Nonstationary Concurrent Service Feature Identification Algorithm

This paper describes an alternative structural health monitoring (SHM) framework for low-light settings or dark environments using underexposed images from vision-based sensors based on the practical implementation of image enhancement algorithms. The proposed framework was validated by two experimental works monitored by two vision systems under ambient lights without assistance from additional lightings. The first experiment monitored six artificial templates attached to a sliding bar that was displaced by a standard one-inch steel block. The effect of image enhancement in the feature identification and bundle adjustment integrated into the close-range photogrammetry were evaluated. The second validation was from a seismic shake table test of a full-scale three-story building tested at E-Defense in Japan. Overall, this study demonstrated the efficiency and robustness of the proposed image enhancement framework in (i) modifying the original image characteristics so the feature identification algorithm is capable of accurately detecting, locating and registering the existing features on the object; (ii) integrating the identified features into the automatic bundle adjustment in the close-range photogrammetry process; and (iii) assessing the measurement of identified features in static and dynamic SHM, and in structural system identification, with high accuracy.

Download Full-text

Boosting the MS1-only proteomics with machine learning allows 2000 protein identifications in 5-minute proteome analysis

10.1101/2020.10.29.359075 ◽

2020 ◽

Author(s):

Mark V. Ivanov ◽

Julia A. Bubis ◽

Vladimir Gorshkov ◽

Daniil A. Abdrakhimov ◽

Frank Kjeldsen ◽

...

Keyword(s):

Machine Learning ◽

Mass Spectra ◽

Learning Algorithm ◽

Proteome Analysis ◽

Time Frame ◽

Mass Analyzer ◽

Identification Algorithm ◽

Feature Identification ◽

Proteome Coverage ◽

Time Prediction

ABSTRACTProteome-wide analyses most often rely on tandem mass spectrometry imposing considerable instrumental time consumption that is one of the main obstacles in a broader acceptance of proteomics in biomedical and clinical research. Recently, we presented a fast proteomic method termed DirectMS1 based on MS1-only mass spectra acquisition and data processing. The method allowed significant squeezing of the proteome-wide analysis to a few minute time frame at the depth of quantitative proteome coverage of 1000 proteins at 1% FDR. In this work, to further increase the capabilities of the DirectMS1 method, we explored the opportunities presented by the recent progress in the machine learning area and applied the LightGBM tree-based learning algorithm into the scoring of peptide-feature matches when processing MS1 spectra. Further, we integrated the peptide feature identification algorithm of DirectMS1 with the recently introduced peptide retention time prediction utility, DeepLC. Additional approaches to improve performance of the DirectMS1 method are discussed and demonstrated, such as FAIMS coupled to the Orbitrap mass analyzer. As a result of all improvements to DirectMS1, we succeeded in identifying more than 2000 proteins at 1% FDR from the HeLa cell line in a 5 minute LC-MS1 analysis.

Download Full-text

Selection of an Optimal Set of Features for Bengali Character Recognition

Technical Challenges and Design Issues in Bangla Language Processing ◽

10.4018/978-1-4666-3970-6.ch005 ◽

2013 ◽

pp. 96-116 ◽

Cited By ~ 1

Author(s):

Hasan Sarwar ◽

Mizanur Rahman ◽

Nasreen Akter ◽

Saima Hossain ◽

Sabrina Ahmed ◽

...

Keyword(s):

Character Recognition ◽

Optical Character Recognition ◽

Individual Characteristic ◽

Identification Algorithm ◽

Feature Identification ◽

Feature Sets ◽

Character Set ◽

Optimal Set ◽

Optimal Feature ◽

Generic Algorithms

Feature extraction is an essential step of Optical Character Recognition. Accurate and distinguishable feature plays a significant role to leverage the performance of a classifier. The complexity level of feature identification algorithm differs for alphabet sets of different languages. Apart from generic algorithms to find features of different alphabet sets, these algorithms take care of individual characteristic common for a particular alphabet set. Dominant features of one alphabet set might completely differ from that of another set. Since there always remains the chance that inaccurate features may cause inefficient recognition, special attention should be given to identify the set of optimal features of a character set. Bengali characters also have some specific issues apart from the existing issues of other character sets. For example, there are about 300 basic, modified, and compound character shapes in the script, the characters in a word are topologically connected, and Bengali is an inflectional language. Literature survey shows that several authors have used different features and classification algorithms. The authors have extensively reviewed all these feature sets. In order to identify an optimal feature set, variability analysis has been proposed here. They focus on the specific peculiarities of Bengali alphabet sets, its different usage as vowel and consonant signs, compound, complex, and touching characters. The authors also took care to generate easily computable features that take less time for generation. However, more attention needs to be given in order to choose an efficient classifier.

Download Full-text

A New Feature Identification Algorithm of Non-Cooperative Spacecraft Based on Convolution Neural Network

Journal of Computational and Theoretical Nanoscience ◽

10.1166/jctn.2016.6066 ◽

2016 ◽

Vol 13 (11) ◽

pp. 8946-8951 ◽

Cited By ~ 1

Author(s):

Xiande Wu ◽

Yuchi Yi ◽

Yaen Xie ◽

Hongtao Cui ◽

Long Tan ◽

...

Keyword(s):

Neural Network ◽

Convolution Neural Network ◽

Identification Algorithm ◽

Feature Identification ◽

New Feature

Download Full-text

SCFIA: a statistical corresponding feature identification algorithm for LC/MS

BMC Bioinformatics ◽

10.1186/1471-2105-12-439 ◽

2011 ◽

Vol 12 (1) ◽

pp. 439 ◽

Cited By ~ 8

Author(s):

Jian Cui ◽

Xuepo Ma ◽

Long Chen ◽

Jianqiu Zhang

Keyword(s):

Identification Algorithm ◽

Feature Identification

Download Full-text

Environmental Monitoring Smart System with Self-Sustaining Wireless Sensor Network Using Data Validation Algorithms

Journal of Engineering Sciences ◽

10.21272/jes.2020.7(1).e3 ◽

2020 ◽

Vol 7 (1) ◽

pp. E10-E19

Author(s):

T. Kanwal ◽

S. Altaf ◽

M. K. Javed

Keyword(s):

Wireless Sensor Network ◽

Sensor Network ◽

Ad Hoc ◽

Wireless Sensor ◽

Identification Algorithm ◽

Data Validation ◽

Feature Identification ◽

Hybrid Form ◽

Multiple Faults ◽

Using Data

Study in Wireless Sensor Network (WSN) has been becoming an emerging and promising research topic aiming for the advancement in the Internet of Things (IoT) for a reliable connection. The capability of the wireless sensor to be used in a complex environment can become hard to reach areas and also be able to communicate in an ad-hoc manner, attracted researchers in recent times. Development in wireless sensor network producing a lot of new applications to sense environment remotely are facing challenges restricting it to perform up to its potential. Data validation and data reliability are such existing problems in this domain that needed to be addressed. Because sensed data cannot be blindly trusted upon, as it may have faults and errors occurred with-in the sensing environment. Besides, to guarantee the active state of the sensing system in a remote area is also essential in terms of power usage and management. The focus of the paper is data validation acquired from sensors deployed in remote areas. Although, lots of data validation algorithms have been proposed by researchers to identify single data fault. However, our research identifies multiple faults, namely spike fault, out of range fault, outliers, and stuck at fault using a hybrid form of an algorithm. A comparison with the existing algorithm shows that the proposed algorithm improved data validation by 97 % in detecting multiple data faults using Artificial Intelligence techniques. Keywords: wireless sensor network, data validation, feature extraction, feature identification, algorithm.

Download Full-text

Tire Rolling Kinematics Model for an Intelligent Tire Based on an Accelerometer

Tire Science and Technology ◽

10.2346/tire.20.190211 ◽

2020 ◽

Vol 48 (4) ◽

pp. 287-314

Author(s):

Yan Wang ◽

Zhe Liu ◽

Michael Kaliske ◽

Yintao Wei

Keyword(s):

Elastic Deformation ◽

Estimation Algorithm ◽

Force Sensor ◽

Euler Method ◽

Rolling Contact ◽

Body Motion ◽

Identification Algorithm ◽

Active Perception ◽

Kinematics Model ◽

Ring Model

ABSTRACT The idea of intelligent tires is to develop a tire into an active perception component or a force sensor with an embedded microsensor, such as an accelerometer. A tire rolling kinematics model is necessary to link the acceleration measured with the tire body elastic deformation, based on which the tire forces can be identified. Although intelligent tires have attracted wide interest in recent years, a theoretical model for the rolling kinematics of acceleration fields is still lacking. Therefore, this paper focuses on an explicit formulation for the tire rolling kinematics of acceleration, thereby providing a foundation for the force identification algorithms for an accelerometer-based intelligent tire. The Lagrange–Euler method is used to describe the acceleration field and contact deformation of rolling contact structures. Then, the three-axis acceleration vectors can be expressed by coupling rigid body motion and elastic deformation. To obtain an analytical expression of the full tire deformation, a three-dimensional tire ring model is solved with the tire–road deformation as boundary conditions. After parameterizing the ring model for a radial tire, the developed method is applied and validated by comparing the calculated three-axis accelerations with those measured by the accelerometer. Based on the features of acceleration, especially the distinct peak values corresponding to the tire leading and trailing edges, an intelligent tire identification algorithm is established to predict the tire–road contact length and tire vertical load. A simulation and experiments are conducted to verify the accuracy of the estimation algorithm, the results of which demonstrate good agreement. The proposed model provides a solid theoretical foundation for an acceleration-based intelligent tire.

Download Full-text

Localization and Non-Localization Node Identification Using Dream in MANET

SMART MOVES JOURNAL IJOSCIENCE ◽

10.24113/ijoscience.v2i2.77 ◽

2016 ◽

Vol 2 (2) ◽

Author(s):

Amit Singh ◽

Nitin Mishra ◽

Angad Singh

Keyword(s):

Ad Hoc Network ◽

Ad Hoc ◽

Mobile Ad Hoc Network ◽

Fundamental Problem ◽

Identification Algorithm ◽

Mobile Nodes ◽

Position Information ◽

Location Services ◽

Wireless Router ◽

Mobile Ad Hoc

A Wireless Mobile Ad-hoc Network consists of variety of mobile nodes that temporally kind a dynamic infrastructure less network. To modify communication between nodes that don’t have direct radio contact, every node should operate as a wireless router and potential forward knowledge traffic of behalf of the opposite node. In MANET Localization is a fundamental problem. Current localization algorithm mainly focuses on checking the localizability of a network and/or how to localize as many nodes as possible. It could provide accurate position information foe kind of expanding application. Localization provide information about coverage, deployment, routing, location, services, target tracking and rescue If high mobility among the mobile nodes occurs path failure breaks. Hence the location information cannot be predicted. Here we have proposed a localization based algorithm which will help to provide information about the localized and non-localized nodes in a network. In the proposed approach DREAM protocol and AODV protocol are used to find the localizability of a node in a network. DREAM protocol is a location protocol which helps to find the location of a node in a network whereas AODV is a routing protocol it discover route as and when necessary it does not maintain route from every node to every other. To locate the mobile nodes in a n/w an node identification algorithm is used. With the help of this algorithm localized and non-localized node can be easily detected in respect of radio range. This method helps to improve the performance of a module and minimize the location error and achieves improved performance in the form of UDP packet loss, received packet and transmitted packets, throughput, routing overhead, packet delivery fraction. All the simulation done through the NS-2 module and tested the mobile ad-hoc network.

Download Full-text