scholarly journals Automated feature extraction from large cardiac electrophysiological data sets

2021 ◽  
Vol 65 ◽  
pp. 157-162
Author(s):  
John Jurkiewicz ◽  
Stacie Kroboth ◽  
Viviana Zlochiver ◽  
Peter Hinow
1996 ◽  
Vol 35 (6) ◽  
pp. 834-840 ◽  
Author(s):  
A. Rosemary Tate ◽  
Des Watson ◽  
Stephen Eglen ◽  
Theodores N. Arvanitis ◽  
E. Louise Thomas ◽  
...  

2021 ◽  
Vol ahead-of-print (ahead-of-print) ◽  
Author(s):  
Jiawei Lian ◽  
Junhong He ◽  
Yun Niu ◽  
Tianze Wang

Purpose The current popular image processing technologies based on convolutional neural network have the characteristics of large computation, high storage cost and low accuracy for tiny defect detection, which is contrary to the high real-time and accuracy, limited computing resources and storage required by industrial applications. Therefore, an improved YOLOv4 named as YOLOv4-Defect is proposed aim to solve the above problems. Design/methodology/approach On the one hand, this study performs multi-dimensional compression processing on the feature extraction network of YOLOv4 to simplify the model and improve the feature extraction ability of the model through knowledge distillation. On the other hand, a prediction scale with more detailed receptive field is added to optimize the model structure, which can improve the detection performance for tiny defects. Findings The effectiveness of the method is verified by public data sets NEU-CLS and DAGM 2007, and the steel ingot data set collected in the actual industrial field. The experimental results demonstrated that the proposed YOLOv4-Defect method can greatly improve the recognition efficiency and accuracy and reduce the size and computation consumption of the model. Originality/value This paper proposed an improved YOLOv4 named as YOLOv4-Defect for the detection of surface defect, which is conducive to application in various industrial scenarios with limited storage and computing resources, and meets the requirements of high real-time and precision.


2003 ◽  
Author(s):  
Neal R. Harvey ◽  
Simon J. Perkins ◽  
Paul A. Pope ◽  
James P. Theiler ◽  
Nancy A. David ◽  
...  

2020 ◽  
Author(s):  
Ying Bi ◽  
Bing Xue ◽  
Mengjie Zhang

© Springer International Publishing AG, part of Springer Nature 2018. Feature extraction is an essential process for image data dimensionality reduction and classification. However, feature extraction is very difficult and often requires human intervention. Genetic Programming (GP) can achieve automatic feature extraction and image classification but the majority of existing methods extract low-level features from raw images without any image-related operations. Furthermore, the work on the combination of image-related operators/descriptors in GP for feature extraction and image classification is limited. This paper proposes a multi-layer GP approach (MLGP) to performing automatic high-level feature extraction and classification. A new program structure, a new function set including a number of image operators/descriptors and two region detectors, and a new terminal set are designed in this approach. The performance of the proposed method is examined on six different data sets of varying difficulty and compared with five GP based methods and 42 traditional image classification methods. Experimental results show that the proposed method achieves better or comparable performance than these baseline methods. Further analysis on the example programs evolved by the proposed MLGP method reveals the good interpretability of MLGP and gives insight into how this method can effectively extract high-level features for image classification.


Research problem introduction. The main research goal of this paper is to provide the urban geosystem research concept with both the theoretical basics presentation of GIS involvement in urban studies, and with examples of its practical applications. An urbogeosystem (UGS) has been presented not as a simple aggregate of cities, but as the emergent entity that produced complicated interconnections and interdependencies among its constituents. By the urbogeosystem concept the authors attempt to introduce a reliable research approach that has been deliberately developed to identify the nature and spatial peculiarities of the urbanization process in a given area. The exigency of this concept elaboration is listed by the number of needs and illustrated with ordinary 2D digital city cadaster limitations. The methodological background has been proposed, and its derivative applied solutions meet the number of necessities for more efficient urban mapping, city understanding, and municipal mana-gement. The geoinformation concept of the urban geographic system research. External and internal urbogeosystems. The authors explain why an UGS can be formalized as three major components: an aggregate of point features, a set of lines, an aggregate of areal features. The external UGS represents a set of cities, the internal one – a set of delineated areas within one urban territory. Algorithmic sequence of the urbogeosystem study with a GIS. The authors introduce algorithmic sequence of research provision with GIS, in which the LiDAR data processing block has been examined in the details with the procedure of the automated feature extraction explanation. Relevant software user interface sample of the visualization of the urban modeled feature attributes is provided. A case study of the external urbogeosystem. The regional case study of the external urbogeosystem modeling is introduced with GIS MapInfo Professional. The authors present the spatial econometric analysis for commuting study directed to a regional workforce market. The results of the external UGS research mainly correspond to some published social economic regularities in the area, but nonetheless it also demonstrates significant deviations that may be explained by this system’s emergent properties. Case studies of the internal urbogeosystem of Kharkiv-City. Two case studies of the internal urbogeosystem of Kharkiv City have been demonstrated, too. In the first one, automated feature extraction provided by the authors’ original software from LiDAR data has been applied for modeling this UGS content throughout a densely built-up urban parcel. In another case the GIS-analysis of the urbogeosystem functional impact on the catering services spatial distribution has been provided with the ArcGIS software. Results and conclusion. Summarizing all primary and derivative data processed with this technique as well as generalizing key ideas discussed in the text, the authors underline this whole methodological approach as such that can be considered as a general outlining showing how to use geoinformation software for the analysis of urban areas. Concluding their research, the authors emphasize that the urbogeosystem concept may be quite useful for visualization and different analysis applied for urban areas, including city planning, facility and other municipal management methods. The short list of the obtained results has been provided at the end of the text.


2019 ◽  
Vol 9 (18) ◽  
pp. 3930 ◽  
Author(s):  
Jaehyun Yoo ◽  
Jongho Park

This paper studies the indoor localization based on Wi-Fi received signal strength indicator (RSSI). In addition to position estimation, this study examines the expansion of applications using Wi-Fi RSSI data sets in three areas: (i) feature extraction, (ii) mobile fingerprinting, and (iii) mapless localization. First, the features of Wi-Fi RSSI observations are extracted with respect to different floor levels and designated landmarks. Second, the mobile fingerprinting method is proposed to allow a trainer to collect training data efficiently, which is faster and more efficient than the conventional static fingerprinting method. Third, in the case of the unknown-map situation, the trajectory learning method is suggested to learn map information using crowdsourced data. All of these parts are interconnected from the feature extraction and mobile fingerprinting to the map learning and the estimation. Based on the experimental results, we observed (i) clearly classified data points by the feature extraction method as regards the floors and landmarks, (ii) efficient mobile fingerprinting compared to conventional static fingerprinting, and (iii) improvement of the positioning accuracy owing to the trajectory learning.


Sign in / Sign up

Export Citation Format

Share Document