Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous human...Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous humaneffort to label the image. Within this field, other research endeavors utilize weakly supervised methods. Theseapproaches aim to reduce the expenses associated with annotation by leveraging sparsely annotated data, such asscribbles. This paper presents a novel technique called a weakly supervised network using scribble-supervised andedge-mask (WSSE-net). This network is a three-branch network architecture, whereby each branch is equippedwith a distinct decoder module dedicated to road extraction tasks. One of the branches is dedicated to generatingedge masks using edge detection algorithms and optimizing road edge details. The other two branches supervise themodel’s training by employing scribble labels and spreading scribble information throughout the image. To addressthe historical flaw that created pseudo-labels that are not updated with network training, we use mixup to blendprediction results dynamically and continually update new pseudo-labels to steer network training. Our solutiondemonstrates efficient operation by simultaneously considering both edge-mask aid and dynamic pseudo-labelsupport. The studies are conducted on three separate road datasets, which consist primarily of high-resolutionremote-sensing satellite photos and drone images. The experimental findings suggest that our methodologyperforms better than advanced scribble-supervised approaches and specific traditional fully supervised methods.展开更多
Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning...Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.展开更多
Recently,weak supervision has received growing attention in the field of salient object detection due to the convenience of labelling.However,there is a large performance gap between weakly supervised and fully superv...Recently,weak supervision has received growing attention in the field of salient object detection due to the convenience of labelling.However,there is a large performance gap between weakly supervised and fully supervised salient object detectors because the scribble annotation can only provide very limited foreground/background information.Therefore,an intuitive idea is to infer annotations that cover more complete object and background regions for training.To this end,a label inference strategy is proposed based on the assumption that pixels with similar colours and close positions should have consistent labels.Specifically,k-means clustering algorithm was first performed on both colours and coordinates of original annotations,and then assigned the same labels to points having similar colours with colour cluster centres and near coordinate cluster centres.Next,the same annotations for pixels with similar colours within each kernel neighbourhood was set further.Extensive experiments on six benchmarks demonstrate that our method can significantly improve the performance and achieve the state-of-the-art results.展开更多
Text classification,by automatically categorizing texts,is one of the foundational elements of natural language processing applications.This study investigates how text classification performance can be improved throu...Text classification,by automatically categorizing texts,is one of the foundational elements of natural language processing applications.This study investigates how text classification performance can be improved through the integration of entity-relation information obtained from the Wikidata(Wikipedia database)database and BERTbased pre-trained Named Entity Recognition(NER)models.Focusing on a significant challenge in the field of natural language processing(NLP),the research evaluates the potential of using entity and relational information to extract deeper meaning from texts.The adopted methodology encompasses a comprehensive approach that includes text preprocessing,entity detection,and the integration of relational information.Experiments conducted on text datasets in both Turkish and English assess the performance of various classification algorithms,such as Support Vector Machine,Logistic Regression,Deep Neural Network,and Convolutional Neural Network.The results indicate that the integration of entity-relation information can significantly enhance algorithmperformance in text classification tasks and offer new perspectives for information extraction and semantic analysis in NLP applications.Contributions of this work include the utilization of distant supervised entity-relation information in Turkish text classification,the development of a Turkish relational text classification approach,and the creation of a relational database.By demonstrating potential performance improvements through the integration of distant supervised entity-relation information into Turkish text classification,this research aims to support the effectiveness of text-based artificial intelligence(AI)tools.Additionally,it makes significant contributions to the development ofmultilingual text classification systems by adding deeper meaning to text content,thereby providing a valuable addition to current NLP studies and setting an important reference point for future research.展开更多
As the realm of enterprise-level conversational AI continues to evolve, it becomes evident that while generalized Large Language Models (LLMs) like GPT-3.5 bring remarkable capabilities, they also bring forth formidab...As the realm of enterprise-level conversational AI continues to evolve, it becomes evident that while generalized Large Language Models (LLMs) like GPT-3.5 bring remarkable capabilities, they also bring forth formidable challenges. These models, honed on vast and diverse datasets, have undoubtedly pushed the boundaries of natural language understanding and generation. However, they often stumble when faced with the intricate demands of nuanced enterprise applications. This research advocates for a strategic paradigm shift, urging enterprises to embrace a fine-tuning approach as a means to optimize conversational AI. While generalized LLMs are linguistic marvels, their inability to cater to the specific needs of businesses across various industries poses a critical challenge. This strategic shift involves empowering enterprises to seamlessly integrate their own datasets into LLMs, a process that extends beyond linguistic enhancement. The core concept of this approach centers on customization, enabling businesses to fine-tune the AI’s functionality to fit precisely within their unique business landscapes. By immersing the LLM in industry-specific documents, customer interaction records, internal reports, and regulatory guidelines, the AI transcends its generic capabilities to become a sophisticated conversational partner aligned with the intricacies of the enterprise’s domain. The transformative potential of this fine-tuning approach cannot be overstated. It enables a transition from a universal AI solution to a highly customizable tool. The AI evolves from being a linguistic powerhouse to a contextually aware, industry-savvy assistant. As a result, it not only responds with linguistic accuracy but also with depth, relevance, and resonance, significantly elevating user experiences and operational efficiency. In the subsequent sections, this paper delves into the intricacies of fine-tuning, exploring the multifaceted challenges and abundant opportunities it presents. It addresses the technical intricacies of data integration, ethical considerations surrounding data usage, and the broader implications for the future of enterprise AI. The journey embarked upon in this research holds the potential to redefine the role of conversational AI in enterprises, ushering in an era where AI becomes a dynamic, deeply relevant, and highly effective tool, empowering businesses to excel in an ever-evolving digital landscape.展开更多
The federated self-supervised framework is a distributed machine learning method that combines federated learning and self-supervised learning, which can effectively solve the problem of traditional federated learning...The federated self-supervised framework is a distributed machine learning method that combines federated learning and self-supervised learning, which can effectively solve the problem of traditional federated learning being difficult to process large-scale unlabeled data. The existing federated self-supervision framework has problems with low communication efficiency and high communication delay between clients and central servers. Therefore, we added edge servers to the federated self-supervision framework to reduce the pressure on the central server caused by frequent communication between both ends. A communication compression scheme using gradient quantization and sparsification was proposed to optimize the communication of the entire framework, and the algorithm of the sparse communication compression module was improved. Experiments have proved that the learning rate changes of the improved sparse communication compression module are smoother and more stable. Our communication compression scheme effectively reduced the overall communication overhead.展开更多
The aim of this paper is to broaden the application of Stochastic Configuration Network (SCN) in the semi-supervised domain by utilizing common unlabeled data in daily life. It can enhance the classification accuracy ...The aim of this paper is to broaden the application of Stochastic Configuration Network (SCN) in the semi-supervised domain by utilizing common unlabeled data in daily life. It can enhance the classification accuracy of decentralized SCN algorithms while effectively protecting user privacy. To this end, we propose a decentralized semi-supervised learning algorithm for SCN, called DMT-SCN, which introduces teacher and student models by combining the idea of consistency regularization to improve the response speed of model iterations. In order to reduce the possible negative impact of unsupervised data on the model, we purposely change the way of adding noise to the unlabeled data. Simulation results show that the algorithm can effectively utilize unlabeled data to improve the classification accuracy of SCN training and is robust under different ground simulation environments.展开更多
Single-molecule force spectroscopy(SMFS)measurements of the dynamics of biomolecules typically require identifying massive events and states from large data sets,such as extracting rupture forces from force-extension ...Single-molecule force spectroscopy(SMFS)measurements of the dynamics of biomolecules typically require identifying massive events and states from large data sets,such as extracting rupture forces from force-extension curves(FECs)in pulling experiments and identifying states from extension-time trajectories(ETTs)in force-clamp experiments.The former is often accomplished manually and hence is time-consuming and laborious while the latter is always impeded by the presence of baseline drift.In this study,we attempt to accurately and automatically identify the events and states from SMFS experiments with a machine learning approach,which combines clustering and classification for event identification of SMFS(ACCESS).As demonstrated by analysis of a series of data sets,ACCESS can extract the rupture forces from FECs containing multiple unfolding steps and classify the rupture forces into the corresponding conformational transitions.Moreover,ACCESS successfully identifies the unfolded and folded states even though the ETTs display severe nonmonotonic baseline drift.Besides,ACCESS is straightforward in use as it requires only three easy-to-interpret parameters.As such,we anticipate that ACCESS will be a useful,easy-to-implement and high-performance tool for event and state identification across a range of single-molecule experiments.展开更多
The coronavirus disease 2019(COVID-19)has severely disrupted both human life and the health care system.Timely diagnosis and treatment have become increasingly important;however,the distribution and size of lesions va...The coronavirus disease 2019(COVID-19)has severely disrupted both human life and the health care system.Timely diagnosis and treatment have become increasingly important;however,the distribution and size of lesions vary widely among individuals,making it challenging to accurately diagnose the disease.This study proposed a deep-learning disease diagnosismodel based onweakly supervised learning and clustering visualization(W_CVNet)that fused classification with segmentation.First,the data were preprocessed.An optimizable weakly supervised segmentation preprocessing method(O-WSSPM)was used to remove redundant data and solve the category imbalance problem.Second,a deep-learning fusion method was used for feature extraction and classification recognition.A dual asymmetric complementary bilinear feature extraction method(D-CBM)was used to fully extract complementary features,which solved the problem of insufficient feature extraction by a single deep learning network.Third,an unsupervised learning method based on Fuzzy C-Means(FCM)clustering was used to segment and visualize COVID-19 lesions enabling physicians to accurately assess lesion distribution and disease severity.In this study,5-fold cross-validation methods were used,and the results showed that the network had an average classification accuracy of 85.8%,outperforming six recent advanced classification models.W_CVNet can effectively help physicians with automated aid in diagnosis to determine if the disease is present and,in the case of COVID-19 patients,to further predict the area of the lesion.展开更多
N-11-azaartemisinins potentially active against Plasmodium falciparum are designed by combining molecular electrostatic potential (MEP), ligand-receptor interaction, and models built with supervised machine learning m...N-11-azaartemisinins potentially active against Plasmodium falciparum are designed by combining molecular electrostatic potential (MEP), ligand-receptor interaction, and models built with supervised machine learning methods (PCA, HCA, KNN, SIMCA, and SDA). The optimization of molecular structures was performed using the B3LYP/6-31G* approach. MEP maps and ligand-receptor interactions were used to investigate key structural features required for biological activities and likely interactions between N-11-azaartemisinins and heme, respectively. The supervised machine learning methods allowed the separation of the investigated compounds into two classes: cha and cla, with the properties ε<sub>LUMO+1</sub> (one level above lowest unoccupied molecular orbital energy), d(C<sub>6</sub>-C<sub>5</sub>) (distance between C<sub>6</sub> and C<sub>5</sub> atoms in ligands), and TSA (total surface area) responsible for the classification. The insights extracted from the investigation developed and the chemical intuition enabled the design of sixteen new N-11-azaartemisinins (prediction set), moreover, models built with supervised machine learning methods were applied to this prediction set. The result of this application showed twelve new promising N-11-azaartemisinins for synthesis and biological evaluation.展开更多
A large variety of complaint reports reflect subjective information expressed by citizens.A key challenge of text summarization for complaint reports is to ensure the factual consistency of generated summary.Therefore...A large variety of complaint reports reflect subjective information expressed by citizens.A key challenge of text summarization for complaint reports is to ensure the factual consistency of generated summary.Therefore,in this paper,a simple and weakly supervised framework considering factual consistency is proposed to generate a summary of city-based complaint reports without pre-labeled sentences/words.Furthermore,it considers the importance of entity in complaint reports to ensure factual consistency of summary.Experimental results on the customer review datasets(Yelp and Amazon)and complaint report dataset(complaint reports of Shenyang in China)show that the proposed framework outperforms state-of-the-art approaches in ROUGE scores and human evaluation.It unveils the effectiveness of our approach to helping in dealing with complaint reports.展开更多
In recent years, the place occupied by the various manifestations of cyber-crime in companies has been considerable. Indeed, due to the rapid evolution of telecommunications technologies, companies, regardless of thei...In recent years, the place occupied by the various manifestations of cyber-crime in companies has been considerable. Indeed, due to the rapid evolution of telecommunications technologies, companies, regardless of their size or sector of activity, are now the target of advanced persistent threats. The Work 2035 study also revealed that cyber crimes (such as critical infrastructure hacks) and massive data breaches are major sources of concern. Thus, it is important for organizations to guarantee a minimum level of security to avoid potential attacks that can cause paralysis of systems, loss of sensitive data, exposure to blackmail, damage to reputation or even a commercial harm. To do this, among other means, hardening is used, the main objective of which is to reduce the attack surface within a company. The execution of the hardening configurations as well as the verification of these are carried out on the servers and network equipment with the aim of reducing the number of openings present by keeping only those which are necessary for proper operation. However, nowadays, in many companies, these tasks are done manually. As a result, the execution and verification of hardening configurations are very often subject to potential errors but also highly consuming human and financial resources. The problem is that it is essential for operators to maintain an optimal level of security while minimizing costs, hence the interest in automating hardening processes and verifying the hardening of servers and network equipment. It is in this logic that we propose within the framework of this work the reinforcement of the security of the information systems (IS) by the automation of the mechanisms of hardening. In our work, we have, on the one hand, set up a hardening procedure in accordance with international security standards for servers, routers and switches and, on the other hand, designed and produced a functional application which makes it possible to: 1) Realise the configuration of the hardening;2) Verify them;3) Correct the non conformities;4) Write and send by mail a verification report for the configurations;5) And finally update the procedures of hardening. Our web application thus created allows in less than fifteen (15) minutes actions that previously took at least five (5) hours of time. This allows supervised network operators to save time and money, but also to improve their security standards in line with international standards.展开更多
Nowadays, in data science, supervised learning algorithms are frequently used to perform text classification. However, African textual data, in general, have been studied very little using these methods. This article ...Nowadays, in data science, supervised learning algorithms are frequently used to perform text classification. However, African textual data, in general, have been studied very little using these methods. This article notes the particularity of the data and measures the level of precision of predictions of naive Bayes algorithms, decision tree, and SVM (Support Vector Machine) on a corpus of computer jobs taken on the internet. This is due to the data imbalance problem in machine learning. However, this problem essentially focuses on the distribution of the number of documents in each class or subclass. Here, we delve deeper into the problem to the word count distribution in a set of documents. The results are compared with those obtained on a set of French IT offers. It appears that the precision of the classification varies between 88% and 90% for French offers against 67%, at most, for Cameroonian offers. The contribution of this study is twofold. Indeed, it clearly shows that, in a similar job category, job offers on the internet in Cameroon are more unstructured compared to those available in France, for example. Moreover, it makes it possible to emit a strong hypothesis according to which sets of texts having a symmetrical distribution of the number of words obtain better results with supervised learning algorithms.展开更多
Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently.However,there are still two challenges.First,most of t...Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently.However,there are still two challenges.First,most of the real‐word system are multiple relations,where entities are linked by different types of relations,and each relation is a view of the graph network.Second,the rich multi‐scale information(structure‐level and feature‐level)of the graph network can be seen as self‐supervised signals,which are not fully exploited.A novel contrastive self‐supervised representation learning framework on attributed multiplex graph networks with multi‐scale(named CoLM^(2)S)information is presented in this study.It mainly contains two components:intra‐relation contrast learning and interrelation contrastive learning.Specifically,the contrastive self‐supervised representation learning framework on attributed single‐layer graph networks with multi‐scale information(CoLMS)framework with the graph convolutional network as encoder to capture the intra‐relation information with multi‐scale structure‐level and feature‐level selfsupervised signals is introduced first.The structure‐level information includes the edge structure and sub‐graph structure,and the feature‐level information represents the output of different graph convolutional layer.Second,according to the consensus assumption among inter‐relations,the CoLM^(2)S framework is proposed to jointly learn various graph relations in attributed multiplex graph network to achieve global consensus node embedding.The proposed method can fully distil the graph information.Extensive experiments on unsupervised node clustering and graph visualisation tasks demonstrate the effectiveness of our methods,and it outperforms existing competitive baselines.展开更多
Rare labeled data are difficult to recognize by using conventional methods in the process of radar emitter recogni-tion.To solve this problem,an optimized cooperative semi-supervised learning radar emitter recognition...Rare labeled data are difficult to recognize by using conventional methods in the process of radar emitter recogni-tion.To solve this problem,an optimized cooperative semi-supervised learning radar emitter recognition method based on a small amount of labeled data is developed.First,a small amount of labeled data are randomly sampled by using the bootstrap method,loss functions for three common deep learning net-works are improved,the uniform distribution and cross-entropy function are combined to reduce the overconfidence of softmax classification.Subsequently,the dataset obtained after sam-pling is adopted to train three improved networks so as to build the initial model.In addition,the unlabeled data are preliminarily screened through dynamic time warping(DTW)and then input into the initial model trained previously for judgment.If the judg-ment results of two or more networks are consistent,the unla-beled data are labeled and put into the labeled data set.Lastly,the three network models are input into the labeled dataset for training,and the final model is built.As revealed by the simula-tion results,the semi-supervised learning method adopted in this paper is capable of exploiting a small amount of labeled data and basically achieving the accuracy of labeled data recognition.展开更多
Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requir...Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.展开更多
In order to obtain a high-quality weld during the laser welding process, extracting the characteristic parameters of weld pool is an important issue for automated welding. In this paper, the type 304 austenitic stainl...In order to obtain a high-quality weld during the laser welding process, extracting the characteristic parameters of weld pool is an important issue for automated welding. In this paper, the type 304 austenitic stainless steel is welded by a 5 kW high-power fiber laser and a high-speed camera is employed to capture the topside images of weld pools. Then we propose a robust visual-detection approach for the molten pool based on the supervised descent method. It provides an elegant framework for representing the outline of a weld pool and is especially efficient for weld pool detection in the presence of strong uncertainties and disturbances. Finally, welding experimental results verified that the proposed approach can extract the weld pool boundary accurately, which will lay a solid foundation for controlling the weld quality of fiber laser welding process.展开更多
The purpose of this study was to explore the effects of supervised movie appreciation on improving the life meaning sense among college students. The intervention combined by “pre-video, post counseling” was conduct...The purpose of this study was to explore the effects of supervised movie appreciation on improving the life meaning sense among college students. The intervention combined by “pre-video, post counseling” was conducted on the experimental group, while the control group received no intervention. Results have shown that the scores on the subscales of will to meaning, life purpose, life control, suffer acceptance and on the total scale have improved significantly. No gender difference was found on the intervention effect, and participants receiving intervention maintained higher level on related subscales a week later, indicating that supervised movie appreciation is an effective way to improve the life meaning sense among college students.展开更多
AIM To evaluate the effect of a 12-mo supervised aerobic and resistance training, on renal function and exercise capacity compared to usual care recommendations.METHODS Ninety-nine kidney transplant recipients(KTRs) w...AIM To evaluate the effect of a 12-mo supervised aerobic and resistance training, on renal function and exercise capacity compared to usual care recommendations.METHODS Ninety-nine kidney transplant recipients(KTRs) were assigned to interventional exercise(Group A; n = 52) and a usual care cohort(Group B; n = 47). Blood and urine chemistry, exercise capacity, muscular strength, anthropometric measures and health-related quality of life(HRQo L) were assessed at baseline, and after 6 and 12 mo. Group A underwent a supervised training three times per week for 12 mo. Group B received only general recommendations about home-based physical activities.RESULTS Eighty-five KTRs completed the study(Group A, n = 44; Group B, n = 41). After 12 mo, renal function remained stable in both groups. Group A significantly increased maximum workload(+13 W, P = 0.0003), V'O2 peak(+3.1 mL/kg per minute, P = 0.0099), muscular strength in plantar flexor(+12 kg, P = 0.0368), height in the countermovement jump(+1.9 cm, P = 0.0293) and decreased in Body Mass Index(-0.5 kg/m^2, P = 0.0013). HRQo L significantly improved in physical function(P = 0.0019), physical-role limitations(P = 0.0321) and social functioning scales(P = 0.0346). Noimprovements were found in Group B.CONCLUSION Twelve-month of supervised aerobic and resistance training improves the physiological variables related to physical fitness and cardiovascular risks without consequences on renal function. Recommendations alone are not sufficient to induce changes in exercise capacity of KTRs. Our study is an example of collaborative working between transplant centres, sports medicine and exercise facilities.展开更多
基金the National Natural Science Foundation of China(42001408,61806097).
文摘Significant advancements have been achieved in road surface extraction based on high-resolution remote sensingimage processing. Most current methods rely on fully supervised learning, which necessitates enormous humaneffort to label the image. Within this field, other research endeavors utilize weakly supervised methods. Theseapproaches aim to reduce the expenses associated with annotation by leveraging sparsely annotated data, such asscribbles. This paper presents a novel technique called a weakly supervised network using scribble-supervised andedge-mask (WSSE-net). This network is a three-branch network architecture, whereby each branch is equippedwith a distinct decoder module dedicated to road extraction tasks. One of the branches is dedicated to generatingedge masks using edge detection algorithms and optimizing road edge details. The other two branches supervise themodel’s training by employing scribble labels and spreading scribble information throughout the image. To addressthe historical flaw that created pseudo-labels that are not updated with network training, we use mixup to blendprediction results dynamically and continually update new pseudo-labels to steer network training. Our solutiondemonstrates efficient operation by simultaneously considering both edge-mask aid and dynamic pseudo-labelsupport. The studies are conducted on three separate road datasets, which consist primarily of high-resolutionremote-sensing satellite photos and drone images. The experimental findings suggest that our methodologyperforms better than advanced scribble-supervised approaches and specific traditional fully supervised methods.
基金This work is part of the research projects LaTe4PoliticES(PID2022-138099OBI00)funded by MICIU/AEI/10.13039/501100011033the European Regional Development Fund(ERDF)-A Way of Making Europe and LT-SWM(TED2021-131167B-I00)funded by MICIU/AEI/10.13039/501100011033the European Union NextGenerationEU/PRTR.Mr.Ronghao Pan is supported by the Programa Investigo grant,funded by the Region of Murcia,the Spanish Ministry of Labour and Social Economy and the European Union-NextGenerationEU under the“Plan de Recuperación,Transformación y Resiliencia(PRTR).”。
文摘Large Language Models(LLMs)are increasingly demonstrating their ability to understand natural language and solve complex tasks,especially through text generation.One of the relevant capabilities is contextual learning,which involves the ability to receive instructions in natural language or task demonstrations to generate expected outputs for test instances without the need for additional training or gradient updates.In recent years,the popularity of social networking has provided a medium through which some users can engage in offensive and harmful online behavior.In this study,we investigate the ability of different LLMs,ranging from zero-shot and few-shot learning to fine-tuning.Our experiments show that LLMs can identify sexist and hateful online texts using zero-shot and few-shot approaches through information retrieval.Furthermore,it is found that the encoder-decoder model called Zephyr achieves the best results with the fine-tuning approach,scoring 86.811%on the Explainable Detection of Online Sexism(EDOS)test-set and 57.453%on the Multilingual Detection of Hate Speech Against Immigrants and Women in Twitter(HatEval)test-set.Finally,it is confirmed that the evaluated models perform well in hate text detection,as they beat the best result in the HatEval task leaderboard.The error analysis shows that contextual learning had difficulty distinguishing between types of hate speech and figurative language.However,the fine-tuned approach tends to produce many false positives.
文摘Recently,weak supervision has received growing attention in the field of salient object detection due to the convenience of labelling.However,there is a large performance gap between weakly supervised and fully supervised salient object detectors because the scribble annotation can only provide very limited foreground/background information.Therefore,an intuitive idea is to infer annotations that cover more complete object and background regions for training.To this end,a label inference strategy is proposed based on the assumption that pixels with similar colours and close positions should have consistent labels.Specifically,k-means clustering algorithm was first performed on both colours and coordinates of original annotations,and then assigned the same labels to points having similar colours with colour cluster centres and near coordinate cluster centres.Next,the same annotations for pixels with similar colours within each kernel neighbourhood was set further.Extensive experiments on six benchmarks demonstrate that our method can significantly improve the performance and achieve the state-of-the-art results.
文摘Text classification,by automatically categorizing texts,is one of the foundational elements of natural language processing applications.This study investigates how text classification performance can be improved through the integration of entity-relation information obtained from the Wikidata(Wikipedia database)database and BERTbased pre-trained Named Entity Recognition(NER)models.Focusing on a significant challenge in the field of natural language processing(NLP),the research evaluates the potential of using entity and relational information to extract deeper meaning from texts.The adopted methodology encompasses a comprehensive approach that includes text preprocessing,entity detection,and the integration of relational information.Experiments conducted on text datasets in both Turkish and English assess the performance of various classification algorithms,such as Support Vector Machine,Logistic Regression,Deep Neural Network,and Convolutional Neural Network.The results indicate that the integration of entity-relation information can significantly enhance algorithmperformance in text classification tasks and offer new perspectives for information extraction and semantic analysis in NLP applications.Contributions of this work include the utilization of distant supervised entity-relation information in Turkish text classification,the development of a Turkish relational text classification approach,and the creation of a relational database.By demonstrating potential performance improvements through the integration of distant supervised entity-relation information into Turkish text classification,this research aims to support the effectiveness of text-based artificial intelligence(AI)tools.Additionally,it makes significant contributions to the development ofmultilingual text classification systems by adding deeper meaning to text content,thereby providing a valuable addition to current NLP studies and setting an important reference point for future research.
文摘As the realm of enterprise-level conversational AI continues to evolve, it becomes evident that while generalized Large Language Models (LLMs) like GPT-3.5 bring remarkable capabilities, they also bring forth formidable challenges. These models, honed on vast and diverse datasets, have undoubtedly pushed the boundaries of natural language understanding and generation. However, they often stumble when faced with the intricate demands of nuanced enterprise applications. This research advocates for a strategic paradigm shift, urging enterprises to embrace a fine-tuning approach as a means to optimize conversational AI. While generalized LLMs are linguistic marvels, their inability to cater to the specific needs of businesses across various industries poses a critical challenge. This strategic shift involves empowering enterprises to seamlessly integrate their own datasets into LLMs, a process that extends beyond linguistic enhancement. The core concept of this approach centers on customization, enabling businesses to fine-tune the AI’s functionality to fit precisely within their unique business landscapes. By immersing the LLM in industry-specific documents, customer interaction records, internal reports, and regulatory guidelines, the AI transcends its generic capabilities to become a sophisticated conversational partner aligned with the intricacies of the enterprise’s domain. The transformative potential of this fine-tuning approach cannot be overstated. It enables a transition from a universal AI solution to a highly customizable tool. The AI evolves from being a linguistic powerhouse to a contextually aware, industry-savvy assistant. As a result, it not only responds with linguistic accuracy but also with depth, relevance, and resonance, significantly elevating user experiences and operational efficiency. In the subsequent sections, this paper delves into the intricacies of fine-tuning, exploring the multifaceted challenges and abundant opportunities it presents. It addresses the technical intricacies of data integration, ethical considerations surrounding data usage, and the broader implications for the future of enterprise AI. The journey embarked upon in this research holds the potential to redefine the role of conversational AI in enterprises, ushering in an era where AI becomes a dynamic, deeply relevant, and highly effective tool, empowering businesses to excel in an ever-evolving digital landscape.
文摘The federated self-supervised framework is a distributed machine learning method that combines federated learning and self-supervised learning, which can effectively solve the problem of traditional federated learning being difficult to process large-scale unlabeled data. The existing federated self-supervision framework has problems with low communication efficiency and high communication delay between clients and central servers. Therefore, we added edge servers to the federated self-supervision framework to reduce the pressure on the central server caused by frequent communication between both ends. A communication compression scheme using gradient quantization and sparsification was proposed to optimize the communication of the entire framework, and the algorithm of the sparse communication compression module was improved. Experiments have proved that the learning rate changes of the improved sparse communication compression module are smoother and more stable. Our communication compression scheme effectively reduced the overall communication overhead.
文摘The aim of this paper is to broaden the application of Stochastic Configuration Network (SCN) in the semi-supervised domain by utilizing common unlabeled data in daily life. It can enhance the classification accuracy of decentralized SCN algorithms while effectively protecting user privacy. To this end, we propose a decentralized semi-supervised learning algorithm for SCN, called DMT-SCN, which introduces teacher and student models by combining the idea of consistency regularization to improve the response speed of model iterations. In order to reduce the possible negative impact of unsupervised data on the model, we purposely change the way of adding noise to the unlabeled data. Simulation results show that the algorithm can effectively utilize unlabeled data to improve the classification accuracy of SCN training and is robust under different ground simulation environments.
基金the support from the Physical Research Platform in the School of Physics of Sun Yat-sen University(PRPSP,SYSU)Project supported by the National Natural Science Foundation of China(Grant No.12074445)the Open Fund of the State Key Laboratory of Optoelectronic Materials and Technologies of Sun Yat-sen University(Grant No.OEMT-2022-ZTS-05)。
文摘Single-molecule force spectroscopy(SMFS)measurements of the dynamics of biomolecules typically require identifying massive events and states from large data sets,such as extracting rupture forces from force-extension curves(FECs)in pulling experiments and identifying states from extension-time trajectories(ETTs)in force-clamp experiments.The former is often accomplished manually and hence is time-consuming and laborious while the latter is always impeded by the presence of baseline drift.In this study,we attempt to accurately and automatically identify the events and states from SMFS experiments with a machine learning approach,which combines clustering and classification for event identification of SMFS(ACCESS).As demonstrated by analysis of a series of data sets,ACCESS can extract the rupture forces from FECs containing multiple unfolding steps and classify the rupture forces into the corresponding conformational transitions.Moreover,ACCESS successfully identifies the unfolded and folded states even though the ETTs display severe nonmonotonic baseline drift.Besides,ACCESS is straightforward in use as it requires only three easy-to-interpret parameters.As such,we anticipate that ACCESS will be a useful,easy-to-implement and high-performance tool for event and state identification across a range of single-molecule experiments.
基金funded by the Open Foundation of Anhui EngineeringResearch Center of Intelligent Perception and Elderly Care,Chuzhou University(No.2022OPA03)the Higher EducationNatural Science Foundation of Anhui Province(No.KJ2021B01)and the Innovation Team Projects of Universities in Guangdong(No.2022KCXTD057).
文摘The coronavirus disease 2019(COVID-19)has severely disrupted both human life and the health care system.Timely diagnosis and treatment have become increasingly important;however,the distribution and size of lesions vary widely among individuals,making it challenging to accurately diagnose the disease.This study proposed a deep-learning disease diagnosismodel based onweakly supervised learning and clustering visualization(W_CVNet)that fused classification with segmentation.First,the data were preprocessed.An optimizable weakly supervised segmentation preprocessing method(O-WSSPM)was used to remove redundant data and solve the category imbalance problem.Second,a deep-learning fusion method was used for feature extraction and classification recognition.A dual asymmetric complementary bilinear feature extraction method(D-CBM)was used to fully extract complementary features,which solved the problem of insufficient feature extraction by a single deep learning network.Third,an unsupervised learning method based on Fuzzy C-Means(FCM)clustering was used to segment and visualize COVID-19 lesions enabling physicians to accurately assess lesion distribution and disease severity.In this study,5-fold cross-validation methods were used,and the results showed that the network had an average classification accuracy of 85.8%,outperforming six recent advanced classification models.W_CVNet can effectively help physicians with automated aid in diagnosis to determine if the disease is present and,in the case of COVID-19 patients,to further predict the area of the lesion.
文摘N-11-azaartemisinins potentially active against Plasmodium falciparum are designed by combining molecular electrostatic potential (MEP), ligand-receptor interaction, and models built with supervised machine learning methods (PCA, HCA, KNN, SIMCA, and SDA). The optimization of molecular structures was performed using the B3LYP/6-31G* approach. MEP maps and ligand-receptor interactions were used to investigate key structural features required for biological activities and likely interactions between N-11-azaartemisinins and heme, respectively. The supervised machine learning methods allowed the separation of the investigated compounds into two classes: cha and cla, with the properties ε<sub>LUMO+1</sub> (one level above lowest unoccupied molecular orbital energy), d(C<sub>6</sub>-C<sub>5</sub>) (distance between C<sub>6</sub> and C<sub>5</sub> atoms in ligands), and TSA (total surface area) responsible for the classification. The insights extracted from the investigation developed and the chemical intuition enabled the design of sixteen new N-11-azaartemisinins (prediction set), moreover, models built with supervised machine learning methods were applied to this prediction set. The result of this application showed twelve new promising N-11-azaartemisinins for synthesis and biological evaluation.
基金supported by National Natural Science Foundation of China(62276058,61902057,41774063)Fundamental Research Funds for the Central Universities(N2217003)Joint Fund of Science&Technology Department of Liaoning Province and State Key Laboratory of Robotics,China(2020-KF-12-11).
文摘A large variety of complaint reports reflect subjective information expressed by citizens.A key challenge of text summarization for complaint reports is to ensure the factual consistency of generated summary.Therefore,in this paper,a simple and weakly supervised framework considering factual consistency is proposed to generate a summary of city-based complaint reports without pre-labeled sentences/words.Furthermore,it considers the importance of entity in complaint reports to ensure factual consistency of summary.Experimental results on the customer review datasets(Yelp and Amazon)and complaint report dataset(complaint reports of Shenyang in China)show that the proposed framework outperforms state-of-the-art approaches in ROUGE scores and human evaluation.It unveils the effectiveness of our approach to helping in dealing with complaint reports.
文摘In recent years, the place occupied by the various manifestations of cyber-crime in companies has been considerable. Indeed, due to the rapid evolution of telecommunications technologies, companies, regardless of their size or sector of activity, are now the target of advanced persistent threats. The Work 2035 study also revealed that cyber crimes (such as critical infrastructure hacks) and massive data breaches are major sources of concern. Thus, it is important for organizations to guarantee a minimum level of security to avoid potential attacks that can cause paralysis of systems, loss of sensitive data, exposure to blackmail, damage to reputation or even a commercial harm. To do this, among other means, hardening is used, the main objective of which is to reduce the attack surface within a company. The execution of the hardening configurations as well as the verification of these are carried out on the servers and network equipment with the aim of reducing the number of openings present by keeping only those which are necessary for proper operation. However, nowadays, in many companies, these tasks are done manually. As a result, the execution and verification of hardening configurations are very often subject to potential errors but also highly consuming human and financial resources. The problem is that it is essential for operators to maintain an optimal level of security while minimizing costs, hence the interest in automating hardening processes and verifying the hardening of servers and network equipment. It is in this logic that we propose within the framework of this work the reinforcement of the security of the information systems (IS) by the automation of the mechanisms of hardening. In our work, we have, on the one hand, set up a hardening procedure in accordance with international security standards for servers, routers and switches and, on the other hand, designed and produced a functional application which makes it possible to: 1) Realise the configuration of the hardening;2) Verify them;3) Correct the non conformities;4) Write and send by mail a verification report for the configurations;5) And finally update the procedures of hardening. Our web application thus created allows in less than fifteen (15) minutes actions that previously took at least five (5) hours of time. This allows supervised network operators to save time and money, but also to improve their security standards in line with international standards.
文摘Nowadays, in data science, supervised learning algorithms are frequently used to perform text classification. However, African textual data, in general, have been studied very little using these methods. This article notes the particularity of the data and measures the level of precision of predictions of naive Bayes algorithms, decision tree, and SVM (Support Vector Machine) on a corpus of computer jobs taken on the internet. This is due to the data imbalance problem in machine learning. However, this problem essentially focuses on the distribution of the number of documents in each class or subclass. Here, we delve deeper into the problem to the word count distribution in a set of documents. The results are compared with those obtained on a set of French IT offers. It appears that the precision of the classification varies between 88% and 90% for French offers against 67%, at most, for Cameroonian offers. The contribution of this study is twofold. Indeed, it clearly shows that, in a similar job category, job offers on the internet in Cameroon are more unstructured compared to those available in France, for example. Moreover, it makes it possible to emit a strong hypothesis according to which sets of texts having a symmetrical distribution of the number of words obtain better results with supervised learning algorithms.
基金support by the National Natural Science Foundation of China(NSFC)under grant number 61873274.
文摘Contrastive self‐supervised representation learning on attributed graph networks with Graph Neural Networks has attracted considerable research interest recently.However,there are still two challenges.First,most of the real‐word system are multiple relations,where entities are linked by different types of relations,and each relation is a view of the graph network.Second,the rich multi‐scale information(structure‐level and feature‐level)of the graph network can be seen as self‐supervised signals,which are not fully exploited.A novel contrastive self‐supervised representation learning framework on attributed multiplex graph networks with multi‐scale(named CoLM^(2)S)information is presented in this study.It mainly contains two components:intra‐relation contrast learning and interrelation contrastive learning.Specifically,the contrastive self‐supervised representation learning framework on attributed single‐layer graph networks with multi‐scale information(CoLMS)framework with the graph convolutional network as encoder to capture the intra‐relation information with multi‐scale structure‐level and feature‐level selfsupervised signals is introduced first.The structure‐level information includes the edge structure and sub‐graph structure,and the feature‐level information represents the output of different graph convolutional layer.Second,according to the consensus assumption among inter‐relations,the CoLM^(2)S framework is proposed to jointly learn various graph relations in attributed multiplex graph network to achieve global consensus node embedding.The proposed method can fully distil the graph information.Extensive experiments on unsupervised node clustering and graph visualisation tasks demonstrate the effectiveness of our methods,and it outperforms existing competitive baselines.
文摘Rare labeled data are difficult to recognize by using conventional methods in the process of radar emitter recogni-tion.To solve this problem,an optimized cooperative semi-supervised learning radar emitter recognition method based on a small amount of labeled data is developed.First,a small amount of labeled data are randomly sampled by using the bootstrap method,loss functions for three common deep learning net-works are improved,the uniform distribution and cross-entropy function are combined to reduce the overconfidence of softmax classification.Subsequently,the dataset obtained after sam-pling is adopted to train three improved networks so as to build the initial model.In addition,the unlabeled data are preliminarily screened through dynamic time warping(DTW)and then input into the initial model trained previously for judgment.If the judg-ment results of two or more networks are consistent,the unla-beled data are labeled and put into the labeled data set.Lastly,the three network models are input into the labeled dataset for training,and the final model is built.As revealed by the simula-tion results,the semi-supervised learning method adopted in this paper is capable of exploiting a small amount of labeled data and basically achieving the accuracy of labeled data recognition.
文摘Sentence classification is the process of categorizing a sentence based on the context of the sentence.Sentence categorization requires more semantic highlights than other tasks,such as dependence parsing,which requires more syntactic elements.Most existing strategies focus on the general semantics of a conversation without involving the context of the sentence,recognizing the progress and comparing impacts.An ensemble pre-trained language model was taken up here to classify the conversation sentences from the conversation corpus.The conversational sentences are classified into four categories:information,question,directive,and commission.These classification label sequences are for analyzing the conversation progress and predicting the pecking order of the conversation.Ensemble of Bidirectional Encoder for Representation of Transformer(BERT),Robustly Optimized BERT pretraining Approach(RoBERTa),Generative Pre-Trained Transformer(GPT),DistilBERT and Generalized Autoregressive Pretraining for Language Understanding(XLNet)models are trained on conversation corpus with hyperparameters.Hyperparameter tuning approach is carried out for better performance on sentence classification.This Ensemble of Pre-trained Language Models with a Hyperparameter Tuning(EPLM-HT)system is trained on an annotated conversation dataset.The proposed approach outperformed compared to the base BERT,GPT,DistilBERT and XLNet transformer models.The proposed ensemble model with the fine-tuned parameters achieved an F1_score of 0.88.
基金Project was supported by the National Key R&D Program of China(Grant No.2017YFB1104404)
文摘In order to obtain a high-quality weld during the laser welding process, extracting the characteristic parameters of weld pool is an important issue for automated welding. In this paper, the type 304 austenitic stainless steel is welded by a 5 kW high-power fiber laser and a high-speed camera is employed to capture the topside images of weld pools. Then we propose a robust visual-detection approach for the molten pool based on the supervised descent method. It provides an elegant framework for representing the outline of a weld pool and is especially efficient for weld pool detection in the presence of strong uncertainties and disturbances. Finally, welding experimental results verified that the proposed approach can extract the weld pool boundary accurately, which will lay a solid foundation for controlling the weld quality of fiber laser welding process.
文摘The purpose of this study was to explore the effects of supervised movie appreciation on improving the life meaning sense among college students. The intervention combined by “pre-video, post counseling” was conducted on the experimental group, while the control group received no intervention. Results have shown that the scores on the subscales of will to meaning, life purpose, life control, suffer acceptance and on the total scale have improved significantly. No gender difference was found on the intervention effect, and participants receiving intervention maintained higher level on related subscales a week later, indicating that supervised movie appreciation is an effective way to improve the life meaning sense among college students.
文摘AIM To evaluate the effect of a 12-mo supervised aerobic and resistance training, on renal function and exercise capacity compared to usual care recommendations.METHODS Ninety-nine kidney transplant recipients(KTRs) were assigned to interventional exercise(Group A; n = 52) and a usual care cohort(Group B; n = 47). Blood and urine chemistry, exercise capacity, muscular strength, anthropometric measures and health-related quality of life(HRQo L) were assessed at baseline, and after 6 and 12 mo. Group A underwent a supervised training three times per week for 12 mo. Group B received only general recommendations about home-based physical activities.RESULTS Eighty-five KTRs completed the study(Group A, n = 44; Group B, n = 41). After 12 mo, renal function remained stable in both groups. Group A significantly increased maximum workload(+13 W, P = 0.0003), V'O2 peak(+3.1 mL/kg per minute, P = 0.0099), muscular strength in plantar flexor(+12 kg, P = 0.0368), height in the countermovement jump(+1.9 cm, P = 0.0293) and decreased in Body Mass Index(-0.5 kg/m^2, P = 0.0013). HRQo L significantly improved in physical function(P = 0.0019), physical-role limitations(P = 0.0321) and social functioning scales(P = 0.0346). Noimprovements were found in Group B.CONCLUSION Twelve-month of supervised aerobic and resistance training improves the physiological variables related to physical fitness and cardiovascular risks without consequences on renal function. Recommendations alone are not sufficient to induce changes in exercise capacity of KTRs. Our study is an example of collaborative working between transplant centres, sports medicine and exercise facilities.