Search results for: forecasting accuracy

Authors: Vincent Schlageter, Maroua Mestiri, Florian Denzinger, Hugo Raetzo, Michel Demierre

Abstract:

Precise landslide monitoring with differential global navigation satellite system (GNSS) is well known, but technical or economic reasons limit its application by geotechnical companies. This study demonstrates the reliability and the usefulness of Geomon (Infrasurvey Sàrl, Switzerland), a stand-alone and cost-effective rover network. The system permits deploying up to 15 rovers, plus one reference station for differential GNSS. A dedicated radio communication links all the modules to a base station, where an embedded computer automatically provides all the relative positions (L1 phase, open-source RTKLib software) and populates an Internet server. Each measure also contains information from an internal inclinometer, battery level, and position quality indices. Contrary to standard GNSS survey systems, which suffer from a limited number of beacons that must be placed in areas with good GSM signal, Geomon offers greater flexibility and permits a real overview of the whole landslide with good spatial resolution. Each module is powered with solar panels, ensuring autonomous long-term recordings. In this study, we have tested the system on several sites in the Swiss mountains, setting up to 7 rovers per site, for an 18 month-long survey. The aim was to assess the robustness and the accuracy of the system in different environmental conditions. In one case, we ran forced blind tests (vertical movements of a given amplitude) and compared various session parameters (duration from 10 to 90 minutes). Then the other cases were a survey of real landslides sites using fixed optimized parameters. Sub centimetric-accuracy with few outliers was obtained using the best parameters (session duration of 60 minutes, baseline 1 km or less), with the noise level on the horizontal component half that of the vertical one. The performance (percent of aborting solutions, outliers) was reduced with sessions shorter than 30 minutes. The environment also had a strong influence on the percent of aborting solutions (ambiguity search problem), due to multiple reflections or satellites obstructed by trees and mountains. The length of the baseline (distance reference-rover, single baseline processing) reduced the accuracy above 1 km but had no significant effect below this limit. In critical weather conditions, the system’s robustness was limited: snow, avalanche, and frost-covered some rovers, including the antenna and vertically oriented solar panels, leading to data interruption; and strong wind damaged a reference station. The possibility of changing the sessions’ parameters remotely was very useful. In conclusion, the rover network tested provided the foreseen sub-centimetric-accuracy while providing a dense spatial resolution landslide survey. The ease of implementation and the fully automatic long-term survey were timesaving. Performance strongly depends on surrounding conditions, but short pre-measures should allow moving a rover to a better final placement. The system offers a promising hazard mitigation technique. Improvements could include data post-processing for alerts and automatic modification of the duration and numbers of sessions based on battery level and rover displacement velocity.

Keywords: GNSS, GSM, landslide, long-term, network, solar, spatial resolution, sub-centimeter.

Procedia PDF Downloads 103

Authors: Hongbo Zhang, Xinlu Tang, Jiangwei Li, Chi Yan

Abstract:

Home zone parking pilot (HPP) is a fast-growing segment in low-speed autonomous driving applications. It requires the car automatically cruise around a parking lot and park itself in a range of up to 100 meters inside a recurrent home/office parking lot, which requires precise parking lot mapping and localization solution. Although Lidar is ideal for SLAM, the car OEMs favor a low-cost fish-eye camera based visual SLAM approach. Recent approaches have employed segmentation models to extract semantic features and improve mapping accuracy, but these AI models are memory unfriendly and computationally expensive, making deploying on embedded ADAS systems difficult. To address this issue, we proposed a new method that utilizes object detection models to extract robust and accurate parking lot features. The proposed method could reduce computational costs while maintaining high accuracy. Once combined with vehicles’ wheel-pulse information, the system could construct maps and locate the vehicle in real-time. This article will discuss in detail (1) the fish-eye based Around View Monitoring (AVM) with transparent chassis images as the inputs, (2) an Object Detection (OD) based feature point extraction algorithm to generate point cloud, (3) a low computational parking lot mapping algorithm and (4) the real-time localization algorithm. At last, we will demonstrate the experiment results with an embedded ADAS system installed on a real car in the underground parking lot.

Keywords: ADAS, home zone parking pilot, object detection, visual SLAM

Procedia PDF Downloads 57

Authors: Thanh Van Hoang, Tien Yin Chou, Yao Min Fang, Yi Min Huang, Xuan Linh Nguyen

Abstract:

Reliable information on the spatial distribution of annual rainfall and temperature is essential in research projects relating to urban and regional planning. This research presents results of a classification of temperature and rainfall in the Red River Delta of northern Vietnam based on measurements from seven meteorological stations (Ha Nam, Hung Yen, Lang, Nam Dinh, Ninh Binh, Phu Lien, Thai Binh) in the river basin over a thirty-years period from 1982-2011. The average accumulated rainfall trends in the delta are analysed and form the basis of research essential to weather and climate forecasting. This study employs interpolation based on the Kriging Method for daily rainfall (min and max) and daily temperature (min and max) in order to improve the understanding of sources of variation and uncertainly in these important meteorological parameters. To the Kriging method, the results will show the different models and the different parameters based on the various precipitation series. The results provide a useful reference to assist decision makers in developing smart agriculture strategies for the Red River Delta in Vietnam.

Keywords: spatial interpolation method, ArcGIS, temperature variability, rainfall variability, Red River Delta, Vietnam

Procedia PDF Downloads 316

Authors: Zhaopeng Zhu, Xianzhi Song, Gensheng Li, Shuo Zhu, Shiming Duan, Xuezhe Yao

Abstract:

Accurate calculation of wellbore pressure is of great significance to prevent wellbore risk during drilling. The traditional mechanism model needs a lot of iterative solving procedures in the calculation process, which reduces the calculation efficiency and is difficult to meet the demand of dynamic control of wellbore pressure. In recent years, many scholars have introduced artificial intelligence algorithms into wellbore pressure calculation, which significantly improves the calculation efficiency and accuracy of wellbore pressure. However, due to the ‘black box’ property of intelligent algorithm, the existing intelligent calculation model of wellbore pressure is difficult to play a role outside the scope of training data and overreacts to data noise, often resulting in abnormal calculation results. In this study, the multi-phase flow mechanism is embedded into the objective function of the neural network model as a constraint condition, and an intelligent prediction model of wellbore pressure under the constraint condition is established based on more than 400,000 sets of pressure measurement while drilling (MPD) data. The constraint of the multi-phase flow mechanism makes the prediction results of the neural network model more consistent with the distribution law of wellbore pressure, which overcomes the black-box attribute of the neural network model to some extent. The main performance is that the accuracy of the independent test data set is further improved, and the abnormal calculation values basically disappear. This method is a prediction method driven by MPD data and multi-phase flow mechanism, and it is the main way to predict wellbore pressure accurately and efficiently in the future.

Keywords: multiphase flow mechanism, pressure while drilling data, wellbore pressure, mechanism constraints, combined drive

Procedia PDF Downloads 162

Authors: A. Dinelka Panagoda, Bathiya Bandara, Chamod Wijetunga, Chathura Malinda, Lakmal Rupasinghe, Chethana Liyanapathirana

Abstract:

This research takes us forward with the concepts of Federated Learning and Software-Defined Networking (SDN) to introduce an efficient malware detection technique and provide a mitigation mechanism to give birth to a resilient and automated healthcare sector network system by also adding the feature of extended privacy preservation. Due to the daily transformation of new malware attacks on hospital Integrated Clinical Environment (ICEs), the healthcare industry is at an undefinable peak of never knowing its continuity direction. The state of blindness by the array of indispensable opportunities that new medical device inventions and their connected coordination offer daily, a factor that should be focused driven is not yet entirely understood by most healthcare operators and patients. This solution has the involvement of four clients in the form of hospital networks to build up the federated learning experimentation architectural structure with different geographical participation to reach the most reasonable accuracy rate with privacy preservation. While the logistic regression with cross-entropy conveys the detection, SDN comes in handy in the second half of the research to stack up the initial development phases of the system with malware mitigation based on policy implementation. The overall evaluation sums up with a system that proves the accuracy with the added privacy. It is no longer needed to continue with traditional centralized systems that offer almost everything but not privacy.

Keywords: software-defined network, federated learning, privacy, integrated clinical environment, decentralized learning, malware detection, malware mitigation

Procedia PDF Downloads 163

Authors: Khanh To Duc, Monica Chiogna, Gianfranco Adimari

Abstract:

With three diagnostic categories, assessment of the performance of diagnostic tests is achieved by the analysis of the receiver operating characteristic (ROC) surface, which generalizes the ROC curve for binary diagnostic outcomes. The volume under the ROC surface (VUS) is a summary index usually employed for measuring the overall diagnostic accuracy. When the true disease status can be exactly assessed by means of a gold standard (GS) test, unbiased nonparametric estimators of the ROC surface and VUS are easily obtained. In practice, unfortunately, disease status verification via the GS test could be unavailable for all study subjects, due to the expensiveness or invasiveness of the GS test. Thus, often only a subset of patients undergoes disease verification. Statistical evaluations of diagnostic accuracy based only on data from subjects with verified disease status are typically biased. This bias is known as verification bias. Here, we consider the problem of correcting for verification bias when continuous diagnostic tests for three-class disease status are considered. We assume that selection for disease verification does not depend on disease status, given test results and other observed covariates, i.e., we assume that the true disease status, when missing, is missing at random. Under this assumption, we discuss several solutions for ROC surface analysis based on imputation and re-weighting methods. In particular, verification bias-corrected estimators of the ROC surface and of VUS are proposed, namely, full imputation, mean score imputation, inverse probability weighting and semiparametric efficient estimators. Consistency and asymptotic normality of the proposed estimators are established, and their finite sample behavior is investigated by means of Monte Carlo simulation studies. Two illustrations using real datasets are also given.

Keywords: imputation, missing at random, inverse probability weighting, ROC surface analysis

Procedia PDF Downloads 403

Authors: Ajibola Isola, Shattri Mansor, Ojogbane Sani, Olugbemi Tope

Abstract:

The cadastral map is the rationale behind city management planning and development. For years, cadastral maps have been produced by ground and photogrammetry platforms. Recent evolution in photogrammetry and remote sensing sensors ignites the use of Unmanned Aerial Vehicle systems (UAVs) for cadastral mapping. Despite the time-saving and multi-dimensional cost-effectiveness of the UAV platform, issues related to cadastral map accuracy are a hindrance to the wide applicability of UAVs' cadastral mapping. This study aims to present an approach leading to the generation and assessing the credibility of UAV cadastral mapping. Different sets of Red, Green, and Blue (RGB) photos were obtained from the Tarot 680-hexacopter UAV platform flown over the Universiti Putra Malaysia campus sports complex at an altitude range of 70 m, 100 m, and 250. Before flying the UAV, twenty-eight ground control points were evenly established in the study area with a real-time kinematic differential global positioning system. The second phase of the study utilizes an image-matching algorithm for photos alignment wherein camera calibration parameters and ten of the established ground control points were used for estimating the inner, relative, and absolute orientations of the photos. The resulting orthoimages are exported to ArcGIS software for digitization. Visual, tabular, and graphical assessments of the resulting cadastral maps showed a different level of accuracy. The results of the study show a gradual approach for generating UAV cadastral mapping and that the cadastral map acquired at 70 m altitude produced better results.

Keywords: aerial mapping, orthomosaic, cadastral map, flying altitude, image processing

Procedia PDF Downloads 66

Authors: Shoaib Yousaf

Abstract:

The main purpose of this research is to the empirical investigation of the bullwhip effect under sensitivity analysis in the two-tier supply chain. The simulation modeling technique has been applied in this research as a research methodology to see the sensitivity analysis of the bullwhip effect in the rice industry of Pakistan. The research comprises two case studies that have been chosen as a sample. The results of this research have confirmed that reduction in production delay reduces the bullwhip effect, which conforms to the time compressing paradigm and the significance of the reduction in production delay to lessen demand amplification. The result of this research also indicates that by increasing the value of time to adjust inventory decreases the bullwhip effect. Furthermore, by decreasing the value of alpha increases the damping effect of the exponential smoother, it is not surprising that it also reduces the bullwhip effect. Moreover, by reducing the value of time to work in progress also reduces the bullwhip effect. This research will help practitioners and operation managers to reduces the major costs of their products in three ways. They can reduce their i) inventory levels, ii) better utilize their capacity and iii) improve their forecasting techniques. However, this study is based on two tier supply chain, while in reality the supply chain has got many tiers. Hence, future work will be extended across more than two-tier supply chains.

Keywords: bullwhip effect, rice industry, supply chain dynamics, simulation, sensitivity analysis

Procedia PDF Downloads 130

Authors: Richard G. Carranza, Juan Ospina

Abstract:

The fin efficiency for a helical fin with a fixed fin tip (or arbitrary) temperature boundary condition is presented. Firstly, the temperature profile throughout the fin is determined via an energy balance around the fin itself. Secondly, the fin efficiency is formulated by integrating across the entire surface of the helical fin. An analytical expression for the fin efficiency is presented and compared with the literature for accuracy.

Keywords: efficiency, fin, heat, helical, transfer

Procedia PDF Downloads 668

Authors: Hu Zhenxing, Gao Jianxin

Abstract:

Stereo-based digital image correlation (also referred to as three-dimensional (3D) digital image correlation (DIC)) is a technique for both 3D shape and surface deformation measurement of a component, which has found increasing applications in academia and industries. The accuracy of the reconstructed coordinate depends on many factors such as configuration of the setup, stereo-matching, distortion, etc. Most of these factors have been investigated in literature. For instance, the configuration of a binocular vision system determines the systematic errors. The stereo-matching errors depend on the speckle quality and the matching algorithm, which can only be controlled in a limited range. And the distortion is non-linear particularly in a complex imaging acquisition system. Thus, the distortion correction should be carefully considered. Moreover, the distortion function is difficult to formulate in a complex imaging acquisition system using conventional models in such cases where microscopes and other complex lenses are involved. The errors of the distortion correction will propagate to the reconstructed 3D coordinates. To address the problem, an accurate mapping method based on 2D B-spline functions is proposed in this study. The mapping functions are used to convert the distorted coordinates into an ideal plane without distortions. This approach is suitable for any image acquisition distortion models. It is used as a prior process to convert the distorted coordinate to an ideal position, which enables the camera to conform to the pin-hole model. A procedure of this approach is presented for stereo-based DIC. Using 3D speckle image generation, numerical simulations were carried out to compare the accuracy of both the conventional method and the proposed approach.

Keywords: distortion, stereo-based digital image correlation, b-spline, 3D, 2D

Procedia PDF Downloads 486

Authors: Mehrnaz Mostafavi

Abstract:

Recent advances in single-molecule protein identification (ID) and quantification techniques are poised to revolutionize proteomics, enabling researchers to delve into single-cell proteomics and identify low-abundance proteins crucial for biomedical and clinical research. This paper introduces a different approach to single-molecule protein ID and quantification using tri-color amino acid tags and a plasmonic nanopore device. A comprehensive simulator incorporating various physical phenomena was designed to predict and model the device's behavior under diverse experimental conditions, providing insights into its feasibility and limitations. The study employs a whole-proteome single-molecule identification algorithm based on convolutional neural networks, achieving high accuracies (>90%), particularly in challenging conditions (95–97%). To address potential challenges in clinical samples, where post-translational modifications affecting labeling efficiency, the paper evaluates protein identification accuracy under partial labeling conditions. Solid-state nanopores, capable of processing tens of individual proteins per second, are explored as a platform for this method. Unlike techniques relying solely on ion-current measurements, this approach enables parallel readout using high-density nanopore arrays and multi-pixel single-photon sensors. Convolutional neural networks contribute to the method's versatility and robustness, simplifying calibration procedures and potentially allowing protein ID based on partial reads. The study also discusses the efficacy of the approach in real experimental conditions, resolving functionally similar proteins. The theoretical analysis, protein labeler program, finite difference time domain calculation of plasmonic fields, and simulation of nanopore-based optical sensing are detailed in the methods section. The study anticipates further exploration of temporal distributions of protein translocation dwell-times and the impact on convolutional neural network identification accuracy. Overall, the research presents a promising avenue for advancing single-molecule protein identification and quantification with broad applications in proteomics research. The contributions made in methodology, accuracy, robustness, and technological exploration collectively position this work at the forefront of transformative developments in the field.

Keywords: nano proteomics, nanopore-based optical sensing, deep learning, artificial intelligence

Procedia PDF Downloads 61

Authors: Asmamaw Yehun

Abstract:

The name “TANA” is one of International Geodetic Service (IGS) Global Positioning System (GPS) station which is found in Bahir Dar University in Institute of Land Administration. The station name taken from one of big Lakes in Africa ,Lake Tana. The Institute of Land Administration (ILA) is part of Bahir Dar University, located in the capital of the Amhara National Regional State, Bahir Dar. The institute is the first of its kind in East Africa. The station is installed by cooperation of ILA and Sweden International Development Agency (SIDA) fund support. The Continues Operating Reference Station (CORS) is a network of stations that provide global satellite system navigation data to help three dimensional positioning, meteorology, space, weather, and geophysical applications throughout the globe. TANA station was as CORS since 2013 and sites are independently owned and operated by governments, research and education facilities and others. The data collected by the reference station is downloadable through Internet for post processing purpose by interested parties who carry out GNSS measurements and want to achieve a higher accuracy. We made a first observation on TANA, monitor stations on May 29th 2013. We used Leica 1200 receivers and AX1202GG antennas and made observations from 11:30 until 15:20 for about 3h 50minutes. Processing of data was done in an automatic post processing service CSRS-PPP by Natural Resources Canada (NRCan) . Post processing was done June 27th 2013 so precise ephemeris was used 30 days after observation. We found Latitude (ITRF08): 11 34 08.6573 (dms) / 0.008 (m), Longitude (ITRF08): 37 19 44.7811 (dms) / 0.018 (m) and Ellipsoidal Height (ITRF08): 1850.958 (m) / 0.037 (m). We were compared this result with GAMIT/GLOBK processed data and it was very closed and accurate. TANA station is one of the second IGS station for Ethiopia since 2015 up to now. It provides data for any civilian users, researchers, governmental and nongovernmental users. TANA station is installed with very advanced choke ring antenna and GR25 Leica receiver and also the site is very good for satellite accessibility. In order to test hydrostatic and wet zenith delay for positional data quality, we used GAMIT/GLOBK and we found that TANA station is the most accurate IGS station in East Africa. Due to lower tropospheric zenith and ionospheric delay, TANA and ADIS IGS stations has 2 and 1.9 meters 3D positional accuracy respectively.

Keywords: atmosphere, GNSS, neutral atmosphere, precipitable water vapour

Procedia PDF Downloads 56

Authors: Stefano M. Spagocci

Abstract:

The efficiency of photovoltaic panels can be calculated with such software packages as RETScreen that allow design engineers to take financial as well as technical considerations into account. RETScreen is interfaced with meteorological databases, so that efficiency calculations can be realistically carried out. The author has recently contributed to the development of solar modules with accumulation capability and an embedded water purifier, aimed at off-grid users such as users in developing countries. The software packages examined do not allow to take ancillary equipment into account, hence the decision to implement a technical and financial model of the system. The author realized that, rather than re-implementing the quite sophisticated model of RETScreen - a mathematical description of which is anyway not publicly available - it was possible to drastically simplify it, including the meteorological factors which, in RETScreen, are presented in a numerical form. The day-by-day efficiency of a photovoltaic solar panel was parametrized by the product of factors expressing, respectively, daytime duration, solar right ascension motion, solar declination motion, cloudiness, temperature. For the sun-motion-dependent factors, positional astronomy formulae, simplified by the author, were employed. Meteorology-dependent factors were fitted by simple trigonometric functions, employing numerical data supplied by RETScreen. The accuracy of our model was tested by comparing it to the predictions of RETScreen; the accuracy obtained was 11%. In conclusion, our study resulted in a model that can be easily implemented in a spreadsheet - thus being easily manageable by non-specialist personnel - or in more sophisticated software packages. The model was used in a number of design exercises, concerning photovoltaic solar panels and ancillary equipment like the above-mentioned water purifier.

Keywords: clean energy, energy engineering, mathematical modelling, photovoltaic panels, solar energy

Procedia PDF Downloads 37

Authors: S. I. Usenko, V. N. Golubeva, I. A. Konopkina, I. V. Astakhova, O. V. Vakhnina, A. A. Korableva, A. A. Kalinina, K. B. Zhogova

Abstract:

Gold can be determined in natural objects and manufactured articles of different origin. The up-to-date status of research and problems of high gold level determination in alloys and manufactured articles are described in detail in the literature. No less important is the task of this metal determination in minerals, process products and waste pieces. The latters, as objects of gold content chemical analysis, are most hard-to-study for two reasons: Because of high requirements to accuracy of analysis results and because of difference in chemical and phase composition. As a rule, such objects are characterized by compound, variable and very often unknown matrix composition that leads to unpredictable and uncontrolled effect on accuracy and other analytical characteristics of analysis technique. In this paper, the methods for the determination of gold are described, using flame atomic-absorption spectrophotometry and gravimetric analysis technique. The techniques are aimed at gold determination in a solution for gold etching (KJ+J2), in the technological mixture formed after cleaning stainless steel members of vacuum-deposit installation with concentrated nitric and hydrochloric acids as well as in gold-containing powder resulted from liquid wastes reprocessing. Optimal conditions for sample preparation and analysis of liquid and solid waste specimens of compound and variable matrix composition were chosen. The boundaries of relative resultant error were determined for the methods within the range of gold mass concentration from 0.1 to 30g/dm3 in the specimens of liquid wastes and mass fractions from 3 to 80% in the specimens of solid wastes.

Keywords: microelectronics waste pieces, gold, sample preparation, atomic-absorption spectrophotometry, gravimetric analysis technique

Procedia PDF Downloads 189

Authors: Ksenia Volkova, Artur Petrosyan, Ignatii Dubyshkin, Alexei Ossadtchi

Abstract:

Brain-computer interfaces are a growing research field producing many implementations that find use in different fields and are used for research and practical purposes. Despite the popularity of the implementations using non-invasive neuroimaging methods, radical improvement of the state channel bandwidth and, thus, decoding accuracy is only possible by using invasive techniques. Electrocorticography (ECoG) is a minimally invasive neuroimaging method that provides highly informative brain activity signals, effective analysis of which requires the use of machine learning methods that are able to learn representations of complex patterns. Deep learning is a family of machine learning algorithms that allow learning representations of data with multiple levels of abstraction. This study explores the potential of deep learning approaches for ECoG processing, decoding movement intentions and the perception of proprioceptive information. To obtain synchronous recording of kinematic movement characteristics and corresponding electrical brain activity, a series of experiments were carried out, during which subjects performed finger movements at their own pace. Finger movements were recorded with a three-axis accelerometer, while ECoG was synchronously registered from the electrode strips that were implanted over the contralateral sensorimotor cortex. Then, multichannel ECoG signals were used to track finger movement trajectory characterized by accelerometer signal. This process was carried out both causally and non-causally, using different position of the ECoG data segment with respect to the accelerometer data stream. The recorded data was split into training and testing sets, containing continuous non-overlapping fragments of the multichannel ECoG. A deep convolutional neural network was implemented and trained, using 1-second segments of ECoG data from the training dataset as input. To assess the decoding accuracy, correlation coefficient r between the output of the model and the accelerometer readings was computed. After optimization of hyperparameters and training, the deep learning model allowed reasonably accurate causal decoding of finger movement with correlation coefficient r = 0.8. In contrast, the classical Wiener-filter like approach was able to achieve only 0.56 in the causal decoding mode. In the noncausal case, the traditional approach reached the accuracy of r = 0.69, which may be due to the presence of additional proprioceptive information. This result demonstrates that the deep neural network was able to effectively find a representation of the complex top-down information related to the actual movement rather than proprioception. The sensitivity analysis shows physiologically plausible pictures of the extent to which individual features (channel, wavelet subband) are utilized during the decoding procedure. In conclusion, the results of this study have demonstrated that a combination of a minimally invasive neuroimaging technique such as ECoG and advanced machine learning approaches allows decoding motion with high accuracy. Such setup provides means for control of devices with a large number of degrees of freedom as well as exploratory studies of the complex neural processes underlying movement execution.

Keywords: brain-computer interface, deep learning, ECoG, movement decoding, sensorimotor cortex

Procedia PDF Downloads 160

Authors: Elia Favarelli, Enrico Testi, Andrea Giorgetti

Abstract:

Autonomous structural health monitoring (SHM) of many structures and bridges became a topic of paramount importance for maintenance purposes and safety reasons. This paper proposes a set of machine learning (ML) tools to perform automatic feature selection and detection of anomalies in a bridge from vibrational data and compare different feature extraction schemes to increase the accuracy and reduce the amount of data collected. As a case study, the Z-24 bridge is considered because of the extensive database of accelerometric data in both standard and damaged conditions. The proposed framework starts from the first four fundamental frequencies extracted through operational modal analysis (OMA) and clustering, followed by density-based time-domain filtering (tracking). The fundamental frequencies extracted are then fed to a dimensionality reduction block implemented through two different approaches: feature selection (intelligent multiplexer) that tries to estimate the most reliable frequencies based on the evaluation of some statistical features (i.e., mean value, variance, kurtosis), and feature extraction (auto-associative neural network (ANN)) that combine the fundamental frequencies to extract new damage sensitive features in a low dimensional feature space. Finally, one class classifier (OCC) algorithms perform anomaly detection, trained with standard condition points, and tested with normal and anomaly ones. In particular, a new anomaly detector strategy is proposed, namely one class classifier neural network two (OCCNN2), which exploit the classification capability of standard classifiers in an anomaly detection problem, finding the standard class (the boundary of the features space in normal operating conditions) through a two-step approach: coarse and fine boundary estimation. The coarse estimation uses classics OCC techniques, while the fine estimation is performed through a feedforward neural network (NN) trained that exploits the boundaries estimated in the coarse step. The detection algorithms vare then compared with known methods based on principal component analysis (PCA), kernel principal component analysis (KPCA), and auto-associative neural network (ANN). In many cases, the proposed solution increases the performance with respect to the standard OCC algorithms in terms of F1 score and accuracy. In particular, by evaluating the correct features, the anomaly can be detected with accuracy and an F1 score greater than 96% with the proposed method.

Keywords: anomaly detection, frequencies selection, modal analysis, neural network, sensor network, structural health monitoring, vibration measurement

Procedia PDF Downloads 111

Authors: Bo Wang

Abstract:

The geometric processing of multi-source remote sensing data using control data of different scale and different accuracy is an important research direction of multi-platform system for earth observation. In the existing block bundle adjustment methods, as the controlling information in the adjustment system, the approach using single observation scale and precision is unable to screen out the control information and to give reasonable and effective corresponding weights, which reduces the convergence and adjustment reliability of the results. Referring to the relevant theory and technology of quotient space, in this project, several subjects are researched. Multi-layer quotient space of multi-geometric features is constructed to describe and filter control data. Normalized granularity merging mechanism of multi-layer control information is studied and based on the normalized scale factor, the strategy to optimize the weight selection of control data which is less relevant to the adjustment system can be realized. At the same time, geometric positioning experiment is conducted using multi-source remote sensing data, aerial images, and multiclass control data to verify the theoretical research results. This research is expected to break through the cliché of the single scale and single accuracy control data in the adjustment process and expand the theory and technology of photogrammetry. Thus the problem to process multi-source remote sensing data will be solved both theoretically and practically.

Keywords: multi-source image geometric process, high precision geometric positioning, quotient space of multi-geometric features, optimized weight selection

Procedia PDF Downloads 271

Authors: Xavier Bertrand, Alexandre Cayrel

Abstract:

The early phase of an aircraft development is instrumental as it really drives the potential of a new concept. Any weakness in the high-level design (wing planform, moveable surfaces layout etc.) will be extremely difficult and expensive to recover later in the aircraft development process. Aerodynamic evaluation in this very early development phase is driven by two main criteria: a short lead-time to allow quick iterations of the geometrical design, and a high quality of the calculations to get an accurate & reliable assessment of the current status. These two criteria are usually quite contradictory. Actually, short lead time of a couple of hours from end-to-end can be obtained with very simple tools (semi-empirical methods for instance) although their accuracy is limited, whereas higher quality calculations require heavier/more complex tools, which obviously need more complex inputs as well, and a significantly longer lead time. At this point, the choice has to be done between accuracy and lead-time. A brand new approach has been developed within Airbus, aiming at obtaining quickly high quality evaluations of the aerodynamic of an aircraft. This methodology is based on a joint use of Surrogate Modelling and a lifting line code. The Surrogate Modelling is used to get the wing sections characteristics (e.g. lift coefficient vs. angle of attack), whatever the airfoil geometry, the status of the moveable surfaces (aileron/spoilers) or the high-lift devices deployment. From these characteristics, the lifting line code is used to get the 3D effects on the wing whatever the flow conditions (low/high Mach numbers etc.). This methodology has been applied successfully to a concept of medium range aircraft.

Keywords: aerodynamics, lifting line, surrogate model, CFD

Procedia PDF Downloads 336

Authors: Cher Rong Matthew Kong, Edmund Tian, Seng Poon Ong, Chee Sian Gan

Abstract:

Gamma-aminobutyric acid (GABA) is a non-protein amino acid that is a functional constituent of certain rice varieties. When consumed, it decreases blood pressure and reduces the risk of hypertension-related diseases. This has led to more research dedicated towards the development of functional food products (e.g. germinated brown rice) with enhanced GABA content, and the development of these functional food products has led to increased demand for instrument-based methods that can efficiently and effectively determine GABA content. Current analytical methods require analyte derivatisation, and have significant disadvantages such as being labour intensive and time-consuming, and being subject to analyte loss due to the increased complexity of the sample preparation process. To address this, an LC-MS-MS method for the determination of GABA in rice products has been developed and validated. This developed method involves a relatively simple sample preparation process before analysis using HILIC LC-MS-MS. This method eliminates the need for derivatisation, thereby significantly reducing the labour and time associated with such an analysis. Using LC-MS-MS also allows for better differentiation of GABA from any potential co-eluting compounds in the sample matrix. Results obtained from the developed method demonstrated high linearity, accuracy, and precision for the determination of GABA (1ng/L to 8ng/L) in a variety of brown rice products. The method can significantly simplify sample preparation steps, improve the accuracy of quantitation, and increase the throughput of analyses, thereby providing a quick but effective alternative to established instrumental analysis methods for GABA in rice.

Keywords: functional food, gamma-aminobutyric acid, germinated brown rice, method development

Procedia PDF Downloads 246

Authors: Zhiyong Zheng, Xu Li, Liang Huang, Zhengliang Sun, Jianhua Xu

Abstract:

Yaw angle plays a significant role in many vehicle safety applications, such as collision avoidance and lane-keeping system. Although the estimation of the yaw angle has been extensively studied in existing literature, it is still the main challenge to simultaneously achieve a reliable and cost-effective solution in complex urban environments. This paper proposes a multi-stage learning framework to estimate the yaw angle with a monocular camera, which can deal with the challenge in a more reliable manner. In the first stage, an efficient road detection network is designed to extract the road region, providing a highly reliable reference for the estimation. In the second stage, a variational auto-encoder (VAE) is proposed to learn the distribution patterns of road regions, which is particularly suitable for modeling the changing patterns of yaw angle under different driving maneuvers, and it can inherently enhance the generalization ability. In the last stage, a gated recurrent unit (GRU) network is used to capture the temporal correlations of the learned patterns, which is capable to further improve the estimation accuracy due to the fact that the changes of deflection angle are relatively easier to recognize among continuous frames. Afterward, the yaw angle can be obtained by combining the estimated deflection angle and the road direction stored in a roadway map. Through effective multi-stage learning, the proposed framework presents high reliability while it maintains better accuracy. Road-test experiments with different driving maneuvers were performed in complex urban environments, and the results validate the effectiveness of the proposed framework.

Keywords: gated recurrent unit, multi-stage learning, reliable estimation, variational auto-encoder, yaw angle

Procedia PDF Downloads 122

Authors: Jiemiao Chen, Shuoxun Xu

Abstract:

The main goal of our research is to apply the Vine copula measuring dependency between price, temperature, and precipitation indices to calculate a fair crop insurance premium. This research is focused on Worth, Iowa, United States, over the period from 2000 to 2020, where the farmers are dependent on precipitation and average temperature during the growth period of corn. Our proposed insurance considers both the natural risk and the price risk in agricultural production. We first estimate the distributions of crops using parametric methods based on Goodness of Fit tests, and then Vine Copula is applied to model dependence between yield price, crop yield, and weather indices. Once the vine structure and its parameters are determined based on AIC/BIC criteria and forecasting price and yield are obtained from the ARIMA model, we calculate this crop insurance premium using the simulation data generated from the vine copula by the Monte Carlo Simulation method. It is shown that, compared with traditional crop insurance, our proposed insurance is more fair and thus less costly for the farmers and government.

Keywords: vine copula, weather index, crop insurance premium, insurance risk management, Monte Carlo simulation

Procedia PDF Downloads 185

Authors: Longxiang Guo, Haoyan Hao, Xueli Sheng, Hanjun Yu, Jingwei Yin

Abstract:

In order to prevent target splitting and ensure the accuracy of fusion, system error registration is an important step in multi-static sonar fusion detection system. To eliminate the inherent system errors including distance error and angle error of each sonar in detection, this paper uses offline estimation method for error registration. Suppose several sonars from different platforms work together to detect a target. The target position detected by each sonar is based on each sonar’s own reference coordinate system. Based on the two-dimensional stereo projection method, this paper uses real-time quality control (RTQC) method and least squares (LS) method to estimate sensor biases. The RTQC method takes the average value of each sonar’s data as the observation value and the LS method makes the least square processing of each sonar’s data to get the observation value. In the underwater acoustic environment, matlab simulation is carried out and the simulation results show that both algorithms can estimate the distance and angle error of sonar system. The performance of the two algorithms is also compared through the root mean square error and the influence of measurement noise on registration accuracy is explored by simulation. The system error convergence of RTQC method is rapid, but the distribution of targets has a serious impact on its performance. LS method can not be affected by target distribution, but the increase of random noise will slow down the convergence rate. LS method is an improvement of RTQC method, which is widely used in two-dimensional registration. The improved method can be used for underwater multi-target detection registration.

Keywords: data fusion, multi-static sonar detection, offline estimation, sensor registration problem

Procedia PDF Downloads 153

Authors: Yufeng Li, Yinan Ma, Jing Wu, Chengnian Long

Abstract:

Infrared object detection aims at separating small and dim target from clutter background and its capabilities extend beyond the limits of visible light, making it invaluable in a wide range of applications such as improving safety, security, efficiency, and functionality. However, existing methods are usually sensitive to the noise of the input infrared image, leading to a decrease in target detection accuracy and an increase in the false alarm rate in high-noise environments. To address this issue, an infrared small target detection algorithm called YOLO-IR is proposed in this paper to improve the robustness to high infrared noise. To address the problem that high noise significantly reduces the clarity and reliability of target features in infrared images, we design a soft-threshold coordinate attention mechanism to improve the model’s ability to extract target features and its robustness to noise. Since the noise may overwhelm the local details of the target, resulting in the loss of small target features during depth down-sampling, we propose a deep and shallow feature fusion neck to improve the detection accuracy. In addition, because the generalized Intersection over Union (IoU)-based loss functions may be sensitive to noise and lead to unstable training in high-noise environments, we introduce a Wasserstein-distance based loss function to improve the training of the model. The experimental results show that YOLO-IR achieves a 5.0% improvement in recall and a 6.6% improvement in F1-score over existing state-of-art model.

Keywords: infrared small target detection, high noise, robustness, soft-threshold coordinate attention, feature fusion

Procedia PDF Downloads 44

Authors: Awais Ahmed, Atif Rana, Haseeb Zia, Maham Jahangir, Rashed Nazir, Faisal Dar

Abstract:

Purpose: Biliary complications represent the most common cause of morbidity in living related liver donor transplantation and detailed preoperative evaluation of biliary anatomic variants is crucial for safe patient selection and improved surgical outcomes. Purpose of this study is to determine the accuracy of preoperative MRCP in predicting biliary variations when compared to intraoperative cholangiography in living related liver donors. Materials and Methods: From 44 potential donors, 40 consecutive living related liver donors (13 females and 28 males) underwent donor hepatectomy at our centre from April 2012 to August 2013. MRCP and IOC of all patients were retrospectively reviewed separately by two radiologists and a transplant surgeon.MRCP was performed on 1.5 Tesla MR magnets using breath-hold heavily T2 weighted radial slab technique. One patient was excluded due to suboptimal MRCP. The accuracy of MRCP for variant biliary anatomy was calculated. Results: MRCP accurately predicted the biliary anatomy in 38 of 39 cases (97 %). Standard biliary anatomy was predicted by MRCP in 25 (64 %) donors (100% sensitivity). Variant biliary anatomy was noted in 14 (36 %) IOCs of which MRCP predicted precise anatomy of 13 variants (93 % sensitivity). The two most common variations were drainage of the RPSD into the LHD (50%) and the triple confluence of the RASD, RPSD and LHD (21%). Conclusion: MRCP is a sensitive imaging tool for precise pre-operative mapping of biliary variations which is critical to surgical decision making in living related liver transplantation.

Keywords: intraoperative cholangiogram, liver transplantation, living related donors, magnetic resonance cholangio-pancreaticogram (MRCP)

Procedia PDF Downloads 379

Authors: Nasrin Bakhshizadeh, Ashkan Forootan

Abstract:

A major problem that affects the quality control of polymer in the industrial polymerization is the lack of suitable on-line measurement tools to evaluate the properties of the polymer such as melt and density indices. Controlling the polymerization in ordinary method is performed manually by taking samples, measuring the quality of polymer in the lab and registry of results. This method is highly time consuming and leads to producing large number of incompatible products. An online application for estimating melt index and density proposed in this study is a neural network based on the input-output data of the polyethylene production plant. Temperature, the level of reactors' bed, the intensity of ethylene mass flow, hydrogen and butene-1, the molar concentration of ethylene, hydrogen and butene-1 are used for the process to establish the neural model. The neural network is taught based on the actual operational data and back-propagation and Levenberg-Marquart techniques. The simulated results indicate that the neural network process model established with three layers (one hidden layer) for forecasting the density and the four layers for the melt index is able to successfully predict those quality properties.

Keywords: polyethylene, polymerization, density, melt index, neural network

Procedia PDF Downloads 129

Authors: Jinyan Li, Simon Fong, Raymond Wong, Mohammed Sabah, Fiaidhi Jinan

Abstract:

Clinical data analysis and forecasting have make great contributions to disease control, prevention and detection. However, such data usually suffer from highly unbalanced samples in class distributions. In this paper, we target at the binary imbalanced dataset, where the positive samples take up only the minority. We investigate two different meta-heuristic algorithms, particle swarm optimization and bat-inspired algorithm, and combine both of them with the synthetic minority over-sampling technique (SMOTE) for processing the datasets. One approach is to process the full dataset as a whole. The other is to split up the dataset and adaptively process it one segment at a time. The experimental results reveal that while the performance improvements obtained by the former methods are not scalable to larger data scales, the later one, which we call Adaptive Swarm Balancing Algorithms, leads to significant efficiency and effectiveness improvements on large datasets. We also find it more consistent with the practice of the typical large imbalanced medical datasets. We further use the meta-heuristic algorithms to optimize two key parameters of SMOTE. Leading to more credible performances of the classifier, and shortening the running time compared with the brute-force method.

Keywords: Imbalanced dataset, meta-heuristic algorithm, SMOTE, big data

Procedia PDF Downloads 428

Authors: Michelle Nighswander

Abstract:

Suicide can be a tragic response to mental illness. It is difficult for people to disclose or discuss suicidal impulses. The stigma surrounding mental health can create a reluctance to seek help for mental illness. Patients may feel pressure to exhibit a socially desirable demeanor rather than reveal these issues, especially if they sense their healthcare provider is pressed for time or does not have an extensive history with their provider. Overcoming these barriers can be challenging. Although there are several validated depression and suicide risk instruments, varying processes used to administer these tools may impact the truthfulness of the responses. A literature review was conducted to find evidence of the impact of the environment on the accuracy of depression screening. Many investigations do not describe the environment and fewer studies use a comparison design. However, three studies demonstrated that computerized self-reporting might be more likely to elicit truthful and accurate responses due to increased privacy when responding compared to a face-to-face interview. These studies showed patients reported positive reactions to computerized screening for other stigmatizing health conditions such as alcohol use during pregnancy. Computerized self-screening for depression offers the possibility of more privacy and patient reflection, which could then send a targeted message of risk to the healthcare provider. This could potentially increase the accuracy while also increasing time efficiency for the clinic. Considering the persistent effects of mental health stigma, how these screening questions are posed can impact patients’ responses. This literature review analyzes trends in depression screening methodologies, the impact of setting on the results and how this may assist in overcoming one barrier caused by stigma.

Keywords: computerized self-report, depression, mental health stigma, suicide risk

Procedia PDF Downloads 118

Authors: Mohammad Lemar Zalmai, Osman Hurol Turkakin, Cemil Akcay, Ekrem Manisali

Abstract:

Most of the construction projects are exposed to time and cost overruns due to various factors and this is a major problem. As a solution to this, the Earned Value Management (EVM) method is considered. EVM is a powerful and well-known method used in monitoring and controlling the project. EVM is a technique that project managers use to track the performance of their project against project baselines. EVM gives an early indication that either project is delayed or not, and the project is either over budget or under budget at any particular day by tracking it. Thus, it helps to improve the management control system of a construction project, to detect and control the problems in potential risk areas and to suggest the importance and purpose of monitoring the construction work. This paper explains the main parameters of the EVM system involved in the calculation of time and cost for construction projects. In this study, the project management software Primavera P6 is used to deals with the project monitoring process of a seven-storeyed (G+6) faculty building whose construction is in progress at Istanbul, Turkey. A comparison between the planned progress of construction activities and actual progress is performed, and the analysis results are interpreted. This case study justifies the benefits of using EVM for project cash flow analysis and forecasting.

Keywords: earned value management (EVM), construction cost management, construction planning, primavera P6, project management, project scheduling

Procedia PDF Downloads 210

Authors: Chakrit Chotamonsak

Abstract:

In this study, the Weather Research and Forecasting (WRF) model was used as regional climate model to dynamically downscale the ECHAM5 Global Climate Model projection for the regional climate change impact on air quality–related meteorological conditions in the upper northern Thailand. The analyses were focused on meteorological variables that potentially impact on the regional air quality such as sea level pressure, planetary boundary layer height (PBLH), surface temperature, wind speed and ventilation. Comparisons were made between the present (1990–2009) and future (2045–2064) climate downscaling results during majority air pollution season (dry season, January-April). Analyses showed that the sea level pressure will be stronger in the future, suggesting more stable atmosphere. Increases in temperature were obvious observed throughout the region. Decreases in surface wind and PBLH were predicted during air pollution season, indicating weaker ventilation rate in this region. Consequently, air quality-related meteorological variables were predicted to change in almost part of the upper northern Thailand, yielding a favorable meteorological condition for pollutant accumulation in the future.

Keywords: climate change, climate impact, air quality, air pollution, Thailand

Procedia PDF Downloads 340

Authors: Bahareh Golchin, Nooshin Riahi

Abstract:

One of the most significant issues as attended a lot in recent years is that of recognizing the sentiments and emotions in social media texts. The analysis of sentiments and emotions is intended to recognize the conceptual information such as the opinions, feelings, attitudes and emotions of people towards the products, services, organizations, people, topics, events and features in the written text. These indicate the greatness of the problem space. In the real world, businesses and organizations are always looking for tools to gather ideas, emotions, and directions of people about their products, services, or events related to their own. This article uses the Twitter social network, one of the most popular social networks with about 420 million active users, to extract data. Using this social network, users can share their information and opinions about personal issues, policies, products, events, etc. It can be used with appropriate classification of emotional states due to the availability of its data. In this study, supervised learning and deep neural network algorithms are used to classify the emotional states of Twitter users. The use of deep learning methods to increase the learning capacity of the model is an advantage due to the large amount of available data. Tweets collected on various topics are classified into four classes using a combination of two Bidirectional Long Short Term Memory network and a Convolutional network. The results obtained from this study with an average accuracy of 93%, show good results extracted from the proposed framework and improved accuracy compared to previous work.

Keywords: emotion classification, sentiment analysis, social networks, deep neural networks

Procedia PDF Downloads 126