Emotion Recognition in Conversation (ERC) is a crucial task for understanding human emotions and enabling natural human-computer interaction. Although Large Language Models (LLMs) have recently shown great potential in this field, their ability to capture the intrinsic connections between explicit and implicit emotions remains limited. We propose a novel ERC training framework, PRC-Emo, which integrates Prompt engineering, demonstration Retrieval, and Curriculum learning, with the goal of exploring whether LLMs can effectively perceive emotions in conversational contexts. Specifically, we design emotion-sensitive prompt templates based on both explicit and implicit emotional cues to better guide the model in understanding the speaker’s psychological states. We construct the first dedicated demonstration retrieval repository for ERC, which includes training samples from widely used datasets, as well as high-quality dialogue examples generated by LLMs and manually verified. Moreover, we introduce a curriculum learning strategy into the LoRA fine-tuning process, incorporating weighted emotional shifts between same-speaker and different-speaker utterances to assign difficulty levels to dialogue samples, which are then organized in an easy-to-hard training sequence. Experimental results on two benchmark datasets—IEMOCAP and MELD—show that our method achieves new state-of-the-art (SOTA) performance, demonstrating the effectiveness and generalizability of our approach in improving LLM-based emotional understanding.

Automatic segmentation of lesions in medical images is a popular and challenging task. CNN-based methods are limited by local receptive fields and struggle to capture longrange spatial dependencies. In contrast, Transformers can model global information; however, their attention mechanism exhibits high computational complexity and low efficiency when processing high-resolution 3D medical images. Therefore, this paper proposes MatFuseU-Net for lesion segmentation. Built on the U-Net architecture, this model converts Non-negative Matrix Factorization (NMF) into a differentiable computational unit and constructs an adaptive module with linear computational complexity to replace the self-attention mechanism. Different from traditional NMF module designs, this paper innovatively introduces a dynamic-rank NMF module based on local feature complexity, which adaptively adjusts the rank of NMF according to the local complexity of the input feature map, thereby enhancing the model's expressive capability. The loss function of MatFuseU-Net combines Dice loss and cross-entropy loss, and the training process is optimized through a deep supervision strategy. In the experiments, the BraTS 2021 and ISLES 2022 datasets were used to evaluate the model's performance. The model achieved promising results in two metrics: average Dice score and 95% Hausdorff Distance, demonstrating its excellent performance.

Emotion Recognition in Conversation (ERC) is a practical and challenging task. This paper proposes a novel multimodal approach, the Long-Short Distance Graph Neural Network (LSDGNN). Based on the Directed Acyclic Graph (DAG), it constructs a long-distance graph neural network and a short-distance graph neural network to obtain multimodal features of distant and nearby utterances, respectively. To ensure that long- and short-distance features are as distinct as possible in representation while enabling mutual influence between the two modules, we employ a Differential Regularizer and incorporate a BiAffine Module to facilitate feature interaction. In addition, we propose an Improved Curriculum Learning (ICL) to address the challenge of data imbalance. By computing the similarity between different emotions to emphasize the shifts in similar emotions, we design a “weighted emotional shift” metric and develop a difficulty measurer, enabling a training process that prioritizes learning easy samples before harder ones. Experimental results on the IEMOCAP and MELD datasets demonstrate that our model outperforms existing benchmarks.

As Named Entity Recognition (NER) tasks have evolved, artificial intelligence has been widely applied in this field. However, most benchmarks are limited to English, making it challenging to replicate successful experiences in other languages. To expand NER to informal and diverse Chinese text scenarios, we have proposed a new large-scale Chinese NER dataset, OmniNER2025. This dataset, obtained from user posts on a popular Chinese social media platform Xiaohongshu, contains 195,568 samples and 89 categories, all manually annotated. To our knowledge, it is currently the largest Chinese open-source NER dataset in terms of sample size, category diversity, and domain coverage. This dataset is more challenging than existing Chinese NER datasets and better reflects real-world applications. The large sample size and diverse entity types provide valuable research resources. Additionally, we introduced the ERRTA tool for error analysis and teacher model guidance, significantly reducing model errors and improving performance. In the future, we will refine the ERRTA framework and explore optimization strategies to enhance the practical value of NER models. By releasing the OmniNER2025 dataset and introducing the ERRTA tool, we have advanced fine-grained NER research and improved model performance, promoting its application and development in real-world scenarios.

The automatic diagnosis of chest diseases is a popular and challenging task. Most current methods are based on convolutional neural networks (CNNs), which focus on local features while neglecting global features. Recently, self-attention mechanisms have been introduced into the field of computer vision, demonstrating superior performance. Therefore, this paper proposes an effective model, CheX-DS, for classifying long-tail multi-label data in the medical field of chest X-rays. The model is based on the excellent CNN model DenseNet for medical imaging and the newly popular Swin Transformer model, utilizing ensemble deep learning techniques to combine the two models and leverage the advantages of both CNNs and Transformers. The loss function of CheX-DS combines weighted binary cross-entropy loss with asymmetric loss, effectively addressing the issue of data imbalance. The NIH ChestX-ray14 dataset is selected to evaluate the model’s effectiveness. The model outperforms previous studies with an excellent average AUC score of 83.76%, demonstrating its superior performance.

Emotion Recognition in Conversation (ERC) aims to analyze the speaker’s emotional state in a conversation. Fully mining the information in multimodal and historical utterances plays a crucial role in the performance of the model. However, recent works in ERC focus on historical utterances modeling and generally concatenate the multimodal features directly, which neglects mining deep multimodal information and brings redundancy at the same time. To address the shortcomings of existing models, we propose a novel model, termed Enhancing Emotion Recognition in Conversation with Speech and Contextual Prefixes (ESCP). ESCP employs a directed acyclic graph (DAG) to model historical utterances in a conversation and incorporates a contextual prefix containing the sentiment and semantics of historical utterances. By adding speech and contextual prefixes, the inter- and intra-modal emotion information is efficiently modeled using the prior knowledge of the large-scale pre-trained model. Experiments conducted on several public benchmarks demonstrate that the proposed approach achieves state-of-the-art (SOTA) performances. These results affirm the effectiveness of the novel ESCP model and underscore the significance of incorporating speech and contextual prefixes to guide the pre-trained model.

Aspect Sentiment Triple Extraction (ASTE) is an emerging task in fine-grained sentiment analysis. Recent studies have employed Graph Neural Networks (GNN) to model the syntax-semantic relationships inherent in triplet elements. However, they have yet to fully tap into the vast potential of syntactic and semantic information within the ASTE task. In this work, we propose a Dual Encoder: Exploiting the potential of Syntactic and Semantic model (D2E2S), which maximizes the syntactic and semantic relationships among words. Specifically, our model utilizes a dual-channel encoder with a BERT channel to capture semantic information, and an enhanced LSTM channel for comprehensive syntactic information capture. Subsequently, we introduce the heterogeneous feature interaction module to capture intricate interactions between dependency syntax and attention semantics, and to dynamically select vital nodes. We leverage the synergy of these modules to harness the significant potential of syntactic and semantic information in ASTE tasks. Testing on public benchmarks, our D2E2S model surpasses the current state-of-the-art(SOTA), demonstrating its effectiveness.

Emotion Recognition in Conversation (ERC) plays an important role in intelligent human-computer interaction. Highly accurate emotion recognition helps to improve the ability of machines to serve humans. Recent works exhibit poor generalization ability and low recognition accuracy, and better performances can only be presented on specific datasets. To be able to adapt to complex real-world application scenarios, we propose a novel model, termed Multi-scale Line Graph ATtention Network for Emotion Recognition in Conversation (MLGAT). MLGAT mines the emotional information dependent on the target utterance by focusing on local context and global context at different scales. Experiments show that our model achieves the second-highest performance among all current methods on both IEMOCAP and MELD datasets. Wa-F1 scores are 71.49% and 75.08%, respectively, which are only slightly different from their respective SOTAs (state of the art). Moreover, the model can show high accuracy in a few classes without additional measures.

Knowledge graphs are more widely utilized to enhance recommendability and explainability. Reinforcement learning agents built to wander around the knowledge graph have been successfully applied in recommendation systems in a form of multi-hop relation reasoning. Some previous multi-hop methods relied on reinforcement learning of discrete actions, making agent space design challenging and a lack of clarity in the meaning of actions because of inconsistent action. To solve the aforementioned issues, we propose Continuous-action Walking-tendency Interest-oriented Path Reasoning (CWIPR), a novel and pioneering method that uses continuous actions provided by reinforcement learning agents to predict inference relations and the next entity. Meanwhile, to better interact with the knowledge graph through continuous actions, we firstly propose a graph search algorithm called the walking tendency algorithm. Moreover, we introduce an interest-oriented reward as the intrinsic reward that encourages the agent to balance the tendency between exploring the most similar entities and exploring the correct recommendation type to achieve more precise recommendations. We extensively evaluate our method on three real-world datasets from Amazon and obtain favorable performance compared with state-of-the-art methods.

A crucial issue in multimodal language processing is representation learning. Previous works joint training the multimodal and unimodal tasks to learn the consistency and difference of modality representations. However, due to the lack of cross-modal interaction, the extraction of complementary features between modalities is not sufficient. Moreover, during multimodal fusion, the generated multimodal embeddings may be redundant, and unimodal representations also contain noise information, which negatively influence the final sentiment prediction. To this end, we construct a Modality-Complementary and Eliminating-Redundancy multi-task learning model (MCER), and additionally add a cross-modal task to learn complementary features between two modal pairs through gated transformer. Then use two label generation modules to learn modality-specific and modality-complementary representations. Additionally, we introduce the multimodal information bottleneck (MIB) in both multimodal and unimodal tasks to filter out noise information in unimodal representations as well as learn powerful and sufficient multimodal embeddings that is free of redundancy. Last, we conduct extensive experiments on two popular sentiment analysis benchmarks, MOSI and MOSEI. Experimental results demonstrate that our model significantly outperforms the current strong baselines.

Ellipsis phenomenon is prevalent, particularly in languages like Chinese, and can be observed across various domains, including everyday conversations, literary works, and product evaluations. Such ellipsis poses challenges for machines, affecting the performance of natural language processing tasks such as machine translation and comprehension. Current approaches to tackle ellipsis primarily involve fine-tuning pretrained language models like BERT(Bidirectional Encoder Representations from Transformers). This approach encompasses two subtasks: 1) detecting ellipsis positions, i.e., identifying locations where ellipsis occurs within a sentence, and 2) completing the elliptical content by predicting the missing information based on the detected positions. This paper proposes a novel model that combines fine-tuned BERT with Generative Adversarial Networks (GANs), incorporating a sampler between the generator and discriminator. The proposed method simultaneously utilizes the generator, discriminator, and sampler to locate and complete ellipsis. Experimental results demonstrate that our approach achieves an F1 score improvement of 0.03 in ellipsis position detection and an EM (Exact Match) improvement of 0.1 in ellipsis content completion compared to the baseline method.

With the development of GPS technology, location-based information services are becoming more and more diverse. Using the trajectory data generated by GPS can analyze and study the various needs of taxi drivers. Big data technology such as interpreting, manipulating data and extracting nugget of information from data is crucial in Intelligent Transportation System (ITS). In order to enhance cruising efficiency of drivers, this paper proposes a Taxi-cruising Recommendation strategy based on Real-time information and Historical Trajectory data (TR-RHT). Primarily, we construct a Passenger-Demand predict model based on Historical Hotspot (PDHH) to predict the passengers’ demand in hotspot area. Then, an Improved Decision Tree (IDT) predicting algorithm is proposed to construct spatio-temporal index to select suitable historical data. Furthermore, we introduce Hotspot Recommendation based on Historical Trajectory (HRHT), wherein it defines cruising event as the process of taxi searching for passengers. The HRHT model performs statistics and analysis on the different states of taxi operation, which can obtain the probability of catching passengers at each hotspot and calculate the travel time between hotspots. The model selects the statistics result of cruising efficiency and driving time between hotspots based on spatio-temporal index, then analyzes the selected result to provide optimal pick-up hotspots for drivers. Experiment results show that TR-RHT can precisely suggest a cruising path to reduce cruising time for drivers.

Most of the classification methods of urban functional areas nowadays are only based on single source data analysis and modeling, which can not make full use of the multi-scale and multi-source data that is easy to obtain. Therefore, this paper proposed a classification model of urban functional areas based on multi-modal machine learning, by analyzing regional remote sensing images and behavior data of visitors in the area, using the combination of supervised methods extracted the deep-seated features and relationships of kinds of data, filtered and merged the overall and local features of the data. The model used dual branch neural network combining SE-ResNeXt and Dual Path Network (DPN) to automatically mined and fused the overall characteristics of multi-source data, and used the designed feature engineering to deeply mine the behavior data of users to obtain more association information, then combined the algorithm based on Gradient Boosting Decision Tree to learn the characteristics of different levels and obtained the classification probability for different levels of features. Finally, we continued to use the algorithm based on the Gradient Boosting Decision Tree to learn the probability distribution of different levels of features to obtain the final prediction results of urban functional area classification. Through the analysis and experimental verification of real data sets, the results showed that MM-UrbanFAC model can effectively integrate the features of multi-modal data. Compared with a single classifier, the integration framework based on gradient lifting tree improved the prediction performance, this method can effectively integrate the results of multiple models and accurately classify urban functional areas, and the model can provide reference for tourism recommendation, urban land planning and urban construction.

Ridesharing is a challenging topic in the urban computing paradigm, which utilizes urban sensors to generate a wealth of benefits and thus is an important branch in ubiquitous computing. Traditionally, ridesharing is achieved by mainly considering the received user ridesharing requests and then returns solutions to users. However, there lack research efforts of examining user acceptance to the proposed solutions. To our knowledge, user decisions in accepting/rejecting a rideshare is one of the crucial, yet not well studied, factors in the context of dynamic ridesharing. Moreover, existing research attention is mainly paid to find the nearest taxi, whilst in reality the nearest taxi may not be the optimal answer. In this paper, we tackle the above un-addressed issues while preserving the scalability of the system. We present a scalable framework, namely TRIPS, which supports the probability of accepting each request by the companion passengers and minimizes users' efforts. In TRIPS, we propose three search techniques to increase the efficiency of the proposed ridesharing service. We also reformulate the criteria for searching and ranking ridesharing alternatives and propose indexing techniques to optimize the process. Our approach is validated using a real, large-scale dataset of 10,357 GPS-equipped taxis in the city of Beijing, China and showcases its effectiveness on the ridesharing task.

Intelligent transportation systems (ITS) have been developed rapidly over the last few decades because of global urbanization and industrialization. ITS involve a wide range of different technologies and applications such as automatic road enforcement, dynamic traffic light sequence, and as a result, a significant number of scientific papers have been published in the field of ITS. In this paper, we present a useful insight into the development of ITS area by systematically analyzing the publications over the period of 20 years. First, we identify the most cited papers and most impactful authors in the field. Second, in the aspect of topic analysis, we identify some active keywords. To do so, we develop a keyword co-occurrence network to find topics in the ITS field. Finally, for the collaboration pattern analysis, we construct two networks to interpret collaboration patterns, including a co-authorship network, and an author co-keyword network to show the development and research tendency of ITS. Some most interesting findings from our investigation include the following: 1) Besides the USA, China and Europe have begun to play an increasingly significant role in this field and 2)GPS,traffic control, androad safetyshow an upward trend from the analysis of the evolution of ITS research topics, given the rise of new research areas such as autonomous vehicles. Our first-hand investigation and analysis of the literature provides a valuable reference to research activities in the development of ITS field and presents worthy insights on the current status and future technical trends.

Intelligent transportation systems (ITS) has been one of the most active research fields in recent years. This paper identifies most productive authors, institutions, and countries/regions inIEEE Transactions on Intelligent Transportation Systemsfrom 2000 to 2015. The results of bibliographic analysis show that the USA is the most influential country in that it not only has the most papers but also has six out of the ten most-cited papers. Meanwhile, researchers from China and Europe have published nearly half of the papers in this field. In addition, we generate three networks (including coauthorship network, keyword co-occurrence network, and author co-keyword network) to analyze collaboration patterns among authors in the field of ITS. The active keywords are investigated, and the top three arevehicles,road vehicles, androad traffic. Finally, visual pictures are presented to show topological interactions of authors' collaboration.

Recommender systems are constructed to search the content of interest from overloaded information by acquiring useful knowledge from massive and complex data. Since the amount of information and the complexity of the data structure grow, it has become a more interesting and challenging topic to find an efficient way to process, model, and analyze the information. Due to the Global Positioning System (GPS) data recording the taxi's driving time and location, the GPS-equipped taxi can be regarded as the detector of an urban transport system. This paper proposes a Taxi-hunting Recommendation System (Taxi-RS) processing the large-scale taxi trajectory data, in order to provide passengers with a waiting time to get a taxi ride in a particular location. We formulated the data offline processing system based on HotSpotScan and Preference Trajectory Scan algorithms. We also proposed a new data structure for frequent trajectory graph. Finally, we provided an optimized online querying subsystem to calculate the probability and the waiting time of getting a taxi. Taxi-RS is built based on the real-world trajectory data set generated by 12 000 taxis in one month. Under the condition of guaranteeing the accuracy, the experimental results show that our system can provide more accurate waiting time in a given location compared with a naïve algorithm.

In the dynamic social network, how to use data mining tools to find the hidden dynamic knowledge in the social network has become the focus of the study. It can be applied to a wide range of areas with good practical value and application significance. We propose a novel algorithm called iDBMM based on the improvement of DBMM algorithm. At first, iDBMM algorithm classifies the training set to obtain the basic characteristics of each role. Then it scores the test set relative to each role and distribute the role of the highest score to the corresponding node. Finally, the transition model is obtained by the statistical method. Experimental results show that new method determines the distribution of the roles of the nodes effectively to make up for the shortcoming of non-negative matrix factorization and improve the prediction accuracy.

Cooperative phenomenon is widely researched within the fields of computational genomics, artificial intelligence, machine learning and data mining technologies. A key idea behind complex system constructed by intelligent agents is to establish cooperation between different agents so as to solve problems more effectively and efficiently than a single agent can do. Understanding the evolutionary mechanisms that promote and maintain cooperative behavior is recognized as a major theoretical problem where the intricacy increases with the complexity of the participating individuals. We presents current research on the effect of the "probability of learning" (Pl) and the "probability of reconnecting" (Pr) in NIPD game in evolution experiment based on complex network system, static and dynamic. We show that the "probability of learning" (Pl) is not the decisive factor on static network but it plays an important role on dynamic network where the "probability of reconnecting" (Pr) is not zero.

Since service science is becoming more mature, many universities have now set up numbers of related courses. Service Science and Engineering Department, has some concrete teaching practice at School of Software, Dalian University of Technology. Our paper, analyses specific scientific knowledge systems for the integration of services in industry-specific systems, shows the new discipline will move to Financial Information Service when the service science is integrated into financial sectors, introduces a bachelor program of service science after presenting the relationship between service science and finance industry, analyses specific scientific knowledge systems for the integration of services in industry-specific systems, is to be expected that could establish knowledge system about finance industry on the basis of science-related courses which means that students in this program will take courses in two field, finance and service.

The microeconomic framework for data mining assumes that an enterprise chooses a decision maximizing the overall utility over all customers. In item selection problem, the store wants to select J item set S that maximizes the overall profit. Based on the microeconomic view, we propose a novel algorithm ItemRank to solve the problem of item selection with the consideration of cross-selling effect which has two major contributions. First, we propose customer behavior model, and demonstrate it with the data of customer-oriented business. Second, we propose the novel algorithm ItemRank which is implemented on the basis of customer behavior model. According to the cross-selling effect and the self-profit of items, ItemRank algorithm could solve the problem of item order objectively and mechanically. We conduct detailed experiments to evaluate our proposed algorithm and experiment results confirm that the new methods have an excellent ability for profit mining and the performance meets the condition which requires better quality and efficiency