Search

One of the largest obstacles facing scanning probe microscopy is the constant need to correct flaws in the scanning probe in situ. This is currently a manual, time-consuming process that would benefit greatly from automation. Here, we introduce a convolutional neural network protocol that enables automated recognition of a variety of desirable and undesirable scanning tunneling tip states on both metal and nonmetal surfaces. By combining the best performing models into majority voting ensembles, we find that the desirable states of H:Si(100) can be distinguished with a mean precision of 0.89 and an average receiver-operator-characteristic curve area of 0.95. More generally, high and low-quality tips can be distinguished with a mean precision of 0.96 and near perfect area-under-curve of 0.98. With trivial modifications, we also successfully automatically identify undesirable, non-surface-specific states on surfaces of Au(111) and Cu(111). In these cases, we find mean precisions of 0.95 and 0.75 and area-under-curves of 0.98 and 0.94, respectively. Provided that training data are available, these ensembles therefore enable fully autonomous scanning tunneling state recognition for a wide range of typical scanning conditions. [ABSTRACT FROM AUTHOR]

The computer network security evaluation simulation model is analyzed based on neural network. Firstly, based on the system security experimental platform, the system security detection algorithm is constructed, and the selection strategy of calculation scale is analyzed. The Prefix Span algorithm is introduced, improving its algorithm. Data mining based on Prefix is carried out, with the relationship between intrusions and their relationships analyzed. Secondly, the implementation steps of the algorithm are explained. Finally, the algorithm is tested, and the results are analyzed from three aspects: entropy value feature, active entropy algorithm and cloud platform performance. The conclusion is that the algorithm designed in this paper has good accuracy and adaptability, and it can play a good supporting role in system safety practice training, and the encryption protocol in the network security protocol is further improved, which has laid a solid foundation for the security development of the network. [ABSTRACT FROM AUTHOR]

UV absorption is widely used for characterizing proteins structures. The mapping of UV spectra to atomic structure of proteins relies on expensive theoretical simulations, circumventing the heavy computational cost which involves repeated quantummechanical simulations of excited-state properties of many fluctuating protein geometries, which has been a long-time challenge. Here we show that a neural network machine-learning technique can predict electronic absorption spectra of N-methylacetamide (NMA), which is a widely used model system for the peptide bond. Using ground-state geometric parameters and charge information as descriptors, we employed a neural network to predict transition energies, ground-state, and transition dipole moments of many molecular-dynamics conformations at different temperatures, in agreement with time-dependent density-functional theory calculations. The neural network simulations are nearly 3,000× faster than comparable quantum calculations. Machine learning should provide a cost-effective tool for simulating optical properties of proteins. [ABSTRACT FROM AUTHOR]

In high diversity node situation, multichannel MAC protocol can improve the frequency efficiency, owing to fewer collisions compared with single-channel MAC protocol. And the performance of cyclic quorum-based multichannel (CQM) MAC protocol is outstanding. Based on cyclic quorum system and channel slot allocation, it can avoid the bottleneck that others suffered from and can be easily realized with only one transceiver. To obtain the accurate performance of CQM MAC protocol, a Markov chain model, which combines the channel-hopping strategy of CQM protocol and IEEE 802.11 distributed coordination function (DCF), is proposed. The results of numerical analysis show that the optimal performance of CQM protocol can be obtained in saturation bound situation. And then we obtain the saturation bound of CQM system by bird swarm algorithm. In addition, to improve the performance of CQM protocol in unsaturation situation, a dynamic channel slot allocation of CQM (DCQM) protocol is proposed, based on wavelet neural network. Finally, the performance of CQM protocol and DCQM protocol is simulated by Qualnet platform. And the simulation results show that the analytic and simulation results match very well; the DCQM performs better in unsaturation situation. [ABSTRACT FROM AUTHOR]

The development of intrusion detection systems (IDS) that are adapted to allow routers and network defence systems to detect malicious network traffic disguised as network protocols or normal access is a critical challenge. This paper proposes a novel approach called SCDNN, which combines spectral clustering (SC) and deep neural network (DNN) algorithms. First, the dataset is divided into k subsets based on sample similarity using cluster centres, as in SC. Next, the distance between data points in a testing set and the training set is measured based on similarity features and is fed into the deep neural network algorithm for intrusion detection. Six KDD-Cup99 and NSL-KDD datasets and a sensor network dataset were employed to test the performance of the model. These experimental results indicate that the SCDNN classifier not only performs better than backpropagation neural network (BPNN), support vector machine (SVM), random forest (RF) and Bayes tree models in detection accuracy and the types of abnormal attacks found. It also provides an effective tool of study and analysis of intrusion detection in large networks. [ABSTRACT FROM AUTHOR]

This paper is concerned with the state estimation problem for a class of artificial neural networks (ANNs) without the assumptions of monotonicity or differentiability of the activation functions. The measured outputs are corrupted by stochastic noise signal whose intensity is quantified by a nonlinear function. In order to accommodate the bandwidth limit of the communication channel between the ANN and the state estimator, an equal allocation scheme (i.e. Round-Robin protocol) of the communication resource is employed to effectively mitigate data congestions and save energies. A set of zero-order holders (ZOHs) is utilized to store the received measurements, such that the utilization of the received measurements can be maximized. An update matrix approach is developed to handle the time-varying yet periodic time-delays resulting from the adoption of the Round-Robin protocol. The aim of the proposed problem is to design a state estimator such that the error dynamics is exponentially ultimately bounded. A combination of the Lyapunov stability theory and the stochastic analysis technique is used to derive some easy-to-test conditions for the existence of the desired state estimator. The estimator gains are characterized by the solution to a convex optimization problem that is solved via the semi-definite programme method. Simulation results are given to demonstrate the effectiveness of the proposed estimation approach. [ABSTRACT FROM AUTHOR]

Containment control of multi-agent system with time-delays is a meaningful topic with considerable realistic significance in the research of multi-agent systems. This paper investigates the distributed containment control of a group of mobile autonomous agents with multiple stationary or dynamic leaders, when considering the fixed time-delay under fixed directed network topologies. In the case of studying the multi-agent delayed system with continuous-time, Laplace transform and final value theorem are employed. Specifically some sufficient conditions are obtained which can ensure the containment of the first-order multi-agent systems. Moreover, an effective control protocol is designed for the first-order discrete-time systems with fixed time-delays. Finally, simulation examples are given to verify the effectiveness of the theoretical results and conclusions. [ABSTRACT FROM AUTHOR]

Inter-Cell Interference (ICI) from neighboring cells is the major challenge that degrades the performance of Orthogonal Frequency Division Multiple Access (OFDMA) cellular mobile systems, particularly for cell edge users. An efficient technique to mitigate ICI is the interference coordination. The most commonly ICI Coordination (ICIC) technique is the Fractional Frequency Reuse (FFR), which effectively mitigates ICI by applying different reuse factors to Users’ Equipments (UEs) situated in different regions in each cell. This paper presents a novel Self-Organized FFR Resource Allocation (SORA) scheme that automatically selects the optimal RA to inner and outer regions of the cell, based on coordination between neighboring evolved NodeBs (eNBs), through a message passing approach over Long Term Evolution (LTE)-X2 interfaces. The performance of the proposed scheme is evaluated using MATLAB and compared with different combinations of RA as well as with frequency reuse-1 and reuse-3 schemes. Simulation results show that the proposed scheme improves the cell-edge performance and achieves high degree of fairness among UEs compared to reference RA schemes. [ABSTRACT FROM AUTHOR]

Abstract: The application of Artificial Neural Networks (ANNs) in the field of environmental and water resources modelling has become increasingly popular since early 1990s. Despite the recognition of the need for a consistent approach to the development of ANN models and the importance of providing adequate details of the model development process, there is no systematic protocol for the development and documentation of ANN models. In order to address this shortcoming, such a protocol is introduced in this paper. In addition, the protocol is used to critically review the quality of the ANN model development and reporting processes employed in 81 journal papers since 2000 in which ANNs have been used for drinking water quality modelling. The results show that model architecture selection is the best implemented step, while greater focus should be given to input selection considering input independence and model validation considering replicative and structural validity. [Copyright &y& Elsevier]

Contract Net Protocol is a suitable method for multi-robot task allocation problems. However, it is difficult to find a function to evaluate robots’ bids when each robot gives more than one bid price to reflect its different abilities. We propose a method to fuse these prices and to decide which robot is the successful bidder using a BP neural network. The experiment result shows that the method is effective. [ABSTRACT FROM AUTHOR]

Abstract: USDA’s nutritional reference database is the primary database used by several nutrient analyses software. Despite the use of one database, variations among systems emerge impacting nutrient estimation. Consequently, this paper explores these critical differences by classifying sources of variations leading to computational errors. Learning Vector Quantization and Bayesian (neural-network) methods were applied to characterize pattern of errors. As a result, two common errors were identified to be prevalent in nutrient analyses. Random errors (37.1% of total variance) stemming from selection process (Operator) because of the enormity of food items listed in the database and system errors (59.5% of total variance) due to measurements (units, tools and procedures) variations. Computerized classification of random and system errors are of significant interest in the field of nutrition and food engineering because, it provides practical solutions to database query and optimization of inherent variations due to measurement errors that are beneficial to research methodologies. [Copyright &y& Elsevier]

Neural synchronization by means of mutual learning provides an avenue to design public key exchange protocols, bringing about what is known as neural cryptography. Two identically structured neural networks learn from each other and reach full synchronization eventually. The full synchronization enables two networks to have the same weight, which can be used as a secret key for many subsequent cryptographic purposes. It is striking to observe that after the first decade of neural cryptography, the tree parity machine (TPM) network with hidden unit K = 3 appears to be the sole network that is suitable for a neural protocol. No convincingly secure neural protocol is well designed by using other network structures despite considerable research efforts. With the goal of overcoming the limitations of a suitable network structure, in this paper we develop a two-layer tree-connected feed-forward neural network (TTFNN) model for a neural protocol. The TTFNN model captures the notion that two partners are capable of exchanging a vector with multiple bits in each time step. An in-depth study of the dynamic process of TTFNN-based protocols is then undertaken, based upon which a feasible condition is theoretically obtained to seek applicable protocols. Afterward, according to two analytically derived heuristic rules, a complete methodology for designing feasible TTFNN-based protocols is elaborated. A variety of feasible neural protocols are constructed, which exhibit the effectiveness and benefits of the proposed model. With another look from the perspective of application, TTFNN-based instances, which can outperform the conventional TPM-based protocol with respect to synchronization speed, are also experimentally confirmed. [ABSTRACT FROM AUTHOR]

The Global Positioning System (GPS) is expected to play an integral role in the development of digital earth; however, the GPS cannot provide positioning information in regions where a majority of the population spends their time, that is, in urban and indoor environments. Hence, alternate positioning systems that work in indoor and urban environments should be developed to achieve the vision of digital earth. Wi-Fi-based positioning systems (WPS) stand out because of the near-ubiquitous presence of the associated infrastructure and signals in indoor environments. The WPS-based fingerprinting is the most widely adopted technique for position determination, but its accuracy is lower than that of techniques such as time of arrival and angle of arrival. Improving the accuracy is still a challenging task because of the complex nature of the propagation of Wi-Fi signals. Here, a novel server-based, genetic-algorithm-optimized, cascading artificial neural network-based positioning model is presented. The model is tested in 2D and 3D indoor environments under varying conditions. The model is thoroughly investigated on a real Wi-Fi network, and its accuracy is found to be better than that of other well-known techniques. A mean accuracy of 1.9 m is achieved with 87% of the distance error within the range of 0–3 m. [ABSTRACT FROM PUBLISHER]

Abstract: This paper proposes a distributed method for cooperative target tracking in hierarchical wireless sensor networks. The concept of leader-based information processing is conducted to achieve object positioning, considering a cluster-based network topology.Random timers and local information are applied to adaptively select a sub-cluster for the localization task. The proposed energy-efficient tracking algorithm allows each sub-cluster member to locally estimate the target position with a Bayesian filtering framework and a neural networking model, and further performs estimation fusion in the leader node with the covariance intersection algorithm. This paper evaluates the merits and trade-offs ofthe protocol design towards developing more efficient and practical algorithms for object position estimation. [ABSTRACT FROM AUTHOR]

In this study, the authors consider the problem of distributed relay beamforming in an underlay-based cognitive relay network in which a secondary network transmits its data using multiple relays under an amplify-and-forward protocol simultaneously with a primary network over the same spectrum. For such a network, assuming that the partial channel state information (CSI) is available, the authors study two different beamforming approaches to improve performance of the secondary transmissions while ensuring the quality-of-service of the primary transmissions. In the first approach, the authors obtain the beamforming weights as well as the transmit power of the secondary source such that the signal-to-interference plus noise ratio (SINR) at the secondary destination is maximised whereas the interference power from the secondary to the primary network is kept below a predefined threshold. In the second approach, the beamforming weights are obtained through minimising the received interference power at the primary receiver subject to a constraint on SINR at the secondary destination. The authors prove that both proposed approaches result in closed-form solutions. Simulation results show that as the uncertainty in CSI decreases, the proposed schemes achieve better performances. In addition, increasing the number of relays improves the overall system performance. [ABSTRACT FROM AUTHOR]

Abstract: Animal welfare is an issue of great importance in modern food production systems. Because animal behavior provides reliable information about animal health and welfare, recent research has aimed at designing monitoring systems capable of measuring behavioral parameters and transforming them into their corresponding behavioral modes. However, network unreliability and high-energy consumption have limited the applicability of those systems. In this study, a 2.4-GHz ZigBee-based mobile ad hoc wireless sensor network (MANET) that is able to overcome those problems is presented. The designed MANET showed high communication reliability, low energy consumption and low packet loss rate (14.8%) due to the deployment of modern communication protocols (e.g. multi-hop communication and handshaking protocol). The measured behavioral parameters were transformed into the corresponding behavioral modes using a multilayer perceptron (MLP)-based artificial neural network (ANN). The best performance of the ANN in terms of the mean squared error (MSE) and the convergence speed was achieved when it was initialized and trained using the Nguyen–Widrow and Levenberg–Marquardt back-propagation algorithms, respectively. The success rate of behavior classification into five classes (i.e. grazing, lying down, walking, standing and others) was 76.2% on average. The results of this study showed an important improvement regarding the performance of the designed MANET and behavior classification compared to the results of other similar studies. [Copyright &y& Elsevier]

This article aims at drive design for a brushless servomotor running in the condition of a networked control system. The proposed methodology employs existing non-networked based controllers and modifying the command with respect to current network traffic conditions which induce delays and the data dropouts. A middleware is implemented and modifies the output of the controller based on gain scheduling tuned by using an artificial neural network to overcome the relative problems. The search of the gain is transformed into an optimization problem of a defined cost function and its solution is given by a genetic algorithm to prevent the local minima. As a result, a user datagram protocol/IP channel suffering with random delays and data drops, for the communication between the controller and the servomotor is considered. Finally, the experiments conducted using a TMS320F2812 (Texas Instruments Inc., USA) digital signal processor based drive demonstrate the validation, performance and advantages of the proposed method. [ABSTRACT FROM PUBLISHER]

In this study, the consensus problem of heterogeneous multi-agent system is considered. First, the heterogeneous multi-agent system is proposed which is composed of first-order and second-order integrator agents in two aspects. Then, the consensus problem of heterogeneous multi-agent system is discussed with the linear consensus protocol and the saturated consensus protocol, respectively. By applying the graph theory and Lyapunov direct method, some sufficient conditions for consensus are established when the communication topologies are undirected connected graphs and leader-following networks. Finally, some examples are presented to illustrate the theoretical results. [ABSTRACT FROM AUTHOR]

Abstract: The recognition of pen-based visual patterns such as sketched symbols is amenable to supervised machine learning models such as neural networks. However, a sizable, labeled training corpus is often required to learn the high variations of freehand sketches. To circumvent the costs associated with creating a large training corpus, improve the recognition accuracy with only a limited amount of training samples and accelerate the development of sketch recognition system for novel sketch domains, we present a neural network training protocol that consists of three steps. First, a large pool of unlabeled, synthetic samples are generated from a small set of existing, labeled training samples. Then, a Deep Belief Network (DBN) is pre-trained with those synthetic, unlabeled samples. Finally, the pre-trained DBN is fine-tuned using the limited amount of labeled samples for classification. The training protocol is evaluated against supervised baseline approaches such as the nearest neighbor classifier and the neural network classifier. The benchmark data sets used are partitioned such that there are only a few labeled samples for training, yet a large number of labeled test cases featuring rich variations. Results suggest that our training protocol leads to a significant error reduction compared to the baseline approaches. [Copyright &y& Elsevier]

Abstract: In this paper, we present an approach to evaluate end-to-end delays in packets switching networked automation systems. Since Client-Server paradigm is considered for communication between the field devices, the existing methods of network delays evaluation are hardly applicable to assess realistic upper bounds of these delays. In an effort to enhance these delays evaluation, we propose an alternative method. Two algorithms, usually used for optimization problems, exhaustive and genetic algorithms, are then developed to achieve this purpose. While a formal proof about the capacity of the former one to ensure the worst delay overestimation is given, the latter proves to provide faster and more accurate results at the same time. This is shown on a practical case study while comparing the results of the two methods. [Copyright &y& Elsevier]

Abstract  In this paper, we present an approach to overcome the scalability issues associated with instance-based learners. Our system uses evolutionary computational techniques to determine the minimal set of training instances needed to achieve good classification accuracy with an instance-based learner. In this way, instance-based learners need not store all the training data available but instead store only those instances that are required for the desired accuracy. Additionally, we explore the utility of evolving the optimal feature set used by the learner for a given problem. In this way, we attempt to deal with the so-called “curse of dimensionality” associated with computational learning systems. To these ends, we introduce the Evolutionary General Regression Neural Network. This design uses an estimation of distribution algorithm to generate both the optimal training set as well as the optimal feature set for a general regression neural network. We compare its performance against a standard general regression neural network and an optimized support vector machine across four benchmark classification problems. [ABSTRACT FROM AUTHOR]

The IEEE 802.11 standard is becoming the most popular and efficient network topology deployed today. Providing and ensuring the security of wireless network is an essential part to its continuous growth. Goals such as confidentiality and trust imply that every data transmitted by each user stays known only to the communication parties. Authorization of users is also a very important aspect of network integrity. There existmechanisms defined by the Wi-Fi Protected Access (WPA) protocol that enable such functionality however, recent attacks on such systems showed that these mechanisms can be defined. In this paper, we propose a new scheme to authenticate and authorize 802.11 wireless nodes within a network. This new layer of security relies on a neural network decision engine that restricts network access to mobile nodes whose physical location is within a threshold distance from the wireless access point or the controller of the network. This method gives an extra layer of security and allows policies to be enforced which only allow network access from a certain section of the network. We give a detailed description of the work done as well as a performance simulation analysis of this scheme. [ABSTRACT FROM AUTHOR]

Abstract: Building a real-time (RT) control network using standard TCP/IP and Ethernet is often difficult, because the communication protocols usually have unpredictable time delays. When RT packets are transported within an ordinary Ethernet network, there may be a significant time delay before receiving them. This sometimes causes loop instability and performance degradation. A compensation scheme that consists of a fuzzy-PID controller and a neural network compensator is proposed here. This diminishes the influence from time delays on stability while maintaining the system performance. The proposed design is experimentally verified in the real-world network environment to show its effectiveness and applicability. [Copyright &y& Elsevier]

We consider the problem of traffic anomaly detection in IP networks. Traffic anomalies typically arise when there is focused overload or when a network element fails and it is desired to infer these purely from the measured traffic. We derive new general formulae for the variance of the cumulative traffic over a fixed time interval and show how the derived analytical expression simplifies for the case of voice over IP traffic, the focus of this paper. To detect load anomalies, we show it is sufficient to consider cumulative traffic over relatively long intervals such as S mm. We also propose simple anomaly detection tests including detection of over/underload. This approach substantially extends the current practice in IP network management where only the first-order statistics and fixed thresholds are used to identify abnormal behavior. We conclude with the application of the scheme to field data from an operational network. [ABSTRACT FROM AUTHOR]

Requirements for Distributed Monitoring and Control Networks (DMCN) differ greatly from those of typical data networks. Specifically, any DMCN technology which employs a fieldbus protocol is different from IP network protocol TCP/IP. In general, one needs to integrate fieldbus protocol and TCP/IP to realize DMCN over IP network or internet, which can be viewed as Virtual Device Network (VDN). Interoperability between devices and equipments is essential to enhance the quality and the performance of predictive maintenance (PM). This paper suggests a basic framework for VDN using DMCN over IP network and a method to guarantee interoperability between devices and equipments. [ABSTRACT FROM AUTHOR]

In recent years, with the continuous development of network science and technology and the continuous promotion of "three networks convergence", IPTV (Interactive Network Television) has shown a rapid development trend. IPTV is different from the traditional one-way broadcasting mode of television, it can achieve interaction with the audience, and provide more personalized and diversified videos. With the rapid development of new media, massive video resources and a large number of video-related information are sweeping in. The evaluation of video can no longer be limited to the ratings of traditional platforms. Video playback on new media platforms, network impact, video content and other related data are also important indicators affecting video evaluation. Video quality is closely related to video content characteristics. Different videos have different sensitivity to the same packet loss rate. The IPTV video quality evaluation model based on content features considers the video content characteristics. Firstly, the QP, bit rate and motion vector (MV) information of the video is obtained by analyzing the video stream. Then, the time complexity of the video is calculated by using the obtained MV, and the spatial complexity of the video is calculated by quantization parameters and bit rate. Videos are classified by clustering analysis. On this basis, the BP neural network is used to establish the model and evaluate the video quality, so as to better reflect the visual perception of the human eye. The model has low computational complexity and is suitable for IPTV video quality assessment with certain computing power in network nodes. [ABSTRACT FROM AUTHOR]