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.
{"title":"Data science methods for response, incremental response and rate sensitivity to response modelling in banking","authors":"Jorge M. Arevalillo","doi":"10.1111/exsy.13644","DOIUrl":"10.1111/exsy.13644","url":null,"abstract":"<p>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.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":null,"pages":null},"PeriodicalIF":3.0,"publicationDate":"2024-06-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.13644","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141198049","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Marisa Bernabeu, Antonio Javier Gallego, Antonio Pertusa
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.
{"title":"Multi-label logo recognition and retrieval based on weighted fusion of neural features","authors":"Marisa Bernabeu, Antonio Javier Gallego, Antonio Pertusa","doi":"10.1111/exsy.13627","DOIUrl":"10.1111/exsy.13627","url":null,"abstract":"<p>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.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":null,"pages":null},"PeriodicalIF":3.0,"publicationDate":"2024-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.13627","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141197888","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
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.
动态潜标 GAN 是一种基于编码器的架构无关生成模型反演方法。本文介绍了一种将感知 VAE 有效集成到动态潜标 GAN 中以提高动态潜标 GAN 性能的方法。当使用正态 i.i.d. 潜随机变量训练动态潜标 GAN 并将潜编码器集成到判别器中时,真实数据的预测潜随机变量和按比例正态噪声之和会跟随正态 i.i.d. 随机变量。由于该随机变量与真实数据配对并跟随潜随机变量,因此可用于 VAE 和 GAN 训练。此外,通过将判别器的中间层输出视为特征编码器输出,可以训练 VAE,使感知重建损失最小。用于最小化感知重构损失的前向传播和反向传播可以与 GAN 训练的前向传播和反向传播相结合。因此,与典型的 GAN 或动态潜标 GAN 相比,所提出的方法不需要额外的计算。将感知 VAE 整合到动态潜在尺度 GAN 中提高了模型的生成和反演性能。
{"title":"Efficient integration of perceptual variational autoencoder into dynamic latent scale generative adversarial network","authors":"Jeongik Cho, Adam Krzyzak","doi":"10.1111/exsy.13618","DOIUrl":"10.1111/exsy.13618","url":null,"abstract":"<p>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.</p>","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":null,"pages":null},"PeriodicalIF":3.0,"publicationDate":"2024-05-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://onlinelibrary.wiley.com/doi/epdf/10.1111/exsy.13618","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141197820","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the last few years, various topics, including sports, have seen social media platforms emerge as significant sources of information and viewpoints. Football fans use social media to express their opinions and sentiments about their favourite teams and players. Analysing these opinions can provide valuable information on the satisfaction of football fans with their teams. In this article, we present Soutcom, a scalable real‐time system that estimates the satisfaction of football fans with their teams. Our approach leverages the power of social media platforms to gather real‐time opinions and emotions of football fans and applies state‐of‐the‐art machine learning‐based sentiment analysis techniques to accurately predict the sentiment of Arabic posts. Soutcom is designed as a cloud‐based scalable system integrated with the X (formerly known as Twitter) API and a football data service to retrieve live posts and match data. The Arabic posts are analysed using our proposed bidirectional LSTM (biLSTM) model, which we trained on a custom dataset specifically tailored for the sports domain. Our evaluation shows that the proposed model outperforms other machine learning models such as Random Forest, XGBoost and Convolutional Neural Networks (CNNs) in terms of accuracy and F1‐score with values of 0.83 and 0.82, respectively. Furthermore, we analyse the inference time of our proposed model and suggest that there is a trade‐off between performance and efficiency when selecting a model for sentiment analysis on Arabic posts.
在过去几年中,包括体育在内的各种话题都出现了社交媒体平台,成为重要的信息和观点来源。足球迷们使用社交媒体表达他们对自己喜爱的球队和球员的意见和情感。对这些观点进行分析,可以为了解球迷对球队的满意度提供有价值的信息。在这篇文章中,我们介绍了 Soutcom,这是一个可扩展的实时系统,用于估算球迷对其球队的满意度。我们的方法利用社交媒体平台的力量来收集球迷的实时意见和情绪,并应用最先进的基于机器学习的情感分析技术来准确预测阿拉伯文帖子的情感。Soutcom 设计为基于云的可扩展系统,与 X(前身为 Twitter)API 和足球数据服务集成,以检索实时帖子和比赛数据。阿拉伯文帖子使用我们提出的双向 LSTM(biLSTM)模型进行分析,该模型是我们在专门为体育领域定制的数据集上训练出来的。我们的评估结果表明,所提出的模型在准确率和 F1 分数方面优于随机森林、XGBoost 和卷积神经网络 (CNN) 等其他机器学习模型,准确率和 F1 分数分别为 0.83 和 0.82。此外,我们还分析了所提模型的推理时间,并指出在选择阿拉伯文帖子情感分析模型时,需要在性能和效率之间进行权衡。
{"title":"Soutcom: Real‐time sentiment analysis of Arabic text for football fan satisfaction using a bidirectional LSTM","authors":"Sultan Alfarhood","doi":"10.1111/exsy.13641","DOIUrl":"https://doi.org/10.1111/exsy.13641","url":null,"abstract":"In the last few years, various topics, including sports, have seen social media platforms emerge as significant sources of information and viewpoints. Football fans use social media to express their opinions and sentiments about their favourite teams and players. Analysing these opinions can provide valuable information on the satisfaction of football fans with their teams. In this article, we present Soutcom, a scalable real‐time system that estimates the satisfaction of football fans with their teams. Our approach leverages the power of social media platforms to gather real‐time opinions and emotions of football fans and applies state‐of‐the‐art machine learning‐based sentiment analysis techniques to accurately predict the sentiment of Arabic posts. Soutcom is designed as a cloud‐based scalable system integrated with the X (formerly known as Twitter) API and a football data service to retrieve live posts and match data. The Arabic posts are analysed using our proposed bidirectional LSTM (biLSTM) model, which we trained on a custom dataset specifically tailored for the sports domain. Our evaluation shows that the proposed model outperforms other machine learning models such as Random Forest, XGBoost and Convolutional Neural Networks (CNNs) in terms of accuracy and <jats:italic>F</jats:italic>1‐score with values of 0.83 and 0.82, respectively. Furthermore, we analyse the inference time of our proposed model and suggest that there is a trade‐off between performance and efficiency when selecting a model for sentiment analysis on Arabic posts.","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141145941","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Currently, video surveillance is generally used to safeguard safety in public places like railway stations, traffic signals, malls, and so on. Video anomaly recognition and localization are the main components of the intelligent video surveillance method. Video anomaly recognition refers to the procedure of spatiotemporal localization of the abnormal design existing in the video. A main task in video surveillance is the classification of anomalies that occur in it like thefts, crimes, and so forth. Also, anomaly recognition in pedestrian walkways has enlarged major attention among the computer vision (CV) groups to improve pedestrian protection. The current developments in Deep Learning (DL) methods have great attention to dissimilar procedures like image classification, object recognition, and so forth. This study designs an Optimal Deep Learning for Effective Anomaly Detection in Pedestrian Walkways (ODL‐EADPW) model. The ODL‐EADPW technique employs a fine‐tuned DL model for the identification of pedestrians and anomalies in the walkways. In the ODL‐EADPW technique, the image pre‐processing is primarily involved in two stages median filtering (MF) based noise removal and adaptive histogram equalization (AHE)‐based contrast enhancement. For anomaly detection in pedestrian walkways, the ODL‐EADPW technique uses the YOLOv5s model with EfficientRep as a backbone network. To enhance the detection results of the ODL‐EADPW technique, a stochastic gradient descent (SGD) optimizer was employed to perfect the hyperparameters of the EfficientRep model. The performance evaluation of the ODL‐EADPW methodology is implemented on the UCSD Anomaly detection dataset. An extensive comparison study stated that the ODL‐EADPW technique gains effectual detection results over other DL models in terms of different measures.
{"title":"Leveraging YOLOv5s with optimization‐based effective anomaly detection in pedestrian walkways","authors":"Allabaksh Shaik, Shaik Mahaboob Basha","doi":"10.1111/exsy.13640","DOIUrl":"https://doi.org/10.1111/exsy.13640","url":null,"abstract":"Currently, video surveillance is generally used to safeguard safety in public places like railway stations, traffic signals, malls, and so on. Video anomaly recognition and localization are the main components of the intelligent video surveillance method. Video anomaly recognition refers to the procedure of spatiotemporal localization of the abnormal design existing in the video. A main task in video surveillance is the classification of anomalies that occur in it like thefts, crimes, and so forth. Also, anomaly recognition in pedestrian walkways has enlarged major attention among the computer vision (CV) groups to improve pedestrian protection. The current developments in Deep Learning (DL) methods have great attention to dissimilar procedures like image classification, object recognition, and so forth. This study designs an Optimal Deep Learning for Effective Anomaly Detection in Pedestrian Walkways (ODL‐EADPW) model. The ODL‐EADPW technique employs a fine‐tuned DL model for the identification of pedestrians and anomalies in the walkways. In the ODL‐EADPW technique, the image pre‐processing is primarily involved in two stages median filtering (MF) based noise removal and adaptive histogram equalization (AHE)‐based contrast enhancement. For anomaly detection in pedestrian walkways, the ODL‐EADPW technique uses the YOLOv5s model with EfficientRep as a backbone network. To enhance the detection results of the ODL‐EADPW technique, a stochastic gradient descent (SGD) optimizer was employed to perfect the hyperparameters of the EfficientRep model. The performance evaluation of the ODL‐EADPW methodology is implemented on the UCSD Anomaly detection dataset. An extensive comparison study stated that the ODL‐EADPW technique gains effectual detection results over other DL models in terms of different measures.","PeriodicalId":51053,"journal":{"name":"Expert Systems","volume":null,"pages":null},"PeriodicalIF":3.3,"publicationDate":"2024-05-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141104243","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":4,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Palvinder Singh Mann, Shailesh D. Panchal, Satvir Singh, Simran Kaur
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