Search

An effective traffic control strategy will improve travel reliability in urban transportation networks. Lack of coordination between vehicles, however, exacerbates congestion due mainly to frequent stops at unsignalized intersections. It is beneficial to develop a conflict-free cooperation method that collects basic safety message from multiple approaching Connected and Autonomous Vehicles (for short, CAVs) and guarantees efficient unsignalized intersection operations with safe and incident free vehicle maneuvers. This paper proposes an interspersed traffic organization method under controlled constraints. Firstly, relied on shared location technology and considered the operating characteristics of CAVs at unsignalized intersections to detect and analyze traffic conflicts to establish a right-of-way judgment model for CAVs. In order to further ensure the safety and operating efficiency of the vehicle, based on the judgment results of right-of-way judgment model, a vehicle speed guidance model is established for different traffic conditions. Taking the real city standard intersection as the experimental analysis object, through data collection and simulation experiment, the signal control method and the organization method proposed in this paper are compared and analyzed. The results showed that the traffic organization method proposed in this paper improves the operational efficiency of 46%, the average travel time is reduced by 6.54s, which is not only better than the signal control method, but also supports the development of car networking technology.

Stochastic models of biomolecular reaction networks are commonly employed in systems and synthetic biology to study the effects of stochastic fluctuations emanating from reactions involving species with low copy-numbers. For such models, the Kolmogorov’s forward equation is called the chemical master equation (CME), and it is a fundamental system of linear ordinary differential equations (ODEs) that describes the evolution of the probability distribution of the random state-vector representing the copy-numbers of all the reacting species. The size of this system is given by the number of states that are accessible by the chemical system, and for most examples of interest this number is either very large or infinite. Moreover, approximations that reduce the size of the system by retaining only a finite number of important chemical states (e.g. those with non-negligible probability) result in high-dimensional ODE systems, even when the number of reacting species is small. Consequently, accurate numerical solution of the CME is very challenging, despite the linear nature of the underlying ODEs. One often resorts to estimating the solutions via computationally intensive stochastic simulations. The goal of the present paper is to develop a novel deep-learning approach for computing solution statistics of high-dimensional CMEs by reformulating the stochastic dynamics using Kolmogorov’s backward equation. The proposed method leverages superior approximation properties of Deep Neural Networks (DNNs) to reliably estimate expectations under the CME solution for several user-defined functions of the state-vector. This method is algorithmically based on reinforcement learning and it only requires a moderate number of stochastic simulations (in comparison to typical simulation-based approaches) to train the “policy function”. This allows not just the numerical approximation of various expectations for the CME solution but also of its sensitivities with respect to all the reaction network parameters (e.g. rate constants). We provide four examples to illustrate our methodology and provide several directions for future research., Author summary We develop a deep learning framework for estimating solutions of the chemical master equation (CME) that is fundamental to stochastic analysis of reaction networks. The CME is a system of ordinary differential equations that describes the time-evolution of the probability density of the random state-vector, and owing to an inherent curse of dimensionality, directly solving the CME is generally impractical with existing approaches. Moreover, the commonly employed simulation-based approaches for estimating CME solutions often require an exorbitant amount of computational time, even for moderately-sized networks. To counter these issues, we develop a deep reinforcement learning based method, called DeepCME, in this paper. DeepCME not only estimates function expectations based on the CME solution, but it also solves the more challenging problem of estimating their sensitivities with respect to all the model parameters. We illustrate our approach with four carefully chosen reaction network examples with varying sizes. Our results demonstrate that DeepCME reliably estimates the expectations of interest, along with all the parametric sensitivities, at a fraction of the computational cost of simulation-based estimators. We present many directions for future research and suggest further improvements to DeepCME that can greatly enhance its accuracy and applicability.

In the case of a fire, the choice of exit in the highway tunnel is strictly limited by fire location, which seriously affects the evacuation time. A spontaneous or disorderly exit choice might result in a decreased evacuation efficiency and utilization rate of exits. In this paper, we propose a strategy to obtain the optimal exit choice based on fire location during highway tunnel evacuations. In our strategy, first, the vehicle distributions and locations of evacuating occupants are determined in the traffic simulation program VISSIM. The evacuation simulation software BuildingEXODUS is employed to obtain the corresponding parameters of the evacuation process and analyze the impacts of different fire locations on the evacuation time. During the analysis, the optimal productivity statistics (OPS) is selected as the evaluation index. Then, the feature points of the crowding occupants are captured by the fuzzy c-means (FCM) cluster algorithm. Next, based on the feature points, the relationship between the location of the fire and boundary of the optimal exit choice under the optimal OPS is obtained through the polynomial regression model. It is found that the R-squared(R2) and sum of squares for error (SSE) of the polynomial regression model, reflecting the accuracy estimation, are 98.02% and 2.79×10−4, respectively. Moreover, different fire locations impact the evacuation time of tunnel entrance and evacuation passageway. This paper shows that the location of the fire and boundary of optimal exit choice have a negative linear correlation. Taking the fire 110 m away from the evacuation passageway as an example, the OPS of our strategy can be decreased by 35.6% when compared with no strategies. Our proposed strategy could be applied to determine the location of variable evacuation signs to help evacuating occupants make optimal exit choices.

Several lifetime distributions have played an important role to fit survival data. However, for some of these models, the computation of maximum likelihood estimators is quite difficult due to presence of flat regions in the search space, among other factors. Several well-known derivative-based optimization tools are unsuitable for obtaining such estimates. To circumvent this problem, we introduce the AdequacyModel computational library version 2.0.0 for the R statistical environment with two major contributions: a general optimization technique based on the Particle Swarm Optimization (PSO) method (with a minor modification of the original algorithm) and a set of statistical measures for assessment of the adequacy of the fitted model. This library is very useful for researchers in probability and statistics and has been cited in various papers in these areas. It serves as the basis for the Newdistns library (version 2.1) published in an impact journal in the area of computational statistics, see https://CRAN.R-project.org/package=Newdistns. It is also the basis of the Wrapped library (version 2.0), see https://CRAN.R-project.org/package=Wrapped. A third package making use of the AdequacyModel library can be found in https://CRAN.Rproject.org/package=sglg. In addition, the proposed library has proved to be very useful for maximizing log-likelihood functions with complex search regions. The library provides a greater control of the optimization process by introducing a stop criterion based on a minimum number of iterations and the variance of a given proportion of optimal values. We emphasize that the new library can be used not only in statistics but in physics and mathematics as proved in several examples throughout the paper.

Background Dementia is a complex disorder characterized by poor outcomes for the patients and high costs of care. After decades of research little is known about its mechanisms. Having prognostic estimates about dementia can help researchers, patients and public entities in dealing with this disorder. Thus, health data, machine learning and microsimulation techniques could be employed in developing prognostic estimates for dementia. Objective The goal of this paper is to present evidence on the state of the art of studies investigating and the prognosis of dementia using machine learning and microsimulation techniques. Method To achieve our goal we carried out a systematic literature review, in which three large databases -Pubmed, Socups and Web of Science were searched to select studies that employed machine learning or microsimulation techniques for the prognosis of dementia. A single backward snowballing was done to identify further studies. A quality checklist was also employed to assess the quality of the evidence presented by the selected studies, and low quality studies were removed. Finally, data from the final set of studies were extracted in summary tables. Results In total 37 papers were included. The data summary results showed that the current research is focused on the investigation of the patients with mild cognitive impairment that will evolve to Alzheimer's disease, using machine learning techniques. Microsimulation studies were concerned with cost estimation and had a populational focus. Neuroimaging was the most commonly used variable. Conclusions Prediction of conversion from MCI to AD is the dominant theme in the selected studies. Most studies used ML techniques on Neuroimaging data. Only a few data sources have been recruited by most studies and the ADNI database is the one most commonly used. Only two studies have investigated the prediction of epidemiological aspects of Dementia using either ML or MS techniques. Finally, care should be taken when interpreting the reported accuracy of ML techniques, given studies' different contexts. © 2017 Dallora et al.This is an open access article distributed under the terms of the Creative Commons Attribution License, which permits unrestricted use, distribution, and reproduction in any medium, provided the original author and source are credited. Open access

With the development of computer network bandwidth, packet classification algorithms which are able to deal with large-scale rule sets are in urgent need. Among the existing algorithms, researches on packet classification algorithms based on hierarchical trie have become an important packet classification research branch because of their widely practical use. Although hierarchical trie is beneficial to save large storage space, it has several shortcomings such as the existence of backtracking and empty nodes. This paper proposes a new packet classification algorithm, Hierarchical Trie Algorithm Based on Expectation-Maximization Clustering (HTEMC). Firstly, this paper uses the formalization method to deal with the packet classification problem by means of mapping the rules and data packets into a two-dimensional space. Secondly, this paper uses expectation-maximization algorithm to cluster the rules based on their aggregate characteristics, and thereby diversified clusters are formed. Thirdly, this paper proposes a hierarchical trie based on the results of expectation-maximization clustering. Finally, this paper respectively conducts simulation experiments and real-environment experiments to compare the performances of our algorithm with other typical algorithms, and analyzes the results of the experiments. The hierarchical trie structure in our algorithm not only adopts trie path compression to eliminate backtracking, but also solves the problem of low efficiency of trie updates, which greatly improves the performance of the algorithm.

Neural Mass Models provide a compact description of the dynamical activity of cell populations in neocortical regions. Moreover, models of regional activity can be connected together into networks, and inferences made about the strength of connections, using M/EEG data and Bayesian inference. To date, however, Bayesian methods have been largely restricted to the Variational Laplace (VL) algorithm which assumes that the posterior distribution is Gaussian and finds model parameters that are only locally optimal. This paper explores the use of Annealed Importance Sampling (AIS) to address these restrictions. We implement AIS using proposals derived from Langevin Monte Carlo (LMC) which uses local gradient and curvature information for efficient exploration of parameter space. In terms of the estimation of Bayes factors, VL and AIS agree about which model is best but report different degrees of belief. Additionally, AIS finds better model parameters and we find evidence of non-Gaussianity in their posterior distribution., Author Summary The activity of populations of neurons in the human brain can be described using a set of differential equations known as a neural mass model. These models can then be connected to describe activity in multiple brain regions and, by fitting them to human brain imaging data, statistical inferences can be made about changes in macroscopic connectivity among brain regions. For example, the strength of a connection from one region to another may be more strongly engaged in a particular patient population or during a specific cognitive task. Current statistical inference approaches use a Bayesian algorithm based on principles of local optimization and the assumption that uncertainty about model parameters (e.g. connectivity), having seen the data, follows a Gaussian distribution. This paper evaluates current methods against a global Bayesian optimization algorithm and finds that the two approaches (local/global) agree about which model is best, but finds that the global approach produces better parameter estimates.

Ensembles are a well established machine learning paradigm, leading to accurate and robust models, predominantly applied to predictive modeling tasks. Ensemble models comprise a finite set of diverse predictive models whose combined output is expected to yield an improved predictive performance as compared to an individual model. In this paper, we propose a new method for learning ensembles of process-based models of dynamic systems. The process-based modeling paradigm employs domain-specific knowledge to automatically learn models of dynamic systems from time-series observational data. Previous work has shown that ensembles based on sampling observational data (i.e., bagging and boosting), significantly improve predictive performance of process-based models. However, this improvement comes at the cost of a substantial increase of the computational time needed for learning. To address this problem, the paper proposes a method that aims at efficiently learning ensembles of process-based models, while maintaining their accurate long-term predictive performance. This is achieved by constructing ensembles with sampling domain-specific knowledge instead of sampling data. We apply the proposed method to and evaluate its performance on a set of problems of automated predictive modeling in three lake ecosystems using a library of process-based knowledge for modeling population dynamics. The experimental results identify the optimal design decisions regarding the learning algorithm. The results also show that the proposed ensembles yield significantly more accurate predictions of population dynamics as compared to individual process-based models. Finally, while their predictive performance is comparable to the one of ensembles obtained with the state-of-the-art methods of bagging and boosting, they are substantially more efficient.

In the theory of belief functions, the approximation of a basic belief assignment (BBA) is for reducing the high computational cost especially when large number of focal elements are available. In traditional BBA approximation approaches, a focal element’s own characteristics such as the mass assignment and the cardinality, are usually used separately or jointly as criteria for the removal of focal elements. Besides the computational cost, the distance between the original BBA and the approximated one is also concerned, which represents the loss of information in BBA approximation. In this paper, an iterative approximation approach is proposed based on maximizing the closeness, i.e., minimizing the distance between the approximated BBA in current iteration and the BBA obtained in the previous iteration, where one focal element is removed in each iteration. The iteration stops when the desired number of focal elements is reached. The performance evaluation approaches for BBA approximations are also discussed and used to compare and evaluate traditional BBA approximations and the newly proposed one in this paper, which include traditional time-based way, closeness-based way and new proposed ones. Experimental results and related analyses are provided to show the rationality and efficiency of our proposed new BBA approximation.

For high-dimensional and massive data sets, traditional centralized gene expression programming (GEP) or improved algorithms lead to increased run-time and decreased prediction accuracy. To solve this problem, this paper proposes a new improved algorithm called distributed function mining for gene expression programming based on fast reduction (DFMGEP-FR). In DFMGEP-FR, fast attribution reduction in binary search algorithms (FAR-BSA) is proposed to quickly find the optimal attribution set, and the function consistency replacement algorithm is given to solve integration of the local function model. Thorough comparative experiments for DFMGEP-FR, centralized GEP and the parallel gene expression programming algorithm based on simulated annealing (parallel GEPSA) are included in this paper. For the waveform, mushroom, connect-4 and musk datasets, the comparative results show that the average time-consumption of DFMGEP-FR drops by 89.09%%, 88.85%, 85.79% and 93.06%, respectively, in contrast to centralized GEP and by 12.5%, 8.42%, 9.62% and 13.75%, respectively, compared with parallel GEPSA. Six well-studied UCI test data sets demonstrate the efficiency and capability of our proposed DFMGEP-FR algorithm for distributed function mining.

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.

Compression at a very low bit rate(≤0.5bpp) causes degradation in video frames with standard decoding algorithms like H.261, H.262, H.264, and MPEG-1 and MPEG-4, which itself produces lots of artifacts. This paper focuses on an efficient pre-and post-processing technique (PP-AFT) to address and rectify the problems of quantization error, ringing, blocking artifact, and flickering effect, which significantly degrade the visual quality of video frames. The PP-AFT method differentiates the blocked images or frames using activity function into different regions and developed adaptive filters as per the classified region. The designed process also introduces an adaptive flicker extraction and removal method and a 2-D filter to remove ringing effects in edge regions. The PP-AFT technique is implemented on various videos, and results are compared with different existing techniques using performance metrics like PSNR-B, MSSIM, and GBIM. Simulation results show significant improvement in the subjective quality of different video frames. The proposed method outperforms state-of-the-art de-blocking methods in terms of PSNR-B with average value lying between (0.7–1.9db) while (35.83–47.7%) reduced average GBIM keeping MSSIM values very close to the original sequence statistically 0.978.

Among various environmental factors associated with triggering or exacerbating autoimmune response, an important role is played by infections. A breakdown of immune tolerance as a byproduct of immune response against these infections is one of the major causes of autoimmune disease. In this paper we analyse the dynamics of immune response with particular emphasis on the role of time delays characterising the infection and the immune response, as well as on interactions between different types of T cells and cytokines that mediate their behaviour. Stability analysis of the model provides insights into how different model parameters affect the dynamics. Numerical stability analysis and simulations are performed to identify basins of attraction of different dynamical states, and to illustrate the behaviour of the model in different regimes.

In this paper, a new innovative type-2 fuzzy-based for microgrid (MG) islanding detection is proposed in the condition of uncertainties. Load and generation uncertainties are two main sources of uncertainties in microgrids (MGs). Regardless of the uncertainties, the results cannot be confirmed. The proposed controller detects islanding in the fastest time under different conditions, and the uncertainties in the system will not considerably affect the controller’s performance. The proposed method is simulated on the sample system and examined in different scenarios. Then, a comparison is made in different conditions and scenarios between the suggested method and some common methods that have been presented so far to demonstrate the ability of the proposed method for islanding detection.

The multi-energy conversion system (MCS) plays an important role in improving the utilization of energy resources and realizing the energy transition. With the application of the new generation of information technologies, the new MCS can realize real-time information interaction, multi-energy collaboration, and real-time demand response, in which energy suppliers can intelligently motivate consumers' energy use behavior. In this paper, an MCS coupled with a cloud platform is proposed to address information explosion and data security issues. Due to the development of Internet technology, the increasing energy data, and the serious energy coupling, it is difficult for traditional optimization methods to deal with the interaction between participants of the MCS. Therefore, the non-cooperative game is used to formulate the interactions between participants with the aim of maximizing the energy suppliers' profit and minimizing the customers' cost. It is proved that the game model is an ordinary game with one Nash equilibrium. The simulation was performed with a gradient projection algorithm and the results show that the proposed MCS improves energy utilization efficiency through energy conversion while ensuring consumer satisfaction, and benefits both the customers and suppliers by reducing the energy consumption cost and the peak load demand, which effectively improve the supply quality and enrich the energy consumption patterns.

The paper presents a new open-source visualization system, named ReVisE, aimed to provide interactive visualization of large datasets, which are results of complex numerical simulations. These datasets are hosted on a remote server or a supercomputer. The design of the system is briefly described. Dataset representation, proposed for interactive visualization and implemented in the system, is discussed. The effectiveness of our approach is confirmed by results of performance measurements on test and real-life large datasets. A comparison with other visualization systems is presented. Future plans of system development are outlined.

The use of image covariates to build a classification model has lots of impact in various fields, such as computer science, medicine, and so on. The aim of this paper is to develop an estimation method for logistic regression model with image covariates. We propose a novel regularized estimation approach, where the regularization is a combination of L1 regularization and Sobolev norm regularization. The L1 penalty can perform variable selection, while the Sobolev norm penalty can capture the shape edges information of image data. We develop an efficient algorithm for the optimization problem. We also establish a nonasymptotic error bound on parameter estimation. Simulated studies and a real data application demonstrate that our proposed method performs very well.

Statistical learning and probabilistic prediction are fundamental processes in auditory cognition. A prominent computational model of these processes is Prediction by Partial Matching (PPM), a variable-order Markov model that learns by internalizing n-grams from training sequences. However, PPM has limitations as a cognitive model: in particular, it has a perfect memory that weights all historic observations equally, which is inconsistent with memory capacity constraints and recency effects observed in human cognition. We address these limitations with PPM-Decay, a new variant of PPM that introduces a customizable memory decay kernel. In three studies—one with artificially generated sequences, one with chord sequences from Western music, and one with new behavioral data from an auditory pattern detection experiment—we show how this decay kernel improves the model’s predictive performance for sequences whose underlying statistics change over time, and enables the model to capture effects of memory constraints on auditory pattern detection. The resulting model is available in our new open-source R package, ppm (https://github.com/pmcharrison/ppm)., Author summary Humans hear a rich variety of sounds throughout everyday life, ranging from the basic (e.g. an alarm clock, a whistling kettle, an ambulance siren) to the complex (e.g. speech, music, birdsong). Understanding these sounds depends on an ability to detect and remember patterns in these sounds, patterns ranging from the two-tone oscillation of the ambulance siren to the classic four-chord progression of Western popular music. A key challenge in audition research is to develop effective computer models of these pattern-detection processes. The Prediction by Partial Matching model is one such model, originally developed for data compression, that learns statistical patterns of varying complexity from sequences of discrete symbols (e.g. ‘A, B, A, A, B, A, B’). In previous research this model has proved particularly effective for simulating listeners’ responses to music as well as other kinds of auditory sequences. However, the model is an unrealistic simulation of human cognition in that it possesses a perfect memory, unbounded in capacity, where historic events are recalled just as clearly as recent events. In this paper we therefore introduce a memory-decay component to the model, whereby the salience of historic auditory events decreases over time in line with the dynamics of human auditory memory. We present an experiment showing that this memory-decay model provides a natural account of experimental data from an auditory pattern detection task, explaining how human performance deteriorates as a function of the length of the patterns being detected and the speed at which they are played. Conversely, we also present two simulation studies showing that this memory-decay component can improve pattern detection in auditory environments whose statistical structure changes dynamically over time. These studies indicate the potential benefit of incorporating memory constraints into statistical models of auditory pattern detection, and highlight how these memory constraints can both impair and improve pattern detection, depending on the environment.

This paper presents a Bayesian analysis of linear mixed models for quantile regression based on a Cholesky decomposition for the covariance matrix of random effects. We develop a Bayesian shrinkage approach to quantile mixed regression models using a Bayesian adaptive lasso and an extended Bayesian adaptive group lasso. We also consider variable selection procedures for both fixed and random effects in a linear quantile mixed model via the Bayesian adaptive lasso and extended Bayesian adaptive group lasso with spike and slab priors. To improve mixing of the Markov chains, a simple and efficient partially collapsed Gibbs sampling algorithm is developed for posterior inference. Simulation experiments and an application to the Age-Related Macular Degeneration Trial data to demonstrate the proposed methods.

This paper presents the potential of applying physics-informed neural networks for solving nonlinear multiphysics problems, which are essential to many fields such as biomedical engineering, earthquake prediction, and underground energy harvesting. Specifically, we investigate how to extend the methodology of physics-informed neural networks to solve both the forward and inverse problems in relation to the nonlinear diffusivity and Biot's equations. We explore the accuracy of the physics-informed neural networks with different training example sizes and choices of hyperparameters. The impacts of the stochastic variations between various training realizations are also investigated. In the inverse case, we also study the effects of noisy measurements. Furthermore, we address the challenge of selecting the hyperparameters of the inverse model and illustrate how this challenge is linked to the hyperparameters selection performed for the forward one.

At present, many researchers see hope that artificial intelligence, machine learning in particular, will improve several aspects of the everyday life for individuals, cities and whole nations alike. For example, it has been speculated that the so-called machine learning could soon relieve employees of part of the duties, which may improve processes or help to find the most effective ways of performing tasks. Consequently, in the long run, it would help to enhance employees' work-life balance. Thus, workers' overall quality of life would improve, too. However, what would happen if machine learning as such were employed to try and find the ways of achieving work-life balance? This is why the authors of the paper decided to utilize a machine learning tool to search for the factors that influence the subjective feeling of one's work-life balance. The possible results could help to predict and prevent the occurrence of work-life imbalance in the future. In order to do so, the data provided by an exceptionally sizeable group of 800 employees was utilised; it was one of the largest sample groups in similar studies in Poland so far. Additionally, this was one of the first studies where so many employees had been analysed using an artificial neural network. In order to enable replicability of the study, the specific setup of the study and the description of the dataset are provided. Having analysed the data and having conducted several experiments, the correlations between some factors and work-life balance have indeed been identified: it has been found that the most significant was the relation between the feeling of balance and the actual working hours; shifting it resulted in the tool predicting the switch from balance to imbalance, and vice versa. Other factors that proved significant for the predicted WLB are the amount of free time a week the employee has for themselves, working at weekends only, being self-employed and the subjective assessment of one's financial status. In the study the dataset gets balanced, the most important features are selected with the selectKbest algorithm, an artificial neural network of 2 hidden layers with 50 and 25 neurons, ReLU and ADAM is constructed and trained on 90% of the dataset. In tests, it predicts WLB based on the prepared dataset and selected features with 81% accuracy.

Allowing members of the crowd to propose novel microtasks for one another is an effective way to combine the efficiencies of traditional microtask work with the inventiveness and hypothesis generation potential of human workers. However, microtask proposal leads to a growing set of tasks that may overwhelm limited crowdsourcer resources. Crowdsourcers can employ methods to utilize their resources efficiently, but algorithmic approaches to efficient crowdsourcing generally require a fixed task set of known size. In this paper, we introduce *cost forecasting* as a means for a crowdsourcer to use efficient crowdsourcing algorithms with a growing set of microtasks. Cost forecasting allows the crowdsourcer to decide between eliciting new tasks from the crowd or receiving responses to existing tasks based on whether or not new tasks will cost less to complete than existing tasks, efficiently balancing resources as crowdsourcing occurs. Experiments with real and synthetic crowdsourcing data show that cost forecasting leads to improved accuracy. Accuracy and efficiency gains for crowd-generated microtasks hold the promise to further leverage the creativity and wisdom of the crowd, with applications such as generating more informative and diverse training data for machine learning applications and improving the performance of user-generated content and question-answering platforms., 12 pages, 5 figures

Sorting spikes from extracellular recording into clusters associated with distinct single units (putative neurons) is a fundamental step in analyzing neuronal populations. Such spike sorting is intrinsically unsupervised, as the number of neurons are not known a priori. Therefor, any spike sorting is an unsupervised learning problem that requires either of the two approaches: specification of a fixed value c for the number of clusters to seek, or generation of candidate partitions for several possible values of c, followed by selection of a best candidate based on various post-clustering validation criteria. In this paper, we investigate the first approach and evaluate the utility of several methods for providing lower dimensional visualization of the cluster structure and on subsequent spike clustering. We also introduce a visualization technique called improved visual assessment of cluster tendency (iVAT) to estimate possible cluster structures in data without the need for dimensionality reduction. Experimental results are conducted on two datasets with ground truth labels. In data with a relatively small number of clusters, iVAT is beneficial in estimating the number of clusters to inform the initialization of clustering algorithms. With larger numbers of clusters, iVAT gives a useful estimate of the coarse cluster structure but sometimes fails to indicate the presumptive number of clusters. We show that noise associated with recording extracellular neuronal potentials can disrupt computational clustering schemes, highlighting the benefit of probabilistic clustering models. Our results show that t-Distributed Stochastic Neighbor Embedding (t-SNE) provides representations of the data that yield more accurate visualization of potential cluster structure to inform the clustering stage. Moreover, The clusters obtained using t-SNE features were more reliable than the clusters obtained using the other methods, which indicates that t-SNE can potentially be used for both visualization and to extract features to be used by any clustering algorithm.

Searching similar pictures for a given picture is an important task in numerous applications, including image recommendation system, image classification and image retrieval. Previous studies mainly focused on the similarities of content, which measures similarities based on visual features, such as color and shape, and few of them pay enough attention to semantics. In this paper, we propose a link-based semantic similarity search method, namely PictureSim, for effectively searching similar pictures by building a picture-tag network. The picture-tag network is built by “description” relationships between pictures and tags, in which tags and pictures are treated as nodes, and relationships between pictures and tags are regarded as edges. Then we design a TF-IDF-based model to removes the noisy links, so the traverses of these links can be reduced. We observe that “similar pictures contain similar tags, and similar tags describe similar pictures”, which is consistent with the intuition of the SimRank. Consequently, we utilize the SimRank algorithm to compute the similarity scores between pictures. Compared with content-based methods, PictureSim could effectively search similar pictures semantically. Extensive experiments on real datasets to demonstrate the effectiveness and efficiency of the PictureSim.

The current COVID-19 pandemic threatens human life, health, and productivity. AI plays an essential role in COVID-19 case classification as we can apply machine learning models on COVID-19 case data to predict infectious cases and recovery rates using chest x-ray. Accessing patient’s private data violates patient privacy and traditional machine learning model requires accessing or transferring whole data to train the model. In recent years, there has been increasing interest in federated machine learning, as it provides an effective solution for data privacy, centralized computation, and high computation power. In this paper, we studied the efficacy of federated learning versus traditional learning by developing two machine learning models (a federated learning model and a traditional machine learning model)using Keras and TensorFlow federated, we used a descriptive dataset and chest x-ray (CXR) images from COVID-19 patients. During the model training stage, we tried to identify which factors affect model prediction accuracy and loss like activation function, model optimizer, learning rate, number of rounds, and data Size, we kept recording and plotting the model loss and prediction accuracy per each training round, to identify which factors affect the model performance, and we found that softmax activation function and SGD optimizer give better prediction accuracy and loss, changing the number of rounds and learning rate has slightly effect on model prediction accuracy and prediction loss but increasing the data size did not have any effect on model prediction accuracy and prediction loss. finally, we build a comparison between the proposed models’ loss, accuracy, and performance speed, the results demonstrate that the federated machine learning model has a better prediction accuracy and loss but higher performance time than the traditional machine learning model.

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.

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.

This paper presents the Hybrid Scalable-Minimized-Butterfly-Fat-Tree (H-SMBFT) topology for on-chip communication. Main aspects of this work are the description of the architectural design and the characteristics as well as a comparative analysis against two established indirect topologies namely Butterfly-Fat-Tree (BFT) and Scalable-Minimized-Butterfly-Fat-Tree (SMBFT). Simulation results demonstrate that the proposed topology outperforms its predecessors in terms of performance, area and power dissipation. Specifically, it improves the link interconnectivity between routing levels, such that the number of required links isreduced. This results into reduced router complexity and shortened routing paths between any pair of communicating nodes in the network. Moreover, simulation results under synthetic as well as real-world embedded applications workloads reveal that H-SMBFT can reduce the average latency by up-to35.63% and 17.36% compared to BFT and SMBFT, respectively. In addition, the power dissipation of the network can be reduced by up-to33.82% and 19.45%, while energy consumption can be improved byup-to32.91% and 16.83% compared to BFT and SMBFT, respectively.

In recent years, with the development of computer science, deep learning is held as competent enough to solve the problem of inference and learning in high dimensional space. Therefore, it has received unprecedented attention from both the academia and the business community. Compared with CPU/GPU, FPGA has attracted much attention for its high-energy efficiency, short development cycle and reconfigurability in the aspect of deep learning algorithm. However, because of the limited research on OpenCL optimization on FPGA of deep learning algorithms, OpenCL tools and models applied to CPU/GPU cannot be directly used on FPGA. This makes it difficult for software programmers to use FPGA when implementing deep learning algorithms for a rewarding performance. To solve this problem, this paper proposed an OpenCL computational model based on FPGA template architecture to optimize the time-consuming convolution layer in deep learning. The comparison between the program applying the computational model and the corresponding optimization program provided by Xilinx indicates that the former is 8-40 times higher than the latter in terms of performance.

In this paper, we present a novel Bayesian adaptive dual controller (ADC) for autonomously programming deep brain stimulation devices. We evaluated the Bayesian ADC’s performance in the context of reducing beta power in a computational model of Parkinson’s disease, in which it was tasked with finding the set of stimulation parameters which optimally reduced beta power as fast as possible. Here, the Bayesian ADC has dual goals: (a) to minimize beta power by exploiting the best parameters found so far, and (b) to explore the space to find better parameters, thus allowing for better control in the future. The Bayesian ADC is composed of two parts: an inner parameterized feedback stimulator and an outer parameter adjustment loop. The inner loop operates on a short time scale, delivering stimulus based upon the phase and power of the beta oscillation. The outer loop operates on a long time scale, observing the effects of the stimulation parameters and using Bayesian optimization to intelligently select new parameters to minimize the beta power. We show that the Bayesian ADC can efficiently optimize stimulation parameters, and is superior to other optimization algorithms. The Bayesian ADC provides a robust and general framework for tuning stimulation parameters, can be adapted to use any feedback signal, and is applicable across diseases and stimulator designs., Author summary Deep brain stimulation (DBS) is an effective therapy for treating motor symptoms of Parkinson’s disease. However, the clinical success of DBS relies on selecting stimulation parameters that both relieve symptoms while avoiding side effects. Currently, DBS devices are programmed using a laborious trial-and-error process, requiring multiple clinic visits over the course of months. As DBS leads and algorithms become more complex, it will become impossible to select optimal DBS parameters manually. There is a clear need for an intelligent, automated approach to parameter tuning. We present a novel Bayesian adaptive dual controller (ADC), which can autonomously tune stimulation parameters. It uses a feedback signal measured from the patient to quantify the efficacy of a set of stimulation parameters, and uses this information to intelligently find the parameters which work best for each individual patient. The Bayesian ADC has the potential to improve DBS efficacy and reduce clinic visits by efficiently finding the best stimulation parameters.

As a supply chain solution integrator, fourth party logistics (4PL) has become an important focus for improving the operational efficiency of the logistics industry in recent days. This paper addresses the mechanism design problem of the 4PL for selecting a third party logistics (3PL) provider who involves loss-averse behavior to form a longer-term strategic partnership in multi-attribute reverse auctions. Due to fluctuating costs of energy or labor and unintentional delivery failures like traffic jam or technology malfunctions, we consider two incomplete attributes, namely cost uncertainty and delivery risk. Integrating the loss-averse behavior of 3PLs, based on the prospect theory, the bid decision model is constructed to obtain 3PLs' bidding strategies. The corresponding efficient and optimal scoring auctions that consist of cost-sharing contract and contingent penalty are developed to maximize the ex ante expected profit of the system or the 4PL depending on whether the 4PL is willing to cooperate or not. Theoretical analysis verified by numerical examples illustrates the advantage of the proposed mechanisms. Impacts of model parameters on the 4PL's decision are also investigated and managerial insights are presented.

Common spatial pattern (CSP) is shown to be an effective pre-processing algorithm in order to discriminate different classes of motor-based EEG signals by obtaining suitable spatial filters. The performance of these filters can be improved by regularized CSP, in which available prior information is added in terms of regularization terms into the objective function of conventional CSP. Variety of prior information can be used in this way. In this paper, we used time correlation between different classes of EEG signal as the prior information, which is clarified similarity between different classes of signal for regularizing CSP. Furthermore, the proposed objective function can be easily extended to more than two-class problems. We used three different standard datasets to evaluate the performance of the proposed method. Correlation-based CSP (CCSP) outperformed original CSP as well as the existing regularized CSP, Principle Component Cnalysis (PCA) and Fisher Discriminate Analysis (FDA) in both two-class and multi-class scenarios. The simulation results showed that the proposed method outperformed conventional CSP by 6.9% in 2-class and 2.23% in multi-class problem in term of mean classification accuracy.

In this research, we have investigated doubly singular ordinary differential equations and a real application problem of studying the temperature profile in a porous fin model. We have suggested a novel soft computing strategy for the training of unknown weights involved in the feed-forward artificial neural networks (ANNs). Our neuroevolutionary approach is used to suggest approximate solutions to a highly nonlinear doubly singular type of differential equations. We have considered a real application from thermodynamics, which analyses the temperature profile in porous fins. For this purpose, we have used the optimizer, namely, the fractional-order particle swarm optimization technique (FO-DPSO), to minimize errors in solutions through fitness functions. ANNs are used to design the approximate series of solutions to problems considered in this paper. We find the values of unknown weights such that the approximate solutions to these problems have a minimum residual error. For global search in the domain, we have initialized FO-DPSO with random solutions, and it collects best so far solutions in each generation/ iteration. In the second phase, we have fine-tuned our algorithm by initializing FO-DPSO with the collection of best so far solutions. It is graphically illustrated that this strategy is very efficient in terms of convergence and minimum mean squared error in its best solutions. We can use this strategy for the higher-order system of differential equations modeling different important real applications.

This paper proposes an intersection management strategy for autonomous vehicles under the vehicle-to-infrastructure circumstance. All vehicles are supposed to be fully autonomous and can communicate with the intersection management unit to check the traffic situation. Priority of passing the intersection is decided by a static conflict matrix which represents the potential conflict between lanes of different directions and a dynamic information list which could capture the real-time occupation of each lane in the intersection. Compared with the existing approaches in the literature, the intersection management unit in our strategy is more like a database rather than a computational center, and therefore, requires less computational resource and more likely satisfies the real-time requirement in heavy traffic situations. Simulations are conducted using SUMO (Simulation of Urban MObility), in which the proposed strategy is compared with both fixed and adaptive traffic light methods. The results indicate that the proposed strategy could significantly reduce the average time delay caused by the intersection and the corresponding variance, which shows the efficiency and fairness of the proposed strategy in intersection management.