Filters








20,344 Hits in 6.4 sec

Automatically detecting asymmetric running using time and frequency domain features

Edmond Mitchell, Amin Ahmadi, Noel E. O'Connor, Chris Richter, Evan Farrell, Jennifer Kavanagh, Kieran Moran
2015 2015 IEEE 12th International Conference on Wearable and Implantable Body Sensor Networks (BSN)  
The framework can automatically classify symmetry/asymmetry using Short Time Fourier Transform (STFT) and other time domain features in conjunction with a customized Random Forest classifier.  ...  In this paper, we present a novel wearable inertial sensor framework to accurately distinguish between symmetrical and asymmetrical running patterns in an unconstrained environment.  ...  domain features have been used extensively to automatically detect different user activities [22] activity, which results in generating different frequency signatures.  ... 
doi:10.1109/bsn.2015.7299404 dblp:conf/bsn/MitchellAORFKM15 fatcat:bexqjcg2szfxfhyk36ddqzgbiu

Automatic interpretation and writing report of the adult waking electroencephalogram

Hiroshi Shibasaki, Masatoshi Nakamura, Takenao Sugi, Shigeto Nishida, Takashi Nagamine, Akio Ikeda
2014 Clinical Neurophysiology  
Therefore, previous attempts of automatic EEG interpretation have been focused only on a specific EEG feature such as paroxysmal abnormalities, delta waves, sleep stages and artifact detection.  ...  A computer-assisted system for automatic, systematic and comprehensive interpretation of the adult waking EEG was developed for the first time. 2.  ...  In this model, the amplitude information of EEG represented in the time domain was shown to be reliably obtained from the power spectrum in the frequency domain by the use of a Markov process amplitude  ... 
doi:10.1016/j.clinph.2013.12.114 pmid:24560132 fatcat:wnyekob7hbb53cned6sofikuk4

Emulating Asymmetric MPSoCs on the Intel SCC Many-Core Processor

Roy Bakker, Michiel W. van Tol, Andy D. Pimentel
2014 2014 22nd Euromicro International Conference on Parallel, Distributed, and Network-Based Processing  
Then, we show how the SCC can be used as a substrate to emulate asymmetric multi processor systems on chip (AMPSoCs) to be used for studying power/performance trade-offs.  ...  It has extensive frequency and voltage scaling support as well as on board power monitors. In this paper we present a detailed study of the power properties of the SCC.  ...  ACKNOWLEDGMENTS We thank Clemens Grelck for his feedback on early drafts of this paper, as well as the people at Intel Labs that provided us with an Intel SCC system through their MARC program.  ... 
doi:10.1109/pdp.2014.104 dblp:conf/pdp/BakkerTP14 fatcat:mwic3fzb3zfvheveqguzpi35g4

Real-Time Smart-Digital Stethoscope System for Heart Diseases Monitoring

Muhammad E.H. Chowdhury, Amith Khandakar, Khawla Alzoubi, Samar Mansoor, Anas M. Tahir, Mamun Bin Ibne Reaz, Nasser Al-Emadi
2019 Sensors  
Twenty-seven t-domain, f-domain, and Mel frequency cepstral coefficients (MFCC) features were used to train a public database to identify the best-performing algorithm for classifying abnormal and normal  ...  The hyper parameter optimization, along with and without a feature reduction method, was tested to improve accuracy.  ...  MFCC is the most commonly used time-frequency feature in the domain of automatic sound wave classification [30] .  ... 
doi:10.3390/s19122781 fatcat:hxhwz5twv5hs7fxf4e2rtka57m

Feature extraction from ear-worn sensor data for gait analysis

Ling Li, Louis Atallah, Benny Lo, Guang-Zhong Yang
2014 IEEE-EMBS International Conference on Biomedical and Health Informatics (BHI)  
CONFLICT OF INTEREST The e-AR sensor used for data acquisition is provided by Sensixa, a spin-off company from Imperial College London.  ...  In the same time, peaks are perserved and detected.  ...  It can also be extended to automatically identification of the vital points in running data.  ... 
doi:10.1109/bhi.2014.6864426 dblp:conf/bhi/LiALY14 fatcat:y76xzr7ld5ad3ckos4ttftx6bm

Automatic detection of auditory salience with optimized linear filters derived from human annotation

Kyungtae Kim, Kai-Hsiang Lin, Dirk B. Walther, Mark A. Hasegawa-Johnson, Tomas S. Huang
2014 Pattern Recognition Letters  
Expanding the feature vector to include other common feature sets does not improve performance. Consistent with intuition, the optimal filter looks like an onset detector in the time domain.  ...  Previous attempts at automatic detection of salient audio events have been hampered by the challenge of defining ground truth.  ...  Filters in the time domain need to be asymmetric, because they can only use current and past but not future parts of the signal.  ... 
doi:10.1016/j.patrec.2013.11.010 fatcat:4n2jbhohpjgtjdumtncc342kiq

On-line fault detection method for induction machines based on signal convolution

Jordi Cusido, Luis Romeral, Antonio Garcia Espinosa, Juan Antonio Ortega, Jordi-Roger Riba Ruiz
2010 European Transactions on Electrical Power  
A new technique for induction motor fault detection and diagnosis is presented.  ...  These functions are tuned to specific fault frequencies taking into account motor speed and load torque, thus considering variable operation conditions of the motor.  ...  ACKNOWLEDGEMENTS The authors wish to acknowledge the financial support received from the ''Ministerio de Ciencia y Tecnología de España'' (Spanish Ministry of Science and Technology) for carrying out this  ... 
doi:10.1002/etep.455 fatcat:6zwxgiimk5fp3n6wex2zomcu2m

A Multi-Classifier Network-based Crypto Ransomware Detection System: A Case study of Locky Ransomware

Ahmad O. Almashhadani, Mustafa Kaiiali, Sakir Sezer, Philip Okane
2019 IEEE Access  
The experimental evaluation of the proposed detection system demonstrates that it offers high detection accuracy, low false positive rate, valid extracted features, and is highly effective in tracking  ...  A dedicated testbed was built, and a set of valuable and informative network features were extracted and classified into multiple types.  ...  [16] analyzed CryptoWall ransomware dynamically in a dedicated environment using a honeypot and automatic run-time malware analytical system, Maltester.  ... 
doi:10.1109/access.2019.2907485 fatcat:dqxpa5uiknherd53m7g37djbym

An algorithm for automatic detection of drowsiness for use in wearable EEG systems

Kwai C. A. Patrick, Syed Anas Imtiaz, Stuart Bowyer, Esther Rodriguez-Villegas
2016 2016 38th Annual International Conference of the IEEE Engineering in Medicine and Biology Society (EMBC)  
In this paper, by analyzing the electroencephalographic (EEG) signals of human subjects in the frequency domain, several features across different EEG channels are explored.  ...  Timely detection of drowsiness can prevent the occurrence of unfortunate accidents thereby improving road and work environment safety.  ...  Finally, the epochs are transformed into frequency domain using 512-point FFT to extract the various discriminating features. B.  ... 
doi:10.1109/embc.2016.7591488 pmid:28269058 dblp:conf/embc/PatrickIBR16 fatcat:wofhljogubbs3fvuvulxweftrq

Supervised Heart Rate Tracking using Wrist-Type Photoplethysmographic (PPG) Signals during Physical Exercise without Simultaneous Acceleration Signals [article]

Mahmoud Essalat, Mahdi Boloursaz Mashhadi, Farokh Marvasti
2020 arXiv   pre-print
By simulations on the benchmark datasets [1], we achieve acceptable estimation accuracy and improved run time in comparison with the literature.  ...  A major contribution of this work is that it alleviates the need to use simultaneous acceleration signals.  ...  are usually uniquely dominant, 'uniqueness' , denoted as , is defined as: Following features are obtained after normalizing signal to its maximum value and using the HR time domain based estimation, denoted  ... 
arXiv:2010.00769v1 fatcat:iwqh77lqpje6fde4x7qb2a4ika

A new method for the extraction of speech features using spectral-delta characteristics and invariant integration

Hassan FARSI, Samana KUHIMOGHADAM
2014 Turkish Journal of Electrical Engineering and Computer Sciences  
Since the current automatic speech recognition systems use invariantintegration and delta-delta techniques for speech feature extraction, the proposed algorithm improves speech recognition accuracy appropriately  ...  We propose a new feature extraction algorithm that is robust against noise. Nonlinear filtering and temporal masking are used for the proposed algorithm.  ...  Nonlinearity indicates that time domain optimization cannot be accurate [12] in the feature domain and, therefore, we use the feature domain for optimizing.  ... 
doi:10.3906/elk-1207-76 fatcat:2qwdpymx55cr3oudz3yv6doeqy

A novel reputation system to detect DGA-based botnets

Reza Sharifnya, Mahdi Abadi
2013 ICCKE 2013  
New generation botnets, such as Conficker and Murofet, tend to use a form of domain fluxing for command and control.  ...  Each domain fluxing bot generates a list of domain names using a domain name generation algorithm (DGA) and queries each of them until one of them is resolved to a C&C server.  ...  The technique uses features derived from DNS query responses to build a Naïve Bayesian classifier for classifying a domain name as malicious or legitimate.  ... 
doi:10.1109/iccke.2013.6682860 fatcat:bfislfxvergonf7734wv7izjxa

Transition State Matrices Approach for Trajectory Segmentation Based on Transport Mode Change Criteria

Martina Erdelić, Tonči Carić, Tomislav Erdelić, Leo Tišljarić
2022 Sustainability  
Transition State Matrices (TSM) were used to automatically detect the transport mode change point in the trajectory. The developed method is based on the sensor data collected from mobile devices.  ...  After testing and validating the method, an overall accuracy of 98% and 96%, respectively, was achieved.  ...  European Union's Horizon 2020 research and innovation programme under grant agreement No. 857592.  ... 
doi:10.3390/su14052756 fatcat:ckmqiheoa5daljilpkg4z3gqx4

A Survey of Emerging Trend Detection in Textual Data Mining [chapter]

April Kontostathis, Leon M. Galitsky, William M. Pottenger, Soma Roy, Daniel J. Phelps
2004 Survey of Text Mining  
For each Emerging Trend Detection (ETD) system we describe components including linguistic and statistical features, learning algorithms, training and test set generation, visualization and evaluation.  ...  Development and use of e ective metrics for evaluation of ETD systems is critical. Work continues on the semi-automatic and fully-automatic systems we are developing at Lehigh University HDD].  ...  Textual Data Mining 39 Workshop, and Doug Bryan at SPSS (LexiQuest) and Barry Graubart at ClearForest for providing timely information included in our commercial products section.  ... 
doi:10.1007/978-1-4757-4305-0_9 fatcat:sw2yexyqhna2bjmrtc6cglzr6u

Automatic recognition of object use based on wireless motion sensors

Stephan Bosch, Raluca Marin-Perianu, Paul Havinga, Arie Horst, Mihai Marin-Perianu, Andrei Vasilescu
2010 International Symposium on Wearable Computers (ISWC) 2010  
In this paper, we present a method for automatic, online detection of a user's interaction with objects.  ...  Our method is based on correlating features extracted from motion sensors worn by the user and attached to objects.  ...  Correlation Algorithm The correlation of the two motion features in the feature vector between two nodes is done in the time domain using the Pearson product-moment correlation coefficient: ρ X,Y = cov  ... 
doi:10.1109/iswc.2010.5665858 dblp:conf/iswc/BoschMHHMV10 fatcat:v725dpia5rf7zity6ylceh44hi
« Previous Showing results 1 — 15 out of 20,344 results