Expert Systems最新文献

This work provides a review of data science methods that can be used to address a wide variety of business problems in the banking sector. The paper examines three modelling paradigms: the response, incremental response and the rate sensitivity to response approaches, emphasising the role they play to address these problems. These paradigms and the methods they involve are presented in combination with real cases to illustrate their potential in extracting valuable business insights from data. It is enhanced their usefulness to help business experts like risk managers, commercial managers, financial directors and chief executive officers to plan their strategies and guide decision making on the basis of the insights given by their outcomes. The scope of the work is twofold: it presents a unified view of the methods and how the fit the aforementioned paradigms while, at the same time, it examines some business cases for their application. Both issues will be of interest for technical and managerial teams involved in running data science projects in banking.

Classifying logo images is a challenging task as they contain elements such as text or shapes that can represent anything from known objects to abstract shapes. While the current state of the art for logo classification addresses the problem as a multi-class task focusing on a single characteristic, logos can have several simultaneous labels, such as different colours. This work proposes a method that allows visually similar logos to be classified and searched from a set of data according to their shape, colour, commercial sector, semantics, general characteristics, or a combination of features selected by the user. Unlike previous approaches, the proposal employs a series of multi-label deep neural networks specialized in specific attributes and combines the obtained features to perform the similarity search. To delve into the classification system, different existing logo topologies are compared and some of their problems are analysed, such as the incomplete labelling that trademark registration databases usually contain. The proposal is evaluated considering 76,000 logos (seven times more than previous approaches) from the European Union Trademarks dataset, which is organized hierarchically using the Vienna ontology. Overall, experimentation attains reliable quantitative and qualitative results, reducing the normalized average rank error of the state-of-the-art from 0.040 to 0.018 for the Trademark Image Retrieval task. Finally, given that the semantics of logos can often be subjective, graphic design students and professionals were surveyed. Results show that the proposed methodology provides better labelling than a human expert operator, improving the label ranking average precision from 0.53 to 0.68.

Dynamic latent scale GAN is an architecture-agnostic encoder-based generative model inversion method. This paper introduces a method to efficiently integrate perceptual VAE into dynamic latent scale GAN to improve the performance of dynamic latent scale GAN. When dynamic latent scale GAN is trained with a normal i.i.d. latent random variable and the latent encoder is integrated into the discriminator, a sum of a predicted latent random variable of real data and a scaled normal noise follows the normal i.i.d. random variable. Since this random variable is paired with real data and follows the latent random variable, it can be used for both VAE and GAN training. Furthermore, by considering the intermediate layer output of the discriminator as the feature encoder output, the VAE can be trained to minimise the perceptual reconstruction loss. The forward propagation & backpropagation for minimising this perceptual reconstruction loss can be integrated with those of GAN training. Therefore, the proposed method does not require additional computations compared to typical GAN or dynamic latent scale GAN. Integrating perceptual VAE to dynamic latent scale GAN improved the generative and inversion performance of the model.

Computationally efficient and time-memory saving compact algorithms become a keystone for solving global optimization problems, particularly the real world problems; which involve devices with limited memory or restricted use of battery power. Compact optimization algorithms represent a probabilistic view of the population to simulate the population behaviour as they broadly explores the decision space at the beginning of the optimization process and keep focus on to search the most promising solution, therefore narrows the search space, moreover few number of parameters need be stored in the memory thus require less space and time to compute efficiently. Role of population-based algorithms remain inevitable as compact algorithms make use of the efficient search ability of these population based algorithms for optimization but only through a probabilistic representation of the population space in order to optimize the real world problems. Artificial bee colony (ABC) algorithm has shown to be competitive over other population-based algorithms for solving optimization problems, however its solution search equation contributes to its insufficiency due to poor exploitation phase coupled with low convergence rate. This paper, presents a compact Artificial bee colony (cABC) algorithm with an improved solution search equation, which will be able to search an optimal solution to improve its exploitation capabilities, moreover in order to increase the global convergence of the proposed algorithm, an improved approach for population sampling is introduced through a compact $��{\text{Student}}^{\text{'}}�s�-�t�$ distribution which helps in maintaining a good balance between exploration and exploitation search abilities of the proposed compact algorithm with least memory requirements, thus became suitable for limited hardware access devices. The proposed algorithm is evaluated extensively on a standard set of benchmark functions proposed at IEEE CEC'13 for large-scale global optimization (LSGO) problems. Numerical results prove that the proposed compact algorithm outperforms other standard optimization algorithms.

Industrial image anomaly detection achieves automated detection and localization of defects or abnormal regions in images through image processing and deep learning techniques. Currently, utilizing the approach of reverse knowledge distillation has yielded favourable outcomes. However, it is still a challenge in terms of the feature extraction capability of the image and the robustness of the decoding of the student network. This study first addresses the issue that the teacher network has not been able to extract global information more effectively. To acquire more global information, a vision transformer network is introduced to enhance the model's global information extraction capability, obtaining better features to further assist the student network in decoding. Second, for anomalous samples, to address the low similarity between features extracted by the teacher network and features restored by the student network, Gaussian noise is introduced. This further increases the probability that the features decoded by the student model match normal sample features, enhancing the robustness of the student model. Extensive experiments were conducted on industrial image datasets AeBAD, MvtecAD, and BTAD. In the AeBAD dataset, under the PRO performance metric, the result is 89.83%, achieving state-of-the-art performance. Under the AUROC performance metric, it reaches 83.35%. Similarly, good results were achieved on the MvtecAD and BTAD datasets. The proposed method's effectiveness and performance advantages were validated across multiple industrial datasets, providing a valuable reference for the application of industrial image anomaly detection methods.

Deep learning techniques have attained substantial progress in various face-related tasks, such as face recognition, face inpainting, and facial expression recognition. To prevent infection or the spread of the virus, wearing of masks in public places has been mandated following the COVID-19 epidemic, which has led to face occlusion and posed significant challenges for face recognition systems. Most prominent masked face recognition solutions rely on mask segmentation tasks. Therefore, segmentation can be used to mitigate the negative impacts of wearing a mask and improve recognition accuracy. Mask region segmentation suffers from two main problems: there is no standard type of masks that people wear, they come in different colours and designs, and there is no publicly available masked face dataset with appropriate ground truth for the mask region. In order to address these issues, we propose an encoder–decoder framework that utilizes a boundary-aware attention network combined with a new hybrid loss to provide a map, patch, and pixel-level supervision. We also introduce a dataset called MFSD, with 11,601 images and 12,758 masked faces for masked face segmentation. Furthermore, we compare the performance of different cutting-edge deep learning semantic segmentation models on the presented dataset. Experimental results on the MSFD dataset reveal that the suggested approach outperforms state-of-the-art, algorithms with 97.623% accuracy, 93.814% IoU, and 96.817% F1-score rate. Our dataset of masked faces with mask region labels and source code will be available online.

Ensemble methods are among the most effective concept-drift adaptation techniques due to their high learning performance and flexibility. However, they are computationally expensive and pose a challenge in applications involving high-speed data streams. In this paper, we present a computationally efficient heterogeneous classifier ensemble entitled OMS-MAB which uses online model selection for concept-drift adaptation by posing it as a non-stationary multi-armed bandit (MAB) problem. We use a MAB to select a single adaptive learner within the ensemble for learning and prediction while systematically exploring promising alternatives. Each ensemble member is made drift resistant using explicit drift detection and is represented as an arm of the MAB. An exploration factor $��ϵ�$ controls the trade-off between predictive performance and computational resource requirements, eliminating the need to continuously train and evaluate all the ensemble members. A rigorous evaluation on 20 benchmark datasets and 9 algorithms indicates that the accuracy of OMS-MAB is statistically at par with state-of-the-art (SOTA) ensembles. Moreover, it offers a significant reduction in execution time and model size in comparison to several SOTA ensemble methods, making it a promising ensemble for resource constrained stream-mining problems.