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 presents an activity detection system using dendrite threshold logic neuron models. This method generates a dendrite weight matrix from the background image and detect the changes in the subsequent images through the trained neuron outputs. Using only one layer of dendrite neuron cells with simplistic threshold logic cells, an accuracy of 98% is reported in realistic imaging conditions...
We propose a new method for fitting an ellipse to a point sequence extracted from an image. This method can fit an ellipse if a point sequence consists of elliptic arcs and non-elliptic arcs such as line segments. Assuming that input points are spatially connected, we iteratively select inlier points and fit an ellipse to them by computing curvatures of the residual graph. By using simulated data...
It is difficult for least square method (LS) to deal with the ill-conditioned matrix of nonlinear polynomial model. In the case of the higher order of system, the matrix inversion is very complicated. A new approach based on LS is present which is combined with mirror-injection algorithm in order to obtain polynomial parameters identification of nonlinear system model. The columns of coefficient matrix...
It has always been difficult to accurately estimate the moment of inertia of an object, e.g. an unmanned aerial vehicle (UAV). Whilst various offline estimation methods exist to allow accurate parametric estimation by minimizing an error cost function, they require large memory consumption, high computational effort, and a long convergence time. The initial estimate's accuracy is also vital in attaining...
To satisfy cost constraints, application implementation in embedded systems requires fixed-point arithmetic. Thus, applications defined in floating-point arithmetic must be converted into a fixed-point specification. This conversion requires accuracy evaluation to ensure algorithm integrity. Indeed, fixed-point arithmetic generates quantization noises due to some bits elimination during a cast operation...
A key issue in system identification is how to cope with high system complexity. In this contribution we stress the importance of taking the application into account in order to cope with this issue. We define the concept “cost of complexity” which is a measure of the minimum required experimental effort (e.g. used input energy) as a function of the system complexity, the noise properties, and the...
Target tracking is one of the most important applications for wireless sensor networks (WSNs). It is usually assumed that the knowledge of the sensor nodes' position is known precisely. However, practically nodes are randomly deployed without prior knowledge about their own positions. In this situation, simultaneous localization and tracking (SLAT) is necessary and is receiving more and more research...
Human listeners are capable of recognizing speech in noisy environment, while most of the traditional speech recognition methods do not perform well in the presence of noise. Unlike traditional Mel-frequency cepstral coefficient (MFCC)-based method, this study proposes a phoneme classification technique using the neural responses of a physiologically-based computational model of the auditory periphery...
Classification is a supervised learning technique typically uses two-thirds of the given annotated data set for training and the remaining for test. In this paper, we developed a frame work which uses less than one-third of the data set for training and tests the remaining two-thirds of the data and still gives results comparable to other classifiers. To achieve good classification accuracy with small...
Almost every computer vision applications used background subtraction method to detect moving objects from video sequence. Moving object detection and tracking is generally the first step in many applications such as face detection, traffic surveillance, object recognition, detection of unattended bags, people counting etc. Background modeling is very useful and effective method for locating objects...
In this work, we employ a pair wise Markov Random Field (MRF) and a Conditional Random Field (CRF) for bi-level image segmentation and denoising. For both tasks, the Ising pair wise model and the Iterative Conditional Mode (ICM) inference method are implemented, assuming the parameters of the unary and pair wise potentials are known. Experimental results demonstrate the effectiveness of the proposed...
The provision of reliable location estimates in WiFi fingerprinting localization is challenging, mainly because users typically carry heterogeneous devices that report Received Signal Strength (RSS) measurements from surrounding Access Points (AP) very differently. This may render the user-carried device incompatible with the fingerprinting system, in case the RSS radiomap was collected with a different...
In this study, we closely examined the performance of inverse solution in terms of equivalent dipole source model. To simulate potential distribution on the body surface, we employed an analytical model of a single current dipole (or a pair of current dipoles) placed within the homogeneous isotropic volume conductor consisting of two non-concentric spheres. Using these data, we evaluated the accuracy...
Estimating extremely low SRAM failure-probabilities by conventional Monte Carlo (MC) approach requires hundreds-of-thousands simulations making it an impractical approach. To alleviate this problem, failure-probability estimation methods with a smaller number of simulations have recently been proposed, most notably variants of consecutive mean-shift based Importance Sampling (IS). In this method,...
Work in indoor positioning so far broadly relies on either signal propagation models or location fingerprinting. The former approach has inherent modelling complexity as a result of intervening walls and movement in the environment which, impacts the accuracy of such models. The latter approach on the other hand, is acclaimed to give better accuracy. However, for it to be used, an added overhead of...
The STRATUS project seeks to provide resilience against cyber threats to distributed systems. STRATUS is designed to anticipate, diagnose, and respond proactively to threats. It uses a reactive technique to respond to the latest events quickly and a more `strategic' technique that recognizes attack plans and responds to them proactively. We focus on a set of experiments where we approximate the behavior...
This paper deals with people counting in stores for business analytics using stereo vision. Among the several problems in this type of applications, two are the most relevant for our purposes: the management of occlusions and the distinction between adult people (potential customers) and other objects (children, trolleys, strollers, animals, etc.). The proposed solution uses a novel approach for object...
Cloud based systems(CBSs) are increasing in the computing world. These systems derive their complexity due to both the disparate components and the diverse stake holders involved in them. The component wise security alone does not solve the problem of securing CBSs, but the stakeholder's computational space spanning across many components of the CBS, needs to be secured too. There have been initial...
Empirical evidence shows that massive data sets have rarely (if ever) a stationary underlying distribution. To obtain meaningful classification models, partitioning data into different concepts is required as an inherent part of learning. However, existing state-of-the-art approaches to concept drift detection work only sequentially (i.e. in a non-parallel fashion) which is a serious scalability limitation...
Simultaneous switching noise (SSN) continues to play an important role in single-ended signaling systems. Modeling and simulating SSN is quite challenging as it requires a complex system model comprised of numerous signal, power, and ground conductors and planes. An efficient modeling approach based on the special property associated with SSN simulation assumptions was published previously. It assumed...
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.