Driven by advancements in the Large Language Model (LLM), there has been significant global attention on integrating the Generative Pre-trained Transformer (GPT) concept into Text-to-Speech (TTS) technologies. However, existing TTS models face issues such as inconsistent training data quality and reliance on autoregressive models, which makes controlling the quality of audio generation challenging. To address these challenges, this study introduces a novel TTS framework known as TTS-Vrefine, which is a new type of TTS architecture based on a self-feedback mechanism, aimed at enhancing the inference capabilities of the model and the quality of generated audio. The Vrefine framework iteratively refines the output, allowing the TTS system to self-train using its own generated data, significantly improving the clarity and quality of the audio. It expands the training dataset and enhances the self-optimization potential of the audio generation model, reducing the Word Error Rate (WER) of the base model by 2.4%, increasing the Perceptual Evaluation of Speech Quality (PESQ) by 2.22%, and improving the Short-Time Objective Intelligibility (STOI) by 4.55%. Additionally, the architecture optimizes the use of low-quality resources through a self-refinement mechanism, effectively expanding the training dataset.

Abstract Experimental economics is an important branch of economics to study human behaviours in a controlled laboratory setting or out in the field. Scientific experiments are conducted in experimental economics to collect what decisions people make in specific circumstances and verify economic theories. As a significant couple of variables in the virtual experimental environment, decisions and outcomes change with the subjective factors of participants and objective circumstances, making it a difficult task to capture human behaviour patterns and establish correlations to verify economic theories. In this paper, we present a visual analytics system, EBPVis, which enables economists to visually explore human behaviour patterns and faithfully verify economic theories, e.g. the vicious cycle of poverty and poverty trap. We utilize a Doc2Vec model to transform the economic behaviours of participants into a vectorized space according to their sequential decisions, where frequent sequences can be easily perceived and extracted to represent human behaviour patterns. To explore the correlation between decisions and outcomes, an Outcome View is designed to display the outcome variables for behaviour patterns. We also provide a Comparison View to support an efficient comparison between multiple behaviour patterns by revealing their differences in terms of decision combinations and time‐varying profits. Moreover, an Individual View is designed to illustrate the outcome accumulation and behaviour patterns of subjects. Case studies, expert feedback and user studies based on a real‐world dataset have demonstrated the effectiveness and practicability of EBPVis in the representation of economic behaviour patterns and certification of economic theories.

Various graph representation learning models convert graph nodes into vectors using techniques like matrix factorization, random walk, and deep learning. However, choosing the right method for different tasks can be challenging. Communities within networks help reveal underlying structures and correlations. Investigating how different models preserve community properties is crucial for identifying the best graph representation for data analysis. This paper defines indicators to explore the perceptual quality of community properties in representation learning spaces, including the consistency of community structure, node distribution within and between communities, and central node distribution. A visualization system presents these indicators, allowing users to evaluate models based on community structures. Case studies demonstrate the effectiveness of the indicators for the visual evaluation of graph representation learning models.

Numerous graph clustering methods have been proposed to explore aggregation structures across multiple graphs. In these methods, single-graph features are merely considered or multigraph features are simply weighted, which are insufficient for the construction of reasonable multiple graph clustering features, since the association information between pairwise graphs is ignored and the varied local correlations might influence the clustering preference. Thus, we propose an interactive multiple graph clustering model, iMGC, in this article, to achieve reasonable multiple graph clustering features, which cannot only express multiple relationships, but also preserve associations of nodes across multiple graphs. First, a unified graph matrix is constructed with the combination of structural differences quantified by graph representation learning, which is further optimized by minimizing the difference of structural characteristics between it and each single graph matrix. Thus, multiple relationships are well integrated and expressed, while the varied local correlations within different graphs are also balanced in the unified graph matrix. Then, a constrained Laplacian rank is applied on the unified graph matrix to generate the unified clustering result directly, which is able to preserve association features across multiple graphs. Furthermore, we provide a set of visualization and interaction interfaces, enabling users to intuitively optimize and evaluate the multiple graph clustering features, and interactively explore the multiple graphs. Case studies and quantitative comparisons based on real-world datasets have demonstrated the effectiveness of iMGC in the clustering performance from various perspectives and exploration of multiple graphs.

Numerous sampling strategies have been proposed to reduce the visual clutter of large-scale geographical point data visualization, which focus on the preservation of original data features, such as randomness, spatial distribution, and associated relationship. However, user preferences and demands are not taken into account in the course of sampling, which will lead to the sampled results deviating from user requirements and impede personalized geospatial analysis in specific application scenarios. In this article, we propose a user-driven sampling model for the visual abstraction of the large-scale geographical point data based on convolutional neural networks (CNN). First, a blue noise sampling model is applied to partition the geographical space into local areas, and a set of visual interfaces are designed to present the data features of those points in the local areas, enabling users to visually select representative points according to their requirements. Then, user preferences are quantified with a CNN model based on the eigenvectors of the representative points, which are further utilized to guide the sampling courses of the other local areas. Thus, all the sampled points will retain the spatial distribution of original data points and fulfill the user preference as far as possible. In addition, we implement a visualization framework to integrate manual point selection, CNN training, automatic point sampling, and visual comparison, allowing users to easily obtain and evaluate the sampled points from the perspectives of data analysis and user requirements. Quantitative comparisons and case studies based on real-world datasets are conducted to demonstrate the effectiveness of our sampling model in the preservation of user preferences and visual exploration of large-scale geospatial point data.

Ranking the node importance in complex networks has been widely applied for different purposes, such as web search, resource allocation, and network security. However, existing node ranking methods are almost single network ranking using only one relationship, or aggregate the node ranking scores on multiple networks with equal weight, which are insufficient to construct reasonable multiple network rankings, since the association information among multiple networks is largely ignored. Thus, we propose a multiple network visualization framework by fusing multiple networks to obtain credible node ranking scores. After measuring the scores of nodes in each single network by the classic PageRank, a network weight self-adjustment model based on structural similarities between pair-wise networks is designed to strengthen the common features of multiple networks or their distinct characteristics. Then, a combined score for each node is computed by a weighted sum of its individual ranking scores on multiple networks. Besides, we provide a set of visualization and interaction interfaces, enabling users to intuitively explore, optimize and compare the multiple network rankings. Case studies on real datasets show that our system is flexible to adapt to different application scenarios, and users can successfully solve multiple network ranking tasks efficiently.

Numerous sampling strategies have been proposed to simplify large-scale networks for highly readable visualizations. It is of great challenge to preserve contextual structures formed by nodes and edges with tight relationships in a sampled graph, because they are easily overlooked during the process of sampling due to their irregular distribution and immunity to scale. In this paper, a new graph sampling method is proposed oriented to the preservation of contextual structures. We first utilize a graph representation learning (GRL) model to transform nodes into vectors so that the contextual structures in a network can be effectively extracted and organized. Then, we propose a multi-objective blue noise sampling model to select a subset of nodes in the vectorized space to preserve contextual structures with the retention of relative data and cluster densities in addition to those features of significance, such as bridging nodes and graph connections. We also design a set of visual interfaces enabling users to interactively conduct context-aware sampling, visually compare results with various sampling strategies, and deeply explore large networks. Case studies and quantitative comparisons based on real-world datasets have demonstrated the effectiveness of our method in the abstraction and exploration of large networks.

Combining1 subjective evaluation with aesthetic criteria, this paper proposes an objective overall quality assessment method for graph layout algorithms. Firstly, we build the subjective rating database of graph layouts. The subjective experiment is designed to rate different graph layouts. Then, for each graph layout, we use the readability metrics of the layout as independent variables, the subjective score of users as the dependent variable, to establish the regression model. Through the regression model, we can get the overall quality score of a graph layout.

As a new visualization technology1, storyline intuitively illustrates the dynamic relationships between entities in a story, which is useful in many applications, including the description of characters' interactions in movies, the evolution of community structure in dynamic social networks, the marital status between people, etc. Previous works optimize the storyline's layout from the perspective of aesthetic standard, significantly reducing line crossings, line wiggles and layout space. But when dealing with large-scale data, there is room for improvement with regard to three issues: insufficient memory space, large time consumption and weak data expression. Therefore, this paper introduces the idea of cluster analysis to the storyline to present the clustering information and reduce the time complexity under the condition where a large number of entities interact in the same period. Meantime a scalable, reusable visualization library of storyline is implemented including some novel interactions.

The study of genealogy is an increasingly popular activity pursued by millions of people, ranging from hobbyists to professional researchers. Such genealogical datasets provide a great opportunity for social science analysts, historians, and the public to study a wide variety of topics in demography, family and household, kinship, stratification, and health. Nevertheless, the large scale and characteristics of the data such as hierarchical, spatiotemporal, and multidimensional also pose special challenges for effective data analysis. In this paper, we introduce GenealogyVis, a visual analytic system to analyze family history and evolution by using the China Multigenerational Panel Dataset-Liaoning, which has more than 1.5 million observations and provides socioeconomic, demographic, and other information for more than 260 000 residents, and further enable users to explore the correlation between the development of families and the social context of environments, economics, policies, and so on. This system includes five main linked views: the Scatter-plot View to provide an overview of the data and further explore the correlation analysis, the Tree View to show the family structure and details for individuals, the Migration View to present the genealogical migratory behaviors, the Matrix View to analyze the reproduction pattern between two generations, and the Stream View to show various statistical information such as demographic information and temporal information. A design study was conducted with a research group led by a domain expert of humanities and social sciences in an iterative manner over half a year. Several in-depth case studies, involving the research group, are described to demonstrate the usefulness of GenealogyVis and discuss new findings.

How to clearly present the internal structure of knowledge graph is particularly important, however, the current visualization researches about it are rare. We construct education knowledge graph utilizing extracted entities and entity relations, and construct a visual analysis platform, EduVis. In EduVis, we design and implement a) a layout of events network based on topological structure to explore in details, b) a layout of event network based on timeline to explore time information, c) a click tracking path to record the history of users' clicks and help users backtrack.

Micro-blog sentiment analysis attracts much attention by companies, governments and other organizations. It could help companies to estimate the extent of product acceptance and to determine marketing strategies, governments to monitor online public perception and to improve government-public relation, etc. Researchers mainly focused on time-varying analysis or space varying analysis.

There would be value to several domains in discovering and visualizing sentiments in online posts. This paper presents SentiView, an interactive visualization system that aims to analyze public sentiments for popular topics on the Internet. SentiView combines uncertainty modeling and model-driven adjustment. By searching and correlating frequent words in text data, it mines and models the changes of the sentiment on public topics. In addition, using a time-varying helix together with an attribute astrolabe to represent sentiments, it can visualize the changes of multiple attributes and relationships among demographics of interest and the sentiments of participants on popular topics. The relationships of interest among different participants are presented in a relationship map. Using a new evolution model that is based on cellular automata, it is able to compare the time-varying features for sentiment-driven forums on both simulated and real data. Adaptable for different social networking platforms, such as Twitter, blog and forum, the methods demonstrate the effectiveness of SentiView in analyzing and visualizing public sentiments on the Web.

Community structure is an important characteristic in real complex networks, meaning the networks are divided naturally into modules or communities, groups of vertices with relatively dense connections within groups but sparser connections between them. Fuzzy c-means clustering have been proposed to detect the community structure in networks for the past few years, and gained some fruitful results. In this paper, we present a new method to find the community structure in complex networks with self-adapted fuzzy c-means clustering, which can find the sum of the community structure voluntarily and overcome the deficiencies of original Fuzzy c-means clustering algorithms. The simulation results on the real-world networks and on synthetic benchmarks verify that the algorithm is more complete and accurate than the other mainstream FCM algorithms.

Due to the excessive items and multiple dimensions of parallel data, traditional visualization methods can not show the prominent information from their characters. This paper proposes a novel method of entity extracting to perform the multi-scale and hierarchical visualization of multi-attribute data set. Firstly, the relationship between these characters can be expressed as entity-relationship and data dimension is expressed as entity attributes, which can eliminate data redundancy and reduce data dimensions. Then a scalable dynamic visualization mode is proposed to show the characters at different levels of details. The method can interactively operate to visualize different data sets, such as electronic commerce data, weather forecast data, and gene expressions data, generating effective visualization results.

Emergency evacuation has many applications in computer animation, virtual reality, architecture planning, safety science, etc. However, current methods most focus on the agent-based modeling and simulation. These simulation results can not consider the human behavior fully and their reliabilities are doubtable. This paper presents a new method to simulate the large-scale crowds in real-time and verify the evacuation data in complex environment. Through analyzing the characteristics of human behavior in emergent condition, a mixed geometry-based ant colony evacuation model is firstly proposed. Then, many behaviors of human are considered to calculate the best evacuation path, including autonomous avoidance, human's warning time, and preferential path selecting. The experimental results show that it is an effective method to simulate large-scale crowds in real time, because the verification makes the simulation more reliable as well as making human behavior logical and the virtual scene realistic.

Recently, there is a strong interest in developing wireless sensor network (WSN) techniques and important applications for moving vehicles, to enable WSN communication between roadside and vehicles or between vehicles. Wireless vehicular sensor networks (VSNs) using all kinds of routing algorithms of low-energy efficiency has recently received considerable attention. Clustering algorithm has a significant impact on the operation of WSN. Effective clustering algorithm leads WSN to operate efficiently. Hierarchical clustering is a new clustering scheme in WSN. This study presents a novel vehicular clustering scheme integrating hierarchical clustering on the basis of classical routing algorithm. Simulation results show that the new scheme efficiently mitigates the hot spot problem in WSN and achieves much improvement in network lifetime and load balance compared to the old algorithm which is Direct, LEACH and DCHS.

P2P networks were factually overlay networks for distributed object store, search and sharing, and they were very popular. But P2P networks frequently lacked of dependability, some peer nodes could be easily lost. In this paper, we presented a small world architecture for P2P networks for information discovery, peer nodes freely linked to each other in inter-groups and not every peer node needed to be connected to remote groups and also could easily find the information in remote peer nodes through some leader peer nodes. It reduced the average distance and the lost of information. From our analysis and simulation, the small world architecture for p2p networks had the same characters as small world networks, and could achieve good performance in both static and dynamic environments.

Peer-to-Peer systems depend on effective techniques to find and retrieve data; however, current techniques used in existing unstructured P2P system are often very inefficient because of the existence of large number of redundant messages. In this paper, we analyze the reason of engendering redundant data packet and put forward the Condensing Forward-List algorithm to reduce redundancy. Through experiments we find that it has good results. In addition, we design our algorithm to be simple, as a module that can be easily incorporated into existing unstructured P2P systems for immediate impact.

In this letter, a new threshold algorithm based on wavelet analysis is applied to smooth noise for a nonlinear time series. By detailing the signals decomposed onto different scales, we smooth the details by using the updated thresholds to different characters of a noisy nonlinear signal. This method is an improvement of Donoho's wavelet methods to nonlinear signals. The approach has been successfully applied to smoothing the noisy chaotic time series generated by the Lorenz system as well as the observed annual runoff of Yellow River. For the nonlinear dynamical system, an attempt is made to analyze the noise reduced data by using multiresolution analysis, i.e., the false nearest neighbors, correlation integral, and autocorrelation function, to verify the proposed noise smoothing algorithm

In this paper, an intelligent vehicle monitoring and management system (IVMMS) based on the multi-net is designed. First, its architecture and functions are introduced. It uses many technologies fusing GPS, GPRS/CDMA, GIS, RS and Internet, and is composed mainly by two major parts: the Mobile Terminal and the Monitoring Center. Especially, GPRS/CDMA technology is the reliable technical support for wireless communication smooth transition from the 2.5G to the 3G; then, the principles and the key technologies of Mobile Terminal and Monitoring Center are discussed respectively in detail, and figures of their structures are also shown below; finally, a novel vehicle scheduling model based on ant algorithms are proposed and the course of scheduling tasks is also introduced. It is indicated that, the vehicles scheduling efficiency is enhanced greatly. The system not only can be used in the vehicles scheduling, but also in the vessel and other fields, and the solid technical support will be provided for the ITS research

A novel model has been proposed in this paper, it considers a pair of clients as the smallest gene, which was assigned secretion respectively based on proper modification of ant algorithm. We transformed the problem of client selecting server to that of server selecting client. And we adopted GT-ITM as Internet topology generator to generate transit-stub model topology for simulation. In the case of large-scale network topology, the simulation results show that the modified ant algorithm performs better than other heuristic algorithms such as the widest path and the optimized widest path ones.