Dual-stream coupling network with wavelet transform for cross-resolution person re-identification

Person re-identification is a prevalent technology deployed on intelligent surveillance.There have been remarkable achievements in person re-identification methods based on the assumption that all person images have a sufficiently high resolution,yet such models are not applicable to the open world.In real world,the changing distance between pedestrians and the camera renders the resolution of pedestrians captured by the camera inconsistent.When low-resolution(LR)images in the query set are matched with high-resolution(HR)images in the gallery set,it degrades the performance of the pedestrian matching task due to the absent pedestrian critical information in LR images.To address the above issues,we present a dualstream coupling network with wavelet transform(DSCWT)for the cross-resolution person re-identification task.Firstly,we use the multi-resolution analysis principle of wavelet transform to separately process the low-frequency and high-frequency regions of LR images,which is applied to restore the lost detail information of LR images.Then,we devise a residual knowledge constrained loss function that transfers knowledge between the two streams of LR images and HR images for accessing pedestrian invariant features at various resolutions.Extensive qualitative and quantitative experiments across four benchmark datasets verify the superiority of the proposed approach.

Attributes-based person re-identification via CNNs with coupled clusters loss

Person re-identification(re-id)involves matching a person across nonoverlapping views,with different poses,illuminations and conditions.Visual attributes are understandable semantic information to help improve the issues including illumination changes,viewpoint variations and occlusions.This paper proposes an end-to-end framework of deep learning for attribute-based person re-id.In the feature representation stage of framework,the improved convolutional neural network(CNN)model is designed to leverage the information contained in automatically detected attributes and learned low-dimensional CNN features.Moreover,an attribute classifier is trained on separate data and includes its responses into the training process of our person re-id model.The coupled clusters loss function is used in the training stage of the framework,which enhances the discriminability of both types of features.The combined features are mapped into the Euclidean space.The L2 distance can be used to calculate the distance between any two pedestrians to determine whether they are the same.Extensive experiments validate the superiority and advantages of our proposed framework over state-of-the-art competitors on contemporary challenging person re-id datasets.

Polynomial-Time Assignment-Based Cell Association with Generic Utility Functions

Cell association is a significant research issue in future mobile communication systems due to the unacceptably large computational time of traditional schemes.This article proposes a polynomial-time cell association scheme which not only completes the association in polynomial time but also fits for a generic optimization objective function.On the one hand,traditional cell association as a non-deterministic polynomial(NP)hard problem with a generic utility function is heuristically transformed into a 2-dimensional assignment optimization and solved by a certain polynomial-time algorithm,which significantly saves computational time.On the other hand,the scheme jointly considers utility maximization and load balancing among multiple base stations(BSs)by maintaining an experience pool storing a set of weighting factor values and their corresponding performances.When an association optimization is required,a suitable weighting factor value is taken from the pool to calculate a long square utility matrix and a certain polynomial-time algorithm will be applied for the association.Comparing with several representative schemes,the proposed scheme achieves large system capacity and high fairness within a relatively short computational time.

Throughput-oriented associated transaction assignment in sharding blockchains for IoT social data storage

Blockchain is a viable solution to provide data integrity for the enormous volume of 5G IoT social data, while we need to break through the throughput bottleneck of blockchain. Sharding is a promising technology to solve the problem of low throughput in blockchains. However, cross-shard communication hinders the effective improvement of blockchain throughput. Therefore, it is critical to reasonably allocate transactions to different shards to improve blockchain throughput. Existing research on blockchain sharding mainly focuses on shards formation, configuration, and consensus, while ignoring the negative impact of cross-shard communication on blockchain throughput. Aiming to maximize the throughput of transaction processing, we study how to allocate blockchain transactions to shards in this paper. We propose an Associated Transaction assignment algorithm based on Closest Fit (ATCF). ATCF classifies associated transactions into transaction groups which are then assigned to different shards in the non-ascending order of transaction group sizes periodically. Within each epoch, ATCF tries to select a shard that can handle all the transactions for each transaction group. If there are multiple such shards, ATCF selects the shard with the remaining processing capacity closest to the number of transactions in the transaction group. When no such shard exists, ATCF chooses the shard with the largest remaining processing capacity for the transaction group. The transaction groups that cannot be completely processed within the current epoch will be allocated in the subsequent epochs. We prove that ATCF is a 2-approximation algorithm for the associated transaction assignment problem. Simulation results show that ATCF can effectively improve the blockchain throughput and reduce the number of cross-shard transactions.

Joint user profiling with hierarchical attention networks

User profiling by inferring user personality traits,such as age and gender,plays an increasingly important role in many real-world applications.Most existing methods for user profiling either use only one type of data or ignore handling the noisy information of data.Moreover,they usually consider this problem from only one perspective.In this paper,we propose a joint user profiling model with hierarchical attention networks(JUHA)to learn informative user representations for user profiling.Our JUHA method does user profiling based on both inner-user and inter-user features.We explore inner-user features from user behaviors(e.g.,purchased items and posted blogs),and inter-user features from a user-user graph(where similar users could be connected to each other).JUHA learns basic sentence and bag representations from multiple separate sources of data(user behaviors)as the first round of data preparation.In this module,convolutional neural networks(CNNs)are introduced to capture word and sentence features of age and gender while the self-attention mechanism is exploited to weaken the noisy data.Following this,we build another bag which contains a user-user graph.Inter-user features are learned from this bag using propagation information between linked users in the graph.To acquire more robust data,inter-user features and other inner-user bag representations are joined into each sentence in the current bag to learn the final bag representation.Subsequently,all of the bag representations are integrated to lean comprehensive user representation by the self-attention mechanism.Our experimental results demonstrate that our approach outperforms several state-of-the-art methods and improves prediction performance.

Intelligent Fast Cell Association Scheme Based on Deep Q-Learning in Ultra-Dense Cellular Networks

To support dramatically increased traffic loads,communication networks become ultra-dense.Traditional cell association(CA)schemes are timeconsuming,forcing researchers to seek fast schemes.This paper proposes a deep Q-learning based scheme,whose main idea is to train a deep neural network(DNN)to calculate the Q values of all the state-action pairs and the cell holding the maximum Q value is associated.In the training stage,the intelligent agent continuously generates samples through the trial-anderror method to train the DNN until convergence.In the application stage,state vectors of all the users are inputted to the trained DNN to quickly obtain a satisfied CA result of a scenario with the same BS locations and user distribution.Simulations demonstrate that the proposed scheme provides satisfied CA results in a computational time several orders of magnitudes shorter than traditional schemes.Meanwhile,performance metrics,such as capacity and fairness,can be guaranteed.

HUSS:A Heuristic Method for Understanding the Semantic Structure of Spreadsheets

Spreadsheets contain a lot of valuable data and have many practical applications.The key technology of these practical applications is how to make machines understand the semantic structure of spreadsheets,e.g.,identifying cell function types and discovering relationships between cell pairs.Most existing methods for understanding the semantic structure of spreadsheets do not make use of the semantic information of cells.A few studies do,but they ignore the layout structure information of spreadsheets,which affects the performance of cell function classification and the discovery of different relationship types of cell pairs.In this paper,we propose a Heuristic algorithm for Understanding the Semantic Structure of spreadsheets(HUSS).Specifically,for improving the cell function classification,we propose an error correction mechanism(ECM)based on an existing cell function classification model[11]and the layout features of spreadsheets.For improving the table structure analysis,we propose five types of heuristic rules to extract four different types of cell pairs,based on the cell style and spatial location information.Our experimental results on five real-world datasets demonstrate that HUSS can effectively understand the semantic structure of spreadsheets and outperforms corresponding baselines.

Multi-view Feature Learning for the Over-penalty in Adversarial Domain Adaptation

Domain adaptation aims to transfer knowledge from the labeled source domain to an unlabeled target domain that follows a similar but different distribution.Recently,adversarial-based methods have achieved remarkable success due to the excellent performance of domain-invariant feature presentation learning.However,the adversarial methods learn the transferability at the expense of the discriminability in feature representation,leading to low generalization to the target domain.To this end,we propose a Multi-view Feature Learning method for the Over-penalty in Adversarial Domain Adaptation.Specifically,multi-view representation learning is proposed to enrich the discriminative information contained in domain-invariant feature representation,which will counter the over-penalty for discriminability in adversarial training.Besides,the class distribution in the intra-domain is proposed to replace that in the inter-domain to capture more discriminative information in the learning of transferrable features.Extensive experiments show that our method can improve the discriminability while maintaining transferability and exceeds the most advanced methods in the domain adaptation benchmark datasets.

Fuzzy-Constrained Graph Pattern Matching in Medical Knowledge Graphs

The research on graph pattern matching(GPM) has attracted a lot of attention. However, most of the research has focused on complex networks, and there are few researches on GPM in the medical field. Hence, with GPM this paper is to make a breast cancer-oriented diagnosis before the surgery. Technically, this paper has firstly made a new definition of GPM, aiming to explore the GPM in the medical field, especially in Medical Knowledge Graphs(MKGs). Then, in the specific matching process, this paper introduces fuzzy calculation, and proposes a multi-threaded bidirectional routing exploration(M-TBRE) algorithm based on depth first search and a two-way routing matching algorithm based on multi-threading. In addition, fuzzy constraints are introduced in the M-TBRE algorithm, which leads to the Fuzzy-M-TBRE algorithm. The experimental results on the two datasets show that compared with existing algorithms, our proposed algorithm is more efficient and effective.

Representation learning via an integrated autoencoder for unsupervised domain adaptation

The purpose of unsupervised domain adaptation is to use the knowledge of the source domain whose data distribution is different from that of the target domain for promoting the learning task in the target domain.The key bottleneck in unsupervised domain adaptation is how to obtain higher-level and more abstract feature representations between source and target domains which can bridge the chasm of domain discrepancy.Recently,deep learning methods based on autoencoder have achieved sound performance in representation learning,and many dual or serial autoencoderbased methods take different characteristics of data into consideration for improving the effectiveness of unsupervised domain adaptation.However,most existing methods of autoencoders just serially connect the features generated by different autoencoders,which pose challenges for the discriminative representation learning and fail to find the real cross-domain features.To address this problem,we propose a novel representation learning method based on an integrated autoencoders for unsupervised domain adaptation,called IAUDA.To capture the inter-and inner-domain features of the raw data,two different autoencoders,which are the marginalized autoencoder with maximum mean discrepancy(mAE)and convolutional autoencoder(CAE)respectively,are proposed to learn different feature representations.After higher-level features are obtained by these two different autoencoders,a sparse autoencoder is introduced to compact these inter-and inner-domain representations.In addition,a whitening layer is embedded for features processed before the mAE to reduce redundant features inside a local area.Experimental results demonstrate the effectiveness of our proposed method compared with several state-of-the-art baseline methods.

Unsupervised statistical text simplification using pre-trained language modeling for initialization

Unsupervised text simplification has attracted much attention due to the scarcity of high-quality parallel text simplification corpora. Recent an unsupervised statistical text simplification based on phrase-based machine translation system (UnsupPBMT) achieved good performance, which initializes the phrase tables using the similar words obtained by word embedding modeling. Since word embedding modeling only considers the relevance between words, the phrase table in UnsupPBMT contains a lot of dissimilar words. In this paper, we propose an unsupervised statistical text simplification using pre-trained language modeling BERT for initialization. Specifically, we use BERT as a general linguistic knowledge base for predicting similar words. Experimental results show that our method outperforms the state-of-the-art unsupervised text simplification methods on three benchmarks, even outperforms some supervised baselines.

A Heuristic Sampling Method for Maintaining the Probability Distribution

Sampling is a fundamental method for generating data subsets.As many data analysis methods are developed based on probability distributions,maintaining distributions when sampling can help to ensure good data analysis performance.However,sampling a minimum subset while maintaining probability distributions is still a problem.In this paper,we decompose a joint probability distribution into a product of conditional probabilities based on Bayesian networks and use the chi-square test to formulate a sampling problem that requires that the sampled subset pass the distribution test to ensure the distribution.Furthermore,a heuristic sampling algorithm is proposed to generate the required subset by designing two scoring functions:one based on the chi-square test and the other based on likelihood functions.Experiments on four types of datasets with a size of 60000 show that when the significant difference level,a,is set to 0.05,the algorithm can exclude 99.9%,99.0%,93.1%and 96.7%of the samples based on their Bayesian networks-ASIA,ALARM,HEPAR2,and ANDES,respectively.When subsets of the same size are sampled,the subset generated by our algorithm passes all the distribution tests and the average distribution difference is approximately 0.03;by contrast,the subsets generated by random sampling pass only 83.8%of the tests,and the average distribution difference is approximately 0.24.

Certainty-based Preference Completion

As from time to time it is impractical to ask agents to provide linear orders over all alternatives,for these partial rankings it is necessary to conduct preference completion.Specifically,the personalized preference of each agent over all the alternatives can be estimated with partial rankings from neighboring agents over subsets of alternatives.However,since the agents’rankings are nondeterministic,where they may provide rankings with noise,it is necessary and important to conduct the certainty-based preference completion.Hence,in this paper firstly,for alternative pairs with the obtained ranking set,a bijection has been built from the ranking space to the preference space,and the certainty and conflict of alternative pairs have been evaluated with a well-built statistical measurement Probability-Certainty Density Function on subjective probability,respectively.Then,a certainty-based voting algorithm based on certainty and conflict has been taken to conduct the certainty-based preference completion.Moreover,the properties of the proposed certainty and conflict have been studied empirically,and the proposed approach on certainty-based preference completion for partial rankings has been experimentally validated compared to state-of-arts approaches with several datasets.