Thesis (M.S. in Electrical Engineering)--Naval Postgraduate School, September 2006. / Thesis Advisor(s): Weillian Su. "September 2006." Includes bibliographical references (p. 79-80). Also available in print.

Thesis (Ph.D)--Civil and Environmental Engineering, Georgia Institute of Technology, 2010. / Committee Chair: Hunter, Michael; Committee Member: Guensler, Randall; Committee Member: Leonard, John; Committee Member: Rodgers, Michael; Committee Member: Roshan J. Vengazhiyil. Part of the SMARTech Electronic Thesis and Dissertation Collection.

The growing popularity of new generation mobile terminals, known as „smartphones‟,has increased the variety and number of such devices. These devices make use of the resources offered by Universal Mobile Telecommunication Services (UMTS) networks toaccess on-line services such as web browsing, e-mail, audio and video streaming, etc. UMTS networks have to deal with an increasing amount of data traffic generated by smartphones. Because of the fact that the smartphone is battery powered and is trying to satisfy the needs ofboth applications and human users there is a need to be smarter about how to manage both network and terminal resources. This thesis explores the possibility of making a better use of the network and terminal resources by exploiting correlations in the events of the smartphone-generated traffic. We propose a mechanism, through which the network can predict if a terminal is going to produce data transmission or reception in a near future, based on past events in its traffic. According to this prediction, the network will be able to decide if it keeps or releases the resources allocated to the terminal. We analyze the benefits from the network and the terminal point ofview. We also describe a method to estimate an upper bound of the time until the next transmission or reception of data in a near future. We show that it is possible a reduction of the time that each terminal wastes in its maximum power consumption state, but this reduction implies a penalty in the transmission/reception throughput of the terminal. The reduction is not uniform for all terminals: terminals whose traffic presents a predictable behavior gain the most. Estimates of upper bounds of time until the next transmission or reception are more accurate if they are made taking as input information about interarrival times of previous packets. / Den växande populariteten för nya generationens mobila terminaler, så kallade"smartphones", har ökat både antal och sådana produkter. Dessa enheter utnyttjar de resursersom Universal Mobile Telecommunication Services (UMTS) att få tillgång till on-line tjänster såsom web webbläsning, e-post, ljud och video streaming, osv. UMTS-nät har hantera med en ökande mängd data som genereras trafik bysmartphones. På grund av det faktum attsmartphone är batteridriven och försöker för att tillgodose behoven hos både applikationer och mänskliga användare det finns ett behov att vara smartare om hur man kan hantera både nätverk och terminaler resurser. Den avhandling undersöker möjligheten att göra en bättre användning av nätverk och terminaler resurser genom att utnyttja samband i händelserna smartphone-genererade trafik. Vi föreslår en mekanism genom vilken nätet kan förutsäga om terminalen kommer att ta fram dataöverföring orreception i en nära framtid, baserat på tidigare händelser i trafiken. Enligt denna förutsägelse, kommer nätet att kunna avgöra om den håller eller frigör resurser till terminalen. Vi analyserar nytta nätet och terminalen synvinkel. Vi beskriver också en metod för att uppskatta övre gränsen för tiden till nästa sändning eller mottagning av data inom ens nar framtidd. Vi visar att det är möjligt att minska den tid som varje terminal avfall i sin maximal strömförbrukning staten, men denna minskning innebär en straffavgift överföring /mottagning genomströmning av terminalen. Minskningen är notuniform för alla terminaler där trafiken utgör en förutsägbart beteende vinna mest. Uppskattningar av övre gränserna för tid untilthe nästa sändning eller mottagning är mer exakta om de görs tar som indata information om interarrival gånger tidigare paket.

No description available.

Thesis (M.S.)--University of Missouri-Columbia, 2007. / The entire dissertation/thesis text is included in the research.pdf file; the official abstract appears in the short.pdf file (which also appears in the research.pdf); a non-technical general description, or public abstract, appears in the public.pdf file. Title from title screen of research.pdf file (viewed on April 4, 2008) Includes bibliographical references.

In this dissertation, we address the problem of discovery and representation of motion patterns in a variety of scenarios, commonly encountered in vision applications. The overarching goal is to devise a generic representation, that captures any kind of object motion observable in video sequences. Such motion is a significant source of information typically employed for diverse applications such as tracking, anomaly detection, and action and event recognition. We present statistical frameworks for representation of motion characteristics of objects, learned from tracks or optical flow, for static as well as moving cameras, and propose algorithms for their application to a variety of problems. The proposed motion pattern models and learning methods are general enough to be employed in a variety of problems as we demonstrate experimentally. We first propose a novel method to model and learn the scene activity, observed by a static camera. The motion patterns of objects in the scene are modeled in the form of a multivariate non-parametric probability density function of spatiotemporal variables (object locations and transition times between them). Kernel Density Estimation (KDE) is used to learn this model in a completely unsupervised fashion. Learning is accomplished by observing the trajectories of objects by a static camera over extended periods of time. The model encodes the probabilistic nature of the behavior of moving objects in the scene and is useful for activity analysis applications, such as persistent tracking and anomalous motion detection. In addition, the model also captures salient scene features, such as, the areas of occlusion and most likely paths. Once the model is learned, we use a unified Markov Chain Monte-Carlo (MCMC) based framework for generating the most likely paths in the scene, improving foreground detection, persistent labelling of objects during tracking and deciding whether a given trajectory represents an anomaly to the observed motion patterns. Experiments with real world videos are reported which validate the proposed approach. The representation and estimation framework proposed above, however, has a few limitations. This algorithm proposes to use a single global statistical distribution to represent all kinds of motion observed in a particular scene. It therefore, does not find a separation between multiple semantically distinct motion patterns in the scene. Instead, the learned model is a joint distribution over all possible patterns followed by objects. To overcome this limitation, we then propose a superior method for the discovery and statistical representation of motion patterns in a scene. The advantages of this approach over the first one are two-fold: first, this model is applicable to scenes of dense crowded motion where tracking may not be feasible, and second, it distinguishes between motion patterns that are distinct at a semantic level of abstraction. We propose a mixture model representation of salient patterns of optical flow, and present an algorithm for learning these patterns from dense optical flow in a hierarchical, unsupervised fashion. Using low level cues of noisy optical flow, K-means is employed to initialize a Gaussian mixture model for temporally segmented clips of video. The components of this mixture are then filtered and instances of motion patterns are computed using a simple motion model, by linking components across space and time. Motion patterns are then initialized and membership of instances in different motion patterns is established by using KL divergence between mixture distributions of pattern instances. Finally, a pixel level representation of motion patterns is proposed by deriving conditional expectation of optical flow. Results of extensive experiments are presented for multiple surveillance sequences containing numerous patterns involving both pedestrian and vehicular traffic. The proposed method exploits optical flow as the low level feature and performs a hierarchical clustering to obtain motion patterns; and we observe that the use of optical flow is also an integral part of a variety of other vision applications, for example, as features based representation of human actions. We, therefore, propose a new representation for articulated human actions using the motion patterns. The representation is based on hierarchical clustering of observed optical flow in four dimensional, spatial and motion flow space. The automatically discovered motion patterns, are the primitive actions, representative of flow at salient regions on the human body, much like trajectories of body joints, which are notoriously difficult to obtain automatically. The proposed method works in a completely unsupervised fashion, and in sharp contrast to state of the art representations like bag of video words, provides a truly semantically meaningful representation. Each primitive action depicts the most atomic sub-action, like left arm moving upwards, or right leg moving downward and leftward, and is represented by a mixture of four dimensional Gaussian distributions. A sequence of primitive actions are discovered in the test video, and labelled by computing the KL divergence between mixtures. The entire video sequence containing the human action, is thus reduced to a simple string, which is matched against similar strings of training videos to classify the action. The string matching is performed by global alignment, using the well-known Needleman-Wunsch algorithm. Experiments reported on multiple human actions data sets, confirm the validity, simplicity, and semantically meaningful nature of the proposed representation. Results obtained are encouraging and comparable to the state of the art.

Data fusion in wireless sensor networks can improve the performance of a network by eliminating redundancy and power consumption, ensuring fault-tolerance between sensors, and managing e®ectively the available com- munication bandwidth between network components. This thesis considers a data fusion approach applied to wireless sensor networks based on fuzzy logic theory. In particular, a cluster-based hierarchical design in wire- less sensor networks is explored combined with two data fusion methods based on fuzzy logic theory. A data fusion algorithm is presented and tested using Mamdani and Tsukamoto fuzzy inference methods. In addition, a concept related to the appropriate queuing models is presented based on classical queuing theory. Results show that the Mamdani method gives better results than the Tsukamoto approach for the two implementations considered. We noted that the proposed algorithm requires low processing and computational power. As a result, it can be applied to WSNs to provide optimal data fusion and ensures maximum sensor lifetime and minimum time delay.

This report covers one of the most demanding issues of network users i.e. network testing. Network testing in this study is about performance evaluation of networks, by putting traffic load gradually to determine the queuing delay for different traffics. Testing of such operations is becoming complex and necessary due to use of real time applications such as voice and video traffic, parallel to elastic data of ordinary applications over WAN links. Huge size elastic data occupies almost 80% resources and causes delay for time sensitive traffic. Performance parameters like service outage, delay, packet loss and jitter are tested to assure the reliability factor of provided Quality of Service (QoS) in the Service Level Agreements (SLAs). Normally these network services are tested after deployment of physical networks. In this case most of the time customers have to experience unavailability (outage) of network services due to increased levels of load and stress. According to user-centric point of view these outages are violation and must be avoided by the net-centric end. In order to meet these challenges network SLAs are tested on simulators in lab environment. This study provides a solution for this problem in a form of testbed simulator named Combinatorial TestBed Simulator (CTBS). Prototype of this simulator is developed for conducting experiment. It provides a systematic approach of combinatorial structures for finding such traffic patterns that exceeds the limit of queuing delay, committed in SLAs. Combinatorics is a branch of mathematics that deals with discrete and normally finite elements. In the design of CTBS, technique of combinatorics is used to generate a variety of test data that cannot be generated manually for testing the given network scenario. To validate the design of CTBS, results obtained by pilot runs are compared with the results calculated using timeline. After validation of CTBS design, actual experiment is conducted to determine the set of traffic patterns that exceeds the threshold value of queuing delay for Voice over Internet Protocol (VOIP) traffic. / 14:36 Folkparksvagan Ronneby 372 40 Sweden

Context. With the increased usage of mobile devices and internet, the cellular network traffic has increased tremendously. This increase in network traffic has led to increased occurrences of communication failures among the network nodes. Each communication failure among the nodes is defined as a bad event and occurrence of one such bad event acts as a source of origin for several consecutive bad events. These bad events as a whole may eventually lead to node failures (not being able to respond to any data requests). But it requires a lot of human effort and cost to be invested in by the telecom companies to implement workarounds for these node failures. So, there is a need to prevent node failures from happening. This can be done by classifying the traffic patterns between nodes in the network, identify bad events in them and deliver the verdict immediately after their detection. Objectives. Through this study, we aim to find the best suitable machine learning algorithm which can efficiently classify the traffic patterns of SGSN-MME (SGSN (Serving GPRS (General Packet Radio Service) Support node) and MME (Mobility Management Entity). SGSN-MME is a network management tool designed to support the functionalities of two nodes namely SGSN and MME. We do this by evaluating the classification performance of four machine learning classification algorithms, namely Support vector machines (SVMs), Naïve Bayes, Decision trees and Random forests, on the traffic patterns of SGSN and MME. The selected classification algorithm will be developed in such a way that, whenever it detects a bad event, it notifies the user about it by prompting a message saying, “Something bad is happening”. Methods. We have conducted an experiment for evaluating the classification performance of our four chosen classification algorithms on the dataset provided by Ericsson AB, Gothenburg. The experimental dataset is a combination of three logs, one of which represents the traffic patterns in real network and the other two logs contain synthetic traffic patterns that are generated manually. The dataset is unlabeled with 720 data instances and 4019 attributes in it. K-means clustering is performed for dividing the data instances into groups and thereby proceed with labeling them accordingly into good and bad events. Also, since the number of attributes in the experimental dataset are more than the number of instances, feature selection is performed for selecting the subset of relevant attributes which best represents the whole data. All the chosen classification algorithms are trained and tested with ten-fold cross validation sets using the selected subset of attributes and the obtained performance measures like classification accuracy, F1 score and training time are analyzed and compared for selecting the best suitable one among them. Finally, the chosen algorithm is tested on unlabeled real data and the performance measures are analyzed in order to check if is able to detect the bad events correctly or not. Results. Experimental results showed that Random forests outperformed Support vector machines, Naïve Bayes and Decision trees with an average classification accuracy of 99.72% and average F1 score of 99.6, when classification accuracy and F1 score are considered. On the other hand, Naive Bayes outperformed Support vector machines, Decision trees and Random forests with an average training time of 0.010 seconds, when training time is considered. Also, the classification accuracy and F1 score of Random forests on unlabeled data are found to be 100% and 100 respectively. Conclusions. Since our study focuses on classifying the traffic patterns of SGSN-MME more accurately, classification accuracy and F1 score are of highest importance than the training time of algorithm. Therefore, based on experimental results, we conclude that Random forests is the best suitable machine learning algorithm for classifying the traffic patterns of SGSN -MME. However, Naive Bayes can be also used if classification has to be performed in the least time possible and with moderate accuracy (around 70%).

Mobile devices have evolved rapidly in recent years and increased usage and performance are pushing contemporary battery technology to its limits. The constrained battery resources mean that the importance of energy-efficient application design is growing and in this regard wireless network accesses are a major contributor to a mobile device's overall energy consumption. Additionally, the energy consumption characteristics of modern cellular technologies make small volumes of poorly scheduled traffic account for a substantial share of a device's total energy consumption. However, quantifying the communication energy footprint is cumbersome, making it difficult for developers to profile applications from an energy consumption perspective and optimize traffic patterns. This thesis examines the traffic patterns of the Android client of the popular multimedia streaming service Spotify with the intention to reduce its energy footprint, in terms of 3G energy consumption. The application's automated test environment is extended to capture network traffic, which is used to estimate energy consumption. Automated system tests are designed and executed on a physical Android device connected to a 3G network, shedding light on the traffic patterns of different application features. All traffic between the Spotify client application and the backend servers is encrypted. To extract information about the traffic, the application code is instrumented to output supplementary information to the Android system log. The system log is then used as a source of information to attribute data traffic to different application modules and specific lines of code. Two simple traffic shaping techniques, traffic aggregation and piggybacking, are implemented in the application to provide more energy-efficient traffic patterns. As a result, 3G energy consumption during normal music playback is reduced by 22-54%, and a more contrived scenario achieves a 60% reduction. The reductions are attained by rescheduling a small class of messages, most notably data tracking application usage. These messages were found to account for a small fraction of total traffic volume, but a large portion of the application's overall 3G energy consumption.