Global ETD Search

1	Indoor and Outdoor Evaluation of Campus RSS Performance Li, Qian, Zhang, Xintong January 2011 (has links) The focus of this thesis work is to evaluate the RSS (Received Signal Strength) Performance of the University of Gävle (HiG) based on IEEE 802.11 standards both indoor and outdoor. Authors investigated the issues of deploying access points for wireless local area networks in the library-2nd floor, building 99-4th floor and outdoor university campus. By using the program VisiWave Site Survey, Global Position System (GPS) and RSS sensor to analysis the received signal strength, throughput and radio map. The influence of the building material and distance for the signal strength and the throughput are done by investigating indoor environment. The results of investigation suggest that most parts of library-2nd floor and building 99-4th floor possess at least a good RSS performance. However, minority parts of these places have a poor RSS performance, and the new resolution of Access Points’ (AP) deployment for these poor-RSS-performance parts is provided. For the outdoor campus part, the RSS in the area which near the walls of building is satisfactory (Received Signal Strength Indication (RSSI) between -79.8 dBm and -57 dBm), however in the centre of outdoor campus the RSS is poor. Thus, the evaluation of APs deployment in HiG is achieved. Evaluation IEEE 802.11 WLAN Access point RSSI RSS Throughput Radio map
2	Deep Learning Approaches to Radio Map Estimation Locke IV, William Alexander 07 1900 (has links) Radio map estimation (RME) is the task of predicting radio power at all locations in a two-dimensional area and at all frequencies in a given band. This thesis explores four deep learning approaches to RME: dual path autoencoders, skip connection autoencoders, diffusion, and joint learning with transmitter localization. Radio Map Estimation Dual Path Autoencoder Skip Connection Diffusion Joint Learning Localization
3	利用動態訊號資料庫以減少測量數之無線網路定位系統 / Reducing Calibration Effort for WLAN Locating System with Dynamic Radio Map 簡盧德, Chien Lu,Te Unknown Date (has links) 隨著無線網路的興起，許多相關的研究議題也應運而生，利用無線網路(WLAN)對於使用者位置的判斷與追蹤就是其中相當熱門的一塊。經過近幾年的發展，室內WLAN定位誤差的進步空間已達到極限，其原因主要出在無線訊號傳播的物理性質所產生的侷限。然而，大部分擁有良好精準度的定位系統是建立在不切實際的人力成本上，故我們將著眼點放在如何減少收集大量訊號所耗費的人力，同時保持不錯的精準度。取得AP位置所消耗的人力資源也是我們考慮的一環。因此，我們提出一套新的定位系統：首先建立少數的資料點，再透過推測基地台位置和插入機制來完成訊號資料庫的初步建置。然後在定位的同時收集使用者接收到連續的訊號強度，透過隱馬可夫鏈建立的模型，再配合其他演算法來更新訊號資料庫。實驗結果顯示，相較於其他兩個定位系統，我們的系統能夠減少最多的人力建置資源，並且達到有競爭力的定位精準度。除此之外，我們也分析了系統在使用舊的資料庫或是不同的實驗環境下，能夠展現怎樣的定位結果。 / Following the raise of Wireless LAN networks, there are a lot of relative research issues in today’s life. Tracking and locating mobile users in RF-based WLAN (IEEE 802.11) is a very important issue in location-based applications area. The error distances of indoor WLAN locating was decreased to approximately 1.5 meter in recent years. However, the improvement in accuracy was limited due to the nature of radio propagation. Many researches which contain precise accuracy were based on an impractical effort of collecting too much signal data which we usually called “calibration” in this area. So this thesis focuses on how to reduce the calibration efforts without losing too much accuracy. Confirming the allocation of access points is another kind of calibration effort we concerned. As a consequence, we proposed a new locating system: first we calibrated few points and utilized inferring AP’s position and interpolation to complete radio map. During location estimation phase, radio map could be updated dynamically using learning mechanism modeled by HMM and other algorithms. In the experimental results, we proved our system maintained a comparable accuracy under reducing much calibration effort than other two locating systems. Besides, we analyzed the performance of our system with elder radio map and in two different experimental environments. 定位無線網路訊號強度機器學習資料庫 locating WLAN signal strength learning radio map
4	Indoor Positioning Using WLAN / Inomhuspositionering med WLAN Andersson, Pierre, Norlander, Arvid January 2012 (has links) This report evaluates various methods that can be used to position a smartphone running the Android platform, without the use of any special hardware or infrastructure and in conditions where GPS is unavailable or unreliable; such as indoors. Furthermore, it covers the implementation of such a system with the use of a deterministic fingerprinting method that is reasonably device independent, a method which involves measuring a series of reference points, called fingerprints, in an area and using those to locate the user. The project was carried on behalf of Sigma, a Swedish software consulting company. / Denna rapport evaluerar olika metoder för att bestämma positionen av en smartphone som använder sig av Android-plattformen. Metoden skall inte använda sig av någon speciell hårdvara eller infrastruktur samt kunna hantera förhållanden där GPS är otillgängligt eller opålitligt, som till exempel inomhus. Den beskriver också implementation av ett sådant system som använder sig av en deterministisk fingerprinting-metod som någorlunda väl kan hantera enheter av olika modeller, en metod som innebär att man mäter upp en mängd med referenspunkter, kallade fingerprints, och använder dessa för att placera användaren. Projektet utfördes på uppdrag av Sigma, ett svenskt mjukvarukonsultbolag. Indoor Positioning WLAN Fingerprinting RSS Signal Strength RSS Difference Cell Phone Mobile Phone Android Radio Map WiFi 802.11 Wireless Indoor Positioning Localisation Localization inomhuspositionering WLAN fingeravtryck RSS signalstyrka RSS skillnad mobiltelefon Android radiokarta WiFi 802.11 trådlös inomhus positionering lokalisering Software Engineering Programvaruteknik

1

Page generated in 0.0624 seconds