Expert Systems with Applications最新文献

{"title":"MEFDPN: Mixture exponential family distribution posterior networks for evaluating data uncertainty","authors":"Xinlei Jin ,&nbsp;Quan Qian","doi":"10.1016/j.eswa.2024.125593","DOIUrl":"10.1016/j.eswa.2024.125593","url":null,"abstract":"<div><div>The computation of uncertainty are crucial for developing a reliable machine learning model. The natural posterior network (NatPN) provides uncertainty estimation for any single exponential family distribution, but real-world data is often complex. Therefore, we introduce a mixture exponential family posterior network (MEFDPN), which extends the prior distribution to a mixture of exponential family distributions, aiming to fit complex distributions that better represent real data. During network training, MEFDPN independently updates the posterior Bayesian estimates for each prior distribution, and the weights of these distributions are updated based on the forward propagation results. Furthermore, MEFDPN calculates two types of uncertainty (aleatoric and epistemic) and combines them using entropy weighting to obtain a comprehensive confidence measure for each data point. Theoretically, MEFDPN achieves higher prediction accuracy, and experimental results demonstrate its capability to compute high-quality data comprehensive confidence. Moreover, it shows encouraging accuracy in Out-of-Distribution(OOD) detection and validation experiments. Finally, we apply MEFDPN to a materials dataset, efficiently filtering out OOD data. This results in a significant enhancement of prediction accuracy for machine learning models. Specifically, removing only 5% of outlier data leads to a 2%–5% improvement in accuracy.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125593"},"PeriodicalIF":7.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142571830","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Phase spectrogram of EEG from S-transform Enhances epileptic seizure detection","authors":"Yingjian Liu ,&nbsp;Guoyang Liu ,&nbsp;Shibin Wu ,&nbsp;Chung Tin","doi":"10.1016/j.eswa.2024.125621","DOIUrl":"10.1016/j.eswa.2024.125621","url":null,"abstract":"<div><div>Automatic epilepsy seizure detection has high clinical value since it can alleviate the burden of manual monitoring. Nevertheless, it remains a technically challenging task to achieve a reliable system. In this study, we investigated the significance of the phase information in EEG signals in seizure detection using machine learning. We used the Stockwell transform (S-transform) to extract both phase and power spectra of the EEG signal in epilepsy patients. A dual-stream convolution neural network (CNN) model was adopted as the classifier, which takes both spectra as inputs. We demonstrated that the phase input allows the CNN model to capture the heightened phase synchronization among EEG channels in seizure and add network attention to both the low- and high-frequency features of the inputs in the CHB-MIT and Bonn databases. We improved the detection AUC-ROC by 6.68% on the CHB-MIT database when adding phase inputs to the power inputs. By incorporating a channel fusion post-processing to the outputs of this CNN model, it achieves a sensitivity and specificity of 79.59% and 92.23%, respectively, surpassing some of the state-of-the-art methods. Our results show that the phase inputs are useful features in seizure detection. This discovery has significant implications for improving the effectiveness of automatic seizure detection systems.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125621"},"PeriodicalIF":7.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142577871","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Recommendation feedback-based dynamic adaptive training for efficient social item recommendation","authors":"Yi Wang ,&nbsp;Chenqi Guo ,&nbsp;Yinglong Ma ,&nbsp;Qianli Feng","doi":"10.1016/j.eswa.2024.125605","DOIUrl":"10.1016/j.eswa.2024.125605","url":null,"abstract":"<div><div>For the application of social item recommendation, how to effectively dig out the implicit relationships between different items plays a crucial role in its performance. However, existing social item recommendation systems constructed their item graphs using a static method based on item features. Considering the fact that most items, such as live streams, can hardly be characterized with limited number of feature tags in reality, the static construction methods make it hard to accurately grasp the underlying item–item relationships. To address the problem, we propose an item graph generation method based on Recommendation Feedback and Dynamic Adaptive Training (RFDAT) to achieve an efficient social item recommendation. Specifically, a multi-task learning technique is leveraged to concurrently predict the item graph and user–item interaction graph, allowing the recommendation task itself to directly participate in the dynamic construction process of the item graph, which is adaptively constructed based on feedback from recommendation results iteratively during the training procedure. Compared with the static construction methods, this allows us to fully explore item–item relationships and item feature representations, therefore improving recommendation accuracy. Furthermore, a lightweight graph convolutional denoising and fusion method based on Laplacian smoothing filter is employed to achieve deep interaction and fusion among multi-graph features, and effectively mitigate the influence of noise in the process of feature learning. Finally, extensive experimental results on four public datasets show that compared with eight state-of-the-art methods, our proposed method achieves improvements of 4.97%, 2.90%, 2.03%, and 4.82% in the important evaluation metric NDCG@10 on Yelp, Ciao, LastFM, and Douban datasets, respectively. It also illustrates very competitive performance against these baselines in the recommendation accuracy for cold users and the recommendation rate for cold items.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125605"},"PeriodicalIF":7.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552577","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Weighted ensemble based on differentiated sampling rates for imbalanced classification and application to credit risk assessment","authors":"Xialin Wang,&nbsp;Yanying Li,&nbsp;Jiaoni Zhang","doi":"10.1016/j.eswa.2024.125595","DOIUrl":"10.1016/j.eswa.2024.125595","url":null,"abstract":"<div><div>Imbalanced data classification is an important research topic in machine learning. The class imbalance problem has a great impact on the classification performance of the algorithm. In this research direction, proposing an effective sampling strategy for imbalanced data is a challenging task. Although a lot of methods have been proposed to classify imbalanced data, the problem remains open. If a method reflects the data distribution and removes noisy samples, then good classification results will be obtained. Therefore, this paper proposes a weighted ensemble algorithm based on differentiated sampling rates (KSDE) and apply it to the field of credit risk assessment. KSDE removes noisy samples using the outlier detection technique. Then, multiple balanced training subsets are generated to train submodels using differentiated sampling rates. These training subsets sufficiently represent the distribution of data. Finally, the well-performing submodels are weighted and integrated to obtain the prediction result. We conducted comprehensive experiments to validate the performance of the proposed method. Comparing 12 state-of-the-art methods on 23 datasets. KSDE outperforms the recently proposed SPE (Self-paced Ensemble) by 12.46% in terms of TPR (True Positive Rate). In addition, KSDE achieves good results on 7 credit risk datasets. The experimental results show that the proposed method is competitive in solving the imbalanced data classification problem.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125595"},"PeriodicalIF":7.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552580","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Class activation map-based slicing-concatenation and contrastive learning: A novel strategy for record-level atrial fibrillation detection","authors":"Qiang Zhu,&nbsp;Lingwei Zhang,&nbsp;Fei Lu,&nbsp;Luping Fang,&nbsp;Qing Pan","doi":"10.1016/j.eswa.2024.125619","DOIUrl":"10.1016/j.eswa.2024.125619","url":null,"abstract":"<div><h3>Background</h3><div>Deep learning-based models for atrial fibrillation (AF) detection require extensive training data, which often necessitates labor-intensive professional annotation. While data augmentation techniques have been employed to mitigate the scarcity of annotated electrocardiogram (ECG) data, specific augmentation methods tailored for recording-level ECG annotations are lacking. This gap hampers the development of robust deep learning models for AF detection.</div></div><div><h3>Methods</h3><div>We propose a novel strategy, a combination of Class Activation Map-based Slicing-Concatenation (CAM-SC) data augmentation and contrastive learning, to address the current challenges. Initially, a baseline model incorporating a global average pooling layer is trained for classification and to generate class activation maps (CAMs), which highlight indicative ECG segments. After that, in each recording, indicative and non-indicative segments are sliced. These segments are subsequently concatenated randomly based on starting and ending Q points of QRS complexes, with indicative segments preserved to maintain label correctness. Finally, the augmented dataset undergoes contrastive learning to learn general representations, thereby enhancing AF detection performance.</div></div><div><h3>Results</h3><div>Using ResNet-101 as the baseline model, training with the augmented data yielded the highest F1-score of 0.861 on the Computing in Cardiology (CinC) Challenge 2017 dataset, a typical AF dataset with recording-level annotations. The metrics outperform most previous studies.</div></div><div><h3>Conclusions</h3><div>This study introduces an innovative data augmentation method specifically designed for recording-level ECG annotations, significantly enhancing AF detection using deep learning models. This approach has substantial implications for future AF detection research.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125619"},"PeriodicalIF":7.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552578","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Signal-devices management and data-driven evidential constraints based robust dispatch strategy of virtual power plant","authors":"Qianchao Wang ,&nbsp;Lei Pan ,&nbsp;Leena Heistrene ,&nbsp;Yoash Levron","doi":"10.1016/j.eswa.2024.125603","DOIUrl":"10.1016/j.eswa.2024.125603","url":null,"abstract":"<div><div>Ensuring the safety and reliability of energy systems is very important in power grid operation. However, inherent intricacies and uncertainties of modern-day power systems, such as the mismatch between signal frequency and equipment response speed and the stochasticity associated with renewable energy and load forecasts, create significant challenges for generation dispatch planning. This study proposes a robust optimization approach with constraints based on signal-devices management and data-driven evidential distribution constraints. The first stage of this approach is to decompose and recombine the net power demand according to the Hilbert-Huang transform and device capability. The signal-device management constraints are then established based on this. The second stage formulates an evidential constraint based on data-driven evidential distribution and chance constraints in a distributionally robust optimization framework that caters to the stochasticity associated with renewable energy and load forecasts. The proposed model is validated on a virtual power plant to assess the approach’s efficacy for different dispatching scenarios. Penalty-based sensitivity analysis provides further insights into the proposed method’s performance for varying levels of <span><math><msub><mrow><mi>CO</mi></mrow><mrow><mn>2</mn></mrow></msub></math></span> emissions. Simulation results demonstrate that system flexibility becomes increasingly crucial for maintaining system stability and security as the penetration of renewable energy grows. Compared with chance constraint, the proposed data-driven evidential constraint effectively enables the optimization framework to handle stochasticity after sacrificing 0.62% more economic loss and 0.7% more environmental loss. Excessively high penalty parameters for <span><math><msub><mrow><mi>CO</mi></mrow><mrow><mn>2</mn></mrow></msub></math></span> do not promote economic development, resulting in 21.08% and 52.51% more economic and environmental losses without obvious environmental protection.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125603"},"PeriodicalIF":7.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552582","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Statistical analyses of solution methods for the multiple-choice knapsack problem with setups: Implications for OR practitioners","authors":"Myung Soon Song ,&nbsp;Yun Lu ,&nbsp;Dominic Rando ,&nbsp;Francis J. Vasko","doi":"10.1016/j.eswa.2024.125622","DOIUrl":"10.1016/j.eswa.2024.125622","url":null,"abstract":"<div><div>An interesting extension of the classic Knapsack Problem (KP) is the Multiple-Choice Knapsack Problem with Setups (MCKS) which is focused on solving practical applications that involve both multiple periods and setups. Sophisticated solution methods for the MCKS that are presented in the operations research (OR) literature are not readily available for use by OR practitioners. Using MCKS test instances that appear in the literature, we demonstrate that the general-purpose integer programming software Gurobi sometimes used in an iterative manner can efficiently solve these MCKS instances using all default parameter values on a standard PC. It is shown both empirically and statistically that these Gurobi solutions are competitive with solution approaches from the literature. Hence, our approach using Gurobi is both easy for the OR practitioner to use and gives results competitive with the best specialized MCKS solution methods in the literature without the need to generate algorithm-specific code. Furthermore, this paper presents significant concerns regarding the solutions stated in the literature by the approximate solution method that reports the best results on 120 MCKS test instances. Specifically, 26% of this method’s solutions violate Gurobi upper bounds and an additional 33% of its solutions, on average, exceed the known guaranteed optimums by a value of 12,510.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125622"},"PeriodicalIF":7.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142538958","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"EdgeFont: Enhancing style and content representations in few-shot font generation with multi-scale edge self-supervision","authors":"Yefei Wang ,&nbsp;Kangyue Xiong ,&nbsp;Yiyang Yuan,&nbsp;Jinshan Zeng","doi":"10.1016/j.eswa.2024.125547","DOIUrl":"10.1016/j.eswa.2024.125547","url":null,"abstract":"<div><div>Font design is a meticulous and resource-intensive endeavor, especially for the intricate Chinese font. The few-shot font generation (FFG), i.e., employing a few reference characters to create diverse characters with the same style, has garnered significant interest recently. Existing models are predominantly based on the aggregation of style and content representations through learning either global or local style representations with neural networks. Yet, existing models commonly lack effective information guidance during the training or necessitate costly character information acquisition, limiting their performance and applicability in more intricate scenarios. To address this issue, this paper proposes a novel self-supervised few-shot font generation model called EdgeFont by introducing a Self-Supervised Multi-Scale edge Information based Self-Supervised (MSEE) module motivated by the observation that the multi-scale edge can simultaneously capture global and local style information. The introduced self-supervised module can not only provide nice supervision for the learning of style and content but also have a low cost of edge extraction. The experimental results on various datasets show that the proposed model outperforms existing models in terms of PSNR, SSIM, MSE, LPIPS, and FID. In the most challenging task for few-shot generation, Unseen fonts and Seen character, the proposed model achieves improvements of 0.95, 0.055, 0.063, 0.085, and 51.73 in PSNR, SSIM, MSE, and LPIPS, respectively, compared to FUNIT. Specifically, after integrating the MESS module into CG-GAN, the FID improves by 4.53, which fully demonstrates the strong scalability of MESS.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125547"},"PeriodicalIF":7.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142561425","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Self-supervised incomplete cross-modal hashing retrieval","authors":"Shouyong Peng ,&nbsp;Tao Yao ,&nbsp;Ying Li ,&nbsp;Gang Wang ,&nbsp;Lili Wang ,&nbsp;Zhiming Yan","doi":"10.1016/j.eswa.2024.125592","DOIUrl":"10.1016/j.eswa.2024.125592","url":null,"abstract":"<div><div>Benefiting from fast retrieval speed and low storage costs, cross-modal hashing retrieval has become a widely-used approximate nearest-neighbor technique in large-scale data retrieval. Most existing cross-modal hashing methods assume that the cross-modal data points are complete. However, cross-modal data completeness is difficult to be satisfied in the real world, because of the indefinite factors in data collecting. Moreover, due to the expensive cost of annotating all data points in large-scale applications, there is a growing interest in unsupervised hashing retrieval that can learn the correlations of cross-modal data without ground-truth. Therefore, how to perform unsupervised hashing retrieval on incomplete cross-modal data becomes a problem worthy of study. In this paper, we propose a Self-supervised Incomplete Cross-modal Hashing retrieval (SICH) method, which integrates data recovery and hashing encoding into a unified framework. Specifically, we first design a self-supervised semantic module to effectively mine the semantic information among pseudo-labels, and then a hash code dictionary is constructed to guide the hashing function learning with an asymmetric guidance mechanism. Besides, to fully take advantage of the incomplete data points in cross-modal learning, we introduce a data recovery network aiming at recovering missing data by minimizing conditional entropy and maximizing mutual information between different modalities. Extensive experiments on two benchmark datasets verify that our method consistently outperforms state-of-the-art cross-modal hashing methods.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125592"},"PeriodicalIF":7.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142662851","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

{"title":"Indifference subspace of deep features for lung nodule classification from CT images","authors":"Mohamad M.A. Ashames ,&nbsp;Ahmet Demir ,&nbsp;Mehmet Koc ,&nbsp;Mehmet Fidan ,&nbsp;Semih Ergin ,&nbsp;Mehmet Bilginer Gulmezoglu ,&nbsp;Atalay Barkana ,&nbsp;Omer Nezih Gerek","doi":"10.1016/j.eswa.2024.125571","DOIUrl":"10.1016/j.eswa.2024.125571","url":null,"abstract":"<div><div>Deep learning (DL) has made substantial contributions to automated diagnoses in biomedical imaging, with various architectures extensively used for critical classifications such as lung nodule detection from CT scans. Despite satisfactory results from basic DL implementations, understanding DL’s inner mechanisms and parameter evolution remains understudied. DL layers typically favor nodes with larger activation values, facilitating a softmax-type decision post-training. This aligns with various alternative final-layer replacements like support vector machines (SVM), random forest, naive Bayes, and k-nearest neighbor (k-NN). However, replacing the decision layer with a classifier that operates in the so-called indifference subspace, like the common vector approach (CVA), may disrupt the standard paradigm, as it requires commonality in feature node magnitudes rather than large feature values. This study investigates the feasibility of adapting standard DL architectures to generate feature nodes with common magnitudes conducive to CVA fine-tuning. Surprisingly, we find that DL networks, even without explicit design for this purpose, can achieve remarkable classification accuracies through CVA, effectively on par with state-of-the-art results. The intriguing high classification accuracy is examined through the relationship between “indifference subspace” and “node value,” scrutinized via an expansive suite of DL architectures, with and without ImageNet pre-training. Although the aim of the study is limited to the possibility of subspace alignment in the feature layers of convolutional neural networks (CNNs), the results demonstrate that CVA fine-tuning not only challenges the prevailing paradigms within DL classifications but also unveils a novel pathway for possibly enhancing classification performance in biomedical imaging, particularly for lung nodule detection.</div></div>","PeriodicalId":50461,"journal":{"name":"Expert Systems with Applications","volume":"262 ","pages":"Article 125571"},"PeriodicalIF":7.5,"publicationDate":"2024-10-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142552576","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}