With the development of economic globalization,distributedmanufacturing is becomingmore andmore prevalent.Recently,integrated scheduling of distributed production and assembly has captured much concern.This research s...With the development of economic globalization,distributedmanufacturing is becomingmore andmore prevalent.Recently,integrated scheduling of distributed production and assembly has captured much concern.This research studies a distributed flexible job shop scheduling problem with assembly operations.Firstly,a mixed integer programming model is formulated to minimize the maximum completion time.Secondly,a Q-learning-assisted coevolutionary algorithmis presented to solve themodel:(1)Multiple populations are developed to seek required decisions simultaneously;(2)An encoding and decoding method based on problem features is applied to represent individuals;(3)A hybrid approach of heuristic rules and random methods is employed to acquire a high-quality population;(4)Three evolutionary strategies having crossover and mutation methods are adopted to enhance exploration capabilities;(5)Three neighborhood structures based on problem features are constructed,and a Q-learning-based iterative local search method is devised to improve exploitation abilities.The Q-learning approach is applied to intelligently select better neighborhood structures.Finally,a group of instances is constructed to perform comparison experiments.The effectiveness of the Q-learning approach is verified by comparing the developed algorithm with its variant without the Q-learning method.Three renowned meta-heuristic algorithms are used in comparison with the developed algorithm.The comparison results demonstrate that the designed method exhibits better performance in coping with the formulated problem.展开更多
Deep learning algorithm is an effective data mining method and has been used in many fields to solve practical problems.However,the deep learning algorithms often contain some hyper-parameters which may be continuous,...Deep learning algorithm is an effective data mining method and has been used in many fields to solve practical problems.However,the deep learning algorithms often contain some hyper-parameters which may be continuous,integer,or mixed,and are often given based on experience but largely affect the effectiveness of activity recognition.In order to adapt to different hyper-parameter optimization problems,our improved Cuckoo Search(CS)algorithm is proposed to optimize the mixed hyper-parameters in deep learning algorithm.The algorithm optimizes the hyper-parameters in the deep learning model robustly,and intelligently selects the combination of integer type and continuous hyper-parameters that make the model optimal.Then,the mixed hyper-parameter in Convolutional Neural Network(CNN),Long-Short-Term Memory(LSTM)and CNN-LSTM are optimized based on the methodology on the smart home activity recognition datasets.Results show that the methodology can improve the performance of the deep learning model and whether we are experienced or not,we can get a better deep learning model using our method.展开更多
BACKGROUND Esophageal squamous cell carcinoma is a major histological subtype of esophageal cancer.Many molecular genetic changes are associated with its occurrence.Raman spectroscopy has become a new method for the e...BACKGROUND Esophageal squamous cell carcinoma is a major histological subtype of esophageal cancer.Many molecular genetic changes are associated with its occurrence.Raman spectroscopy has become a new method for the early diagnosis of tumors because it can reflect the structures of substances and their changes at the molecular level.AIM To detect alterations in Raman spectral information across different stages of esophageal neoplasia.METHODS Different grades of esophageal lesions were collected,and a total of 360 groups of Raman spectrum data were collected.A 1D-transformer network model was proposed to handle the task of classifying the spectral data of esophageal squamous cell carcinoma.In addition,a deep learning model was applied to visualize the Raman spectral data and interpret their molecular characteristics.RESULTS A comparison among Raman spectral data with different pathological grades and a visual analysis revealed that the Raman peaks with significant differences were concentrated mainly at 1095 cm^(-1)(DNA,symmetric PO,and stretching vibration),1132 cm^(-1)(cytochrome c),1171 cm^(-1)(acetoacetate),1216 cm^(-1)(amide III),and 1315 cm^(-1)(glycerol).A comparison among the training results of different models revealed that the 1Dtransformer network performed best.A 93.30%accuracy value,a 96.65%specificity value,a 93.30%sensitivity value,and a 93.17%F1 score were achieved.CONCLUSION Raman spectroscopy revealed significantly different waveforms for the different stages of esophageal neoplasia.The combination of Raman spectroscopy and deep learning methods could significantly improve the accuracy of classification.展开更多
The controller is a main component in the Software-Defined Networking(SDN)framework,which plays a significant role in enabling programmability and orchestration for 5G and next-generation networks.In SDN,frequent comm...The controller is a main component in the Software-Defined Networking(SDN)framework,which plays a significant role in enabling programmability and orchestration for 5G and next-generation networks.In SDN,frequent communication occurs between network switches and the controller,which manages and directs traffic flows.If the controller is not strategically placed within the network,this communication can experience increased delays,negatively affecting network performance.Specifically,an improperly placed controller can lead to higher end-to-end(E2E)delay,as switches must traverse more hops or encounter greater propagation delays when communicating with the controller.This paper introduces a novel approach using Deep Q-Learning(DQL)to dynamically place controllers in Software-Defined Internet of Things(SD-IoT)environments,with the goal of minimizing E2E delay between switches and controllers.E2E delay,a crucial metric for network performance,is influenced by two key factors:hop count,which measures the number of network nodes data must traverse,and propagation delay,which accounts for the physical distance between nodes.Our approach models the controller placement problem as a Markov Decision Process(MDP).In this model,the network configuration at any given time is represented as a“state,”while“actions”correspond to potential decisions regarding the placement of controllers or the reassignment of switches to controllers.Using a Deep Q-Network(DQN)to approximate the Q-function,the system learns the optimal controller placement by maximizing the cumulative reward,which is defined as the negative of the E2E delay.Essentially,the lower the delay,the higher the reward the system receives,enabling it to continuously improve its controller placement strategy.The experimental results show that our DQL-based method significantly reduces E2E delay when compared to traditional benchmark placement strategies.By dynamically learning from the network’s real-time conditions,the proposed method ensures that controller placement remains efficient and responsive,reducing communication delays and enhancing overall network performance.展开更多
The overall performance of multi-robot collaborative systems is significantly affected by the multi-robot task allocation.To improve the effectiveness,robustness,and safety of multi-robot collaborative systems,a multi...The overall performance of multi-robot collaborative systems is significantly affected by the multi-robot task allocation.To improve the effectiveness,robustness,and safety of multi-robot collaborative systems,a multimodal multi-objective evolutionary algorithm based on deep reinforcement learning is proposed in this paper.The improved multimodal multi-objective evolutionary algorithm is used to solve multi-robot task allo-cation problems.Moreover,a deep reinforcement learning strategy is used in the last generation to provide a high-quality path for each assigned robot via an end-to-end manner.Comparisons with three popular multimodal multi-objective evolutionary algorithms on three different scenarios of multi-robot task allocation problems are carried out to verify the performance of the proposed algorithm.The experimental test results show that the proposed algorithm can generate sufficient equivalent schemes to improve the availability and robustness of multi-robot collaborative systems in uncertain environments,and also produce the best scheme to improve the overall task execution efficiency of multi-robot collaborative systems.展开更多
Path planning and obstacle avoidance are two challenging problems in the study of intelligent robots. In this paper, we develop a new method to alleviate these problems based on deep Q-learning with experience replay ...Path planning and obstacle avoidance are two challenging problems in the study of intelligent robots. In this paper, we develop a new method to alleviate these problems based on deep Q-learning with experience replay and heuristic knowledge. In this method, a neural network has been used to resolve the "curse of dimensionality" issue of the Q-table in reinforcement learning. When a robot is walking in an unknown environment, it collects experience data which is used for training a neural network;such a process is called experience replay.Heuristic knowledge helps the robot avoid blind exploration and provides more effective data for training the neural network. The simulation results show that in comparison with the existing methods, our method can converge to an optimal action strategy with less time and can explore a path in an unknown environment with fewer steps and larger average reward.展开更多
Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,w...Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,which are commonly utilized in radiology.To fully exploit their potential,researchers have suggested utilizing deep learning methods to construct computer-aided diagnostic systems.However,constructing and compressing these systems presents a significant challenge,as it relies heavily on the expertise of data scientists.To tackle this issue,we propose an automated approach that utilizes an evolutionary algorithm(EA)to optimize the design and compression of a convolutional neural network(CNN)for X-Ray image classification.Our approach accurately classifies radiography images and detects potential chest abnormalities and infections,including COVID-19.Furthermore,our approach incorporates transfer learning,where a pre-trainedCNNmodel on a vast dataset of chest X-Ray images is fine-tuned for the specific task of detecting COVID-19.This method can help reduce the amount of labeled data required for the task and enhance the overall performance of the model.We have validated our method via a series of experiments against state-of-the-art architectures.展开更多
This research paper presents a comprehensive investigation into the effectiveness of the DeepSurNet-NSGA II(Deep Surrogate Model-Assisted Non-dominated Sorting Genetic Algorithm II)for solving complex multiobjective o...This research paper presents a comprehensive investigation into the effectiveness of the DeepSurNet-NSGA II(Deep Surrogate Model-Assisted Non-dominated Sorting Genetic Algorithm II)for solving complex multiobjective optimization problems,with a particular focus on robotic leg-linkage design.The study introduces an innovative approach that integrates deep learning-based surrogate models with the robust Non-dominated Sorting Genetic Algorithm II,aiming to enhance the efficiency and precision of the optimization process.Through a series of empirical experiments and algorithmic analyses,the paper demonstrates a high degree of correlation between solutions generated by the DeepSurNet-NSGA II and those obtained from direct experimental methods,underscoring the algorithm’s capability to accurately approximate the Pareto-optimal frontier while significantly reducing computational demands.The methodology encompasses a detailed exploration of the algorithm’s configuration,the experimental setup,and the criteria for performance evaluation,ensuring the reproducibility of results and facilitating future advancements in the field.The findings of this study not only confirm the practical applicability and theoretical soundness of the DeepSurNet-NSGA II in navigating the intricacies of multi-objective optimization but also highlight its potential as a transformative tool in engineering and design optimization.By bridging the gap between complex optimization challenges and achievable solutions,this research contributes valuable insights into the optimization domain,offering a promising direction for future inquiries and technological innovations.展开更多
Surface wave inversion is a key step in the application of surface waves to soil velocity profiling.Currently,a common practice for the process of inversion is that the number of soil layers is assumed to be known bef...Surface wave inversion is a key step in the application of surface waves to soil velocity profiling.Currently,a common practice for the process of inversion is that the number of soil layers is assumed to be known before using heuristic search algorithms to compute the shear wave velocity profile or the number of soil layers is considered as an optimization variable.However,an improper selection of the number of layers may lead to an incorrect shear wave velocity profile.In this study,a deep learning and genetic algorithm hybrid learning procedure is proposed to perform the surface wave inversion without the need to assume the number of soil layers.First,a deep neural network is adapted to learn from a large number of synthetic dispersion curves for inferring the layer number.Then,the shear-wave velocity profile is determined by a genetic algorithm with the known layer number.By applying this procedure to both simulated and real-world cases,the results indicate that the proposed method is reliable and efficient for surface wave inversion.展开更多
In blood or bone marrow,leukemia is a form of cancer.A person with leukemia has an expansion of white blood cells(WBCs).It primarily affects children and rarely affects adults.Treatment depends on the type of leukemia...In blood or bone marrow,leukemia is a form of cancer.A person with leukemia has an expansion of white blood cells(WBCs).It primarily affects children and rarely affects adults.Treatment depends on the type of leukemia and the extent to which cancer has established throughout the body.Identifying leukemia in the initial stage is vital to providing timely patient care.Medical image-analysis-related approaches grant safer,quicker,and less costly solutions while ignoring the difficulties of these invasive processes.It can be simple to generalize Computer vision(CV)-based and image-processing techniques and eradicate human error.Many researchers have implemented computer-aided diagnosticmethods andmachine learning(ML)for laboratory image analysis,hopefully overcoming the limitations of late leukemia detection and determining its subgroups.This study establishes a Marine Predators Algorithm with Deep Learning Leukemia Cancer Classification(MPADL-LCC)algorithm onMedical Images.The projectedMPADL-LCC system uses a bilateral filtering(BF)technique to pre-process medical images.The MPADL-LCC system uses Faster SqueezeNet withMarine Predators Algorithm(MPA)as a hyperparameter optimizer for feature extraction.Lastly,the denoising autoencoder(DAE)methodology can be executed to accurately detect and classify leukemia cancer.The hyperparameter tuning process using MPA helps enhance leukemia cancer classification performance.Simulation results are compared with other recent approaches concerning various measurements and the MPADL-LCC algorithm exhibits the best results over other recent approaches.展开更多
The Advanced Geosynchronous Radiation Imager(AGRI)is a mission-critical instrument for the Fengyun series of satellites.AGRI acquires full-disk images every 15 min and views East Asia every 5 min through 14 spectral b...The Advanced Geosynchronous Radiation Imager(AGRI)is a mission-critical instrument for the Fengyun series of satellites.AGRI acquires full-disk images every 15 min and views East Asia every 5 min through 14 spectral bands,enabling the detection of highly variable aerosol optical depth(AOD).Quantitative retrieval of AOD has hitherto been challenging,especially over land.In this study,an AOD retrieval algorithm is proposed that combines deep learning and transfer learning.The algorithm uses core concepts from both the Dark Target(DT)and Deep Blue(DB)algorithms to select features for the machinelearning(ML)algorithm,allowing for AOD retrieval at 550 nm over both dark and bright surfaces.The algorithm consists of two steps:①A baseline deep neural network(DNN)with skip connections is developed using 10 min Advanced Himawari Imager(AHI)AODs as the target variable,and②sunphotometer AODs from 89 ground-based stations are used to fine-tune the DNN parameters.Out-of-station validation shows that the retrieved AOD attains high accuracy,characterized by a coefficient of determination(R2)of 0.70,a mean bias error(MBE)of 0.03,and a percentage of data within the expected error(EE)of 70.7%.A sensitivity study reveals that the top-of-atmosphere reflectance at 650 and 470 nm,as well as the surface reflectance at 650 nm,are the two largest sources of uncertainty impacting the retrieval.In a case study of monitoring an extreme aerosol event,the AGRI AOD is found to be able to capture the detailed temporal evolution of the event.This work demonstrates the superiority of the transfer-learning technique in satellite AOD retrievals and the applicability of the retrieved AGRI AOD in monitoring extreme pollution events.展开更多
Failure detection is an essential task in industrial systems for preventing costly downtime and ensuring the seamlessoperation of the system. Current industrial processes are getting smarter with the emergence of Indu...Failure detection is an essential task in industrial systems for preventing costly downtime and ensuring the seamlessoperation of the system. Current industrial processes are getting smarter with the emergence of Industry 4.0.Specifically, various modernized industrial processes have been equipped with quite a few sensors to collectprocess-based data to find faults arising or prevailing in processes along with monitoring the status of processes.Fault diagnosis of rotating machines serves a main role in the engineering field and industrial production. Dueto the disadvantages of existing fault, diagnosis approaches, which greatly depend on professional experienceand human knowledge, intellectual fault diagnosis based on deep learning (DL) has attracted the researcher’sinterest. DL reaches the desired fault classification and automatic feature learning. Therefore, this article designs a Gradient Optimizer Algorithm with Hybrid Deep Learning-based Failure Detection and Classification (GOAHDLFDC)in the industrial environment. The presented GOAHDL-FDC technique initially applies continuous wavelettransform (CWT) for preprocessing the actual vibrational signals of the rotating machinery. Next, the residualnetwork (ResNet18) model was exploited for the extraction of features from the vibration signals which are thenfed into theHDLmodel for automated fault detection. Finally, theGOA-based hyperparameter tuning is performedtoadjust the parameter valuesof theHDLmodel accurately.The experimental result analysis of the GOAHDL-FD Calgorithm takes place using a series of simulations and the experimentation outcomes highlight the better resultsof the GOAHDL-FDC technique under different aspects.展开更多
Internet of Things(IoTs)provides better solutions in various fields,namely healthcare,smart transportation,home,etc.Recognizing Denial of Service(DoS)outbreaks in IoT platforms is significant in certifying the accessi...Internet of Things(IoTs)provides better solutions in various fields,namely healthcare,smart transportation,home,etc.Recognizing Denial of Service(DoS)outbreaks in IoT platforms is significant in certifying the accessibility and integrity of IoT systems.Deep learning(DL)models outperform in detecting complex,non-linear relationships,allowing them to effectually severe slight deviations fromnormal IoT activities that may designate a DoS outbreak.The uninterrupted observation and real-time detection actions of DL participate in accurate and rapid detection,permitting proactive reduction events to be executed,hence securing the IoT network’s safety and functionality.Subsequently,this study presents pigeon-inspired optimization with a DL-based attack detection and classification(PIODL-ADC)approach in an IoT environment.The PIODL-ADC approach implements a hyperparameter-tuned DL method for Distributed Denial-of-Service(DDoS)attack detection in an IoT platform.Initially,the PIODL-ADC model utilizes Z-score normalization to scale input data into a uniformformat.For handling the convolutional and adaptive behaviors of IoT,the PIODL-ADCmodel employs the pigeon-inspired optimization(PIO)method for feature selection to detect the related features,considerably enhancing the recognition’s accuracy.Also,the Elman Recurrent Neural Network(ERNN)model is utilized to recognize and classify DDoS attacks.Moreover,reptile search algorithm(RSA)based hyperparameter tuning is employed to improve the precision and robustness of the ERNN method.A series of investigational validations is made to ensure the accomplishment of the PIODL-ADC method.The experimental outcome exhibited that the PIODL-ADC method shows greater accomplishment when related to existing models,with a maximum accuracy of 99.81%.展开更多
To support dramatically increased traffic loads,communication networks become ultra-dense.Traditional cell association(CA)schemes are timeconsuming,forcing researchers to seek fast schemes.This paper proposes a deep Q...To support dramatically increased traffic loads,communication networks become ultra-dense.Traditional cell association(CA)schemes are timeconsuming,forcing researchers to seek fast schemes.This paper proposes a deep Q-learning based scheme,whose main idea is to train a deep neural network(DNN)to calculate the Q values of all the state-action pairs and the cell holding the maximum Q value is associated.In the training stage,the intelligent agent continuously generates samples through the trial-anderror method to train the DNN until convergence.In the application stage,state vectors of all the users are inputted to the trained DNN to quickly obtain a satisfied CA result of a scenario with the same BS locations and user distribution.Simulations demonstrate that the proposed scheme provides satisfied CA results in a computational time several orders of magnitudes shorter than traditional schemes.Meanwhile,performance metrics,such as capacity and fairness,can be guaranteed.展开更多
The chirp sub-bottom profiler,for its high resolution,easy accessibility and cost-effectiveness,has been widely used in acoustic detection.In this paper,the acoustic impedance and grain size compositions were obtained...The chirp sub-bottom profiler,for its high resolution,easy accessibility and cost-effectiveness,has been widely used in acoustic detection.In this paper,the acoustic impedance and grain size compositions were obtained based on the chirp sub-bottom profiler data collected in the Chukchi Plateau area during the 11th Arctic Expedition of China.The time-domain adaptive search matching algorithm was used and validated on our established theoretical model.The misfit between the inversion result and the theoretical model is less than 0.067%.The grain size was calculated according to the empirical relationship between the acoustic impedance and the grain size of the sediment.The average acoustic impedance of sub-seafloor strata is 2.5026×10^(6) kg(s m^(2))^(-1)and the average grain size(θvalue)of the seafloor surface sediment is 7.1498,indicating the predominant occurrence of very fine silt sediment in the study area.Comparison of the inversion results and the laboratory measurements of nearby borehole samples shows that they are in general agreement.展开更多
Deep Reinforcement Learning(DRL)is a class of Machine Learning(ML)that combines Deep Learning with Reinforcement Learning and provides a framework by which a system can learn from its previous actions in an environmen...Deep Reinforcement Learning(DRL)is a class of Machine Learning(ML)that combines Deep Learning with Reinforcement Learning and provides a framework by which a system can learn from its previous actions in an environment to select its efforts in the future efficiently.DRL has been used in many application fields,including games,robots,networks,etc.for creating autonomous systems that improve themselves with experience.It is well acknowledged that DRL is well suited to solve optimization problems in distributed systems in general and network routing especially.Therefore,a novel query routing approach called Deep Reinforcement Learning based Route Selection(DRLRS)is proposed for unstructured P2P networks based on a Deep Q-Learning algorithm.The main objective of this approach is to achieve better retrieval effectiveness with reduced searching cost by less number of connected peers,exchangedmessages,and reduced time.The simulation results shows a significantly improve searching a resource with compression to k-Random Walker and Directed BFS.Here,retrieval effectiveness,search cost in terms of connected peers,and average overhead are 1.28,106,149,respectively.展开更多
Q-learning is a popular temporal-difference reinforcement learning algorithm which often explicitly stores state values using lookup tables. This implementation has been proven to converge to the optimal solution, but...Q-learning is a popular temporal-difference reinforcement learning algorithm which often explicitly stores state values using lookup tables. This implementation has been proven to converge to the optimal solution, but it is often beneficial to use a function-approximation system, such as deep neural networks, to estimate state values. It has been previously observed that Q-learning can be unstable when using value function approximation or when operating in a stochastic environment. This instability can adversely affect the algorithm’s ability to maximize its returns. In this paper, we present a new algorithm called Multi Q-learning to attempt to overcome the instability seen in Q-learning. We test our algorithm on a 4 × 4 grid-world with different stochastic reward functions using various deep neural networks and convolutional networks. Our results show that in most cases, Multi Q-learning outperforms Q-learning, achieving average returns up to 2.5 times higher than Q-learning and having a standard deviation of state values as low as 0.58.展开更多
Beamforming is significant for millimeter wave multi-user massive multi-input multi-output systems.In the meanwhile,the overhead cost of channel state information and beam training is considerable,especially in dynami...Beamforming is significant for millimeter wave multi-user massive multi-input multi-output systems.In the meanwhile,the overhead cost of channel state information and beam training is considerable,especially in dynamic environments.To reduce the overhead cost,we propose a multi-user beam tracking algorithm using a distributed deep Q-learning method.With online learning of users’moving trajectories,the proposed algorithm learns to scan a beam subspace to maximize the average effective sum rate.Considering practical implementation,we model the continuous beam tracking problem as a non-Markov decision process and thus develop a simplified training scheme of deep Q-learning to reduce the training complexity.Furthermore,we propose a scalable state-action-reward design for scenarios with different users and antenna numbers.Simulation results verify the effectiveness of the designed method.展开更多
At present,the prediction of brain tumors is performed using Machine Learning(ML)and Deep Learning(DL)algorithms.Although various ML and DL algorithms are adapted to predict brain tumors to some range,some concerns st...At present,the prediction of brain tumors is performed using Machine Learning(ML)and Deep Learning(DL)algorithms.Although various ML and DL algorithms are adapted to predict brain tumors to some range,some concerns still need enhancement,particularly accuracy,sensitivity,false positive and false negative,to improve the brain tumor prediction system symmetrically.Therefore,this work proposed an Extended Deep Learning Algorithm(EDLA)to measure performance parameters such as accuracy,sensitivity,and false positive and false negative rates.In addition,these iterated measures were analyzed by comparing the EDLA method with the Convolutional Neural Network(CNN)way further using the SPSS tool,and respective graphical illustrations were shown.The results were that the mean performance measures for the proposed EDLA algorithm were calculated,and those measured were accuracy(97.665%),sensitivity(97.939%),false positive(3.012%),and false negative(3.182%)for ten iterations.Whereas in the case of the CNN,the algorithm means accuracy gained was 94.287%,mean sensitivity 95.612%,mean false positive 5.328%,and mean false negative 4.756%.These results show that the proposed EDLA method has outperformed existing algorithms,including CNN,and ensures symmetrically improved parameters.Thus EDLA algorithm introduces novelty concerning its performance and particular activation function.This proposed method will be utilized effectively in brain tumor detection in a precise and accurate manner.This algorithm would apply to brain tumor diagnosis and be involved in various medical diagnoses aftermodification.If the quantity of dataset records is enormous,then themethod’s computation power has to be updated.展开更多
文摘With the development of economic globalization,distributedmanufacturing is becomingmore andmore prevalent.Recently,integrated scheduling of distributed production and assembly has captured much concern.This research studies a distributed flexible job shop scheduling problem with assembly operations.Firstly,a mixed integer programming model is formulated to minimize the maximum completion time.Secondly,a Q-learning-assisted coevolutionary algorithmis presented to solve themodel:(1)Multiple populations are developed to seek required decisions simultaneously;(2)An encoding and decoding method based on problem features is applied to represent individuals;(3)A hybrid approach of heuristic rules and random methods is employed to acquire a high-quality population;(4)Three evolutionary strategies having crossover and mutation methods are adopted to enhance exploration capabilities;(5)Three neighborhood structures based on problem features are constructed,and a Q-learning-based iterative local search method is devised to improve exploitation abilities.The Q-learning approach is applied to intelligently select better neighborhood structures.Finally,a group of instances is constructed to perform comparison experiments.The effectiveness of the Q-learning approach is verified by comparing the developed algorithm with its variant without the Q-learning method.Three renowned meta-heuristic algorithms are used in comparison with the developed algorithm.The comparison results demonstrate that the designed method exhibits better performance in coping with the formulated problem.
基金Supported by the Anhui Province Sports Health Information Monitoring Technology Engineering Research Center Open Project (KF2023012)。
文摘Deep learning algorithm is an effective data mining method and has been used in many fields to solve practical problems.However,the deep learning algorithms often contain some hyper-parameters which may be continuous,integer,or mixed,and are often given based on experience but largely affect the effectiveness of activity recognition.In order to adapt to different hyper-parameter optimization problems,our improved Cuckoo Search(CS)algorithm is proposed to optimize the mixed hyper-parameters in deep learning algorithm.The algorithm optimizes the hyper-parameters in the deep learning model robustly,and intelligently selects the combination of integer type and continuous hyper-parameters that make the model optimal.Then,the mixed hyper-parameter in Convolutional Neural Network(CNN),Long-Short-Term Memory(LSTM)and CNN-LSTM are optimized based on the methodology on the smart home activity recognition datasets.Results show that the methodology can improve the performance of the deep learning model and whether we are experienced or not,we can get a better deep learning model using our method.
基金Supported by Beijing Hospitals Authority Youth Programme,No.QML20200505.
文摘BACKGROUND Esophageal squamous cell carcinoma is a major histological subtype of esophageal cancer.Many molecular genetic changes are associated with its occurrence.Raman spectroscopy has become a new method for the early diagnosis of tumors because it can reflect the structures of substances and their changes at the molecular level.AIM To detect alterations in Raman spectral information across different stages of esophageal neoplasia.METHODS Different grades of esophageal lesions were collected,and a total of 360 groups of Raman spectrum data were collected.A 1D-transformer network model was proposed to handle the task of classifying the spectral data of esophageal squamous cell carcinoma.In addition,a deep learning model was applied to visualize the Raman spectral data and interpret their molecular characteristics.RESULTS A comparison among Raman spectral data with different pathological grades and a visual analysis revealed that the Raman peaks with significant differences were concentrated mainly at 1095 cm^(-1)(DNA,symmetric PO,and stretching vibration),1132 cm^(-1)(cytochrome c),1171 cm^(-1)(acetoacetate),1216 cm^(-1)(amide III),and 1315 cm^(-1)(glycerol).A comparison among the training results of different models revealed that the 1Dtransformer network performed best.A 93.30%accuracy value,a 96.65%specificity value,a 93.30%sensitivity value,and a 93.17%F1 score were achieved.CONCLUSION Raman spectroscopy revealed significantly different waveforms for the different stages of esophageal neoplasia.The combination of Raman spectroscopy and deep learning methods could significantly improve the accuracy of classification.
基金supported by the Researcher Supporting Project number(RSPD2024R582),King Saud University,Riyadh,Saudi Arabia.
文摘The controller is a main component in the Software-Defined Networking(SDN)framework,which plays a significant role in enabling programmability and orchestration for 5G and next-generation networks.In SDN,frequent communication occurs between network switches and the controller,which manages and directs traffic flows.If the controller is not strategically placed within the network,this communication can experience increased delays,negatively affecting network performance.Specifically,an improperly placed controller can lead to higher end-to-end(E2E)delay,as switches must traverse more hops or encounter greater propagation delays when communicating with the controller.This paper introduces a novel approach using Deep Q-Learning(DQL)to dynamically place controllers in Software-Defined Internet of Things(SD-IoT)environments,with the goal of minimizing E2E delay between switches and controllers.E2E delay,a crucial metric for network performance,is influenced by two key factors:hop count,which measures the number of network nodes data must traverse,and propagation delay,which accounts for the physical distance between nodes.Our approach models the controller placement problem as a Markov Decision Process(MDP).In this model,the network configuration at any given time is represented as a“state,”while“actions”correspond to potential decisions regarding the placement of controllers or the reassignment of switches to controllers.Using a Deep Q-Network(DQN)to approximate the Q-function,the system learns the optimal controller placement by maximizing the cumulative reward,which is defined as the negative of the E2E delay.Essentially,the lower the delay,the higher the reward the system receives,enabling it to continuously improve its controller placement strategy.The experimental results show that our DQL-based method significantly reduces E2E delay when compared to traditional benchmark placement strategies.By dynamically learning from the network’s real-time conditions,the proposed method ensures that controller placement remains efficient and responsive,reducing communication delays and enhancing overall network performance.
基金the Shanghai Pujiang Program (No.22PJD030),the National Natural Science Foundation of China (Nos.61603244 and 71904116)the National Natural Science Foundation of China-Shandong Joint Fund (No.U2006228)。
文摘The overall performance of multi-robot collaborative systems is significantly affected by the multi-robot task allocation.To improve the effectiveness,robustness,and safety of multi-robot collaborative systems,a multimodal multi-objective evolutionary algorithm based on deep reinforcement learning is proposed in this paper.The improved multimodal multi-objective evolutionary algorithm is used to solve multi-robot task allo-cation problems.Moreover,a deep reinforcement learning strategy is used in the last generation to provide a high-quality path for each assigned robot via an end-to-end manner.Comparisons with three popular multimodal multi-objective evolutionary algorithms on three different scenarios of multi-robot task allocation problems are carried out to verify the performance of the proposed algorithm.The experimental test results show that the proposed algorithm can generate sufficient equivalent schemes to improve the availability and robustness of multi-robot collaborative systems in uncertain environments,and also produce the best scheme to improve the overall task execution efficiency of multi-robot collaborative systems.
基金supported by the National Natural Science Foundation of China(61751210,61572441)。
文摘Path planning and obstacle avoidance are two challenging problems in the study of intelligent robots. In this paper, we develop a new method to alleviate these problems based on deep Q-learning with experience replay and heuristic knowledge. In this method, a neural network has been used to resolve the "curse of dimensionality" issue of the Q-table in reinforcement learning. When a robot is walking in an unknown environment, it collects experience data which is used for training a neural network;such a process is called experience replay.Heuristic knowledge helps the robot avoid blind exploration and provides more effective data for training the neural network. The simulation results show that in comparison with the existing methods, our method can converge to an optimal action strategy with less time and can explore a path in an unknown environment with fewer steps and larger average reward.
基金via funding from Prince Sattam bin Abdulaziz University Project Number(PSAU/2023/R/1444).
文摘Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,which are commonly utilized in radiology.To fully exploit their potential,researchers have suggested utilizing deep learning methods to construct computer-aided diagnostic systems.However,constructing and compressing these systems presents a significant challenge,as it relies heavily on the expertise of data scientists.To tackle this issue,we propose an automated approach that utilizes an evolutionary algorithm(EA)to optimize the design and compression of a convolutional neural network(CNN)for X-Ray image classification.Our approach accurately classifies radiography images and detects potential chest abnormalities and infections,including COVID-19.Furthermore,our approach incorporates transfer learning,where a pre-trainedCNNmodel on a vast dataset of chest X-Ray images is fine-tuned for the specific task of detecting COVID-19.This method can help reduce the amount of labeled data required for the task and enhance the overall performance of the model.We have validated our method via a series of experiments against state-of-the-art architectures.
文摘This research paper presents a comprehensive investigation into the effectiveness of the DeepSurNet-NSGA II(Deep Surrogate Model-Assisted Non-dominated Sorting Genetic Algorithm II)for solving complex multiobjective optimization problems,with a particular focus on robotic leg-linkage design.The study introduces an innovative approach that integrates deep learning-based surrogate models with the robust Non-dominated Sorting Genetic Algorithm II,aiming to enhance the efficiency and precision of the optimization process.Through a series of empirical experiments and algorithmic analyses,the paper demonstrates a high degree of correlation between solutions generated by the DeepSurNet-NSGA II and those obtained from direct experimental methods,underscoring the algorithm’s capability to accurately approximate the Pareto-optimal frontier while significantly reducing computational demands.The methodology encompasses a detailed exploration of the algorithm’s configuration,the experimental setup,and the criteria for performance evaluation,ensuring the reproducibility of results and facilitating future advancements in the field.The findings of this study not only confirm the practical applicability and theoretical soundness of the DeepSurNet-NSGA II in navigating the intricacies of multi-objective optimization but also highlight its potential as a transformative tool in engineering and design optimization.By bridging the gap between complex optimization challenges and achievable solutions,this research contributes valuable insights into the optimization domain,offering a promising direction for future inquiries and technological innovations.
基金provided through research grant No.0035/2019/A1 from the Science and Technology Development Fund,Macao SARthe assistantship from the Faculty of Science and Technology,University of Macao。
文摘Surface wave inversion is a key step in the application of surface waves to soil velocity profiling.Currently,a common practice for the process of inversion is that the number of soil layers is assumed to be known before using heuristic search algorithms to compute the shear wave velocity profile or the number of soil layers is considered as an optimization variable.However,an improper selection of the number of layers may lead to an incorrect shear wave velocity profile.In this study,a deep learning and genetic algorithm hybrid learning procedure is proposed to perform the surface wave inversion without the need to assume the number of soil layers.First,a deep neural network is adapted to learn from a large number of synthetic dispersion curves for inferring the layer number.Then,the shear-wave velocity profile is determined by a genetic algorithm with the known layer number.By applying this procedure to both simulated and real-world cases,the results indicate that the proposed method is reliable and efficient for surface wave inversion.
基金funded by Researchers Supporting Program at King Saud University,(RSPD2024R809).
文摘In blood or bone marrow,leukemia is a form of cancer.A person with leukemia has an expansion of white blood cells(WBCs).It primarily affects children and rarely affects adults.Treatment depends on the type of leukemia and the extent to which cancer has established throughout the body.Identifying leukemia in the initial stage is vital to providing timely patient care.Medical image-analysis-related approaches grant safer,quicker,and less costly solutions while ignoring the difficulties of these invasive processes.It can be simple to generalize Computer vision(CV)-based and image-processing techniques and eradicate human error.Many researchers have implemented computer-aided diagnosticmethods andmachine learning(ML)for laboratory image analysis,hopefully overcoming the limitations of late leukemia detection and determining its subgroups.This study establishes a Marine Predators Algorithm with Deep Learning Leukemia Cancer Classification(MPADL-LCC)algorithm onMedical Images.The projectedMPADL-LCC system uses a bilateral filtering(BF)technique to pre-process medical images.The MPADL-LCC system uses Faster SqueezeNet withMarine Predators Algorithm(MPA)as a hyperparameter optimizer for feature extraction.Lastly,the denoising autoencoder(DAE)methodology can be executed to accurately detect and classify leukemia cancer.The hyperparameter tuning process using MPA helps enhance leukemia cancer classification performance.Simulation results are compared with other recent approaches concerning various measurements and the MPADL-LCC algorithm exhibits the best results over other recent approaches.
基金supported by the National Natural Science of Foundation of China(41825011,42030608,42105128,and 42075079)the Opening Foundation of Key Laboratory of Atmospheric Sounding,the CMA and the CMA Research Center on Meteorological Observation Engineering Technology(U2021Z03).
文摘The Advanced Geosynchronous Radiation Imager(AGRI)is a mission-critical instrument for the Fengyun series of satellites.AGRI acquires full-disk images every 15 min and views East Asia every 5 min through 14 spectral bands,enabling the detection of highly variable aerosol optical depth(AOD).Quantitative retrieval of AOD has hitherto been challenging,especially over land.In this study,an AOD retrieval algorithm is proposed that combines deep learning and transfer learning.The algorithm uses core concepts from both the Dark Target(DT)and Deep Blue(DB)algorithms to select features for the machinelearning(ML)algorithm,allowing for AOD retrieval at 550 nm over both dark and bright surfaces.The algorithm consists of two steps:①A baseline deep neural network(DNN)with skip connections is developed using 10 min Advanced Himawari Imager(AHI)AODs as the target variable,and②sunphotometer AODs from 89 ground-based stations are used to fine-tune the DNN parameters.Out-of-station validation shows that the retrieved AOD attains high accuracy,characterized by a coefficient of determination(R2)of 0.70,a mean bias error(MBE)of 0.03,and a percentage of data within the expected error(EE)of 70.7%.A sensitivity study reveals that the top-of-atmosphere reflectance at 650 and 470 nm,as well as the surface reflectance at 650 nm,are the two largest sources of uncertainty impacting the retrieval.In a case study of monitoring an extreme aerosol event,the AGRI AOD is found to be able to capture the detailed temporal evolution of the event.This work demonstrates the superiority of the transfer-learning technique in satellite AOD retrievals and the applicability of the retrieved AGRI AOD in monitoring extreme pollution events.
基金The Deanship of Scientific Research(DSR)at King Abdulaziz University(KAU),Jeddah,Saudi Arabia has funded this project under Grant No.(G:651-135-1443).
文摘Failure detection is an essential task in industrial systems for preventing costly downtime and ensuring the seamlessoperation of the system. Current industrial processes are getting smarter with the emergence of Industry 4.0.Specifically, various modernized industrial processes have been equipped with quite a few sensors to collectprocess-based data to find faults arising or prevailing in processes along with monitoring the status of processes.Fault diagnosis of rotating machines serves a main role in the engineering field and industrial production. Dueto the disadvantages of existing fault, diagnosis approaches, which greatly depend on professional experienceand human knowledge, intellectual fault diagnosis based on deep learning (DL) has attracted the researcher’sinterest. DL reaches the desired fault classification and automatic feature learning. Therefore, this article designs a Gradient Optimizer Algorithm with Hybrid Deep Learning-based Failure Detection and Classification (GOAHDLFDC)in the industrial environment. The presented GOAHDL-FDC technique initially applies continuous wavelettransform (CWT) for preprocessing the actual vibrational signals of the rotating machinery. Next, the residualnetwork (ResNet18) model was exploited for the extraction of features from the vibration signals which are thenfed into theHDLmodel for automated fault detection. Finally, theGOA-based hyperparameter tuning is performedtoadjust the parameter valuesof theHDLmodel accurately.The experimental result analysis of the GOAHDL-FD Calgorithm takes place using a series of simulations and the experimentation outcomes highlight the better resultsof the GOAHDL-FDC technique under different aspects.
文摘Internet of Things(IoTs)provides better solutions in various fields,namely healthcare,smart transportation,home,etc.Recognizing Denial of Service(DoS)outbreaks in IoT platforms is significant in certifying the accessibility and integrity of IoT systems.Deep learning(DL)models outperform in detecting complex,non-linear relationships,allowing them to effectually severe slight deviations fromnormal IoT activities that may designate a DoS outbreak.The uninterrupted observation and real-time detection actions of DL participate in accurate and rapid detection,permitting proactive reduction events to be executed,hence securing the IoT network’s safety and functionality.Subsequently,this study presents pigeon-inspired optimization with a DL-based attack detection and classification(PIODL-ADC)approach in an IoT environment.The PIODL-ADC approach implements a hyperparameter-tuned DL method for Distributed Denial-of-Service(DDoS)attack detection in an IoT platform.Initially,the PIODL-ADC model utilizes Z-score normalization to scale input data into a uniformformat.For handling the convolutional and adaptive behaviors of IoT,the PIODL-ADCmodel employs the pigeon-inspired optimization(PIO)method for feature selection to detect the related features,considerably enhancing the recognition’s accuracy.Also,the Elman Recurrent Neural Network(ERNN)model is utilized to recognize and classify DDoS attacks.Moreover,reptile search algorithm(RSA)based hyperparameter tuning is employed to improve the precision and robustness of the ERNN method.A series of investigational validations is made to ensure the accomplishment of the PIODL-ADC method.The experimental outcome exhibited that the PIODL-ADC method shows greater accomplishment when related to existing models,with a maximum accuracy of 99.81%.
基金This work was supported by the Fundamental Research Funds for the Central Universities of China under grant no.PA2019GDQT0012by National Natural Science Foundation of China(Grant No.61971176)by the Applied Basic Research Program ofWuhan City,China,under grand 2017010201010117.
文摘To support dramatically increased traffic loads,communication networks become ultra-dense.Traditional cell association(CA)schemes are timeconsuming,forcing researchers to seek fast schemes.This paper proposes a deep Q-learning based scheme,whose main idea is to train a deep neural network(DNN)to calculate the Q values of all the state-action pairs and the cell holding the maximum Q value is associated.In the training stage,the intelligent agent continuously generates samples through the trial-anderror method to train the DNN until convergence.In the application stage,state vectors of all the users are inputted to the trained DNN to quickly obtain a satisfied CA result of a scenario with the same BS locations and user distribution.Simulations demonstrate that the proposed scheme provides satisfied CA results in a computational time several orders of magnitudes shorter than traditional schemes.Meanwhile,performance metrics,such as capacity and fairness,can be guaranteed.
基金supported by the National Key R&D Program of China (No.2021YFC2801202)the National Natural Science Foundation of China (No.42076224)the Fundamental Research Funds for the Central Universities (No.202262012)。
文摘The chirp sub-bottom profiler,for its high resolution,easy accessibility and cost-effectiveness,has been widely used in acoustic detection.In this paper,the acoustic impedance and grain size compositions were obtained based on the chirp sub-bottom profiler data collected in the Chukchi Plateau area during the 11th Arctic Expedition of China.The time-domain adaptive search matching algorithm was used and validated on our established theoretical model.The misfit between the inversion result and the theoretical model is less than 0.067%.The grain size was calculated according to the empirical relationship between the acoustic impedance and the grain size of the sediment.The average acoustic impedance of sub-seafloor strata is 2.5026×10^(6) kg(s m^(2))^(-1)and the average grain size(θvalue)of the seafloor surface sediment is 7.1498,indicating the predominant occurrence of very fine silt sediment in the study area.Comparison of the inversion results and the laboratory measurements of nearby borehole samples shows that they are in general agreement.
基金Authors would like to thank the Deanship of Scientific Research at Shaqra University for supporting this work under Project No.g01/n04.
文摘Deep Reinforcement Learning(DRL)is a class of Machine Learning(ML)that combines Deep Learning with Reinforcement Learning and provides a framework by which a system can learn from its previous actions in an environment to select its efforts in the future efficiently.DRL has been used in many application fields,including games,robots,networks,etc.for creating autonomous systems that improve themselves with experience.It is well acknowledged that DRL is well suited to solve optimization problems in distributed systems in general and network routing especially.Therefore,a novel query routing approach called Deep Reinforcement Learning based Route Selection(DRLRS)is proposed for unstructured P2P networks based on a Deep Q-Learning algorithm.The main objective of this approach is to achieve better retrieval effectiveness with reduced searching cost by less number of connected peers,exchangedmessages,and reduced time.The simulation results shows a significantly improve searching a resource with compression to k-Random Walker and Directed BFS.Here,retrieval effectiveness,search cost in terms of connected peers,and average overhead are 1.28,106,149,respectively.
文摘Q-learning is a popular temporal-difference reinforcement learning algorithm which often explicitly stores state values using lookup tables. This implementation has been proven to converge to the optimal solution, but it is often beneficial to use a function-approximation system, such as deep neural networks, to estimate state values. It has been previously observed that Q-learning can be unstable when using value function approximation or when operating in a stochastic environment. This instability can adversely affect the algorithm’s ability to maximize its returns. In this paper, we present a new algorithm called Multi Q-learning to attempt to overcome the instability seen in Q-learning. We test our algorithm on a 4 × 4 grid-world with different stochastic reward functions using various deep neural networks and convolutional networks. Our results show that in most cases, Multi Q-learning outperforms Q-learning, achieving average returns up to 2.5 times higher than Q-learning and having a standard deviation of state values as low as 0.58.
文摘Beamforming is significant for millimeter wave multi-user massive multi-input multi-output systems.In the meanwhile,the overhead cost of channel state information and beam training is considerable,especially in dynamic environments.To reduce the overhead cost,we propose a multi-user beam tracking algorithm using a distributed deep Q-learning method.With online learning of users’moving trajectories,the proposed algorithm learns to scan a beam subspace to maximize the average effective sum rate.Considering practical implementation,we model the continuous beam tracking problem as a non-Markov decision process and thus develop a simplified training scheme of deep Q-learning to reduce the training complexity.Furthermore,we propose a scalable state-action-reward design for scenarios with different users and antenna numbers.Simulation results verify the effectiveness of the designed method.
基金supported by Project No.R-2023-23 of the Deanship of Scientific Research at Majmaah University.
文摘At present,the prediction of brain tumors is performed using Machine Learning(ML)and Deep Learning(DL)algorithms.Although various ML and DL algorithms are adapted to predict brain tumors to some range,some concerns still need enhancement,particularly accuracy,sensitivity,false positive and false negative,to improve the brain tumor prediction system symmetrically.Therefore,this work proposed an Extended Deep Learning Algorithm(EDLA)to measure performance parameters such as accuracy,sensitivity,and false positive and false negative rates.In addition,these iterated measures were analyzed by comparing the EDLA method with the Convolutional Neural Network(CNN)way further using the SPSS tool,and respective graphical illustrations were shown.The results were that the mean performance measures for the proposed EDLA algorithm were calculated,and those measured were accuracy(97.665%),sensitivity(97.939%),false positive(3.012%),and false negative(3.182%)for ten iterations.Whereas in the case of the CNN,the algorithm means accuracy gained was 94.287%,mean sensitivity 95.612%,mean false positive 5.328%,and mean false negative 4.756%.These results show that the proposed EDLA method has outperformed existing algorithms,including CNN,and ensures symmetrically improved parameters.Thus EDLA algorithm introduces novelty concerning its performance and particular activation function.This proposed method will be utilized effectively in brain tumor detection in a precise and accurate manner.This algorithm would apply to brain tumor diagnosis and be involved in various medical diagnoses aftermodification.If the quantity of dataset records is enormous,then themethod’s computation power has to be updated.
