Information Mining Research Articles

Does corporate digital transformation affect investor trading behaviour? – A perspective based on investor divergence

ABSTRACT This paper takes A-share listed companies during 2010–2021 as the research object, and finds that the digital transformation (DT) of enterprises affects investors’ trading behaviours; more specifically, the digital transformation of enterprises increases investor divergence. This paper also finds that external governance factors mitigate the impact of digital transformation on investor divergence; specifically, analyst tracking mitigates the impact of digital transformation on investor divergence by alleviating information asymmetry. As more professional investors, institutional investors have stronger information mining and analysis capabilities, so the impact of digital transformation on investor divergence could also be mitigated with the increase in the proportion of institutional investors. The intermediary mechanism test suggests that corporate digital transformation triggers investor divergence by increasing surplus volatility. Further research finds that, firstly, different approaches to digital transformation have different impacts, with digital transformation through self-developed technology being more likely to trigger investor divergence. Secondly, different firm natures have different impacts, with the digital transformation of non-high-tech firms having relatively greater impacts on investor divergence. Finally, the digital transformation of non-state-owned enterprises has greater impact on investor analysis.

Multi-attribute decision-making analysis based on the bipolar N-soft PROMETHEE method

The multi-attribute decision-making (MADM) methods can deeply mine hidden information in data and make a more reliable decision with actual needs and human cognition. For this reason, this paper proposes the bipolar N-soft PROMETHEE (preference ranking organization method for enrichment of evaluation) method. The method fully embodies the advantages of the PROMETHEE method, which can limit the unconditional compensation between attribute values and effectively reflect the priority between attribute values. Further, by introducing an attribute threshold to filter research objects, the proposed method not only dramatically reduces the amount of computation but also considers the impact of the size of the attribute value itself on decision-making. Secondly, the paper proposes the concepts of attribute praise, attribute popularity, total praise, and total popularity for the first time, fully mining information from bipolar N-soft sets, which can effectively handle situations where attribute values have different orders of magnitude. In addition, this paper presents the decision-making process of the new method, closely integrating theoretical models with real life. Finally, this paper analyses and compares the proposed method with the existing ones, further verifying the effectiveness and flexibility of the proposed method.

Chemical space deconstruction-based dynamic model ensemble architecture for molecular property prediction

Green solvents, catalysts, functional materials, drugs, and other chemical products now have a quick engine for design thanks to machine learning (ML) based prediction of molecular properties. However, the accuracy and stability of ML-based models can be impeded by poor data quality, which is rarely studied in chemical product discovery and design. Inspired by the dynamic ensemble selection (DES), an improved DES based on chemical space deconstruction is proposed in this work to accommodate the prediction task of molecular properties. We innovatively developed a chemical space representation and deconstruction model based on a self-organizing mapping (SOM) neural network, facilitating the rapid implementation of the improved DES on molecular samples. Consequently, a novel dynamic model ensemble architecture (SOM-DES) is proposed as a model enhancement technology to build a more accurate and stable ensemble model, aiming to improve the predictive performance on the chemical subspace within poor-quality data. To achieve the architecture, a supervised dimensionality reduction algorithm has been improved to enhance the deep mining of molecular feature information for DES optimization. Additionally, a novel resampling strategy based on the combination of the geometric synthetic minority oversampling technique (G-SMOTE) algorithm and chemical space deconstruction, as a data augmentation technology, has been proposed for mitigating the disadvantage of unbalanced data during DES training. The prediction task for enthalpy of formation of the ideal gas is applied as a case study to demonstrate the superiority of the proposed SOM-DES. The results indicate that the proposed SOM-DES (R2 = 0.9731, RMSE = 55.4639) outperforms the traditional static ensemble strategy (SES, R2 = 0.9552, RMSE = 71.5045) in terms of global chemical spatial precision. More importantly, for chemical subspaces that are difficult to predict due to low data quality, SOM-DES shows a significant reduction in prediction errors compared to SES.

Salient object detection via multi-grained refinement polygon topology positive feedback

Despite significant progress in current salient object detection (SOD) tasks, they are limited by overlapping regions, broken connections, voids and neglecting explicit exploration of background regions. In this paper, we propose a multi-grained refinement polygonal topology network (MPT) that explores two important components of background mining information and the impact of topological segmentation errors. (1) Unlike existing models that focus on inter-image relationships, we introduce a multi-grained refinement module to discriminate between saliency objects and background information, and introduce inter-image relationships into the pixel-by-pixel segmentation features to enhance the discrimination of segmentation features, and this Multi-grained refinement is the basis for mining saliency objects. (2) Based on the multi-grained refinement features, we introduce a polygonal topology-aware module and add topological constraints as penalty terms to regularize the focus loss to effectively resolve topological errors to enhance the quality of the performance of salient object detection. Meanwhile, we introduce a measurements-based on positive feedback model to integrate the decision fusion of multi-model perception results to obtain higher accuracy of saliency prediction while ensuring that the prediction results will not deteriorate. Extensive experiments on six benchmark and extended datasets demonstrate that our proposed MPTNet exhibits excellent performance both qualitatively and quantitatively and outperforms state-of-the-art saliency detectors.

A Review on The Spatial Mining

Public and confidential associations have heritage or then again functional spatial information bases or non-spatial information bases, which are likewise some ways or another connected to a spatial data set or a spatial significance. Notwithstanding mission related information bases, these associations either have or access a few information bases containing like registration, financial, security, picture, interactive media, factual data for arranging, insight, choice and strategy making. The lengthy size of these informational indexes makes it hard to look for significant examples or connections among information. Spatial information mining is the course offending fascinating and already obscure, however possibly valuable examples from huge spatial datasets. This paper centers around Procedures and the special highlights that recognize spatial information mining from old style information mining, at long last it recognizes areas of spatial information mining where further examination is required.

Prior-knowledge-guided mode filtering network for interpretable equipment intelligent diagnosis under varying speed conditions

The speed variation poses great hardships to the intelligent fault diagnosis of mechanical equipment. Existing solutions rarely consider the interpretable representation of fault information, and still suffer from the “black box” issue that weakens their own practicability and credibility. Motivated by these issues, this study mathematically derives the modal response model of fault-impulsive signals of rotating machinery under variable speed conditions. On this foundation, an interpretable architecture collaborating signal processing with deep learning—prior-knowledge-guided mode filtering network (PKG-MFNet) is proposed, which consists of three sub-structures: mode filtering layer, prior knowledge pooling layer and classifier. In the mode filtering layer, multiple FIR filtering kernels are first constructed by an explainable speed fusion strategy. Each filtering kernel has a center frequency and a bandwidth coefficient fitted from the speed, which is used to extract fault-sensitive modes under varying speed conditions as the explainable feature representations of fault information. Subsequently, the extracted modes are pooled into 12 modal prior indicators (MPIs) that represent health status information in the prior knowledge pooling layer. Finally, the classifier employs two fully-connected layers to make the final decision. Different from the conventional interpretable network for speed information characterization, the speed information is innovatively fused into a novel mechanism framework for sensitive information mining with rigorous theoretical support. Extensive experiments are conducted to verify the superiority of the proposed method over six state-of-the-art methods. Particularly, the visualization analysis not only demonstrates the mode filtering capacity of FIR filtering kernels under variable speed conditions, but also interprets the guiding significance of MPIs for the final decision.

Joint contrastive learning and belief rule base for named entity recognition in cybersecurity

Named Entity Recognition (NER) in cybersecurity is crucial for mining information during cybersecurity incidents. Current methods rely on pre-trained models for rich semantic text embeddings, but the challenge of anisotropy may affect subsequent encoding quality. Additionally, existing models may struggle with noise detection. To address these issues, we propose JCLB, a novel model that Joins Contrastive Learning and Belief rule base for NER in cybersecurity. JCLB utilizes contrastive learning to enhance similarity in the vector space between token sequence representations of entities in the same category. A Belief Rule Base (BRB) is developed using regexes to ensure accurate entity identification, particularly for fixed-format phrases lacking semantics. Moreover, a Distributed Constraint Covariance Matrix Adaptation Evolution Strategy (D-CMA-ES) algorithm is introduced for BRB parameter optimization. Experimental results demonstrate that JCLB, with the D-CMA-ES algorithm, significantly improves NER accuracy in cybersecurity.

DEFM: Delay-embedding-based forecast machine for time series forecasting by spatiotemporal information transformation.

Making accurate forecasts for a complex system is a challenge in various practical applications. The major difficulty in solving such a problem concerns nonlinear spatiotemporal dynamics with time-varying characteristics. Takens' delay embedding theory provides a way to transform high-dimensional spatial information into temporal information. In this work, by combining delay embedding theory and deep learning techniques, we propose a novel framework, delay-embedding-based forecast Machine (DEFM), to predict the future values of a target variable in a self-supervised and multistep-ahead manner based on high-dimensional observations. With a three-module spatiotemporal architecture, the DEFM leverages deep neural networks to effectively extract both the spatially and temporally associated information from the observed time series even with time-varying parameters or additive noise. The DEFM can accurately predict future information by transforming spatiotemporal information to the delay embeddings of a target variable. The efficacy and precision of the DEFM are substantiated through applications in three spatiotemporally chaotic systems: a 90-dimensional (90D) coupled Lorenz system, the Lorenz 96 system, and the Kuramoto-Sivashinsky equation with inhomogeneity. Additionally, the performance of the DEFM is evaluated on six real-world datasets spanning various fields. Comparative experiments with five prediction methods illustrate the superiority and robustness of the DEFM and show the great potential of the DEFM in temporal information mining and forecasting.

Short‐term electric load forecasting based on empirical wavelet transform and temporal convolutional network

AbstractShort‐term load forecasting is the basis of power system operation and analysis and is of great significance for the stable operation of power systems. To solve the problems of insufficient mining of the intrinsic information of load data, randomness, and non‐linearity, and to improve the accuracy of load prediction, the authors propose a short‐term power load prediction model based on empirical wavelet transform (EWT) decomposition and the temporal convolutional network (TCN). First, the Pearson coefficient is used to eliminate the less relevant influencing factors to reduce the complexity of the model. Then, the EWT algorithm is used to decompose the original load signal to fully exploit the load data time domain and frequency domain information, while solving the problems of non‐linearity and randomness. Finally, the decomposed subsequences are input to the TCN network for prediction superposition to obtain the final results. The experimental results show that, compared with the single models TCN, gated recurrent units (GRU), and long short‐term memory (LSTM), and the hybrid models EWT‐GRU, EWT‐LSTM, and VMD‐TCN, the R2 of the short‐term power load forecasting model based on EWT‐TCN is improved by 0.2099%, 0.2519%, 0.3453%, 0.0334%, 0.1766%, and 0.1228%, respectively.

NC process information mining based optimization method of roughing tool sequence selection for pocket features

The appropriate and intelligent selection of roughing tool sequence for pocket features is essential to improve the efficiency of NC machining. However, there exist few researches exploring how to discover and utilize the valuable NC process information imbedded in 3D CAD models. In this paper, a NC process information mining based optimization method of roughing tool sequence selection for pocket features is presented. Firstly, the medial axis transform (MAT) is introduced to represent the tool paths of a pocket feature, and corresponding parameters of MAT are calculated. Secondly, considering the restrictions of tool movements during machining, the mapping mechanism between geometry and NC process is elaborated based on MAT to reveal the association of 3D CAD models and NC machining. The deeper information for NC process planning is mined to reflect the machining procedure feasibly. Then, the multi-objective optimization model is constructed by considering material removal amount and cutting consistency synthetically. Moreover, the precedence and distances between roughing tools are formulated in a Candidate Tools Graph (CTG). Finally, a hybrid ant colony algorithm (ACA) and simulated annealing (SA) approach based on CTG is proposed to generate the global optimal roughing tool sequence. In the experiment, various pocket features are conducted to illustrate the application effectiveness of the proposed method. The experimental results show that our method can achieve highly satisfactory results and outperforms other approaches.

Identifying Novel Coronavirus Pneumonia With CT Images: A Deep Learning Approach With Detail Upsampling and Attention Guidance

To construct a deep learning-based target detection method to help radiologists perform rapid diagnosis of lesions in the CT images of patients with novel coronavirus pneumonia (NCP) by restoring detailed information and mining local information. We present a deep learning approach that integrates detail upsampling and attention guidance. A linear upsampling algorithm based on bicubic interpolation algorithm was adopted to improve the restoration of detailed information within feature maps during the upsampling phase. Additionally, a visual attention mechanism based on vertical and horizontal spatial dimensions embedded in the feature extraction module to enhance the capability of the object detection algorithm to represent key information related to NCP lesions. Experimental results on the NCP dataset showed that the detection method based on the detail upsampling algorithm improved the recall rate by 1.07% compared with the baseline model, with the AP50 reaching 85.14%. After embedding the attention mechanism in the feature extraction module, 86.13% AP50, 73.92% recall, and 90.37% accuracy were achieved, which were better than those of the popular object detection models. The feature information mining of CT images based on deep learning can further improve the lesion detection ability. The proposed approach helps radiologists rapidly identify NCP lesions on CT images and provides an important clinical basis for early intervention and high-intensity monitoring of NCP patients.

Distributed wide-field electromagnetic method for coal mining goaf detection in a complex urban environment: A case study in Jinan, China

Urban expansion has resulted in many proposed projects located over coal mining zones, which has highlighted the importance of detecting the spatial scope and water abundance of goafs before the commencement of construction work. Although electromagnetic (EM) methods have proven effective for goaf detection, their applications in intensely noisy and urbanized environments remain limited. To address this challenge, we evaluate an investigation of a coal mining goaf in Jinan, China, using the distributed wide-field EM (DWFEM) method. A third-order [Formula: see text] sequence pseudorandom signal with 39 survey frequencies is transmitted to achieve long-time data acquisition at each station. Unlike the controlled-source audio-frequency magnetotellurics method, the DWFEM records only the electric field [Formula: see text] component. The synthetic model tests and field data demonstrate the consistency of the [Formula: see text] apparent resistivity and the Cagniard resistivity in the far field. The long-time acquisition and 1C recording greatly improve data quality and exploration efficiency. We also use an all-angle resistivity calculation formula and an electrode layout method parallel to the wire source to obtain electrical connections in different directions. The DWFEM inversion results are obtained using the 1D Gauss-Newton iterative method under a plane-wave assumption. By interpolating the data from different measurement stations, we image resistivity depth profiles and obtain 3D subsurface electrical data for the subsurface from 0 to 1000 m. We interpret the obtained profiles with geologic and mining information, revealing two significant water-enriched goaf areas. Validation is performed using seismic data and drill cores. The results significantly enhance our understanding of the characteristics of the coal mine under our project and highlight the applicability of the DWFEM for detecting goafs in complex urban environments.

Prediction of bitcoin stock price using feature subset optimization

In light of recent cryptocurrency value fluctuations, Bitcoin is gradually gaining recognition as an investment vehicle. Given the market's inherent volatility, accurate forecasting becomes crucial for making informed investment decisions. Notably, previous research has utilized machine learning methods to enhance the accuracy of Bitcoin price predictions. However, few studies have explored the potential of employing diverse modeling methods for sampling with varying data formats and dimensional characteristics. This study aims to identify the internal feature subset that yields the highest returns in forecasting Bitcoin's price. Specifically, Bitcoin's internal features were categorized into four groups: currency data, block details, mining information, and network difficulty. Subsequently, a long short-term memory (LSTM) artificial neural network was employed to predict the next day's Bitcoin closing price, utilizing various categorizations of feature subsets. The model underwent training using two and a half years of historical data for each feature. The findings revealed a mean absolute error rate of 6.38% when modeling with the block details category features. This enhanced performance primarily stemmed from the positive relationship between Bitcoin price and this data subset's low ambiguity. Experimental results underscored that, compared to other investigated feature subsets, the categorization of block detail features provided the most accurate Bitcoin price predictions, laying the foundation for future research in this domain.

MSDRA-NET: A MULTI-SCALE ATTENTION-GUIDED NETWORK FOR MAGNETIC RESONANCE IMAGE RESTORATION

The acquisition and transmission of magnetic resonance (MR) images are frequently affected by random noise pollution, which hampers the diagnosis of diseases by doctors or automated systems. Hence, the search for advanced denoising methods is of great research interest, particularly in magnetic resonance imaging (MRI) denoising models, which are based on deep learning networks and achieve satisfactory results. However, the mining of noisy contextual information and effective information-guided transfer are often neglected in the denoising process, which leads to poor extraction of information at different scales, and poor retention of details. This greatly hinders the further development of MR image denoising methods. Here, we propose a denoising method, MSDRA-Net, for the mining and exploitation of different hierarchical noise features and construct a multi-scale dilated residual (MSDR) structure to transfer and retain noise information at different levels across the layer. Next, a contextual guidance attention (CGA) module guides and transfers contextual information, utilizing the features learnt from different layers of the model as weights. A reconstruction refinement block (RRB) is utilized to construct clean images from the obtained noise bias and the given noisy images. Experiments on simulated and clinical MRI data validated the effectiveness of our method, which demonstrated a superior performance compared to several state-of-the-art methods.

Feature selection for classification with Spearman’s rank correlation coefficient-based self-information in divergence-based fuzzy rough sets

Feature selection facilitates uncertainty disposal and information mining, and it has received widespread research interests. Divergence-based fuzzy rough sets (Div-FRSs), a new kind of fuzzy rough sets, have been applied to feature selection and induced two efficient algorithms, FS-AFS and FS-RFS. Nevertheless, FS-AFS and FS-RFS still have advancement space, because the dependency functions only focus on lower approximation and ignore the uncertainty in upper approximation, which will certainly undermine the algorithmic evaluation effects. To this end, this paper introduces the upper approximation and fuses it with lower approximation via class-specific pattern and Spearman coefficient to construct a new information measurement for metric perfection, called Spearman-based self-information. Relying on this new measurement, a novel feature selection algorithm SPESI is established to improve FS-AFS and FS-RFS. At first, Spearman coefficient is introduced and upper approximation is defined. Second, class-driven precision and roughness are built by incorporating Spearman coefficient-based class-specific weight vectors with class-driven lower and upper approximations. Meanwhile, the granulation monotonicity of newly-defined measurements is also explored. Then, the core measurement Spearman-based self-information is firstly given and its feature significance motivates a feature selection algorithm SPESI with heuristic search. Finally, data experiments are implemented to validate the effectiveness of SPESI, and a conclusion can be drawn that SPESI outperforms FS-AFS and FS-RFS to acquire better classification performances with fewer feature numbers and less running time.

A person re‐identification method for sports event scenes incorporating textual information mining

AbstractPerson re‐identification represents a pivotal sub‐problem in image retrieval, boasting broad application prospects in fields such as intelligent security and video surveillance. However, most existing person re‐identification methods predominantly focus solely on visual features pertaining to the person targets, thereby disregarding some supporting information closely related to the scene context. In the context of athlete re‐identification during sports event scenes, the athlete bib number is fully considered, an important clue that can provide different athletes' identities, and the traditional visual features of the person and high‐level semantic information of the bib number text are fused. A multi‐source information mutual gain mechanism is designed to improve the accuracy of the person re‐identification task. In the existing only publicly available marathon bib number dataset RBNR, the recognition accuracy of this method is significantly superior to that of the existing person re‐identification method. In addition, this paper constructs and publishes an athlete re‐identification dataset (HNNU‐ReID8000) for mainstream sports events, and the mean average precision (mAP) value of this method reaches 96.1% on this dataset, significantly ahead of existing state‐of‐the‐art person re‐identification methods. The code and the HNNU‐ReID8000 dataset will be released at https://github.com/yanbin‐zhu/zyb_person‐reid.

Time series procession for monitoring land disturbance caused by surface coal mining in China

Surface mining has been subject to increased criticism and pressure due to its potential to cause environmental damage. China accounts for more than half of world coal consumption, and this continued demand for coal, combined with low costs, has accelerated surface coal mining worldwide. However, it isn't easy to understand the impact of surface mining in China. Therefore, combined with POI, the Exposed Coal Frequency Index (ECFI) was constructed without any mining information in China. A LandTrendr algorithm was used to identify past mining disturbances and reclamation events (1986–2021). While examining these events, surface destruction due to coal mining in China was revealed. Based on the results, (1) the detection accuracy of statistical surface mining sites by province reaches 91.8%, while the detection accuracy of disturbance and reclamation events exceeds 72.59 %. Also, by comparing the mine data, our results provide more accurate information regarding both time and spatial consistency. (2) 253.61 km2 of surface mining sites were identified in 14 provinces or autonomous regions during 1986–2021. Of these, Inner Mongolia, Ningxia, Shanxi and Xinjiang ranked in the top four occupying 89.0% of the total mining site. (3) China has cumulatively disturbed 545.84 km2 and reclaimed 169.41 km2 including more comprehensive human activities. In the last 12 years, large-scale mining and reclamation have accounted for 51.63% and 75.17% of the cumulative area, respectively. (4) Generally, reclamation in China can be completed within four years. In contrast, reclamation time intervals and the proportion of reclamation varied widely between mining areas. Clearly, this study provides the most accurate data on surface coal mining disturbances in China, which will be beneficial for future studies in spatial geography related to mining. It also includes more policies and management creation for mines.

Enhanced computer network security assessment through employing an integrated LogTODIM-TOPSIS technique under interval neutrosophic sets

In the context of the development of the new era, computer network technology has become an indispensable and important technological means in people’s daily work and life. Through network technology, information resources can be collected, integrated, processed, and applied, thereby improving information analysis and mining capabilities, constructing big data environments for various industries, providing convenient and fast intelligent information services, and promoting social transformation and development. However, in practical development, network security issues seriously affect information security and social stability, and computer viruses and hackers pose a huge threat to computer systems. The computer network security evaluation is the MAGDM problems. Recently, the Logarithmic TODIM (LogTODIM) and TOPSIS technique has been utilized to cope with MAGDM issues. The interval neutrosophic sets (INSs) are utilized as a technique for characterizing uncertain information during the computer network security evaluation. In this paper, the interval neutrosophic number Logarithmic TODIM-TOPSIS (INN-LogTODIM-TOPSIS) technique is conducted to solve the MAGDM under INSs. Finally, a numerical case study for computer network security evaluation is utilized to validate the proposed technique. The prime contributions of this paper are put forward: (1) The entropy technique based on score values and accuracy value are conducted to obtain weight information under INSs; (2) an integrated INN-LogTODIM-TOPSIS technique is conducted to put forward the MAGDM issue; (3) An illustrative example for computer network security evaluation has been accomplished to put forward the INN-LogTODIM-TOPSIS technique.

Multivariate statistical approach in food and pharmaceutical quality control

IR spectra contain chemical information of matter and can be acquired from raw/untreated samples. The spectra are, however, complicated to interpret and could not be used directly for both qualitative and quantitative purposes. In this research a statistical approach namely, multivariate data analysis (MVDA) or chemometrics was employed for mining information related to chemical compositions from spectroscopic data. Two examples are used to illustrate the potential of this approach, one is edible oil (using benchtop FT-IR), and pharmaceuticals (using handheld NIR). Olive oil was differentiated from adulterants (sesame, sunflower, palm oil) in PCA, and the content of olive oil was successfully determined by the PLS model the error of olive oil content < 5%. Norfloxacin content in lab-scale powder formulation yield the auspicious results with the error < 6%. The results proved the developed techniques are promising for rapid analysis at significantly lower costs.

Dynamic Modeling Framework Based on Automatic Identification of Operating Conditions for Sintering Carbon Consumption Prediction

In iron and steel industry, sintering process requires huge carbon consumption. Achieving accurate and dynamic prediction of carbon consumption in this process is of evident significance to protect the environment and raise the economic efficiency of iron and steel industry. This paper develops an original dynamic modeling framework including automatic identification of operating conditions, modeling in different conditions, and dynamic prediction model of sintering carbon consumption. Firstly, an automatic kernel-based fuzzy C-means algorithm is presented for automatic identification of operating conditions. Dynamic relationships between the inputs and output of the model are analyzed by Copula Entropy, and then the relevant production data in each operating condition are determined by just-in-time learning method. Next, broad learning models are established under different operating conditions. Further, dynamic prediction model of sintering carbon consumption is designed, and the prediction error is adopted to quantify performance of the model and as one criteria to determine the update of production database. Finally, results of experiments using actual production data demonstrate the advantage and validity of the developed model compared with some advanced modeling methods. The developed model considers complex characteristics of the sintering process and presents a better dynamic performance and information mining performance.