Search Results (13)

Many readers continue to pursue Chinese long novels in the past several decades because of diverse characters and fascinating plots. The climactic chapter is an important part of a Chinese long novel, where the key conflict develops to the extreme point. However, how to quickly and accurately recognize the climactic chapter remains a common problem for many readers in their reading choices. This paper conducts research on recognizing the climactic chapter of a Chinese long novel by accurately describing its plot. The proposed method consists of two parts; one is the extraction of key elements, such as viewpoint paragraphs, non-viewpoint paragraphs, chapter keywords, major characters etc. The other part is the climactic chapter recognition, which applies the Bidirectional Gate Recurrent Unit (BiGRU) model and the multi-head attention to recognize the climactic chapter, on the basis of the chapter plot description matrix. Comparative experiments on the corpus named The Condor Trilogy show that the proposed method in this paper has a better recognition performance compared with the existing models, such as Naive Bayesian (NB), Support Vector Machine (SVM), Roberta-large, and the Bidirectional Long-Short Term Memory (BiLSTM) network. Ablation experiments validated the effectiveness of primary components in the proposed method. Full article

This study addresses the challenge of automating the creation of Exchange Information Requirements (EIRs) for construction projects using Building Information Modelling (BIM) and Digital Twins, as specified in the ISO 19650 standard. This paper focuses on automating the classification of EIR paragraphs according to the ISO 19650 standard’s categories, aiming to improve information management in construction projects. It addresses a gap in applying AI to enhance BIM project management, where barriers often include technological limitations, a shortage of specialists, and limited understanding of the methodology. The proposed method uses Word2Vec for text vectorisation and Support Vector Machines (SVMs) with an RBF kernel for text classification, and it attempts to apply Word2Vec with cosine similarity for text generation. The model achieved an average F1 score of 0.7, with predicted categories for provided sentences and similar matches for selected phrases. While the text classification results were promising, further refinement is required for the text generation component. This study concludes that integrating AI tools such as Word2Vec and SVM offers a feasible solution for enhancing EIR creation. However, further development of text generation, particularly using advanced techniques such as GPT, is recommended. These findings contribute to improving managing complex construction projects and advancing digitalization in the AECO sector. Full article

This is an overview paper. This paper is an attempt to show that fractional calculus can be reached through statistical distribution theory. This paper brings together results on fractional integrals and fractional derivatives of the first and second kinds in the real and complex domains in the scalar, vector, and matrix-variate cases, and shows that all these results can be reached through statistical distribution theory. It is shown that the whole area of fractional integrals can be reached through distributions of products and ratios in the scalar variable case and distributions of symmetric products and symmetric ratios in the matrix-variate cases. While summarizing the materials, the real domain results are also listed side by side with the complex domain results so that a comparative study is possible. Fractional integrals and derivatives in the real domain mean that the parameters involved could be real or complex with appropriate conditions, the arbitrary function is real-valued, and the variables involved are all real. These in the complex domain mean that the parameters could be real or complex and the arbitrary function is still real-valued but the variables involved are in the complex domain. Fully complex domain means the variables as well as the arbitrary function are in the complex domain. Most of the materials on fractional integrals and fractional derivatives involving a single matrix or a number of matrices in the real or complex domain are of this author. Slight modifications of the results, compared with the published works in various papers, are there in various sections. In the paragraph on notations, the lemmas that are taken from this author’s own book on Jacobians are common with published works and hence the similarity index with this author’s works will be high. Section Matrix-Variate Joint Distributions and Fractional Integrals in Many Matrix-Variate Cases material on a statistical approach to Kiryakova’s multi-index fractional integral and its extension to the real scalar case of second kind integrals as well as extensions of first and second kind integrals to real and complex matrix-variate cases are believed to be new. Matrix differential operators are introduced in Section Fractional Derivatives and, with the help of these operators, fractional derivatives are constructed from the corresponding fractional integrals. These operators are applicable in a large variety of functions. Applicability is shown through identities created from scale transformed gamma random variables. Some concluding remarks are given and some open problems are pointed out in Section Concluding Remarks. Full article

Authorship attribution for less-resourced languages like Romanian, characterized by the scarcity of large, annotated datasets and the limited number of available NLP tools, poses unique challenges. This study focuses on a hybrid Transformer combining handcrafted linguistic features, ranging from surface indices like word frequencies to syntax, semantics, and discourse markers, with contextualized embeddings from a Romanian BERT encoder. The methodology involves extracting contextualized representations from a pre-trained Romanian BERT model and concatenating them with linguistic features, selected using the Kruskal–Wallis mean rank, to create a hybrid input vector for a classification layer. We compare this approach with a baseline ensemble of seven machine learning classifiers for authorship attribution employing majority soft voting. We conduct studies on both long texts (full texts) and short texts (paragraphs), with 19 authors and a subset of 10. Our hybrid Transformer outperforms existing methods, achieving an F1 score of 0.87 on the full dataset of the 19-author set (an 11% enhancement) and an F1 score of 0.95 on the 10-author subset (an increase of 10% over previous research studies). We conduct linguistic analysis leveraging textual complexity indices and employ McNemar and Cochran’s Q statistical tests to evaluate the performance evolution across the best three models, while highlighting patterns in misclassifications. Our research contributes to diversifying methodologies for effective authorship attribution in resource-constrained linguistic environments. Furthermore, we publicly release the full dataset and the codebase associated with this study to encourage further exploration and development in this field. Full article

The aedes mosquito-borne dengue viruses cause dengue fever, an arboviral disease (DENVs). In 2019, the World Health Organization forecasts a yearly occurrence of infections from 100 million to 400 million, the maximum number of dengue cases ever testified worldwide, prompting WHO to label the virus one of the world’s top ten public health risks. Dengue hemorrhagic fever can progress into dengue shock syndrome, which can be fatal. Dengue hemorrhagic fever can also advance into dengue shock syndrome. To provide accessible and timely supportive care and therapy, it is necessary to have indispensable practical instruments that accurately differentiate Dengue and its subcategories in the early stages of illness development. Dengue fever can be predicted in advance, saving one’s life by warning them to seek proper diagnosis and treatment. Predicting infectious diseases such as dengue is difficult, and most forecast systems are still in their primary stages. In developing dengue predictive models, data from microarrays and RNA-Seq have been used significantly. Bayesian inferences and support vector machine algorithms are two examples of statistical methods that can mine opinions and analyze sentiment from text. In general, these methods are not very strong semantically, and they only work effectively when the text passage inputs are at the level of the page or the paragraph; they are poor miners of sentiment at the level of the sentence or the phrase. In this research, we propose to construct a machine learning method to forecast dengue fever. Full article

The paper presents a machine-learning based approach to text-to-ontology mapping. We explore a possibility of matching texts to the relevant ontologies using a combination of artificial neural networks and classifiers. Ontologies are formal specifications of the shared conceptualizations of application domains. While describing the same domain, different ontologies might be created by different domain experts. To enhance the reasoning and data handling of concepts in scientific papers, finding the best fitting ontology regarding description of the concepts contained in a text corpus. The approach presented in this work attempts to solve this by selection of a representative text paragraph from a set of scientific papers, which are used as data set. Then, using a pre-trained and fine-tuned Transformer, the paragraph is embedded into a vector space. Finally, the embedded vector becomes classified with respect to its relevance regarding a selected target ontology. To construct representative embeddings, we experiment with different training pipelines for natural language processing models. Those embeddings in turn are later used in the task of matching text to ontology. Finally, the result is assessed by compressing and visualizing the latent space and exploring the mappings between text fragments from a database and the set of chosen ontologies. To confirm the differences in behavior of the proposed ontology mapper models, we test five statistical hypotheses about their relative performance on ontology classification. To categorize the output from the Transformer, different classifiers are considered. These classifiers are, in detail, the Support Vector Machine (SVM), k-Nearest Neighbor, Gaussian Process, Random Forest, and Multilayer Perceptron. Application of these classifiers in a domain of scientific texts concerning catalysis research and respective ontologies, the suitability of the classifiers is evaluated, where the best result was achieved by the SVM classifier. Full article

To explore and understand the state-of-the-art innovations in any given domain, researchers often need to study many domain patents and synthesize their knowledge content. This study provides a smart patent knowledge graph generation system, adopting a machine learning (ML) natural language modeling approach, to help researchers grasp the patent knowledge by generating deep knowledge graphs. This research focuses on converting chemical utility patents, consisting of chemistries and chemical processes, into summarized knowledge graphs. The research methods are in two parts, i.e., the visualization of the chemical processes in the chemical patents’ most relevant paragraphs and a knowledge graph of any domain-specific collection of patent texts. The ML language modeling algorithms, including ALBERT for text vectorization, Sentence-BERT for sentence classification, and KeyBERT for keyword extraction, are adopted. These models are trained and tested in the case study using 879 chemical patents in the carbon capture domain. The results demonstrate that the average retention rate of the summary graphs for five clustered patent texts exceeds 80%. The proposed approach is novel and proven to be reliable in graphical deep knowledge representation. Full article

Text classification aims to assign labels to textual units such as documents, sentences and paragraphs. Some applications of text classification include sentiment classification and news categorization. In this paper, we present a soft computing technique-based algorithm (TSC) to classify sentiment polarities of tweets as well as news categories from text. The TSC algorithm is a supervised learning method based on tolerance near sets. Near sets theory is a more recent soft computing methodology inspired by rough sets where instead of set approximation operators used by rough sets to induce tolerance classes, the tolerance classes are directly induced from the feature vectors using a tolerance level parameter and a distance function. The proposed TSC algorithm takes advantage of the recent advances in efficient feature extraction and vector generation from pre-trained bidirectional transformer encoders for creating tolerance classes. Experiments were performed on ten well-researched datasets which include both short and long text. Both pre-trained SBERT and TF-IDF vectors were used in the experimental analysis. Results from transformer-based vectors demonstrate that TSC outperforms five well-known machine learning algorithms on four datasets, and it is comparable with all other datasets based on the weighted F1, Precision and Recall scores. The highest AUC-ROC (Area under the Receiver Operating Characteristics) score was obtained in two datasets and comparable in six other datasets. The highest ROC-PRC (Area under the Precision–Recall Curve) score was obtained in one dataset and comparable in four other datasets. Additionally, significant differences were observed in most comparisons when examining the statistical difference between the weighted F1-score of TSC and other classifiers using a Wilcoxon signed-ranks test. Full article

In the domain of law and legal systems, jurisprudence principles (JPs) are considered major sources of legislative reasoning by jurisprudence scholars. Generally accepted JPs are often used to support the reasoning for a given jurisprudence case (JC). Although eliciting the JPs associated with a specific JC is a central task of legislative reasoning, it is complex and requires expertise, knowledge of the domain, and significant and lengthy human exertion by jurisprudence scholars. This study aimed to leverage advances in language modeling to support the task of JP elicitation. We investigated neural embeddings—specifically, doc2vec architectures—as a representation model for the task of JP elicitation using Arabic legal texts. Four experiments were conducted to evaluate three different architectures for document embedding models for the JP elicitation task. In addition, we explored an approach that integrates task-oriented word embeddings (ToWE) with document embeddings (paragraph vectors). The results of the experiments showed that using neural embeddings for the JP elicitation task is a promising approach. The paragraph vector distributed bag-of-words (PV-DBOW) architecture produced the best results for this task. To evaluate how well the ToWE model performed for the JP elicitation task, a graded relevance ranking measure, discounted cumulative gain (DCG), was used. The model achieved good results with a normalized DCG of 0.9 for the majority of the JPs. The findings of this study have significant implications for the understanding of how Arabic legal texts can be modeled and how the semantics of jurisprudence principles can be elicited using neural embeddings. Full article

Hybrid spam is an undesirable e-mail (electronic mail) that contains both image and text parts. It is more harmful and complex as compared to image-based and text-based spam e-mail. Thus, an efficient and intelligent approach is required to distinguish between spam and ham. To our knowledge, a small number of studies have been aimed at detecting hybrid spam e-mails. Most of these multimodal architectures adopted the decision-level fusion method, whereby the classification scores of each modality were concatenated and fed to another classification model to make a final decision. Unfortunately, this method not only demands many learning steps, but it also loses correlation in mixed feature space. In this paper, we propose a deep multimodal feature-level fusion architecture that concatenates two embedding vectors to have a strong representation of e-mails and increase the performance of the classification. The paragraph vector distributed bag of words (PV-DBOW) and the convolutional neural network (CNN) were used as feature extraction techniques for text and image parts, respectively, of the same e-mail. The extracted feature vectors were concatenated and fed to the random forest (RF) model to classify a hybrid e-mail as either spam or ham. The experiments were conducted on three hybrid datasets made using three publicly available corpora: Enron, Dredze, and TREC 2007. According to the obtained results, the proposed model provides a higher accuracy of 99.16% compared to recent state-of-the-art methods. Full article

Controlling stability of dynamical systems is one of the most important challenges in science and engineering. Hence, there appears to be continuous need to study and develop numerical algorithms of control methods. One of the most frequently applied invariants characterizing systems’ stability are Lyapunov exponents (LE). When information about the stability of a system is demanded, it can be determined based on the value of the largest Lyapunov exponent (LLE). Recently, we have shown that LLE can be estimated from the vector field properties by means of the most basic mathematical operations. The present article introduces new methods of LLE estimation for continuous systems and maps. We have shown that application of our approaches will introduce significant improvement of the efficiency. We have also proved that our approach is simpler and more efficient than commonly applied algorithms. Moreover, as our approach works in the case of dynamical maps, it also enables an easy application of this method in noncontinuous systems. We show comparisons of efficiencies of algorithms based our approach. In the last paragraph, we discuss a possibility of the estimation of LLE from maps and for noncontinuous systems and present results of our initial investigations. Full article

To effectively process textual data, many approaches have been proposed to create text representations. The transformation of a text into a form of numbers that can be computed using computers is crucial for further applications in downstream tasks such as document classification, document summarization, and so forth. In our work, we study the quality of text representations using statistical methods and compare them to approaches based on neural networks. We describe in detail nine different algorithms used for text representation and then we evaluate five diverse datasets: BBCSport, BBC, Ohsumed, 20Newsgroups, and Reuters. The selected statistical models include Bag of Words (BoW), Term Frequency-Inverse Document Frequency (TFIDF) weighting, Latent Semantic Analysis (LSA) and Latent Dirichlet Allocation (LDA). For the second group of deep neural networks, Partition-Smooth Inverse Frequency (P-SIF), Doc2Vec-Distributed Bag of Words Paragraph Vector (Doc2Vec-DBoW), Doc2Vec-Memory Model of Paragraph Vectors (Doc2Vec-DM), Hierarchical Attention Network (HAN) and Longformer were selected. The text representation methods were benchmarked in the document classification task and BoW and TFIDF models were used were used as a baseline. Based on the identified weaknesses of the HAN method, an improvement in the form of a Hierarchical Weighted Attention Network (HWAN) was proposed. The incorporation of statistical features into HAN latent representations improves or provides comparable results on four out of five datasets. The article presents how the length of the processed text affects the results of HAN and variants of HWAN models. Full article

Assessing nutritional content is very relevant for patients suffering from various diseases, professional athletes, and for health reasons is becoming part of everyday life for many. However, it is a very challenging task as it requires complete and reliable sources. We introduce a machine learning pipeline for predicting macronutrient values of foods using learned vector representations from short text descriptions of food products. On a dataset used from health specialists, containing short descriptions of foods and macronutrient values: we generate paragraph embeddings, introduce clustering in food groups, using graph-based vector representations, that include food domain knowledge information, and train regression models for each cluster. The predictions are for four macronutrients: carbohydrates, fat, protein and water. The highest accuracy was obtained for carbohydrate predictions – 86%, compared to the baseline – 27% and 36%. The protein predictions yielded the best results across all clusters, 53%–77% of the values fall in the tolerance-level range. These results were obtained using short descriptions, the embeddings can be improved if they are learned on longer descriptions, which would lead to better prediction results. Since the task of calculating macronutrients requires exact quantities of ingredients, these results obtained only from short description are a huge leap forward. Full article