Automated Identification Process Research Articles

Jacobian-Sensitivity Approach for Identifying Machine Dynamic Model Parameters of Robots with Flexible Joints

The versatility and large work envelope have made robots a fixture in the field of assembly for years. However, their lower stiffness and pose dependency require robust models to find optimal trajectories even for high accuracy applications. A significant obstacle in this domain is parametrizing such models of compliant robots during operation. Addressing this gap, and considering the trend of robots performing manufacturing tasks in parallel with assembly, we present an automated identification process to estimate the stiffness and damping parameters of robot joints within a milling process. This method relies solely on universally accessible kinematic chain data and force and acceleration measurements at the tool center point, eliminating the need for specialized equipment. The approach is based on a multi-body simulation, which includes flexible 6-DOF bushing joints. Key to our approach is using Jacobian-based sensitivities inside a Random Search (RS) algorithm to navigate the complexities of a sparse multi-dimensional parameter space. Our approach is versatile enough to accommodate various parameter types. We test our approach on a simulated 3-joint robot with 6 DOF per joint. By pairing the Jacobian-based sensitivities with adaptions made to the RS algorithm, we obtain accurate predictions for unknown input data with a mean relative displacement error of 2%.

Novel Orbit-based CNN Model for Automatic Fault Identification of Rotating Machines

Various faults in high-fidelity turbomachinery such as steam turbines and centrifugal compressors usually result in unplanned outage thus lowering the reliability and productivity while largely increasing the maintenance costs. Condition monitoring has been increasingly applied to provide early alerting on component faults by using the vibration signals. However, each type of fault in different types of rotating machines usually require an individual model to isolate the damage for accurate condition monitoring, which require costly computation efforts and resources due to the data uncertainties and modeling complexity. This paper presents a generalized deep learning methodology for accurately automatic diagnostics of various faults in general rotating machines by utilizing the shaft orbits generated from vibration signals, considering the high non-linearity and uncertainty of the sensed vibration signals. The sensor anomalies and environmental noise in the vibration signals are first addressed through waveform compensation and Bayesian wavelet noise reduction filtering. Shaft orbit images are generated from the cleansed vibration data collected from different turbomachinery with various fault modes. A multi-layer convolutional neural network model is then developed to classify and identify the shaft orbit images of each fault. Finally, the fault diagnosis of rotating machinery is realized through the automated identification process. The proposed approach retains the fault information in the axis trajectory to the greatest extent, and can adeptly extract and accurately identify features of various faults. The effectiveness and feasibility of the proposed methodology is demonstrated by using the sensed vibration signals collected from real-world centrifugal compressors and steam turbines with different fault modes.

METHOD FOR DETERMINING A PERIODIC WAVE ITERACY OF PHOTOPLETISMOGRAM FOR BIOMETRIC IDENTIFICATION

Background. In recent years, the development of an automated identification process using biometric authentication has been observed, which has a high level of protection, since it allows you to evaluate the physical parameters and characteristics of a particular person. Such access control is more reliable since identifiers cannot be transferred to third parties or duplicated to bypass security systems. Over the past decades, a significant number of systems with biometric identification has been developed, but systems with identification according to the characteristics of the photoplethysmogram still receive little attention. The main task of biometric personality identification using photoplethysmogram is the search and implementation of machine learning methods to determine their belonging to a particular patient.Objective. The purpose of the paper is to develop an algorithm for distinguishing pulse wave iterations using the calculation of the temporal characteristics of photoplethysmograms, such as the maximum amplitude value, variance, mean absolute deviation, Wilson amplitude and the total sum of signal amplitude values.Methods. Based on the study of the temporal characteristics of the photoplethysmogram, an algorithm for distinguishing pulse wave iterations is created, which can be used for further biometric identification of a person using machine-learning methods.Results. The results can be used for further development of automated access control and management systems using biometric identification.Conclusions. Known methods of biometric identification are usually based on the static parameters of a person (the structure of the cornea of the eye, palm, fingerprints, geometry of the auricle, etc.), but have a low level of protection, since using special equipment you can create a copy of the biometric key. Therefore, today, the use of methods based on the parameters of dynamic biometric identification (plethysmogram, cardiogram and others) provides the highest degree of protection, but requires a more accurate software device to isolate and determine common symptoms. The proposed approach to calculating individual parameters of the photoplethysmogram with the aim of their subsequent classification by machine learning methods may be an acceptable solution for patient biometric identification systems.

Toward Automated N-Glycopeptide Identification in Glycoproteomics.

Advances in software-driven glycopeptide identification have facilitated N-glycoproteomics studies reporting thousands of intact N-glycopeptides, i.e., N-glycan-conjugated peptides, but the automated identification process remains to be scrutinized. Herein, we compare the site-specific glycoprofiling efficiency of the PTM-centric search engine Byonic relative to manual expert annotation utilizing typical glycoproteomics acquisition and data analysis strategies but with a single glycoprotein, the uncharacterized multiple N-glycosylated human basigin. Detailed site-specific reference glycoprofiles of purified basigin were manually established using ion-trap CID-MS/MS and high-resolution Q-Exactive Orbitrap HCD-MS/MS of tryptic N-glycopeptides and released N-glycans. The micro- and macroheterogeneous basigin N-glycosylation was site-specifically glycoprofiled using Byonic with or without a background of complex peptides using Q-Exactive Orbitrap HCD-MS/MS. The automated glycoprofiling efficiencies were assessed against the site-specific reference glycoprofiles and target/decoy proteome databases. Within the limits of this single glycoprotein analysis, the search criteria and confidence thresholds (Byonic scores) recommended by the vendor provided high glycoprofiling accuracy and coverage (both >80%) and low peptide FDRs (<1%). The data complexity, search parameters including search space (proteome/glycome size), mass tolerance and peptide modifications, and confidence thresholds affected the automated glycoprofiling efficiency and analysis time. Correct identification of ambiguous peptide modifications (methionine oxidation/carbamidomethylation) whose mass differences coincide with several monosaccharide mass differences (Fuc/Hex/HexNAc) and of ambiguous isobaric (Hex1NeuAc1-R/Fuc1NeuGc1-R) or near-isobaric (NeuAc1-R/Fuc2-R) monosaccharide subcompositions remains challenging in automated glycoprofiling, arguing particular attention paid to N-glycopeptides displaying such "difficult-to-identify" features. This study provides valuable insights into the automated glycopeptide identification process, stimulating further developments in FDR-based glycoproteomics.

A software system for automated identification and retrieval of moth images based on wing attributes

Manually collecting, identifying, archiving and retrieving specimen images is an expensive and time-consuming work for entomologists. There is a clear need to introduce fast systems integrated with modern image processing and analysis algorithms to accelerate the process. In this paper, we describe the development of an automated moth species identification and retrieval system (SPIR) using computer vision and pattern recognition techniques. The core of the system is a probabilistic model that infers Semantically Related Visual (SRV) attributes from low-level visual features of moth images in the training set, where moth wings are segmented into information-rich patches from which the local features are extracted, and the SRV attributes are provided by human experts as ground-truth. For the large amount of unlabeled test images in the database or added into the database later on, an automated identification process is evoked to translate the detected salient regions of low-level visual features on the moth wings into meaningful semantic SRV attributes. We further propose a novel network analysis based approach to explore and utilize the co-occurrence patterns of SRV attributes as contextual cues to improve individual attribute detection accuracy. Working with a small set of labeled training images, the approach constructs a network with nodes representing the SRV attributes and weighted edges denoting the co-occurrence correlation. A fast modularity maximization algorithm is proposed to detect the co-occurrence patterns as communities in the network. A random walk process working on the discovered co-occurrence patterns is applied to refine the individual attribute detection results. The effectiveness of the proposed approach is evaluated in automated moth identification and attribute-based image retrieval. In addition, a novel image descriptor called SRV attribute signature is introduced to record the visual and semantic properties of an image and is used to compare image similarity. Experiments are performed on an existing entomology database to illustrate the capabilities of our proposed system. We observed that the system performance is improved by the SRV attribute representation and their co-occurrence patterns.

Sail-assisted motor vessels weather routing using a fuzzy logic model

In this study sail-assisted motor vessels weather routing is investigated to establish the most economical route by applying available information of the ship's behavior regarding the encountered sea-conditions. To derive the vessel’s fuel use on a route, a fuzzy logic model is constructed through an automated identification process. Only data collected from actual integrated bridge measurements systems is used. Fuzzy modeling is a framework providing a flexible and transparent mathematical structure to describe the physical relationships in a vessel's behavior. This consumption model is integrated into a determinist weather-routing optimization workflow based on a systematic meshing scheme of the sailing area. Pareto-optimization with a multi-objective genetic algorithm is used to maximize fuel economy in a limited or optimum time. The benefits of the developed decision helping tool in sail-assisted motor vessel routing are highlighted on a westbound north Transatlantic journey.

3D dental biometrics: Alignment and matching of dental casts for human identification

A 3D dental biometrics framework and a pose invariant dental identification (PIDI) technique are proposed for human identification in this study. As best as we can tell, this study is the first attempt at 3D dental biometrics. Using 3D overcomes a number of key hurdles that plague 2D methods in dental identification. 60 Postmortem (PM) samples and 200 Ante mortem (AM) samples taken from multi ethnic Asian groups (Chinese, Indian and Malay) are used in this study. The PIDI technique includes algorithms for feature extraction, feature description and correspondence. The proposed feature extraction algorithm can extract the salient points from the scanned model of dental cast. The proposed feature description and the correspondence algorithm have been tested and shown to be more robust to rigid transformations compared with the related work. Preliminary experimental result achieves 94% rank-1 accuracy in a human-assisted process, while in an automated identification process, the rank-1 accuracy decreases to 80%. In addition, the developed methodology, as it is also feasible to be applied to identifying severely corrupted dental, could promptly provide a potential candidate list in mass disasters before expert investigation. The high accuracy, fast retrieval speed and the facilitated identification process suggest that the developed 3D framework is more suitable for practical use in dental biometrics applications in the future. The limitations and future work are also presented. It could be used adjunctively with the traditional 2D X-ray radiograph identification scheme to improve the efficiency of current identification process.

Structural elucidation of low abundant metabolites in complex sample matrices

Identification of metabolites is a major challenge in biological studies and relies in principle on mass spectrometry (MS) and nuclear magnetic resonance (NMR) methods. The increased sensitivity and stability of both NMR and MS systems have made dereplication of complex biological samples feasible. Metabolic databases can be of help in the identification process. Nonetheless, there is still a lack of adequate spectral databases that contain high quality spectra, but new developments in this area will assist in the (semi-)automated identification process in the near future. Here, we discuss new developments for the structural elucidation of low abundant metabolites present in complex sample matrices. We describe how a recently developed combination of high resolution MS multistage fragmentation (MSn) and high resolution one dimensional (1D)-proton (1H)-NMR of liquid chromatography coupled to solid phase extraction (LC–SPE) purified metabolites can circumvent the need for isolating extensive amounts of the compounds of interest to elucidate their structures. The LC–MS–SPE–NMR hardware configuration in conjunction with high quality databases facilitates complete structural elucidation of metabolites even at sub-microgram levels of compound in crude extracts. However, progress is still required to optimally exploit the power of an integrated MS and NMR approach. Especially, there is a need to improve and expand both MSn and NMR spectral databases. Adequate and user-friendly software is required to assist in candidate selection based on the comparison of acquired MS and NMR spectral information with reference data. It is foreseen that these focal points will contribute to a better transfer and exploitation of structural information gained from diverse analytical platforms.

Deutocerebrum of the cockroach Blaberus craniifer Burm. Quantitative study and automated identification of the glomeruli.

The glomerular organization of the hemideutocerebrum is analyzed quantitatively, using only spatial position, in four individuals (eight hDTCs) after a visual identification of glomeruli on graphic reconstructions. In order to assess directly the invariance of the neuropil in an insect brain the following is done: (1) The position of each glomerulus is compared to the position A' it should occupy if the hDTCs were identical. It is shown that in 80 and 71% of the cases, respectively, intra- and interindividual comparisons in the studied glomerulus is the nearest to A'. (2) The actual position is equally compared to the theoretical location A" each glomerulus should occupy if its absolute position could be changed but not its relative position with respect to its neighbors. The calculation of A" is based on process (3). In 86 and 80% of the cases, respectively, it is found that the actual position is that which is nearest to A". (3) An automated identification process, based on absolute and relative locations, but completely independent of visual identification, is described. It allows the identification of 77 and 74% of glomeruli, respectively. These matchings are in 96 and 90% of the cases identical to the visual matchings. The location predictability of most glomeruli is discussed to show the existence, nature, and limits of the hemideutocerebral invariance.