89,919 Hits in 3.7 sec

Set-labelled filters and sensor transformations

Fatemeh Zahra Saberifar, Shervin Ghasemlou, Jason M. O'Kane, Dylan A. Shell
Robotics: Science and Systems XII  
Utilizing and extending the language of combinatorial filters, this paper aims to fill that lacuna by introducing theoretical tools for reasoning about sensors and representations of sensors.  ...  It introduces new representations for sensors and filters, exploring the relationship between those elements and the specific information needed to perform a task.  ...  Sensor maps take some filter (R in the picture) and transform it into another (as h does).  ... 
doi:10.15607/rss.2016.xii.015 dblp:conf/rss/SaberifarGOS16 fatcat:ipbnkrvj2ra3bbtpbypyngktai

Identifying Electromyography Sensor Placement using Dense Neural Networks

Paolo Cappellari, Robert Gaunt, Carl Beringer, Misagh Mansouri, Massimiliano Novelli
2018 Proceedings of the 7th International Conference on Data Science, Technology and Applications  
Neural networks are increasingly being used in medical settings to support medical practitioners and researchers in performing their work.  ...  In the field of prosthetics for amputees, sensors can be used to monitor the activity of remaining muscle and ultimately control prosthetic limbs.  ...  We perform the following transformation steps: signal filtering, and feature extraction.  ... 
doi:10.5220/0006912501300141 dblp:conf/data/CappellariGBMN18 fatcat:2dr3kx7olbdthdtdtoftqht2du

Discrete Signal Processing on Graphs

Aliaksei Sandryhaila, José M. F. Moura
2013 IEEE Transactions on Signal Processing  
This paper extends to signals on graphs DSP and its basic tenets, including filters, convolution, z-transform, impulse response, spectral representation, Fourier transform, frequency response, and illustrates  ...  In social settings, individuals interact through webs of relationships. Each individual is a node in a complex network (or graph) of interdependencies and generates data, lots of data.  ...  Instead, we read and label only a few blogs, and use these labels to adaptively build a filter h(A) in (31) .  ... 
doi:10.1109/tsp.2013.2238935 fatcat:er2wivkywnapnfhfepx4lbxwmq

Tactile Convolutional Networks for Online Slip and Rotation Detection [chapter]

Martin Meier, Florian Patzelt, Robert Haschke, Helge J. Ritter
2016 Lecture Notes in Computer Science  
By integrating spatial and temporal tactile sensor data from a piezo-resistive sensor array through deep learning techniques, the network is not only able to classify the contact state into stable versus  ...  slipping, but also to distinguish between rotational and translation slippage.  ...  Acknowledgments The research leading to these results has received funding from the European Community's Framework Programme Horizon 2020 -under grant agreement No 644938 -SARAFun and was supported by  ... 
doi:10.1007/978-3-319-44781-0_2 fatcat:5cubxgpq5raxdicqwnnea6emom

Toward a language-theoretic foundation for planning and filtering [article]

Fatemeh Zahra Saberifar, Shervin Ghasemlou, Dylan A. Shell, Jason M. O'Kane
2018 arXiv   pre-print
Specifically, we consider the impact that degradations of a robot's sensor and actuation suites may have on the ability of that robot to complete its tasks.  ...  We also highlight the connections between this new approach and existing threads of research, including combinatorial filtering, Erdmann's strategy complexes, and hybrid automata.  ...  O'Kane and Dylan A. Shell  ... 
arXiv:1807.08856v1 fatcat:n3hverw3ubfnjdo6oe6t7bnzre

Electroencephalography Based Fusion Two-Dimensional (2D)-Convolution Neural Networks (CNN) Model for Emotion Recognition System

Yea-Hoon Kwon, Sae-Byuk Shin, Shin-Dug Kim
2018 Sensors  
Section 3 discusses the current paper's main contributions, including the details of label processing, EEG signal transformation, GSR data feature extraction, and introduces the proposed CNN model architecture  ...  Therefore, we propose a suitable CNN model for feature extraction by tuning hyper parameters in convolution filters.  ...  [23] used the DEAP data set to classify PNS and CNS sensor data, and measured the emotional classification performance.  ... 
doi:10.3390/s18051383 pmid:29710869 pmcid:PMC5982398 fatcat:dglbfrlpubc5hl2qi3qf772nsq

Discrete Signal Processing on Graphs: Frequency Analysis [article]

Aliaksei Sandryhaila, Jose M. F. Moura
2013 arXiv   pre-print
We study the design of graph filters with specified frequency response, and illustrate our approach with applications to sensor malfunction detection and data classification.  ...  This paper studies the concepts of low and high frequencies on graphs, and low-, high-, and band-pass graph filters.  ...  The filter coefficients h are obtained from (28) by setting α m to 1 for frequencies lower than λ cut and to 0 otherwise; and vice versa for g .  ... 
arXiv:1307.0468v2 fatcat:k6tux6kqpfd5rojkf2ow5v4yjm

Frequency Aliasing-Based Spatial-Wavenumber Filter for Online Damage Monitoring

Bin Liu, Tingzhang Liu, Jianfei Zhao, Dan Hang
2020 Shock and Vibration  
Finally, the damage is localized using the spatial-wavenumber filter and cruciform PZT sensor array. This method was validated on an epoxy laminate plate.  ...  The spatial-wavenumber filter method can extract the specific mode of the Lamb wave, thereby distinguishing the incident wave and the damage reflection wave.  ...  Science and Technology Plan Project (no.  ... 
doi:10.1155/2020/8856241 fatcat:ob5a7p2ganfz7pv4yviol4v5ja

Detecting Production Phases Based on Sensor Values using 1D-CNNs [article]

Burkhard Hoppenstedt, Manfred Reichert, Ghada El-Khawaga, Klaus Kammerer, Karl-Michael Winter, Rüdiger Pryss
2020 arXiv   pre-print
The data set stems from a tempering furnace used for metal heat treating.  ...  In the context of Industry 4.0, the knowledge extraction from sensor information plays an important role.  ...  By using the filter-based approach, the network automatically weights more important features. To validate the approach, the data set is split up with a 80/20 ratio of train and test set.  ... 
arXiv:2004.14475v1 fatcat:26sbgccxcjbordtitqanvod7s4

Discrete Signal Processing on Graphs: Frequency Analysis

Aliaksei Sandryhaila, Jose M. F. Moura
2014 IEEE Transactions on Signal Processing  
We study the design of graph filters with specified frequency response, and illustrate our approach with applications to sensor malfunction detection and data classification.  ...  This paper studies the concepts of low and high frequencies on graphs, and low-, high-and band-pass graph signals and graph filters.  ...  We adopted the weighted adjacency matrix of the graph as the shift operator and then developed appropriate concepts of z-transform, impulse and frequency response, filtering, convolution, and Fourier transform  ... 
doi:10.1109/tsp.2014.2321121 fatcat:co5lmubojra4vca7egk627p5oe

Multi-Target Localization and Tracking Using TDOA and AOA Measurements Based on Gibbs-GLMB Filtering

Zhengwang Tian, Weifeng Liu, Xinfeng Ru
2019 Sensors  
labelled multi-Bernoulli (Gibbs-GLMB) filter and considers an acoustic array of a fixed arrangement for the tracking of targets by joint time difference of arrival (TDOA) and angle of arrival (AOA) measurements  ...  Secondly, we assume the independence of the targets and fuse the measurements which are used to track the multiple targets via the Gibbs-GLMB filter.  ...  The distinct label indicator is defined by ∆ (X) = δ |X| (|L (X)|). The parameter of a labeled multi-Bernoulli(LMB) RFS can be described as a set {(r (ζ) , p (ζ) ) : ζ ∈ Ψ} with index set Ψ.  ... 
doi:10.3390/s19245437 pmid:31835492 pmcid:PMC6960764 fatcat:e3fegojazbb2joa3a4ggaimqsa

Sensor Transformation Attention Networks [article]

Stefan Braun, Daniel Neil, Enea Ceolini, Jithendar Anumula, Shih-Chii Liu
2017 arXiv   pre-print
Moreover, the proposed sensor transformation network architecture naturally introduces a number of advantages that merit exploration, including ease of adding new sensors to existing architectures, attentional  ...  We evaluate the particular role of attentional switching in the presence of dynamic noise in the sensors, and demonstrate how the attentional signal responds dynamically to changing noise levels in the  ...  This architecture also permits investigation of common latent representations reused between sensors and modalities.  ... 
arXiv:1708.01015v1 fatcat:ndjayfflonh4rff3x4fjnv7mbq

People Tracking on a Mobile Companion Robot

Michael Volkhardt, Christoph Weinrich, Horst-Michael Gross
2013 2013 IEEE International Conference on Systems, Man, and Cybernetics  
Evaluation was done on a newly collected indoor data set which we made publicly available for comparison and benchmarking.  ...  This paper presents a realtime people tracking system for mobile robots that filters asynchronous, multi-modal detections using a Kalman filter for each person.  ...  While the data set of [2] is very large and contains various sensor modalities, it does not provide a global robot position with uncertainties and labeled person IDs which are both useful to evaluate  ... 
doi:10.1109/smc.2013.743 dblp:conf/smc/VolkhardtWG13 fatcat:vsx6iv65qjbwbmswfmtmnj73om

FALCON: Framework for Anomaly Detection in Industrial Control Systems

Subin Sapkota, A K M Nuhil Mehdy, Stephen Reese, Hoda Mehrpouyan
2020 Electronics  
The sensor/actuator data are passed through a unique feature engineering pipeline where wavelet transformation is applied to the sensor signals to extract features that are fed into the model.  ...  The proposed methodology uses dilated convolution and long short-term memory (LSTM) layers to learn temporal as well as long term dependencies within sensor and actuator data in an ICS.  ...  ) program: Formal TOols foR SafEty aNd.  ... 
doi:10.3390/electronics9081192 fatcat:b5rcqwub7vahxnnbc5nqzntcoq

Automatic identification of artifacts in electrodermal activity data

Sara Taylor, Natasha Jaques, Weixuan Chen, Szymon Fedor, Akane Sano, Rosalind Picard
2015 2015 37th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)  
We have encoded our results into a freely available web-based tool for artifact and peak detection.  ...  This paper describes the development of a machine learning algorithm for automatically detecting EDA artifacts, and provides an empirical evaluation of classification performance.  ...  by the Q sensor.  ... 
doi:10.1109/embc.2015.7318762 pmid:26736662 pmcid:PMC5413200 dblp:conf/embc/TaylorJCFSP15 fatcat:cdw5wp57n5ft5e3c5jxlldyl3u
« Previous Showing results 1 — 15 out of 89,919 results