Search

A Hyperspectral (HS) image provides observational powers beyond human vision capability but represents more than 100 times the data compared to a traditional image. To transmit and store the huge volume of an HS image, we argue that a fundamental shift is required from the existing “original pixel intensity”-based coding approaches using traditional image coders (e.g., JPEG2000) to the “residual”-based approaches using a video coder for better compression performance. A modified video coder is required to exploit spatial-spectral redundancy using pixel-level reflectance modelling due to the different characteristics of HS images in their spectral and shape domain of panchromatic imagery compared to traditional videos. In this paper a novel coding framework using Reflectance Prediction Modelling (RPM) in the latest video coding standard High Efficiency Video Coding (HEVC) for HS images is proposed. An HS image presents a wealth of data where every pixel is considered a vector for different spectral bands. By quantitative comparison and analysis of pixel vector distribution along spectral bands, we conclude that modelling can predict the distribution and correlation of the pixel vectors for different bands. To exploit distribution of the known pixel vector, we estimate a predicted current spectral band from the previous bands using Gaussian mixture-based modelling. The predicted band is used as the additional reference band together with the immediate previous band when we apply the HEVC. Every spectral band of an HS image is treated like it is an individual frame of a video. In this paper, we compare the proposed method with mainstream encoders. The experimental results are fully justified by three types of HS dataset with different wavelength ranges. The proposed method outperforms the existing mainstream HS encoders in terms of rate-distortion performance of HS image compression. [ABSTRACT FROM AUTHOR]

Stereo matching is essential and fundamental in computer vision tasks. In this paper, a novel stereo matching algorithm based on disparity propagation using edge-aware filtering is proposed. By extracting disparity subsets for reliable points and customizing the cost volume, the initial disparity map is refined through filtering-based disparity propagation. Then, an edge-aware filter with low computational complexity is adopted to formulate the cost column, which makes the proposed method independent on the local window size. Experimental results demonstrate the effectiveness of the proposed scheme. Bad pixels in our output disparity map are considerably decreased. The proposed method greatly outperforms the adaptive support-weight approach and other conditional window-based local stereo matching algorithms. [ABSTRACT FROM AUTHOR]

This paper presents an interface system based on the Dual Active Bridge (DAB) converter for Photovoltaic (PV) arrays. Two control strategies are proposed for the DAB converter to harvest the maximum power from the PV array. The first strategy is based on a simple PI controller to regulate the terminal PV voltage through the phase shift angle of the DAB converter. The Perturb and Observe (P&O) Maximum Power Point Tracking (MPPT) technique is utilized to set the reference of the PV terminal voltage. The second strategy presented in this paper employs the Artificial Neural Network (ANN) to directly set the phase shift angle of the DAB converter that results in harvesting maximum power. This feed-forward strategy overcomes the stability issues of the feedback strategy. The proposed PV interface systems are modeled and simulated using MATLAB/SIMULINK and the EMTDC/PSCAD software packages. The simulation results reveal accurate and fast response of the proposed systems. The dynamic performance of the proposed feed-forward strategy outdoes that of the feedback strategy in terms of accuracy and response time. Moreover, an experimental prototype is built to test and validate the proposed PV interface system. [ABSTRACT FROM AUTHOR]

This paper proposes a method to predict fluctuations in the prices of cryptocurrencies, which are increasingly used for online transactions worldwide. Little research has been conducted on predicting fluctuations in the price and number of transactions of a variety of cryptocurrencies. Moreover, the few methods proposed to predict fluctuation in currency prices are inefficient because they fail to take into account the differences in attributes between real currencies and cryptocurrencies. This paper analyzes user comments in online cryptocurrency communities to predict fluctuations in the prices of cryptocurrencies and the number of transactions. By focusing on three cryptocurrencies, each with a large market size and user base, this paper attempts to predict such fluctuations by using a simple and efficient method. [ABSTRACT FROM AUTHOR]

The DEM generalization is the basis of multi-dimensional observation, the basis of expressing and analyzing the terrain. DEM is also the core of building the Multi-Scale Geographic Database. Thus, many researchers have studied both the theory and the method of DEM generalization. This paper proposed a new method of generalizing terrain, which extracts feature points based on the tree model construction which considering the nested relationship of watershed characteristics. The paper used the 5 m resolution DEM of the Jiuyuan gully watersheds in the Loess Plateau as the original data and extracted the feature points in every single watershed to reconstruct the DEM. The paper has achieved generalization from 1:10000 DEM to 1:50000 DEM by computing the best threshold. The best threshold is 0.06. In the last part of the paper, the height accuracy of the generalized DEM is analyzed by comparing it with some other classic methods, such as aggregation, resample, and VIP based on the original 1:50000 DEM. The outcome shows that the method performed well. The method can choose the best threshold according to the target generalization scale to decide the density of the feature points in the watershed. Meanwhile, this method can reserve the skeleton of the terrain, which can meet the needs of different levels of generalization. Additionally, through overlapped contour contrast, elevation statistical parameters and slope and aspect analysis, we found out that the W8D algorithm performed well and effectively in terrain representation. [ABSTRACT FROM AUTHOR]

In this paper, we propose a human action recognition method using HOIRM (histogram of oriented interest region motion) feature fusion and a BOW (bag of words) model based on AP (affinity propagation) clustering. First, a HOIRM feature extraction method based on spatiotemporal interest points ROI is proposed. HOIRM can be regarded as a middle-level feature between local and global features. Then, HOIRM is fused with 3D HOG and 3D HOF local features using a cumulative histogram. The method further improves the robustness of local features to camera view angle and distance variations in complex scenes, which in turn improves the correct rate of action recognition. Finally, a BOW model based on AP clustering is proposed and applied to action classification. It obtains the appropriate visual dictionary capacity and achieves better clustering effect for the joint description of a variety of features. The experimental results demonstrate that by using the fused features with the proposed BOW model, the average recognition rate is 95.75% in the KTH database, and 88.25% in the UCF database, which are both higher than those by using only 3D HOG+3D HOF or HOIRM features. Moreover, the average recognition rate achieved by the proposed method in the two databases is higher than that obtained by other methods. [ABSTRACT FROM AUTHOR]

The development of high-throughput sequencing technologies for 16S rRNA gene profiling provides higher quality compositional data for microbe communities. Inferring the direct interaction network under a specific condition and understanding how the network structure changes between two different environmental or genetic conditions are two important topics in biological studies. However, the compositional nature and high dimensionality of the data are challenging in the context of network and differential network recovery. To address this problem in the present paper, we proposed two new loss functions to incorporate the data transformations developed for compositional data analysis into D-trace loss for network and differential network estimation, respectively. The sparse matrix estimators are defined as the minimizer of the corresponding lasso penalized loss. Our method is characterized by its straightforward application based on the ADMM algorithm for numerical solution. Simulations show that the proposed method outperforms other state-of-the-art methods in network and differential network inference under different scenarios. Finally, as an illustration, our method is applied to a mouse skin microbiome data. [ABSTRACT FROM AUTHOR]

We investigate the use of Twitter data to deliver signals for syndromic surveillance in order to assess its ability to augment existing syndromic surveillance efforts and give a better understanding of symptomatic people who do not seek healthcare advice directly. We focus on a specific syndrome—asthma/difficulty breathing. We outline data collection using the Twitter streaming API as well as analysis and pre-processing of the collected data. Even with keyword-based data collection, many of the tweets collected are not be relevant because they represent chatter, or talk of awareness instead of an individual suffering a particular condition. In light of this, we set out to identify relevant tweets to collect a strong and reliable signal. For this, we investigate text classification techniques, and in particular we focus on semi-supervised classification techniques since they enable us to use more of the Twitter data collected while only doing very minimal labelling. In this paper, we propose a semi-supervised approach to symptomatic tweet classification and relevance filtering. We also propose alternative techniques to popular deep learning approaches. Additionally, we highlight the use of emojis and other special features capturing the tweet’s tone to improve the classification performance. Our results show that negative emojis and those that denote laughter provide the best classification performance in conjunction with a simple word-level n-gram approach. We obtain good performance in classifying symptomatic tweets with both supervised and semi-supervised algorithms and found that the proposed semi-supervised algorithms preserve more of the relevant tweets and may be advantageous in the context of a weak signal. Finally, we found some correlation (r = 0.414, p = 0.0004) between the Twitter signal generated with the semi-supervised system and data from consultations for related health conditions. [ABSTRACT FROM AUTHOR]

This paper attempts to design an automated, efficient and intelligent tomato grading method that facilitates the graded selling of the fruit. Based on machine vision, the color images of tomatoes with different morphologies were studied, and the color, shape and size were selected as the key features. On this basis, an automated grading classifier was created based on the surface features of tomatoes, and a grading platform was set up to verify the effect of the classifier. Specifically, the Hue value distributions of tomatoes with different maturities were investigated, and the Hue value ranges were determined for mature, semi-mature and immature tomatoes, producing the color classifier. Next, the first-order Fourier descriptor (1D- FD) was adopted to describe the radius sequence of tomato contour, and an equation was established to compute the irregularity of tomato contour, creating the shape classifier. After that, a linear regression equation was constructed to reflect the relationship between the transverse diameters of actual tomatoes and tomato images, and a classifier between large, medium and small tomatoes was produced based on the transverse diameter. Finally, a comprehensive tomato classifier was built based on the color, shape and size diameters. The experimental results show that the mean grading accuracy of the proposed method was 90.7%. This means our method can achieve automated real-time grading of tomatoes. [ABSTRACT FROM AUTHOR]

The user interaction in online social networks can not only reveal the social relationships among users in e-commerce systems, but also imply the social preferences of a target user for recommendation services. However, the current research has rarely explored the impact of social interaction on recommendation performance, especially now that recommender systems face increasing challenges and suffer from poor efficiency due to social data overload. Therefore, applied research on user interaction has become increasingly necessary in the field of social recommendation. In this paper, we develop a novel social recommendation method based on the user interaction in complex social networks, called the SRUI model, to present a basis for improving the efficiency of the recommender systems. Specifically, a weighted social interaction network is first mapped to represent the interactions among social users according to the gathered information about historical user behavior. Thereafter, the complete path set is mined by the complete path mining (CPM) algorithm to find social similar neighbors with tastes similar to those of the target user. Finally, the social similar tendencies of the users on the complete paths are obtained to predict the final ratings of items through the SRUI model. A series of experimental results based on two real public datasets show that our approach performs better than other state-of-the-art methods in terms of recommendation performance. [ABSTRACT FROM AUTHOR]

Several studies have shown that the performance of a supply chain is heavily influenced by the pattern of relationships among firms. This paper analyzes the structure of relationships (network topology) that leads to the highest agility of a food supply chain when sudden demand changes occur. To do this, a simulation model that represents a supply chain and specific rules to allocate orders is built. The supply chain in the model follows the specific characteristics of trade in the primary sector. The model is fitted to the conditions of a real seafood supply chain in Mexico. Agility is measured through the effect on the order fulfillment of a sudden demand shock and the recovery time of this rate to previous values. The simulation results show that the most suitable structure depends on how product is distributed among suppliers. If product is evenly shared, supply chains with homogeneous topologies are more agile than supply chains with heterogeneous topologies, but the result is the opposite if product is unevenly shared among suppliers. Other previous recommendations, such as having multiple suppliers and horizontal links, are confirmed by the simulations. These findings contribute to the general debate on which is the optimal topology for an agile supply chain. [ABSTRACT FROM AUTHOR]

Motivation: Disease progression originates from the concept that an individual disease may go through different changes as it evolves, and such changes can cause new diseases. It is important to find a progression between diseases since knowing the prior-posterior relationship beforehand can prevent further complications or evolutions to other diseases. Furthermore, the series of progressions can be represented in the form of a chain, which enables us to readily infer successive influences from one disease to another after many passages through other diseases. Methods: In this paper, we propose a systematic approach for finding a disease progression chain from a source disease to a target one via exploring a disease network. The network is constructed based on various sets of biomedical data. To find the most influential progression chains, the k-shortest path search algorithm is employed. The most representative algorithms such as A*, Dijkstra, and Yen’s are incorporated into the proposed method. Results: A disease network consisting of 3,302 diseases was constructed based on four sources of biomedical data: disease-protein relations, biological pathways, clinical history, and biomedical literature information. The last three sets of data contain prior-posterior information, and they endow directionality on the edges of the network. The results were interesting and informative: for example, when colitis and respiratory insufficiency were set as a source disease and a target one, respectively, five progression chains were found within several seconds (when k = 5). Each chain was provided with a progression score, which indicates the strength of plausibility relative to others. Similarly, the proposed method can be expanded to any pair of source-target diseases in the network. This can be utilized as a preliminary tool for inferring complications or progressions between diseases. [ABSTRACT FROM AUTHOR]

How can we extract hidden relations from a tensor and a matrix data simultaneously in a fast, accurate, and scalable way? Coupled matrix-tensor factorization (CMTF) is an important tool for this purpose. Designing an accurate and efficient CMTF method has become more crucial as the size and dimension of real-world data are growing explosively. However, existing methods for CMTF suffer from lack of accuracy, slow running time, and limited scalability. In this paper, we propose S3CMTF, a fast, accurate, and scalable CMTF method. In contrast to previous methods which do not handle large sparse tensors and are not parallelizable, S3CMTF provides parallel sparse CMTF by carefully deriving gradient update rules. S3CMTF asynchronously updates partial gradients without expensive locking. We show that our method is guaranteed to converge to a quality solution theoretically and empirically. S3CMTF further boosts the performance by carefully storing intermediate computation and reusing them. We theoretically and empirically show that S3CMTF is the fastest, outperforming existing methods. Experimental results show that S3CMTF is up to 930× faster than existing methods while providing the best accuracy. S3CMTF shows linear scalability on the number of data entries and the number of cores. In addition, we apply S3CMTF to Yelp rating tensor data coupled with 3 additional matrices to discover interesting patterns. [ABSTRACT FROM AUTHOR]

Background: System science approaches are increasingly used to explore complex public health problems. Quantitative methods, such as participatory dynamic simulation modelling, can mobilise knowledge to inform health policy decisions. However, the analytic and practical steps required to turn collaboratively developed, qualitative system maps into rigorous and policy-relevant quantified dynamic simulation models are not well described. This paper reports on the processes, interactions and decisions that occurred at the interface between modellers and end-user participants in an applied health sector case study focusing on diabetes in pregnancy. Methods: An analysis was conducted using qualitative data from a participatory dynamic simulation modelling case study in an Australian health policy setting. Recordings of participatory model development workshops and subsequent meetings were analysed and triangulated with field notes and other written records of discussions and decisions. Case study vignettes were collated to illustrate the deliberations and decisions made throughout the model development process. Results: The key analytic objectives and decision-making processes included: defining the model scope; analysing and refining the model structure to maximise local relevance and utility; reviewing and incorporating evidence to inform model parameters and assumptions; focusing the model on priority policy questions; communicating results and applying the models to policy processes. These stages did not occur sequentially; the model development was cyclical and iterative with decisions being re-visited and refined throughout the process. Storytelling was an effective strategy to both communicate and resolve concerns about the model logic and structure, and to communicate the outputs of the model to a broader audience. Conclusion: The in-depth analysis reported here examined the application of participatory modelling methods to move beyond qualitative conceptual mapping to the development of a rigorously quantified and policy relevant, complex dynamic simulation model. The analytic objectives and decision-making themes identified provide guidance for interpreting, understanding and reporting future participatory modelling projects and methods. [ABSTRACT FROM AUTHOR]

Motivated by the concepts of quantum mechanics and particle swarm optimization (PSO), quantum-behaved particle swarm optimization (QPSO) was developed to achieve better global search ability. This paper proposes a new method to improve the global search ability of QPSO with fractional calculus (FC). Based on one of the most frequently used fractional differential definitions, the Grünwald-Letnikov definition, we introduce its discrete expression into the position updating of QPSO. Extensive experiments on well-known benchmark functions were performed to evaluate the performance of the proposed fractional-order quantum particle swarm optimization (FQPSO). The experimental results demonstrate its superior ability in achieving optimal solutions for several different optimizations. [ABSTRACT FROM AUTHOR]

A brain-computer interface (BCI), based on motor imagery EEG, uses information extracted from the electroencephalography signals generated by a person who intends to perform any action. One of the most important issues of current research is how to detect automatically whether the user intends to send some message to a certain device. This study presents a proposal, based on a hierarchical structured system, for recognising intentional and non-intentional mental tasks on a BCI system by applying machine learning techniques to the EEG signals. First-level clustering is performed to distinguish between intentional control (IC) and non-intentional control (NC) state patterns. Then, the patterns recognised as IC are passed on to a second stage where supervised learning techniques are used to classify them. In BCI applications, it is critical to correctly classify NC states with a low false positive rate (FPR) to avoid undesirable effects. According to the literature, we selected a maximum FPR of 10%. Under these conditions, our proposal achieved an average test accuracy of 66.6%, with an 8.2% FPR, for the BCI competition IIIa dataset. The main contribution of this paper is the hierarchical approach, based on machine learning paradigms, which performs intentional and non-intentional discrimination and, depending on the case, classifies the intended command selected by the user. [ABSTRACT FROM AUTHOR]

Freely-available satellite data streams and the ability to process these data on cloud-computing platforms such as Google Earth Engine have made frequent, large-scale landcover mapping at high resolution a real possibility. In this paper we apply these technologies, along with machine learning, to the mapping of peatlands–a landcover class that is critical for preserving biodiversity, helping to address climate change impacts, and providing ecosystem services, e.g., carbon storage–in the Boreal Forest Natural Region of Alberta, Canada. We outline a data-driven, scientific framework that: compiles large amounts of Earth observation data sets (radar, optical, and LiDAR); examines the extracted variables for suitability in peatland modelling; optimizes model parameterization; and finally, predicts peatland occurrence across a large boreal area (397, 958 km2) of Alberta at 10 m spatial resolution (equalling 3.9 billion pixels across Alberta). The resulting peatland occurrence model shows an accuracy of 87% and a kappa statistic of 0.57 when compared to our validation data set. Differentiating peatlands from mineral wetlands achieved an accuracy of 69% and kappa statistic of 0.37. This data-driven approach is applicable at large geopolitical scales (e.g., provincial, national) for wetland and landcover inventories that support long-term, responsible resource management. [ABSTRACT FROM AUTHOR]

With the emergence and widespread application of cloud computing, the use of cloud platforms to solve the problem of secure multi-party computation has emerged as a new research direction. The traditional computation of a solid geometry is performed through mutual interactions between two parties, which is not suitable in an untrusted cloud computing environment. In this paper, we first design a basic protocol for a secure Euclidean distance calculation that is suitable for cloud platforms and can serve as a building block for other protocols on cloud platforms. Using the solution of the Euclidean distance problem as such a building block, we provide a new method that converts the problems of calculating solid triangular areas and solid tetrahedral volumes into the calculation of distances and determinants in three-dimensional space. Then, we discuss solid point-line distance calculations, which extent the idea of the spatial geometry security problem. We present protocols for the above problems and prove that the proposed protocols can resist conspiracy among users and the untrusted cloud platform so that they can effectively ensure the privacy of the users. We also analyze the performances of these solutions. The analysis results show that our scheme is more versatile. [ABSTRACT FROM AUTHOR]

The reuse of business processes (BPs) requires similarities between them to be suitably identified. Various approaches have been introduced to address this problem, but many of them feature a high computational cost and a low level of automation. This paper presents a clustering algorithm that groups business processes retrieved from a multimodal search system (based on textual and structural information). The algorithm is based on Incremental Covering Arrays (ICAs) with different alphabets to determine the possible number of groups to be created for each row of the ICA. The proposed algorithm also incorporates Balanced Bayesian Information Criterion to determine the optimal number of groups and the best solution for each query. Experimental evaluation shows that the use of ICAs with strength four (4) and different alphabets reduces the number of solutions needed to be evaluated and optimizes the number of clusters. The proposed algorithm outperforms other algorithms in various measures (precision, recall, and F-measure) by between 12% and 88%. Friedman and Wilcoxon non-parametric tests gave a 90–95% significance level to the obtained results. Better options of repository search for BPs help companies to reuse them. By thus reusing BPs, managers and analysts can more easily get to know the evolution and trajectory of the company processes, a situation that could be expected to lead to improved managerial and commercial decision making. [ABSTRACT FROM AUTHOR]

Kernel regression models have been used as non-parametric methods for fitting experimental data. However, due to their non-parametric nature, they belong to the so-called “black box” models, indicating that the relation between the input variables and the output, depending on the kernel selection, is unknown. In this paper we propose a new methodology to retrieve the relation between each input regressor variable and the output in a least squares support vector machine (LS-SVM) regression model. The method is based on oblique subspace projectors (ObSP), which allows to decouple the influence of input regressors on the output by including the undesired variables in the null space of the projection matrix. Such functional relations are represented by the nonlinear transformation of the input regressors, and their subspaces are estimated using appropriate kernel evaluations. We exploit the properties of ObSP in order to decompose the output of the obtained regression model as a sum of the partial nonlinear contributions and interaction effects of the input variables, we called this methodology Nonlinear ObSP (NObSP). We compare the performance of the proposed algorithm with the component selection and smooth operator (COSSO) for smoothing spline ANOVA models. We use as benchmark 2 toy examples and a real life regression model using the concrete strength dataset from the UCI machine learning repository. We showed that NObSP is able to outperform COSSO, producing stable estimations of the functional relations between the input regressors and the output, without the use of prior-knowledge. This methodology can be used in order to understand the functional relations between the inputs and the output in a regression model, retrieving the physical interpretation of the regression models. [ABSTRACT FROM AUTHOR]

Cell segmentation in microscopy is a challenging problem, since cells are often asymmetric and densely packed. Successful cell segmentation algorithms rely identifying seed points, and are highly sensitive to variablility in cell size. In this paper, we present an efficient and highly parallel formulation for symmetric three-dimensional contour evolution that extends previous work on fast two-dimensional snakes. We provide a formulation for optimization on 3D images, as well as a strategy for accelerating computation on consumer graphics hardware. The proposed software takes advantage of Monte-Carlo sampling schemes in order to speed up convergence and reduce thread divergence. Experimental results show that this method provides superior performance for large 2D and 3D cell localization tasks when compared to existing methods on large 3D brain images. [ABSTRACT FROM AUTHOR]

The carrying pole has existed as a load carrying tool for thousands of years and is still popular in many parts of Asia. Previous studies attempted to determine whether the elasticity of the carrying pole is energetically beneficial compared with other load carrying methods. However, conflicting results indicate that the effects of the carrying pole stiffness on the carrier are still unclear. The carrying pole exhibits more complex characteristics beyond stiffness, which invites further investigation. As the first step towards the goal, this paper explores the underlying mechanics of the carrying pole, including the structural and dynamic properties, to determine its impact on the carrier. The structure of the carrying pole is modeled and characterized by pole length, pole stiffness, and length of suspension rope. We argue that maintaining the pole’s balance should be a major prerequisite during load carriage and that active feedback control from the carrier is required. Simulations reveal that the structural parameters of the pole have significant influences on the pole’s balance and the interaction between the pole and the carrier. This work suggests mechanical characteristics of the carrying pole can potentially have an extensive impact on gait mechanics and energetics of the carrier. [ABSTRACT FROM AUTHOR]

Pallet is a very important innovation in logistics industry. Pallets are so widely used that we can find them in nearly every logistical operation scenario. In order to manage pallets efficiently, researchers have developed several pallet management strategies (PMS). The most common and widely accepted PMS includes extensive management of pallets (EMP), transfer of pallet's ownership (TPO), and pallet rent (PR). This paper addresses mainly on how to help pallet managers choose a certain kind of PMS from the perspective of supply chain cost. Firstly, cost models of three kinds of PMS are presented. Secondly, all parameters involved in the models are valued based on data that is collected from industry survey. The results show that the cost of PR is constantly lower than EMP, and also lower than TPO when the operation period is no more than 37 months. Finally, the effect of several important parameters on the cost is studied by sensitivity analysis. The selection strategies of PMS are proposed based on the results. [ABSTRACT FROM AUTHOR]

Unless the targeted mesh is developable, metric distortion is inevitable during the process of surface mesh parameterization, thus one important objective of all involved parametric studies is to reduce the metric distortion. In order to further reduce area and angle distortion, a novel method of boundary-free mesh parameterization is presented in the paper. Firstly, the initial boundary-fixed conformal parameterization from 3D surface mesh patch to a plane is performed in the method. Then, based on the initial parameterization, the iterations of boundary-free quasi-harmonic parameterization are developed, where the tensor field is updated in each iterative step and the principal curvature direction is utilized to terminate the iteration. The solution of the novel method is convenient to calculate since it involves a series of linear systems. In our novel parameterization method, lower metric distortion and considerable efficiency have been obtained in experiments. [ABSTRACT FROM AUTHOR]

With the prosperity of machine learning and cloud computing, meaningful information can be mined from mass electronic medical data which help physicians make proper disease diagnosis for patients. However, using medical data and disease information of patients frequently raise privacy concerns. In this paper, based on single-layer perceptron, we propose a scheme of privacy-preserving clinical decision with cloud support (PPCD), which securely conducts disease model training and prediction for the patient. Each party learns nothing about the other’s private information. In PPCD, a lightweight secure multiplication is presented and introduced to improve the model training. Security analysis and experimental results on real data confirm the high accuracy of disease prediction achieved by the proposed PPCD without the risk of privacy disclosure. [ABSTRACT FROM AUTHOR]

The performance of data clustering algorithms is mainly dependent on their ability to balance between the exploration and exploitation of the search process. Although some data clustering algorithms have achieved reasonable quality solutions for some datasets, their performance across real-life datasets could be improved. This paper proposes an adaptive memetic differential evolution optimisation algorithm (AMADE) for addressing data clustering problems. The memetic algorithm (MA) employs an adaptive differential evolution (DE) mutation strategy, which can offer superior mutation performance across many combinatorial and continuous problem domains. By hybridising an adaptive DE mutation operator with the MA, we propose that it can lead to faster convergence and better balance the exploration and exploitation of the search. We would also expect that the performance of AMADE to be better than MA and DE if executed separately. Our experimental results, based on several real-life benchmark datasets, shows that AMADE outperformed other compared clustering algorithms when compared using statistical analysis. We conclude that the hybridisation of MA and the adaptive DE is a suitable approach for addressing data clustering problems and can improve the balance between global exploration and local exploitation of the optimisation algorithm. [ABSTRACT FROM AUTHOR]

The framework of dynamical systems offers powerful tools to understand the relation between stability and variability in human cognition in general and in speech in particular. In the current paper, we propose a dynamical systems approach to the description of German nuclear pitch accents in focus marking to account for both the categorical as well as the continuous variation found in intonational data. We report on results from 27 native speakers and employ an attractor landscape to represent pitch accent types in terms of f0 measures in a continuous dimension. We demonstrate how the same system can account for both the categorical variation (relative stability of one prosodic category) as well as the continuous variation (detailed modifications within one prosodic category). The model is able to capture the qualitative aspects of focus marking such as falling vs. rising pitch accent types as well as the quantitative aspects such as less rising vs. more rising accents in one system by means of scaling a single parameter. Furthermore, speaker group specific strategies are analysed and modelled as differences in the scaling of this parameter. Thus, the model contributes to the ongoing debate about the relation between phonetics and phonology and the importance of variation in language and speech. [ABSTRACT FROM AUTHOR]

DIBR-3D technology has evolved over the past few years with the demands of consumers increasing in recent times for future free-view 3D videos on their home televisions. The main issue in 3D technology is the lack of 3D content available to watch using the traditional TV systems. Although, some sophisticated devices like stereoscopic cameras have been used to fill the gap between the 3D content demand and 3D content supply. But the content generated through these sophisticated devices can not be displayed on the traditional TV systems, so there needs to be some mechanism which is inline with the traditional TV. Furthermore, the huge collection of existing 2D content should be converted to 3D using depth image-based rendering techniques. This conversion technique can highly contribute in overcoming the shortage problem of the 3D content. This paper presents a novel approach for converting 2D degraded image for DIBR 3D-TV view. This degraded or noisy/blur image is enhanced through image dehazing and Directional Filter Bank (DFB). This enhancement is necessary because of the occlusion effect or hole filling problem that occurs due to imperfect depth map. The enhanced image is then segmented into the foreground image and the background image. After the segmentation, the depth map is generated using image profiles. Moreover, Stereoscopic images are finally produced using the DIBR procedure which is based on the 2D input image and the corresponding depth map. We have verified the results of the proposed approach by comparing the results with the existing state-of-the-art techniques. [ABSTRACT FROM AUTHOR]

Digital public displays installed in various locations provide valuable information for the passers-by. However, the static characteristic of the digital public display limits the consumption of the displayed content to a small area. Personal mobile devices such as smartphones are now capable of interacting with digital public displays, which enables the passers-by to “take-away” the content and consume it on-the-go. This process requires device binding, content selection, and transfer between the two devices. In this paper, we propose a device binding method which utilizes the content brightness changing pattern as a unique content ID on the public display and an illuminance sensor on the mobile to bind and transfer between two devices. We conducted performance evaluations for binding algorithm robustness in different conditions. Also comparative studies among other binding interaction methods were conducted. Our results show that our proposed method performed stably across the various conditions and overall performance in interaction completion time and error rate was similar or superior to the existing methods. [ABSTRACT FROM AUTHOR]

Electroencephalogram (EEG) is a common base signal used to monitor brain activities and diagnose sleep disorders. Manual sleep stage scoring is a time-consuming task for sleep experts and is limited by inter-rater reliability. In this paper, we propose an automatic sleep stage annotation method called SleepEEGNet using a single-channel EEG signal. The SleepEEGNet is composed of deep convolutional neural networks (CNNs) to extract time-invariant features, frequency information, and a sequence to sequence model to capture the complex and long short-term context dependencies between sleep epochs and scores. In addition, to reduce the effect of the class imbalance problem presented in the available sleep datasets, we applied novel loss functions to have an equal misclassified error for each sleep stage while training the network. We evaluated the performance of the proposed method on different single-EEG channels (i.e., Fpz-Cz and Pz-Oz EEG channels) from the Physionet Sleep-EDF datasets published in 2013 and 2018. The evaluation results demonstrate that the proposed method achieved the best annotation performance compared to current literature, with an overall accuracy of 84.26%, a macro F1-score of 79.66% and κ = 0.79. Our developed model can be applied to other sleep EEG signals and aid the sleep specialists to arrive at an accurate diagnosis. The source code is available at . [ABSTRACT FROM AUTHOR]

Control problem in a biological system is the problem of finding an interventional policy for changing the state of the biological system from an undesirable state, e.g. disease, into a desirable healthy state. Boolean networks are utilized as a mathematical model for gene regulatory networks. This paper provides an algorithm to solve the control problem in Boolean networks. The proposed algorithm is implemented and applied on two biological systems: T-cell receptor network and Drosophila melanogaster network. Results show that the proposed algorithm works faster in solving the control problem over these networks, while having similar accuracy, in comparison to previous exact methods. Source code and a simple web service of the proposed algorithm is available at . [ABSTRACT FROM AUTHOR]

Antenna selection in Multiple-Input Multiple-Output (MIMO) systems has attracted increasing attention due to the challenge of keeping a balance between communication performance and computational complexity. Recently, deep learning based methods have achieved promising performance in many application fields. This paper proposed a deep learning (DL) based antenna selection technique. First, we generated the label of training antenna systems by maximizing the channel capacity. Then, we adopted the deep convolutional neural network (CNN) on the channel matrices to explicitly exploit the massive latent cues of attenuation coefficients. Finally, we used the adopted CNN to assign the class label and then select the optimal antenna subset. Experimental results demonstrate that our method can achieve better performance than the state-of-the-art baselines for data-driven based antenna selection. [ABSTRACT FROM AUTHOR]

Systems biology models are used to understand complex biological and physiological systems. Interpretation of these models is an important part of developing this understanding. These models are often fit to experimental data in order to understand how the system has produced various phenomena or behaviour that are seen in the data. In this paper, we have outlined a framework that can be used to perform Bayesian analysis of complex systems biology models. In particular, we have focussed on analysing a systems biology of the brain using both simulated and measured data. By using a combination of sensitivity analysis and approximate Bayesian computation, we have shown that it is possible to obtain distributions of parameters that can better guard against misinterpretation of results, as compared to a maximum likelihood estimate based approach. This is done through analysis of simulated and experimental data. NIRS measurements were simulated using the same simulated systemic input data for the model in a ‘healthy’ and ‘impaired’ state. By analysing both of these datasets, we show that different parameter spaces can be distinguished and compared between different physiological states or conditions. Finally, we analyse experimental data using the new Bayesian framework and the previous maximum likelihood estimate approach, showing that the Bayesian approach provides a more complete understanding of the parameter space. [ABSTRACT FROM AUTHOR]

Due to continuous evolution of biomedical data, biomedical ontologies are becoming larger and more complex, which leads to the existence of many overlapping information. To support semantic inter-operability between ontology-based biomedical systems, it is necessary to identify the correspondences between these information, which is commonly known as biomedical ontology matching. However, it is a challenge to match biomedical ontologies, which dues to: (1) biomedical ontologies often possess tens of thousands of entities, (2) biomedical terminologies are complex and ambiguous. To efficiently match biomedical ontologies, in this paper, an interactive biomedical ontology matching approach is proposed, which utilizes the Evolutionary Algorithm (EA) to implement the automatic matching process, and gets a user involved in the evolving process to improve the matching efficiency. In particular, we propose an Evolutionary Tabu Search (ETS) algorithm, which can improve EA’s performance by introducing the tabu search algorithm as a local search strategy into the evolving process. On this basis, we further make the ETS-based ontology matching technique cooperate with the user in a reasonable amount of time to efficiently create high quality alignments, and make use of EA’s survival of the fittest to eliminate the wrong correspondences brought by erroneous user validations. The experiment is conducted on the Anatomy track and Large Biomedic track that are provided by the Ontology Alignment Evaluation Initiative (OAEI), and the experimental results show that our approach is able to efficiently exploit the user intervention to improve its non-interactive version, and the performance of our approach outperforms the state-of-the-art semi-automatic ontology matching systems. [ABSTRACT FROM AUTHOR]

Providing complete mobility along with minimizing the poor quality of service (QoS) is one of the highest essential challenges in mobile wireless networks. Handover prediction can overcome these challenges. In this paper, two novel prediction schemes are proposed. The first, depends on scanning the quality of all signals among mobile station and all nearby stations in the surrounding area, while the second one is based on a multi-criteria prediction decision using both the signal-to-noise ratio SNR value and station’s bandwidth. Moreover, the prediction efficiency is improved by reducing the number of redundant/ unnecessary handovers. The proposed schemes are evaluated using different scenarios with several mobile stations’ numbers, different WLAN access points, LTE-base station number & location, and random mobile station movement manner. The proposed schemes achieved a success rate of 99% with the different scenarios using LTE-WLAN architecture. The performance of the proposed prediction schemes outperformed the performance of the existing prediction schemes in terms of the accuracy percentage. [ABSTRACT FROM AUTHOR]

In the carrier-based coverage repair problem, a single mobile robot replaces damaged sensors by picking up spare ones in the region of interest or carrying them from a base station in wireless sensor and robot networks. The objective is to find the shortest path of the robot. The problem is an extension of the traveling salesman problem (TSP). Thus, it is also called the one-commodity traveling salesman problem with selective pickup and delivery (1-TSP-SELPD). In order to solve this problem in a larger sensor distribution scenario more efficiently, we propose a two-stage approach in this paper. In the first stage, the mature and effective Lin–Kernighan–Helsgaun (LKH) algorithm is used to form a Hamiltonian cycle for all delivery nodes, which is regarded as a heuristic for the second stage. In the second stage, elliptical regions are set for selecting pickup nodes‚ and an edge-ordered list (candidate edge list, CEL) is constructed to provide major axes for the ellipses. The process of selecting pickup nodes and constructing the CEL is repeated until all the delivery nodes are visited. The final CEL stores a feasible solution. To update it, three operations—expansion, extension, and constriction—are applied to the CEL. The experimental results show that the proposed method reduces the computing time and achieves better results in higher-dimensional problems, which may facilitate the provision of solutions for more complicated sensor networks and can contribute to the development of effective and efficient algorithms for the one-commodity pickup-and-delivery traveling salesman problem (1-PDTSP). [ABSTRACT FROM AUTHOR]

The unrivaled computing capabilities of modern GPUs meet the demand of processing massive amounts of data seen in many application domains. While traditional HPC systems support applications as standalone entities that occupy entire GPUs, there are GPU-based DBMSs where multiple tasks are meant to be run at the same time in the same device. To that end, system-level resource management mechanisms are needed to fully unleash the computing power of GPUs in large data processing, and there were some researches focusing on it. In our previous work, we explored the single compute-bound kernel modeling on GPUs under NVidia’s CUDA framework and provided an in-depth anatomy of the NVidia’s concurrent kernel execution mechanism (CUDA stream). This paper focuses on resource allocation of multiple GPU applications towards optimization of system throughput in the context of systems. Comparing to earlier studies of enabling concurrent tasks support on GPU such as MultiQx-GPU, we use a different approach that is to control the launching parameters of multiple GPU kernels as provided by compile-time performance modeling as a kernel-level optimization and also a more general pre-processing model with batch-level control to enhance performance. Specifically, we construct a variation of multi-dimensional knapsack model to maximize concurrency in a multi-kernel environment. We present an in-depth analysis of our model and develop an algorithm based on dynamic programming technique to solve the model. We prove the algorithm can find optimal solutions (in terms of thread concurrency) to the problem and bears pseudopolynomial complexity on both time and space. Such results are verified by extensive experiments running on our microbenchmark that consists of real-world GPU queries. Furthermore, solutions identified by our method also significantly reduce the total running time of the workload, as compared to sequential and MultiQx-GPU executions. [ABSTRACT FROM AUTHOR]

Ex-ante online risk assessment for building emergency evacuation is essential to protect human life and property. Current risk assessment methods are limited by the tradeoff between accuracy and efficiency. In this paper, we propose an online method that overcomes this tradeoff based on multimedia data (e.g. videos data from surveillance cameras) and deep learning. The method consists of two parts. The first estimates the evacuee position as input for training the assessment model to then perform risk assessment in real scenarios. The second considers a social force model based on the evacuation simulation for the output of training model. We verify the proposed method in simulation and real scenarios. Model sensitivity analyses and large-scale tests demonstrate the usability and superiority of the proposed method. By the method, the computation time of risk assessment could be decreased from 10 minutes (by traditional simulation method) to 2.18 s. [ABSTRACT FROM AUTHOR]

In this paper, we put forward a real-time multiple GPUs (multi-GPU) accelerated virtual-reality interaction simulation framework where the reconstructed objects from camera images interact with virtual deformable objects. Firstly, based on an extended voxel-based visual hull (VbVH) algorithm, we design an image-based 3D reconstruction platform for real objects. Then, an improved hybrid deformation model, which couples the geometry constrained fast lattice shape matching method (FLSM) and total Lagrangian explicit dynamics (TLED) algorithm, is proposed to achieve efficient and stable simulation of the virtual objects’ elastic deformations. Finally, one-way virtual-reality interactions including soft tissues’ virtual cutting with bleeding effects are successfully simulated. Moreover, with the purpose of significantly improving the computational efficiency of each time step, we propose an entire multi-GPU implementation method of the framework using compute unified device architecture (CUDA). The experiment results demonstrate that our multi-GPU accelerated virtual-reality interaction framework achieves real-time performance under the moderate calculation scale, which is a new effective 3D interaction technique for virtual reality applications. [ABSTRACT FROM AUTHOR]

High dimensional biomedical data contain tens of thousands of features, accurate and effective identification of the core features in these data can be used to assist diagnose related diseases. However, there are often a large number of irrelevant or redundant features in biomedical data, which seriously affect subsequent classification accuracy and machine learning efficiency. To solve this problem, a novel filter feature selection algorithm based on redundant removal (FSBRR) is proposed to classify high dimensional biomedical data in this paper. First of all, two redundant criteria are determined by vertical relevance (the relationship between feature and class attribute) and horizontal relevance (the relationship between feature and feature). Secondly, to quantify redundant criteria, an approximate redundancy feature framework based on mutual information (MI) is defined to remove redundant and irrelevant features. To evaluate the effectiveness of our proposed algorithm, controlled trials based on typical feature selection algorithm are conducted using three different classifiers, and the experimental results indicate that the FSBRR algorithm can effectively reduce the feature dimension and improve the classification accuracy. In addition, an experiment of small sample dataset is designed and conducted in the section of discussion and analysis to clarify the specific implementation process of FSBRR algorithm more clearly. [ABSTRACT FROM AUTHOR]

Orienteering problem (OP) is a routing problem, where the aim is to generate a path through set of nodes, which would maximize total score and would not exceed the budget. In this paper, we present an extension of classic OP—Orienteering Problem with Functional Profits (OPFP), where the score of a specific point depends on its characteristics, position in the route, and other points in the route. For solving OPFP, we developed an open-source framework for solving orienteering problems, which utilizes four core components of OP in its modular architecture. Fully-written in Go programming language our framework can be extended for solving different types of tasks with different algorithms; this was demonstrated by implementation of two popular algorithms for OP solving—Ant Colony Optimization and Recursive Greedy Algorithm. Computational efficiency of the framework was shown through solving four well-known OP types: classic Orienteering Problem (OP), Orienteering Problem with Compulsory Vertices (OPCV), Orienteering Problem with Time Windows (OPTW), and Time Dependent Orienteering Problem (TDOP) along with OPFP. Experiments were conducted on a large multi-source dataset for Saint Petersburg, Russia, containing data from Instagram, TripAdvisor, Foursquare and official touristic website. Our framework is able to construct touristic paths for different OP types within few seconds using dataset with thousands of points of interest. [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]

Given a real-world graph, how can we measure relevance scores for ranking and link prediction? Random walk with restart (RWR) provides an excellent measure for this and has been applied to various applications such as friend recommendation, community detection, anomaly detection, etc. However, RWR suffers from two problems: 1) using the same restart probability for all the nodes limits the expressiveness of random walk, and 2) the restart probability needs to be manually chosen for each application without theoretical justification. We have two main contributions in this paper. First, we propose R W E R (RWER), a random walk based measure which improves the expressiveness of random walks by using a distinct restart probability for each node. The improved expressiveness leads to superior accuracy for ranking and link prediction. Second, we propose SR (pervised start for RWER), an algorithm for learning the restart probabilities of RWER from a given graph. SR eliminates the need to heuristically and manually select the restart parameter for RWER. Extensive experiments show that our proposed method provides the best performance for ranking and link prediction tasks. [ABSTRACT FROM AUTHOR]

This paper addresses the problem of energy management of mixed criticality applications in a multi-core partitioned architecture. Instead of focusing on new scheduling algorithms to adjust frequency in order to save energy, we propose a partition to CPU allocation that takes into account not only the different frequencies at which the CPU can operate but the level of criticality of the partitions. The goal is to provide a set of pre-calculated allocations, called profiles, so at run time the system can switch to different modes depending on the battery level. These profiles achieve different levels of energy saving and performance applying different strategies. We also present a comparison in terms of energy saving of the most used bin-packing algorithms for partition allocation. As this is an heuristic, it is not possible to ensure that our results involve the minimum energy consumption. For this reason, we also provide a comparison with a exact method, such as constraint programming. [ABSTRACT FROM AUTHOR]

Temperament and Psychological Types can be defined as innate psychological characteristics associated with how we relate with the world, and often influence our study and career choices. Furthermore, understanding these features help us manage conflicts, develop leadership, improve teaching and many other skills. Assigning temperament and psychological types is usually made by filling specific questionnaires. However, it is possible to identify temperamental characteristics from a linguistic and behavioral analysis of social media data from a user. Thus, machine-learning algorithms can be used to learn from a user’s social media data and infer his/her behavioral type. This paper initially provides a brief historical review of theories on temperament and then brings a survey of research aimed at predicting temperament and psychological types from social media data. It follows with the proposal of a framework to predict temperament and psychological types from a linguistic and behavioral analysis of Twitter data. The proposed framework infers temperament types following the David Keirsey’s model, and psychological types based on the MBTI model. Various data modelling and classifiers are used. The results showed that Random Forests with the LIWC technique can predict with 96.46% of accuracy the Artisan temperament, 92.19% the Guardian temperament, 78.68% the Idealist, and 83.82% the Rational temperament. The MBTI results also showed that Random Forests achieved a better performance with an accuracy of 82.05% for the E/I pair, 88.38% for the S/N pair, 80.57% for the T/F pair, and 78.26% for the J/P pair. [ABSTRACT FROM AUTHOR]

An important segment of the reliability-based optimization problems is to get access to the sensitivity derivatives. However, since the failure probability is not a closed-form function of the input variables, the derivatives are not explicitly computable and rather require a full reliability analysis which is computationally expensive. In this paper, a step-by-step algorithm has been presented to calculate the derivatives of the probability of failure and safety index with respect to the input parameters based on the advanced first-order second-moment (AFOSM) reliability method. The proposed algorithm is then implemented in a spreadsheet using Visual Basic for Application (VBA) programming language. Two geotechnical and structural examples are then presented to examine the program and describe the modeling procedure. The robustness of the proposed method is examined using a Gaussian random perturbation. The capability of the proposed method in the calculation of the sensitivity derivatives of the model uncertainty is explained in a separate section. Finally, the proposed model has been compared to the forward finite difference (FFD) method and the results are validated. [ABSTRACT FROM AUTHOR]

A new Interpolation based Reversible Data Hiding (IRDH) scheme is reported in this paper. For different applications of an IRDH scheme to the digital image, video, multimedia, big-data and biological data, the embedding capacity requirement usually varies. Disregarding this important consideration, existing IRDH schemes do not offer a better embedding rate-distortion performance for varying size payloads. To attain this varying capacity requirement with our proposed adaptive embedding, we formulate a capacity control parameter and propose to utilize it to determine a minimum set of embeddable bits in a pixel. Additionally, we use a logical (or bit-wise) correlation between the embeddable pixel and estimated versions of an embedded pixel. Thereby, while a higher range between an upper and lower limit of the embedding capacity is maintained, a given capacity requirement within that limit is also attained with a better-embedded image quality. Computational modeling of all new processes of the scheme is presented, and performance of the scheme is evaluated with a set of popular test-images. Experimental results of our proposed scheme compared to the prominent IRDH schemes have recorded a significantly better-embedding rate-distortion performance. [ABSTRACT FROM AUTHOR]

A new dynamic mode decomposition (DMD) method is introduced for simultaneous system identification and denoising in conjunction with the adoption of an extended Kalman filter algorithm. The present paper explains the extended-Kalman-filter-based DMD (EKFDMD) algorithm which is an online algorithm for dataset for a small number of degree of freedom (DoF). It also illustrates that EKFDMD requires significant numerical resources for many-degree-of-freedom (many-DoF) problems and that the combination with truncated proper orthogonal decomposition (trPOD) helps us to apply the EKFDMD algorithm to many-DoF problems, though it prevents the algorithm from being fully online. The numerical experiments of a noisy dataset with a small number of DoFs illustrate that EKFDMD can estimate eigenvalues better than or as well as the existing algorithms, whereas EKFDMD can also denoise the original dataset online. In particular, EKFDMD performs better than existing algorithms for the case in which system noise is present. The EKFDMD with trPOD, which unfortunately is not fully online, can be successfully applied to many-DoF problems, including a fluid-problem example, and the results reveal the superior performance of system identification and denoising. [ABSTRACT FROM AUTHOR]

Wang et al. proposed a method for obtaining elliptic curves with embedding degree 1 for securing critical infrastructures, and presented several elliptic curves generated by their method with torsion points of 160 bits and 189 bits orders. They also presented some experimental results and claimed that their implementation of an elliptic curve generated with their method is faster than an implementation for embedded devices presented by Bertoni et al. In this paper, we point out that the security and efficiency claims given by Wang et al. are flawed. Specifically, we show that it is possible to solve finite field discrete logarithm problems defined over their elliptic curves in practice. On the elliptic curves with torsion points of 160 bits orders generated by Wang et al., their instances of finite field discrete logarithm problems are solved in around 4 hours by using a standard desktop PC. On the torsion points of 189 bits orders, their instances are solved in around 10 days by using two standard desktop PCs. The hardness of the finite field discrete logarithm problems is one of the most important bases of security; therefore, their elliptic curves should not be used for cryptographic purposes. [ABSTRACT FROM AUTHOR]

The data collected by mobile methane (CH4) sensors can be used to find natural gas (NG) leaks in urban distribution systems. Extracting actionable insights from the large volumes of data collected by these sensors requires several data processing steps. While these survey platforms are commercially available, the associated data processing software largely constitute a black box due to their proprietary nature. In this paper we describe a step-by-step algorithm for developing leak indications using data from mobile CH4 surveys, providing an under-the-hood look at the choices and challenges associated with data analysis. We also describe how our algorithm has evolved over time, and the data-driven insights that have prompted these changes. Applying our algorithm to data collected in 15 cities produced more than 6100 leak indications and estimates of the leaks’ size. We use these results to characterize the distribution of leak sizes in local NG distribution systems. Mobile surveys are already an effective and necessary tool for managing NG distribution systems, but improvements in the technology and software will continue to increase its value. [ABSTRACT FROM AUTHOR]