investigated intensively to address highly complex combinatorial optimisation problems. However, most metaheuristic algorithms have been designed manually by researchers of different expertise without a consistent framework to support effective algorithm design. This paper proposes a general search framework to formulate in a unified way a range of different metaheuristics. This framework defines generic algorithmic components, including selection heuristics and evolution operators. The unified general search framework aims to serve as the basis of analysing algorithmic components for automated algorithm design. With the established new general search framework, two reinforcement learning based methods, deep Q-network based and proximal policy optimisation based methods, have been developed to automatically design a new general population-based algorithm. The proposed reinforcement learning based methods are able to intelligently select and combine appropriate algorithmic components during different stages of the optimisation process. The effectiveness and generalization of the proposed reinforcement learning based methods are validated comprehensively across different benchmark instances of the capacitated vehicle routing problem with time windows. This study contributes to making a key step towards automated algorithm design with a general framework supporting fundamental analysis by effective machine learning.