Search

Open source software has been widely used in various industries due to its openness and flexibility, but it also brings potential security problems. Therefore, security analysis is required before using open source software. The current mainstream open source software vulnerability analysis technology is based on source code, and there are problems such as false positives, false negatives and restatements. In order to solve the problems, based on the further study of behavior feature extraction and vulnerability detection technology, a method of using dynamic behavior features to detect open source software vulnerabilities is proposed. Firstly, the relationship between open source software vulnerability and API call sequence is studied. Then, the behavioral risk vulnerability database of open source software is proposed as a support for vulnerability detection. In addition, the CNN-IndRNN classification model is constructed by improving the Independently Recurrent Neural Net-work (IndRNN) algorithm and applies to open source software security vulnerability detection. The experimental results verify the effectiveness of the proposed open source software security vulnerability detection method based on dynamic behavior features. [ABSTRACT FROM AUTHOR]

An extreme learning machine (ELM) is a novel training method for single-hidden layer feedforward neural networks (SLFNs) in which the hidden nodes are randomly assigned and fixed without iterative tuning. ELMs have earned widespread global interest due to their fast learning speed, satisfactory generalization ability and ease of implementation. In this paper, we extend this theory to hypercomplex space and attempt to simultaneously consider multisource information using a hypercomplex representation. To illustrate the performance of the proposed hypercomplex extreme learning machine (HELM), we have applied this scheme to the task of multispectral palmprint recognition. Images from different spectral bands are utilized to construct the hypercomplex space. Extensive experiments conducted on the PolyU and CASIA multispectral databases demonstrate that the HELM scheme can achieve competitive results. The source code together with datasets involved in this paper can be available for free download at . [ABSTRACT FROM AUTHOR]

Background and objectives: ECG signal is relatively weak and vulnerable to various noise interferences, such as electromyography. There will be robustness problems when detecting the instantaneous heart rate independently. In some cases, multiple human physiologic parameters are monitored to help in heart rate detection. Methods: In this paper, an algorithm that marks the R-wave peaks with the help of simultaneously recorded continuous blood pressure is proposed and tested on two databases. One database, called the challenge database, is provided by the PhysioNet/Computing in Cardiology Challenge 2014, and the other is the MGH/MF waveform database. Results: The final scores of the proposed algorithm are 97.3% for the challenge database and 96.6% for the MGH/MF waveform database. Conclusions: The experimental results show that this algorithm has high detection accuracy and a relatively strong robustness. [ABSTRACT FROM AUTHOR]

Metabolic models can estimate intrinsic product yields for microbial factories, but such frameworks struggle to predict cell performance (including product titer or rate) under suboptimal metabolism and complex bioprocess conditions. On the other hand, machine learning, complementary to metabolic modeling necessitates large amounts of data. Building such a database for metabolic engineering designs requires significant manpower and is prone to human errors and bias. We propose an approach to integrate data-driven methods with genome scale metabolic model for assessment of microbial bio-production (yield, titer and rate). Using engineered E. coli as an example, we manually extracted and curated a data set comprising about 1200 experimentally realized cell factories from ~100 papers. We furthermore augmented the key design features (e.g., genetic modifications and bioprocess variables) extracted from literature with additional features derived from running the genome-scale metabolic model iML1515 simulations with constraints that match the experimental data. Then, data augmentation and ensemble learning (e.g., support vector machines, gradient boosted trees, and neural networks in a stacked regressor model) are employed to alleviate the challenges of sparse, non-standardized, and incomplete data sets, while multiple correspondence analysis/principal component analysis are used to rank influential factors on bio-production. The hybrid framework demonstrates a reasonably high cross-validation accuracy for prediction of E.coli factory performance metrics under presumed bioprocess and pathway conditions (Pearson correlation coefficients between 0.8 and 0.93 on new data not seen by the model). [ABSTRACT FROM AUTHOR]

Web service has become irreplaceable for service-oriented application in both academia and industry in recent years. Quality of Service (QoS) is used to describe the nonfunctional characteristics of Web service. Identifying Web service QoS is crucial for service-oriented application designers because service users may obtain very different QoS performance of the same service in the client-side due to dynamic changes of Internet environment as well as user context. However, evaluating QoS performance of a large scale of Web services requires considerable time and resources in real-world. Existing methods can make a personalized prediction for average QoS values by employing historical data but fail to take into consideration the fluctuation feature of Web service QoS values. To address this issue, this paper proposes a novel method for personalized QoS prediction of dynamic Web Services. First, a novel approach is used to extract feature points of QoS sequences and dynamic time warping distance is used to compute the similarity instead of Euclidean distance. By finding the most similar QoS sequences of the target QoS sequence, the missing QoS values can be predicted without extra Web services invoking. To validate our method, we conduct a large number of experiments based on real-world Web service QoS data set. The experimental studies show that our method has higher accuracy rate compared with the existing methods. [ABSTRACT FROM AUTHOR]

A significant approach for the discovery of biological regulatory rules of genes, protein and their inheritance relationships is the extraction of meaningful patterns from biological sequence data. The existing algorithms of sequence pattern discovery, like MSPM and FBSB, suffice their low efficiency and accuracy. In order to deal with this issue, this paper presents a new algorithm for biological sequence pattern mining abbreviated MpBsmi based on the data index structure. The MpBsmi algorithm employs a sequence position table abbreviated ST and a sequence database index structure named DB-Index for data storing, mining and pattern expansion. The ST and DB-Index of single items are firstly obtained through scanning sequence database once. Then a new algorithm for fast support counting is developed to mine the table ST to identify the frequent single items. Based on a connection strategy, the frequent patterns are expanded and the expanded table ST is updated by scanning the DB-Index. The fast support counting algorithm is used for obtaining the frequent expansion patterns. Finally, a new pruning technique is developed for extended pattern to avoid the generation of unnecessarily large number of candidate patterns. The experiments results on multiple classical protein sequences from the Pfam database validate the performance of the proposed algorithm including the accuracy, stability and scalability. It is showed that the proposed algorithm has achieved the better space efficiency, stability and scalability comparing with MSPM, FBSB which are the two main algorithms for biological sequence mining. [ABSTRACT FROM AUTHOR]

Approximate string matching with k-differences has a number of practical applications, ranging from pattern recognition to computational biology. This paper proposes an efficient memory-access algorithm for parallel approximate string matching with k-differences on Graphics Processing Units (GPUs). In the proposed algorithm, all threads in the same GPUs warp share data using warp-shuffle operation instead of accessing the shared memory. Moreover, we implement the proposed algorithm by exploiting the memory structure of GPUs to optimize its performance. Experiment results for real DNA packages revealed that the performance of the proposed algorithm and its implementation archived up to 122.64 and 1.53 times compared to that of sequential algorithm on CPU and previous parallel approximate string matching algorithm on GPUs, respectively. [ABSTRACT FROM AUTHOR]

Double cycling is an efficient tool to increase the efficiency of quay crane (QC) in container terminals. In this paper, an optimization model for double cycling is developed to optimize the operation sequence of multiple QCs. The objective is to minimize the makespan of the ship handling operation considering the ship balance constraint. To solve the model, an algorithm based on Lagrangian relaxation is designed. Finally, we compare the efficiency of the Lagrangian relaxation based heuristic with the branch-and-bound method and a genetic algorithm using instances of different sizes. The results of numerical experiments indicate that the proposed model can effectively reduce the unloading and loading times of QCs. The effects of the ship balance constraint are more notable when the number of QCs is high. [ABSTRACT FROM AUTHOR]

In big data area a significant challenge about string similarity join is to find all similar pairs more efficiently. In this paper, we propose a parallel processing framework for efficient string similarity join. First, the input is split into some disjoint small subsets according to the joint frequency distribution and the interval distribution of strings. Then the filter-verification strategy is adopted in the computation of string similarity for each subset so that the number of candidate pairs is reduced before an effective pruning strategy is used to improve the performance. Finally, the operation of string join is executed in parallel. Para-Join algorithm based on the multi-threading technique is proposed to implement the framework in a multi-core system while Pada-Join algorithm based on Spark platform is proposed to implement the framework in a cluster system. We prove that Para-Join and Pada-Join cannot only avoid reduplicate computation but also ensure the completeness of the result. Experimental results show that Para-Join can achieve high efficiency and significantly outperform than state-of-the-art approaches, meanwhile, Pada-Join can work on large datasets. [ABSTRACT FROM AUTHOR]

Information confidentiality is an essential requirement for cyber security in critical infrastructure. Identity-based cryptography, an increasingly popular branch of cryptography, is widely used to protect the information confidentiality in the critical infrastructure sector due to the ability to directly compute the user’s public key based on the user’s identity. However, computational requirements complicate the practical application of Identity-based cryptography. In order to improve the efficiency of identity-based cryptography, this paper presents an effective method to construct pairing-friendly elliptic curves with low hamming weight 4 under embedding degree 1. Based on the analysis of the Complex Multiplication(CM) method, the soundness of our method to calculate the characteristic of the finite field is proved. And then, three relative algorithms to construct pairing-friendly elliptic curve are put forward. 10 elliptic curves with low hamming weight 4 under 160 bits are presented to demonstrate the utility of our approach. Finally, the evaluation also indicates that it is more efficient to compute Tate pairing with our curves, than that of Bertoni et al. [ABSTRACT FROM AUTHOR]

Background: Identifying conserved regions in protein sequences is a fundamental operation, occurring in numerous sequence-driven analysis pipelines. It is used as a way to decode domain-rich regions within proteins, to compute protein clusters, to annotate sequence function, and to compute evolutionary relationships among protein sequences. A number of approaches exist for identifying and characterizing protein families based on their domains, and because domains represent conserved portions of a protein sequence, the primary computation involved in protein family characterization is identification of such conserved regions. However, identifying conserved regions from large collections (millions) of protein sequences presents significant challenges. Methods: In this paper we present a new, alignment-free method for detecting conserved regions in protein sequences called NADDA (No-Alignment Domain Detection Algorithm). Our method exploits the abundance of exact matching short subsequences (k-mers) to quickly detect conserved regions, and the power of machine learning is used to improve the prediction accuracy of detection. We present a parallel implementation of NADDA using the MapReduce framework and show that our method is highly scalable. Results: We have compared NADDA with Pfam and InterPro databases. For known domains annotated by Pfam, accuracy is 83%, sensitivity 96%, and specificity 44%. For sequences with new domains not present in the training set an average accuracy of 63% is achieved when compared to Pfam. A boost in results in comparison with InterPro demonstrates the ability of NADDA to capture conserved regions beyond those present in Pfam. We have also compared NADDA with ADDA and MKDOM2, assuming Pfam as ground-truth. On average NADDA shows comparable accuracy, more balanced sensitivity and specificity, and being alignment-free, is significantly faster. Excluding the one-time cost of training, runtimes on a single processor were 49s, 10,566s, and 456s for NADDA, ADDA, and MKDOM2, respectively, for a data set comprised of approximately 2500 sequences. [ABSTRACT FROM AUTHOR]

Forgery detection is essential to verify the integrity and authenticity of images. Existing block-based detection techniques detect forgery in the same image, most of which use similar frameworks while differ in the feature extraction schemes. These methods have high accuracy in detecting the forged regions, but the computational load is heavy when facing exhaustive search problems. This paper describes a forgery detection method based on local binary pattern residue classes and color regions. An image is divided into overlapped blocks. Local binary pattern residue classes are computed for each block. The plane formed by a dimensional and b dimensional from Lab color space is divided into 16 regions. Similar blocks are searched in the overlapped blocks with the same local binary pattern residue class and color region, then they are grouped into several suspicious regions. Finally, we analyze the multi-region relation of these suspicious regions and their areas to locate the tampered regions. The small hole is filled through the morphologic operation. The results of experiments demonstrated that our method has good performance in that it improved detection accuracy and reduced execution time under various challenging conditions. As the proposed method reduces the search range for similar blocks, it has a higher speed than exhaustive search and has comparable detection results at the same time. [ABSTRACT FROM AUTHOR]

In order to retrieve similar trademarks from large-scale trademark databases, combining the characteristics of trademark images, this paper presents a trademark image retrieval method based on regional and border feature fusion. Based on the target image extraction, the proposed approach describes the target region and border features. The region feature description is mainly based on the concept of partition block statistics. The region is divided into equal-area unit using concentric circles, and feature extraction is performed in each small block unit. For the border feature description, this study first detect corners, and then construct a Delaunay graph and extract features by combining the corner detected and the Delaunay triangulation reconstruction. In the search process, the method also incorporates information such as the trademark's color characteristics, trademark classification, and trademark keywords. The present study carried out image retrieval experiment on CE-SHAPE-1 database containing 1400 MPEG-7 core experimental shape, a classification trademark database containing 2000 images, and a national trademark database containing approximately 4.89 million images. The experimental results show that the proposed approach combines the advantages of region and border feature description, and can choose the best among various local optimizations, which makes the retrieval result more effective, more in line with human visual perception, and improves the retrieval accuracy. [ABSTRACT FROM AUTHOR]

To predict what products customers will buy in next transaction is an important task. Existing work in next-basket prediction can be summarized into two paradigms. One is the item-centric paradigm, where sequential patterns are mined from customers’ transactional data and leveraged for prediction. However, these approaches usually suffer from the data sparseness problem. The other is the user-centric paradigm, where collaborative filtering techniques have been applied on customers’ historical data. However, these methods ignore the sequential behaviors of customers which is often crucial for next-basket prediction. In this paper, we introduce a hybrid method, namely the Co-Factorization model over Sequential and Historical purchase data (CFSH for short) for next-basket recommendation. Compared with existing methods, our approach conveys the following merits: 1) By mining global sequential patterns, we can avoid the sparseness problem in traditional item-centric methods; 2) By factorizing product-product and customer-product matrices simultaneously, we can fully exploit both sequential and historical behaviors to learn customer and product representations better; 3) By using a hybrid recommendation method, we can achieve better performance in next-basket prediction. Experimental results on three real-world purchase datasets demonstrated the effectiveness of our approach as compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Due to recent developments in technologies associated with the Internet of Things (IoT), a large number of people now regularly use smart devices, such as smartwatches and smartphones. However, these devices are prone to data leaks because of security vulnerabilities. In particular, Android devices use permission-based security, which allows users to directly approve permissions requested by an app when installing it. As a result, many malicious apps can obtain and leak private user data by requesting more permissions than are needed. However, it is difficult to identify malicious apps based solely on the requested permissions. A system is hence needed to accurately identify malicious apps and protect private data from them. In this paper, we propose a system for hiding data related to a user’s contacts or providing virtual data according to preconfigured policies when an Android app requests access to them. By hiding data related to the contacts, the proposed system can protect them from malicious apps. By using virtual data, it can even detect malicious apps that leak private data. The system requires less storage and provides faster access to user contacts than prevalent solutions to similar problems. [ABSTRACT FROM AUTHOR]

Non-invasive fetal electrocardiography (ECG) is based on the acquisition of signals from abdominal surface electrodes. The composite abdominal signal consists of the maternal electrocardiogram along with the fetal electrocardiogram and other electrical interferences. These recordings allow for the acquisition of valuable and reliable information that helps ensure fetal well-being during pregnancy. This paper introduces a procedure for fetal heart rate extraction from a single-channel abdominal ECG signal. The procedure is composed of three main stages: a method based on wavelet for signal denoising, a new clustering-based methodology for detecting fetal QRS complexes, and a final stage to correct false positives and false negatives. The novelty of the procedure thus relies on using clustering techniques to classify singularities from the abdominal ECG into three types: maternal QRS complexes, fetal QRS complexes, and noise. The amplitude and time distance of all the local maxima followed by a local minimum were selected as features for the clustering classification. A wide set of real abdominal ECG recordings from two different databases, providing a large range of different characteristics, was used to illustrate the efficiency of the proposed method. The accuracy achieved shows that the proposed technique exhibits a competitve performance when compared to other recent works in the literature and a better performance over threshold-based techniques. [ABSTRACT FROM AUTHOR]

Arabic script is highly sensitive to changes in meaning with respect to the accurate arrangement of diacritics and other related symbols. The most sensitive Arabic text available online is the Digital Qur’an, the sacred book of Revelation in Islam that all Muslims including non-Arabs recite as part of their worship. Due to the different characteristics of the Arabic letters like diacritics (punctuation symbols), kashida (extended letters) and other symbols, it is written and available in different styles like Kufi, Naskh, Thuluth, Uthmani, etc. As social media has become part of our daily life, posting downloaded Qur’anic verses from the web is common. This leads to the problem of authenticating the selected Qur’anic passages available in different styles. This paper presents a residual approach for authenticating Uthmani and plain Qur’an verses using one common database. Residual (difference) is obtained by analyzing the differences between Uthmani and plain Quranic styles using XOR operation. Based on predefined data, the proposed approach converts Uthmani text into plain text. Furthermore, we propose to use the Tuned BM algorithm (BMT) exact pattern matching algorithm to verify the substituted Uthmani verse with a given database of plain Qur’anic style. Experimental results show that the proposed approach is useful and effective in authenticating multi-style texts of the Qur’an with 87.1% accuracy. [ABSTRACT FROM AUTHOR]

In this paper, we present a research work on a novel methodology of identifying abnormal behaviors at the underlying network monitor layer during runtime based on the execution patterns of Web of Things (WoT) applications. An execution pattern of a WoT application is a sequence of profiled time delays between the invocations of involved Web services, and it can be obtained from WoT platforms. We convert the execution pattern to a time sequence of network flows that are generated when the WoT applications are executed. We consider such time sequences as a whitelist. This whitelist reflects the valid application execution patterns. At the network monitor layer, our applied RETE algorithm examines whether any given runtime sequence of network flow instances does not conform to the whitelist. Through this approach, it is possible to interpret a sequence of network flows with regard to application logic. Given such contextual information, we believe that the administrators can detect and reason about any abnormal behaviors more effectively. Our empirical evaluation shows that our RETE-based algorithm outperforms the baseline algorithm in terms of memory usage. [ABSTRACT FROM AUTHOR]

In this paper, we propose a face recognition algorithm based on a combination of vector quantization (VQ) and Markov stationary features (MSF). The VQ algorithm has been shown to be an effective method for generating features; it extracts a codevector histogram as a facial feature representation for face recognition. Still, the VQ histogram features are unable to convey spatial structural information, which to some extent limits their usefulness in discrimination. To alleviate this limitation of VQ histograms, we utilize Markov stationary features (MSF) to extend the VQ histogram-based features so as to add spatial structural information. We demonstrate the effectiveness of our proposed algorithm by achieving recognition results superior to those of several state-of-the-art methods on publicly available face databases. [ABSTRACT FROM AUTHOR]

Proteomic analysis of cancers' stages has provided new opportunities for the development of novel, highly sensitive diagnostic tools which helps early detection of cancer. This paper introduces a new feature ranking approach called FRMT. FRMT is based on the Technique for Order of Preference by Similarity to Ideal Solution method (TOPSIS) which select the most discriminative proteins from proteomics data for cancer staging. In this approach, outcomes of 10 feature selection techniques were combined by TOPSIS method, to select the final discriminative proteins from seven different proteomic databases of protein expression profiles. In the proposed workflow, feature selection methods and protein expressions have been considered as criteria and alternatives in TOPSIS, respectively. The proposed method is tested on seven various classifier models in a 10-fold cross validation procedure that repeated 30 times on the seven cancer datasets. The obtained results proved the higher stability and superior classification performance of method in comparison with other methods, and it is less sensitive to the applied classifier. Moreover, the final introduced proteins are informative and have the potential for application in the real medical practice. [ABSTRACT FROM AUTHOR]

High-utility sequential pattern mining (HUSPM) has become an important issue in the field of data mining. Several HUSPM algorithms have been designed to mine high-utility sequential patterns (HUPSPs). They have been applied in several real-life situations such as for consumer behavior analysis and event detection in sensor networks. Nonetheless, most studies on HUSPM have focused on mining HUPSPs in precise data. But in real-life, uncertainty is an important factor as data is collected using various types of sensors that are more or less accurate. Hence, data collected in a real-life database can be annotated with existing probabilities. This paper presents a novel pattern mining framework called high utility-probability sequential pattern mining (HUPSPM) for mining high utility-probability sequential patterns (HUPSPs) in uncertain sequence databases. A baseline algorithm with three optional pruning strategies is presented to mine HUPSPs. Moroever, to speed up the mining process, a projection mechanism is designed to create a database projection for each processed sequence, which is smaller than the original database. Thus, the number of unpromising candidates can be greatly reduced, as well as the execution time for mining HUPSPs. Substantial experiments both on real-life and synthetic datasets show that the designed algorithm performs well in terms of runtime, number of candidates, memory usage, and scalability for different minimum utility and minimum probability thresholds. [ABSTRACT FROM AUTHOR]

Public cloud storage services are becoming prevalent and myriad data sharing, archiving and collaborative services have emerged which harness the pay-as-you-go business model of public cloud. To ensure privacy and confidentiality often encrypted data is outsourced to such services, which further complicates the process of accessing relevant data by using search queries. Search over encrypted data schemes solve this problem by exploiting cryptographic primitives and secure indexing to identify outsourced data that satisfy the search criteria. Almost all of these schemes rely on exact matching between the encrypted data and search criteria. A few schemes which extend the notion of exact matching to similarity based search, lack realism as those schemes rely on trusted third parties or due to increase storage and computational complexity. In this paper we propose Oblivious Similarity based Search () for encrypted data. It enables authorized users to model their own encrypted search queries which are resilient to typographical errors. Unlike conventional methodologies, ranks the search results by using similarity measure offering a better search experience than exact matching. It utilizes encrypted bloom filter and probabilistic homomorphic encryption to enable authorized users to access relevant data without revealing results of search query evaluation process to the untrusted cloud service provider. Encrypted bloom filter based search enables to reduce search space to potentially relevant encrypted data avoiding unnecessary computation on public cloud. The efficacy of is evaluated on Google App Engine for various bloom filter lengths on different cloud configurations. [ABSTRACT FROM AUTHOR]

This paper describes the design, acquisition process and baseline evaluation of the new e-BioSign database, which includes dynamic signature and handwriting information. Data is acquired from 5 different COTS devices: three Wacom devices (STU-500, STU-530 and DTU-1031) specifically designed to capture dynamic signatures and handwriting, and two general purpose tablets (Samsung Galaxy Note 10.1 and Samsung ATIV 7). For the two Samsung tablets, data is collected using both pen stylus and also the finger in order to study the performance of signature verification in a mobile scenario. Data was collected in two sessions for 65 subjects, and includes dynamic information of the signature, the full name and alpha numeric sequences. Skilled forgeries were also performed for signatures and full names. We also report a benchmark evaluation based on e-BioSign for person verification under three different real scenarios: 1) intra-device, 2) inter-device, and 3) mixed writing-tool. We have experimented the proposed benchmark using the main existing approaches for signature verification: feature- and time functions-based. As a result, new insights into the problem of signature biometrics in sensor-interoperable scenarios have been obtained, namely: the importance of specific methods for dealing with device interoperability, and the necessity of a deeper analysis on signatures acquired using the finger as the writing tool. This e-BioSign public database allows the research community to: 1) further analyse and develop signature verification systems in realistic scenarios, and 2) investigate towards a better understanding of the nature of the human handwriting when captured using electronic COTS devices in realistic conditions. [ABSTRACT FROM AUTHOR]

As the quality of crucial entities can directly affect that of software, their identification and protection become an important premise for effective software development, management, maintenance and testing, which thus contribute to improving the software quality and its attack-defending ability. Most analysis and evaluation on important entities like codes-based static structure analysis are on the destruction of the actual software running. In this paper, from the perspective of software execution process, we proposed an approach to mine dynamic noteworthy functions (DNFM)in software execution sequences. First, according to software decompiling and tracking stack changes, the execution traces composed of a series of function addresses were acquired. Then these traces were modeled as execution sequences and then simplified so as to get simplified sequences (SFS), followed by the extraction of patterns through pattern extraction (PE) algorithm from SFS. After that, evaluating indicators inner-importance and inter-importance were designed to measure the noteworthiness of functions in DNFM algorithm. Finally, these functions were sorted by their noteworthiness. Comparison and contrast were conducted on the experiment results from two traditional complex network-based node mining methods, namely PageRank and DegreeRank. The results show that the DNFM method can mine noteworthy functions in software effectively and precisely. [ABSTRACT FROM AUTHOR]

The 3D High Efficiency Video Coding (3D-HEVC) standard aims to code 3D videos that usually contain multi-view texture videos and its corresponding depth information. It inherits the same quadtree prediction structure of HEVC to code both texture videos and depth maps. Each coding unit (CU) allows recursively splitting into four equal sub-CUs. At each CU depth level, it enables 10 types of inter modes and 35 types of intra modes in inter frames. Furthermore, the inter-view prediction tools are applied to each view in the test model of 3D-HEVC (HTM), which uses variable size disparity-compensated prediction to exploit inter-view correlation within neighbor views. It also exploits redundancies between a texture video and its associated depth using inter-component coding tools. These achieve the highest coding efficiency to code 3D videos but require a very high computational complexity. In this paper, we propose a context-adaptive based fast CU processing algorithm to jointly optimize the most complex components of HTM including CU depth level decision, mode decision, motion estimation (ME) and disparity estimation (DE) processes. It is based on the hypothesis that the optimal CU depth level, prediction mode and motion vector of a CU are correlated with those from spatiotemporal, inter-view and inter-component neighboring CUs. We analyze the video content based on coding information from neighboring CUs and early predict each CU into one of five categories i.e., DE-omitted CU, ME-DE-omitted CU, SPLIT CU, Non-SPLIT CU and normal CU, and then each type of CU adaptively adopts different processing strategies. Experimental results show that the proposed algorithm saves 70% encoder runtime on average with only a 0.1% BD-rate increase on coded views and 0.8% BD-rate increase on synthesized views. Our algorithm outperforms the state-of-the-art algorithms in terms of coding time saving or with better RD performance. [ABSTRACT FROM AUTHOR]

Cipher-policy attribute-based encryption (CP-ABE) focus on the problem of access control, and keyword-based searchable encryption scheme focus on the problem of finding the files that the user interested in the cloud storage quickly. To design a searchable and attribute-based encryption scheme is a new challenge. In this paper, we propose an efficiently multi-user searchable attribute-based encryption scheme with attribute revocation and grant for cloud storage. In the new scheme the attribute revocation and grant processes of users are delegated to proxy server. Our scheme supports multi attribute are revoked and granted simultaneously. Moreover, the keyword searchable function is achieved in our proposed scheme. The security of our proposed scheme is reduced to the bilinear Diffie-Hellman (BDH) assumption. Furthermore, the scheme is proven to be secure under the security model of indistinguishability against selective ciphertext-policy and chosen plaintext attack (IND-sCP-CPA). And our scheme is also of semantic security under indistinguishability against chosen keyword attack (IND-CKA) in the random oracle model. [ABSTRACT FROM AUTHOR]

Retinal microaneurysms (MAs) are the earliest clinically observable lesions of diabetic retinopathy. Reliable automated MAs detection is thus critical for early diagnosis of diabetic retinopathy. This paper proposes a novel method for the automated MAs detection in color fundus images based on gradient vector analysis and class imbalance classification, which is composed of two stages, i.e. candidate MAs extraction and classification. In the first stage, a candidate MAs extraction algorithm is devised by analyzing the gradient field of the image, in which a multi-scale log condition number map is computed based on the gradient vectors for vessel removal, and then the candidate MAs are localized according to the second order directional derivatives computed in different directions. Due to the complexity of fundus image, besides a small number of true MAs, there are also a large amount of non-MAs in the extracted candidates. Classifying the true MAs and the non-MAs is an extremely class imbalanced classification problem. Therefore, in the second stage, several types of features including geometry, contrast, intensity, edge, texture, region descriptors and other features are extracted from the candidate MAs and a class imbalance classifier, i.e., RUSBoost, is trained for the MAs classification. With the Retinopathy Online Challenge (ROC) criterion, the proposed method achieves an average sensitivity of 0.433 at 1/8, 1/4, 1/2, 1, 2, 4 and 8 false positives per image on the ROC database, which is comparable with the state-of-the-art approaches, and 0.321 on the DiaRetDB1 V2.1 database, which outperforms the state-of-the-art approaches. [ABSTRACT FROM AUTHOR]

Spatial-temporal k-anonymity has become a mainstream approach among techniques for protection of users’ privacy in location-based services (LBS) applications, and has been applied to several variants such as LBS snapshot queries and continuous queries. Analyzing large-scale spatial-temporal anonymity sets may benefit several LBS applications. In this paper, we propose two location prediction methods based on transition probability matrices constructing from sequential rules for spatial-temporal k-anonymity dataset. First, we define single-step sequential rules mined from sequential spatial-temporal k-anonymity datasets generated from continuous LBS queries for multiple users. We then construct transition probability matrices from mined single-step sequential rules, and normalize the transition probabilities in the transition matrices. Next, we regard a mobility model for an LBS requester as a stationary stochastic process and compute the n-step transition probability matrices by raising the normalized transition probability matrices to the power n. Furthermore, we propose two location prediction methods: rough prediction and accurate prediction. The former achieves the probabilities of arriving at target locations along simple paths those include only current locations, target locations and transition steps. By iteratively combining the probabilities for simple paths with n steps and the probabilities for detailed paths with n-1 steps, the latter method calculates transition probabilities for detailed paths with n steps from current locations to target locations. Finally, we conduct extensive experiments, and correctness and flexibility of our proposed algorithm have been verified. [ABSTRACT FROM AUTHOR]

Fingerprint recognition plays an important role in many commercial applications and is used by millions of people every day, e.g. for unlocking mobile phones. Fingerprint image segmentation is typically the first processing step of most fingerprint algorithms and it divides an image into foreground, the region of interest, and background. Two types of error can occur during this step which both have a negative impact on the recognition performance: ‘true’ foreground can be labeled as background and features like minutiae can be lost, or conversely ‘true’ background can be misclassified as foreground and spurious features can be introduced. The contribution of this paper is threefold: firstly, we propose a novel factorized directional bandpass (FDB) segmentation method for texture extraction based on the directional Hilbert transform of a Butterworth bandpass (DHBB) filter interwoven with soft-thresholding. Secondly, we provide a manually marked ground truth segmentation for 10560 images as an evaluation benchmark. Thirdly, we conduct a systematic performance comparison between the FDB method and four of the most often cited fingerprint segmentation algorithms showing that the FDB segmentation method clearly outperforms these four widely used methods. The benchmark and the implementation of the FDB method are made publicly available. [ABSTRACT FROM AUTHOR]

The differential evolution algorithm has been widely applied on unmanned aerial vehicle (UAV) path planning. At present, four random tuning parameters exist for differential evolution algorithm, namely, population size, differential weight, crossover, and generation number. These tuning parameters are required, together with user setting on path and computational cost weightage. However, the optimum settings of these tuning parameters vary according to application. Instead of trial and error, this paper presents an optimization method of differential evolution algorithm for tuning the parameters of UAV path planning. The parameters that this research focuses on are population size, differential weight, crossover, and generation number. The developed algorithm enables the user to simply define the weightage desired between the path and computational cost to converge with the minimum generation required based on user requirement. In conclusion, the proposed optimization of tuning parameters in differential evolution algorithm for UAV path planning expedites and improves the final output path and computational cost. [ABSTRACT FROM AUTHOR]

The research on service supply chain has attracted more and more focus from both academia and industrial community. In a service supply chain, the selection of supplier portfolio is an important and difficult problem due to the fact that a supplier portfolio may include multiple suppliers from a variety of fields. To address this problem, we propose a novel supplier portfolio selection method based on a well known machine learning approach, i.e., Ranking Neural Network (RankNet). In the proposed method, we regard the problem of supplier portfolio selection as a ranking problem, which integrates a large scale of decision making features into a ranking neural network. Extensive simulation experiments are conducted, which demonstrate the feasibility and effectiveness of the proposed method. The proposed supplier portfolio selection model can be applied in a real corporation easily in the future. [ABSTRACT FROM AUTHOR]

In life sciences, accompanied by the rapid growth of sequencing technology and the advancement of research, vast amounts of data are being generated. It is known that as the size of Resource Description Framework (RDF) datasets increases, the more efficient loading to triple stores is crucial. For example, UniProt’s RDF version contains 44 billion triples as of December 2018. PubChem also has an RDF dataset with 137 billion triples. As data sizes become extremely large, loading them to a triple store consumes time. To improve the efficiency of this task, parallel loading has been recommended for several stores. However, with parallel loading, dataset consistency must be considered if the dataset contains blank nodes. By definition, blank nodes do not have global identifiers; thus, pairs of identical blank nodes in the original dataset are recognized as different if they reside in separate files after the dataset is split for parallel loading. To address this issue, we propose the Split4Blank tool, which splits a dataset into multiple files under the condition that identical blank nodes are not separated. The proposed tool uses connected component and multiprocessor scheduling algorithms and satisfies the above condition. Furthermore, to confirm the effectiveness of the proposed approach, we applied Split4Blank to two life sciences RDF datasets. In addition, we generated synthetic RDF datasets to evaluate scalability based on the properties of various graphs, such as a scale-free and random graph. [ABSTRACT FROM AUTHOR]

In psychotherapy, movement synchrony seems to be associated with higher patient satisfaction and treatment outcome. However, it remains unclear whether movement synchrony rated by humans and movement synchrony identified by automated methods reflect the same construct. To address this issue, video sequences showing movement synchrony of patients and therapists (N = 10) or not (N = 10), were analyzed using motion energy analysis. Three different synchrony conditions with varying levels of complexity (naturally embedded, naturally isolated, and artificial) were generated for time series analysis with windowed cross-lagged correlation/ -regression (WCLC, WCLR). The concordance of ratings (human rating vs. automatic assessment) was computed for 600 different parameter configurations of the WCLC/WCLR to identify the parameter settings that measure movement synchrony best. A parameter configuration was rated as having a good identification rate if it yields high concordance with human-rated intervals (Cohen’s kappa) and a low amount of over-identified data points. Results indicate that 76 configurations had a good identification rate (IR) in the least complex condition (artificial). Two had an acceptable IR with regard to the naturally isolated condition. Concordance was low with regard to the most complex (naturally embedded) condition. A valid identification of movement synchrony strongly depends on parameter configuration and goes beyond the identification of synchrony by human raters. Differences between human-rated synchrony and nonverbal synchrony measured by algorithms are discussed. [ABSTRACT FROM AUTHOR]

Different performance measures are used to assess the behaviour, and to carry out the comparison, of classifiers in Machine Learning. Many measures have been defined on the literature, and among them, a measure inspired by Shannon’s entropy named the Confusion Entropy (CEN). In this work we introduce a new measure, MCEN, by modifying CEN to avoid its unwanted behaviour in the binary case, that disables it as a suitable performance measure in classification. We compare MCEN with CEN and other performance measures, presenting analytical results in some particularly interesting cases, as well as some heuristic computational experimentation. [ABSTRACT FROM AUTHOR]

The security strength of the traditional one-time-pad encryption system depends on the randomness of the secret key. However, It can hardly to generatea truerandom key by using the existing technologies and methods, and it is also difficult to issue and store the random keywhich is at least as long as the plaintext. Therefore, we pay more attention to the logical operation used in the encryption and decryption but not to how to generate the random key. The calculator, a three-dimensional DNA self-assembly pyramid structure, is designed to construct four common logical operations (AND, OR, NOT, XOR) by programming DNA interactions. And two novel one-time-pad cryptography schemes, a single-bit one-time-pad algorithm and improved double-bit one-time-pad algorithm, are proposed based on the calculator. The security fragments, used to construct the three-dimensional DNA self-assembly pyramid structure, are intercepted from a reference chain which is selected from the DNA database. All of the interception parameters are transmitted to recipient by hiding in DNA sequences. Only the authorized user can get all secret parameters to reconstruct the structure. The secret random key sequences for the two one-time-pad cryptography algorithms are generated by using logistic map. It only needs to share two parameters and thresholding function in sender and recipient without code books. The simulation results and security analysis show that the encryption algorithms are effective and can provide higher computational complexity as well as a reduced cracking probability except for the difficult of biological experiments. [ABSTRACT FROM AUTHOR]

With the development of outsourcing data services, data security has become an urgent problem that needs to be solved. Attribute-based encryption is a valid solution to data security in cloud storage. There is no existing scheme that can guarantee the privacy of access structures and achieve attribute-based encryption with keyword search and attribute revocation. In this article, we propose a new searchable and revocable multi-data owner attribute-based encryption scheme with a hidden policy in cloud storage. In the new scheme, the same access policy is used in both the keyword index and message encryption. The advantage of keyword index with access policy is that as long as a user’s attributes satisfy the access policy, the searched ciphertext can be correctly decrypted. This property improves the accuracy of the search results. The hidden policy is used in both the ciphertext and the keyword index to protect users’ privacy. The new scheme contains attribute revocation, which is suitable for the actual situation that a user’s attributes maybe changed over time. In the general bilinear group model, the security of the scheme is demonstrated, and the efficiency of the scheme is analyzed. [ABSTRACT FROM AUTHOR]

The minimization of open stacks problem (MOSP) aims to determine the ideal production sequence to optimize the occupation of physical space in manufacturing settings. Most of current methods for solving the MOSP were not designed to work with large instances, precluding their use in specific cases of similar modeling problems. We therefore propose a PageRank-based heuristic to solve large instances modeled in graphs. In computational experiments, both data from the literature and new datasets up to 25 times fold larger in input size than current datasets, totaling 1330 instances, were analyzed to compare the proposed heuristic with state-of-the-art methods. The results showed the competitiveness of the proposed heuristic in terms of quality, as it found optimal solutions in several cases, and in terms of shorter run times compared with the fastest available method. Furthermore, based on specific graph densities, we found that the difference in the value of solutions between methods was small, thus justifying the use of the fastest method. The proposed heuristic is scalable and is more affected by graph density than by size. [ABSTRACT FROM AUTHOR]

Exact pattern matching algorithms are popular and used widely in several applications, such as molecular biology, text processing, image processing, web search engines, network intrusion detection systems and operating systems. The focus of these algorithms is to achieve time efficiency according to applications but not memory consumption. In this work, we propose a novel idea to achieve both time efficiency and memory consumption by splitting query string for searching in Corpus. For a given text, the proposed algorithm split the query pattern into two equal halves and considers the second (right) half as a query string for searching in Corpus. Once the match is found with second halves, the proposed algorithm applies brute force procedure to find remaining match by referring the location of right half. Experimental results on different S1 Dataset, namely Arabic, English, Chinese, Italian and French text databases show that the proposed algorithm outperforms the existing S1 Algorithm in terms of time efficiency and memory consumption as the length of the query pattern increases. [ABSTRACT FROM AUTHOR]

Patient registry data are commonly collected as annual snapshots that need to be amalgamated to understand the longitudinal progress of each patient. However, patient identifiers can either change or may not be available for legal reasons when longitudinal data are collated from patients living in different countries. Here, we apply astronomical statistical matching techniques to link individual patient records that can be used where identifiers are absent or to validate uncertain identifiers. We adopt a Bayesian model framework used for probabilistically linking records in astronomy. We adapt this and validate it across blinded, annually collected data. This is a high-quality (Danish) sub-set of data held in the European Cystic Fibrosis Society Patient Registry (ECFSPR). Our initial experiments achieved a precision of 0.990 at a recall value of 0.987. However, detailed investigation of the discrepancies uncovered typing errors in 27 of the identifiers in the original Danish sub-set. After fixing these errors to create a new gold standard our algorithm correctly linked individual records across years achieving a precision of 0.997 at a recall value of 0.987 without recourse to identifiers. Our Bayesian framework provides the probability of whether a pair of records belong to the same patient. Unlike other record linkage approaches, our algorithm can also use physical models, such as body mass index curves, as prior information for record linkage. We have shown our framework can create longitudinal samples where none existed and validate pre-existing patient identifiers. We have demonstrated that in this specific case this automated approach is better than the existing identifiers. [ABSTRACT FROM AUTHOR]

Studies in sentiment analysis and opinion mining have been focused on many aspects related to opinions, namely polarity classification by making use of positive, negative or neutral values. However, most studies have overlooked the identification of extreme opinions (most negative and most positive opinions) in spite of their vast significance in many applications. We use an unsupervised approach to search for extreme opinions, which is based on the automatic construction of a new lexicon containing the most negative and most positive words. [ABSTRACT FROM AUTHOR]

A common goal in data-analysis is to sift through a large data-matrix and detect any significant submatrices (i.e., biclusters) that have a low numerical rank. We present a simple algorithm for tackling this biclustering problem. Our algorithm accumulates information about 2-by-2 submatrices (i.e., ‘loops’) within the data-matrix, and focuses on rows and columns of the data-matrix that participate in an abundance of low-rank loops. We demonstrate, through analysis and numerical-experiments, that this loop-counting method performs well in a variety of scenarios, outperforming simple spectral methods in many situations of interest. Another important feature of our method is that it can easily be modified to account for aspects of experimental design which commonly arise in practice. For example, our algorithm can be modified to correct for controls, categorical- and continuous-covariates, as well as sparsity within the data. We demonstrate these practical features with two examples; the first drawn from gene-expression analysis and the second drawn from a much larger genome-wide-association-study (GWAS). [ABSTRACT FROM AUTHOR]

Many modern applications of AI such as web search, mobile browsing, image processing, and natural language processing rely on finding similar items from a large database of complex objects. Due to the very large scale of data involved (e.g., users’ queries from commercial search engines), computing such near or nearest neighbors is a non-trivial task, as the computational cost grows significantly with the number of items. To address this challenge, we adopt Locality Sensitive Hashing (a.k.a, ) methods and evaluate four variants in a distributed computing environment (specifically, Hadoop). We identify several optimizations which improve performance, suitable for deployment in very large scale settings. The experimental results demonstrate our variants of achieve the robust performance with better recall compared with “vanilla” , even when using the same amount of space. [ABSTRACT FROM AUTHOR]

One method of solving the single-image super-resolution problem is to use Heaviside functions. This has been done previously by making a binary classification of image components as “smooth” and “non-smooth”, describing these with approximated Heaviside functions (AHFs), and iteration including l1 regularization. We now introduce a new method in which the binary classification of image components is extended to different degrees of smoothness and non-smoothness, these components being represented by various classes of AHFs. Taking into account the sparsity of the non-smooth components, their coefficients are l1 regularized. In addition, to pick up more image details, the new method uses an iterative refinement for the residuals between the original low-resolution input and the downsampled resulting image. Experimental results showed that the new method is superior to the original AHF method and to four other published methods. [ABSTRACT FROM AUTHOR]

Registration of laser scans, or point clouds in general, is a crucial step of localization and mapping with mobile robots or in object modeling pipelines. A coarse alignment of the point clouds is generally needed before applying local methods such as the Iterative Closest Point (ICP) algorithm. We propose a feature-based approach to point cloud registration and evaluate the proposed method and its individual components on challenging real-world datasets. For a moderate overlap between the laser scans, the method provides a superior registration accuracy compared to state-of-the-art methods including Generalized ICP, 3D Normal-Distribution Transform, Fast Point-Feature Histograms, and 4-Points Congruent Sets. Compared to the surface normals, the points as the underlying features yield higher performance in both keypoint detection and establishing local reference frames. Moreover, sign disambiguation of the basis vectors proves to be an important aspect in creating repeatable local reference frames. A novel method for sign disambiguation is proposed which yields highly repeatable reference frames. [ABSTRACT FROM AUTHOR]

Reducing duplicated data of database backups is an important application scenario for data deduplication technology. NewSQL is an emerging database system and is now being used more and more widely. NewSQL systems need to improve data reliability by periodically backing up in-memory data, resulting in a lot of duplicated data. The traditional deduplication method is not optimized for the NewSQL server system and cannot take full advantage of hardware resources to optimize deduplication performance. A recent research pointed out that the future NewSQL server will have thousands of CPU cores, large DRAM and huge NVRAM. Therefore, how to utilize these hardware resources to optimize the performance of data deduplication is an important issue. To solve this problem, we propose a deduplication optimization method (DOMe) for NewSQL system backup. To take advantage of the large number of CPU cores in the NewSQL server to optimize deduplication performance, DOMe parallelizes the deduplication method based on the fork-join framework. The fingerprint index, which is the key data structure in the deduplication process, is implemented as pure in-memory hash table, which makes full use of the large DRAM in NewSQL system, eliminating the performance bottleneck problem of fingerprint index existing in traditional deduplication method. The H-store is used as a typical NewSQL database system to implement DOMe method. DOMe is experimentally analyzed by two representative backup data. The experimental results show that: 1) DOMe can reduce the duplicated NewSQL backup data. 2) DOMe significantly improves deduplication performance by parallelizing CDC algorithms. In the case of the theoretical speedup ratio of the server is 20.8, the speedup ratio of DOMe can achieve up to 18; 3) DOMe improved the deduplication throughput by 1.5 times through the pure in-memory index optimization method. [ABSTRACT FROM AUTHOR]

The adaptation of the CRISPR-Cas9 system as a genome editing technique has generated much excitement in recent years owing to its ability to manipulate targeted genes and genomic regions that are complementary to a programmed single guide RNA (sgRNA). However, the efficacy of a specific sgRNA is not uniquely defined by exact sequence homology to the target site, thus unintended off-targets might additionally be cleaved. Current methods for sgRNA design are mainly concerned with predicting off-targets for a given sgRNA using basic sequence features and employ elementary rules for ranking possible sgRNAs. Here, we introduce CRISTA (CRISPR Target Assessment), a novel algorithm within the machine learning framework that determines the propensity of a genomic site to be cleaved by a given sgRNA. We show that the predictions made with CRISTA are more accurate than other available methodologies. We further demonstrate that the occurrence of bulges is not a rare phenomenon and should be accounted for in the prediction process. Beyond predicting cleavage efficiencies, the learning process provides inferences regarding patterns that underlie the mechanism of action of the CRISPR-Cas9 system. We discover that attributes that describe the spatial structure and rigidity of the entire genomic site as well as those surrounding the PAM region are a major component of the prediction capabilities. [ABSTRACT FROM AUTHOR]

Integration of sensory information across multiple senses is most likely to occur when signals are spatiotemporally coupled. Yet, recent research on audiovisual rate discrimination indicates that random sequences of light flashes and auditory clicks are integrated optimally regardless of temporal correlation. This may be due to 1) temporal averaging rendering temporal cues less effective; 2) difficulty extracting causal-inference cues from rapidly presented stimuli; or 3) task demands prompting integration without concern for the spatiotemporal relationship between the signals. We conducted a rate-discrimination task (Exp 1), using slower, more random sequences than previous studies, and a separate causal-judgement task (Exp 2). Unisensory and multisensory rate-discrimination thresholds were measured in Exp 1 to assess the effects of temporal correlation and spatial congruence on integration. The performance of most subjects was indistinguishable from optimal for spatiotemporally coupled stimuli, and generally sub-optimal in other conditions, suggesting observers used a multisensory mechanism that is sensitive to both temporal and spatial causal-inference cues. In Exp 2, subjects reported whether temporally uncorrelated (but spatially co-located) sequences were perceived as sharing a common source. A unified percept was affected by click-flash pattern similarity and the maximum temporal offset between individual clicks and flashes, but not on the proportion of synchronous click-flash pairs. A simulation analysis revealed that the stimulus-generation algorithms of previous studies is likely responsible for the observed integration of temporally independent sequences. By combining results from Exps 1 and 2, we found better rate-discrimination performance for sequences that are more likely to be integrated than those that are not. Our results support the principle that multisensory stimuli are optimally integrated when spatiotemporally coupled, and provide insight into the temporal features used for coupling in causal inference. [ABSTRACT FROM AUTHOR]

Analyzing large-scale spatial-temporal k-anonymity datasets recorded in location-based service (LBS) application servers can benefit some LBS applications. However, such analyses can allow adversaries to make inference attacks that cannot be handled by spatial-temporal k-anonymity methods or other methods for protecting sensitive knowledge. In response to this challenge, first we defined a destination location prediction attack model based on privacy-sensitive sequence rules mined from large scale anonymity datasets. Then we proposed a novel on-line spatial-temporal k-anonymity method that can resist such inference attacks. Our anti-attack technique generates new anonymity datasets with awareness of privacy-sensitive sequence rules. The new datasets extend the original sequence database of anonymity datasets to hide the privacy-sensitive rules progressively. The process includes two phases: off-line analysis and on-line application. In the off-line phase, sequence rules are mined from an original sequence database of anonymity datasets, and privacy-sensitive sequence rules are developed by correlating privacy-sensitive spatial regions with spatial grid cells among the sequence rules. In the on-line phase, new anonymity datasets are generated upon LBS requests by adopting specific generalization and avoidance principles to hide the privacy-sensitive sequence rules progressively from the extended sequence anonymity datasets database. We conducted extensive experiments to test the performance of the proposed method, and to explore the influence of the parameter K value. The results demonstrated that our proposed approach is faster and more effective for hiding privacy-sensitive sequence rules in terms of hiding sensitive rules ratios to eliminate inference attacks. Our method also had fewer side effects in terms of generating new sensitive rules ratios than the traditional spatial-temporal k-anonymity method, and had basically the same side effects in terms of non-sensitive rules variation ratios with the traditional spatial-temporal k-anonymity method. Furthermore, we also found the performance variation tendency from the parameter K value, which can help achieve the goal of hiding the maximum number of original sensitive rules while generating a minimum of new sensitive rules and affecting a minimum number of non-sensitive rules. [ABSTRACT FROM AUTHOR]

Scientists have unprecedented access to a wide variety of high-quality datasets. These datasets, which are often independently curated, commonly use unstructured spreadsheets to store their data. Standardized annotations are essential to perform synthesis studies across investigators, but are often not used in practice. Therefore, accurately combining records in spreadsheets from differing studies requires tedious and error-prone human curation. These efforts result in a significant time and cost barrier to synthesis research. We propose an information retrieval inspired algorithm, Synthesize, that merges unstructured data automatically based on both column labels and values. Application of the Synthesize algorithm to cancer and ecological datasets had high accuracy (on the order of 85–100%). We further implement Synthesize in an open source web application, Synthesizer (). The software accepts input as spreadsheets in comma separated value (CSV) format, visualizes the merged data, and outputs the results as a new spreadsheet. Synthesizer includes an easy to use graphical user interface, which enables the user to finish combining data and obtain perfect accuracy. Future work will allow detection of units to automatically merge continuous data and application of the algorithm to other data formats, including databases. [ABSTRACT FROM AUTHOR]

Objectives: This study evaluates the accuracy and transferability of Bayesian case detection systems (BCD) that use clinical notes from emergency department (ED) to detect influenza cases. Methods: A BCD uses natural language processing (NLP) to infer the presence or absence of clinical findings from ED notes, which are fed into a Bayesain network classifier (BN) to infer patients’ diagnoses. We developed BCDs at the University of Pittsburgh Medical Center (BCDUPMC) and Intermountain Healthcare in Utah (BCDIH). At each site, we manually built a rule-based NLP and trained a Bayesain network classifier from over 40,000 ED encounters between Jan. 2008 and May. 2010 using feature selection, machine learning, and expert debiasing approach. Transferability of a BCD in this study may be impacted by seven factors: development (source) institution, development parser, application (target) institution, application parser, NLP transfer, BN transfer, and classification task. We employed an ANOVA analysis to study their impacts on BCD performance. Results: Both BCDs discriminated well between influenza and non-influenza on local test cases (AUCs > 0.92). When tested for transferability using the other institution’s cases, BCDUPMC discriminations declined minimally (AUC decreased from 0.95 to 0.94, p<0.01), and BCDIH discriminations declined more (from 0.93 to 0.87, p<0.0001). We attributed the BCDIH decline to the lower recall of the IH parser on UPMC notes. The ANOVA analysis showed five significant factors: development parser, application institution, application parser, BN transfer, and classification task. Conclusion: We demonstrated high influenza case detection performance in two large healthcare systems in two geographically separated regions, providing evidentiary support for the use of automated case detection from routinely collected electronic clinical notes in national influenza surveillance. The transferability could be improved by training Bayesian network classifier locally and increasing the accuracy of the NLP parser. [ABSTRACT FROM AUTHOR]