Search results

In order to estimate the value of semi-automated subject indexing in operative library catalogues, the study aimed to investigate five different automated implementations of an open source software package on a large set of Swedish union catalogue metadata records, with Dewey Decimal Classification (DDC) as the target classification system. It also aimed to contribute to the body of research on aboutness and related challenges in automated subject indexing and evaluation.

On a sample of over 230,000 records with close to 12,000 distinct DDC classes, an open source tool Annif, developed by the National Library of Finland, was applied in the following implementations: lexical algorithm, support vector classifier, fastText, Omikuji Bonsai and an ensemble approach combing the former four. A qualitative study involving two senior catalogue librarians and three students of library and information studies was also conducted to investigate the value and inter-rater agreement of automatically assigned classes, on a sample of 60 records.

The best results were achieved using the ensemble approach that achieved 66.82% accuracy on the three-digit DDC classification task. The qualitative study confirmed earlier studies reporting low inter-rater agreement but also pointed to the potential value of automatically assigned classes as additional access points in information retrieval.

The paper presents an extensive study of automated classification in an operative library catalogue, accompanied by a qualitative study of automated classes. It demonstrates the value of applying semi-automated indexing in operative information retrieval systems.

An abundance of techniques has been presented so forth for waste classification but, they deliver inefficient results with low accuracy. Their achievement on various repositories is different and also, there is insufficiency of high-scale databases for training. The purpose of the study is to provide high security.

In this research, optimization-assisted federated learning (FL) is introduced for thermoplastic waste segregation and classification. The deep learning (DL) network trained by Archimedes Henry gas solubility optimization (AHGSO) is used for the classification of plastic and resin types. The deep quantum neural networks (DQNN) is used for first-level classification and the deep max-out network (DMN) is employed for second-level classification. This developed AHGSO is obtained by blending the features of Archimedes optimization algorithm (AOA) and Henry gas solubility optimization (HGSO). The entities included in this approach are nodes and servers. Local training is carried out depending on local data and updations to the server are performed. Then, the model is aggregated at the server. Thereafter, each node downloads the global model and the update training is executed depending on the downloaded global and the local model till it achieves the satisfied condition. Finally, local update and aggregation at the server is altered based on the average method. The Data tag suite (DATS_2022) dataset is used for multilevel thermoplastic waste segregation and classification.

By using the DQNN in first-level classification the designed optimization-assisted FL has gained an accuracy of 0.930, mean average precision (MAP) of 0.933, false positive rate (FPR) of 0.213, loss function of 0.211, mean square error (MSE) of 0.328 and root mean square error (RMSE) of 0.572. In the second level classification, by using DMN the accuracy, MAP, FPR, loss function, MSE and RMSE are 0.932, 0.935, 0.093, 0.068, 0.303 and 0.551.

The multilevel thermoplastic waste segregation and classification using the proposed model is accurate and improves the effectiveness of the classification.

With the increasing number of Web services, correct and efficient classification of Web services is crucial to improve the efficiency of service discovery. However, existing Web service classification approaches ignore the class overlap in Web services, resulting in poor accuracy of classification in practice. This paper aims to provide an approach to address this issue.

This paper proposes a label confusion and priori correction-based Web service classification approach. First, functional semantic representations of Web services descriptions are obtained based on BERT. Then, the ability of the model is enhanced to recognize and classify overlapping instances by using label confusion learning techniques; Finally, the predictive results are corrected based on the label prior distribution to further improve service classification effectiveness.

Experiments based on the ProgrammableWeb data set show that the proposed model demonstrates 4.3%, 3.2% and 1% improvement in Macro-F1 value compared to the ServeNet-BERT, BERT-DPCNN and CARL-NET, respectively.

This paper proposes a Web service classification approach for the overlapping categories of Web services and improve the accuracy of Web services classification.

Single-shot multi-category clothing recognition and retrieval play a crucial role in online searching and offline settlement scenarios. Existing clothing recognition methods based on RGBD clothing images often suffer from high-dimensional feature representations, leading to compromised performance and efficiency.

To address this issue, this paper proposes a novel method called Manifold Embedded Discriminative Feature Selection (MEDFS) to select global and local features, thereby reducing the dimensionality of the feature representation and improving performance. Specifically, by combining three global features and three local features, a low-dimensional embedding is constructed to capture the correlations between features and categories. The MEDFS method designs an optimization framework utilizing manifold mapping and sparse regularization to achieve feature selection. The optimization objective is solved using an alternating iterative strategy, ensuring convergence.

Empirical studies conducted on a publicly available RGBD clothing image dataset demonstrate that the proposed MEDFS method achieves highly competitive clothing classification performance while maintaining efficiency in clothing recognition and retrieval.

This paper introduces a novel approach for multi-category clothing recognition and retrieval, incorporating the selection of global and local features. The proposed method holds potential for practical applications in real-world clothing scenarios.

Higher education plays an essential role in achieving the United Nations sustainable development goals (SDGs). However, there are only scattered studies on monitoring how universities promote SDGs through their curriculum. The purpose of this study is to investigate the connection of existing common core courses in a university to SDG education. In particular, this study wanted to know how common core courses can be classified by machine-learning approach according to SDGs.

In this report, the authors used machine learning techniques to tag the 166 common core courses in a university with SDGs and then analyzed the results based on visualizations. The training data set comes from the OSDG public community data set which the community had verified. Meanwhile, key descriptions of common core courses had been used for the classification. The study used the multinomial logistic regression algorithm for the classification. Descriptive analysis at course-level, theme-level and curriculum-level had been included to illustrate the proposed approach’s functions.

The results indicate that the machine-learning classification approach can significantly accelerate the SDG classification of courses. However, currently, it cannot replace human classification due to the complexity of the problem and the lack of relevant training data.

The study can achieve a more accurate model training through adopting advanced machine learning algorithms (e.g. deep learning, multioutput multiclass machine learning algorithms); developing a more effective test data set by extracting more relevant information from syllabus and learning materials; expanding the training data set of SDGs that currently have insufficient records (e.g. SDG 12); and replacing the existing training data set from OSDG by authentic education-related documents (such as course syllabus) with SDG classifications. The performance of the algorithm should also be compared to other computer-based and human-based SDG classification approaches for cross-checking the results, with a systematic evaluation framework. Furthermore, the study can be analyzed by circulating results to students and understanding how they would interpret and use the results for choosing courses for studying. Furthermore, the study mainly focused on the classification of topics that are taught in courses but cannot measure the effectiveness of adopted pedagogies, assessment strategies and competency development strategies in courses. The study can also conduct analysis based on assessment tasks and rubrics of courses to see whether the assessment tasks can help students understand and take action on SDGs.

The proposed approach explores the possibility of using machine learning for SDG classifications in scale.

Consequence prediction is an emerging topic in safety management concerning the severity outcome of accidents. In practical applications, it is usually implemented through supervised learning methods; however, the evaluation of classification results remains a challenge. The previous studies mostly adopted simplex evaluation based on empirical and quantitative assessment strategies. This paper aims to shed new light on the comprehensive evaluation and comparison of diverse classification methods through visualization, clustering and ranking techniques.

An empirical study is conducted using 9 state-of-the-art classification methods on a real-world data set of 653 construction accidents in China for predicting the consequence with respect to 39 carefully featured factors and accident type. The proposed comprehensive evaluation enriches the interpretation of classification results from different perspectives. Furthermore, the critical factors leading to severe construction accidents are identified by analyzing the coefficients of a logistic regression model.

This paper identifies the critical factors that significantly influence the consequence of construction accidents, which include accident type (particularly collapse), improper accident reporting and handling (E21), inadequate supervision engineers (O41), no special safety department (O11), delayed or low-quality drawings (T11), unqualified contractor (C21), schedule pressure (C11), multi-level subcontracting (C22), lacking safety examination (S22), improper operation of mechanical equipment (R11) and improper construction procedure arrangement (T21). The prediction models and findings of critical factors help make safety intervention measures in a targeted way and enhance the experience of safety professionals in the construction industry.

The empirical study using some well-known classification methods for forecasting the consequences of construction accidents provides some evidence for the comprehensive evaluation of multiple classifiers. These techniques can be used jointly with other evaluation approaches for a comprehensive understanding of the classification algorithms. Despite the limitation of specific methods used in the study, the presented methodology can be configured with other classification methods and performance metrics and even applied to other decision-making problems such as clustering.

This study sheds new light on the comprehensive comparison and evaluation of classification results through visualization, clustering and ranking techniques using an empirical study of consequence prediction of construction accidents. The relevance of construction accident type is discussed with the severity of accidents. The critical factors influencing the accident consequence are identified for the sake of taking prevention measures for risk reduction. The proposed method can be applied to other decision-making tasks where the evaluation is involved as an important component.

The purpose of this study is twofold. On the one hand, it studies the impact of IFRS 9 adoption on the firm value; and on the other hand, it investigates the impact of the classification of financial assets on the firm value.

The study covers a sample of 55 listed banks in the Middle Eastern and North African (MENA) region. Data is collected for three years (2017–2019).

The findings show that banks’ value is not impacted by IFRS 9 adoption but by financial assets’ classification. Firm value is positively affected by fair value through other comprehensive income assets, while it is negatively affected by amortized cost and fair value through profit or loss assets. The results of the additional analysis show consistent outcomes.

This research reveals important managerial implications. Priority should be given to the financial assets’ classification strategy following the adoption of IFRS 9 to boost the market valuation of banks. It may be useful for investors, managers and regulators in their decision-making.

This study enriches previous research as IFRS 9 is a new standard, and its adoption consequences need to be investigated. A few recent studies have focused on IFRS 9 as a whole or on other parts of IFRS 9, namely, the impairment regime and hedge accounting and concern developed contexts. However, this research adds to the knowledge of capital market studies by investigating the application of IFRS 9 in terms of classification in the MENA region.

The purpose of this paper is to describe a new approach to sentence representation learning leading to text classification using Bidirectional Encoder Representations from Transformers (BERT) embeddings. This work proposes a novel BERT-convolutional neural network (CNN)-based model for sentence representation learning and text classification. The proposed model can be used by industries that work in the area of classification of similarity scores between the texts and sentiments and opinion analysis.

The approach developed is based on the use of the BERT model to provide distinct features from its transformer encoder layers to the CNNs to achieve multi-layer feature fusion. To achieve multi-layer feature fusion, the distinct feature vectors of the last three layers of the BERT are passed to three separate CNN layers to generate a rich feature representation that can be used for extracting the keywords in the sentences. For sentence representation learning and text classification, the proposed model is trained and tested on the Stanford Sentiment Treebank-2 (SST-2) data set for sentiment analysis and the Quora Question Pair (QQP) data set for sentence classification. To obtain benchmark results, a selective training approach has been applied with the proposed model.

On the SST-2 data set, the proposed model achieved an accuracy of 92.90%, whereas, on the QQP data set, it achieved an accuracy of 91.51%. For other evaluation metrics such as precision, recall and F1 Score, the results obtained are overwhelming. The results with the proposed model are 1.17%–1.2% better as compared to the original BERT model on the SST-2 and QQP data sets.

The novelty of the proposed model lies in the multi-layer feature fusion between the last three layers of the BERT model with CNN layers and the selective training approach based on gated pruning to achieve benchmark results.

Feature extraction from 3D datasets is a current problem. Machine learning is an important tool for classification of complex 3D datasets. Machine learning classification techniques are widely used in various fields, such as text classification, pattern recognition, medical disease analysis, etc. The aim of this study is to apply the most popular classification and regression methods to determine the best classification and regression method based on the geodesics.

The feature vector is determined by the unit normal vector and the unit principal vector at each point of the 3D surface along with the point coordinates themselves. Moreover, different examples are compared according to the classification methods in terms of accuracy and the regression algorithms in terms of R-squared value.

Several surface examples are analyzed for the feature vector using classification (31 methods) and regression (23 methods) machine learning algorithms. In addition, two ensemble methods XGBoost and LightGBM are used for classification and regression. Also, the scores for each surface example are compared.

To the best of the author’s knowledge, this is the first study to analyze datasets based on geodesics using machine learning algorithms for classification and regression.

This study aims to examine the impact of national culture on classification shifting in Eastern European Member States of EU Eastern European countries (EEU) vis-à-vis the Western Member States of EU (WEU). The EEU provides a unique sample to study the quality of financial reporting that the authors measure with classification shifting given that for more than five decades they were following the model of a centrally planned economy, where market-based financial reporting was absent. Yet, the EEU transitioned to a market-based economy and completed its accession to the EU.

This study uses a panel data set of firm year observations from 1996 and 2020 that covers the full transition of EEU. This empirical analysis is based on fixed effects panel regression analysis where the authors report a plethora of identifications.

This study finds classification shifting in the EEU countries since their transition to the market-based economy, though they have no long record of market-based financial reporting. This study also notices that cultural factors are associated with classification shifting across all Member States of the EU. This study further examines the impact of interactions between cultural characteristics and special items and reveal variability between WEU and EEU. As part of the robustness analysis, this study also tests the impact of culture on real earnings management measures for both WEU vs EEU, confirming the variability of the impact of culture on earnings management.

Future research could explore the role of religion differences in WEU vis-à-vis EEU states, as they are also subject to cultural differences.

The findings are important for regulators, external monitors and investors, as they show that cultural factors affect earnings management with some variability across countries in the EU, and they should be acknowledged in policymaking.

The findings show that cultural differences between EEU and the “old” Member States of the EU could explain classification shifting.

To the best of the authors’ knowledge, this is the first study that sheds light on the impact of national culture on classification shifting in EEU of EU vis-à-vis the “old” WEU of EU.