- نمایش 15 محصول در هر صفحه
A machine learning bayesian network for refrigerant charge faults of variable refrigerant flow air conditioning system
0 تومانAn intelligent fault diagnosis network for variable refrigerant flow air conditioning system is proposed in this study. The network is developed under the foundation of bayesian belief network theory, which comprises two main elements: the structure and parameters. The structure obtained by machine learning and experts’ experiences illustrates the relationships among faults and physical variables from the qualitative prospective, and its parameters (including prior probability distribution and conditional distribution) describe the uncertainty between them quantitatively. Once the structure and parameters are determined, the posterior probability distribution which can be used to complete fault diagnosis and isolation will be calculated by some algorithms. In comparison with other fault diagnosis approaches, the proposed approach can make full use of performance information. Moreover, it is more reasonable and precise to express the relationship between faults and variables rather than Boolean variables. Evaluation was conducted on a variable refrigerant flow air conditioning system, which demonstrated that this strategy is effective and efficient.
A Neural Network Based Expert System for the Diagnosis of Diabetes Mellitus
0 تومانDiabetes is a disease in which the blood glucose, or blood sugar levels in the body are too high. The damage caused by diabetes can be very severe and even more pronounced in pregnant women due to the tendency of transmitting the hereditary disease to the next generation. Expert systems are now used in medical diagnosis of diseases in patients so as to detect the ailment and help in providing a solution to it. This research developed and trained a neural network model for the diagnosis of diabetes mellitus in pregnant women. The model is a four-layer feed forward network, trained using back-propagation and Bayesian Regulation algorithm. The input layer has 8 neurons, two hidden layers have 10 neurons each, and the output layer has one neuron which is the diagnosis result. The developed model was also incorporated into a web-based application to facilitate its use. Validation by regression shows that the trained network is over 92% accurate.
A robust and anonymous patient monitoring system using wireless medical sensor networks
0 تومانIn wireless medical sensor network (WMSN), bio-sensors are implanted within the patient body to sense the sensitive information of a patient which later on can be transmitted to the remote medical centres for further processing. The patient’s data can be accessed using WMSN by medical professionals from anywhere across the globe with the help of Internet. As the patient sensitive information is transmitted over an insecure WMSN, so providing the secure access and privacy of the patient’s data are various challenging issues in WMSN nvironments. To provide secure data access, in the literature very less number of user authentication protocols are available. But, most of these existing protocols may not be applicable to WMSNs for providing user’s anonymity. In this article, we propose an architecture for patient monitoring health-care system in WMSN and then design an anonymitypreserving mutual authentication protocol for mobile users. We used the AVISPA tool to simulate the proposed protocol. Theresults obtained indicate that the proposed authentication protocol resists the known attacks. In addition, the BAN logic model confirms mutual authentication feature of the proposed protocol. Moreover, an informal cryptanalysis is also given, which ensures that the proposed protocol withstands all known attacks. We perform a comparative discussion of the proposed protocol against the existing protocols and the comparative results demonstrate that the proposed protocol is efficient and robust. Specifically, the proposed protocol is not only effective for complexity and robustness against common security threats, but it also offers efficient login, robust mutual authentication, and user-friendly password change phases.
Application of Analytic Hierarchy Process in Network Level Pavement Maintenance Decision-making
0 تومانThis paper proposes an Analytic Hierarchical Process (AHP) theory based method to determine the weight of the decision-making influence factors, considering their relative significance and generating an overall ranking for each road section. A case study on the highway network maintenance priority was conducted to illustrate the proposed procedure. A total of five pavement maintenance decision-making related factors were considered in the study, including pavement performance, pavement structure strength, traffic loads, pavement age and road grade. The weightings of the five factors were quantified through AHP method. Then, the comprehensive ranking index value Ui was determined, which indicated the maintenance priority of a road section in network level decision-making. From the aspect of maintenance cost, the sensitivity analysis results were in accordance with the weightings of different maintenance decision-making factors. The pavement maintenance cost was significantly sensitive to the change of pavement performance. The case study clearly demonstrated the applicability and rationality of the AHP .theory based decision-making method and it can be used as a guideline for pavement maintenance agencies
CAMP: cluster aided multi-path routing protocol for wireless sensor networks
0 تومانIn this article, we propose a novel routing algorithm for wireless sensor network, which achieves uniform energy depletion across all the nodes and thus leading to prolonged network lifetime. The proposed algorithm, divides the Region of Interest into virtual zones, each having some designated cluster head nodes. In the entire process, a node can either be a part of a cluster or it may remain as an independent entity. A non-cluster member transmits its data to next hop node using IRPIntelligent Routing Process (based on the trade-off between the residual energy of itself as well as its neighbor, and therequired energy to transmit packets to its neighbor). If on the transmission path, some cluster member is elected as a next hop, it rejects IRP and transmits the packets to cluster head, which later forwards them to sink (adopting multihop communication among cluster heads). Routing is not solely performed using clusters, rather they aid the overall routing process, hence this protocol is named as Cluster Aided Multipath Routing (CAMP). CAMP has been compared with various sensor network routing protocols, viz., LEACH, PEGASIS, DIRECT TRANSMISSION, CEED, and CBMR. It is found that the proposed algorithm outperformed them in network lifetime, energy consumption and coverage ratio.
Deep Artificial Neural Networks as a Tool for the Analysis of Seismic Data
0 تومانThe number of seismological studies based on artificial neural networks has been increasing. However, neural networks with one hidden layer have almost reached the limit of their capabilities. In the last few years, there has been a new boom in neuroinformatics associated with the development of third- generationnetworks, deep neural networks. These networks operate with data at a higher level. Unlabeled data can be used to pretrain the network, i.e., there is no need for an expert to determine in advance the phenomenon to which these data correspond. Final training requires a small amount of labeled data. Deep networks have a higher level of abstraction and produce fewer errors. The same network can be used to solve several tasks at the same time, or it is easy to retrain it from one task to another. The paper discusses the possibility of applying deep networks in seismology. We have described what deep networks are, their advantages, how they are trained, how to adapt them to the features of seismic data, and what prospects are opening up in connection with their use.
Do personality characteristics explain the associations between self-esteem and online social networking behaviour?
0 تومانThe relationships between online social networking (OSN) behaviour and users’ selfesteem are as important as well as ambiguous: Both positive and negative self-esteem can encourage users to engage in OSNs. This work examined whether personality traits and attitudes toward traits can explain this controversy. Data from 830 users of a local OSN were analysed. I hypothesised that extraversion and attitudes toward extraversion eliminated correlations between positive self-esteem and users’ popularity (the number of friends and likes). In contrast, neuroticism and attitudes toward neuroticism failed to eliminate a negative correlation between self-esteem and an indicator of users’ self-validation (the number of impersonal avatars). This association also remained significant when conscientiousness as well as negative attitudes toward conscientiousness and agreeableness were controlled. However, self-esteem did not correlate with the two other self-validation indicators―the number of posts and portraits. This study casts doubt on the possibility of direct associations between positive self-esteem and users’ popularity beyond such factors as extraversion. Nevertheless, it lends partial support to the association between negative self-esteem and users’ self-validation such as the use of impersonal .avatars even when other personality characteristics are considered
EMD2FNN: A strategy combining empirical mode decomposition and factorization machine based neural network for stock market trend prediction
0 تومانStock market forecasting is a vital component of financial systems. However, the stock prices are highly noisy and non-stationary due to the fact that stock markets are affected by a variety of factors. Predicting stock market trend is usually subject to big challenges. The goal of this paper is to introduce a new hybrid, endto-end approach containing two stages, the Empirical Mode ecomposition and Factorization Machine basedNeural Network (EMD2FNN), to predict the stock market trend. To illustrate the method, we apply EMD2FNN to predict the daily closing prices from the Shanghai Stock Exchange Composite (SSEC) index, the National Association of Securities Dealers Automated Quotations (NASDAQ) index and the Standard & Poor’s 500 Composite Stock Price Index (S&P 500), which respectively exhibit oscillatory, upward and downward patterns. The results are compared with predictions obtained by other methods, including the neural network (NN) model, the factorization machine based neural network (FNN) model, the empirical mode decomposition based neural network (EMD2NN) model and the wavelet de-noising-based back propagation (WDBP) neural network model.
Under the same conditions, the experiments indicate that the proposed methods perform better than the other ones according to the metrics of Mean Absolute Error (MAE), Root Mean Square Error (RMSE) and Mean Absolute Percentage Error (MAPE). Furthermore, we compute the profitability with a simple long-short trading strategy to examine the trading performance of our models in the metrics of Average Annual Return (AAR), Maximum Drawdown (MD), Sharpe Ratio (SR) and AAR/MD. The performances in two different scenarios, when taking or not taking the transaction cost into consideration, are found economically significant.Hidden Markov Model based channel selection framework for cognitive radio network
0 تومانDue to the effective utilization rate of the radio frequency spectrum, Cognitive Radio Network (CRN) has gained more popularity in the current research field. The spectrum sensing techniques detect the presence of the idle channel and reallocate to the Secondary Users (SUs). However, the existing spectrum sensing and channel estimation approaches incursdelay while searching for the new channels. To reduce the delay and achieve optimal selection of the channel in CRN, this paper proposes a Hidden Markov Model (HMM)-based channel selection framework. The Time-Slot based optimal routing mechanism is introduced to minimize the delay occurred during the channel search and optimize the rangeof the spectrum band. Therefore, the bandwidth range of the node is estimated, and the channel is allocated to the SU. The proposed framework exhibit better end-to-end throughput, bandwidth-power product and lower running time, energy consumption, and average end-to-end delay when compared to the existing schemes.
Hybrid energy-efficient APTEEN protocol based on ant colony algorithm in wireless sensor network
0 تومانDue to the limited energy of the sensor nodes, the unreasonable clustering routing algorithm will cause node premature death and low utilization of energy efficiency in wireless sensor network (WSN). In Adaptive hresholdsensitive Energy Efficient Network (APTEEN), the assignments of the cluster head (CH) are much heavier than other nodes. The CH unbalanced energy dissipation between nodes that make them die prematurely. Ant colony algorithm can avoid this problem, so this paper presents a double cluster heads Adaptive Threshold-sensitive Energy Efficient Network based on ant colony (ADCAPTEEN). ADCAPTEEN optimizes the cluster head election method compared with APTEEN. It suggests that one master cluster head (MCH) and one vice cluster head (VCH) will be selected in each cluster. The double cluster heads (DCH) can co-work on data collection, fusion, transition, etc. To make routes more stable and energy efficient, this paper proposes a Multiple Adaptive Threshold-sensitive Energy Efficient Network based on Ant-colony (AMAPTEEN). It is the optimization of ADCAPTEEN. And CH selects intermediate node (IM_node) multiple times with ant colony algorithm per round in each cluster, and this way forms multiple route transmission data. Simulation in OPNET proves that compared with APTEEN, ADCAPTEEN reduces energy dissipation, improves node survival rate, and extends network life cycle. AMAPTEEN delays the time of node death, balances energy consumption, and extends network lifetime further operating in the same settings compared with ADCAPTEEN. The proposed two algorithms have good scalability, and they are suitable for large-scale network.
Impact of random weights on nonlinear system identification using convolutional neural networks
0 تومانRandomized algorithms have been successfully applied in modelling dynamic system. How do random weights affect system identification and why do they sometimes work well? In this paper, we use the convolutional neural network (CNN) as an identification model to answer these questions. Since the convolution operation is an important property of the dynamic system and in the frequency domain it becomes the product, the CNN model is analyzed inthe frequency domain. We first modify the CNN model, so that it can model both the input and the output series. Then we analyze the impact of the random weights of CNN in the frequency domain. We prove the existence of optimal weights and analyze the modeling accuracy under optimal weights and random weights. Through theoretical analysis, we propose a two-step training method and compare it with the random weight algorithm. .The proposed CNN model with random weights is validated with three benchmark problems
IoT security: Review, blockchain solutions, and open challenges
0 تومانWith the advent of smart homes, smart cities, and smart everything, the Internet of Things (IoT) has emerged as an area of incredible impact, potential, and growth, with Cisco Inc. predicting to have 50 billion connected devices by 2020. However, most of these IoT devices are easy to hack and compromise.Typically, these IoT devices are limited in compute, storage, and network capacity, and therefore they are more vulnerable to attacks than other endpoint devices such as smartphones, tablets, or computers. In this paper, we present and survey major security issues for IoT. We review and categorize popular security issues with regard to the IoT layered architecture, in addition to rotocols used for networking, communication, and management. We outline security requirements for IoT along with the existing attacks, threats, and state-of-the-art solutions. Furthermore, we tabulate and map IoT security problems against existing solutions found in the literature. More importantly, we discuss, how blockchain, which is the underlying technology for bitcoin, can be a key enabler to solve many IoT security problems. The paper also identifies open research problems and challenges for IoT security.
IoT security: Review, blockchain solutions, and open challenges
0 تومانWith the advent of smart homes, smart cities, and smart everything, the Internet of Things (IoT) has emerged as an area of incredible impact, potential, and growth, with Cisco Inc. predicting to have 50 billion connected devices by 2020. However, most of these IoT devices are easy to hack and compromise. Typically, these IoT devices are limited in compute, storage, and network capacity, and therefore they are more vulnerable to attacks than other endpoint devices such as smartphones, tablets, or computers. In this paper, we present and survey major security issues for IoT. We review and categorize popular security issues with regard to the IoT layered architecture, in addition to protocols used for networking, communication, and management. We outline security requirements for IoT along with the existing attacks, threats, and state-of-the-art solutions. Furthermore, we tabulate and map IoT security problems against existing solutions found in the literature. More importantly, we discuss, how blockchain, which is the underlying technology for bitcoin, can be a key enabler to solve many IoT security problems. The paper also identifies open research problems and challenges for IoT .security
Modeling and maximizing influence diffusion in social networks for viral marketing
0 تومانModeling influence diffusion in social networks is an important challenge. We investigate influence-diffusion modeling and maximization in the setting of viral marketing, in which a node’s influence is measured by the number of nodes it can activate to adopt a new technology or purchase a new product. One of the fundamental problems in viral marketing is to find a small set of initial adopters who can trigger the most further adoptions through word-of-mouth-based influence propagation in the network. We propose a novel multiple-path asynchronous threshold(MAT) model, in which we quantify influence and track its diffusion and aggregation. Our MAT model captures not only direct influence from neighboring influencers but also indirect influence passed along by messengers. Moreover, our MAT framework models influence attenuation along diffusion paths, temporal influence decay, and individual diffusion dynamics. Our work is an important step toward a more realistic diffusion model. Further, we develop an effective and efficient heuristic to tackle the influence-maximization problem. Our experiments on four real-life networks demonstrate its excellent performance in terms of both influence spread and time efficiency. Our work provides preliminary but significant insights and implications for diffusion research .and marketing practice
Multi-objective Embedding of Software-Defined Virtual Networks
0 تومانSoftwarization is the current trend of networking based on the success of technologies like Software Defined Networking (SDN) and Network Virtualization. Network as a Service (NaaS) is a new paradigm based on virtualization that enables customers toinstantiate their virtual networks over a physical substrate network, mapping necessary resources by a Virtual Network Embedding (VNE) algorithm. Each VNE algorithm defines a resource allocation strategy of the NaaS provider, and determines its expenditures and revenues. Even though the problem of VNE has been widely investigated in recent years, virtualization in SDN introduces new challenges due to the new role of the controller and additional architectural constraints. In this paper, we investigate the VNE problem whereboth virtual and substrate networks are software defined. We propose a mathematical programming formulation that considers both the objectives of the NaaS provider (profit maximization) and the customers (switch-controller delay minimization). Proposing new design metrics (i.e., k-hop delay, correlation, and distance), we develop a heuristic algorithm,and prove its effectiveness through extensive simulations in the well-known VNE evaluation tool, ALEVIN, and comparisons with other algorithms and mathematical bounds.
