Search

We consider the exact channel synthesis problem. This problem concerns the determination of the minimum amount of information required to create exact correlation remotely when there is a certain rate of randomness shared by two terminals. This problem generalizes an existing approximate version, in which the generated joint distribution is required to be close to a target distribution under the total variation (TV) distance measure (instead being exactly equal to the target distribution). We provide single-letter inner and outer bounds on the admissible region of the shared randomness rate and the communication rate for the exact channel synthesis problem. These two bounds coincide for doubly symmetric binary sources. We observe that for such sources, the admissible rate region for exact channel synthesis is strictly included in that for the TV-approximate version. We also extend the exact and TV-approximate channel synthesis problems to sources with countably infinite alphabets and continuous sources; the latter includes Gaussian sources. As by-products, lemmas concerning soft-covering under R\'enyi divergence measures are derived., Comment: This is the final version. To appear in IEEE Transactions on Information Theory

Traffic splitting is essential for load balancing over multiple servers, middleboxes, and paths. Often the target traffic distribution is not uniform (e.g., due to heterogeneous servers or path capacities). A natural approach is to implement traffic split in existing rule matching tables in commodity switches. In this paper we suggest an analytical study of such an approach. To do that, we relate the description of distributions in switches to signed representations of positive integers. We suggest an optimal algorithm that minimizes the number of rules needed to represent a weighted traffic distribution. Since switches often have limited rule-table space, the target distribution cannot always be exactly achieved. Accordingly, we also develop a solution that, given a restricted number of rules, finds a distribution that can be implemented within the limited space. To select among different solutions, we describe metrics for quantifying the accuracy of an approximation. We demonstrate the efficiency of the solutions through extensive experiments.

In this paper, we propose a novel stochastic fractional Hamiltonian Monte Carlo approach which generalizes the Hamiltonian Monte Carlo method within the framework of fractional calculus and L\'evy diffusion. Due to the large ``jumps'' introduced by L\'evy noise and momentum term, the proposed dynamics is capable of exploring the parameter space more efficiently and effectively. We have shown that the fractional Hamiltonian Monte Carlo could sample the multi-modal and high-dimensional target distribution more efficiently than the existing methods driven by Brownian diffusion. We further extend our method for optimizing deep neural networks. The experimental results show that the proposed stochastic fractional Hamiltonian Monte Carlo for training deep neural networks could converge faster than other popular optimization schemes and generalize better.

We show some connections between distributional robust and causal inference. Distributional robustness is here understood as optimizing the predictive accuracy for a whole class of distributions instead of just a single target distribution. The class of distributions considered is often a ball around the empirical distribution, using a Wasserstein or Kullback-Leibler distance. Causal inference can be seen as a special case of distributional robustness, where the class of distributions is generated by a causal model. Different choices for these classes are discussed, which correspond to different assumptions about the type of interventions and presence or absence of latent confounding variables.

In order to surmount the major difficulties in multi-target tracking, one was that the observation model and target distribution was highly non-linear and non-Gaussian, the other was varying number of targets bring about overlapping complex interactions and ambiguities. We proposed a kind of system that is able of learning, detecting and tracking the multi-targets. In the method we combine the advantages of two algorithms: mixture particle filters and Multiple Instance Boosting. The key design issues in particle filtering are the selecting of the proposal distribution and the handling the problem of objects leaving and entering the scene. We construct the proposal distribution using a compound model that incorporates information from the dynamic models of each object and the detection hypotheses generated by Multiple Instance Boosting. The learned Multiple Instance Boosting proposal distribution makes us to detect quickly object which is entering the scene, while the filtering process allows us to keep the tracking of the simple object. An automatic multiple targets tracking system is constructed, and it can learn and detect and track the interest object. Finally, the algorithm is tested on multiple pedestrian objects in video sequences. The experiment results show that the algorithm can effectively track the targets the number is changed.

This work addresses the problem of Shannon entropy estimation in countably infinite alphabets studying and adopting some recent convergence results of the entropy functional, which is known to be a discontinuous function in the space of probabilities in ∞-alphabets. Sufficient conditions for the convergence of the entropy are used in conjunction with some deviation inequalities (including scenarios with both finitely and infinitely supported assumptions on the target distribution). From this perspective, four plug-in histogram-based estimators are studied showing that convergence results are instrumental to derive new strong consistent estimators for the entropy. The main application of this methodology is a new data-driven partition (plug-in) estimator. This scheme uses the data to restrict the support where the distribution is estimated by finding an optimal balance between estimation and approximation errors. The proposed scheme offers a consistent (distribution-free) estimator of the entropy in ∞-alphabets and optimal rates of convergence under certain regularity conditions on the problem (finite and unknown supported assumptions and tail bounded conditions on the target distribution).

Beasiswa adalah pemberian berupa bantuan keuangan yang diberikan kepada perorangan, mahasiswa atau pelajar. Namun sering kali dalam pendistribusian beasiswa tersebut tidak tepat sasaran. Hal ini disebabkan karena pemberi beasiswa belum menggunakan alat bantu atau metode yang digunakan untuk menentukan penerima beasiswa. Untuk itu dirancang suatu sistem dalam menentukan penerima beasiswa dengan menggunakan metode Fuzzy Multi Decision Making (FMADM) dan Simple Additive Weighting (SAW). Metode FMADM digunakan untuk mencari alternatif dari sejumlah alternatif dengan kriteria-kriteria yang telah ditentukan. Sedangkan Metode SAW digunakan untuk merangking dari alternatif yang ada. Diharapkan hasil penelitian ini dapat digunakan sebagai alat bantu dalam mengambil keputusan untuk merekomendasikan penerima beasiswa.

Multivalued maps have many applications. We consider one-dimensional multivalued maps whose graphs are defined by lower and upper boundary maps. Let I = [0, 1] and let be a partition of I into a finite number of intervals. Let τl, τu: I → I be two piecewise expanding maps on such that τl ≤ τu. Let G ⊂ I×I be the region bounded by the graphs of τl and τu. Any map η: I → I that takes values in G is called a selector of the multivalued map defined by G. We assume that τl and τu as well as all the selectors we consider have invariant distribution functions. Let F* be a target distribution. We prove the existence of a selector η* which minimizes the functional , where η has invariant distribution Fη. Other results pertain to the functional , where Pη is the Frobenius–Perron operator of η acting on distribution functions. We present an algorithm for finding selectors which minimize J1(η).

Markov Chain Monte Carlo (MCMC) methods are possibly the most popular tools for random sampling nowadays. They generate “chains” (sequences) of samples from a target distribution that can be selected with few constraints. However, as highlighted by the term “chain,” the draws output by the MCMC method are statistically dependent (and often highly correlated), which makes such algorithms not directly comparable with the methods in the rest of this monograph. In this chapter, we describe two families of non-standard MCMC techniques that enjoy the property of producing samples that become asymptotically independent as a parameter grows to infinity or the number of random draws in the algorithm is increased. The methods of the first family are based on generating a pool of candidate samples at each iteration of the chain, instead of only one as in conventional procedures. The techniques in the second family rely on an adaptive, non-parametric approximation of the target density, which is improved as new samples are generated. We describe the general methodology for the two families, and provide some specific algorithms as examples.

The accept/reject method, also known as rejection sampling (RS), was suggested by John von Neumann in 1951. It is a classical Monte Carlo technique for universal sampling that can be used to generate samples virtually from any target density p o (x) by drawing from a simpler proposal density π(x). The sample is either accepted or rejected by an adequate test of the ratio of the two pdfs, and it can be proved that accepted samples are actually distributed according to the target distribution. Specifically, the RS algorithm can be viewed as choosing a subsequence of i.i.d. realizations from the proposal density π(x) in such a way that the elements of the subsequence have density p o (x).

Random search has gained increasing attention from researchers in increasingly many fields and many papers have shown that Levy searching strategy achieves a higher searching efficiency when the targets are sparse in some area. However, we have to face the question that what is the relationship between the optimal searching strategy and the target distribution. In this paper, three different searching strategies, i.e., δ-distribution (fixed flight distance), Gaussian distribution, and Levy distribution, and three different target distributions, i.e., uniform distribution, Gaussian-like distribution, and Levy-like distribution, are considered. We optimize the searching efficiency for three different searching strategies theoretically, which can be used to tune the parameters in the later experiments. According to the experimental results, it is found that Levy searching strategy achieves the highest efficiency for uniform-distributed targets, while Gaussian searching strategy performs the best for Gaussian-distributed and some specific Levy -like distributed targets. This study validates that the optimal searching strategy is closely related to the target distribution.

Definition of the clinical target volume (CTV) is one of the weakest links in the radiation therapy chain. In particular, inability to account for uncertainties is a severe limitation in the traditional CTV delineation approach. Here, we introduce and test a new concept for tumor target definition, the clinical target distribution (CTD). The CTD is a continuous distribution of the probability of voxels to be tumorous. We describe an approach to incorporate the CTD in treatment plan optimization algorithms, and implement it in a commercial treatment planning system. We test the approach in two synthetic and two clinical cases, a sarcoma and a glioblastoma case. The CTD is straightforward to implement in treatment planning and comes with several advantages. It allows one to find the most suitable tradeoff between target coverage and sparing of surrounding healthy organs at the treatment planning stage, without having to modify or redraw a CTV. Owing to the variable probabilities afforded by the CTD, a more flexible and more clinically meaningful sparing of critical structure becomes possible. Finally, the CTD is expected to reduce the inter-user variability of defining the traditional CTV.

Recently, most electric power substations have adopted production control systems, such as SCADA systems, which communicate with field devices and remotely control processes from a computer screen. However, these systems together with protection measures and additional control actions (using protocol IEC61850) seem not to be enough to free substations of security attacks (e.g. virus, intruders, forgery or unauthorized data manipulation). This paper analyzes the main features of an electric power substation together with the aspects that might be significantly affected by cyber-attacks. The paper also presents the implementation of a specific security system (i.e. firewall-wise system) intended to protect a target distribution network.

Organizations are exposed to various cyber-attacks. When a component is exploited, the overall computed damage is impacted by the number of components the network includes. This work is focuses on estimating the Target Distribution characteristic of an attacked network. According existing security assessment models, Target Distribution is assessed by using ordinal values based on users' intuitive knowledge. This work is aimed at defining a formula which enables measuring quantitatively the attacked components' distribution. The proposed formula is based on the real-time configuration of the system. Using the proposed measure, firms can quantify damages, allocate appropriate budgets to actual real risks and build their configuration while taking in consideration the risks impacted by components' distribution. The formula is demonstrated as part of a security continuous monitoring system.

Generally, the performance of a generic detector decreases significantly when it is tested on a specific scene due to the large variation between the source training dataset and the samples from the target scene. To solve this problem, we propose a new formalism of transfer learning based on the theory of a Sequential Monte Carlo (SMC) filter to automatically specialize a scene-specific Faster R-CNN detector. The suggested framework uses different strategies based on the SMC filter steps to approximate iteratively the target distribution as a set of samples in order to specialize the Faster R-CNN detector towards a target scene. Moreover, we put forward a likelihood function that combines spatio-temporal information extracted from the target video sequence and the confidence-score given by the output layer of the Faster R-CNN, to favor the selection of target samples associated with the right label. The effectiveness of the suggested framework is demonstrated through experiments on several public traffic datasets. Compared with the state-of-the-art specialization frameworks, the proposed framework presents encouraging results for both single and multi-traffic object detections.

Approximate Bayesian computation (ABC) performs statistical inference for otherwise intractable probability models by accepting parameter proposals when corresponding simulated datasets are sufficiently close to the observations. Producing the large quantity of simulations needed requires considerable computing time. However, it is often clear before a simulation ends that it is unpromising: it is likely to produce a poor match or require excessive time. This paper proposes lazy ABC, an ABC importance sampling algorithm which saves time by sometimes abandoning such simulations. This makes ABC more scalable to applications where simulation is expensive. By using a random stopping rule and appropriate reweighting step, the target distribution is unchanged from that of standard ABC. Theory and practical methods to tune lazy ABC are presented and illustrated on a simple epidemic model example. They are also demonstrated on the computationally demanding spatial extremes application of Erhardt and Smith (Comput Stat Data Anal 56:1468---1481, 2012), producing efficiency gains, in terms of effective sample size per unit CPU time, of roughly 3 times for a 20 location dataset, and 8 times for 35 locations.

The confidence of target detection can be used to evaluate the reliability and risk level of the detected targets and can effective help to exclude the false alarms, but very little investigation was involved in the past. In this letter, a confidence-driven infrared target detection method is proposed. We develop three confidence evaluating methods: (1) the median classification confidence of the cascade classifier; (2) the context confidence based on the number and the confidence of the merged detection rectangles around the detected target; and (3) the contrast confidence based on the difference between the detected target distribution and the around background distribution. The three confidences are combined to form the final confidence of the detected targets. We then use the confidence to refine the localization of the targets. The evaluation using real infrared images demonstrates the good performance of the proposed confidence-driven infrared detection algorithm on both undetected error and false alarm.

We examined how observers use one aspect of their own morphology, height, when judging the physical characteristics of other people. To address this, participants judged the heights of people as they walked past. We tested the hypothesis that differences between participant and target height account for systematic patterns of variability and bias in height estimation. Height estimate error and error variability increased as the difference between participant height and target height increased, suggesting that estimates are scaled to observers' heights. Furthermore, participants' height estimates were biased toward two standards, demonstrating classic category effects. First, estimates were biased toward participants' own heights. Second, participants biased height estimates toward the average height of the target distribution. These results support past research on using both the body and categorical information to estimate target properties but extend to real-world situations involving interactions with moving people, such as height judgments provided during eyewitness testimony.

A finite mixture model has been used to fit the data from heterogeneous populations to many applications. An Expectation Maximization (EM) algorithm is the most popular method to estimate parameters in a finite mixture model. A Bayesian approach is another method for fitting a mixture model. However, the EM algorithm often converges to the local maximum regions, and it is sensitive to the choice of starting points. In the Bayesian approach, the Markov Chain Monte Carlo (MCMC) sometimes converges to the local mode and is difficult to move to another mode. Hence, in this paper we propose a new method to improve the limitation of EM algorithm so that the EM can estimate the parameters at the global maximum region and to develop a more effective Bayesian approach so that the MCMC chain moves from one mode to another more easily in the mixture model. Our approach is developed by using both simulated annealing (SA) and adaptive rejection metropolis sampling (ARMS). Although SA is a well-known approach for detecting distinct modes, the limitation of SA is the difficulty in choosing sequences of proper proposal distributions for a target distribution. Since ARMS uses a piecewise linear envelope function for a proposal distribution, we incorporate ARMS into an SA approach so that we can start a more proper proposal distribution and detect separate modes. As a result, we can detect the maximum region and estimate parameters for this global region. We refer to this approach as ARMS annealing. By putting together ARMS annealing with the EM algorithm and with the Bayesian approach, respectively, we have proposed two approaches: an EM-ARMS annealing algorithm and a Bayesian-ARMS annealing approach. We compare our two approaches with traditional EM algorithm alone and Bayesian approach alone using simulation, showing that our two approaches are comparable to each other but perform better than EM algorithm alone and Bayesian approach alone. Our two approaches detect the global maximum region well and estimate the parameters in this region. We demonstrate the advantage of our approaches using an example of the mixture of two Poisson regression models. This mixture model is used to analyze a survey data on the number of charitable donations.

In the Seel–Strack contest (J Econ Theory 148(5):2033–2048, 2013), \(n\) agents each privately observe an independent copy of a drifting Brownian motion which starts above zero and is absorbed at zero. Each agent chooses when to stop the process she observes, and the winner of the contest is the agent who stops her Brownian motion at the highest value. The objective of each agent is to maximise her probability of winning the contest. Seel and Strack derived a Nash equilibrium under a joint feasibility condition on the drift and the number of players. We consider a generalisation of the Seel–Strack contest in which the observed processes are independent copies of some time-homogeneous diffusion. This naturally leads us to consider the problem in cases where the analogue of the feasibility condition is violated. We solve the problem via a change of scale and a Lagrangian method. Unlike in the Seel–Strack problem, it turns out that the optimal strategy may involve a target distribution which has an atom, and the rule used for breaking ties becomes important.

The assessment of activity cliffs has thus far mostly focused on compound pairs, although the majority of activity cliffs are not formed in isolation but in a coordinated manner involving multiple active compounds and cliffs. However, the composition of coordinated activity cliff configurations and their topologies are unknown. Therefore, we have identified all activity cliff configurations formed by currently available bioactive compounds and analyzed them in network representations where activity cliff configurations occur as clusters. The composition, topology, frequency of occurrence, and target distribution of activity cliff clusters have been determined. A limited number of large cliff clusters with unique topologies were identified that were centers of activity cliff formation. These clusters originated from a small number of target sets. However, most clusters were of small to moderate size. Three basic topologies were sufficient to describe recurrent activity cliff cluster motifs/topologies. For example, frequently occurring clusters with star topology determined the scale-free character of the global activity cliff network and represented a characteristic activity cliff configuration. Large clusters with complex topology were often found to contain different combinations of basic topologies. Our study provides a first view of activity cliff configurations formed by currently available bioactive compounds and of the recurrent topologies of activity cliff clusters. Activity cliff clusters of defined topology can be selected, and from compounds forming the clusters, SAR information can be obtained. The SAR information of activity cliff clusters sharing a/one specific activity and topology can be compared.

Normal state-space models are prevalent, but to increase the applicability of the Kalman filter, we propose mixtures of skewed, and extended skewed, Kalman filters. To do so, the closed skew-normal distribution is extended to a scale mixture class of closed skew-normal distributions. Some basic properties are derived and a class of closed skew-t distributions is obtained. Our suggested family of distributions is skewed and has heavy tails too, so it is appropriate for robust analysis. Our proposed special sequential Monte Carlo methods use a random mixture of the closed skew-normal distributions to approximate a target distribution. Hence it is possible to handle skewed and heavy tailed data simultaneously. These methods are illustrated with numerical experiments.

Markov chain Monte Carlo methods are now hugely popular and are used in all aspects of scientific learning. One of the most widely used and efficient methods is the Metropolis--Hastings algorithm. In this note, we introduce an alternative to the Metropolis--Hastings sampler when the state space is countably infinite and the stationary or target distribution is represented by a set of unnormalized probabilities. We illustrate with a comparison of the Metropolis--Hastings sampler.

For importance sampling (IS), multiple proposals can be combined to address different aspects of a target distribution. There are various methods for IS with multiple proposals, including Hesterberg's stratified IS estimator, Owen and Zhou's regression estimator, and Tan's maximum likelihood estimator. For the problem of efficiently allocating samples to different proposals, it is natural to use a pilot sample to select the mixture proportions before the actual sampling and estimation. However, most current discussions are in an empirical sense for such a two-stage procedure. In this article, we establish a theoretical framework of applying the two-stage procedure for various methods, including the asymptotic properties and the choice of the pilot sample size. By our simulation studies, these two-stage estimators can outperform estimators with naive choices of mixture proportions. Furthermore, while Owen and Zhou's and Tan's estimators are designed for estimating normalizing constants, we extend their usa...

This paper presents a particle method designed for high-dimensional state estimation. Instead of weighing random forecasts by their distance to given observations, the method samples an ensemble of particles around an optimal solution based on the observations (i.e., it is implicit). It differs from other implicit methods because it includes the state at the previous assimilation time as part of the optimal solution (i.e., it is a lag-1 smoother). This is accomplished through the use of a mixture model for the background distribution of the previous state. In a high-dimensional, linear, Gaussian example, the mixture-based implicit particle smoother does not collapse. Furthermore, using only a small number of particles, the implicit approach is able to detect transitions in two nonlinear, multi-dimensional generalizations of a double-well. Adding a step that trains the sampled distribution to the target distribution prevents collapse during the transitions, which are strongly nonlinear events. To produce similar estimates, other approaches require many more particles.

Based on the analysis of statistic characteristics of target distribution area of the anti-ship missile, three kinds of equivalent calculation model and graphical programming on it were presented. On this condition, some simulation tests on typical situation were carried out and contrastive analysis of the three distribution area of equivalent calculation methods, so as to obtain the applicable situation of each.

This paper deals with a new problem that is a generalization of the many to many pickup and delivery problem and which is motivated by operating self-service bike sharing systems. There is only one commodity, initially distributed among the vertices of a graph, and a capacitated single vehicle aims to redistribute the commodity in order to reach a target distribution. Each vertex can be visited several times and also can be used as a buffer in which the commodity is stored for a later visit. This problem is NP-hard, since it contains several NP-hard problems as special cases (the TSP being maybe the most obvious one). Even finding a tractable exact formulation remains problematic. This paper presents efficient algorithms for solving instances of reasonable size, and contains several theoretical results related to these algorithms. A branch-and-cut algorithm is proposed for solving a relaxation of the problem. An upper bound of the optimal solution of the problem is obtained by a tabu search, which is based on some theoretical properties of the solution, once fixed the sequence of the visited vertices. The possibility of using the information provided by the relaxation receives a special attention, both from a theoretical and a practical point of view. It is proven that to build a feasible solution of the problem by using the one obtained by the relaxation is an NP-hard problem. Nevertheless, a tabu search initialized with the optimal solution of the relaxation often shows that it is the optimal one. The algorithms have been tested on a set of instances coming from the literature, proving their effectiveness.

It is well known that Markov chain Monte Carlo (MCMC) methods scale poorly with dataset size. A popular class of methods for solving this issue is stochastic gradient MCMC (SGMCMC). These methods use a noisy estimate of the gradient of the log-posterior, which reduces the per iteration computational cost of the algorithm. Despite this, there are a number of results suggesting that stochastic gradient Langevin dynamics (SGLD), probably the most popular of these methods, still has computational cost proportional to the dataset size. We suggest an alternative log-posterior gradient estimate for stochastic gradient MCMC which uses control variates to reduce the variance. We analyse SGLD using this gradient estimate, and show that, under log-concavity assumptions on the target distribution, the computational cost required for a given level of accuracy is independent of the dataset size. Next we show that a different control variate technique, known as zero variance control variates, can be applied to SGMCMC algorithms for free. This post-processing step improves the inference of the algorithm by reducing the variance of the MCMC output. Zero variance control variates rely on the gradient of the log-posterior; we explore how the variance reduction is affected by replacing this with the noisy gradient estimate calculated by SGMCMC.

В роботі розглянуто оцінку похибки визначення часу висування бойової машини (вогневої одиниці) із зони «затінення» в зону прямої видимості цілі. Досліджено залежність цієї похибки від точності визначення геоінформаційною системою координат найближчого до бойової машини ланцюга межі зони «затінення», точності визначення координат бойової машини навігаційною системою та швидкості пересування бойової машини на полі бою., В роботе рассмотрено оценку погрешности определения времени выдвижения боевой машины (огневой единицы) из зоны «затенения» в зону прямой видимости цели. Исследована зависимость этой погрешности от точности определения геоинформационной системой координат ближайшей цепи границы зоны «затенения», точности определения координат боевой машины навигационной системой и скорости передвижения машины на поле боя., In the considered assessment of the timing error for the nomination battle machines (firepower units) from the zone of «shading» in the zone of direct visibility goal. The dependence of this bias from the accuracy of the geographic information system of coordinates of the nearest chain border zone «shading», positioning accuracy vehicle navigation system and speed the movement of machine on the battlefield. The mathematical model of evaluation of error determine the time of the nomination battle machines from the zone «shading» in the zone of direct visibility goal. Mathematical modelling was conducted using the application package in Wednesday for the most common Maple arrangements combat vehicle to the nearest chain border zone «shading». It is shown that positioning error nearest to battle machine chain border zone «shading» geoinformation system and positioning errors of combat vehicle navigation system commensurate with the contribution to the total amount of error in determining the time of the nomination battle machines from the zone «shading» in the zone of direct visibility goal. The magnitude of the error in determining the extension time of the combat vehicle from the zone of «shade» in the line of sight of the goal decreases with increase in the speed of movement of the combat vehicle, and is increased by increasing the error of determining the coordinates of the nearest combat car circuit border zone «shading» and the error of determination of coordinates of a combat vehicle. The obtained analytical relation that allows to make demands to the magnitude of the measurement errors of the coordinates closest to the military machine of the circuit of the border zone, «shading» geoinformational system and coordinates combat vehicle navigation system according to the specified requirements for the size of the error in determining the extension time of the combat vehicle from the zone of «shade» in the line of sight of the target.

Modern recommendation systems leverage some forms of collaborative user or crowd sourced collection of information. For instance, services like TripAdvisor, Airbnb and HungyGoWhere rely on user-generated content to describe and classify hotels, vacation rentals and restaurants. By nature of such independent collection of information, the multiplicity, diversity and varying quality of the information collected result in uncertainty. Objects, such as the services offered by hotels, vacation rentals and restaurants, have uncertain scores for their various features.In this context, ranking of uncertain data becomes a crucial issue. Several data models for uncertain data and several semantics for probabilistic top-k queries have been proposed in the literature. We consider here a model of objects with uncertain scores given as probability distributions and the semantics proposed by the state of the art reference work of Soliman, Hyas and Ben-David.In this paper, we explore the design space of Metropolis-Hastings Markov chain Monte Carlo algorithms for answering probabilistic top-k queries over a database of objects with uncertain scores. We are able to devise several algorithms that yield better performance than the reference algorithm. We empirically and comparatively prove the effectiveness and efficiency of these new algorithms.

The moving targets only exist in a few range cells for space-time adaptive processing (STAP), i.e. targets are sparsely distributed in the entire range cells and most of the range cells are target-free. By utilizing the sparsity of the target distribution, we proposed a novel STAP method based on minimizing the l 1 -norm of the output magnitude. Unlike the conventional STAP which exclude the cell under test from the training samples to avoid target self-nulling, our method process the cell under test (CUT) and training samples simultaneously without samples selection. Unlike the slide window processor whose weights need to be updated for each range cell, the adaptive weight of our method for a block of samples requires no updating. Consequently, the computation complexity is much less than the conventional STAP. Simulation results demonstrate the superiority of the proposed STAP method over several state-of-the-art STAP methods.

In this paper, we investigate the use of coarse image features for predicting class label distributions at a finer scale. The major contributions of this work are 1) use of coarse image features to improve the optimization formulation of conventional rank based approaches 2) use of inter class compatibility information from coarse images to refine the predicted target distribution 3) an enhanced unsupervised variogram based sub-pixel mapping approach 4) inclusion of abundance estimation uncertainty in the unmixing process. The proposed modifications on rank based and variogram based approaches have produced an accuracy improvement of 10–15%. The sensitivities of these approaches towards tunable parameters are also analyzed.

We propose an adaptive Metropolis-Hastings algorithm in which sampled data are used to update the proposal distribution. We use the samples found by the algorithm at a particular step to form the information-theoretically optimal mean-field approximation to the target distribution, and update the proposal distribution to be that approximatio. We employ our algorithm to sample the energy distribution for several spin-glasses and we demonstrate the superiority of our algorithm to the conventional MH algorithm in sampling and in annealing optimization., To appear in Europhysics Letters

Real-world visual searches often contain a variable and unknown number of targets. Such searches present difficult metacognitive challenges, as searchers must decide when to stop looking for additional targets, which results in high miss rates in multiple-target searches. In the study reported here, we quantified human strategies in multiple-target search via an ecological optimal foraging model and investigated whether searchers adapt their strategies to complex target-distribution statistics. Separate groups of individuals searched displays with the number of targets per trial sampled from different geometric distributions but with the same overall target prevalence. As predicted by optimal foraging theory, results showed that individuals searched longer when they expected more targets to be present and adjusted their expectations on-line during each search by taking into account the higher-order, across-trial target distributions. However, compared with modeled ideal observers, participants systematically responded as if the target distribution were more uniform than it was, which suggests that training could improve multiple-target search performance.

In this paper, we examine whether a more ambiguity-averse individual will invest in more effort to shift her initial starting wealth distribution toward a better target distribution. We assume that the individual has ambiguous beliefs regarding two target (starting) distributions and that one distribution is preferred to the other. We find that an increase in ambiguity aversion will decrease (increase) the optimal effort when the cost of effort is non-monetary. When the cost of effort is monetary, the effect depends on whether the individual would make more effort when the target (starting) distribution is the preferred distribution than the target (starting) distributions, the inferior one. We further characterize the individual’s higher-order risk preferences to examine the sufficient conditions.

The slope of the z-transformed receiver-operating characteristic (zROC) in recognition memory experiments is usually less than 1, which has long been interpreted to mean that the variance of the target distribution is greater than the variance of the lure distribution. The greater variance of the target distribution could arise because the different items on a list receive different increments in memory strength during study (the “encoding variability” hypothesis). In a test of that interpretation, Koen and Yonelinas (2010) attempted to further increase encoding variability to see whether it would further decrease the slope of the zROC. To do so, they presented items on a list for 2 different durations and then mixed the weak and strong targets together. After performing 3 tests on the mixed-strength data, Koen and Yonelinas concluded that encoding variability does not explain why the slope of the zROC is typically less than 1. However, we show that their tests have no bearing on the encoding variability account. Instead, they bear on the mixture-unequal-variance signal-detection (UVSD) model that corresponds to their experimental design. On the surface, the results reported by Koen and Yonelinas appear to be inconsistent with the predictions of the mixture-UVSD model (though they were taken to be inconsistent with the predictions of the encoding variability hypothesis). However, all 3 of the tests they performed contained errors. When those errors are corrected, the same 3 tests show that their data support, rather than contradict, the mixture-UVSD model (but they still have no bearing on the encoding variability hypothesis).

Summary A new model for computing the allowable cut for uneven-aged stands is described. The model is focused on the Gini index against basal area and the target structure of stand volume on diameter classes, assumed to be achieved by the end of transformation period from even-aged to the uneven-aged structure. The real structure of the stand is characterized by a given Gini index while the target structure is characterized by a benchmark Gini index. In order to determine the benchmark Gini index, the model allows the establishment of target structure of the stand based on a new idea: target structure of trees number in diameter classes for a particular stand corresponds to a certain target distribution of volumes on diameter classes. According to the difference between the two mentioned Gini indices, a certain period for directing the real structure to the target structure is further chosen while the computation of the allowable cut is based on the assumption of Gaussian distribution of volume against diameter classes. Eventually, the computation of allowable cut takes into account the stand growth, the differences between the real and the target growing stock, the adopted transformation period and the management goals.

Using process samples to develop near infrared prediction models can generate artefacts in the calibration set, potentially reducing model performance. Due to the inherent variability of manufacturing processes, the assumption that all samples from a given batch have the same concentration for the compound of interest is incorrect. A tablet press will produce compacts with different drug concentrations, distributed around a nominal value, due to mechanical effects, vibrations and powder segregation that occur in the hopper. Differences in tablet crushing strength may also be observed for those same reasons. Consequently, using such samples and their associated nominal concentrations for the development of a calibration model for the prediction of content uniformity of tablets might produce models with rather high error while able to cope with a large range of process variability. The objective of this work was to investigate empirical approaches for optimising the target (reference) concentrations of prediction samples to best match the underlying spectral variance in an attempt to mitigate interferences that may be responsible for select portions of calibration error. Three approaches were developed. The first used samples presenting a low residual from an original model to re-predict high residual samples. The second approach was an iterative search of the best target value for each sample. The third method used target values generated from a normal distribution. These approaches were compared with the classical slope and bias correction methods on their ability to predict two independent validation sets. While several methods showed significant over-fitting and a high validation error, the iterative search routine enhanced calibration performance compared to post-regression correction methods and was proven to be a viable alternative to current industry practices.

Coherence analysis is a powerful tool in seismic interpretation for imaging geological discontinuities such as faults and fractures. However, subtle faults or fractures of one stratum are difficult to be distinguished on coherence sections (time slices or profiles) due to interferences from adjacent strata, especially these with strong reflectivity. In this paper, we propose a coherence enhancement method which applies local histogram specification (LHS) techniques to enhance subtle faults or fractures in the coherence cubes. Unlike the traditional histogram specification (HS) algorithm, our method processes 3D coherence data without discretization. This method partitions a coherence cube into many sub-blocks and self-adaptively specifies the target distribution in each block based on the whole distribution of the coherence cube. Furthermore, the neighboring blocks are partially overlapped to reduce the edge effect. Applications to real datasets show that the new method enhances the details of subtle faults and fractures noticeably.

Although an input distribution may not majorize a target distribution, it may majorize a distribution which is close to the target. Here we introduce a notion of approximate majorization. For any distribution, and given a distance $\delta$, we find the approximate distributions which majorize (are majorized by) all other distributions within the distance $\delta$. We call these the steepest and flattest approximation. This enables one to compute how close one can get to a given target distribution under a process governed by majorization. We show that the flattest and steepest approximations preserve ordering under majorization. Furthermore, we give a notion of majorization distance. This has applications ranging from thermodynamics, entanglement theory, and economics.

Due to the relative scarcity of long-term toxicity data, assessment factors for extrapolation from relatively short to chronic exposures have an important role in the risk assessment of chemicals. A recent REACH guidance document includes recommended default assessment factors that cover subacute-subchronic, subchronic-chronic, and subacute-chronic extrapolations. The recommended assessment factors are smaller than in most previous proposals, since they are calibrated to achieve central estimates (50th percentile of the target distribution) rather than a higher percentile such as the 95th, as has been more common. These assessment factors are nevertheless presented as representing a "widely agreed level of conservatism", a statement that may lead to misunderstandings of what is achieved by using them in a risk assessment. Assessment factors have been based on evidence from animal studies with different designs, in particular with focus on different endpoints. Our re-analysis of experimental data shows that using mortality as an endpoint leads to smaller assessment factors than if the factors are derived from corresponding ratios for non-lethal toxicity.

European Union (EU) road safety policies include reduction in road fatalities by 50% during 2000-2010. The original territorial distribution of this target is uniform, as all the territories have to halve the number of fatalities regardless of their previous record. We propose a simple method of distributing the total effort required to reach the EU target of halving fatalities in a territory in such a way that those areas with a higher proportion of fatalities (relative to their populations) have the highest targets and the sum of all of the areas is the 50% reduction. The distribution function we use here is based on an inverse logarithmic function selected from among several alternative functions analyzed in an initial study. This use of weighted distribution functions has been applied since 2000 by the EU in other policies, such as the use of renewable energies. We applied the proposed distribution function to two territorial aggregation levels in the EUROSTAT Nomenclature of Territorial Units for Statistics (NUTS): NUTS0 for EU-15 and EU-25 Member States, and NUTS3 for the 50 Spanish provinces, comparing the new and old targets with the real achievements for the 2000-2006 period, and new and old targets for the 2000-2010 period. This is a simple proposal for modification of target distribution that can be further improved using other parameters, such as road or weather conditions.

The minimum averaged mean squared error nonparametric adaptive weights use data from m possibly different populations to infer about one population of interest. The definition of these weights is based on the properties of the empirical distribution function. We use the Kaplan-Meier estimate to let the weights accommodate right-censored data and use them to define the weighted Kaplan-Meier estimate. The proposed estimate is smoother than the usual Kaplan-Meier estimate and converges uniformly in probability to the target distribution. Simulations show that the performances of the weighted Kaplan-Meier estimate on finite samples exceed that of the usual Kaplan-Meier estimate. A case study is also presented.