No abstract

No abstract

Finger vein biometrics is one of the most promising ways to identify a person because it can provide uniqueness, protection against forgery, and bioassay. Due to the limitations of the imaging environments, however, the finger vein images that are taken can quickly become low-contrast, blurry, and very noisy. Therefore, more robust and relevant feature extraction from the finger vein images is still open research that should be addressed. In this paper, we propose a new technique of deep learning that is based on the attention mechanisms for human finger vein image identification and recognition and is called deep regional learning. Our proposed model relies on an unsupervised learning method that depends on optimized K-Means clustering for localized finger vein mask generation. The generated binary mask is used to build our attention learning model by making the deep learning structure focus on the region-of-interest (ROI) learning instead of learning the whole feature domain. This technique makes the Deep Regional Attention Model learn more significant features with less time and computational resources than the regular deep learning model. For experimental validation, we used different finger vein imaging datasets that have been extracted and generated using our model. Original finger vein images, localized finger vein images (with no background), localized grayscale finger vein images (grayscale images with no background and projected finger vein lines), and localized colored finger vein images (colored images with no background and projected finger vein lines) are used to train and test our model, which gets better results than traditional deep learning and other methods.

No abstract

The improvement of operational planning in the field of oil refinery management is becoming increasingly essential and valid. The influential primary factor, among others, is the ever-changing economic climate. The industry must continually assess the potential impacts of variations in the final product demand, price fluctuations, crude oil compositions and even seek out immediate opportunities within the market. The Master Production Schedule (MPS) is a planned process within the Production Management System that provides a mechanism for active collaboration between the marketing and manufacturing processes. However, the problem of MPS is a predictable non-deterministic, polynomial-time and NP-hard combination optimisation issue. The global search for the best solution to the MPS problem involves determination and funds that many industries are reluctant to provide. Hence, the alternative approach using meta-heuristics could provide desirable and workable answers in a realistic computing period. In this paper, a unique hybrid Multi-Objective Evolutionary Imperialist Competitive Algorithm (MOEICA) is proposed. The algorithm combines the advantages of an Imperialist Competitive Algorithm (ICA) and a Genetic Algorithm (GA) to optimise a Multi-Objective Master Production Schedule (MOMPS). The primary objective is to integrate the ICA with GA operators. The paper will also apply the optimised MOMPS to the Kalak Refinery System (KRS) operations using the proposed algorithm. The application involves determining the available capacity of each production line by estimating the parametric values for all failures. In addition, the gross requirements using demand forecasting and neural networks are defined. The proposed algorithm proved efficient in resolving the issues of the MOMPS model within KRS compared to the NSGAII and MOPSO algorithms. The results reflect that the novel MOEICA algorithm outperformed NSGAII and MOPSO in almost all measurements.