Search

Biometric recognition technology based on eye-movement dynamics has been in development for more than ten years. Different visual tasks, feature extraction and feature recognition methods are proposed to improve the performance of eye movement biometric system. However, the correct identification and verification rates, especially in long-term experiments, as well as the effects of visual tasks and eye trackers’ temporal and spatial resolution are still the foremost considerations in eye movement biometrics. With a focus on these issues, we proposed a new visual searching task for eye movement data collection and a new class of eye movement features for biometric recognition. In order to demonstrate the improvement of this visual searching task being used in eye movement biometrics, three other eye movement feature extraction methods were also tested on our eye movement datasets. Compared with the original results, all three methods yielded better results as expected. In addition, the biometric performance of these four feature extraction methods was also compared using the equal error rate (EER) and Rank-1 identification rate (Rank-1 IR), and the texture features introduced in this paper were ultimately shown to offer some advantages with regard to long-term stability and robustness over time and spatial precision. Finally, the results of different combinations of these methods with a score-level fusion method indicated that multi-biometric methods perform better in most cases. [ABSTRACT FROM AUTHOR]

Past research on the process of extinguishing a fire typically used a traditional linear water jet falling point model and the results ignored external factors, such as environmental conditions and the status of the fire engine, even though the water jet falling point location prediction was often associated with these parameters and showed a nonlinear relationship. This paper constructed a BP (Back Propagation) neural network model. The fire gun nozzle characteristics were included as model inputs, and the water discharge point coordinates were the model outputs; thus, the model could precisely predict the water discharge point with small error and high precision to determine an accurate firing position and allow for the timely adjustment of the spray gun. To improve the slow convergence and local optimality problems of the BP neural network (BPNN), this paper further used a genetic algorithm to optimize the BPNN (GA-BPNN). The BPNN can be used to optimize the weights in the network to train them for global optimization. A genetic algorithm was introduced into the neural network approach, and the water jet landing prediction model was further improved. The simulation results showed that the prediction accuracy of the GA-BP model was better than that of the BPNN alone. The established model can accurately predict the location of the water jet, making the prediction results more useful for firefighters. [ABSTRACT FROM AUTHOR]

Open source software has been widely used in various industries due to its openness and flexibility, but it also brings potential security problems. Therefore, security analysis is required before using open source software. The current mainstream open source software vulnerability analysis technology is based on source code, and there are problems such as false positives, false negatives and restatements. In order to solve the problems, based on the further study of behavior feature extraction and vulnerability detection technology, a method of using dynamic behavior features to detect open source software vulnerabilities is proposed. Firstly, the relationship between open source software vulnerability and API call sequence is studied. Then, the behavioral risk vulnerability database of open source software is proposed as a support for vulnerability detection. In addition, the CNN-IndRNN classification model is constructed by improving the Independently Recurrent Neural Net-work (IndRNN) algorithm and applies to open source software security vulnerability detection. The experimental results verify the effectiveness of the proposed open source software security vulnerability detection method based on dynamic behavior features. [ABSTRACT FROM AUTHOR]

In the Bayesian Reinforcement Learning (BRL) setting, agents try to maximise the collected rewards while interacting with their environment while using some prior knowledge that is accessed beforehand. Many BRL algorithms have already been proposed, but the benchmarks used to compare them are only relevant for specific cases. The paper addresses this problem, and provides a new BRL comparison methodology along with the corresponding open source library. In this methodology, a comparison criterion that measures the performance of algorithms on large sets of Markov Decision Processes (MDPs) drawn from some probability distributions is defined. In order to enable the comparison of non-anytime algorithms, our methodology also includes a detailed analysis of the computation time requirement of each algorithm. Our library is released with all source code and documentation: it includes three test problems, each of which has two different prior distributions, and seven state-of-the-art RL algorithms. Finally, our library is illustrated by comparing all the available algorithms and the results are discussed. [ABSTRACT FROM AUTHOR]

This paper studies the drive-response synchronization for quaternion-valued shunting inhibitory cellular neural networks (QVSICNNs) with mixed delays. First, QVSICNN is decomposed into an equivalent real-valued system in order to avoid the non-commutativity of the multiplicity. Then, the existence of almost periodic solutions is obtained based on the Banach fixed point theorem. An novel state-feedback controller is designed to ensure the global exponential almost periodic synchronization. At the end of the paper, an example is given to illustrate the effectiveness of the obtained results. [ABSTRACT FROM AUTHOR]

China’s fast economic growth contributes to the rapid development of its urbanization process, and also renders a series of industrial accidents, which often cause loss of life, damage to property and environment, thus requiring the associated risk analysis and safety control measures to be implemented in advance. However, incompleteness of historical failure data before the occurrence of accidents makes it difficult to use traditional risk analysis approaches such as probabilistic risk analysis in many cases. This paper aims to develop a new methodology capable of assessing regional industrial safety (RIS) in an uncertain environment. A hierarchical structure for modelling the risks influencing RIS is first constructed. The hybrid of evidential reasoning (ER) and Analytical Hierarchy Process (AHP) is then used to assess the risks in a complementary way, in which AHP is hired to evaluate the weight of each risk factor and ER is employed to synthesise the safety evaluations of the investigated region(s) against the risk factors from the bottom to the top level in the hierarchy. The successful application of the hybrid approach in a real case analysis of RIS in several major districts of Beijing (capital of China) demonstrates its feasibility as well as provides risk analysts and safety engineers with useful insights on effective solutions to comprehensive risk assessment of RIS in metropolitan cities. The contribution of this paper is made by the findings on the comparison of risk levels of RIS at different regions against various risk factors so that best practices from the good performer(s) can be used to improve the safety of the others. [ABSTRACT FROM AUTHOR]

Machine Learning (ML) methods have been proposed in the academic literature as alternatives to statistical ones for time series forecasting. Yet, scant evidence is available about their relative performance in terms of accuracy and computational requirements. The purpose of this paper is to evaluate such performance across multiple forecasting horizons using a large subset of 1045 monthly time series used in the M3 Competition. After comparing the post-sample accuracy of popular ML methods with that of eight traditional statistical ones, we found that the former are dominated across both accuracy measures used and for all forecasting horizons examined. Moreover, we observed that their computational requirements are considerably greater than those of statistical methods. The paper discusses the results, explains why the accuracy of ML models is below that of statistical ones and proposes some possible ways forward. The empirical results found in our research stress the need for objective and unbiased ways to test the performance of forecasting methods that can be achieved through sizable and open competitions allowing meaningful comparisons and definite conclusions. [ABSTRACT FROM AUTHOR]

In developing nations, many expanding cities are facing challenges that result from the overwhelming numbers of people and vehicles. Collecting real-time, reliable and precise traffic flow information is crucial for urban traffic management. The main purpose of this paper is to develop an adaptive model that can assess the real-time vehicle counts on urban roads using computer vision technologies. This paper proposes an automatic real-time background update algorithm for vehicle detection and an adaptive pattern for vehicle counting based on the virtual loop and detection line methods. In addition, a new robust detection method is introduced to monitor the real-time traffic congestion state of road section. A prototype system has been developed and installed on an urban road for testing. The results show that the system is robust, with a real-time counting accuracy exceeding 99% in most field scenarios. [ABSTRACT FROM AUTHOR]

This paper aims to optimize a desirable fare structure for the public transit service along a bus-subway corridor with the consideration of those factors related to equity in trip, including travel distance and comfort level. The travel distance factor is represented by the distance-based fare strategy, which is an existing differential strategy. The comfort level one is considered in the area-based fare strategy which is a new differential strategy defined in this paper. Both factors are referred to by the combined fare strategy which is composed of distance-based and area-based fare strategies. The flat fare strategy is applied to determine a reference level of social welfare and obtain the general passenger flow along transit lines, which is used to divide areas or zones along the corridor. This problem is formulated as a bi-level program, of which the upper level maximizes the social welfare and the lower level capturing traveler choice behavior is a variable-demand stochastic user equilibrium assignment model. A genetic algorithm is applied to solve the bi-level program while the method of successive averages is adopted to solve the lower-level model. A series of numerical experiments are carried out to illustrate the performance of the models and solution methods. Numerical results indicate that all three differential fare strategies play a better role in enhancing the social welfare than the flat fare strategy and that the fare structure under the combined fare strategy generates the highest social welfare and the largest resulting passenger demand, which implies that the more equity factors a differential fare strategy involves the more desirable fare structure the strategy has. [ABSTRACT FROM AUTHOR]

In this paper, new Network Data Envelopment Analysis (NDEA) models are developed to evaluate the efficiency of regional electricity power networks. The primary objective of this paper is to consider perturbation in data and develop new NDEA models based on the adaptation of robust optimization methodology. Furthermore, in this paper, the efficiency of the entire networks of electricity power, involving generation, transmission and distribution stages is measured. While DEA has been widely used to evaluate the efficiency of the components of electricity power networks during the past two decades, there is no study to evaluate the efficiency of the electricity power networks as a whole. The proposed models are applied to evaluate the efficiency of 16 regional electricity power networks in Iran and the effect of data uncertainty is also investigated. The results are compared with the traditional network DEA and parametric SFA methods. Validity and verification of the proposed models are also investigated. The preliminary results indicate that the proposed models were more reliable than the traditional Network DEA model. [ABSTRACT FROM AUTHOR]

With the development of computer network bandwidth, packet classification algorithms which are able to deal with large-scale rule sets are in urgent need. Among the existing algorithms, researches on packet classification algorithms based on hierarchical trie have become an important packet classification research branch because of their widely practical use. Although hierarchical trie is beneficial to save large storage space, it has several shortcomings such as the existence of backtracking and empty nodes. This paper proposes a new packet classification algorithm, Hierarchical Trie Algorithm Based on Expectation-Maximization Clustering (HTEMC). Firstly, this paper uses the formalization method to deal with the packet classification problem by means of mapping the rules and data packets into a two-dimensional space. Secondly, this paper uses expectation-maximization algorithm to cluster the rules based on their aggregate characteristics, and thereby diversified clusters are formed. Thirdly, this paper proposes a hierarchical trie based on the results of expectation-maximization clustering. Finally, this paper respectively conducts simulation experiments and real-environment experiments to compare the performances of our algorithm with other typical algorithms, and analyzes the results of the experiments. The hierarchical trie structure in our algorithm not only adopts trie path compression to eliminate backtracking, but also solves the problem of low efficiency of trie updates, which greatly improves the performance of the algorithm. [ABSTRACT FROM AUTHOR]

Stochastic link capacity degradations are common phenomena in transport network which can cause travel time variations and further can affect travelers’ daily route choice behaviors. This paper formulates a deterministic dynamic model, to capture the day-to-day (DTD) flow evolution process in the presence of degraded link capacity degradations. The aggregated network flow dynamics are driven by travelers’ study of uncertain travel time and their choice of risky routes. This paper applies the exponential-smoothing filter to describe travelers’ study of travel time variations, and meanwhile formulates risk attitude parameter updating equation to reflect travelers’ endogenous risk attitude evolution schema. In addition, this paper conducts theoretical analyses to investigate several significant mathematical characteristics implied in the proposed DTD model, including fixed point existence, uniqueness, stability and irreversibility. Numerical experiments are used to demonstrate the effectiveness of the DTD model and verify some important dynamic system properties. [ABSTRACT FROM AUTHOR]

An extreme learning machine (ELM) is a novel training method for single-hidden layer feedforward neural networks (SLFNs) in which the hidden nodes are randomly assigned and fixed without iterative tuning. ELMs have earned widespread global interest due to their fast learning speed, satisfactory generalization ability and ease of implementation. In this paper, we extend this theory to hypercomplex space and attempt to simultaneously consider multisource information using a hypercomplex representation. To illustrate the performance of the proposed hypercomplex extreme learning machine (HELM), we have applied this scheme to the task of multispectral palmprint recognition. Images from different spectral bands are utilized to construct the hypercomplex space. Extensive experiments conducted on the PolyU and CASIA multispectral databases demonstrate that the HELM scheme can achieve competitive results. The source code together with datasets involved in this paper can be available for free download at . [ABSTRACT FROM AUTHOR]

This paper addresses the problem of energy management of mixed criticality applications in a multi-core partitioned architecture. Instead of focusing on new scheduling algorithms to adjust frequency in order to save energy, we propose a partition to CPU allocation that takes into account not only the different frequencies at which the CPU can operate but the level of criticality of the partitions. The goal is to provide a set of pre-calculated allocations, called profiles, so at run time the system can switch to different modes depending on the battery level. These profiles achieve different levels of energy saving and performance applying different strategies. We also present a comparison in terms of energy saving of the most used bin-packing algorithms for partition allocation. As this is an heuristic, it is not possible to ensure that our results involve the minimum energy consumption. For this reason, we also provide a comparison with a exact method, such as constraint programming. [ABSTRACT FROM AUTHOR]

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]

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]

Diabetic retinopathy (DR) is a disease which is widely diagnosed using (colour fundus) images. Efficiency and accuracy are critical in diagnosing DR as lack of timely intervention can lead to irreversible visual impairment. In this paper, we examine strategies for scrutinizing images which affect diagnostic performance of medical practitioners via an eye-tracking study. A total of 56 subjects with 0 to 18 years of experience participated in the study. Every subject was asked to detect DR from 40 images. The findings indicate that practitioners use mainly two types of strategies characterized by either higher dwell duration or longer track length. The main findings of the study are that higher dwell-based strategy led to higher average accuracy (> 85%) in diagnosis, irrespective of the expertise of practitioner; whereas, the average obtained accuracy with a long-track length-based strategy was dependent on the expertise of the practitioner. In the second part of the paper, we use the experimental findings to recommend a scanning strategy for fast and accurate diagnosis of DR that can be potentially used by image readers. This is derived by combining the eye-tracking gaze maps of medical experts in a novel manner based on a set of rules. This strategy requires scrutiny of images in a manner which is consistent with spatial preferences found in human perception in general and in the domain of fundus images in particular. The Levenshtein distance-based assessment of gaze patterns also establish the effectiveness of the derived scanning pattern and is thus recommended for image readers. [ABSTRACT FROM AUTHOR]

This paper develops a new machine vision framework for efficient detection and classification of manufacturing defects in metal boxes. Previous techniques, which are based on either visual inspection or on hand-crafted features, are both inaccurate and time consuming. In this paper, we show that by using autoencoder deep neural network (DNN) architecture, we are able to not only classify manufacturing defects, but also localize them with high accuracy. Compared to traditional techniques, DNNs are able to learn, in a supervised manner, the visual features that achieve the best performance. Our experiments on a database of real images demonstrate that our approach overcomes the state-of-the-art while remaining computationally competitive. [ABSTRACT FROM AUTHOR]

In the existing centralized location services system structure, the server is easily attracted and be the communication bottleneck. It caused the disclosure of users’ location. For this, we presented a new distributed collaborative recommendation strategy that is based on the distributed system. In this strategy, each node establishes profiles of their own location information. When requests for location services appear, the user can obtain the corresponding location services according to the recommendation of the neighboring users’ location information profiles. If no suitable recommended location service results are obtained, then the user can send a service request to the server according to the construction of a k-anonymous data set with a centroid position of the neighbors. In this strategy, we designed a new model of distributed collaborative recommendation location service based on the users’ location information profiles and used generalization and encryption to ensure the safety of the user’s location information privacy. Finally, we used the real location data set to make theoretical and experimental analysis. And the results show that the strategy proposed in this paper is capable of reducing the frequency of access to the location server, providing better location services and protecting better the user’s location privacy. [ABSTRACT FROM AUTHOR]

Product aspect recognition is a key task in fine-grained opinion mining. Current methods primarily focus on the extraction of aspects from the product reviews. However, it is also important to cluster synonymous extracted aspects into the same category. In this paper, we focus on the problem of product aspect clustering. The primary challenge is to properly cluster and generalize aspects that have similar meanings but different representations. To address this problem, we learn two types of background knowledge for each extracted aspect based on two types of effective aspect relations: relevant aspect relations and irrelevant aspect relations, which describe two different types of relationships between two aspects. Based on these two types of relationships, we can assign many relevant and irrelevant aspects into two different sets as the background knowledge to describe each product aspect. To obtain abundant background knowledge for each product aspect, we can enrich the available information with background knowledge from the Web. Then, we design a hierarchical clustering algorithm to cluster these aspects into different groups, in which aspect similarity is computed using the relevant and irrelevant aspect sets for each product aspect. Experimental results obtained in both camera and mobile phone domains demonstrate that the proposed product aspect clustering method based on two types of background knowledge performs better than the baseline approach without the use of background knowledge. Moreover, the experimental results also indicate that expanding the available background knowledge using the Web is feasible. [ABSTRACT FROM AUTHOR]

This paper provides a description of how market competitiveness evaluations concerning mechanical equipment can be made in the context of multi-criteria decision environments. It is assumed that, when we are evaluating the market competitiveness, there are limited number of candidates with some required qualifications, and the alternatives will be pairwise compared on a ratio scale. The qualifications are depicted as criteria in hierarchical structure. A hierarchical decision model called PCbHDM was used in this study based on an analysis of its desirable traits. Illustration and comparison shows that the PCbHDM provides a convenient and effective tool for evaluating the market competitiveness of mechanical equipment. The researchers and practitioners might use findings of this paper in application of PCbHDM. [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]

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]

In this paper we compare systematically the most promising neuroevolutionary methods and two new original methods on the double-pole balancing problem with respect to: the ability to discover solutions that are robust to variations of the environment, the speed with which such solutions are found, and the ability to scale-up to more complex versions of the problem. The results indicate that the two original methods introduced in this paper and the Exponential Natural Evolutionary Strategy method largely outperform the other methods with respect to all considered criteria. The results collected in different experimental conditions also reveal the importance of regulating the selective pressure and the importance of exposing evolving agents to variable environmental conditions. The data collected and the results of the comparisons are used to identify the most effective methods and the most promising research directions. [ABSTRACT FROM AUTHOR]

This paper addresses a chaos kernel function for the relevance vector machine (RVM) in EEG signal classification, which is an important component of Brain-Computer Interface (BCI). The novel kernel function has evolved from a chaotic system, which is inspired by the fact that human brain signals depict some chaotic characteristics and behaviors. By introducing the chaotic dynamics to the kernel function, the RVM will be enabled for higher classification capacity. The proposed method is validated within the framework of one versus one common spatial pattern (OVO-CSP) classifier to classify motor imagination (MI) of four movements in a public accessible dataset. To illustrate the performance of the proposed kernel function, Gaussian and Polynomial kernel functions are considered for comparison. Experimental results show that the proposed kernel function achieved higher accuracy than Gaussian and Polynomial kernel functions, which shows that the chaotic behavior consideration is helpful in the EEG signal classification. [ABSTRACT FROM AUTHOR]

Aiming to solve the safety problems of high-speed railway operation and management, one new method is urgently needed to construct on the basis of the rough set theory and the uncertainty measurement theory. The method should carefully consider every factor of high-speed railway operation that realizes the measurement indexes of its safety operation. After analyzing the factors that influence high-speed railway safety operation in detail, a rough measurement model is finally constructed to describe the operation process. Based on the above considerations, this paper redistricts the safety influence factors of high-speed railway operation as 16 measurement indexes which include staff index, vehicle index, equipment index and environment. And the paper also provides another reasonable and effective theoretical method to solve the safety problems of multiple attribute measurement in high-speed railway operation. As while as analyzing the operation data of 10 pivotal railway lines in China, this paper respectively uses the rough set-based measurement model and value function model (one model for calculating the safety value) for calculating the operation safety value. The calculation result shows that the curve of safety value with the proposed method has smaller error and greater stability than the value function method’s, which verifies the feasibility and effectiveness. [ABSTRACT FROM AUTHOR]

In business replenishment, discount offers of multi-item may either provide different discount schedules with a single discount type, or provide schedules with multiple discount types. The paper investigates the joint effects of multiple discount schemes on the decisions of multi-item joint replenishment. In this paper, a joint replenishment problem (JRP) model, considering three discount (all-unit discount, incremental discount, total volume discount) offers simultaneously, is constructed to determine the basic cycle time and joint replenishment frequencies of multi-item. To solve the proposed problem, a heuristic algorithm is proposed to find the optimal solutions and the corresponding total cost of the JRP model. Numerical experiment is performed to test the algorithm and the computational results of JRPs under different discount combinations show different significance in the replenishment cost reduction. [ABSTRACT FROM AUTHOR]

This paper presents an integrated hybrid optimization algorithm for training the radial basis function neural network (RBF NN). Training of neural networks is still a challenging exercise in machine learning domain. Traditional training algorithms in general suffer and trap in local optima and lead to premature convergence, which makes them ineffective when applied for datasets with diverse features. Training algorithms based on evolutionary computations are becoming popular due to their robust nature in overcoming the drawbacks of the traditional algorithms. Accordingly, this paper proposes a hybrid training procedure with differential search (DS) algorithm functionally integrated with the particle swarm optimization (PSO). To surmount the local trapping of the search procedure, a new population initialization scheme is proposed using Logistic chaotic sequence, which enhances the population diversity and aid the search capability. To demonstrate the effectiveness of the proposed RBF hybrid training algorithm, experimental analysis on publicly available 7 benchmark datasets are performed. Subsequently, experiments were conducted on a practical application case for wind speed prediction to expound the superiority of the proposed RBF training algorithm in terms of prediction accuracy. [ABSTRACT FROM AUTHOR]

Data gathering is a fundamental task in Wireless Visual Sensor Networks (WVSNs). Features of directional antennas and the visual data make WVSNs more complex than the conventional Wireless Sensor Network (WSN). The virtual backbone is a technique, which is capable of constructing clusters. The version associating with the aggregation operation is also referred to as the virtual backbone tree. In most of the existing literature, the main focus is on the efficiency brought by the construction of clusters that the existing methods neglect local-balance problems in general. To fill up this gap, Directional Virtual Backbone based Data Aggregation Scheme (DVBDAS) for the WVSNs is proposed in this paper. In addition, a measurement called the energy consumption density is proposed for evaluating the adequacy of results in the cluster-based construction problems. Moreover, the directional virtual backbone construction scheme is proposed by considering the local-balanced factor. Furthermore, the associated network coding mechanism is utilized to construct DVBDAS. Finally, both the theoretical analysis of the proposed DVBDAS and the simulations are given for evaluating the performance. The experimental results prove that the proposed DVBDAS achieves higher performance in terms of both the energy preservation and the network lifetime extension than the existing methods. [ABSTRACT FROM AUTHOR]

Public transport (PT) is a key element in most major cities around the world. With the development of smartphones, available journey planning information is becoming an integral part of the PT system. Each traveler has specific preferences when undertaking a trip, and these preferences can also be reflected on the smartphone. This paper considers transit assignment in urban public-transport networks in which the passengers receive smartphone-based information containing elements that might influence the travel decisions in relation to line loads, as well as passenger benefits, and the paper discusses the transition from the current widespread choosing approach to a personalized decision-making approach based on smartphone information. The approach associated with smartphone guidance that considers passengers’ preference on travel time, waiting time and transfer is proposed in the process of obtaining his/her preferred route from the potential travel routes generated by the Deep First Search (DFS) method. Two other approaches, based on the scenarios reflecting reality, include passengers with access to no real time information, and passengers that only have access to the arrival time at the platform are used as comparisons. For illustration, the same network proposed by Spiess and Florian is utilized on the experiments in an agent-based model. Two experiments are conducted respectively according to whether each passenger’s choosing method is consistent. As expected, the results in the first experiment showed that the travel for consistent passengers with smartphone guidance was clearly shorter and that it can reduce travel time exceeding 15% and weighted cost exceeding 20%, and the average saved time approximated 3.88 minutes per passenger. The second experiment presented that travel cost, as well as cost savings, gradually decreased by employing smartphone guidance, and the maximum cost savings accounted for 14.2% of the total weighted cost. [ABSTRACT FROM AUTHOR]

Pruning is applied in order to combat over-fitting problem where the tree is pruned back with the goal of identifying decision tree with the lowest error rate on previously unobserved instances, breaking ties in favour of smaller trees with high accuracy. In this paper, pruning with Bayes minimum risk is introduced for estimating the risk-rate. This method proceeds in a bottom-up fashion converting a parent node of a subtree to a leaf node if the estimated risk-rate of the parent node for that subtree is less than the risk-rates of its leaf. This paper proposes a post-pruning method that considers various evaluation standards such as attribute selection, accuracy, tree complexity, and time taken to prune the tree, precision/recall scores, TP/FN rates and area under ROC. The experimental results show that the proposed method produces better classification accuracy and its complexity is not much different than the complexities of reduced-error pruning and minimum-error pruning approaches. The experiments also demonstrate that the proposed method shows satisfactory performance in terms of precision score, recall score, TP rate, FP rate and area under ROC. [ABSTRACT FROM AUTHOR]

Human-computer interface systems whose input is based on eye movements can serve as a means of communication for patients with locked-in syndrome. Eye-writing is one such system; users can input characters by moving their eyes to follow the lines of the strokes corresponding to characters. Although this input method makes it easy for patients to get started because of their familiarity with handwriting, existing eye-writing systems suffer from slow input rates because they require a pause between input characters to simplify the automatic recognition process. In this paper, we propose a continuous eye-writing recognition system that achieves a rapid input rate because it accepts characters eye-written continuously, with no pauses. For recognition purposes, the proposed system first detects eye movements using electrooculography (EOG), and then a hidden Markov model (HMM) is applied to model the EOG signals and recognize the eye-written characters. Additionally, this paper investigates an EOG adaptation that uses a deep neural network (DNN)-based HMM. Experiments with six participants showed an average input speed of 27.9 character/min using Japanese Katakana as the input target characters. A Katakana character-recognition error rate of only 5.0% was achieved using 13.8 minutes of adaptation data. [ABSTRACT FROM AUTHOR]

The selection of seismic attributes is a key process in reservoir prediction because the prediction accuracy relies on the reliability and credibility of the seismic attributes. However, effective selection method for useful seismic attributes is still a challenge. This paper presents a novel selection method of seismic attributes for reservoir prediction based on the gray relational degree (GRD) and support vector machine (SVM). The proposed method has a two-hierarchical structure. In the first hierarchy, the primary selection of seismic attributes is achieved by calculating the GRD between seismic attributes and reservoir parameters, and the GRD between the seismic attributes. The principle of the primary selection is that these seismic attributes with higher GRD to the reservoir parameters will have smaller GRD between themselves as compared to those with lower GRD to the reservoir parameters. Then the SVM is employed in the second hierarchy to perform an interactive error verification using training samples for the purpose of determining the final seismic attributes. A real-world case study was conducted to evaluate the proposed GRD-SVM method. Reliable seismic attributes were selected to predict the coalbed methane (CBM) content in southern Qinshui basin, China. In the analysis, the instantaneous amplitude, instantaneous bandwidth, instantaneous frequency, and minimum negative curvature were selected, and the predicted CBM content was fundamentally consistent with the measured CBM content. This real-world case study demonstrates that the proposed method is able to effectively select seismic attributes, and improve the prediction accuracy. Thus, the proposed GRD-SVM method can be used for the selection of seismic attributes in practice. [ABSTRACT FROM AUTHOR]

Traffic surveillance systems are interesting to many researchers to improve the traffic control and reduce the risk caused by accidents. In this area, many published works are only concerned about vehicle detection in normal conditions. The camera may vibrate due to wind or bridge movement. Detection and tracking of vehicles is a very difficult task when we have bad weather conditions in winter (snowy, rainy, windy, etc.), dusty weather in arid and semi-arid regions, at night, etc. Also, it is very important to consider speed of vehicles in the complicated weather condition. In this paper, we improved our method to track and count vehicles in dusty weather with vibrating camera. For this purpose, we used a background subtraction based strategy mixed with an extra processing to segment vehicles. In this paper, the extra processing included the analysis of the headlight size, location, and area. In our work, tracking was done between consecutive frames via a generalized particle filter to detect the vehicle and pair the headlights using the connected component analysis. So, vehicle counting was performed based on the pairing result, with Centroid of each blob we calculated distance between two frames by simple formula and hence dividing it by the time between two frames obtained from the video. Our proposed method was tested on several video surveillance records in different conditions such as dusty or foggy weather, vibrating camera, and in roads with medium-level traffic volumes. The results showed that the new proposed method performed better than our previously published method and other methods, including the Kalman filter or Gaussian model, in different traffic conditions. [ABSTRACT FROM AUTHOR]

Authorship attribution is to identify the most likely author of a given sample among a set of candidate known authors. It can be not only applied to discover the original author of plain text, such as novels, blogs, emails, posts etc., but also used to identify source code programmers. Authorship attribution of source code is required in diverse applications, ranging from malicious code tracking to solving authorship dispute or software plagiarism detection. This paper aims to propose a new method to identify the programmer of Java source code samples with a higher accuracy. To this end, it first introduces back propagation (BP) neural network based on particle swarm optimization (PSO) into authorship attribution of source code. It begins by computing a set of defined feature metrics, including lexical and layout metrics, structure and syntax metrics, totally 19 dimensions. Then these metrics are input to neural network for supervised learning, the weights of which are output by PSO and BP hybrid algorithm. The effectiveness of the proposed method is evaluated on a collected dataset with 3,022 Java files belong to 40 authors. Experiment results show that the proposed method achieves 91.060% accuracy. And a comparison with previous work on authorship attribution of source code for Java language illustrates that this proposed method outperforms others overall, also with an acceptable overhead. [ABSTRACT FROM AUTHOR]

This paper studies the problem of the restoration of images corrupted by mixed Gaussian-impulse noise. In recent years, low-rank matrix reconstruction has become a research hotspot in many scientific and engineering domains such as machine learning, image processing, computer vision and bioinformatics, which mainly involves the problem of matrix completion and robust principal component analysis, namely recovering a low-rank matrix from an incomplete but accurate sampling subset of its entries and from an observed data matrix with an unknown fraction of its entries being arbitrarily corrupted, respectively. Inspired by these ideas, we consider the problem of recovering a low-rank matrix from an incomplete sampling subset of its entries with an unknown fraction of the samplings contaminated by arbitrary errors, which is defined as the problem of matrix completion from corrupted samplings and modeled as a convex optimization problem that minimizes a combination of the nuclear norm and the -norm in this paper. Meanwhile, we put forward a novel and effective algorithm called augmented Lagrange multipliers to exactly solve the problem. For mixed Gaussian-impulse noise removal, we regard it as the problem of matrix completion from corrupted samplings, and restore the noisy image following an impulse-detecting procedure. Compared with some existing methods for mixed noise removal, the recovery quality performance of our method is dominant if images possess low-rank features such as geometrically regular textures and similar structured contents; especially when the density of impulse noise is relatively high and the variance of Gaussian noise is small, our method can outperform the traditional methods significantly not only in the simultaneous removal of Gaussian noise and impulse noise, and the restoration ability for a low-rank image matrix, but also in the preservation of textures and details in the image. [ABSTRACT FROM AUTHOR]

Approximate string matching with k-differences has a number of practical applications, ranging from pattern recognition to computational biology. This paper proposes an efficient memory-access algorithm for parallel approximate string matching with k-differences on Graphics Processing Units (GPUs). In the proposed algorithm, all threads in the same GPUs warp share data using warp-shuffle operation instead of accessing the shared memory. Moreover, we implement the proposed algorithm by exploiting the memory structure of GPUs to optimize its performance. Experiment results for real DNA packages revealed that the performance of the proposed algorithm and its implementation archived up to 122.64 and 1.53 times compared to that of sequential algorithm on CPU and previous parallel approximate string matching algorithm on GPUs, respectively. [ABSTRACT FROM AUTHOR]

With the rapid development of the Metro network in China, the greatly increased route alternatives make passengers’ route choice behavior and passenger flow assignment more complicated, which presents challenges to the operation management. In this paper, a path sized logit model is adopted to analyze passengers’ route choice preferences considering such parameters as in-vehicle time, number of transfers, and transfer time. Moreover, the “perceived transfer threshold” is defined and included in the utility function to reflect the penalty difference caused by transfer time on passengers’ perceived utility under various numbers of transfers. Next, based on the revealed preference data collected in the Guangzhou Metro, the proposed model is calibrated. The appropriate perceived transfer threshold value and the route choice preferences are analyzed. Finally, the model is applied to a personalized route planning case to demonstrate the engineering practicability of route choice behavior analysis. The results show that the introduction of the perceived transfer threshold is helpful to improve the model’s explanatory abilities. In addition, personalized route planning based on route choice preferences can meet passengers’ diversified travel demands. [ABSTRACT FROM AUTHOR]

Urban spaces have a great impact on how people’s emotion and behaviour. There are number of factors that impact our brain responses to a space. This paper presents a novel urban place recommendation approach, that is based on modelling in-situ EEG data. The research investigations leverages on newly affordable Electroencephalogram (EEG) headsets, which has the capability to sense mental states such as meditation and attention levels. These emerging devices have been utilized in understanding how human brains are affected by the surrounding built environments and natural spaces. In this paper, mobile EEG headsets have been used to detect mental states at different types of urban places. By analysing and modelling brain activity data, we were able to classify three different places according to the mental state signature of the users, and create an association map to guide and recommend people to therapeutic places that lessen brain fatigue and increase mental rejuvenation. Our mental states classifier has achieved accuracy of (%90.8). NeuroPlace breaks new ground not only as a mobile ubiquitous brain monitoring system for urban computing, but also as a system that can advise urban planners on the impact of specific urban planning policies and structures. We present and discuss the challenges in making our initial prototype more practical, robust, and reliable as part of our on-going research. In addition, we present some enabling applications using the proposed architecture. [ABSTRACT FROM AUTHOR]

Introducing electric vehicles (EVs) into urban transportation network brings higher requirement on travel time reliability and charging reliability. Specifically, it is believed that travel time reliability is a key factor influencing travelers’ route choice. Meanwhile, due to the limited cruising range, EV drivers need to better learn about the required energy for the whole trip to make decisions about whether charging or not and where to charge (i.e., charging reliability). Since EV energy consumption is highly related to travel speed, network uncertainty affects travel time and charging demand estimation significantly. Considering the network uncertainty resulted from link degradation, which influences the distribution of travel demand on transportation network and the energy demand on power network, this paper aims to develop a reliability-based network equilibrium framework for accommodating degradable road conditions with the addition of EVs. First, based on the link travel time distribution, the mean and variance of route travel time and monetary expenses related to energy consumption are deduced, respectively. And the charging time distribution of EVs with charging demand is also estimated. Then, a nested structure is considered to deal with the difference of route choice behavior derived by the different uncertainty degrees between the routes with and without degradable links. Given the expected generalized travel cost and a psychological safety margin, a traffic assignment model with the addition of EVs is formulated. Subsequently, a heuristic solution algorithm is developed to solve the proposed model. Finally, the effects of travelers’ risk attitude, network degradation degree, and EV penetration rate on network performance are illustrated through an example network. The numerical results show that the difference of travelers’ risk attitudes does have impact on the route choice, and the widespread adoption of EVs can cut down the total system travel cost effectively when the transportation network is more reliable. [ABSTRACT FROM AUTHOR]

This paper presents the use of the Aimsun microsimulation program to simulate vehicle violating behaviors and observe their impact on road traffic crash risk. Plugins for violations of speeding, slow driving, and abrupt stopping were developed using Aimsun’s API and SDK module. A safety analysis plugin for investigating probability of rear-end collisions was developed, and a method for analyzing collision risk is proposed. A Fuzzy C-mean Clustering algorithm was developed to identify high risk states in different road segments over time. Results of a simulation experiment based on the G15 Expressway in Shanghai showed that abrupt stopping had the greatest impact on increasing collision risk, and the impact of violations increased with traffic volume. The methodology allows for the evaluation and monitoring of risks, alerting of road hazards, and identification of hotspots, and could be applied to the operations of existing facilities or planning of future ones. [ABSTRACT FROM AUTHOR]

Recently, echo state network (ESN) has attracted a great deal of attention due to its high accuracy and efficient learning performance. Compared with the traditional random structure and classical sigmoid units, simple circle topology and leaky integrator neurons have more advantages on reservoir computing of ESN. In this paper, we propose a new model of ESN with both circle reservoir structure and leaky integrator units. By comparing the prediction capability on Mackey-Glass chaotic time series of four ESN models: classical ESN, circle ESN, traditional leaky integrator ESN, circle leaky integrator ESN, we find that our circle leaky integrator ESN shows significantly better performance than other ESNs with roughly 2 orders of magnitude reduction of the predictive error. Moreover, this model has stronger ability to approximate nonlinear dynamics and resist noise than conventional ESN and ESN with only simple circle structure or leaky integrator neurons. Our results show that the combination of circle topology and leaky integrator neurons can remarkably increase dynamical diversity and meanwhile decrease the correlation of reservoir states, which contribute to the significant improvement of computational performance of Echo state network on time series prediction. [ABSTRACT FROM AUTHOR]

Wireless Sensor Networks (WSNs) are becoming ubiquitous in everyday life due to their applications in weather forecasting, surveillance, implantable sensors for health monitoring and other plethora of applications. WSN is equipped with hundreds and thousands of small sensor nodes. As the size of a sensor node decreases, critical issues such as limited energy, computation time and limited memory become even more highlighted. In such a case, network lifetime mainly depends on efficient use of available resources. Organizing nearby nodes into clusters make it convenient to efficiently manage each cluster as well as the overall network. In this paper, we extend our previous work of grid-based hybrid network deployment approach, in which merge and split technique has been proposed to construct network topology. Constructing topology through our proposed technique, in this paper we have used analytical network process (ANP) model for cluster head selection in WSN. Five distinct parameters: distance from nodes (DistNode), residual energy level (REL), distance from centroid (DistCent), number of times the node has been selected as cluster head (TCH) and merged node (MN) are considered for CH selection. The problem of CH selection based on these parameters is tackled as a multi criteria decision system, for which ANP method is used for optimum cluster head selection. Main contribution of this work is to check the applicability of ANP model for cluster head selection in WSN. In addition, sensitivity analysis is carried out to check the stability of alternatives (available candidate nodes) and their ranking for different scenarios. The simulation results show that the proposed method outperforms existing energy efficient clustering protocols in terms of optimum CH selection and minimizing CH reselection process that results in extending overall network lifetime. This paper analyzes that ANP method used for CH selection with better understanding of the dependencies of different components involved in the evaluation process. [ABSTRACT FROM AUTHOR]

Vision-based vehicle detection is an important issue for advanced driver assistance systems. In this paper, we presented an improved multi-vehicle detection and tracking method using cascade Adaboost and Adaptive Kalman filter(AKF) with target identity awareness. A cascade Adaboost classifier using Haar-like features was built for vehicle detection, followed by a more comprehensive verification process which could refine the vehicle hypothesis in terms of both location and dimension. In vehicle tracking, each vehicle was tracked with independent identity by an Adaptive Kalman filter in collaboration with a data association approach. The AKF adaptively adjusted the measurement and process noise covariance through on-line stochastic modelling to compensate the dynamics changes. The data association correctly assigned different detections with tracks using global nearest neighbour(GNN) algorithm while considering the local validation. During tracking, a temporal context based track management was proposed to decide whether to initiate, maintain or terminate the tracks of different objects, thus suppressing the sparse false alarms and compensating the temporary detection failures. Finally, the proposed method was tested on various challenging real roads, and the experimental results showed that the vehicle detection performance was greatly improved with higher accuracy and robustness. [ABSTRACT FROM AUTHOR]

Among Parkinson’s disease (PD) symptoms, freezing of gait (FoG) is one of the most debilitating. To assess FoG, current clinical practice mostly employs repeated evaluations over weeks and months based on questionnaires, which may not accurately map the severity of this symptom. The use of a non-invasive system to monitor the activities of daily living (ADL) and the PD symptoms experienced by patients throughout the day could provide a more accurate and objective evaluation of FoG in order to better understand the evolution of the disease and allow for a more informed decision-making process in making adjustments to the patient’s treatment plan. This paper presents a new algorithm to detect FoG with a machine learning approach based on Support Vector Machines (SVM) and a single tri-axial accelerometer worn at the waist. The method is evaluated through the acceleration signals in an outpatient setting gathered from 21 PD patients at their home and evaluated under two different conditions: first, a generic model is tested by using a leave-one-out approach and, second, a personalised model that also uses part of the dataset from each patient. Results show a significant improvement in the accuracy of the personalised model compared to the generic model, showing enhancement in the specificity and sensitivity geometric mean (GM) of 7.2%. Furthermore, the SVM approach adopted has been compared to the most comprehensive FoG detection method currently in use (referred to as MBFA in this paper). Results of our novel generic method provide an enhancement of 11.2% in the GM compared to the MBFA generic model and, in the case of the personalised model, a 10% of improvement with respect to the MBFA personalised model. Thus, our results show that a machine learning approach can be used to monitor FoG during the daily life of PD patients and, furthermore, personalised models for FoG detection can be used to improve monitoring accuracy. [ABSTRACT FROM AUTHOR]

This paper proposed a method to update the on-line health reference baseline of the On-Board Engine Model (OBEM) to maintain the effectiveness of an in-flight aircraft sensor Fault Detection and Isolation (FDI) system, in which a Hybrid Kalman Filter (HKF) was incorporated. Generated from a rapid in-flight engine degradation, a large health condition mismatch between the engine and the OBEM can corrupt the performance of the FDI. Therefore, it is necessary to update the OBEM online when a rapid degradation occurs, but the FDI system will lose estimation accuracy if the estimation and update are running simultaneously. To solve this problem, the health reference baseline for a nonlinear OBEM was updated using the proposed channel controller method. Simulations based on the turbojet engine Linear-Parameter Varying (LPV) model demonstrated the effectiveness of the proposed FDI system in the presence of substantial degradation, and the channel controller can ensure that the update process finishes without interference from a single sensor fault. [ABSTRACT FROM AUTHOR]

A Mesh topology is one of the most promising architecture due to its regular and simple structure for on-chip communication. Performance of mesh topology degraded greatly by increasing the network size due to small bisection width and large network diameter. In order to overcome this limitation, many researchers presented modified Mesh design by adding some extra links to improve its performance in terms of network latency and power consumption. The Cross-By-Pass-Mesh was presented by us as an improved version of Mesh topology by intelligent addition of extra links. This paper presents an efficient topology named Cross-By-Pass-Torus for further increase in the performance of the Cross-By-Pass-Mesh topology. The proposed design merges the best features of the Cross-By-Pass-Mesh and Torus, to reduce the network diameter, minimize the average number of hops between nodes, increase the bisection width and to enhance the overall performance of the network. In this paper, the architectural design of the topology is presented and analyzed against similar kind of 2D topologies in terms of average latency, throughput and power consumption. In order to certify the actual behavior of proposed topology, the synthetic traffic trace and five different real embedded application workloads are applied to the proposed as well as other competitor network topologies. The simulation results indicate that Cross-By-Pass-Torus is an efficient candidate among its predecessor’s and competitor topologies due to its less average latency and increased throughput at a slight cost in network power and energy for on-chip communication. [ABSTRACT FROM AUTHOR]

Background: Identifying conserved regions in protein sequences is a fundamental operation, occurring in numerous sequence-driven analysis pipelines. It is used as a way to decode domain-rich regions within proteins, to compute protein clusters, to annotate sequence function, and to compute evolutionary relationships among protein sequences. A number of approaches exist for identifying and characterizing protein families based on their domains, and because domains represent conserved portions of a protein sequence, the primary computation involved in protein family characterization is identification of such conserved regions. However, identifying conserved regions from large collections (millions) of protein sequences presents significant challenges. Methods: In this paper we present a new, alignment-free method for detecting conserved regions in protein sequences called NADDA (No-Alignment Domain Detection Algorithm). Our method exploits the abundance of exact matching short subsequences (k-mers) to quickly detect conserved regions, and the power of machine learning is used to improve the prediction accuracy of detection. We present a parallel implementation of NADDA using the MapReduce framework and show that our method is highly scalable. Results: We have compared NADDA with Pfam and InterPro databases. For known domains annotated by Pfam, accuracy is 83%, sensitivity 96%, and specificity 44%. For sequences with new domains not present in the training set an average accuracy of 63% is achieved when compared to Pfam. A boost in results in comparison with InterPro demonstrates the ability of NADDA to capture conserved regions beyond those present in Pfam. We have also compared NADDA with ADDA and MKDOM2, assuming Pfam as ground-truth. On average NADDA shows comparable accuracy, more balanced sensitivity and specificity, and being alignment-free, is significantly faster. Excluding the one-time cost of training, runtimes on a single processor were 49s, 10,566s, and 456s for NADDA, ADDA, and MKDOM2, respectively, for a data set comprised of approximately 2500 sequences. [ABSTRACT FROM AUTHOR]

Traffic state estimation from the floating car system is a challenging problem. The low penetration rate and random distribution make available floating car samples usually cover part space and time points of the road networks. To obtain a wide range of traffic state from the floating car system, many methods have been proposed to estimate the traffic state for the uncovered links. However, these methods cannot provide traffic state of the entire road networks. In this paper, the traffic state estimation is transformed to solve a missing data imputation problem, and the tensor completion framework is proposed to estimate missing traffic state. A tensor is constructed to model traffic state in which observed entries are directly derived from floating car system and unobserved traffic states are modeled as missing entries of constructed tensor. The constructed traffic state tensor can represent spatial and temporal correlations of traffic data and encode the multi-way properties of traffic state. The advantage of the proposed approach is that it can fully mine and utilize the multi-dimensional inherent correlations of traffic state. We tested the proposed approach on a well calibrated simulation network. Experimental results demonstrated that the proposed approach yield reliable traffic state estimation from very sparse floating car data, particularly when dealing with the floating car penetration rate is below 1%. [ABSTRACT FROM AUTHOR]

Stock price prediction is an important and challenging problem in stock market analysis. Existing prediction methods either exploit autocorrelation of stock price and its correlation with the supply and demand of stock, or explore predictive indictors exogenous to stock market. In this paper, using transaction record of stocks with identifier of traders, we introduce an index to characterize market confidence, i.e., the ratio of the number of traders who is active in two successive trading days to the number of active traders in a certain trading day. Strong Granger causality is found between the index of market confidence and stock price. We further predict stock price by incorporating the index of market confidence into a neural network based on time series of stock price. Experimental results on 50 stocks in two Chinese Stock Exchanges demonstrate that the accuracy of stock price prediction is significantly improved by the inclusion of the market confidence index. This study sheds light on using cross-day trading behavior to characterize market confidence and to predict stock price. [ABSTRACT FROM AUTHOR]