Search

These papers collectively showcase the adaptability and effectiveness of data mining techniques, making substantial contributions to the broader realm of " I Methods and Applications of Data Mining in Business Domains i ". In a business context, the challenge is that one would like to see (i) how the algorithms can be repeatable in the real world, (ii) how the patterns mined can be utilized by the business, and (iii) how the resulting model can be understood and utilized in the business environment [[1]]. Additionally, they provide insights into factors influencing the adoption of business intelligence systems (BISs) in small and medium-sized enterprises (SMEs) [[26]], and conduct a systematic literature review on AI-based methods for automating business processes and decision support [[27]]. This Special Issue invited researchers to contribute original research in the field of data mining, particularly in its application to diverse domains, like healthcare, software development, logistics, and human resources. [Extracted from the article]

Background: MicroRNAs (miRNAs) emerge in various organisms, ranging from viruses to humans, and play crucial regulatory roles within cells, participating in a variety of biological processes. In numerous prediction methods for miRNA-disease associations, the issue of over-dependence on both similarity measurement data and the association matrix still hasn't been improved. In this paper, a miRNA-Disease association prediction model (called TP-MDA) based on tree path global feature extraction and fully connected artificial neural network (FANN) with multi-head self-attention mechanism is proposed. The TP-MDA model utilizes an association tree structure to represent the data relationships, multi-head self-attention mechanism for extracting feature vectors, and fully connected artificial neural network with 5-fold cross-validation for model training. Results: The experimental results indicate that the TP-MDA model outperforms the other comparative models, AUC is 0.9714. In the case studies of miRNAs associated with colorectal cancer and lung cancer, among the top 15 miRNAs predicted by the model, 12 in colorectal cancer and 15 in lung cancer were validated respectively, the accuracy is as high as 0.9227. Conclusions: The model proposed in this paper can accurately predict the miRNA-disease association, and can serve as a valuable reference for data mining and association prediction in the fields of life sciences, biology, and disease genetics, among others. [ABSTRACT FROM AUTHOR]

Lower-dimensional representation of scientific text has attracted much attention among researchers due to its impact on many data mining and recommendation tasks. This paper studies two main research streams in scientific literature representation. First, both local and distributed representation viewpoints are reviewed and their advantages and disadvantages in lower dimensional representation are discussed. The paper then proposes a novel hybrid distributed technique for text representation. Using scientific articles as the major source of textual information, both the article's content and citation network are used to build a distributed and universal lower dimensional representation. The superiority of the new technique to the traditional methods is then justified in predicting the existence of links in large citation graphs. [ABSTRACT FROM AUTHOR]

Rapid mapping demands efficient methods for a fast extraction of information from satellite data while minimizing data requirements. This paper explores the potential of deep learning for the generation of high-resolution urban elevation data from Synthetic Aperture Radar (SAR) imagery. In order to mitigate occlusion effects caused by the side-looking nature of SAR remote sensing, two SAR images from opposing aspects are leveraged and processed in an end-to-end deep neural network. The presented approach is the first of its kind to implicitly handle the transition from the SAR-specific slant range geometry to a ground-based mapping geometry within the model architecture. Comparative experiments demonstrate the superiority of the dual-aspect fusion over single-image methods in terms of reconstruction quality and geolocation accuracy. Notably, the model exhibits robust performance across diverse acquisition modes and geometries, showcasing its generalizability and suitability for height mapping applications. The study's findings underscore the potential of deep learning-driven SAR techniques in generating high-quality urban surface models efficiently and economically. [ABSTRACT FROM AUTHOR]

The aim of this paper is to mine the information contained in the bridge health monitoring data as well as to improve the shortcomings of traditional identification methods. In this paper, a bridge damage identification method based on the combination of data mining and deep neural networks is introduced. Firstly, a noise reduction method based on parameter optimisation of wavelet threshold decomposition is proposed, which further removes the noise signal by introducing two adjustment parameters in the threshold function to adapt to different wavelet decomposition layers. Furthermore, the Fast Fourier Transform is used to analyse the feature pattern of the original signal in the frequency domain, and the modal frequency features that exhibit the difference in damage categories are extracted from the spectrogram through sliding windows. Finally, a large number of irrelevant variables with small weight contributions are discarded by principal component analysis, and only the sensitive features with the most informative categories are retained as the input to the deep neural networks. The experimental results show that the new metrics after the feature engineering process improve the ability of damage identification and have stronger robustness, while our damage identification scheme achieves a good balance between the model computation and recognition accuracy. Furthermore, the recognition accuracy of the deep neural networks reaches over 93% with only three feature dimensions retained. [ABSTRACT FROM AUTHOR]

Dark web vendor identification can be seen as an authorship aliasing problem, aiming to determine whether different accounts on different markets belong to the same real-world vendor, in order to locate cybercriminals involved in dark web market transactions. Existing open-source datasets for dark web marketplaces are outdated and cannot simulate real-world situations, while data labeling methods are difficult and suffer from issues such as inaccurate labeling and limited cross-market research. The problem of identifying vendors' multiple identities on the dark web involves a large number of categories and a limited number of samples, making it difficult to use traditional multiclass classification models. To address these issues, this paper proposes a metric learning-based method for dark web vendor identification, collecting product data from 21 currently active English dark web marketplaces and using a multi-dimensional feature extraction method based on product titles, descriptions, and images. Using pseudo-labeling technology combined with manual labeling improves data labeling accuracy compared to previous labeling methods. The proposed method uses a Siamese neural network with metric learning to learn the similarity between vendors and achieve the recognition of vendors' multiple identities. This method achieved better performance with an average F1-score of 0.889 and an accuracy rate of 97.535% on the constructed dataset. The contributions of this paper lie in the proposed method for collecting and labeling data for dark web marketplaces and overcoming the limitations of traditional multiclass classifiers to achieve effective recognition of vendors' multiple identities. [ABSTRACT FROM AUTHOR]

Deep learning‐based models have become ubiquitous across a wide range of applications, including computer vision, natural language processing, and robotics. Despite their efficacy, one of the significant challenges associated with deep neural network (DNN) models is the potential risk of copyright leakage due to the inherent vulnerability of the entire model architecture and the communication burden of the large models during publishing. So far, it is still challenging for us to safeguard the intellectual property rights of these DNN models while reducing the communication time during model publishing. To this end, this paper introduces a novel approach using knowledge distillation techniques aimed at training a surrogate model to stand in for the original DNN model. To be specific, a knowledge distillation generative adversarial network (KDGAN) model is proposed to train a student model capable of achieving remarkable performance levels while simultaneously safeguarding the copyright integrity of the original large teacher model and improving communication efficiency during model publishing. Herein, comprehensive experiments are conducted to showcase the efficacy of model copyright protection, communication‐efficient model publishing, and the superiority of the proposed KDGAN model over other copyright protection mechanisms. [ABSTRACT FROM AUTHOR]

Purpose: The objective of this paper is to evaluate whether the data from consignors, logistics service providers (LSPs) and consignees contribute to the prediction of air transport shipment delays in a machine learning application. Design/methodology/approach: The research database contained 2,244 air freight intercontinental shipments to 4 automotive production plants in Latin America. Different algorithm classes were tested in the knowledge discovery in databases (KDD) process: support vector machine (SVM), random forest (RF), artificial neural networks (ANN) and k-nearest neighbors (KNN). Findings: Shipper, consignee and LSP data attribute selection achieved 86% accuracy through the RF algorithm in a cross-validation scenario after a combined class balancing procedure. Originality/value: These findings expand the current literature on machine learning applied to air freight delay management, which has mostly focused on weather, airport structure, flight schedule, ground delay and congestion as explanatory attributes. [ABSTRACT FROM AUTHOR]

In the data retrieval process of the Data recommendation system, the matching prediction and similarity identification take place a major role in the ontology. In that, there are several methods to improve the retrieving process with improved accuracy and to reduce the searching time. Since, in the data recommendation system, this type of data searching becomes complex to search for the best matching for given query data and fails in the accuracy of the query recommendation process. To improve the performance of data validation, this paper proposed a novel model of data similarity estimation and clustering method to retrieve the relevant data with the best matching in the big data processing. In this paper advanced model of the Logarithmic Directionality Texture Pattern (LDTP) method with a Metaheuristic Pattern Searching (MPS) system was used to estimate the similarity between the query data in the entire database. The overall work was implemented for the application of the data recommendation process. These are all indexed and grouped as a cluster to form a paged format of database structure which can reduce the computation time while at the searching period. Also, with the help of a neural network, the relevancies of feature attributes in the database are predicted, and the matching index was sorted to provide the recommended data for given query data. This was achieved by using the Distributional Recurrent Neural Network (DRNN). This is an enhanced model of Neural Network technology to find the relevancy based on the correlation factor of the feature set. The training process of the DRNN classifier was carried out by estimating the correlation factor of the attributes of the dataset. These are formed as clusters and paged with proper indexing based on the MPS parameter of similarity metric. The overall performance of the proposed work can be evaluated by varying the size of the training database by 60%, 70%, and 80%. The parameters that are considered for performance analysis are Precision, Recall, F1-score and the accuracy of data retrieval, the query recommendation output, and comparison with other state-of-art methods. [ABSTRACT FROM AUTHOR]

Agricultural sustainability is dependent on the ability to predict crop yield, which is vital for farmers, consumers, and researchers. Most of the works used the amount of rainfall, average monthly temperature, relative humidity, etc. as inputs. In this paper, an attempt was made to predict the yield of the citrus crop (Washington Navel orange, Valencia orange, Murcott mandarin, Fremont mandarin, and Bearss Seedless lime) using weather factors and the accumulated heat units. These variables were used as input parameters in an artificial neural network (ANN) model. The necessary information was gathered during the growing seasons between 2010/2011 and 2021/2022 under Egyptian conditions. Weather factors were daily precipitation, yearly average air temperature, and yearly average of air relative humidity. A base air temperature of 13.0 °C was used to determine the accumulated heat units. The heat use efficiency (HUE) for cultivars was determined. The Bearss Seedless lime had the lowest HUE of 9.5 kg/ha °C day, while the Washington Navel orange had the highest HUE of 20.2 kg/ha °C day. The predictive performance of the ANN model with a structure of 9-20-1 with the backpropagation was evaluated using standard statistical measures. The actual and estimated yields from the ANN model were compared using a testing dataset, resulting in a value of RMSE, MAE, and MAPE of 2.80 t/ha, 2.58 t/ha, and 5.41%, respectively. The performance of the ANN model in the training phase was compared to multiple linear regression (MLR) models using values of R2; for MLR models for all cultivars, R2 ranged between 0.151 and 0.844, while the R2 value for the ANN was 0.87. Moreover, the ANN model gave the best performance criteria for evaluation of citrus yield prediction with a high R2, low root mean squared error, and low mean absolute error compared to the performance criteria of data mining algorithms such as K-nearest neighbor (KNN), KStar, and support vector regression. These encouraging outcomes show how the current ANN model can be used to estimate fruit yields, including citrus fruits and other types of fruit. The novelty of the proposed ANN model lies in the combination of weather parameters and accumulated heat units for accurate citrus yield prediction, specifically tailored for Egyptian regional citrus crops. Furthermore, especially in low- to middle-income countries such as Egypt, the findings of this study can greatly enhance the reliance on statistics when making decisions regarding agriculture and climate change. The citrus industry can benefit greatly from these discoveries, which can help with optimization, harvest planning, and postharvest logistics. We recommended furthering proving the robustness and generalization ability of the results in this study by adding more data points. [ABSTRACT FROM AUTHOR]

In recent years, the use of deep neural network in effective network feature extraction and the design of efficient and high-precision hyperspectral image classification algorithms has gradually become a research hotspot for scholars. However, due to the difficulty of obtaining hyperspectral images and the high cost of annotation, the training samples are very limited. In order to cope with the small sample problem, researchers often deepen the network model and use the attention mechanism to extract features; however, as the network model continues to deepen, the gradient disappears, the feature extraction ability is insufficient, and the computational cost is high. Therefore, how to make full use of the spectral and spatial information in limited samples has gradually become a difficult problem. In order to cope with such problems, this paper proposes two-branch multiscale spatial–spectral feature aggregation with a self-attention mechanism for a hyperspectral image classification model (FHDANet); the model constructs a dense two-branch pyramid structure, which can achieve the high efficiency extraction of joint spatial–spectral feature information and spectral feature information, reduce feature loss to a large extent, and strengthen the model's ability to extract contextual information. A channel–space attention module, ECBAM, is proposed, which greatly improves the extraction ability of the model for salient features, and a spatial information extraction module based on the deep feature fusion strategy HLDFF is proposed, which fully strengthens feature reusability and mitigates the feature loss problem brought about by the deepening of the model. Compared with five hyperspectral image classification algorithms, SVM, SSRN, A2S2K-ResNet, HyBridSN, SSDGL, RSSGL and LANet, this method significantly improves the classification performance on four representative datasets. Experiments have demonstrated that FHDANet can better extract and utilise the spatial and spectral information in hyperspectral images with excellent classification performance under small sample conditions. [ABSTRACT FROM AUTHOR]

Currently, many fault diagnosis methods for rolling bearings based on deep learning are facing two main challenges. Firstly, the deep learning model exhibits poor diagnostic performance and limited generalization ability in the presence of noise signals and varying loads. Secondly, there is incomplete utilization of fault information and inadequate extraction of fault features, leading to the low diagnostic accuracy of the model. To address these problems, this paper proposes an improved dual-branch convolutional capsule neural network for rolling bearing fault diagnosis. This method converts the collected bearing vibration signals into grayscale images to construct a grayscale image dataset. By fully considering the types of bearing faults and damage diameters, the data are labeled using a dual-label format. A multi-scale convolution module is introduced to extract features from the data and maximize feature information extraction. Additionally, a coordinate attention mechanism is incorporated into this module to better extract useful channel features and enhance feature extraction capability. Based on adaptive fusion between fault type (damage diameter) features and labels, a dual-branch convolutional capsule neural network model for rolling bearing fault diagnosis is established. The model was experimentally validated using both Case Western Reserve University's bearing dataset and self-made datasets. The experimental results demonstrate that the fault type branch of the model achieves an accuracy rate of 99.88%, while the damage diameter branch attains an accuracy rate of 99.72%. Both branches exhibit excellent classification performance and display robustness against noise interference and variable working conditions. In comparison with other algorithm models cited in the reference literature, the diagnostic capability of the model proposed in this study surpasses them. Furthermore, the generalization ability of the model is validated using a self-constructed laboratory dataset, yielding an average accuracy rate of 94.25% for both branches. [ABSTRACT FROM AUTHOR]

Financial fraud, considered as deceptive tactics for gaining financial benefits, has recently become a widespread menace in companies and organizations. Conventional techniques such as manual verifications and inspections are imprecise, costly, and time consuming for identifying such fraudulent activities. With the advent of artificial intelligence, machine-learning-based approaches can be used intelligently to detect fraudulent transactions by analyzing a large number of financial data. Therefore, this paper attempts to present a systematic literature review (SLR) that systematically reviews and synthesizes the existing literature on machine learning (ML)-based fraud detection. Particularly, the review employed the Kitchenham approach, which uses well-defined protocols to extract and synthesize the relevant articles; it then report the obtained results. Based on the specified search strategies from popular electronic database libraries, several studies have been gathered. After inclusion/exclusion criteria, 93 articles were chosen, synthesized, and analyzed. The review summarizes popular ML techniques used for fraud detection, the most popular fraud type, and evaluation metrics. The reviewed articles showed that support vector machine (SVM) and artificial neural network (ANN) are popular ML algorithms used for fraud detection, and credit card fraud is the most popular fraud type addressed using ML techniques. The paper finally presents main issues, gaps, and limitations in financial fraud detection areas and suggests possible areas for future research. [ABSTRACT FROM AUTHOR]

Big data technology has been developed rapidly in recent years. The performance improvement mechanism of targeted poverty alleviation is studied through the big data technology to further promote the comprehensive application of big data technology in poverty alleviation and development. Using the data mining knowledge to accurately identify the poor population under the framework of big data, compared with the traditional identification method, it is obviously more accurate and persuasive, which is also helpful to find out the real causes of poverty and assist the poor residents in the future. In the current targeted poverty alleviation work, the identification of poor households and the matching of assistance measures are mainly through the visiting of village cadres and the establishment of documents. Traditional methods are time-consuming, laborious, and difficult to manage. It always omits lots of useful family information. Therefore, new technologies need to be introduced to realize intelligent identification of poverty-stricken households and reduce labor costs. In this paper, we introduce a novel DBSCAN clustering algorithm via the edge computing-based deep neural network model for targeted poverty alleviation. First, we deploy an edge computing-based deep neural network model. Then, in this constructed model, we execute data mining for the poverty-stricken family. In this paper, the DBSCAN clustering algorithm is used to excavate the poverty features of the poor households and complete the intelligent identification of the poor households. In view of the current situation of high-dimensional and large-volume poverty alleviation data, the algorithm uses the relative density difference of grid to divide the data space into regions with different densities and adopts the DBSCAN algorithm to cluster the above result, which improves the accuracy of DBSCAN. This avoids the need for DBSCAN to traverse all data when searching for density connections. Finally, the proposed method is utilized for analyzing and mining the poverty alleviation data. The average accuracy is more than 96%. The average F -measure, NMI, and PRE values exceed 90%. The results show that it provides decision support for precise matching and intelligent pairing of village cadres in poverty alleviation work. [ABSTRACT FROM AUTHOR]

Modern data mining techniques using machine learning (ML) and deep learning (DL) algorithms have been shown to excel in the regression-based task of materials property prediction using various materials representations. In an attempt to improve the predictive performance of the deep neural network model, researchers have tried to add more layers as well as develop new architectural components to create sophisticated and deep neural network models that can aid in the training process and improve the predictive ability of the final model. However, usually, these modifications require a lot of computational resources, thereby further increasing the already large model training time, which is often not feasible, thereby limiting usage for most researchers. In this paper, we study and propose a deep neural network framework for regression-based problems comprising of fully connected layers that can work with any numerical vector-based materials representations as model input. We present a novel deep regression neural network, iBRNet, with branched skip connections and multiple schedulers, which can reduce the number of parameters used to construct the model, improve the accuracy, and decrease the training time of the predictive model. We perform the model training using composition-based numerical vectors representing the elemental fractions of the respective materials and compare their performance against other traditional ML and several known DL architectures. Using multiple datasets with varying data sizes for training and testing, We show that the proposed iBRNet models outperform the state-of-the-art ML and DL models for all data sizes. We also show that the branched structure and usage of multiple schedulers lead to fewer parameters and faster model training time with better convergence than other neural networks. Scientific contribution: The combination of multiple callback functions in deep neural networks minimizes training time and maximizes accuracy in a controlled computational environment with parametric constraints for the task of materials property prediction. [ABSTRACT FROM AUTHOR]

Multimedia data mining plays a crucial role in various fields, such as image and video analysis, natural language processing, and recommendation systems. Multimedia data refers to any form of data that involves multiple modes of communication, such as text, images, audio, and video. To effectively mine valuable insights from multimedia data, a new framework is proposed in this paper that employs a transformer-based intelligent deep neural network (DNN) model architecture. The framework includes an extensive data preprocessing step that involves obtaining multimedia data from internet searches and removing duplicates to ensure that each image is unique. The proposed transformer-based intelligent DNN model architecture processes the multimedia data in a hierarchical manner and utilizes shifted windows to achieve high accuracy in image classification task. The exploited dataset details are provided in the experimental evaluation section. Experimental results show that the proposed framework outperforms existing multimedia data mining methods in terms of accuracy and efficiency. This framework provides valuable insights that can be used in various applications, including content-based image retrieval, sentiment analysis, and automated captioning. [ABSTRACT FROM AUTHOR]

In order to solve the technical problem of fault signal recognition in the field of communication, this paper proposes an electronic communication fault signal recognition method based on data mining algorithm. Firstly, the K-means clustering algorithm is used to determine the cluster number k according to some attributes or class characteristics of the communication class samples, and the communication sample types are classified into a certain class so that the communication sample data in the cluster can be closely distributed and the data within a certain class range can be calculated by Euclidean distance formula. Then, this paper clusters the data. In the clustering data, BP neural network model is used to train and calculate the obtained clustering data again, which can map and deal with the complex nonlinear relationship between the fault information data of different clustering categories. The results show that the final error accuracy can be raised to about 20% by using the method in this paper. Conclusion. The algorithm designed in this paper can quickly predict the factors affecting the communication and find the communication fault information. [ABSTRACT FROM AUTHOR]

This paper addresses data mining and neural network model construction and analysis to design a data interaction process model based on data mining and topology visualization. This paper performs preprocessing data operations such as data filtering and cleaning of the collected data. A typical multichannel convolutional neural network (MCNN) in deep learning techniques is applied to alert students' academic performance. In addition, the network topology of the CNN is optimized to improve the performance of the model. The CNN has many hyperparameters that need to be tuned to construct an optimal model that can effectively interact with the data. In this paper, we propose a method to visualize the network topology within unstable regions to address the current problem of lacking an effective way to layout the network topology into specified areas. The technique transforms the network topology layout problem within the unstable region into a circular topology diffusion problem within a convex polygon, ensuring a clear, logical topology connection, and dramatically reducing the gaps in the area, making the layout more uniform beautiful. This paper constructs a real-time data interaction model based on JSON format and database triggers using message queues for reliable delivery. A platform-based real-time data interaction solution is designed by combining the timer method with the original key. The solution designed in this paper considers the real-time accuracy, security and reliability of data interaction. It satisfies the platform's initial and newly discovered requirements for data interaction. [ABSTRACT FROM AUTHOR]

Event extraction technology is one of the important researches in the field of information extraction, which helps people accurately retrieve, find, classify, and summarize effective information from a large amount of information streams. This paper uses the neural network hybrid model to identify the trigger words and event categories of the legal domain knowledge graph events, extracts the events of interest from a large amount of free text, and displays them in a structured format. First, the original text is preprocessed, and then, the distributed semantic word vector is combined with the dependent syntactic structure and location attributes to create a semantic representation in the form of a vector. The combined deep learning model is used to extract activated words, the long-term memory loop neural network uses temporal semantics to extract deep features, and the convergent neural network completes the extraction of activated words and event categories. Finally, the experimental results show that the accuracy of event extraction of the neural network hybrid model designed in this paper has reached 77.1%, and the recall rate has reached 76.8%, which is greatly improved compared with the traditional model. [ABSTRACT FROM AUTHOR]

This paper proposes a network model recurrent fully connected network (RFC-Net) based on recurrent full convolution and polarization change. RFC-Net enriches the network by reconstructing and fine-tuning the fully convolutional network and adding recurrent convolutions to it. By studying the data mining technology of multidimensional association rules, based on the existing algorithms, this paper improves the shortcomings of the algorithms and realizes an efficient and practical method for data mining based on interdimensional multidimensional association rules. On the basis of mastering the actual student information, the effectiveness of the method is tested, and an employment analysis system based on association rules is established. Aiming at the fact that traditional grade prediction methods ignore the different influences of different behavioral characteristics on grades, and considering that behavioral data in different periods have different influences on student grades, the grade prediction problem is abstracted into a time series classification problem. The mechanism is combined with long short-term memory neural network to construct a performance prediction model based on Attention-BiLSTM. Experiments show that the prediction model proposed in this paper improves the accuracy and effectively improves the prediction quality compared with the logistic regression model with a better prediction effect in the traditional benchmark model and the long short-term memory neural network model without the introduction of the attention mechanism. Research shows that physical performance and academic performance are not contradictory. We must face up to the status of physical exercise in schools; as long as physical exercise is properly arranged, it can inspire students to form a spirit of unity, interaction, positivity, and perseverance in cultural studies. [ABSTRACT FROM AUTHOR]

Deep neural networks (DNNs), including convolutional neural networks (CNNs) and residual networks (ResNets) models, are able to learn abstract representations from the input data by considering a deep hierarchy of layers that perform advanced feature extraction. The combination of these models with visual attention techniques can assist with the identification of the most representative parts of the data from a visual standpoint, obtained through more detailed filtering of the features extracted by the operational layers of the network. This is of significant interest for analyzing remotely sensed hyperspectral images (HSIs), characterized by their very high spectral dimensionality. However, few efforts have been conducted in the literature in order to adapt visual attention methods to remotely sensed HSI data analysis. In this paper, we introduce a new visual attention-driven technique for the HSI classification. Specifically, we incorporate attention mechanisms to a ResNet in order to better characterize the spectral–spatial information contained in the data. Our newly proposed method calculates a mask that is applied to the features obtained by the network in order to identify the most desirable ones for classification purposes. Our experiments, conducted using four widely used HSI data sets, reveal that the proposed deep attention model provides competitive advantages in terms of classification accuracy when compared to other state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Simple Summary: In radiotherapy treatment, organs at risk and target volumes are contoured by the clinicians to prepare a dosimetry plan. In retrospective data, these structures are not often standardised to universal names across the patients plans, which is required to enable data mining and analysis. In this paper, a new method was proposed and evaluated to automatically standardise radiotherapy structures names using machine learning algorithms. The proposed approach was deployed over a dataset with 1613 patients collected from Liverpool & Macarthur Cancer Therapy Centres, New South Wales, Australia. It was concluded that machine learning techniques can standardise the dosimetry plan structures, taking into consideration the integration of multiple modalities representing each structure during the training process. In progressing the use of big data in health systems, standardised nomenclature is required to enable data pooling and analyses. In many radiotherapy planning systems and their data archives, target volumes (TV) and organ-at-risk (OAR) structure nomenclature has not been standardised. Machine learning (ML) has been utilised to standardise volumes nomenclature in retrospective datasets. However, only subsets of the structures have been targeted. Within this paper, we proposed a new approach for standardising all the structures nomenclature by using multi-modal artificial neural networks. A cohort consisting of 1613 breast cancer patients treated with radiotherapy was identified from Liverpool & Macarthur Cancer Therapy Centres, NSW, Australia. Four types of volume characteristics were generated to represent each target and OAR volume: textual features, geometric features, dosimetry features, and imaging data. Five datasets were created from the original cohort, the first four represented different subsets of volumes and the last one represented the whole list of volumes. For each dataset, 15 sets of combinations of features were generated to investigate the effect of using different characteristics on the standardisation performance. The best model reported 99.416% classification accuracy over the hold-out sample when used to standardise all the nomenclatures in a breast cancer radiotherapy plan into 21 classes. Our results showed that ML based automation methods can be used for standardising naming conventions in a radiotherapy plan taking into consideration the inclusion of multiple modalities to better represent each volume. [ABSTRACT FROM AUTHOR]

This paper represents a neural network model for the Web page information extraction based on the depth learning technology, and implements the model algorithm using the TensorFlow system. We then complete a detailed experimental analysis of the information extraction effect of Web pages on the same website, then show statistics on the accuracy index of the page information extraction, and optimize some parameters in the model according to the experimental results. On the premise of achieving ideal experimental results, an algorithm for migrating the model to the same pages of other websites for information extraction is proposed, and the experimental results are analyzed. Although the overall effect of the experiment is not as good as that of the page information extraction in different websites, it is far more effective than that of using the model directly on new websites. A new method is proposed to improve the portability of the information extraction system based on machine learning technology. At the same time, the deep nonlinear learning method of the depth learning model can prove deeper features, can have a more essential description of the abstract language, and can better express and understand sentences from the syntactic and semantic levels. [ABSTRACT FROM AUTHOR]

Understanding students' learning of knowledge components (KCs) is an important educational data mining task and enables many educational applications. However, in the domain of computing education, where program exercises require students to practice many KCs simultaneously, it is a challenge to attribute their errors to specific KCs and, therefore, to model student knowledge of these KCs. In this paper, we define this task as the KC attribution problem. We first demonstrate a novel approach to addressing this task using deep neural networks and explore its performance in identifying expert-defined KCs (RQ1). Because the labeling process takes costly expert resources, we further evaluate the effectiveness of transfer learning for KC attribution, using more easily acquired labels, such as problem correctness (RQ2). Finally, because prior research indicates the incorporation of educational theory in deep learning models could potentially enhance model performance, we investigated how to incorporate learning curves in the model design and evaluated their performance (RQ3). Our results show that in a supervised learning scenario, we can use a deep learning model, code2vec, to attribute KCs with a relatively high performance (AUC > 75% in two of the three examined KCs). Further using transfer learning, we achieve reasonable performance on the task without any costly expert labeling. However, the incorporation of learning curves shows limited effectiveness in this task. Our research lays important groundwork for personalized feedback for students based on which KCs they applied correctly, as well as more interpretable and accurate student models. [ABSTRACT FROM AUTHOR]

Data mining plays a crucial role in extracting meaningful knowledge fromlarge-scale data repositories, such as data warehouses and databases. Association rule mining, a fundamental process in data mining, involves discovering correlations, patterns, and causal structures within datasets. In the healthcare domain, association rules offer valuable opportunities for building knowledge bases, enabling intelligent diagnoses, and extracting invaluable information rapidly. This paper presents a novel approach called the Machine Learning based Association Rule Mining and Classification for Healthcare Data Management System (MLARMC-HDMS). The MLARMC-HDMS technique integrates classification and association rule mining (ARM) processes. Initially, the chimp optimization algorithm-based feature selection (COAFS) technique is employed within MLARMC-HDMS to select relevant attributes. Inspired by the foraging behavior of chimpanzees, the COA algorithm mimics their search strategy for food. Subsequently, the classification process utilizes stochastic gradient descent with a multilayer perceptron (SGD-MLP) model, while the Apriori algorithm determines attribute relationships.We propose a COA-based feature selection approach for medical data classification using machine learning techniques. This approach involves selecting pertinent features from medical datasets through COA and training machine learning models using the reduced feature set. We evaluate the performance of our approach on various medical datasets employing diverse machine learning classifiers. Experimental results demonstrate that our proposed approach surpasses alternative feature selection methods, achieving higher accuracy and precision rates in medical data classification tasks. The study showcases the effectiveness and efficiency of the COA-based feature selection approach in identifying relevant features, thereby enhancing the diagnosis and treatment of various diseases. To provide further validation, we conduct detailed experiments on a benchmark medical dataset, revealing the superiority of the MLARMCHDMS model over other methods, with a maximum accuracy of 99.75%. Therefore, this research contributes to the advancement of feature selection techniques in medical data classification and highlights the potential for improving healthcare outcomes through accurate and efficient data analysis. The presented MLARMC-HDMS framework and COA-based feature selection approach offer valuable insights for researchers and practitioners working in the field of healthcare data mining and machine learning. [ABSTRACT FROM AUTHOR]

While recent developments of neural network (NN) models have led to a series of record-breaking achievements in many applications, the lack of sufficiently good datasets remains a problem for some applications. For such a problem, we can however exploit a large number of unstructured text corpora as an external knowledge to complement the training data, and most prevailing neural network solutions employ word embedding methods for such purposes. In this paper, we propose LDA-Reg, a novel knowledge driven regularization framework based on Latent Dirichlet Allocation (LDA) as an alternative to the word embedding methods to adaptively utilize abundant external knowledge and to interpret the NN model. For the joint learning of the parameters, we propose EM-SGD, an effective update method which incorporates Expectation Maximization (EM) and Stochastic Gradient Descent (SGD) to update parameters iteratively. Moreover, we also devise a lazy update and sparse update method for the high-dimensional inputs and sparse inputs respectively. We validate the effectiveness of our regularization framework through an extensive experimental study over real world and standard benchmark datasets. The results show that our proposed framework not only achieves significant improvement over state-of-the-art word embedding methods but also learns interpretable and significant topics for various tasks. [ABSTRACT FROM AUTHOR]

In recent years, with the increase in computing power, the sharp drop in costs, and the successful use of data management technology, a large amount of data has been rapidly spread and stored in various fields of the company. How can we passively find active data and form active knowledge from these big data information, know how to use equipment to quickly and accurately obtain high-quality information, use the obtained information to guide users in decision-making, and provide more economic and social benefits? This paper focuses on the study of the classifier model based on BP neural network, and the combination of BP neural network model and other optimization algorithms, including genetic algorithm (GA), particle swarm algorithm (PSO), Adaboost algorithm, GA, and PSO have global search performance. It is mostly used to optimize the weight threshold of the network and the number of hidden layer nodes. The Adaboost algorithm builds an enhanced classifier based on the idea of integration. At present, data mining technology has moved from the laboratory research stage to the commercialization stage. The use of widely owned knowledge and information as analysis tools can be used in many fields: such as financial analysis, engineering design, scientific research, management, and production control. At the end of this paper, the improved Adaboost_BP classifier is used, and the result proves that the efficiency of hotel management has increased by at least 75%. [ABSTRACT FROM AUTHOR]

The paper conducts a literature review of applications of autoregressive methods to short-term forecasting of power demand. This need is dictated by the advancement of modern forecasting methods and their achievement in good forecasting efficiency in particular. The annual effectiveness of forecasting power demand for the Polish National Power Grid for the next day is approx. 1%; therefore, the main objective of the review is to verify whether it is possible to improve efficiency while maintaining the minimum financial outlays and time-consuming efforts. The methods that fulfil these conditions are autoregressive methods; therefore, the paper focuses on autoregressive methods, which are less time-consuming and, as a result, cheaper in development and applications. The prepared review ranks the forecasting models in terms of the forecasting effectiveness achieved in the literature on the subject, which enables the selection of models that may improve the currently achieved effectiveness of the transmission system operator. Due to the applied approach, a transparent set of forecasting methods and models was obtained, in addition to knowledge about their potential in the context of the needs for short-term forecasting of electricity demand in the national power system. The articles in which the MAPE error was used to assess the quality of short-term forecasts were analyzed. The investigation included 47 articles, several dozen forecasting methods, and 264 forecasting models. The articles date from 1997 and, apart from the autoregressive methods, also include the methods and models that use explanatory variables (non-autoregressive ones). The input data used come from the period 1998–2014. The analysis included 25 power systems located on four continents (Asia, Europe, North America, and Australia) that were published by 44 different research teams. The results of the review show that in the autoregressive methods applied to forecasting short-term power demand, there is a potential to improve forecasting effectiveness in power systems. The most promising prognostic models using the autoregressive approach, based on the review, include Fuzzy Logic, Artificial Neural Networks, Wavelet Artificial Neural Networks, Adaptive Neurofuse Inference Systems, Genetic Algorithms, Fuzzy Regression, and Data Envelope Analysis. These methods make it possible to achieve the efficiency of short-term forecasting of electricity demand with hourly resolution at the level below 1%, which confirms the assumption made by the authors about the potential of autoregressive methods. Other forecasting models, the effectiveness of which is high, may also prove useful in forecasting by electricity system operators. The paper also discusses the classical methods of Artificial Intelligence, Data Mining, Big Data, and the state of research in short-term power demand forecasting in power systems using autoregressive and non-autoregressive methods and models. [ABSTRACT FROM AUTHOR]

Contextual information plays an important role in solving various image and scene understanding tasks. Prior works have focused on the extraction of contextual information from an image and use it to infer the properties of some object(s) in the image or understand the scene behind the image, e.g., context-based object detection, recognition and semantic segmentation. In this paper, we consider an inverse problem, i.e., how to hallucinate the missing contextual information from the properties of standalone objects. We refer to it as object-level scene context prediction. This problem is difficult, as it requires extensive knowledge of the complex and diverse relationships among objects in the scene. We propose a deep neural network, which takes as input the properties (i.e., category, shape, and position) of a few standalone objects to predict an object-level scene layout that compactly encodes the semantics and structure of the scene context where the given objects are. Quantitative experiments and user studies demonstrate that our model can generate more plausible scene contexts than the baselines. Our model also enables the synthesis of realistic scene images from partial scene layouts. Finally, we validate that our model internally learns useful features for scene recognition and fake scene detection. [ABSTRACT FROM AUTHOR]

In order to further improve the performance of the automatic grammar error detection system, a new Chinese grammar recognition and correction model is proposed in this paper. Based on the transformer attention mechanism, the bias matrix of Gaussian distribution is added to improve the attention of the model to local text and strengthen the information extraction of wrong words and surrounding words in the wrong text. In addition, the ON_LSTM model is used to extract grammatical information from the special grammatical structure of error text. The experimental results show that the two methods can effectively improve the accuracy and recall rate, and the fused model achieves the highest F1 value. Finally, the Chinese text error correction system is designed to expand the application scope of the model, which helps to reduce the human cost in language learning. [ABSTRACT FROM AUTHOR]

In the context of electrical power systems, modeling the edge-end interaction involves understanding the dynamic relationship between different components and endpoints of the system. However, the time series of electrical power obtained by user terminals often suffer from low-quality issues such as missing values, numerical anomalies, and noisy labels. These issues can easily reduce the robustness of data mining results for edge-end interaction models. Therefore, this paper proposes a time–frequency noisy label classification (TF-NLC) model, which improves the robustness of edge-end interaction models in dealing with low-quality issues. Specifically, we employ two deep neural networks that are trained concurrently, utilizing both the time and frequency domains. The two networks mutually guide each other's classification training by selecting clean labels from batches within small loss data. To further improve the robustness of the classification of time and frequency domain feature representations, we introduce a time–frequency domain consistency contrastive learning module. By classifying the selection of clean labels based on time–frequency representations for mutually guided training, TF-NLC can effectively mitigate the negative impact of noisy labels on model training. Extensive experiments on eight electrical power and ten other different realistic scenario time series datasets show that our proposed TF-NLC achieves advanced classification performance under different noisy label scenarios. Also, the ablation and visualization experiments further demonstrate the robustness of our proposed method. [ABSTRACT FROM AUTHOR]

The design of concrete mixtures is crucial in concrete technology, aiming to produce concrete that meets specific quality and performance criteria. Modern standards require not only strength but also eco-friendliness and production efficiency. Based on the Three Equation Method, conventional mix design methods involve analytical and laboratory procedures but are insufficient for contemporary concrete technology, leading to overengineering and difficulty predicting concrete properties. Machine learning-based methods offer a solution, as they have proven effective in predicting concrete compressive strength for concrete mix design. This paper scrutinises the association between the computational complexity of machine learning models and their proficiency in predicting the compressive strength of concrete. This study evaluates five deep neural network models of varying computational complexity in three series. Each model is trained and tested in three series with a vast database of concrete mix recipes and associated destructive tests. The findings suggest a positive correlation between increased computational complexity and the model's predictive ability. This correlation is evidenced by an increment in the coefficient of determination (R2) and a decrease in error metrics (mean squared error, Minkowski error, normalized squared error, root mean squared error, and sum squared error) as the complexity of the model increases. The research findings provide valuable insights for increasing the performance of concrete technical feature prediction models while acknowledging this study's limitations and suggesting potential future research directions. This research paves the way for further refinement of AI-driven methods in concrete mix design, enhancing the efficiency and precision of the concrete mix design process. [ABSTRACT FROM AUTHOR]

The application of machine learning (ML) to corrosion research has become an important trend in corrosion science in recent years. In this paper, the feature extraction method for corrosion data and the ML algorithms commonly used (including artificial neural networks, support vector machines, ensemble learning and other widely used algorithms) in corrosion field is introduced. Then, the characteristics of different algorithms and their application scenarios in the corrosion prediction are summarized. Finally, the development trend of ML in material corrosion field is prospected. [ABSTRACT FROM AUTHOR]

Convolutional Neural Networks (CNN) and Graph Neural Networks (GNN), such as Graph Attention Networks (GAT), are two classic neural network models, which are applied to the processing of grid data and graph data respectively. They have achieved outstanding performance in hyperspectral images (HSIs) classification field, which have attracted great interest. However, CNN has been facing the problem of small samples and GNN has to pay a huge computational cost, which restrict the performance of the two models. In this paper, we propose Weighted Feature Fusion of Convolutional Neural Network and Graph Attention Network (WFCG) for HSI classification, by using the characteristics of superpixel-based GAT and pixel-based CNN, which proved to be complementary. We first establish GAT with the help of superpixel-based encoder and decoder modules. Then we combined the attention mechanism to construct CNN. Finally, the features are weighted fusion with the characteristics of two neural network models. Rigorous experiments on three real-world HSI data sets show WFCG can fully explore the high-dimensional feature of HSI, and obtain competitive results compared to other state-of-the art methods. [ABSTRACT FROM AUTHOR]

Premature damage to heavy-duty pavement has been found to be significantly caused by the vehicle–highway alignment interaction, especially in mountainous regions. This phenomenon was further verified by field pavement damage investigations and field tests. In order to elucidate the potential mechanism of this interaction, it is important to address the vehicle dynamic loads generated by the interaction between vehicle and pavement. Based on this, the paper realizes a new method of vehicle dynamic load prediction using data mining techniques, namely artificial neural network (ANN) and support vector machine (SVM)). The data, including dynamic loads and highway geometric characteristics, were collected by a wheel force transducer (WFT) and global positioning system (GPS), respectively. The coefficient of determination (R2) and root mean square error (RMSE) were used to evaluate the performance of the prediction models. The results showed that the proposed dynamic load prediction model established by ANN was better than that by SVM. Moreover, the model implied that dynamic loads were highly correlated with curvature and longitudinal grade, and furthermore, curvature was found to have a larger effect. The proposed dynamic load prediction technique provides a feasible and rapid approach to identify pavement damage under complex vehicle–highway alignment interactions. [ABSTRACT FROM AUTHOR]

There has been a resurgence of research in the design of deep architecture models and learning algorithms, i.e., methods that rely on the extraction of a multilayer representation of the data. Often referred to as deep learning, this topic of research has been building on and contributing to many different research topics, such as neural networks, graphical models, feature learning, unsupervised learning, optimization, pattern recognition, and signal processing. Deep learning is also motivated and inspired by neuroscience and has had a tremendous impact on various applications such as computer vision, speech recognition, and natural language processing. The clearly multidisciplinary nature of deep learning led to a call for papers for a special issue dedicated to learning deep architectures. [ABSTRACT FROM PUBLISHER]

Machine learning methods have been frequently used for the diagnosis of several diseases recently because of its reliability and convenience. In this paper, a comprehensive overview of the literature related to diabetes and diabetic retinopathy has been done and diagnosis of diabetic retinopathy disease is investigated. Artificial Neural Networks (ANN) method has been applied to the problem using Rapid Miner, a data mining tool. Some other methods have also adapted to the problem, but ANN based detection approach gave the best results. 88.52% sensitivity has been obtained using the features of Messidor dataset. Besides showing the success of ANN in diabetic retinopathy detection, this study also proved that Rapid Miner can be used effectively for the analysis of diabetic retinopathy. [ABSTRACT FROM AUTHOR]

Biomedical researchers and biologists often search a large amount of literature to find the relationship between biological entities, such as drug-drug and compound-protein. With the proliferation of medical literature and the development of deep learning, the automatic extraction of biological entity interaction relationships from literature has shown great potential. The fundamental scope of this research is that the approach described in this research uses technologies like dynamic word vectors and multichannel convolution to learn a larger variety of relational expression semantics, allowing it to detect more entity connections. The extraction of biological entity relationships is the foundation for achieving intelligent medical care, which may increase the effectiveness of intelligent medical question answering and enhance the development of precision healthcare. In the past, deep learning methods have achieved specific results, but there are the following problems: the model uses static word vectors, which cannot distinguish polysemy; the weight of words is not considered, and the extraction effect of long sentences is poor; the integration of various models can improve the sample imbalance problem, the model is more complex. The purpose of this work is to create a global approach for eliminating different physical entity links, such that the model can effectively extract the interpretation of the expression relationship without having to develop characteristics manually. To this end, a deep multichannel CNN model (MC-CNN) based on the residual structure is proposed, generating dynamic word vectors through BERT (Bidirectional Encoder Representation from Transformers) to improve the accuracy of lexical semantic representation and uses multihead attention to capture the dependencies of long sentences and by designing the Ranking loss function to replace the multimodel ensemble to reduce the impact of sample imbalance. Tested on multiple datasets, the results show that the proposed method has good performance. [ABSTRACT FROM AUTHOR]

Social production and life have become increasingly prominent. Cluster analysis is the basis for further processing of the data. The concept of data mining and the application of neural networks in data mining are introduced. According to the related technology of data mining, this article introduces in detail the two-layer perceptron, backpropagation (BP) neural network, RBF radial basis function network for processing classification problems, and self-organizing map (SOM) self-organizing neural network for unsupervised clustering problems. According to the characteristics of self-adaptive and self-organizing capabilities of these algorithms, we learn and design and implement data mining clustering optimization algorithms. In this paper, the neural network-based data mining process consists of three stages: data preparation, rule extraction, and rule evaluation. This paper studies the teaching-type and decomposition-type rule extraction algorithms. After analyzing the BP decomposition-type algorithm, the correlation method is used to calculate the correlation of the input and output neurons. After sorting by the degree of correlation, the RBF neural network is used for node selection. This can greatly reduce the number of input nodes of the neural network, simplify the network structure, reduce the number of recursive splits of the subnet, and improve calculation efficiency. Taking the model as an example, the training error is calculated through data mining technology and clustering algorithm. Data mining clustering optimization algorithm mainly improves the popular neural network from two aspects: finer model design and model pruning, and simulates model complexity, computational complexity, and errors through simulation experiments. The rate is measured, and finally, the simulation experiment is performed. The results show that the proposed algorithm for differential distributed data mining has higher accuracy and stronger convergence ability and overcomes the shortcomings and shortcomings of several original genetic algorithm optimization neural network data mining models; it can effectively improve the searchability and search accuracy of the algorithm and improve the efficiency of data mining. Accuracy and accuracy have a wide range of applications. [ABSTRACT FROM AUTHOR]

The credit risk assessment acts as an important part in daily affairs for financial institutions. But in the era of big data, the growing business volume makes it an urgent demand to develop digital ways of credit risk assessment. Currently, the machine learning is universally employed to establish various data-driven models for this purpose. However, machine learning models generally suffer from limited ability of feature representation and robustness, and cannot deal with more complex financial security scenarios. To deal with this issue, this work introduces ensemble learning to construct a stronger credit risk prediction model via integration of several basic machine learning models. Thus, an ensemble learning-enhanced smart prediction model for financial credit risk is proposed in this paper. Three classification-based machine learning models (support vector machine, artificial neural network and radial basis function) are selected as the basic classifiers, and "voting" strategy is utilized to integrate them into a novel strong classifier. A real-world financial credit dataset released by a Chinese commercial bank was selected as the experimental scenario. The obtained results show that the proposal has better prediction accuracy compared with basic machine learning models without ensemble learning. [ABSTRACT FROM AUTHOR]

The saving banks of "umbilical cord blood stem cells" are considered as strategic health-based institutions in most countries. Due to the limited capacity of cord blood sample storage tanks, the samples should be evaluated according to their quality. So these banks need a method to assess quality. In this paper, first, the effective factors on the quality index of the extracted cord blood from newborn infants are identified using the electronic records and database of Royan's umbilical cord blood bank. Then by machine learning and various statistical methods such as Multilayer Perceptron Neural Networks (MLPNNs), Radial Basis Function Neural Networks (RBFNNs), Logistic Regression (LR), and C4.5 Decision Tree (DT), the quality value of blood samples and their proper category (for discarding or freezing) are determined. Two different sets of data have been used to evaluate the proposed methods. The results show that the ensemble of RBFNN with k-means clustering model has the best accuracy compared to other methods, which categorizing the samples with 91.5% accuracy for the first data set and 81.6% accuracy for the second one. The results also show that using this method can save about 1 million dollars annually. [ABSTRACT FROM AUTHOR]

Background: With the advancement in technology the amount of data generated, in almost every sphere of life, is increasing exponentially. This enormous amount of data needs new powerful tools for analysis and inference drawing. One such process is data mining which is the automated extraction of hidden, previously unknown, and useful knowledge from big data. Data mining is crucial as conventional strategies cannot keep up with the analysis of rapidly accumulating data and they are also inflexible in the wake of new challenges. Animal sciences are no exception to the changing scenario, especially when animal farms are quickly becoming more data intensive. The amount of data generated on the farms is also growing exponentially as farms become more intensive and mechanized. There is thus a need to utilize the knowledge of multidisciplinary fields like advanced statistics, artificial intelligence, machine learning, and database management, for revamping animal sciences. Artificial neural networks (ANNs) offer a lot of promise in this direction since they are motivated by the distributed, massively parallel computation in the brain. ANNs are powerful machine learning tools that offer multiple advantages for data mining over traditional techniques in being fast, accurate, self-organizing, robust, and highly accepting of noisy and imprecise data. Neural networks are being applied successfully for a myriad of supervised and unsupervised learning applications to draw useful hitherto unknown inferences, patterns, and relationships. Neural networks have been used successfully for pattern recognition, clustering, forecasting, prediction, and classification in animal sciences due to their capacity to learn from data, their nonparametric nature, and their ability to generalize well. Today ANN computing is a major element within any data mining tool kit. Popular methods used for neural network computing include feed-forward networks, feedback networks, and self-organization networks. ANN also offers powerful and distributed computing architecture, especially under a scenario where the data are readily available in significant quantity. Short conclusion: This paper gives an overview of ANN and their applications in animal sciences and reviews major research conducted in this new and exciting area of artificial intelligence. Research in many aspects of ANN in Animal Sciences has been conducted globally although there is scope for more research in aspects of animal health, monitoring, breeding as well as nutrition. [ABSTRACT FROM AUTHOR]

Classifying bank accounts by using transaction data is encouraging in cracking down on illegal financial activities. However, few research simultaneously use heterogenous features, which are embedded in the time series data. In this paper, a two route convolution neural network TRHD-CNN model, fed with two types of heterogeneous feature matrices, is proposed for classifying the bank accounts. TRHD-CNN adopts divide and conquer strategy to extract characteristics from two types of data source independently. The strategy is proved able in mining complementary classification characteristics. We firstly transfer the original log data into a directed and dynamic transaction network. On the basis of that, two feature generation methods are devised for extracting information from local topological structure and time series transaction respectively. A DirectedWalk method is developed in this paper to learning the network vector of vertices used for embedding the neighbor relationship of bank account. The extensive experimental results, conducted on a real bank transaction dataset that contains illegal pyramid selling accounts, show the significant advantage of TRHD-CNN over the existing methods. TRHD-CNN can provide recall scores up to 5.15% higher than competing methods. In addition, the two-route architecture of TRHD-CNN is easy to extend to multi-route scenarios and other fields. [ABSTRACT FROM AUTHOR]

This paper presents a novel approach for video-based person re-identification using multiple convolutional neural networks (CNNs). Unlike the previous work, we intend to extract a compact yet discriminative appearance representation from several frames rather than the whole sequence. Specifically, given a video, the representative frames are selected based on the walking profile of consecutive frames. A multiple CNN architecture incorporated with feature pooling is proposed to learn and compile the features of the selected representative frames into a compact description about the pedestrian for identification. Experiments are conducted on benchmark data sets to demonstrate the superiority of the proposed method over existing person re-identification approaches. [ABSTRACT FROM AUTHOR]

Time series classification is an important research topic in machine learning and data mining communities, since time series data exist in many application domains. Recent studies have shown that machine learning algorithms could benefit from good feature representation, explaining why deep learning has achieved breakthrough performance in many tasks. In deep learning, the convolutional neural network (CNN) is one of the most well-known approaches, since it incorporates feature learning and classification task in a unified network architecture. Although CNN has been successfully applied to image and text domains, it is still a challenge to apply CNN to time series data. This paper proposes a tensor scheme along with a novel deep learning architecture called multivariate convolutional neural network (MVCNN) for multivariate time series classification, in which the proposed architecture considers multivariate and lag-feature characteristics. We evaluate our proposed method with the prognostics and health management (PHM) 2015 challenge data, and compare with several algorithms. The experimental results indicate that the proposed method outperforms the other alternatives using the prediction score, which is the evaluation metric used by the PHM Society 2015 data challenge. Besides performance evaluation, we provide detailed analysis about the proposed method. [ABSTRACT FROM AUTHOR]

A multilevel cell (MLC) memristor that provides high-density on-chip memory has become a promising solution for energy-efficient artificial neural networks (ANNs). However, MLC storage that stores multiple bits per cell is prone to device variation. In this paper, the device variation tolerance of ANN training is investigated based on our cell-specific variation modeling method, which focuses on characterizing realistic cell-level variation. The parameters of cycle-to-cycle variation (CCV) and device-to-device variation (DDV) are extracted separately from the experimental data of a 39-nm, 1-Gb phase-change random access memory (PCRAM) array. A quantized neural network designed for low bit-width (≥6-bit) training is used for simulations to demonstrate the potential of MLC storage. Our results demonstrate that training is more vulnerable to DDV than CCV, and CCV can even compensate for accuracy degradation caused by severe DDV. As a result, for a multilayer perceptron (MLP) on Modified National Institute of Standards and Technology (MNIST) database, 95% accuracy can be achieved with three MLC PCRAM devices per weight, which is a 40% reduction in the number of cells compared with using conventional single-level cells (SLCs). If the size of DDV is reduced by half, then only two cells, that is 60% fewer cells than using SLC, are needed. [ABSTRACT FROM AUTHOR]

We propose a novel end-to-end approach, namely, the semantic-containing double-level embedding Bi-LSTM model (SCDE-Bi-LSTM), to solve the three key problems of Q&A matching in the Chinese medical field. In the similarity calculation of the Q&A core module, we propose a text similarity calculation method that contains semantic information, to solve the problem that previous Q&A methods do not incorporate the deep information of a sentence into the similarity calculations. For the sentence vector representation module, we present a double-level embedding sentence representation method to reduce the error caused by Chinese medical word segmentation. In addition, due to the problem of the attention mechanism tending to cause backward deviation of the features, we propose an improved algorithm based on Bi-LSTM in the feature extraction stage. The Q&A framework proposed in this paper not only retains important timing features but also loses low-frequency features and noise. Additionally, it is applicable to different domains. To verify the framework, extensive Chinese medical Q&A corpora are created. We run several state-of-the-art Q&A methods as contrastive experiments on the medical corpora and the current popular insuranceQA dataset under different performance measures. The experimental results on the medical corpora show that our framework significantly outperforms several strong baselines and achieves an improvement of top-1 accuracy of up to 14%, reaching 79.15%. [ABSTRACT FROM AUTHOR]

Change detection is one of the central problems in earth observation and was extensively investigated over recent decades. In this paper, we propose a novel recurrent convolutional neural network (ReCNN) architecture, which is trained to learn a joint spectral–spatial–temporal feature representation in a unified framework for change detection in multispectral images. To this end, we bring together a convolutional neural network and a recurrent neural network into one end-to-end network. The former is able to generate rich spectral-spatial feature representations, while the latter effectively analyzes temporal dependence in bitemporal images. In comparison with previous approaches to change detection, the proposed network architecture possesses three distinctive properties: 1) it is end-to-end trainable, in contrast to most existing methods whose components are separately trained or computed; 2) it naturally harnesses spatial information that has been proven to be beneficial to change detection task; and 3) it is capable of adaptively learning the temporal dependence between multitemporal images, unlike most of the algorithms that use fairly simple operation like image differencing or stacking. As far as we know, this is the first time that a recurrent convolutional network architecture has been proposed for multitemporal remote sensing image analysis. The proposed network is validated on real multispectral data sets. Both visual and quantitative analyses of the experimental results demonstrate competitive performance in the proposed mode. [ABSTRACT FROM AUTHOR]

Camera shake or target movement often leads to undesired blur effects in videos captured by a hand-held camera. Despite significant efforts having been devoted to video-deblur research, two major challenges remain: 1) how to model the spatio-temporal characteristics across both the spatial domain (i.e., image plane) and the temporal domain (i.e., neighboring frames) and 2) how to restore sharp image details with respect to the conventionally adopted metric of pixel-wise errors. In this paper, to address the first challenge, we propose a deblurring network (DBLRNet) for spatial-temporal learning by applying a 3D convolution to both the spatial and temporal domains. Our DBLRNet is able to capture jointly spatial and temporal information encoded in neighboring frames, which directly contributes to the improved video deblur performance. To tackle the second challenge, we leverage the developed DBLRNet as a generator in the generative adversarial network (GAN) architecture and employ a content loss in addition to an adversarial loss for efficient adversarial training. The developed network, which we name as deblurring GAN, is tested on two standard benchmarks and achieves the state-of-the-art performance. [ABSTRACT FROM AUTHOR]

The data space collected by a wireless sensor network (WSN) is the basis of data mining and data visualization. In the process of monitoring physical quantities with large time and space correlations, incomplete acquisition strategy with data interpolation can be adopted to reduce the deployment cost. To improve the performance of data interpolation in such a scenario, we proposed a robust data interpolation based on a back propagation artificial neural network operator. In this paper, a neural network learning operator is proposed based on the strong fault tolerance of artificial neural networks. The learning operator is trained by using the historical data of the data acquisition nodes of WSN and is transferred to estimate the value of physical quantities at the locations where sensors are not deployed. The experimental results show that our proposed method yields smaller interpolation error than the traditional inverse-distance-weighted interpolation (IDWI) method. [ABSTRACT FROM AUTHOR]