Narrow Results

The ranking of events is a powerful way to study the complexity of rare catastrophic events as earthquakes and hurricanes. Hurricane activity can be quantified by the annual accumulated cyclone energy index (ACE), which contains the information of the maximum sustained wind speed, duration and frequency of the tropical cyclone season. Here, the ranking of the Northeast Pacific annual ACE is obtained and fitted using nonlinear regression with several two- and three-parameter ranking laws that fit the tail and head of the data, where lives the information of relevant events for human society. The logarithmic like function $k-alog(n)+blog(N+1-n)$ overperforms all other fits. A sliding window analysis of the parameters $a$ and $b$ of such a function shows that forcing and dissipation processes are anticorrelated.

In this paper, the problem we study is how to maximize a monotone non-submodular function with cardinality constraint. Different from the previous streaming algorithms, this paper mainly considers the sliding window model. Based on the concept of diminishing-return ratio $\gamma$, we propose a $(\frac{1}{3}{\gamma }^2-𝜀)$-approximation algorithm with the memory $O(\frac{k{log}^2(k\mathrm{\Phi }\frac{1}{\gamma })}{{𝜀}^2})$, where $\mathrm{\Phi }$ is the ratio between maximum and minimum values of any singleton element of function $f$. Then, we improve the approximation ratio to $(\frac{1}{2}\gamma -𝜀)$ through the sub-windows at the expense of losing some memory. Our results generalize the corresponding results for the submodular case.

Traditional methods for automatic recognition of container code in visual images are based on segmentation and recognition of isolated characters. However, when the segment fails to separate each character from the others, those methods will not function properly. Sometimes the container code characters are printed or arranged very closely, which makes it a challenge to isolate each character. To address this issue, a new framework for automatic container code recognition (ACCR) in visual images is proposed in this paper. In this framework, code-character regions are first located by applying a horizontal high-pass filter and scan line analysis. Then, character blocks are extracted from the code-character regions and further classified into two categories, i.e. single-character block and multi-character block. Finally, a segmentation-based approach is implemented for recognition of the characters in single-character blocks, and a hidden Markov model (HMM)-based method is proposed for the multi-character blocks. The experimental results demonstrate the effectiveness of the proposed method, which can successfully recognize the container code with closely arranged characters.

Recent emerging applications, such as network traffic analysis, web click stream mining, power consumption measurement, sensor network data analysis, and dynamic tracing of stock fluctuation, call for study of a new kind of data, stream data. Many data stream management systems, prototype systems and software components have been developed to manage the streams or extract knowledge from stream data. Mining frequent patterns is a foundational job for the methods of data mining and knowledge discovery. This paper proposes an algorithm for mining the recent frequent patterns over an online data stream. This method uses RFP-tree to store compactly the recent frequent patterns of a stream. The content of each transaction is incrementally updated into the pattern tree upon its arrival by scanning the stream only once. Moreover, the strategy of conservative computation and time decaying model are used to ensure the correctness of the mining results. Finally, the performance results of extensive simulation show that our work can reduce the average processing time of stream data element and it is superior to other analogous algorithms.

We study the problem of maintaining a (1 + ∊)-factor approximation of the diameter of a stream of points under the sliding window model. In one dimension, we give a simple algorithm that only needs to store points at any time, where the parameter R denotes the "spread" of the point set. This bound is optimal and improves Feigenbaum, Kannan, and Zhang's recent solution by two logarithmic factors. We then extend our one-dimensional algorithm to higher constant dimensions and, at the same time, correct an error in the previous solution. In high nonconstant dimensions, we also observe a constant-factor approximation algorithm that requires sublinear space. Related optimization problems, such as the width, are also considered in the two-dimensional case.

In this work, multifractal methods have been successfully used to characterize the temporal fluctuations of daily Jiuzhai Valley domestic and foreign tourists before and after Wenchuan earthquake in China. We used multifractal detrending moving average method (MF-DMA). It showed that Jiuzhai Valley tourism markets are characterized by long-term memory and multifractal nature in. Moreover, the major sources of multifractality are studied. Based on the concept of sliding window, the time evolutions of the multifractal behavior of domestic and foreign tourists were analyzed and the influence of Wenchuan earthquake on Jiuzhai Valley tourism system dynamics were evaluated quantitatively. The study indicates that the inherent dynamical mechanism of Jiuzhai Valley tourism system has not been fundamentally changed from long views, although Jiuzhai Valley tourism system was seriously affected by the Wenchuan earthquake. Jiuzhai Valley tourism system has the ability to restore to its previous state in the short term.

This paper performs a systematic investigation into the temporal evolution of daily death cases of COVID-19 worldwide lethality considering 90 countries. We apply the information theory quantifiers, more specifically the Permutation entropy $(H_s)$ and Fisher information measure $(F_s)$ to construct the Shannon-Fisher causality plane (SFCP), which allows us to quantify the disorder and evaluate randomness present in the time series of daily death cases related to COVID-19 in each country. Moreover, we employ $H_s$ and $F_s$ to rank the COVID-19 lethality in these countries based on the complexity hierarchy. Our findings reveal that the countries that are located farther from the random ideal position ($H_s=1$, $F_s=0$) in the SFCP such as Taiwan, Vietnam, New Zealand, Singapore, Monaco, Iceland, Thailand, Bahamas, Cyprus, Australia, and Norway are characterized by a less entropy and low disorder, which leads to high predictability of the COVID-19 lethality. Otherwise, the countries that are located near to the random ideal position ($H_s=1$, $F_s=0$) in the SFCP such as Ecuador, Czechia, Iraq, Colombia, Belgium, Italy, Philippines, Iran, Peru, and Japan are characterized by high entropy and high disorder, which implies low predictability of the COVID-19 lethality. We also employ two cluster techniques to analyze the similarity considering the temporal evolution of COVID-19 worldwide lethality for the countries investigated. Based on the values of $H_s$, $F_s$ and our cluster analysis, we suggest that this health crisis will only be adequately combated through global adherence to scientific exchange and technology sharing to homogenize the actions to combat the COVID-19.

This research explores the predictability of the Brazilian inflation monthly price indexes time series by information theory quantifiers. Given this, we apply the Bandt and Pompe method to estimate the information theory quantifiers, specifically the Permutation entropy ($H_s$) and the Fisher information measure ($F_s$). Based on the values of both complexity measures, we construct the 2D plane called the Shannon-Fisher causality plane, which allows us to explore the disorder and quantify the randomness inherent to the temporal evolution of the significant Brazilian inflation indexes. Also, we apply $H_s$ and $F_s$ to rank the Brazilian inflation indexes based on the complexity hierarchy. An overview shows that the Brazilian inflation indexes display lower entropy which implies in higher predictability. The sliding window approach reveals that Brazilian inflation indexes (IPA, IPCA, IGP, IPC, and INPC) present decrease related to efficiency. The only exception is the INCC, which shows an increase in efficiency.

This research uses all of the listed electronic stocks in the Taiwan Stock Exchange as a sample to test the performance of the return rate of stock prices. In addition, this research compares it with the electronic stock returns. The empirical result shows that no matter which kind of stock selection strategy we choose, a majority of the return rate is higher than that of the electronics index. Evident in the results, the predicted effect of BPNN is better than that of the general average decentralized investment strategy. Furthermore, the low price-to-earning ratio and the low book-to-market ratio have a significant long-term influence.

This paper aims to analyze whether the financial crises of the past 20 years have reduced efficiency, in its weak form, in 19 stock markets belonging to the 20 most developed economies (G-20). The sample period comprises the period from 2 January 2000 to 5 February 2021 with the respective financial crises, namely, Dot-com, Argentina, Subprime, Sovereign debt, China stock market crash (2015–2016), UK’s withdrawal from the European Union and the global pandemic of 2020. The results highlight that most markets show signs of (in)efficiency in each sliding window (1000 days), that is, they show asymmetries and non-Gaussian distributions, and ${\alpha }_{\mathrm{\text{DFA}}}\ne 0.5$. These findings suggest that the random walk hypothesis is rejected in certain markets, which has implications for investors, since some returns may be expected, creating arbitrage and abnormal profit opportunities, contrary to the random walk and informational efficiency hypotheses. The results found also open room for market regulators to take steps to ensure better informational data across international financial markets.

Though nowadays high-throughput genotyping techniques' quality improves, missing data still remains fairly common. Studies have shown that even a low percentage of missing SNPs is detrimental to the reliability of down-stream analyses such as SNP-disease association tests. This paper investigates the potentiality for improving the accuracy of an SNP inference method based on the algorithm formerly designed by Roberts and co-workers (NPUTE, 2007). This initial algorithm performs a single scan of an SNP array, inferring missing SNPs in the context of sliding windows. We have first designed a variant, KNNWinOpti, which fully exploits backward and forward dependencies between the overlapping windows and thus restores the genuine dependency of inference upon direction scanning. Our major contribution, algorithm SNPShuttle, therefore iterates bi-directional scanning to predict SNP values with more confidence. We have run simulations on realistic benchmarks built after the high resolution map of mouse strains published by the Perlegen Project. For each of the 20 mouse chromosomes and for missing data percentage varying in range 5%–30%, SNPShuttle has always been shown to increase yet high KNNWinOpti's accuracies.

There are growing interests in algorithms over data streams recently. This paper introduces the problem of sampling from sliding windows of recent data items from data streams and presents two random sampling algorithms for this problem. The first algorithm is a basic window-based sampling algorithm (BWRS Algorithm) for count-based sliding window. BWRS algorithm extends classic reservoir sampling to deal with the expiration of data elements from count-based sliding window, and can avoid drawbacks of classic reservoir sampling. The second algorithm is a stratified multistage sampling algorithm for time-based sliding window (SMS Algorithm). The SMS algorithm takes different sampling fraction in different strata from time-based sliding window, and works even when the number of data items in the sliding window varies dynamically over time. The theoretic analysis and experiments show that the algorithms are effective and efficient for continuous data streams processing.

Give a simple but practical scheme for detecting and defending against Distributed Denial of Service (DDoS), especially for Highly Distributed Denial of Service (HDDoS) attacks by monitoring the increase of new IP addresses. Unlike previous proposals, this proposal includes three modules: detecting, filtering, and illegal-packets analyzing. To improve the detection accuracy, we also proposed a simple but robust algorithm: sliding window algorithm. In the filtering module, a filter performs its tasks only during attacks. While the attack-packets-analyzing module uses a trap to analyze attack packets, perfects the defense system. Simulation results demonstrate the effectiveness of the proposed scheme under varieties of DDoS attack scenarios.

Sliding window protocol (SWP) is the most widely used flow and error control procedure in network. How to describe its dynamic activity in a formal modeling way poses a considerable challenge to us. After analyzing the SWP, we proposed an improved Colored Petri Nets (CPN) model to show how this protocol works. The construction of the CPN model and its analysis are given in detail in this paper. Furthermore, unlike traditional modeling method, CPN arc inscriptions are fully used in our paper to represent system states and simplify the model, so that our method is not only more automated and simpler than previously known CPN modeling method, but also thoroughly avoid the traditionally manual trouble of CPN hierarchy.

The harmonic/interharmonic emission principle of DFIG is derived theoretically and also verified through simulation and field measurements in this paper. To deal with sample data of variable-speed wind turbines accurately and get current spectrum including harmonic and interharmonic, a rotor speed based sliding window for harmonic analysis is proposed. The proposed method is applied to simulation results and field measurements to verify the effectiveness. Compared with spectral analysis using IEC61000-4-7, the frequency spectrum got from the proposed method is more complete.

In this paper the characteristics of data stream are analyzed, the common mode of data stream mining is studied and the difference between the data stream and the traditional database management system is analyzed. The data stream mining technique is introduced into the fault diagnosis application, with the help of a flowchart. The accuracy and effectiveness to solve new problems is improved and the case database can be updated with real-time and dynamically. This paper provides a useful exploration for application of data stream mining.

Frequent items detection is a very useful technique in many applications, such as network monitor, network intrusion detection, worm virus detection, and so on, where data is generally uncertain and could be described using probability. While having been studied intensively in the field of deterministic data, frequent items detection is still novel in the emerging uncertain data field. In this paper, we study the semantic of frequent items detection on uncertain data stream and present a new definition of frequent items over sliding window. Based on the definition, an efficient algorithm is proposed to detect frequent items on uncertain data stream. The algorithm finds the recursion rule in probability computation and greatly improves the efficiency of single data detection, and dynamically detects recent m elements incrementally. Finally, detailed analysis and thorough experimental results demonstrate the efficiency and scalability of our approach.