Applied Intelligence最新文献

{"title":"A Nash equilibria decision tree for binary classification","authors":"Mihai-Alexandru Suciu,&nbsp;Rodica Ioana Lung","doi":"10.1007/s10489-024-06132-3","DOIUrl":"10.1007/s10489-024-06132-3","url":null,"abstract":"<div><p>Decision trees rank among the most popular and efficient classification methods. They are used to represent rules for recursively partitioning the data space into regions from which reliable predictions regarding classes can be made. These regions are usually delimited by axis-parallel or oblique hyperplanes. Axis-parallel hyperplanes are intuitively appealing and have been widely studied. However, there is still room for exploring different approaches. In this paper, a splitting rule that constructs axis-parallel hyperplanes by computing the Nash equilibrium of a game played at the node level is used to induct a Nash Equilibrium Decision Tree for binary classification. Numerical experiments are used to illustrate the behavior of the proposed method.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-20","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-024-06132-3.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142858653","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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}

{"title":"An active object detection model with multi-step prediction based on deep q-learning network and innovative training algorithm","authors":"Jianyu Wang,&nbsp;Feng Zhu,&nbsp;Qun Wang,&nbsp;Yunge Cui,&nbsp;Haibo Sun,&nbsp;Pengfei Zhao","doi":"10.1007/s10489-024-05993-y","DOIUrl":"10.1007/s10489-024-05993-y","url":null,"abstract":"<p>Active Object Detection (AOD) gathers additional information by deliberately adjusting the agent’s viewpoint, ensuring precise detection results in complex environments. Viewpoint planning(VP) is one of the focal points of attention in AOD. Until now, the predominant approach in implementing AOD algorithms has involved the use of deep q-learning networks(DQNs), with a single discrete action as the output. Nevertheless, these methods exhibit shortcomings in both implementation efficiency and success rate. To address these challenges, an AOD algorithm is proposed in this paper, allowing for multistep prediction and employing a novel training strategy. In more detail, the AOD network using a shared decision-making approach is first constructed, simultaneously outputting the action category and range. Moreover, a novel training method based on the Prioritized Experience Replay(PER) is introduced in this article, enhancing the operational success rate of the AOD algorithm. Finally, the reward function is optimized for the designed framework, thereby promoting the convergence of network training. Several comparable methods are tested on a public dataset(Active Vision Dataset), and the results clearly illustrate the superiority of the approach presented in this article.</p>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845126","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"SAPTSTA-AnoECG: a PatchTST-based ECG anomaly detection method with subtractive attention and data augmentation","authors":"Yifan Li,&nbsp;Mengjue Wang,&nbsp;Mingxiang Guan,&nbsp;Chen Lu,&nbsp;Zhiyong Li,&nbsp;Tieming Chen","doi":"10.1007/s10489-024-05881-5","DOIUrl":"10.1007/s10489-024-05881-5","url":null,"abstract":"<div><p>An electrocardiogram (ECG) is a crucial noninvasive medical diagnostic method that enables real-time monitoring of the electrical activity of the heart. ECGs hold a significant position in the rapid diagnosis and routine monitoring of cardiac diseases due to their user-friendly operation, prompt detection, broad range of diagnosable problems, and cost-effectiveness. However, thorough comprehension of ECG readings requires a high level of medical expertise due to the complex variations in ECG patterns, substantial interindividual differences, and numerous interfering factors. Consequently, current ECG machines and ECG Holters typically provide simplistic indications of ECG anomalies. Nonetheless, current ECG anomaly detection (EAD) algorithms lack precision; therefore, these medical devices cannot accurately report the specific types of diseases reflected in ECG results. In response to these challenges, this paper proposes enhancing the accuracy of electrocardiogram detection by improving algorithms. Therefore, we propose SAPTSTA-AnoECG, a PatchTST-based ECG anomaly detection method with subtractive attention and data augmentation. This method introduces a subtractive attention mechanism to make the Transformer architecture more suitable for time series data. We also use data augmentation to increase the robustness of the model. In addition, a patch-based approach is employed to reduce the algorithm’s computational complexity of the model. Furthermore, we introduce a new publicly available ECG dataset named HCE in this paper and conduct comparative experiments using this dataset along with the PTB-XL and CPSC 2018 datasets. The experimental results demonstrate the effectiveness of this method.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845132","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Precipitation nowcasting with generative diffusion models","authors":"Andrea Asperti,&nbsp;Fabio Merizzi,&nbsp;Alberto Paparella,&nbsp;Giorgio Pedrazzi,&nbsp;Matteo Angelinelli,&nbsp;Stefano Colamonaco","doi":"10.1007/s10489-024-06048-y","DOIUrl":"10.1007/s10489-024-06048-y","url":null,"abstract":"<div><p>In recent years traditional numerical methods for accurate weather prediction have been increasingly challenged by deep learning methods. Numerous historical datasets used for short and medium-range weather forecasts are typically organized into a regular spatial grid structure. This arrangement closely resembles images: each weather variable can be visualized as a map or, when considering the temporal axis, as a video. Several classes of generative models, comprising Generative Adversarial Networks, Variational Autoencoders, or the recent Denoising Diffusion Models have largely proved their applicability to the next-frame prediction problem, and is thus natural to test their performance on the weather prediction benchmarks. Diffusion models are particularly appealing in this context, due to the intrinsically probabilistic nature of weather forecasting: what we are really interested to model is the <i>probability distribution</i> of weather indicators, whose expected value is the most likely prediction. In our study, we focus on a specific subset of the ERA-5 dataset, which includes hourly data pertaining to Central Europe from the years 2016 to 2021. Within this context, we examine the efficacy of diffusion models in handling the task of precipitation nowcasting, with a lead time of 1 to 3 hours. Our work is conducted in comparison to the performance of well-established U-Net models, as documented in the existing literature. An additional comparative analysis has been done with the forecasting capabilities of the CERRA system, part of the Copernicus Climate Change Service. The novelty of our approach, Generative Ensemble Diffusion (GED), lies in its innovative use of a diffusion model to generate a diverse set of possible weather scenarios. These scenarios are then amalgamated into a single prediction in a post-processing phase. This approach mimics the usual weather forecasting technique consisting in running an ensemble of numerical simulations under slightly different initial conditions by exploiting instead the intrinsic stochasticity of the generative model. In comparison to recent deep learning models addressing the same problem, our approach results in approximately a 25% reduction in the mean squared error. Reverse diffusion is a core concept in our GED approach, is particularly relevant to weather forecasting. In the context of diffusion models, reverse diffusion refers to the process of iteratively refining a noisy initial prediction into a coherent and realistic forecast. By leveraging reverse diffusion, our model effectively simulates the complex temporal dynamics of weather systems, mirroring the inherent uncertainty and variability in weather patterns.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845128","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"HFedCWA: heterogeneous federated learning algorithm based on contribution-weighted aggregation","authors":"Jiawei Du,&nbsp;Huaijun Wang,&nbsp;Junhuai Li,&nbsp;Kan Wang,&nbsp;Rong Fei","doi":"10.1007/s10489-024-06123-4","DOIUrl":"10.1007/s10489-024-06123-4","url":null,"abstract":"<div><p>The aim of heterogeneous federated learning (HFL) is to address the issues of data heterogeneity, computational resource disparity, and model generalizability and security in federated learning (FL). To facilitate the collaborative training of data and enhance the predictive performance of models, a heterogeneous federated learning algorithm based on contribution-weighted aggregation (HFedCWA) is proposed in this paper. First, weights are assigned on the basis of the distribution differences and quantities of heterogeneous device data, and a contribution-based weighted aggregation method is introduced to dynamically adjust weights and balance data heterogeneity. Second, personalized strategies based on regularization are formulated for heterogeneous devices with different weights, enabling each device to participate in the overall task in an optimal manner. Differential privacy methods are concurrently utilized in FL training to further enhance the security of the system. Finally, experiments are conducted under various data heterogeneity scenarios using the MNIST and CIFAR10 datasets, and the results demonstrate that the HFedCWA can effectively improve the model’s generalizability ability and adaptability to heterogeneous data, thereby enhancing the overall efficiency and performance of the HFL system.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845125","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Text-dominant multimodal perception network for sentiment analysis based on cross-modal semantic enhancements","authors":"Zuhe Li,&nbsp;Panbo Liu,&nbsp;Yushan Pan,&nbsp;Jun Yu,&nbsp;Weihua Liu,&nbsp;Haoran Chen,&nbsp;Yiming Luo,&nbsp;Hao Wang","doi":"10.1007/s10489-024-06150-1","DOIUrl":"10.1007/s10489-024-06150-1","url":null,"abstract":"<p>Multimodal sentiment analysis (MSA) aims to discern the emotional information expressed by users in the multimodal data they upload on various social media platforms. In most previous studies, these modalities (audio A, visual V, and text T) were typically treated equally, overlooking the lower representation quality inherent in audio and visual modalities. This oversight often results in inaccurate interaction information when audio or visual modalities are used as the primary input, thereby negatively impacting the model’s sentiment predictions. In this paper, we propose a text-dominant multimodal perception network with cross-modal transformer-based semantic enhancement. The network comprises primarily a text-dominant multimodal perception (TDMP) module and a cross-modal transformer-based semantic enhancement (TSE) module. TDMP leverages the text modality to dominate intermodal interactions, extracting high correlation and differentiation features from each modality, thereby obtaining more accurate representations for each modality. The TSE module uses a transformer architecture to convert the audio and visual modality features into text features. By applying KL divergence constraints, it ensures that the translated modality representations capture as much emotional information as possible while maintaining high similarity to the original text modality representations. This enhances the original text modality semantics while mitigating the negative impact of the input. Extensive experiments on the CMU-MOSI and CMU-MOSEI datasets demonstrate the effectiveness of our proposed model.</p><p>The overview of Text-dominant Multimodal Perception Network</p>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142845129","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Two novel deep multi-view support vector machines for multiclass classification","authors":"Yanfeng Li,&nbsp;Xijiong Xie","doi":"10.1007/s10489-024-06126-1","DOIUrl":"10.1007/s10489-024-06126-1","url":null,"abstract":"<div><p>Multi-view classification methods have better generalization performance compared to the single-view classification methods due to the consistency information from multiple views. In recent years, the combination of support vector machine (SVM) and multi-view learning has been widely studied. To improve the robustness of multi-view classification methods, emphasis has shifted to the integration of multi-view classification approaches with fully-connected and convolutional neural networks. A classical deep two-view classification method named deep SVM-2K is a combination of support vector machine with two stage kernel canonical correlation analysis (SVM-2K) and deep learning. However, limitations of deep SVM-2K are that it can not cope with multi-view classification and multiclass classification problems. To address these issues, we propose two novel deep multi-view models named deep multi-view support vector machine (DMVSVM) for multiclass classification. DMVSVM uses the learned features by auto-encoder (AE) or deep neural network (DNN) to train the SVM classifier for each view. The two models then impose some constraints to make the output of the multi-view SVM classifiers as consistent as possible, which used to exploring intrinsic relations. Experiments performed on different real-word datasets show the effectiveness of our proposed approaches.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844896","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"WRGAT-PTBERT: weighted relational graph attention network over post-trained BERT for aspect based sentiment analysis","authors":"Sharad Verma,&nbsp;Ashish Kumar,&nbsp;Aditi Sharan","doi":"10.1007/s10489-024-06011-x","DOIUrl":"10.1007/s10489-024-06011-x","url":null,"abstract":"<div><p>Aspect-based sentiment analysis (ABSA) focused on forecasting the sentiment orientation of a given aspect target within the input. Existing methods employ neural networks and attention mechanisms to encode input and discern aspect-context relationships. Bidirectional Encoder Representation from Transformer(BERT) has become the standard contextual encoding method in the textual domain. Researchers have ventured into utilizing graph attention networks(GAT) to incorporate syntactic information into the task, yielding cutting-edge results. However, current approaches overlook the potential advantages of considering word dependency relations. This work proposes a hybrid model combining contextual information obtained from a post-trained BERT with syntactic information from a relational GAT (RGAT) for the ABSA task. Our approach leverages dependency relation information effectively to improve ABSA performance in terms of accuracy and F1-score, as demonstrated through experiments on SemEval-14 Restaurant and Laptop, MAMS, and ACL-14 Twitter datasets.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844905","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"NQF-RNN: probabilistic forecasting via neural quantile function-based recurrent neural networks","authors":"Jungyoon Song,&nbsp;Woojin Chang,&nbsp;Jae Wook Song","doi":"10.1007/s10489-024-06077-7","DOIUrl":"10.1007/s10489-024-06077-7","url":null,"abstract":"<div><p>Probabilistic forecasting offers insights beyond point estimates, supporting more informed decision-making. This paper introduces the Neural Quantile Function with Recurrent Neural Networks (NQF-RNN), a model for multistep-ahead probabilistic time series forecasting. NQF-RNN combines neural quantile functions with recurrent neural networks, enabling applicability across diverse time series datasets. The model uses a monotonically increasing neural quantile function and is trained with a continuous ranked probability score (CRPS)-based loss function. NQF-RNN’s performance is evaluated on synthetic datasets generated from multiple distributions and six real-world time series datasets with both periodicity and irregularities. NQF-RNN demonstrates competitive performance on synthetic data and outperforms benchmarks on real-world data, achieving lower average forecast errors across most metrics. Notably, NQF-RNN surpasses benchmarks in CRPS, a key probabilistic metric, and tail-weighted CRPS, which assesses tail event forecasting with a narrow prediction interval. The model outperforms other deep learning models by 5% to 41% in CRPS, with improvements of 5% to 53% in left tail-weighted CRPS and 6% to 34% in right tail-weighted CRPS. Against its baseline model, DeepAR, NQF-RNN achieves a 41% improvement in CRPS, indicating its effectiveness in generating reliable prediction intervals. These results highlight NQF-RNN’s robustness in managing complex and irregular patterns in real-world forecasting scenarios.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844899","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"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":"Multi-constraint distributed terminal distribution path planning for fresh agricultural products","authors":"Huan Liu,&nbsp;Jizhe Zhang,&nbsp;Yongqiang Dai,&nbsp;Lijing Qin,&nbsp;Yongkun Zhi","doi":"10.1007/s10489-024-06076-8","DOIUrl":"10.1007/s10489-024-06076-8","url":null,"abstract":"<div><p>A common combinatorial optimization issue in actual engineering is the vehicle routing problem (VRP). Examples of these problems include logistics distribution, solid waste recycling planning, and underwater routing planning. The optimization algorithms are important for the solution quality of the proposed VRP. As the scale of the vehicle routing problem increases, the problem becomes more difficult. It is hard for the traditional algorithm to obtain the optimal solution to the problem in an acceptable computing time. In this paper, an adaptive large neighborhood water wave optimization (ALNSWWO) algorithm is designed to solve multi-depot capacitated vehicle routing problems with time windows (MDCVRPTW). Aimed at addressing the main problems of the original algorithm, an improvement strategy is designed. In the breaking operation, variable neighborhood search (VNS) and large neighborhood search (LNS) local search strategies are added. In the refinement operation, the learning operator based on the genetic algorithm and the adaptive large neighborhood search (ALNS) search mechanism is added. The above mechanism solves the problems that the original algorithm is prone to falling into local optima. The experimental results demonstrate that the distribution path scheme of fresh agricultural products (FAP) can be optimized through the ALNSWWO. The proposed ALNSWWO can reduce the distribution distance, time, cost, carbon emissions, and improve customer satisfaction.\u0000</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142844898","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}