Search

Detecting plagiarism in academic papers is crucial for maintaining academic integrity, preserving the originality of published work, and safeguarding intellectual property. While existing applications excel at text plagiarism detection, they fall short when it comes to image plagiarism. This paper introduces a novel algorithm, named "VIBRANT-WALK," designed to detect image plagiarism in academic manuscripts. The challenge of identifying plagiarized images is formidable, requiring a unique approach. Traditional Computer Vision algorithms, proficient in image similarity tasks, face limitations in determining whether an image has been previously used in an article. To address this, the proposed algorithm leverages a repository of all published article pages, focusing on absolute identicality rather than image similarity. The algorithm comprises two stages. In the first stage, a "Vibrancy Matrix" is created through image preprocessing, aiding in contour determination. The second stage involves pixel-by-pixel comparison with images from published manuscripts. To enhance efficiency, the algorithm initiates comparisons from the pixel with the highest score in the Vibrancy Matrix, followed by pixel comparisons through random walks, significantly reducing complexity. To conduct the study, a custom dataset was compiled from 69 research articles, capturing snapshots of each page and figure. Overall, we present 485 unique test cases where we can test the accuracy and efficiency of the algorithm. The lack of publicly available datasets necessitated this approach. The proposed algorithm outperformed the existing models and algorithms in this field by achieving an overall accuracy of 94.8% on the collated dataset, identifying 460 instances of plagiarism out of the 485 test cases. The algorithm also demonstrated a 100% accuracy rate in avoiding false positives. [ABSTRACT FROM AUTHOR]

With the exponential growth in the number of academic researchers, it is crucial for editors of scientific journals to identify the highest-quality papers. While several measures exist to evaluate a paper's impact post-publication, the challenge of determining the potential impact of a manuscript during the review process remains an understudied issue. In this paper, we propose a reviewer-reputation ranking algorithm to identify high-quality papers based on paper citations, where a reviewer's reputation is computed from the correlation between their past ratings and the current number of citations received by the papers they have evaluated. During the review process, reviewers with high reputation scores are given more weight to determine the quality of papers. We test the algorithm on an artificial network with 200 reviewers and 600 papers, as well as on the American Physical Society (APS) data set, including in the analysis 308,243 papers and 274,154 mutual citations. We compare our approach with two existing methods, demonstrating that our algorithm significantly outperforms the others in identifying manuscripts with the highest quality. Our findings can help improve the impact of scientific journals, thereby contributing to academic and scientific progress. • We propose an algorithm to identify the papers with the highest quality from a large number of submissions. • We compare our new algorithm with other existing methods of aggregating user ratings in various online services. • We test our algorithm both with an artificial network and with the empirical data of the APS data set. • We show that our algorithm outperforms the other methods in identifying the papers with the highest quality. [ABSTRACT FROM AUTHOR]

Proper equipment maintenance can significantly reduce overall operating costs by boosting productivity. Management personnel often consider maintenance an expense; however, a more positive approach is to view maintenance as a profit center. Considering this new perspective, the requirements for maintenance management have changed drastically from the traditional concept of fix-it-when-broken to a more complex approach that entails adopting a maintenance strategy for a more integrated approach and alignment. This paper presents a Goal Programming (GP) approach to define the most cost-effective method for maintaining some critical pumps in the paper industry. The failure mode and effects analysis (FMEA) criteria consider each machine failure's occurrence, severity, and detection. After determining the weights, the optimal strategy for each failure is calculated by solving the goal programming. Thus, FMEA can be used to design a network structure for each pump failure mode. For this purpose, the limitations and goals affecting the model are obtained from research literature and interviews with experts. Regarding resource utilization and failure reduction, the results demonstrate that predictive and preventive maintenance strategies are superior to corrective strategies. Therefore, these strategies can predict failures, provide helpful information to maintenance managers, and limit the negative aspects of a failure regarding safety and cost. [ABSTRACT FROM AUTHOR]

Based on the rapid development of intelligent technologies in recent years, the digital transformation of the whole industry and society has become increasingly important. Among them, digital twins and artificial intelligence have great potentials in improving industry processes and further enhancing productivity. This paper proposes an Intelligent Digital Twin System (IDTS) based on artificial intelligence and digital twins for the paper industry. The system includes the prediction models for the stirring speed of the dump chest, the water consumption of the deflaker, the supply air pressure of the dryer, and the exhaust air temperature of the dryer. The sensors, 5G network slices, and other equipment collect related data during the papermaking process for generating twin data, and we use the prediction models to analyze the data and monitor important indicators (stirring speeds, water consumptions, supply air pressures, and exhaust air temperatures) for the manufacturing processes, which are used to improve the energy utilization and production efficiency of the paper industry and thus facilitate cost saving. We apply this intelligent digital twin system and its associated prediction models to an actual paper manufacturing factory and show their effectiveness by improving the operational efficiency and saving labor and maintenance costs. [ABSTRACT FROM AUTHOR]

Currently, many summarization models are based on Transformer architectures, which regard text as a connected graph of words and tokens, thus fail to fully leverage the text's hierarchical structure. However, hierarchical structural information is crucial in understanding long documents, especially scientific papers. To exploit the structural information, we propose a H eterogeneous T ree structure augmented with T riplet P ositions for extractive Sum marization of scientific papers (HTPosum). The proposed model constructs a heterogeneous tree for each document, introducing section nodes and a global node to capture the documents' structural information. The tree is then augmented with a novel triplet position, which consists of three values that represent the depth, parent width position, and sibling width position of each node in a tree. The triplet position provides a unified view of the document structure. Experimental results show that the proposed model achieves state-of-the-art extractive performance on the PubMed and arXiv datasets compared with the latest scientific paper summarization models. • A heterogeneous tree is built to model scientific papers' hierarchical structure. • A triplet position and unique triplet position encoding method is proposed. • The proposed model achieves competitive results compared to latest baselines. [ABSTRACT FROM AUTHOR]

Scientific papers, as pivotal tools for academic communication, should be articulated with clarity and precision to ensure the effective conveyance of scholarly ideas and to prevent reader confusion. Yet, many such papers conspicuously lack in-depth research, and their core content is often ambiguously presented. This pattern poses a significant impediment to the progressive evolution of science and technology. While numerous researchers have recognized this widespread challenge, a holistic theoretical or methodological solution remains elusive in the academic realm. To bridge this gap, we introduce the INTEGrity vERification (INTEGER) task. This task aids researchers in assessing the integrity of their papers by verifying the clarity of each knowledge unit. To implement this task on text, we propose a multi-task learning model that utilizes the Tucker decomposition and span-level attention mechanism to identify terms and their integrity precisely. More specifically, to provide insights into the INTEGER task and validate the effectiveness of the proposed model, we collect 8076 sentences and construct three new datasets containing various types of terms and descriptions in different domains. Extensive experimental results show that our proposed model has an average performance improvement of 1.1% F1 over the three datasets compared to a series of state-of-the-art baseline methods. [ABSTRACT FROM AUTHOR]

Paper recommendation based on author preferences has gained widespread attention. Current methods focus on the heterogeneous information network (HIN) to infer correlation clues based on the metapath with single-type association (closed-metapath). However, the closed-metapath approach only considers sparse correlations between a few type nodes, which brings great challenges for preference learning. To address this issue, we propose a novel metapath with multiple-type correlations (open-metapath) approach for paper recommendation to capture rich correlations between various type nodes in HIN. First, the academic heterogeneous information network is transformed into open-metapaths to acquire whole semantic correlations among varying type nodes, enriching sparse associations. Then, neighbor attention is designed to explore highly relevant structural and semantic information, which initializes author preferences and paper features. Next, metapath attention is constructed to measure the impact intensity of open-metapaths and distinguish their representations. Finally, static and interactive features are fused to learn vectors of authors and papers, providing desired papers. Substantial experiments demonstrate that the proposed model outperforms other existing models significantly. • Open-metapath is proposed to capture correlations between various type nodes in HIN. • Neighbor attention is designed to explore relevant structural and semantic information. • A new metapath attention mechanism is constructed. [ABSTRACT FROM AUTHOR]

The paper recommender system has provided great convenience for people to obtain knowledge of what they are interested in. Existing recommendation works mainly rely on learning entities' feature representations (network embedding) from the Heterogeneous Information Networks (HINs) through meta-paths. Most of them suffer from the difficulty of designing and selecting meta-paths in HIN. Moreover, changes in papers' captive audiences and users' reading favor in the recent trends are always covered up by long-term trends. To this end, we introduce a multi-attention aware recommendation method, named MARec. Specifically, to efficiently design and select meta-paths, we propose an auxiliary node-driven HIN construction method and combine it with the graph attention network (GAT) to learn the entities' feature representations. To endow the recommendation results with timeliness, we design an attention-aware Bi-directional LSTM (Bi-LSTM) and a compensation mechanism to incorporate the recent trend changes. Furthermore, to take advantage of the importance of different papers/users, we utilize an attention mechanism to capture their importance by adaptively fusing the interactive historical data of those paper/user entities. We use extensive experiments on three real-world datasets to show that our proposed MARec outperforms current representative baselines by 11.49%, 11.40%, and 13.37% on average on three main metrics. • A general heterogeneous information network towards simplifying meta-path design. • Embedding with attention mechanism avoids painstakingly selecting meta-paths. • Feature extraction under multi-time scale greatly improves the recommended results. • MARec demonstrates superior performance on different real-world domain datasets. [ABSTRACT FROM AUTHOR]

Highlights • An active learning-based tool supporting researchers finding relevant paper faster. • Use of domain knowledge to faster find the first relevant paper deterministically. • An accurate estimator for the total number of relevant papers. • With the estimator, the system can stop at target recall with little overhead. • An error correction strategy efficiently resolves human errors. Abstract Literature reviews are essential for any researcher trying to keep up to date with the burgeoning software engineering literature. Finding relevant papers can be hard due to the huge amount of candidates provided by search. FAST2 is a novel tool for assisting the researchers to find the next promising paper to read. This paper describes FAST2 and tests it on four large systematic literature review datasets. We show that FAST2 robustly optimizes the human effort to find most (95%) of the relevant software engineering papers while also compensating for the errors made by humans during the review process. The effectiveness of FAST2 can be attributed to three key innovations: (1) a novel way of applying external domain knowledge (a simple two or three keyword search) to guide the initial selection of papers—which helps to find relevant research papers faster with less variances; (2) an estimator of the number of remaining relevant papers yet to be found—which helps the reviewer decide when to stop the review; (3) a novel human error correction algorithm—which corrects a majority of human misclassifications (labeling relevant papers as non-relevant or vice versa) without imposing too much extra human effort. [ABSTRACT FROM AUTHOR]

For the Nordic paper industry the years 2001–2007 were a culmination point as to paper production and deliveries. The study uses plant level empirical time series data from these years from one large integrated Finnish paper mill. The research data covers complete customer data and cost components, and a major supplier for European paper markets. The case company worked actively with a customer base and concentrated on the most profitable markets. However, some unprofitable deliveries, which still covered the variable and fixed costs, also supported the operation of the mill and the continuing of the 24/7 shift. The results indicate that even with matured and bulky products like paper, it is still possible to operate on the basis of separated pricing, some bargaining power, and customized focus. In this respect, the markets do not seem to follow the economic theory expectation entirely, that is, for such a mature and bulky product market price differentiation should not be possible. However, to utilize this, it requires up-to-date information system concerning internal cost accounting, together with an emphasis on the management to have an active role with the customer base. [ABSTRACT FROM AUTHOR]

With the rapid growth of research publications, it has become time-consuming and cumbersome for researchers to find research papers relevant to their research. Research paper recommendation, which provides a reference list for a given manuscript, providing convenience for researchers. In the past, researchers embedded papers into a low-dimensional vector space through textual information and network structure to obtain paper embeddings, and then made recommendations based on the paper embeddings. This paper argues that in addition to the network structure and textual information, the co-authorship of a paper should also be considered, as it reveals the author's interaction preference in the papers involved and reflects the topic of the paper from the author's perspective. In this paper, we consider network structure, textual information and co-authorship of a paper simultaneously, and develop a mutual reinforcement network embedding (MRNE) model to enhance network embedding via mutual reinforcement between co-authorship and textual information based on network structure. Based on this model, we propose a cold-start research paper recommendation approach, which is evaluated on the link prediction-based paper recommendation and cold-start-based paper recommendation, respectively. Experimental results on HepTh and AAN datasets demonstrate effectiveness of the proposed method. This paper provides a new idea for the study of the cold start problem in research paper recommendation. • A novel network embedding model is proposed for scientific paper recommendation. • Our model integrate co-authorship, text and network with mutual reinforcement. • A inductive method is developed to recommend reference papers for cold-start papers. • Our method achieves state-of-art performance in HepTh and AAN datasets. [ABSTRACT FROM AUTHOR]

Scientific paper summarization aims at generating a short and concise digest while preserving important information of the original document. Currently, scientific paper summarization faces two main challenges. First, inter-sentence relations are hard to learn, especially in the case of long-form scientific papers. Second, structural information of the well-structured scientific papers has not been fully exploited. To overcome the above two challenges, we propose a novel Het erogeneous Tree structure-based extractive Sum marization (HetTreSum) model, where each document is modeled as a tree structure to learn inter-sentence relations and structural information of the original document is incorporated, enabling the tree structure to have a global perspective of the whole document. Then an iterative updating strategy is presented to interactively refine nodes of the tree structure for better contextualized representations, which can further enhance summarization performance. Experimental results on PubMed and arXiv datasets show that our proposed HetTreeSum model achieves significantly advanced performance compared with various scientific paper summarization models. • A novel tree structure-based extractive summarization model is proposed for scientific papers. • Structural information and inter-sentence relations are captured with graph transformer networks. • A Bottom-Up-Top-Down iterative updating strategy is developed for mutual reinforcement. • Our method achieves state-of-the-art performance in PubMed and arXiv datasets. [ABSTRACT FROM AUTHOR]

Nowadays, there has been a rapidly increasing number of scientific submissions in multiple research domains. A large number of journals have various acceptance rates, impact factors, and rankings in different publishers. It becomes time-consuming for many researchers to select the most suitable journal to submit their work with the highest acceptance rate. A paper submission recommendation system is more critical for the research community and publishers as it gives scientists another support to complete their submission conveniently. This paper investigates the submission recommendation system for two main research topics: computer science and applied mathematics. Unlike the previous works (Wang et al., 2018; Son et al., 2020) that extract TF–IDF and statistical features as well as utilize numerous machine learning algorithms (logistics regression and multiple perceptrons) for building the recommendation engine, we present an efficient paper submission recommendation algorithm by using different bidirectional transformer encoders and the Mixture of Transformer Encoders technique. We compare the performance between our methodology and other approaches by one dataset from Wang et al. (2018) with 14012 papers in computer science and another dataset collected by us with 223,782 articles in 178 Springer applied mathematics journals in terms of top K accuracy (K = 1 , 3 , 5 , 10). The experimental results show that our proposed method extensively outperforms other state-of-the-art techniques with a significant margin in all top K accuracy for both two datasets. We publish all datasets collected and our implementation codes for further references. 1 1 https://github.com/BinhMisfit/PSRMTE. • Bidirectional transformer encoders can improve the performance of the paper submission recommendation system. • The Mixture of Transformer Encoders framework shows the efficiency in the paper submission recommendation problem. • Proposed techniques can surpass other recent techniques on two datasets related. [ABSTRACT FROM AUTHOR]

• Offering a novel fuzzy robust approach for closed-loop supply chain network design. • Examining the hybrid uncertainties and flexibility of constraints in the problem. • Considering economic, responsibility, and environmental subjects in modeling. • Using the interactive fuzzy programming approach to solve the multi-objective model. • Introducing a new application for stone paper closed-loop supply chain network design. Nowadays, the production of stone paper, in addition to its widespread utilization in various fields, does not require water consumption, cutting down trees, and stone paper products are easily recyclable and recoverable. Due to the importance of developing and using stone paper and paying attention to environmental matters, Closed-Loop Supply Chain Network Design (CLSCND) is very important for stone paper products. Moreover, due to epistemic, randomness uncertainties, the uncertainties in Objective Function (OF), and the flexible constraints for CLSCND in the real world, this paper introduces a novel Mixed Robust Stochastic, Possibilistic, and Flexible Programming (MRSPFP) approach based on credibility theory. The different attitudes of the Decision-Makers (DMs) are addressed by a more flexible measurement of the optimistic and pessimistic parameters using the criterion of credibility. In the study, a comprehensive procedure is proposed for stone paper CLSCND, to minimize costs, increase responsiveness by minimizing transit time between different facilities, and regarding environmental concerns into account through minimizing carbon emissions. The model is solved utilizing an interactive fuzzy programming solution procedure and the Best-Worst Method (BWM). The results of sensitivity analysis, the effect of changing the problem parameters, and the performance of the proposed model are investigated and compared. The results show that the MRSPFP model has a better performance compared to other previous models. The MRSPFP model performs better in strategic decisions that require high investment costs due to the minimization of the absolute deviation of OF from its mean. Also, the applied results of the study show that CLSCND has a good capability and potential for sustainable development in the field of stone paper. [ABSTRACT FROM AUTHOR]

• Recommend citations from the perspective of cited paper instead of citing paper. • Design four forms of citation content for different citation motivations. • Design 132 methods for generating semantic representation of cited paper. • Find the most suitable form and method through quantitative comparisons. Citation recommendation can help researchers quickly find supplementary or alternative references in massive academic resources. Current research on citation recommendation mainly focuses on the citing papers, resulting in the enormous cited papers are ignored, including the relations among cited papers and their citation context cited in citing papers. Moreover, cited paper's content is often denoted with its original title and abstract, which is hard to acquire and rarely considers different citation motivations. Furthermore, the most appropriate method for semantic representation of cited papers' relations and content is uncertain. Therefore, this paper studies citation recommendation from the perspective of semantic representation of cited papers' relations and content. Firstly, four forms of citation context are designed and extracted as cited papers' content considering citation motivations, as well as co-citation relationships are extracted as cited papers' relations. Secondly, 132 methods are designed for generating semantic vector of cited paper, including four network embedding methods, 16 methods by combining four text representation algorithms with four forms of citation content, and 112 fusion methods. Finally, similarity among cited papers is calculated for citation recommendation and a quantitative evaluation method based on link prediction is designed, to find the most appropriate form of citation content and the optimal method. The result shows that doc2vecC (Document to Vector through Corruption) with the form of CS&SS (Current Sentences and Surrounding Sentences) performs best, in which the AUC (Area Under Curve) and MAP (Macro Average Precision) reach 0.877 and 0.889 and have increased by 0.462 and 0.370 compared with the worst-performing method. This performance is slightly improved by parameters adjustment, and a case study is performed whose results have further proved the effectiveness of this method. In addition, among four forms of cited papers' content, CS&SS performs best in almost all methods. Furthermore, the fusion methods not always perform better than the single methods, where doc2vecC (CS&SS) performs better than the best fusion method GCN (Graph Convolutional Network). These results not only prove the effectiveness of citation recommendation from the perspective of cited paper, but also provide helpful and useful suggestions for method selection and citation content selection. The data and conclusions can be extended to other text mining-related tasks. Simultaneously, it is a preliminary research which needs to be further studied in other domains using emerging semantic representation methods. [ABSTRACT FROM AUTHOR]

Formulaic expressions, such as ' in this paper we propose ', are helpful for authors of scholarly papers because they convey communicative functions; in the above, it is ' showing the aim of this paper '. Thus, resources of formulaic expressions, such as a dictionary, that could be looked up easily would be useful. However, forms of formulaic expressions can often vary to a great extent. For example, ' in this paper we propose ', ' in this study we propose ' and ' in this paper we propose a new method to ' are all regarded as formulaic expressions. Such a diversity of spans and forms causes problems in both extraction and evaluation of formulaic expressions. In this paper, we propose a new approach that is robust to variation of spans and forms of formulaic expressions. Our approach regards a sentence as consisting of a formulaic part and non-formulaic part. Then, instead of trying to extract formulaic expressions from a whole corpus, by extracting them from each sentence, different forms can be dealt with at once. Based on this formulation, to avoid the diversity problem, we propose evaluating extraction methods by how much they convey specific communicative functions rather than by comparing extracted expressions to an existing lexicon. We also propose a new extraction method that utilises named entities and dependency structures to remove the non-formulaic part from a sentence. Experimental results show that the proposed extraction method achieved the best performance compared to other existing methods. • Formulaic expression extraction using named entities and dependency structure. • Sentence retrieval task as an extrinsic evaluation for formulaic expressions. • Changing weights on word embeddings captures characteristics of extraction methods. [ABSTRACT FROM AUTHOR]

Automatically generating a survey draft is a challenge to text summarization research because it needs to select important sentences from important references in a large set of candidate papers for composing sections that are in line with section titles and different sections discuss the most relevant reference papers of different number, which are beyond the capability of previous text summarization approaches as they assume that all candidate papers should be included into one summary. This paper proposes an approach to generating survey draft according to a pattern consisting of sections with titles given by the user who requests the survey. The problem of generating each section can be divided into the following sub-problems: (1) rank the input scientific documents (in short documents) according to the title of a section, (2) determine the number of documents that are most relevant to the title, and (3) rank and select sentences from the selected documents according to the title. A position closeness distance of key word is proposed to rank a set of documents by measuring how closely two key words within section title are distributed within each document, which is used to rank the documents. The rationale is that the positions of the neighboring key words of a section title should be closer in more relevant documents than other words. As different sections have different number of selected documents, a method is proposed to determine the number of documents to be included into the current section based on the slope shape of the sorted rank curve of documents according to the section title. Based on the duality property of the closeness, ranks of sentences within a document can be directly obtained when the document is ranked according to the title of section, and both the importance and coherence of selected sentences can be reflected without extra calculation for ranking sentences. Experiments and manual evaluation show that the proposed methods achieve significant improvements compared with other approaches. The proposed approach is significant in applications as different surveys can be generated according to different patterns given by different users. [ABSTRACT FROM AUTHOR]

Regular Ship hull maintenance is an essential for sustainability. The maintenance work of ship hulls that involve human labor suffers from many shortcomings. Maintenance robots have been introduced for drydocks to eliminate these shortcomings. An energy-efficient Complete Coverage Path Planning (CCPP) is a crucial requirement from a ship hull maintenance robot. This paper proposes a novel energy-efficient CCPP method based on Glasius Bioinspired Neural Network (GBNN) for a ship hull inspection robot. The proposed method accounts for a comprehensive energy model for path planning. This energy model reflects the energy usage of a ship hull maintenance robot due to changes in direction, distance, and vertical position. Furthermore, the proposed method is effective for dynamic workspaces since it performs online path planning. These are the major contributions made to state of the art by the work proposed in this paper. The behavior and the performance of the proposed method have been compared against state of the art through simulations considering Hornbill, a multipurpose ship hull maintenance robot. The validation confirms the ability of the proposed in realizing a complete coverage of a given dynamic workspace. According to the statistical outcomes of the comparison, the performance of the proposed method significantly surpasses that of the state-of-the-art methods in terms of energy usage. Therefore, the proposed method contributes to the development of energy-efficient CCPP methods for a ship hull maintenance robot. • A novel coverage method based on Glasius Bioinspired Neural Network is proposed. • The proposed method is intended for a multipurpose ship hull maintenance robot. • A comprehensive energy model is utilized by the proposed method for path planning. • The proposed method is significantly efficient than the state of the art methods. • The paper contributes to the development of a ship hull maintenance robot. [ABSTRACT FROM AUTHOR]

Machine learning-based methods have emerged as competitors to traditional metaheuristic-based solutions in many areas. Besides investigating their effectiveness, it raises the question of whether these methods can be combined. This paper presents a systematic literature review based on P.R.I.S.M.A. methodology to provide a state-of-the-art overview of machine learning-assisted metaheuristics, focusing on local search algorithms such as Hill Climbing, Tabu Search, and Simulated Annealing. The review is based on a comprehensive evaluation of 48 related articles. These studies illustrate the most common applications of hybrid methods in various fields, including physical simulations and scheduling problems. This paper demonstrates commonly used assembly options, such as metamodeling and machine learning aided initialization, along with some novel ideas like early stopping and cooling control based on neural networks. The evaluation of the results reveals several potential machine learning methods, such as Deep Neural Networks, Hopfield Networks, and Self-Organizing Maps, to assist the metaheuristics. Different training methods for these approaches, including online vs offline training and sources of training data, are also reviewed. Most papers address real-world problems, but there are several intriguing ideas for improving local searches in general. • A P.R.I.S.M.A. review of machine learning assisted metaheuristic methods is presented. • The study focuses on local search hybrids such as Tabu Search and Simulated Annealing. • Several potential machine learning methods are revealed (DNN, Hopfield, SOM, etc.). • Commonly used assembly options, such as metamodeling, are discussed. • Different available training methods, both online and offline, are reviewed. [ABSTRACT FROM AUTHOR]

At present, traffic state prediction primarily relies on purely data-driven methods, ignoring the incorporation of physical constraints within the field of traffic flow. Taking this as a starting point, this paper endeavors to embed the physical mechanism of the traffic flow fundamental graph into the deep learning model, and proposes a physics-integrated spatiotemporal graph neural network with fundamental diagram learner (PI-STGnet) for highway traffic flow prediction. The PI-STGnet mainly comprises a semantic enhancement module (SE), a spatiotemporal correlation extraction module (ST-Block), and a fundamental diagram learner module (FD-learner). These modules are strategically designed to sequentially enhance the contextual semantic relationships of the traffic flow and speed inputs, extract intricate spatiotemporal correlations of traffic states, and adaptively learn the dynamic evolution of the physical relationships between traffic flow and speed. The real-world dataset employed to assess the performance of the PI-STGnet is sourced from the monitoring data of highway gantry sensors located in Ningde City, Fujian Province, China. The experimental results demonstrate that the proposed PI-STGnet has the advantages to extract spatiotemporal features and achieve prediction, surpassing the accuracy of cutting-edge baseline models. In summary, as an exploratory work, this paper provides a novel approach that driven by the fusion of deep learning and physical mechanisms for traffic flow prediction to a certain extent. • A physics-integrated graph neural network is proposed for traffic flow prediction. • Multi-source data is fused to achieve complete characteristics representation. • An improved ST-Block module is proposed. • A fundamental diagram learner module is designed and fused into GCN. • The experiment results prove PI-STGnet is superior to existing competitive models. [ABSTRACT FROM AUTHOR]

Digital twins belong to ten of the strategic technology trends according to the Gartner list from 2019, and have encountered a big expansion, especially with the introduction of Industry 4.0. Sport, on the other hand, has become a constant companion of the modern human suffering a lack of a healthy way of life. The application of digital twins in sport has brought dramatic changes not only in the domain of sport training, but also in managing athletes during competitions, searching for strategical solutions before and tactical solutions during the games by coaches. In this paper, the domain of digital twins in sport is reviewed based on papers which have emerged in this area. At first, the concept of a digital twin is discussed in general. Then, taxonomies of digital twins are appointed. According to these taxonomies, the collection of relevant papers is analyzed, and some real examples of digital twins are exposed. The review finishes with a discussion about how the digital twins affect changes in the modern sport disciplines, and what challenges and opportunities await the digital twins in the future. [ABSTRACT FROM AUTHOR]

Information Recommendation (IR) systems are conventionally designed to operate within a single modality at a time, such as Text2Text or Image2Image. However, the concept of cross-modality aims to facilitate a versatile recommendation experience across different modalities, such as Text2Image. In recent years, significant strides have been made in developing neural recommender models that are multimodal and capable of generalizing across a broad spectrum of domains in a zero-shot manner, thanks to the robust representation capabilities of neural networks. These architectures enable the generation of embeddings for assets (i.e., content uploaded on a platform by users), presenting a concise representation of their semantics and allowing for comparisons through similarity ranking. In this paper, we present ZCCR, a Zero-shot Content-based Crossmodal Recommendation System that leverages knowledge from large-scale pretrained Vision-Language Models (VLMs) such as CLIP and ALBEF to redefine the recommendation task as a zero-shot retrieval task, eliminating the need for labeled data or prior knowledge about the recommended content. Furthermore, ZCCR performs crossmodal similarity search on an optimized index, such as FAISS, to improve the speed of recommendation. The goal is to recommend to the user assets that are similar to those they have previously uploaded, commonly referred to as their user profile. Within the user profile, we identify "areas of interest"—groups of assets associated with specific user interests, such as cooking, sports, or cars. To identify these areas of interest and construct the search query for the retrieval operation, ZCCR employs an innovative use of Agglomerative Clustering. This technique groups user past assets by similarity without requiring prior knowledge of the number of clusters. Once the areas of interest, or clusters, are identified, the centroid is utilized as the search seed to find similar assets. Experimental results demonstrate the efficiency of the selected components in terms of search time and retrieval performance on modified MSCOCO and FLICKR30k datasets tailored for the recommendation task. Furthermore, ZCCR outperforms both a baseline tagging system (BT) and a more advanced tag system which utilizes a Large Language Model (LLM) to extract embeddings from tags. The results show that, even compared with the latter, embeddings directly extracted from raw assets yield superior outcomes compared to relying on intermediate tags generated by other tools. The code implementation to reproduce all experiments and results shown in this paper is provided at the following link: ZCCR-experiments. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic exposed the importance of research on the spread of epidemic diseases. In this paper, we apply Artificial Intelligence and statistics techniques to build prediction models to estimate the SARS-CoV-2 seroprevalence in the United States, using multiple estimates of COVID-19 prevalence and other explanatory variables. We propose the use of stacking techniques based on multiple model building techniques (Linear and Beta Regression, Genetic Programming and Neural Networks) to obtain Predictive Ensemble Models. There has been extensive research on this field, but there has not been in-depth research on the application of stacking methods to estimate and forecast seroprevalence in the USA specifically. This paper provides a novel comparison of the behaviour and performance of different building techniques for stacking ensemble models and presents which methods are better for different scenarios. We find that Genetic Programming and Neural Networks are the best models with trained data within single states, and when multiple states are considered Genetic Programming is still better than the Regression models, but Neural Networks fail to estimate the seroprevalence accurately. Another novelty of our work is the use of cross-state validation to evaluate the models with new data, as well as temporal forecasting. Depending on how the data is processed, Linear Regression performs very well with cross-state validation and temporal forecasting, and Genetic Programming is very accurate with the former while Neural Networks work better with the latter. • COVID-19 seropositivity modelling in the USA. • Use of stacking and ensemble ML models. • Comparison of ML methods (linear regression, beta regression, genetic programming, neural network). • Trade-off between explainability and performance. [ABSTRACT FROM AUTHOR]

• Propose a dual-branch model that realizes the mutual benefits of both detections. • DB-FCN combines the advantages of both one-stage and two-stage object detections. • Coarse detection suppresses the background of the image to improve the accuracy. • We designs a three-stage training method to fully exploit the model's performance. • DB-FCN achieves highest scores on various datasets. Detecting cells or nuclei in histopathological image analysis is a crucial prerequisite for subsequent cancer diagnosis. By precisely locating cell nuclei, pathologists can quantitatively analyze the morphology of each cell nucleus. This enables accurate cancer grading, allowing for the implementation of tailored treatment plans based on distinct cancer stages. Manual nucleus detection methods are labor-intensive, making the development of automatic cell nucleus detection algorithms highly necessary. However, due to the small size of the nucleus and increased adhesions between cells, tissue staining may be uneven, leading to a higher occurrence of false positives in the results of the current automatic nucleus detection algorithm. This paper introduces an end-to-end dual-branch-based fully convolutional neural network (DB-FCN) that effectively addresses the aforementioned challenges, thereby enhancing the accuracy of automatic nucleus detection. This algorithm introduces for the first time the use of two detection branches, namely the coarse detection branch and the fine detection branch, to accomplish the detection task. The role of the coarse detection branch is to identify all cell regions in the pathological image as comprehensively as possible and then transmit the detection results as prior information to the fine detection branch. The fine detection branch is necessary solely to conduct more precise detection based on the coarse detection results. Given that the coarse detection branch has already eliminated interference from many background regions, the fine detection branch can focus on detecting the nucleus region, thereby significantly enhancing the efficiency and accuracy of model detection. The detection model proposed in this paper was evaluated on three classic datasets and compared with many existing detection algorithms. Compared with other algorithms, the detection algorithm proposed in this paper has made significant progress in detecting cell nuclei in histopathological images. [ABSTRACT FROM AUTHOR]

This paper proposes a fully decentralized approach to address the challenge of general mixed cooperation and competition within the domain of Multi-Agent Reinforcement Learning (MARL). Conventional MARL approaches do not achieve full decentralization as they necessitate either the communication of implicit information or the retention of a centralized critic, rendering them impractical in mixed cooperative and competitive environments. To address these challenges, this paper proposes a Decentralized Counterfactual Value (DCV) to model the behaviors of other agents and mitigate the non-stationary problem, accompanied by a Threat Detection (TD) mechanism to discern latent competitive or cooperative relationships. In addition, DCVTD is incorporated into both value-based and policy-based RL paradigms with theoretical convergence guarantee. Finally, empirical validation across four representative environments demonstrates the superior performance of DCVTD in terms of collective returns, computational efficiency, and agent scalability over other fully decentralized approaches, centralized training with decentralized execution approaches, and alternative approaches involving agent modeling or reward shaping in comprehensive experiments. [ABSTRACT FROM AUTHOR]

Given the nonlinearity and complexity inherent in the dynamics of industrial systems, model-based control methods are deemed inadequate for addressing the evolving needs of industries, often resulting in high levels of complexity in control system design. Presently, in response to industrial requirements, data-driven control methods are undergoing significant development and progress. This paper introduces a novel method, namely Fractional Order Data-Driven Sliding Mode Control (FODDSMC), based on a newly proposed Fractional Order Sliding Mode Observer (FOSMO), specifically designed for nonlinear systems. All control parameters in the proposed controller and the novel FOSMO are optimized using Artificial Neural Networks (ANN). By virtue of harnessing the advantages of fractional calculus, the proposed method is capable of enhancing system robustness against external disturbances. This paper aims to propose a novel control method in the design of nonlinear controllers capable of addressing the challenges and enhancing the performance of the system. In this context, the performance of the proposed control system is evaluated under normal conditions and in the presence of internal uncertainty, noise and external disturbances applied to the nonlinear system to demonstrate the benefits of the proposed approach. Furthermore, the performance of the proposed method is compared against that of sliding mode controllers and optimal sliding mode controllers to underscore its superiority. The proposed method has significant performance improvement compared to the discussed sliding mode controllers. To evaluate the performance of the proposed method and validate its superiority, the performance of the proposed method has been examined under two different case studies. The proposed method has demonstrated suitable performance under ideal conditions, external disturbances, and system uncertainties, with the proposed observer providing accurate estimates. Also the proposed adaptive neural networks ensure the optimality of controller's coefficient. In both examples, the superiority of the proposed method compared to the other methods considered for comparison is clearly observable. [ABSTRACT FROM AUTHOR]

Subgraph representation learning is a burgeoning field within graph representation learning. However, current methods in this field face several issues, including the inability to facilitate information interaction between subgraphs, the destruction of original node feature information, and the detrimental effect of the structural information of the entire graph on the extracted subgraph structural information. To address these issues, this paper proposes a method named the subgraph autoencoder with bridge nodes (SAWBN). Specifically, first, SAWBN enhances the data interaction capability by adding a bridge node and connecting it to all nodes within a subgraph. The addition of the bridge node creates indirect connections between subgraphs, enabling them to interact and exchange information during the message-passing phase. To the best of our knowledge, this is the first paper to propose the concept of bridge nodes and to introduce bridge nodes into subgraph representation learning. Second, SAWBN utilizes a new message-passing paradigm called graph convolution with different weights (GDW). During the convolution process, GDW can assign different weights to nodes inside and outside a subgraph, effectively distinguishing the importance of nodes without compromising the original node feature information. Third, SAWBN uses an autoencoder to reconstruct subgraph node features. This reconstruction can eliminate the interference of the structural information of the entire graph and regenerate subgraph node features that are rich in subgraph structural information. Finally, these subgraph node features are aggregated to achieve a good representation of the subgraph structural information. Extensive results on four real-world subgraph datasets demonstrate that SAWBN outperforms state-of-the-art baselines. The source code of SAWBN is publicly available at https://github.com/denggaoqin/SAWBN. • The new message-passing paradigm is suitable for subgraph-level convolution. • The bridge node improves information interaction between subgraphs. • The subgraph autoencoder enhances subgraph structural information. • This paper first introduces bridge nodes into subgraph representation learning. [ABSTRACT FROM AUTHOR]

As diabetes management becomes more complicated, there is an increasing interest in understanding how to manage diabetes with physical activity. Our study aimed to investigate the role of wearable, non-invasive technologies in collecting data related to physical activity to model them via artificial intelligence methods for efficient diabetes management. We followed the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (also known as PRISMA) protocol and searched three databases, namely PubMed, Scopus, and Web of Science. Out of 960 titles, we included 32 in the full-text analysis. Results showed two main methods were used for the analysis, i.e., statistical and classification modeling. Results indicate among the employed regression methods, linear regression was used more than other methods, and the most common classification-based method for analyzing data was the Artificial Neural Network method. Assessing the quality of papers that used the classification method was done through Prediction model Risk Of Bias Assessment Tool (also known as PROBAST) and Transparent Reporting of a multivariable prediction model for Individual Prognosis Or Diagnosis (also known as TRIPOD) tools. Based on PROBAST outcomes, although the risk of bias was low in most of the works, explaining the analyzing method specifically, the method of handling missing data needs more attention. Upon evaluating papers using the TRIPOD, it realized that there is a need to place emphasis on improving the quality of the presentation and explanation of the result. According to our review, the conjunction of non-invasive technologies and artificial intelligence is promising in managing diabetic risk factors for real-time monitoring of physical activities, enabling regular clinical intervention and optimized medical treatment. [ABSTRACT FROM AUTHOR]

To evaluate some real-life multi-criteria decision-making (MCDM) problems, the decision-makers (DMs) need an interactive and flexible MCDM approach that works well for extended decision-making space and has the ability to apply any suitable operational laws to fuse the information under incomplete criteria weighting information. The objective of this study is to propose a multi-criteria group decision-making (MCGDM) approach to evaluate any real-life MCDM problem under incomplete criteria weighting information. To achieve the objective, the paper proposes an integrated MCGDM approach in which the q -rung orthopair fuzzy set (q-ROFS) is used to provide the extended decision-making space to the DMs, a transformative approach is applied to find the DMs' weights, the maximizing deviation method is implemented to find the criteria weights, Archimedean t -norm and t -conorm (ATU)-based operational laws are adopted to fuse the information, and the TOPSIS method is applied to rank the alternatives. The proposed integrated MCGDM approach has been applied to a real-life MCDM problem associated with the evaluation of different strategies implemented by governments to contain the COVID-19 pandemic. A sensitivity analysis is conducted to examine the impact of changes in the parameters involved in the proposed MCGDM approach on the results. A comparative analysis is also performed with some existing classical and aggregation operator-based MCDM methods to demonstrate the consistency of the proposed approach. Findings suggest that the proposed MCGDM approach is general and flexible enough to evaluate any real-life MCDM problem under unknown criteria weighting conditions. • The paper proposes ATU based qROF-TOPSIS method for unknown criteria weights. • The method applies q-ROFS to quantify uncertainty and ATU to fuse the information. • The maximizing deviation method is used to evaluate the criteria weights. • The TOPSIS method is applied to rank the alternatives. • The method is applied to evaluate government strategies against COVID-19 pandemic. [ABSTRACT FROM AUTHOR]

Because of the prevalence of depression, its often-chronic course, relapse and associated disability, early detection and non-intrusive monitoring is a crucial tool for timely diagnosis and treatment, remission of depression and prevention of relapse. In this way, its impact on quality of life and well-being can be limited. Current attempts to use artificial intelligence for the early classification of depression are mostly data-driven and thus non-transparent and lack effective means to deal with uncertainties. Therefore, in this paper, we propose an end-to-end framework for extracting observable depression cues from diary recordings. Furthermore, we also explore its feasibility for automatic detection of depression symptoms using observable behavioural cues. The proposed end-to-end framework for extracting depression was used to evaluate 28 video recordings from the Symptom Media dataset and 27 recordings from the DAIC-WOZ dataset. We compared the presence of the extracted features between recordings of individuals with and without a depressive disorder. We identified several cues consistent with previous studies in terms of their differentiation between individuals with and without depressive disorder across both datasets among language (i.e., use of negatively valanced words, use of first-person singular pronouns, some features of language complexity, explicit mentions of treatment for depression), speech (i.e., monotonous speech, voiced speech and pauses, speaking rate, low articulation rate), and facial cues (i.e., rotational energy of head movements). The nature/context of the discourse, the impact of other disorders and physical/psychological stress, and the quality and resolution of the recordings all play an important role in matching the digital features to the relevant background. In this way, the work presented in this paper provides a novel approach to extracting a wide range of cues relevant to the classification of depression and opens up new opportunities for further research. [ABSTRACT FROM AUTHOR]

The rapid development of the Vision Transformer backbones has enabled the capture of feature information with global dependencies, leading to excellent performance in salient object detection tasks. However, it fails to adequately emphasize fine local features of edges, resulting in coarse and blurry edges in the final output. Therefore, this paper proposes a set prediction method for salient object detection. The approach enables the model to simultaneously consider both saliency (salient object) and edge features, achieving an end-to-end edge feature fusion. There is no need to design multiple complex branch structures and multiple training as with other methods. The model integrates random edge neighborhood sampling to enhance the recognition accuracy of local edge features in images. This approach addresses the weak perception of local features by Transformers and the issue encountered during actual training, where edge pixels typically occupy a much smaller proportion of the image compared to the background, resulting in insufficient learning of edge features by the model. The proposed end-to-end model in this paper fuses multiple features, including edge and salient objects. They are extracted within a unified framework while simultaneously outputting edge and salient object maps. Experimental results on six public datasets show that the proposed method significantly improves model performance benchmarks for detecting salient objects. • Vision Transformer lacks in its ability to focus on local information. • The Hungarian algorithm is effectively employed for feature fusion. • Utilizing random edge neighborhood sampling for localization of local details. • The network produces both precise salient objects and fine edges. • The proposed method enhances the performance benchmark in salient object detection. [ABSTRACT FROM AUTHOR]

Driving risk evaluation is a critical task for traffic safety and vehicle insurance. Unfortunately, many existing methods disregard the unknown and uncertain nature of driving behavior in real-world scenarios. In this paper, we formula this task as a multi-criteria group decision-making problem and propose a dual perspective information volume method for evaluating the driving risk score based on linguistic Z-number. Our proposed method accurately captures the uncertainties and reliability of driving behavior by utilizing two fuzzy numbers A and B. The main contributions of our paper are as follows: firstly, we introduce the α -truncation set and the information volume-based utility function and credibility probability model, which form the basis of the vehicle evaluation method. Secondly, we consider cross-information to model the divergence of information between dual perspectives, based on different experts and features. We calculate the credibility value for each perspective using the Z + -based information volume. Thirdly, we present the dual perspective calculation method used to assess driving risk. This method assigns risk scores to individual vehicles based on a utility function. Finally, we conduct a case study using the historical trajectories of vehicles obtained from an insurance company. The results are compared against the damages coefficient. Furthermore, we perform dependability and parameter analysis to demonstrate the effectiveness and superiority of our approach. Our approach provides valuable insights and suggestions for the insurance industry and traffic safety departments in relevant fields. • Linguistic Z-number for driving behavior risk evaluation. • Dual perspective information volume calculation method. • Determines the credibility probability based on the information divergence value. • Utility function value based on Z-number for ranking of driving behavior risk. [ABSTRACT FROM AUTHOR]

With the development of intelligent manufacturing driven by new-generation information technology, manufacturing service collaborative chains (MSCC) based on Industrial Internet Platforms have become the main way to cope with mass personalized production. To adapt the dynamics and variability of personalized demands, manufacturing services are required to be frequently reorganized. This leads to dynamic changes in manufacturing service availability and ambiguous reliable collaboration mechanisms, making it challenging for existing methods to consistently maintain stable MSCC. Therefore, this paper proposes a three-stage deep reinforcement learning method (TSDRL) to improve the reliability of MSCC while guaranteeing the satisfaction of personalized demands. The method comprehensively considers the dynamic changes of manufacturing services and service reliability, and solves the reliable MSCC recommendation problem. Specifically, in stage one, high-quality services are selected through DRL state. In stage two, the improved NSGA-III algorithm is used to optimize the MSCC. In stage three, the BP+GA algorithm is used to mine user preferences and recommend high-satisfaction MSCC. By leveraging the exploratory process of DRL, cyclic optimization of MSCC is performed. Through comprehensive analysis and experimental research, it is shown that the method of this paper is robust and practical in dynamic environment. [ABSTRACT FROM AUTHOR]

The protection of digital image privacy in Big Data environment is a hot issue of increasing concern. To address the contradiction between efficiency and security for privacy protection, this paper proposes a high-quality restored image privacy protection scheme based on Discrete Cosine Transform (DCT) frequency domain compression and nonlinear dynamics. First, the RGB space of the color image is converted to YCbCr domain with 4:2:0 sampling. Then, the image is divided into sub-blocks in the spatial domain, followed by block-wise DCT and quantization into frequency domain information. Next, both Alternating Current (AC) and Direct Current (DC) coefficients of all sub-blocks are individually extracted and subjected to compression encoding. Finally, a Rubik's Cube permutation and filtering diffusion encryption algorithm based on a nonlinear dynamical chaotic system is designed. Moreover, a mechanism for generating dynamic chaotic sequences associated with plaintext is introduced to effectively counter cryptographic attacks. The combined approach of compression and encryption significantly reduces computational complexity while improving encryption efficiency. Through experimental simulation results, the compression encryption scheme demonstrates high compression ratios as well as excellent image recovery quality while providing enhanced security against common cryptographic attacks. The work in this paper provides a preferred joint compression and encryption technical solution for digital image privacy protection in Big Data network. • Joint compression method propose makes the image size very small for the first time. • Make targeted security enhancements based on our existing cryptanalytic research base. • The proposed scheme is characterized by high compression rate and high image recovery quality. • The scheme has good encryption effect compared with classic algorithms and recent algorithms. • The impact of quantization matrices on compression is explored. [ABSTRACT FROM AUTHOR]

In recent years, detection techniques using computer vision and deep learning have shown promise in assessing driver distraction. This paper proposes a fusion network that combines a Spatial-Temporal Graph Convolutional Network (ST-GCN) and a hybrid convolutional network to integrate multimodal input data for recognizing distracted driver behavior. Specifically, to address the limitations of the ST-GCN method in modeling long-distance joint interaction features and inadequate temporal feature extraction, we design the Spatially Symmetric Configuration Partitioning Graph Convolutional Network (SSCP-GCN) to model relative motion information of symmetric relationships between limbs. Specifically, we utilize densely connected blocks for processing multi-scale temporal information between consecutive frames, thereby enhancing the reuse of bottom features. Furthermore, the expression of important temporal information is augmented by the introduction of the channel attention mechanism. To tackle the problem that the Mixed Convolution (MC) combining 3D convolution with 2D convolution cannot extract higher-order timing information and has limitations in modeling global dependency relationships, we compensate for its inability to capture higher-order temporal semantic information using the Time Shift Module (TSM) without consuming additional computational resources. Additionally, the 3D Multi-Head Self-Attention mechanism (3D MHSA) is employed to integrate global spatial–temporal information of high-level features, avoiding the issue of model complexity proliferation caused by the deep stacking design of Convolutional Neural Networks (CNN). Lastly, we introduce a multistream network framework that integrates driver posture and appearance features to harness complementary advantages, enabling us to combine multimodal input features to achieve better model performance. Experimental results indicate that the accuracy of the network designed in this paper reaches 95.6% and 94.3% on ASU dataset and NTU-RGB+D dataset, respectively. The small size of the model offers the possibility for practical application of the algorithm. [ABSTRACT FROM AUTHOR]

The Low-rate Denial-of-Service (LDoS) attack is a stealthy and periodic attack, which belongs to the category of DoS attacks. The LDoS attack maliciously preempts and consumes target resources, causing the targeted network performance to decline and affecting the service quality. The LDoS attack is highly destructive and difficult to detect and defend against due to its abnormal attack behavior. In this paper, we discuss the network traffic behavior in the time domain, frequency domain, and time–frequency domain, and we find that the time–frequency domain contains more detailed information than the time domain and frequency domain alone. Considering the limitations of the existing time–frequency domain transformation methods, an LDoS attack detection method based on Frequency Slice Wavelet Transformation (FSWT) is presented in this paper. The entropy, ratio of energy, contrast, and correlation are extracted from the time–frequency distribution to depict the network traffic, and a decision tree is trained to detect the LDoS attack in this paper. According to the experimental results on NS2, testbed, and the comparative experiment, we conclude that the method presented in this paper performs well. • Pointing the time–frequency domain contains more detailed information on network traffic analysis. • A method based on Frequency Slice Wavelet Transformation to detect LDoS attacks. • We integrate the network time domain and frequency domain features. • We conduct experiments on different environments, including NS2, testbed and SDN. [ABSTRACT FROM AUTHOR]

In order to accurately predict the remaining useful life (RUL) of mechanical equipment under conditions of missing data, this paper proposes a novel integrated framework for data repair and RUL prediction, named DRTCR. DRTCR possesses the dual functionality of missing data repair and RUL prediction. Initially, considering the underlying trends and periodic fluctuations in the signals, polynomial and trigonometric functions are incorporated into the implicit feature matrix (IFM) generated by Gaussian random functions. This approach involves constructing a data repair deep learning framework primarily based on LSTM and CNN. This framework facilitates the repair of missing data. Furthermore, this paper introduces the integration of trend, correlation, and robustness within the LSTM units. A predictive unit named TCRcell is devised, which enhances the feature extraction capability of the prediction model. Additionally, a corrective unit within TCRcell is constructed, predominantly centered around discrete Fourier transform (DFT) and discrete wavelet transform (DWT) as frequency domain feature extraction techniques. This incorporation introduces the physical mechanism information into DRTCR and refines the predictive outcomes of TCRcell. The global frequency perspective of DFT aids in capturing the overall trend in signal variations, while DWT precisely captures localized temporal details in the time series, resulting in a dynamically corrected TCRcell prediction outcome that combines both global trends and local intricacies. Finally, experimental validation was conducted to assess the predictive performance and robustness of DRTCR. [ABSTRACT FROM AUTHOR]

Load prediction is crucial to unit commitment and scheduling in electricity systems; however, load prediction models consume considerable electricity. Most conventional prediction methods are based on deep learning (DL) models, such as long short-term memory and gated recurrent units. The nonlinear activation functions and backpropagation mechanisms used in these methods result in high computational complexity and correspondingly high energy consumption. This paper proposes a prediction model based on a green learning (GL) framework aimed at reducing energy consumption. The proposed GL model replaces the activation functions conventionally used for feature extraction with a hybrid scheme combining categorical and numerical features, such as seasonal climate features and multi-autoregression terms. The proposed GL model also eliminates the backpropagation methods used to optimize hyperparameters by employing seasonal centroids and the quantile auto-regression forest algorithm for classification/regression. In a case study, the proposed GL model significantly outperformed conventional DL models in terms of energy consumption without compromising accuracy. The energy savings of the proposed GL model are equivalent to the annual electricity consumption of 211 ∼ 565 households, increasing with model penetration. This paper demonstrates the importance of energy-saving models in mitigating the linkage effect of industrial carbon emissions. It also explores policy implications for the implementation of GL models. [ABSTRACT FROM AUTHOR]

This paper evaluates five strategies for mitigating imbalanced data: oversampling, undersampling, ensemble methods, specialized algorithms, class weight adjustments, plus a no-mitigation approach referred to as the baseline. These strategies were tested on 58 real-life binary imbalanced datasets with imbalance rates ranging from 3 to 120. We conducted a comparative analysis of 10 under-sampling algorithms, 5 over-sampling algorithms, 2 ensemble methods, and 3 specialized algorithms across eight different performance metrics: accuracy, area under the ROC curve (AUC-ROC), balanced accuracy, F1-measure, G-mean, Matthew's correlation coefficient, precision, and recall. Additionally, we assessed the five strategies plus the baseline on altered datasets, derived from real-life data, with both low (3) and high (100 or 300) imbalance ratios (IR). This paper tries to assist a practitioner in selecting a small set of algorithms within one or few of the strategies for testing for a specific imbalanced problem. The principal finding indicates that the effectiveness of each strategy significantly varies depending on the metric used. The paper also examines a selection of newer algorithms within the categories of specialized algorithms, oversampling, and ensemble methods. The findings suggest that the current hierarchy of best-performing strategies for each metric is unlikely to change with the introduction of newer algorithms. • This paper tests imbalanced algorithms grouped under five strategies. • The paper tests 20 algorithms on 53 imbalanced data sets, testing 6 different metrics of quality. • The effectiveness of each strategy varies significantly depending on the evaluation metric employed. • The paper suggests that the ranking of the strategies remains stable with the introduction of new algorithms within each strategy. [ABSTRACT FROM AUTHOR]

The interbank lending network, while facilitating transactions, poses risk contagion in the banking system. To address challenges in existing research, this paper models the interbank lending network using a multi-agent approach and generates a dynamic network through a bidirectional matching mechanism(BiMM). Additionally, We divide banks into three categories based on realistic bank balance sheet data. Given the fact that banks of different categories exhibit different degrees of contagion, we propose the weighted DebtRank (W-DebtRank). Then, comprehensive simulation analysis is conducted on the risk contagion of heterogeneous banks in the dynamic network using W-DebtRank. The proposed method addresses four issues: the heterogeneity of banks, the dynamic nature of networks, the practicality of lending strategies, and the comprehensiveness of risk analysis. The model is validated using the SRISK metric and the Monte Carlo-based SYMBOL simulation model. Through multiple perspectives in simulation experiments, the risk contagion process among banks is deeply investigated in our paper. [ABSTRACT FROM AUTHOR]

The effective identification of bond credit risk is critical for maintaining stability in the bond market and safeguarding investor rights. This paper proposes a URP-CNN model for evaluating bond credit risk of Chinese listed companies. This model effectively combines the unique advantages of the Unthresholded Recurrence plot in extracting and representing spatial domain association information, along with the powerful performance of Convolutional Neural Networks in image feature extraction and classification tasks, thus demonstrating outstanding overall performance in tackling the complex task of predicting default of listed company bonds. The research results show that the URP-CNN model constructed in this paper improves accuracy by 1 %–10 % and F1 score by 10 %–30 % compared to other methods, ensuring accurate identification of non-defaulting enterprises while effectively reducing Type II-Error occurrence rates. Furthermore, the combination of URP method and machine learning models significantly enhances model effectiveness. Compared to single models, models combined with the URP method show varying degrees of improvement in accuracy and F1-score numerical indicators. [ABSTRACT FROM AUTHOR]

Consensus analysis is required to ensure the quality of decision results. It means that some DMs' opinions must be adjusted to reach a consensus. As a result, it harms DMs' benefits because their opinions are not fully considered. Additionally, the consensus-reaching needs cooperation between DMs. Therefore, the consensus improvement can be seen as a cooperative game among DMs. Considering the benefit conflicts of DMs, this paper studies the adjustments of DMs in view of the Nash-bargaining game, which can ensure the global Pareto optimality and maximum fairness of the consensus adjustment scheme. Considering the inconsistency between the Pareto and individual optimal solutions, we first study the Nash-bargaining consensus adjustment solutions between individual DMs. For the situation where DMs form coalitions to reduce their adjustments, two cases for the coalitional Nash-bargaining consensus adjustment solutions of DMs are further studied. Meanwhile, interactive algorithms for the formation of DM coalitions are provided. The main characteristics of the Nash-bargaining consensus adjustment solution are the consideration of personal interest, the rationality of DMs, and the fairness of the allocation scheme. Moreover, this paper takes the choice of the cooperative partner of elderly care institutions as an example to show the concrete application of built models. [ABSTRACT FROM AUTHOR]

Vehicle routing problems (VRP) are a kind of typical combinational optimization problem, particularly in the logistics industry. This paper proposes a constrained evolutionary optimization algorithm, called CEOA, for solving many-objective VRP with simultaneous delivery, pickup, and time windows (VRPSDPTW). Specifically, we first define the weight value vectors based on the constraint satisfaction situation, which can adaptively adjust according to the feedback of population solutions during the search process. Subsequently, based on the feedback from the weight value vectors, the environmental selection strategy is employed to identify promising solutions for both infeasible and feasible situations. Furthermore, considering the data characteristics of the problem at hand, the crossover and mutation operations are tailored to better align with the VRPSDPTW, which is further explained and illustrated in detail regarding solution construction. The experimental results demonstrate the effectiveness of the proposed algorithm for VRPSDPTW in comparison with other state-of-the-art methods. • This paper designs an adapting weight value vector to indicate infeasible solutions, which cannot compare together. • We use a constrained satisfaction strategy to select feasible solutions and select infeasible solutions, respectively. • The crossover and mutation operations are redesigned to make it more fit the real problem. [ABSTRACT FROM AUTHOR]

• First comprehensive, systematic review of deep learning in radiology for lung cancer. • Review 153 papers for segmentation, survival prediction, subtype classification, etc. • Categorize state-of-the-art models on different imaging modalities (PET, CT, PET/CT). • Present the best models across each image modality and lung cancer-related task. • Review current challenges, future directions for efficient lung cancer investigation. This study presents a comprehensive systematic review focusing on the applications of deep learning techniques in lung cancer radiomics. Through a rigorous screening process of 589 scientific publications following the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) guidelines, we selected 153 papers for an in-depth analysis. These papers were categorized based on imaging modality, deep learning model type, and practical applications in lung cancer, such as detection and survival prediction. We specifically emphasized deep learning models and examined their strengths and limitations for each application and imaging modality. Furthermore, we identified potential limitations within the field and proposed future research directions. This study serves as a pioneering resource, being the first comprehensive and systematic review of deep learning techniques, specifically in the context of lung cancer-related applications. Our primary objective was to provide a reference for future research, encouraging the advancement of deep learning techniques in the diagnosis and treatment of lung cancer. By suggesting the most effective deep learning tools for specific application areas, we offer a benchmark for future studies. In summary, this study consolidates and expands existing knowledge on deep learning and radiomics applications in lung cancer. It provides a foundation for further research and serves as a guide for developing and evaluating deep learning models in lung cancer-related applications. [ABSTRACT FROM AUTHOR]

In multi-attribute group decision-making (MAGDM), the social relationships among group members, professional backgrounds and psychological behaviors of decision makers are important factors for achieving high-quality group decisions. However, realizing the consideration of these factors in fuzzy and complex group decision-making scenarios is an important and urgent issue. In MAGDM problems, interval-valued hesitant fuzzy sets (IVHFSs) can better show the hesitant and fuzzy uncertainty information because they are an extension of fuzzy sets. This paper focuses on the score function of IVHFSs and develops a generalized TODIM evaluation method utilizing the novel score functions of IVHFEs and trust networks. The developed method effectively realizes the application of these factors in fuzzy and complex group decision making scenarios. In this contribution, a new deviation function for IVHFSs is created in this paper. It takes into account two types of deviation that are common in IVHFSs: the ambiguity of interval width and the hesitation and uncertainty of multiple intervals. In the sequel, a novel score function for IVHFSs is developed with help of the novel deviation function and the traditional score function. Concerning the perspective of group consistency, a model for determining expert weights is constructed using quality parameters, which combine the novel score function with the trust network. A subjective and objective comprehensive weighting model is made to get attribute weights based on how certain decision information is and the experts' subjective experience. This is done because the more uncertain something is, the higher the risk. Eventually, we develop a generalized TODIM technique for MAGDM based on the novel score function and trust network in IVHFS environment. The developed approach is demonstrated with a preventive engineering decision-making problem. Sensitivity and comparative analyses are implemented to demonstrate the superiority, stability, and validity of the proposed method in this paper. According to the findings of this study, we conclude that the proposed methodology offers a comprehensive and systematic approach to evaluate MAGDM in the context of IVHFS with trust networks. [ABSTRACT FROM AUTHOR]

Powder bed quality is critical in Laser Powder Bed Fusion (LPBF) as defects in the powder bed will affect the quality of the forming parts. Recently, numerous powder bed defect detection methods based on semantic segmentation algorithms have been developed. However, due to the computational resource constraints and real-time requirements in industry scenarios, these heavy models face challenges in deploying into the LPBF process monitoring system. Meanwhile, existing lightweight models struggle to achieve sufficient performance on industrial data due to their limited feature extraction capabilities. To address the challenges in industrial deployment, this paper proposes a lightweight and efficient LPBF layer-wise defect detection paradigm to achieve a balance between performance and efficiency. Aiming at improving the performance of the lightweight model, this paper proposes a structured Knowledge Distillation framework, in which a pre-trained high-performance segmentation model (UNet++) is used to guide the training process of a lightweight model. To address the impact of model discrepancies on the effectiveness of Knowledge Distillation and further improve the inference speed, this paper constructs a specific lightweight model and applies Structural Re-parameterization to deeply compress the model. Moreover, we created a dataset comprising 406 images of powder-bed defects, with each image annotated at the pixel level. Massive experiments based on the dataset demonstrate the effectiveness of the proposed paradigm, with an excellent trade-off in performance and efficiency. The speed of the proposed model is approximately 5 times faster than that of high-performance models while maintaining comparable performance. • A lightweight and efficient paradigm for LPBF in-situ defect detection. • Introduced Structure Re-parameterization to enhance the Knowledge Distillation. • An excellent trade-off in performance and efficiency for model deployment. [ABSTRACT FROM AUTHOR]

• A bidirectional knowledge graph of the vehicle tire/road structure-borne noise is developed. • A Task-Conditional Gate Control (TCGC) approach is proposed for multi-task learning. • A novel method that combines knowledge graph and multi-task ResNet is proposed. • The proposed method has advantages in effectiveness, robustness and interpretability. Pure electric vehicles (PEVs) offer a significant advantage in their lower interior noise levels compared to traditional combustion engines, making them increasingly popular among consumers. However, the absence of engine noise has brought attention to other sources of noise, particularly tire/road structure-borne (TRS) noise, which significantly impacts the sound quality of the PEV interior and passengers' psychological comfort. To address this issue, numerous studies have employed simulation analysis, data-driven approaches, and experimental test methods for the prediction and optimization of TRS noise. Nevertheless, the optimization and rectification of TRS noise problems present recurring challenges and difficulties due to the involvement of numerous variables and the weak correlation between TRS noise and vibration. In response to these challenges, this paper introduces a novel approach that combines knowledge graph and multi-task ResNet for predicting and optimizing PEV TRS noise. The proposed method has been experimentally validated and has demonstrated superior effectiveness and robustness compared to three commonly used prediction and optimization methods. The paper's main contributions are twofold: Firstly, it introduces a novel mechanism that fuses mechanism-driven and data-driven approaches by utilizing a knowledge graph to establish dependency and correlation relationships among TRS entities. This fusion, together with the multi-task ResNet, enhances the interpretability of the solution results while improving computational efficiency. Secondly, it introduces a multi-task ResNet prediction method, named TCGC-ResNet, which incorporates a Task-Conditional Gate Control (TCGC) technique. By explicitly separating shared components from task-common components and implementing a gate control mechanism, TCGC-ResNet enables the gradual extraction and separation of task conditional information knowledge. These advancements contribute to a more comprehensive and effective solution for predicting and optimizing PEV TRS noise. [ABSTRACT FROM AUTHOR]

Integrating smart industrial products (SIPs) into production processes introduces new dynamics of capabilities and challenges within organisations. However, a prevalent issue is the ad hoc adoption of SIPs without a cohesive strategy, resulting in isolated solutions that do not effectively enhance core organisational functions. Our research fills this critical gap by identifying and combining the capabilities and barriers posed by SIPs. Our findings allow us to propose a framework comprising the stages each main organisational function needs to develop to move from a traditional to a completely autonomous decision-making function. This evolutional path requires that each organisational function acquires selected capabilities and overcomes specific barriers. Our approach encompasses a multi-method methodology, commencing with a systematic literature review (SLR) encompassing 44 papers, leading to the identification of 20 capabilities and 23 barriers. Subsequently, through rigorous content analyses and expert interviews, we formulate the framework. This paper contributes to academia by providing a framework with an evolutional path that main organisational functions may follow according to the capability they acquire from the SIP and which barriers should be surpassed at each level. For managers in practice, the proposed framework enables a better understanding of the stage of their operations and which capabilities will take their main organisational function from traditional (level 0) to autonomous (level 3) stages. [ABSTRACT FROM AUTHOR]

Accurate remaining useful life (RUL) prediction holds significant importance for health management of aero-engines, ensuring safety and reducing the maintenance cost. The coupling between variable operating conditions and diverse sensor signals makes it hard to construct an accurate and stable model, which predicts precise results and simultaneously obtains condition-independent features reflecting the degradation trend. To address the problem, this paper proposes a novel approach named residual-based adversarial feature decoupling (RAFD) for RUL prediction of aero-engine which achieves decoupling both explicitly and implicitly. The paper formally defines the coupling relationships within the signals, consisting of information from normal pattern, degradation pattern, and operating conditions which are decoupled explicitly and implicitly. An operation-condition-mapping model (OCMM) is developed to explicitly decouple normal pattern, establishing the mapping between operation conditions and sensor signals in the healthy stage. Residuals serve as inputs of the prediction model, a continuous adversarial neural network specifically designed for implicit decoupling which extracts condition-independent features and predicts RUL accurately. The effectiveness of our method is validated on NASA's N-CMAPSS dataset, resulting in superior prediction performance and feature visualization when compared with other existing methods. • Signal coupling is defined and decoupled by RAFD explicitly and implicitly. • OCMM is proposed to extract residuals for explicit degradation indication. • CANN is proposed to capture implicit decoupling of operation conditions. • The superiority of the method is validated on N-CMAPSS dataset. [ABSTRACT FROM AUTHOR]

Intelligent fault diagnosis, detection, and prognostics (DDP) for complex equipment prognostics and health management (PHM) have achieved remarkable breakthroughs. Equipment in industrial scenarios often operates in normal conditions, resulting in missing anomalies, limited failures, and incomplete degradation paths. Thus the limited information on the state of the equipment collected from sensor readings severely hinders the cognitive capabilities of discriminative artificial intelligence (AI) for PHM. Data augmentation and generation (DA&G) techniques, represented by generative AI, have shown great promise in overcoming the limitations of PHM application scenarios. Research on DA&G has yielded significant achievements, but a comprehensive review in the mechanical field is still lacking. To this end, this paper provides a comprehensive review of DA&G techniques aimed at solving the DDP problems, which are divided into three categories insights of data, mechanism, and features. The data-based randomized approach applies controlled randomness for augmentation. The mechanism-based domain-specific techniques advocate for exploring relationships between the physical entity and monitoring data for generating by reasoned inference. The feature-based generative model aims to identify the latent space of data and subsequently resample it. Finally, the paper explores strategies for evaluating DA&G and provides a deep insight into the challenges and opportunities of DA&G techniques. [ABSTRACT FROM AUTHOR]