Search

Detecting the boundaries of protein domains has been an important and challenging problem in experimental and computational structural biology. In this paper the domain detection is first taken as an imbalanced data learning problem. A novel undersampling method using distance-based maximal entropy in the feature space of SVMs is proposed. On multiple sequence alignments that are derived from a database search, multiple measures are defined to quantify the domain information content of each position along the sequence. The overall accuracy is about 87% together with high sensitivity and specificity. Simulation results demonstrate that the utility of the method can help not only in predicting the complete 3D structure of a protein but also in the machine learning system on general imbalanced datasets. [ABSTRACT FROM AUTHOR]

Provide these intelligent medical services, it is necessary to understand the situation information generated in a hospital. There should be infra technologies that can classify and control the information for processing situation data, not mere collection of conceptual information, with clear standards. This paper, as a study to seize the information generated from medical situation more clearly, understood the property of data using neural network and applied the security ratings of information so that the system to provide the user appropriate to designated rating with analyzed medical information is established. It will be an effective measure to enhance the effectiveness of medical devices and backup data already introduced and understand the various medical data that will be generated from medical devices to be introduced. [ABSTRACT FROM AUTHOR]

An edge detection method by combining image entropy and Self -Organizing Map (SOM) is proposed in this paper. First, according to information theory image entropy is used to curve up the smooth region and the region of gray level abruptly changed. Then we transform the gray level image to ideal binary pattern of pixels. We define six classes' edge and six edge prototype vectors. These edge prototype vectors are fed into input layer of the Self-Organizing Map (SOM). Classifying the type of edge through this network, the edge image is obtained. At last, the speckle edges are discarded from the edge image. Experimental results show that it gained better edge image compared with Canny edge detection method. [ABSTRACT FROM AUTHOR]

With the development of Intelligent Transport Systems (ITS), automatic license plate recognition (LPR) plays an important role in numerous applications in reality. In this paper, a coarse to fine algorithm to detect license plates in images and video frames with complex background is proposed. First, the method based on Component Connect (CC) is used to detect the possible license plate regions in the coarse detection. Second, the method based on texture analysis is applied in the fine detection. Finally, a BP Neural Network is adopted as classifier, parts of the features is selected based on statistic diagram to make the network efficient. The average accuracy of detection is 95.3% from the images with different angles and different lighting conditions. [ABSTRACT FROM AUTHOR]

In this paper, synchronization is investigated for an array of nonlinearly coupled identical connected neural networks with delay. By employing the Lyapunov functional method and the Kronecker product technique, several sufficient conditions are derived. It is shown that global exponential synchronization of the coupled neural networks is guaranteed by a suitable design of the coupling matrix, the inner linking matrix and some free matrices representing the relationships between the system matrices. The conditions obtained in this paper are in the form of linear matrix inequalities, which can be easily computed and checked in practice. A typical example with chaotic nodes is finally given to illustrate the effectiveness of the proposed synchronization scheme. [ABSTRACT FROM AUTHOR]

Of the possible interactions between human and robot, touch is an important means of providing human beings with emotional relief. However, most previous studies have focused on interactions based on voice and images. In this paper, a method of recognizing human touching behaviors is proposed for developing a robot that can naturally interact with humans through touch. In this method, the recognition process is divided into pre-process phase and recognition phase. In the pre-process phase, recognizable characteristics are calculated from the data generated by the touch detector which was fabricated using force sensors. The force sensor used an FSR (force sensing register). The recognition phase classifies human touching behaviors using a multi-layer perceptron which is a neural network model. We measured three different human touching behaviors for six men. The human touching behaviors are ‘hitting,' 'stroking,' and ‘tickling'. In the test conducted with recognizers generated for each user, the average recognition rate was 93.8%, while the test conducted with a single recognizer showed a 79.8% average recognition rate. These results show the feasibility of the proposed human touching behavior recognition method. [ABSTRACT FROM AUTHOR]

This paper investigates the construction of a wide class of singlehidden layer neural networks (SLNNs) with or without tunable parameters in the hidden nodes. It is a challenging problem if both the parameter training and determination of network size are considered simultaneously. Two alternative network construction methods are considered in this paper. Firstly, the discrete construction of SLNNs is introduced. The main objective is to select a subset of hidden nodes from a pool of candidates with parameters fixed ‘a priori'. This is called discrete construction since there are no parameters in the hidden nodes that need to be trained. The second approach is called continuous construction as all the adjustable network parameters are trained on the whole parameter space along the network construction process. In the second approach, there is no need to generate a pool of candidates, and the network grows one by one with the adjustable parameters optimized. The main contribution of this paper is to show that the network construction can be done using the above two alternative approaches, and these two approaches can be integrated within a unified analytic framework, leading to potentially significantly improved model performance and/or computational efficiency. [ABSTRACT FROM AUTHOR]

At present, most of the algorithms for learning Bayesian Networks (BNs) use EM algorithm to deal with incomplete data. They are of low efficiency because EM algorithm has to perform iterative process of probability reasoning to complete the incomplete data. In this paper we present an efficient BN learning algorithm, which use the combination of EMI method and a scoring function based on mutual information theory. The algorithm first uses EMI method to estimate, from incomplete data, probability distributions over local structures of BNs, then evaluates BN structures with the scoring function and searches for the best one. The detailed procedure of the algorithm is depicted in the paper. The experimental results on Asia and Alarm networks show that when achieving high accuracy, the algorithm is much more efficient than two EM based algorithms, SEM and EM-EA algorithms. [ABSTRACT FROM AUTHOR]

Fuzzy Petri net (FPN) is a powerful modeling tool for fuzzy production rules based knowledge systems. But it is lack of learning mechanism, which is the main weakness while modeling uncertain knowledge systems. Fuzzy neural Petri net (FNPN) is proposed in this paper, in which fuzzy neuron components are introduced into FPN as a sub-net model of FNPN. For neuron components in FNPN, back propagation (BP) learning algorithm of neural network is introduced. And the parameters of fuzzy production rules in FNPN neurons can be learnt and trained by this means. At the same time, different neurons on different layers can be learnt and trained independently. The FNPN proposed in this paper is meaningful for Petri net models and fuzzy systems. [ABSTRACT FROM AUTHOR]

Consumer demand for intelligent battery charges is increasing as portable electronic applications continue to grow. Fast charging of battery packs is a problem which is difficult, and often expensive, to solve using conventional techniques. Conventional techniques only perform a linear approximation of a nonlinear behavior of a battery packs. The battery charging is a nonlinear electrochemical dynamic process and there is no exact mathematical model of battery. Better techniques are needed when a higher degree of accuracy and minimum charging time are desired. In this paper we propose soft computing approach based on fuzzy recurrent neural networks (RFNN) training by genetic algorithms to control batteries charging process. This technique does not require mathematical model of battery packs, which are often difficult, if not impossible, to obtain. Nonlinear and uncertain dynamics of the battery pack is modeled by recurrent fuzzy neural network. On base of this FRNN model, the fuzzy control rules of the control system for battery charging is generated. Computational experiments show that the suggested approach gives least charging time and least Tend-Tstart results according to the other intelligent battery charger works. [ABSTRACT FROM AUTHOR]

In this paper we will study the naïve Bayes, one of the popular machine learning algorithms, and improve its accuracy without seriously affecting its computational efficiency. Naïve Bayes assumes positional independence, which makes the computation of the joint probability value easier at the expense of the accuracy or the underlying reality. In addition, the prior probabilities of positive and negative instances are computed from the training instances, which often do not accurately reflect the real prior probabilities. In this paper we address these two issues. We have developed algorithms that automatically perturb the computed prior probabilities and search around the neighborhood to maximize a given objective function. To improve the prediction accuracy we introduce limited dependency on the underlying pattern. We have demonstrated the importance of these extensions by applying them to solve the problem in discriminating a TATA box from putative TATA boxes found in promoter regions of plant genome. The best prediction accuracy of a naïve Bayes with 10 fold cross validation was 69% while the second extension gave the prediction accuracy of 79% which is better than the best solution from an artificial neural network prediction. [ABSTRACT FROM AUTHOR]

This paper proposes a novel ranking function, called RFHOS by incorporating higher order cumulants into the ranking function for finding differentially expressed genes. Traditional ranking functions assume a data distribution (e.g., Normal) and use only first two cumulants for statistical significance analysis. Ranking functions based on second order statistics are often inadequate in ranking small sampled data (e.g., Microarray data). Also, relatively small number of samples in the data makes it hard to estimate the parameters accurately causing inaccuracies in ranking of the genes. The proposed ranking function is based on higher order statistics (RFHOS) that account for both the amplitude and the phase information by incorporating the HOS. The incorporation of HOS deviates from implicit symmetry assumed for Gaussian distribution. In this paper the performance of the RFHOS is compared against other well known ranking functions designed for ranking the genes in two sample microarray experiments. [ABSTRACT FROM AUTHOR]

This paper presents an approach for speech information hiding based on G.721 scheme. This approach proposes an Analysis-By-Synthesis (ABS)-based speech information hiding and extracting algorithm, is called ABS algorithm, which form the theoretical basis for designing a secure speech communication system. The ABS algorithm adopts a speech synthesizer in a speech coder. Speech embedding and coding are synchronous, i.e. fusing of secret speech information data into speech coding. Dynamic secret speech information data bits can be embedded into original carrier speech data, with high efficiency in steganography and good quality in output speech. This method is superior to available classical algorithms on hiding capacity and robustness. This paper implements the proposed approach based on speech coding scheme G.721 and the experiments show that this approach meets the requirements of information hiding, satisfies the constraints of speech quality for secure communication, and achieves high hiding capacity of 1.6Kbps with an excellent speech quality and complicating speakers' recognition. [ABSTRACT FROM AUTHOR]

In this paper, an efficient approach to search for the global threshold of image using Gaussian mixture model is proposed. Firstly, a gray-level histogram of an image is represented as a function of the frequencies of gray-level. Then to fit the Gaussian mixtures to the histogram of image, the Expectation Maximisation (EM) algorithm is developed to estimate the number of Gaussian mixture of such histograms. Finally, the optimal threshold which is the average of these means is chosen. The paper compares the new method with the classical discriminate analysis method of Otsu's. And the experimental results show that the new algorithm performs better than that of Otsu's. [ABSTRACT FROM AUTHOR]

In this paper, we proposed image processing technique for automatic real time fire and smoke detection in tunnel environment. To avoid the large scale of damage of fire occurred in the tunnel, it is necessary to have a system to minimize and to discover the incident as fast as possible. However it is impossible to keep the human observation of Closed-Circuit Television (CCTV) in tunnel for 24 hour. So if the fire and smoke detection system through image processing can warn fire state, it will be very convenient, and it can be possible to minimize damage even when people is not in front of monitor. The fire and smoke detection is different from the forest fire detection as there are elements such as car and tunnel lights and others that are different from the forest environment so that an indigenous algorithm has to be developed. The two algorithms proposed in this paper, are able to detect the exact position, at the earlier stage of incident. In addition, by comparing properties of each algorithm throughout experiment, we have proved the validity and efficiency of proposed algorithm. [ABSTRACT FROM AUTHOR]

In speaker recognition fields, score normalization is a widely used and effective technique to enhance the recognition performances and is developing further. In this paper, we are focused on the comparison among many kinds of candidates of score normalization methods and a new implementation of the speaker adaptive test normalization (ATnorm) based on a cross similarity measurement is presented which doesn't need an extra corpus for speaker adaptive impostor cohort selection. The use of ATnorm for the language robustness of the multi-language speaker verification is also investigated. Experiments are conducted on the core task of the 2006 NIST Speaker Recognition Evaluation (SRE) corpus. The experimental results indicate that all the score normalization methods mentioned can improve the recognition performances and ATnorm behaves best. Moreover, ATnorm can further contribute to the performance as a means of language robustness. [ABSTRACT FROM AUTHOR]

Based on neural network with favorable adaptability to handwritten Chinese character multi-features, in this paper a new method is proposed, using existing multi-features as inputs to structure multi neural network recognition subsystems and these subsystems are integrated with parallel connection mode. The integrated system has the lowest false recognition rate. When using traditional von Neumann architecture computer to implement this system, the system response time is longer as a result of serial computation. This paper introduces a kind of parallel computation method of using pc cluster to implement multi subsystems. It can reduce effectively recognition system's response time. [ABSTRACT FROM AUTHOR]

According to Cachin's steganography security criterion, if the statistical distributions of cover and stego images are identical, the hidden message is assumed undetectable. However, any steganographic method will surely cause some statistical distortions, which gives steganalyst a hint. This paper presents a steganalysis method for JPEG images based on Cachin criterion. It estimates the cover image from the stego one by using a small-scale geometrical transform, and then detects the statistical distortions between the cover and stego images based on some features, which are sensitive to the steganographic modifications. Then a classifier is trained on these features. Three different modern steganographic schemes are tested. Experimental results show that the proposed steganalysis scheme has better performance compared to the current steganalysis methods. [ABSTRACT FROM AUTHOR]

Traditional speech recognition systems have relied on power spectral densities, Mel-frequency cepstral, linear prediction coding and formant analysis. This paper introduces two novel input feature sets and their extraction methods for intelligent phoneme identification. These input sets are based on intrinsic phonetic characteristics of Arabic speech comprising of the dimensionally reduced Power Spectral Densities (DPSD) and Location, Trend, Gradient (LTG) values of the captured speech signal spectrum. These characteristics have been subsequently utilized as inputs to four different neural network based recognition classifiers. The classifiers have been tested for twenty-eight Arabic phonemes utterances from over one hundred non-native speakers. The results obtained using the proposed feature sets have been compared and it has been observed that LTG based input feature set provides an average phoneme identification accuracy of 86% as compared to 70% obtained through applying DPSD based inputs for similar classifiers. It is worthwhile to note that the methods proposed in this paper are generic and are equally applicable to other regional languages such as Persian and Urdu. [ABSTRACT FROM AUTHOR]

In this paper, two new properties of singular value decomposition (SVD) on images are proved. The first property demonstrates the quantitative relationship between singular values and power spectrum. The second one proves that under the condition of losing equal power spectrum, the square-error of the reconstructed image is much smaller when we reduce all singular values proportionally instead of neglect the smaller ones. Based on the two properties, a new data-hiding scheme is proposed. It performs well as for robustness, for it satisfies power-spectrum condition (PSC), and PSC-compliant watermarks are proven to be most robust. Besides, the proposed scheme has a good performance as for capacity and adaptability. [ABSTRACT FROM AUTHOR]

With the growth of critical worm threats, many researchers have studied worm-related topics and internet anomalies. The researches are mainly concentrated on worm propagation and detection more than the fundamental characteristics of worms. It is very important to know worms' characteristics because the characteristics provide basic resource for worm prevention. Unfortunately, this kind of research cases are very few until now. Moreover the existing researches only focus on understanding the function structure of the worm propagation or the taxonomy of the worm according to a sequence of worm attacks. Thus, in this paper, we try to confirm the formalized pattern of the worm action from the existing researches and analyze the report of the anti-virus companies. Finally, we define the formalized actions based on temporal behaviors and worm packet flows, and we apply our proposed method for the new worm classification. [ABSTRACT FROM AUTHOR]

Recent advances in networking technology have increased the potential collaborations for virtual enterprises (VEs) on a global scale. Due to the dynamic nature of collaborations, building and evolving trust is essential to support the formation of VEs. There is a critical need for the new approach suited to this environment. This paper presents a trust-based approach for partner selection problem in the VEs. The proposed model explores the dynamic properties of trustworthy index, which provides a multi-perspective and interactive overview of potential partners to the decision-makers. The model uses the hybrid learning algorithm of fuzzy cognitive map (FCM). As FCM has the excellent ability in modeling complex systems, the proposed model can support historical data mining automatically, and revise the existing model according to the new requirements. Results of three experiments show that this model provides reasonable performance and high adaptability for diverse partner selection problems. [ABSTRACT FROM AUTHOR]

This paper proposes obstacle collision avoidance algorithm for a mobile robot. To navigate without colliding with obstacles the mobile robot uses both the vision system approach and edge detection approach using ultrasonic sensor. The vision system approach is used when the obstacle is located more than 2 meters away from the mobile robot, and the edge detection approach using ultrasonic sensor is used for detecting obstacle remains within 2 meters range. The collision avoidance algorithm proposed in this paper utilizes both the limit-cycle method and the nearness diagram navigation method. The proposed method is tested using Pioneer 2-DX mobile robot. Through experiment, the effectiveness of proposed methods for navigating a mobile robot in the dynamic environment is demonstrated. [ABSTRACT FROM AUTHOR]

The are various definitions of instantaneous frequency (IF) but most of them have short comings. The most popular of these definitions, is the one given by Cohen. To estimate IF accuratly, techniques become more and more complex. This paper introduces the idea of aggregate spectrogram (AS). When we are not interested in the entire spectrum (e.g., finding IF), it is better to find out AS which gives an aggregate view of the spectrogram rather than calculating the individual frequencies. Some properties of AS are also defined. The AS lowers the computational complexity. This paper also presents a technique to construct an AS and finding the IF from the AS. [ABSTRACT FROM AUTHOR]

Conventional hysteresis control schemes for direct torque control (DTC) of dual-three-phase induction machine (DTPIM) usually result highly distorted current waveforms. In this paper, fuzzy space voltage modulation technique is presented for DTPIM. Using two fuzzy controllers, amplitude and space angle of desired stator voltage vector, are obtained dynamically. Combined with unified pulse width modulation method, direct torque control is applied to DTPIM. Simulation results show that fast dynamic responses are achieved. The ripple of torque and the harmonics of stator current in steady state can be reduced remarkably compared with conventional DTC method. [ABSTRACT FROM AUTHOR]

The focus of situation-aware ubiquitous computing has increased lately. An example of situation-aware applications is a multimedia education system. The development of multimedia computers and communication techniques has made it possible for a mind to be transmitted from a teacher to a student in distance environment. This paper proposed a new model of dynamic window binding by analyzing the window and attributes of the attributes of the object, and based on this, a mechanism that offers a seamless view without interfering with concurrency control is also suggested. As the result of this system's experimental implementation and analysis of the increase of delay factors accordant with the size of collaboration increase, the simulation results clearly showed that the seam increases seriously in that case, and that the dynamic window binding mechanism proposed in this paper is worth implementation and effective when a large scale of collaboration is required. [ABSTRACT FROM AUTHOR]

Bearing fault detection with the aid of the vibration signals is presented. In this paper, time-domain features are extracted to indicate bearing fault, which collected from tri-axial vibration signal. Decision tree is chosen as an effective diagnostic tool to obtain bearing status. The paper also introduces principal component analysis (PCA) algorithm to reduce training data dimension and remove irrelevant data. Both original data and PCA-based data are used to train C4.5 decision tree models. Then, the result of PCA-based decision tree is compared with normal decision tree to get the best performance of classification process. [ABSTRACT FROM AUTHOR]

This paper proposed a novel residual capacity estimation method for lead-acid battery. Generally, the battery residual capacity is related to open-circuit-voltage (OCV) and inner resistance. Due to complexities, delay, coupling and nonlinearity on the relation described above, the residual capacity estimation is difficult to be obtained by the voltage or inner resistance measurement only. In this paper, by observing and recording the constant current discharging process, we generated the residual capacity pattern for different capacity levels and built a CMAC (Cerebellar Model Articulation Controller) neural network to estimate the lead-acid battery residual capacity. The characteristic of self-learning and generalization, like the cerebellum of human being, a CMAC NN estimation scheme enables powerful, straightforward, and efficient battery residual capacity estimation. With application of this scheme to the experimental data test, the estimation results demonstrate the new scheme with high accuracy and high noise rejection ability. [ABSTRACT FROM AUTHOR]

The real-time information access of goods plays an increasingly important role for decision-making in operations management of supply chain. Based on mobile agent and radio-frequency identification (RFID) technology, this paper proposes a novel solution to track in transit goods. Firstly, mobile RFID reader integrated in a smart phone retrieves information automatically from RFID tags bound to goods. Then, the front-end system that works on the smart phone send information back to the back-end system via short message system of mobile telecommunication platform. Because the solution is built on mobile agent platform, it enables the back-end system to dispatch mobile agents to the front-end system to process raw RFID data locally, and only the filtered results are fed back. Therefore, the solution promises to reduce time and cost of data transfer between the front-end system and the back-end system. Finally, a prototype system, GTSys named, is implemented and verified on simulation platform. [ABSTRACT FROM AUTHOR]

This paper explores the attributes that drive company wealth creation in the Miscellaneous Industrials sector of the Australian Stock Market. It looks at how the company's wealth creation changes in comparison to the changes in the Miscellaneous Industrial Index. We examine traditional and artificial intelligent (AI) feature selection techniques, to select attributes that drive company wealth and observe if a multiple domain model outperforms a single domain model with regards to predicting company wealth. Using a large number of calculated attributes, our empirical findings suggest that a multiple domain model was most effective. We found that WACC, Funds from Operation / EBITDA and EPS assist in guiding the direction of change in shareholder wealth. Whereas ROA, Capital Turnover and Gross Debt / Cashflow are key attributes in understanding the behaviour of the relative shareholder growth. We observed that ROIC, Ordinary Share Price, EVA, EPS and Trading Revenue / Total Assets are the important attributes that drive relative shareholder wealth in this industry. [ABSTRACT FROM AUTHOR]

With the rapid development of WWW, HTML documents become one of the main file formats on the Web. However, blind people find difficulty in accessing the HTML documents for their complex structure and visual reliability. The main methods for the blind to browse the web pages are through screen reader and text web browser with TTS engine. These methods can only read text on the screen without knowing the relationship among the texts. It's very difficult and time consuming to find out some information from a bunch of texts. In this paper, a special web browser called eGuideDog is designed for the visually impaired people. This web browser can extract the structure and the content of an HTML document and represent it in the form of audio. It helps the blind finding out information they concern more quickly. [ABSTRACT FROM AUTHOR]

Driven by new regulations and animal welfare, the need to develop in silico models has increased recently as alternative approaches to safety assessment of chemicals without animal testing. This paper describes a novel machine learning ensemble approach to building an in silico model for the prediction of the Ames test mutagenicity, one of a battery of the most commonly used experimental in vitro and in vivo genotoxicity tests for safety evaluation of chemicals. Evolutionary random neural ensemble with negative correlation learning (ERNE) [1] was developed based on neural networks and evolutionary algorithms. ERNE combines the method of bootstrap sampling on training data with the method of random subspace feature selection to ensure diversity in creating individuals within an initial ensemble. Furthermore, while evolving individuals within the ensemble, it makes use of the negative correlation learning, enabling individual NNs to be trained as accurate as possible while still manage to maintain them as diverse as possible. Therefore, the resulting individuals in the final ensemble are capable of cooperating collectively to achieve better generalization of prediction. The empirical experiment suggest that ERNE is an effective ensemble approach for predicting the Ames test mutagenicity of chemicals. [ABSTRACT FROM AUTHOR]

This paper presents a novel fault detection and section estimation method for unbalanced underground distribution systems (UDS). The method proposed is based on artificial neural networks (ANNs) and wavelet transforms (WTs). The majority of UDS are characterized by having several single/double phase laterals and non-symmetrical lines. Also, Digital Fourier Transforms (DFT), used in the majority of traditional protection relays, supplies a low level of robustness to the fault diagnosis process due to its inversely proportional time-frequency characteristic. These characteristics compromise the traditional fault diagnosis methods performance. ANNs are capable of learning and generalizing, whereas WTs are robust tools capable of evaluating a signal's frequency range that can characterize the fault phenomenon. This paper describes the proposed diagnosis method and discusses the results obtained from simulated implementation. The obtained results demonstrate the capability and robustness of the technique indicating its potential for on-line applications. [ABSTRACT FROM AUTHOR]

This paper presents a Genetic algorithm (GA) based solution to co-optimize test scheduling and wrapper design for core based SOCs. Core testing solutions are generated as a set of wrapper configurations, represented as rectangles with width equal to the number of TAM (Test Access Mechanism) channels and height equal to the corresponding testing time. A locally optimal best-fit heuristic based bin packing algorithm has been used to determine placement of rectangles minimizing the overall test times, whereas, GA has been utilized to generate the sequence of rectangles to be considered for placement. Experimental result on ITC'02 benchmark SOCs shows that the proposed method provides better solutions compared to the recent works reported in the literature. [ABSTRACT FROM AUTHOR]

Kernel methods like support vector machine, kernel principal component analysis and kernel fisher discriminant analysis have recently been successfully applied to solve pattern recognition problems such as face recognition. However, most of the papers present the results without giving kernel parameters, or giving parameters without any explains. In this paper, we present an experiments based approach to optimize the performance of a Gabor feature and kernel method based face recognition system. During the process of parameter tuning, the robustness of the system against variations of kernel function, kernel parameters and Gabor features are extensively tested. The results suggest that the kernel method based approach, with tuned parameters, achieves significantly better results than other algorithms available in literature. [ABSTRACT FROM AUTHOR]

Gyro survey technique has applied and played an important role in many areas, such as offshore oil drilling, directional drilling and so on. Considering the influence of the compensation for the large surveying azimuth error, in this paper, the principle of the gyro survey system is described, and the ANFIS architecture is employed to model the survey azimuth error, predict a chaotic current, all yielding remarkable results according to the gyro survey principle and the data sampled from the two-axis turntable. From the simulation and the testing result, we can see that ANFIS is an effective and feasible way to model and compensate the azimuth error, and the precision of the ANFIS method is higher than the methods of the bilinear interpolation and the radius basis function (RBF), so it is available and advisable in engineering. [ABSTRACT FROM AUTHOR]

Understanding and adapting to changes of customer behavior is an important aspect of surviving in a continuously changing market environment for a modern company. The concept of customer change model mining is introduced and its process is analyzed in this paper. A customer change model mining method based on swarm intelligence is presented, and the strategies of pheromone updating and items searching are given. Finally, an examination on two customer datasets of a telecom company illuminates that this method can achieve customer change model efficiently. [ABSTRACT FROM AUTHOR]

In this paper, a new framework for data analysis based on the "key points" in data distribution is proposed. Here, the key points contain three types of data points: bridge points, border points, and skeleton points, where our main contribution is the bridge points. For each type of key points, we have developed the corresponding detection algorithm and tested its effectiveness with several synthetic data sets. Meanwhile, we further developed a new hierarchical clustering algorithm SPHC (Skeleton Point based Hierarchical Clustering) to demonstrate the possible applications of the key points acquired. Based on some real-world data sets, we experimentally show that SPHC performs better compared with several classical clustering algorithms including Complete-Link Hierarchical Clustering, Single-Link Hierarchical Clustering, KMeans, Ncut, and DBSCAN. [ABSTRACT FROM AUTHOR]

In this paper, we develop a novel approach to perform kernel parameter selection for Kernel Fisher discriminant analysis (KFDA) based on the viewpoint that optimal kernel parameter is associated with the maximum linear separability of samples in the feature space. This makes our approach for selecting kernel parameter of KFDA completely comply with the essence of KFDA. Indeed, this paper is the first paper to determine the kernel parameter of KFDA using a search algorithm. Our approach proposed in this paper firstly constructs an objective function whose minimum is exactly equivalent to the maximum of linear separability. Then the approach exploits a minimum search algorithm to determine the optimal kernel parameter of KFDA. The convergence properties of the search algorithm allow our approach to work well. The algorithm is also simple and not computationally complex. Experimental results illustrate the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

The problem of mean square exponential stability of uncertain stochastic Hopfield neural networks with interval time-varying delays is investigated in this paper. The delay factor is assumed to be time-varying and belongs to a given interval, which means that the derivative of the delay function can exceed one. The uncertainties considered in this paper are norm-bounded and possibly time-varying. By Lyapunov-Krasovskii functional approach and stochastic analysis approach, a new delay-dependent stability criteria for the exponential stability of stochastic Hopfield neural networks is derived in terms of linear matrix inequalities(LMIs). A simulation example is given to demonstrate the effectiveness of the developed techniques. [ABSTRACT FROM AUTHOR]

This paper newly proposes a novel round-based synchronous system suffering crash and probabilistic omission failures. In this model, a novel class of adversaries, called p-probabilistic omission adversary (p-POA) is introduced. In addition to the ability of complete control of the crash-failure behavior, p-POA can select any subset of all transmitted messages as omission candidates. Then, each message in the omission candidates is lost with probability p. This paper investigates the feasiblity and complexity of the consensus problem under p-POA. We first show two impossibility results that (1) for any p > 0, there exists no uniform consensus algorithm tolerating more than or equal to n/2 crash failures, and that (2) for any p > 0, any uniform consensus algorithm cannot halt. We also show two consensus algorithms CPO and F-CPO. Both algorithms work under (1/2)-POA and respectively have distinct advantages. The algorithm CPO can tolerate at most n/2 − 1 crash failures and achieves O(f) expected round complexity, where f is the actual number of crash failures. This implies that CPO has maximum crash-failure resiliency. While the second algorithm F-CPO assumes the maximum number of crash failures less than n/3, it achieves f + O(1) round compexity in expectation. Since it is known that the lower bound for crash-tolerant consensus is f + 1, this result implies that only a constant number of extra rounds is necessary to tolerate a drastic number of message omissions. [ABSTRACT FROM AUTHOR]

"Pulse Synchronization" intends to invoke a recurring distributed event at the different nodes, of a distributed system as simultaneously as possible and with a frequency that matches a predetermined regularity. This paper shows how to achieve that goal when the system is facing both transient and permanent (Byzantine) failures. Byzantine nodes might incessantly try to de-synchronize the correct nodes. Transient failures might throw the system into an arbitrary state in which correct nodes have no common notion what-so-ever, such as time or round numbers, and thus cannot use any aspect of their own local states to infer anything about the states of other correct nodes. The algorithm we present here guarantees that eventually all correct nodes will invoke their pulses within a very short time interval of each other and will do so regularly. The problem of pulse synchronization was recently solved in a system in which there exists an outside beat system that synchronously signals all nodes at once. In this paper we present a solution for a bounded-delay system. When the system in a steady state, a message sent by a correct node arrives and is processed by all correct nodes within a bounded time, say d time units, where at steady state the number of Byzantine nodes, f, should obey the n > 3f inequality, for a network of n nodes. [ABSTRACT FROM AUTHOR]

Collaborative work can be supported by many tools and it has been included in a large number of learning environments design. This paper presents issues related to an educational portal design and collaboration in Intelligent Tutoring Systems (ITS). In order to achieve the collaboration it was necessary to provide a way to interoperate knowledge among the heterogeneous systems. We have been developing ITS as resources to improve the individual and personalized learning. We believe that individual experiences can be more successful when the student has more autonomy and he is less dependent of the professor. In this research direction, this paper details the Social Agent reasoning, an agent to improve student's learning stimulating his interaction with other students, and how this agent exchange bayesian knowledge among AMPLIA agents. The AMPLIA environment is an Intelligent Probabilistic Multi-agent Environment to support the diagnostic reasoning development and the diagnostic hypotheses modeling of domains with complex and uncertain knowledge, like medical area. [ABSTRACT FROM AUTHOR]

This paper addresses the characterization of a large text collection by introducing a method for retrieving sets of relevant WordNet concepts as descriptors of the collection contents. The method combines models for identifying interesting word co-occurrences with an extension of a word sense disambiguation algorithm in order to retrieve the concepts that better fit in with the collection topics. Multi-word nominal concepts that do not explicitly appear in the texts, can be found among the retrieved concepts. We evaluate our proposal using extensions of recall and precision that are also introduced in this paper. [ABSTRACT FROM AUTHOR]

Desharnais, Gupta, Jagadeesan and Panangaden introduced a family of behavioural pseudometrics for probabilistic transition systems. These pseudometrics are a quantitative analogue of probabilistic bisimilarity. Distance zero captures probabilistic bisimilarity. Each pseudometric has a discount factor, a real number in the interval (0, 1]. The smaller the discount factor, the more the future is discounted. If the discount factor is one, then the future is not discounted at all. Desharnais et al. showed that the behavioural distances can be calculated up to any desired degree of accuracy if the discount factor is smaller than one. In this paper, we show that the distances can also be approximated if the future is not discounted. A key ingredient of our algorithm is Tarski's decision procedure for the first order theory over real closed fields. By exploiting the Kantorovich-Rubinstein duality theorem we can restrict to the existential fragment for which more efficient decision procedures exist. [ABSTRACT FROM AUTHOR]

In a seminal paper from 1985, Sistla and Clarke showed that satisfiability for Linear Temporal Logic (LTL) is either NP-complete or PSPACE-complete, depending on the set of temporal operators used . If, in contrast, the set of propositional operators is restricted, the complexity may decrease. This paper undertakes a systematic study of satisfiability for LTL formulae over restricted sets of propositional and temporal operators. Since every propositional operator corresponds to a Boolean function, there exist infinitely many propositional operators. In order to systematically cover all possible sets of them, we use Post's lattice. With its help, we determine the computational complexity of LTL satisfiability for all combinations of temporal operators and all but two classes of propositional functions. Each of these infinitely many problems is shown to be either PSPACE-complete, NP-complete, or in P. Keywords: computational complexity, linear temporal logic. [ABSTRACT FROM AUTHOR]

In this paper, we attempt to implement classical conditioning with spiking neurons instead of connectionist neural networks. The neuron model used is a leaky linear integrate-and-fire model with a learning algorithm combining spike-time dependent Hebbian learning and spike-time dependent anti-Hebbian learning. Experimental results show that the major phenomena of classical conditioning, including Pavlovian conditioning, extinction, partial conditioning, blocking, inhibitory conditioning, overshadow and secondary conditioning, can be implemented by the spiking neuron model proposed here and further indicate that spiking neuron models are well suited to implementing classical conditioning. [ABSTRACT FROM AUTHOR]

The performance of a Radial Basis Functions network (RBF) can be increased with the use of an ensemble of RBF networks because the RBF networks are successfully applied to solve classification problems and they can be trained by gradient descent algorithms. Reviewing the bibliography we can see that the performance of ensembles of Multilayer Feedforward (MF) networks can be improved by the use of the two combination methods based on Stacked Generalization described in [1]. We think that we could get a better classification system if we applied these combiners to an RBF ensemble. In this paper we satisfactory apply these two new methods, Stacked and Stacked+, on ensembles of RBF networks. Increasing the number of networks used in the combination module is also successfully proposed in this paper. The results show that training 3 MF networks to combine an RBF ensemble is the best alternative. [ABSTRACT FROM AUTHOR]

Classifier Combination has been investigated as an alternative to obtain improvements in design and/or accuracy for difficult pattern recognition problems. In the literature, many combination methods and algorithms have been developed, including methods based on computational Intelligence, such as: fuzzy sets, neural networks and fuzzy neural networks. This paper presents an evaluation of how different levels of diversity reached by the choice of the components can affect the accuracy of some combination methods. The aim of this analysis is to investigate whether or not fuzzy, neural and fuzzy-neural combination methods are affected by the choice of the ensemble members. [ABSTRACT FROM AUTHOR]

This paper proposes a novel approach for directly tuning the gaussian kernel matrix for one class learning. The popular gaussian kernel includes a free parameter, σ, that requires tuning typically performed through validation. The value of this parameter impacts model performance significantly. This paper explores an automated method for tuning this kernel based upon a hill climbing optimization of statistics obtained from the kernel matrix. [ABSTRACT FROM AUTHOR]