Benchmarks for text analysis: A response to Budge and Pennings

Similarity or distance measures between two time series play an important role in analysis and retrieval of time series database, which is a fundamental problem in time series data mining. Mathematical model is widely used as a representation of time series, but few papers discuss it in similarity measure of time series. In this paper, we propose a Markov model based technique for similarity/distance measures of variable-length time sequences. State space of Markov model is partitioned by hierarchical clustering method, and the information of state-transition is used to represent a time series. The similarity/distance measures of time sequences can be defined as various functions of the difference between their state-transition information, and some widely used distance measures can be considered as our specific cases. In addition, in modeling procedure, the vector sequence in reconstructed phase space is used instead of the original time sequence, which more effectively reflects the dynamical property of time series. Experimental results show that it works well under the strong noise environment, and it is versatile for various applications by its flexible definition.

The work revisits the autocovariance function estimation, a fundamental problem in statistical inference for time series. We convert the function estimation problem into constrained penalized regression with a generalized penalty that provides us with flexible and accurate estimation, and study the asymptotic properties of the proposed estimator. In case of a nonzero mean time series, we apply a penalized regression technique to a differenced time series, which does not require a separate detrending procedure. In penalized regression, selection of tuning parameters is critical and we propose four different data-driven criteria to determine them. A simulation study shows effectiveness of the tuning parameter selection and that the proposed approach is superior to three existing methods. We also briefly discuss the extension of the proposed approach to interval-valued time series. Supplementary materials for this article are available online.

The similarity measure is a fundamental and key problem for time series analysis, which is widely used in classification, cluster, motif discovery and etc. Time series similarity calculation has been studied a lot and many methods have been proposed, such as Euclidean distance and elastic distance measures. However, all these methods are distance-based which get the similarity by accumulating the distances between optimal match pairs and ignore the intrinsic differences of time series. In order to solve the drawback, we discard this distance-based technique and design a Siamese Convolutional Neural Network(SCNN) to obtain the similarity of time series in this paper. Concretely, we first extract the essential features for similarity calculation by Convolutional Neural Network and then ontain the absolute difference between the essential features of time series. To conveniently train the proposed model, we make full use of the label information of datasets and construct a new binary dataset which each example contains two original time series and a binary label. In the proposed Siamese network, the parameters are shared between two branches and we take binary cross-entropy function to train our model. Experimental results on synthetic and real time series datasets show that our SCNN model is effective and achieves improved accuracy for time series classification task compared to other time series similarity calculation methods.

Abstract. A fundamental problem in paleoclimatology is to take fully into account the various error sources when examining proxy records with quantitative methods of statistical time series analysis. Records from dated climate archives such as speleothems add extra uncertainty from the age determination to the other sources that consist in measurement and proxy errors. This paper examines three stalagmite time series of oxygen isotopic composition (δ18O) from two caves in western Germany, the series AH-1 from the Atta Cave and the series Bu1 and Bu4 from the Bunker Cave. These records carry regional information about past changes in winter precipitation and temperature. U/Th and radiocarbon dating reveals that they cover the later part of the Holocene, the past 8.6 thousand years (ka). We analyse centennial- to millennial-scale climate trends by means of nonparametric Gasser–Müller kernel regression. Error bands around fitted trend curves are determined by combining (1) block bootstrap resampling to preserve noise properties (shape, autocorrelation) of the δ18O residuals and (2) timescale simulations (models StalAge and iscam). The timescale error influences on centennial- to millennial-scale trend estimation are not excessively large. We find a "mid-Holocene climate double-swing", from warm to cold to warm winter conditions (6.5 ka to 6.0 ka to 5.1 ka), with warm–cold amplitudes of around 0.5‰ δ18O; this finding is documented by all three records with high confidence. We also quantify the Medieval Warm Period (MWP), the Little Ice Age (LIA) and the current warmth. Our analyses cannot unequivocally support the conclusion that current regional winter climate is warmer than that during the MWP.

[1] A recent article by Rosenlof and Reid [2008] (hereinafter referred to as RR08) examines the relationship in the tropics between long-term cooling in the stratosphere and warming of the sea surface, with special emphasis in the western Pacific. In the stratosphere, radiosonde observations seem to show that most of the cooling took place since the mid-1990s, apparently coincident to a considerable extent with an increase in the rate of warming of sea surface temperatures (SSTs). A link was proposed by RR08 whereby the increase in SSTs leads to enhanced convection, which is responsible, dynamically, for cooling in the stratosphere. [2] The stratospheric analyses of RR08 rely considerably on tropical radiosonde observations, particularly those from several island stations in the western tropical Pacific. There is extensive evidence that the long-term variation in worldwide radiosonde temperatures is affected critically by inhomogeneities introduced through changes in instruments and measurement practices [e.g., Gaffen, 1994; Gaffen et al., 2000; Lanzante et al . , 2003a, 2003b; Climate Change Science Program (CCSP), 2006], a fact which is acknowledged by RR08. However, they minimize the importance of any such inhomogeneities in the six stations located in the ‘‘warm pool’’ region which they employ [RR08, paragraph 10]: ‘‘However, for our analysis, and in particular for changes noted post-1990, these discontinuities are not sufficient to preclude the use of these stations.’’ The purpose of this comment is to demonstrate that in fact such discontinuities are present, post-1990, and critically affect the evaluation of stratospheric temperatures made by RR08. [3] In their Figures 2, 3, and 5, RR08 display temperature time series for several levels in the lower stratosphere for the four stations located in the heart of the western Pacific warm pool. They note that while most of the earlier part of the records show little long-term trend, a pronounced cooling is seen for about the last 10 years of the record ( 1995–2005). Furthermore, they note an abrupt rise in temperature in early 1999 that lasts for about 2 years. As further evidence to bolster their findings, they note [RR08, paragraph 12] the similarity of the time series from the different stations: ‘‘. . . the overall similarity of the time series in Figure 2 shows that the assumption of homogeneity over the warm pool region is reasonable.’’ Unfortunately, there is considerable evidence to dispute the veracity of these claims. [4] The apparent substantial cooling during the final 10 years of the record can be explained largely by a change in radiosonde instrument type, specifically the transition from Viz to Vaisala, hereafter referred to as the VVT. Abrupt cooling upon introduction of Vaisala radiosondes was noted by Parker et al. [1997] for stations in Australia and New Zealand in the mid to late 1980s, and for U.S. controlled tropical Pacific stations beginning in 1995 [Stendel et al., 2000]. More generally, there has been a systematic worldwide change to Vaisala radiosondes since the 1980s with an expected artificial cooling, especially in the stratosphere [Lanzante et al., 2003a; Christy et al., 2003; CCSP, 2006] (see also Integrated Global Radiosonde Archive (IGRA) station history metadata available at http:// www1.ncdc.noaa.gov/pub/data/igra/igra-metadata.txt). [5] The IGRA metadata indicate that the VVT occurs in November or December 1995 for five of the six stations shown in Figure 1 of RR08 (Lihue, Truk, Koror, Yap, and Pago Pago). The literature cited above suggests that the major part of the drop in stratospheric temperature after 1995 (as seen quite clearly in Figure 5 of RR08) is almost certainly artificial. To further illustrate this point, Figure 1a shows several time series of stratospheric temperatures at Koror. The thick black curve is based on the IGRA data [Durre et al., 2006], which were used by RR08. Note that the IGRA data, although of very high quality (i.e., they have been carefully checked for consistency in time and in the vertical, random errors and outliers, as well as duplicate soundings, etc.), have not been adjusted to account for artificial inhomogeneities. A number of teams have produced adjusted radiosonde temperature time series, each using a different homogenization method. Also shown in Figure 1a are corresponding adjusted time series (HadAT2) [Thorne et al., 2005], RATPAC [Free et al., 2005], IUK [Sherwood et al., 2008], RAOBCORE 1.4 [Haimberger et al., 2008], and RICH [Haimberger et al., 2008] produced by these teams. In comparing the IGRA with the various adjusted time series in Figure 1a it is seen that the adjusted versions all show much less long-term cooling, as indicated by the accompanying trend lines. A closer look at Figure 1a reveals that most of the difference is attributable to the transition across 1995. The adjusted time series shows a JOURNAL OF GEOPHYSICAL RESEARCH, VOL. 114, D12104, doi:10.1029/2008JD010542, 2009 Click Here for Full Article

The Pitfalls of International Human Rights Monitoring: Some Critical Remarks on the 1995 Human Rights Watch/Helsinki Report on Xenophobia in Germany Manfred H. Wiegandt (bio) The euphoria of the opening of the iron curtain in Germany in 1989 and the unification one year later of a country that had been divided since the end of World War II was just abating when the ugly face of xenophobia started to reappear in the country. Pictures of skinheads lashing out at “foreigners,” of shelters for asylum seekers beleaguered by neo-Nazis, and of burned down dwellings housing Turks did the rounds in the international media. Increasingly hostile attitudes and behavior towards foreigners, which occurred amidst a public debate on how to curb the influx of hundreds of [End Page 833] thousands of asylum seekers into Germany, alerted many observers who were concerned about the situation of foreigners in Germany. One of the human rights groups that reacted to the dramatic increase of violence against foreigners was Helsinki Watch, now called Human Rights Watch/Helsinki. In October 1992, Human Rights Watch/Helsinki issued its first report on xenophobic violence in Germany (1992 Report). 1 In April 1995, it released a more elaborate follow-up report on the subject (1995 Report). 2 One may suggest that the international reaction to Human Rights Watch/Helsinki’s allegations of a wave of violent xenophobia in Germany both alerted the public to problems in Germany and put pressure on the German federal and state governments to make changes after they had partly given the fatal impression of silently tolerating, ignoring or, at least, belittling the degree of violence against foreigners in the country. However, despite the beneficial effect of evaluations by Human Rights Watch/Helsinki and other groups, 3 the 1995 Report by Human Rights Watch/Helsinki gives rise to a critique of its approach to human rights monitoring—a critique that may, to some extent, be valid for other human rights groups that pursue a similar approach. There are some fundamental problems with the 1995 Human Rights Watch/Helsinki Report itself. In addition, one might voice some objections to the principles that Human Rights Watch/Helsinki voiced in its dealing with Germany, in particular its “hate speech” policy. The first critique concerns the introductory section of the 1995 Report. Human Rights Watch/Helsinki mentions that Germany has experienced widespread beatings and even killings of foreigners. 4 The 1995 Report states that “[i]t is clear that racist attacks and killings are not unique to Germany. Genocide has been committed in Rwanda and the former Yugoslavia. Many violent attacks against foreigners have occurred in France, England, Sweden, and other Western European democracies in the early 1990s.” 5 It might be just sloppy language that seems to insinuate that the xenophobic attacks in Germany fall under the same category as the genocides in Rwanda and the former Yugoslavia. However, it is unwise to start a serious human rights [End Page 834] investigation with an overdramatization of the situation. Strong words are warranted to attract the attention of the public to the serious human rights violations that have occurred in Germany, particularly because initially the authorities, as the 1992 Report concluded, 6 did not take the violations seriously. However, a comparison between the events in Germany and the genocides in Rwanda and the former Yugoslavia is so out of proportion as to cast doubt on the lack of bias in the whole 1995 Report. The advantage of nongovernmental human rights organizations (human rights NGOs) is that they do not have to feel confined by “diplomatic” usages. Unlike intergovernmental human rights organizations, NGOs are able to speak out and arouse immediate international attention to a specific problem. However, this relative flexibility, which makes human rights NGOs a valuable supplement to “official” and often very inert international human rights organizations, should not be compromised for cheap showmanship. If NGOs in the human rights field were to act like the international media then they could spotlight some situations, but, in doing this they might not be taken seriously by the governments of the countries they were evaluating. It is this type of behavior that could give governments a valid reason not...

INTRODUCTION It is widely believed that the Federal Deposit Insurance Corporation's (FDIC's) flat-rate deposit insurance premium structure encouraged excessively risky bank lending and thereby contributed to the spate of U.S. bank failures during the 1980s and early 1990s. Several reforms have already been introduced to curb this incentive for bank moral hazard behavior. For instance, the 1991 FDIC Improvement Act (FDICIA) mandates the imposition of risk-adjusted capital standards and deposit insurance premiums and early bank closure policies that would reduce the financial burden on the FDIC.(1) However, the fundamental problem in implementing any reform is that the regulator may be less informed than the bank about the quality of the bank's loan portfolio. Several authors have therefore analyzed the design of incentive-compatible regulations which would lead the bank to truthfully reveal its loan quality. But there is little consensus about the existence and nature of such regulations.(2) Furthermore, the regulator's problem is not over if incentive-compatible regulations can be designed. The regulator must next choose one scheme, from an array of incentive-compatible regulations, which will maximize social welfare. However, the welfare implications of regulatory design under asymmetric information have been relatively unexplored in the literature.(3) This article has two main objectives. First, it examines the existence of incentive-compatible regulations in a framework that explicitly incorporates two important features of banking activity: monitoring services provided by the bank to its clients, and potential collusion between the bank and the borrower (through side-payments) to extract a regulatory subsidy. Second, it analyzes the nature of socially optimal incentive-compatible regulations under full information and asymmetric information. A bank in our model performs two intermediation functions. First, the bank provides liquidity services to its depositors for an implicit fee. In equilibrium, this fee equals the value of the services provided. Second, the bank monitors its borrower's project to improve its chance of success.(4) Such monitoring is costly and unobservable by outsiders. Therefore, the market and the regulator make inferences about the bank's optimal level of monitoring which influence the competitive loan rate charged, as well as the regulatory capital requirement and deposit insurance premium actually imposed on the bank. In equilibrium, these inferences are correct. This paradigm yields four main results. First, under full information, banks have an interior optimum capital structure even in the absence of capital regulations. This arises due to the tradeoff between the costs of monitoring and the liquidity service fees foregone and the monitoring benefits earned through increased equity financing. Bank equityholders have a larger residual claim on the loan's payoff and thus have an incentive to increase monitoring effort to improve the loan's probability of success. Optimally, banks use greater equity financing for higher quality loans which are more sensitive to bank monitoring. This result offers a new and empirically testable rationale for the existence of depository institutions. It also provides an explanation of regulatory policy introduced by FDICIA whereby banks with high risk-adjusted capital standards are subject to less regulatory supervision since they are believed to be safer.(5) Second, under full information, social welfare is maximized if the regulator does not impose any capital requirements, when the loan and liability markets are both competitive. There are currently two opposing views in the literature on the effects of capital requirements on bank loan portfolio risk. Koehn and Santomero (1980) and Kim and Santomero (1988) argue that stricter capital requirements would not necessarily lower bank risk, whereas Keeley and Furlong (1990) and Yoon and Mazumdar (forthcoming) support conventional wisdom that they could. …

Two debates over labor market structure have occurred in the U.S. since World War II: the structuralist/aggregate demand school debate in the early 1960s and the deindustrialization debate of the 1980s. In both controversies one side offers a structural explanation in which difficulties in the labor market derive from an overall transformation of the economy. The opposing view is that labor market trends cannot be explained by a structural transformation, since no such transformation has taken place. Despite heated policy debates and impressive data collection the essential point of disagreement in both debates remains unresolved: the existence of structural change in the labor market. This paper argues that two fundamental problems have hindered a satisfactory outcome to these recurring debates over structural change in the labor market. First, each side in the debate has a different concept of structure. If a consensus cannot be reached on what structural change in U.S. labor markets means, any debate over the existence and implications of this change is bound to be fruitless. With an imprecise or inconsistent definition of structure the question cannot be settled empirically. The second and more serious difficulty is that both sides use concepts of structure that have more to do with product markets than labor markets. The focus on product markets results from the fundamental assumption that labor demand is a derived demand. This assumption is axiomatic in neoclassical theory and exerts a powerful influence even on structuralist labor economists who reject much of the orthodox approach to labor. The first part of this paper looks at the consequences of this approach to structure. Despite the fact that the debates were sparked by high unemployment and other disturbing trends in the labor market, the debates address labor market structure only indirectly. The theoretical arguments underlying the assorted views reflect a paradigmatic dispute over the nature of economic growth. The second part of the paper discusses the concept of labor market structure and suggests an alternative approach. The paper then returns briefly to the debates over structure to demonstrate how this alternative approach would clarify this controversy. The Two Labor Market Debates The initial impetus to both debates was a secular rise in average unemployment rates. The structuralist/aggregate demand school controversy resulted from an increase in the average unemployment rate to 5.8% between 1958 and 1964 (Frumkin, 1987).(1) Killingsworth (1965) argued that the trend toward higher unemployment rates was due to a structural transformation of the labor market. The disproportionate incidence of high rates of unemployment in specific segments of the labor market led to the Killingsworth twist, a forerunner of the declining middle of the 1980s. Killingsworth's conclusions were based on the observation of lower unemployment rates among more highly skilled and educated workers. However, despite the use of statistics on labor supply to support his argument, Killingsworth was arguing that it was the structure of labor demand that was undergoing transformation. Killingsworth's structuralist arguments were countered by the Council of Economic Advisors (Bowen, 1965). The Council's contention was that although specific sub-groups of the labor force were affected differently over the business cycle, there had been no secular increase in the level of structural unemployment nor had there been significant increases in the unemployment rates of groups considered to be dominated by unskilled workers. The higher unemployment rates after 1957 were attributed to a deficiency of aggregate demand. During the 1980s unemployment reached its highest level since the Depression. Many manufacturing industries were particularly hard hit by the recessions of the early 1980s leading to widespread layoffs and plant closings. Economists such as Robert Reich (1983), Barry Bluestone and Bennett Harrison (1982) argued that high unemployment rates and the loss of manufacturing jobs reflected long-term structural changes in U. …

As the device technology is progressing in the nanometer regime towards atomic scale, the famous comment “There is plenty of room at the bottom” by Richard Feynman about 60 years ago needs to be reviewed carefully and understood in detail. A recent comment “There is plenty of difficulty near the bottom” by device manufacturers depicts another face of the advancement in technology. The difficulty observed is in the path for building reliable devices. Device reliability is the resultant of various analyses of the design, process and product and understanding innumerable phenomenon to control the extension of even atomic level defects, especially when the dimensions are at nanometer level. At the early stages of technology development, the reliability estimation was through specific tests prediction to weed out defects. Many such tests are a routine and has helped to develop technology. However, at that time itself it was known that understanding device physics and solving the related problems at smaller dimensions are the key to success. As such, the device development at any technology level has been through the critical understanding of the failures through physical analysis and hence solving the issues. This procedure is the Building-in reliability in devices. It could be noted that many fundamental physics problems such as hot carriers, issues of dielectric breakdown and strength, electro migration and stress migration, electrostatic discharge issues, etc which paused the threat at different stages were solved fully or partially through physical failure analysis and understanding the related failure mechanisms. However, as the technology progressed with new materials at new dimensions, the problems also became more challenging. The tools which helped and being used for analysis itself have limitations due to the dimensional miniaturization. Moreover, the diversification in the manufacture from design to product through different vendors and stages invites a separate approach for building the product reliability. This tutorial discusses the fundamentals of reliability and failure analysis in its basic concepts and from where it can be understood using a physics based approach. The progression in devices from the conventional MOSFET and its dimensional shrinkage to nano scale MOSFET and then to new FinFET is discussed with a view to understand how the physical failure analysis can reveal the failure mechanisms to improve reliability. While evolving these processes to build reliability in nano scale devices, it is also understood that the fundamental problem remains the same as in early 1960s. That is where the “the plenty of room” is emerged as “plenty of difficulty”.

The question of characterizing those time-delay systems which are equivalent (up to bicausal transformations) to a delay-free system is a natural and fundamental problem which has been raised since the early 1980s. Surprisingly, this problem remains largely open despite that some partial answers have been provided. This technical note tackles this problem for linear systems with constant time delays, and gives necessary and sufficient conditions to eliminate, whenever is possible, or to reduce the number of time delays and a constructive way to get the corresponding bicausal change of coordinates.

Shape‐from‐shading (SfS) is a fundamental problem in computer vision. Its goal is reconstruction of surface depth (i.e., distance from camera plane) based on a single image of the surface. The problem was introduced in the early 1970s by Horn. A very common assumption in this field is that image projection is orthographic. We will present the orthographic shape‐from‐shading problem and an algorithm for its solution: the fast marching method of Kimmel and Sethian. We shall than reexamine the basis of SfS, which is the image irradiance equation, under a perspective projection assumption. The resultant equation does not depend on the depth function directly, but on its natural logarithm, and as such it is invariant to scale changes of the depth function. A reconstruction method based on the perspective formula is then described; it is a modification of the aforementioned orthographic fast marching method. Then, a comparison of the orthographic fast marching, perspective fast marching, and the perspective algorithm of Prados and Faugeras on synthetic images is are presented. The two perspective methods equate with each other and show better reconstruction results than the orthographic. We then compare the orthographic and perspective versions of the fast marching method on endoscopic images. The perspective algorithm outperformed the orthographic one. These findings suggest that the more realistic set of assumptions of perspective SfS improves reconstruction significantly with respect to orthographic SfS. The findings also provide evidence that perspective SfS can be used for real‐life applications in fields such as endoscopy.

The focus of this dissertation is to derive and demonstrate effective stochastic models for the speech recognition problem. Acoustic modeling for speech recognition typically involves representing the speech process within stochastic models. Modeling this high frequency time series effectively is a fundamental problem. This dissertation devised an objective function that relates the true speech distribution to its estimate. It is shown that through optimizing this function the speech process time series can be modeled without loss of information. The thesis proposes two such models that are developed to optimize the devised objective function. The first an acoustic model formulated for the speech with noise problem. The second a discriminately trained model consisting of optimal discriminant ML estimators. The first, a combination of recognizers that through a simple system fusion, combines multiple speech processes at the decision level. This is a stochastic modeling method devised to combine a parameterized spectral missing data, MD, theory based and a cepstral based speech process using a coupled hidden variable topology. In using a fused coupled hidden Markov model, HMM, topology, an optimal acoustic model is proposed that is inherently more robust than single process models under noisy conditions. The theoretical capability of this model is tested under both stationary and non stationary noise conditions. Under these test conditions the fused model has greater recognition accuracies than those of single process models. The second, formulated with a methodology that segments the acoustic space appropriately for discriminately trained models that optimize the devised objective function. This acoustic space is modeled with discriminant ML estimators formed with optimal decision boundaries using the large margin, support vector machine, SVM, learning method. These discriminately trained models maximize the entropy of the observation space and thereby are capable to model the speech process without loss. This is demonstrated experimentally with frame level classification error rates that are ∼ ≤ 3%.

Classification of time series is a fundamental problem in energy distribution, especially to extract information about events that occurred during the observation period. In this paper, we propose a solution to the problem of identifying energy thefts by introducing a classification method based on convolutional neural networks. The input structure to the model is based on real data that have been certified by external authorities and regards thefts operated by the final user with physical intervention. The training of the neural network is done by means of yearly time series of monthly data, which pertain to different physical quantities relevant to the user profile. The proposed method has been experimentally tested and verified against acceptable test results in different conditions, even giving an indication on where in the sequence the theft has occurred.

A fundamental problem in whole sequence matching and subsequence matching is the problem of representation of time series. In the last decade many high level representations of time series have been proposed for data mining which involve a trade-off between accuracy and compactness. In this paper the author proposes a novel time series representation called GMBR based on Minimum Bounding Rectangle in which the binary idea is applied into the MBR. The experiments have been performed on synthetic, as well as real data sequences to evaluate the proposed method. The experiment demonstrates that 69-92 percent of irrelevant sequences are pruned using the proposed method.

State estimation of space targets is a fundamental problem in autonomous relative navigation. Due to the influence of the complex space environment, systems are subject to various forms of uncertain noise, which can adversely affect state estimation performance. To address this issue, this paper proposes a monocular state estimation method for space targets based on a Global Robust Extended Kalman Filter (GREKF). First, a monocular state estimation system model for space targets is established using spacecraft camera offset. Second, the problem of Global Robust Estimation (GRE) is introduced. Subsequently, for nonlinear system models with uncertainties, the algorithm workflow of the GREKF is derived, and a GREKF based on the space target state estimation system model is developed. This filter enables comprehensive estimation of the targets relative position, relative velocity, attitude, angular velocity, inertia ratio, and feature point positions. Finally, simulation experiments are conducted to validate the superiority of the proposed GREKF algorithm.