Search

• Gas turbine life management monitors and assesses turbine status and conditions. • Inlet and exit air passages impact gas turbine performance, not physical attributes. • Study gap: An incomplete gas-turbine model limits big data's predictive analysis. • Big data analytics drive optimized informed integrated health monitoring decisions for gas turbines. • Data mining extends gas turbine life by forecasting faults for the future. In addition to power generation, gas turbines (GT) are crucial components in many engineering applications, including those for aircraft, ships, and other machinery that needs a prime mover. One of the main concerns was predicting a comprehensive GT model, including intake, exit, and power-generator characteristics. Hence, this study provides a comprehensive review of GT's main components, parameters, faults, and predicting models using machine learning and data mining applications. Forty-four publications between 2014 and 2023 were chosen for this review study based on the primary keywords associated with the paper title. This study focuses solely on the GT model prediction aspects, considering the significance of field distribution, applications of data mining, research goals, benefits, constraints, and contributions to aviation, the oil and gas industry, and marine propulsion fields. Based on the examined studies, ANN, ELM, and KF applications show promise for potential GT life management. The typical limitations of GT life prediction, as observed in 93.2% of the review papers, involved the absence of a comprehensive GT model that incorporates all vibration factors and the use of substantial amounts of real data for predictive modelling. Another notable finding that underscores the knowledge gap in this area is the utilization of complete GT units to monitor unit life and facilitate life management. Apparently, the development of GT life management is still riddled with several limitations, which call for more improvement. [ABSTRACT FROM AUTHOR]

• A feature selection method based on binary dandelion algorithm is proposed. • The algorithm applies a sine-cosine operator and a restart strategy. • Mutual information and quick bit mutation improve the performance of the algorithm. • The algorithm performs well on datasets with larger dimensions. Feature selection (FS) is an important data preprocessing technology for machine learning and data mining. Metaheuristic algorithm (MH) has been widely used in feature selection because of its powerful search function. This paper presents an improved Binary Dandelion Algorithm using Sine Cosine operator and Restart strategy (SCRBDA) for feature selection. First, the sine cosine operator is used in the radius formula of the core dandelions (CD), which significantly enhances the ability of algorithm development and exploration. Secondly, the algorithm uses a restart strategy to increase its ability to get rid of local optimum. Thirdly, mutual information is used to guide the generation of some dandelions, which pays more attention to the correlation between the selected features and categories. Finally, quick bit mutation is used as the mutation strategy to improve the diversity of the population. The SCRBDA proposed in this paper was tested on 18 datasets of different sizes from UCI machine learning database. The SCRBDA was compared with 8 other classical feature selection algorithms, and the performance of the proposed algorithm was evaluated through feature subset size, classification accuracy, fitness value, and F1-score. The experimental results show that SCRBDA achieves the best performance, which has stronger feature reduction ability and achieves better overall performance on most datasets. Especially on large-scale datasets, SCRBDA can obtain extremely smaller feature subsets while maintaining much higher classification accuracy, and satisfactory F1-score. [ABSTRACT FROM AUTHOR]

Odor sensory evaluation is broadly applied in food, clothing, cosmetics, and other fields. Traditional artificial sensory evaluation has poor repeatability, and the machine olfaction represented by the electronic nose (E-nose) is difficult to reflect human feelings. Olfactory electroencephalogram (EEG) contains features associated with human olfactory preference, which has unique advantages in odor sensory evaluation. However, the difficulty of cross-subject olfactory EEG recognition dramatically limits its application. In this paper, a human–machine collaborative multimodal learning method is proposed for cross-subject olfactory preference recognition. Firstly, the olfactory EEG and E-nose multimodal data acquisition and preprocessing paradigms are established. Secondly, a complementary multimodal data mining strategy is proposed to effectively mine the individual and common features representing subjects' olfactory preferences from multimodal data. Finally, the cross-subject olfactory preference recognition is achieved in 24 subjects by fusing the extracted common and individual features, and the recognition effect is superior to the state-of-the-art recognition methods. Furthermore, the advantages of the proposed method in cross-subject olfactory preference recognition indicate its potential for practical odor evaluation applications. [ABSTRACT FROM AUTHOR]

In the era of data-driven decision-making, extracting meaningful insights from vast amounts of information is paramount. In organizing this data, classification methods play a pivotal role. Among the existing classification techniques, rule-based classifiers have gained prominence for their effectiveness and interpretability. One such is the R ule A ggregation C lassifi ER (RACER), known for its exceptional performance but limited when dealing with high-dimensional, low-sample-size datasets. In this paper, we introduce the R ule OP timized A ggregation C lassifier (ROPAC) as an extension of RACER that incorporates two different rule optimization methods, resulting in ROPAC-L and ROPAC-M, which aim to improve overall performance and classification accuracy. We evaluated this algorithm through experimentation with fifty datasets from reputable sources, such as the OpenML website and the UCI Machine Learning Repository. Furthermore, the proposed algorithm's accuracy is compared with fifteen well-known classifiers. Our results demonstrate that ROPAC outperforms all the other algorithms in terms of accuracy, showcasing its superiority and dominance in various data scenarios. • Proposed ROPAC, Rule OPtimized Aggregation Classifier, a novel rule-based classifier. • Introduced ROPAC-L and ROPAC-M to optimize rules and expand search space exploration. • Evaluated ROPAC on 50 diverse datasets, comparing accuracy with 15 famous algorithms. • Confirmed ROPAC-L as the most accurate, leading classifier based on the experiments. [ABSTRACT FROM AUTHOR]

Over the years, several neural network architectures have been proposed to process and represent texts using dense vectors (known as word embeddings): mathematical representations that encode the meaning of words or phrases. Word embeddings can be computed by many different algorithms, usually trained on large amounts of textual data aiming to capture semantic relationships between words. These embeddings revolutionized many Natural Language Processing applications, enabling more accurate and nuanced language understanding. Recently, it was demonstrated that it is possible to employ word embeddings to uncover latent knowledge, i.e., information that may be implicit in a set of texts and that would hardly be perceptible to humans. In this context, this study extends such strategy by combining different unsupervised models to accelerate discoveries in medicine. Our word embeddings were trained on a large corpus of medical papers related to Acute Myeloid Leukemia, a highly malignant form of cancer. Our study shows that established therapies could have been developed before their first proposal due to treatment testing notifications issued by our system up to 11 years in advance. The results show the potential of uncovering latent knowledge from the biomedical field to empower faster and more efficient drug testing for medical discoveries. • A new embedding-based system is proposed to uncover latent knowledge from literature. • The system coherently encodes biomedical knowledge about Acute Myeloid Leukemia. • The system is capable of anticipating discoveries years before they are published. • Medical discoveries can be sped up through a data-driven drug-testing strategy. [ABSTRACT FROM AUTHOR]

Drug-target interaction (DTI) prediction refers to the use of computational methods and models to predict the interaction between drugs and biological targets. DTI can help researchers understand the mechanism of action of drugs, discover new drug targets, and screen drug candidates. Recently, a large number of DTI models integrating deep drug-target interaction features have emerged to make up for the dilemma of incomplete information on shallow drug and target features. However, these models ignore the challenge of overlapping interaction information by simply integrating deep interaction information. This paper proposes a flexible DTI prediction with interactive information extraction and trade-off (FDTIIT) to address the above challenges. The main idea of FDTIIT is to use flexible mutual attention to extract interaction information about drugs and targets, and then limit the dependence between them to avoid redundant information. Specifically, FDTIIT mainly includes three parts: drug and target representation, drug-target interactive information extraction, and drug-target interactive information trade-off. Among them, the drug and target representation module mainly uses the graph convolutional network and convolutional neural network to learn the representation of drugs and targets. Then, the drug-target interactive information extraction module extracts the drug information hidden in the target and the target information hidden in the drug based on mutual attention. To avoid possible information overlap between drug representation and target representation after the fusion of interaction information, FDTIIT designs an interactive information trade-off module. This module limits the dependence between drug and target representation, providing more comprehensive information to support high-performance drug-target interaction prediction. Multiple experiments designed on three publicly available datasets validated FDTIIT's effectiveness. • We propose a flexible interactive information extraction module. • We consider the interaction information overlap problem for the first time. • A novel interactive information trade-off strategy is proposed. • We integrate shallow and deep interaction features to predict DTI. • Experimental results on multiple datasets validate the effectiveness. [ABSTRACT FROM AUTHOR]

The goal of pansharpening methods is to complement the spectral and spatial information contained in Multi-spectral (MS) and panchromatic (PAN) images to obtain the desired High-resolution multispectral (HRMS) image. The existing majority of pansharpening methods either extract feature information separately from the MS image and PAN image, or extract feature information after concatenating the MS image and PAN image. However, the entire extraction process lacks the utilization of complementary information and tends to generate redundant information, thereby leading to the loss of certain important information during the extraction process, which in turn affects the overall performance. In order to better utilize the complementary information between the MS image and PAN image and enhance the interpretability of the network, we propose the Deep Unfolding Convolutional-Dictionary Network (DUCD) for pansharpening in this paper. This network fully integrates complementary information between the MS image and PAN image to generate the final fused image. The entire network structure consists of two parts: The encoder and the decoder. In the encoder part of the network, we clarify the common and unique feature information between MS and PAN images by constructing an observation model. Simultaneously, we use the approximate gradient algorithm to continuously optimize the model and iteratively unfold it into a deep network structure. In the decoder part of the network, we concatenate the obtained common and specific information from MS and PAN images and pass them through convolutional and activation layers. Subsequently, they are input into the introduced Frequency Domain-based Transformer (FDT) module and an information-lossless inversible neural network(INN). This provides a more efficient method for establishing long-range dependency relationships between feature extraction and feature fusion. To demonstrate the effectiveness of our proposed method, we conduct extensive experiments on three benchmark datasets QB, GF2 and WV3. Experimental results show that our method outperforms the current SOTA Pansharpening methods in terms of performance. • Convolutional-Dictionary Network, Pansharpening. • Prior knowledge, Proximal gradient algorithm, strong interpretability. • Inversible neural network, Attention mechanism. [ABSTRACT FROM AUTHOR]

Class imbalance problems pose significant challenges in the field of data mining. The skewed distribution of classes in imbalanced datasets often leads conventional classification methods to neglect the importance of minority classes, favoring the majority ones. In this paper, we propose an imbalanced complemented subspace representation model with adaptive weight learning to address imbalanced classification challenges. This approach incorporates a novel regularization technique and an adaptive weighting mechanism. The regularization technique integrates a complemented subspace term based on space theory into the efficient collaborative representation-based classification (CRC) framework, enhancing the overall accuracy of existing CRC-based methods. Furthermore, it takes into account both intra-class and inter-class density information to assign greater weights to minority classes. This highlights the contribution of minority classes and mitigates bias towards majority classes. Additionally, it is demonstrated that the proposed model can be efficiently solved with a closed-form solution. Extensive experiments conducted on diverse imbalanced datasets showcase the superiority of our method over most state-of-the-art imbalanced classification algorithms. • A complemented subspace regularization term is introduced into CRC. • An adaptive weight learning strategy is present. • The closed-form solution is provided to ensure the efficiency of our model. • Experimental results show the effectiveness of our method. [ABSTRACT FROM AUTHOR]

Imbalanced data severely hinder the classification performance of learning-based algorithms and attract a great deal of attention from researchers. The undersampling method of selecting the majority class from samples through the prototype is one of the most common techniques to address class imbalance. However, traditional undersampling-based methods inherently lead to information loss. Meanwhile, they tend to perform undersampling for the majority class using distance-based locality methods, resulting in completely ignoring the density of the minority class samples. To this end, this paper proposes a novel undersampling method that incorporates the density distribution information of the minority class. Specifically, the probability density distribution of the minority class samples is learned by kernel density estimation, and the majority class samples located in the high-density band of the minority class are removed through filtering. Based on this, sampling fitness is proposed to evaluate the desirable value of each majority class sample to select information-rich samples. The research was carried out in 25 publicly available datasets and compared with state-of-art methods. The results show that our approach offers clear superiority. • The method learns the distribution of the minority class with time complexity O (n l o g n). • The sampling fitness combined with the roulette operator reduces information loss. • The experiments confirmed the effectiveness of the proposed method. [ABSTRACT FROM AUTHOR]

The state-of-the-art in automated processing of unstructured business documents has evolved from manual labor to advanced AI systems in the span of mere decades. Such systems involve learning techniques, rule or clause sets, neural models – either used alone or in combination – for the extraction to work. As an example, rule-based processes operate on a perceived layout or positioning of the information, whereas model-based frameworks adopt a semantic, and often uninspectable, approach. Verb-Based Semantic Role Labeling (VBSRL) is a novel system presented in a former paper that uses a hybrid foundation to inform the extraction phase via a set of rules modeling natural language. We propose a new VBSRL-based document processing method, aided by valuable and innovative architectural choices, which has been implemented for the Italian language and experimented upon with promising results. Even in its infancy, in fact, the first implementation of this system shows better results than comparable IE solutions, obtaining an aggregate, average F-measure of nearly 79%. • Automating business document analysis is crucial and time consuming in enterprises. • Classification and information extraction for unstructured documents are hard tasks. • Document processing method via pre-processing, normalization and post-processing. • Information Extraction as Conceptual Dependency Theory plus Semantic Role Labeling. • Performances on real case scenario show better results than comparable IE solutions. [ABSTRACT FROM AUTHOR]

The Internet of Things (IoT) has become an essential part of our daily lives. However, with the increasing use of IoT, the number of botnet attacks targeting resource-constrained IoT devices is also on the rise. To mitigate these threats, intrusion detection systems (IDSs) have been developed. However, traditional IDSs based on heavyweight deep/machine learning, fuzzy logic, rough set theories, or data mining techniques, often lack in detection accuracy and energy efficiency. Therefore, there is a crucial need for more lightweight, accurate, and energy-efficient IDSs capable of detecting a broad spectrum of cyber attacks. This paper presents a solution to these challenges by introducing lightweight and accurate IDSs that use a stochastic gradient descent classifier (SGDC) and four feature-selection algorithms based on a ridge regressor. The hyperparameters of the SGDC algorithm and ridge regressor model were fine-tuned to enhance the accuracy of IDSs while reducing computational complexity. Moreover, the fine-tuned feature selectors were used to decrease the dataset's dimensionality and improve the accuracy of IDSs. To evaluate the proposed IDSs, three network traffic datasets (KDD-CUP-1999, BotIoT-2018, and N-BaIoT-2021) were used. The systems achieved an average accuracy of 92.69%, and the number of features was reduced by an average of 79.93%. The results demonstrate that the proposed systems can be utilized for lightweight IDSs on resource-constrained IoT devices. Overall, this paper presents a significant contribution to the field of IDSs for IoT devices by offering an efficient and accurate solution. The proposed lightweight IDSs have the potential to enhance IoT security and privacy, safeguarding sensitive IoT data. • SGDC-based lightweight IDSs were developed for resource-constrained IoT devices. • The optimal hyperparameters of SGDC were determined with a grid-search algorithm. • The fine-tuned SGDC boosted accuracy and reduced IDSs packet processing time greatly. • The ridge regression-based feature selectors determined the most efficient features. • The fine-tuned feature selectors reduced feature space greatly and improved accuracy. [ABSTRACT FROM AUTHOR]

With the growing awareness of the limitations of unimodal data, research on joint classification using multimodal remote sensing data has garnered increasing attention. However, existing methods still have certain deficiencies in dealing with feature extraction and feature fusion of multimodal remote sensing data. In order to obtain more accurate classification results, it is crucial to fully exploit and utilize the complementary information in multimodal remote sensing data. In this paper, a multi-level interactive fusion network based on adversarial learning (MLIF-AL) is proposed for hyperspectral image (HSI) and light detection and ranging (LiDAR) data fusion classification. First, the feature extraction part based on generative adversarial network (GAN) utilizes adversarial training between the generator and the discriminator to guide the network to learn more discriminative and distinguished feature representations. Meanwhile, a cross-modal interactive information extraction (CMIIE) module is also designed for the generator encoding part to promote the interaction between multimodal data from a global perspective and realize the full utilization of multimodal complementary information. In addition, in the multi-level feature fusion classification (MLFFC) part, the complementarities between the features learned by the neural networks at each layer are comprehensively utilized to obtain higher-level multimodal fusion semantic information. Finally, the adversarial loss and classification loss are combined for network training. Extensive experiments on three commonly used HSI and LiDAR datasets and comparisons with state-of-the-art methods demonstrate the effectiveness and superiority of the model. [ABSTRACT FROM AUTHOR]

In the field of data mining, outlier detection is an important and challenging task. This paper focuses on studying the impacts of outliers on the performance of models learned from large-scale datasets while it is unknown whether a data point is outlier or not. In the proposed approach, a fuzzy c-means clustering algorithm is applied and outliers are defined as those that have greater membership values in the cluster and are located further away from the cluster centroid. Ideally, the sample with a higher membership value should be located closer to the cluster centroid. In this context, we calculate the weight of each sample using the AdaBoost algorithm, where a weight determines the representativeness of each sample within the data distribution. Additionally, in this study, the impact of weighted loss functions in different situations are discussed in detail. At last, our method is evaluated on 12 UCI datasets and the accuracy of our method is greater than 95% on some datasets, such as banknote 99.99%, biodeg 99.01%, optdigits 99.19%, and letters 97.37%. The experimental results show the efficiency and effectiveness of the proposed approach. • Outlier impact is investigated in a classification context. • Outliers are identified as having higher membership and found outside cluster center. • Different weighted loss functions are also discussed in detail in various situations. • The efficiency and effectiveness of the proposed method are verified experimentally. [ABSTRACT FROM AUTHOR]

The ubiquity sensory devices across scientific and industrial settings have made time-series data mining an important research topic in the IoT domain. Among all time-series mining techniques, the similarity search is considered the most essential and noteworthy because it is frequently employed as a fundamental subroutine for other procedures. The Dynamic Time Warping (DTW) was once considered the best similarity measure in time-series data mining community; however, two recent studies have demonstrated that the Move-Split-Merge (MSM) performs better than DTW in both supervised and unsupervised settings. Computing MSM between two time-series incurs costly computation because MSM has quadratic time complexity. Regrettably, there is little research on accelerating time-series similarity search under MSM. This paper provides an efficient method named DSEMSM for speeding up this procedure. DSEMSM utilizes dissimilarity space embedding to transform time-series into low-dimensional vectors. The filter-and-verification framework is subsequently employed to reduce the large number of actual MSM computations and to identify the final search results from the candidate set. The furthest prototype selection strategy and lower bound based technique are applied in DSEMSM to improve its retrieval accuracy and efficiency, respectively. We validate the effectiveness of the proposed method on a large number of datasets. The experimental results indicate that, in comparison to its relevant competitors, DSEMSM achieves a more stable speedup rate and higher retrieval accuracy. • The method DSEMSM is proposed for accelerating time-series similarity search. • The lower bound technique is used in DSEMSM to improve its efficiency further. • A Furthest approach is used in DSEMSM to perform prototype selection. • We conduct extensive experiments to validate the effectiveness of the proposals. [ABSTRACT FROM AUTHOR]

User intents are ever-changing, which requires deep learning models to have the ability to classify unknown intents. Meta-learning aims to solve this problem by improving the model's generalization ability to unknown intent. However, learning on a small amount of text can easily lead to overfitting of the model. Domain adaptation can help us train a more robust model. However, most existing methods only focus on global feature alignment and ignore alignment in subdomains. Therefore, in this study, we first consider the case where the model can maintain robustness with a small amount of data and then explore and mine the higher quality transferable features. Based on these ideas, we propose Dynamic Balance Domain Adaptation Meta-learning (DBDAML), which adaptively learns higher quality transferable features in both the global domain and subdomains. 1 1 in this paper, each subdomain represents the domain under a separate class. At the same time, we define a dynamic balance factor to enable DBDAML to dynamically focus on the global domain and subdomains. This allows the model to give different attention to different domain adaptations and prevents it from overfitting of a domain feature alignment. The dynamic balance factor is estimated by the contribution of different domain discriminators to the loss, which also makes it easy to calculate and accurate. Finally, we use the meta-learning framework to model the entire theoretical idea. Extensive experiments demonstrate that our approach achieves better performance than state-of-the-art baseline methods. • Multi-domain feature alignment can produce higher quality transferable features. • Model dynamic learning can alleviate domain feature alignment overfitting. • We manually labeled a high-quality Chinese intent detection dataset called InDs-CoV. • Extensive experiments demonstrate the superiority and effectiveness of our method. [ABSTRACT FROM AUTHOR]

Knowledge tracing (KT) aims to predict students' future performance by tracking their learning behaviors in intelligent tutoring systems (ITS). In KT, three main types of entities are involved: students, exercises, and knowledge concepts. Graph structures provide an effective framework for establishing relationships between different entities. However, existing KT methods have neglected complex connections and implicit relational features, thus facing challenges in capturing high-order information in educational data. To this end, this paper proposes MPSG, a M eta- P ath S tructured G raph method designed to harness high-order information between entities to pre-train informative exercise embeddings for improving KT. Technically, structured by different meta-paths, four relation graphs are derived to establish implicit cross-entity relationships. On each graph, the surrounding neighbors of each node are then obtained through an intimacy-based sampling strategy. Subsequently, during the representation learning stage, node features under different meta-path views are generated and then aggregated to obtain the final exercise embeddings. The learned embeddings are optimized through three auxiliary tasks, anchored within a self-supervised learning paradigm. Extensive experiments across four public datasets demonstrate that our method can significantly enhance the predictive performance of downstream KT models. • Introduction of an original graph pre-training method for knowledge tracing. • Advanced intimacy-based sampling strategy for each node's contextual surroundings. • Creation of three targeted constraints for effective self-supervised learning. • Predictive performance improvements for existing knowledge tracing models. [ABSTRACT FROM AUTHOR]

Conducting a maturity assessment allows companies to measure their readiness in implementing novel technologies. However, this task is challenging due to the multidimensional, complex, unpredictable, and non-linear nature of innovation. In this paper, we introduce an innovative approach to maturity assessment that enables both intra- and inter-company analysis. Our approach evaluates a company's absolute maturity score concerning a specific technology or area. By leveraging a Natural Language Processing pipeline applied to a semi-structured questionnaire we extract popular concepts from the answers and present them to a human expert for analysis. The expert can refine the analysis by adding or removing concepts as needed. Subsequently, we compute a similarity metric for each answer to determine a company's maturity in specific concepts. The output of our analysis is presented through human-readable plots, offering clear insights into the internal maturity level of the company and allowing for a comparison with competitors across the chosen concepts. To demonstrate the capabilities of our method, we provide a running example showcasing both quantitative and qualitative results of the analysis. Our approach demonstrates efficiency, with preprocessing completed in 1.967 ± 0.758 s, and information extraction in 0.074 ± 0.017 s on average, excluding human intervention time, and requiring low hardware resources. • We propose a novel approach to assess the maturity level in Digital Era. • We propose an embedded representation to provide inter/intra visual representation. • We measure how mature is a company profile related to a set of topic/technologies. • We design an advanced NLP approach based on deep learning to analyze questionnaires. [ABSTRACT FROM AUTHOR]

Outlier detection is an important research topic in data mining. The existing outlier detection method does not consider ordinal data, such as heterogeneous data. Fuzzy β covering is an information granularity representation tool, which can better fit the distribution of objects in real data and characterize the differences of objects. This paper studies outlier detection for heterogeneous data via fuzzy β covering. Firstly, some new properties of fuzzy β covering are proposed. Then, the fuzzy similarity relation between any two objects in heterogeneous data is defined, and fuzzy information granules are constructed by fuzzy β covering to obtain the new fuzzy approximation accuracy. Next, the outlier factor based on fuzzy β covering is established by integrating the outlier degree and weight function of fuzzy information granules. Moreover, the corresponding algorithm (called FBCOD algorithm) is designed. Finally, the FBCOD algorithm is compared with eight existing outlier detection algorithms on 12 UCI data sets. The experimental results of AUC value, statistical test and F1 measurement show that the FBCOD algorithm has better effectiveness and flexibility than some existing algorithms. • Some new properties of fuzzy β covering are proposed. • A new fuzzy approximation accuracy is obtained by fuzzy β covering. • The outlier factor based on fuzzy β covering is established. • The FBCOD algorithm is designed. [ABSTRACT FROM AUTHOR]

Feature selection refers to the process of identifying the most relevant and valuable features or characteristics in a dataset, and it is an important step that can improve the performance and accuracy of predictive models for machine learning and data mining. Feature selection is crucial in efficiently reducing the number of features, thereby enhancing classification accuracy. This, in turn, alleviates computational burdens and elevates the overall performance of machine learning algorithms. This paper extended the conventional manta ray foraging optimization (MRFO) algorithm to an improved binary MRFO (IBMFO) algorithm. IBMRFO serves as a search strategy for designing a wrapper-based feature selection approach. To commence, we introduce a novel mechanism, termed the chaotic tent map (CTM), aimed at initializing the population to fortify both the algorithm's exploitation capabilities and population diversity. Second, an adaptive somersault foraging (ASF) factor is tuned to avoid premature convergence. Finally, a binary mechanism is introduced to adapt the algorithm for binary feature selection dilemmas. Experiments are performed on 30 renowned UC Irvine machine learning repository datasets. The results of the student's t-test show that the classification algorithm has statistical significance. The findings unequivocally exhibit the superior performance of the proposed IBMRFO compared to other algorithms under scrutiny. Notably, the efficiency of the enhanced factors is assessed through rigorous testing. For post-publications supporting this work, readers can refer to https://github.com/ELF-CHEUNG/IBMRFO. • Novel chaotic tent map for population initialization from evolutionary computation. • Optimization methods based on enhanced evolutionary computation. • Adaptive factor enhances convergence rate and search efficiency of algorithm. • Extensive numerical and scientific simulations for verifications with UCI dataset. [ABSTRACT FROM AUTHOR]

• A new biomedical text summarization based on clustering and frequent itemsets mining. • Biomedical texts are represented using concepts instead of terms. • This combination enhances the quality of the generated summaries. • The clustering has a crucial impact on the discovered frequent itemsets. • Contribute all clusters in the sentence selection step yields to better performances. Text summarization has become an important research area, especially in the biomedical domain, where information overload is a major problem. In this paper, we propose a novel biomedical text summarization system that combines two popular data mining techniques: clustering and frequent itemset mining. Biomedical paper is expressed as a set of biomedical concepts using the UMLS metathesaurus. The K-means algorithm is used to cluster similar sentences. Then, the Apriori algorithm is applied to discover the frequent itemsets among the clustered sentences. Finally, the salient sentences from each cluster are selected to build the summary using the discovered frequent itemsets. For the evaluation step, we selected randomly 100 biomedical papers from the BioMed Central database full-text , and we evaluated the performances of our system by comparing the resulting summaries with the abstracts of these papers using the ROUGE metrics in term of recall, precision, and F-measure. We also compared the obtained summaries with those achieved by five well-known summarizers: TextRank, TextTeaser, SweSum, ItemSet Based Summarizer, Microsoft AutoSummarize , and two baselines: summarization using only the frequent itemsets mining (FRQ-CL), and summarization using only the clustering (CL-FRQ). The results demonstrate that this combination can successfully enhance the summarization performances, and the proposed system outperforms other tested summarizers. [ABSTRACT FROM AUTHOR]

Domain relation extraction (DRE) aims to understand domain semantics of unstructured text to mine structural knowledge. However, most existing DRE models may fail to fully represent the domain entity that is usually absent in the corpus of pre-trained language models. In addition, almost all these models directly use contextual semantics for relation classification that ignore purifying the task relevant features. To address these challenging problems, we propose a novel and effective M ulti- M odal S emantics F usion (MMSF) model, which can automatically capture domain semantics to discover the important semantics contained in images, thus enhancing the representations of the domain entity by exploiting the multi-modal semantics. Afterwards, we introduce heterogeneous graph neural networks to learn contextual semantics. To obtain the task relevant features for DRE, we design a new purified feature architecture by exploring the mutual information between contextual semantics and the labels of domain relation. With the enhanced representations of the domain entity and purified the task relevant features, the satisfactory results of relation classification can be guaranteed. Extensive experiments on two real domain relation extraction datasets demonstrate the superiority of our proposed model over several state-of-the-art models. The source code and experiment details of this paper can be obtained from https://github.com/SWT-AITeam/MMSF. • Proposing a novel MMSF model for domain relation extraction. • The MMSF can enrich the representations of the domain entity. • We introduce the IB theory to extract task relevant features. • Our MMSF achieves the state-of-the-art. [ABSTRACT FROM AUTHOR]

In real-life applications, data mining task involves extracting valuable but hidden information from massive data. How to effectively find out interesting patterns from large databases is a current topic. Sequential pattern mining is the most popular approach in data mining domain. Traditional sequential pattern mining research generally focuses on discovering frequent sequential patterns. However, the account of occurrence times of patterns does not adequately indicate their importance. For instance, frequent patterns (e.g., pencil and eraser) are not profitable, whereas infrequent patterns (e.g., extreme weather) are high-risk. To extract more useful information, researchers study a weighted sequential pattern mining task. In this paper, an efficient algorithm for weighted sequential pattern mining task, called EWSPM, is proposed. Two new strict upper bounds, namely MWEbound and MSRIWbound , are designed based on the concepts of maximum weight estimation (simplified as MWE) and maximum sumation of remaining item weights (simplified as MSRIW), respectively. These upper bounds achieve better pruning effects and reduce the size of search space during the mining process, which significantly shortens execution time. In addition, a database-projection method is employed to optimize memory usage. It addresses potential memory explosion issues in a certain degree. Finally, we also conducted extensive experiments on nine datasets (including real and synthetic). The experimental results demonstrate that the EWSPM algorithm is capable of mining all interesting patterns efficiently, with the smallest size of search space. Additionally, the novel algorithm also exhibits superior performance in terms of execution time and memory consumption. • A novel optimization strategy for projection technology is proposed to accelerate mining. • Maximum weighted estimation method evaluates weight values of low-level patterns. • The sum of weight values of remaining items reveals the maximum weight value of super-patterns. [ABSTRACT FROM AUTHOR]

Remote sensing scene understanding is crucial for extracting valuable information from high-resolution images, including object detection and classification. Traditional object detection methods face challenges in handling the diverse scales, orientations, and complex backgrounds present in remote sensing data. In this paper, we propose a novel remote sensing scene understanding system called multiscale-attention R-CNN (MSA R-CNN), which incorporates a super multiscale feature extraction network (SMENet) for enhanced feature extraction from multiscale images, an adaptive dynamic inner lateral (ADIL) connection module to tackle information loss in feature pyramid networks (FPN), and a distributed lightweight attention module (DLAM) to refine feature information processing. Furthermore, a new dataset combining the DIOR and DOTA datasets is introduced to extract the background information of detected objects and evaluate the proposed system's performance. MSA R-CNN achieved an mAP of 74.37% on the DIOR dataset when the gamma value was set to 0.2 and 81.97% on the DOTA dataset when the gamma value was set to 0.1 with the same learning rate, outperforming state-of-the-art models on both datasets. The proposed system demonstrates significant improvements in both object detection and background information extraction, providing a comprehensive solution for remote sensing scene understanding. • MSA R-CNN is proposed for remote sensing scene understanding. • SMENet enhances multi-scale feature extraction in MSA R-CNN. • ADIL module tackles FPN information loss. • DLAM refines feature information processing in FPN. • Achieved state-of-the-art performance on DIOR & DOTA dataset. [ABSTRACT FROM AUTHOR]

Document-level event extraction (DEE) is a branch of information extraction task that is valuable but difficult at present. To effectively implement DEE, previous works with better performance are often accompanied by larger parameters and computation. In this paper, we propose a novel framework based on global information enhancement and subgraph-level weakly contrastive learning, which bring better performance at lower extra computing costs. We verify the effectiveness of our method in a lightweight DEE model. The experimental results indicate that our proposed method outperforms other approaches in terms of the F1 score for both overall event extraction evaluation and single event extraction. In the inference phase, our model uses only 25% of the GPU memory required by the optimal model and maintains the advantage of 6.4 times faster inference speed. • We propose an approach for cross-sentence event extraction. • Our method injects context information with low extra computational costs. • The lightweight model has superior performance in the ChFinAnn dataset. • Our method shows a degree of flexibility when dealing with imbalanced data. • Our method has the potential to be implemented in tasks based on a graph network. [ABSTRACT FROM AUTHOR]

Association rule mining is intended for searching for the relationships between attributes in transaction databases. The whole process of rule discovery is very complex, and involves pre-processing techniques, a rule mining step, and post-processing, in which visualization is carried out. Visualization of discovered association rules is an essential step within the whole association rule mining pipeline, to enhance the understanding of users on the results of rule mining. Several association rule mining and visualization methods have been developed during the past decades. This review paper aims to create a literature review, identify the main techniques published in peer-reviewed literature, examine each method's main features, and present the main applications in the field. Defining the future steps of this research area is another goal of this review paper. [ABSTRACT FROM AUTHOR]

Artificial intelligence (AI) that utilizes neural networks (NNs) has a broad range of applications. However, NNs necessitate significant amounts of computation and data storage, which imposes considerable hardware demands and drives the need for AI chip research. To address this need, AI chip researchers must delve into extensive literature for entity information on hardware issues, architectures, optimizations, performances, and applications. Nevertheless, the influx of relevant papers has far surpassed their ability to read and absorb all the information. In this article, automatic information extraction in the AI chip domain using entity recognition techniques is conducted to alleviate the burden of paper reading for AI chip researchers. Our approach involves creating a manually annotated dataset called the ACER dataset to support automatic information extraction from literature in the field of AI chips. To address the challenge of recognizing entities with complex structures and lacking explicit features, the GIA-PME model is proposed, which utilizes a gated interaction attention mechanism and probability-matrix encoding. Our proposed approach enhances entity cognition by utilizing the keyword sequence of each entity type as prior knowledge. It also incorporates a dedicated embedding to learn the eigenvectors of entity structures. Finally, it combines the prior knowledge with eigenvectors using a designed gated interactive attention mechanism to assist with recognition. In addition, the proposed probability matrix encoding is used to detect nested entities to avoid information loss. Experimental results show that our GIA-PME model achieves the best performance compared to existing models, thus improving the strict/relaxed F1-score to 70.9/81.7 (+5.3 ∼ 9.1) on the ACER dataset. [ABSTRACT FROM AUTHOR]

• The prediction task of CoIL challenge 2000 is addressed in the paper. • Three different methods are proposed for direct mailing problem of CoIL challenge 2000. • The proposed methods outperform the method proposed by the winner of the challenge. • The proposed methods overcome, also, the unbalanced dataset issue of the problem. This paper presents some approaches based on data mining techniques to solve the prediction task of Computational Intelligence and Learning (CoIL) Challenge 2000. The prediction task of the contest is a direct mailing problem and the goal is to improve its response rate. The main issue in this competition is the incompatibility of the dataset in which the distribution of the classes of the target attribute is highly unbalanced. This in turn causes high error rate in identifying the minority class samples. Three different level methods including data-level, algorithm-level, and hybrid method are used to overcome this issue. The specificity, sensitivity, precision-recall, and ROC criteria are employed to compare the performance of the methods. Among the methods proposed in this paper, the best one performs much better than the winner of the competition. [ABSTRACT FROM AUTHOR]

Highlights • This approach utilises multidimensional process mining for internal logistics. • The event data is used for automatically mapping physical logistics activities. • We provide a discovery, performance and conformance analysis for each process cube. • The analysis results can be used to continuously quantify different types of waste. • A case study in the automotive industry evaluates the benefits of the approach. Abstract Pen and paper-based value stream mapping (VSM) is the established tool for recording processes, identifying waste and deriving recommendations for action. However, today, its application in manufacturing industry requires a high level of effort and is challenging due to product and process complexity, as well as dynamics. To overcome these shortcomings, we are developing a methodology to apply process mining (PM) to internal logistics for a mixed-model assembly line. The methodology combines multidimensional process mining (MDPM) techniques with proven principles of lean production and VSM. Firstly, internal logistics is modelled using existing event data by automatically mapping physical logistics activities (e.g. transport, store). Secondly, to enable PM, the event data is transformed into enriched event logs. Thirdly, the MDPM approach contains (1) a discovery analysis, (2) a performance analysis and (3) a conformance analysis including a reference process classification for each individual part and process. Finally, a waste analysis and strategy for practitioners is designed to identify and prioritise wasteful parts and processes. The methodology has been applied and evaluated in a case study at a German automotive manufacturer. In the case study, we analysed 7500 parts and 15 reference processes. An analysis for each individual part and process has not been available yet. We could both identify part-specific root causes (e.g. a long lead time) and process-specific root causes (e.g. a low trace fitness). The main contribution of this paper is to provide an MDPM methodology for practitioners to enable a continuous recording, evaluation and waste analysis of each individual part and process within internal logistics. [ABSTRACT FROM AUTHOR]

Highlights • A discretization approach based on mutual information concept was proposed. • This research aims to extract RUARs in accordance with discretization result. • A large dataset with about 12,000 medical data records is used to generate RUARs. • Our MID method provides a high coverage ratio of RUARs. • Graph-based visualization is used to represent RUARs clearly and easily. ABSTRACT In knowledge discovery studies, association rules mining has been extensively studied to discover hidden knowledge and relationships among set of items in a transactional dataset. Most research on association rule mining focuses on discovering frequent patterns based on the most frequent items occurring in the dataset. However, the process of extracting rare rules has received less attention. In medical dataset studies, the discovery of rare association rules (RARs) is more challenging, because it could likely be used to obtain more potentially rare and unusual knowledge for physicians, beside frequent association rules. Hence, the aim of this paper is to discover non-frequent or rare-unusual association rules (RUARs) from a stroke medical dataset to provide potential meaningful knowledge to the user domain. A discretization method needs to be performed as the data preprocessing step before generating rules. To the best of our knowledge, fewer studies have focused on the role of discretization results to support the extraction of a better amount and quality of RUARs, particularly for medical datasets. In addition, the extracted RUARs is expected to provide potential new unusual insights on stroke risk patterns. This paper applies mutual information measure to discretize a stroke examination dataset collected from a medical center in Taiwan. The interval merging method was proposed to simplify the discrete form and enrich the quality of generated rules. Towards the end, rare association rules, with relatively low support, were generated by employing the Apriori-Rare method accordingly. In addition, a filtering process was applied to the content of the rule itemsets to discover the expected set of RUARs for physicians. Furthermore, the extracted RUARs was analyzed based on the relative risk values toward the occurrence of stroke. Results indicated that the mutual information discretization outperformed the traditional discretization methods in terms of how the discretization scheme can support the extraction of RUARs with a better quantity and quality measurements for further analysis purpose in medical point of view. Moreover, the proposed method had a relatively higher number of RUARs. The knowledge of unusual rule patterns from rare association rules might provide potential new and unusual insights for medical pratitioners and increase the awareness of stroke examination results. [ABSTRACT FROM AUTHOR]

This paper presents a novel indoor tracking system built with common data mining techniques on radio frequency identification (RFID) tags readings. The system allows tracking of several objects in real-time in a smart home context and is a building block toward the deployment of an expert system to enable aging in place through technology. The indoor localization is modelled as a classification problem, instead of a regression problem as commonly seen in the literature. The paper is divided in two parts. The first one focuses on the ground truth collection that led to the model construction. The second part focuses on the filters that were designed to enable this model to be used in real-time in the smart home as a tracking software. Results from the first part show that most classifiers perform well on the static positioning of RFID tags task, with a random forest of 100 trees performing best at 97% accuracy and 0.9740974 F-Measure. However, collecting data to train the classifier is a long and tedious process. Results from the second part indicate that the accuracy of the random forest drops significantly when confronted with human interference. With the help of some filters, the tracking accuracy of objects can still be as high as 75%. Those results confirm that using passive RFID tags for an indoor tracking system is viable. Our system is easy to deploy and more flexible than trilateration or fingerprinting systems. [ABSTRACT FROM AUTHOR]

Mobile application (app) websites such as Google Play and AppStore allow users to review their downloaded apps. Such reviews can be useful for app users, as they may help users make an informed decision; such reviews can also be potentially useful for app developers, if they contain valuable information concerning user needs and requirements. However, in order to unleash the value of app reviews for mobile app development, intelligent mining tools that can help discern relevant reviews from irrelevant ones must be provided. This paper surveys the state of the art in the development of such tools and techniques behind them. To gain insight into the maturity of the current support mining tools, the paper will also find out what app development information these tools have discovered and what challenges they are facing. The results of this survey can inform the development of more effective and intelligent app review mining techniques and tools. [ABSTRACT FROM AUTHOR]

Along with future sustainability, factors such as environmental protection, co-prosperity, and ethical management are also gaining attention, resulting in the increased significance of the non-financial performance of companies. Accordingly, many institutions are evaluating the non-financial activities of companies using environmental, social, and governance (ESG) as evaluation indicators. However, the use of the current ESG rating as a reliable indicator has a limitation as the criteria are different for each evaluation institution and the ESG rating for the same company may differ when provided by different evaluation institutions. Accordingly, it is important to directly extract non-financial information generated by various media to provide objective ESG information, but the studies that focus on the need for automatic and direct extraction and classification of ESG information are limited. Therefore, this paper proposes a classifier that can discriminate ESG information. To train the ESG classifier, a dataset was constructed by manually labeling ESG data, and the ESG classifier recorded a classification accuracy of 86.66% for the 4-class classification problem of the constructed dataset. In addition, three application experiments were conducted to verify the usability of the proposed model. First, the results confirmed that the ESG classifier showed a significant performance of 83.96% accuracy for sectors not included in the training data. Second, the results qualitatively confirmed that the proposed model properly extracts ESG-related information from multi-source text data. Finally, the ESG dataset was additionally constructed through the pseudo-labeling technique, and the performance improvement of the data augmentation and classifier was verified. The ESG classifier proposed in this paper will provide appropriate ESG information to stakeholders. In future studies, we intend to extract and classify ESG-related information from more diverse types of data through an advanced ESG classifier. Further, we will use the information for investigating methods for reflecting the non-financial performance of companies in ESG ratings. • ESG is an indicator of a company's nonfinancial performance. • Develop a model for extracting ESG-related information. • Building a dataset for ESG information extraction and classification. • Applying ESG-classifier to other sectors and multisource text data. • Proposal of additional construction of ESG dataset using pseudo labeling technique. [ABSTRACT FROM AUTHOR]

With the rapid advancements in computer vision object detection networks, several detection networks based on remote sensing data have been proposed for oriented object detection. However, existing oriented networks have limitations in terms of feature extraction and oriented information extraction. To address these limitations, in this paper, we proposed an advanced adaptive points-based anchor-free oriented detection network called RA 2 DC-Net which includes a residual augment-convolutions (Res-AugConvs) module that uses residual structures and attention mechanisms to enhance feature focus information and minimize the loss of focus feature information. In addition, we proposed a method called adaptive deformable convolution (ADConv) to fine-tune custom convolution weights according to the features and generate high-quality adaptive offsets for accurate orientation information. Furthermore, we evaluated the performance of RA 2 DC-Net on two large-scale datasets: the Dataset for Object deTection in Aerial images (DOTA), the rotated object DetectIon in Optical Remote sensing images (DIOR-R) and the High-Resolution Ship Collection 2016 (HRSC2016). Experimental results demonstrated that RA 2 DC-Net achieved mAP values of 76.25%, 68.73% and 89.75% on the three datasets, respectively, with high AP values for various object classes on DOTA. • Decreased the continuous convolutions losses of oriented information in oriented object detection. • Enabling adaptive orientations of object features improves the precision of offset calculations. • Devising a new head structure facilitates focused oriented object features. [ABSTRACT FROM AUTHOR]

Measuring student growth and providing diagnostic feedback are core components of cognitive diagnostic assessment. However, most current cognitive diagnostic models solely rely on data from a single occasion to diagnose student skill states, overlooking the substantial long-term information encapsulated in the learning history from multiple occasions. In this paper, we propose a long short-term attentional cognitive diagnostic (LS-ENCD) model for skill growth assessment in intelligent tutoring systems. Specifically, we first embed exercise and student features into high-dimensional vectors. Then, we use a measurement module with a bilayer architecture to establish the interaction between students and exercises, considering guessing and slipping factors. To capture long short-term dependencies on historical data, we design the long short-term learning transfer module based on the attention mechanism, which computes state transfer weights by incorporating occasion time and mastery state. Finally, extensive experimental results on four public datasets demonstrate the superiority and good interpretability of our proposed model. [ABSTRACT FROM AUTHOR]

Feature extraction from planetary remote sensing images is a primary image processing task for object recognition, crater counter, morphological structure dimension and unpaired image co-registration. The paper presents a novel methodology to extract features directly from Bayer Pattern raw planetary images. Gradient information is extracted from Bayer Pattern image using standard edge operator that follows Color Difference Constancy (CDC) assumption. The proposed method's advantage is that it can skip the computationally intensive image processing pipeline and can have the Bayer Pattern raw planetary image flow directly for useful information extraction. Sobel Edge Detector is applied on Indian Mars Color Camera (MCC) Bayer Pattern raw images, and Gradient Magnitude Map (GMM) is generated at different Martian terrains. In addition, we have developed a direct image co-registration approach for MCC Bayer intensity raw image with respect to Mars Digital Image Model (MDIM) 2.1 reference using Mode-Mean Combo Patch Filler and Gradient Intensity induced Scale Invariant Feature Transform (GI-SIFT) based feature matching. The outlier matched points are removed by Feature Similarity Score guided Random Sample Consensus (FSS-RANSAC) estimation technique. The visual evaluation and quantitative metrics indicate that GMM from MCC Bayer Pattern raw image has negligible degradation with respect to GMM extracted from MCC demosaic image. The Root Mean Square Error (RMSE) is computed at different Mars regions, and it is found that the average image co-registration accuracy is less than 0.5 pixel. [ABSTRACT FROM AUTHOR]

Collaborative filtering (CF) is a widely used technique in recommender systems. While many CF methods primarily focus on collaborative signals derived from user–item interactions, they often overlook other types of similarities (e.g., user similarity in loving actors, movie similarity in sharing genres, etc.). These similarities offer the fine-grained knowledge to understand users and items, which can complement the collaborative signal. In this paper, we introduce a model that harnesses these additional similarities for improved recommendations. Our approach involves constructing both a user and an item relational graph, based on multiple item attributes. These graphs reflect semantic similarities from various perspectives among users and items. Then, we develop a recommendation framework that employs a dual graph neural network, integrating these graphs into the recommendation process. We name our approach I tem A ttribute-aware G raph C ollaborative F iltering (IAGCF). Through evaluations on six real-world datasets, we found that IAGCF surpasses several state-of-the-art recommenders. [ABSTRACT FROM AUTHOR]

The Knowledge Discovery from Data (KDD) process is widely used across various domains to get valuable insights from data. Many platforms, like KNIME or RapidMiner, offer effective tools for KDD analysts, allowing them to perform data analytics tasks in a visual fashion, without writing code. In recent years, the increasing availability of mobility data has led to a surge in KDD-based initiatives from both industry and academia in the Intelligent Transportation Systems (ITS) domain. Still, KDD platforms lack comprehensive support for some typical mobility data manipulation tasks. As a result, mobility data analysis still requires a significant coding phase, with reduced productivity and hindered replicability of results. To address this gap, this paper presents a novel solution aimed at supporting ITS data analysts in defining KDD processes more efficiently. More in detail, we extended the KNIME platform by introducing a collection of new components explicitly tailored to facilitate some peculiar KDD tasks from mobility data. These components encompass critical functionalities such as map coverage analysis, trajectory partitioning and map-matching. To showcase the effectiveness of the proposed solution, we used it to replicate a study published in the ITS data analytics domain. Thanks to our proposal, such replication can be accomplished in a few minutes and with just a few clicks, without any manual coding, resulting in a pipeline that is easier to understand, distribute and re-execute, also for domain experts with no programming experience. Our solution is open-source and freely downloadable from the Knime Hub. In this way, we aim to foster data-driven research and practice in the ITS field, by providing researchers and practitioners with more effective analytics tools to handle mobility data. • Visual analytics platforms lack support for handling mobility data in ITS scenarios. • We present a visual-based toolkit to support mobility data analytics for ITS. • The solution allows practitioners to perform complex analyses without writing code. • The solution is open-source and integrated within the KNIME Analytics Platform. • The effectiveness of the solution is assessed in a real-world ITS analytics scenario. [ABSTRACT FROM AUTHOR]

• State the limitations of the PatternList and dynamic Bit-vector data structures. • Introduce the pseudo-IDList data structure for the inter-sequence mining problem. • ISP-PI algorithm is proposed for inter-sequence mining using pseudo-IDList data. • Propose ISP-IC pruning method to reduce the number of generated patterns. Mining inter-sequence patterns represents a relatively novel research direction, yielding significant contributions to the field of data mining research since its inception. Its versatile applications span various domains, with numerous research avenues emerging as a result. However, it is worth noting that inter-sequence mining algorithms tend to generate a substantial volume of frequent patterns. To date, research efforts in the realm of inter-sequence pattern mining have predominantly focused on creating, copying, and storing all candidate information. This approach has led to potential performance inefficiencies, necessitating more resources than may be inherently required. It is worth highlighting the recent introduction of the pseudo-IDList data structure, which has demonstrated promise in enhancing both runtime efficiency and memory utilization during mining tasks. Nevertheless, this innovation has thus far found application exclusively in clickstream mining and sequential pattern mining contexts. In this paper, we propose an extension of this data structure for the mining of frequent inter-sequence patterns and introduce a novel algorithm named Inter-Sequence Pattern mining based on Pseudo-Index. Additionally, our proposed algorithm incorporates a pruning method known as Inter-Sequence Pattern Mining with Index Intersection Checking, designed to effectively curtail the proliferation of generated candidates. Our experimental results unequivocally demonstrate that the proposed algorithm excels in processing time and storage space utilization when compared to existing state-of-the-art algorithms designed for mining inter-sequence patterns. [ABSTRACT FROM AUTHOR]

Emotion recognition has recently attracted extensive interest due to its significant applications to human–computer interaction. The expression of human emotion depends on various verbal and non-verbal languages like audio, visual, text, etc. Emotion recognition is thus well suited as a multimodal rather than single-modal learning problem. Owing to the powerful feature learning capability, extensive deep learning methods have been recently leveraged to capture high-level emotional feature representations for multimodal emotion recognition (MER). Therefore, this paper makes the first effort in comprehensively summarize recent advances in deep learning-based multimodal emotion recognition (DL-MER) involved in audio, visual, and text modalities. We focus on: (1) MER milestones are given to summarize the development tendency of MER, and conventional multimodal emotional datasets are provided; (2) The core principles of typical deep learning models and its recent advancements are overviewed; (3) A systematic survey and taxonomy is provided to cover the state-of-the-art methods related to two key steps in a MER system, including feature extraction and multimodal information fusion; (4) The research challenges and open issues in this field are discussed, and promising future directions are given. [ABSTRACT FROM AUTHOR]

The study of High-Utility Itemset Mining (HUIM) and Frequent Itemset Mining (FIM) is crucial since it explains consumer behavior and offers actionable advice to improve business results. HUIM algorithms have been successfully established to identify high-utility itemsets, including those with negative utilities. The problem with these approaches is that they presume incorrectly that items with negative utility across transactions would always be losses. Products with positive profitability may seem negative when combined with other items to increase sales or reduce inventory. Using strict upper-bound approaches, this paper presents strategies for making database scanning more efficient and reducing the number of prospective candidates. We also prove that it is correct to use the proposed upper-bounds for pruning on several types of items in the database. Based on all the proposed solutions, we develop a novel algorithm to solve this problem efficiently. To demonstrate their efficiency, the algorithms are tested against states-of-art HUIM algorithm on diverse datasets with regard to size and characteristics with unstable negative profits. [ABSTRACT FROM AUTHOR]

The rapid growth of educational data creates the requirement to mine useful information from learning behavior patterns. The development of data mining technology makes educational data mining possible. The paper intends to use a public educational data set to study learning behavior patterns from the perspective of educational data mining, so as to promote the innovation of educational management. Firstly, in order to reduce the dimension of data analysis that facilitates the improvement in efficiency, principal component analysis is carried out to reduce the number of attributes in the data set. The significant attributes in the rotating principal component matrix rather than principal components which are not closely related to learning behavior patterns are extracted as the research variables. Then, a pseudo statistic is proposed to determine the number of clusters and the preprocessed data set is clustered according to the extracted attributes. The clustering results are applied to add class labels to the data, which is convenient for the later data training. Finally, six classification algorithms J48, K-Nearest Neighbor, Bayes Net, Random Forest, Support Vector Machine and Logit Boost are used to train the data with labels and build prediction models. At the same time, the performance and applicable conditions of six classifiers in terms of accuracy, efficiency, error, and so on are discussed and compared. It is found that the performance of the integrated algorithm is better than that of a single classifier. In the integrated algorithm, compared with Random Forest, the running time of Logit Boost is shorter. • Significant attributes are extracted as research variables. • A pseudo statistic is proposed to determine clustering number. • Clustering results are used as the label to analyze the learning behavior patterns. • Summarize and compare the performance and applicable conditions of six classifiers. [ABSTRACT FROM AUTHOR]

With the development of data mining techniques, user-generated data has become a valuable resource in diverse research areas. In product design research, many studies have been utilizing user data to discover implications for new product design. However, previous works focused on analyzing existing features, whereas companies also need strategies for new features. Some studies discovered new feature ideas from user data but did not provide design implications. This paper addresses the above limitation by extracting comprehensive design implications for both features from user data. The method first defines the lists of existing/new features and collects spec data for these features. Then, it constructs customer choice sets based on the online review and spec data. Regarding spec values, this study presents a newness merit function that reflects the changing value of new features and applies it to the choice sets. The final stage trains a neural network model based on choice sets and conducts SHAP (SHapley Additive exPlanations) on the model. The method draws design implications by further analyzing the resultant SHAP values. The suggested methodology was tested on real-world datasets. The result provides design guidance, including strategies for new features and recommended spec ranges for existing features. This article validates the result by showing that the obtained design implications are consistent with previous market research for product features. • Customer choice sets are constructed based on online reviews. • A newness merit function quantifies the value of new features in choice sets. • The analysis of SHAP values provides design guidance for new products. • Recommended spec values for existing features are presented. • Effective strategies for new features are suggested. [ABSTRACT FROM AUTHOR]

The mining of frequent itemsets and association rules is a core problem in data mining and an essential task in data analysis. In this paper, we present SufRec, a new algorithm for finding frequent itemsets and association rules. We give two versions. In both versions, the mining of the frequent itemsets is decomposed as a sequence of tasks. The first version (the SufRecDep algorithm) proceeds the tasks successively, each one using the results of the previous ones. The second version (the SufRecInd algorithm) performs the tasks independently of each other. Both versions are recursive with respect to the items and have thus the advantage to be particularly efficient for updating the mining process when new items are added to the database or when others are excluded. Moreover, the task-independent processing of SufRecInd makes it very easy to build parallel versions of SufRec. We present two parallel SufRec algorithms. With the first one, P-FIFO-SufRec, the processors perform the tasks according to the order in which the items appear in the database, preserving the recursive nature of SufRec. For second one, P-PAST-SufRec, the set of items is fixed and the tasks are pre-assigned to each processor. In order to evaluate the performance of SufRec, we carry out a consequent experimental study. In particular, we compare its running times with those of well-known parallel and non-parallel frequent itemsets mining algorithms. • Construction of SufRec, a new algorithm for frequent itemsets mining (FIM). • Construction of parallel versions of SufRec algorithm. • Experimental study comparing SufRec with well-known FIM algorithms. • Applications to the case where the list of items changes over time. [ABSTRACT FROM AUTHOR]

Mining incrementally closed item sets is an essential problem in data mining. Once closed item sets and their frequencies are found, the frequentation of a found closed item set is always determined. In recent times, concept lattice has been used as an intermediate structure for the purpose of mining incrementally (frequent) closed sets. However, lattice operations are very time-consuming when data fluctuates as well as the memory for lattice is consumed a lot when data becomes large. This paper proposes an intermediate structure called constructive set to produce closed sets along with their occurrence frequencies. The constructive set is constructed from a set of group patterns – an extended form of bit chains. This paper also proposes algorithms based on the constructive set for mining incrementally closed sets when adding and removing transactions. The proposed algorithms along with storing and calculating on bit data have significant advantages shown through experiments and comparisons. [ABSTRACT FROM AUTHOR]

Several biological research studies have shown that the number of individuals of certain species of anurans in a specific geographical region, and the evolution of this number over time, can be used as an indicator of climate change. To detect the presence of anurans, Wireless Sensor Networks (WSNs) are usually deployed with the aim of obtaining bio-acoustic information in a set covering numerous locations. However, the identification of the anuran species from a huge number of recordings usually involves an overwhelming task that has to be undertaken by expert and intelligent systems. Previous studies into this issue have proposed several classification techniques with a common approach: they all take into account the sequential characteristic of sounds by considering syllables or other kinds of vocal segments. In noisy sounds, as it is usually the case in recordings made in natural habitats, segmentation of the signal is no straightforward task and may cause low classification accuracy. To override this problem, a new non-sequential approach is proposed in this paper. It is based on considering very small pieces of sounds (frames) each of which is then classified without considering preceding or subsequent information. Up to nine frame-based classifiers are explored in this paper and their performances are compared to the most commonly used sequential classifier: the Hidden Markov Model (HMM). Additionally, for featuring the frames, many choices have been described, although the application of the Mel Frequency Cepstral Coefficients (MFCCs) has probably become the most common method. In this work, an alternative methodology is suggested: the use of a set of MPEG-7 parameters, which offers a normalized solution with a much greater semantic content. The experimental results have shown that the proposed method clearly outperforms the HMM, thereby showing the non-sequential classification of anuran sounds to be feasible. From among the algorithms tested, the decision-tree classifier has shown the best performance with an overall classification success rate of 87.30%, which is an especially striking result considering that the analyzed sounds were affected by a decidedly noisy background. [ABSTRACT FROM AUTHOR]

After digitally designing components of vehicles, a design team creates a virtual manufacturing environment that resembles actual manufacturing facilities. During this digital pre-assembly process, a review team examines each component, and records its problems and requirements in part verification reports. Once these reports are delivered to specific design team responsible for each part, the design team can make appropriate adjustments to their designs. This digital pre-assembly process can evaluate and prevent flaws in design prior to actual manufacturing, improving production quality and reducing manufacturing cost. As these reports are written in free text form, they, however, are not fully utilized for understanding problems arising from the design process. This paper proposes a method of applying text mining techniques on verification reports to extract insights for quality improvement. In this paper, following three text mining approaches are proposed: (1) Extracting n-grams for text preprocessing and constructing domain ontology; (2) Extracting meaningful insights from text preprocessing; (3) Creating intuitive visual tools to understand the extracted insights. The proposed method is applied on approximately 140,000 reports, and is validated through the quality of the answers obtained for the questions posed by the domain experts. The proposed method successfully extracts useful information from the text database, and provides intuitive graphical interface, thereby satisfying the need of the domain experts. This paper proposes a systematic framework of transforming huge amount of raw text data into intuitive visualization. Through this framework, meaningful knowledge can be extracted, analyzed and shared to improve the quality of the products. Main contribution of our paper is that it proposes a framework for knowledge extraction from pre-assembly process. Not only does it systematically arrange the data, but it also combines various data sources and creates a knowledge system to improve efficiency of the design process. [ABSTRACT FROM AUTHOR]

• Two phase MapReduce algorithm is proposed for incremental mining of sequential patterns. • Backward mining makes use of the knowledge obtained during the previous mining process. • Co-occurrence reverse map data structure efficiently generates the candidate sequences. • Candidate generation rules avoids the generation of too many false candidates. • Three novel early prune properties are introduced based on the study of item co-occurrences. Sequential Pattern Mining (SPM) is a popular data mining task with broad applications. With the advent of big data, traditional SPM algorithms are not scalable. Hence, many of the researchers have migrated to big data frameworks such as MapReduce and proposed distributed algorithms. However, the existing MapReduce algorithms assume the data as static and do not handle the incremental database updates. Moreover, they use to re-mine the updated database while new sequences are inserted. In this paper, we propose an efficient distributed algorithm for incremental sequential pattern mining (MR-INCSPM) using the MapReduce framework that can handle big data. The proposed algorithm incorporates the backward mining approach that efficiently makes use of the knowledge obtained during the previous mining process. Also, based on the study of item co-occurrences, we propose Co-occurrence Reverse Map (CRMAP) data structure. The issue of combinatorial explosion of candidate sequences is dealt using the proposed CRMAP data structure. Besides, a novel candidate generation and early prune mechanisms are designed using CRMAP to speed up the mining process. The proposed algorithm is evaluated on both the real and synthetic datasets. The experimental results prove the efficacy of MR-INCSPM with respect to processing time, memory and pruning efficiency. [ABSTRACT FROM AUTHOR]

• New notion of apprehensibility to represent the quality of pattern mining output. • Two constraints to improve apprehensibility and noise-resistance of pattern mining. • A generic, highly parameterizable and efficient pattern mining algorithm. • Experimentations on various datasets to evaluate the algorithm and both constraints. Sequential pattern mining has been the focus of many works, but still faces a tough challenge in the mining of large databases for both efficiency and apprehensibility of its resulting set. To overcome these issues, the most promising direction taken by the literature relies on the use of constraints, including the well-known closedness constraint. However, such a mining is not resistant to noise in data, a characteristic of most real-world data. The main research question raised in this paper is thus: how to efficiently mine an apprehensible set of sequential patterns from noisy data? In order to address this research question, we introduce 1) two original constraints designed for the mining of noisy data: the robustness and the extended-closedness constraints, 2) a generic pattern mining algorithm, C3Ro, designed to mine a wide range of sequential patterns, going from closed or maximal contiguous sequential patterns to closed or maximal regular sequential patterns. C3Ro is dedicated to practitioners and is able to manage their multiple constraints. C3Ro also is the first sequential pattern mining algorithm to be as generic and parameterizable. Extensive experiments have been conducted and reveal the high efficiency of C3Ro, especially in large datasets, over well-known algorithms from the literature. Additional experiments have been conducted on a real-world job offers noisy dataset, with the goal to mine activities. This experiment offers a more thorough insight into C3Ro algorithm: job market experts confirm that the constraints we introduced actually have a significant positive impact on the apprehensibility of the set of mined activities. [ABSTRACT FROM AUTHOR]

Mining frequent items from high-dimensional historical data (set-valued data) from massive users can extract the most routine data, playing a vital role in data mining. However, frequent item mining requires the collection of a large amount of user data, posing the potential risk of leaking user privacy. Local differential privacy is a mainstream privacy-preserving technique. It has been widely used for user privacy protection in various scenarios as it provides strict privacy protection. Mining frequent items from high-dimensional set-valued data under local differential privacy preservation has recently attracted much attention from researchers. Existing works usually use random sampling to reduce the communication cost of publishing perturbed data but hardly guarantee frequent item mining accuracy. This is because they sample minimal items from each user's high-dimensional set-value data (e.g., LDPMiner samples one item), making it difficult to focus on the scope of frequent item mining. The motivation of this paper to solve the above problem is that the frequent items mined from the data of a portion of users (e.g., half of the users) are similar to those mined from the data of the global users. Therefore, we randomly divide users into two groups and mine the set of candidate frequent items from the first group of users. Then, we focus on the candidate set in the second group of users and mine frequent items from it. Besides, we observe that the larger the sample size of user data, the better the frequent item mining accuracy and, subsequently, the higher the communication cost. Therefore, we randomly group the contents and randomly sample from each group, thus improving the frequent item mining accuracy by publishing more data than existing works. On this basis, we adaptively perturb the sampled group data according to the communication cost to trade off the communication cost and frequent item mining accuracy. Finally, we analyze the privacy and utility of our method theoretically. The experiments with state-of-the-art methods such as FIML, SVIM, and LDPMiner show that our proposed method improves about 15% in accuracy and 10% in utility for mining frequent items in high-dimensional set-valued data. • Protection of user privacy in frequent item mining by local differential privacy. • Grouping users to achieve different mining tasks. • Adaptively perturbs user data according to the content dimension. • Proof theoretically that the mechanism satisfies local differential privacy. [ABSTRACT FROM AUTHOR]

Keyword extraction is the foundation for solving various text mining tasks. However, the literature heavily relies on statistical, linguistic feature-based, or graph-based metrics to gauge corpus-representative keywords, the process of which is sensitive to preprocessing and stopword selection. In this paper, we propose a general-use keyword extraction model designed to work with document groups of various sizes, domains, and readability, as well as the existence of keyword labels. To extract a better selection of keywords, we employ a simple logistic regression model with the least absolute shrinkage and selection operator regularization (Tibshirani, 1996). The classification-based structure of our approach ensures learning words that distinctively characterize the given document group against the comparison groups, enhancing the representativeness of the extracted keywords. Furthermore, our model repeatedly modifies coefficients as it learns the document label classifiers, rather than relying directly on the term frequencies, reducing the model's sensitivity to words of very high and very low frequencies. We test our model's performance against numerous classic keyword extraction frameworks as baseline models using online customer reviews, news articles, and patent documentation. The results indicate that our proposed method has robust performance in terms of representability and distinctiveness across document groups with varying sizes, number of class labels, levels of readability, and domain. Additionally, we show that our model beats baseline models even when applied to documents without class labels compared with the baseline models. Given its generalizability and simplicity, we believe that our proposed model may serve as an easy-to-use, yet a powerful, general-use tool for keyword extraction, especially when working with various groups of documents from different domains. • We propose an all-purpose keyword extraction model without requiring keyword label. • Our model is scalable to corpora of any sizes and types with competitive performance. • Our method may serve as an easy-to-use yet powerful tool for keyword extraction. [ABSTRACT FROM AUTHOR]