PUMA publications for /tag/LocalizationMon Jan 26 14:53:09 CET 202609Evaluation of Field-Coupled Measurement Methods for Sensitive Detection and Localization of Partial Discharges in Motor Stators for Electric Vehicles2025Detection Discharges Electric Evaluation Field-Coupled Localization Measurement Methods Motor Partial Sensitive Stators Vehicles and for in of Mon Jan 15 10:11:24 CET 202408Localization of Partial Discharge Sources in Power Transformers using Neural Networks2023Discharge Localization Networks Neural Partial Power Sources Transformers in of using Wed Jun 15 11:26:56 CEST 2022Chemical Physics Letters4431--434First observation of resolved ESR hyperfine structure for a reduced ruthenium(II) polyazine complex1181985ESR bipyridyl cation;tetrazine complex electron localization pyridyltetrazine ruthenium A resolved ESR spectrum of a Ru(II) polyazine radical complex was obsd. in the binuclear species ([(bpy)4Ru2(dptz)]3+ (dptz: 3,6-di-2-pyridyl-1,2,4,5-tetrazine). ESR in conjunction with HMO McLachlan calcns. reveal the localization of the unpaired electron in the tetrazine \textgreek{p} system and a strongly polarizing effect of the [Ru(bpy)2]2+ fragment. [on SciFinder(R)]Tue Mar 22 12:24:26 CET 20222018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)June1-5On Deep Learning-Based Massive MIMO Indoor User Localization2018localization myown from:sdnr ml We examine the usability of deep neural networks for multiple-input multiple-output (MIMO) user positioning solely based on the orthogonal frequency division multiplex (OFDM) complex channel coefficients. In contrast to other indoor positioning systems (IPSs), the proposed method does not require any additional piloting overhead or any other changes in the communications system itself as it is deployed on top of an existing OFDM MIMO system. Supported by actual measurements, we are mainly interested in the more challenging non-line of sight (NLoS) scenario. However, gradient descent optimization is known to require a large amount of data-points for training, i.e., the required database would be too large when compared to conventional methods. Thus, we propose a two-step training procedure, with training on simulated line of sight (LoS) data in the first step, and finetuning on measured NLoS positions in the second step. This turns out to reduce the required measured training positions and thus, reduces the effort for data acquisition.Tue Mar 22 12:19:34 CET 20222019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall)Sep.1-6Towards Practical Indoor Positioning Based on Massive MIMO Systems2019localization myown from:sdnr ml We showcase the practicability of an indoor positioning system (IPS) solely based on neural networks (NNs) and the channel state information (CSI) of a (Massive) multiple-input multiple-output (MIMO) communication system, i.e., only build on the basis of data that is already existent in today's systems. As such our IPS system promises both, a good accuracy without the need of any additional protocol/signaling overhead for the user localization task. In particular, we propose a tailored NN structure with an additional phase branch as feature extractor and (compared to previous results) a significantly reduced amount of trainable parameters, leading to a minimization of the amount of required training data. We provide actual measurements for indoor scenarios with up to 64 antennas covering a large area of 80m 2 . In the second part, several robustness investigations for real-measurements are conducted, i.e., once trained, we analyze the recall accuracy over a period of several days. Further, we analyze the impact of pedestrians walking in-between the measurements and show that finetuning and pre-training of the NN helps to mitigate effects of hardware drifts and alterations in the propagation environment over time. This reduces the amount of required training samples at equal precision and, thereby, decreases the effort of the costly training data acquisition.Fri Jan 29 12:33:34 CET 2021288-293Evaluation of the Frequency Information Contained in PD Signals for Localization in Power Cable Monitoring2020Cable Contained Evaluation Frequency Information Localization Monitoringsend:unibiblio PD Power Signals for in of the Thu Jan 21 11:45:33 CET 20212020 International Conference on Intelligent Robots and Systems (IROS)October9545-9552Kinematic Multibody Model Generation of Deformable Linear Objects from Point Clouds20202020 EXC2075 SimTech Soft-Tissue-Robotics deformable grk2198 hze isw localization multibody myown xwk Tue Aug 11 13:06:43 CEST 2020All-Acoustic PD measurements of oil/paper-insulated transformers for PD-localization2004Acoustic PD algorithms approach direct equations iterative localization measurements non-linear observation online pseudo-time solution solver strategies time-differences Thu Jul 23 14:39:17 CEST 2020Improvement of acoustic detection and localization accuracy by sensitive electromagnetic PD measurements under oil in the UHF range 2005PD UHF accuracy acoustic detection electromagnetic localization measurements oil range sensitive Thu Jul 23 14:29:29 CEST 2020A New Procedure for Partial Discharge Localization in Gas-Insulated Switchgear in Frequency Domain 2005Discharge Domain Frequency Gas-Insulated Localization Partial Switchgear Mon Jul 13 14:08:02 CEST 2020New Procedures for Partial Discharge Localization in Gas-Insulated Switchgears in Frequency and Time Domain 2007Discharge Domain Frequency Gas-Insulated Localization New Partial Procedures Switchgears Time Mon Jun 29 14:54:28 CEST 2020European Transactions on Electrical Power (ETEP)July5749–762Localization of Winding Radial Deformation and Determination of Deformation Extent using Vector Fitting-based Estimated Transfer Function192009Deformation Determination Estimated Extent Fitting-based Function Localization Radial Transfer Vector Winding Wed Jun 24 14:22:14 CEST 2020Localization of PD Sources inside Transformers by Acoustic Sensor Array and UHF Measurements2010Acoustic Array EC60270 PD Power Sensor UHF discharge localization partial transformer Tue Jun 23 15:06:49 CEST 2020Localization of Partial Discharges in Power Transformer by Acoustic Method2010Acoustic Discharges Localization Method Partial Power Transformer Wed May 13 15:22:44 CEST 2020Partial Discharge Localization in Power Transformers2013Discharge Localization Partial Power Transformers Wed May 13 14:31:37 CEST 2020New Methods for Multisource PD Localization On Power Transfomers by an Acoustic Sensor Array2013Acoustic Array Localization Multisource PD Power Sensor Transfomers Tue May 12 15:14:15 CEST 2020Practical Aspects of PD Localization for Long Length Power Cables2013Cables Length Localization Long PD Power Fri Mar 20 15:07:06 CET 20202019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall)Sep.1-6Towards Practical Indoor Positioning Based on Massive MIMO Systems2019extractor;Artificial multiple-output myown from:sdnr (artificial communication;neural nets;telecommunication system;neural extraction arrays;Feature structure;phase measurements;Training;Antenna radio;learning system;user intelligence);MIMO acquisition;feature NN localization communication;indoor neural data networks;channel branch;indoor extraction;indoor systems;indoor scenarios;recall positioning MIMO accuracy;training networks;Antenna information;multiple-input state system;IPS computing;massive task;tailored communication Thu Mar 19 13:20:38 CET 20202018 IEEE 19th International Workshop on Signal Processing Advances in Wireless Communications (SPAWC)June1-5On Deep Learning-Based Massive MIMO Indoor User Localization2018localization ml myown We examine the usability of deep neural networks for multiple-input multiple-output (MIMO) user positioning solely based on the orthogonal frequency division multiplex (OFDM) complex channel coefficients. In contrast to other indoor positioning systems (IPSs), the proposed method does not require any additional piloting overhead or any other changes in the communications system itself as it is deployed on top of an existing OFDM MIMO system. Supported by actual measurements, we are mainly interested in the more challenging non-line of sight (NLoS) scenario. However, gradient descent optimization is known to require a large amount of data-points for training, i.e., the required database would be too large when compared to conventional methods. Thus, we propose a two-step training procedure, with training on simulated line of sight (LoS) data in the first step, and finetuning on measured NLoS positions in the second step. This turns out to reduce the required measured training positions and thus, reduces the effort for data acquisition.Thu Mar 19 13:20:38 CET 20202019 IEEE 90th Vehicular Technology Conference (VTC2019-Fall)Sep.1-6Towards Practical Indoor Positioning Based on Massive MIMO Systems2019localization ml myown We showcase the practicability of an indoor positioning system (IPS) solely based on neural networks (NNs) and the channel state information (CSI) of a (Massive) multiple-input multiple-output (MIMO) communication system, i.e., only build on the basis of data that is already existent in today's systems. As such our IPS system promises both, a good accuracy without the need of any additional protocol/signaling overhead for the user localization task. In particular, we propose a tailored NN structure with an additional phase branch as feature extractor and (compared to previous results) a significantly reduced amount of trainable parameters, leading to a minimization of the amount of required training data. We provide actual measurements for indoor scenarios with up to 64 antennas covering a large area of 80m 2 . In the second part, several robustness investigations for real-measurements are conducted, i.e., once trained, we analyze the recall accuracy over a period of several days. Further, we analyze the impact of pedestrians walking in-between the measurements and show that finetuning and pre-training of the NN helps to mitigate effects of hardware drifts and alterations in the propagation environment over time. This reduces the amount of required training samples at equal precision and, thereby, decreases the effort of the costly training data acquisition.LocalizationCommunity for tag(s) Localization