The Infona portal uses cookies, i.e. strings of text saved by a browser on the user's device. The portal can access those files and use them to remember the user's data, such as their chosen settings (screen view, interface language, etc.), or their login data. By using the Infona portal the user accepts automatic saving and using this information for portal operation purposes. More information on the subject can be found in the Privacy Policy and Terms of Service. By closing this window the user confirms that they have read the information on cookie usage, and they accept the privacy policy and the way cookies are used by the portal. You can change the cookie settings in your browser.
This paper mainly describes a search module, based on the BP neural network model, in Beijing Vocational College of Electronic Science Student Work Management System. The module is for selecting the appropriate work based on the machine learning. This module creates the BP model for every user and adjusts the weight and threshold of the BP model while students use the search module to browse other...
In this paper we present a Dynamic Sampling Framework for use with multi-class imbalanced data containing any number of classes. The framework makes use of existing sampling techniques such as RUS, ROS, and SMOTE and ties the classification algorithm into the sampling process in a wrapper like manner. In doing so the framework is able to search for a desirably sampled training set, thus eliminating...
The BP Neural Network's application in financial pre-warning is studied in this paper. Use the dynamic cluster method to classify enterprise's standardized data and get enterprise's pre-warning model through training the BP neural network using classified data. Discuss its implementation on computer in J2EE platform. Through taking test on the panel data, this method can provide accurate forecast...
Functional Network(FN) has been used in many field successfully, can not be found in blind equalization or detection. The original idea of blind signal detection directly algorithm using the framework of multi-input multi-output Functional Networks (MIMO-FN) is given out. The method of designing the network structure and the role of network state are shown. Then, the advantages and disadvantages of...
This paper presents a new BPNN model for image restoration by using area information around center pixel from degraded image and its edge image. This method gains edge image of blurred image by Sobel operator, and then uses BPNN model to build nonlinear restoration mapping relation by area pixel information from original and edge image. The edge information is extracted as a priori knowledge to recover...
To deal with the defects of BP neural networks used in balance control of inverted pendulum, such as longer train time and converging in partial minimum, this article reaLizes the control of double inverted pendulum with improved BP algorithm of artificial neural networks(ANN), builds up a training model of test simulation and the BP network is 6-10-1 structure. Tansig function is used in hidden layer...
This paper proposes a competitive stop Mahalanobis distance based expectation-maximization (CSMDEM) algorithm for learning a Gaussian mixture model (GMM) from multivariate data. This algorithm embeds a splitting failure condition and a competitive stop condition into the original Mahalanobis distance based EM (MDEM) algorithm. The goal of introducing the above two conditions is to avoid over-splitting...
A new image scrambling method is proposed in this paper. It is based on a folding transform with folding matrix which is orthogonal and enables us to fold images either up-down or left-right. When an image is folded through this way repeatedly, it becomes scrambled. The experimental results demonstrate that the proposed image scrambling algorithm has effective hiding ability for image information...
Analytic Hierarchy Process (AHP) is adopted to determine the weight of index for the comprehensive quality evaluation of the college students. The fuzzy theory is adopted for the level-four fuzzy judgment on the comprehensive quality. Based on results of the analysis and judgment, an improved algorithm for the comprehensive evaluation of the fuzzy neural network is produced. The BP algorithm is used...
The traditional evolutionary algorithm for teacher/class timetabling problem commonly evolves in a slow speed and trends to be stick to local optima. In this study, an immune-inspired evolutionary algorithm is proposed to solve the above problems. The algorithm utilizes the immune mechanisms including clonal selection, hypermutation, affinity evaluation, immune elimination and memory. The corresponding...
The paper focuses on the improvement by giving consideration to density degree of featured points', after carefully scrutinizing on feature matching algorithm, along with the former way to examine the similarity degree of featured points'. We decrease the threshold of correlation degree of corners, to avoid the unsuccessful matching by the unsuitable threshold setting. It is through the experiment...
A (t, n) threshold multi-secret sharing scheme based on the properties of a circle in multi-dimensional space is proposed in this paper. Only t or more shadows can reconstruct the secrets; while any less than t shadows cannot obtain any information of the secrets. One-way hash functions and a notice board are introduced to enable the secrets to be distributed efficiently. When the dealer computes...
Infeasible paths increase program complexity and program redundancy, generate useless DU(def-use) chains, and affect the result of program static analysis. Based on the valid information produced in the process of program compilation, this paper presents a translucent technique to analyze infeasible paths. It first requires the complier construct an information pool for each judge node and variables...
ROUSTIDA algorithm is used to data completing in rough set for incomplete information systems, however its coverage is not good enough. To solve the problem, an improved algorithm is proposed from the angle of group decision. Direction-area of attributes on columns and simple-majority-rule ratio of objects on rows of decision table is defined respectively, and they are combined with ROUSTIDA algorithm,...
Short range wireless technologies such as WLAN, Bluetooth, RFID, ultrasound and IrDA can be used to supply location information in indoor areas in which their coverage is assured. With respect to outdoor techniques, these technologies are more accurate but with smaller covering areas. In this paper, we present the comparison of the existing location techniques in WLAN networks and a novel approach...
The nonlinear transmission control protocol (TCP) dynamic model in the domain of Internet congestion control is considered in this paper. An observer is designed to estimate the unmeasured state. By applying the backstepping recursive technique and Lyapunov direct method, a kind of active queue management (AQM) algorithm is designed to asymptotically stabilize the closed-loop system through output...
In this paper, we proposed a sampling based FANT (S-FANT) for the 3-dimensional assignment problem (AP3). The AP3 is a well-known NP-hard problem, which aims to choose n disjoint triplets with minimum cost from 3 disjoint sets of size n. Due to its intractability, many heuristics have been proposed to obtain near optimal solutions in reasonable time. Since the solution space size of the AP3 is (n!)...
With the development of optimization heads toward large-scale problems, a series of optimization packages were developed for large-scale NLP optimization. The RSQP (reduced sequential quadratic programming) we concerned is one of best large scale NLP algorithm, and is especially efficient in process operation optimization. In this paper, the performance of our concerned algorithm RSQP, CONOPT2 and...
Measuring oxygen content in flue gas timely and accurate is the assurance of the high combustion efficiency in power plant. This paper presents a Adaptive Sequential Minimal Optimization (ASMO) algorithm combined with selection parameter algorithm based on Support Vector Machine (SVM) and Sequential Minimal Optimization (SMO) algorithm. It build the grey soft-sensing model for oxygen content in flue...
Set the date range to filter the displayed results. You can set a starting date, ending date or both. You can enter the dates manually or choose them from the calendar.