Scheme Based on Multi-Level Patch Attention and Lesion Localization for Diabetic Retinopathy Grading

Early screening of diabetes retinopathy(DR)plays an important role in preventing irreversible blindness.Existing research has failed to fully explore effective DR lesion information in fundus maps.Besides,traditional attention schemes have not considered the impact of lesion type differences on grading,resulting in unreasonable extraction of important lesion features.Therefore,this paper proposes a DR diagnosis scheme that integrates a multi-level patch attention generator(MPAG)and a lesion localization module(LLM).Firstly,MPAGis used to predict patches of different sizes and generate a weighted attention map based on the prediction score and the types of lesions contained in the patches,fully considering the impact of lesion type differences on grading,solving the problem that the attention maps of lesions cannot be further refined and then adapted to the final DR diagnosis task.Secondly,the LLM generates a global attention map based on localization.Finally,the weighted attention map and global attention map are weighted with the fundus map to fully explore effective DR lesion information and increase the attention of the classification network to lesion details.This paper demonstrates the effectiveness of the proposed method through extensive experiments on the public DDR dataset,obtaining an accuracy of 0.8064.

Deep neural network based on multi-level wavelet and attention for structured illumination microscopy

Structured illumination microscopy(SIM)is a popular and powerful super-resolution(SR)technique in biomedical research.However,the conventional reconstruction algorithm for SIM heavily relies on the accurate prior knowledge of illumination patterns and signal-to-noise ratio(SNR)of raw images.To obtain high-quality SR images,several raw images need to be captured under high fluorescence level,which further restricts SIM’s temporal resolution and its applications.Deep learning(DL)is a data-driven technology that has been used to expand the limits of optical microscopy.In this study,we propose a deep neural network based on multi-level wavelet and attention mechanism(MWAM)for SIM.Our results show that the MWAM network can extract high-frequency information contained in SIM raw images and accurately integrate it into the output image,resulting in superior SR images compared to those generated using wide-field images as input data.We also demonstrate that the number of SIM raw images can be reduced to three,with one image in each illumination orientation,to achieve the optimal tradeoff between temporal and spatial resolution.Furthermore,our MWAM network exhibits superior reconstruction ability on low-SNR images compared to conventional SIM algorithms.We have also analyzed the adaptability of this network on other biological samples and successfully applied the pretrained model to other SIM systems.

FPGA based hardware platform for trapped-ion-based multi-level quantum systems

We report a design and implementation of a field-programmable-gate-arrays(FPGA)based hardware platform,which is used to realize control and signal readout of trapped-ion-based multi-level quantum systems.This platform integrates a four-channel 2.8 Gsps@14 bits arbitrary waveform generator,a 16-channel 1 Gsps@14 bits direct-digital-synthesisbased radio-frequency generator,a 16-channel 8 ns resolution pulse generator,a 10-channel 16 bits digital-to-analogconverter module,and a 2-channel proportion integration differentiation controller.The hardware platform can be applied in the trapped-ion-based multi-level quantum systems,enabling quantum control of multi-level quantum system and highdimensional quantum simulation.The platform is scalable and more channels for control and signal readout can be implemented by utilizing more parallel duplications of the hardware.The hardware platform also has a bright future to be applied in scaled trapped-ion-based quantum systems.

Deep reinforcement learning based multi-level dynamic reconfiguration for urban distribution network:a cloud-edge collaboration architecture

With the construction of the power Internet of Things(IoT),communication between smart devices in urban distribution networks has been gradually moving towards high speed,high compatibility,and low latency,which provides reliable support for reconfiguration optimization in urban distribution networks.Thus,this study proposed a deep reinforcement learning based multi-level dynamic reconfiguration method for urban distribution networks in a cloud-edge collaboration architecture to obtain a real-time optimal multi-level dynamic reconfiguration solution.First,the multi-level dynamic reconfiguration method was discussed,which included feeder-,transformer-,and substation-levels.Subsequently,the multi-agent system was combined with the cloud-edge collaboration architecture to build a deep reinforcement learning model for multi-level dynamic reconfiguration in an urban distribution network.The cloud-edge collaboration architecture can effectively support the multi-agent system to conduct“centralized training and decentralized execution”operation modes and improve the learning efficiency of the model.Thereafter,for a multi-agent system,this study adopted a combination of offline and online learning to endow the model with the ability to realize automatic optimization and updation of the strategy.In the offline learning phase,a Q-learning-based multi-agent conservative Q-learning(MACQL)algorithm was proposed to stabilize the learning results and reduce the risk of the next online learning phase.In the online learning phase,a multi-agent deep deterministic policy gradient(MADDPG)algorithm based on policy gradients was proposed to explore the action space and update the experience pool.Finally,the effectiveness of the proposed method was verified through a simulation analysis of a real-world 445-node system.

Neighborhood Effects and Political Trust: A Multi-level Analysis of Chinese Rural-to-Urban Migrants’ Trust in County Government

Massive rural-to-urban migration in China is consequential for political trust: rural-to-urban migrants have been found to hold lower levels of trust in local government than their rural peers who choose to stay in the countryside (mean 4.92 and 6.34 out of 10, respectively, p < 0.001). This article explores why migrants have a certain level of political trust in their county-level government. Using data of rural-to-urban migrants from the China Family Panel Survey, this study performs a hierarchical linear modeling (HLM) to unpack the multi-level explanatory factors of rural-to-urban migrants’ political trust. Findings show that the individual-level socio-economic characteristics and perceptions of government performance (Level-1), the neighborhood-level characteristics-the physical and social status and environment of neighborhoods (Level-2), and the objective macroeconomic performance of county-level government (Level-3), work together to explain migrants’ trust levels. These results suggest that considering the effects of neighborhood-level factors on rural-to-urban migrants’ political trust merits policy and public management attention in rapidly urbanizing countries.

Pixelated non-volatile programmable photonic integrated circuits with 20-level intermediate states

Multi-level programmable photonic integrated circuits(PICs)and optical metasurfaces have gained widespread attention in many fields,such as neuromorphic photonics,opticalcommunications,and quantum information.In this paper,we propose pixelated programmable Si_(3)N_(4)PICs with record-high 20-level intermediate states at 785 nm wavelength.Such flexibility in phase or amplitude modulation is achieved by a programmable Sb_(2)S_(3)matrix,the footprint of whose elements can be as small as 1.2μm,limited only by the optical diffraction limit of anin-house developed pulsed laser writing system.We believe our work lays the foundation for laser-writing ultra-high-level(20 levels and even more)programmable photonic systems and metasurfaces based on phase change materials,which could catalyze diverse applications such as programmable neuromorphic photonics,biosensing,optical computing,photonic quantum computing,and reconfigurable metasurfaces.

BC-BLPM:A Multi-Level Security Access Control Model Based on Blockchain Technology

Traditional multi-level security(MLS)systems have the defect of centralizing authorized facilities,which is difficult to meet the security requirements of modern distributed peer-to-peer network architecture.Blockchain is widely used in the field of access control with its decentralization,traceability and non-defective modification.Combining the blockchain technology and the Bell-LaPadula model,we propose a new access control model,named BCBLPM,for MLS environment.The“multi-chain”blockchain architecture is used for dividing resources into isolated access domains,providing a fine-grained data protection mechanism.The access control policies are implemented by smart contracts deployed in each access domain,so that the side chains of different access domains storage access records from outside and maintain the integrity of the records.Finally,we implement the BC-BLPM prototype system using the Hyperledger Fabric.The experimental and analytical results show that the model can adapt well to the needs of multi-level security environment,and it has the feasibility of application in actual scenarios.

An effective multi-level algorithm based on ant colony optimization for graph bipartitioning

Partitioning is a fundamental problem with applications to many areas including data mining, parellel processing and Very-large-scale integration （VLSI） design. An effective multi-level algorithm for bisecting graph is proposed. During its coarsening phase, an improved matching approach based on the global information of the graph core is developed with its guidance function. During the refinement phase, the vertex gain is exploited as ant＇s heuristic information and a positive feedback method based on pheromone trails is used to find the global approximate bipartitioning. It is implemented with American National Standards Institute （ANSI） C and compared to MeTiS. The experimental evaluation shows that it performs well and produces encouraging solutions on 18 different graphs benchmarks.

Fatigue Properties of RPC under Cyclic Loads of Single-stage and Multi-level Amplitude

Fatigue properties of Reactive Powder Concrete （RPC） under axial compression of single-stage and multi-level amplitude in cycles were studied. The tests reveal the fatigue life, the strain and residual life of the RPC samples. Through the analysis of the test results under cyclic loads of single amplitude, the S-N curve of RPC and the evolution rule of macro-damage of RPC were presented, which can be divided into latency stage, stable development stage and instability development stage according to the evolution pattern of the fatigue crack. Accordingly, the development of longitudinal deformation presents the similar three-stage-model, and the proportion of each stage is 15%, 75%, and 10%. According to test results, the fatigue strength reduction factor is 0.564. We brought forward an empirical formula to predict the life of RPC via total longitudinal strain and got the evolving rule for the residual strength of the RPC. The analysis of the test results under cyclic loads of multi-level amplitude shows that the strain under this loading pattern experiences three stages. The characteristic value for the residual strain was obtained. The irreversible damage and non-linear evolution of RPC was described by the development of the residual plastic strain.

Design of Irregular QC-LDPC Code Based Multi-Level Coded Modulation Scheme for High Speed Optical Communication Systems

In this paper, we focus on the design of irregular QC-LDPC code based multi-level coded modulation(MLCM) scheme by jointly optimizing the component code rate and the degree distribution of the irregular QC-LDPC component code. Firstly, the sub-channel capacities of MLCM systems is analyzed and discussed, based on which the optimal component code rate can be obtained. Secondly, an extrinsic information transfer chart based two-stage searching algorithm is proposed to find the good irregular QC-LDPC code ensembles with optimal component code rates for their corresponding sub-channels. Finally, by constructing the irregular QC-LDPC component codes from the designed ensembles with the aim of possibly enlarging the girth and reducing the number of the shortest cycles, the designed irregular QC-LDPC code based 16QAM and 64QAM MLCM systems can achieve 0.4 dB and 1.2 dB net coding gain, respectively, compared with the recently proposed regular QC-LDPC code based 16QAM and 64QAM MLCM systems.

A Parameterization of Cooling Rate Calculation under the Non-LTE Condition: Multi-Level Model

Calculations of cooling rate by CO2 15 μm band in the earth's upper mesosphere and lower thermosphere be-come very difficult because of the non-LTE. This is primarily due to the nonlinear vibration-vibrational (VV) transition processes between CO, molecules in different states. This paper suggests that the non-LTE source function be parameterized as a linear combination of two limiting source functions. One limiting source function neglects the VV transitions while the other limiting source function assumes VV transitions being dominant. These two limiting source functions can be derived by linear models. The parameterization schemes proposed here can be applied to the general circulation models including those non-LTE regions.

A new tracking error detection method using amplitude difference detection for signal waveform modulation multi-level discs

The sub-land/sub-pit affects the characteristic of the tracking error signal which is generated by the conventional differential phase detection （DPD） method in the signal waveform modulation multi-level （SWML） read-only disc. To solve this problem, this paper proposes a new tracking error detection method using amplitude difference. Based on the diffraction theory, the amplitude difference is proportional to the tracking error and is feasible to be used for obtaining the off-track information. The experimental system of the amplitude difference detection method is developed. The experimental results show that the tracking error signal derived from the new method has better performance in uniformity and signal-to-noise ratio than that derived from the conventional DPD method in the SWML read-only disc.

Improved Fibroblast Adhesion and Proliferation by Controlling Multi-level Structure of Polycaprolactone Microfiber

Improving wound healing efficiency is a key issue for high performance dressings.The surface topology of fibers in wound dressings plays an important role in regulating cell behaviors during the regeneration.Herein,a polycaprolactone(PCL)scaffold with a shish-kebab structure was prepared by electrospinning and solution-induced crystallization.L929 cells were used to investigate the behavior of fibroblasts on the multi-level microfiber.The results showed that the shish-kebab fiber-based scaffold enhanced the cell proliferation when compared with the normal fiber and the fiber with a porous structure.Protein absorption,cell adhesive force,and cell modulus also increased by the shish-kebab fiber.The shish-kebab fiber-based scaffold with improved fibroblast-regulation ability can be applied in rapid wound healing.

A Multi-Level Threshold Method for Edge Detection and Segmentation Based on Entropy

The essential tool in image processing,computer vision and machine vision is edge detection,especially in the fields of feature extraction and feature detection.Entropy is a basic area in information theory.The entropy,in image processing field has a role associated with image settings.As an initial step in image processing,the entropy is always used the image’s segmentation to determine the regions of image which is used to separate the background and objects in image.Image segmentation known as the process which divides the image into multiple regions or sets of pixels.Many applications have been development to enhance the image processing.This paper utilizes the Shannon entropy to achieve edge detection process and segmentation of the image.It introduces a new method of edge detection for 2-D histogram and Shannon entropy based on multilevel threshold.The method utilizes the gray value and the average gray value of the pixels to achieve the two dimensional histogram.The current method has apriority in comparison to some upper classical methods.The experimental results exhibited that the proposed method could capture a moderate quality and execution time better than other comparative methods,particularly in the largest images size.The proposed method offers good results when applied with images of different sizes from the civilization of ancient Egyptians.

Fabrication of multi-level 3-dimension microstructures by phase inversion process

One process based on phase inversion of fillers in microstructures for the fabrication of multi-level three-dimensional(3-D) microstructures is described using SU-8, a kind of epoxy photoresist, as the model constructing materials. This process is depicted by use of the routine photolithography technique to construct the top layer of 3-D microstructures on the bottom layer of 3-D microstructures layer by layer. This process makes it possible to fabricate multi-level 3-D microstructures with connectors at desired locations, and to seal long span microstructures(e.g. very shallow channels with depth less than 50 μm and width more than 300 μm) without blockage. In addition, this process can provide a sealing layer by the solidification of a liquid polymer layer, which can be as strong as the bulk constructing materials for microstructures due to a complete contact and cross-linking between the sealing layer and the patterned layers. The hydrodynamic testing indicates that this kind of sealing and interconnection can endure a static pressure of more than 10 MPa overnight and a hydrodynamic pressure drop of about 5.3 MPa for more than 8 hours by pumping the tetrahydrofuran solution through a 60 μm wide micro-channels.

Method of multi-level recursive and application to nonlinear dynamic deformation forecasting

The time-dependence bilinear mixed-regression deformation model and time-dependence bilinear dynamic system deformation model are established for deformation observation series. According to the multi- level recursive method, the time-dependence parameters are first traced and predicted, and then the dynamic system states. Due to the method considering time-dependence of deformation and having stronger adaptability to time-dependence system, it can improve forecast’s precision. It is very effective for data processing of nonlinear dynamic deformation monitoring to make multi-step forecasting.

Neural Network Based Multi-level Fuzzy Evaluation Model for Mechanical Kinematic Scheme

To implement a quantificational evaluation for mechanical kinematic scheme more effectively,a multi-level and multi-objective evaluation model is presented using neural network and fuzzy theory. Firstly,the structure of evaluation model is constructed according to evaluation indicator system. Then evaluation samples are generated and provided to train this model. Thus it can reflect the relation between attributive value and evaluation result,as well as the weight of evaluation indicator. Once evaluation indicators of each candidate are fuzzily quantified and fed into the trained network model,the corresponding evaluation result is outputted and the best alternative can be selected. Under this model,expert knowledge can be effectively acquired and expressed,and the quantificational evaluation can be implemented for kinematic scheme with multi-level evaluation indicator system. Several key problems on this model are discussed and an illustration has demonstrated that this model is feasible and can be regarded as a new idea for solving kinematic scheme evaluation.

Multi-level Flocculation Structures of Fresh Cement Paste by Confocal Laser Scanning Microscope

Under saturation dosage of all kinds of SP, the free water amount was examined by centrifuge. The distribution of solution and flocculation microstructures in fresh cement paste was observed in three- dimensional space by confocal laser scanning microscope（CLSM）. Results indicate that SP can increase the free water amount by destroying the flocculated cement particle structure and different free water amount is released by different kinds of SP. The changes of the size of flocculation structures and the dispersion of solution were obviously detected with confocal laser scanning microscope： the size of flocculation structures was smaller and more dispersed in fresh cement paste with polycarboxylate superplasticizer, but the size of flocculation structures was bigger and cannot be dispersed uniformly in fresh cement paste with others SP. The multi- level flocculation structures theoretical model of fresh cement paste was then set up. The theory indicates that different kinds of SP with different dispersion strength will open the flocculation structures at different levels, which in turn present different water reducing rate.

Multi-Level Feature-Based Ensemble Model for Target-Related Stance Detection

Stance detection is the task of attitude identification toward a standpoint.Previous work of stance detection has focused on feature extraction but ignored the fact that irrelevant features exist as noise during higher-level abstracting.Moreover,because the target is not always mentioned in the text,most methods have ignored target information.In order to solve these problems,we propose a neural network ensemble method that combines the timing dependence bases on long short-term memory(LSTM)and the excellent extracting performance of convolutional neural networks(CNNs).The method can obtain multi-level features that consider both local and global features.We also introduce attention mechanisms to magnify target information-related features.Furthermore,we employ sparse coding to remove noise to obtain characteristic features.Performance was improved by using sparse coding on the basis of attention employment and feature extraction.We evaluate our approach on the SemEval-2016Task 6-A public dataset,achieving a performance that exceeds the benchmark and those of participating teams.

Equal Switching Distribution Method for Multi-Level Cascaded Inverters

The paper proposes a new method of equal switching distribution that can be applied to cascaded multi-level inverters. This method is based on the fact that in the cascaded multilevel inverters, the output phase voltage is the sum of voltage waveforms produced by all cascaded cells. By periodically exchanging cells’ voltage waveforms, the proposed method ensures equal average switchings distribution between all cascaded cells. This method is applied to the 13-level inverter, which consists of three cascaded 5-level H-bridge cells per phase. However, the proposed method can be extended to any desired number of voltage levels and applied to any type of cascaded multi-level inverter. Extensive simulation results of the tested 13-level inverter with the equal switching distribution are presented. Moreover, the proposed method is compared to the standard control approaches and its advantages are shown.