Automation Algorithms Research Articles

A method for a priori estimation of best feasible DVH for organs-at-risk: Validation for head and neck VMAT planning.

Despite improvements in optimization and automation algorithms, the quality of radiation treatment plans still varies dramatically. A tool that allows a priori estimation of the best possible sparing (Feasibility DVH, or FDVH) of an organ at risk (OAR) in high-energy photon planning may help reduce plan quality variability by deriving patient-specific OAR goals prior to optimization. Such a tool may be useful for (a) meaningfully evaluating patient-specific plan quality and (b) supplying best theoretically achievable DVH goals, thus pushing the solution toward automatic Pareto optimality. This work introduces such a tool and validates it for clinical Head and Neck (HN) datasets. To compute FDVH, first the targets are assigned uniform prescription doses, with no reference to any particular beam arrangement. A benchmark 3D dose built outside the targets is estimated using a series of energy-specific dose spread calculations reflecting observed properties of radiation distribution in media. For the patient, the calculation is performed on the heterogeneous dataset, taking into account the high- (penumbra driven) and low- (PDD and scatter-driven) gradient dose spreading. The former is driven mostly by target dose and surface shape, while the latter adds the dependence on target volume. This benchmark dose is used to produce the "best possible sparing" FDVH for an OAR, and based on it, progressively more easily achievable FDVH curves can be estimated. Validation was performed using test cylindrical geometries as well as 10 clinical HN datasets. For HN, VMAT plans were prepared with objectives of covering the primary and the secondary (bilateral elective neck) PTVs while addressing only one OAR at a time, with the goal of maximum sparing. The OARs were each parotid, the larynx, and the inferior pharyngeal constrictor. The difference in mean OAR doses was computed for the achieved vs. FDVHs, and the shapes of those DVHs were compared by means of the Dice similarity coefficient (DSC). For all individually optimized HN OARs (N = 38), the average DSC between the planned DVHs and the FDVHs was 0.961 ± 0.018 (95% CI 0.955-0.967), with the corresponding average of mean OAR dose differences of 1.8 ± 5.8% (CI -0.1-3.6%). For realistic plans the achieved DVHs run no lower than the FDVHs, except when target coverage is compromised at the target/OAR interface. For the validation of VMAT plans, the OAR DVHs optimized one-at-a-time were similar in shape to and bound on the low side by the FDVHs, within the confines of planner's ability to precisely cover the target(s) with the prescription dose(s). The method is best suited for the OARs close to the target. This approach is fundamentally different from "knowledge-based planning" because it is (a) independent of the treatment plan and prior experience, and (b) it approximates, from nearly first principles, the lowest possible boundary of the OAR DVH, but not necessarily its actual shape in the presence of competing OAR sparing and target dose homogeneity objectives.

Performance of an automated algorithm to process artefacts for quantitative EEG analysis during a simultaneous driving simulator performance task

BackgroundArtefact removal from noisy EEG signals is cumbersome, and often requires manual intervention. We tested the performance of an automated method to detect and remove artefacts from EEG recorded during a driving simulation task. MethodsFive patients with obstructive sleep apnea (OSA) and five healthy controls were randomly selected from 17 participants undergoing a 40-h extended wakefulness study with 2-hourly 30-minute simulated driving tasks with simultaneous EEG. Two EEG recordings from each individual were studied. EEG data was first processed by independent component analysis (ICA). The accuracy of the automated algorithm (AA) to detect residual EEG artefact was evaluated against a reference-standard (RS) of visually identified artefact-contaminated epochs. EEG spectral power was calculated using 1) the RS method, 2) the AA, and 3) raw data without any artefact rejection (ICA only). ResultsThe algorithm showed good sensitivity (median: 83.9%), excellent specificity (91.1%), and high accuracy (87.0%) to detect noisy epochs. Cohen's κ indicated a substantial agreement between the two methods (0.72). EEG spectral power calculated using the RS and the AA did not differ significantly, while the power of the raw signal was significantly higher than those produced by any artefact rejection method. Increased EEG delta and theta power were significantly correlated with poorer driving performance. ConclusionsThese preliminary findings demonstrate an effective automated method to process EEG artefact recorded during driving simulation. This approach may facilitate the routine application of quantitative EEG analyses in future studies and identify new markers of impaired driving performance associated with sleep disorders.

Development and testing of a novel multiplex serodiagnostic assay for Zika and other arboviruses

Abstract Human immunoglobulin (IgM) antibody capture enzyme linked immunosorbent assay (MAC-ELISA) is recommended by US Centers for Disease Control (CDC) to detect the Zika Virus (ZIKV) infection in samples collected after few days of the onset of disease. However, the cross-reactivity of IgM and immunoglobulin G (IgG) antibodies to ZIKV with dengue virus (DENV), West Nile virus (WNV), yellow fever virus (YFV) and some other related flaviviruses poses a significant challenge for an accurate detection of ZIKV infection in a singleplex serological assay. To overcome these challenges we developed a novel multiplex serological assay that will simultaneously detect antibody response to ZIKV, other related flaviviruses and Chikungunya virus (CHIKV). Various recombinant arboviral antigens were coupled to optically-coded microspheres from Luminex Corporation. This fluorescent labeled microsphere assay was used to differentiate between recent, past arbovirus infections, or co-infections that may occur in endemic regions. We used plasma samples from non-human primates (NHPs) prior to and after ZIKV infection for longitudinal assessment of IgM and IgG antibody responses for evaluation of this method. 37 blood samples from 5 different animals challenged with either African strain or Asian lineage strain of ZIKV were analyzed for antibody responses to multiple antigens included in this test. We developed a detection algorithm for automation of IgM result analysis to differentiate ZIKV IgM response from other arboviruses. Thus this multiplex arbovirus assay has great promise for testing human samples for detecting ZIKV infection.

Application of microelectronics CAD tools to synthetic biology

Synthetic biology is an emerging science that aims to create new biological functions that do not exist in nature, based on the knowledge acquired in life science over the last century. Since the beginning of this century, several projects in synthetic biology have emerged. The complexity of the developed artificial bio-functions is relatively low so that empirical design methods could be used for the design process. Nevertheless, with the increasing complexity of biological circuits, this is no longer the case and a large number of computer aided design softwares have been developed in the past few years. These tools include languages for the behavioral description and the mathematical modelling of biological systems, simulators at different levels of abstraction, libraries of biological devices and circuit design automation algorithms. All of these tools already exist in other fields of engineering sciences, particularly in microelectronics. This is the approach that is put forward in this paper.

Derivation and validation of an automated electronic search algorithm to identify patients at risk for obstructive sleep apnea

Background. Automated extraction of data from electronic health records has allowed high-quality retrospective analyses of large cohorts. Objectives. To derive and validate an au-tomated electronic search algorithm to identify surgical patients with a diagnosis of or at high risk for obstructive sleep ap-nea (OSA).Methods. From 558 adult patients who underwent surgery from January 1, 2011, through December 31, 2015, we construct-ed a derivation cohort of 100 subjects se-lected using the initial search algorithm to have equal numbers of patients with high and low likelihood of having OSA. This algorithm conducted a free-text electronic search of patient diagnoses and interro-gated results of a preoperative checklist that specifically queried patients regarding OSA history and screened for OSA risk us-ing Flemons criteria. The derivation cohort was then manually reviewed to identify patients with OSA risk and results were used to refine the algorithm. Second, the algorithm was validated with the other 458 patients (the validation cohort). The sensi-tivity and specificity were compared again with manual chart review of the respective group.Results. In the derivation cohort, the auto-mated electronic algorithm achieved a sen-sitivity of 98.2% and a specificity of 100.0% compared with the manual review. In the validation cohort, sensitivity was 100.0% and specificity was 98.4% in this compari-son.Conclusion. An automated electronic search algorithm was developed that interrogates electronic health records to identi-fy, with a high degree of accuracy, surgical patients with a diagnosis of or at high risk for OSA.

Reconfiguration on nanocrossbar using material implication

Reconfigurable architectures (FPGA) with embedded memory elements face problems in retaining data for longer duration due to leakage current as it becomes dominant in nanometer devices in conventional technologies. Also, LUT-based designs consume more area, are slow in processing data and dissipate more power because of complex interconnection network. Memristor, a new nonvolatile memory element, can be used to overcome these limitations. In this paper, we propose an implication-NOR logic-gate-based FPGA architecture using memristors for implementation of logic functions and with embedded memory for storing data. The automation algorithm for the same is presented.

Stochastic simulation of electron-hole recombination in two-dimensional and three-dimensional inhomogeneous semiconductors. Part I. Stochastic model and algorithms

This paper describes the stochastic models of electron-hole recombination in inhomogeneous semiconductors in two-dimensional and three-dimensional cases, which were developed on the basis of discrete (cellular automation) and continuous (Monte Carlo method) approaches. The mathematical model of electron-hole recombination, constructed on the basis of a system of spatially inhomogeneous nonlinear integro-differential Smoluchowski equations, is illustrated. The continuous algorithm of the Monte Carlo method and the discrete cellular automation algorithm used for the simulation of particle recombination in semiconductors are shown.

Editorial: “One Robot is Robotics, Ten Robots is Automation”

Automation has come of age. As Raja Chatila aptly summarized in the quote above, automation addresses the challenges that arise when robots scale beyond proof-of-concept. Germany approved a $5B sale of Kuka to Midea Corp in China to provide robots for assembly automation. General Electric Corporation is now focusing on automation algorithms and data analytics and predicts this will be a $225 billion market within five years. These developments build on ongoing research in Big Data, Cloud Computing, Deep Learning, Open-Source Software, and Government/Industry initiatives, such as The “Internet of Things,” “Smarter Planet,” “Industrial Internet,” “Industrie 4.0,” and “Made in China 2025.” Automation is playing an increasingly central role in the global economy and in our daily lives.

Autonomous Flight Envelope Estimation for Loss-of-Control Prevention

A nonlinear aircraft dynamics modeling and system identification approach is formulated and used to derive a rapid, convex optimization-based algorithm for the estimation of aerodynamic force coefficients from noisy sensor data, with uncertainty quantification. Furthermore, with the aerodynamic force coefficients identified, a computationally fast method for generating the corresponding aircraft trim envelope given safe limits on achievable thrust and angle of attack is presented. This unified approach achieves the online Bayesian inference of the aircraft aerodynamic performance capability while running in the background as the aircraft is controlled independently by the pilot or automation system. The resulting information is readily incorporated into the determination of the extended safe maneuvering envelope, pilot displays, and automation algorithms for flight planning, trajectory generation, and guidance: all to help maintain safe aircraft operations under both nominal and off-nominal flight conditions.

Comparison of irrigation automation algorithms for drip-irrigated apple trees

Seven irrigation scheduling algorithms and an automatic control system along with a wireless network of soil, thermal and weather sensors were developed and assessed in Prosser, WA in the growing season of 2013. The system was comprised of six wireless sensor and valve actuating nodes installed across an apple orchard, a central base station made up of a transceiver connected to a laptop, and a graphical user interface (GUI). The irrigation algorithms/treatments included the time-temperature threshold (TTT), crop water stress index with dynamic threshold (CWSI), soil-based using granular matrix sensors (SOIL), weather-based using a temperature-only-based evapotranspiration (ET) model and soil water balance (WB), a combination of SOIL and WB (SL+WB), a conventional irrigation practice used in the region (CNTRL), and soil-based using a neutron probe (NP) as benchmark. Different treatments were compared based on the total irrigation water (It) applied during the season. They were also compared based on simplicity and expense for a grower to implement. Soil water content (θs) and stem water potential (ψstem) were monitored in a number of treatment plots. The total applied water for CNTRL was significantly higher than all other treatments (p<0.001). The thermal-based TTT and CWSI treatments applied the same amount of water as NP and WB (p<0.001). CWSI and TTT substantially reduced water applied (70%) while maintaining ψstem within the non-stressed range. In addition, θs in the treatment plots of TTT and CWSI did not exceed the maximum allowed deficit recommended for apple trees (MAD of 50%) showing a strong agreement with NP. The SOIL and SL+WB treatments resulted in tangible under-irrigation as leaf drop, decreased leaf turgidity, growth reduction and abnormally small fruits were seen. Among all the strategies, WB seemed to bear the characteristics of being economical, easy to implement and fairly accurate. Our preliminary results also support the use of wireless sensor network for automatic irrigation management of drip-irrigated apple trees.

On the effectiveness of performance-based adaptive automation

ABSTRACTThis article examines the effectiveness of different forms of performance-based adaptive automation (PBAA). Using data from three experiments (N = 10, N = 38, N = 40), different models of algorithm design were compared for their effectiveness in driving PBAA. The following components were varied: type of task (i.e. primary or secondary tasks), baseline of performance data (e.g. moving average), and triggering criterion (i.e. level of deviation from standard performance). The data were generated by operators working with a computer-based simulation of a process control environment. The results showed that none of the models enjoyed a convincing level of effectiveness. The automation algorithms generally achieved higher levels of miss prevention than false alarm prevention. Surprisingly, primary task performance was generally better at driving PBAA than secondary task performance. The results suggest that it may be difficult to design an effective algorithm of PBAA if the work environment is highly complex.

BIM을 활용한 가설물 계획 및 안전 관리

The entire construction safety is significantly influenced by proper uses of temporary structures. However, in current practices, temporary structures are used without sufficient planning and analysis on their impact on safety. Consequently, problems in worker safety and loss of productivity are frequently caused related to temporary structures. This paper introduces an approach that uses Building Information Modeling (BIM) to automatically create temporary structures as part of construction plans and identifies potential safety hazards related to the temporary structures. In this study, the type of temporary structure is limited to scaffolding. Automation algorithms were developed and applied to (1) analyze daily construction site conditions (2) create required scaffolding objects, and (3) identify potential safety hazards related to scaffolding. A case study using a real-world construction project demonstrated that scaffolding objects were properly created based on user-input and potential safety hazards were successfully identified without human intervention.

선체 청소로봇 자동화를 위한 광 변위센서 기반의 위치추정 방법

This paper presents the new position estimation method which contains the optical displacement sensor and the dead reckoning based position estimation algorithm for automation of hull cleaning robot. To evaluate feasibility of the proposed position estimation method on the hull cleaning robot, it was applied on the small scale robot model which has an identical drive method with the hull cleaning robot and then a set of the position estimation experiments were performed. The experimental results of the position estimation demonstrate that the estimated results with the optical displacement sensors is more accurate than used rotary encoder method. In addition, it continuously calculated the robot position quite close to the real robot driving path. In a follow-up study, the proposed position estimation method will be complemented and exploited on the actual hull cleaning robot by adding additional sensor modules that correct measurement errors.

Generation of Test Case using Automation in Software Systems – A Review

Background: The main objective of this paper is to review the literature about automatic test case generation. Test Automation methods involves the following major factors for generating test case such as Unified Modelling Language (UML) diagrams, Testing types like Black Box Testing, White Box Testing, Testing techniques like model based, search based and symbolic execution, coverage criteria includes code based, fault based and function based, UML and Automation Testing tools and algorithms. Suggestions and Conclusion: Test Case Generation (TCG) can improve the performance of the automation in an effective way and some open research problems have been discussed for bio-inspired algorithms. This paper presents a systematic survey about Test Automation by optimisation search techniques, by novel techniques and various other approaches. The optimisation search technique provides the best solution of the problem definition. Hence test automation using optimisation approach gives an efficient test suite for the given problem model. Test case Generation are applied for various software systems, hardware systems, embedded systems, real time systems, nuclear safety systems.

Guest Editorial Special Section on the 2014 Workshop on the Algorithmic Foundations of Robotics

The papers in this special section were presented at the 11th Workshop on the Algorithmic Foundation of Robotics (WAFR), which was held at Bogazici University, Istanbul, Turkey, during August 3–5, 2014. WAFR is a prestigious biennial single-track workshop on algorithms for robotics and automation. It features cutting-edge research in a broad range of planning problems (such as manipulation, motion, path, multi-robot, and kynodynamic planning), geometric and topological computation, and novel applications like surgical planning, active sensing, and informative path planning.

Segment and fit thresholding: a new method for image analysis applied to microarray and immunofluorescence data.

Experiments involving the high-throughput quantification of image data require algorithms for automation. A challenge in the development of such algorithms is to properly interpret signals over a broad range of image characteristics, without the need for manual adjustment of parameters. Here we present a new approach for locating signals in image data, called Segment and Fit Thresholding (SFT). The method assesses statistical characteristics of small segments of the image and determines the best-fit trends between the statistics. Based on the relationships, SFT identifies segments belonging to background regions; analyzes the background to determine optimal thresholds; and analyzes all segments to identify signal pixels. We optimized the initial settings for locating background and signal in antibody microarray and immunofluorescence data and found that SFT performed well over multiple, diverse image characteristics without readjustment of settings. When used for the automated analysis of multicolor, tissue-microarray images, SFT correctly found the overlap of markers with known subcellular localization, and it performed better than a fixed threshold and Otsu's method for selected images. SFT promises to advance the goal of full automation in image analysis.

Ещё раз об автоматической расшифровке рентгеновских снимков сварных швов

Introduction. This article is dedicated to a possible approach to automatic inspection of welded joints X-Ray images. This problem is very urgent but there is no established practice of the automated X-Ray images inspection and image objects recognition. The purpose of the article was to highlight the tasks included in the X-Ray interpretation process that can be automated, and to offer possible solutions. &#x0D; Method. Analysis and interpretation of images were made using &amp;#34;X-Vizor&amp;#34; software by “Newcom-NDT”.&#x0D; Results. Studies have shown that the straight and elliptical seam areas could be recognized automatically. It provides the possibility for a signal-noise ratio to be automatically measured. Wire image quality indicators and grooving gages also could be recognized automatically in approximately 80% cases. So it is possible to automatically calculate the sensitivity of the inspection. It is also achievable to automatically determine the basic spatial resolution using duplex wire image quality indicator. But the task of automation of defect recognition is still not solved. The possible alternative was offered. It is semi automation of defects recognition and analysis. This procedure needs the human to take part in image interpretation process. &#x0D; Conclusion. The conclusion is that the total automation of digital X-Ray image interpretation of welded joints is now unavailable. Nevertheless using automation algorithms in all parts of interpretation process where it is possible can highly increase the performance of the inspection and its reliability.

Autonomous Operation in Surgical Robotics

The article focuses on developing an algorithm for automation based on stereo computer vision and dynamic registration in a surgical robotic context. The performance of the algorithm was further tested experimentally utilizing the block transfer task which corresponds to tissue manipulation as designed by Fundamentals of Laparoscopic Surgery (FLS). The surgical robotics field as a whole progresses towards the reduction of invasiveness limiting the trauma at the periphery of the surgical site and increase of semi-autonomous operation while positioning the surgeon as a decision maker rather than as an operator. The autonomous FLS task is implemented successfully and tested experimentally with the Raven II surgical robot system. The data indicate that the autonomous operational mode has better overall performance and limited tool-environment interaction compared with the human teleoperation mode. Surgeon’s intention may also be extracted from a database that may lead to seamless switching between the human operator and the autonomous system and in that sense, it may allow the autonomous algorithm to cope with more complex surgical environments.

AUTOMATIC WATER OBJECTS CLASSIFICATION AND NATURAL WATER QUALITY ASSESSMENT

Assessment of water quality and classification of water object plays significant role in an environmental and ecology study. Water quality evaluation by hydrochemical parameters is fairly difficult and required a long period of time. Automatic expert system was created to solve this problem. Automatization of objects classification and quality assessment for humus zone based on Karelian water bodies research data are presented in this study. Automation algorithms of the surface water geochemical classification based on the principal chemical transactions was obtained during research. Classification based on implicit scaling data by classification parameter. Alkalinity, pH, huminity, Fecom and total phosphorous were chosen as the main classification parameters. For classification by alkalinity were used alkalinity and pH, for huminity classification were used coefficient of huminity – Hum? Color OD?C Mn and Fecom, for trophic state were used huminity class and total phosphorous concentration. The water objects distribution by huminity, alkalinity and trophic state was obtained and basic geochemical classes were picked out. Natural water quality was assessed as combination of geochemical classes. Results of research presented as maps and trends of geochemical classes and natural water quality distribution over the area of Republic of Karelia.

A Survey on Unsupervised Machine Learning Algorithms for Automation, Classification and Maintenance

The paper is comprehensive survey of methodologies and techniques used for Unsupervised Machine Learning that are used for learn complex, highly non-linear models with millions parameters to used large amount of unlabeled data. Deep belief networks (DBNs) and sparse coding are the two well known techniques of unsupervised learning models. Data clustering distinguishes by the absence of category information. Basically structure in data is finding in clustering and it has long history in scientific field .K-means is the most popular and simple clustering algorithm. This Algorithm was published in 1955. Hierarchical matching pursuit (HMP) for RGB-D data is discussed. Sparse coding learns hierarchical feature representations from raw RGB-D data in an unsupervised way by using hierarchical matching pursuit. The formal study of learning systems is deduced from Machine learning; which is a field of research. It has found to be highly interdisciplinary field which acquires and constructs upon ideas from statistics, computer science (engineering), optimization theory, and numerous other disciplines of science and mathematics.