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.
Based on model reference adaptive control (MRAC), a MRAC synchronous controller is designed. And the reference model of the MRAC is determined according to the linear mathematical model of the electro-hydraulic servo system. Then the synchronous controller is applied to position synchronization of two cylinders system. The experiment results show that the proposed controller can effectively reduce...
This research aims to investigate the required sample size of probe vehicles that are necessary to report the real-time travel time with a desired statistical accuracy in different traffic conditions on freeways. The corridor studied is SR78-E in the North County of San Diego that connects Oceanside and Escondido. The field data used in this study was collected from PeMS during the period from 0:00...
This paper proposes a novel people counting method based on head detection and tracking to evaluate the number of people who move under an over-head camera. There are four main parts in the proposed method: foreground extraction, head detection, head tracking, and crossing-line judgment. The proposed method first utilizes an effective foreground extraction method to obtain foreground regions of moving...
Preserving sample's pair wise similarity is essential for feature selection. In supervised learning, labels can be used as a direct measure to check whether two samples are similar with each other. In unsupervised learning, however, such similarity information is usually unavailable. In this paper, we propose a new feature selection method through spectral clustering based on discriminative information...
It has great significance to analyze the kinematics reliability of the manipulator, which can reflect the motion performance comprehensively. In paper, kinematics reliability of manipulator is discussed, and the mathematical description is derived when the manipulator is kinematics reliable. Taking elasticity factors into account, a multi-level model for the pose (position and posture) accuracy of...
Scalability to large numbers of classes is an important challenge for multi-class classification. It can often be computationally infeasible at test phase when class prediction is performed by using every possible classifier trained for each individual class. This paper proposes an attribute-based learning method to overcome this limitation. First is to define attributes and their associations with...
Node localization is one of the important issues in wireless sensor networks. In order to lower the cost of a sensor network and improve localization accuracy and efficiency, we put forward a virtual cluster based mobile beacon aided localization algorithm (VCMBLA) in this paper. A multi-hop distance estimation method based on neighbor distribution (MDEND) is presented and a path planning strategy...
Transfer learning aims to improve a targeted learning task using other related auxiliary learning tasks and data. Most current transfer-learning methods focus on scenarios where the auxiliary and the target learning tasks are very similar: either (some of) the auxiliary data can be directly used as training examples for the target task or the auxiliary and the target data share the same representation...
This paper presents an active learning approach for recognizing human actions in videos based on multiple kernel combined method. We design the classifier based on Multiple Kernel Learning (MKL) through Gaussian Processes (GP) regression. This classifier is then trained in an active learning approach. In each iteration, one optimal sample is selected to be interactively annotated and incorporated...
This paper presents a unified framework for recognizing human action in video using human pose estimation. Due to high variation of human appearance and noisy context background, accurate human pose analysis is hard to achieve and rarely employed for the task of action recognition. In our approach, we take advantage of the current success of human detection and view invariability of local feature-based...
We introduce a new method for classification called the influence machine. The influence machine assigns influence powers to the instances in the training sample so that they can apply their influence to other instances through the connections between the instances specified by a connection matrix. A new instance is classified to be positive if the overall influence it receives is positive and vice...
Recently traffic identification based on Machine Learning (ML) techniques has attracted a great deal of interest. Two challenging issues for these methods are how to deal with encrypted flows and cope with the rapid growing number of new application types correctly and early. We propose a hybrid traffic identification method and a novel unsupervised clustering algorithm, On-Line Density Based Spatial...
In this paper, we present a robust framework for action recognition in video, that is able to perform competitively against the state-of-the-art methods, yet does not rely on sophisticated background subtraction preprocess to remove background features. In particular, we extend the Implicit Shape Modeling (ISM) of [10] for object recognition to 3D to integrate local spatiotemporal features, which...
With pixel un-mixing, the omission of pixel caused by mixed pixel can be resolved so as to improve the classification accuracy. But the trouble is only the proportion of each end member object in one pixel which can be got through pixel un-mixing, while the spatial distribution of is uncertain. The objective of this study is to introduce the sub-pixel mapping based on spatial attraction model and...
Transfer learning is a new learning paradigm, in which, besides the training data for the targeted learning task, data that are related to the task (often under a different distribution) are also employed to help train a better learner. For example, out-dated data can be used as such related data. In this paper, we propose a new transfer learning framework for training neural network (NN) ensembles...
Indexing and query multimedia data is a challenging problem due to the high dimension of multimedia data. Clustering-based indexing structures are quite efficient for high-dimensional data indexing. Unfortunately, clustering-based indexing structures are normally static, and the whole structures have to be rebuilt after inserting new data. To resolve this issue, a two-level indexing method, called...
Traffic classifications based on Statistics methods and Machine Learning techniques have attracted a great deal of interest. One challenging issue is that most of supervised algorithms need traffic application information and training data sets to generate classification model offline, which is infeasible to cope with the fast growing number of new applications and online traffic classifications....
Recently traffic classifications based on statistics methods and machine learning techniques have attracted a great deal of interest. Some challenging issues for these methods are that most of them need prior analysis to detect traffic applications and training data sets to generate classification model offline; some require a high amount computation and memory resource. These are infeasible to cope...
Efficiently and accurately detecting pedestrians plays a crucial role in many vision applications such as video surveillance, multimedia retrieval and smart car etc. In order to find the right feature for this task, we first present a comprehensive experimental study on pedestrian detection using state-of-the-art locally-extracted features. Building upon our findings, we propose a new, simpler pedestrian...
The watch crystal oscillator can achieve very-low-power time-keeping, even less than 1 muW, which best overall accuracy with temperature-compensation has remained at about 1 ppm. For comparison, the timing system using microprocessor compensated (AT or SC-cut) crystal oscillator is capable of providing at least 10- to 100-times improvement in time-keeping accuracy, milliseconds-per-day, with the penalty...
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.