Global ETD Search

11	Time synchronization error detection in a radio access network / Tidssynkroniseringsfel upptäckt i ett radioåtkomstnätverk Madana, Moulika January 2023 (has links) Time synchronization is a process of ensuring all the time difference between the clocks of network components(like base stations, boundary clocks, grandmasters, etc.) in the mobile network is zero or negligible. It is one of the important factors responsible for ensuring effective communication between two user-equipments in a mobile network. Nevertheless, the presence of asymmetries can lead to faults, making the detection of these errors indispensable, especially in technologies demanding ultra-low latency, such as 5G technology. Developing methods to ensure time-synchronized mobile networks, would not only improve the network performance, and contribute towards cost-effective telecommunication infrastructure. A rulebased simulator to simulate the mobile network was built, using the rules provided by the domain experts, in order to generate more data for further studies. The possibility of using Reinforcement Learning to perform fault detection in the mobile network was explored. In addition to the simulator dataset, an unlabelled customer dataset, which consists of time error differences between the base stations, and additional features for each of its network components was provided. Classification algorithms to label the customer dataset were designed, and a comparative analysis of each of them has been presented. Mathematical algorithm and Graph Neural Network models were built to detect error, for both the simulator and customer dataset, for the faulty node detection task. The approach of using a Mathematical algorithm and Graph Neural Network architectures provided an accuracy of 95% for potential fault node detection. The feature importance of the additional features of the network components was analyzed using the best Graph Neural Network model which was used to train for the node classification task (to classify the base stations as faulty and non-faulty). Additionally, an attempt was made to predict the individual time error value for each of the links using Graph Neural Network, however, it failed potentially due to the presence of fewer features to train from. / Tidssynkronisering är en process för att säkerställa att all tidsskillnad mellan klockorna för nätverkskomponenter (som basstationer, gränsklockor, stormästare, etc.) i mobilnätet är noll eller försumbar. Det är en av de viktiga faktorerna som är ansvariga för att säkerställa effektiv kommunikation mellan två användarutrustningar i ett mobilnät. Icke desto mindre kan närvaron av asymmetrier leda till fel, vilket gör upptäckten av dessa fel oumbärlig, särskilt i tekniker som kräver ultralåg latens, som 5G-teknik. En regelbaserad simulator för att simulera mobilnätet byggdes, med hjälp av reglerna från domänexperterna, för att generera mer data för vidare studier. Möjligheten att använda RL för att utföra feldetektering i mobilnätet undersöktes. Utöver simulatordataset tillhandahölls en omärkt kunddatauppsättning, som består av tidsfelsskillnader mellan basstationerna och ytterligare funktioner för var och en av dess nätverkskomponenter. Klassificeringsalgoritmer för att märka kunddataset utformades, och en jämförande analys av var och en av dem har presenterats. Matematisk algoritm och GNN-modeller byggdes för att upptäcka fel, för både simulatorn och kunddatauppsättningen, för uppgiften att detektera felaktig nod. Metoden att använda en matematisk algoritm och GNN-arkitekturer gav en noggrannhet på 95% för potentiell felnoddetektering. Funktionens betydelse för de ytterligare funktionerna hos nätverkskomponenterna analyserades med den bästa GNN-modellen som användes för att träna för nodklassificeringsuppgiften (för att klassificera basstationerna som felaktiga och icke-felaktiga). Dessutom gjordes ett försök att förutsäga det individuella tidsfelsvärdet för var och en av länkarna med GNN, men det misslyckades potentiellt på grund av närvaron av färre funktioner att träna från. Read more OAS - Over-the air-synchronization PRTC - primary reference time clock PTP - precision time protocol Gauss Jordan elimination GNN- Graph Neural Network GNSS -Globalt navigationssatellitsystem OAS - Över-the-air tidssynkronisering PRTC - Primär referenstidklocka PTP - Precisionstidprotokoll Gauss Jordan eliminering GNN- Graf neurala nätverk Elektroteknik och elektronik
12	Traffic Prediction From Temporal Graphs Using Representation Learning / Trafikförutsägelse från dynamiska grafer genom representationsinlärning Movin, Andreas January 2021 (has links) With the arrival of 5G networks, telecommunication systems are becoming more intelligent, integrated, and broadly used. This thesis focuses on predicting the upcoming traffic to efficiently promote resource allocation, guarantee stability and reliability of the network. Since networks modeled as graphs potentially capture more information than tabular data, the construction of the graph and choice of the model are key to achieve a good prediction. In this thesis traffic prediction is based on a time-evolving graph, whose node and edges encode the structure and activity of the system. Edges are created by dynamic time-warping (DTW), geographical distance, and $k$-nearest neighbors. The node features contain different temporal information together with spatial information computed by methods from topological data analysis (TDA). To capture the temporal and spatial dependency of the graph several dynamic graph methods are compared. Throughout experiments, we could observe that the most successful model GConvGRU performs best for edges created by DTW and node features that include temporal information across multiple time steps. / Med ankomsten av 5G nätverk blir telekommunikationssystemen alltmer intelligenta, integrerade, och bredare använda. Denna uppsats fokuserar på att förutse den kommande nättrafiken, för att effektivt hantera resursallokering, garantera stabilitet och pålitlighet av nätverken. Eftersom nätverk som modelleras som grafer har potential att innehålla mer information än tabulär data, är skapandet av grafen och valet av metod viktigt för att uppnå en bra förutsägelse. I denna uppsats är trafikförutsägelsen baserad på grafer som ändras över tid, vars noder och länkar fångar strukturen och aktiviteten av systemet. Länkarna skapas genom dynamisk time warping (DTW), geografisk distans, och $k$-närmaste grannarna. Egenskaperna för noderna består av dynamisk och rumslig information som beräknats av metoder från topologisk dataanalys (TDA). För att inkludera såväl det dynamiska som det rumsliga beroendet av grafen, jämförs flera dynamiska grafmetoder. Genom experiment, kunde vi observera att den mest framgångsrika modellen GConvGRU presterade bäst för länkar skapade genom DTW och noder som innehåller dynamisk information över flera tidssteg. Read more Dynamic time warping (DTW) embedding graph convolutional networks (GCN) graph neural networks (GNN) persistent homology spectral graph theory temporal graphs topological data analysis (TDA) Dynamisk time warping (DTW) inbäddning convolutional grafnätverk (GCN) neurala grafnätverk (GNN) persistent homologi spektral graf teori dynamisk graf topologisk dataanalys (TDA) Probability Theory and Statistics Sannolikhetsteori och statistik
13	Improving the Performance of Clinical Prediction Tasks by Using Structured and Unstructured Data Combined with a Patient Network Nouri Golmaei, Sara 08 1900 (has links) Indiana University-Purdue University Indianapolis (IUPUI) / With the increasing availability of Electronic Health Records (EHRs) and advances in deep learning techniques, developing deep predictive models that use EHR data to solve healthcare problems has gained momentum in recent years. The majority of clinical predictive models benefit from structured data in EHR (e.g., lab measurements and medications). Still, learning clinical outcomes from all possible information sources is one of the main challenges when building predictive models. This work focuses mainly on two sources of information that have been underused by researchers; unstructured data (e.g., clinical notes) and a patient network. We propose a novel hybrid deep learning model, DeepNote-GNN, that integrates clinical notes information and patient network topological structure to improve 30-day hospital readmission prediction. DeepNote-GNN is a robust deep learning framework consisting of two modules: DeepNote and patient network. DeepNote extracts deep representations of clinical notes using a feature aggregation unit on top of a state-of-the-art Natural Language Processing (NLP) technique - BERT. By exploiting these deep representations, a patient network is built, and Graph Neural Network (GNN) is used to train the network for hospital readmission predictions. Performance evaluation on the MIMIC-III dataset demonstrates that DeepNote-GNN achieves superior results compared to the state-of-the-art baselines on the 30-day hospital readmission task. We extensively analyze the DeepNote-GNN model to illustrate the effectiveness and contribution of each component of it. The model analysis shows that patient network has a significant contribution to the overall performance, and DeepNote-GNN is robust and can consistently perform well on the 30-day readmission prediction task. To evaluate the generalization of DeepNote and patient network modules on new prediction tasks, we create a multimodal model and train it on structured and unstructured data of MIMIC-III dataset to predict patient mortality and Length of Stay (LOS). Our proposed multimodal model consists of four components: DeepNote, patient network, DeepTemporal, and score aggregation. While DeepNote keeps its functionality and extracts representations of clinical notes, we build a DeepTemporal module using a fully connected layer stacked on top of a one-layer Gated Recurrent Unit (GRU) to extract the deep representations of temporal signals. Independent to DeepTemporal, we extract feature vectors of temporal signals and use them to build a patient network. Finally, the DeepNote, DeepTemporal, and patient network scores are linearly aggregated to fit the multimodal model on downstream prediction tasks. Our results are very competitive to the baseline model. The multimodal model analysis reveals that unstructured text data better help to estimate predictions than temporal signals. Moreover, there is no limitation in applying a patient network on structured data. In comparison to other modules, the patient network makes a more significant contribution to prediction tasks. We believe that our efforts in this work have opened up a new study area that can be used to enhance the performance of clinical predictive models. Read more Electronic Health Record (EHR) Clinical Note Clinical Predictive Models Multimodal Model Natural Language Processing (NLP) Patient Network Graph Neural Network (GNN) Structured Temporal Data Unstructured Data Data Fusion Deep Learning Feature Aggregation Readmission Prediction Mortality Prediction Length of Stay (LOS) prediction
14	Evaluation of Target Tracking Using Multiple Sensors and Non-Causal Algorithms Vestin, Albin, Strandberg, Gustav January 2019 (has links) Today, the main research field for the automotive industry is to find solutions for active safety. In order to perceive the surrounding environment, tracking nearby traffic objects plays an important role. Validation of the tracking performance is often done in staged traffic scenarios, where additional sensors, mounted on the vehicles, are used to obtain their true positions and velocities. The difficulty of evaluating the tracking performance complicates its development. An alternative approach studied in this thesis, is to record sequences and use non-causal algorithms, such as smoothing, instead of filtering to estimate the true target states. With this method, validation data for online, causal, target tracking algorithms can be obtained for all traffic scenarios without the need of extra sensors. We investigate how non-causal algorithms affects the target tracking performance using multiple sensors and dynamic models of different complexity. This is done to evaluate real-time methods against estimates obtained from non-causal filtering. Two different measurement units, a monocular camera and a LIDAR sensor, and two dynamic models are evaluated and compared using both causal and non-causal methods. The system is tested in two single object scenarios where ground truth is available and in three multi object scenarios without ground truth. Results from the two single object scenarios shows that tracking using only a monocular camera performs poorly since it is unable to measure the distance to objects. Here, a complementary LIDAR sensor improves the tracking performance significantly. The dynamic models are shown to have a small impact on the tracking performance, while the non-causal application gives a distinct improvement when tracking objects at large distances. Since the sequence can be reversed, the non-causal estimates are propagated from more certain states when the target is closer to the ego vehicle. For multiple object tracking, we find that correct associations between measurements and tracks are crucial for improving the tracking performance with non-causal algorithms. Read more evaluation target tracking multiple sensors non-causal smoother smoothing tracking vehicle tracking camera lidar estimate estimation prediction vehicle dynamics sensor fusion real-time tracking extended kalman filter filter validation validation position estimation velocity estimation dynamic model model complexity multi object tracking multiple object tracking single object tracking data association tracking fundamentals iterated kalman filter track management gnn global nearest neighbour mahalanobis mahalanobis distance performance evaluation differential gps dgps roi ego several sensors sensors rmse root mean square error invertible motion anti-causal motion anti-causal tracking constant velocity gnn imu tfs two filter smoother ekf rts radar inertial measurement unit nonlinear nonlinear systems mono camera monocular camera noise model tracking performance fixed interval smoothing m/n logic centralized fusion non-causal object tracker car tracking car dynamics automotive active safety object tracking automotive industry thesis master reverse dynamics reverse tracking reverse sequence sequence tracking data propagation ground truth estimating ground truth additional sensors mounted sensors true estimates environment comparison algorithm independent targets overlapping measurements occluded track switch improve lower uncertainty more certain state process noise covariance sampling image sprt adas cnn cv pdf track target ego tracker tentative track observatiom online tracking offline tracking online offline recorded sequences robust self driving self-driving car traffic trajectory true state scenario scenarios future accurate output advanced driver assistance systems non-linear complex noise pedestrian truck bus maneuvering vehicles processed measurement frame state correction probability density function tuning likelihood transition measurement motion model recursion gaussian approximation distribution linear jacobian multiplicative noise ratio ad hoc ad hoc state space approach backward auction euclidean distance statistical threshold gating association margin normalize covariance matrix fusion confirmed rejected tentative history absolute error modular ego motion parameters variables logg hardware specification fused causal factorization independent uncorrelated transform moving rotation translation oncoming overtaking Control Engineering Reglerteknik

Page generated in 0.0461 seconds