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.
The presence of Lombard Effect in speech is proven to have severe effects on the performance of speech systems, especially speaker recognition. Varying kinds of Lombard speech are produced by speakers under influence of varying noise types [1]. This study proposes a high-accuracy classifier using deep neural networks for detecting various kinds of Lombard speech against neutral speech, independent...
GNSS scalar tracking loop tracks each satellite signal in one channel separately, while vector tracking loop track all of the satellite signals in one navigation filter. Three major advantages of the vector tracking loop are reduction of estimated parameters, aiding weak signal tracking by strong signal and aiding signal tracking by navigation solutions. Differ from the former researches in which...
Contactless palmprint recognition systems alleviate the concerns on personal hygiene, acquisition flexibility, etc. Unfortunately, the preprocessing of contactless palmprint image faces several severe challenges, including unconstrained hand placement, complex background, light interference, etc. This paper proposes logical conjunction of triple-perpendicular-directional translation residual (TPDTR)...
Distribution of data stream is always changed in the real world. This problem is usually defined as concept drift [1]. The state-of-the-art decision tree classification method CVFDT[2] can solve the concept drift problem well, but the efficiency is debased because of its general method of handling instances in CVFDT without considering the types of concept drift. In this paper, an algorithm called...
Remaining useful life (RUL) estimation is an important part in modern prognostic and health management (PHM) approach. In this paper, a particular prognostic named similarity-based RUL estimation is proposed. In some complex condition, typical methods will perform inefficient, and in engineering application background, some traditional methods may be hard implemented. On the other hand, similarity-based...
Locality sensitive hashing (LSH) has been introduced as an indexing structure for fast large-scale data retrieval. A significant drawback of this technique is that a large number of hash functions require lots of hash computation time. To resolve this issue, the paper presents a new index construction algorithm called boundary-expanding LSH, where the boundary of each bucket is expanded so that each...
Based on Atmel Corporation's microcontroller ATmega16L and ultrasonic sensor TCT40-16F, designs an ultrasonic measurement and alarm system with high precision. Using the method of MJ echo capture, the system can realize measuring the distance well and truly, and can send the real time distance data to the LCD screen of system. Once the distance was less than the setting value, the system would alarm...
This paper presents an improved pruning method taking into account of the number of states possessed by hypotheses in some certain frames. With conventional pruning strategy, the hypotheses with a low score or a bad ranking will be discarded. However, it neglects a fact that the hypotheses several states ahead of or behind the right hypothesis in the prefix tree, which should be discarded, have similar...
Using melody and/or lyric to query a music retrieval system is convenient for users but challenging for developers. This paper proposes efficient schemes for realizing key algorithms in such a kind of system. Specifically, we characterize our system by adding lyric to query as follows: A Support Vector Machine (SVM) is employed to distinguish humming queries from singing queries, For a singing query,...
Nearest neighbor problem has recently been a research focus, especially on large amounts of data. Locality sensitive hashing (LSH) scheme based on p-stable distributions is a good solution to the approximate nearest neighbor (ANN) problem, but points are always mapped to a poor distribution. This paper proposes a set of new hash mapping functions based on entropy for LSH. Using our new hash functions...
In this paper we propose a methodology of multilayer filters based on tempo variation for realizing a query by humming (QBH) system. Firstly the original query clip is used to search for the candidate songs. If the results are unreliable, the clip is linearly scaled twice for more candidates. If the results are still unreliable, the clip is scaled more times for retrieval. To sort all the candidates,...
on mobile terminals, voice-based local search services are quickly becoming a new important application. Voice search is essentially a large vocabulary speech recognition task with an open ended vocabulary, and this is a problem because speed and accuracy are essential for a good user experience. Fortunately when a user submits a local search query, contextual information such as the user's current...
With the wide application of web database, Web pages are continuously deepened. In order to use Deep Web resources effectively, the Deep Web data need to be integrated on a large scale, and data sources discover is the primary work of Deep Web resources integration. The Deep Web site found efficiently is the key of the Deep Web data Integration. This paper puts forward a kind of Deep Web entry automatic...
According to the Optimization Design of a single-precision-floating divider based on SRT, Using VHDL on a FPGA Chip and linking the Flying Transition, the author improved the length of time-lag of the key component on the divider so that the divider is suitable for the demands of adptive speech coding for its higher precision and wider operating range. In the article, the pre-sim and the post-sim...
Lacking of dataset is still a serious problem for researchers who study on online handwriting word recognition (HWR). In this paper, a handwritten Chinese word synthesis method is proposed for the first time to generate a large scale handwritten Chinese word dataset. The distributions of shape and position characteristics, such as aspect radio, character interval and the angle of gravity center line...
An approach to identification of the phishing target of a given (suspicious) webpage is proposed by clustering the webpage set consisting of its all associated webpages and the given webpage itself. We first find its associated webpages, and then explore their relationships to the given webpage as their features for clustering. Such relationships include link relationship, ranking relationship, text...
In this paper, a polymorphic viruses detection method based on neural network ensemble in the Windows platform is proposed. Our approach rests on an analysis using the Windows API calling sequence that reflects the behavior of a particular piece of code. Firstly, the system calling sequence of a program is extracted as eigenvector, and then bootstrap sampling is employed to generate several training...
In high dimensional data space, clusters are likely to exist in different subspaces. K-means is a classic clustering algorithm, but it cannot be used to find subspace clusters. In this paper, an algorithm called GKM is designed to generalize k-means algorithm for high dimensional data. In the objective function of GKM, we associate a weight vector with each cluster to indicate which dimensions are...
As a new modeling thought, the accurate soft sensing model of power plant parameter was established by data mining method, which obtained effective information from the large number of real-time operation data and avoided low accuracy of conventional modeling method caused by some assumption. A kind of basic modeling mode, including data preprocessing, mining model, verification model and the strategy...
As an important method for the evaluation of quantity of area rainfall, Thiessen polygon method is widely applied because of its high calculation accuracy and fast computation. The calculation of Thiessen polygon method is simple because only area data of sample point is needed. When dataset is stable, accuracy of Thiessen polygon method is higher than the arithmetic average method. But there are...
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.