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.
We investigate the problem of churn detection and prediction using sequential cellular network data. We introduce a cleaning and preprocessing of the dataset that makes it suitable for the analysis. We draw a comparison of the churn prediction results from the-state-of-the-art algorithms such as the Gradient Boosting Trees, Random Forests, basic Long Short-Term Memory (LSTM) and Support Vector Machines...
Use of Wireless Multimedia Sensor Networks has significantly revolutionized the field of communication and has provided an ease for researchers to get a clear insight of areas which were inaccessible to human beings. The concerning part of the Wireless Multimedia Sensor Networks is its limited living period or energy constraint, small size, limited bandwidth, low processing speed and inaccessibility...
We study online sequential logistic regression for churn detection in cellular networks when the feature vectors lie in a high dimensional space on a time varying manifold. We escape the curse of dimensionality by tracking the subspace of the underlying manifold using a hierarchical tree structure. We use the projections of the original high dimensional feature space onto the underlying manifold as...
Motivated by recent interest in deep brain stimulation and its application to the treatment of neurological diseases, this paper addresses the problem of synchronization control for a class of interconnected compartmental models. In view of the measurement and actuation constraints typical of biological systems, it is assumed that the information available for feedback is a mean field quantity. It...
We study online sequential regression with nonlinearity and time varying statistical distribution when the regressors lie in a high dimensional space. We escape the curse of dimensionality by tracking the subspace of the underlying manifold using a hierarchical tree structure. We use the projections of the original high dimensional regressor space onto the underlying manifold as the modified regressor...
Wireless multimedia sensor networks have captured the attention of many due to their portability and their easy access in hard-to-access areas. They consist of a group of sensor nodes with their own transceiver and power source. The optimal connection and structure of these components allows the wireless multimedia sensor network to effectively measure and sense the physical characteristics of the...
We address nonlinear sequential regression in high dimensional settings when the data lies on a time varying manifold. We solve the curse of dimensionality by tracking the subspace of the underlying manifold using a hierarchical tree structure. Therefore, instead of using the original feature vectors as the input, we use the projections of the high dimensional feature space onto the underlying manifold...
Wireless sensor networks (WSNs) are receiving more popularity in mission critical and delay sensitive industrial applications because they offer low latency and reliable message transmission. In applications like gas leakage detection, monitoring of pressure and industrial process control etc. reliable communication between sink and the sensing nodes is very important. In wireless sensor networks...
This paper proposes a modification of Bi-Histogram Equalization (Bi-HE) method, for intensity saturation free contrast enhancement of images. The proposed method segments the input histogram into two sub-histograms using Otsu thresholding criteria. Prior to HE process, the narrow ranged segment are identified and allocated with full dynamic range. Then both of the equalized segments are combined together...
The national energy generation resources ofPakistan are becoming insufficient due to increased demandof electrical energy. The country is suffering from acontinuous shortfall of thousands of megawatts especially insummer when the demand increases many folds. Theadditional support to the national grid by means of smallhydro projects on canals can be much beneficial. A techniquecan be devised through...
This paper presents the background of low back problem caused by repetitive fatigue loading. We emphasize on mechanism of Intervertebral Disc (IVD) and conditions for which the disc does not recover its original status under repetitive work and cause low back pain. The objective of this study is to identify structural changes in system parameters for fatigue loaded intervertebral disc. Principal component...
We investigate the coordinated path following problem for unicycles. We define the problem in general but focus on the case of two agent systems with circular paths.
Histogram equalization (HE) is one of the most effective method for contrast enhancement, but it fails to preserve the mean brightness of images. To overcome such drawback, several Bi- and Multi-histogram equalization methods have been proposed. Among them, Bi-HE methods may preserve the brightness, but they introduce some undesirable artifacts in the processed image. On the other hand, Multi-HE methods...
Application level gateways (ALGs) are physical network entities that are used to provide application specific proxies and deep packet inspection. ALG typically evaluates and examines all the incoming traffic to its interface and after applying security policies it allows traffic to enter into the internal network. In this paper we explain ALG network architecture, ALG working principle and its impact...
Session initiation protocol (SIP) is a well-known protocol that is used to provide voice over IP (VoIP) signaling and multimedia services in today's evolving Internet. With the popularity of peer-to-peer (P2P) system, it is envisioned to use SIP in P2P networks, to increase the communication flexibility without a centralized organization and control. The REsource LOcation And Discovery (RELOAD) protocol...
In this paper, a novel Joint Watermarking and Encryption scheme is presented. The design of proposed joint watermarking and encryption scheme involves the development of the encryption and watermarking schemes such that both the techniques are compliant with each other. Based on statistical analysis of continuous-tone still images, media data, in DCT domain, is partitioned into two parts. The encryption...
Recent advancement in 4th generation (4G) heterogeneous networking has opened the door for the deployment of femto-cells on a large scale. Deployment of femtocells in the existing macrocell networks and in 4G networks will significantly increase because femtocells offer increase coverage, capacity and user friendly mode of operations in both home and office environments. Therefore, these low power...
A femtocell offers increased coverage and capacity in both home and office environments because these low power home based access points are going to change the landscape of mobile technology and the networking business in the coming years. Therefore, deployment of a femtocell in the existing macrocell networks and in 4th generation (4G) networks will significantly increase. The objective of this...
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.