Search

Information carried by an image can be distorted due to different image processing steps introduced by different electronic means of storage and communication. Therefore, development of algorithms which can automatically assess a quality of the image in a way that is consistent with human evaluation is important. In this paper, an approach to image quality assessment (IQA) is proposed in which the quality of a given image is evaluated jointly by several IQA approaches. At first, in order to obtain such joint models, an optimisation problem of IQA measures aggregation is defined, where a weighted sum of their outputs, i.e., objective scores, is used as the aggregation operator. Then, the weight of each measure is considered as a decision variable in a problem of minimisation of root mean square error between obtained objective scores and subjective scores. Subjective scores reflect ground-truth and involve evaluation of images by human observers. The optimisation problem is solved using a genetic algorithm, which also selects suitable measures used in aggregation. Obtained multimeasures are evaluated on four largest widely used image benchmarks and compared against state-of-the-art full-reference IQA approaches. Results of comparison reveal that the proposed approach outperforms other competing measures. [ABSTRACT FROM AUTHOR]

Privacy-preserving profile matching, a challenging task in mobile social networks, is getting more attention in recent years. In this paper, we propose a novel scheme that is based on ciphertext-policy attribute-based encryption to tackle this problem. In our scheme, a user can submit a preference-profile and search for users with matching-profile in decentralized mobile social networks. In this process, no participant’s profile and the submitted preference-profile is exposed. Meanwhile, a secure communication channel can be established between the pair of successfully matched users. In contrast to existing related schemes which are mainly based on the secure multi-party computation, our scheme can provide verifiability (both the initiator and any unmatched user cannot cheat each other to pretend to be matched), and requires few interactions among users. We provide thorough security analysis and performance evaluation on our scheme, and show its advantages in terms of security, efficiency and usability over state-of-the-art schemes. [ABSTRACT FROM AUTHOR]

Privacy-aware intersection set computation (PISC) can be modeled as secure multi-party computation. The basic idea is to compute the intersection of input sets without leaking privacy. Furthermore, PISC should be sufficiently flexible to recommend approximate intersection items. In this paper, we reveal two previously unpublished attacks against PISC, which can be used to reveal and link one input set to another input set, resulting in privacy leakage. We coin these as Set Linkage Attack and Set Reveal Attack. We then present a lightweight and flexible PISC scheme (LiPISC) and prove its security (including against Set Linkage Attack and Set Reveal Attack). [ABSTRACT FROM AUTHOR]

The identification of a subset of genes having the ability to capture the necessary information to distinguish classes of patients is crucial in bioinformatics applications. Ensemble and bagging methods have been shown to work effectively in the process of gene selection and classification. Testament to that is random forest which combines random decision trees with bagging to improve overall feature selection and classification accuracy. Surprisingly, the adoption of these methods in support vector machines has only recently received attention but mostly on classification not gene selection. This paper introduces an ensemble SVM-Recursive Feature Elimination (ESVM-RFE) for gene selection that follows the concepts of ensemble and bagging used in random forest but adopts the backward elimination strategy which is the rationale of RFE algorithm. The rationale behind this is, building ensemble SVM models using randomly drawn bootstrap samples from the training set, will produce different feature rankings which will be subsequently aggregated as one feature ranking. As a result, the decision for elimination of features is based upon the ranking of multiple SVM models instead of choosing one particular model. Moreover, this approach will address the problem of imbalanced datasets by constructing a nearly balanced bootstrap sample. Our experiments show that ESVM-RFE for gene selection substantially increased the classification performance on five microarray datasets compared to state-of-the-art methods. Experiments on the childhood leukaemia dataset show that an average 9% better accuracy is achieved by ESVM-RFE over SVM-RFE, and 5% over random forest based approach. The selected genes by the ESVM-RFE algorithm were further explored with Singular Value Decomposition (SVD) which reveals significant clusters with the selected data. [ABSTRACT FROM AUTHOR]

Decreasing the route rediscovery time process in reactive routing protocols is challenging in mobile ad hoc networks. Links between nodes are continuously established and broken because of the characteristics of the network. Finding multiple routes to increase the reliability is also important but requires a fast update, especially in high traffic load and high mobility where paths can be broken as well. The sender node keeps re-establishing path discovery to find new paths, which makes for long time delay. In this paper we propose an improved multipath routing protocol, called Receiver-based ad hoc on demand multipath routing protocol (RB-AOMDV), which takes advantage of the reliability of the state of the art ad hoc on demand multipath distance vector (AOMDV) protocol with less re-established discovery time. The receiver node assumes the role of discovering paths when finding data packets that have not been received after a period of time. Simulation results show the delay and delivery ratio performances are improved compared with AOMDV. [ABSTRACT FROM AUTHOR]

Intelligent Transportation Systems rely on understanding, predicting and affecting the interactions between vehicles. The goal of this paper is to choose a small subset from the larger set so that the resulting regression model is simple, yet have good predictive ability for Vehicle agent speed relative to Vehicle intruder. The method of ANFIS (adaptive neuro fuzzy inference system) was applied to the data resulting from these measurements. The ANFIS process for variable selection was implemented in order to detect the predominant variables affecting the prediction of agent speed relative to intruder. This process includes several ways to discover a subset of the total set of recorded parameters, showing good predictive capability. The ANFIS network was used to perform a variable search. Then, it was used to determine how 9 parameters (Intruder Front sensors active (boolean), Intruder Rear sensors active (boolean), Agent Front sensors active (boolean), Agent Rear sensors active (boolean), RSSI signal intensity/strength (integer), Elapsed time (in seconds), Distance between Agent and Intruder (m), Angle of Agent relative to Intruder (angle between vehicles °), Altitude difference between Agent and Intruder (m)) influence prediction of agent speed relative to intruder. The results indicated that distance between Vehicle agent and Vehicle intruder (m) and angle of Vehicle agent relative to Vehicle Intruder (angle between vehicles °) is the most influential parameters to Vehicle agent speed relative to Vehicle intruder. [ABSTRACT FROM AUTHOR]

In recent years social and news media have increasingly been used to explain patterns in disease activity and progression. Social media data, principally from the Twitter network, has been shown to correlate well with official disease case counts. This fact has been exploited to provide advance warning of outbreak detection, forecasting of disease levels and the ability to predict the likelihood of individuals developing symptoms. In this paper we introduce DEFENDER, a software system that integrates data from social and news media and incorporates algorithms for outbreak detection, situational awareness and forecasting. As part of this system we have developed a technique for creating a location network for any country or region based purely on Twitter data. We also present a disease nowcasting (forecasting the current but still unknown level) approach which leverages counts from multiple symptoms, which was found to improve the nowcasting accuracy by 37 percent over a model that used only previous case data. Finally we attempt to forecast future levels of symptom activity based on observed user movement on Twitter, finding a moderate gain of 5 percent over a time series forecasting model. [ABSTRACT FROM AUTHOR]

Due to the ever-growing popularity mobile devices of various kinds have received worldwide, the demands on large-scale wireless network infrastructure development and enhancement have been rapidly swelling in recent years. A mobile device holder can get online at a wireless network access point, which covers a limited area. When the client leaves the access point, there will be a temporary disconnection until he/she enters the coverage of another access point. Even when the coverages of two neighboring access points overlap, there is still work to do to make the wireless connection smoothly continue. The action of one wireless network access point passing a client to another access point is referred to as the handover. During handover, for security concerns, the client and the new access point should perform mutual authentication before any Internet access service is practically gained/provided. If the handover protocol is inefficient, in some cases discontinued Internet service will happen. In 2013, Li et al. proposed a fast handover authentication mechanism for wireless mesh network (WMN) based on tickets. Unfortunately, Li et al.’s work came with some weaknesses. For one thing, some sensitive information such as the time and date of expiration is sent in plaintext, which increases security risks. For another, Li et al.’s protocol includes the use of high-quality tamper-proof devices (TPDs), and this unreasonably high equipment requirement limits its applicability. In this paper, we shall propose a new efficient handover authentication mechanism. The new mechanism offers a higher level of security on a more scalable ground with the client’s privacy better preserved. The results of our performance analysis suggest that our new mechanism is superior to some similar mechanisms in terms of authentication delay. [ABSTRACT FROM AUTHOR]

Biometric based authentication protocols for multi-server architectures have gained momentum in recent times due to advancements in wireless technologies and associated constraints. Lu et al. recently proposed a robust biometric based authentication with key agreement protocol for a multi-server environment using smart cards. They claimed that their protocol is efficient and resistant to prominent security attacks. The careful investigation of this paper proves that Lu et al.’s protocol does not provide user anonymity, perfect forward secrecy and is susceptible to server and user impersonation attacks, man-in-middle attacks and clock synchronization problems. In addition, this paper proposes an enhanced biometric based authentication with key-agreement protocol for multi-server architecture based on elliptic curve cryptography using smartcards. We proved that the proposed protocol achieves mutual authentication using Burrows-Abadi-Needham (BAN) logic. The formal security of the proposed protocol is verified using the AVISPA (Automated Validation of Internet Security Protocols and Applications) tool to show that our protocol can withstand active and passive attacks. The formal and informal security analyses and performance analysis demonstrates that the proposed protocol is robust and efficient compared to Lu et al.’s protocol and existing similar protocols. [ABSTRACT FROM AUTHOR]

Swarming behavior is common in biology, from cell colonies to insect swarms and bird flocks. However, the conditions leading to the emergence of such behavior are still subject to research. Since Reynolds’ boids, many artificial models have reproduced swarming behavior, focusing on details ranging from obstacle avoidance to the introduction of fixed leaders. This paper presents a model of evolved artificial agents, able to develop swarming using only their ability to listen to each other’s signals. The model simulates a population of agents looking for a vital resource they cannot directly detect, in a 3D environment. Instead of a centralized algorithm, each agent is controlled by an artificial neural network, whose weights are encoded in a genotype and adapted by an original asynchronous genetic algorithm. The results demonstrate that agents progressively evolve the ability to use the information exchanged between each other via signaling to establish temporary leader-follower relations. These relations allow agents to form swarming patterns, emerging as a transient behavior that improves the agents’ ability to forage for the resource. Once they have acquired the ability to swarm, the individuals are able to outperform the non-swarmers at finding the resource. The population hence reaches a neutral evolutionary space which leads to a genetic drift of the genotypes. This reductionist approach to signal-based swarming not only contributes to shed light on the minimal conditions for the evolution of a swarming behavior, but also more generally it exemplifies the effect communication can have on optimal search patterns in collective groups of individuals. [ABSTRACT FROM AUTHOR]

This paper develops an agent-based computational model of violent political revolutions in which a subjugated population of citizens and an armed revolutionary organisation attempt to overthrow a central authority and its loyal forces. The model replicates several patterns of rebellion consistent with major historical revolutions, and provides an explanation for the multiplicity of outcomes that can arise from an uprising. The relevance of the heterogeneity of scenarios predicted by the model can be understood by considering the recent experience of the Arab Spring involving several rebellions that arose in an apparently similar way, but resulted in completely different political outcomes: the successful revolution in Tunisia, the failed protests in Saudi Arabia and Bahrain, and civil war in Syria and Libya. [ABSTRACT FROM AUTHOR]

Constrained ordination methods aims at finding an environmental gradient along which the species abundances are maximally separated. The species response functions, which describe the expected abundance as a function of the environmental score, are according to the ecological fundamental niche theory only meaningful if they are bell-shaped. Many classical model-based ordination methods, however, use quadratic regression models without imposing the bell-shape and thus allowing for meaningless U-shaped response functions. The analysis output (e.g. a biplot) may therefore be potentially misleading and the conclusions are prone to errors. In this paper we present a log-likelihood ratio criterion with a penalisation term to enforce more bell-shaped response shapes. We report the results of a simulation study and apply our method to metagenomics data from microbial ecology. [ABSTRACT FROM AUTHOR]

A number of circular regression models have been proposed in the literature. In recent years, there is a strong interest shown on the subject of outlier detection in circular regression. An outlier detection procedure can be developed by defining a new statistic in terms of the circular residuals. In this paper, we propose a new measure which transforms the circular residuals into linear measures using a trigonometric function. We then employ the row deletion approach to identify observations that affect the measure the most, a candidate of outlier. The corresponding cut-off points and the performance of the detection procedure when applied on Down and Mardia’s model are studied via simulations. For illustration, we apply the procedure on circadian data. [ABSTRACT FROM AUTHOR]

The spiking neural networks (SNNs) are the third generation of neural networks and perform remarkably well in cognitive tasks such as pattern recognition. The spike emitting and information processing mechanisms found in biological cognitive systems motivate the application of the hierarchical structure and temporal encoding mechanism in spiking neural networks, which have exhibited strong computational capability. However, the hierarchical structure and temporal encoding approach require neurons to process information serially in space and time respectively, which reduce the training efficiency significantly. For training the hierarchical SNNs, most existing methods are based on the traditional back-propagation algorithm, inheriting its drawbacks of the gradient diffusion and the sensitivity on parameters. To keep the powerful computation capability of the hierarchical structure and temporal encoding mechanism, but to overcome the low efficiency of the existing algorithms, a new training algorithm, the Normalized Spiking Error Back Propagation (NSEBP) is proposed in this paper. In the feedforward calculation, the output spike times are calculated by solving the quadratic function in the spike response model instead of detecting postsynaptic voltage states at all time points in traditional algorithms. Besides, in the feedback weight modification, the computational error is propagated to previous layers by the presynaptic spike jitter instead of the gradient decent rule, which realizes the layer-wised training. Furthermore, our algorithm investigates the mathematical relation between the weight variation and voltage error change, which makes the normalization in the weight modification applicable. Adopting these strategies, our algorithm outperforms the traditional SNN multi-layer algorithms in terms of learning efficiency and parameter sensitivity, that are also demonstrated by the comprehensive experimental results in this paper. [ABSTRACT FROM AUTHOR]

In high efficiency video coding (HEVC), coding tree contributes to excellent compression performance. However, coding tree brings extremely high computational complexity. Innovative works for improving coding tree to further reduce encoding time are stated in this paper. A novel low complexity coding tree mechanism is proposed for HEVC fast coding unit (CU) encoding. Firstly, this paper makes an in-depth study of the relationship among CU distribution, quantization parameter (QP) and content change (CC). Secondly, a CU coding tree probability model is proposed for modeling and predicting CU distribution. Eventually, a CU coding tree probability update is proposed, aiming to address probabilistic model distortion problems caused by CC. Experimental results show that the proposed low complexity CU coding tree mechanism significantly reduces encoding time by 27% for lossy coding and 42% for visually lossless coding and lossless coding. The proposed low complexity CU coding tree mechanism devotes to improving coding performance under various application conditions. [ABSTRACT FROM AUTHOR]

To discover regularities in human mobility is of fundamental importance to our understanding of urban dynamics, and essential to city and transport planning, urban management and policymaking. Previous research has revealed universal regularities at mainly aggregated spatio-temporal scales but when we zoom into finer scales, considerable heterogeneity and diversity is observed instead. The fundamental question we address in this paper is at what scales are the regularities we detect stable, explicable, and sustainable. This paper thus proposes a basic measure of variability to assess the stability of such regularities focusing mainly on changes over a range of temporal scales. We demonstrate this by comparing regularities in the urban mobility patterns in three world cities, namely London, Singapore and Beijing using one-week of smart-card data. The results show that variations in regularity scale as non-linear functions of the temporal resolution, which we measure over a scale from 1 minute to 24 hours thus reflecting the diurnal cycle of human mobility. A particularly dramatic increase in variability occurs up to the temporal scale of about 15 minutes in all three cities and this implies that limits exist when we look forward or backward with respect to making short-term predictions. The degree of regularity varies in fact from city to city with Beijing and Singapore showing higher regularity in comparison to London across all temporal scales. A detailed discussion is provided, which relates the analysis to various characteristics of the three cities. In summary, this work contributes to a deeper understanding of regularities in patterns of transit use from variations in volumes of travellers entering subway stations, it establishes a generic analytical framework for comparative studies using urban mobility data, and it provides key points for the management of variability by policy-makers intent on for making the travel experience more amenable. [ABSTRACT FROM AUTHOR]

The wealth of sensory data coming from different modalities has opened numerous opportunities for data analysis. The data are of increasing volume, complexity and dimensionality, thus calling for new methodological innovations towards multimodal data processing. However, multimodal architectures must rely on models able to adapt to changes in the data distribution. Differences in the density functions can be due to changes in acquisition conditions (pose, illumination), sensors characteristics (number of channels, resolution) or different views (e.g. street level vs. aerial views of a same building). We call these different acquisition modes domains, and refer to the adaptation problem as domain adaptation. In this paper, instead of adapting the trained models themselves, we alternatively focus on finding mappings of the data sources into a common, semantically meaningful, representation domain. This field of manifold alignment extends traditional techniques in statistics such as canonical correlation analysis (CCA) to deal with nonlinear adaptation and possibly non-corresponding data pairs between the domains. We introduce a kernel method for manifold alignment (KEMA) that can match an arbitrary number of data sources without needing corresponding pairs, just few labeled examples in all domains. KEMA has interesting properties: 1) it generalizes other manifold alignment methods, 2) it can align manifolds of very different complexities, performing a discriminative alignment preserving each manifold inner structure, 3) it can define a domain-specific metric to cope with multimodal specificities, 4) it can align data spaces of different dimensionality, 5) it is robust to strong nonlinear feature deformations, and 6) it is closed-form invertible, which allows transfer across-domains and data synthesis. To authors’ knowledge this is the first method addressing all these important issues at once. We also present a reduced-rank version of KEMA for computational efficiency, and discuss the generalization performance of KEMA under Rademacher principles of stability. Aligning multimodal data with KEMA reports outstanding benefits when used as a data pre-conditioner step in the standard data analysis processing chain. KEMA exhibits very good performance over competing methods in synthetic controlled examples, visual object recognition and recognition of facial expressions tasks. KEMA is especially well-suited to deal with high-dimensional problems, such as images and videos, and under complicated distortions, twists and warpings of the data manifolds. A fully functional toolbox is available at . [ABSTRACT FROM AUTHOR]

The present paper examines the relation between size, accumulation and performance for research grants, where we examine the relation between grant size for Centres of Excellence (CoE) funded by the Danish National Research Foundation (DNRF) and various ex post research performance measures, including impact and shares of highly cited articles. We examine both the relation between size and performance and also how performance for CoEs evolves over the course of grant periods. In terms of dynamics, it appears that performance over the grant period (i.e. 10 years) is falling for the largest CoEs, while it is increasing for those among the smallest half. Overall, multivariate econometric analysis finds evidence that performance is increasing in grant size and over time. In both cases, the relation appears to be non-linear, suggesting that there is a point at which performance peaks. The CoEs have also been very successful in securing additional funding, which can be viewed as a ‘cumulative effect’ of center grants. In terms of new personnel, the far majority of additional funding is spent on early career researchers, hence, this accumulation would appear to have a ‘generational’ dimension, allowing for scientific expertise to be passed on to an increasing number of younger researchers. [ABSTRACT FROM AUTHOR]

The problem of handling non-ignorable non-response has been typically addressed under the design-based approach using the well-known sub-sampling technique introduced by Hansen and Hurwitz [1946, Journal of the American Statistical Association, Vol 41(236), Page 517- 529]. Alternatively, the model-based paradigm emphasizes on utilizing the underlying model relationship between the outcome variable and one or more covariate(s) whose population values are known prior to the survey. This article utilizes the model relationship between the study variable and covariate(s) for handling non-ignorable non-response and obtaining an unbiased estimator for the population total under the sub-sampling technique. The main idea is to combine the estimates obtained from the sample on first call and the sub-sample from second call using separate model relationships. The contribution of this paper helps us in providing unbiased estimates with an improved efficiency under model-based paradigm in presence of non-ignorable non-response. The provided method is more economical than the available estimators under callback methods as we are working sub-sampling and also increase response rate as a stronger mode of interview is employed for data collection. A numerical study using Monte Carlo is presented to illustrate the behavior of the proposed and the efficiency comparison. [ABSTRACT FROM AUTHOR]

Slope one is a popular recommendation algorithm due to its simplicity and high efficiency for sparse data. However, it often suffers from under-fitting since the global information of all relevant users/items are considered. In this paper, we propose a new scheme called enhanced slope one recommendation through local information embedding. First, we employ clustering algorithms to obtain the user clusters as well as item clusters to represent local information. Second, we predict ratings using the local information of users and items in the same cluster. The local information can detect strong localized associations shared within clusters. Third, we design different fusion approaches based on the local information embedding. In this way, both under-fitting and over-fitting problems are alleviated. Experiment results on the real datasets show that our approaches defeats slope one in terms of both mean absolute error and root mean square error. [ABSTRACT FROM AUTHOR]

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

Sensor network intrusion detection has attracted extensive attention. However, previous intrusion detection methods face the highly imbalanced attack class distribution problem, and they may not achieve a satisfactory performance. To solve this problem, we propose a new intrusion detection algorithm based on normalized cut spectral clustering for sensor network in this paper. The main aim is to reduce the imbalance degree among classes in an intrusion detection system. First, we design a normalized cut spectral clustering to reduce the imbalance degree between every two classes in the intrusion detection data set. Second, we train a network intrusion detection classifier on the new data set. Finally, we do extensive experiments and analyze the experimental results in detail. Simulation experiments show that our algorithm can reduce the imbalance degree among classes and reserves the distribution of the original data on the one hand, and improve effectively the detection performance on the other hand. [ABSTRACT FROM AUTHOR]

Temporal hierarchies have been widely used during the past few years as they are capable to provide more accurate coherent forecasts at different planning horizons. However, they still display some limitations, being mainly subject to the forecasting methods used for generating the base forecasts and the particularities of the examined series. This paper deals with such limitations by considering three different strategies: (i) combining forecasts of multiple methods, (ii) applying bias adjustments and (iii) selectively implementing temporal hierarchies to avoid seasonal shrinkage. The proposed strategies can be applied either separately or simultaneously, being complements to the method considered for reconciling the base forecasts and completely independent from each other. Their effect is evaluated using the monthly series of the M and M3 competitions. The results are very promising, displaying lots of potential for improving the performance of temporal hierarchies, both in terms of accuracy and bias. [ABSTRACT FROM AUTHOR]

There is a vivid research on securely deliver a secret message by using a data hiding technique in digital images. However, most existing solutions of data-hiding need to encrypt secret data first, and embed the encrypt message into cover image, which is not promising any security once the embedding algorithm is leaked. In this paper, an efficient and adaptive data hiding scheme is presented which is based on a new reference matrix named secure reference matrix. The scheme is flexible enough to meet different data hiding capacities and image quality as needed, and we allow the reference matrix to be more secure since it is randomly generated each time and make it much harder for being attack with exhaustive manner by extending the possible solution. We give the detail protocol for our scheme and provide the practical test and performance analysis. Experimental results show that our scheme has a better flexibility and efficiency in embedding process, and the average value of Peak Signal to Noise Ratio (PSNR) for the stego-images which are generated by our scheme have a higher visual quality for different embedding capacities, and our scheme is more efficient compared with related work. [ABSTRACT FROM AUTHOR]

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

Cancer driver genes, i.e., oncogenes and tumor suppressor genes, are involved in the acquisition of important functions in tumors, providing a selective growth advantage, allowing uncontrolled proliferation and avoiding apoptosis. It is therefore important to identify these driver genes, both for the fundamental understanding of cancer and to help finding new therapeutic targets or biomarkers. Although the most frequently mutated driver genes have been identified, it is believed that many more remain to be discovered, particularly for driver genes specific to some cancer types. In this paper, we propose a new computational method called LOTUS to predict new driver genes. LOTUS is a machine-learning based approach which allows to integrate various types of data in a versatile manner, including information about gene mutations and protein-protein interactions. In addition, LOTUS can predict cancer driver genes in a pan-cancer setting as well as for specific cancer types, using a multitask learning strategy to share information across cancer types. We empirically show that LOTUS outperforms five other state-of-the-art driver gene prediction methods, both in terms of intrinsic consistency and prediction accuracy, and provide predictions of new cancer genes across many cancer types. [ABSTRACT FROM AUTHOR]

The solution to the job shop scheduling problem (JSSP) is of great significance for improving resource utilization and production efficiency of enterprises. In this paper, in view of its non-deterministic polynomial properties, a multi-agent genetic algorithm based on tabu search (MAGATS) is proposed to solve JSSPs under makespan constraints. Firstly, a multi-agent genetic algorithm (MAGA) is proposed. During the process, a multi-agent grid environment is constructed based on characteristics of multi-agent systems and genetic algorithm (GA), and a corresponding neighbor interaction operator, a mutation operator based on neighborhood structure and a self-learning operator are designed. Then, combining tabu search algorithm with a MAGA, the algorithm MAGATS are presented. Finally, 43 benchmark instances are tested with the new algorithm. Compared with four other algorithms, the optimization performance of it is analyzed based on obtained test results. Effectiveness of the new algorithm is verified by analysis results. [ABSTRACT FROM AUTHOR]

In this paper, we present a new multi-focus microscope (MFM) system based on a phase mask and HiLo algorithm, achieving high-speed (20 volumes per second), high-resolution, low-noise 3-D fluorescent imaging. During imaging, the emissions from the specimen at nine different depths are simultaneously modulated and focused to different regions on a single CCD chip, i.e., the CCD chip is subdivided into nine regions to record images from the different selected depths. Next, HiLo algorithm is applied to remove the background noises and to form clean 3-D images. To visualize larger volumes, the nine layers are scanned axially, realizing fast 3-D imaging. In the imaging experiments, a mouse kidney sample of ~ 60 × 60 × 16 μm3 is visualized with only 10 raw images, demonstrating substantially enhanced resolution and contrast as well as suppressed background noises. The new method will find important applications in 3-D fluorescent imaging, e.g., recording fast dynamic events at multiple depths in vivo. [ABSTRACT FROM AUTHOR]

This paper quantifies the effect of speed cameras on road traffic collisions using an approximate Bayesian doubly-robust (DR) causal inference estimation method. Previous empirical work on this topic, which shows a diverse range of estimated effects, is based largely on outcome regression (OR) models using the Empirical Bayes approach or on simple before and after comparisons. Issues of causality and confounding have received little formal attention. A causal DR approach combines propensity score (PS) and OR models to give an average treatment effect (ATE) estimator that is consistent and asymptotically normal under correct specification of either of the two component models. We develop this approach within a novel approximate Bayesian framework to derive posterior predictive distributions for the ATE of speed cameras on road traffic collisions. Our results for England indicate significant reductions in the number of collisions at speed cameras sites (mean ATE = -15%). Our proposed method offers a promising approach for evaluation of transport safety interventions. [ABSTRACT FROM AUTHOR]

Magnetic loops are one of the most popular and used traffic sensors because of their widely extended technology and simple mode of operation. Nevertheless, very simple models have been traditionally used to simulate the effect of the passage of vehicles on these loops. In general, vehicles have been considered simple rectangular metal plates located parallel to the ground plane at a certain height close to the vehicle chassis. However, with such a simple model, it is not possible to carry out a rigorous study to assess the performance of different models of vehicles with the aim of obtaining basic parameters such as the vehicle type, its speed or its direction in traffic. For this reason and because computer simulation and analysis have emerged as a priority in intelligent transportation systems (ITS), this paper aims to present a more complex vehicle model capable of characterizing vehicles as multiple metal plates of different sizes and heights, which will provide better results in virtual simulation environments. This type of modeling will be useful when reproducing the actual behavior of systems installed on roads based on inductive loops and will also facilitate vehicle classification and the extraction of basic traffic parameters. [ABSTRACT FROM AUTHOR]

Filter or screening methods are often used as a preprocessing step for reducing the number of variables used by a learning algorithm in obtaining a classification or regression model. While there are many such filter methods, there is a need for an objective evaluation of these methods. Such an evaluation is needed to compare them with each other and also to answer whether they are at all useful, or a learning algorithm could do a better job without them. For this purpose, many popular screening methods are partnered in this paper with three regression learners and five classification learners and evaluated on ten real datasets to obtain accuracy criteria such as R-square and area under the ROC curve (AUC). The obtained results are compared through curve plots and comparison tables in order to find out whether screening methods help improve the performance of learning algorithms and how they fare with each other. Our findings revealed that the screening methods were useful in improving the prediction of the best learner on two regression and two classification datasets out of the ten datasets evaluated. [ABSTRACT FROM AUTHOR]

Short-term metro passenger flow forecasting is an essential component of intelligent transportation systems (ITS) and can be applied to optimize the passenger flow organization of a station and offer data support for metro passenger flow early warning and system management. LSTM neural networks have recently achieved remarkable recent in the field of natural language processing (NLP) because they are well suited for learning from experience to predict time series. For this purpose, we propose an empirical mode decomposition (EMD)-based long short-term memory (LSTM) neural network model for predicting short-term metro inbound passenger flow. The EMD algorithm decomposes the original sequential passenger flow into several intrinsic mode functions (IMFs) and a residual. Selected IMFs that are strongly correlated with the original data can be obtained via feature selection. The selected IMFs and the original data are integrated into inputs for LSTM neural networks, and a single LSTM prediction model and an EMD-LSTM hybrid forecasting model are developed. Finally, historical real automatic fare collection (AFC) data from metro passengers are collected from Chengdu Metro to verify the validity of the proposed EMD-LSTM prediction model. The results indicate that the proposed EMD-LSTM hybrid forecasting model outperforms the LSTM, ARIMA and BPN models. [ABSTRACT FROM AUTHOR]

Due to the fast speed of data generation and collection from advanced equipment, the amount of data obviously overflows the limit of available memory space and causes difficulties achieving high learning accuracy. Several methods based on discard-after-learn concept have been proposed. Some methods were designed to cope with a single incoming datum but some were designed for a chunk of incoming data. Although the results of these approaches are rather impressive, most of them are based on temporally adding more neurons to learn new incoming data without any neuron merging process which can obviously increase the computational time and space complexities. Only online versatile elliptic basis function (VEBF) introduced neuron merging to reduce the space-time complexity of learning only a single incoming datum. This paper proposed a method for further enhancing the capability of discard-after-learn concept for streaming data-chunk environment in terms of low computational time and neural space complexities. A set of recursive functions for computing the relevant parameters of a new neuron, based on statistical confidence interval, was introduced. The newly proposed method, named streaming chunk incremental learning (SCIL), increases the plasticity and the adaptabilty of the network structure according to the distribution of incoming data and their classes. When being compared to the others in incremental-like manner, based on 11 benchmarked data sets of 150 to 581,012 samples with attributes ranging from 4 to 1,558 formed as streaming data, the proposed SCIL gave better accuracy and time in most data sets. [ABSTRACT FROM AUTHOR]

To balance the supply and demand in China's beef market, beef consumption must be scientifically and effectively forecasted. Beef consumption is affected by many factors and is characterized by gray uncertainty. Therefore, gray theory can be used to forecast the beef consumption, In this paper, the structural defects and unreasonable parameter design of the traditional gray model are analyzed. Then, a new gray model termed, EGM(1,1,r), is built, and the modeling conditions and error checking methods of EGM(1,1,r) are studied. Then, EGM(1,1,r) is used to simulate and forecast China’s beef consumption. The results show that both the simulation and prediction precisions of the new model are better than those of other gray models. Finally, the new model is used to forecast China’s beef consumption for the period from 2019–2025. The findings will serve as an important reference for the Chinese government in formulating policies to ensure the balance between the supply and demand for Chinese beef. [ABSTRACT FROM AUTHOR]

With the development and universal application of satellite technology, an important way to expand the function of satellites is setting up inter-satellite networks to make them work together. Traditional satellite networking methods generally adopt a fixed time slot allocation method, which is not suitable for small satellite groups with low latency and high throughput requirements. In order to solve this problem, it has been proposed to apply the traditional Wifi protocol in satellite networking. As there are differences between satellite networks and terrestrial networks, it’s necessary to improve the traditional 802.11 protocol. The Media Access Control (MAC) protocol in 802.11 is improved in this paper, which mainly includes the adaptive algorithm of maximum contention window size and the growth algorithm of Contention Window (CW) size. The maximum contention window is adjusted according to the conflict state of the current network, which makes the network accommodate more satellite nodes. The CW growth algorithm improves the traditional Binary Exponential Back-off (BEB) algorithm, where the CW is designed according to the priority of the data frame or the network load. In this way, high-priority satellite accusation information will have higher reliability or tolerate greater network load. [ABSTRACT FROM AUTHOR]

In this paper, from the practical point of view, we focus on modeling traumatic brain injury data considering different stages of hospitalization, related to patients’ survival rates following traumatic brain injury caused by traffic accidents. From the statistical point of view, the primary objective is related to overcoming the limited number of traumatic brain injury patients available for studying by considering different estimation methods to obtain improved estimators of the model parameters, which can be recommended to be used in the presence of small samples. To have a general methodology, at least in principle, we consider the very flexible Generalized Gamma distribution. We compare various estimation methods using extensive numerical simulations. The results reveal that the penalized maximum likelihood estimators have the smallest mean square errors and biases, proving to be the most efficient method among the investigated ones, mainly to be used in the presence of small samples. The Simulated Annealing technique is used to avoid numerical problems during the optimization process, as well as the need for good initial values. Overall, we considered an amount of three real data sets related to traumatic brain injury caused by traffic accidents to demonstrate that the Generalized Gamma distribution is a simple alternative to be used in this type of applications for different occurrence rates and risks, and in the presence of small samples. [ABSTRACT FROM AUTHOR]

Forgery detection is essential to verify the integrity and authenticity of images. Existing block-based detection techniques detect forgery in the same image, most of which use similar frameworks while differ in the feature extraction schemes. These methods have high accuracy in detecting the forged regions, but the computational load is heavy when facing exhaustive search problems. This paper describes a forgery detection method based on local binary pattern residue classes and color regions. An image is divided into overlapped blocks. Local binary pattern residue classes are computed for each block. The plane formed by a dimensional and b dimensional from Lab color space is divided into 16 regions. Similar blocks are searched in the overlapped blocks with the same local binary pattern residue class and color region, then they are grouped into several suspicious regions. Finally, we analyze the multi-region relation of these suspicious regions and their areas to locate the tampered regions. The small hole is filled through the morphologic operation. The results of experiments demonstrated that our method has good performance in that it improved detection accuracy and reduced execution time under various challenging conditions. As the proposed method reduces the search range for similar blocks, it has a higher speed than exhaustive search and has comparable detection results at the same time. [ABSTRACT FROM AUTHOR]

The analyses of large volumes of metagenomic data extracted from aggregate populations of microscopic organisms residing on and in the human body are advancing contemporary understandings of the integrated participation of microbes in human health and disease. Next generation sequencing technology facilitates said analyses in terms of diversity, community composition, and differential abundance by filtering and binning microbial 16S rRNA genes extracted from human tissues into operational taxonomic units. However, current statistical tools restrict study designs to investigations of limited numbers of host characteristics mediated by limited numbers of samples potentially yielding a loss of relevant information. This paper presents a Bayesian hierarchical negative binomial model as an efficient technique capable of compensating for multivariable sets including tens or hundreds of host characteristics as covariates further expanding analyses of human microbiome count data. Simulation studies reveal that the Bayesian hierarchical negative binomial model provides a desirable strategy by often outperforming three competing negative binomial model in terms of type I error while simultaneously maintaining consistent power. An application of the Bayesian hierarchical negative binomial model using subsets of the open data published by the American Gut Project demonstrates an ability to identify operational taxonomic units significantly differentiable among persons diagnosed by a medical professional with either inflammatory bowel disease or irritable bowel syndrome that are consistent with contemporary gastrointestinal literature. [ABSTRACT FROM AUTHOR]

Single-point incremental forming (SPIF) is a technology that allows incremental manufacturing of complex parts from a flat sheet using simple tools; further, this technology is flexible and economical. Measuring the forming force using this technology helps in preventing failures, determining the optimal processes, and implementing on-line control. In this paper, an experimental study using SPIF is described. This study focuses on the influence of four different process parameters, namely, step size, tool diameter, sheet thickness, and feed rate, on the maximum forming force. For an efficient force predictive model based on an adaptive neuro-fuzzy inference system (ANFIS), an artificial neural network (ANN) and a regressions model were applied. The predicted forces exhibited relatively good agreement with the experimental results. The results indicate that the performance of the ANFIS model realizes the full potential of the ANN model. [ABSTRACT FROM AUTHOR]

Big web data from sources including online news and Twitter are good resources for investigating deep learning. However, collected news articles and tweets almost certainly contain data unnecessary for learning, and this disturbs accurate learning. This paper explores the performance of word2vec Convolutional Neural Networks (CNNs) to classify news articles and tweets into related and unrelated ones. Using two word embedding algorithms of word2vec, Continuous Bag-of-Word (CBOW) and Skip-gram, we constructed CNN with the CBOW model and CNN with the Skip-gram model. We measured the classification accuracy of CNN with CBOW, CNN with Skip-gram, and CNN without word2vec models for real news articles and tweets. The experimental results indicated that word2vec significantly improved the accuracy of the classification model. The accuracy of the CBOW model was higher and more stable when compared to that of the Skip-gram model. The CBOW model exhibited better performance on news articles, and the Skip-gram model exhibited better performance on tweets. Specifically, CNN with word2vec models was more effective on news articles when compared to that on tweets because news articles are typically more uniform when compared to tweets. [ABSTRACT FROM AUTHOR]

A major tenet in theoretical neuroscience is that cognitive and behavioral processes are ultimately implemented in terms of the neural system dynamics. Accordingly, a major aim for the analysis of neurophysiological measurements should lie in the identification of the computational dynamics underlying task processing. Here we advance a state space model (SSM) based on generative piecewise-linear recurrent neural networks (PLRNN) to assess dynamics from neuroimaging data. In contrast to many other nonlinear time series models which have been proposed for reconstructing latent dynamics, our model is easily interpretable in neural terms, amenable to systematic dynamical systems analysis of the resulting set of equations, and can straightforwardly be transformed into an equivalent continuous-time dynamical system. The major contributions of this paper are the introduction of a new observation model suitable for functional magnetic resonance imaging (fMRI) coupled to the latent PLRNN, an efficient stepwise training procedure that forces the latent model to capture the ‘true’ underlying dynamics rather than just fitting (or predicting) the observations, and of an empirical measure based on the Kullback-Leibler divergence to evaluate from empirical time series how well this goal of approximating the underlying dynamics has been achieved. We validate and illustrate the power of our approach on simulated ‘ground-truth’ dynamical systems as well as on experimental fMRI time series, and demonstrate that the learnt dynamics harbors task-related nonlinear structure that a linear dynamical model fails to capture. Given that fMRI is one of the most common techniques for measuring brain activity non-invasively in human subjects, this approach may provide a novel step toward analyzing aberrant (nonlinear) dynamics for clinical assessment or neuroscientific research. [ABSTRACT FROM AUTHOR]

Our understanding of how chromosomes structurally organize and dynamically interact has been revolutionized through the lens of long-chain polymer physics. Major protein contributors to chromosome structure and dynamics are condensin and cohesin that stochastically generate loops within and between chains, and entrap proximal strands of sister chromatids. In this paper, we explore the ability of transient, protein-mediated, gene-gene crosslinks to induce clusters of genes, thereby dynamic architecture, within the highly repeated ribosomal DNA that comprises the nucleolus of budding yeast. We implement three approaches: live cell microscopy; computational modeling of the full genome during G1 in budding yeast, exploring four decades of timescales for transient crosslinks between 5kbp domains (genes) in the nucleolus on Chromosome XII; and, temporal network models with automated community (cluster) detection algorithms applied to the full range of 4D modeling datasets. The data analysis tools detect and track gene clusters, their size, number, persistence time, and their plasticity (deformation). Of biological significance, our analysis reveals an optimal mean crosslink lifetime that promotes pairwise and cluster gene interactions through “flexible” clustering. In this state, large gene clusters self-assemble yet frequently interact (merge and separate), marked by gene exchanges between clusters, which in turn maximizes global gene interactions in the nucleolus. This regime stands between two limiting cases each with far less global gene interactions: with shorter crosslink lifetimes, “rigid” clustering emerges with clusters that interact infrequently; with longer crosslink lifetimes, there is a dissolution of clusters. These observations are compared with imaging experiments on a normal yeast strain and two condensin-modified mutant cell strains. We apply the same image analysis pipeline to the experimental and simulated datasets, providing support for the modeling predictions. [ABSTRACT FROM AUTHOR]

In this paper we consider the process of the second harmonic generation in a gradient waveguide, taking into account diffraction and relatively weak temporal dispersion. Using the slowly varying envelope approximation and neglecting the dispersion of the nonlinear part of the response of the medium we obtain the system of parabolic equations for the envelopes of both harmonics. We also derive integrals of motion of this system. To solve it numerically we construct a nonlinear finite-difference scheme based on the Crank-Nicolson method preserving the integrals. Primarily, we focus our investigations on the processes of a two-component light bullets generation. We demonstrate that the generation of a coupled pair is possible in a planar waveguide even at normal group velocity dispersion. [ABSTRACT FROM AUTHOR]

In this paper, we propose a new approach for learning node embeddings for weighted undirected networks. We perform a random walk on the network to extract the latent structural information and perform node embedding learning under a similarity-based framework. Unlike previous works, we apply a different criterion to capture the proximity information between nodes in a network, and use it for improved modeling of similarities between nodes. We show that the mean commute time (MCT) between two nodes, defined as the average time a random walker takes to reach a target node and return to the source, plays a crucial role in quantifying the actual degree of proximity between two nodes of the network. We then introduce a novel definition of a similarity matrix that is based on the pair-wise mean commute time captured, which enables us to adequately represent the connection of similar nodes. We utilize pseudoinverse of the Laplacian matrix of the graph for calculating such a proximity measure, capturing rich structural information out of the graph for learning more adequate node representations of a network. The results of different experiments on three real-world networks demonstrate that our proposed method outperforms existing related efforts in classification, clustering, visualization as well as link prediction tasks. [ABSTRACT FROM AUTHOR]

While there have been many studies using machine learning (ML) algorithms to predict process outcomes and device performance in semiconductor manufacturing, the extensively developed technology computer-aided design (TCAD) physical models should play a more significant role in conjunction with ML. While TCAD models have been effective in predicting the trends of experiments, a machine learning statistical model is more capable of predicting the anomalous effects that can be dependent on the chambers, machines, fabrication environment, and specific layouts. In this paper, we use an analytics-statistics mixed training (ASMT) approach using TCAD. Under this method, the TCAD models are incorporated into the machine learning training procedure. The mixed dataset with the experimental and TCAD results improved the prediction in terms of accuracy. With the application of ASMT to the BOSCH process, we show that the mean square error (MSE) can be effectively decreased when the analytics-statistics mixed training (ASMT) scheme is used instead of the classic neural network (NN) used in the baseline study. In this method, statistical induction and analytical deduction can be combined to increase the prediction accuracy of future intelligent semiconductor manufacturing. [ABSTRACT FROM AUTHOR]

SPEC CPU is one of the most common benchmark suites used in computer architecture research. CPU2017 has recently been released to replace CPU2006. In this paper we present a detailed evaluation of the memory hierarchy performance for both the CPU2006 and single-threaded CPU2017 benchmarks. The experiments were executed on an Intel Xeon Skylake-SP, which is the first Intel processor to implement a mostly non-inclusive last-level cache (LLC). We present a classification of the benchmarks according to their memory pressure and analyze the performance impact of different LLC sizes. We also test all the hardware prefetchers showing they improve performance in most of the benchmarks. After comprehensive experimentation, we can highlight the following conclusions: i) almost half of SPEC CPU benchmarks have very low miss ratios in the second and third level caches, even with small LLC sizes and without hardware prefetching, ii) overall, the SPEC CPU2017 benchmarks demand even less memory hierarchy resources than the SPEC CPU2006 ones, iii) hardware prefetching is very effective in reducing LLC misses for most benchmarks, even with the smallest LLC size, and iv) from the memory hierarchy standpoint the methodologies commonly used to select benchmarks or simulation points do not guarantee representative workloads. [ABSTRACT FROM AUTHOR]

Shape Up Under 5 (SUU5) was a two-year early childhood obesity prevention pilot study in Somerville, Massachusetts (2015–2017) designed to test a novel conceptual framework called Stakeholder-driven Community Diffusion. For whole-of-community interventions, this framework posits that diffusion of stakeholders’ knowledge about and engagement with childhood obesity prevention efforts through their social networks will improve the implementation of health-promoting policy and practice changes intended to reduce obesity risk. SUU5 used systems science methods (agent-based modeling, group model building, social network analysis) to design, facilitate, and evaluate the work of 16 multisector stakeholders (‘the Committee’). In this paper, we describe the design and methods of SUU5 using the conceptual framework: the approach to data collection, and methods and rationale for study inputs, activities and evaluation, which together may further our understanding of the hypothesized processes within Stakeholder-driven Community Diffusion. We also present a generalizable conceptual framework for addressing childhood obesity and similar complex public health issues through whole-of-community interventions. [ABSTRACT FROM AUTHOR]

When many events contributed to an outcome, people consistently judge some more causal than others, based in part on the prior probabilities of those events. For instance, when a tree bursts into flames, people judge the lightning strike more of a cause than the presence of oxygen in the air—in part because oxygen is so common, and lightning strikes are so rare. These effects, which play a major role in several prominent theories of token causation, have largely been studied through qualitative manipulations of the prior probabilities. Yet, there is good reason to think that people’s causal judgments are on a continuum—and relatively little is known about how these judgments vary quantitatively as the prior probabilities change. In this paper, we measure people’s causal judgment across parametric manipulations of the prior probabilities of antecedent events. Our experiments replicate previous qualitative findings, and also reveal several novel patterns that are not well-described by existing theories. [ABSTRACT FROM AUTHOR]

Targeted environmental and ecosystem management remain crucial in control of dengue. However, providing detailed environmental information on a large scale to effectively target dengue control efforts remains a challenge. An important piece of such information is the extent of the presence of potential dengue vector breeding sites, which consist primarily of open containers such as ceramic jars, buckets, old tires, and flowerpots. In this paper we present the design and implementation of a pipeline to detect outdoor open containers which constitute potential dengue vector breeding sites from geotagged images and to create highly detailed container density maps at unprecedented scale. We implement the approach using Google Street View images which have the advantage of broad coverage and of often being two to three years old which allows correlation analyses of container counts against historical data from manual surveys. Containers comprising eight of the most common breeding sites are detected in the images using convolutional neural network transfer learning. Over a test set of images the object recognition algorithm has an accuracy of 0.91 in terms of F-score. Container density counts are generated and displayed on a decision support dashboard. Analyses of the approach are carried out over three provinces in Thailand. The container counts obtained agree well with container counts from available manual surveys. Multi-variate linear regression relating densities of the eight container types to larval survey data shows good prediction of larval index values with an R-squared of 0.674. To delineate conditions under which the container density counts are indicative of larval counts, a number of factors affecting correlation with larval survey data are analyzed. We conclude that creation of container density maps from geotagged images is a promising approach to providing detailed risk maps at large scale. [ABSTRACT FROM AUTHOR]

Demand for spring onion seeds is variable and maintaining its supply is crucial to the success of seed companies. Spring onion seed demand forecasting, which can help reduce the high operational costs increased by long-period propagation and complex logistics, has not previously been investigated yet. This paper provides a novel perspective on spring onion seed demand forecasting and proposes a hybrid Holt-Winters and support vector machine (SVM) forecasting model. The model uses dynamic factors, including historical seed sales, seed inventory, spring onion crop market price and weather data, as inputs to forecast spring onion seed demand. Forecasting error, i.e. the difference between actual and forecasted demand, is assessed. Two advanced machine learning models are trained on the same dataset as benchmark models. Numerical experiments using actual commercial sales data for three spring onion seed varieties show the proposed hybrid model outperformed the statistical-based models for all three forecasting errors. Seed inventory, spring onion crop market price and historical seed sales are the most important dynamic factors, among which seed inventory has short-term influence while other two have mid-term influence on seed demand forecasting. The absolute minimum temperature is the only factor having long-term influence. This study provides a promising spring onion seed demand forecasting model that helps understand the relationships between seed demand and other dynamic factors and the model could potentially be applied to demand forecasting of other crop seeds to reduce total operational costs. [ABSTRACT FROM AUTHOR]