Information Mining Research Articles

Attention-Driven Memory Network for Online Visual Tracking.

A memory mechanism has attracted growing popularity in tracking tasks due to the ability of learning long-term-dependent information. However, it is very challenging for existing memory modules to provide the intrinsic attribute information of the target to the tracker in complex scenes. In this article, by considering the biological visual memory mechanisms, we propose the novel online tracking method via an attention-driven memory network, which can mine discriminative memory information and enhance the robustness and reliability of the tracker. First, to reinforce effectiveness of memory content, we design a novel attention-driven memory network. In the network, the long memory module gains property-level memory information by focusing on the state of the target at both the channel and spatial levels. Meanwhile, in reciprocity, we add a short-term memory module to maintain good adaptability when confronting drastic deformation of the target. The attention-driven memory network can adaptively adjust the contribution of short-term and long-term memories to tracking results under the weighted gradient harmonized loss. On this basis, to avoid model performance degradation, an online memory updater (MU) is further proposed. It is designed to mining for target information in tracking results through the Mixer layer and the online head network together. By evaluating the confidence of the tracking results, the memory updater can accurately judge the time of updating the model, which guarantees the effectiveness of online memory updates. Finally, the proposed method performs favorably and has been extensively validated on several benchmark datasets, including object tracking benchmark-50/100 (OTB-50/100), temple color-128 (TC-128), unmanned aerial vehicles-123 (UAV-123), generic object tracking -10k (GOT-10k), visual object tracking-2016 (VOT-2016), and VOT-2018 against several advanced methods.

A unified framework of community hiding using symmetric nonnegative matrix factorization

Community detection can help us to deeply understand community structures and reveal potential social relationships among members. However, as people's concerns over the excessive mining of personal information have grown, the idea of community hiding has been proposed for privacy protection. Most existing community hiding methods based on heuristic approaches and genetic algorithms ignore the generative process of the network and cannot provide a better explanation of the rationality of the hiding mechanism. In addition, they are not simultaneously applicable to the global community, target community, or target nodes. In this study, we address the community hiding problem on three scales: global community hiding (macroscopic), target community hiding (mesoscopic), and target node hiding (microscopic). We propose a unified community hiding framework (CH-SNMF) that can be applied to all three scales. The basic idea is to use symmetric nonnegative matrix factorization to describe the network generative mechanism. It has a potential clustering capability that can mine key links and link sets during the network generation process. Therefore, they can be used to disrupt community structures with minimal perturbation budgets. The experimental results show that CH-SNMF outperforms many advanced baseline methods and effectively protects organizational and individual privacy.

CDI-NSTSEG: A clinical diagnosis-inspired effective and efficient framework for non-salient small tumor segmentation.

To accurately segment various clinical lesions from computed tomography(CT) images is a critical task for the diagnosis and treatment of many diseases. However, current segmentation frameworks are tailored to specific diseases, and limited frameworks can detect and segment different types of lesions. Besides, it is another challenging problem for current segmentation frameworks to segment visually inconspicuous and small-scale tumors (such as small intestinal stromal tumors and pancreatic tumors). Our proposed framework, CDI-NSTSEG, efficiently segments small non-salient tumors using multi-scale visual information and non-local target mining. CDI-NSTSEG follows the diagnostic process of clinicians, including preliminary screening, localization, refinement, and segmentation. Specifically, we first explore to extract the unique features at three different scales (1×, 0.5×, and 1.5×) based on the scale space theory. Our proposed scale fusion module (SFM) hierarchically fuses features to obtain a comprehensive representation, similar to preliminary screening in clinical diagnosis. The global localization module (GLM) is designed with a non-local attention mechanism. It captures the long-range semantic dependencies of channels and spatial locations from the fused features. GLM enables us to locate the tumor from a global perspective and output the initial prediction results. Finally, we design the layer focusing module (LFM) to gradually refine the initial results. LFM mainly conducts context exploration based on foreground and background features, focuses on suspicious areas layer-by-layer, and performs element-by-element addition and subtraction to eliminate errors. Our framework achieves state-of-the-art segmentation performance on small intestinal stromal tumor and pancreatic tumor datasets. CDI-NSTSEG outperforms the best comparison segmentation method by 7.38% Dice on small intestinal stromal tumors.

Research on the Assessment Technology of Land Available for PV

Based on the high-resolution satellite image data, the information mining technology of the available surface elements of PV is studied, and the investigation of the available surface elements of PV in 98 counties and cities of South Hebei grid is realized. Based on the large-scale and high-resolution remote sensing data obtained by multi-source remote sensing data fusion technology, the depth-learning-based surface feature recognition technology for photovoltaic development is studied. Based on the method of automatic identification and artificial combination of depth-learning, it can identify the available ground elements (roof, water surface, road surface, dry beach, etc.), the available surface elements of PV in 98 counties and cities of Hebei South Grid were obtained. From the overall point of view, the photovoltaic land, the building occupies the main position, in the four cities are relatively high, are in the 6% ~ 15%

The Construction of Digital Management Platform for Civic and Political Education for Future College Education and Its Intelligent Teaching Practice

Abstract Civic education in colleges and universities is facing the transformation of digital management mode, and this paper proposes to build a whole-process autonomous multi-dimensional fusion platform for the implementation and management of civic education in colleges and universities. The platform takes the big data analysis layer, object application layer and service management layer as the overall structure, builds the dynamic database of the Civic and Political Education program, and superimposes the tripartite comprehensive evaluation database. This paper improves the Apriori algorithm for association rules and applies the improved algorithm to the management platform for information mining. Intelligent teaching practices are designed based on the digital management platform, and their teaching effectiveness is analyzed. The performance of the Apriori algorithm before and after optimization is compared, and with the optimized algorithm, the execution efficiency is improved by about 10% to 15%. Students using the Civics education platform showed significant differences at the 1% level in all three dimensions of cognitive load, learning motivation, and mind-flow experience compared to students in the traditional teaching mode.

SIM-OFE: Structure Information Mining and Object-Aware Feature Enhancement for Fine-Grained Visual Categorization.

Fine-grained visual categorization (FGVC) aims to distinguish visual objects from multiple subcategories of the coarse-grained category. Subtle inter-class differences among various subcategories make the FGVC task more challenging. Existing methods primarily focus on learning salient visual patterns while ignoring how to capture the object's internal structure, causing difficulty in obtaining complete discriminative regions within the object to limit FGVC performance. To address the above issue, we propose a Structure Information Mining and Object-aware Feature Enhancement (SIM-OFE) method for fine-grained visual categorization, which explores the visual object's internal structure composition and appearance traits. Concretely, we first propose a simple yet effective hybrid perception attention module for locating visual objects based on global-scope and local-scope significance analyses. Then, a structure information mining module is proposed to model the distribution and context relation of critical regions within the object, highlighting the whole object and discriminative regions for distinguishing subtle differences. Finally, an object-aware feature enhancement module is proposed to combine global-scope and local-scope discriminative features in an attentive coupling way for powerful visual representations in fine-grained recognition. Extensive experiments on three FGVC benchmark datasets demonstrate that our proposed SIM-OFE method can achieve state-of-the-art performance.

The Current Situation of the Implementation of College Admission System and the Way of Reform in the Digital Age

Abstract With the progress of science and technology and social changes, higher education in China is experiencing unprecedented challenges and opportunities. The digital era has not only changed teaching methods but has also profoundly affected the enrollment system of colleges and universities. The study uses a decision tree-based enrollment information mining algorithm and a gray prediction model to construct a data mining model of the current status of enrollment system implementation. Through the data mining model, the data mining and analysis of the student source status of college enrollment are used to propose targeted reform proposals. The number of female students in School Z has been increasing each year, while the number of male students has decreased significantly. The number of students with grades A and B is much lower than that of students with grades B and C. Among the special types of enrollment sources, the enrollment of national defense students and high-level athletes has decreased year by year, while the enrollment of the poverty special program has shown a yearly increasing trend. During the four years, the enrollment of national defense students was 61, 54, 46, and 39, and the enrollment of high-level athletes was 15, 14, 12, and 10. The enrollment in special programs for people experiencing poverty increased from 9 to 47 during the four years. The reform of the college enrollment system should focus on reforming the content of the examination, and government departments to do a good job of coordinating planning, improving laws and regulations, and putting an end to malpractice and irregularities.

Exploring Japanese Values Education from a Cultural Perspective

Abstract Cultural patterns, through the process of socialization, determine the national identity of a nation and influence the way of thinking, value orientation, and behavior of individuals. In this paper, we analyze Japanese values education from the dimensions of “group”, “interpersonal”, and “self”. The information mining algorithm based on web logs is used to establish a correlation matrix of Japanese learners’ values, and the values of Japanese learners are clustered according to the similarity of access subgraphs between the correlation matrices. During the period, the ID3 algorithm is used under the decision tree to eliminate the gap in metric size between clustering subgroups and achieve spatial division of learners’ value types. The three critical dimensions of Japanese values education and their sub-dimensions were empirically analyzed, and the F-values of the three dimensions of values for students of different majors were 0.265, 0.431, and 0.078, respectively, with P-values of 0.05 or higher, so there was no significant difference in the perception of values among students of different majors. In the value analysis of “self” sub-dimension, the descriptive statistics mean prestige, economy, and society values are 4.3592, 4.249, and 3.8696 respectively, which are all above 3. The value of education in Japanese universities is practical.

The Path of Digital Protection and Innovative Development of Rural Traditional Cultural Resources Supported by Intelligent Information

Abstract The digitized quality of rural traditional cultural resources is relatively low, and there are problems such as heterogeneity and incompleteness in the resource data, resulting in the limitation of related cultural data information mining and the inability to realize deep development and innovation. Therefore, this paper combines the fully connected neural network and fuzzy C-mean clustering algorithm to construct a cultural digital resource clustering model, and based on the clustering results combined with CR-LDA and collaborative filtering algorithm to achieve personalized recommendation of rural traditional cultural digital resources. The experimental results show that the clustering model combining a fully connected neural network and a fuzzy C-mean clustering algorithm has a better clustering effect than the other three clustering models, and it also shows good robustness and stability. In addition, although the collaborative filtering model combining the CR-LDA algorithm has a slight increase in runtime compared to the LDA model runtime, the classification accuracy is significantly improved. It thus can provide platform users with practical and reliable cultural resource recommendations. Most users indicated in the survey that they agreed with the results of the model’s personalized cultural digital resource recommendations.

Algorithm selection model based on fuzzy multi-criteria decision in big data information mining

Algorithm selection model based on fuzzy multi-criteria decision in big data information mining

Research on FinTech Promoting Financial Innovation and Growth in Emerging Markets

With the rapid development of science and technology, financial technology has become an important force driving global financial innovation and growth. Especially in emerging markets, the application of FinTech enhances financial services' efficiency, promotes financial inclusion, and injects new vitality into economic growth. This article explores the concept and components of fintech and describes its role in emerging markets. The article begins by unpacking the definition and functional scope of FinTech and provides a compendium of its information categorization. It then delves into the specific steps of FinTech in blockchain implementation, encompassing the construction of knowledge architectures and technological processes, highlighting the mechanisms of information mining, integration, and access. Taking the case of developing countries in particular, the article reviews the positive contribution of the practical application of blockchain in conjunction with fintech to financial innovation in these countries in terms of expanding financial penetration, enhancing the effectiveness and security of transactions, and stimulating new service models. In addition, the challenges faced by these countries in implementing fintech strategies are also analyzed. Overall, the analysis in this paper provides insights into how FinTech can support financial development and economic growth in emerging markets.

IoT devices with data analytics capabilities Using machine learning algorithms for intelligent decision making: a review of patents and the cited academic literature

Innovation in IoT data analytics is essential for social and economic advancement as well as for opening up new business prospects. IoT data analytics applications have garnered a lot of attention lately for information mining, knowledge extraction, and prediction/inference making. Another field of study that has been effectively used to address a variety of networking issues, including resource allocation, routing, traffic engineering, and security, is machine learning. The use of machine learning (ML)-based techniques to enhance different Internet of Things applications has increased recently. Despite a wealth of research on machine learning and IoT data analytics, there is a dearth of studies that only address the development of ML-based methods for IoT data analysis. The present study examines the patenting practices of various international jurisdictions in the domain of IoT data analytics, in addition to the academically cited literature. Between 2000 and 2023, we gathered 24,931 patent applications, and 13,432 scholarly works were cited by the patents. Our research details the trends in the development of IoT data analytics technologies and the relationship between patenting activity and the referenced scientific literature. Additionally, it examines and displays the social networks found in scientific publications and patents. As a result, it discloses the patenting practices of international jurisdictions concerning IoT data analytics technologies, the degree to which different agents such as Lens Id and Applicants interact within social networks, and the connection between patents and science. According to this study, information retrieval, database structures, and file system structures make up the majority of the IPC categories for filed IoT data analytics patent applications. Chinese businesses and individuals make up the bulk of the patent Lens Id and Applicants. Computer science and medicine are scientific fields that are more strongly connected within the network of co-fields. The relationship between scientific works and inventions is not very strong.

Ultra-short-term forecasting model of power load based on fusion of power spectral density and Morlet wavelet.

An accurate ultra-short-term time series prediction of a power load is an important guarantee for power dispatching and the safe operation of power systems. Problems of the current ultra-short-term time series prediction algorithms include low prediction accuracy, difficulty capturing the local mutation features, poor stability, and others. From the perspective of series decomposition, a multi-scale sequence decomposition model (TFDNet) based on power spectral density and the Morlet wavelet transform is proposed that combines the multidimensional correlation feature fusion strategy in the time and frequency domains. By introducing the time-frequency energy selection module, the "prior knowledge" guidance module, and the sequence denoising decomposition module, the model not only effectively delineates the global trend and local seasonal features, completes the in-depth information mining of the smooth trend and fluctuating seasonal features, but more importantly, realizes the accurate capture of the local mutation seasonal features. Finally, on the premise of improving the forecasting accuracy, single-point load forecasting and quantile probabilistic load forecasting for ultra-short-term load forecasting are realized. Through the experiments conducted on three public datasets and one private dataset, the TFDNet model reduces the mean square error (MSE) and mean absolute error (MAE) by 19.80 and 11.20% on average, respectively, as compared with the benchmark method. These results indicate the potential applications of the TFDNet model.

RETRACTION: College Sports Decision‐Making Algorithm Based on Machine Few‐Shot Learning and Health Information Mining Technology

RETRACTION: College Sports Decision‐Making Algorithm Based on Machine Few‐Shot Learning and Health Information Mining Technology

Quality Innovation Cultivation Strategy for College Students in the Internet Era Oriented on the Cultivation of Innovative Ability

Abstract Addressing the imperative of cultivating innovation and learning quality in 21st-century college education, this research proposes a strategic CTDE model to enhance college students’ innovative capacities. By implementing a personalized information mining technique, we have established a sophisticated user profile model that strategically distributes learning resources geared towards innovation. The methodology integrates factor analysis with K-means clustering for a customized learning experience. A targeted survey reveals notable achievements: a standout innovation ability score of 3.92 for an individual student and a class-wide enhancement, with improvements ranging from 14% to 21% after detailed work evaluations. These findings affirm the CTDE model’s efficacy in fostering student innovation and quality learning.

Research on Short Text Information Mining and Classification Methods for Social Media

Research on Short Text Information Mining and Classification Methods for Social Media

Technology for Public Service Translators and Interpreters in Spain: Enhancing Employability Through Training

Despite rapid technological advances and how they affect public service interpreting and translation (psit), as a subfield of translation and interpretation, very few studies focus on how technological competence affects or facilitates employability in psit. This descriptive study carried out among graduates of the University of Alcalá’s psit programme intends to fill that gap by examining the usefulness of its technology-related training. This descriptive case study sought (1) to establish which technological tools graduates had to use in their jobs and the technological requirements in the labour market for psit; (2) to establish potential differences between the T&I and the psit sectors regarding technological requirements or needs; and (3) to assess how useful the training received was. Findings show similarities in the use of sources and tools in both T&I and psit, but also differences in information mining sources, highlighting varied needs. Moreover, although computer-assisted-translation tools and machine translation are widely demanded nowadays, their use by graduates was shown to be lower than expected. This study gives critical insights for researchers, trainers, and programme designers to ensure that their syllabi encompass comprehensive content tailored to both in-house and freelance translators to increase their employability.

Practical Application of Professional Group Curriculum Resource Library in Art Design Teaching

Abstract This paper studies the relevant functions and contents of the professional group course resource library and constructs the architecture of the professional group course resource library. In the specific construction, the Lian Li VSM model and LDA topic model establish the domain ontology of the resource library, retrieve the content of educational resources from the resource document based on the retrieval request for resource filtering, extraction, and integration, and through the information mining algorithm to browse the degree of interest in the learning resources to calculate, to achieve the personalized recommendation of educational resources. Finally, the satisfaction of teachers and students with the professional group course resource library was analyzed respectively, and the effect of the application of the professional group course resource library in art and design teaching practice was studied using t-test and regression analysis. The results show that the regression coefficient values of the professional group course resource library on teachers’ concept of teaching, teaching content, and teaching effect are 0.148, 0.145, and 0.059, respectively. The t-values are 2.342, 2.644, and 1.212, respectively, with p<0.05, and the professional group course resource library has a significant positive effect on the teaching of art design. This study provides a new direction for the development of art design teaching, and it offers important reference content for universities to build a professional group course resource library.

Knowledge Graph Contrastive Learning Based on Relation-Symmetrical Structure

Knowledge graph embedding (KGE) aims at learning powerful representations to benefit various artificial intelligence applications. Meanwhile, contrastive learning has been widely leveraged in graph learning as an effective mechanism to enhance the discriminative capacity of the learned representations. However, the complex structures of KG make it hard to construct appropriate contrastive pairs. Only a few attempts have integrated contrastive learning strategies with KGE. But, most of them rely on language models ( e.g., Bert) for contrastive pair construction instead of fully mining information underlying the graph structure, hindering expressive ability. Surprisingly, we find that the entities within a relational symmetrical structure are usually similar and correlated. To this end, we propose a knowledge graph contrastive learning framework based on relation-symmetrical structure, KGE-SymCL, which mines symmetrical structure information in KGs to enhance the discriminative ability of KGE models. Concretely, a plug-and-play approach is proposed by taking entities in the relation-symmetrical positions as positive pairs. Besides, a self-supervised alignment loss is designed to pull together positive pairs. Experimental results on link prediction and entity classification datasets demonstrate that our KGE-SymCL can be easily adopted to various KGE models for performance improvements. Moreover, extensive experiments show that our model could outperform other state-of-the-art baselines.

Scrutinizing the most prominent competencies for a well-rounded translator from Iranian publishers’ perspective

The present study aims to examine the competencies that Iranian managers of publishing companies consider when hiring translators. To achieve this, a Likert scale questionnaire with 16 items was designed to gather opinions from managers in publishing companies in Iran about the competencies necessary for a well-rounded translator A chi-square test was conducted to determine if there is a significant relationship between each competency and the publishers. As the results showed, there is a significant relationship between the publishers and translation service provision and language competencies. However, there is no significant relationship between the publishers and intercultural, information mining, thematic, and technological competencies. The results indicated that the most important competencies for enhancing a translator's productivity are technological, language, and translation service provision competencies. Additionally, the present study provides some pedagogical implications that can be beneficial to translation students and those involved in the translation sector, such as translation offices. Keywords: Competence; translator; publishing company; well-rounded translator