Dissertations / Theses on the topic 'Backaction of the detection system'
To see the other types of publications on this topic, follow the link: Backaction of the detection system.
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 'Backaction of the detection system.'
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
Ohlson, Frida, and Nadim Al-Mosawi. "Occupant Detection System." Thesis, Högskolan i Halmstad, Bio- och miljösystemforskning (BLESS), 2015. http://urn.kb.se/resolve?urn=urn:nbn:se:hh:diva-28617.
Full textAbstract:
The purpose of the ODS (Occupant Detection System) project is to develop a car safety camera system that is able to discriminate human occupants in order to activate safety features depending on the human size. In order to discriminate the size of an occupant anthropometric measurements need to be performed. The aim of this study was to investigate the possibility of anthropometric measurements of human height and weight with a Kinect for Windows v2 sensor for discrimination of different occupants inside a vehicle. The goal was to find valid anthropometric methods for determination of human height and weight from landmarks on the upper body, then test if it is possible to perform these methods with the Kinect for Windows v2 sensor. The execution of this study was performed as a literature study with anthropometric tests on ATD-dummies (anthropomorphic test device) and on human test subjects. Measurements were performed first physically and then with the Kinect v2 sensor to obtain data in form of distance of 8 regions of the body. Three tests were performed, first on dummies, second was a pilot study and last the measurement study. The result revealed that it is hard to estimate human weight from body landmarks due to lack of information, therefor no tests were performed in this area. For height the result showed that the most valid methods were the measurements on arm span and ulna, both on physical measurements and with the camera. The conclusion is that it is possible estimating height from body landmarks but the positioning of the camera needs to be change in order for the measurements to be more accurate. This study has contributed to a greater understanding of measurement technology, automotive safety and anthropometric measurements.
2
Matos, Diogo Silva. "Person detection system." Master's thesis, Universidade de Aveiro, 2017. http://hdl.handle.net/10773/23853.
Full textAbstract:
mestrado em Engenharia Eletrónica e TelecomunicaçõesO RADAR é para fins militares já relativamente antigo que sofreu um grande impulso durante a Segunda Guerra Mundial. Hoje em dia existe um forte desenvolvimento no RADAR em aplicações de navegação ou vigilância/segurança. Esta dissertação surge no seguimento destas novas aplicações, em que se pretende o desenvolvimento de um RADAR de baixo custo que permita ao utilizador detetar pessoas, bem como, os seus movimentos através de paredes ou objetos opacos. O desenvolvimento deste RADAR recaiu em tecnologias emergentes como antenas adaptativas e rádio definido por software que permitem uma grande versatilidade e adaptação em termos de aplicações. A utilização de um RADAR com múltiplas entradas e múltiplas saídas fornece uma maior diversidade de informação que garante mais probabilidades de deteção. A aplicação de técnicas digitais de beamforming, possibilita conhecer a posição e o movimento da pessoa. Com a implementação destas técnicas um protótipo capaz de detetar pessoas e os seus movimentos através de paredes e tijolos foi desenvolvido com sucesso solucionando o problema inicial. Na fase de projeto de RADAR houve necessidade de caracterizar a propagação de ondas de rádio em materiais de construção, como tijolos e madeira, medindo-se a sua atenuação. Deste modo foi possível fazer o balanço de potencia para varios canarios.
The RADAR is already relatively old for military purposes that underwent a major development during World War II. Nowadays there is a strong development in RADAR in navigation or surveillance/security applications. This dissertation follows on from these new applications, which aim to develop a low cost RADAR that allows the user to detect people as well as their movements through walls or opaque objects. The development of this RADAR has relied on emerging technologies such as adaptive antennas and SDR that allow for great versatility and adaptation in terms of applications. The use of a MIMO RADAR provides a greater diversity of information that guarantees more probabilities of detection and the application of digital techniques of beamforming, allows to know the position and the movement of the person. With the implementation of these techniques a prototype capable of detecting people and their movements through walls and bricks was successfully developed solving the initial problem. In the RADAR design phase it was necessary to characterize the propagation of radio waves in building materials, such as bricks and wood, by measuring their attenuation. In this way it was possible to perform the power balance for several scenarios.
3
Michala, Anna-Lito. "Capillary glucose detection system." Thesis, University of Strathclyde, 2008. http://ethos.bl.uk/OrderDetails.do?uin=uk.bl.ethos.502356.
Full textAbstract:
Glucose absorbs electromagnetic energy in the near infrared (NIR) spectrum at characteristic wavelengths. An NIR beam is transmitted and as it passes through a solution this absorbance causes detectable spectral changes. The amount of spectral absorbance can be correlated to the concentration of glucose in the solution. In this study we used NIR Spectroscopy and micro sensors and detectors in order to detect glucose in small volume samples with economic instrumentation. The goal was to accurately measure the concentration of glucose in a solution held in a glass capillary vessel.
4
Sainani, Varsha. "Hybrid Layered Intrusion Detection System." Scholarly Repository, 2009. http://scholarlyrepository.miami.edu/oa_theses/44.
Full textAbstract:
The increasing number of network security related incidents has made it necessary for the organizations to actively protect their sensitive data with network intrusion detection systems (IDSs). Detecting intrusion in a distributed network from outside network segment as well as from inside is a difficult problem. IDSs are expected to analyze a large volume of data while not placing a significant added load on the monitoring systems and networks. This requires good data mining strategies which take less time and give accurate results. In this study, a novel hybrid layered multiagent-based intrusion detection system is created, particularly with the support of a multi-class supervised classification technique. In agent-based IDS, there is no central control and therefore no central point of failure. Agents can detect and take predefined actions against malicious activities, which can be detected with the help of data mining techniques. The proposed IDS shows superior performance compared to central sniffing IDS techniques, and saves network resources compared to other distributed IDSs with mobile agents that activate too many sniffers causing bottlenecks in the network. This is one of the major motivations to use a distributed model based on a multiagent platform along with a supervised classification technique. Applying multiagent technology to the management of network security is a challenging task since it requires the management on different time instances and has many interactions. To facilitate information exchange between different agents in the proposed hybrid layered multiagent architecture, a low cost and low response time agent communication protocol is developed to tackle the issues typically associated with a distributed multiagent system, such as poor system performance, excessive processing power requirement, and long delays. The bandwidth and response time performance of the proposed end-to-end system is investigated through the simulation of the proposed agent communication protocol on our private LAN testbed called Hierarchical Agent Network for Intrusion Detection Systems (HAN-IDS). The simulation results show that this system is efficient and extensible since it consumes negligible bandwidth with low cost and low response time on the network.
5
Johansson, Emil, and Kim Myhrman. "GSM/WCDMA Leakage Detection System." Thesis, Linköpings universitet, Elektroniksystem, 2011. http://urn.kb.se/resolve?urn=urn:nbn:se:liu:diva-66963.
Full textAbstract:
Ericsson in Linkoping houses one of the largest test laboratories within thewhole Ericsson Company. Mainly, the laboratories contain equipment forGSM, WCDMA and LTE. To test these systems, a quite large number ofRadio Base Stations are needed. The RBS's are housed in a proportionatelysmall area. Instead of sending signals through the air, cables are used totransfer the RF signals. In this way the equipment communicating witheach other are well speci ed. However this may not be the case if leakageoccur.This thesis work is about developing a system for monitoring the radioenvironment and detect leakages in the test site. There is a need to de newhat a leakage really is and measurements needs to be performed in order toaccomplish this. This report describes how the work has proceeded towardsthe nal implemented solution.
6
Ballard, B., T. Degnan, M. Kipp, J. Johnson, D. Miller, and M. Minto. "Mine Safety Detection System (MSDS)." Thesis, Monterey, California. Naval Postgraduate School, 2012. http://hdl.handle.net/10945/17457.
Full textAbstract:
Systems Engineering Project ReportApproved for public release, distribution unlimited
The search, detection, identification and assessment components of the U.S. Navys organic modular in-stride Mine Countermeasure (MCM) Concept of Operations (CONOPS) have been evaluated for their effectiveness as part of a hypothetical exercise in response to the existence of sea mines placed in the sea lanes of the Strait of Hormuz. The current MCM CONOPS has been shown to be capable of supporting the mine search and detection effort component allocation needs by utilizing two Airborne Mine Countermeasure (AMCM) deployed systems. This adequacy assessment is tenuous. The CONOPS relies heavily upon the Sikorsky MH- 60/S as the sole platform from which the systems operate. This reliance is further compounded by the fact both AMCM systems are not simultaneously compatible on board the MH-60/S. As such, resource availability will challenge the MCM CONOPS as well as the other missions for which the MH-60/S is intended. Additionally, the AMCM CONOPS systems are dependent upon the presence of warfighters in the helicopters above the minefield and as integral participants in the efforts to identify sea mines and to assess their threat level. Model Based System Engineering (MBSE) techniques have been combined with research and stakeholder inputs in an analysis that supports these assertions.m
7
Maharjan, Nadim, and Paria Moazzemi. "Telemetry Network Intrusion Detection System." International Foundation for Telemetering, 2012. http://hdl.handle.net/10150/581632.
Full textAbstract:
ITC/USA 2012 Conference Proceedings / The Forty-Eighth Annual International Telemetering Conference and Technical Exhibition / October 22-25, 2012 / Town and Country Resort & Convention Center, San Diego, CaliforniaTelemetry systems are migrating from links to networks. Security solutions that simply encrypt radio links no longer protect the network of Test Articles or the networks that support them. The use of network telemetry is dramatically expanding and new risks and vulnerabilities are challenging issues for telemetry networks. Most of these vulnerabilities are silent in nature and cannot be detected with simple tools such as traffic monitoring. The Intrusion Detection System (IDS) is a security mechanism suited to telemetry networks that can help detect abnormal behavior in the network. Our previous research in Network Intrusion Detection Systems focused on "Password" attacks and "Syn" attacks. This paper presents a generalized method that can detect both "Password" attack and "Syn" attack. In this paper, a K-means Clustering algorithm is used for vector quantization of network traffic. This reduces the scope of the problem by reducing the entropy of the network data. In addition, a Hidden-Markov Model (HMM) is then employed to help to further characterize and analyze the behavior of the network into states that can be labeled as normal, attack, or anomaly. Our experiments show that IDS can discover and expose telemetry network vulnerabilities using Vector Quantization and the Hidden Markov Model providing a more secure telemetry environment. Our paper shows how these can be generalized into a Network Intrusion system that can be deployed on telemetry networks.
8
Sonbul, O., M. Byamukama, S. Alzebda, and A. N. Kalashnikov. "Autonomous intrusion detection information system." Thesis, Сумський державний університет, 2012. http://essuir.sumdu.edu.ua/handle/123456789/28777.
Full textAbstract:
Abstract – Implementation of security arrangements for insecure premises, for example, for temporary exhibitions or infrequent public events, usually results in substantial security personnel costs which can be potentially reduced by employing an easily installable ad hoc intrusion detection information system. In the paper we described the architecture, design and experimental results for a fully prototyped information system that utilizes ultrasonic sensors operating in the pulse echo mode for the perimeter control and ZigBee transceivers for wireless networking. The system consists of inexpensive autonomous sensor nodes with the component cost of less than £25 and a control terminal with a graphical user interface controlled by a touch screen. The nodes are programmed wirelessly to detect intrusion within any user set distance up to the operating distance of the node, and can operate unattended for days.
When you are citing the document, use the following link http://essuir.sumdu.edu.ua/handle/123456789/28777
9
Ademi, Muhamet. "Web-Based Intrusion Detection System." Thesis, Malmö högskola, Fakulteten för teknik och samhälle (TS), 2013. http://urn.kb.se/resolve?urn=urn:nbn:se:mau:diva-20271.
Full textAbstract:
Web applications are growing rapidly and as the amount of web sites globallyincreases so do security threats. Complex applications often interact with thirdparty services and databases to fetch information and often interactions requireuser input. Intruders are targeting web applications specifically and they are ahuge security threat to organizations and a way to combat this is to haveintrusion detection systems. Most common web attack methods are wellresearched and documented however due to time constraints developers oftenwrite applications fast and may not implement the best security practices. Thisreport describes one way to implement a intrusion detection system thatspecifically detects web based attacks.
10
Khan, Muhammad. "Hand Gesture Detection & Recognition System." Thesis, Högskolan Dalarna, Datateknik, 2012. http://urn.kb.se/resolve?urn=urn:nbn:se:du-6496.
Full textAbstract:
The project introduces an application using computer vision for Hand gesture recognition. A camera records a live video stream, from which a snapshot is taken with the help of interface. The system is trained for each type of count hand gestures (one, two, three, four, and five) at least once. After that a test gesture is given to it and the system tries to recognize it.A research was carried out on a number of algorithms that could best differentiate a hand gesture. It was found that the diagonal sum algorithm gave the highest accuracy rate. In the preprocessing phase, a self-developed algorithm removes the background of each training gesture. After that the image is converted into a binary image and the sums of all diagonal elements of the picture are taken. This sum helps us in differentiating and classifying different hand gestures.Previous systems have used data gloves or markers for input in the system. I have no such constraints for using the system. The user can give hand gestures in view of the camera naturally. A completely robust hand gesture recognition system is still under heavy research and development; the implemented system serves as an extendible foundation for future work.
11
Satam, Shalaka Chittaranjan, and Shalaka Chittaranjan Satam. "Bluetooth Anomaly Based Intrusion Detection System." Thesis, The University of Arizona, 2017. http://hdl.handle.net/10150/625890.
Full textAbstract:
Bluetooth is a wireless technology that is used to communicate over personal area networks (PAN). With the advent of Internet of Things (IOT), Bluetooth is the technology of choice for small and short range communication networks. For instance, most of the modern cars have the capability to connect to mobile devices using Bluetooth. This ubiquitous presence of Bluetooth makes it important that it is secure and its data is protected. Previous work has shown that Bluetooth is vulnerable to attacks like the man in the middle attack, Denial of Service (DoS) attack, etc. Moreover, all Bluetooth devices are mobile devices and thus power utilization is an import performance parameter. The attacker can easily increase power consumption of a mobile device by launching an attack vector against that device.
As a part of this thesis we present an anomaly based intrusion detection system for Bluetooth network, Bluetooth IDS (BIDS). The BIDS uses Ngram based approach to characterize the normal behavior of the Bluetooth protocol. Machine learning algorithms were used to build the normal behavior models for the protocol during the training phase of the system, and thus allowing classification of observed Bluetooth events as normal or abnormal during the operational phase of the system. The experimental results showed that the models that were developed in this thesis had a high accuracy with precision of 99.2% and recall of 99.5%.
12
Prasad, Praveen. "A dynamically reconfigurable intrusion detection system." NCSU, 2003. http://www.lib.ncsu.edu/theses/available/etd-05202003-181843/.
Full textAbstract:
This dissertation implements a Network Based Intrusion Detection System on a Dynamically Reconfigurable Architecture. The design is captured using synthesizable Verilog HDL. The Dynamically Reconfigurable Intrusion Detection System (DRIDS) addresses the challenges faced by typical applications that use Reconfigurable devices that do not exploit their full computational density because of the limited FPGA memory, inefficient FPGA utilization, processor to FPGA communication bottlenecks and high reconfiguration latencies. The implementation of Intrusion Detection on the DRIDS boasts of high computational density and better performance through the exploitation of parallelism inherent in this application.
13
Chu, Liang. "ADSL system enhancement with multiuser detection." Diss., Georgia Institute of Technology, 2001. http://hdl.handle.net/1853/14972.
Full text
14
Song, Jingping. "Feature selection for intrusion detection system." Thesis, Aberystwyth University, 2016. http://hdl.handle.net/2160/3143de58-208f-405e-ab18-abcecfc8f33b.
Full textAbstract:
Intrusion detection is an important task for network operators in today?s Internet. Traditional network intrusion detection systems rely on either specialized signatures of previously seen attacks, or on labeled traffic datasets that are expensive and difficult to reproduce for user-profiling to hunt out network attacks. Machine learning methods could be used in this area since they could get knowledge from signatures or as normal-operation profiles. However, there is usually a large volume of data in intrusion detection systems, for both features and instances. Feature selection can be used to optimize the classifiers used to identify attacks by removing redundant or irrelevant features while improving the quality. In this thesis, six feature selection algorithms are developed, and their application to intrusion detection is evaluated. They are: Cascading Fuzzy C Means Clustering and C4.5 Decision Tree Classification Algorithm, New Evidence Accumulation Ensemble with Hierarchical Clustering Algorithm, Modified Mutual Information-based Feature Selection Algorithm, Mutual Information-based Feature Grouping Algorithm, Feature Grouping by Agglomerative Hierarchical Clustering Algorithm, and Online Streaming Feature Selection Algorithm. All algorithms are evaluated on the KDD 99 dataset, the most widely used data set for the evaluation of anomaly detection methods, and are compared with other algorithms. The potential application of these algorithms beyond intrusion detection is also examined and discussed.
15
Kindle, Alexander Lawrence. "An Embedded Seizure Onset Detection System." Digital WPI, 2013. https://digitalcommons.wpi.edu/etd-theses/1035.
Full textAbstract:
"A combined hardware and software platform for ambulatory seizure onset detection is presented. The hardware is developed around commercial off-the-shelf components, featuring ADS1299 analog front ends for electroencephalography from Texas Instruments and a Broadcom ARM11 microcontroller for algorithm execution. The onset detection algorithm is a patient-specific support vector machine algorithm. It outperforms a state-of-the-art detector on a reference data set, with 100% sensitivity, 3.4 second average onset detection latency, and on average 1 false positive per 24 hours. The more comprehensive European Epilepsy Database is then evaluated, which highlights several real-world challenges for seizure onset detection, resulting in reduced average sensitivity of 93.5%, 5 second average onset detection latency, and 85.5% specificity. Algorithm enhancements to improve this reduced performance are proposed."
16
Barrios, Rita M. "An Adaptive Database Intrusion Detection System." NSUWorks, 2011. http://nsuworks.nova.edu/gscis_etd/86.
Full textAbstract:
Intrusion detection is difficult to accomplish when attempting to employ current methodologies when considering the database and the authorized entity. It is a common understanding that current methodologies focus on the network architecture rather than the database, which is not an adequate solution when considering the insider threat. Recent findings suggest that many have attempted to address this concern with the utilization of various detection methodologies in the areas of database authorization, security policy management and behavior analysis but have not been able to find an adequate solution to achieve the level of detection that is required.
While each of these methodologies has been addressed on an individual basis, there has been very limited work to address the methodologies as a single entity in an attempt to function within the detection environment in a harmonious fashion. Authorization is at the heart of most database implementations however, is not enough to prevent a rogue, authorized entity from instantiating a malicious action. Similarly, eliminating the current security policies only exacerbates the problem due to a lack of knowledge in a fashion when the policies have been modified. The behavior of the authorized entity is the most significant concern in terms of intrusion detection. However, behavior identification methodologies alone will not produce a complete solution. The detection of the insider threat during database access by merging the individual intrusion detection methodologies as noted will be investigated.
To achieve the goal, this research is proposing the creation of a procedural framework to be implemented as a precursor to the effecting of the data retrieval statement. The intrusion model and probability thresholds will be built utilizing the intrusion detection standards as put forth in research and industry. Once an intrusion has been indicated, the appropriate notifications will be distributed for further action by the security administrator while the transaction will continue to completion.
This research is proposing the development of a Database Intrusion Detection framework with the introduction of a process as defined in this research, to be implemented prior to data retrieval. This addition will enable an effective and robust methodology to determine the probability of an intrusion by the authorized entity, which will ultimately address the insider threat phenomena.
17
Abas, Ashardi B. "Non-intrusive driver drowsiness detection system." Thesis, University of Bradford, 2011. http://hdl.handle.net/10454/5521.
Full textAbstract:
The development of technologies for preventing drowsiness at the wheel is a major challenge in the field of accident avoidance systems. Preventing drowsiness during driving requires a method for accurately detecting a decline in driver alertness and a method for alerting and refreshing the driver. As a detection method, the authors have developed a system that uses image processing technology to analyse images of the road lane with a video camera integrated with steering wheel angle data collection from a car simulation system. The main contribution of this study is a novel algorithm for drowsiness detection and tracking, which is based on the incorporation of information from a road vision system and vehicle performance parameters. Refinement of the algorithm is more precisely detected the level of drowsiness by the implementation of a support vector machine classification for robust and accurate drowsiness warning system. The Support Vector Machine (SVM) classification technique diminished drowsiness level by using non intrusive systems, using standard equipment sensors, aim to reduce these road accidents caused by drowsiness drivers. This detection system provides a non-contact technique for judging various levels of driver alertness and facilitates early detection of a decline in alertness during driving. The presented results are based on a selection of drowsiness database, which covers almost 60 hours of driving data collection measurements. All the parameters extracted from vehicle parameter data are collected in a driving simulator. With all the features from a real vehicle, a SVM drowsiness detection model is constructed. After several improvements, the classification results showed a very good indication of drowsiness by using those systems.
18
Moyers, Benjamin. "Multi-Vector Portable Intrusion Detection System." Thesis, Virginia Tech, 2009. http://hdl.handle.net/10919/34265.
Full textAbstract:
This research describes an intrusion detection system designed to fulfill the need for increased mobile device security. The Battery-Sensing Intrusion Protection System (B-SIPS) [1] initially took a non-conventional approach to intrusion detection by recognizing attacks based on anomalous Instantaneous Current (IC) drainage. An extension of B-SIPS, the Multi-Vector Portable Intrusion Detection System (MVP-IDS) validates the idea of recognizing attacks based on anomalous IC drain by correlating the detected anomalies with wireless attack traffic from both the Wi-Fi and Bluetooth mediums. To effectively monitor the Wi-Fi and Bluetooth mediums for malicious packet streams, the Snort-Based Wi-Fi and Bluetooth Attack Detection and Signature System (BADSS) modules were introduced.
MVP-IDS illustrates that IC anomalies, representing attacks, can be correlated with wireless attack traffic through a collaborative and multi-module approach. Furthermore, MVP-IDS not only correlates wireless attacks, but mitigates them and defends its clients using an administrative response mechanism.
This research also provides insight into the ramifications of battery exhaustion Denial of Service (DoS) attacks on battery-powered mobile devices. Several IEEE 802.11 Wi-Fi, IEEE 802.15.1 Bluetooth, and blended attacks are studied to understand their effects on device battery lifetimes. In the worst case, DoS attacks against mobile devices were found to accelerate battery depletion as much as 18.5%. However, if the MVP-IDS version of the B-SIPS client was allowed to run in the background during a BlueSYN flood attack, it could mitigate the attack and preserve as much as 16% of a mobile deviceâ s battery lifetime as compared with an unprotected device.Master of Science
19
Lino, Fábio Blessa Fernandes. "Development of a botnet detection system." Master's thesis, Universidade de Aveiro, 2009. http://hdl.handle.net/10773/2194.
Full textAbstract:
Mestrado em Engenharia de Computadores e TelemáticaO tráfego ilícito é um dos maiores problemas da segurança em redes. É necessária uma estratégia global contra esta ameaça, uma vez que este problema pode afectar a economia gerada pela internet a um nível global nos próximos anos. As técnicas tradicionais de detecção de computadores zombie, como antivírus, firewalls e anti-spywares não são eficientes contra esta ameaça. A principal razão para este fracasso é a limitação imposta pelas metodologias tradicionais face ás novas ameaças que constantemente aparecem. Para ultrapassar esta limitação, propomos uma nova abordagem diferente dos actuais sistemas de detecção de intrusões, que conjugada com os métodos tradicionais pode garantir um nível elevado de segurança. Esta nova abordagem é baseada na identificação de padrões de tráfego de rede. Cada serviço de rede tem uma característica que o define e, sendo assim, podemos tirar partido desse facto para identificar o tráfego ilícito correspondente a botnets e outros malwares. Para identificar o que é tráfego ilícito e o que é lícito, é usada uma Rede Neuronal Artificial que é treinada para identificar os padrões de tráfego de rede correspondentes ao tráfico ilícito. Depois de identificado o tráfego ilícito, o sistema proposto neste trabalho vai gerar alarmes que alertarão o administrador do sistema em caso de identificação de computadores zombie ou infectados. O próximo passo será tomar uma medida preventiva, que pode ir desde bloquear o endereço IP correspondente a essa máquina até colocá-la sob um nível de vigilância extra. Os resultados obtidos mostram que esta metodologia de identificação de tráfego ilícito é uma técnica possível de ser usada no dia-a-dia devido à sua elevada taxa de identificação e à sua baixa carga computacional. Esta técnica pode identificar problemas actualmente indetectáveis pelas metodologias vulgarmente usadas. ABSTRACT: Illicit traffic is one of the major issues in network security. A strategy for a global partnership against it is needed in order to avoid illicit traffic from becoming a serious threat to the Internet economy and to global security in the forthcoming years. Traditional Zombie detection techniques, such as antivirus, firewalls and anti-spyware are not effective against this threat. The main reason for this failure is the limitation of these traditional methodologies to detect new threats. To overcome this limitation, we propose a new intrusion detection approach that works together with traditional methods in order to ensure a higher level of protection/security. This new approach is based on the identification of traffic patterns. Each network service, as well as illicit traffic corresponding to botnets and other malwares, has a characteristic traffic pattern that can univocally identify it. In order to decide which network traffic is illicit or licit, we use an Artificial Neural Network that is trained to identify the illicit patterns. After identifying the illicit traffic, the proposed system will generate alarms to the system administrator in order to alert him about a Zombie or an infected computer. After this identification phase, the system administrator can take a security action, like blocking the corresponding IP Address or putting it under a deeper surveillance. The results obtained show that this is a feasible and efficient methodology, since it provides high detection rates with low computational overhead. So, we believe that this methodology can be an emergent technique that will deal with untraceable threats that current methodologies are unable to deal with.
20
Chung, Chieh-Hao, and 鍾杰澔. "Extravasation detection system." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/vv8pge.
Full textAbstract:
碩士國立陽明大學
生物醫學工程學系
105
Peripheral intravenous therapy(PIV) has been existed for a long time and it is one of the important and common therapies in the hospital. However, it causes lots of medical lawsuits about extravasation in clinical until Gautier and Massa invented a plastic catheter in 1950. It reduces the rate of happenings of extravasation and almost intravenous therapies are using this kind of catheters. But now the problems about extravasation are still existing in hospitals all over the world. There are a lot of risk factors, such as patient's physiological, patient's condition and the medical properties...and so on, resulting to extravasation and it occurs usually with no consciousness, for example sleeping and moving. Furthermore, the situation of lacking medical human resource, health care personnel cannot observe the events immediately leading to the serious injuries happened. Thus, the research is about a system using microcontroller and amplifier circuit to detect the happenings of extravasation when patients are using PIV therapies. We claim to use a non-invasive method to detect the incidents efficiently and alarm immediately. In order to achieve this goal, we design a special sensor with an infrared laser diode and photodiodes arranged like a matrix. In paper review, it is called a serious extravasation incident when the medicine leak to peripheral tissue over 20ml. However, it also cause a serious damage on tissue when the leakage of medicine less than 20ml. This study is to require only the liquid of leakage within 3ml can be able to identify the occurrence of extravasation, and to reduce extravasation injury.
21
Han, Hsiao-Yu, and 韓孝羽. "Pedestrian Detection System." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/17041573286496364901.
Full textAbstract:
碩士國立交通大學
電機與控制工程系
89
In this thesis, we propose a new pedestrian detection algorithm, and use it to develop a real-time pedestrian detection system. The pedestrian detection algorithm can be functionally partitioned into two parts: moving object segmentation and pedestrian recognition. In moving object segmentation, we segment the moving objects in the scene by modified temporal differencing method. This method combines general temporal differencing method with detection nets. In pedestrian recognition, we obtain multi-type wavelet templates from input images. Interest points are extracted from wavelet templates. We exploit frequency analysis and multi-scale features in wavelet templates and local features in interest point templates. Then, feature points are extracted by statistical method from interest point templates. Finally, these feature points are fed into a trained multilayer back-propagation neural network. The output of the neural network implies the result — pedestrian or non-pedestrian. The pedestrian detection algorithm has the following advantages: (1) Learning from masses of example images: this avoids the drawback of general shape-based methods that need handcrafted models. (2) Not relying on motion patterns: the pedestrian recognition procedure only needs one image. (3) The system can detect pedestrians in variety of clothes, hairstyles, gender, walking poses and walking directions. (4) The processing speed in pedestrian detection is fast. This algorithm can be realized in real time. (5) From experiments, accuracy rate of recognition achieves 95%. We implement this algorithm in a real-time pedestrian detection system. The system can detect pedestrians in the scene in real time. The pedestrian detection rate is 89.58%.
22
LO, SHENG-TI, and 羅聖迪. "Abandoned Object Detection System." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/22353809856672699178.
Full textAbstract:
碩士國立聯合大學
電子工程學系碩士班
104
The study proposes a surveillance system to detect the abandoned objects in the region under surveillance. The CMOS sensor is used to acquire frames including the region to be kept under surveillance. The acquired frame is analysed by the proposed abandoned object detection algorithm. The algorithm can segment foreground from the acquired frame, remove shadows in the segmented foreground, determine whether there are objects. If there are objects in the acquired frame, the algorithm distinguishes between abandoned objects and missing ones and issue the corresponding warning signals. The MATLAB simulation results demonstrate the system possesses the following features: (1) The system can continuously renew the background frame to preserve the latest environmental information. (2) It can remove the shadow to obtain accurate foreground objects. (3) It can detect all the abandoned and missing objects and issue warning signals correctly. (4) All the overlapping abandoned objects can be detected correctly. Moreover, for the purpose of real-time image processing and development environment similar to an embedded system, we install Linux OS environment to realize the proposed algorithm in C++ with OpenCV library on PC with the real video source of lobby scope.
23
Pawar, Rohit S. "Multilingual Cyberbullying Detection System." Thesis, 2019. http://hdl.handle.net/1805/18942.
Full textAbstract:
Indiana University-Purdue University Indianapolis (IUPUI)Since the use of social media has evolved, the ability of its users to bully others has increased. One of the prevalent forms of bullying is Cyberbullying, which occurs on the social media sites such as Facebook©, WhatsApp©, and Twitter©. The past decade has witnessed a growth in cyberbullying – is a form of bullying that occurs virtually by the use of electronic devices, such as messaging, e-mail, online gaming, social media, or through images or mails sent to a mobile. This bullying is not only limited to English language and occurs in other languages. Hence, it is of the utmost importance to detect cyberbullying in multiple languages. Since current approaches to identify cyberbullying are mostly focused on English language texts, this thesis proposes a new approach (called Multilingual Cyberbullying Detection System) for the detection of cyberbullying in multiple languages (English, Hindi, and Marathi). It uses two techniques, namely, Machine Learning-based and Lexicon-based, to classify the input data as bullying or non-bullying. The aim of this research is to not only detect cyberbullying but also provide a distributed infrastructure to detect bullying. We have developed multiple prototypes (standalone, collaborative, and cloud-based) and carried out experiments with them to detect cyberbullying on different datasets from multiple languages. The outcomes of our experiments show that the machine-learning model outperforms the lexicon-based model in all the languages. In addition, the results of our experiments show that collaboration techniques can help to improve the accuracy of a poor-performing node in the system. Finally, we show that the cloud-based configurations performed better than the local configurations.
24
蘇芳生. "Facial Expression Detection System." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/14647436644952580750.
Full textAbstract:
碩士國立中正大學
通訊工程研究所
92
In this research, we develop a system to recognize facial expression automatically. First , we extract the seventeen significant feature points of a face and then use these feature points to recognize facial expression. During recognition, we first compare feature points of the novel face and the expressional face. We then project the feature vector on decided expressions feature vector in order to choose the possible emotion by using database of facial expression. Finally, we decide an emotion of a facial expression. In here, we train expressions feature vectors by using the method of multi-category Gradient Descent to improve our recognition rate. We use pictures offered by Department of Psychology, NCCU, to recognize facial expression in this research. The four emotion are anger, happiness, surprise, and sadness and we have successfully classified these four emotions with average error smaller than 15%.
25
林佑達. "Driver Fatigue Detection System." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/75892498724729345339.
Full textAbstract:
碩士國立彰化師範大學
電子工程學系
102
Traffic accidents take place at present multifarious, have already become the biggest secret worry of government and society gradually. For need of a driver who drives for a long time to come to say, the attention is not centralized, the easy doze goes more the most take place and dangerous condition among the car! How to effectively avoid the accident occurrence, promote people's life security, is already the subject that the public pay attention to. The system built up by this research's making use of eyes to open, shut to judge a pilot has already had no fatigue for a set of driver's fatigue detects the system", this way is through photograph device to pick the image, again make use of the YCbCr color space, ray in expiation of, image processing the technique and eyes distinguish to the spirit condition of keeping watch on the pilot, once the system detects pilot's eyes to shut too long last time, then will immediately send out an alarm voice, make the pilot able to immediately wide awake, ensure the car safety.
26
謝昌甫. "Human face detection system." Thesis, 2001. http://ndltd.ncl.edu.tw/handle/33813411288787563185.
Full textAbstract:
碩士中華大學
資訊工程學系碩士班
89
With the improvement of science and technology, the usage of human-machine interface is more popular and convenient in the recent years. A fast and accu-rate face detection approach is important for several applications, such as face recognition, security system, human-machine interface and TV-conference,etc. This thesis proposes a new method to detect human eyes and uses feature-based approach with fuzzy logic theorem for face candidates confirmation. According to this detecting scheme, we can obtain the face location, face tilt angle, face size and predict the distance between a human and the camera. These information are very useful for further applications.
27
Vigo, Jr John L. "Wireless intrusion detection system." 2004. http://etd-db.uno.edu/theses/available/etd-11242004-142849/.
Full textAbstract:
Thesis (M.S.)--University of New Orleans, 2004.Title from electronic submission form. "A thesis ... in partial fulfillment of the requirements for the degree of Master of Science in the Department of Computer Science."--Thesis t.p. Vita. Includes bibliographical references.
28
Lin, I.-Ting, and 林翊庭. "Trace Biomolecule detection system." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/48040027795353165060.
Full textAbstract:
碩士臺灣大學
材料科學與工程學研究所
98
Biomolecule detection system has been rapidly developed, and it has also been generally applied onto early diagnosis of cancer. Commonly seen system such as immunoradiometric assay(IRMA)、fluorescence immunoassay(FIA)、chemiluminescence immunoassay(CLIA)、enzyme-linked immunoassay(ELISA)、immuno-polymerase chain reaction(Immuno-PCR) are all functioning effectively. Among them, there is a system which is called immuno-PCR is working through specific binding between antibody in the system and the antigen/biomplecules. The antigen which is captured will be combined with detection antibody –DNA fragment complex in the system, and the DNA fragment can be duplicated by PCR technology to enlarge the signal. Therefore, the sensitivity of immuno-PCR is much better than the commonly used ELISA system. So far we have known that immuno-PCR is to fix antibody on glass substrate by any means in order to catch antigen. However, the hydrophilic antigen or proteins are easily attached to hydrophilic glass substrate, and cause non-specific binding which leads to the inaccuracy in examination result. To improve the accuracy in examination result, a layer of hydrophobic diamond film has been grown on silicon substrate by MPCVD to decrease non-specific binding, subsequently the multi-walled carbon nanotubes are grown on it by HFCVD. After that the substrate processed an acid treatment, and then connected with PEG bis-amine, which can decrease non-specific binding by its steric repulsion, and the repulsion due to its negative electricity, which caused a waving effect . Moreover, it was connected to the C-terminal of α-1 antitrypsin antibody, and let the N-terminal of antibody can still remain active and caught the corresponded α-1 antitrypsin protein. After that we added in the detection antibody, that is, biotinylated α-1 antitrypsin antibody, which could be captured by the α-1 antitrypsin protein on the substrate. At the same time, the detection antibody was connected to the biotinylated DNA fragment through streptavidin, therefore we could amplify the signal by PCR. In order to know the sensitivity and specificity of the system, α-1 antitrypsin proteins with different concentration have been detected. Polylysine has also been added in to compare that if the non-specific binding has diminished or not. The experiment result turns out that the diamond film which is under 300 sccm hydrogen, 20 sccm methane, 1.5 sccm nitrogen, 100 torr chamber pressure, 1200W microwave power, 180 minutes growing time and processed for 1 hour heat treatment under 580°C demonstrates best quality of hydrophobicity and is also better for following growth of carbon nanotubes, while under the condition of 140 sccm nitrogen, 17.5 sccm C2H2, growing temperature 800°C, precursor sublimed temperature 200°C, growing time 120 minutes can grow the carbon nanotubes which is longer, has larger specific surface area, with uniform thickness, and the directionality. Also, from the experiment result, it shows that the detection limit of the trace biomolecule detection system built up by this research is about 0.02 μg/ml, and the unwanted signal will not appear if the concentration of non-specific protein is less than 100 μg/ml.
29
(6613247), Rohit Sidram Pawar. "MULTILINGUAL CYBERBULLYING DETECTION SYSTEM." Thesis, 2019.
Find full textAbstract:
Since the use of social media has evolved, the ability of its users to bully others has increased. One of the prevalent forms of bullying is Cyberbullying, which occurs on the social media sites such as Facebook©, WhatsApp©, and Twitter©. The past decade has witnessed a growth in cyberbullying – is a form of bullying that occurs virtually by the use of electronic devices, such as messaging, e-mail, online gaming, social media, or through images or mails sent to a mobile. This bullying is not only limited to English language and occurs in other languages. Hence, it is of the utmost importance to detect cyberbullying in multiple languages. Since current approaches to identify cyberbullying are mostly focused on English language texts, this thesis proposes a new approach (called Multilingual Cyberbullying Detection System) for the detection of cyberbullying in multiple languages (English, Hindi, and Marathi). It uses two techniques, namely, Machine Learning-based and Lexicon-based, to classify the input data as bullying or non-bullying. The aim of this research is to not only detect cyberbullying but also provide a distributed infrastructure to detect bullying. We have developed multiple prototypes (standalone, collaborative, and cloud-based) and carried out experiments with them to detect cyberbullying on different datasets from multiple languages. The outcomes of our experiments show that the machine-learning model outperforms the lexicon-based model in all the languages. In addition, the results of our experiments show that collaboration techniques can help to improve the accuracy of a poor-performing node in the system. Finally, we show that the cloud-based configurations performed better than the local configurations.
30
Chen, Hung-Yuan, and 陳鴻源. "Android malware detection system." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/89zu7w.
Full textAbstract:
碩士國立臺中科技大學
資訊工程系碩士班
104
Currently, android system has a high market share in the mobile device market, because of the system allows users to install the unofficial apps. Besides, applications decompilation and modification is not difficult, so it will be targeted by malware easily. Using general anti-virus software to scan apps usually detected a known virus species only. As for new type of unknown variant, is not detectable normally. This study proposes a tremendous amount of malicious and benign program sample files, scanning and recording features for both required and used permissions of the list, using machine learning techniques. LibSVM to make the system classify unknown apps. The experimental result indicate the accurate rate of 99% for the correct identification of both benign and malware even for the unknown applications. We propose not only a simple but also feasible approach to detect mobile apps.
31
CHEN, CHIH-CHING, and 陳智卿. "Handmade environmental detection system." Thesis, 2019. http://ndltd.ncl.edu.tw/handle/96dd2u.
Full textAbstract:
碩士建國科技大學
電子工程系暨研究所
107
In traditional industries, it is inconvenient to detecting the numerical value of the environment and the data of the object to be tested. But through the advance of science and technology, the use of information technology is more mature. Many technological applications are used in agriculture or industry. In order to facilitate the user operation and smooth, we make a cheap handmade environmental detection system. In this paper, we link each sensing devices in the handmade environmental detection system by using an arduino chip controller and its expanded board. Then measure the voltage and current of the object to be tested and add gesture control to control the panel operation and use the wi-fi module to upload data. It saves a lot of time. In this paper, we design an integration environmental detection system.
32
Tripathy, Birendra Nath, and Abinash Dash. "Prototype Drowsiness Detection System." Thesis, 2012. http://ethesis.nitrkl.ac.in/3373/1/thesis-108EI038-026.pdf.
Full textAbstract:
Driver fatigue is one of the major causes of accidents in the world. Detecting the drowsiness of the driver is one of the surest ways of measuring driver fatigue. In this project we aim to develop a prototype drowsiness detection system. This system works by monitoring the eyes of the driver and sounding an alarm when he/she is drowsy.
The system so designed is a non-intrusive real-time monitoring system. The priority is on improving the safety of the driver without being obtrusive. In this project the eye blink of the driver is detected. If the drivers eyes remain closed for more than a certain period of time, the driver is said to be drowsy and an alarm is sounded. The programming for this is done in OpenCV using the Haarcascade library for the detection of facial features.
33
Pawan, Prateek, and Kushagra Pandey. "Human Facial Detection System." Thesis, 2012. http://ethesis.nitrkl.ac.in/3480/1/project_report.pdf.
Full textAbstract:
Augmenting human computer interaction with automated analysis and synthesis of facial expressions is the goal towards which much research effort has been devoted to in the last few years. Face recognition and detection is one of the important aspects of natural human machine interfaces; this technology has great applications such as in security systems, capturing image, authentication and in clinical practice. Although humans recognize facial parts virtually without effort or delay, reliable face detection and recognition by a computer system is still a challenging task. The facial part recognition and detection problem is challenging because different individuals have different structure for their nose, eye and ears differently. In this project we are trying to design a face detection and recognition system in real time using the concepts of Haar wavelets, Eigen faces and template matching. In this project we will be using our system for detecting face area, eyes, mouth ears and nose.
34
Sahoo, Chandraprakash. "Driver Drowsiness Detection System." Thesis, 2016. http://ethesis.nitrkl.ac.in/8057/1/2016_BT_CSahoo_112EI0563_Driver.pdf.
Full textAbstract:
In recent years’ driver fatigue is one of the major causes of vehicle accidents in the world. A direct way of measuring driver fatigue is measuring the state of the driver i.e. drowsiness. So it is very important to detect the drowsiness of the driver to save life and property. This project is aimed towards developing a prototype of drowsiness detection system. This system is a real time system which captures image continuously and measures the state of the eye according to the specified algorithm and gives warning if required.
Though there are several methods for measuring the drowsiness but this approach is completely non-intrusive which does not affect the driver in any way, hence giving the exact condition of the driver. For detection of drowsiness the per closure value of eye is considered. So when the closure of eye exceeds a certain amount then the driver is identified to be sleepy. For implementing this system several OpenCv libraries are used including Haar-cascade. The entire system is implemented using Raspberry-Pi.
35
Cheng, Chao-Hsiang, and 鄭兆翔. "A Modified Face Detection System with Wider Detection Range." Thesis, 2007. http://ndltd.ncl.edu.tw/handle/87857329597643017763.
Full textAbstract:
碩士國立清華大學
電機工程學系
95
Face detection is a more and more important topic nowadays. Because of the need on machine vision and surveillance system, we have to let a computer detect the faces in a picture rapidly and accurately. Viola and Jones [1] proposed a rapid and robust method, but it is just suitable for a frontal and upright face. Detecting multi-view faces is also a discussed problem today. In this thesis, a face detection system applicable for wider range is proposed. It contains analyzing the face pose, rotating the face back, and applying the traditional viola-jones detector. First, we search for potential face regions by performing skin-color detection. From these skin-color blocks, check if there is a pair of eyes inside and preserve window candidates that are much like faces. Second, according to the result of the pair of eyes candidate, we choose the angle to rotate each face candidate to frontal and upright face. Finally, the rotated face candidate is computed by viola-jones detector to judge whether it is a genuine face or not. In the experiment, our method extends the detection range of rotation-off-plane (ROP) and rotation-in-plane (RIP) face. Some faces, including profiled and rotated faces, that can not be detected by original viola-jones face detector are detected by our modified face detector with complemented pre-processing. The processing time is also acceptable. Especially for simple and small size images, it can achieve nearly real-time.
36
CHAN, YA-LI, and 詹雅莉. "The System of Fire Detection." Thesis, 2016. http://ndltd.ncl.edu.tw/handle/48622000131579802333.
Full textAbstract:
碩士吳鳳科技大學
光機電暨材料研究所
104
Due to the high frequency of fire occurrence in modern environments, how to prevent fire effectively is an important issue. The fire loss can be minimized by taking a suitable fire prevention. Early the fire prevention was performed by people; and later the flame sensors were developed to detect the smoke and temperature. However the diffusion rates of the smoke and the temperature are slower, it leads to the shortcomings of the time delay and lower coverage on detection. Visual flame detection system can improve these shortcomings. The visual flame detection system can immediately identify the flame pixels, so that it can early find the fire point to avoid the fire expansion. This thesis is to develop a modular robot with automatic fire monitoring; the main controller is AT89S52 produced by Atmel; and a wireless remote computer is designed as an automatic fire detection robot control system to remotely control and immediately detect the temperature changes of environments. In the experiments, the robot is free to walk around, and detects the flame and the ambient temperature in an unknown environment. The human-machine interface is designed to control the robot action. The Sensirion's "SHT71" temperature sensor and the Logitech camera are used to detect temperature and to capture image around the environment. Finally, the flame recognition algorithm is employed to identify the suspicious fire zone. Keywords: robot, temperature sensors, fire detection, human-machine interface
37
Ping-Hsun, Wu. "Analysis of Range Detection System." 2005. http://www.cetd.com.tw/ec/thesisdetail.aspx?etdun=U0001-2707200511035800.
Full text
38
Tsai, Kuo-Shou, and 蔡國手. "An Embedded Intrusion Detection System." Thesis, 2000. http://ndltd.ncl.edu.tw/handle/40544653703402308739.
Full textAbstract:
碩士國立交通大學
資訊管理所
88
An Intrusion Detection System (IDS) is used to protect data from being misused or unauthorized accessed. It monitors the system activities to find whether they contain any predefined attack signature. But the weakness of all common IDSs is the security problem of the IDS themselves. An IDS may be the first target of experienced attackers. An Embedded Intrusion Detection System trys to avoid the problem by hiding itself in a protected host. The idea is intuitive and simple, if we want to use IDS to protect a web server, we put together the IDS and the web server. We use HTTP to talk to the IDS, and normal web visitor uses HTTP to access what he want. The IDS is “ Embedded” within the web server. It is not easy for attackers to find the IDS such that the IDS should be more secure.
39
Wu, Ping-Hsun, and 吳秉勳. "Analysis of Range Detection System." Thesis, 2005. http://ndltd.ncl.edu.tw/handle/93354284053509492750.
Full textAbstract:
碩士國立臺灣大學
電信工程學研究所
93
In this thesis, a range detection system using frequency-modulated continuous-wave radar is designed at 2.45 GHz. The system consists of low-noise amplifier, local oscillator, mixer and DSP processor. Advanced high-electron-mobility transistors (HEMT) are used in RF circuit to reduce noise. Specific algorithms are chosen to analyze the echoed signal. Three systems with DSP are proposed to reduce the complexity of the conventional systems. They are simulated with Matlab, and the results matches well with theoretical prediction.
40
Yang, Su-Chiu, and 楊素秋. "Flow-based Flooding Detection System." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/34348603346790516894.
Full textAbstract:
博士國立中央大學
資訊工程研究所
92
Abstract In this thesis, we present two specific contributions, the flow-based flooding detection system (FDS) and P2P traffic measurement system. The key idea of FDS is constructing the set of features and corresponding criteria according to the interested flooding behaviors, and aggregating the flooding traffic based on the constructed features. Then, the detection module accumulates the interested statistical variables, and compares those traffic variables with the thresholds. Once all the variables exceeded the estimated quantifiers, the detector alarms the anomalies and trigs response module to notify owners of the anomalous systems, and limit the significant real-time flooding traffic. The flow-based P2P traffic measurement system is developed based on the connection-intensive feature of P2P network for providing network users grasp the P2P traffic and the aggressive participants. FDS and P2P traffic measurement systems have been deployed over an aggregate network of TANet backbone for effectively detecting and limiting the significant flooding anomalies. The detection result shows that a high proportion of the notified abuse traffic, including port scanning, spam, and copyright infringement, could be picked up from the detected anomalies and the measured aggressive P2P peers.
41
Chang, Yu-Ching, and 張育境. "Removable Sliding Slope Detection System." Thesis, 2014. http://ndltd.ncl.edu.tw/handle/2ybhf8.
Full textAbstract:
碩士國立高雄應用科技大學
電子工程系碩士班
102
In Taiwan, the topography is complicated and there are numerous mountain ranges. Arterial roads, ranging from railways to highways, have to go through rugged mountain topography. The climate in Taiwan changes rapidly and dramatically; the rainfall also increases fast year by year. They cause the multiplication of water capacity on the surface layer in the mountain range. Besides, due to the exploitation of slopes, imperfection of soil-water conservation and frequent earthquakes, stones and rocks on the slope crumble, which result in serious injuries and deaths. This situation leaves railway system and highway system no exception. Most slopes appear steady and still.When the slopes move downward unexpectedly, rock fall happens and the following mudslide will be so fast that it is difficult to be noticed. Currently, slope monitoring ways include visual check, distribution of cables and installation of tilt detectors. However the mudslide happening on the slope surface cannot be detected promptly with all of these devices; moreover, the construction will consume a great amount of labor power and material resources. In order to acquire safer protection, this system can promptly monitor slopes through camera and monitoring software. When slight displacement and collapse occur on the slope, the detecting board installed on the slope will do interpretation through the monitoring software in industrial computer. Then the warning messages will be transmitted to cell phones through wireless internet. On-site images can be watched on cellphones. Control center can notify the vicinal trains. Train drivers can determine whether the trains should be stopped immediately or not. Also, the departments concerned can be in the grasp of on-site information and can arrange consequent rescue.
42
LI, CHUN-JUNG, and 李浚榮. "Orchid Virus Detection Analysis System." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/h8cnj7.
Full textAbstract:
碩士國立高雄應用科技大學
電子工程系
105
Taiwan's most suitable for planting Phalaenopsis, the industry actively cultivate new varieties, new colors, making the orchid petals colorful, Petals size large and gorgeous, sometimes small and delicate, and flowering up to two to three months or more, has become the world's winter indoor pots of important options. Orchids if infected with the virus in the young period will not be a significant feature, when the orchids infected by the virus, the orchids in the petals, orchids on the leaves showed gangrene, chipping, spots and other symptoms, resulting in poor commodity prices. In order to enable the growers to grow healthy seedlings, the system for the breeding of orchids for the analysis, in a large number of breeding before the first confirmation of the reproduction of the orchid mother no Cymbidium mosaic virus (CymMV) and Odontoglossum ringspot virus (ORSV), After the virus infection into the tissue culture. The system based on the Android platform, through the modification of the Linux base, so that the relevant hardware required for testing machine can be integrated with the image recognition software. The hardware required for the inspection machine includes: Tiny 210 core board, motherboard, monitor, touch panel, CCD (Charge Coupled Device) camera, storage device, LED light source module (Light Emitting Diode), Bluetooth thermal Printers, battery devices and related components control module. Image recognition software based on the Android platform, through the Android official SDK (Software Development Kit) kit, for the rapid detection of reagents presented test results (C/T line color phenomenon) for image recognition software development, software content includes : Image capture, image processing, quantify the results of the color analysis of the test area, the results of the output and database management.
43
HUANG, PIN-RUI, and 黃品叡. "Indoor Trapped-Victim Detection System." Thesis, 2017. http://ndltd.ncl.edu.tw/handle/b3abt9.
Full textAbstract:
碩士國立雲林科技大學
資訊工程系
105
Large scale disasters usually caused people trapped inside buildings. In many cases, these people lost their moving ability and consciousness. For example, after a strong earthquake struck, people might first be hit by heavy objects or forced down by dropped objects, and then lost consciousness. The situation becomes serious if trapped people cannot be detected and pull out in time. Therefore, finding trapped victims inside a building in time becomes a very important issue for command centers or rescue teams. Nowadays, surveillance systems are commonly used to monitor and assess damage inside a building. However, checking camera images manually can be a very time-consuming and inefficient process, especially for a large surveillance system. Several image-based methods have been proposed to detect trapped people by using machine learning technology and human features. However, trapped victims were usually covered by fallen objects. Detecting human features of trapped victims could be difficult. In this paper, we proposed, Indoor Trapped-Victim Detection System (iTEDS), an image recognition system to identify and recognize trapped victims inside a building. Given a video, we track people and other objects, such as bookcases, tables, chests and so on, inside the video. If a huge object falls on top of a person and makes the person unable to move for a while, we mark the person as a trapped victim. In order to investigate the effectiveness of iTEDS, we applied iTEDS to the real accident that a dresser fell on twin boys and other forty one test cases we made. Our results showed that iTEDS can achieve an average accuracy of 88\%.
44
Yung-Chih and 鄭詠之. "Automatic Pulmonary Embolism Detection System." Thesis, 2010. http://ndltd.ncl.edu.tw/handle/22500728132765554239.
Full textAbstract:
碩士中山醫學大學
應用資訊科學學系碩士班
98
Pulmonary embolism (PE) is a blockage of the pulmonary artery or one of its branches, usually occurring when a deep vein thrombus (blood clot from a vein) becomes dislodged from its site of formation and travels, or embolisms, to the arterial blood supply of one of the lungs. This process is termed embolism. Most of the traditional detection of PE needs to rely on the professional judgments of physicians. With advances in CT technology, faster scanning and greatly enhanced the quality of image improve the diagnostic accuracy. Serious PE will lead to dead. However, it is very important for diagnosis PE. First, we use ACM method to find the lung area of the preprocessed image. And then we perform vessel searching and tracking to detect the pulmonary embolism in lung. Finally, we use the template matching method to do comparison between compare the result of system and doctor’s and obtain the precision rate. The system shows the result to help doctors checking the position of the embolism and release their work loads.
45
Teng, Chih-Yang, and 鄧智陽. "Automated Pavement Distress Detection System." Thesis, 2008. http://ndltd.ncl.edu.tw/handle/93211487656644541185.
Full textAbstract:
碩士國立臺灣大學
土木工程學研究所
96
Automated Pavement Distress Detection System (APDDS) has been a useful tool for pavement management in the world. APDDS can evaluate pavement performance and make maintenance and reconstruction（M&R）decisions based on distress and roughness data, it. In Taiwan, road authorities use pavement condition indices to evaluate pavement condition. However, insufficient labor and budget cause inefficient management works. Therefore, using efficient way to manage pavement performance is an important issue in the future. This study investigates several flexible pavement sections and collects automated/manual pavement distress data according to experiment design. Further, the data are analyzed and compared. It was found that the data collected by APDDS are undesirable due to frequent patches and other inferences. However, this study found that the ability of detecting cracks in PicCrack could be improved by spraying water on flexible pavement. In addition, this study discussed the differences of automatically/manually-collected survey results. This study analyzes the total time needed in semi-automated and manual survey. The results show that in all sections the total time needed in semi-automated survey (average 36.49 minutes) is longer than the total time needed in manual survey (average 13.03 minutes). This phenomenon indicates that using APDDS to collect image data takes more time because the surveyors have to go through the data and note down distresses. However, using APDDS can obviously reduce the time and labor during field survey. Moreover, manual field survey is easily affected by complex traffic condition in Taiwan. Therefore, by using APDDS, road data could be obtained quickly and the safely of surveyor could be protected.
46
CAI, WEN-HONG, and 蔡旻宏. "Distribution system fault location detection." Thesis, 1993. http://ndltd.ncl.edu.tw/handle/76633038178686425633.
Full text
47
Lin, Han-Yu, and 林漢佑. "A Parking Space Detection System." Thesis, 2013. http://ndltd.ncl.edu.tw/handle/34810000079350810740.
Full textAbstract:
碩士明新科技大學
電子工程研究所
101
A parking space detection system is proposed in this thesis. The system mainly consists of three parts. The first part, using digital cameras to detect the position of the vehicle, this method combines the benefits of low cost and eliminating the shortcoming of complexity for conventional sensor-based construction. The second part is license plate recognition. The license plate fonts and numbers are captured from an unknown image and it can automatically distinguish and query the parking location of official and special vehicles. The third is vehicle guidance that through the appropriate indicator lights to guide the owners can reach their parking spaces. In Taiwan, according to “2011 Survey & Summary Analysis of Private Automobile Usage” analyzed by the Ministry of Transportation and Statistics Department, the average time taken is 9.4 minutes for a drivers to looking for a parking space near home. By country & city classification, the longest is 14.0 minutes for Taipei which is higher 2.5 & 5.6 minutes than New Taipei & Taichung cities, respectively. Moreover, the parking space shortage issue often occurs in airports, hospitals, shopping centers and public / private parking areas, it is very difficult to find a parking space in these crowded parkings. Therefore, the enhancement and improvement of parking management, increasing utilization, effectively control and reducing administrative costs become a major and important topic.
48
Shen, Chi-Liang, and 沈啟亮. "Real Time Face Detection System." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/51621379084753012144.
Full textAbstract:
碩士淡江大學
電機工程學系碩士在職專班
92
Real-time face detection and face recognition from cluttered images is a challenging work. This dissertation proposes a hierarchical window based on the facial features as an operating mask for human eyes detection so as to be adaptable for different face sizes in images. After the input image is processed using the Sobel filter edge detection, we first make use of the characteristics of symmetric relationships of human-eyes region to find out the possible region of human eyes. Then, to exclude the region of without-human eyes and quickly reach the locations of possible face region, the author capitalizes the geometric characteristic of human-eyes region. Finally, after the eyes verification we accomplish the real-time face detection. The dissertation adopts video card and CCD as live video images for face detection system. It carries out on the computer of PC (Pentium 4 1.8 G). From the website, the author establishes the Color database (WCset) which amounts to 328 pieces of color images. On the average takes only 0.05 seconds for each color image (256*384*1.6M) and the accuracy is 90%(296/328). Again from the faces of FERET (384*256*256) the author establishes the gray-level image database Which contains 2164 pieces. Each image takes about 0.02 seconds and the accurate rate is 95.7 % (2071/2164). The performance is better than the other current face detection systems.
49
Wang, Po-Wei, and 王博瑋. "NetFlow Based Intrusion Detection System." Thesis, 2004. http://ndltd.ncl.edu.tw/handle/82779373654190533992.
Full textAbstract:
碩士大同大學
資訊工程學系(所)
92
Due to the popularity of Internet, people can access remote resource on the Internet conveniently. But numerous malicious network events such as computer virus and hacker attack make the network management more difficult. A network intrusion detection system is thus more and more demanding. In this thesis, a NetFlow based anomaly intrusion detection system is presented. In addition, guidelines to properly configure and setup network device to minimize the possibilities that network attacks come from inside are also proposed. As the Internet becomes the platform of daily activities, the threat of network attack is also become more serious. Firewall along is not capable to protect the system from being attacked through normal service channel. Furthermore, most of the current intrusion detection system focus on the border of organization network which does not provide protection to hosts in the local network and the network itself if the attack is from inside. Therefore, in addition to the firewall and border IDS, we need to use other type of intrusion detection system to protect the critical system as well as the network itself.We propose an inexpensive and easy to implement way to perform the anomaly type intrusion detection based on the NetFlow information exported from the routers or other network probes. Our system can detect several types of network attack from inside or outside and perform counter maneuver accordingly.
50
Chen, Kuang-Yue, and 陳寬裕. "Study of Fire Detection System." Thesis, 1999. http://ndltd.ncl.edu.tw/handle/67465975375746935114.
Full textAbstract:
碩士國立交通大學
電機與控制工程系
87
This thesis focus on the study of current fire detection systems. Recent research results on the fire detection systems are also studied. In this thesis, we divide the current system into four parts: Sensor, Interface, Controller and Actuator. We not only investigate the three major problems about current systems (reconstruction of fire situations, effective slaking the fire and promoting system’s stability) but also present a structure of an ideal intelligent fire detection system. After discussing the problems of the current system with respect to the three major problems, we utilize power line transmit networks to integrate the fire detection system and Home Automation to realize the aforementioned improving ideas with respective to the three major problems in real systems.