arXiv subjects

Hongzhi Wang

Publications and source records attributed to Hongzhi Wang.

At least 109 records · Page 6Linked to original sources

arXiv2020

ExperienceThinking: Constrained Hyperparameter Optimization based on Knowledge and Pruning

Machine learning algorithms are very sensitive to the hyperparameters, and their evaluations are generally expensive. Users desperately need intelligent methods to quickly optimize hyperparameter settings according to known evaluation information, and thus reduce computational cost and promote optimization efficiency. Motivated by this, we propose ExperienceThinking algorithm to quickly find the best possible hyperparameter configuration of machine learning algorithms within a few configuration evaluations. ExperienceThinking design two novel methods, which intelligently infer optimal configurations from two aspects: search space pruning and knowledge utilization respectively. Two methods complement each other and solve the constrained hyperparameter optimization problems effectively. To demonstrate the benefit of ExperienceThinking, we compare it with 3 classical hyperparameter optimization algorithms with a small number of configuration evaluations. The experimental results present that our proposed algorithm provides superior results and achieve better performance.

cs.LG↗

arXiv2020

Neural Network Segmentation of Cell Ultrastructure Using Incomplete Annotation

The Pancreatic beta cell is an important target in diabetes research. For scalable modeling of beta cell ultrastructure, we investigate automatic segmentation of whole cell imaging data acquired through soft X-ray tomography. During the course of the study, both complete and partial ultrastructure annotations were produced manually for different subsets of the data. To more effectively use existing annotations, we propose a method that enables the application of partially labeled data for full label segmentation. For experimental validation, we apply our method to train a convolutional neural network with a set of 12 fully annotated data and 12 partially annotated data and show promising improvement over standard training that uses fully annotated data alone.

q-bio.QM↗

arXiv2020

LAQP: Learning-based Approximate Query Processing

Querying on big data is a challenging task due to the rapid growth of data amount. Approximate query processing (AQP) is a way to meet the requirement of fast response. In this paper, we propose a learning-based AQP method called the LAQP. The LAQP builds an error model learned from the historical queries to predict the sampling-based estimation error of each new query. It makes a combination of the sampling-based AQP, the pre-computed aggregations and the learned error model to provide high-accurate query estimations with a small off-line sample. The experimental results indicate that our LAQP outperforms the sampling-based AQP, the pre-aggregation-based AQP and the most recent learning-based AQP method.

cs.DB↗

arXiv2020

Automatic Hyper-Parameter Optimization Based on Mapping Discovery from Data to Hyper-Parameters

Machine learning algorithms have made remarkable achievements in the field of artificial intelligence. However, most machine learning algorithms are sensitive to the hyper-parameters. Manually optimizing the hyper-parameters is a common method of hyper-parameter tuning. However, it is costly and empirically dependent. Automatic hyper-parameter optimization (autoHPO) is favored due to its effectiveness. However, current autoHPO methods are usually only effective for a certain type of problems, and the time cost is high. In this paper, we propose an efficient automatic parameter optimization approach, which is based on the mapping from data to the corresponding hyper-parameters. To describe such mapping, we propose a sophisticated network structure. To obtain such mapping, we develop effective network constrution algorithms. We also design strategy to optimize the result futher during the application of the mapping. Extensive experimental results demonstrate that the proposed approaches outperform the state-of-the-art apporaches significantly.

cs.LG↗

arXiv2019

Automatic Weighted Matching Rectifying Rule Discovery for Data Repairing

Data repairing is a key problem in data cleaning which aims to uncover and rectify data errors. Traditional methods depend on data dependencies to check the existence of errors in data, but they fail to rectify the errors. To overcome this limitation, recent methods define repairing rules on which they depend to detect and fix errors. However, all existing data repairing rules are provided by experts which is an expensive task in time and effort. Besides, rule-based data repairing methods need an external verified data source or user verifications; otherwise they are incomplete where they can repair only a small number of errors. In this paper, we define weighted matching rectifying rules (WMRRs) based on similarity matching to capture more errors. We propose a novel algorithm to discover WMRRs automatically from dirty data in-hand. We also develop an automatic algorithm for rules inconsistency resolution. Additionally, based on WMRRs, we propose an automatic data repairing algorithm (WMRR-DR) which uncovers a large number of errors and rectifies them dependably. We experimentally verify our method on both real-life and synthetic data. The experimental results prove that our method can discover effective WMRRs from the dirty data in-hand, and perform dependable and full-automatic repairing based on the discovered WMRRs, with higher accuracy than the existing dependable methods.

cs.DB↗

arXiv2019

Autoregressive-Model-Based Methods for Online Time Series Prediction with Missing Values: an Experimental Evaluation

Time series prediction with missing values is an important problem of time series analysis since complete data is usually hard to obtain in many real-world applications. To model the generation of time series, autoregressive (AR) model is a basic and widely used one, which assumes that each observation in the time series is a noisy linear combination of some previous observations along with a constant shift. To tackle the problem of prediction with missing values, a number of methods were proposed based on various data models. For real application scenarios, how do these methods perform over different types of time series with different levels of data missing remains to be investigated. In this paper, we focus on online methods for AR-model-based time series prediction with missing values. We adapted five mainstream methods to fit in such a scenario. We make detailed discussion on each of them by introducing their core ideas about how to estimate the AR coefficients and their different strategies to deal with missing values. We also present algorithmic implementations for better understanding. In order to comprehensively evaluate these methods and do the comparison, we conduct experiments with various configurations of relative parameters over both synthetic and real data. From the experimental results, we derived several noteworthy conclusions and shows that imputation is a simple but reliable strategy to handle missing values in online prediction tasks.

stat.ML↗

arXiv2019

A General Data Renewal Model for Prediction Algorithms in Industrial Data Analytics

In industrial data analytics, one of the fundamental problems is to utilize the temporal correlation of the industrial data to make timely predictions in the production process, such as fault prediction and yield prediction. However, the traditional prediction models are fixed while the conditions of the machines change over time, thus making the errors of predictions increase with the lapse of time. In this paper, we propose a general data renewal model to deal with it. Combined with the similarity function and the loss function, it estimates the time of updating the existing prediction model, then updates it according to the evaluation function iteratively and adaptively. We have applied the data renewal model to two prediction algorithms. The experiments demonstrate that the data renewal model can effectively identify the changes of data, update and optimize the prediction model so as to improve the accuracy of prediction.

cs.LG↗

arXiv2019

LSTM-based Flow Prediction

In this paper, a method of prediction on continuous time series variables from the production or flow -- an LSTM algorithm based on multivariate tuning -- is proposed. The algorithm improves the traditional LSTM algorithm and converts the time series data into supervised learning sequences regarding industrial data's features. The main innovation of this paper consists in introducing the concepts of periodic measurement and time window in the industrial prediction problem, especially considering industrial data with time series characteristics. Experiments using real-world datasets show that the prediction accuracy is improved, 54.05% higher than that of traditional LSTM algorithm.

cs.LG↗

arXiv2019

Automated Detection and Type Classification of Central Venous Catheters in Chest X-Rays

Central venous catheters (CVCs) are commonly used in critical care settings for monitoring body functions and administering medications. They are often described in radiology reports by referring to their presence, identity and placement. In this paper, we address the problem of automatic detection of their presence and identity through automated segmentation using deep learning networks and classification based on their intersection with previously learned shape priors from clinician annotations of CVCs. The results not only outperform existing methods of catheter detection achieving 85.2% accuracy at 91.6% precision, but also enable high precision (95.2%) classification of catheter types on a large dataset of over 10,000 chest X-rays, presenting a robust and practical solution to this problem.

eess.IV↗

arXiv2019

Regular Expression Matching on billion-nodes Graphs

In many applications, it is necessary to retrieve pairs of vertices with the path between them satisfying certain constraints, since regular expression is a powerful tool to describe patterns of a sequence. To meet such requirements, in this paper, we define regular expression (RE) query on graphs to use regular expression to represent the constraints between vertices. To process RE queries on large graphs such as social networks, we propose the RE query processing method with the index size sublinear to the graph size. Considering that large graphs may be randomly distributed in multiple machines, the parallel RE processing algorithms are presented without the assumption of graph distribution. To achieve high efficiency for complex RE query processing, we develop cost-based query optimization strategies with only a small size statistical information which is suitable for querying large graphs. Comprehensive experimental results show that this approach works scale well for large graphs.

cs.DB↗

arXiv2019

GPU-based Efficient Join Algorithms on Hadoop

The growing data has brought tremendous pressure for query processing and storage, so there are many studies that focus on using GPU to accelerate join operation, which is one of the most important operations in modern database systems. However, existing GPU acceleration join operation researches are not very suitable for the join operation on big data. Based on this, this paper speeds up nested loop join, hash join and theta join, combining Hadoop with GPU, which is also the first to use GPU to accelerate theta join. At the same time, after the data pre-filtering and pre-processing, using Map-Reduce and HDFS in Hadoop proposed in this paper, the larger data table can be handled, compared to existing GPU acceleration methods. Also with Map-Reduce in Hadoop, the algorithm proposed in this paper can estimate the number of results more accurately and allocate the appropriate storage space without unnecessary costs, making it more efficient. The rigorous experiments show that the proposed method can obtain 1.5 to 2 times the speedup, compared to the traditional GPU acceleration equi join algorithm. And in the synthetic data set, the GPU version of the proposed method can get 1.3 to 2 times the speedup, compared to CPU version.

cs.DB↗

arXiv2019

An Iterative Scheme for Leverage-based Approximate Aggregation

The current data explosion poses great challenges to the approximate aggregation with an efficiency and accuracy. To address this problem, we propose a novel approach to calculate the aggregation answers with a high accuracy using only a small portion of the data. We introduce leverages to reflect individual differences in the samples from a statistical perspective. Two kinds of estimators, the leverage-based estimator, and the sketch estimator (a "rough picture" of the aggregation answer), are in constraint relations and iteratively improved according to the actual conditions until their difference is below a threshold. Due to the iteration mechanism and the leverages, our approach achieves a high accuracy. Moreover, some features, such as not requiring recording the sampled data and easy to extend to various execution modes (e.g., the online mode), make our approach well suited to deal with big data. Experiments show that our approach has an extraordinary performance, and when compared with the uniform sampling, our approach can achieve high-quality answers with only 1/3 of the same sample size.

cs.DB↗

arXiv2018

Hierarchical Spatial-aware Siamese Network for Thermal Infrared Object Tracking

Most thermal infrared (TIR) tracking methods are discriminative, treating the tracking problem as a classification task. However, the objective of the classifier (label prediction) is not coupled to the objective of the tracker (location estimation). The classification task focuses on the between-class difference of the arbitrary objects, while the tracking task mainly deals with the within-class difference of the same objects. In this paper, we cast the TIR tracking problem as a similarity verification task, which is coupled well to the objective of the tracking task. We propose a TIR tracker via a Hierarchical Spatial-aware Siamese Convolutional Neural Network (CNN), named HSSNet. To obtain both spatial and semantic features of the TIR object, we design a Siamese CNN that coalesces the multiple hierarchical convolutional layers. Then, we propose a spatial-aware network to enhance the discriminative ability of the coalesced hierarchical feature. Subsequently, we train this network end to end on a large visible video detection dataset to learn the similarity between paired objects before we transfer the network into the TIR domain. Next, this pre-trained Siamese network is used to evaluate the similarity between the target template and target candidates. Finally, we locate the candidate that is most similar to the tracked target. Extensive experimental results on the benchmarks VOT-TIR 2015 and VOT-TIR 2016 show that our proposed method achieves favourable performance compared to the state-of-the-art methods.

cs.CV↗

arXiv2018

Predicting Learning Status in MOOCs using LSTM

Real-time and open online course resources of MOOCs have attracted a large number of learners in recent years. However, many new questions were emerging about the high dropout rate of learners. For MOOCs platform, predicting the learning status of MOOCs learners in real time with high accuracy is the crucial task, and it also help improve the quality of MOOCs teaching. The prediction task in this paper is inherently a time series prediction problem, and can be treated as time series classification problem, hence this paper proposed a prediction model based on RNNLSTMs and optimization techniques which can be used to predict learners' learning status. Using datasets provided by Chinese University MOOCs as the inputs of model, the average accuracy of model's outputs was about 90%.

cs.CY↗

arXiv2018

Schema Integration on Massive Data Sources

As the fundamental phrase of collecting and analyzing data, data integration is used in many applications, such as data cleaning, bioinformatics and pattern recognition. In big data era, one of the major problems of data integration is to obtain the global schema of data sources since the global schema could be hardly derived from massive data sources directly. In this paper, we attempt to solve such schema integration problem. For different scenarios, we develop batch and incremental schema integration algorithms. We consider the representation difference of attribute names in various data sources and propose ED Join and Semantic Join algorithms to integrate attributes with different representations. Extensive experimental results demonstrate that the proposed algorithms could integrate schemas efficiently and effectively.

cs.DB↗

arXiv2018

Mining CFD Rules on Big Data

Current conditional functional dependencies (CFDs) discovery algorithms always need a well-prepared training data set. This makes them difficult to be applied on large datasets which are always in low-quality. To handle the volume issue of big data, we develop the sampling algorithms to obtain a small representative training set. For the low-quality issue of big data, we then design the fault-tolerant rule discovery algorithm and the conflict resolution algorithm. We also propose parameter selection strategy for CFD discovery algorithm to ensure its effectiveness. Experimental results demonstrate that our method could discover effective CFD rules on billion-tuple data within reasonable time.

cs.DB↗

arXiv2018

On the Fairness of Quality-based Data Markets

For data pricing, data quality is a factor that must be considered. To keep the fairness of data market from the aspect of data quality, we proposed a fair data market that considers data quality while pricing. To ensure fairness, we first design a quality-driven data pricing strategy. Then based on the strategy, a fairness assurance mechanism for quality-driven data marketplace is proposed. In this mechanism, we ensure that savvy consumers cannot cheat the system and users can verify each consumption with Trusted Third Party (TTP) that they are charged properly. Based on this mechanism, we develop a fair quality-driven data market system. Extensive experiments are performed to verify the effectiveness of proposed techniques. Experimental results show that our quality-driven data pricing strategy could assign a reasonable price to the data according to data quality and the fairness assurance mechanism could effectively protect quality-driven data pricing from potential cheating.

cs.DB↗

arXiv2018

Error Detection in a Large-Scale Lexical Taxonomy

Knowledge base (KB) is an important aspect in artificial intelligence. One significant challenge faced by KB construction is that it contains many noises, which prevents its effective usage. Even though some KB cleansing algorithms have been proposed, they focus on the structure of the knowledge graph and neglect the relation between the concepts, which could be helpful to discover wrong relations in KB. Motived by this, we measure the relation of two concepts by the distance between their corresponding instances and detect errors within the intersection of the conflicting concept sets. For efficient and effective knowledge base cleansing, we first apply a distance-based Model to determine the conflicting concept sets using two different methods. Then, we propose and analyze several algorithms on how to detect and repairing the errors based on our model, where we use hash method for an efficient way to calculate distance. Experimental results demonstrate that the proposed approaches could cleanse the knowledge bases efficiently and effectively.

cs.AI↗