SSD Real-Time Illegal Parking Detection Based on Contextual Information Transmission

With the improvement of the national economic level,the number of vehicles is still increasing year by year.According to the statistics of National Bureau of Statics,the number is approximately up to 327 million in China by the end of 2018,which makes urban traffic pressure continues to rise so that the negative impact of urban traffic order is growing.Illegal parking-the common problem in the field of transportation security is urgent to be solved and traditional methods to address it are mainly based on ground loop and manual supervision,which may miss detection and cost much manpower.Due to the rapidly developing deep learning sweeping the world in recent years,object detection methods relying on background segmentation cannot meet the requirements of complex and various scenes on speed and precision.Thus,an improved Single Shot MultiBox Detector(SSD)based on deep learning is proposed in our study,we introduce attention mechanism by spatial transformer module which gives neural networks the ability to actively spatially transform feature maps and add contextual information transmission in specified layer.Finally,we found out the best connection layer in the detection model by repeated experiments especially for small objects and increased the precision by 1.5%than the baseline SSD without extra training cost.Meanwhile,we designed an illegal parking vehicle detection method by the improved SSD,reaching a high precision up to 97.3%and achieving a speed of 40FPS,superior to most of vehicle detection methods,will make contributions to relieving the negative impact of illegal parking.

A Blockchain-Based Framework for Secure Storage and Sharing of Resumes

In response to problems in the centralized storage of personal resumes on third-party recruitment platforms,such as inadequate privacy protection,inability of individuals to accurately authorize downloads,and inability to determine who downloaded the resume and when,this study proposes a blockchain-based framework for secure storage and sharing of resumes.Users can employ an authorized access mechanism to protect their privacy rights.The proposed framework uses smart contracts,interplanetary file system,symmetric encryption,and digital signatures to protect,verify,and share resumes.Encryption keys are split and stored in multiple depositories through secret-sharing technology to improve the security of these keys.Corresponding key escrow incentives are implemented using smart contracts to automatically verify the correctness of keys and encourage the active participation of honest key escrow parties.This framework combines blockchain and searchable symmetric encryption technology to realize multikeyword search using inverted indexing and Bloom filters and verify search results on the chain.Escrow search service fees are charged through contracts.Only after the search results are verified can the search service provider obtain the search fee,thus ensuring fair and efficient search for encrypted resumes.The framework is decentralized,secure,and tamper-evident,and achieves controlled sharing while protecting personal privacy and information security.

Excellent Practical Byzantine Fault Tolerance

With the rapid development of blockchain technology,more and more people are paying attention to the consensus mechanism of blockchain.Practical Byzantine Fault Tolerance(PBFT),as the first efficient consensus algorithm solving the Byzantine Generals Problem,plays an important role.But PBFT also has its problems.First,it runs in a completely closed environment,and any node can't join or exit without rebooting the system.Second,the communication complexity in the network is as high as O(n2),which makes the algorithm only applicable to small-scale networks.For these problems,this paper proposes an Optimized consensus algorithm,Excellent Practical Byzantine Fault Tolerance(EPBFT),in which nodes can dynamically participate in the network by combining a view change protocol with a node's add or quit request.Besides,in each round of consensus,the algorithm will randomly select a coordination node.Through the cooperation of the primary and the coordination node,we reduce the network communication complexity to O(n).Besides,we have added a reputation credit mechanism and a wrong node removal protocol to the algorithm for clearing the faulty nodes in time and improving the robustness of the system.Finally,we design experiments to compare the performance of the PBFT and EPBFT algorithms.Through experimental,we found that compared with the PBFT algorithm,the EPBFT algorithm has a lower delay,communication complexity,better scalability,and more practical.

Classification Algorithm Optimization Based on Triple-GAN

Generating an Adversarial network(GAN)has shown great development prospects in image generation and semi-supervised learning and has evolved into Triple-GAN.However,there are still two problems that need to be solved in Triple-GAN:based on the KL divergence distribution structure,gradients are easy to disappear and training instability occurs.Since Triple-GAN tags the samples manually,the manual marking workload is too large.Marked uneven and so on.This article builds on this improved Triple-GAN model(Improved Triple-GAN),which uses Random Forests to classify real samples,automate tagging of leaf nodes,and use Least Squares Generative Adversarial Networks(LSGAN)ideological structure loss function to avoid gradients disappear.Experiments were performed on the Improved Triple-GAN model and the Triple-GAN model using the MINIST,cifar10 and cifar100 datasets respectively,experiments show that the error rate of generated samples is greatly reduced.At the same time,the classification effect of the data set and the sharpness of the samples are greatly improved.And it has greatly improved the stability of model training and automation of labels.

Urdnet:A Cryo-EM Particle Automatic Picking Method

Cryo-Electron Microscopy(Cryo-EM)images are characterized by the low signal-to-noise ratio,low contrast,serious background noise,more impurities,less data,difficult data labeling,simpler image semantics,and relatively fixed structure,while U-Net obtains low resolution when downsampling rate information to complete object category recognition,obtains highresolution information during upsampling to complete precise segmentation and positioning,fills in the underlying information through skip connection to improve the accuracy of image segmentation,and has advantages in biological image processing like Cryo-EM image.This article proposes A U-Net based residual intensive neural network(Urdnet),which combines point-level and pixel-level tags,used to accurately and automatically locate particles from cryo-electron microscopy images,and solve the bottleneck that cryo-EM Single-particle biologicalmacromolecule reconstruction requires tens of thousands of automatically picked particles.The 80S ribosome,HCN1 channel and TcdA1 toxin subunits,and other public protein datasets have been trained and tested on Urdnet.The experimental results show that Urdnet could reach the same excellent particle picking performances as the mainstream methods of RELION,DeepPicker,and acquire the 3Dstructure of picked particleswith higher resolution.

A Noise Extraction Method for Cryo-EM Single-Particle Denoising

Cryo-Electron Microscopy(cryo-EM)has become a powerful method to study the structure and function of biological macromolecules.However,in clustering tasks based on the projection angle of particles in cryoEM,the noise considerably affects the clustering results.Existing denoising algorithms are ineffective due to the extremely low signal-to-noise ratio(SNR)of cryo-EM images and the complexity of noise types.The noise of a single particle greatly influences the orientation estimation of the subsequent clustering task,and the result of the clustering task directly affects the accuracy of the 3D reconstruction.In this paper,we propose a construction method of cryo-EM denoising dataset that uses U-Net to extract noise blocks from cryoEM images,superimpose the noise block with the projected pure particles to construct our simulated dataset.Then we adopt a supervised generative adversarial network(GAN)with perceptual loss to train on our simulated dataset and denoise the real cryo-EM single particle.The method can solve the problem of poor denoising performance caused by assuming that the noise of the Gaussian distribution does not conform to the noise distribution of cryo-EM,and it can retain the useful information of particles to a great extent.We compared traditional image filtering methods and the classic deep learning denoising algorithm DnCNN on the simulated and real datasets.Experiment results show that the method based on deep learning has more advantages than traditional image denoising methods.It is worth mentioning that our method achieves a competitive peak signal to noise ratio(PSNR)and structural similarity(SSIM).Moreover,visualization results,indicate that our method can retain the structure information and orientation information of particles to a greater extent compared with other state-of-the-art image denoising methods.It means that our denoising task can provide considerable help for subsequent cryo-EM clustering tasks.

CenterPicker:An Automated Cryo-EM Single-Particle Picking Method Based on Center Point Detection

Cryo-electron microscopy(cryo-EM)has become one of the mainstream techniques for determining the structures of proteins andmacromolecular complexes,with prospects for development and significance.Researchers must select hundreds of thousands of particles from micrographs to acquire the database for single-particle cryo-EM reconstruction.However,existing particle picking methods cannot ensure that the particles are in the center of the bounding box because the signal-to-noise ratio(SNR)of micrographs is extremely low,thereby directly affecting the efficiency and accuracy of 3D reconstruction.We propose an automated particle-picking method(CenterPicker)based on particle center point detection to automatically select a large number of high-quality particles from low signal-to-noise,low-contrast refrigerated microscopy images.The method uses a fully convolutional neural network to generate a keypoint heatmap.The heatmap value represents the probability that a micrograph pixel belongs to a particle center area.CenterPicker can process images of any size and can directly predict the center point and size of the particle.The network implements multiscale feature fusion and introduces an attention mechanism to improve the feature fusion part to obtain more accurate selection results.We have conducted a detailed evaluation of CenterPicker on a range of datasets,and results indicate that it excels in single-particle picking tasks.

Research on Denoising of Cryo-em Images Based on Deep Learning

Cryo-em(Cryogenic electron microscopy)is a technology this can build bio-macromolecule of three-dimensional structure.Under the condition of now,the projection image of the biological macromolecule which is collected by the Cryo-em technology that the contrast is low,the signal to noise is low,image blurring,and not easy to distinguish single particle from background,the corresponding processing technology is lagging behind.Therefore,make Cryo-em image denoising useful,and maintaining bio-macromolecule of contour or signal of function-construct improve Cryo-em image quality or resolution of Cryo-em three-dimensional structure have important effect.This paper researched a denoising function base on GANs(generative adversarial networks),purpose an improved discriminant model base on Wasserstein distance and an improved image denoising model by add gray constraint.Our model turn discriminant model’s training process from binary classification’s training process into regression task training process,it make GANs in training process more stable,more reasonable parameter passing.Meantime,we also propose an improved generative model by add gray constraint.The experimental results show that our model can increase the peak signal-to-noise ratio of the Cryo-em simulation image by 10.3 dB and improve SSIM(Structural Similarity Index)of the denoised image results by 0.43.Compared with traditional image denoising algorithms such as BM3D(Block Matching 3D),our model can better save the model structure and the vein signal in the original image and the operation speed is faster.

Android Oriented Image Visualization Exploratory Search

When using traditional image search engines, smartphone users often complain about their poor user interface including poor user experience, and weak interaction. Moreover, users are unable to find a desired picture partly due to the unclear key words. This paper proposes the word-bag co-occurrence scheme by defining the correlation between images. Through exploratory search, the search range can be expanded and help users refine retrieval of the expected images. Firstly, the proposed scheme applied the bag of visual words (BoVW) vector by processing images on Hadoop. Secondly, similarity matrix was constructed to organize the image data. Finally, the images in which users were interested was visually displayed on the android mobile phone via exploratory search. Comparing the proposed method to current methods by testing with image data sets on ImageNet, the experimental results show that the former is superior to the latter on visual representation, and the proposed scheme can provide a better user experience.