Pattern-based Methods Research Articles

Neural Network Assisted Pathology Case Identification

BackgroundTraditionally, cases for cohort selection and quality assurance purposes are identified through structured query language (SQL) searches matching specific keywords. Recently, several neural network-based natural language processing (NLP) pipelines have emerged as an accurate alternative/complementary method for case retrieval. MethodsThe diagnosis section of 1000 pathology reports with the terms “colon” and “carcinoma” were retrieved from our laboratory information system through a SQL query. Each of the reports were labeled as either positive or negative, where cases are considered positive if the case was a primary adenocarcinoma of the colon. Negative cases comprised adenocarcinoma from other sites, metastatic adenocarcinomas, benign conditions, rectal cancers, and other cases that do not fit in the primary colonic adenocarcinoma category. The 1000 cases were randomly separated into training, validation, and holdout sets. A convolutional neural network (CNN) model built using Keras (a neural network library) was trained to identify positive cases, and the model was applied to the holdout set to predict the category for each case. ResultsThe CNN model classified 141 out of 149 primary colonic adenocarcinoma cases, and 43 out of 51 negative cases correctly, achieving an accuracy of 92% and area under the ROC curve (AUC) of 0.957. ConclusionTrained convolutional neural network models by itself, or as an adjunct to keyword and pattern-based text extraction methods may be used to search for pathology cases of interest with high accuracy.

Pattern-based downscaling of snowpack variability in the western United States

The decline in snowpack across the western United States is one of the most pressing threats posed by climate change to regional economies and livelihoods. Earth system models are important tools for exploring past and future snowpack variability, yet their coarse spatial resolutions distort local topography and bias spatial patterns of accumulation and ablation. Here, we explore pattern-based statistical downscaling for spatially-continuous interannual snowpack estimates. We find that a few leading patterns capture the majority of snowpack variability across the western US in observations, reanalyses, and free-running simulations. Pattern-based downscaling methods yield accurate, high resolution maps that correct mean and variance biases in domain-wide simulated snowpack. Methods that use large-scale patterns as both predictors and predictands perform better than those that do not and all are superior to an interpolation-based “delta change” approach. These findings suggest that pattern-based methods are appropriate for downscaling interannual snowpack variability and that using physically meaningful large-scale patterns is more important than the details of any particular downscaling method.

Comparison of Whole Genome Sequencing and Repetitive Element PCR for Multidrug-Resistant Pseudomonas aeruginosa Strain Typing

Hospital-acquired infections pose significant costly global challenges to patient care. Rapid and sensitive methods to identify potential outbreaks are integral to infection control measures. Whole-genome sequencing (WGS)-based bacterial strain typing provides higher discriminatory power over standard nucleotide banding pattern-based methods such as repetitive sequence-based PCR (rep-PCR). However, integration of WGS into clinical epidemiology is limited by the lack of consensus in methodology and data analysis/interpretation. In this study, WGS was performed on genomic DNA extracted from 22 multidrug-resistant Pseudomonas aeruginosa (MDR-PA) isolates using next-generation sequencing. Resulting high-quality reads were analyzed for phylogenetic relatedness using a whole-genome multilocus sequence typing (wgMLST)-based software program and single-nucleotide variant phylogenomics (SNVPhyl). WGS-based results were compared with conventional MLST and archived rep-PCR results. Rep-PCR identified three independent clonal clusters of MDR-PA. Only one clonal cluster identified by rep-PCR, an endemic strain within the pediatric cystic fibrosis population at Texas Children's Hospital, was concordantly identified using wgMLST and SNVPhyl. Results were highly consistent between the three sequence-based analyses (conventional MLST, wgMLST, and SNVPhyl), and these results remained consistent with the addition of 74 MDR-PA genomes. These WGS-based methods provided greater resolution for strain discrimination than rep-PCR or standard MLST classification, and the ease of use of wgMLST software renders it clinically viable for analysis, interpretation, and reporting of WGS-based strain typing.

A novel construction scheduling framework for a mixed construction process of precast components and cast-in-place parts in prefabricated buildings

The mixing of precast components and cast-in-place parts is a major feature of prefabricated buildings , but the existing pattern-based scheduling methods lack consideration of it. The main objective of this paper is to describe the mixing construction process of precast building faithfully, and schedule the process in a single BIM environment. This study presents a novel scheduling framework for prefabricated buildings. By using IFC, flexible work break-down structure (WBS) and constraints based simulation (CBS) method, this framework integrates scheduling information in a single BIM model, and organizes construction process in a flexible WBS structure to consistent with the mixing construction of precast and cast-in-place, and finally generate valid schedule to meet various constraints by using CBS. A case study is conducted to verify the framework, and a comparison with the traditional method is carried out. The result shows that this scheduling framework can faithfully scheduling the mixed construction process at different scale in a single BIM environment, and the comparison with traditional way shows it reduces the scheduling burden, improve the resources usage efficiency. This study contributes to solving the knowledge gap of the inapplicability of the process pattern-based method in describing the mixed construction process, and the heterogeneous and scattered information sources in scheduling. This methodology can conveniently organize large amount of mesoscale tasks into mixed scale task network, and facilitate the reuse of scheduling-related knowledge, improve the resource usage efficiency, help managers understand the construction process at different scales, improve the BIM-based information collaboration in scheduling. In the future, a faithful construction process description at the activity level can digitalize the actual construction process, pave the way to apply the activity data obtained by ICT. ● The existing scheduling method cannot truly reflect the actual construction process of the fabricated components and cast-in-place parts hybrid building. ● This paper presents a novel scheduling framework that schedule the mixed construction process at different scales in a single BIM environment. ● Organized in flexible WBS structure, the generated schedule could be detailed to the activity level while conform to the large-scale tasks at the same time. ● The results show that this methodology could reduce the scheduling burden, improve the resources usage efficiency; and facilitate the reuse of scheduling-related knowledge.

An efficient anomaly detection method for uncertain data based on minimal rare patterns with the consideration of anti-monotonic constraints

The pattern-based anomaly detection method has obtained more attention since it was proposed. This is due to its ability to fully identify anomalies by considering two key features, including appearing rarely and deviating from most data elements. Although most pattern-based anomaly detection methods identify the anomalies from full data space, the process involved in performing this functionality is very time-consuming. Therefore, to solve this problem, this paper introduces a novel method, namely minimal rare pattern-based anomaly detection method through considering anti-monotonic constraints (MRPAC), for identifying anomalies in uncertain data. MRPAC detects the anomalies from a small scale of uncertain data that satisfy preset anti-monotonic constraints by mining constrained minimal rare patterns, thus, the time efficiency is increased. In addition, MRPAC also defines multiple deviation factors to compute the anomaly score for all transactions, to accurately discover potential anomalies through sorting their anomaly scores. Extensive experimental outcomes indicate that the MRPAC significantly outperforms five state-of-the-art pattern-based anomaly methods in terms of detection accuracy and time efficiency, and obtains good scalability.

Comparisons of Molecular Structure Generation Methods Based on Fragment Assemblies and Genetic Graphs.

The use of quantitative structure-property relationships (QSPRs) helps in predicting molecular properties for several decades, while the automatic design of new molecular structures is still emerging. The choice of algorithms to generate molecules is not obvious and is related to several factors such as the desired chemical diversity (according to an initial dataset's content) and the level of construction (the use of atoms, fragments, pattern-based methods). In this paper, we address the problem of molecular structure generation by revisiting two approaches: fragment-based methods (FMs) and genetic-based methods (GMs). We define a set of indices to compare generation methods on a specific task. New indices inform about the explored data space (coverage), compare how the data space is explored (representativeness), and quantifies the ratio of molecules satisfying requirements (generation specificity) without the use of a database composed of real chemicals as a reference. These indices were employed to compare generations of molecules fulfilling the desired property criterion, evaluated by QSPR.

Comparison of current state of control valve stiction detection and quantification techniques

The process control and automation system is one of the significant features in any process plant. The control valve is considered a fundamental part of the process control system. It regulates the fluid flow by changing the size of the flow passage as directed by the controller. If properly maintained, the control valves can help to reduce process variability and improve product quality, which in turn increases the overall efficiency of the plant. But control valve stiction is an enduring concern within process industries which eventually affects the efficiency of plant operation. Hence, it is extremely essential to detect and quantify stiction at the earliest opportunity, to determine the correct maintenance measures. Numerous methods related to stiction detection and estimation have been carried out so far by researchers. A literature study of the latest publications in stiction detection and quantification discloses that research in the conventional methods of stiction detection and quantification such as limit cycle pattern-based, waveform shape-based, nonlinearity-based, and model-based methods is gradually declining. At the same time, most stiction detection/quantification methods reported in the recent literature are based on artificial neural network and convolutional neural network. This implies that future stiction detection and quantification research will be focused towards machine learning (ML) algorithms. Taking this into consideration, this paper aims to provide a literature review of stiction detection and quantification methods by focusing on the latest research ideas and innovative approaches. This review also aims to compare recent techniques based on ML algorithms with conventional methods by pointing out the relationship among different methods, differences, and possible points of weakness.

Low-Cost and Device-Free Human Activity Recognition Based on Hierarchical Learning Model.

Human activity recognition (HAR) has been a vital human–computer interaction service in smart homes. It is still a challenging task due to the diversity and similarity of human actions. In this paper, a novel hierarchical deep learning-based methodology equipped with low-cost sensors is proposed for high-accuracy device-free human activity recognition. ESP8266, as the sensing hardware, was utilized to deploy the WiFi sensor network and collect multi-dimensional received signal strength indicator (RSSI) records. The proposed learning model presents a coarse-to-fine hierarchical classification framework with two-level perception modules. In the coarse-level stage, twelve statistical features of time–frequency domains were extracted from the RSSI measurements filtered by a butterworth low-pass filter, and a support vector machine (SVM) model was employed to quickly recognize the basic human activities by classifying the signal statistical features. In the fine-level stage, the gated recurrent unit (GRU), a representative type of recurrent neural network (RNN), was applied to address issues of the confused recognition of similar activities. The GRU model can realize automatic multi-level feature extraction from the RSSI measurements and accurately discriminate the similar activities. The experimental results show that the proposed approach achieved recognition accuracies of 96.45% and 94.59% for six types of activities in two different environments and performed better compared the traditional pattern-based methods. The proposed hierarchical learning method provides a low-cost sensor-based HAR framework to enhance the recognition accuracy and modeling efficiency.

Identifying comparable entities from online question-answering contents

As an emerging platform, online question-answering (Q&A) communities are becoming valuable corpus sources that reflect the opinions of expert consumers on comparable entities. In this study, a novel method-Identifying Comparable entities from online Question-Answering contents (ICQA)-is proposed to effectively extract comparable entities from online Q&A communities. In ICQA, candidate entities are firstly extracted by utilizing the advantages of pattern-based methods and supervised learning-based methods. An entity comparison network is then built by considering the credibility difference and entity relatedness in Q&A contents to analyze competitiveness between entities and extract comparable entities from candidate entities accordingly. Thus, within the same method framework, comparable entities and their competitiveness ranks can be simultaneously identified for a given entity specified by managers or consumers. By taking the automotive industry as the experimental background, the effectiveness of ICQA is demonstrated with comprehensive experiments regarding comparable entity identification and comparable entity ranking. Experimental results demonstrate that compared with state-of-the-art methods, ICQA can identify more accurate and broader comparable entities, find novel entities ignored by other methods, and provide a more solid comparable entity rank-features that are deemed desirable and applicable for both managers and consumers in making rational decisions based on online Q&A contents.

Relevance Feature Discovery for Text Mining

Due to large size words also data patterns, it is difficult to ensure the quality of relevant characteristics that are found in text documents that describe user preferences. Most widely used text mining and classification techniques now in use have embraced term-based strategies. However, polysemy and synonymy issues have affected them all. The theory that pattern-based approaches should outperform term-based ones in performance in expressing user preferences has been often held throughout the years, however text mining still struggles with how to employ large-scale patterns successfully. This research introduces a novel methodology for relevance feature discovery to address this hard problem. It finds higher level features in text texts that are both positive and negative patterns and uses them instead of low-level features (terms). Additionally, it organised terms into categories and updates term weights according to the patterns and specificity of those distributions. Significant tests employing this model on the datasets RCV1, TREC themes, and Reuters-21578 reveal that it performs noticeably better than both the most advanced term-based approaches and pattern-based methods.

Finger Vein Recognition via Sparse Reconstruction Error Constrained Low-Rank Representation

Vein pattern-based methods have powerfully promoted the performance of finger vein recognition. However, it is not easy to precisely extract vein patterns from images, especially from low-quality images, and the non-vein area have been proved to be helpful for recognition. This paper proposes to use low-rank representation to extract as much noiseless discriminative information as possible from finger vein images. However, image deformation and image quality variations weaken the correlation of genuine images, and therefore damage the low-rank linear representation. To further deal with this problem, the class labels of training images and the local geometric structure between testing images and training images, reflected by sparse reconstruction errors of testing images, are used as constraints of low-rank coefficients. In particular, vein backbone decomposition based sparse representation is proposed to fast compute the deformation-robust reconstruction errors of each testing image. The reconstruction errors on sub-backbones of one training image are summed and modified as the constraint of the low-rank coefficient on this training image. We evaluate the proposed method on three widely used finger vein databases, and experimental results show that the proposed method performs well in finger vein recognition.

An efficient approach for outlier detection from uncertain data streams based on maximal frequent patterns

Outlier identification is an important technology to improve the credibility of data and aims at detecting patterns that rarely appear and exhibit a significant difference from other data. However, the detection accuracy achieved by the simple deviation factors of existing pattern-based outlier detection methods is not competitive. In addition, given the large scale of uncertain data streams, the efficiency of many pattern-based outlier detection methods is not high because they use a vast number of frequent patterns to conduct the outlier detection. In this paper, to contend with the uncertain data streams, we propose a maximal-frequent-pattern-based outlier detection method, namely, MFP-OD, for identifying the outliers with a lower time cost. For further improving the detection accuracy of existing outlier detection methods, we design three deviation factors to measure the deviation degree of each transaction. The experimental results indicate that the proposed MFP-OD method can quickly and accurately identify the outliers from uncertain data streams.

Identifying the tissues-of-origin of circulating cell-free DNAs is a promising way in noninvasive diagnostics.

Advances in sequencing technologies facilitate personalized disease-risk profiling and clinical diagnosis. In recent years, some great progress has been made in noninvasive diagnoses based on cell-free DNAs (cfDNAs). It exploits the fact that dead cells release DNA fragments into the circulation, and some DNA fragments carry information that indicates their tissues-of-origin (TOOs). Based on the signals used for identifying the TOOs of cfDNAs, the existing methods can be classified into three categories: cfDNA mutation-based methods, methylation pattern-based methods and cfDNA fragmentation pattern-based methods. In cfDNA mutation-based methods, the SNP information or the detected mutations in driven genes of certain diseases are employed to identify the TOOs of cfDNAs. Methylation pattern-based methods are developed to identify the TOOs of cfDNAs based on the tissue-specific methylation patterns. In cfDNA fragmentation pattern-based methods, cfDNA fragmentation patterns, such as nucleosome positioning or preferred end coordinates of cfDNAs, are used to predict the TOOs of cfDNAs. In this paper, the strategies and challenges in each category are reviewed. Furthermore, the representative applications based on the TOOs of cfDNAs, including noninvasive prenatal testing, noninvasive cancer screening, transplantation rejection monitoring and parasitic infection detection, are also reviewed. Moreover, the challenges and future work in identifying the TOOs of cfDNAs are discussed. Our research provides a comprehensive picture of the development and challenges in identifying the TOOs of cfDNAs, which may benefit bioinformatics researchers to develop new methods to improve the identification of the TOOs of cfDNAs.

Hybrid geological modeling: Combining machine learning and multiple-point statistics

Accurately modeling and constructing a geologically realistic subsurface model remains an outstanding problem as the morphology controls the flow behaviors. Particularly, one of the pattern-based methods, namely cross-correlation based simulation, has been proved to be an effective way to reconstruct a realistic model, at both small and large scales. However, conditioning to point data in the large-scale problems is still a crucial issue in these algorithms, since there is always a trade-off between the quality of the realizations and the degree of point data reproduction. Specifically, it is not practical to build a training image (TI) which includes all the possibilities and variabilities. Therefore, finding a pattern that can represent the point data and, at the same time, preserving the connectivities is difficult. This leads to producing highly-connected realizations with a significant mismatch or poor models with a reasonable degree of point data reproduction. To accurately reproduce the densely distributed hard data, pixel-based methods can also produce some unrealistic artifacts around the hard data. In this paper, to overcome this challenge, however, we use pattern-based methods as they often produce more disconnected geobodies when dealing with dense hard data, and proposed a hybrid algorithm using the pattern-based methods and convolutional neural network (CNN). The trained CNN model is utilized to improve the quality of conditioning to point data for the original realizations generated by the pattern-based algorithm. As such, the mismatch locations are identified, and the same regions are used in the training of CNN to mimic the procedure through which a missing region can be filled. To evaluate the performance of the proposed hybrid algorithm, it is tested on cases with different dimensions and different numbers of facies. Then, the newly improved realizations are compared with the initial realizations generated by the pattern-based algorithm. The comparison is also conducted by the flow simulation test. And it indicates that the proposed hybrid algorithm can better reproduce the point data, while the connectivities are better preserved.

Functionality Discovery and Prediction of Physical Objects

Functionality is a fundamental attribute of an object which indicates the capability to be used to perform specific actions. It is critical to empower robots the functionality knowledge in discovering appropriate objects for a task e.g. cut cake using knife. Existing research works have focused on understanding object functionality through human-object-interaction from extensively annotated image or video data and are hard to scale up. In this paper, we (1) mine object-functionality knowledge through pattern-based and model-based methods from text, (2) introduce a novel task on physical object-functionality prediction, which consumes an image and an action query to predict whether the object in the image can perform the action, and (3) propose a method to leverage the mined functionality knowledge for the new task. Our experimental results show the effectiveness of our methods.

A nonparametric framework for water consumption data cleansing: an application to a smart water network in Naples (Italy)

Abstract Remote monitoring and collection of water consumption has gained pivotal importance in the field of demand understanding, modelling and prediction. However, most of the analyses that can be performed on such databases could be jeopardized by inconsistencies due to technological or behavioural issues causing significant amounts of missing or anomalous values. In the present paper, a nonparametric, unsupervised approach is presented to investigate the reliability of a consumption database, applied to the dataset of a district metering area in Naples (Italy) and focused on the detection of suspicious amounts of zero or outlying data. Results showed that the methodology is effective in identifying criticalities both in terms of unreliable time series, namely time series having huge amounts of invalid data, and in terms of unreliable data, namely data values suspiciously different from some suitable central parameters, irrespective of the source causing the anomaly. As such, the proposed approach is suitable for large databases when no prior information is known about the underlying probability distribution of data, and it can also be coupled with other nonparametric, pattern-based methods in order to guarantee that the database to be analysed is homogeneous in terms of water uses.

Augmented Intention Model for Next-Location Prediction from Graphical Trajectory Context

Human trajectory prediction is an essential task for various applications such as travel recommendation, location-sensitive advertisement, and traffic planning. Most existing approaches are sequential-model based and produce a prediction by mining behavior patterns. However, the effectiveness of pattern-based methods is not as good as expected in real-life conditions, such as data sparse or data missing. Moreover, due to the technical limitations of sensors or the traffic situation at the given time, people going to the same place may produce different trajectories. Even for people traveling along the same route, the observed transit records are not exactly the same. Therefore trajectories are always diverse, and extracting user intention from trajectories is difficult. In this paper, we propose an augmented-intention recurrent neural network (AI-RNN) model to predict locations in diverse trajectories. We first propose three strategies to generate graph structures to demonstrate travel context and then leverage graph convolutional networks to augment user travel intentions under graph view. Finally, we use gated recurrent units with augmented node vectors to predict human trajectories. We experiment with two representative real-life datasets and evaluate the performance of the proposed model by comparing its results with those of other state-of-the-art models. The results demonstrate that the AI-RNN model outperforms other methods in terms of top-k accuracy, especially in scenarios with low similarity.

An efficient content-based medical image indexing and retrieval using local texture feature descriptors

This paper presents an efficient medical image indexing and retrieval method using two new proposed feature descriptors named as threshold local binary AND pattern (TLBAP) and local adjacent neighborhood average difference pattern (LANADP). In basic local binary pattern (LBP), every center pixel is considered as a threshold to generate the binary pattern, whereas in the proposed method a threshold value is calculated using the highest pixel intensity of the neighboring pixels to construct the threshold local binary pattern (TLBP). Thereafter, logical AND operation is performed between LBP and TLBP pattern to produce TLBAP pattern. The objective of the other feature descriptor named here as LANADP is to explore the relationship of neighboring pixels with its adjacent neighbors in vertical, horizontal and diagonal directions. In the proposed work, both TLBAP and LANADP features are concatenated in the form of the histograms to generate the final features vector and the performance of the system is evaluated. To test the effectiveness of the proposed method, three publicly available medical image databases, namely OASIS-MRI brain images, NEMA-CT images and VIA/ELCAP-CT images, are used. Two measures, viz. average retrieval precision and average retrieval rate, have been used to evaluate the performance of the method proposed which is further compared with some existing local pattern-based methods. The experimental results show that the proposed methods give better results as compared to the other existing methods considered in this study.

A Multiperson Behavior Feature Generation Model Based on Noise Reduction Using WiFi

Benefiting from modeling human behavior and the multipath propagation of wireless signals in the environment, passive behavior-sensing systems can effectively identify individual behaviors by model-based or pattern-based methods. The existing methods use an individual sample to model or profile behavior feature, which leads to their failure in multiperson scenarios due to time-varying environments. In this paper, an online method on modeling the position-behavior feature of multiperson scene is presented. First, a position-based model of individual behavioral feature transformation is proposed. The behavior features in other positions are generated by the behavior of the individual in a particular position. Second, a multiperson behavior feature generation method based on noise reduction is proposed to generate the same behavior feature in an online pattern. Finally, taking advantage of the models, a multiperson fitness coaching system is designed and implemented, named multiuser fitness coach. The system can identify the irregular behavior of individuals in the multiperson environment. The performance of the system is evaluated in different scenarios, and the results show that the precision of feature generation can be effectively applied to the decision of irregular behavior in multiperson scenarios.

Accelerating pattern-based time series classification: a linear time and space string mining approach

Subsequences-based time series classification algorithms provide interpretable and generally more accurate classification models compared to the nearest neighbor approach, albeit at a considerably higher computational cost. A number of discretized time series-based algorithms have been proposed to reduce the computational complexity of these algorithms; however, the asymptotic time complexity of the proposed algorithms is also cubic or higher-order polynomial. We present a remarkably fast and resource-efficient time series classification approach which employs a linear time and space string mining algorithm for extracting frequent patterns from discretized time series data. Compared to other subsequence or pattern-based classification algorithms, the proposed approach only requires a few parameters, which can be chosen arbitrarily and do not require any fine-tuning for different datasets. The time series data are discretized using symbolic aggregate approximation, and frequent patterns are extracted using a string mining algorithm. An independence test is used to select the most discriminative frequent patterns, which are subsequently used to create a transformed version of the time series data. Finally, a classification model can be trained using any off-the-shelf algorithm. Extensive empirical evaluations demonstrate the competitive classification accuracy of our approach compared to other state-of-the-art approaches. The experiments also show that our approach is at least one to two orders of magnitude faster than the existing pattern-based methods due to the extremely fast frequent pattern extraction, which is the most computationally intensive process in pattern-based time series classification approaches.