Is this you? Claim this profile to correct it, add a bio and choose the work people see first.
Claim this profileWorks145 from public data
- Survey on sentiment analysis: evolution of research methods and topics215
This survey not only compares and analyzes the connections between research methods and topics over the past two decades but also uncovers the hotspots and trends over time, thus providing guidance for researchers.
- A review of emotion sensing: categorization models and algorithms144
This paper reviews and discusses existing emotion categorization models for emotion analysis and proposes methods that enhance existing emotion research.
- Seven Pillars for the Future of Artificial Intelligence96
Seven pillars are proposed that are believed to represent the key hallmark features for the future of AI, namely, multidisciplinarity, task decomposition, parallel analogy, symbol grounding, similarity measure, intention awareness, and trustworthiness.
- Multi-Level Fine-Scaled Sentiment Sensing with Ambivalence Handling90
A new opinion analysis scheme, i.e., a multi-level fine-scaled sentiment sensing with ambivalence handling with the strength-level tune parameters for analyzing the strength and the fine-scale of both positive or negative sentiments.
- A review of Chinese sentiment analysis: subjects, methods, and trends51
This study tracing the interplay between research methodologies and emerging topics over the past two decades not only facilitates a comparative analysis of their correlations but also illuminates evolving patterns, identifying significant hotspots and trends over time for Chinese language text analysis.
- 48
- MiMuSA—mimicking human language understanding for fine-grained multi-class sentiment analysis33
This paper proposes a new explainable fine-grained multi- class sentiment analysis method, namely MiMuSA, which mimics the human language understanding processes and outperforms other existing multi-class sentiment analysis methods in terms of accuracy and F1-Score.
- Hierarchical Fuzzy Logic System for Implementing Maintenance Schedules of Offshore Power Systems32
An innovative approach for the smart grid to handle uncertainties arising from condition monitoring and maintenance of power plant and the ability of the proposed approach for handling operational variations occurring in an offshore substation with manageable computational complexity is demonstrated.
- Machine Learning for Refining Knowledge Graphs: A Survey30
A survey of machine learning approaches to KG refinement according to the kind of operations in KG refinement, the training datasets, mode of learning, and process multiplicity is presented.
- 30
- 29
- Harmonic analysis in integrated energy system based on compressed sensing29
The results of the experiment shows that the proposed scheme effectively enhances the precision of harmonic and inter-harmonic detection with low computing complexity, and has good capability of signal reconstruction.
- Enhancing Machine-Learning Methods for Sentiment Classification of Web Data29
Investigation of the enhancement techniques in machine-learning methods for sentiment classification of Web data for feature selection, negation dealing, and emoticon handling shows that different enhancement methods can improve classification efficacy and accuracy differently.
- Explainable Sentiment Analysis With DeepSeek-R1: Performance, Efficiency, and Few-Shot Learning25
While its reasoning process reduces throughput, DeepSeek-R1 offers superior explainability via transparent, step-by-step traces, establishing it as a powerful, interpretable open source alternative.
- Clinical and urodynamic characteristics of underactive bladder24
The comprehensive clinical and urodynamic characteristics of UAB in patients with lower urinary tract symptoms are described and can provide a reasonable basis for the future research.
- 24
- Performance Analysis of Llama 2 Among Other LLMs23
The findings indicate that Llama 2 holds significant promise for applications involving in-context learning, with notable strengths in both answer quality and inference speed.
- QoS routing optimization strategy using genetic algorithm in optical fiber communication networks22
The simulation results show that the proposed routing method by using this optimal maintain operator genetic algorithm (OMOGA) is superior to the common genetic algorithms (CGA), it not only is robust and efficient but also converges quickly and can be carried out simply, that makes it better than other complicated GA.
- Average Consensus in Directed Networks of Multi-agents with Uncertain Time-varying Delays20
A less conservative upper bound of time-varying communication delays is derived in comparison with the existing results and numerical examples confirm the effectiveness of the proposed method.
- How to guarantee compliance between workflows and product lifecycles?20
This paper formally defines the notion of compliance between these two artifacts in product lifecycle management and develops a compliance checking method which employs a well-established workflow analysis technique and forms the basis of a tool which offers automated support to the proposed approach.
- 19
- Delayed Effects of Climate Variables on Incidence of Dengue in Singapore during 2000-201016
It is found that using the short term data and the long term data can provide complementary insights into the relationship between dengue incidence and climate variables.
- 16
- Extreme Learning Machine for Multi-class Sentiment Classification of Tweets13
Experimental results show that Extreme Learning Machine (ELM) achieves better performance than other machine learning methods in multi-class sentiment classification of tweets.
- Verification of workflow nets with transition conditions13
This paper can determine which execution paths of a WTC-net that are possible according to the control-flow dependencies, are actually possible when considering the conditions based on data, and is able to more accurately determine at design time whether a workflow net with transition conditions is sound.
- Image Inpainting Method based on Evolutionary Algorithm13
An optimizing method based on evolutionary algorithm is proposed to analyze the structure information to find out the related structural information and calculate the related contour lines that should be connected to each other.
- Online fault detection of induction motors using independent component analysis and fuzzy neural network13
The most dominating components of the stator currents measured from laboratory motors are directly identified by an improved method of independent component analysis and used to train a fuzzy neural network for detecting induction-motor problems such as broken rotor bars and bearing fault.
- 12
- 11
- 10
- 10
- 9
- 9
- Structure-Priority Image Restoration Through Genetic Algorithm Optimization9
This paper proposes a novel GA-based image restoration method that can successfully restore a damaged image and names it structure-priority image restoration through GA optimization, and develops a GA optimization algorithm to solve it.
- Analysis of Bus Ride Comfort Using Smartphone Sensor Data9
This study investigates the relationship between bus ride comfort based on ride smoothness and the vehicle’s motion detected by the smartphone sensors and demonstrates that it is possible to make use of larger and readily available kinematic data to assess passenger comfort.
- 9
- 8
- Knowledge Graph enhanced Aspect-Based Sentiment Analysis Incorporating External Knowledge8
This research introduces an approach to ABSA that leverages knowledge graphs to improve completeness, accuracy, and performance efficacy and offers a complementary overview and analysis of various deep learning heuristics and optimization strategies that could further enhance ABSA performance.
- 8
- Large-Scale Dataset Incremental Association Rules Mining Model and Optimization Algorithm7
Based on IFP-Growth increment of association rules mining model and to modify the FP-tree, put forward the suitable for transaction data and support the tree model of change, and reduce the frequency of the original dataset range query and query, and ensure load balancing, improve operation efficiency.
- 7
- Abdominal Sonography for Diagnosis of Vaginal Grains in Chinese Children7
Sonographic characteristics of vaginal grains embedded as vaginal foreign bodies sometime occur in Chinese children and abdominal sonography can be the first choice for diagnosis because of its noninvasive nature, high specificity, and low cost.
- 7
- Learning-Based Stock Market Trending Analysis by Incorporating Social Media Sentiment Analysis6
This research not only demonstrates the merits and weaknesses of different learning-based methods, but also points out that incorporating social opinion is a right direction for improving the performance of stock market trending prediction.
- Research on fuzzy neural network algorithms for nonlinear network traffic predicting6
From the effective forecasting results obtained, it can be concluded that fuzzy neural networks can be well applicable for the traffic series prediction.
- 5
- 5
- 5
- 5
- Describing fuzzy sets using a new concept: fuzzify functor5
Using the fuzzify functor the authors can exactly describe the type-1 fuzzy sets, type-2 fuzzy sets and higher type or higher order fuzzy sets.
- 5
- 4
- 4
- Language and Robotics: Complex Sentence Understanding4
This research work illustrates that two important steps are necessary to translate a language-dependent surface sentential structure into a language independent deep-level predicate representation, and then the next step is to translate the predicate representation into grounded real-world references and constructs that enable a robot to carry out the language instructions accordingly.
- 4
- 4
- The Correlation Between the Strategies of Emotion Work and Nurses' Burnout4
There is significant correlation between the emotion work and the nurses' burnout and deep acting is a better choice if there is a conflict between actual feeling and display rule.
- 4
- 3
- 3
- Joint Weakly Supervised Image Emotion Analysis Based on Interclass Discrimination and Intraclass Correlation3
A novel approach, which combines interclass discrimination and intraclass correlation joint learning capabilities for image emotion analysis, and improves interclass descriptive ability and enhances emotional categories, resulting in the production of pseudomaps that provide more precise emotional region information.
- Mining Consumer Brand Relationship from Social Media Data: A Natural Language Processing Approach3
This study reviews consumer brand relationship analysis focusing on leveraging NLP and machine learning techniques to address some challenges associated with discovering customer brand relationship from social media data and proposes a methodological framework for the approach.
- 3
- Event‐Triggered Average Consensus for Multiagent Systems with Time‐Varying Delay3
The paper investigates average consensus for multiagent systems with time-varying delay by using event-triggered mechanism to reduce network load and a comprehensive model is proposed, which considers communication delay and triggered issue.
- 3
- An automated method for acquiring design knowledge from product patents3
To acquire associational knowledge from descriptions of product function and structure in patents, a new method for knowledge acquisition based on association rules was proposed and the results obtained prove the validity of this method.
- 3
- Counterfactual Thinking Driven Emotion Regulation for Image Sentiment Recognition2
A counterfactual thinking driven emotion regulation network (CTERNet), which simulates the Emotion Regulation Theory by modeling the entire process of ISR based on human causality-driven mechanisms, proving its effectiveness in addressing the key challenges of region-based ISR.
- 2
- 2
- 2
- 2
- Bipartite Consensus Problems of Directed Cooperative and Antagonistic Networks with Communication Time‐Varying Delays2
A model transformation is introduced, based on which the consensus can be equivalently transformed into the asymptotic stability of a reduced‐order system, and sufficient conditions are provided to ensure the bipartite consensus of CANs whose topologies are structurally balanced.
- 2
- Distributed event-triggered hybrid wired-wireless networked control with $${H_2}/{H_\infty }$$ H 2 / H ∞ filtering2
A general closed-feedback filtering and control system model with distributed event-triggered parameters and network-induced delays of hybrid wired-wireless networks is proposed, and simulation results confirm the effectiveness of the proposed method.
- A wireless sensor network node design based on ZigBee protocol2
A wireless sensor network node is designed in this paper which includes temperature, humidity monitoring signal collection and communication protocol design based on ZigBee, to prove the design is reasonable, reliable, and can be widely used.
- 2
- 2
- Working Structure Knowledge Acquisition from Mechanical Product Patent Based on Natural Language Understanding2
According to the increasing demand of patent knowledge in product innovative design, a working structure knowledge acquisition method, from mechanical product patent, was presented and the key technique of syntactic analysis and semantic analysis was illuminated.
- Quality of service routing strategy using supervised genetic algorithm2
A supervised genetic algorithm (SGA) is proposed to solve the quality of service (QoS) routing problems in computer networks and shows that SGA improves the ability of searching an optimum solution and accelerates the convergent process up to 20 times.
- ConvPayMAS: Conversational Payment Multi-Agent System with Agent-to-Agent Protocol and Three-Mandate Verification1
ConvPayMAS is presented, an LLM-based conversational payment multi-agent system that encapsulates payment execution behind a Conversational Supervisor Agent (CSA), allowing shopping and merchant agents to invoke payment without handling sensitive card data.
- LLM-as-a-Judge for Scalable Test Coverage Evaluation: Accuracy, Operational Reliability, and Cost1
LLM-as-a-Judge (LAJ), a production-ready, rubric-driven framework for evaluating Gherkin acceptance tests with structured JSON outputs, is presented and the Evaluation Completion Rate (ECR@1) is introduced to quantify first-attempt success.
- 1
- 1
- Consensus for criteria of running a pediatric inflammatory bowel disease center using a modified Delphi approach1
A comprehensive set of quality indicators (QIs) for evaluating PIBD center in China was developed using a modified Delphi consensus-based approach to identify a set of QIs of structure, process, and outcomes.
- Quantitative Evaluation of Percutaneous Local Drug Perfusion Against Refractory Infantile Hemangioma via 3-D Power Doppler Angiography1
Three-dimensional CPA can quantitatively assess changes in lesion volume and guide the effective and rational use of interventional drugs and can provide abundant information on internal lesions.
- 1
- Construction of training course for specialized wound nurses based on Delphi method1
The context of training course for specialized wound nurses is determined from three dimensions including professional attitude, knowledge and skills, and this study provides suggestions and theoretical support for the training of specialized nurses.
- 1
- Detecting Infeasible Traces in Process Models1
This paper builds on the theory of workflow nets and introduces workflow nets where transitions have conditions associated with them and demonstrates that it can be determined which execution traces, that are possible according to the controlflow dependencies, are actually possible taking the data perspective into account.
- 1
- 1
- Research and improvement of intermediate currency therapeutic unit1
The improved intermediate currency therapeutic unit is with complete functions and it can reach better treatment effect through simple operations.
- 1
- 1
- Optical properties reconstruction of layered tissue and the experimental demonstration1
A flexible and fast perturbation model of diffuse reflectance has been developed for the extraction of the information of photon migration in tissue from MC model and the inverse problem for obtaining the optical properties was solved by a Gauss-Newton nonlinear least-squares algorithm.
- –
- –
- –
- A Survey of Commonsense Reasoning in LLMs–
The role of commonsense reasoning in LLMs is discussed, how they strive to emulate human-like reasoning, and why they often struggle to capture the nuanced inferences associated with commonsense understanding of the physical and social world.
- Quantitative Three-Dimensional Color Power Angiography Parameters Predict Response to Locally Injected Bleomycin in Infantile Hemangioma–
The vascularization–flow index can be used as an objective predictor of the response of infantile hemangioma to locally injected bleomycin and should be used as an objective predictor of the response of infantile hemangioma to locally injected bleomycin.
- –
- Short term heat load forecasting method based on deep belief network–
The experimental results show that the forecasting accuracy of the proposed method is better than the method based on support vector machine and the method based on long and short-term memory network.
- –
- –
- –
- –
- A Metadata Management Method Base on Directory Path Code–
A new metadata management method to store directory and file metadata separately, and effectively solving the unbalanced metadata distribution and access hot point problems in Sub-tree partition and the excessive reading times and large metadata migration amount after directory property modification in hash algorithm is presented.
- –
- –
- Formal modeling language of workflow with data-data-aware workflow nets–
To model and verify the workflow formally before implementing workflow, the research status of workflow with data's formal modeling was summarized and the strong formal capacity of data-aware workflow net was verified.
- The Design and Practice of Educational Administration System——Take Tibet University as Case Study–
This thesis aims at realizing full information management to ed ucation administration field by developing analysizing and procedure designing connectted with the its practice situation of Tibet University.
- Design of Wireless Temperature Monitoring System for High-voltage Transformer Based on ZigBee–
A temperature monitoring node of wireless network for HVT (high electricity voltage transformers) is designed and a self-organizing wireless sensor networks is fulfilled, suitable for the use of temperature detecting in high-voltage substations.
- –
- Auxiliary decision-making system for container loading–
Analysis of two examples illustrates that the container loading scheme proposed by the software can provide auxiliary decision-making for workers, and improve the space utilization of container.
- Automated support for versioning compliance checking between workflow management and product lifecycle management (in Chinese)–
The evaluation and feedback from practitioners further evidence the practical significance of this research question in the PLM field and demonstrate that the proposed solution with its automated tool support possesses a high application potential.
- –
- The Role and Practice of Doctor-Patient Communication in Medical Activities–
A good doctor-patient communication helps to improve the quality of medical services to ensure the safety of health care, improve the economic and social benefits to the hospital, and achieve a win-win situation for both doctors and patients.
- The Improved Transductive Support Vector Machine and Its Application to Environment Monitoring in Industrial Seaculture–
This work tries to transform the problem of TSVM optimization into an unconstrained one before constructing the smooth unconStrained optimization that has a kernel, and on the basis of which to devise a TSVM whose optimization problem is easier to solve to breakthrough the bottleneck.
- Research of a new low frequency physical therapy system–
This method combined the technology of double single-chip microprocessor with a variety of software programming to obtain the waveform synthesis and double amplitude frequency adjustable for the bipolar output signal.
- Investigation and study on senior citizen physique health state of Zhoukou–
The author found that the physique of woman was better than that of man and the overall growth of physique showed a downward trend with age.
- –
- The practice and effect of education on nursing core regulations to students in clinical nursing–
Paying close attention to the education on nursing core regulations can strengthen nursing students' understanding and implementation Nursing core regulations, which can reduce nursing errors and improve the quality of clinical teaching.
- Research on Technology of Torque Measurement Based on SCM–
A kind of torque measurement system based on SCM technology is described, in which strain torque transducer is used to accomplish the monitoring of torque and axial force.
- –
- –
- Uncertain proximal Support Vector Machine–
The training set is modified, in which yi is replaced by zi+,zi+ and classification optimal model and Uncertain Proximal Support Vector Machine are construct in turn.
- –
- –
- –
- –
- Application of matrix approach for transaction management–
The DC power flow algorithm is reviewed, the method of transaction matrix for analyzing transmission management is presented, solutions to some different condition by simpler way are considered and relevant opinions are concluded.
- –
- –
- –
- Research for Process Schedule Fundamental and Improved Algorithm of Linux Kernel–
An improved algorithm is presented for the process schedule of Linux that rebuilds the data structure of the scheduling queue, replaces the traverse step by a straight computing step for choosing the process with highest priority, and changes the uniform strategy into a dispersed recalculated strategy for time slice distributing.
- Algorithm of Classifying Network Traffic Using Ensemble Neural Networks–
Simulation result demonstrates that ENN not only can be well applicable for classifying the network traffic, but also is superior to NN and FNN.
- –
- An Effective Method for Transforming XML Query to SQL–
The algorithm was used to bijective mapping, and pretreating before the run time translation to show that the algorithm is more effective than some normal algorithms such as SilkRoute, Xperanto etc.
- –
- –
- –
- –
- –
- –
Publication data from OpenAlex, with missing venues and authors filled in from Crossref; citation counts are the higher of OpenAlex and Semantic Scholar; position from the scholar’s ORCID record, last synced 2026-10-10. One-sentence summaries under some papers are written by Semantic Scholar’s model. Citation counts may be lower than on Google Scholar, which indexes more sources.
Report an error
Wrong papers, two people merged into one, or a profile that should not be here? Tell us and we will fix or hide it. You will be asked to sign in.