Applied Intelligence最新文献

{"title":"Enhancing the imitation game: a trust-based model for distinguishing human and machine participants","authors":"Tanisha Gupta,&nbsp;Akarsh Tripathi,&nbsp;Ashutosh Kumar Dubey,&nbsp;Ravita Chahar","doi":"10.1007/s10489-024-06133-2","DOIUrl":"10.1007/s10489-024-06133-2","url":null,"abstract":"<div><p>Since 1950, the imitation game has captured the interest of researchers investigating human‒machine differences. Designed to evaluate machine cognition through a game-based framework, its complexity demands refinement. The imitation game utilizes this game-based setup, but its inherent intricacy calls for further enhancements. The fundamental question of whether machines are capable of genuine thought has been a key issue in artificial intelligence (AI) studies. Recent developments challenge the ease of differentiation, as AI enables machines to display human-like characteristics. This paper seeks to address the shortcomings of the original Turing test and criticisms of the imitation game by introducing an integrated model. Although machines currently operate based on our instructions, they can learn from errors and produce novel responses through generative AI techniques, even though they do not experience emotions. In this study, a new trust-based model was introduced to improve the imitation game. This model integrated various factors to assess the reliability of participants’ responses, including grammatical accuracy, response time, thinking duration, response speed, creativity, and the use of human-like expressions. The goal was to calculate a trust factor that determines the likelihood of a participant being a human or machine. To evaluate the model’s performance, a comprehensive dataset was developed using a chat generative pretrained transformer (ChatGPT-3.5). Two other large language models (LLMs), the large language model meta AI (Llama 3) and the Claude LLM, were also taken into account. To simulate the experiment with human participants, human-generated text was also included. The simulation results revealed that GPT-3.5 Turbo, Llama 3, and Claude LLM performed differently in terms of grammatical accuracy, human-like phrasing, creativity, and trust factors. GPT-3.5 and Llama 3 had lower error rates but struggled with human-like phrases. Claude resulted in more grammatical errors but better creativity. The human participants consistently showed greater trust and human-like phrase usage. Probability assessments categorized machines with 71–78% accuracy, whereas humans were identified with only a 29–36% chance of being a machine.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143109971","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":"You are what your feeds make you: A study of user aggressive behavior on Twitter","authors":"Swapnil Mane,&nbsp;Suman Kundu,&nbsp;Rajesh Sharma","doi":"10.1007/s10489-025-06286-8","DOIUrl":"10.1007/s10489-025-06286-8","url":null,"abstract":"<div><p>The widespread use of aggressive language on Twitter raises concerns about potential negative influences on user behavior. Despite previous research exploring aggression and negativity on the platform, the relationship between consuming aggressive content and users’ aggressive behavior remains underexplored. This study investigates whether exposure to aggressive content on Twitter can lead users to behave more aggressively. Our methodological approach contains four stages: data collection and annotation, aggressive post detection, user aggression intensity metric, and user profiling. We proposed the English Twitter Aggression dataset (TAG-EN) with substantial inter-annotator agreement (Krippendorff’s alpha=0.78). Subsequently, we benchmark the aggression detection performance on TAG-EN dataset (macro F1=0.92) by fine-tuning a pre-trained RoBERTa-large. We quantified user aggression with a proposed “user aggression intensity” metric based on their overall aggressive activity. Our analysis of 14M posts from 63K users revealed that aggressive Twitter feeds can influence users to behave more aggressively online. Furthermore, the study found that users tend to support and encourage aggressive content on social media, which can contribute to the proliferation of aggressive behavior.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143109889","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":"Improving vehicle detection accuracy in complex traffic scenes through context attention and multi-scale feature fusion module","authors":"Wenbo Liu,&nbsp;Binglin Zhao,&nbsp;Yuxin Zhu,&nbsp;Tao Deng,&nbsp;Fei Yan","doi":"10.1007/s10489-024-06146-x","DOIUrl":"10.1007/s10489-024-06146-x","url":null,"abstract":"<div><p>Vehicle detection is a fundamental task for automated driving systems. However, achieving robust performance in complex traffic scenarios remains a formidable challenge. In this paper, we propose a novel vehicle detection model that leverages contextual attention mechanisms and multi-scale feature fusion to effectively tackle the inherent challenges presented by complex scenarios, such as occlusion, truncation, and small-scale vehicle instances. The proposed model introduces a contextual attention module tailored to address vehicle occlusion, augmenting the model’s reasoning ability and overall performance through the integration of global contextual information. Additionally, we introduce a Multi-Scale Feature Fusion Module to mitigate the impact of drastic changes in vehicle scales observed in dynamic traffic scenarios. Through the deployment of a dedicated multi-scale feature fusion module, our model adeptly adapts to significant size variations of vehicles in traffic scene images, thereby enhancing its capability to handle vehicles of varying sizes. Our contributions are validated through comprehensive qualitative and quantitative experiments conducted on both the KITTI dataset and the Cityscapes dataset. The experimental results demonstrate the exceptional robustness and accuracy of our proposed model. These findings provide conclusive evidence of the superior performance and effectiveness of our model in real-world applications.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-01-29","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143110023","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":"PTLO: A model-agnostic training strategy based on progressive training and label optimization for fine-grained image classification","authors":"Yiming Chen,&nbsp;Xiuting Tao,&nbsp;Bo Chen,&nbsp;Jian Guo,&nbsp;Shi Li","doi":"10.1007/s10489-025-06276-w","DOIUrl":"10.1007/s10489-025-06276-w","url":null,"abstract":"<div><p>Compared to conventional image recognition, fine-grained classification exhibits increased vulnerability to labeling noise due to the presence of closely related categories, resulting in degraded performance on complex and non-representative samples. While existing approaches mitigate these issues through data cleaning, loss modification, and semi-supervised learning techniques, they often overlook the intrinsic attributes within training samples. Instead of designing any network architectures, this study introduces a model-agnostic progressive training strategy comprising of progressive training and label optimization, where the former is to decrease the affect from the noisy samples by facilitating a graduated learning approach in an easy-to-hard manner, while the latter is to denoise the label noises. Theoretical analysis also demonstrates that the proposed method uncovers valuable cues hidden in the training data, thereby enhancing the robustness of any learning-based models. Experimental evaluations on fine-grained classification benchmarks (e.g., CUB-200-2011, DTD, and Food-101) across various mainstream classification networks demonstrate the effectiveness of our training strategy. Code is available at https://github.com/cb-rep/LPPT.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143109456","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":"Unsupervised feature learning using locality-preserved auto-encoder with complexity-invariant distance for intelligent fault diagnosis of machinery","authors":"Zhenghua Lu,&nbsp;Zhaobi Chu,&nbsp;Min Zhu,&nbsp;Xueping Dong","doi":"10.1007/s10489-025-06278-8","DOIUrl":"10.1007/s10489-025-06278-8","url":null,"abstract":"<div><p>Unsupervised feature learning (UFL) has been recognized as a promising feature extractor in machinery fault diagnosis, where the auto-encoder is a very popular UFL framework. For the auto-encoder methods, however, it is still a great challenge to learn discriminative features from complex signals in an unsupervised manner. In this paper, a new UFL method named locality-preserved auto-encoder (LPAE) is proposed by explicitly designing a locality-preserved penalty term. Concretely, the penalty term constrains local geometry of samples in the original space to be well preserved in the reconstruction space, enabling more discriminative features to be learned accordingly. To better formulate this term, the complexity-invariant distance (CID) is employed to measure similarity between two mechanical signals so as to construct a reliable neighbor graph. On a rolling bearing dataset, experimental results verify that the proposed LPAE can learn sufficiently discriminative features from complex vibration signals collected from varying operating conditions, and achieves a remarkable and superior diagnosis performance over the existing advanced UFL methods. Moreover, the effectiveness of CID has been adequately validated by comparing with several other distance measurement methods. The proposed LPAE can be applied to the feature extraction stage of machinery fault diagnosis, which provides a potential solution for engineers to realize unsupervised learning of discriminative features.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143109459","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 user preference knowledge graph incorporating spatio-temporal transfer features for next POI recommendation","authors":"Chun-Yan Sang,&nbsp;Yang Yang,&nbsp;Yi-Bo Zhang,&nbsp;Shi-Gen Liao","doi":"10.1007/s10489-025-06290-y","DOIUrl":"10.1007/s10489-025-06290-y","url":null,"abstract":"<div><p>Knowledge graphs can improve the performance of recommendation systems and provide explanations for recommendation results, which have been widely applied in the next Point-of-Interest (POI) recommendation. However, the current knowledge graph method for the next POI recommendation focuses on the static attributes of POIs, and only describes the spatio-temporal characteristics when the user transfers between POIs. To fully tap into user preferences for different POIs, we have done the following innovative work. (1) We construct a user preference knowledge graph with spatio-temporal characteristics, named UPSTKG, which expresses preference information from both individual user and global user perspectives. (2) We use local preference triplets in preference knowledge graphs to construct user preference graphs. And use GCN to obtain user preference vectors to replace common user vectors in the sequence, thereby strengthening the potential connection between users and different POIs. (3) We combine UPSTKG and user preference graph to propose the UPSTKGRec method for the next POI recommendation. To evaluate the effectiveness of UPSTKGRec, it is compared to six highly regarded techniques on three distinct benchmark datasets. Compared with the baseline, the average performance of indicators recell@5 and NDCG@5 has increased by 13.8% and 13.1%.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143109460","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":"Daily power generation forecasting for a grid-connected solar power plant using transfer learning technique","authors":"Salwan Tajjour,&nbsp;Shyam Singh Chandel,&nbsp;Hasmat Malik,&nbsp;Fausto Pedro García Márquez,&nbsp;Majed A. Alotaibi","doi":"10.1007/s10489-024-06090-w","DOIUrl":"10.1007/s10489-024-06090-w","url":null,"abstract":"<div><p>Deep learning is efficiently used for photovoltaic power generation forecasting to handle the intermittent nature of solar energy. However, big data are required for training deep networks which are not available for newly installed plants. Therefore, in this study, a novel strategy is proposed to train a deep learning model using a transfer learning technique to cop up with the unavailability of enough training datasets. A new 400 kWp solar power plant installed in the Himalayan region is considered as a case study to evaluate the proposed model. The proposed approach utilizes solar radiation data to train a deep neural network and then fine-tune the model using the power generation data from the plant. The network architecture is optimized using grey wolf optimizer to find the best suitable model for the data. The evaluation results show that the same model can achieve higher performance in generation forecasting with percentage error improved by 2% and R-value increased by 7.7% after applying transfer learning. Moreover, SHapley Additive exPlanation and Partial Dependence Plots are used to interpret the model behavior and showed that the model is mostly dependent on the previous generation values (up to 4 days) followed by the temperature and solar radiation.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://link.springer.com/content/pdf/10.1007/s10489-024-06090-w.pdf","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143109793","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":"Reinforcement knowledge graph reasoning based on dual agents and attention mechanism","authors":"Xu-Hua Yang,&nbsp;Tao Wang,&nbsp;Ji-Song Gan,&nbsp;Liang-Yu Gao,&nbsp;Gang-Feng Ma,&nbsp;Yan-Bo Zhou","doi":"10.1007/s10489-024-06162-x","DOIUrl":"10.1007/s10489-024-06162-x","url":null,"abstract":"<div><p>Reinforcement learning can model knowledge graph multi-hop reasoning as Markov Decision Processes and improve the accuracy and interpretability of predicting paths between entities. Existing reasoning methods usually ignore the logic of action selection when facing one-to-many or many-to-many relationships, resulting in poor performance in knowledge graph reasoning. Furthermore, the general multi-hop reasoning only achieves effective short-path reasoning and lacks efficiency in long-distance reasoning. To address the above challenges, we propose a reinforcement learning reasoning model based on dual agents and attention mechanism, where two agents are trained at the macro and micro levels, and the macro agent guides the reasoning of the micro agent. The model employs an attention mechanism to enhance the representation of the current state of the agent, to help the policy network in making more appropriate action selections when facing one-to-many or many-to-many relationships, so as to improve the selection efficiency. Simultaneously, we propose a reward function with a penalty mechanism that penalizes the agent for prematurely reaching the correct answer without staying in place, and enhances the reward of the micro agent with the reward of the macro agent. The two agents cooperate with each other to find reasoning paths on the knowledge graph. Finally, we compare the proposed model with six well-known inference method baselines on three benchmark datasets, and the experimental results show that our proposed method achieves very competitive results.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143109461","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":"Rate maximization based on soft actor-critic reset for RIS-assisted MU-MISO symbiotic radio systems","authors":"Kaitian Cao,&nbsp;Yetao Ji","doi":"10.1007/s10489-025-06297-5","DOIUrl":"10.1007/s10489-025-06297-5","url":null,"abstract":"<div><p>In this paper, we investigate a reconfigurable intelligent surface (RIS)-assisted multiuser multiple input single output (MU-MISO) symbiotic radio system that incorporates hardware impairments in the RIS. This paper is aimed at solving the optimization problem to maximize the primary transmission rate while guaranteeing the rate of the secondary transmission in the RIS-assisted MU-MISO system. To this end, we formulate an optimization model that considers the transmit power and RIS phase shift constraints as well as the rate constraint of the secondary transmission. This joint optimization problem is complex and coupled, which is difficult to solve. To tackle this issue, we transform the original optimization problem into a Markov decision process characterized by a mixed-signal reward function. To enhance the reward outcome, we propose a novel algorithm based on soft actor-critic (SAC) reset. Simulation results demonstrate that that the proposed SAC-reset method can achieve a higher average reward compared with the conventional SAC schemes and other state-of-the-art deep reinforcement learning (DRL) algorithms.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143109559","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":"Freeway optimal control based on emission oriented microscopic graph convolutional neural network","authors":"Jie Fang,&nbsp;Mingwen Lu,&nbsp;Lina Fu,&nbsp;Juanmeizi Wang,&nbsp;Mengyun Xu","doi":"10.1007/s10489-024-06143-0","DOIUrl":"10.1007/s10489-024-06143-0","url":null,"abstract":"<div><p>Traffic flow prediction and control in the active traffic control system is considered as one of the most critical issues in Intelligent Transportation Systems (ITS). Among the proposed AI-based approaches, Deep Learning (DL) has been largely applied while showing better performances. This research improves macroscopic traffic flow model METANET by establishing a graph convolution neural network (GCN) to explicitly and more precisely incorporate microscopic traffic flow dynamics. The microscopic emission model utilizes the feature extraction function of GCN to reduce the complexity of measuring the environmental profits for the whole traffic network. By introducing the GCN model to facilitate the aggregation of vehicle information, the proposed framework reduces the computational burden and obtains better optimization performance. The designed algorithms are tested on a microscopic simulation platform based on field data. The results demonstrate that the proposed control method produce a more robust and smooth traffic flow environment, which leads to improved traffic efficiency and overall carbon emissions of the road network.</p></div>","PeriodicalId":8041,"journal":{"name":"Applied Intelligence","volume":"55 6","pages":""},"PeriodicalIF":3.4,"publicationDate":"2025-01-28","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143109455","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}