Search

This paper constructed a stacked-autoencoder neural network model (SAE model) to estimate sea state bias (SSB) based on radar altimeter data. Six cycles of the geophysical data record (GDR) from Jason-1/2 radar altimeters were used as a training dataset, and the other 2 cycles of the GDR from Jason-1/2 were used for testing. The inputs to this SAE model include the significant wave height (SWH), wind speed (U), sea surface height (SSH), backscatter coefficient (σ0) and automatic gain control (AGC), and the model outputs the SSB. The model includes one input layer, three hidden layers and one output layer. The SSBs in the GDR of Jason-1/2 were obtained from a nonparametric model based on the SWH and U as input variables; thus, the model has high accuracy but low efficiency. The SSBs in the GDR of HY-2A were computed using a four-parameter parametric model that uses the SWH and U as input variables; therefore, this model’s computational speed is high but its accuracy is low. Thus, we used the HY-2A radar altimeter as an unseen validation dataset to evaluate the performance of the SAE model. Then, we analyzed the contrasting results of these methods, including the differences in the SSB, explained variance, residual error and operational efficiency. The results demonstrate not only that the accuracy of the SAE model is superior to that of the conventional parametric model but also that its operational efficiency is better than that of the nonparametric model. [ABSTRACT FROM AUTHOR]

Bitcoin is a digital currency and electronic payment system operating over a peer-to-peer network on the Internet. One of its most important properties is the high level of anonymity it provides for its users. The users are identified by their Bitcoin addresses, which are random strings in the public records of transactions, the blockchain. When a user initiates a Bitcoin transaction, his Bitcoin client program relays messages to other clients through the Bitcoin network. Monitoring the propagation of these messages and analyzing them carefully reveal hidden relations. In this paper, we develop a mathematical model using a probabilistic approach to link Bitcoin addresses and transactions to the originator IP address. To utilize our model, we carried out experiments by installing more than a hundred modified Bitcoin clients distributed in the network to observe as many messages as possible. During a two month observation period we were able to identify several thousand Bitcoin clients and bind their transactions to geographical locations. [ABSTRACT FROM AUTHOR]

Heterogeneous mobile authentication is a crucial technique to securely retrieve the resource of e-healthcare cloud servers which are commonly implemented in a public key Infrastructure (PKI). Conventionally, a mobile data user can utilize a self-chosen password along with a portable device to request the access privilege of clouds. However, to validate the membership of users, a cloud server usually has to make use of a password table, which not only increases the burden of management, but also raises the possibility of information leakage. In this paper, we propose a secure heterogeneous mobile authentication and key agreement scheme for e-healthcare cloud systems. In our system structure, an e-healthcare cloud server of traditional PKIs does not have to store a password table. A legitimate data user only possesses a security token hardware and keeps an offline updatable password without using any private key. Our scheme is classified into the category of dynamic ID authentication techniques, since a data user is able to preserve his/her anonymity during authentication processes. We formally prove that the proposed mechanism fulfills the essential authenticated key exchange (AKE) security and owns lower computational costs. To further ensure the practical application security, an automatic security validation tool called AVISPA is also adopted to analyze possible attacks and pitfalls of our designed protocol. [ABSTRACT FROM AUTHOR]

Certificateless aggregate signature (CLAS) is a crucial cryptosystem. It can not only compress multiple signatures into a short signature, but also ensure the validity of each signature participating in the aggregation by verifying the validity of an resulting aggregate signature. Therefore, a secure and efficient CLAS scheme is very useful for resource-constrained environments because it greatly reduces the overall length of the signature and the verifier’s computational overhead. Cheng et al. presented an efficient CLAS scheme and proved its security in the random oracle model. However, we find that their scheme has security flaws. In this paper, we demonstrate that Cheng et al.’s CLAS scheme is vulnerable to coalition attacks from internal signers. To overcome these attacks, we present an improved CLAS scheme and prove that it is existentially unforgeable under the computational Diffie-Hellman assumption. In addition, our CLAS scheme can not only resist coalition attacks but also generate a very short aggregate signature. The performance analysis results show that our improved CLAS scheme is lower than the related CLAS schemes in terms of communication overhead and computation cost. [ABSTRACT FROM AUTHOR]

LncRNA-protein interactions play important roles in post-transcriptional gene regulation, poly-adenylation, splicing and translation. Identification of lncRNA-protein interactions helps to understand lncRNA-related activities. Existing computational methods utilize multiple lncRNA features or multiple protein features to predict lncRNA-protein interactions, but features are not available for all lncRNAs or proteins; most of existing methods are not capable of predicting interacting proteins (or lncRNAs) for new lncRNAs (or proteins), which don’t have known interactions. In this paper, we propose the sequence-based feature projection ensemble learning method, “SFPEL-LPI”, to predict lncRNA-protein interactions. First, SFPEL-LPI extracts lncRNA sequence-based features and protein sequence-based features. Second, SFPEL-LPI calculates multiple lncRNA-lncRNA similarities and protein-protein similarities by using lncRNA sequences, protein sequences and known lncRNA-protein interactions. Then, SFPEL-LPI combines multiple similarities and multiple features with a feature projection ensemble learning frame. In computational experiments, SFPEL-LPI accurately predicts lncRNA-protein associations and outperforms other state-of-the-art methods. More importantly, SFPEL-LPI can be applied to new lncRNAs (or proteins). The case studies demonstrate that our method can find out novel lncRNA-protein interactions, which are confirmed by literature. Finally, we construct a user-friendly web server, available at . [ABSTRACT FROM AUTHOR]

Pneumonia is one of the major causes of child mortality, yet with a timely diagnosis, it is usually curable with antibiotic therapy. In many developing regions, diagnosing pneumonia remains a challenge, due to shortages of medical resources. Lung ultrasound has proved to be a useful tool to detect lung consolidation as evidence of pneumonia. However, diagnosis of pneumonia by ultrasound has limitations: it is operator-dependent, and it needs to be carried out and interpreted by trained personnel. Pattern recognition and image analysis is a potential tool to enable automatic diagnosis of pneumonia consolidation without requiring an expert analyst. This paper presents a method for automatic classification of pneumonia using ultrasound imaging of the lungs and pattern recognition. The approach presented here is based on the analysis of brightness distribution patterns present in rectangular segments (here called “characteristic vectors“) from the ultrasound digital images. In a first step we identified and eliminated the skin and subcutaneous tissue (fat and muscle) in lung ultrasound frames, and the “characteristic vectors”were analyzed using standard neural networks using artificial intelligence methods. We analyzed 60 lung ultrasound frames corresponding to 21 children under age 5 years (15 children with confirmed pneumonia by clinical examination and X-rays, and 6 children with no pulmonary disease) from a hospital based population in Lima, Peru. Lung ultrasound images were obtained using an Ultrasonix ultrasound device. A total of 1450 positive (pneumonia) and 1605 negative (normal lung) vectors were analyzed with standard neural networks, and used to create an algorithm to differentiate lung infiltrates from healthy lung. A neural network was trained using the algorithm and it was able to correctly identify pneumonia infiltrates, with 90.9% sensitivity and 100% specificity. This approach may be used to develop operator-independent computer algorithms for pneumonia diagnosis using ultrasound in young children. [ABSTRACT FROM AUTHOR]

Radio frequency identification (RFID) has recently experienced unprecedented development. Among many other areas, it has been widely applied in blood station management, automatic supermarket checkout, and logistics. In the application of RFID for large-scale passive tags, tag collision is inevitable owing to the non-cooperation mechanism among tags. Therefore, a tag anti-collision method is a key factor affecting the identification efficiency. In this paper, we propose a tag anti-collision method based on Aloha technology for RFID. It estimates the number of remaining tags using the secant iteration method. To achieve optimal identification efficiency, it adaptively and dynamically adjusts the lengths of the subsequent frames according to the principle that the length of a frame should be the same as the number of tags to be identified. For pseudo-solutions of tag population estimation while using secant iteration, we present an elimination method by two probing frames. The simulation results show that the estimation precision of our method can reach above 97%. Thus, it can meet the requirement of the tag anti-collision estimation accuracy. Its global throughput is obviously superior to the Q algorithm adopted by the current international standard, and it is close to the ideal system. It consequently outperforms existing schemes. [ABSTRACT FROM AUTHOR]

The multi-group asset flow model is a nonlinear dynamical system originally developed as a tool for understanding the behavioral foundations of market phenomena such as flash crashes and price bubbles. In this paper we use a modification of this model to analyze the dynamics of a single-asset market in situations when the trading rates of investors (i.e., their desire to exchange stock for cash) are prescribed ahead of time and independent of the state of the market. Under the assumption of fast trading compared to the time-rate of change in the prescribed trading rates we decompose the dynamics of the system to fast and slow components. We use the model to derive a variety of observations regarding the dynamics of price and investors’ wealth, and the dependence of these quantities on the prescribed trading rates. In particular, we show that strategies with constant trading rates, which represent the well-known constant-rebalanced portfolio (CRP) strategies, are optimal in the sense that they minimize investment risks. In contrast, we show that investors pursuing non-CRP strategies are at risk of loss of wealth, as a result of the slow system not being integrable in the sense that cyclic trading rates do not always result in periodic price variations. [ABSTRACT FROM AUTHOR]

Hepatitis C virus (HCV) infection is endemic in people who inject drugs (PWID), with prevalence estimates above 60% for PWID in the United States. Previous modeling studies suggest that direct acting antiviral (DAA) treatment can lower overall prevalence in this population, but treatment is often delayed until the onset of advanced liver disease (fibrosis stage 3 or later) due to cost. Lower cost interventions featuring syringe access (SA) and medically assisted treatment (MAT) have shown mixed results in lowering HCV rates below current levels. However. little is known about the potential cumulative effects of combining DAA and MAT treatment. While simulation experiments can reveal likely long-term effects, most prior simulations have been performed on closed populations of model agents—a scenario quite different from the open, mobile populations known to most health agencies. This paper uses data from the Centers for Disease Control’s National HIV Behavioral Surveillance project, IDU round 3, collected in New York City in 2012 to parameterize simulations of open populations. To test the effect of combining DAA treatment with SA/MAT participation, multiple, scaled implementations of the two intervention strategies were simulated. Our results show that, in an open population, SA/MAT by itself has only small effects on HCV prevalence, while DAA treatment by itself can lower both HCV and HCV-related advanced liver disease prevalence. More importantly, the simulation experiments suggest that combinations of the two strategies can, when implemented together and at sufficient levels, dramatically reduce HCV incidence. We conclude that adopting SA/MAT implementations alongside DAA interventions can play a critical role in reducing the long-term consequences of ongoing HCV infection. [ABSTRACT FROM AUTHOR]

The modelling of deceptions in game theory and decision theory has not been well studied, despite the increasing importance of this problem in social media, public discourse, and organisational management. This paper presents an improved formulation of the extant information-theoretic models of deceptions, a framework for incorporating these models of deception into game and decision theoretic models of deception, and applies these models and this framework in an agent based evolutionary simulation that models two very common deception types employed in “fake news” attacks. The simulation results for both deception types modelled show, as observed empirically in many social systems subjected to “fake news” attacks, that even a very small population of deceivers that transiently invades a much larger population of non-deceiving agents can strongly alter the equilibrium behaviour of the population in favour of agents playing an always defect strategy. The results also show that the ability of a population of deceivers to establish itself or remain present in a population is highly sensitive to the cost of the deception, as this cost reduces the fitness of deceiving agents when competing against non-deceiving agents. Diffusion behaviours observed for agents exploiting the deception producing false beliefs are very close to empirically observed behaviours in social media, when fitted to epidemiological models. We thus demonstrate, using the improved formulation of the information-theoretic models of deception, that agent based evolutionary simulations employing the Iterated Prisoner’s Dilemma can accurately capture the behaviours of a population subject to deception attacks introducing uncertainty and false perceptions, and show that information-theoretic models of deception have practical applications beyond trivial taxonomical analysis. [ABSTRACT FROM AUTHOR]

The recent availability of digital traces generated by cellphone calls has significantly increased the scientific understanding of human mobility. Until now, however, based on low time resolution measurements, previous works have ignored to study human mobility under various time scales due to sparse and irregular calls, particularly in the era of mobile Internet. In this paper, we introduced Mobile Flow Records, flow-level data access records of online activity of smartphone users, to explore human mobility. Mobile Flow Records collect high-resolution information of large populations. By exploiting this kind of data, we show the models and statistics of human mobility at a large-scale (3,542,235 individuals) and finer-granularity (7.5min). Next, we investigated statistical variations and biases of mobility models caused by different time scales (from 7.5min to 32h), and found that the time scale does influence the mobility model, which indicates a deep coupling of human mobility and time. We further show that mobility behaviors like transportation modes contribute to the diversity of human mobility, by exploring several novel and refined features (e.g., motion speed, duration, and trajectory distance). Particularly, we point out that 2-hour sampling adopted in previous works is insufficient to study detailed motion behaviors. Our work not only offers a macroscopic and microscopic view of spatial-temporal human mobility, but also applies previously unavailable features, both of which are beneficial to the studies on phenomena driven by human mobility. [ABSTRACT FROM AUTHOR]

Big data classification is very slow when using traditional machine learning classifiers, particularly when using a lazy and slow-by-nature classifier such as the k-nearest neighbors algorithm (KNN). This paper proposes a new approach which is based on sorting the feature vectors of training data in a binary search tree to accelerate big data classification using the KNN approach. This is done using two methods, both of which utilize two local points to sort the examples based on their similarity to these local points. The first method chooses the local points based on their similarity to the global extreme points, while the second method chooses the local points randomly. The results of various experiments conducted on different big datasets show reasonable accuracy rates compared to state-of-the-art methods and the KNN classifier itself. More importantly, they show the high classification speed of both methods. This strong trait can be used to further improve the accuracy of the proposed methods. [ABSTRACT FROM AUTHOR]

The exponential growth of mobile traffic means that operators must upgrade their mobile networks to provide higher capacity to final users. A promising alternative is to deploy heterogeneous networks (HetNets) that combine macro Base Stations (BSs) and SmallCells (SCs), although this increases the complexity and cost of the transport (SCs to Fiber Access Point–FAP). Most of the planning strategies outlined in the literature are aimed at reducing the number of SCs and ignore the impact that the transport segment might have on the total cost of network deployment. In this paper, heuristics are used for the joint planning of radio (i.e., SCs) and transport resources (i.e., point-to-point fiber links). These were compared and examined to determine the advantages and disadvantages of each approach, and in some cases, this led to a 50% reduction in total costs, while still creating a non-scalable network. [ABSTRACT FROM AUTHOR]

The objective of this study is to establish a framework for analyzing infrastructure dynamics affecting the long-term steady state, and hence resilience in civil infrastructure systems. To this end, a multi-agent simulation model was created to capture important phenomena affecting the dynamics of coupled human-infrastructure systems and model the long-term performance regimes of infrastructure. The proposed framework captures the following three factors that shape the dynamics of coupled human-infrastructure systems: (i) engineered physical infrastructure; (ii) human actors; and (iii) chronic and acute stressors. A complex system approach was adopted to examine the long-term resilience of infrastructure based on the understanding of performance regimes, as well as tipping points at which shifts in the performance regime of infrastructure occur under the impact of external stressors and/or change in internal dynamics. The application of the proposed framework is demonstrated in a case of urban water distribution infrastructure using the data from a numerical case study network. The developed multi-agent simulation model was then used in examining the system resilience over a 100-year horizon under stressors such as population change and funding constraints. The results identified the effects of internal dynamics and external stressors on the resilience landscape of infrastructure systems. Furthermore, the results also showed the capability of the framework in capturing and simulating the underlying mechanisms affecting human-infrastructure dynamics, as well as long-term regime shifts and tipping point behaviors. Therefore, the integrated framework proposed in this paper enables building complex system-based theories for a more advanced understanding of civil infrastructure resilience. [ABSTRACT FROM AUTHOR]

Quantum information processing made a tremendous and remarkable impact on number of classical mechanic’s problems. The impact does not only stop at classical mechanics but also the cyber security paradigm. Quantum information and cryptography are two classes of quantum information processing which use the idea of qubits instead of bits as in classical information security. The idea of fast computations with multiple complexity level is becoming more realistic in the age of quantum information due to quantum parallelism where a single quantum computer does allow to compute hundreds of classical computers with less efforts and more accuracy. The evolution of quantum information processing replaces a number of classical mechanic’s aspects in computational and cyber security sciences. Our aim here is to introduce concepts of applied quantum dynamics in cryptography, which leads to an evolution of quantum cryptography. Quantum cryptography is one of the most astonishing solicitations of quantum information theory. To measure the quantum state of any system is not possible without disturbing that system. The facts of quantum mechanics on traditional cryptosystems lead to a new protocol and achieving maximum remarkable security for systems. The scope of this paper is to design an innovative encryption scheme for digital data based on quantum spinning and rotation operators. [ABSTRACT FROM AUTHOR]

The integration of oilfield multidisciplinary ontology is increasingly important for the growth of the Semantic Web. However, current methods encounter performance bottlenecks either in storing data and searching for information when processing large amounts of data. To overcome these challenges, we propose a domain-ontology process based on the Neo4j graph database. In this paper, we focus on data storage and information retrieval of oilfield ontology. We have designed mapping rules from ontology files to regulate the Neo4j database, which can greatly reduce the required storage space. A two-tier index architecture, including object and triad indexing, is used to keep loading times low and match with different patterns for accurate retrieval. Therefore, we propose a retrieval method based on this architecture. Based on our evaluation, the retrieval method can save 13.04% of the storage space and improve retrieval efficiency by more than 30 times compared with the methods of relational databases. [ABSTRACT FROM AUTHOR]

It is usually assumed that each cooperator contributes equally to different public pools in spatial public goods game. However, it is more reasonable to invest differently according to individual investment preference. In this paper, an extended public goods game, in which cooperators contribute to the groups according to the investment preference, is developed. The investment preference of a cooperator is characterized by the fraction of the cooperator from his/her own memory about a group and the intensity of investment preference is represented by a tunable parameter α. The well-mixed population and the structured population are analyzed under this mechanism. It is shown that the investment preference can give rise to coordination. Moreover, the extensive numerical simulation results show that with the increasing of investment preference density or memory length, the proportion of cooperation can increase monotonously. This is because the investment preference could help cooperators resist the invasion from defectors. Compared with the basic version, the new mechanism is able to promote cooperation effectively. Our research may provide a valuable insight for further exploring the nature of cooperation in the real world. [ABSTRACT FROM AUTHOR]

We introduce a new agent-based model of opinion dynamics in which binary opinions of each agent can be measured and described regarding both pre- and post-influence at both of two levels, public and private, vis-à-vis the influence source. The model combines ideas introduced within the q-voter model with noise, proposed by physicists, with the descriptive, four-dimensional model of social response, formulated by social psychologists. We investigate two versions of the same model that differ only by the updating order: an opinion on the public level is updated before an opinion on the private level or vice versa. We show how the results on the macroscopic scale depend on this order. The main finding of this paper is that both models produce the same outcome if one looks only at such a macroscopic variable as the total number of the individuals with positive opinions. However, if also the level of internal harmony (viz., dissonance) is measured, then significant, qualitative differences are seen between these two versions of the model. All results were obtained simultaneously within Monte Carlo simulations and analytical calculations. We discuss the importance of our studies and findings from three points of view: the theory of phase transitions, agent-based modeling of social systems, and social psychology. [ABSTRACT FROM AUTHOR]

The process of inferring parameter values from experimental data can be a cumbersome task. In addition, the collection of experimental data can be time consuming and costly. This paper covers both these issues by addressing the following question: “Which experimental outputs should be measured to ensure that unique model parameters can be calculated?”. Stated formally, we examine the topic of minimal output sets that guarantee a model’s structural identifiability. To that end, we introduce an algorithm that guides a researcher as to which model outputs to measure. Our algorithm consists of an iterative structural identifiability analysis and can determine multiple minimal output sets of a model. This choice in different output sets offers researchers flexibility during experimental design. Our method can determine minimal output sets of large differential equation models within short computational times. [ABSTRACT FROM AUTHOR]

In this paper we present a family of models that allows us to estimate egos’ unobserved action dispositions from a joint behavioural outcome of a dyadic social interaction process of both egos’ and alters’ action dispositions. The method is put to test on a data set containing two different types of dyadic activities of high relevance for the spread of sexually transmitted infections (STI), condom use and anal sex. The data consists of individuals older than 15 years old who visited one of the nine youth clinics in the Vastra Gotaland region of Sweden between February 2010 and March 2011 for STI testing. This is hence a group of special interest for STI interventions. We cannot find any difference in condom disposition between women and men. Condoms are initially used more often in less risky types of relationships, especially if the partner ends up as a main partner. When studying the disposition towards anal sex we do however find a difference between men and women. Women are more against practising anal sex than men while the majority of men are neutral towards anal sex. [ABSTRACT FROM AUTHOR]

Participative branding is a process by which DMOs, locals and visitors contribute, through their activity in social media, to the definition of the emotional values associated to a destination. From the communicative point of view it is particularly important that DMOs and local citizens work together in the transmission of a set of coherent values that compose a personalised identity. This paper presents a novel methodology, based on semantic similarity measures, that permits to make an automated analysis of the emotional values transmitted by official tourist offices and by local citizens through social media. A study of 54,000 tweets from 9 main European tourist destinations highlights the lack of a strategy towards the communication of a distinctive brand and a strong gap between the official view transmitted by the DMOs of the destinations and the one communicated by their residents. [ABSTRACT FROM AUTHOR]

The accuracy and diversity of recommendation algorithms have always been the research hotspot of recommender systems. A good recommender system should not only have high accuracy and diversity, but also have adequate robustness against spammer attacks. However, the issue of recommendation robustness has received relatively little attention in the literature. In this paper, we systematically study the influences of different spammer behaviors on the recommendation results in various recommendation algorithms. We further propose an improved algorithm by incorporating the inner-similarity of user’s purchased items in the classic KNN approach. The new algorithm effectively enhances the robustness against spammer attacks and thus outperforms traditional algorithms in recommendation accuracy and diversity when spammers exist in the online commercial systems. [ABSTRACT FROM AUTHOR]

In this paper we describe how to efficiently record the entire genetic history of a population in forwards-time, individual-based population genetics simulations with arbitrary breeding models, population structure and demography. This approach dramatically reduces the computational burden of tracking individual genomes by allowing us to simulate only those loci that may affect reproduction (those having non-neutral variants). The genetic history of the population is recorded as a succinct tree sequence as introduced in the software package msprime, on which neutral mutations can be quickly placed afterwards. Recording the results of each breeding event requires storage that grows linearly with time, but there is a great deal of redundancy in this information. We solve this storage problem by providing an algorithm to quickly ‘simplify’ a tree sequence by removing this irrelevant history for a given set of genomes. By periodically simplifying the history with respect to the extant population, we show that the total storage space required is modest and overall large efficiency gains can be made over classical forward-time simulations. We implement a general-purpose framework for recording and simplifying genealogical data, which can be used to make simulations of any population model more efficient. We modify two popular forwards-time simulation frameworks to use this new approach and observe efficiency gains in large, whole-genome simulations of one to two orders of magnitude. In addition to speed, our method for recording pedigrees has several advantages: (1) All marginal genealogies of the simulated individuals are recorded, rather than just genotypes. (2) A population of N individuals with M polymorphic sites can be stored in O(N log N + M) space, making it feasible to store a simulation’s entire final generation as well as its history. (3) A simulation can easily be initialized with a more efficient coalescent simulation of deep history. The software for recording and processing tree sequences is named tskit. [ABSTRACT FROM AUTHOR]

Classical definitions of observability classify a system as either being observable or not. Observability has been recognized as an important feature to study complex networks, and as for dynamical systems the focus has been on determining conditions for a network to be observable. About twenty years ago continuous measures of observability for nonlinear dynamical systems started to be used. In this paper various aspects of observability that are established for dynamical systems will be investigated in the context of networks. In particular it will be discussed in which ways simple networks can be ranked in terms of observability using continuous measures of such a property. Also it is pointed out that the analysis of the network topology is typically not sufficient for observability purposes, since both the dynamics and the coupling of such nodes play a vital role. Some of the main ideas are illustrated by means of numerical simulations. [ABSTRACT FROM AUTHOR]

Tourist satisfaction has always been a crucial research issue in the tourism economy. This paper utilizes the Spatial Durbin Model (SDM) to analyze the impact of urban tourism satisfaction on urban macroeconomics from a macro perspective, using quarterly data on tourist satisfaction in 35 large and medium-sized cities along with major urban macroeconomic variables. This study is quite distinct from previous research that focused on constructing a tourist satisfaction index and analyzing the influence factors of tourism satisfaction from the perspective of the micro-level internal composition of tourism. The empirical results show: Firstly, in respect of the impact of urban tourists' satisfaction on the GDP income of cities, the SDM and the SDM with a lagged first-order dependent variable (SDM_dlag) show that the short-term and long-term indirect effects of log-tourist satisfaction are significantly positive, indicating that city satisfaction has a significant positive spatial spillover effect on GDP growth in other cities; Secondly, in respect of the influence of urban tourist satisfaction on the cost of urban life in the SDM, the long-term direct and indirect effects of logarithmic satisfaction are significantly positive, implying, in the long run, that tourist satisfaction has a positive intraregional spillover effect and spatial spillover effect on urban living costs; Finally, the SDM_dlag for the regression of urban tourist satisfaction on the cost of urban daily life shows that the short-run direct and indirect effects of city tourist satisfaction are significantly negative, indicating that tourist satisfaction has intra-regional and spatial spillover effects, and its rise will reduce the cost of living expenses in local and other cities in the short term. Overall, we have further elucidated the role of different levels of urban tourist satisfaction in city macroeconomics from the spatial dimension, thereby enriching the existing research on tourist satisfaction to some certain extent. [ABSTRACT FROM AUTHOR]

Due to recent advances in genetic manipulation, transgenic mosquitoes may be a viable alternative to reduce some diseases. Feasibility conditions are obtained by simulating and analyzing mathematical models that describe the behavior of wild and transgenic populations living in the same geographic area. In this paper, we present a reaction–diffusion model in which the reaction term is a nonlinear function that describes the interaction between wild and transgenic mosquitoes, considering the zygosity, and the diffusive term that represents a nonuniform spatial spreading characterized by a random diffusion parameter. The resulting nonlinear system of partial differential equations is numerically solved using the sequential operator splitting technique, combining the finite element method and Runge-Kutta method. This scheme is numerically implemented considering uncertainty in the diffusion parameters of the model. Several scenarios simulating spatial release strategies of transgenic mosquitoes are analyzed, demonstrating an intrinsic association between the transgene frequency in the total population and the strategy adopted. [ABSTRACT FROM AUTHOR]

In this paper, a new method is proposed for prediction of ship roll motion based on extreme learning machine (ELM). To improve the prediction accuracy and avoid over or under fitting, two techniques are adopted to select the appropriate structure of ELM. First, the inputs of the ELM are selected from the roll motion time series using Lipschitz quotient method. Second, the number of hidden layer nodes is determined via ℓ1 regularized technique. Finally, the ℓ1 regularized ELM is solved by least angle regression (LAR) algorithm. The effectiveness of the proposed method is demonstrated by ship roll motion prediction experiments based on the real measured ship roll motion time series. [ABSTRACT FROM AUTHOR]

Community structures are ubiquitous in various complex networks, implying that the networks commonly be composed of groups of nodes with more internal links and less external links. As an important topic in network theory, community detection is of importance for understanding the structure and function of the networks. Optimizing statistical measures for community structures is one of most popular strategies for community detection in complex networks. In the paper, by using a type of self-loop rescaling strategy, we introduced a set of global modularity functions and a set of local modularity functions for community detection in networks, which are optimized by a kind of the self-consistent method. We carefully compared and analyzed the behaviors of the modularity-based methods in community detection, and confirmed the superiority of the local modularity for detecting community structures on large-size and heterogeneous networks. The local modularity can more quickly eliminate the first-type limit of modularity, and can eliminate or alleviate the second-type limit of modularity in networks, because of the use of the local information in networks. Moreover, we tested the methods in real networks. Finally, we expect the research can provide useful insight into the problem of community detection in complex networks. [ABSTRACT FROM AUTHOR]

Wireless Body Area Network (WBAN) has become the emerging technology due to its ability to provide intelligent and cost-effective healthcare monitoring solution. The biological sensors used in WBAN are energy-constrained and required to be functional for a longer duration. Also, the sensed data should be communicated in reasonable time. Therefore, network lifetime and delay have become the primary concerns in the design of WBAN. In this paper, Receive Diversity based Transmission Data Rate Optimization (RDTDRO) scheme is proposed to improve the network lifetime and delay efficiency of Multi level-Quadrature Amplitude Modulation (M-QAM) based WBAN. In the proposed RDTDRO scheme, minimum energy consumption is ensured by optimizing the transmission data rate with respect to a given transmission distance and number of receive antennas while satisfying the Bit Error Rate (BER) requirements. The performance of proposed RDTDRO is analyzed in terms of network lifetime and delay difference and is compared with conventional Baseline and Rate optimized schemes. The results show that at a transmission distance of 0.3 m, the proposed RDTDRO scheme with a receive diversity order of 4 achieves 1.30 times and 1.27 times improvement in network lifetime over conventional Baseline and Rate optimized schemes respectively. From the results, it is also evident that at a transmission distance of 0.3 m, the proposed RDTDRO scheme with a receive diversity order of 4 is delay efficient as it achieves delay difference of 0.75 μs and 0.29 μs over conventional Baseline and Rate optimized schemes respectively. [ABSTRACT FROM AUTHOR]

Background: Regular expression matching (REM) is widely employed as the major tool for deep packet inspection (DPI) applications. For automatic processing, the regular expression patterns need to be converted to a deterministic finite automata (DFA). However, with the ever-increasing scale and complexity of pattern sets, state explosion problem has brought a great challenge to the DFA based regular expression matching. Rule grouping is a direct method to solve the state explosion problem. The original rule set is divided into multiple disjoint groups, and each group is compiled to a separate DFA, thus to significantly restrain the severe state explosion problem when compiling all the rules to a single DFA. Objective: For practical implementation, the total number of DFA states should be as few as possible, thus the data structures of these DFAs can be deployed on fast on-chip memories for rapid access. In addition, to support fast pattern update in some applications, the time cost for grouping should be as small as possible. In this study, we aimed to propose an efficient grouping method, which generates as few states as possible with as little time overhead as possible. Methods: When compiling multiple patterns into a single DFA, the number of DFA states is usually greater than the total number of states when compiling each pattern to a separate DFA. This is mainly caused by the semantic overlaps among different rules. By quantifying the interaction values for each pair of rules, the rule grouping problem can be reduced to the maximum k-cut graph partitioning problem. Then, we propose a heuristic algorithm called the one-step greedy (OSG) algorithm to solve this NP-hard problem. What’s more, a subroutine named the heuristic initialization (HI) algorithm is devised to further optimize the grouping algorithms. Results: We employed three practical rule sets for the experimental evaluation. Results show that the OSG algorithm outperforms the state-of-the-art grouping solutions regarding both the total number of DFA states and time cost for grouping. The HI subroutine also demonstrates its significant optimization effect on the grouping algorithms. Conclusions: The DFA state explosion problem has became the most challenging issue in the regular expression matching applications. Rule grouping is a practical direction by dividing the original rule sets into multiple disjoint groups. In this paper, we investigate the current grouping solutions, and propose a compact and efficient grouping algorithm. Experiments conducted on practical rule sets demonstrate the superiority of our proposal. [ABSTRACT FROM AUTHOR]

This paper examines social class-based differences in influence in online review contexts. We explore four mechanisms for how a review writer’s social class may affect readers’ evaluations of the organization. First, we argue that, via a “contagion” process, organizations reviewed by higher-class individuals will be evaluated more positively than organizations reviewed by lower-class individuals. Second, we expect that higher-class reviewers will be seen as more knowledgeable; thus, their opinions will be more influential in shaping others’ opinions. Third, we expect that reviewers will be seen more influential when they review organizations that match their social class. Fourth, we expect people to be more influenced by those who share their own class background. A large-scale observational study of reviews (N = 1,234,665) from finds support for the contagion, the organization-reviewer social class matching, and the reviewer-participant social matching hypotheses, but disconfirms the hypothesis that higher-class reviewers are always treated as having more expertise. Two experimental studies (N = 354 and N = 638) demonstrate that reviewer class plays a causal role in both a contagion process and in an assumption of higher-class knowledge process, but do not provide evidence for the reviewer-participant social matching hypothesis. [ABSTRACT FROM AUTHOR]

This paper presents a lightweight synthesis algorithm, named adaptive region segmentation based piecewise linear (ARSPL) algorithm, for reconstructing standard 12-lead electrocardiogram (ECG) signals from a 3-lead subset (I, II and V2). Such a lightweight algorithm is particularly suitable for healthcare mobile devices with limited resources for computing, communication and data storage. After detection of R-peaks, the ECGs are segmented by cardiac cycles. Each cycle is further divided into four regions according to different cardiac electrical activity stages. A personalized linear regression algorithm is then applied to these regions respectively for improved ECG synthesis. The proposed ARSPL method has been tested on 39 subjects randomly selected from the PTB diagnostic ECG database and achieved accurate synthesis of remaining leads with an average correlation coefficient of 0.947, an average root-mean-square error of 55.4μV, and an average runtime performance of 114ms. Overall, these results are significantly better than those of the common linear regression method, the back propagation (BP) neural network and the BP optimized using the genetic algorithm. We have also used the reconstructed ECG signals to evaluate the denivelation of ST segment, which is a potential symptom of intrinsic myocardial disease. After ARSPL, only 10.71% of the synthesized ECG cycles are with a ST-level synthesis error larger than 0.1mV, which is also better than those of the three above-mentioned methods. [ABSTRACT FROM AUTHOR]

B cells develop high affinity receptors during the course of affinity maturation, a cyclic process of mutation and selection. At the end of affinity maturation, a number of cells sharing the same ancestor (i.e. in the same “clonal family”) are released from the germinal center; their amino acid frequency profile reflects the allowed and disallowed substitutions at each position. These clonal-family-specific frequency profiles, called “substitution profiles”, are useful for studying the course of affinity maturation as well as for antibody engineering purposes. However, most often only a single sequence is recovered from each clonal family in a sequencing experiment, making it impossible to construct a clonal-family-specific substitution profile. Given the public release of many high-quality large B cell receptor datasets, one may ask whether it is possible to use such data in a prediction model for clonal-family-specific substitution profiles. In this paper, we present the method “Substitution Profiles Using Related Families” (SPURF), a penalized tensor regression framework that integrates information from a rich assemblage of datasets to predict the clonal-family-specific substitution profile for any single input sequence. Using this framework, we show that substitution profiles from similar clonal families can be leveraged together with simulated substitution profiles and germline gene sequence information to improve prediction. We fit this model on a large public dataset and validate the robustness of our approach on two external datasets. Furthermore, we provide a command-line tool in an open-source software package () implementing these ideas and providing easy prediction using our pre-fit models. [ABSTRACT FROM AUTHOR]

Morphological classification of living things has challenged science for several centuries and has led to a wide range of objective morphometric approaches in data gathering and analysis. In this paper we explore those methods using apple cultivars, a model biological system in which discrete groups are pre-defined but in which there is a high level of overall morphological similarity. The effectiveness of morphometric techniques in discovering the groups is evaluated using statistical learning tools. No one technique proved optimal in classification on every occasion, linear morphometric techniques slightly out-performing geometric (72.6% accuracy on test set versus 66.7%). The combined use of these techniques with post-hoc knowledge of their individual successes with particular cultivars achieves a notably higher classification accuracy (77.8%). From this we conclude that even with pre-determined discrete categories, a range of approaches is needed where those categories are intrinsically similar to each other, and we raise the question of whether in studies where potentially continuous natural variation is being categorised the level of match between categories is routinely set too high. [ABSTRACT FROM AUTHOR]

Wireless Mesh Networks (WMNs) integrate the advantages of WLANs and mobile Ad Hoc networks, which have become the key techniques of next-generation wireless networks in the context of emergency recovery. Wireless Mesh Networks (WMNs) are multi-hop wireless networks with instant deployment, self-healing, self-organization and self-configuration features. These capabilities make WMNs a promising technology for incident and emergency communication. An incident area network (IAN) needs a reliable and lively routing path during disaster recovery and emergency response operations when infrastructure-based communications and power resources have been destroyed and no routes are available. Power aware routing plays a significant role in WMNs, in order to provide continuous efficient emergency services. The existing power aware routing algorithms used in wireless networks cannot fully fit the characteristics of WMNs, to be used for emergency recovery. This paper proposes a power aware routing algorithm (PARA) for WMNs, which selects optimal paths to send packets, mainly based on the power level of next node along the path. This algorithm was implemented and tested in a proven simulator. The analytic results show that the proposed power node-type aware routing algorithm metric can clearly improve the network performance by reducing the network overheads and maintaining a high delivery ratio with low latency. [ABSTRACT FROM AUTHOR]

To predict what products customers will buy in next transaction is an important task. Existing work in next-basket prediction can be summarized into two paradigms. One is the item-centric paradigm, where sequential patterns are mined from customers’ transactional data and leveraged for prediction. However, these approaches usually suffer from the data sparseness problem. The other is the user-centric paradigm, where collaborative filtering techniques have been applied on customers’ historical data. However, these methods ignore the sequential behaviors of customers which is often crucial for next-basket prediction. In this paper, we introduce a hybrid method, namely the Co-Factorization model over Sequential and Historical purchase data (CFSH for short) for next-basket recommendation. Compared with existing methods, our approach conveys the following merits: 1) By mining global sequential patterns, we can avoid the sparseness problem in traditional item-centric methods; 2) By factorizing product-product and customer-product matrices simultaneously, we can fully exploit both sequential and historical behaviors to learn customer and product representations better; 3) By using a hybrid recommendation method, we can achieve better performance in next-basket prediction. Experimental results on three real-world purchase datasets demonstrated the effectiveness of our approach as compared with the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

In recent years, finding the cause of pathogenesis is expected by observing the cell images. In this paper, we propose a cell particle detection method in cell images. However, there are mainly two kinds of problems in particle detection in cell image. The first is the different properties between cell images and standard images used in computer vision researches. Edges of cell particles are ambiguous, and overlaps between cell particles are often occurred in dense regions. It is difficult to detect cell particles by simple detection method using a binary classifier. The second is the ground truth made by cell biologists. The number of training samples for training a classifier is limited, and incorrect samples are included by the subjectivity of observers. From the background, we propose a cell particle detection method to address those problems. In our proposed method, we predict the center of a cell particle from the peripheral regions by convolutional neural network, and the prediction results are voted. By using the obvious peripheral edges, we can robustly detect overlapped cell particles because all edges of overlapping cell particles are not ambiguous. In addition, voting from peripheral views enables reliable detection. Moreover, our method is useful in practical applications because we can prepare many training samples from a cell particle. In experiments, we evaluate our detection methods on two kinds of cell detection datasets. One is challenging dataset for synthetic cells, and our method achieved the state-of-the-art performance. The other is real dataset of lipid droplets, and our method outperformed the conventional detector using CNN with binary outputs for particles and non-particles classification. [ABSTRACT FROM AUTHOR]

The paper investigates the effect of preferential gathering sites on urban insurgency in an agent-based model (ABM). The ABM model was proposed in earlier work and has been validated using FBI data. There is a nonlinear tradeoff between the local density of citizens due to the number of preferential gathering sites and the ability of law enforcement officers (LEOs) to adequately patrol that leads to a non-monotonic behavior in the number of large scale outburst of insurgency with respect to the number of gathering sites. The inclusion of a moderate number of sites decreases the number of large-scale outbursts. Having no gathering sites or a large number of gathering sites has a dilutive effect on the number of large-scale outbursts. Thus, this non-monotonicity indicates that a small number of organized units produces a larger insurgency effect than a larger number of distributed units. It is also shown, using Koopman mode analysis, that the spatial morphology of agents due to the gathering sites gives rise to temporal organization of the model dynamics; there is a prominent quasi-periodic component in the number of active and intimidated citizens and in the spatial distribution of the LEOs. [ABSTRACT FROM AUTHOR]

This paper describes an approach for improving the accuracy of memory-based collaborative filtering, based on the technique for order of preference by similarity to ideal solution (TOPSIS) method. Recommender systems are used to filter the huge amount of data available online based on user-defined preferences. Collaborative filtering (CF) is a commonly used recommendation approach that generates recommendations based on correlations among user preferences. Although several enhancements have increased the accuracy of memory-based CF through the development of improved similarity measures for finding successful neighbors, there has been less investigation into prediction score methods, in which rating/preference scores are assigned to items that have not yet been selected by a user. A TOPSIS solution for evaluating multiple alternatives based on more than one criterion is proposed as an alternative to prediction score methods for evaluating and ranking items based on the results from similar users. The recommendation accuracy of the proposed TOPSIS technique is evaluated by applying it to various common CF baseline methods, which are then used to analyze the MovieLens 100K and 1M benchmark datasets. The results show that CF based on the TOPSIS method is more accurate than baseline CF methods across a number of common evaluation metrics. [ABSTRACT FROM AUTHOR]

The global trade system can be viewed as a dynamic ecosystem in which exporters struggle for resources: the markets in which they export. We can think that the aim of an exporter is to gain the entirety of a market share (say, car imports from the United States). This is similar to the objective of an organism in its attempt to monopolize a given subset of resources in an ecosystem. In this paper, we adopt a multilayer network approach to describe this struggle. We use longitudinal, multiplex data on trade relations, spanning several decades. We connect two countries with a directed link if the source country’s appearance in a market correlates with the target country’s disappearing, where a market is defined as a country-product combination in a given decade. Each market is a layer in the network. We show that, by analyzing the countries’ network roles in each layer, we are able to classify them as out-competing, transitioning or displaced. This classification is a meaningful one: when testing the future export patterns of these countries, we show that out-competing countries have distinctly stronger growth rates than the other two classes. [ABSTRACT FROM AUTHOR]

The Colless index is one of the most popular and natural balance indices for bifurcating phylogenetic trees, but it makes no sense for multifurcating trees. In this paper we propose a family of Colless-like balance indices that generalize the Colless index to multifurcating phylogenetic trees. Each is determined by the choice of a dissimilarity D and a weight function . A balance index is sound when the most balanced phylogenetic trees according to it are exactly the fully symmetric ones. Unfortunately, not every Colless-like balance index is sound in this sense. We prove then that taking f(n) = ln(n + e) or f(n) = en as weight functions, the resulting index is sound for every dissimilarity D. Next, for each one of these two functions f and for three popular dissimilarities D (the variance, the standard deviation, and the mean deviation from the median), we find the most unbalanced phylogenetic trees according to with any given number n of leaves. The results show that the growth pace of the function f influences the notion of “balance” measured by the indices it defines. Finally, we introduce our R package “CollessLike,” which, among other functionalities, allows the computation of Colless-like indices of trees and their comparison to their distribution under Chen-Ford-Winkel’s α-γ-model for multifurcating phylogenetic trees. As an application, we show that the trees in TreeBASE do not seem to follow either the uniform model for multifurcating trees or the α-γ-model, for any values of α and γ. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new model of memristive multidirectional associative memory neural networks, which concludes the time-varying delays in leakage terms via sampled-data control. We use the input delay method to turn the sampling system into a continuous time-delaying system. Then we analyze the exponential stability and asymptotic stability of the equilibrium points for this model. By constructing a suitable Lyapunov function, using the Lyapunov stability theorem and some inequality techniques, some sufficient criteria for ensuring the stability of equilibrium points are obtained. Finally, numerical examples are given to demonstrate the effectiveness of our results. [ABSTRACT FROM AUTHOR]

Minimization functionals related to Euler’s elastica energy has a broad range of applications in computer vision and image processing. This paper proposes a novel Euler’s elastica and curvature-based variational model for image restoration corrupted with multiplicative noise. It combines Euler’s elastica curvature with a Weberized total variation (TV) regularization and gets a novel Euler’s elastica energy and TV-based minimization functional. The combined approach in this variational model can preserve edges while reducing the blocky effect in smooth regions. The implicit gradient descent scheme is applied to efficiently finding the minimizer of the proposed functional. Experimental results demonstrate the effectiveness of the proposed model in visual improvement, as well as an increase in the peak signal-to-noise ratio, compared to the PDE-based methods. [ABSTRACT FROM AUTHOR]

Integrated Information Theory (IIT) has become nowadays the most sensible general theory of consciousness. In addition to very important statements, it opens the door for an abstract (mathematical) formulation of the theory. Given a mechanism in a particular state, IIT identifies a conscious experience with a conceptual structure, an informational object which exists, is composed of identified parts, is informative, integrated and maximally irreducible. This paper introduces a space-time continuous version of the concept of integrated information. To this aim, a graph and a dynamical systems treatment is used to define, for a given mechanism in a state for which a dynamics is settled, an Informational Structure, which is associated to the global attractor at each time of the system. By definition, the informational structure determines all the past and future behavior of the system, possesses an informational nature and, moreover, enriches all the points of the phase space with cause-effect power by means of its associated Informational Field. A detailed description of its inner structure by invariants and connections between them allows to associate a transition probability matrix to each informational structure and to develop a measure for the level of integrated information of the system. [ABSTRACT FROM AUTHOR]

In palynology, the visual classification of pollen grains from different species is a hard task which is usually tackled by human operators using microscopes. Its complete automatization would save a high quantity of resources and provide valuable improvements especially for allergy-related information systems, but also for other application fields as paleoclimate reconstruction, quality control of honey based products, collection of evidences in criminal investigations or fabric dating and tracking. This paper presents three state-of-the-art deep learning classification methods applied to the recently published POLEN23E image dataset. The three methods make use of convolutional neural networks: the first one is strictly based on the idea of transfer learning, the second one is based on feature extraction and the third one represents a hybrid approach, combining transfer learning and feature extraction. The results from the three methods are indeed very good, reaching over 97% correct classification rates in images not previously seen by the models, where other authors reported around 70. [ABSTRACT FROM AUTHOR]

This paper proposes a novel robust control method for the control of a 7-DOF exoskeleton robot. The external disturbances and unknown dynamics in the form of friction forces, different upper-limb’s mass, backlash, and input saturation make robot unstable, which prevents the robot from correctly following the defined path. A new fractional sliding mode controller (NFSMC) is designed, which is robust against unknown dynamic and external disturbances. Fractional PID controller (FPID) has high trajectory tracking, but it is not robust against external disturbances. Therefore, by combining NFSMC and FPID controllers, a new compound fractional PID sliding mode controller (NCFPIDSMC) is proposed, which benefits high trajectory tracking of FPID and robustness of NFSMC. The stability of the proposed control method is verified by Lyapunov theory. A random noise is applied in order to confirm the robustness of the proposed control method. [ABSTRACT FROM AUTHOR]

A growing framework of legal and ethical requirements limit scientific and commercial evaluation of personal data. Typically, pseudonymization, encryption, or methods of distributed computing try to protect individual privacy. However, computational infrastructures still depend on human system administrators. This introduces severe security risks and has strong impact on privacy: system administrators have unlimited access to the computers that they manage including encryption keys and pseudonymization-tables. Distributed computing and data obfuscation technologies reduce but do not eliminate the risk of privacy leakage by administrators. They produce higher implementation effort and possible data quality degradation. This paper proposes the Trusted Server as an alternative approach that provides a sealed and inaccessible computational environment in a cryptographically strict sense. During operation or by direct physical access to storage media, data stored and processed inside the Trusted Server can by no means be read, manipulated or leaked, other than by brute-force. Thus, secure and privacy-compliant data processing or evaluation of plain person-related data becomes possible even from multiple sources, which want their data kept mutually secret. [ABSTRACT FROM AUTHOR]

Tie strength and tags have been separately suggested as possible attributes for photo access controls in Social Network Services. However, an evaluation is missing about the benefits/drawbacks of adding one or both of these attributes to the ones already used in access controls for Social Network Services (groups and individuals). In this paper, we describe an experiment with 48 participants using access controls that include tie strength and tags (separately and simultaneously) together with attributes for groups and individuals. We analyze the results using several quantitative and qualitative metrics. We find that users consider these two new attributes useful in defining their sharing policies, and they prefer to employ access controls that consider tags and tie strength jointly. Specifically, users believe that tie strength improves policy understandability and that tags help them define sharing policies faster. However, we also observe that when users employ these two attributes they tend to make more mistakes in terms of the resulting sharing policy. We hypothesize that this could be caused by the lack of experience using tie strength and tags in access controls. [ABSTRACT FROM AUTHOR]

The research about unmanned aerial vehicle (UAV) swarm has developed rapidly in recent years, especially the UAV swarm with sensors which is becoming common means of achieving situational awareness. Due to inadequate researches of the UAV swarm with complex control structure currently, we propose a patrolling task planning algorithm for the UAV swarm with double-layer centralized control structure under the uncertain and dynamic environment. The main objective of the UAV swarm is to collect environment information as much as possible. To summarized, the primary contributions of this paper are as follows. We first define the patrolling problem. After that, the patrolling problem is modeled as the Partially Observable Markov Decision Process (POMDP) problem. Building upon this, we put forward a myopic and scalable online task planning algorithm. The algorithm contains online heuristic function, sequential allocation method, and the mechanism of bottom-up information flow and top-down command flow, reducing the computation complexity effectively. Moreover, as the number of control layers increases, this algorithm guarantees the performance without increasing the computation complexity for the swarm leader. Finally, we empirically evaluate our algorithm in the specific scenarios. [ABSTRACT FROM AUTHOR]

This paper investigates suitability of supervised machine learning classification methods for classification of biomes using pollen datasets. We assign modern pollen samples from Africa and Arabia to five biome classes using a previously published African pollen dataset and a global ecosystem classification scheme. To test the applicability of traditional and machine-learning based classification models for the task of biome prediction from high dimensional modern pollen data, we train a total of eight classification models, including Linear Discriminant Analysis, Logistic Regression, Naïve Bayes, K-Nearest Neighbors, Classification Decision Tree, Random Forest, Neural Network, and Support Vector Machine. The ability of each model to predict biomes from pollen data is statistically tested on an independent test set. The Random Forest classifier outperforms other models in its ability correctly classify biomes given pollen data. Out of the eight models, the Random Forest classifier scores highest on all of the metrics used for model evaluations and is able to predict four out of five biome classes to high degree of accuracy, including arid, montane, tropical and subtropical closed and open systems, e.g. forests and savanna/grassland. The model has the potential for accurate reconstructions of past biomes and awaits application to fossil pollen sequences. The Random Forest model may be used to investigate vegetation changes on both long and short time scales, e.g. during glacial and interglacial cycles, or more recent and abrupt climatic anomalies like the African Humid Period. Such applications may contribute to a better understanding of past shifts in vegetation cover and ultimately provide valuable information on drivers of climate change. [ABSTRACT FROM AUTHOR]