Applied Intelligence最新文献

{"title":"A hierarchical set-enumeration tree enabling high occupancy item set mining and the use of an adaptive occupancy threshold","authors":"Thanh-Nam Tran,&nbsp;Vinh Truong Hoang,&nbsp;Thanh-Cong Truong,&nbsp;Miroslav Voznak","doi":"10.1007/s10489-024-06166-7","DOIUrl":"10.1007/s10489-024-06166-7","url":null,"abstract":"<div><p>The highly efficient HEP algorithm is a useful tool for mining High Occupancy (HO) item sets. Occupancy is an important measure that describes the interestingness of frequent item sets. The current study examines the efficiency problems in mining HO item sets and proposes an improved HEP algorithm, named advanced HEP (A–HEP), based on set theory rules which eliminate a large number of redundant iterations. The study also proposes a novel adaptive-and-modified HEP (NAM–HEP) algorithm that uses HO Set-Enumeration (SE) trees to store HO item sets. The study proposes definitions for adaptive thresholds such as support threshold and occupancy threshold based on the attributes of the transaction database for efficient pruning of the HO-SE tree. Two pseudo-code blocks are presented in addition to a detailed description of the A–HEP and NAM–HEP algorithms and their advantages. Using the A–HEP and NAM–HEP algorithms, HO item sets are investigated from the practical transaction databases named mushroom and retail. The results indicate that the proposed A–HEP and NAM–HEP algorithms enhance mining performance and runtime benchmarks.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142870408","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":"An effective dynamical evaluation and optimization mechanism for accurate motion primitives learning","authors":"Chunfang Liu,&nbsp;Changfeng Li,&nbsp;Xiaoli Li,&nbsp;Guoyu Zuo,&nbsp;Pan Yu","doi":"10.1007/s10489-024-06147-w","DOIUrl":"10.1007/s10489-024-06147-w","url":null,"abstract":"<div><p>Trajectory planning is an important stage in robot operation. Many imitation learning methods have been researched for learning operation skills from demonstrated trajectories. However, it is still a challenge to use the learned skill models to generate motion trajectories suitable for various changing conditions. In this paper, a closed-loop dynamical evaluation and optimization mechanism is proposed for imitation learning model to generate the optimal trajectories that can adapt to multiple conditions. This mechanism works by integrating the following parts: (1) imitation learning based on an improved dynamic motion primitive; (2) constructing the trajectory similarity evaluation function; (3) presenting an enhanced whale optimization algorithm(EWOA) by introducing the piecewise decay rate and inertia weight for avoiding getting stuck in local optima. The EWOA iteratively optimizes the key parameter of the skill learning model based on the cost function of the trajectory similarity evaluation for generating the trajectory with the highest similarity to the teaching trajectory. The effectiveness of the EWOA is validated using 10 functions by comparing with the other two methods. And the feasibility of the dynamical optimization mechanism is proved under different motion primitives and various generation conditions.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142870462","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":"Efficient strategies for spatial data clustering using topological relations","authors":"Trang T. D. Nguyen,&nbsp;Loan T. T. Nguyen,&nbsp;Quang-Thinh Bui,&nbsp;Le Nhat Duy,&nbsp;Witold Pedrycz,&nbsp;Bay Vo","doi":"10.1007/s10489-024-05927-8","DOIUrl":"10.1007/s10489-024-05927-8","url":null,"abstract":"<div><p>Using topology in data analysis is a promising new field, and recently, it has attracted numerous researchers and played a vital role in both research and application. This study explores the burgeoning field of topology-based data analysis, mainly focusing on its application in clustering algorithms within data mining. Our research addresses the critical challenges of reducing execution time and enhancing clustering quality, which includes decreasing the dependency on input parameters - a notable limitation in current methods. We propose five innovative strategies to optimize clustering algorithms that utilize topological relationships by combining solutions of expanding points fewer times, merging clusters, and using a jump to increase the radius value according to the nearest neighbor distance array index. These strategies aim to refine clustering performance by improving algorithmic efficiency and the quality of clustering outcomes. This approach elevates the standard of cluster analysis and contributes significantly to the evolving landscape of data mining and analysis.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142870463","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":"Exploring emotional stability: from conventional approaches to machine learning insights","authors":"Marcos Romero Madroñal,&nbsp;Eduar S. Ramírez,&nbsp;Luis Gonzaga Baca Ruiz,&nbsp;María José Serrano-Fernández,&nbsp;Elena Pérez-Moreiras,&nbsp;María del Carmen Pegalajar Jiménez","doi":"10.1007/s10489-024-06130-5","DOIUrl":"10.1007/s10489-024-06130-5","url":null,"abstract":"<div><p>In contemporary psychological assessments, diverse traits are often evaluated using extensive questionnaires. This study focuses on the trait of emotional stability, and acknowledges the inherent limitations and issues associated with prolonged survey instruments. To address these challenges, we propose a Machine Learning (ML) approach to directly predict emotional stability, offering a more efficient alternative to bulky questionnaires. The study carefully selected variables with previously established relationships to emotional stability, utilizing a dataset of 2203 individuals who responded to a series of psychometric questionnaires. The proposed method yields promising results, achieving an R2 score of approximately 0.71 on the test set, indicating robust predictive performance. These models highlighted the significance of variables such as emotional stress and self-esteem, emphasizing their substantial role in predicting emotional stability. It is noteworthy that even with a reduced set of variables, the models remained statistically equivalent. The results provide valuable insights for predicting stability with smaller sets of variables and contribute knowledge that complements the understanding of emotional stability.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142875228","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":"An asynchronous federated learning-assisted data sharing method for medical blockchain","authors":"Chenquan Gan,&nbsp;Xinghai Xiao,&nbsp;Yiye Zhang,&nbsp;Qingyi Zhu,&nbsp;Jichao Bi,&nbsp;Deepak Kumar Jain,&nbsp;Akanksha Saini","doi":"10.1007/s10489-024-06172-9","DOIUrl":"10.1007/s10489-024-06172-9","url":null,"abstract":"<div><p>Currently, medical blockchain data sharing methods that rely on federated learning face challenges, including node disconnection, vulnerability to poisoning attacks, and insufficient consideration of conflicts of interest among participants. To address these issues, we propose a novel method for data sharing in medical blockchain systems based on asynchronous federated learning. First, we develop an aggregation algorithm designed specifically for asynchronous federated learning to tackle the problem of node disconnection. Next, we introduce a Proof of Reputation (PoR) consensus algorithm and establish a consensus committee to mitigate the risk of poisoning attacks. Furthermore, we integrate a tripartite evolutionary game model to examine conflicts of interest among publishing nodes, committee nodes, and participating nodes. This framework enables all parties involved to make strategic decisions that promote sustainable data-sharing practices. Finally, we conduct a security analysis to validate the theoretical effectiveness of the proposed method. Experimental evaluations using real medical datasets demonstrate that our method outperforms existing approaches.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142870461","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":"Entity alignment in noisy knowledge graph","authors":"Yuhong Zhang,&nbsp;Xiaolong Zhu,&nbsp;Xuegang Hu","doi":"10.1007/s10489-024-06131-4","DOIUrl":"10.1007/s10489-024-06131-4","url":null,"abstract":"<div><p>Entity alignment is an important task in Knowledge Graph(KG), which aims to find identical entities in two different KGs. Existing methods include two steps, graph representation and alignment inference. The representation is learned based on the semantics and structure of KG. In applications, however, incorrect triples (which are also called structure noise) inevitably exist in KGs due to low-quality corpora and low-performance construction algorithms. The structure noise in KGs affects the representation of KGs and the alignment inference. To this end, we propose an entity alignment method in noisy knowledge graphs for the first time. Firstly, a noise-aware module is designed to recognize the noisy triples and exclude them from KG representation. Secondly, we design a more strict semi-supervised algorithm that combines local similarity and global alignment cost together to obtain high-quality pseudo-alignments in noisy environments. The experimental results demonstrate the effectiveness of our method in noisy KGs and the good compatibility with other baselines.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142875207","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":"Visual semantic navigation with real robots","authors":"Carlos Gutiérrez-Álvarez,&nbsp;Pablo Ríos-Navarro,&nbsp;Rafael Flor-Rodríguez-Rabadán,&nbsp;Francisco Javier Acevedo-Rodríguez,&nbsp;Roberto Javier López-Sastre","doi":"10.1007/s10489-024-06115-4","DOIUrl":"10.1007/s10489-024-06115-4","url":null,"abstract":"<div><p>Visual Semantic Navigation (VSN) is the ability of a robot to learn visual semantic information for navigating in unseen environments. These VSN models are typically tested in those virtual environments where they are trained, mainly using reinforcement learning based approaches. Therefore, we do not yet have an in-depth analysis of how these models would behave in the real world. In this work, we propose a new solution to integrate VSN models into real robots, so that we have true embodied agents. We also release a novel ROS-based framework for VSN, ROS4VSN, so that any VSN-model can be easily deployed in any ROS-compatible robot and tested in a real setting. Our experiments with two different robots, where we have embedded two state-of-the-art VSN agents, confirm that there is a noticeable performance difference of these VSN solutions when tested in real-world and simulation environments. We hope that this research will endeavor to provide a foundation for addressing this consequential issue, with the ultimate aim of advancing the performance and efficiency of embodied agents within authentic real-world scenarios. Code to reproduce all our experiments can be found at https://github.com/gramuah/ros4vsn.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-23","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142870457","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":"Technical analysis-based unsupervised intraday trading djia index stocks: is it profitable in long term?","authors":"Mussadiq Abdul Rahim,&nbsp;Muhammad Mushafiq,&nbsp;Sultan Daud Khan,&nbsp;Rafi Ullah,&nbsp;Salabat Khan,&nbsp;Muhammad Ishaque","doi":"10.1007/s10489-024-05903-2","DOIUrl":"10.1007/s10489-024-05903-2","url":null,"abstract":"<div><p>The paradigm shift from conventional stock market trading rings to computer-driven algorithmic trading has given rise to a new era characterized by specialized trading systems and indicators meticulously engineered to decode price charts and enhance the prospects of profitable trading. Nevertheless, despite these notable advancements, the majority of traders continue to grapple with losses rather than realizing gains, echoing the historical pursuit of the elusive philosopher’s stone by alchemists of yore. In response to this challenge, our research delves into the realm of artificial neural networks (ANNs) to cultivate more sophisticated trading methodologies. Our empirical investigations suggest that trading strategies relying on price chart analysis generally achieve a moderate level of accuracy. However, it is imperative to acknowledge that the intricate patterns that materialize over time, coupled with return metrics, persistently elude precise prediction within the framework of unsupervised automated trading. These findings underscore the critical importance of embracing a progressive approach to trading that synergizes human expertise with cutting-edge technological capabilities.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142859554","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":"A dual transfer learning method based on 3D-CNN and vision transformer for emotion recognition","authors":"Zhifen Guo,&nbsp;Jiao Wang,&nbsp;Bin Zhang,&nbsp;Yating Ku,&nbsp;Fengbin Ma","doi":"10.1007/s10489-024-05976-z","DOIUrl":"10.1007/s10489-024-05976-z","url":null,"abstract":"<div><p>In the domain of medical science, emotion recognition based on electroencephalogram (EEG) has been widely used in emotion computing. Despite the prevalence of deep learning in EEG signals analysis, standard convolutional and recurrent neural networks fall short in effectively processing EEG data due to their inherent limitations in capturing global dependencies and addressing the non-linear and unstable characteristics of EEG signals. We propose a dual transfer learning method based on 3D Convolutional Neural Networks (3D-CNN) with a Vision Transformer (ViT) to enhance emotion recognition. This paper aims to utilize 3D-CNN effectively to capture the spatial characteristics of EEG signals and reduce data covariance, extracting shallow features. Additionally, ViT is incorporated to improve the model’s ability to capture long-range dependencies, facilitating deep feature extraction. The methodology involves a two-stage process: initially, the front end of a pre-trained 3D-CNN is employed as a shallow feature extractor to mitigate EEG data covariance and transformer biases, focusing on low-level feature detection. The subsequent stage utilizes ViT as a deep feature extractor, adept at modeling the global aspects of EEG signals and employing attention mechanisms for precise classification. We also present an innovative algorithm for data mapping in transfer learning, ensuring consistent feature representation across both spatio-temporal dimensions. This approach significantly improves global feature processing and long-range dependency detection, with the integration of color channels augmenting the model’s sensitivity to signal variations. In a 10-fold cross-validation experiment on the DEAP, experimental results demonstrate that the proposed method achieves classification accuracies of 92.44<span>(%)</span> and 92.85<span>(%)</span> for the valence and arousal dimensions, and the accuracies of four-class classification across valence and arousal are HVHA: 88.01<span>(%)</span>, HVLA: 88.27<span>(%)</span>, LVHA: 90.89<span>(%)</span>, LVLA: 78.84<span>(%)</span>. Similarly, it achieves an accuracy of 98.69<span>(%)</span> on the SEED. Overall, this methodology not only holds substantial potential in advancing emotion recognition tasks but also contributes to the broader field of affective computing.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142859553","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":"GFENet: group-wise feature-enhanced network for steering angle prediction by fusing events and images","authors":"Duo-Wen Chen,&nbsp;Chi Guo,&nbsp;Jian-Lang Hu","doi":"10.1007/s10489-024-06019-3","DOIUrl":"10.1007/s10489-024-06019-3","url":null,"abstract":"<div><p>Existing end-to-end networks for steering angle prediction usually use images generated by standard cameras as input. However, standard cameras are susceptible to poor lighting conditions and motion blur, which is not conducive to training an accurate and robust end-to-end network. In contrast, biological vision-inspired event cameras overcome the aforementioned shortcomings with their unique working principle and offer significant advantages such as high temporal resolution, high dynamic range and low power consumption. Nevertheless, event cameras generate a lot of noise and are unable to provide texture information on static region. Therefore, these two types of cameras are complementary to each other to some extent. To explore the benefits of fusing information from these two types of cameras in autonomous driving tasks, we propose GFENet, an attention-based two-stream encoder-decoder architecture for steering angle prediction by combining events and images. Firstly, asynchronous and sparse events are converted into synchronous and dense event frames. Then, event frames and corresponding image frames are fed into two symmetric encoders to extract features. Next, We introduce a Group-Wise Feature-Enhanced (GEF) module that can refine features and suppress noise to guide the fusion of two modalities features at different levels. Finally, The final fused features are passed through a simple decoder to predict the steering angle. Experiments results on the DDD20 and EventScape datasets shows that our GFEFNet outperforms the state-of-the-art image-event fusion method.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 2","pages":""},"PeriodicalIF":3.4,"publicationDate":"2024-12-21","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"142859555","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}