Search

Abstract Aiming at the problem that the geomagnetic sensor is vulnerable to external interference in the navigation process, this paper analyzes the frequency distribution range of geomagnetic signal and the noise characteristics in geomagnetic signal and proposes an improved morphological filtering and Hilbert–Huang transform (IMMF–IHHT) algorithm to extract and recognize the features of geomagnetic measurement signal. To avoid frequency aliasing and distortion caused by empirical mode decomposition, an improved morphological filtering algorithm based on mean constraint is used to preprocess the measured signal. The Hilbert spectrum of the decomposed signal is solved, the signal components are discriminated by the similarity criterion, and the signal components in line with the frequency range of the geomagnetic signal are extracted and processed to reconstruct the geomagnetic measurement signal. Simulation and experiments show that the signal-to-noise ratio and root-mean-square error of IMMF–IHHT combination algorithm are better than MF-HHT combination algorithm and IHHT algorithm. This algorithm has good signal feature extraction and recognition ability.

Aiming at the problem that the geomagnetic sensor is vulnerable to external interference in the navigation process, this paper analyzes the frequency distribution range of geomagnetic signal and the noise characteristics in geomagnetic signal and proposes an improved morphological filtering and Hilbert–Huang transform (IMMF–IHHT) algorithm to extract and recognize the features of geomagnetic measurement signal. To avoid frequency aliasing and distortion caused by empirical mode decomposition, an improved morphological filtering algorithm based on mean constraint is used to preprocess the measured signal. The Hilbert spectrum of the decomposed signal is solved, the signal components are discriminated by the similarity criterion, and the signal components in line with the frequency range of the geomagnetic signal are extracted and processed to reconstruct the geomagnetic measurement signal. Simulation and experiments show that the signal-to-noise ratio and root-mean-square error of IMMF–IHHT combination algorithm are better than MF-HHT combination algorithm and IHHT algorithm. This algorithm has good signal feature extraction and recognition ability. [ABSTRACT FROM AUTHOR]

The intersection between part features caused ambiguousness in featurerepresentation because the topology in this case will be change. To overcome this no unique and ambiguousness by combine the topology and characteristics to extract and recognize the intersection features. This paper introduces new general algorithm to: (1) construct developed Attributes Adjacency Matrix (DAAM) and (2) analysis the DAAM to extract and recognize the isolated and intersection (complex) manufacturing features. This algorithm consists of two stages, preprocessorstage which performs extraction of information from Design ExchangeFormat (DXF) file, and post-processor stage which recognizes part’s features depending on the relations included in DAAM. The parts are represented in AutoCAD using Constructive Solid Geometry (CSG) technique and the algorithm built in visual basic. Several parts tested and succeed to recognize several types of intersection (complex) manufacturing features. The main contributions of this research include building the adjacent relations between faces of the part bygeometrical characteristics in form of matrix, and use clustering operation to extract the exact faces of feature and use different classes of geometrical characteristics to assisting to recognize interacting depression prismatic features.

This paper introduces Developed Attributes Adjacency Matrix (DAAM)approach for extracting and recognizing of part’s features, by deal with decouplingor isolated manufacturing features. The proposed algorithm consists of two stages,pre-processor stage which perform extraction of information from DesignExchange Format (DXF) file format in Computer Aided Design (CAD), and postprocessorstage which recognizes part’s features depending on attributesadjacency matrix.The main contributions of this research include building the adjacent relationsbetween faces of the part by geometrical characteristics in form of matrix, and useclustering operation to extract the exact faces of feature and use different classesof geometrical characteristics to assisting to recognize depression prismaticfeatures useful in machining and other application such as dimensional inspectionand assembly.

Automatic seizure detection is significant for long-term monitoring of epilepsy, as well as for diagnostics and rehabilitation, and can decrease the duration of work required when inspecting the EEG signals. In this study we propose a novel method for feature extraction and pattern recognition of ictal EEG, based upon empirical mode decomposition (EMD) and support vector machine (SVM). First the EEG signal is decomposed into Intrinsic Mode Functions (IMFs) using EMD, and then the coefficient of variation and fluctuation index of IMFs are extracted as features. SVM is then used as the classifier for recognition of ictal EEG. The experimental results show that this algorithm can achieve the sensitivity of 97.00% and specificity of 96.25% for interictal and ictal EEGs, and the sensitivity of 98.00% and specificity of 99.40% for normal and ictal EEGs on Bonn data sets. Besides, the experiment with interictal and ictal EEGs from Qilu Hospital dataset also yields a satisfactory sensitivity of 98.05% and specificity of 100%. [ABSTRACT FROM AUTHOR]