6G is desired to support more intelligence networks and this trend attaches importance to the self-healing capability if degradation emerges in the cellular networks.As a primary component of selfhealing networks,faul...6G is desired to support more intelligence networks and this trend attaches importance to the self-healing capability if degradation emerges in the cellular networks.As a primary component of selfhealing networks,fault detection is investigated in this paper.Considering the fast response and low timeand-computational consumption,it is the first time that the Online Broad Learning System(OBLS)is applied to identify outages in cellular networks.In addition,the Automatic-constructed Online Broad Learning System(AOBLS)is put forward to rationalize its structure and consequently avoid over-fitting and under-fitting.Furthermore,a multi-layer classification structure is proposed to further improve the classification performance.To face the challenges caused by imbalanced data in fault detection problems,a novel weighting strategy is derived to achieve the Multilayer Automatic-constructed Weighted Online Broad Learning System(MAWOBLS)and ensemble learning with retrained Support Vector Machine(SVM),denoted as EMAWOBLS,for superior treatment with this imbalance issue.Simulation results show that the proposed algorithm has excellent performance in detecting faults with satisfactory time usage.展开更多
Multi-label classification is a challenging problem that has attracted significant attention from researchers, particularly in the domain of image and text attribute annotation. However, multi-label datasets are prone...Multi-label classification is a challenging problem that has attracted significant attention from researchers, particularly in the domain of image and text attribute annotation. However, multi-label datasets are prone to serious intra-class and inter-class imbalance problems, which can significantly degrade the classification performance. To address the above issues, we propose the multi-label weighted broad learning system(MLW-BLS) from the perspective of label imbalance weighting and label correlation mining. Further, we propose the multi-label adaptive weighted broad learning system(MLAW-BLS) to adaptively adjust the specific weights and values of labels of MLW-BLS and construct an efficient imbalanced classifier set. Extensive experiments are conducted on various datasets to evaluate the effectiveness of the proposed model, and the results demonstrate its superiority over other advanced approaches.展开更多
With the exponential rise in global air traffic,ensuring swift passenger processing while countering potential security threats has become a paramount concern for aviation security.Although X-ray baggage monitoring is...With the exponential rise in global air traffic,ensuring swift passenger processing while countering potential security threats has become a paramount concern for aviation security.Although X-ray baggage monitoring is now standard,manual screening has several limitations,including the propensity for errors,and raises concerns about passenger privacy.To address these drawbacks,researchers have leveraged recent advances in deep learning to design threatsegmentation frameworks.However,these models require extensive training data and labour-intensive dense pixelwise annotations and are finetuned separately for each dataset to account for inter-dataset discrepancies.Hence,this study proposes a semi-supervised contour-driven broad learning system(BLS)for X-ray baggage security threat instance segmentation referred to as C-BLX.The research methodology involved enhancing representation learning and achieving faster training capability to tackle severe occlusion and class imbalance using a single training routine with limited baggage scans.The proposed framework was trained with minimal supervision using resource-efficient image-level labels to localize illegal items in multi-vendor baggage scans.More specifically,the framework generated candidate region segments from the input X-ray scans based on local intensity transition cues,effectively identifying concealed prohibited items without entire baggage scans.The multi-convolutional BLS exploits the rich complementary features extracted from these region segments to predict object categories,including threat and benign classes.The contours corresponding to the region segments predicted as threats were then utilized to yield the segmentation results.The proposed C-BLX system was thoroughly evaluated on three highly imbalanced public datasets and surpassed other competitive approaches in baggage-threat segmentation,yielding 90.04%,78.92%,and 59.44%in terms of mIoU on GDXray,SIXray,and Compass-XP,respectively.Furthermore,the limitations of the proposed system in extracting precise region segments in intricate noisy settings and potential strategies for overcoming them through post-processing techniques were explored(source code will be available at https://github.com/Divs1159/CNN_BLS.)展开更多
As one important type of post-translational modifications(PTMs),protein lysine succinylation regulates many important biological processes.It is also closely involved with some major diseases in the aspects of Cardiom...As one important type of post-translational modifications(PTMs),protein lysine succinylation regulates many important biological processes.It is also closely involved with some major diseases in the aspects of Cardiometabolic,liver metabolic,nervous system and so on.Therefore,it is imperative to predict the succinylation sites in proteins for both basic research and drug development.In this paper,a novel predictor called i Succ Lys-BLS was proposed by not only introducing a new machine learning algorithm—Broad Learning System,but also optimizing the imbalanced data by randomly labeling samples.Rigorous cross-validation and independent test indicate that the success rate of i Succ Lys-BLS for positive samples is overwhelmingly higher than its counterparts.展开更多
Target tracking has a wide range of applications in intelligent transportation,real‐time monitoring,human‐computer interaction and other aspects.However,in the tracking process,the target is prone to deformation,occ...Target tracking has a wide range of applications in intelligent transportation,real‐time monitoring,human‐computer interaction and other aspects.However,in the tracking process,the target is prone to deformation,occlusion,loss,scale variation,background clutter,illumination variation,etc.,which bring great challenges to realize accurate and real‐time tracking.Tracking based on Siamese networks promotes the application of deep learning in the field of target tracking,ensuring both accuracy and real‐time performance.However,due to its offline training,it is difficult to deal with the fast motion,serious occlusion,loss and deformation of the target during tracking.Therefore,it is very helpful to improve the performance of the Siamese networks by learning new features of the target quickly and updating the target position in time online.The broad learning system(BLS)has a simple network structure,high learning efficiency,and strong feature learning ability.Aiming at the problems of Siamese networks and the characteristics of BLS,a target tracking method based on BLS is proposed.The method combines offline training with fast online learning of new features,which not only adopts the powerful feature representation ability of deep learning,but also skillfully uses the BLS for re‐learning and re‐detection.The broad re‐learning information is used for re‐detection when the target tracking appears serious occlusion and so on,so as to change the selection of the Siamese networks search area,solve the problem that the search range cannot meet the fast motion of the target,and improve the adaptability.Experimental results show that the proposed method achieves good results on three challenging datasets and improves the performance of the basic algorithm in difficult scenarios.展开更多
In this paper, the containment control problem in nonlinear multi-agent systems(NMASs) under denial-of-service(DoS) attacks is addressed. Firstly, a prediction model is obtained using the broad learning technique to t...In this paper, the containment control problem in nonlinear multi-agent systems(NMASs) under denial-of-service(DoS) attacks is addressed. Firstly, a prediction model is obtained using the broad learning technique to train historical data generated by the system offline without DoS attacks. Secondly, the dynamic linearization method is used to obtain the equivalent linearization model of NMASs. Then, a novel model-free adaptive predictive control(MFAPC) framework based on historical and online data generated by the system is proposed, which combines the trained prediction model with the model-free adaptive control method. The development of the MFAPC method motivates a much simpler robust predictive control solution that is convenient to use in the case of DoS attacks. Meanwhile, the MFAPC algorithm provides a unified predictive framework for solving consensus tracking and containment control problems. The boundedness of the containment error can be proven by using the contraction mapping principle and the mathematical induction method. Finally, the proposed MFAPC is assessed through comparative experiments.展开更多
Broad learning system(BLS)is an emerging neural network characterized by its rapid processing and robust generalization capabilities.However,determining the appropriate structure for broad learning system is also a ch...Broad learning system(BLS)is an emerging neural network characterized by its rapid processing and robust generalization capabilities.However,determining the appropriate structure for broad learning system is also a challenge.In addition,broad learning system may perform overfitting due to the dependence between nodes in processing fully connected network.To deal with these problems,an efficient ensemble broad learning system based on Dropout and Dropconnect is proposed in this paper.The proposed Dropout ensemble broad learning system randomly discards hidden nodes to improve diversity between individuals and reduce the synergy between nodes to improve prediction stability.The Dropconnect ensemble broad learning system randomly drops connection weights to generate more complementary models by adding input attribute disturbance.The experimental results on the UCI datasets confirm that the method proposed in this paper can solve the problem of model overfitting caused by the strong dependence between the nodes of ensemble broad learning system.The proposed algorithm outperforms the original BLS in terms of prediction stability and classification accuracy.展开更多
The popularity of the Internet of Things(IoT)has enabled a large number of vulnerable devices to connect to the Internet,bringing huge security risks.As a network-level security authentication method,device fingerprin...The popularity of the Internet of Things(IoT)has enabled a large number of vulnerable devices to connect to the Internet,bringing huge security risks.As a network-level security authentication method,device fingerprint based on machine learning has attracted considerable attention because it can detect vulnerable devices in complex and heterogeneous access phases.However,flexible and diversified IoT devices with limited resources increase dif-ficulty of the device fingerprint authentication method executed in IoT,because it needs to retrain the model network to deal with incremental features or types.To address this problem,a device fingerprinting mechanism based on a Broad Learning System(BLS)is proposed in this paper.The mechanism firstly characterizes IoT devices by traffic analysis based on the identifiable differences of the traffic data of IoT devices,and extracts feature parameters of the traffic packets.A hierarchical hybrid sampling method is designed at the preprocessing phase to improve the imbalanced data distribution and reconstruct the fingerprint dataset.The complexity of the dataset is reduced using Principal Component Analysis(PCA)and the device type is identified by training weights using BLS.The experimental results show that the proposed method can achieve state-of-the-art accuracy and spend less training time than other existing methods.展开更多
Based on Broad Learning System with preprocessing,the impenetrable obstacles were reconstructed.Firstly,the far-field data were preprocessed by Random Forest,and the shapes of the obstacles were classified by dividing...Based on Broad Learning System with preprocessing,the impenetrable obstacles were reconstructed.Firstly,the far-field data were preprocessed by Random Forest,and the shapes of the obstacles were classified by dividing the far-field data into different categories.Secondly,the broad learning system was employed for reconstructing the unknown scatterer.The far-field data of the scatterer were regarded as the input nodes of mapped features in the network,and all the mapped features were connected with the enhancement nodes of random weights to the output layer.Subsequently,the coefficient of the output can be obtained by the pseudoinverse.This method for the recovery of the scattering obstacles is named RF-BLS.Finally,numerical experiments revealed that the proposed method is effective,and that the training speed was significantly improved,compared with the deep learning method.展开更多
High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency...High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.展开更多
The development of communication technologies which support traffic-intensive applications presents new challenges in designing a real-time traffic analysis architecture and an accurate method that suitable for a wide...The development of communication technologies which support traffic-intensive applications presents new challenges in designing a real-time traffic analysis architecture and an accurate method that suitable for a wide variety of traffic types.Current traffic analysis methods are executed on the cloud,which needs to upload the traffic data.Fog computing is a more promising way to save bandwidth resources by offloading these tasks to the fog nodes.However,traffic analysis models based on traditional machine learning need to retrain all traffic data when updating the trained model,which are not suitable for fog computing due to the poor computing power.In this study,we design a novel fog computing based traffic analysis system using broad learning.For one thing,fog computing can provide a distributed architecture for saving the bandwidth resources.For another,we use the broad learning to incrementally train the traffic data,which is more suitable for fog computing because it can support incremental updates of models without retraining all data.We implement our system on the Raspberry Pi,and experimental results show that we have a 98%probability to accurately identify these traffic data.Moreover,our method has a faster training speed compared with Convolutional Neural Network(CNN).展开更多
Data sharing in Internet of Vehicles(IoV)makes it possible to provide personalized services for users by service providers in Intelligent Transportation Systems(ITS).As IoV is a multi-user mobile scenario,the reliabil...Data sharing in Internet of Vehicles(IoV)makes it possible to provide personalized services for users by service providers in Intelligent Transportation Systems(ITS).As IoV is a multi-user mobile scenario,the reliability and efficiency of data sharing need to be further enhanced.Federated learning allows the server to exchange parameters without obtaining private data from clients so that the privacy is protected.Broad learning system is a novel artificial intelligence technology that can improve training efficiency of data set.Thus,we propose a federated bidirectional connection broad learning scheme(FeBBLS)to solve the data sharing issues.Firstly,we adopt the bidirectional connection broad learning system(BiBLS)model to train data set in vehicular nodes.The server aggregates the collected parameters of BiBLS from vehicular nodes through the federated broad learning system(FedBLS)algorithm.Moreover,we propose a clustering FedBLS algorithm to offload the data sharing into clusters for improving the aggregation capability of the model.Some simulation results show our scheme can improve the efficiency and prediction accuracy of data sharing and protect the privacy of data sharing.展开更多
The proliferation of Internet of Things(IoT)rapidly increases the possiblities of Simple Service Discovery Protocol(SSDP)reflection attacks.Most DDoS attack defence strategies deploy only to a certain type of devices ...The proliferation of Internet of Things(IoT)rapidly increases the possiblities of Simple Service Discovery Protocol(SSDP)reflection attacks.Most DDoS attack defence strategies deploy only to a certain type of devices in the attack chain,and need to detect attacks in advance,and the detection of DDoS attacks often uses heavy algorithms consuming lots of computing resources.This paper proposes a comprehensive DDoS attack defence approach which combines broad learning and a set of defence strategies against SSDP attacks,called Broad Learning based Comprehensive Defence(BLCD).The defence strategies work along the attack chain,starting from attack sources to victims.It defends against attacks without detecting attacks or identifying the roles of IoT devices in SSDP reflection attacks.BLCD also detects suspicious traffic at bots,service providers and victims by using broad learning,and the detection results are used as the basis for automatically deploying defence strategies which can significantly reduce DDoS packets.For evaluations,we thoroughly analyze attack traffic when deploying BLCD to different defence locations.Experiments show that BLCD can reduce the number of packets received at the victim to 39 without affecting the standard SSDP service,and detect malicious packets with an accuracy of 99.99%.展开更多
With the rapid development in the field of artificial intelligence and natural language processing(NLP),research on music retrieval has gained importance.Music messages express emotional signals.The emotional classifi...With the rapid development in the field of artificial intelligence and natural language processing(NLP),research on music retrieval has gained importance.Music messages express emotional signals.The emotional classification of music can help in conveniently organizing and retrieving music.It is also the premise of using music for psychological intervention and physiological adjustment.A new chord-to-vector method was proposed,which converted the chord information of music into a chord vector of music and combined the weight of the Mel-frequency cepstral coefficient(MFCC) and residual phase(RP) with the feature fusion of a cochleogram.The music emotion recognition and classification training was carried out using the fusion of a convolution neural network and bidirectional long short-term memory(BiLSTM).In addition,based on the self-collected dataset,a comparison of the proposed model with other model structures was performed.The results show that the proposed method achieved a higher recognition accuracy compared with other models.展开更多
Data-driven surrogate models that assist with efficient evolutionary algorithms to find the optimal development scheme have been widely used to solve reservoir production optimization problems.However,existing researc...Data-driven surrogate models that assist with efficient evolutionary algorithms to find the optimal development scheme have been widely used to solve reservoir production optimization problems.However,existing research suggests that the effectiveness of a surrogate model can vary depending on the complexity of the design problem.A surrogate model that has demonstrated success in one scenario may not perform as well in others.In the absence of prior knowledge,finding a promising surrogate model that performs well for an unknown reservoir is challenging.Moreover,the optimization process often relies on a single evolutionary algorithm,which can yield varying results across different cases.To address these limitations,this paper introduces a novel approach called the multi-surrogate framework with an adaptive selection mechanism(MSFASM)to tackle production optimization problems.MSFASM consists of two stages.In the first stage,a reduced-dimensional broad learning system(BLS)is used to adaptively select the evolutionary algorithm with the best performance during the current optimization period.In the second stage,the multi-objective algorithm,non-dominated sorting genetic algorithm II(NSGA-II),is used as an optimizer to find a set of Pareto solutions with good performance on multiple surrogate models.A novel optimal point criterion is utilized in this stage to select the Pareto solutions,thereby obtaining the desired development schemes without increasing the computational load of the numerical simulator.The two stages are combined using sequential transfer learning.From the two most important perspectives of an evolutionary algorithm and a surrogate model,the proposed method improves adaptability to optimization problems of various reservoir types.To verify the effectiveness of the proposed method,four 100-dimensional benchmark functions and two reservoir models are tested,and the results are compared with those obtained by six other surrogate-model-based methods.The results demonstrate that our approach can obtain the maximum net present value(NPV)of the target production optimization problems.展开更多
Emotion classification in textual conversations focuses on classifying the emotion of each utterance from textual conversations.It is becoming one of the most important tasks for natural language processing in recent ...Emotion classification in textual conversations focuses on classifying the emotion of each utterance from textual conversations.It is becoming one of the most important tasks for natural language processing in recent years.However,it is a challenging task for machines to conduct emotion classification in textual conversations because emotions rely heavily on textual context.To address the challenge,we propose a method to classify emotion in textual conversations,by integrating the advantages of deep learning and broad learning,namely DBL.It aims to provide a more effective solution to capture local contextual information(i.e.,utterance-level)in an utterance,as well as global contextual information(i.e.,speaker-level)in a conversation,based on Convolutional Neural Network(CNN),Bidirectional Long Short-Term Memory(Bi-LSTM),and broad learning.Extensive experiments have been conducted on three public textual conversation datasets,which show that the context in both utterance-level and speaker-level is consistently beneficial to the performance of emotion classification.In addition,the results show that our proposed method outperforms the baseline methods on most of the testing datasets in weighted-average F1.展开更多
This paper develops a fully data-driven,missingdata tolerant method for post-fault short-term voltage stability(STVS)assessment of power systems against the incomplete PMU measurements.The super-resolution perception(...This paper develops a fully data-driven,missingdata tolerant method for post-fault short-term voltage stability(STVS)assessment of power systems against the incomplete PMU measurements.The super-resolution perception(SRP),based on a deep residual learning convolutional neural network,is employed to cope with the missing PMU measurements.The incremental broad learning(BL)is used to rapidly update the model to maintain and enhance the online application performance.Being different from the state-of-the-art methods,the proposed method is fully data-driven and can fill up missing data under any PMU placement information loss and network topology change scenario.Simulation results demonstrate that the proposed method has the best performance in terms of STVS assessment accuracy and missing-data tolerance among the existing methods on the benchmark testing system.展开更多
Cross-domain emotion classification aims to leverage useful information in a source domain to help predict emotion polarity in a target domain in a unsupervised or semi-supervised manner.Due to the domain discrepancy,...Cross-domain emotion classification aims to leverage useful information in a source domain to help predict emotion polarity in a target domain in a unsupervised or semi-supervised manner.Due to the domain discrepancy,an emotion classifier trained on source domain may not work well on target domain.Many researchers have focused on traditional cross-domain sentiment classification,which is coarse-grained emotion classification.However,the problem of emotion classification for cross-domain is rarely involved.In this paper,we propose a method,called convolutional neural network(CNN)based broad learning,for cross-domain emotion classification by combining the strength of CNN and broad learning.We first utilized CNN to extract domain-invariant and domain-specific features simultaneously,so as to train two more efficient classifiers by employing broad learning.Then,to take advantage of these two classifiers,we designed a co-training model to boost together for them.Finally,we conducted comparative experiments on four datasets for verifying the effectiveness of our proposed method.The experimental results show that the proposed method can improve the performance of emotion classification more effectively than those baseline methods.展开更多
Deep learning has led to tremendous success in machine maintenance and fault diagnosis.However,this success is predicated on the correctly annotated datasets.Labels in large industrial datasets can be noisy and thus d...Deep learning has led to tremendous success in machine maintenance and fault diagnosis.However,this success is predicated on the correctly annotated datasets.Labels in large industrial datasets can be noisy and thus degrade the performance of fault diagnosis models.The emerging concept of broad learning shows the potential to address the label noise problem.Compared with existing deep learning algorithms,broad learning has a simple architecture and high training efficiency.An active label denoising algorithm based on broad learning(ALDBL)is proposed.First,ALDBL captures the embedded representation from the time-frequency features by a recurrent memory cell.Second,it augments wide features with a sparse autoencoder and projects the sparse features into an orthogonal space.A proposed corrector then iteratively changes the weights of source examples during the training and corrects the labels by using a label adaptation matrix.Finally,ALDBL finetunes the model parameters with actively sampled target data with reliable pseudo labels.The performance of ALDBL is validated with three benchmark datasets,including 30 label denoising tasks.Computational results demonstrate the effectiveness and advantages of the proposed algorithm over the other label denoising algorithms.展开更多
Negative emotion classification refers to the automatic classification of negative emotion of texts in social networks.Most existing methods are based on deep learning models,facing challenges such as complex structur...Negative emotion classification refers to the automatic classification of negative emotion of texts in social networks.Most existing methods are based on deep learning models,facing challenges such as complex structures and too many hyperparameters.To meet these challenges,in this paper,we propose a method for negative emotion classification utilizing a Robustly Optimized BERT Pretraining Approach(RoBERTa)and p-norm Broad Learning(p-BL).Specifically,there are mainly three contributions in this paper.Firstly,we fine-tune the RoBERTa to adapt it to the task of negative emotion classification.Then,we employ the fine-tuned RoBERTa to extract features of original texts and generate sentence vectors.Secondly,we adopt p-BL to construct a classifier and then predict negative emotions of texts using the classifier.Compared with deep learning models,p-BL has advantages such as a simple structure that is only 3-layer and fewer parameters to be trained.Moreover,it can suppress the adverse effects of more outliers and noise in data by flexibly changing the value of p.Thirdly,we conduct extensive experiments on the public datasets,and the experimental results show that our proposed method outperforms the baseline methods on the tested datasets.展开更多
基金supported in part by the National Key Research and Development Project under Grant 2020YFB1806805partially funded through a grant from Qualcomm。
文摘6G is desired to support more intelligence networks and this trend attaches importance to the self-healing capability if degradation emerges in the cellular networks.As a primary component of selfhealing networks,fault detection is investigated in this paper.Considering the fast response and low timeand-computational consumption,it is the first time that the Online Broad Learning System(OBLS)is applied to identify outages in cellular networks.In addition,the Automatic-constructed Online Broad Learning System(AOBLS)is put forward to rationalize its structure and consequently avoid over-fitting and under-fitting.Furthermore,a multi-layer classification structure is proposed to further improve the classification performance.To face the challenges caused by imbalanced data in fault detection problems,a novel weighting strategy is derived to achieve the Multilayer Automatic-constructed Weighted Online Broad Learning System(MAWOBLS)and ensemble learning with retrained Support Vector Machine(SVM),denoted as EMAWOBLS,for superior treatment with this imbalance issue.Simulation results show that the proposed algorithm has excellent performance in detecting faults with satisfactory time usage.
基金supported in part by the National Key R&D Program of China (2023YFA1011601)the Major Key Project of PCL, China (PCL2023AS7-1)+3 种基金in part by the National Natural Science Foundation of China (U21A20478, 62106224, 92267203)in part by the Science and Technology Major Project of Guangzhou (202007030006)in part by the Major Key Project of PCL (PCL2021A09)in part by the Guangzhou Science and Technology Plan Project (2024A04J3749)。
文摘Multi-label classification is a challenging problem that has attracted significant attention from researchers, particularly in the domain of image and text attribute annotation. However, multi-label datasets are prone to serious intra-class and inter-class imbalance problems, which can significantly degrade the classification performance. To address the above issues, we propose the multi-label weighted broad learning system(MLW-BLS) from the perspective of label imbalance weighting and label correlation mining. Further, we propose the multi-label adaptive weighted broad learning system(MLAW-BLS) to adaptively adjust the specific weights and values of labels of MLW-BLS and construct an efficient imbalanced classifier set. Extensive experiments are conducted on various datasets to evaluate the effectiveness of the proposed model, and the results demonstrate its superiority over other advanced approaches.
基金supported by research funds from Khalifa University,No.CIRA-2021-052the Advanced Technology Research Center Program(ASPIRE),No.AARE20-279.
文摘With the exponential rise in global air traffic,ensuring swift passenger processing while countering potential security threats has become a paramount concern for aviation security.Although X-ray baggage monitoring is now standard,manual screening has several limitations,including the propensity for errors,and raises concerns about passenger privacy.To address these drawbacks,researchers have leveraged recent advances in deep learning to design threatsegmentation frameworks.However,these models require extensive training data and labour-intensive dense pixelwise annotations and are finetuned separately for each dataset to account for inter-dataset discrepancies.Hence,this study proposes a semi-supervised contour-driven broad learning system(BLS)for X-ray baggage security threat instance segmentation referred to as C-BLX.The research methodology involved enhancing representation learning and achieving faster training capability to tackle severe occlusion and class imbalance using a single training routine with limited baggage scans.The proposed framework was trained with minimal supervision using resource-efficient image-level labels to localize illegal items in multi-vendor baggage scans.More specifically,the framework generated candidate region segments from the input X-ray scans based on local intensity transition cues,effectively identifying concealed prohibited items without entire baggage scans.The multi-convolutional BLS exploits the rich complementary features extracted from these region segments to predict object categories,including threat and benign classes.The contours corresponding to the region segments predicted as threats were then utilized to yield the segmentation results.The proposed C-BLX system was thoroughly evaluated on three highly imbalanced public datasets and surpassed other competitive approaches in baggage-threat segmentation,yielding 90.04%,78.92%,and 59.44%in terms of mIoU on GDXray,SIXray,and Compass-XP,respectively.Furthermore,the limitations of the proposed system in extracting precise region segments in intricate noisy settings and potential strategies for overcoming them through post-processing techniques were explored(source code will be available at https://github.com/Divs1159/CNN_BLS.)
基金the National Natural Science Foundation of China(61761023,31760315)the Natural Science Foundation of Jiangxi Province,China(20202BABL202004,20202BAB202007)the Scientific Research Plan of the Department of Education of Jiangxi Province(GJJ190695)。
文摘As one important type of post-translational modifications(PTMs),protein lysine succinylation regulates many important biological processes.It is also closely involved with some major diseases in the aspects of Cardiometabolic,liver metabolic,nervous system and so on.Therefore,it is imperative to predict the succinylation sites in proteins for both basic research and drug development.In this paper,a novel predictor called i Succ Lys-BLS was proposed by not only introducing a new machine learning algorithm—Broad Learning System,but also optimizing the imbalanced data by randomly labeling samples.Rigorous cross-validation and independent test indicate that the success rate of i Succ Lys-BLS for positive samples is overwhelmingly higher than its counterparts.
基金supported in part by the National Natural Science Foundation of China(under Grant Nos.51939001,61976033,U1813203,61803064,and 61751202)Natural Foundation Guidance Plan Project of Liaoning(2019‐ZD‐0151)+2 种基金Science&Technology Innovation Funds of Dalian(under Grant No.2018J11CY022)Fundamental Research Funds for the Central Universities(under Grant No.3132019345)Dalian High‐level Talents Innovation Support Program(Young Sci-ence and Technology Star Project)(under Grant No.2021RQ067).
文摘Target tracking has a wide range of applications in intelligent transportation,real‐time monitoring,human‐computer interaction and other aspects.However,in the tracking process,the target is prone to deformation,occlusion,loss,scale variation,background clutter,illumination variation,etc.,which bring great challenges to realize accurate and real‐time tracking.Tracking based on Siamese networks promotes the application of deep learning in the field of target tracking,ensuring both accuracy and real‐time performance.However,due to its offline training,it is difficult to deal with the fast motion,serious occlusion,loss and deformation of the target during tracking.Therefore,it is very helpful to improve the performance of the Siamese networks by learning new features of the target quickly and updating the target position in time online.The broad learning system(BLS)has a simple network structure,high learning efficiency,and strong feature learning ability.Aiming at the problems of Siamese networks and the characteristics of BLS,a target tracking method based on BLS is proposed.The method combines offline training with fast online learning of new features,which not only adopts the powerful feature representation ability of deep learning,but also skillfully uses the BLS for re‐learning and re‐detection.The broad re‐learning information is used for re‐detection when the target tracking appears serious occlusion and so on,so as to change the selection of the Siamese networks search area,solve the problem that the search range cannot meet the fast motion of the target,and improve the adaptability.Experimental results show that the proposed method achieves good results on three challenging datasets and improves the performance of the basic algorithm in difficult scenarios.
基金supported in part by the National Natural Science Foundation of China(62403396,62433018,62373113)the Guangdong Basic and Applied Basic Research Foundation(2023A1515011527,2023B1515120010)the Postdoctoral Fellowship Program of CPSF(GZB20240621)
文摘In this paper, the containment control problem in nonlinear multi-agent systems(NMASs) under denial-of-service(DoS) attacks is addressed. Firstly, a prediction model is obtained using the broad learning technique to train historical data generated by the system offline without DoS attacks. Secondly, the dynamic linearization method is used to obtain the equivalent linearization model of NMASs. Then, a novel model-free adaptive predictive control(MFAPC) framework based on historical and online data generated by the system is proposed, which combines the trained prediction model with the model-free adaptive control method. The development of the MFAPC method motivates a much simpler robust predictive control solution that is convenient to use in the case of DoS attacks. Meanwhile, the MFAPC algorithm provides a unified predictive framework for solving consensus tracking and containment control problems. The boundedness of the containment error can be proven by using the contraction mapping principle and the mathematical induction method. Finally, the proposed MFAPC is assessed through comparative experiments.
基金supported by the National Natural Science Foundation of China(Nos.61973304,61873049,and 62073060)the Open Foundation of State Key Laboratory of Intelligent Optimized Manufacturing in Mining&Metallurgy Process(No.BGRIMM-KZSKL-2023-5)+1 种基金the Selection and Training Project of High Level Talents in the Sixteenth/Six Talent Peak of Jiangsu Province(No.DZXX-045)the“Double First-Class”Construction to Enhance Independent Innovation Capability Project(No.2022ZZCX01K01).
文摘Broad learning system(BLS)is an emerging neural network characterized by its rapid processing and robust generalization capabilities.However,determining the appropriate structure for broad learning system is also a challenge.In addition,broad learning system may perform overfitting due to the dependence between nodes in processing fully connected network.To deal with these problems,an efficient ensemble broad learning system based on Dropout and Dropconnect is proposed in this paper.The proposed Dropout ensemble broad learning system randomly discards hidden nodes to improve diversity between individuals and reduce the synergy between nodes to improve prediction stability.The Dropconnect ensemble broad learning system randomly drops connection weights to generate more complementary models by adding input attribute disturbance.The experimental results on the UCI datasets confirm that the method proposed in this paper can solve the problem of model overfitting caused by the strong dependence between the nodes of ensemble broad learning system.The proposed algorithm outperforms the original BLS in terms of prediction stability and classification accuracy.
基金supported by National Key R&D Program of China(2019YFB2102303)National Natural Science Foundation of China(NSFC61971014,NSFC11675199)Young Backbone Teacher Training Program of Henan Colleges and Universities(2021GGJS170).
文摘The popularity of the Internet of Things(IoT)has enabled a large number of vulnerable devices to connect to the Internet,bringing huge security risks.As a network-level security authentication method,device fingerprint based on machine learning has attracted considerable attention because it can detect vulnerable devices in complex and heterogeneous access phases.However,flexible and diversified IoT devices with limited resources increase dif-ficulty of the device fingerprint authentication method executed in IoT,because it needs to retrain the model network to deal with incremental features or types.To address this problem,a device fingerprinting mechanism based on a Broad Learning System(BLS)is proposed in this paper.The mechanism firstly characterizes IoT devices by traffic analysis based on the identifiable differences of the traffic data of IoT devices,and extracts feature parameters of the traffic packets.A hierarchical hybrid sampling method is designed at the preprocessing phase to improve the imbalanced data distribution and reconstruct the fingerprint dataset.The complexity of the dataset is reduced using Principal Component Analysis(PCA)and the device type is identified by training weights using BLS.The experimental results show that the proposed method can achieve state-of-the-art accuracy and spend less training time than other existing methods.
基金This research of W.Yin has been supported by Science and Technology Research Project of Jilin Provincial Department of Education grant(No.JJKH20210797KJ).
文摘Based on Broad Learning System with preprocessing,the impenetrable obstacles were reconstructed.Firstly,the far-field data were preprocessed by Random Forest,and the shapes of the obstacles were classified by dividing the far-field data into different categories.Secondly,the broad learning system was employed for reconstructing the unknown scatterer.The far-field data of the scatterer were regarded as the input nodes of mapped features in the network,and all the mapped features were connected with the enhancement nodes of random weights to the output layer.Subsequently,the coefficient of the output can be obtained by the pseudoinverse.This method for the recovery of the scattering obstacles is named RF-BLS.Finally,numerical experiments revealed that the proposed method is effective,and that the training speed was significantly improved,compared with the deep learning method.
基金supported in part by the National Natural Science Foundation of China(62371116 and 62231020)in part by the Science and Technology Project of Hebei Province Education Department(ZD2022164)+2 种基金in part by the Fundamental Research Funds for the Central Universities(N2223031)in part by the Open Research Project of Xidian University(ISN24-08)Key Laboratory of Cognitive Radio and Information Processing,Ministry of Education(Guilin University of Electronic Technology,China,CRKL210203)。
文摘High-efficiency and low-cost knowledge sharing can improve the decision-making ability of autonomous vehicles by mining knowledge from the Internet of Vehicles(IoVs).However,it is challenging to ensure high efficiency of local data learning models while preventing privacy leakage in a high mobility environment.In order to protect data privacy and improve data learning efficiency in knowledge sharing,we propose an asynchronous federated broad learning(FBL)framework that integrates broad learning(BL)into federated learning(FL).In FBL,we design a broad fully connected model(BFCM)as a local model for training client data.To enhance the wireless channel quality for knowledge sharing and reduce the communication and computation cost of participating clients,we construct a joint resource allocation and reconfigurable intelligent surface(RIS)configuration optimization framework for FBL.The problem is decoupled into two convex subproblems.Aiming to improve the resource scheduling efficiency in FBL,a double Davidon–Fletcher–Powell(DDFP)algorithm is presented to solve the time slot allocation and RIS configuration problem.Based on the results of resource scheduling,we design a reward-allocation algorithm based on federated incentive learning(FIL)in FBL to compensate clients for their costs.The simulation results show that the proposed FBL framework achieves better performance than the comparison models in terms of efficiency,accuracy,and cost for knowledge sharing in the IoV.
基金supported by JSPS KAKENHI Grant Number JP16K00117, JP19K20250KDDI Foundationthe China Scholarship Council (201808050016)
文摘The development of communication technologies which support traffic-intensive applications presents new challenges in designing a real-time traffic analysis architecture and an accurate method that suitable for a wide variety of traffic types.Current traffic analysis methods are executed on the cloud,which needs to upload the traffic data.Fog computing is a more promising way to save bandwidth resources by offloading these tasks to the fog nodes.However,traffic analysis models based on traditional machine learning need to retrain all traffic data when updating the trained model,which are not suitable for fog computing due to the poor computing power.In this study,we design a novel fog computing based traffic analysis system using broad learning.For one thing,fog computing can provide a distributed architecture for saving the bandwidth resources.For another,we use the broad learning to incrementally train the traffic data,which is more suitable for fog computing because it can support incremental updates of models without retraining all data.We implement our system on the Raspberry Pi,and experimental results show that we have a 98%probability to accurately identify these traffic data.Moreover,our method has a faster training speed compared with Convolutional Neural Network(CNN).
基金supported by the National Natural Science Foundation of China under Grant No.61901099, 61972076, 61973069 and 62061006the Natural Science Foundation of Hebei Province under Grant No.F2020501037the Natural Science Foundation of Guangxi under Grant No.2018JJA170167
文摘Data sharing in Internet of Vehicles(IoV)makes it possible to provide personalized services for users by service providers in Intelligent Transportation Systems(ITS).As IoV is a multi-user mobile scenario,the reliability and efficiency of data sharing need to be further enhanced.Federated learning allows the server to exchange parameters without obtaining private data from clients so that the privacy is protected.Broad learning system is a novel artificial intelligence technology that can improve training efficiency of data set.Thus,we propose a federated bidirectional connection broad learning scheme(FeBBLS)to solve the data sharing issues.Firstly,we adopt the bidirectional connection broad learning system(BiBLS)model to train data set in vehicular nodes.The server aggregates the collected parameters of BiBLS from vehicular nodes through the federated broad learning system(FedBLS)algorithm.Moreover,we propose a clustering FedBLS algorithm to offload the data sharing into clusters for improving the aggregation capability of the model.Some simulation results show our scheme can improve the efficiency and prediction accuracy of data sharing and protect the privacy of data sharing.
基金The work presented in this paper is supported by the Shandong Provincial Natural Science Foundation(No.ZR2020MF04)National Natural Science Foundation of China(No.62072469)+2 种基金the Fundamental Research Funds for the Central Universities(19CX05027B,19CX05003A-11)West Coast Artificial Intelligence Technology Innovation Center(2019-1-5,2019-1-6)the Opening Project of Shanghai Trusted Industrial Control Platform(TICPSH202003015-ZC).
文摘The proliferation of Internet of Things(IoT)rapidly increases the possiblities of Simple Service Discovery Protocol(SSDP)reflection attacks.Most DDoS attack defence strategies deploy only to a certain type of devices in the attack chain,and need to detect attacks in advance,and the detection of DDoS attacks often uses heavy algorithms consuming lots of computing resources.This paper proposes a comprehensive DDoS attack defence approach which combines broad learning and a set of defence strategies against SSDP attacks,called Broad Learning based Comprehensive Defence(BLCD).The defence strategies work along the attack chain,starting from attack sources to victims.It defends against attacks without detecting attacks or identifying the roles of IoT devices in SSDP reflection attacks.BLCD also detects suspicious traffic at bots,service providers and victims by using broad learning,and the detection results are used as the basis for automatically deploying defence strategies which can significantly reduce DDoS packets.For evaluations,we thoroughly analyze attack traffic when deploying BLCD to different defence locations.Experiments show that BLCD can reduce the number of packets received at the victim to 39 without affecting the standard SSDP service,and detect malicious packets with an accuracy of 99.99%.
基金National Natural Science Foundation of China (No.61801106)。
文摘With the rapid development in the field of artificial intelligence and natural language processing(NLP),research on music retrieval has gained importance.Music messages express emotional signals.The emotional classification of music can help in conveniently organizing and retrieving music.It is also the premise of using music for psychological intervention and physiological adjustment.A new chord-to-vector method was proposed,which converted the chord information of music into a chord vector of music and combined the weight of the Mel-frequency cepstral coefficient(MFCC) and residual phase(RP) with the feature fusion of a cochleogram.The music emotion recognition and classification training was carried out using the fusion of a convolution neural network and bidirectional long short-term memory(BiLSTM).In addition,based on the self-collected dataset,a comparison of the proposed model with other model structures was performed.The results show that the proposed method achieved a higher recognition accuracy compared with other models.
基金This work is supported by the National Natural Science Foundation of China under Grant 52274057,52074340 and 51874335the Major Scientific and Technological Projects of CNPC under Grant ZD2019-183-008+2 种基金the Major Scientific and Technological Projects of CNOOC under Grant CCL2022RCPS0397RSNthe Science and Technology Support Plan for Youth Innovation of University in Shandong Province under Grant 2019KJH002111 Project under Grant B08028.
文摘Data-driven surrogate models that assist with efficient evolutionary algorithms to find the optimal development scheme have been widely used to solve reservoir production optimization problems.However,existing research suggests that the effectiveness of a surrogate model can vary depending on the complexity of the design problem.A surrogate model that has demonstrated success in one scenario may not perform as well in others.In the absence of prior knowledge,finding a promising surrogate model that performs well for an unknown reservoir is challenging.Moreover,the optimization process often relies on a single evolutionary algorithm,which can yield varying results across different cases.To address these limitations,this paper introduces a novel approach called the multi-surrogate framework with an adaptive selection mechanism(MSFASM)to tackle production optimization problems.MSFASM consists of two stages.In the first stage,a reduced-dimensional broad learning system(BLS)is used to adaptively select the evolutionary algorithm with the best performance during the current optimization period.In the second stage,the multi-objective algorithm,non-dominated sorting genetic algorithm II(NSGA-II),is used as an optimizer to find a set of Pareto solutions with good performance on multiple surrogate models.A novel optimal point criterion is utilized in this stage to select the Pareto solutions,thereby obtaining the desired development schemes without increasing the computational load of the numerical simulator.The two stages are combined using sequential transfer learning.From the two most important perspectives of an evolutionary algorithm and a surrogate model,the proposed method improves adaptability to optimization problems of various reservoir types.To verify the effectiveness of the proposed method,four 100-dimensional benchmark functions and two reservoir models are tested,and the results are compared with those obtained by six other surrogate-model-based methods.The results demonstrate that our approach can obtain the maximum net present value(NPV)of the target production optimization problems.
基金supported by the National Natural Science Foundation of China(No.61876205)the National Key Research and Development Program of China(No.2020YFB1005804)the MOE Project at Center for Linguistics and Applied Linguistics,Guangdong University of Foreign Studies.
文摘Emotion classification in textual conversations focuses on classifying the emotion of each utterance from textual conversations.It is becoming one of the most important tasks for natural language processing in recent years.However,it is a challenging task for machines to conduct emotion classification in textual conversations because emotions rely heavily on textual context.To address the challenge,we propose a method to classify emotion in textual conversations,by integrating the advantages of deep learning and broad learning,namely DBL.It aims to provide a more effective solution to capture local contextual information(i.e.,utterance-level)in an utterance,as well as global contextual information(i.e.,speaker-level)in a conversation,based on Convolutional Neural Network(CNN),Bidirectional Long Short-Term Memory(Bi-LSTM),and broad learning.Extensive experiments have been conducted on three public textual conversation datasets,which show that the context in both utterance-level and speaker-level is consistently beneficial to the performance of emotion classification.In addition,the results show that our proposed method outperforms the baseline methods on most of the testing datasets in weighted-average F1.
基金The work was supported in part by National Natural Science Foundation of China(51807009,71931003,72061147004).
文摘This paper develops a fully data-driven,missingdata tolerant method for post-fault short-term voltage stability(STVS)assessment of power systems against the incomplete PMU measurements.The super-resolution perception(SRP),based on a deep residual learning convolutional neural network,is employed to cope with the missing PMU measurements.The incremental broad learning(BL)is used to rapidly update the model to maintain and enhance the online application performance.Being different from the state-of-the-art methods,the proposed method is fully data-driven and can fill up missing data under any PMU placement information loss and network topology change scenario.Simulation results demonstrate that the proposed method has the best performance in terms of STVS assessment accuracy and missing-data tolerance among the existing methods on the benchmark testing system.
基金This work was partially supported by the National Natural Science Foundation of China(No.61876205)the Natural Science Foundation of Guangdong(No.2021A1515012652)the Science and Technology Program of Guangzhou(No.2019050001).
文摘Cross-domain emotion classification aims to leverage useful information in a source domain to help predict emotion polarity in a target domain in a unsupervised or semi-supervised manner.Due to the domain discrepancy,an emotion classifier trained on source domain may not work well on target domain.Many researchers have focused on traditional cross-domain sentiment classification,which is coarse-grained emotion classification.However,the problem of emotion classification for cross-domain is rarely involved.In this paper,we propose a method,called convolutional neural network(CNN)based broad learning,for cross-domain emotion classification by combining the strength of CNN and broad learning.We first utilized CNN to extract domain-invariant and domain-specific features simultaneously,so as to train two more efficient classifiers by employing broad learning.Then,to take advantage of these two classifiers,we designed a co-training model to boost together for them.Finally,we conducted comparative experiments on four datasets for verifying the effectiveness of our proposed method.The experimental results show that the proposed method can improve the performance of emotion classification more effectively than those baseline methods.
基金supported by the China Scholarship Council during a research visit of Guokai Liu to the University of Iowa(Grant No.201906160078)the Fundamental Research Funds for the Central Universities(Grant No.HUST:2021GCRC058)。
文摘Deep learning has led to tremendous success in machine maintenance and fault diagnosis.However,this success is predicated on the correctly annotated datasets.Labels in large industrial datasets can be noisy and thus degrade the performance of fault diagnosis models.The emerging concept of broad learning shows the potential to address the label noise problem.Compared with existing deep learning algorithms,broad learning has a simple architecture and high training efficiency.An active label denoising algorithm based on broad learning(ALDBL)is proposed.First,ALDBL captures the embedded representation from the time-frequency features by a recurrent memory cell.Second,it augments wide features with a sparse autoencoder and projects the sparse features into an orthogonal space.A proposed corrector then iteratively changes the weights of source examples during the training and corrects the labels by using a label adaptation matrix.Finally,ALDBL finetunes the model parameters with actively sampled target data with reliable pseudo labels.The performance of ALDBL is validated with three benchmark datasets,including 30 label denoising tasks.Computational results demonstrate the effectiveness and advantages of the proposed algorithm over the other label denoising algorithms.
基金This work was partially supported by the National Natural Science Foundation of China(No.61876205)the Ministry of Education of Humanities and Social Science Project(No.19YJAZH128)+1 种基金the Science and Technology Plan Project of Guangzhou(No.201804010433)the Bidding Project of Laboratory of Language Engineering and Computing(No.LEC2017ZBKT001).
文摘Negative emotion classification refers to the automatic classification of negative emotion of texts in social networks.Most existing methods are based on deep learning models,facing challenges such as complex structures and too many hyperparameters.To meet these challenges,in this paper,we propose a method for negative emotion classification utilizing a Robustly Optimized BERT Pretraining Approach(RoBERTa)and p-norm Broad Learning(p-BL).Specifically,there are mainly three contributions in this paper.Firstly,we fine-tune the RoBERTa to adapt it to the task of negative emotion classification.Then,we employ the fine-tuned RoBERTa to extract features of original texts and generate sentence vectors.Secondly,we adopt p-BL to construct a classifier and then predict negative emotions of texts using the classifier.Compared with deep learning models,p-BL has advantages such as a simple structure that is only 3-layer and fewer parameters to be trained.Moreover,it can suppress the adverse effects of more outliers and noise in data by flexibly changing the value of p.Thirdly,we conduct extensive experiments on the public datasets,and the experimental results show that our proposed method outperforms the baseline methods on the tested datasets.
