Search

Early detection of the motor faults is essential and artificial neural networks are widely used for this purpose. The typical systems usually encapsulate two distinct blocks: feature extraction and classification. Such fixed and hand-crafted features may be a suboptimal choice and require a significant computational cost that will prevent their usage for real-time applications. In this paper, we propose a fast and accurate motor condition monitoring and early fault-detection system using 1-D convolutional neural networks that has an inherent adaptive design to fuse the feature extraction and classification phases of the motor fault detection into a single learning body. The proposed approach is directly applicable to the raw data (signal), and, thus, eliminates the need for a separate feature extraction algorithm resulting in more efficient systems in terms of both speed and hardware. Experimental results obtained using real motor data demonstrate the effectiveness of the proposed method for real-time motor condition monitoring. Scopus

Medical Technologies Congress (TIPTEKNO) -- OCT 03-05, 2019 -- Izmir, TURKEY, WOS: 000516830900058, Parkinson's disease can be diagnosed by the speech signals. In general, the data obtained by feature extraction algorithms from the speech signals are used in any classification algorithm. Some of the extracted features have a high ability to represent the relevant problem, while others are low. In the diagnosis of Parkinson's disease, it is very important to determine which of the extracted features from the speech signals may increase the classification performance. In this paper, Artificial Bee Colony algorithm based feature selection approach is proposed for the solution of the mentioned problem. The proposed method has been analyzed in comparison with the well-known classification methods including support vector machine, k nearest neighbor, Naive Bayesian, decision tree., Biyomedikal Klinik Muhendisligi Dernegi, Izmir Katip Celebi Univ, Biyomedikal Muhendisligi Bolumu

A software application for automatic descriptive feature extraction from image-objects, FETEX 2.0, is presented and described in this paper. The input data include a multispectral high resolution digital image and a vector file in shapefile format containing the polygons or objects, usually extracted from a geospatial database. The design of the available descriptive features or attributes has been mainly focused on the description of agricultural parcels, providing a variety of information: spectral information from the different image bands; textural descriptors of the distribution of the intensity values based on the grey level co-occurrence matrix, the wavelet transform and a factor of edgeness; structural features describing the spatial arrangement of the elements inside the objects, based on the semivariogram curve and the Hough transform; and several descriptors of the object shape. The output file is a table that can be produced in four alternative formats, containing a vector of features for every object processed. This table of numeric values describing the objects from different points of view can be externally used as input data for any classification software. Additionally, several types of graphs and images describing the feature extraction procedure are produced, useful for interpretation and understanding the process. A test of the processing times is included, as well as an application of the program in a real parcel-based classification problem, providing some results and analyzing the applicability, the future improvement of the methodologies, and the use of additional types of data sets. This software is intended to be a dynamic tool, integrating further data and feature extraction algorithms for the progressive improvement of land use/land cover database classification and agricultural database updating processes. © 2011 Elsevier B.V., The authors appreciate the financial support provided by the Spanish Ministerio de Ciencia e Innovacion and the FEDER in the framework of the Project CGL2009-14220 and CGL2010-19591/BTE, the Spanish Institut Geografico Nacional (IGN), Institut Cartografico Valenciano (ICV), Institut Murciano de Investigacion y Desarrollo Agrario y Alimentario (IMIDA) and Banco de Terras de Galicia (Bantegal).

Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. R. P. Krish, J. Fierrez and D. Ramos, "Integrating rare minutiae in generic fingerprint matchers for forensics," 2015 IEEE International Workshop on Information Forensics and Security (WIFS), Rome, 2015, pp. 1-6. doi: 10.1109/WIFS.2015.7368557, Automated Fingerprint Identification Systems (AFIS) are commonly used by law enforcement agencies to narrow down the possible suspects from a criminal database. AFIS do not use all discriminatory features available in fingerprints but typically use only some types of features automatically extracted by a feature extraction algorithm. Latent fingerprints obtained from crime scenes are usually partial in nature which results to only very few number of reliable minutiae. Comparing a partial minutiae pattern to a full minutiae pattern is a difficult problem. Towards solving this challenge, we propose a method that exploits extended fingerprint features (unusual/rare minutiae) not commonly considered in typical minutiae-based matchers. The method we propose in this work can be combined with any existing minutiae-based matcher. We first compute a quantitative measure based on least squares between latent and tenprint minutiae points, with rare minutia feature as reference point. Then the similarity score of the reference minutiae-based matcher is modified based on the least square quantitative measure. The modified similarity score thus obtained incorporates the contribution of rare minutia features. We use a realistic forensic fingerprint casework database in our experiments which contains rare minutia features obtained from Guardia Civil, the Spanish law enforcement agency. Experiments are conducted using two reference minutiae-based matchers, namely: NIST-Bozorth3 and VeriFinger. We report a significant improvement in the rank identification accuracies when the reference minutiae matchers are augmented with our proposed algorithm based on rare minutia features., R.K. was supported by a Marie Curie Fellowship under project BBfor2 (FP7-ITN-238803) from EU. This work has also been partially supported by Spanish Guardia Civil, project Bio-Shield (TEC2012-34881) from Spanish MINECO, and project BEAT (FP7-SEC-284989) from EU.

Date of Conference: 24-26 April 2013 In this paper, a Compressive Sensing based feature extraction algorithm is proposed for flame detection using infrared cameras. First, bright and moving regions in videos are detected. Then the videos are divided into spatio-temporal blocks and spatial and temporal feature vectors are exctracted from these blocks. Compressive Sensing is used to exctract spatial feature vectors. Compressed measurements are obtained by multiplying the pixels in the block with the sensing matrix. A new method is also developed to generate the sensing matrix. A random vector generated according to standard Gaussian distribution is passed through a wavelet transform and the resulting matrix is used as the sensing matrix. Temporal features are obtained from the vector that is formed from the difference of mean intensity values of the frames in two neighboring blocks. Spatial feature vectors are classified using Adaboost. Temporal feature vectors are classified using hidden Markov models. To reduce the computational cost only moving and bright regions are classified and classification is performed at specified intervals instead of every frame. © 2013 IEEE.

Sparse optical flow algorithms, such as the Lucas-Kanade approach, provide more robustness to noise than dense optical flow algorithms and are the preferred approach in many scenarios. Sparse optical flow algorithms estimate the displacement for a selected number of pixels in the image. These pixels can be chosen randomly. However, pixels in regions with more variance between the neighbours will produce more reliable displacement estimates. The selected pixel locations should therefore be chosen wisely. In this study, the suitability of Harris corners, Shi-Tomasi's “Good features to track", SIFT and SURF interest point extractors, Canny edges, and random pixel selection for the purpose of frame-by-frame tracking using a pyramidical Lucas-Kanade algorithm is investigated. The evaluation considers the important factors of processing time, feature count, and feature trackability in indoor and outdoor scenarios using ground vehicles and unmanned aerial vehicles, and for the purpose of visual odometry estimation.

Assessing similarity between features is a key step in object recognition and scene categorization tasks. We argue that knowledge on the distribution of distances generated by similarity functions is crucial in deciding whether features are similar or not. Intuitively one would expect that similarities between features could arise from any distribution. In this paper, we will derive the contrary, and report the theoretical result that L p-norms -a class of commonly applied distance metrics- from one feature vector to other vectors are Weibull-distributed if the feature values are correlated and non-identically distributed. Besides these assumptions being realistic for images, we experimentally show them to hold for various popular feature extraction algorithms, for a diverse range of images. This fundamental insight opens new directions in the assessment of feature similarity, with projected improvements in object and scene recognition algorithms.