To see the other types of publications on this topic, follow the link: Classification of network devices.
Dissertations / Theses on the topic 'Classification of network devices'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 dissertations / theses for your research on the topic 'Classification of network devices.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse dissertations / theses on a wide variety of disciplines and organise your bibliography correctly.
1
Eis, Pavel. "Datová sada pro klasifikaci síťových zařízení pomocí strojového učení." Master's thesis, Vysoké učení technické v Brně. Fakulta informačních technologií, 2021. http://www.nusl.cz/ntk/nusl-445543.
Full textAbstract:
Automatic classification of devices in computer network can be used for detection of anomalies in a network and also it enables application of security policies per device type. The key to creating a device classifier is a quality data set, the public availability of which is low and the creation of a new data set is difficult. The aim of this work is to create a tool, that will enable automated annotation of the data set of network devices and to create a classifier of network devices that uses only basic data from network flows. The result of this work is a modular tool providing automated annotation of network devices using system ADiCT of Cesnet's association, search engines Shodan and Censys, information from PassiveDNS, TOR, WhoIs, geolocation database and information from blacklists. Based on the annotated data set are created several classifiers that classify network devices according to the services they use. The results of the work not only significantly simplify the process of creating new data sets of network devices, but also show a non-invasive approach to the classification of network devices.
2
Sleem, Lama. "Design and implementation of lightweight and secure cryptographic algorithms for embedded devices." Thesis, Bourgogne Franche-Comté, 2020. http://www.theses.fr/2020UBFCD018.
Full textAbstract:
Nous vivons actuellement dans une ère avec sans cesse de nouveaux appareils technologiques (smartphone, réseaux de capteurs sans fil, aux caméras haute résolution, etc). En partant des médias sociaux, en passant par des caméras de surveillance très puissantes, et sans oublier la surveillance de la santé en temps réel, on constate qu'une grande quantité de données est stockée dans le cloud et les serveurs. Cela représente un grand défi de stockage et de transmission, en particulier dans les plates-formes aux ressources limitées qui sont caractérisées par : (a) des capacités de calcul limitées, (b) une source d'énergie limitées et (c) des infrastructures ouvertes qui transmettent des données sur des réseaux sans fil peu fiables. Dans cette thèse, nous nous concentrons sur l'amélioration de la sécurité des contenus multimédia transmis sur des plates-formes à capacité de calcul limitée, tout en préservant un niveau de sécurité élevé. Dans la première partie, nous avons étudié les réseaux ad hoc véhiculaire. Nous avons proposé un état de l'art qui permet de résumer la plupart des travaux récents et d'explorer presque tous les aspects de ce domaine en illustrant les différents aspects que possède cette plateforme. Ensuite, afin de proposer une nouvelle solution de sécurité et de valider sa robustesse et le niveau de caractère aléatoire d'une image chiffrée, nous avons proposé un test simple et efficace. Celui-ci est basé sur des outils pour tester statistiquement le caractère aléatoire de nombres pseudo aléatoires, TestU01 et Practrand. Après avoir effectué ces tests sur des algorithmes de chiffrement bien connus, certaines failles ont été exposées et une nouvelle proposition visant à améliorer le système de chiffrement ultra-léger Speck est proposée. La principale contribution de ce travail est d'obtenir une meilleure version par rapport à Speck. Dans cette nouvelle proposition, appelée Speck-R, nous utilisons seulement 7 itérations contrairement à Speck qui en utilise 26 et nous réduisons le temps d'exécution d'au moins 50%. Tout d'abord, nous validons que Speck-R répond aux tests de statistiques pour mesurer l'aléatoire, proposés précédemment. De plus, nous avons rajouté un système de clé dynamique qui procure plus de sécurité contre les attaques liées à la clé. Speck-R a été implémenté sur différentes cartes de type arduino et dans tous les cas, Speck-R était plus rapide que Speck. Ensuite, afin de prouver que ce chiffrement peut être utilisé pour sécuriser les images, en particulier dans les réseaux VANETS/IoV, plusieurs tests ont été effectués et les résultats montrent que Speck-R possède effectivement le haut niveau de sécurité souhaité. Des expérimentations valident notre proposition du point de vue de la sécurité et de la performance et démontrent la robustesse du système proposé face aux types d'attaques les plus connusLiving in an era where new devices are astonishing considering their high capabilities, new visions and terms have emerged. Moving to smart phones, Wireless Sensor Networks, high-resolution cameras, pads and much more, has mandated the need to rethink the technological strategy that is used today. Starting from social media, where apparently everything is being exposed, moving to highly powerful surveillance cameras, in addition to real time health monitoring, it can be seen that a high amount of data is being stored in the Cloud and servers. This introduced a great challenge for their storage and transmission especially in the limited resourced platforms that are characterized by: (a) limited computing capabilities, (b) limited energy and source of power and (c) open infrastructures that transmit data over wireless unreliable networks. One of the extensively studied platforms is the Vehicular Ad-hoc Networks which tends to have many limitations concerning the security field. In this dissertation, we focus on improving the security of transmitted multimedia contents in different limited platforms, while preserving a high security level. Limitations of these platforms are taken into consideration while enhancing the execution time of the secure cipher. Additionally, if the proposed cipher is to be used for images, the intrinsic voluminous and complex nature of the managed images is also taken into account. In the first part, we surveyed one of the limited platforms that is interesting for many researchers, which is the Vehicular Ad-hoc Networks. In order to pave the way for researchers to find new efficient security solutions, it is important to have one reference that can sum most of the recent works. It almost investigates every aspect in this field shedding the light over different aspects this platform possesses. Then, in order to propose any new security solution and validate its robustness and the level of randomness of the ciphered image, a simple and efficient test is proposed. This test proposes using the randomness tools, TestU01 and Practrand, in order to assure a high level of randomness. After running these tests on well known ciphers, some flaws were exposed. Proceeding to the next part, a novel proposal for enhancing the well-known ultra lightweight cipher scheme, Speck, is proposed. The main contribution of this work is to obtain a better version compared to Speck. In this proposal, 26 rounds in Speck were reduced to 7 rounds in Speck-R while enhancing the execution time by at least 50%. First, we validate that Speck-R meets the randomness tests that are previously proposed. Additionally, a dynamic substitution layer adds more security against key related attacks and highly fortifies the cipher. Speck-R was implemented on different limited arduino chips and in all cases, Speck-R was ahead of Speck. Then, in order to prove that this cipher can be used for securing images, especially in VANETS/IoV, where images can be extensively re/transmitted, several tests were exerted and results showed that Speck-R indeed possesses the high level of security desired in any trusted cipher. Extensive experiments validate our proposal from both security and performance point of views and demonstrate the robustness of the proposed scheme against the most-known types of attacks
3
Erlandsson, Niklas. "Utilizing machine learning in wildlife camera traps for automatic classification of animal species : An application of machine learning on edge devices." Thesis, Linnéuniversitetet, Institutionen för datavetenskap och medieteknik (DM), 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:lnu:diva-104952.
Full textAbstract:
A rapid global decline in biodiversity has been observed in the past few decades, especially in large vertebrates and the habitats supporting these animal populations. This widely accepted fact has made it very important to understand how animals respond to modern ecological threats and to understand the ecosystems functions. The motion activated camera (also known as a camera trap) is a common tool for research in this field, being well-suited for non-invasive observation of wildlife. The images captured by camera traps in biological studies need to be classified to extract information, a traditionally manual process that is time intensive. Recent studies have shown that the use of machine learning (ML) can automate this process while maintaining high accuracy. Until recently the use of machine learning has required significant computing power, relying on data being processed after collection or transmitted to the cloud. This need for connectivity introduces potentially unsustainable overheads that can be addressed by placing computational resources on the camera trap and processing data locally, known as edge computing. Including more computational power in edge and IoT devices makes it possible to keep the computation and data storage on the edge, commonly referred to as edge computing. Applying edge computing to the camera traps enables the use of ML in environments with slow or non-existent network accesss since their functionality does not rely on the need for connectivity. This project shows the feasibility of running machine learning algorithms for the purpose of species identification on low-cost hardware with similar power to what is commonly found in edge and IoT devices, achieving real-time performance and maintaining high energy efficiency sufficient for more than 12 hours of runtime on battery power. Accuracy results were mixed, indicating the need for more tailor-made network models for performing this task and the importance of high quality images for classification.
4
Luckhardt, Christoph [Verfasser]. "Development of thermo-analytical prediction and classification models for food in thermal devices using a multi sensor system and artificial neural networks / Christoph Luckhardt." Kassel : Universitätsbibliothek Kassel, 2013. http://d-nb.info/1043361863/34.
Full text
5
Akarapu, Deepika. "Object Identification Using Mobile Device for Visually Impaired Person." University of Dayton / OhioLINK, 2021. http://rave.ohiolink.edu/etdc/view?acc_num=dayton1628092619349812.
Full text
6
Wolf, Robert, Niko Joram, Stefan Schumann, and Frank Ellinger. "Dual-band impedance transformation networks for integrated power amplifiers." Cambridge University Press, 2016. https://tud.qucosa.de/id/qucosa%3A70680.
Full textAbstract:
This paper shows that the two most common impedance transformation networks for power amplifiers (PAs) can be designed to achieve optimum transformation at two frequencies. Hence, a larger bandwidth for the required impedance transformation ratio is achieved. A design procedure is proposed, which takes imperfections like losses into account. Furthermore, an analysis method is presented to estimate the maximum uncompressed output power of a PA with respect to frequency. Based on these results, a fully integrated PA with a dual-band impedance transformation network is designed and its functionality is proven by large signal measurement results. The amplifier covers the frequency band from 450 MHz to 1.2 GHz (3 dB bandwidth of the output power and efficiency), corresponding to a relative bandwidth of more than 100%. It delivers 23.7 dBm output power in the 1 dB compression point, having a power-added efficiency of 33%.
7
Kühnert, Wolfram. "Dynamic Devices Network Architecture." [S.l. : s.n.], 2003. http://www.bsz-bw.de/cgi-bin/xvms.cgi?SWB10952962.
Full text
8
Alexander, David. "A Network Metadata Infrastructure for Locating Network Devices." Ohio University / OhioLINK, 2004. http://www.ohiolink.edu/etd/view.cgi?ohiou1088176648.
Full text
9
Zenteno, Efrain. "Vector Measurements for Wireless Network Devices." Licentiate thesis, KTH, Signalbehandling, 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-111863.
Full textAbstract:
Wireless networks are an iconic technology of today’s modern era, theyare present in our daily activities as can be exemplified by cellular communications,wi-fi, bluetooth, and others. Vector measurements play an importantrole in the design, simulation, and testing of wireless networks and are usedto characterize key devices operating in the radio interface, such as amplifiers,filters, and mixers.Accurate characterization is the key for improving the capacity and efficiencyof wireless networks. As the demand for network capacity continuouslyincreases, the accuracy of vector measurements must also improve. Further,it is anticipated that such trends will continue in the years to come. Consequently,the wireless industry needs to include nonlinear behavior in theircharacterization and analysis, to assess and guaranty the operation of the devices,and to comply to the specifications from governmental regulations. Incontrast to linear behavior, nonlinear behavior presents an additional bandwidthrequirement because the signal bandwidth grows when it passes throughnonlinear devices. In this thesis, vector measurements for devices operatingin wireless networks are studied, emphasizing a synthetic approach for theinstrumentation. This approach enables the use of digital post-processing algorithms,which enhances the measurement accuracy and/or speed and canovercome hardware impairments. This thesis presents the design of a vectorialmeasurement system for wireless devices considering the aforementionedtrends and requirements. It also explores the advantages of the proposedapproach, describes its limitations, and discusses the digital signal processingalgorithms used to reach its final functionality. Finally, measurement resultsof the proposed setup are presented, analyzed and compared to those of modernindustrial instruments.QC 20130204
10
Omer, Mahgoub Saied Khalid. "Network Latency Estimation Leveraging Network Path Classification." Thesis, KTH, Network Systems Laboratory (NS Lab), 2018. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-229955.
Full textAbstract:
With the development of the Internet, new network services with strict network latency requirements have been made possible. These services are implemented as distributed systems deployed across multiple geographical locations. To provide low response time, these services require knowledge about the current network latency. Unfortunately, network latency among geo-distributed sites often change, thus distributed services rely on continuous network latency measurements. One goal of such measurements is to differentiate between momentary latency spikes from relatively long-term latency changes. The differentiation is achieved through statistical processing of the collected samples. This approach of high-frequency network latency measurements has high overhead, slow to identify network latency changes and lacks accuracy. We propose a novel approach for network latency estimation by correlating network paths to network latency. We demonstrate that network latency can be accurately estimated by first measuring and identifying the network path used and then fetching the expected latency for that network path based on previous set of measurements. Based on these principles, we introduce Sudan traceroute, a network latency estimation tool. Sudan traceroute can be used to both reduce the latency estimation time as well as to reduce the overhead of network path measurements. Sudan traceroute uses an improved path detection mechanism that sends only a few carefully selected probes in order to identify the current network path. We have developed and evaluated Sudan traceroute in a test environment and evaluated the feasibility of Sudan traceroute on real-world networks using Amazon EC2. Using Sudan traceroute we have shortened the time it takes for hosts to identify network latency level changes compared to existing approaches.Med utvecklingen av Internet har nya nätverkstjänster med strikta fördröjningskrav möjliggjorts. Dessa tjänster är implementerade som distribuerade system spridda över flera geografiska platser. För att tillgodose låg svarstid kräver dessa tjänster kunskap om svarstiden i det nuvarande nätverket. Tyvärr ändras ofta nätverksfördröjningen bland geodistribuerade webbplatser, således är distribuerade tjänster beroende av kontinuerliga mätvärden för nätverksfördröjning. Ett mål med sådana mätningar är att skilja mellan momenta ökade svarstider från relativt långsiktiga förändringar av svarstiden. Differentieringen uppnås genom statistisk bearbetning av de samlade mätningarna. Denna högfrekventa insamling av mätningar av nätverksfördröjningen har höga overheadkostnader, identifierar ändringar långsamt och saknar noggrannhet. Vi föreslår ett nytt tillvägagångssätt för beräkningen av nätverksfördröjning genom att korrelera nätverksvägar till nätverksfördröjning. Vi visar att nätverksfördröjningen kan vara exakt uppskattad genom att man först mäter och identifierar den nätverksväg som används och sedan hämtar den förväntade fördröjningen för den nätverksvägen baserad på en tidigare uppsättning av mätningar. Baserat på dessa principer introducerar vi Sudan traceroute, ett Verktyg för att uppskatta nätverksfördröjning. Sudan traceroute kan användas för att både minska tiden att uppskatta fördröjningen samt att minska overhead för mätningarna i nätverket. Sudan traceroute använder en förbättrad vägdetekteringsmekanism som bara skickar några försiktigt valda prober för att identifiera den aktuella vägen i nätverket. Vi har utvecklat och utvärderat Sudan traceroute i en testmiljö och utvärderade genomförbarheten av Sudan traceroute i verkliga nätverk med hjälp av Amazon EC2. Med hjälp av Sudan traceroute har vi förkortat den tid det tar för värdar att identifiera nätverksfördröjnings förändringar jämfört med befintliga tillvägagångssätt.
11
Cardwell, Gregory S. "Residual network data structures in Android devices." Thesis, Monterey, California. Naval Postgraduate School, 2011. http://hdl.handle.net/10945/5506.
Full textAbstract:
Approved for public release; distribution is unlimitedThe emergence and recent ubiquity of Smartphones present new opportunities and challenges to forensic examiners. Smartphones enable new mobile application and use paradigms by being constantly attached to the Internet via one of several physical communication media, e.g. cellular radio, WiFi, or Bluetooth. The Smartphone's storage medium represents a potential source of current and historical network metadata and records of prior data transfers. By using known ground truth data exchanges in a controlled experimental environment, this thesis identifies network metadata stored by the Android operating system that can be readily retrieved from the device's internal non-volatile storage. The identified network metadata can ascertain the identity of prior network access points to which the device associated. An important by-product of this research is a well-labeled Android Smartphone image corpus, allowing the mobile forensic community to perform repeatable, scientific experiments, and to test mobile forensic tools.
12
Anderson, Pehr C. (Pehr Christian) 1974. "Filaments : lightweight network interfaces for embedded devices." Thesis, Massachusetts Institute of Technology, 1998. http://hdl.handle.net/1721.1/46249.
Full textAbstract:
Thesis (M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 1998.Includes bibliographical references (leaf 63).
Filaments are low-cost interfaces for attaching devices to an Ethernet network. While most networking research pushes for faster high-end systems, the filament project targets low-end devices with the goal of making networking easy. Filaments wrap the complexity of the network into a simple and convenient package. The vast majority of device communications require only a tiny thread or filament of connectivity. Before filaments, one could either tie each device to a desktop PC or to deploy a specialized device network. Filaments allow you to leverage the same network used by desktop computers without making devices dependent on them.
by Pehr C. Anderson.
M.Eng.
13
Tan, SiewYeen Agnes. "A Network Measurement Tool for Handheld Devices." Thesis, Virginia Tech, 2003. http://hdl.handle.net/10919/32982.
Full textAbstract:
This thesis describes a performance measurement tool that allows a user to measure network performance using a handheld device. The measurement tool consists of a client program that runs on a Microsoft Pocket PC device and a server program that runs on a regular Microsoft Windows computer. Both programs are Windows applications implemented in C/C++ using the Microsoft Embedded Visual Tool and Microsoft Visual Studio. The use of a Pocket PC device provides mobility to users, which can save time and energy when performing experiments. The thesis describes the design of the performance measurement application, implementation issues, and tests conducted using the tool.Master of Science
14
Rimer, Michael Edwin. "Improving Neural Network Classification Training." Diss., CLICK HERE for online access, 2007. http://contentdm.lib.byu.edu/ETD/image/etd2094.pdf.
Full text
15
Yusuf, Adewale, Jerry Lartey, and Vilhelm Wareus. "Network Admission Control (NAC)Securing end point devices." Thesis, Halmstad University, School of Information Science, Computer and Electrical Engineering (IDE), 2010. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-5507.
Full textAbstract:
There have been remarkable growths in wireless communication networks in
recent years; this is because of its merits over the wired networks such as
Mobility and convenience. Wireless networks transmit the signal over the
open air via radio waves of different frequencies, this makes it to be
vulnerable to several attacks and anybody on the street can easily intercept the
wireless data or inject new data into the entire network. There has been
existence of wired equivalent privacy (WEP) protocol (IEEE 802.11i), which
was designed for wireless network security. There were concerns of security
vulnerabilities in WEP; this made it necessary for the implementation of
another solution to overcome the weaknesses of the previous wireless
network security. The IEEE 802.1X (port-based network admission control)
which is defined on Extensible Authentication protocol (EAP) provides
effective and efficient admission control to wireless and other networks
devices [8].
Our thesis investigates the efficiency of NAC (IEEE 802.1X) as a security
solution, access different vendor solutions, protocols supported and look into
the inter-operability of these various vendors. In as much as we support the
premise of NAC being an excellent solution, we will also make brilliant
recommendations in this thesis to be considered for future refinements of this
security solution as well as deployment scenarios for the university network.
16
Spadavecchia, Ljiljana. "A network-based asynchronous architecture for cryptographic devices." Thesis, University of Edinburgh, 2006. http://hdl.handle.net/1842/860.
Full textAbstract:
The traditional model of cryptography examines the security of the cipher as a mathematical function. However, ciphers that are secure when specified as mathematical functions are not necessarily secure in real-world implementations. The physical implementations of ciphers can be extremely difficult to control and often leak socalled side-channel information. Side-channel cryptanalysis attacks have shown to be especially effective as a practical means for attacking implementations of cryptographic algorithms on simple hardware platforms, such as smart-cards. Adversaries can obtain sensitive information from side-channels, such as the timing of operations, power consumption and electromagnetic emissions. Some of the attack techniques require surprisingly little side-channel information to break some of the best known ciphers. In constrained devices, such as smart-cards, straightforward implementations of cryptographic algorithms can be broken with minimal work. Preventing these attacks has become an active and a challenging area of research. Power analysis is a successful cryptanalytic technique that extracts secret information from cryptographic devices by analysing the power consumed during their operation. A particularly dangerous class of power analysis, differential power analysis (DPA), relies on the correlation of power consumption measurements. It has been proposed that adding non-determinism to the execution of the cryptographic device would reduce the danger of these attacks. It has also been demonstrated that asynchronous logic has advantages for security-sensitive applications. This thesis investigates the security and performance advantages of using a network-based asynchronous architecture, in which the functional units of the datapath form a network. Non-deterministic execution is achieved by exploiting concurrent execution of instructions both with and without data-dependencies; and by forwarding register values between instructions with data-dependencies using randomised routing over the network. The executions of cryptographic algorithms on different architectural configurations are simulated, and the obtained power traces are subjected to DPA attacks. The results show that the proposed architecture introduces a level of non-determinism in the execution that significantly raises the threshold for DPA attacks to succeed. In addition, the performance analysis shows that the improved security does not degrade performance.
17
Krishna, Ashwin. "Composing and connecting devices in animal telemetry network." Kansas State University, 2016. http://hdl.handle.net/2097/32882.
Full textAbstract:
Master of ScienceDepartment of Computing and Information Sciences
Venkatesh P. Ranganath
As the Internet of Things (IoT) continues to grow, the need for services that span multiple application domains will continue to increase to realise the numerous possibilities enabled by IoT. Today, however, heterogeneity among devices leads to interoperability issues while building a system of systems and often give rise to closed ecosystems. The issues with interoperability are driven by the inability of devices and apps from different vendors to communicate with each other. The interoperability problem forces the users to stick to one particular vendor, leading to vendor lock-in. To achieve interoperability, the users have to do the heavy lifting (at times impossible) of connecting heterogeneous devices. As we slowly move towards system-of-systems and IoT, there is a real need to support heterogeneity and interoperability. A recent effort in Santos Lab developed Medical Device Coordination Framework (MDCF), which was a step to address these issues in the space of human medical systems. Subsequently, we have been wondering if a similar solution can be employed in the area of animal science. In this effort, by borrowing observations from MDCF and knowledge from on-field experience, we have created a demonstration showcasing how a combination of precise component descriptions (via DSL) and communication patterns can be used in software development and deployment to overcome barriers due to heterogeneity, interoperability and to enable an open ecosystem of apps and devices in the space of animal telemetry.
18
Bailer-Jones, Coryn Andreas. "Neural network classification of stellar spectra." Thesis, University of Cambridge, 1997. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.627444.
Full text
19
Brophy, Jonathan. "Collective Classification of Social Network Spam." Thesis, University of Oregon, 2017. http://hdl.handle.net/1794/22625.
Full textAbstract:
Unsolicited messages affects virtually every popular social media website, and spammers have become increasingly proficient at bypassing conventional filters, prompting a stronger effort to develop new methods. First, we build an independent model using features that capture the cases where spam is obvious. Second, a relational model is built, taking advantage of the interconnected
nature of users and their comments. By feeding our initial predictions from the independent model into the relational model, we can propagate and jointly infer the labels of all comments at the same time. This allows us to capture the obfuscated spam comments missed by the independent model that are only found by looking at the relational structure of the social network. The results from our experiments shows that models utilizing the underlying structure of the social network are more effective at detecting spam than ones that do not.
This thesis includes previously published coauthored material.
20
Harris, David Anthony. "Neural network studies of lithofacies classification." Thesis, University of Edinburgh, 1994. http://hdl.handle.net/1842/14001.
Full textAbstract:
Exploration for hydrocarbons and other resources requires that large amounts of data be interpreted and used to infer the geology of extensive regions. Many different types of data are used. They are interpreted by geologists and sedimentologists in the light of experience. Artificial neural network models implemented on computers provide a powerful means of performing tasks such as pattern classification. Such tasks are difficult to perform using rule based methods, as we often do not know how to specify appropriate rules. We show that artificial neural networks can be used to discriminate between images of different lithofacies (types of rocks). This discrimination is based upon textural differences in the rocks, which are quantified by measures of texture derived from the rock images and used as inputs to the network. Neural network performance is good compared to a very simple alternative technique, that of K nearest neighbours. A particular set of texture measures is that based on the grey level coocurrence method. These measures have interesting properties; in particular, their expectation values can be calculated exactly for images generated by exactly solvable Ising models. The measures are themselves probabilities for the joint distribution of pixel values in an image, so that they can be used to generate images in a stochastic process.
21
McMahon, Michael J. "An approach for enhanced management of network-attached devices." abstract and full text PDF (free order & download UNR users only), 2007. http://0-gateway.proquest.com.innopac.library.unr.edu/openurl?url_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:dissertation&res_dat=xri:pqdiss&rft_dat=xri:pqdiss:1442840.
Full text
22
Lykouropoulos, Efstathios, Andreas Kostoulas, and Zainab Jumaa. "Connect street light control devices in a secure network." Thesis, Högskolan i Halmstad, 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-28180.
Full textAbstract:
Wireless communications is a constantly progressing technology in network engineering society, creating an environment full of opportunities that are targeting in financial growth, quality of life and humans prosperity. Wireless security is the science that has as a goal to provide safe data communication between authorized users and prevent unauthorized users from gaining access, deny access, damage or counterfeit data in a wireless environment. In order to success it uses layers of protection that consist of software and hardware mechanisms that are able to monitor network’s behavior and in coordination provide a safe and secure environment for the user. In this thesis, a scientific research will be conducted in a given wireless network topology designed for an original application. This is about an intelligent street lightning system and it has already been implemented by Greinon Engineering which is the company that we are cooperating with. It is a matter of great importance that this thesis was conducted under real life criteria and in cooperation with an engineering company. This means that our programming, our ideas, our study research were all rotated and concentrated in certain type of hardware – software and network topology. In this thesis there is a detailed overview of basic wireless security mechanisms – vulnerabilities – types of attacks and countermeasures focused on 802.11b protocol. Moreover there will be security weak point’s analysis on the given industrial network; our proposals to protect and secure this network based on our threat analysis of the current system. There is an analysis on the most up to date VPN security implementations and reasoning that guided our team to conclude in a specific procedure - protocol and implementation, including limitation factors – obstacles faces during this procedure. During this research iterative approach in procedures – ideas and implementation attempts is followed. Basic goal is to provide security solutions that are easy applicable, low cost, easy to maintain and monitor.
23
Deng, Shuo. "Intelligent network selection and energy reduction for mobile devices." Thesis, Massachusetts Institute of Technology, 2015. http://hdl.handle.net/1721.1/99819.
Full textAbstract:
Thesis: Ph. D., Massachusetts Institute of Technology, Department of Electrical Engineering and Computer Science, 2015.Cataloged from PDF version of thesis.
Includes bibliographical references (pages 137-142).
The popularity of mobile devices has stimulated rapid progress in both Wi-Fi and cellular technologies. Before LTE was widely deployed, Wi-Fi speeds dominated cellular network speeds. But that is no longer true today. In a study we conducted with a crowd-sourced measurement tool used by over 1,000 users in 16 countries, we found that 40% of the time LTE outperforms Wi-Fi, and 75% of the time the difference between LTE and Wi-Fi throughput is higher than 1 Mbits/s. Thus, instead of the currently popular "always prefer Wi-Fi" policy, we argue that mobile devices should use the best available combination of networks: Wi-Fi, LTE, or both. Selecting the best network combination, however, is a challenging problem because: 1) network conditions vary with both location and time; 2) many network transfers are short, which means that the decision must be made with low overhead; and, 3) the best choice is determined not only by best network performance, but also constrained by practical factors such as monetary cost and battery life. In this dissertation, we present Delphi, a software controller for network selection on mobile devices. Delphi makes intelligent network selection decisions according to current network conditions and monetary cost concerns, as well as battery-life considerations. Our experiments show that Delphi reduces application network transfer time by 46% for web browsing and by 49% for video streaming, compared with Android's default policy of always using Wi-Fi when it is available. Delphi can also be configured to achieve high throughput while being energy efficient; in this configuration, it achieves 1.9 x the through-put of Android's default policy while only consuming 6% more energy. Delphi improves performance but uses the cellular network more extensively than the status quo, consuming more energy than before. To address this problem, we develop a general method to reduce the energy consumption of cellular interfaces on mobile devices. The key idea is to use the statistics of data transfers to determine the best times at which to put the radio in different power states. These techniques not only make Delphi more useful in practice but can be deployed independently without Delphi to improve energy efficiency for any cellular-network-enabled devices. Experiments show that our techniques reduce energy consumption by 15% to 60% across various traffic patterns.
by Shuo Deng.
Ph. D.
24
Qian, Xiaolan 1977. "A protocol for a wireless network of mobile devices." Thesis, Massachusetts Institute of Technology, 2000. http://hdl.handle.net/1721.1/86494.
Full textAbstract:
Thesis (S.B. and M.Eng.)--Massachusetts Institute of Technology, Dept. of Electrical Engineering and Computer Science, 2000.Includes bibliographical references (leaf 53).
by Xiaolan Qian.
S.B.and M.Eng.
25
Guulay, Biniam Gebregergs. "CheesePi: Measuring Home Network Performance Using Dedicated Hardware Devices." Thesis, KTH, Skolan för elektro- och systemteknik (EES), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-184917.
Full textAbstract:
Internet users may not get the service quality promised by theirproviders, and also may not know what service they can receive.When users experience poor Internet connection performance, itis not easy to identify the source of the problem. We developCheesePi, a distributed measurement system that measures theInternet connection experience of home users based on some net-work performance attributes (e.g. latency, packet loss rate, andWiFi signal quality). The CheesePi runs on a Raspberry Pi (acredit card sized computer) connected to the user’s home networkas a measurement agent. It is important to measure the networkperformance from the user’s side since it is difficult to measureeach individual’s link from the operator (provider) side. Eachmeasurement agent conducts measurement periodically withoutdisturbing the user’s Internet quality. Measurements are con-ducted during popular media events from SICS (Swedish Insti-tute of Computer Science) and student accommodations. Themeasurement results show customers with an Ethernet connectionexperienced significantly better latency and packet loss comparedto WiFi users. In most of the measurements users at SICS per-ceived better latency and packet loss compared to the users at thestudent accommodation. We also quantify how customers experi-enced lower performance when streaming from websites which donot use CDN technology compared to the websites which do useCDN, particularly during popular media events.CheesePi
26
Nyrönen, P. (Pekka). "Convolutional neural network based super-resolution for mobile devices." Master's thesis, University of Oulu, 2018. http://urn.fi/URN:NBN:fi:oulu-201812083250.
Full textAbstract:
Super-resolution is a challenging problem of restoring details lost to diffraction in the image capturing process. Degradations from the environment and the imaging device increase its difficulty, and they are strongly present in mobile phone cameras. The latest promising approaches involve convolutional neural networks, but little testing has been done on degraded images. Also, sizes of neural networks raise a question of their applicability on mobile devices. A wide review of published super-resolution neural networks is done. Four of the network architectures are chosen, and their TensorFlow models are trained and tested for their output quality on high quality and degraded images and compared against bicubic interpolation with sharpening. For the first time, MTF and CPIQ acutance responses are measured from their outputs after processing photographs of a resolution chart. Their execution times on a mobile device are measured for small image sizes and typical phone camera photo sizes. It is shown that the networks are able to learn degradation resilience, and that quality of their results surpasses that of the bicubic interpolations with sharpening. However, even the lightest models still take a considerable time to process images on a mobile device. Moreover, it is shown that the current way of training and evaluating super-resolution neural networks with high quality images is inadequate for practical purposes, and that degradations have to be incorporated into training data in order to overcome the problemSuperresoluutio on haastava diffraktion kuvaa otettaessa hävittämien yksityiskotien palautusongelma. Ympäristöstä ja kuvantamislaitteistosta syntyvät rappeumat lisäävät sen vaikeutta, ja ne ovat voimakkaasti läsnä matkapuhelinten kameroissa. Viimeisimmät lupaavat lähestymistavat hyödyntävät konvoluutioneuroverkkoja, mutta niiden testausta heikkolaatuisilla kuvilla on tehty vähän. Lisäksi neuroverkkojen koot herättävät kysymyksen niiden käytettävyydestä mobiililaitteilla. Julkaistuista superresoluutioverkoista tehdään laaja katsaus. Neljän valitun verkkoarkkitehtuurin TensorFlow-mallien ulostulojen laatua testataan puhtailla ja heikompilaatuisilla kuvilla ja tuloksia verrataan terävöitettyyn kuutiolliseen interpolaatioon. Ensimmäistä kertaa MTF- ja CPIQ-terävyysvaste mitataan niiden ulostulokuvista niiden käsiteltyä valokuvia resoluutiokartasta. Mallien suoritusaikoja mitataan niin pienille kuville kuin tyypillisille kännykkäkameroiden kuvakoille. Tulokset osoittavat, että verkot pystyvät oppimaan kestäviksi laadun heikennyksille, ja että niiden tulosten laatu ylittää terävöitetyn kuutiollisen interpolaation tulokset. Kevyimmätkin mallit vaativat kuitenkin huomattavasti laskenta-aikaa mobiililaitteella. Lisäksi osoitetaan, että nykyinen tapa kouluttaa ja arvioida superresoluutioneuroverkkoja korkealaatuisilla kuvilla on riittämätön käytännön tarkoitusperiin, ja että laadun heikennys on sisällytettävä koulutusaineistoon ongelman yli pääsemiseksi
27
Ammermüller, Sebastian, Oliver Bohl, Oliver Gerstheimer, and Shakib Manouchehri. "Ansätze zur Nutzung Sozialer Netzwerke mittels mobiler Endgeräte." Technische Universität Dresden, 2007. https://tud.qucosa.de/id/qucosa%3A27898.
Full textAbstract:
Die Vernetzung einer Vielzahl unterschiedlicher Nutzergruppen in privaten und beruflichen Kontexten wird durch webbasierte Soziale Netzwerke (Social Networks) wie Myspace, Linkedin und Flickr gefördert. Zahlreiche Personen nutzen zudem so genannte Social Software wie Skype, Del.icio.us, YouTube oder den aktuellen Newcomer twitter. Entsprechende Anwendungen werden durch moderne Informationsund Kommunikationstechnologien (IKT), zumeist durch Internettechnologien, realisiert und ermöglichen es den Nutzern, entweder neue Inhalte zu erstellen, und diese dann mit ausgewählten Personen (oder auch mit der Öffentlichkeit) zu teilen, oder sie dienen dazu, Verbindungen mit bestehenden Kontakten abzubilden sowie Neue aufzubauen. Gleichzeitig ist für die meisten Menschen heutzutage der Gebrauch mobiler Endgeräte ein wesentlicher Bestandteil ihres alltäglichen Lebens. In Folge dessen wird in der Verbindung dieser beiden, zunächst separaten, Felder eine, wenn nicht gar die „Killer-Anwendung“ für mobile Dienstleistungen vermutet. Der vorliegende Beitrag hat das Ziel, Potentiale und Grenzen der weit reichenden Verbreitung von Social Software und Sozialen Netzwerken auf mobile Endgeräte zu analysieren.
28
Krkusic, Enis. "Security of the mobile devices in VäxjöKommun and corporation." Thesis, Växjö University, School of Mathematics and Systems Engineering, 2009. http://urn.kb.se/resolve?urn=urn:nbn:se:vxu:diva-6253.
Full text
29
Altrabsheh, Bilal. "Investigation of low cost techniques for realising microwave and millimeter-wave network analysers." Thesis, University of Surrey, 2003. http://epubs.surrey.ac.uk/843309/.
Full textAbstract:
The work presented in this thesis is on the development of reliable low cost measurement systems for measuring microwave and millimetre-wave devices. The purpose of this work is to find techniques which use multiple power detectors and can measure magnitude and phase without the need for expensive superheterodyne receivers. Two novel microwave measurement systems have been designed with the intention of providing a measurement facility which enables the characterisation of both active and passive devices in terms of their scattering parameters. The first method is based on using a multistate reflectometer, which uses dielectric waveguide in the frequency range of 110GHz up to 170GHz. The dielectric multistate reflectometer is a four-port reflectometer, which uses a programmable phase shifter to give a flat relative phase shift over the entire frequency range of the dielectric waveguides used in the multistate reflectometer. The phase shifter has an eccentric rotating cylinder with an offset axis to allow a number of different phase shifts to the wave travelling in the dielectric waveguides in the multistate reflectometer. This system has been developed as an equivalent to a one-port network analyser. The second method is based on using the multi-probe reflectometer in which the standing wave in a line is measured using a number of fixed detector probes. A microstrip line prototype in the frequency range of 1GHz to 5.5GHz has been demonstrated and the design of a monolithic microwave integrated circuit (MMIC) version for the frequency range of 40GHz to 325GHz has been earned out. Improved methods of calibration of the system have been derived as well as different methods for error correction. The realisation of a full two-port network analyser using the technique has been demonstrated. Key words: dielectric multistate reflectometer, programmable phase shifter, multi-probe reflectometer, detection, microwave measurement, millimetre-wave measurement, calibration, error corrections.
30
Coue, Dominique Xavier Henri Leon. "Feedforward artificial neural network design utilising subthreshold mode CMOS devices." Thesis, University of Plymouth, 1997. http://hdl.handle.net/10026.1/1633.
Full textAbstract:
This thesis reviews various previously reported techniques for simulating artificial neural networks and investigates the design of fully-connected feedforward networks based on MOS transistors operating in the subthreshold mode of conduction as they are suitable for performing compact, low power, implantable pattern recognition systems. The principal objective is to demonstrate that the transfer characteristic of the devices can be fully exploited to design basic processing modules which overcome the linearity range, weight resolution, processing speed, noise and mismatch of components problems associated with weak inversion conduction, and so be used to implement networks which can be trained to perform practical tasks. A new four-quadrant analogue multiplier, one of the most important cells in the design of artificial neural networks, is developed. Analytical as well as simulation results suggest that the new scheme can efficiently be used to emulate both the synaptic and thresholding functions. To complement this thresholding-synapse, a novel current-to-voltage converter is also introduced. The characteristics of the well known sample-and-hold circuit as a weight memory scheme are analytically derived and simulation results suggest that a dummy compensated technique is required to obtain the required minimum of 8 bits weight resolution. Performance of the combined load and thresholding-synapse arrangement as well as an on-chip update/refresh mechanism are analytically evaluated and simulation studies on the Exclusive OR network as a benchmark problem are provided and indicate a useful level of functionality. Experimental results on the Exclusive OR network and a 'QRS' complex detector based on a 10:6:3 multilayer perceptron are also presented and demonstrate the potential of the proposed design techniques in emulating feedforward neural networks.
31
Kao, Yi-Hsuan. "Optimizing task assignment for collaborative computing over heterogeneous network devices." Thesis, University of Southern California, 2016. http://pqdtopen.proquest.com/#viewpdf?dispub=10124490.
Full textAbstract:
The Internet of Things promises to enable a wide range of new applications involving sensors, embedded devices and mobile devices. Different from traditional cloud computing, where the centralized and powerful servers offer high quality computing service, in the era of the Internet of Things, there are abundant computational resources distributed over the network. These devices are not as powerful as servers, but are easier to access with faster setup and short-range communication. However, because of energy, computation, and bandwidth constraints on smart things and other edge devices, it will be imperative to collaboratively run a computational-intensive application that a single device cannot support individually. As many IoT applications, like data processing, can be divided into multiple tasks, we study the problem of assigning such tasks to multiple devices taking into account their abilities and the costs, and latencies associated with both task computation and data communication over the network.
A system that leverages collaborative computing over the network faces highly variant run-time environment. For example, the resource released by a device may suddenly decrease due to the change of states on local processes, or the channel quality may degrade due to mobility. Hence, such a system has to learn the available resources, be aware of changes and flexibly adapt task assignment strategy that efficiently makes use of these resources.
We take a step by step approach to achieve these goals. First, we assume that the amount of resources are deterministic and known. We formulate a task assignment problem that aims to minimize the application latency (system response time) subject to a single cost constraint so that we will not overuse the available resource. Second, we consider that each device has its own cost budget and our new multi-constrained formulation clearly attributes the cost to each device separately. Moving a step further, we assume that the amount of resources are stochastic processes with known distributions, and solve a stochastic optimization with a strong QoS constraint. That is, instead of providing a guarantee on the average latency, our task assignment strategy gives a guarantee that p% of time the latency is less than t, where p and t are arbitrary numbers. Finally, we assume that the amount of run-time resources are unknown and stochastic, and design online algorithms that learn the unknown information within limited amount of time and make competitive task assignment.
We aim to develop algorithms that efficiently make decisions at run-time. That is, the computational complexity should be as light as possible so that running the algorithm does not incur considerable overhead. For optimizations based on known resource profile, we show these problems are NP-hard and propose polynomial-time approximation algorithms with performance guarantee, where the performance loss caused by sub-optimal strategy is bounded. For online learning formulations, we propose light algorithms for both stationary environment and non-stationary environment and show their competitiveness by comparing the performance with the optimal offline policy (solved by assuming the resource profile is known).
We perform comprehensive numerical evaluations, including simulations based on trace data measured at application run-time, and validate our analysis on algorithm's complexity and performance based on the numerical results. Especially, we compare our algorithms with the existing heuristics and show that in some cases the performance loss given by the heuristic is considerable due to the sub-optimal strategy. Hence, we conclude that to efficiently leverage the distributed computational resource over the network, it is essential to formulate a sophisticated optimization problem that well captures the practical scenarios, and provide an algorithm that is light in complexity and suggests a good assignment strategy with performance guarantee.
32
Lindqvist, Anna. "Threats to smart buildings : Securing devices in a SCADA network." Thesis, Linköpings universitet, Institutionen för datavetenskap, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-176723.
Full textAbstract:
This paper examines the possibilities of performing tests with the aim to ensure that devices in a SCADA network can be deemed secure before deployment. SCADA systems are found in most industries and have recently seen an increased use in building automation, most importantly the healthcare sector, which means that a successful attack toward such a system could endanger lives of patients and healthcare professionals.The method of testing was created to examine whether devices conflicted with the security flaws identified by OWASP IoT Top 10 list, meaning that OWASP IoT Top 10 was the foundation for the methodology used in this paper.Results of the tests show that the devices used in testing are not in conflict with the OWASP IoT Top 10 list when using the default settings. However, some settings that can be enabled on the devices would constitute a security risk if enabled.
33
Dikme, Altay. "A Quantum Neural Network for Noisy Intermediate Scale Quantum Devices." Thesis, KTH, Tillämpad fysik, 2021. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-300394.
Full textAbstract:
Neural networks have helped the field of machine learning grow tremendously in the past decade, and can be used to solve a variety of real world problems such as classification problems. On another front, the field of quantum computing has advanced, with quantum devices publicly available via the cloud. The availability of such systems has led to the creation of a new field of study, Quantum Machine Learning, which attempts to create quantum analogues of classical machine learning techniques. One such method is the Quantum Neural Network (QNN) inspired by classical neural networks. In this thesis we design a QNN compatible with Noisy Intermediate Scale Quantum (NISQ) devices, which are characterised by a limited number of qubits and small decoherence times. Furthermore we provide an implementation of the QNN classifier using the open source quantum computing software development kit, Qiskit provided by IBM. We perform a binary classification experiment on a subset of the MNIST data set, and our results showed a classification accuracy of 80.6% for a QNN with circuit depth 20.Neurala nätverk har varit en stor del av utvecklingen av maskininlärning som ett forskningsområde i det senaste årtiondet, och dessa nätverk har flera appliceringsområden, som till exempel klassificieringsproblemet. Parallelt med denna utveckling, har forskning kring kvantdatorer vuxit fram, med flera kvantsystem allmänt tillgängliga via molnet. Denna tillgänglighet har lett till skapandet av ett nytt forskningsområde; kvantmaskininlärning, som försöker skapa motsvarigheter till klassiska maskininlärningsmetoder på kvantdatorer. En sån metod är kvantneurala nätverk som inspireras av klassiska neurala nätverk. I denna avhandling designar vi ett kvantneuralt närverk som är kompatibel med nuvarande kvantsystem, som kännetecknas av ett begränsat antal qubits och korta dekoherenstider. Dessutom tillhandahåller vi en implementering av en klassificerare med ett kvantneuralt nätverk, med hjälp av IBMs programvaruutvecklingsmiljö Qiskit. Vi utför ett binärt klassificeringsexperiment på en delmängd av MNIST-datamängden, och våra resultatvisar en klassificeringsnoggrannhet på 80,6% för ett kvantneuralt nätverk med kretsdjup 20.
34
Nafziger, Jonathan W. "A Novel Cache Migration Scheme in Network-on-Chip Devices." University of Cincinnati / OhioLINK, 2010. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1282327354.
Full text
35
Phillips, Ian D. "OTDM network processing using all-optical and electro-optical devices." Thesis, Aston University, 1998. http://publications.aston.ac.uk/15370/.
Full textAbstract:
The current optical communications network consists of point-to-point optical transmission paths interconnected with relatively low-speed electronic switching and routing devices. As the demand for capacity increases, then higher speed electronic devices will become necessary. It is however hard to realise electronic chip-sets above 10 Gbit/s, and therefore to increase the achievable performance of the network, electro-optic and all-optic switching and routing architectures are being investigated. This thesis aims to provide a detailed experimental analysis of high-speed optical processing within an optical time division multiplexed (OTDM) network node. This includes the functions of demultiplexing, 'drop and insert' multiplexing, data regeneration, and clock recovery. It examines the possibilities of combining these tasks using a single device. Two optical switching technologies are explored. The first is an all-optical device known as 'semiconductor optical amplifier-based nonlinear optical loop mirror' (SOA-NOLM). Switching is achieved by using an intense 'control' pulse to induce a phase shift in a low-intensity signal propagating through an interferometer. Simultaneous demultiplexing, data regeneration and clock recovery are demonstrated for the first time using a single SOA-NOLM. The second device is an electroabsorption (EA) modulator, which until this thesis had been used in a uni-directional configuration to achieve picosecond pulse generation, data encoding, demultiplexing, and 'drop and insert' multiplexing. This thesis presents results on the use of an EA modulator in a novel bi-directional configuration. Two independent channels are demultiplexed from a high-speed OTDM data stream using a single device. Simultaneous demultiplexing with stable, ultra-low jitter clock recovery is demonstrated, and then used in a self-contained 40 Gbit/s 'drop and insert' node. Finally, a 10 GHz source is analysed that exploits the EA modulator bi-directionality to increase the pulse extinction ratio to a level where it could be used in an 80 Gbit/s OTDM network.
36
Carela, Español Valentín. "Network traffic classification : from theory to practice." Doctoral thesis, Universitat Politècnica de Catalunya, 2014. http://hdl.handle.net/10803/283573.
Full textAbstract:
Since its inception until today, the Internet has been in constant transformation. The analysis and monitoring of data networks try to shed some light on this huge black box of interconnected computers. In particular, the classification of the network traffic has become crucial for understanding the Internet. During the last years, the research community has proposed many solutions to accurately identify and classify the network traffic. However, the continuous evolution of Internet applications and their techniques to avoid detection make their identification a very challenging task, which is far from being completely solved.
This thesis addresses the network traffic classification problem from a more practical point of view, filling the gap between the real-world requirements from the network industry, and the research carried out.
The first block of this thesis aims to facilitate the deployment of existing techniques in production networks. To achieve this goal, we study the viability of using NetFlow as input in our classification technique, a monitoring protocol already implemented in most routers. Since the application of packet sampling has become almost mandatory in large networks, we also study its impact on the classification and propose a method to improve the accuracy in this scenario. Our results show that it is possible to achieve high accuracy with both sampled and unsampled NetFlow data, despite the limited information provided by NetFlow.
Once the classification solution is deployed it is important to maintain its accuracy over time. Current network traffic classification techniques have to be regularly updated to adapt them to traffic changes. The second block of this thesis focuses on this issue with the goal of automatically maintaining the classification solution without human intervention. Using the knowledge of the first block, we propose a classification solution that combines several techniques only using Sampled NetFlow as input for the classification. Then, we show that classification models suffer from temporal and spatial obsolescence and, therefore, we design an autonomic retraining system that is able to automatically update the models and keep the classifier accurate along time.
Going one step further, we introduce next the use of stream-based Machine Learning techniques for network traffic classification. In particular, we propose a classification solution based on Hoeffding Adaptive Trees. Apart from the features of stream-based techniques (i.e., process an instance at a time and inspect it only once, with a predefined amount of memory and a bounded amount of time), our technique is able to automatically adapt to the changes in the traffic by using only NetFlow data as input for the classification.
The third block of this thesis aims to be a first step towards the impartial validation of state-of-the-art classification techniques. The wide range of techniques, datasets, and ground-truth generators make the comparison of different traffic classifiers a very difficult task. To achieve this goal we evaluate the reliability of different Deep Packet Inspection-based techniques (DPI) commonly used in the literature for ground-truth generation. The results we obtain show that some well-known DPI techniques present several limitations that make them not recommendable as a ground-truth generator in their current state. In addition, we publish some of the datasets used in our evaluations to address the lack of publicly available datasets and make the comparison and validation of existing techniques easier.
37
Lim, Chee Peng. "Autonomous neural network systems for pattern classification." Thesis, University of Sheffield, 1996. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.242285.
Full text
38
Van, Heerden Renier Pelser. "A formalised ontology for network attack classification." Thesis, Rhodes University, 2014. http://hdl.handle.net/10962/d1011603.
Full textAbstract:
One of the most popular attack vectors against computers are their network connections. Attacks on computers through their networks are commonplace and have various levels of complexity. This research formally describes network-based computer attacks in the form of a story, formally and within an ontology. The ontology categorises network attacks where attack scenarios are the focal class. This class consists of: Denial-of- Service, Industrial Espionage, Web Defacement, Unauthorised Data Access, Financial Theft, Industrial Sabotage, Cyber-Warfare, Resource Theft, System Compromise, and Runaway Malware. This ontology was developed by building a taxonomy and a temporal network attack model. Network attack instances (also know as individuals) are classified according to their respective attack scenarios, with the use of an automated reasoner within the ontology. The automated reasoner deductions are verified formally; and via the automated reasoner, a relaxed set of scenarios is determined, which is relevant in a near real-time environment. A prototype system (called Aeneas) was developed to classify network-based attacks. Aeneas integrates the sensors into a detection system that can classify network attacks in a near real-time environment. To verify the ontology and the prototype Aeneas, a virtual test bed was developed in which network-based attacks were generated to verify the detection system. Aeneas was able to detect incoming attacks and classify them according to their scenario. The novel part of this research is the attack scenarios that are described in the form of a story, as well as formally and in an ontology. The ontology is used in a novel way to determine to which class attack instances belong and how the network attack ontology is affected in a near real-time environment.
39
Labarge, Isaac E. "Neural Network Pruning for ECG Arrhythmia Classification." DigitalCommons@CalPoly, 2020. https://digitalcommons.calpoly.edu/theses/2136.
Full textAbstract:
Convolutional Neural Networks (CNNs) are a widely accepted means of solving complex classification and detection problems in imaging and speech. However, problem complexity often leads to considerable increases in computation and parameter storage costs. Many successful attempts have been made in effectively reducing these overheads by pruning and compressing large CNNs with only a slight decline in model accuracy. In this study, two pruning methods are implemented and compared on the CIFAR-10 database and an ECG arrhythmia classification task. Each pruning method employs a pruning phase interleaved with a finetuning phase. It is shown that when performing the scale-factor pruning algorithm on ECG, finetuning time can be expedited by 1.4 times over the traditional approach with only 10% of expensive floating-point operations retained, while experiencing no significant impact on accuracy.
40
Shu, Xingliang. "Electrocardiograph Signal Classification By Using Neural Network." University of Cincinnati / OhioLINK, 2020. http://rave.ohiolink.edu/etdc/view?acc_num=ucin1592395089900722.
Full text
41
Zhou, Wei. "Autonomous smart antenna systems for future mobile devices." Thesis, University of Edinburgh, 2015. http://hdl.handle.net/1842/9959.
Full textAbstract:
Along with the current trend of wireless technology innovation, wideband, compact size, low-profile, lightweight and multiple functional antenna and array designs are becoming more attractive in many applications. Conventional wireless systems utilise omni-directional or sectored antenna systems. The disadvantage of such antenna systems is that the electromagnetic energy, required by a particular user located in a certain direction, is radiated unnecessarily in every direction within the entire cell, hence causing interference to other users in the system. In order to limit this source of interference and direct the energy to the desired user, smart antenna systems have been investigated and developed. This thesis presents the design, simulation, fabrication and full implementation of a novel smart antenna system for future mobile applications. The design and characterisation of a novel antenna structure and four-element liner array geometry for smart antenna systems are proposed in the first stage of this study. Firstly, a miniaturised microstrip-fed planar monopole antenna with Archimedean spiral slots to cover WiFi/Bluetooth and LTE mobile applications has been demonstrated. The fundamental structure of the proposed antenna element is a circular patch, which operates in high frequency range, for the purpose of miniaturising the circuit dimension. In order to achieve a multi-band performance, Archimedean spiral slots, acting as resonance paths, have been etched on the circular patch antenna. Different shapes of Archimedean spiral slots have been investigated and compared. The miniaturised and optimised antenna achieves a bandwidth of 2.2GHz to 2.9GHz covering WiFi/Bluetooth (2.45GHz) and LTE (2.6GHz) mobile standards. Then a four-element linear antenna array geometry utilising the planar monopole elements with Archimedean spiral slots has been described. All the relevant parameters have been studied and evaluated. Different phase shifts are excited for the array elements, and the main beam scanning range has been simulated and analysed. The second stage of the study presents several feeding network structures, which control the amplitude and phase excitations of the smart antenna elements. Research begins with the basic Wilkinson power divider configuration. Then this thesis presents a compact feeding network for circular antenna array, reconfigurable feeding networks for tuning the operating frequency and polarisations, a feeding network on high resistivity silicon (HRS), and an ultrawide-band (UWB) feeding network covering from 0.5GHz to 10GHz. The UWB feeding network is used to establish the smart antenna array system. Different topologies of phase shifters are discussed in the third stage, including ferrite phase shifters and planar phase shifters using switched delay line and loaded transmission line technologies. Diodes, FETs, MMIC and MEMS are integrated into different configurations. Based on the comparison, a low loss and high accurate Hittite MMIC analogue phase shifter has been selected and fully evaluated for this implementation. For the purpose of impedance matching and field matching, compact and ultra wideband CPW-to-Microstrip transitions are utilised between the phase shifters, feeding network and antenna elements. Finally, the fully integrated smart antenna array achieves a 10dB reflection coefficient from 2.25GHz to 2.8GHz, which covers WiFi/Bluetooth (2.45GHz) and LTE (2.6GHz) mobile applications. By appropriately controlling the voltage on the phase shifters, the main beam of the antenna array is steered ±50° and ±52°, for 2.45GHz and 2.6GHz, respectively. Furthermore, the smart antenna array demonstrates a gain of 8.5dBi with 40° 3dB bandwidth in broadside direction, and has more than 10dB side lobe level suppression across the scan. The final stage of the study investigates hardware and software automatic control systems for the smart antenna array. Two microcontrollers PIC18F4550 and LPC1768 are utilised to build the control PCBs. Using the graphical user interfaces provided in this thesis, it is able to configure the beam steering of the smart antenna array, which allows the user to analyse and optimise the signal strength of the received WiFi signals around the mobile device. The design strategies proposed in this thesis contribute to the realisation of adaptable and autonomous smart phone systems.
42
Pierfederici, Eugenio. "Inferring the behaviour and security of networked devices via communication analysis." Master's thesis, Alma Mater Studiorum - Università di Bologna, 2019. http://amslaurea.unibo.it/19418/.
Full textAbstract:
In the last years the number of devices connected to the Internet has been increasing exponentially and it has reached huge numbers, just days ago the RIPE Network Coordination Center announced it run out of IPv4 addresses.
As a consequence, it's extremely complex to control what is happening on the network and what, or whom, a device is communicating with. We are losing control over many of our devices. It's becoming everyday more difficult to know what the device is doing and what is it sharing on the Internet.
Luckily, in the last years the attention to security, privacy and awareness is ever increasing: the users pay more attention to what their devices are doing and care about it.
While big software (like the operative systems and most mobile devices) make available an increasing number of tools to monitor the device traffic, some devices cannot be inspected or those same tools may be forged in a way that makes it impossible to detect some specific malicious behaviours.
Until now every successful method to detect or filter the behaviour of the devices has been trying to only detect anomalies or manually lock some specific behaviours; this means nobody ever tried to understand at a discrete
level of accuracy what the device does relying only on the analysis of the metadata of the traffic intercepted.
That’s why in this thesis I defined a model able to detect the behaviour which is occurring on the device by the mere observation of its network traffic. In doing so, I first defined a model that takes the raw low-level information regarding the communications occurring, process them and return information about the high-level operations occurring on the device. I then built a demo that uses that model and demonstrates its feasibility. The data used are low-level information on the traffic without ever inspecting its payload.
To improve the efficiency of the algorithm, I also use a form of Recurrent Neural Networks to finally infer the device behaviour.
43
Chu, Guang Yong. "Photonic devices for next generation fiber-to-the-home access network." Doctoral thesis, Universitat Politècnica de Catalunya, 2016. http://hdl.handle.net/10803/386564.
Full textAbstract:
It would be unaffordable if the WDM-PON technologies were directly applied for massive deployment. Hence, the potential WDM-PON is to be integrated and improved in order to adapt it for NGPON and the future 5G. The UDWDM-PON can be considered as an ultimate solution for the next-generation access network capable of providing unlimited bandwidth for each user, thanks to the coherent detection.
Plenty of scientists have believed that it is crucial to increase the operating speed and maximum reach of WDM-PON, while it has no sense if people achieve them without a ordable cost.
In order to apply them cost-effciently, the system should require colorless ONUs and bidirectional systems. It is desired that the whole system use modulators on a low bias consumption, even limit the number of amplifiers.
However, for bidirectional transmission the backscattering effects would limit the performance if we want to reuse the carrier from OLT. So, we should design a method to separate the wavelength between upstream and downstream.
The traditional UDWDM-PON uses 2 laser at ONU, in this thesis, the single-DFB based ONUs are presented with integrated devices.
What is the most plausible configuration? The photonic devices such as RSOA, DEML, FML with advanced configurations are presented in this thesis with different applications.
The proposed thesis includes these parts: key devices for WDM-PON and the chirp parameters of these integrated photonic devices are measured, the polarization independent RSOA with different applications is also included, demonstration of dual output DEML with bidirectional coherent UDWDM-PON transmission, mitigating residual AM of DEML for phase modulation, and fast tuning for the UDWDM channel via FML are described.Por sus altos requerimientos técnicos, sería inasumible aplicar las tecnologías WDM-PON directamente para el despliegue masivo de Fiber-to-the-Home de nueva generación. Por lo tanto, el potencial se WDM-PON se debe integrar y mejorar con el fin de adaptarlo para NGPON y el futuro 5G. Hoy dia, operadores, usuarios y científicos, ven crucial augmentar la velocitat de funcionament y el alcance de las redes de acceso PON, si bien no tiene sentido conseguirlo con un coste inasequible. El UDWDM-PON puede considerarse como una solución definitiva para la red de acceso de próxima generación, capaz de proporcionar ancho de banda ilimitado para cada usuario, gracias a la detección coherente, por lo que en esta tesis se aborda su realización con un coste e integración prácticos. Con el fin de aplicarlos de manera rentable, el sistema debería exigir a las ONU que sean idénticas, si láseres preseleccionados o incoloros, y ser bidireccionales. Se desea que el conjunto de moduladores del sistema tengan en un bajo consumo, e incluso limitar el número de amplificadores. Sin embargo, para la transmisión bidireccional los efectos de retrodispersión limitarían el rendimiento si queremos volver a utilizar la portadora generada en la OLT. Por lo tanto, debemos diseñar un método para separar la longitud de onda en las transmisiones de bajada y de retorno del usuario a la central. El tradicional UDWDM-PON utiliza 2 láseres en la ONU; en esta tesis, las ONUs usan dispositivos integrados basados en un sólo DFB. ¿Cuál es la configuración más plausible? Los dispositivos fotónicos como RSOA, DEML, FML con configuraciones avanzadas se presentan en esta tesis con diferentes aplicaciones, que resuelven distintos problemas técnicos. La tesis incluye las siguientes partes: análisis y medida de dispositivos fotónicos clave para WDM-PON con modulación de fase, la independencia a la polarización de RSOA con diferentes aplicaciones, demostración de DEML con doble salida para transmisión bidireccional coherente UDWDM-PON, mitigación de AM residual de DEML para la modulación de fase, y la sintonía rápida de canal de UDWDM a través de FML.
44
Martínez, Anny. "An ontology-based approach toward the configuration of heterogeneous network devices." Doctoral thesis, Universitat Politècnica de Catalunya, 2015. http://hdl.handle.net/10803/299803.
Full textAbstract:
Despite the numerous efforts of standardization, semantic issues remain in effect in many subfields of networking. The inability to exchange data unambiguously between information systems and human resources is an issue that hinders technology implementation, semantic interoperability, service deployment, network management, technology migration, among many others. In this thesis, we will approach the semantic issues in two critical subfields of networking, namely, network configuration management and network addressing architectures. The fact that makes the study in these areas rather appealing is that in both scenarios semantic issues have been around from the very early days of networking. However, as networks continue to grow in size and complexity current practices are becoming neither scalable nor practical.
One of the most complex and essential tasks in network management is the configuration of network devices. The lack of comprehensive and standard means for modifying and controlling the configuration of network elements has led to the continuous and extended use of proprietary Command Line Interfaces (CLIs). Unfortunately, CLIs are generally both, device and vendor-specific. In the context of heterogeneous network infrastructures---i.e., networks typically composed of multiple devices from different vendors---the use of several CLIs raises serious Operation, Administration and Management (OAM) issues. Accordingly, network administrators are forced to gain specialized expertise and to continuously keep knowledge and skills up to date as new features, system upgrades or technologies appear. Overall, the utilization of proprietary mechanisms allows neither sharing knowledge consistently between vendors' domains nor reusing configurations to achieve full automation of network configuration tasks---which are typically required in autonomic management. Due to this heterogeneity, CLIs typically provide a help feature which is in turn an useful source of knowledge to enable semantic interpretation of a vendor's configuration space. The large amount of information a network administrator must learn and manage makes Information Extraction (IE) and other forms of natural language analysis of the Artificial Intelligence (AI) field key enablers for the network device configuration space. This thesis presents the design and implementation specification of the first Ontology-Based Information Extraction (OBIE) System from the CLI of network devices for the automation and abstraction of device configurations. Moreover, the so-called semantic overload of IP addresses---wherein addresses are both identifiers and locators of a node at the same time---is one of the main constraints over mobility of network hosts, multi-homing and scalability of the routing system. In light of this, numerous approaches have emerged in an effort to decouple the semantics of the network addressing scheme. In this thesis, we approach this issue from two perspectives, namely, a non-disruptive (i.e., evolutionary) solution to the current Internet and a clean-slate approach for Future Internet. In the first scenario, we analyze the Locator/Identifier Separation Protocol (LISP) as it is currently one of the strongest solutions to the semantic overload issue. However, its adoption is hindered by existing problems in the proposed mapping systems. Herein, we propose the LISP Redundancy Protocol (LRP) aimed to complement the LISP framework and strengthen feasibility of deployment, while at the same time, minimize mapping table size, latency time and maximize reachability in the network. In the second scenario, we explore TARIFA a Next Generation Internet architecture and introduce a novel service-centric addressing scheme which aims to overcome the issues related to routing and semantic overload of IP addresses.A pesar de los numerosos esfuerzos de estandarización, los problemas de semántica continúan en efecto en muchas subáreas de networking. La inabilidad de intercambiar data sin ambiguedad entre sistemas es un problema que limita la interoperabilidad semántica. En esta tesis, abordamos los problemas de semántica en dos áreas: (i) la gestión de configuración y (ii) arquitecturas de direccionamiento. El hecho que hace el estudio en estas áreas de interés, es que los problemas de semántica datan desde los inicios del Internet. Sin embargo, mientras las redes continúan creciendo en tamaño y complejidad, los mecanismos desplegados dejan de ser escalabales y prácticos. Una de las tareas más complejas y esenciales en la gestión de redes es la configuración de equipos. La falta de mecanismos estándar para la modificación y control de la configuración de equipos ha llevado al uso continuado y extendido de interfaces por líneas de comando (CLI). Desafortunadamente, las CLIs son generalmente, específicos por fabricante y dispositivo. En el contexto de redes heterogéneas--es decir, redes típicamente compuestas por múltiples dispositivos de distintos fabricantes--el uso de varias CLIs trae consigo serios problemas de operación, administración y gestión. En consecuencia, los administradores de red se ven forzados a adquirir experiencia en el manejo específico de múltiples tecnologías y además, a mantenerse continuamente actualizados en la medida en que nuevas funcionalidades o tecnologías emergen, o bien con actualizaciones de sistemas operativos. En general, la utilización de mecanismos propietarios no permite compartir conocimientos de forma consistente a lo largo de plataformas heterogéneas, ni reutilizar configuraciones con el objetivo de alcanzar la completa automatización de tareas de configuración--que son típicamente requeridas en el área de gestión autonómica. Debido a esta heterogeneidad, las CLIs suelen proporcionar una función de ayuda que fundamentalmente aporta información para la interpretación semántica del entorno de configuración de un fabricante. La gran cantidad de información que un administrador debe aprender y manejar, hace de la extracción de información y otras formas de análisis de lenguaje natural del campo de Inteligencia Artificial, potenciales herramientas para la configuración de equipos en entornos heterogéneos. Esta tesis presenta el diseño y especificaciones de implementación del primer sistema de extracción de información basada en ontologías desde el CLI de dispositivos de red, para la automatización y abstracción de configuraciones. Por otra parte, la denominada sobrecarga semántica de direcciones IP--en donde, las direcciones son identificadores y localizadores al mismo tiempo--es una de las principales limitaciones sobre mobilidad, multi-homing y escalabilidad del sistema de enrutamiento. Por esta razón, numerosas propuestas han emergido en un esfuerzo por desacoplar la semántica del esquema de direccionamiento de las redes actuales. En esta tesis, abordamos este problema desde dos perspectivas, la primera de ellas una aproximación no-disruptiva (es decir, evolucionaria) al problema del Internet actual y la segunda, una nueva propuesta en torno a futuras arquitecturas del Internet. En el primer escenario, analizamos el protocolo LISP (del inglés, Locator/Identifier Separation Protocol) ya que es en efecto, una de las soluciones con mayor potencial para la resolucion del problema de semántica. Sin embargo, su adopción está limitada por problemas en los sistemas de mapeo propuestos. En esta tesis, proponemos LRP (del inglés, LISP Redundancy Protocol) un protocolo destinado a complementar LISP e incrementar la factibilidad de despliegue, a la vez que, reduce el tamaño de las tablas de mapeo, tiempo de latencia y maximiza accesibilidad. En el segundo escenario, exploramos TARIFA una arquitectura de red de nueva generación e introducimos un novedoso esquema de direccionamiento orientado a servicios.
45
Mandowara, Piyush. "Live video streaming for handheld devices over an ad hoc network." Manhattan, Kan. : Kansas State University, 2008. http://hdl.handle.net/2097/941.
Full text
46
Larsson, Magnus. "Sanitization of embedded network devices : Investigation of vendor’s factory reset procedure." Thesis, KTH, Radio Systems Laboratory (RS Lab), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-166305.
Full textAbstract:
Embedded devices such as routers, switches, and firewalls commonly have sensitive information stored on them such as passwords, cryptographic keys, and information about the network around them and services that these device(s) provide. When disposing of or reselling this equipment in the secondary market it is crucial to erase this sensitive information. However, there is an important question that must be asked: Do the erase commands and routines offered by the device manufacturers actually erase the sensitive data? This thesis investigates methods and tools to determine the completeness of this erasure in some common network devices. These methods are used on a sample of networking equipment found to still contain sensitive information after being erased according to vendor recommendations. A computer program was developed to show how this information can be removed. The information in this document is useful for equipment owners, brokers and others looking to remarket their current equipment; all of whom want to minimize the risk of leaking sensitive data to other parties.Nätverksutrustning såsom routrar, switchar och brandväggar har ofta känslig information lagrad internt, som lösenord, kryptografiska nycklar, information om nätverket runt dem samt tjänster de tillhandahåller. Om denna utrustning ska säljas på andrahandsmarkanden eller på annat sätt byta ägare är det viktigt att all känslig information raderas. Men kan man lita på att raderings rutiner och metoder som tillhandahålls av tillverkaren verkligen raderar känslig data? Denna avhandling undersöker lämpliga verktyg och metoder för att granska vilken information som minnen i inbyggda system innehåller. Dessa metoder testas praktiskt på några system som visar sig ha kvar känslig information efter att de raderats enligt tillverkarens rekommendationer. Ett datorprogram som demonstrerar hur denna information kan undersökas och raderas finns med som en del av avhandlingen. Informationen i detta dokument är användbar för ägare av datakomutrustning, mäklare av sådana samt andra som vill minimera risken för att läcka känslig information vid återförsäljning av sin begagnade utrustning.
47
Kobezak, Philip D. "Frequent Inventory of Network Devices for Incident Response: A Data-driven Approach to Cybersecurity and Network Operations." Thesis, Virginia Tech, 2018. http://hdl.handle.net/10919/83375.
Full textAbstract:
Challenges exist in higher education networks with host inventory and identification. Any student, staff, faculty, or dedicated IT administrator can be the primary responsible personnel for devices on the network. Confounding the problem is that there is also a large mix of personally-owned devices. These network environments are a hybrid of corporate enterprise, federated network, and Internet service provider. This management model has survived for decades based on the ability to identify responsible personnel when a host, system, or user account is suspected to have been compromised or is disrupting network availability for others. Mobile devices, roaming wireless access, and users accessing services from multiple devices has made the task of identification onerous. With increasing numbers of hosts on networks of higher education institutions, strategies such as dynamic addressing and address translation become necessary. The proliferation of the Internet of Things (IoT) makes this identification task even more difficult. Loss of intellectual property, extortion, theft, and reputational damage are all significant risks to research institution networks. Quickly responding to and remediating incidents reduces exposure and risk.
This research evaluates what universities are doing for host inventory and creates a working prototype of a system for associating relevant log events to one or more responsible people. The prototype reduces the need for human-driven updates while enriching the dynamic host inventory with additional information. It also shows the value of associating application and service authentications to hosts. The prototype uses live network data which is de-identified to protect privacy.Master of Science
48
San, Pedro Miguel G. "Signal classification using the mean separator neural network." Thesis, Monterey, Calif. : Springfield, Va. : Naval Postgraduate School ; Available from National Technical Information Service, 2000. http://handle.dtic.mil/100.2/ADA377744.
Full textAbstract:
Thesis (M.S. in Electrical Engineering) Naval Postgraduate School, March 2000.Thesis advisor(s): Fargues, Monique P. ; Hippenstiel, Ralph D. "March 2000." Includes bibliographical references (p. 193-194). Also available online.
49
au, P. Kraipeerapun@murdoch edu, and Pawalai Kraipeerapun. "Neural network classification based on quantification of uncertainty." Murdoch University, 2009. http://wwwlib.murdoch.edu.au/adt/browse/view/adt-MU20090526.100525.
Full textAbstract:
This thesis deals with feedforward backpropagation neural networks and interval neutrosophic sets for the binary and multiclass classification problems. Neural networks are used to predict true and false output values. These results together with the uncertainty of type error and vagueness occurred in the prediction are then represented in the form of interval neutrosophic sets. Each element in an interval neutrosophic set consists of three membership values: truth, indeterminacy, and false. These three membership values are then used in the classification process. For binary classification, a pair of neural networks is first applied in order to predict the degrees of truth and false membership values. Subsequently, bagging technique is applied to an ensemble of pairs of neural networks in order to improve the performance. For multiclass classification, two basic multiclass classification methods are proposed. A pair of neural networks with multiple outputs and multiple pairs of binary neural network are experimented. A number of aggregation techniques are proposed in this thesis. The difference between each pair of the truth and false membership values determines the vagueness value. Error occurred in the prediction are estimated using an interpolation technique. Both vagueness and error then form the indeterminacy membership. Two and three dimensional visualization of the three membership values are also presented. Ten data sets obtained from UCI machine learning repository are experimented with the proposed approaches. The approaches are also applied to two real world problems: mineral prospectivity prediction and lithofacies classification.
50
Kraipeerapun, Pawalai. "Neural network classification based on quantification of uncertainty." Kraipeerapun, Pawalai (2009) Neural network classification based on quantification of uncertainty. PhD thesis, Murdoch University, 2009. http://researchrepository.murdoch.edu.au/699/.
Full textAbstract:
This thesis deals with feedforward backpropagation neural networks and interval neutrosophic sets for the binary and multiclass classification problems. Neural networks are used to predict “true” and “false” output values. These results together with the uncertainty of type error and vagueness occurred in the prediction are then represented in the form of interval neutrosophic sets. Each element in an interval neutrosophic set consists of three membership values: truth, indeterminacy, and false. These three membership values are then used in the classification process. For binary classification, a pair of neural networks is first applied in order to predict the degrees of truth and false membership values. Subsequently, bagging technique is applied to an ensemble of pairs of neural networks in order to improve the performance. For multiclass classification, two basic multiclass classification methods are proposed. A pair of neural networks with multiple outputs and multiple pairs of binary neural network are experimented. A number of aggregation techniques are proposed in this thesis. The difference between each pair of the truth and false membership values determines the vagueness value. Error occurred in the prediction are estimated using an interpolation technique. Both vagueness and error then form the indeterminacy membership. Two and three dimensional visualization of the three membership values are also presented. Ten data sets obtained from UCI machine learning repository are experimented with the proposed approaches. The approaches are also applied to two real world problems: mineral prospectivity prediction and lithofacies classification.