Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-a...Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-aided diagnosis system is highly required.Ultrasound is an important examination technique for breast cancer diagnosis due to its low cost.Recently,many learning-based techniques have been introduced to classify breast cancer using breast ultrasound imaging dataset(BUSI)datasets;however,the manual handling is not an easy process and time consuming.The authors propose an EfficientNet-integrated ResNet deep network and XAI-based framework for accurately classifying breast cancer(malignant and benign).In the initial step,data augmentation is performed to increase the number of training samples.For this purpose,three-pixel flip mathematical equations are introduced:horizontal,vertical,and 90°.Later,two pretrained deep learning models were employed,skipped some layers,and fine-tuned.Both fine-tuned models are later trained using a deep transfer learning process and extracted features from the deeper layer.Explainable artificial intelligence-based analysed the performance of trained models.After that,a new feature selection technique is proposed based on the cuckoo search algorithm called cuckoo search controlled standard error mean.This technique selects the best features and fuses using a new parallel zeropadding maximum correlated coefficient features.In the end,the selection algorithm is applied again to the fused feature vector and classified using machine learning algorithms.The experimental process of the proposed framework is conducted on a publicly available BUSI and obtained 98.4%and 98%accuracy in two different experiments.Comparing the proposed framework is also conducted with recent techniques and shows improved accuracy.In addition,the proposed framework was executed less than the original deep learning models.展开更多
In 6G era,service forms in which computing power acts as the core will be ubiquitous in the network.At the same time,the collaboration among edge computing,cloud computing and network is needed to support edge computi...In 6G era,service forms in which computing power acts as the core will be ubiquitous in the network.At the same time,the collaboration among edge computing,cloud computing and network is needed to support edge computing service with strong demand for computing power,so as to realize the optimization of resource utilization.Based on this,the article discusses the research background,key techniques and main application scenarios of computing power network.Through the demonstration,it can be concluded that the technical solution of computing power network can effectively meet the multi-level deployment and flexible scheduling needs of the future 6G business for computing,storage and network,and adapt to the integration needs of computing power and network in various scenarios,such as user oriented,government enterprise oriented,computing power open and so on.展开更多
With the increasing dimensionality of network traffic,extracting effective traffic features and improving the identification accuracy of different intrusion traffic have become critical in intrusion detection systems(...With the increasing dimensionality of network traffic,extracting effective traffic features and improving the identification accuracy of different intrusion traffic have become critical in intrusion detection systems(IDS).However,both unsupervised and semisupervised anomalous traffic detection methods suffer from the drawback of ignoring potential correlations between features,resulting in an analysis that is not an optimal set.Therefore,in order to extract more representative traffic features as well as to improve the accuracy of traffic identification,this paper proposes a feature dimensionality reduction method combining principal component analysis and Hotelling’s T^(2) and a multilayer convolutional bidirectional long short-term memory(MSC_BiLSTM)classifier model for network traffic intrusion detection.This method reduces the parameters and redundancy of the model by feature extraction and extracts the dependent features between the data by a bidirectional long short-term memory(BiLSTM)network,which fully considers the influence between the before and after features.The network traffic is first characteristically downscaled by principal component analysis(PCA),and then the downscaled principal components are used as input to Hotelling’s T^(2) to compare the differences between groups.For datasets with outliers,Hotelling’s T^(2) can help identify the groups where the outliers are located and quantitatively measure the extent of the outliers.Finally,a multilayer convolutional neural network and a BiLSTM network are used to extract the spatial and temporal features of network traffic data.The empirical consequences exhibit that the suggested approach in this manuscript attains superior outcomes in precision,recall and F1-score juxtaposed with the prevailing techniques.The results show that the intrusion detection accuracy,precision,and F1-score of the proposed MSC_BiLSTM model for the CIC-IDS 2017 dataset are 98.71%,95.97%,and 90.22%.展开更多
In this paper, we propose an optical burst network architecture supporting the ge- netic mesh topology. The intermediate node architecture of the mesh network can be the same with current wavelength switching Wave- le...In this paper, we propose an optical burst network architecture supporting the ge- netic mesh topology. The intermediate node architecture of the mesh network can be the same with current wavelength switching Wave- length Division Multiplexing （WDM） net- works, and thus can reuse existing deployed infrastructure. We employ a novel Optical Time Slot Interchange （OTSI） at the source nodes for the first time to mitigate the burst conten- tion and to increase the bandwidth utilization. Time- and wavelength-domain reuse in the OTSI significantly saves optical components and red- uces blocking probability.展开更多
To promote reliable and secure communications in the cognitive radio network,the automatic modulation classification algorithms have been mainly proposed to estimate a single modulation.In this paper,we address the cl...To promote reliable and secure communications in the cognitive radio network,the automatic modulation classification algorithms have been mainly proposed to estimate a single modulation.In this paper,we address the classification of superimposed modulations dedicated to 5G multipleinput multiple-output(MIMO)two-way cognitive relay network in realistic channels modeled with Nakagami-m distribution.Our purpose consists of classifying pairs of users modulations from superimposed signals.To achieve this goal,we apply the higher-order statistics in conjunction with the Multi-BoostAB classifier.We use several efficiency metrics including the true positive(TP)rate,false positive(FP)rate,precision,recall,F-Measure and receiver operating characteristic(ROC)area in order to evaluate the performance of the proposed algorithm in terms of correct superimposed modulations classification.Computer simulations prove that our proposal allows obtaining a good probability of classification for ten superimposed modulations at a low signal-to-noise ratio,including the worst case(i.e.,m=0.5),where the fading distribution follows a one-sided Gaussian distribution.We also carry out a comparative study between our proposal usingMultiBoostAB classifier with the decision tree(J48)classifier.Simulation results show that the performance of MultiBoostAB on the superimposed modulations classifications outperforms the one of J48 classifier.In addition,we study the impact of the symbols number,path loss exponent and relay position on the performance of the proposed automatic classification superimposed modulations in terms of probability of correct classification.展开更多
As users’access to the network has evolved into the acquisition of mass contents instead of IP addresses,the IP network architecture based on end-to-end communication cannot meet users’needs.Therefore,the Informatio...As users’access to the network has evolved into the acquisition of mass contents instead of IP addresses,the IP network architecture based on end-to-end communication cannot meet users’needs.Therefore,the Information-Centric Networking(ICN)came into being.From a technical point of view,ICN is a promising future network architecture.Researching and customizing a reasonable pricing mechanism plays a positive role in promoting the deployment of ICN.The current research on ICN pricing mechanism is focused on paid content.Therefore,we study an ICN pricing model for free content,which uses game theory based on Nash equilibrium to analysis.In this work,advertisers are considered,and an advertiser model is established to describe the economic interaction between advertisers and ICN entities.This solution can formulate the best pricing strategy for all ICN entities and maximize the benefits of each entity.Our extensive analysis and numerical results show that the proposed pricing framework is significantly better than existing solutions when it comes to free content.展开更多
Inter-datacenter elastic optical networks(EON)need to provide the service for the requests of cloud computing that require not only connectivity and computing resources but also network survivability.In this paper,to ...Inter-datacenter elastic optical networks(EON)need to provide the service for the requests of cloud computing that require not only connectivity and computing resources but also network survivability.In this paper,to realize joint allocation of computing and connectivity resources in survivable inter-datacenter EONs,a survivable routing,modulation level,spectrum,and computing resource allocation algorithm(SRMLSCRA)algorithm and three datacenter selection strategies,i.e.Computing Resource First(CRF),Shortest Path First(SPF)and Random Destination(RD),are proposed for different scenarios.Unicast and manycast are applied to the communication of computing requests,and the routing strategies are calculated respectively.Simulation results show that SRMLCRA-CRF can serve the largest amount of protected computing tasks,and the requested calculation blocking probability is reduced by 29.2%,28.3%and 30.5%compared with SRMLSCRA-SPF,SRMLSCRA-RD and the benchmark EPS-RMSA algorithms respectively.Therefore,it is more applicable to the networks with huge calculations.Besides,SRMLSCRA-SPF consumes the least spectrum,thereby exhibiting its suitability for scenarios where the amount of calculation is small and communication resources are scarce.The results demonstrate that the proposed methods realize the joint allocation of computing and connectivity resources,and could provide efficient protection for services under single-link failure and occupy less spectrum.展开更多
The deep understanding on sand and sand dunes scale can be useful to reveal the formation mechanism of the sandstorm for early sandstorm forecast. The current sandstorm observation methods are mainly based on conventi...The deep understanding on sand and sand dunes scale can be useful to reveal the formation mechanism of the sandstorm for early sandstorm forecast. The current sandstorm observation methods are mainly based on conventional meteorological station and satellites remote sensing, which are difficult to acquire sand scale information. A wireless sensing network is implemented in the hinterland of desert, which includes ad hoc network,sensor, global positioning system(GPS) and system integration technology. The wireless network is a three-layer architecture and daisy chain topology network, which consists of control station, master robots and slave robots.Every three robots including one master robot and its two slave robots forms an ad hoc network. Master robots directly communicate with radio base station. Information will be sent to remote information center. Data sensing system including different kinds of sensors and desert robots is developed. A desert robot is designed and implemented as unmanned probing movable nodes and sensors' carrier. A new optical fiber sensor is exploited to measure vibration of sand in particular. The whole system, which is delivered to the testing field in hinterland of desert(25 km far from base station), has been proved efficient for data acquisition.展开更多
A quantum access network has been implemented by frequency division multiple access and time division multiple access, while code division multiple access is limited for its difficulty to realize the orthogonality of ...A quantum access network has been implemented by frequency division multiple access and time division multiple access, while code division multiple access is limited for its difficulty to realize the orthogonality of the code. Recently,the chaotic phase shifters were proposed to guarantee the orthogonality by different chaotic signals and spread the spectral content of the quantum states. In this letter, we propose to implement the code division multiple access quantum network by using chaotic phase shifters and synchronization. Due to the orthogonality of the different chaotic phase shifter, every pair of users can faithfully transmit quantum information through a common channel and have little crosstalk between different users. Meanwhile, the broadband spectra of chaotic signals efficiently help the quantum states to defend against channel loss and noise.展开更多
A fundamental requirement for any cellular system is the possibility for the device to request a connection setup, commonly referred to as random access procedure. In LTE （long term evolution） networks, the distribu...A fundamental requirement for any cellular system is the possibility for the device to request a connection setup, commonly referred to as random access procedure. In LTE （long term evolution） networks, the distribution of a limited number of radio resources among H2H （Human-to-Human） users and increasing number of MTC （Machine-Type-Communication） devices in M2M （Machine-to-Machine） communications is one of the main problems. An analytical model is conducted to compute the throughput for message 1 and message 2. This is done using a Markov chain model for the four messages signaling flow with buffering for message 4. This model is used in LTE 3GPP （Third-Generation Partnership Project） random access. The network performance will be enhanced by determining a dedicated arrival rate corresponding to maximum throughput of message 2 that will assist the network planner to optimize the network performance. In this paper, a deduced arrival rate less than 3.333 requests/ms will maximize network throughput.展开更多
Network coding is able to address output conflicts when fanout splitting is allowed for multicast switching.Hence,it successfully achieves a larger rate region than non-coding approaches in crossbar switches.However,n...Network coding is able to address output conflicts when fanout splitting is allowed for multicast switching.Hence,it successfully achieves a larger rate region than non-coding approaches in crossbar switches.However,network coding requires large coding buffers and a high computational cost on encoding and decoding.In this paper,we propose a novel Online Network Coding framework called Online NC for multicast switches,which is adaptive to constrained buffers.Moreover,it enjoys a much lower decoding complexity by a Vandermonde matrix based approach,as compared to conven-tional randomized network coding Our approach realizes online coding with one coding algo-rithm that synchronizes buffering and coding.Therefore,we significantly reduce requirements on buffer space,while also sustaining high throughputs.We confirm the superior advantages of our contributions using empirical studies.展开更多
The call admission control (CAC) optimizes the use of allocated channels against offered traffic maintaining the required quality of service (QoS). Provisioning QoS to user at cell-edge is a challenge where there is l...The call admission control (CAC) optimizes the use of allocated channels against offered traffic maintaining the required quality of service (QoS). Provisioning QoS to user at cell-edge is a challenge where there is limitation in cell resources due to inter-cell interference (ICI). Soft Frequency Reuse is ICI mitigation scheme that controls the distribution of resources between users. In this paper, the Impact of four CAC schemes (Cutoff Priority scheme (CP), Uniform Fractional Guard Channel (UFGC), Limited Fractional Guard Channel (LFGC), New Call Bounding (NCB) scheme) at cell-edge have investigated using queuing analysis in a comparative manner. The comparison is based on two criteria. The first criterion guarantees a particular level of service to already admitted users while trying to optimize the revenue obtained. The second criterion determines the minimum of number of radio resources that provides hard constraints in both of blocking and dropping probabilities. The four schemes are compared at different scenarios of new and handover call arrival rates.展开更多
Dropping probability of handoff calls and blocking probability of new calls are two important Quality of Service (QoS) measures for LTE-Advanced networks. Applying QoS for Cell edge users in soft frequency reuse schem...Dropping probability of handoff calls and blocking probability of new calls are two important Quality of Service (QoS) measures for LTE-Advanced networks. Applying QoS for Cell edge users in soft frequency reuse scheme in LTE system is a challenge as they already suffer from limited resources. Assigning some resources for handover calls may enhance dropping probability but this is in price of degradation in the blocking probability for new calls in cell-edge. Uniform Fractional Guard Channel (UFGC) is a call admission policy that provides QoS without reserving resources for handover calls. In this paper, the performance of Soft Frequency Reuse (SFR) in presence of Uniform Fractional Guard Channel (UFGC) will be investigated using queuing analysis. The mathematical model and performance metrics will be deduced in this assessment. The impact of UFGC will be evaluated in edge and core part separately. Then the optimal value for the parameter of UFGC will be obtained to minimize the blocking probability of new calls with the constraint on the upper bound on the dropping probability of handoff calls.展开更多
Object detection in occluded environments remains a core challenge in computer vision(CV),especially in domains such as autonomous driving and robotics.While Convolutional Neural Network(CNN)-based twodimensional(2D)a...Object detection in occluded environments remains a core challenge in computer vision(CV),especially in domains such as autonomous driving and robotics.While Convolutional Neural Network(CNN)-based twodimensional(2D)and three-dimensional(3D)object detection methods havemade significant progress,they often fall short under severe occlusion due to depth ambiguities in 2D imagery and the high cost and deployment limitations of 3D sensors such as Light Detection and Ranging(LiDAR).This paper presents a comparative review of recent 2D and 3D detection models,focusing on their occlusion-handling capabilities and the impact of sensor modalities such as stereo vision,Time-of-Flight(ToF)cameras,and LiDAR.In this context,we introduce FuDensityNet,our multimodal occlusion-aware detection framework that combines Red-Green-Blue(RGB)images and LiDAR data to enhance detection performance.As a forward-looking direction,we propose a monocular depth-estimation extension to FuDensityNet,aimed at replacing expensive 3D sensors with a more scalable CNN-based pipeline.Although this enhancement is not experimentally evaluated in this manuscript,we describe its conceptual design and potential for future implementation.展开更多
Responding to the stochasticity and uncertainty in the power height of distributed photovoltaic power generation.This paper presents a distributed photovoltaic ultra-short-term power forecasting method based on Variat...Responding to the stochasticity and uncertainty in the power height of distributed photovoltaic power generation.This paper presents a distributed photovoltaic ultra-short-term power forecasting method based on Variational Mode Decomposition(VMD)and Channel Attention Mechanism.First,Pearson’s correlation coefficient was utilized to filter out the meteorological factors that had a high impact on historical power.Second,the distributed PV power data were decomposed into a relatively smooth power series with different fluctuation patterns using variational modal decomposition(VMD).Finally,the reconstructed distributed PV power as well as other features are input into the combined CNN-SENet-BiLSTM model.In this model,the convolutional neural network(CNN)and channel attention mechanism dynamically adjust the weights while capturing the spatial features of the input data to improve the discriminative ability of key features.The extracted data is then fed into the bidirectional long short-term memory network(BiLSTM)to capture the time-series features,and the final output is the prediction result.The verification is conducted using a dataset from a distributed photovoltaic power station in the Northwest region of China.The results show that compared with other prediction methods,the method proposed in this paper has a higher prediction accuracy,which helps to improve the proportion of distributed PV access to the grid,and can guarantee the safe and stable operation of the power grid.展开更多
With the emergence of new attack techniques,traffic classifiers usually fail to maintain the expected performance in real-world network environments.In order to have sufficient generalizability to deal with unknown ma...With the emergence of new attack techniques,traffic classifiers usually fail to maintain the expected performance in real-world network environments.In order to have sufficient generalizability to deal with unknown malicious samples,they require a large number of new samples for retraining.Considering the cost of data collection and labeling,data augmentation is an ideal solution.We propose an optimized noise-based traffic data augmentation system,ONTDAS.The system uses a gradient-based searching algorithm and an improved Bayesian optimizer to obtain optimized noise.The noise is injected into the original samples for data augmentation.Then,an improved bagging algorithm is used to integrate all the base traffic classifiers trained on noised datasets.The experiments verify ONTDAS on 6 types of base classifiers and 4 publicly available datasets respectively.The results show that ONTDAS can effectively enhance the traffic classifiers’performance and significantly improve their generalizability on unknown malicious samples.The system can also alleviate dataset imbalance.Moreover,the performance of ONTDAS is significantly superior to the existing data augmentation methods mentioned.展开更多
Coupled-waveguide devices are essential in photonic integrated circuits for coupling,polarization handling,and mode manipulation.However,the performance of these devices usually suffers from high wavelength and struct...Coupled-waveguide devices are essential in photonic integrated circuits for coupling,polarization handling,and mode manipulation.However,the performance of these devices usually suffers from high wavelength and structure sensitivity,which makes it challenging to realize broadband and reliable on-chip optical functions.Recently,topological pumping of edge states has emerged as a promising solution for implementing robust optical couplings.In this paper,we propose and experimentally demonstrate broadband on-chip mode manipulation with very large fabrication tolerance based on the Rice–Mele modeled silicon waveguide arrays.The Thouless pumping mechanism is employed in the design to implement broadband and robust mode conversion and multiplexing.The experimental results prove that various mode-order conversions with low insertion losses and intermodal crosstalk can be achieved over a broad bandwidth of 80 nm ranging from 1500 to 1580 nm.Thanks to such a topological design,the device has a remarkable fabrication tolerance of±70 nm for the structural deviations in waveguide width and gap distance,which is,to the best of our knowledge,the highest among the coupled-waveguide mode-handling devices reported so far.As a proof-of-concept experiment,we cascade the topological mode-order converters to form a four-channel mode-division multiplexer and demonstrate the transmission of a 200-Gb/s 16-quadrature amplitude modulation signal for each mode channel,with the bit error rates below the 7%forward error correction threshold of 3.8×10^(-3).We reveal the possibility of developing new classes of broadband and fabrication-tolerant coupled-waveguide devices with topological photonic approaches,which may find applications in many fields,including optical interconnects,quantum communications,and optical computing.展开更多
Complex-valued double-sideband direct detection(DD)can reconstruct the optical field and achieve a high electrical spectral efficiency(ESE)comparable to that of a coherent homodyne receiver,and DD does not require a c...Complex-valued double-sideband direct detection(DD)can reconstruct the optical field and achieve a high electrical spectral efficiency(ESE)comparable to that of a coherent homodyne receiver,and DD does not require a costly local oscillator laser.However,a fundamental question remains if there is an optimal DD receiver structure with the simplest design to approach the performance of the coherent homodyne detection.This study derives the optimal DD receiver structure with an optimal transfer function to recover a quadrature amplitude modulation(QAM)signal with a near-zero guard band at the central frequency of the signal.We derive the theoretical ESE limit for various detection schemes by invoking Shannon’s formula.Our proposed scheme is closest to coherent homodyne detection in terms of the theoretical ESE limit.By leveraging a WaveShaper to construct the optimal transfer function,we conduct a proof-of-concept experiment to transmit a net 228.85-Gb/s 64-QAM signal over an 80-km single-mode fiber with a net ESE of 8.76 b/s/Hz.To the best of our knowledge,this study reports the highest net ESE per polarization per wavelength for DD transmission beyond 40-km single-mode fiber.For a comprehensive metric,denoted as 2ESE×Reach,we achieve the highest 2ESE×Reach per polarization per wavelength for DD transmission.展开更多
Inflammatory bowel disease(IBD),comprising Crohn’s disease and ulcerative colitis,represents the two predominant clinical entities within this spectrum of gastrointestinal disorders.Current evidence indicates that th...Inflammatory bowel disease(IBD),comprising Crohn’s disease and ulcerative colitis,represents the two predominant clinical entities within this spectrum of gastrointestinal disorders.Current evidence indicates that the etiology of IBD is multifactorial,involving a complex interplay between host genetic susceptibility and environmental determinants.In recent years,non-pharmacological strategies such as physical exercise and vagus nerve stimulation have gained increasing attention as adjunctive therapeutic approaches.Vagus nerve stimulation has emerged as a promising therapeutic modality,particularly in conditions characterized by autonomic dysfunction and diminished vagal tone.Conversely,vagotomy,by disrupting vagal control,abolishes parasympathetic reflexes and may potentiate inflammatory responses and exacerbate IBD symptomatology under stress conditions.Physical exercise has likewise been investigated as a non-pharmacological intervention in Crohn’s disease and ulcerative colitis.Although the precise mechanisms remain to be fully elucidated,accumulating evidence suggests that skeletal muscle contractions promote the secretion of myokines,with recognized anti-inflammatory properties.These myokines act on the intestinal microenvironment,conferring protection against malignant transformation and modulating the composition and function of the gut microbiota.In this review,we critically examine the interplay between physical exercise,vagus nerve stimulation,and vagotomy in the pathophysiology and management of IBD,with particular emphasis on their immunomodulatory and therapeutic potential.展开更多
Due to the indirect bandgap nature,the widely used silicon CMOS is very inefficient at light emitting.The integration of silicon lasers is deemed as the‘Mount Everest’for the full take-up of Si photonics.The major c...Due to the indirect bandgap nature,the widely used silicon CMOS is very inefficient at light emitting.The integration of silicon lasers is deemed as the‘Mount Everest’for the full take-up of Si photonics.The major challenge has been the materials dissimilarity caused impaired device performance.We present a brief overview of the recent advances of integratedⅢ-Ⅴlaser on Si.We will then focus on the heterogeneous direct/adhesive bonding enabling methods and associated light coupling structures.A selected review of recent representative novel heterogeneously integrated Si lasers for emerging applications like spectroscopy,sensing,metrology and microwave photonics will be presented,including DFB laser array,ultra-dense comb lasers and nanolasers.Finally,the challenges and opportunities of heterogeneous integration approach are discussed.展开更多
文摘Breast cancer is one of the major causes of deaths in women.However,the early diagnosis is important for screening and control the mortality rate.Thus for the diagnosis of breast cancer at the early stage,a computer-aided diagnosis system is highly required.Ultrasound is an important examination technique for breast cancer diagnosis due to its low cost.Recently,many learning-based techniques have been introduced to classify breast cancer using breast ultrasound imaging dataset(BUSI)datasets;however,the manual handling is not an easy process and time consuming.The authors propose an EfficientNet-integrated ResNet deep network and XAI-based framework for accurately classifying breast cancer(malignant and benign).In the initial step,data augmentation is performed to increase the number of training samples.For this purpose,three-pixel flip mathematical equations are introduced:horizontal,vertical,and 90°.Later,two pretrained deep learning models were employed,skipped some layers,and fine-tuned.Both fine-tuned models are later trained using a deep transfer learning process and extracted features from the deeper layer.Explainable artificial intelligence-based analysed the performance of trained models.After that,a new feature selection technique is proposed based on the cuckoo search algorithm called cuckoo search controlled standard error mean.This technique selects the best features and fuses using a new parallel zeropadding maximum correlated coefficient features.In the end,the selection algorithm is applied again to the fused feature vector and classified using machine learning algorithms.The experimental process of the proposed framework is conducted on a publicly available BUSI and obtained 98.4%and 98%accuracy in two different experiments.Comparing the proposed framework is also conducted with recent techniques and shows improved accuracy.In addition,the proposed framework was executed less than the original deep learning models.
基金This work was supported by the National Key R&D Program of China No.2019YFB1802800.
文摘In 6G era,service forms in which computing power acts as the core will be ubiquitous in the network.At the same time,the collaboration among edge computing,cloud computing and network is needed to support edge computing service with strong demand for computing power,so as to realize the optimization of resource utilization.Based on this,the article discusses the research background,key techniques and main application scenarios of computing power network.Through the demonstration,it can be concluded that the technical solution of computing power network can effectively meet the multi-level deployment and flexible scheduling needs of the future 6G business for computing,storage and network,and adapt to the integration needs of computing power and network in various scenarios,such as user oriented,government enterprise oriented,computing power open and so on.
基金supported by Tianshan Talent Training Project-Xinjiang Science and Technology Innovation Team Program(2023TSYCTD).
文摘With the increasing dimensionality of network traffic,extracting effective traffic features and improving the identification accuracy of different intrusion traffic have become critical in intrusion detection systems(IDS).However,both unsupervised and semisupervised anomalous traffic detection methods suffer from the drawback of ignoring potential correlations between features,resulting in an analysis that is not an optimal set.Therefore,in order to extract more representative traffic features as well as to improve the accuracy of traffic identification,this paper proposes a feature dimensionality reduction method combining principal component analysis and Hotelling’s T^(2) and a multilayer convolutional bidirectional long short-term memory(MSC_BiLSTM)classifier model for network traffic intrusion detection.This method reduces the parameters and redundancy of the model by feature extraction and extracts the dependent features between the data by a bidirectional long short-term memory(BiLSTM)network,which fully considers the influence between the before and after features.The network traffic is first characteristically downscaled by principal component analysis(PCA),and then the downscaled principal components are used as input to Hotelling’s T^(2) to compare the differences between groups.For datasets with outliers,Hotelling’s T^(2) can help identify the groups where the outliers are located and quantitatively measure the extent of the outliers.Finally,a multilayer convolutional neural network and a BiLSTM network are used to extract the spatial and temporal features of network traffic data.The empirical consequences exhibit that the suggested approach in this manuscript attains superior outcomes in precision,recall and F1-score juxtaposed with the prevailing techniques.The results show that the intrusion detection accuracy,precision,and F1-score of the proposed MSC_BiLSTM model for the CIC-IDS 2017 dataset are 98.71%,95.97%,and 90.22%.
文摘In this paper, we propose an optical burst network architecture supporting the ge- netic mesh topology. The intermediate node architecture of the mesh network can be the same with current wavelength switching Wave- length Division Multiplexing （WDM） net- works, and thus can reuse existing deployed infrastructure. We employ a novel Optical Time Slot Interchange （OTSI） at the source nodes for the first time to mitigate the burst conten- tion and to increase the bandwidth utilization. Time- and wavelength-domain reuse in the OTSI significantly saves optical components and red- uces blocking probability.
文摘To promote reliable and secure communications in the cognitive radio network,the automatic modulation classification algorithms have been mainly proposed to estimate a single modulation.In this paper,we address the classification of superimposed modulations dedicated to 5G multipleinput multiple-output(MIMO)two-way cognitive relay network in realistic channels modeled with Nakagami-m distribution.Our purpose consists of classifying pairs of users modulations from superimposed signals.To achieve this goal,we apply the higher-order statistics in conjunction with the Multi-BoostAB classifier.We use several efficiency metrics including the true positive(TP)rate,false positive(FP)rate,precision,recall,F-Measure and receiver operating characteristic(ROC)area in order to evaluate the performance of the proposed algorithm in terms of correct superimposed modulations classification.Computer simulations prove that our proposal allows obtaining a good probability of classification for ten superimposed modulations at a low signal-to-noise ratio,including the worst case(i.e.,m=0.5),where the fading distribution follows a one-sided Gaussian distribution.We also carry out a comparative study between our proposal usingMultiBoostAB classifier with the decision tree(J48)classifier.Simulation results show that the performance of MultiBoostAB on the superimposed modulations classifications outperforms the one of J48 classifier.In addition,we study the impact of the symbols number,path loss exponent and relay position on the performance of the proposed automatic classification superimposed modulations in terms of probability of correct classification.
基金supported by the Key R&D Program of Anhui Province in 2020 under Grant No.202004a05020078China Environment for Network Innovations(CENI)under Grant No.2016-000052-73-01-000515.
文摘As users’access to the network has evolved into the acquisition of mass contents instead of IP addresses,the IP network architecture based on end-to-end communication cannot meet users’needs.Therefore,the Information-Centric Networking(ICN)came into being.From a technical point of view,ICN is a promising future network architecture.Researching and customizing a reasonable pricing mechanism plays a positive role in promoting the deployment of ICN.The current research on ICN pricing mechanism is focused on paid content.Therefore,we study an ICN pricing model for free content,which uses game theory based on Nash equilibrium to analysis.In this work,advertisers are considered,and an advertiser model is established to describe the economic interaction between advertisers and ICN entities.This solution can formulate the best pricing strategy for all ICN entities and maximize the benefits of each entity.Our extensive analysis and numerical results show that the proposed pricing framework is significantly better than existing solutions when it comes to free content.
基金supported by the National Natural Science Foundation of China(No.62001045)Beijing Municipal Natural Science Foundation(No.4214059)+1 种基金Fund of State Key Laboratory of IPOC(BUPT)(No.IPOC2021ZT17)Fundamental Research Funds for the Central Universities(No.2022RC09).
文摘Inter-datacenter elastic optical networks(EON)need to provide the service for the requests of cloud computing that require not only connectivity and computing resources but also network survivability.In this paper,to realize joint allocation of computing and connectivity resources in survivable inter-datacenter EONs,a survivable routing,modulation level,spectrum,and computing resource allocation algorithm(SRMLSCRA)algorithm and three datacenter selection strategies,i.e.Computing Resource First(CRF),Shortest Path First(SPF)and Random Destination(RD),are proposed for different scenarios.Unicast and manycast are applied to the communication of computing requests,and the routing strategies are calculated respectively.Simulation results show that SRMLCRA-CRF can serve the largest amount of protected computing tasks,and the requested calculation blocking probability is reduced by 29.2%,28.3%and 30.5%compared with SRMLSCRA-SPF,SRMLSCRA-RD and the benchmark EPS-RMSA algorithms respectively.Therefore,it is more applicable to the networks with huge calculations.Besides,SRMLSCRA-SPF consumes the least spectrum,thereby exhibiting its suitability for scenarios where the amount of calculation is small and communication resources are scarce.The results demonstrate that the proposed methods realize the joint allocation of computing and connectivity resources,and could provide efficient protection for services under single-link failure and occupy less spectrum.
基金International S&T Cooperation Program of China(No.2011DFA11780)
文摘The deep understanding on sand and sand dunes scale can be useful to reveal the formation mechanism of the sandstorm for early sandstorm forecast. The current sandstorm observation methods are mainly based on conventional meteorological station and satellites remote sensing, which are difficult to acquire sand scale information. A wireless sensing network is implemented in the hinterland of desert, which includes ad hoc network,sensor, global positioning system(GPS) and system integration technology. The wireless network is a three-layer architecture and daisy chain topology network, which consists of control station, master robots and slave robots.Every three robots including one master robot and its two slave robots forms an ad hoc network. Master robots directly communicate with radio base station. Information will be sent to remote information center. Data sensing system including different kinds of sensors and desert robots is developed. A desert robot is designed and implemented as unmanned probing movable nodes and sensors' carrier. A new optical fiber sensor is exploited to measure vibration of sand in particular. The whole system, which is delivered to the testing field in hinterland of desert(25 km far from base station), has been proved efficient for data acquisition.
基金supported by the National Natural Science Foundation of China(Grant Nos.61475099 and 61102053)the Program of State Key Laboratory of Quantum Optics and Quantum Optics Devices(Grant No.KF201405)+1 种基金the Open Fund of IPOC(BUPT)(Grant No.IPOC2015B004)the Program of State Key Laboratory of Information Security(Grant No.2016-MS-05)
文摘A quantum access network has been implemented by frequency division multiple access and time division multiple access, while code division multiple access is limited for its difficulty to realize the orthogonality of the code. Recently,the chaotic phase shifters were proposed to guarantee the orthogonality by different chaotic signals and spread the spectral content of the quantum states. In this letter, we propose to implement the code division multiple access quantum network by using chaotic phase shifters and synchronization. Due to the orthogonality of the different chaotic phase shifter, every pair of users can faithfully transmit quantum information through a common channel and have little crosstalk between different users. Meanwhile, the broadband spectra of chaotic signals efficiently help the quantum states to defend against channel loss and noise.
文摘A fundamental requirement for any cellular system is the possibility for the device to request a connection setup, commonly referred to as random access procedure. In LTE （long term evolution） networks, the distribution of a limited number of radio resources among H2H （Human-to-Human） users and increasing number of MTC （Machine-Type-Communication） devices in M2M （Machine-to-Machine） communications is one of the main problems. An analytical model is conducted to compute the throughput for message 1 and message 2. This is done using a Markov chain model for the four messages signaling flow with buffering for message 4. This model is used in LTE 3GPP （Third-Generation Partnership Project） random access. The network performance will be enhanced by determining a dedicated arrival rate corresponding to maximum throughput of message 2 that will assist the network planner to optimize the network performance. In this paper, a deduced arrival rate less than 3.333 requests/ms will maximize network throughput.
基金Supported by the National 863 Projects of China(2009AA01Z205)the Fund of National Laboratory(P080010)+2 种基金the Natural Science Foundation of China(60872010,60972016)the Program for New Century Excellent Talents in University (NCET070339)the Funds for Distinguished Young Scientists of Hubei,China(2009 CDA150)
文摘Network coding is able to address output conflicts when fanout splitting is allowed for multicast switching.Hence,it successfully achieves a larger rate region than non-coding approaches in crossbar switches.However,network coding requires large coding buffers and a high computational cost on encoding and decoding.In this paper,we propose a novel Online Network Coding framework called Online NC for multicast switches,which is adaptive to constrained buffers.Moreover,it enjoys a much lower decoding complexity by a Vandermonde matrix based approach,as compared to conven-tional randomized network coding Our approach realizes online coding with one coding algo-rithm that synchronizes buffering and coding.Therefore,we significantly reduce requirements on buffer space,while also sustaining high throughputs.We confirm the superior advantages of our contributions using empirical studies.
文摘The call admission control (CAC) optimizes the use of allocated channels against offered traffic maintaining the required quality of service (QoS). Provisioning QoS to user at cell-edge is a challenge where there is limitation in cell resources due to inter-cell interference (ICI). Soft Frequency Reuse is ICI mitigation scheme that controls the distribution of resources between users. In this paper, the Impact of four CAC schemes (Cutoff Priority scheme (CP), Uniform Fractional Guard Channel (UFGC), Limited Fractional Guard Channel (LFGC), New Call Bounding (NCB) scheme) at cell-edge have investigated using queuing analysis in a comparative manner. The comparison is based on two criteria. The first criterion guarantees a particular level of service to already admitted users while trying to optimize the revenue obtained. The second criterion determines the minimum of number of radio resources that provides hard constraints in both of blocking and dropping probabilities. The four schemes are compared at different scenarios of new and handover call arrival rates.
文摘Dropping probability of handoff calls and blocking probability of new calls are two important Quality of Service (QoS) measures for LTE-Advanced networks. Applying QoS for Cell edge users in soft frequency reuse scheme in LTE system is a challenge as they already suffer from limited resources. Assigning some resources for handover calls may enhance dropping probability but this is in price of degradation in the blocking probability for new calls in cell-edge. Uniform Fractional Guard Channel (UFGC) is a call admission policy that provides QoS without reserving resources for handover calls. In this paper, the performance of Soft Frequency Reuse (SFR) in presence of Uniform Fractional Guard Channel (UFGC) will be investigated using queuing analysis. The mathematical model and performance metrics will be deduced in this assessment. The impact of UFGC will be evaluated in edge and core part separately. Then the optimal value for the parameter of UFGC will be obtained to minimize the blocking probability of new calls with the constraint on the upper bound on the dropping probability of handoff calls.
文摘Object detection in occluded environments remains a core challenge in computer vision(CV),especially in domains such as autonomous driving and robotics.While Convolutional Neural Network(CNN)-based twodimensional(2D)and three-dimensional(3D)object detection methods havemade significant progress,they often fall short under severe occlusion due to depth ambiguities in 2D imagery and the high cost and deployment limitations of 3D sensors such as Light Detection and Ranging(LiDAR).This paper presents a comparative review of recent 2D and 3D detection models,focusing on their occlusion-handling capabilities and the impact of sensor modalities such as stereo vision,Time-of-Flight(ToF)cameras,and LiDAR.In this context,we introduce FuDensityNet,our multimodal occlusion-aware detection framework that combines Red-Green-Blue(RGB)images and LiDAR data to enhance detection performance.As a forward-looking direction,we propose a monocular depth-estimation extension to FuDensityNet,aimed at replacing expensive 3D sensors with a more scalable CNN-based pipeline.Although this enhancement is not experimentally evaluated in this manuscript,we describe its conceptual design and potential for future implementation.
基金supported by the Inner Mongolia Power Company 2024 Staff Innovation Studio Innovation Project“Research on Cluster Output Prediction and Group Control Technology for County-Wide Distributed Photovoltaic Construction”.
文摘Responding to the stochasticity and uncertainty in the power height of distributed photovoltaic power generation.This paper presents a distributed photovoltaic ultra-short-term power forecasting method based on Variational Mode Decomposition(VMD)and Channel Attention Mechanism.First,Pearson’s correlation coefficient was utilized to filter out the meteorological factors that had a high impact on historical power.Second,the distributed PV power data were decomposed into a relatively smooth power series with different fluctuation patterns using variational modal decomposition(VMD).Finally,the reconstructed distributed PV power as well as other features are input into the combined CNN-SENet-BiLSTM model.In this model,the convolutional neural network(CNN)and channel attention mechanism dynamically adjust the weights while capturing the spatial features of the input data to improve the discriminative ability of key features.The extracted data is then fed into the bidirectional long short-term memory network(BiLSTM)to capture the time-series features,and the final output is the prediction result.The verification is conducted using a dataset from a distributed photovoltaic power station in the Northwest region of China.The results show that compared with other prediction methods,the method proposed in this paper has a higher prediction accuracy,which helps to improve the proportion of distributed PV access to the grid,and can guarantee the safe and stable operation of the power grid.
基金supported in part by the National Key Research and Development Program of China(No.2022YFB4500800)the National Science Foundation of China(No.42071431).
文摘With the emergence of new attack techniques,traffic classifiers usually fail to maintain the expected performance in real-world network environments.In order to have sufficient generalizability to deal with unknown malicious samples,they require a large number of new samples for retraining.Considering the cost of data collection and labeling,data augmentation is an ideal solution.We propose an optimized noise-based traffic data augmentation system,ONTDAS.The system uses a gradient-based searching algorithm and an improved Bayesian optimizer to obtain optimized noise.The noise is injected into the original samples for data augmentation.Then,an improved bagging algorithm is used to integrate all the base traffic classifiers trained on noised datasets.The experiments verify ONTDAS on 6 types of base classifiers and 4 publicly available datasets respectively.The results show that ONTDAS can effectively enhance the traffic classifiers’performance and significantly improve their generalizability on unknown malicious samples.The system can also alleviate dataset imbalance.Moreover,the performance of ONTDAS is significantly superior to the existing data augmentation methods mentioned.
基金supported by the National Key R&D Program of China(Grant No.2023YFB2905503)the National Natural Science Foundation of China(Grant Nos.62035016,62105200,62475146,and 62341508).
文摘Coupled-waveguide devices are essential in photonic integrated circuits for coupling,polarization handling,and mode manipulation.However,the performance of these devices usually suffers from high wavelength and structure sensitivity,which makes it challenging to realize broadband and reliable on-chip optical functions.Recently,topological pumping of edge states has emerged as a promising solution for implementing robust optical couplings.In this paper,we propose and experimentally demonstrate broadband on-chip mode manipulation with very large fabrication tolerance based on the Rice–Mele modeled silicon waveguide arrays.The Thouless pumping mechanism is employed in the design to implement broadband and robust mode conversion and multiplexing.The experimental results prove that various mode-order conversions with low insertion losses and intermodal crosstalk can be achieved over a broad bandwidth of 80 nm ranging from 1500 to 1580 nm.Thanks to such a topological design,the device has a remarkable fabrication tolerance of±70 nm for the structural deviations in waveguide width and gap distance,which is,to the best of our knowledge,the highest among the coupled-waveguide mode-handling devices reported so far.As a proof-of-concept experiment,we cascade the topological mode-order converters to form a four-channel mode-division multiplexer and demonstrate the transmission of a 200-Gb/s 16-quadrature amplitude modulation signal for each mode channel,with the bit error rates below the 7%forward error correction threshold of 3.8×10^(-3).We reveal the possibility of developing new classes of broadband and fabrication-tolerant coupled-waveguide devices with topological photonic approaches,which may find applications in many fields,including optical interconnects,quantum communications,and optical computing.
基金supported by the National Natural Science Foundation of China(62341508).
文摘Complex-valued double-sideband direct detection(DD)can reconstruct the optical field and achieve a high electrical spectral efficiency(ESE)comparable to that of a coherent homodyne receiver,and DD does not require a costly local oscillator laser.However,a fundamental question remains if there is an optimal DD receiver structure with the simplest design to approach the performance of the coherent homodyne detection.This study derives the optimal DD receiver structure with an optimal transfer function to recover a quadrature amplitude modulation(QAM)signal with a near-zero guard band at the central frequency of the signal.We derive the theoretical ESE limit for various detection schemes by invoking Shannon’s formula.Our proposed scheme is closest to coherent homodyne detection in terms of the theoretical ESE limit.By leveraging a WaveShaper to construct the optimal transfer function,we conduct a proof-of-concept experiment to transmit a net 228.85-Gb/s 64-QAM signal over an 80-km single-mode fiber with a net ESE of 8.76 b/s/Hz.To the best of our knowledge,this study reports the highest net ESE per polarization per wavelength for DD transmission beyond 40-km single-mode fiber.For a comprehensive metric,denoted as 2ESE×Reach,we achieve the highest 2ESE×Reach per polarization per wavelength for DD transmission.
文摘Inflammatory bowel disease(IBD),comprising Crohn’s disease and ulcerative colitis,represents the two predominant clinical entities within this spectrum of gastrointestinal disorders.Current evidence indicates that the etiology of IBD is multifactorial,involving a complex interplay between host genetic susceptibility and environmental determinants.In recent years,non-pharmacological strategies such as physical exercise and vagus nerve stimulation have gained increasing attention as adjunctive therapeutic approaches.Vagus nerve stimulation has emerged as a promising therapeutic modality,particularly in conditions characterized by autonomic dysfunction and diminished vagal tone.Conversely,vagotomy,by disrupting vagal control,abolishes parasympathetic reflexes and may potentiate inflammatory responses and exacerbate IBD symptomatology under stress conditions.Physical exercise has likewise been investigated as a non-pharmacological intervention in Crohn’s disease and ulcerative colitis.Although the precise mechanisms remain to be fully elucidated,accumulating evidence suggests that skeletal muscle contractions promote the secretion of myokines,with recognized anti-inflammatory properties.These myokines act on the intestinal microenvironment,conferring protection against malignant transformation and modulating the composition and function of the gut microbiota.In this review,we critically examine the interplay between physical exercise,vagus nerve stimulation,and vagotomy in the pathophysiology and management of IBD,with particular emphasis on their immunomodulatory and therapeutic potential.
基金supported by Natural Science Foundation of China (NSFC) under Grant 61805137Natural Science Foundation of Shanghai under Grant 19ZR1475400+1 种基金Shanghai Sailing Program under Grant 18YF1411900the Open Project Program of Wuhan National Laboratory for Optoelectronics No. 2018WNLOKF012
文摘Due to the indirect bandgap nature,the widely used silicon CMOS is very inefficient at light emitting.The integration of silicon lasers is deemed as the‘Mount Everest’for the full take-up of Si photonics.The major challenge has been the materials dissimilarity caused impaired device performance.We present a brief overview of the recent advances of integratedⅢ-Ⅴlaser on Si.We will then focus on the heterogeneous direct/adhesive bonding enabling methods and associated light coupling structures.A selected review of recent representative novel heterogeneously integrated Si lasers for emerging applications like spectroscopy,sensing,metrology and microwave photonics will be presented,including DFB laser array,ultra-dense comb lasers and nanolasers.Finally,the challenges and opportunities of heterogeneous integration approach are discussed.
