Search results for: classifiers accuracy

Authors: Omowunmi E. Isafiade, Isaac O. Osunmakinde, Antoine B. Bagula

Abstract:

Robots- visual perception is a field that is gaining increasing attention from researchers. This is partly due to emerging trends in the commercial availability of 3D scanning systems or devices that produce a high information accuracy level for a variety of applications. In the history of mining, the mortality rate of mine workers has been alarming and robots exhibit a great deal of potentials to tackle safety issues in mines. However, an effective vision system is crucial to safe autonomous navigation in underground terrains. This work investigates robots- perception in underground terrains (mines and tunnels) using statistical region merging (SRM) model. SRM reconstructs the main structural components of an imagery by a simple but effective statistical analysis. An investigation is conducted on different regions of the mine, such as the shaft, stope and gallery, using publicly available mine frames, with a stream of locally captured mine images. An investigation is also conducted on a stream of underground tunnel image frames, using the XBOX Kinect 3D sensors. The Kinect sensors produce streams of red, green and blue (RGB) and depth images of 640 x 480 resolution at 30 frames per second. Integrating the depth information to drivability gives a strong cue to the analysis, which detects 3D results augmenting drivable and non-drivable regions in 2D. The results of the 2D and 3D experiment with different terrains, mines and tunnels, together with the qualitative and quantitative evaluation, reveal that a good drivable region can be detected in dynamic underground terrains.

Keywords: Drivable Region Detection, Kinect Sensor, Robots' Perception, SRM, Underground Terrains.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1784

Authors: Daohong Yang, Xiang Zhang, Wanting Zhou, Lei Li

Abstract:

Visual Simultaneous Localization and Mapping (VSLAM) is a technology that gathers information about the surrounding environment to ascertain its own position and create a map. It is widely used in computer vision, robotics, and various other fields. Many visual SLAM systems, such as OBSLAM3, utilize a constant velocity motion model. The utilization of this model facilitates the determination of the initial pose of the current frame, thereby enhancing the efficiency and precision of feature matching. However, it is often difficult to satisfy the constant velocity motion model in actual situations. This can result in a significant deviation between the obtained initial pose and the true value, leading to errors in nonlinear optimization results. Therefore, this paper proposes a motion model based on acceleration that can be applied to most SLAM systems. To provide a more accurate description of the camera pose acceleration, we separate the pose transformation matrix into its rotation matrix and translation vector components. The rotation matrix is now represented by a rotation vector. We assume that, over a short period, the changes in rotating angular velocity and translation vector remain constant. Based on this assumption, the initial pose of the current frame is estimated. In addition, the error of the constant velocity model is analyzed theoretically. Finally, we apply our proposed approach to the ORBSLAM3 system and evaluate two sets of sequences from the TUM datasets. The results show that our proposed method has a more accurate initial pose estimation, resulting in an improvement of 6.61% and 6.46% in the accuracy of the ORBSLAM3 system on the two test sequences, respectively.

Keywords: Error estimation, constant acceleration motion model, pose estimation, visual SLAM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 146

Authors: Hossein Jafari, Xiangfang Li, Lijun Qian, Alexander Aved, Timothy Kroecker

Abstract:

Traditionally in sensor networks and recently in the Internet of Things, numerous heterogeneous sensors are deployed in distributed manner to monitor a phenomenon that often can be model by an underlying stochastic process. The big time-series data collected by the sensors must be analyzed to detect change in the stochastic process as quickly as possible with tolerable false alarm rate. However, sensors may have different accuracy and sensitivity range, and they decay along time. As a result, the big time-series data collected by the sensors will contain uncertainties and sometimes they are conflicting. In this study, we present a framework to take advantage of Evidence Theory (a.k.a. Dempster-Shafer and Dezert-Smarandache Theories) capabilities of representing and managing uncertainty and conflict to fast change detection and effectively deal with complementary hypotheses. Specifically, Kullback-Leibler divergence is used as the similarity metric to calculate the distances between the estimated current distribution with the pre- and post-change distributions. Then mass functions are calculated and related combination rules are applied to combine the mass values among all sensors. Furthermore, we applied the method to estimate the minimum number of sensors needed to combine, so computational efficiency could be improved. Cumulative sum test is then applied on the ratio of pignistic probability to detect and declare the change for decision making purpose. Simulation results using both synthetic data and real data from experimental setup demonstrate the effectiveness of the presented schemes.

Keywords: CUSUM, evidence theory, KL divergence, quickest change detection, time series data.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 950

Authors: Ali Hamadi Dicko, Nicolas Tong-Yette, Benjamin Gilles, François Faure, Olivier Palombi

Abstract:

A novel hybrid model of the lumbar spine, allowing fast static and dynamic simulations of the disc pressure and the spine mobility, is introduced in this work. Our contribution is to combine rigid bodies, deformable finite elements, articular constraints, and springs into a unique model of the spine. Each vertebra is represented by a rigid body controlling a surface mesh to model contacts on the facet joints and the spinous process. The discs are modeled using a heterogeneous tetrahedral finite element model. The facet joints are represented as elastic joints with six degrees of freedom, while the ligaments are modeled using non-linear one-dimensional elastic elements. The challenge we tackle is to make these different models efficiently interact while respecting the principles of Anatomy and Mechanics. The mobility, the intradiscal pressure, the facet joint force and the instantaneous center of rotation of the lumbar spine are validated against the experimental and theoretical results of the literature on flexion, extension, lateral bending as well as axial rotation. Our hybrid model greatly simplifies the modeling task and dramatically accelerates the simulation of pressure within the discs, as well as the evaluation of the range of motion and the instantaneous centers of rotation, without penalizing precision. These results suggest that for some types of biomechanical simulations, simplified models allow far easier modeling and faster simulations compared to usual full-FEM approaches without any loss of accuracy.

Keywords: Hybrid, modeling, fast simulation, lumbar spine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2340

Authors: Iman A. Saad, Loay E. George

Abstract:

Iris pattern is an important biological feature of human body; it becomes very hot topic in both research and practical applications. In this paper, an algorithm is proposed for iris recognition and a simple, efficient and fast method is introduced to extract a set of discriminatory features using first order gradient operator applied on grayscale images. The gradient based features are robust, up to certain extents, against the variations may occur in contrast or brightness of iris image samples; the variations are mostly occur due lightening differences and camera changes. At first, the iris region is located, after that it is remapped to a rectangular area of size 360x60 pixels. Also, a new method is proposed for detecting eyelash and eyelid points; it depends on making image statistical analysis, to mark the eyelash and eyelid as a noise points. In order to cover the features localization (variation), the rectangular iris image is partitioned into N overlapped sub-images (blocks); then from each block a set of different average directional gradient densities values is calculated to be used as texture features vector. The applied gradient operators are taken along the horizontal, vertical and diagonal directions. The low order norms of gradient components were used to establish the feature vector. Euclidean distance based classifier was used as a matching metric for determining the degree of similarity between the features vector extracted from the tested iris image and template features vectors stored in the database. Experimental tests were performed using 2639 iris images from CASIA V4-Interival database, the attained recognition accuracy has reached up to 99.92%.

Keywords: Iris recognition, contrast stretching, gradient features, texture features, Euclidean metric.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1917

Authors: Theerawat Songyot, Tham Manjing, Bunyarit Uyyanonvara, Chanjira Sinthanayothin

Abstract:

Corner detection and optical flow are common techniques for feature-based video stabilization. However, these algorithms are computationally expensive and should be performed at a reasonable rate. This paper presents an algorithm for discarding irrelevant feature points and maintaining them for future use so as to improve the computational cost. The algorithm starts by initializing a maintained set. The feature points in the maintained set are examined against its accuracy for modeling. Corner detection is required only when the feature points are insufficiently accurate for future modeling. Then, optical flows are computed from the maintained feature points toward the consecutive frame. After that, a motion model is estimated based on the simplified affine motion model and least square method, with outliers belonging to moving objects presented. Studentized residuals are used to eliminate such outliers. The model estimation and elimination processes repeat until no more outliers are identified. Finally, the entire algorithm repeats along the video sequence with the points remaining from the previous iteration used as the maintained set. As a practical application, an efficient video stabilization can be achieved by exploiting the computed motion models. Our study shows that the number of times corner detection needs to perform is greatly reduced, thus significantly improving the computational cost. Moreover, optical flow vectors are computed for only the maintained feature points, not for outliers, thus also reducing the computational cost. In addition, the feature points after reduction can sufficiently be used for background objects tracking as demonstrated in the simple video stabilizer based on our proposed algorithm.

Keywords: background object tracking, feature point reduction, low cost tracking, video stabilization.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1721

Authors: Siti Nor Hafizah binti Mohd Zaid, Mohamed Abdel-Maguid, Abdel-Hamid Soliman

Abstract:

An Advance Driver Assistance System (ADAS) is a computer system on board a vehicle which is used to reduce the risk of vehicular accidents by monitoring factors relating to the driver, vehicle and environment and taking some action when a risk is identified. Much work has been done on assessing vehicle and environmental state but there is still comparatively little published work that tackles the problem of driver state. Visual attention is one such driver state. In fact, some researchers claim that lack of attention is the main cause of accidents as factors such as fatigue, alcohol or drug use, distraction and speeding all impair the driver-s capacity to pay attention to the vehicle and road conditions [1]. This seems to imply that the main cause of accidents is inappropriate driver behaviour in cases where the driver is not giving full attention while driving. The work presented in this paper proposes an ADAS system which uses an image based template matching algorithm to detect if a driver is failing to observe particular windscreen cells. This is achieved by dividing the windscreen into 24 uniform cells (4 rows of 6 columns) and matching video images of the driver-s left eye with eye-gesture templates drawn from images of the driver looking at the centre of each windscreen cell. The main contribution of this paper is to assess the accuracy of this approach using Receiver Operating Characteristic analysis. The results of our evaluation give a sensitivity value of 84.3% and a specificity value of 85.0% for the eye-gesture template approach indicating that it may be useful for driver point of regard determinations.

Keywords: Advanced Driver Assistance Systems, Eye-Tracking, Hazard Detection.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1584

Authors: Feng-Sheng Wang, Wu-Hsiung Wu, Kai-Cheng Hsu

Abstract:

The optimization of biological systems, which is a branch of metabolic engineering, has generated a lot of industrial and academic interest for a long time. In the last decade, metabolic engineering approaches based on mathematical optimizations have been used extensively for the analysis and manipulation of metabolic networks. In practical optimization of metabolic reaction networks, designers have to manage the nature of uncertainty resulting from qualitative characters of metabolic reactions, e.g., the possibility of enzyme effects. A deterministic approach does not give an adequate representation for metabolic reaction networks with uncertain characters. Fuzzy optimization formulations can be applied to cope with this problem. A fuzzy multi-objective optimization problem can be introduced for finding the optimal engineering interventions on metabolic network systems considering the resilience phenomenon and cell viability constraints. The accuracy of optimization results depends heavily on the development of essential kinetic models of metabolic networks. Kinetic models can quantitatively capture the experimentally observed regulation data of metabolic systems and are often used to find the optimal manipulation of external inputs. To address the issues of optimizing the regulatory structure of metabolic networks, it is necessary to consider qualitative effects, e.g., the resilience phenomena and cell viability constraints. Combining the qualitative and quantitative descriptions for metabolic networks makes it possible to design a viable strain and accurately predict the maximum possible flux rates of desired products. Considering the resilience phenomena in metabolic networks can improve the predictions of gene intervention and maximum synthesis rates in metabolic engineering. Two case studies will present in the conference to illustrate the phenomena.

Keywords: Fuzzy multi-objective optimization problem, kinetic model, metabolic engineering.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1973

Authors: L. Basha, E. Gjika

Abstract:

This study is focused on analyzing climate change in Albania and its potential effects on cereal yields. Initially, monthly temperature and rainfalls in Albania were studied for the period 1960-2021. Climacteric variables are important variables when trying to model cereal yield behavior, especially when significant changes in weather conditions are observed. For this purpose, in the second part of the study, linear and nonlinear models explaining cereal yield are constructed for the same period, 1960-2021. The multiple linear regression analysis and lasso regression method are applied to the data between cereal yield and each independent variable: average temperature, average rainfall, fertilizer consumption, arable land, land under cereal production, and nitrous oxide emissions. In our regression model, heteroscedasticity is not observed, data follow a normal distribution, and there is a low correlation between factors, so we do not have the problem of multicollinearity. Machine learning methods, such as Random Forest (RF), are used to predict cereal yield responses to climacteric and other variables. RF showed high accuracy compared to the other statistical models in the prediction of cereal yield. We found that changes in average temperature negatively affect cereal yield. The coefficients of fertilizer consumption, arable land, and land under cereal production are positively affecting production. Our results show that the RF method is an effective and versatile machine-learning method for cereal yield prediction compared to the other two methods: multiple linear regression and lasso regression method.

Keywords: Cereal yield, climate change, machine learning, multiple regression model, random forest.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 101

Authors: Ah-young Jeon, In-cheol Kim, Jae-hee Jung, Soo-young Ye, Jae-hyung Kim, Ki-gon Nam, Seoung-wan Baik, Jung-hoon Ro, Gye-rok Jeon

Abstract:

The aged are faced with increasing risk for falls. The aged have the easily fragile bones than others. When falls have occurred, it is important to detect this emergency state because such events often lead to more serious illness or even death. A implementation of PDA system, for detection of emergency situation, was developed using 3-axis accelerometer in this paper as follows. The signals were acquired from the 3-axis accelerometer, and then transmitted to the PDA through Bluetooth module. This system can classify the human activity, and also detect the emergency state like falls. When the fall occurs, the system generates the alarm on the PDA. If a subject does not respond to the alarm, the system determines whether the current situation is an emergency state or not, and then sends some information to the emergency center in the case of urgent situation. Three different studies were conducted on 12 experimental subjects, with results indicating a good accuracy. The first study was performed to detect the posture change of human daily activity. The second study was performed to detect the correct direction of fall. The third study was conducted to check the classification of the daily physical activity. Each test was lasted at least 1 min. in third study. The output of acceleration signal was compared and evaluated by changing a various posture after attaching a 3-axis accelerometer module on the chest. The newly developed system has some important features such as portability, convenience and low cost. One of the main advantages of this system is that it is available at home healthcare environment. Another important feature lies in low cost to manufacture device. The implemented system can detect the fall accurately, so will be widely used in emergency situation.

Keywords: Alarm System, Ambulatory monitoring, Emergency detection, Classification of activity, and 3-axis accelerometer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1558

Authors: Jingling Li, Yi Zhang, Wei Liang, Tao Cui, Jun Li

Abstract:

Compared with terrestrial network, the traffic of spatial information network has both self-similarity and short correlation characteristics. By studying its traffic prediction method, the resource utilization of spatial information network can be improved, and the method can provide an important basis for traffic planning of a spatial information network. In this paper, considering the accuracy and complexity of the algorithm, the spatial information network traffic is decomposed into approximate component with long correlation and detail component with short correlation, and a time series hybrid prediction model based on wavelet decomposition is proposed to predict the spatial network traffic. Firstly, the original traffic data are decomposed to approximate components and detail components by using wavelet decomposition algorithm. According to the autocorrelation and partial correlation smearing and truncation characteristics of each component, the corresponding model (AR/MA/ARMA) of each detail component can be directly established, while the type of approximate component modeling can be established by ARIMA model after smoothing. Finally, the prediction results of the multiple models are fitted to obtain the prediction results of the original data. The method not only considers the self-similarity of a spatial information network, but also takes into account the short correlation caused by network burst information, which is verified by using the measured data of a certain back bone network released by the MAWI working group in 2018. Compared with the typical time series model, the predicted data of hybrid model is closer to the real traffic data and has a smaller relative root means square error, which is more suitable for a spatial information network.

Keywords: Spatial Information Network, Traffic prediction, Wavelet decomposition, Time series model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 571

Authors: Behrang Tavousi Tehrani, Mohammad-Zaman Kabir

Abstract:

Shape memory alloys (SMA) are often implemented in smart structures as the active components. Their ability to recover large displacements has been used in many applications, including structural stability/response enhancement and active structural acoustic control. SMA wires or fibers can be embedded with composite cylinders to increase their critical buckling load, improve their load-deflection behavior, and reduce the radial deflections under various thermo-mechanical loadings. This paper presents a semi-analytical investigation on the non-linear load-deflection response of SMA-reinforced composite circular cylindrical shells. The cylinder shells are under uniform external pressure load. Based on first-order shear deformation shell theory (FSDT), the equilibrium equations of the structure are derived. One-dimensional simplified Brinson’s model is used for determining the SMA recovery force due to its simplicity and accuracy. Airy stress function and Galerkin technique are used to obtain non-linear load-deflection curves. The results are verified by comparing them with those in the literature. Several parametric studies are conducted in order to investigate the effect of SMA volume fraction, SMA pre-strain value, and SMA activation temperature on the response of the structure. It is shown that suitable usage of SMA wires results in a considerable enhancement in the load-deflection response of the shell due to the generation of the SMA tensile recovery force.

Keywords: Airy stress function, cylindrical shell, Galerkin technique, load-deflection curve, recovery stress, shape memory alloy.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 667

Authors: A. Arockia Selvakumar, R. Sivaramakrishnan, Srinivasa Karthik.T.V, Valluri Siva Ramakrishna, B.Vinodh.

Abstract:

Industrial robots play a vital role in automation however only little effort are taken for the application of robots in machining work such as Grinding, Cutting, Milling, Drilling, Polishing etc. Robot parallel manipulators have high stiffness, rigidity and accuracy, which cannot be provided by conventional serial robot manipulators. The aim of this paper is to perform the modeling and the workspace analysis of a 3 DOF Parallel Manipulator (3 DOF PM). The 3 DOF PM was modeled and simulated using 'ADAMS'. The concept involved is based on the transformation of motion from a screw joint to a spherical joint through a connecting link. This paper work has been planned to model the Parallel Manipulator (PM) using screw joints for very accurate positioning. A workspace analysis has been done for the determination of work volume of the 3 DOF PM. The position of the spherical joints connected to the moving platform and the circumferential points of the moving platform were considered for finding the workspace. After the simulation, the position of the joints of the moving platform was noted with respect to simulation time and these points were given as input to the 'MATLAB' for getting the work envelope. Then 'AUTOCAD' is used for determining the work volume. The obtained values were compared with analytical approach by using Pappus-Guldinus Theorem. The analysis had been dealt by considering the parameters, link length and radius of the moving platform. From the results it is found that the radius of moving platform is directly proportional to the work volume for a constant link length and the link length is also directly proportional to the work volume, at a constant radius of the moving platform.

Keywords: Three Degrees of freedom Parallel Manipulator (3DOF PM), ADAMS, Work volume, MATLAB, AUTOCAD, Pappus- Guldinus Theorem.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2953

Authors: Machimontorn Promtong, Sherman C. P. Cheung, Guan H. Yeoh, Sara Vahaji, Jiyuan Tu

Abstract:

The wide range of industrial applications involved with boiling flows promotes the necessity of establishing fundamental knowledge in boiling flow phenomena. For this purpose, a number of experimental and numerical researches have been performed to elucidate the underlying physics of this flow. In this paper, the improved wall boiling models, implemented on ANSYS CFX 14.5, were introduced to study subcooled boiling flow at elevated pressure. At the heated wall boundary, the Fractal model, Force balance approach and Mechanistic frequency model are given for predicting the nucleation site density, bubble departure diameter, and bubble departure frequency. The presented wall heat flux partitioning closures were modified to consider the influence of bubble sliding along the wall before the lift-off, which usually happens in the flow boiling. The simulation was performed based on the Two-fluid model, where the standard k-ω SST model was selected for turbulence modelling. Existing experimental data at around 5 bars were chosen to evaluate the accuracy of the presented mechanistic approach. The void fraction and Interfacial Area Concentration (IAC) are in good agreement with the experimental data. However, the predicted bubble velocity and Sauter Mean Diameter (SMD) are over-predicted. This over-prediction may be caused by consideration of only dispersed and spherical bubbles in the simulations. In the future work, the important physical mechanisms of bubbles, such as merging and shrinking during sliding on the heated wall will be incorporated into this mechanistic model to enhance its capability for a wider range of flow prediction.

Keywords: CFD, mechanistic model, subcooled boiling flow, two-fluid model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1215

Authors: Ravneet Kaur, Joydeep Acharya, Sudhanshu Gaur

Abstract:

Artificial Intelligence (AI) has the potential to transform manufacturing by improving shop floor processes such as production, maintenance and quality. However, industrial datasets are notoriously difficult to extract in a real-time, streaming fashion thus, negating potential AI benefits. The main example is some specialized industrial controllers that are operated by custom software which complicates the process of connecting them to an Information Technology (IT) based data acquisition network. Security concerns may also limit direct physical access to these controllers for data acquisition. To connect the Operational Technology (OT) data stored in these controllers to an AI application in a secure, reliable and available way, we propose a novel Industrial IoT (IIoT) solution in this paper. In this solution, we demonstrate how video cameras can be installed in a factory shop floor to continuously obtain images of the controller HMIs. We propose image pre-processing to segment the HMI into regions of streaming data and regions of fixed meta-data. We then evaluate the performance of multiple Optical Character Recognition (OCR) technologies such as Tesseract and Google vision to recognize the streaming data and test it for typical factory HMIs and realistic lighting conditions. Finally, we use the meta-data to match the OCR output with the temporal, domain-dependent context of the data to improve the accuracy of the output. Our IIoT solution enables reliable and efficient data extraction which will improve the performance of subsequent AI applications.

Keywords: Human machine interface, industrial internet of things, internet of things, optical character recognition, video analytic.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 684

Authors: John Tarus, Zhendong Niu, Bakhti Khadidja

Abstract:

In recent years, e-learning recommender systems has attracted great attention as a solution towards addressing the problem of information overload in e-learning environments and providing relevant recommendations to online learners. E-learning recommenders continue to play an increasing educational role in aiding learners to find appropriate learning materials to support the achievement of their learning goals. Although general recommender systems have recorded significant success in solving the problem of information overload in e-commerce domains and providing accurate recommendations, e-learning recommender systems on the other hand still face some issues arising from differences in learner characteristics such as learning style, skill level and study level. Conventional recommendation techniques such as collaborative filtering and content-based deal with only two types of entities namely users and items with their ratings. These conventional recommender systems do not take into account the learner characteristics in their recommendation process. Therefore, conventional recommendation techniques cannot make accurate and personalized recommendations in e-learning environment. In this paper, we propose a recommendation technique combining collaborative filtering and ontology to recommend personalized learning materials to online learners. Ontology is used to incorporate the learner characteristics into the recommendation process alongside the ratings while collaborate filtering predicts ratings and generate recommendations. Furthermore, ontological knowledge is used by the recommender system at the initial stages in the absence of ratings to alleviate the cold-start problem. Evaluation results show that our proposed recommendation technique outperforms collaborative filtering on its own in terms of personalization and recommendation accuracy.

Keywords: Collaborative filtering, e-learning, ontology, recommender system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3052

Authors: Isao Taguchi, Yasuo Sugai

Abstract:

This paper proposes an efficient learning method for the layered neural networks based on the selection of training data and input characteristics of an output layer unit. Comparing to recent neural networks; pulse neural networks, quantum neuro computation, etc, the multilayer network is widely used due to its simple structure. When learning objects are complicated, the problems, such as unsuccessful learning or a significant time required in learning, remain unsolved. Focusing on the input data during the learning stage, we undertook an experiment to identify the data that makes large errors and interferes with the learning process. Our method devides the learning process into several stages. In general, input characteristics to an output layer unit show oscillation during learning process for complicated problems. The multi-stage learning method proposes by the authors for the function approximation problems of classifying learning data in a phased manner, focusing on their learnabilities prior to learning in the multi layered neural network, and demonstrates validity of the multi-stage learning method. Specifically, this paper verifies by computer experiments that both of learning accuracy and learning time are improved of the BP method as a learning rule of the multi-stage learning method. In learning, oscillatory phenomena of a learning curve serve an important role in learning performance. The authors also discuss the occurrence mechanisms of oscillatory phenomena in learning. Furthermore, the authors discuss the reasons that errors of some data remain large value even after learning, observing behaviors during learning.

Keywords: data selection, function approximation problem, multistage leaning, neural network, voluntary oscillation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1389

Authors: Mohammad R. Kavian Nezhad, Carlos F. Lange, Brian A. Fleck

Abstract:

This research presents the validation study of a computational fluid dynamics (CFD) model developed to simulate the scalar dispersion emitted from rooftop sources around the buildings at the University of Alberta North Campus. The ANSYS CFX code was used to perform the numerical simulation of the wind regime and pollutant dispersion by solving the 3D steady Reynolds-averaged Navier-Stokes (RANS) equations on a building-scale high-resolution grid. The validation study was performed in two steps. First, the CFD model performance in 24 cases (eight wind directions and three wind speeds) was evaluated by comparing the predicted flow fields with the available data from the previous measurement campaign designed at the North Campus, using the standard deviation method (SDM), while the estimated results of the numerical model showed maximum average percent errors of approximately 53% and 37% for wind incidents from the North and Northwest, respectively. Good agreement with the measurements was observed for the other six directions, with an average error of less than 30%. In the second step, the reliability of the implemented turbulence model, numerical algorithm, modeling techniques, and the grid generation scheme was further evaluated using the Mock Urban Setting Test (MUST) dispersion dataset. Different statistical measures, including the fractional bias (FB), the mean geometric bias (MG), and the normalized mean square error (NMSE), were used to assess the accuracy of the predicted dispersion field. Our CFD results are in very good agreement with the field measurements.

Keywords: CFD, plume dispersion, complex urban geometry, validation study, wind flow.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 279

Authors: Suman Senapati, Goutam Saha

Abstract:

Real world Speaker Identification (SI) application differs from ideal or laboratory conditions causing perturbations that leads to a mismatch between the training and testing environment and degrade the performance drastically. Many strategies have been adopted to cope with acoustical degradation; wavelet based Bayesian marginal model is one of them. But Bayesian marginal models cannot model the inter-scale statistical dependencies of different wavelet scales. Simple nonlinear estimators for wavelet based denoising assume that the wavelet coefficients in different scales are independent in nature. However wavelet coefficients have significant inter-scale dependency. This paper enhances this inter-scale dependency property by a Circularly Symmetric Probability Density Function (CS-PDF) related to the family of Spherically Invariant Random Processes (SIRPs) in Log Gabor Wavelet (LGW) domain and corresponding joint shrinkage estimator is derived by Maximum a Posteriori (MAP) estimator. A framework is proposed based on these to denoise speech signal for automatic speaker identification problems. The robustness of the proposed framework is tested for Text Independent Speaker Identification application on 100 speakers of POLYCOST and 100 speakers of YOHO speech database in three different noise environments. Experimental results show that the proposed estimator yields a higher improvement in identification accuracy compared to other estimators on popular Gaussian Mixture Model (GMM) based speaker model and Mel-Frequency Cepstral Coefficient (MFCC) features.

Keywords: Speaker Identification, Log Gabor Wavelet, Bayesian Bivariate Estimator, Circularly Symmetric Probability Density Function, SIRP.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1597

Authors: Razib M. Othman, Safaai Deris, Rosli M. Illias

Abstract:

Annotation of a protein sequence is pivotal for the understanding of its function. Accuracy of manual annotation provided by curators is still questionable by having lesser evidence strength and yet a hard task and time consuming. A number of computational methods including tools have been developed to tackle this challenging task. However, they require high-cost hardware, are difficult to be setup by the bioscientists, or depend on time intensive and blind sequence similarity search like Basic Local Alignment Search Tool. This paper introduces a new method of assigning highly correlated Gene Ontology terms of annotated protein sequences to partially annotated or newly discovered protein sequences. This method is fully based on Gene Ontology data and annotations. Two problems had been identified to achieve this method. The first problem relates to splitting the single monolithic Gene Ontology RDF/XML file into a set of smaller files that can be easy to assess and process. Thus, these files can be enriched with protein sequences and Inferred from Electronic Annotation evidence associations. The second problem involves searching for a set of semantically similar Gene Ontology terms to a given query. The details of macro and micro problems involved and their solutions including objective of this study are described. This paper also describes the protein sequence annotation and the Gene Ontology. The methodology of this study and Gene Ontology based protein sequence annotation tool namely extended UTMGO is presented. Furthermore, its basic version which is a Gene Ontology browser that is based on semantic similarity search is also introduced.

Keywords: automatic clustering, bioinformatics tool, gene ontology, protein sequence annotation, semantic similarity search

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3092

Authors: Yepeng Cheng, Yasuhiko Morimoto

Abstract:

Customer relationship analysis is vital for retail stores, especially for supermarkets. The point of sale (POS) systems make it possible to record the daily purchasing behaviors of customers as an identification point of sale (ID-POS) database, which can be used to analyze customer behaviors of a supermarket. The customer value is an indicator based on ID-POS database for detecting the customer loyalty of a store. In general, there are many supermarkets in a city, and other nearby competitor supermarkets significantly affect the customer value of customers of a supermarket. However, it is impossible to get detailed ID-POS databases of competitor supermarkets. This study firstly focused on the customer value and distance between a customer's home and supermarkets in a city, and then constructed the models based on logistic regression analysis to analyze correlations between distance and purchasing behaviors only from a POS database of a supermarket chain. During the modeling process, there are three primary problems existed, including the incomparable problem of customer values, the multicollinearity problem among customer value and distance data, and the number of valid partial regression coefficients. The improved customer value, Huff’s gravity model, and inverse attractiveness frequency are considered to solve these problems. This paper presents three types of models based on these three methods for loyal customer classification and competitors’ influence analysis. In numerical experiments, all types of models are useful for loyal customer classification. The type of model, including all three methods, is the most superior one for evaluating the influence of the other nearby supermarkets on customers' purchasing of a supermarket chain from the viewpoint of valid partial regression coefficients and accuracy.

Keywords: Customer value, Huff's Gravity Model, POS, retailer.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 545

Authors: Shidvash Vakilipour, Scott Ormiston, Masoud Mohammadi, Rouzbeh Riazi, Kimia Amiri, Sahar Barati

Abstract:

Two-phase and multi-phase flows are common flow types in fluid mechanics engineering. Among the basic and applied problems of these flow types, two-phase parallel flow is the one that two immiscible fluids flow in the vicinity of each other. In this type of flow, fluid properties (e.g. density, viscosity, and temperature) are different at the two sides of the interface of the two fluids. The most challenging part of the numerical simulation of two-phase flow is to determine the location of interface accurately. In the present work, a coupled interface tracking algorithm is developed based on Arbitrary Lagrangian-Eulerian (ALE) approach using a cell-centered, pressure-based, coupled solver. To validate this algorithm, an analytical solution for fully developed two-phase flow in presence of gravity is derived, and then, the results of the numerical simulation of this flow are compared with analytical solution at various flow conditions. The results of the simulations show good accuracy of the algorithm despite using a nearly coarse and uniform grid. Temporal variations of interface profile toward the steady-state solution show that a greater difference between fluids properties (especially dynamic viscosity) will result in larger traveling waves. Gravity effect studies also show that favorable gravity will result in a reduction of heavier fluid thickness and adverse gravity leads to increasing it with respect to the zero gravity condition. However, the magnitude of variation in favorable gravity is much more than adverse gravity.

Keywords: Coupled solver, gravitational force, interface tracking, Reynolds number to Froude number, two-phase flow.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 969

Authors: Mahdiyeh Zafaranchi, Ethan S. Cantor, William T. Riddell, Jess W. Everett

Abstract:

The New Jersey Department of Military and Veteran’s Affairs (NJ DMAVA) operates over 50 facilities throughout the state of New Jersey, US. NJ DMAVA is under a mandate to move toward decarbonization, which will eventually include eliminating the use of natural gas and other fossil fuels for heating. At the same time, the organization requires increased resiliency regarding electric grid disruption. These competing goals necessitate adopting the use of on-site renewables such as photovoltaic and geothermal power, as well as implementing power control strategies through microgrids. Planning for these changes requires a detailed understanding of current and future electricity use on yearly, monthly, and shorter time scales, as well as a breakdown of consumption by heating, ventilation, and air conditioning (HVAC) equipment. This paper discusses case studies of two buildings that were simulated using the QUick Energy Simulation Tool (eQUEST). Both buildings use electricity from the grid and photovoltaics. One building also uses natural gas. While electricity use data are available in hourly intervals and natural gas data are available in monthly intervals, the simulations were developed using monthly and yearly totals. This approach was chosen to reflect the information available for most NJ DMAVA facilities. Once completed, simulation results are compared to metrics recommended by several organizations to validate energy use simulations. In addition to yearly and monthly totals, the simulated peak demands are compared to actual monthly peak demand values. The simulations resulted in monthly peak demand values that were within 30% of the measured values. These benchmarks will help to assess future energy planning efforts for NJ DMAVA.

Keywords: Building Energy Modeling, eQUEST, peak demand, smart meters.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 71

Authors: Y. H. Mugahed Amran, Raizal S. M. Rashid, Farzad Hejazi, Nor Azizi Safiee, A. A. Abang Ali

Abstract:

Experimental and analytical studies were accomplished to examine the structural behavior of precast foamed concrete sandwich panel (PFCSP) under vertical in-plane shear load. PFCSP full-scale specimens with total number of six were developed with varying heights to study an important parameter slenderness ratio (H/t). The production technique of PFCSP and the procedure of test setup were described. The results obtained from the experimental tests were analysed in the context of in-plane shear strength capacity, load-deflection profile, load-strain relationship, slenderness ratio, shear cracking patterns and mode of failure. Analytical study of finite element analysis was implemented and the theoretical calculations of the ultimate in-plane shear strengths using the adopted ACI318 equation for reinforced concrete wall were determined aimed at predicting the in-plane shear strength of PFCSP. The decrease in slenderness ratio from 24 to 14 showed an increase of 26.51% and 21.91% on the ultimate in-plane shear strength capacity as obtained experimentally and in FEA models, respectively. The experimental test results, FEA models data and theoretical calculation values were compared and provided a significant agreement with high degree of accuracy. Therefore, on the basis of the results obtained, PFCSP wall has the potential use as an alternative to the conventional load-bearing wall system.

Keywords: Deflection profiles, foamed concrete, load-strain relationships, precast foamed concrete sandwich panel, slenderness ratio, vertical in-plane shear strength capacity.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2592

Authors: Zhongmin Wang, Wudong Fan, Hengshan Zhang, Yimin Zhou

Abstract:

In data-driven prognostic methods, the prediction accuracy of the estimation for remaining useful life of bearings mainly depends on the performance of health indicators, which are usually fused some statistical features extracted from vibrating signals. However, the existing health indicators have the following two drawbacks: (1) The differnet ranges of the statistical features have the different contributions to construct the health indicators, the expert knowledge is required to extract the features. (2) When convolutional neural networks are utilized to tackle time-frequency features of signals, the time-series of signals are not considered. To overcome these drawbacks, in this study, the method combining convolutional neural network with gated recurrent unit is proposed to extract the time-frequency image features. The extracted features are utilized to construct health indicator and predict remaining useful life of bearings. First, original signals are converted into time-frequency images by using continuous wavelet transform so as to form the original feature sets. Second, with convolutional and pooling layers of convolutional neural networks, the most sensitive features of time-frequency images are selected from the original feature sets. Finally, these selected features are fed into the gated recurrent unit to construct the health indicator. The results state that the proposed method shows the enhance performance than the related studies which have used the same bearing dataset provided by PRONOSTIA.

Keywords: Continuous wavelet transform, convolution neural network, gated recurrent unit, health indicators, remaining useful life.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 707

Authors: Abeer Aljohani

Abstract:

The COVID-19 virus spread has been one of the extreme pandemics across the globe. It is also referred as corona virus which is a contagious disease that continuously mutates into numerous variants. Currently, the B.1.1.529 variant labeled as Omicron is detected in South Africa. The huge spread of COVID-19 disease has affected several lives and has surged exceptional pressure on the healthcare systems worldwide. Also, everyday life and the global economy have been at stake. Numerous COVID-19 cases have produced a huge burden on hospitals as well as health workers. To reduce this burden, this paper predicts COVID-19 disease based on the symptoms and medical history of the patient. As machine learning is a widely accepted area and gives promising results for healthcare, this research presents an architecture for COVID-19 detection using ML techniques integrated with feature dimensionality reduction. This paper uses a standard University of California Irvine (UCI) dataset for predicting COVID-19 disease. This dataset comprises symptoms of 5434 patients. This paper also compares several supervised ML techniques on the presented architecture. The architecture has also utilized 10-fold cross validation process for generalization and Principal Component Analysis (PCA) technique for feature reduction. Standard parameters are used to evaluate the proposed architecture including F1-Score, precision, accuracy, recall, Receiver Operating Characteristic (ROC) and Area under Curve (AUC). The results depict that Decision tree, Random Forest and neural networks outperform all other state-of-the-art ML techniques. This result can be used to effectively identify COVID-19 infection cases.

Keywords: Supervised machine learning, COVID-19 prediction, healthcare analytics, Random Forest, Neural Network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 320

Authors: Hanifeh Imanian, Morteza Kolahdoozan

Abstract:

The purpose of this study is to present a mathematical phrase for calculating the dispersion rate of spilled oil in water column under non-breaking waves. In this regard, a multiphase numerical model is applied for which waves and oil phase were computed concurrently, and accuracy of its hydraulic calculations have been proven. More than 200 various scenarios of oil spilling in wave waters were simulated using the multiphase numerical model and its outcome were collected in a database. The recorded results were investigated to identify the major parameters affected vertical oil dispersion and finally 6 parameters were identified as main independent factors. Furthermore, some statistical tests were conducted to identify any relationship between the dependent variable (dispersed oil mass in the water column) and independent variables (water wave specifications containing height, length and wave period and spilled oil characteristics including density, viscosity and spilled oil mass). Finally, a mathematical-statistical relationship is proposed to predict dispersed oil in marine waters. To verify the proposed relationship, a laboratory example available in the literature was selected. Oil mass rate penetrated in water body computed by statistical regression was in accordance with experimental data was predicted. On this occasion, it was necessary to verify the proposed mathematical phrase. In a selected laboratory case available in the literature, mass oil rate penetrated in water body computed by suggested regression. Results showed good agreement with experimental data. The validated mathematical-statistical phrase is a useful tool for oil dispersion prediction in oil spill events in marine areas.

Keywords: Dispersion, marine environment, mathematical-statistical relationship, oil spill.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1107

Authors: A. Yavar, S. Sarmani, K. S. Khoo

Abstract:

The analysis of trace elements in human hair provides crucial insights into an individual's nutritional status and environmental exposure. This research aimed to examine the levels of toxic and essential elements in the scalp hair of school children aged 12-17 from three villages (Anglong Romiot (AR), Svay Romiot (SR), and Kampong Kong (KK)) in Cambodia's Kandal province, a region where residents are especially vulnerable to toxic elements, notably arsenic (As), due to their dietary habits, lifestyle, and environmental conditions. The scalp hair samples were analyzed using the k0-Instrumental Neutron Activation method (k0-INAA), with a six-hour irradiation period in the Malaysian Nuclear Agency (MNA) research reactor followed by High Purity Germanium (HPGe) detector use to identify the gamma peaks of radionuclides. The analysis identified 31 elements in the human hair from the study area, including As, Au, Br, Ca, Ce, Co, Dy, Eu-152m, Hg-197, Hg-203, Ho, Ir, K, La, Lu, Mn, Na, Pa, Pt-195m, Pt-197, Sb, Sc-46, Sc-47, Sm, Sn-117m, W-181, W-187, Yb-169, Yb-175, Zn, and Zn-69m. The accuracy of the method was verified through the analysis of ERM-DB001-human hair as a Certified Reference Material (CRM), with the results demonstrating consistency with the certified values. Given the prevalent arsenic pollution in the research area, the study also examined the relationship between the concentration of As and other elements using Pearson's correlation test. The outcomes offer a comprehensive resource for future investigations into toxic and essential element presence in the region. In the main body of the paper, a more extensive discussion on the implications of arsenic pollution and the correlations observed is provided to enhance understanding and inform future research directions.

Keywords: Human scalp hair, toxic and essential elements, Kandal Province, Cambodia, k0-Instrumental Neutron Activation Method.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 189

Authors: Fatema Akram, Mohammad Golam Rasul, Mohammad Masud Kamal Khan, Md. Sharif Imam Ibne Amir

Abstract:

A variety of routing techniques are available to develop surface runoff hydrographs from rainfall. The selection of runoff routing method is very vital as it is directly related to the type of watershed and the required degree of accuracy. There are different modelling softwares available to explore the rainfall-runoff process in urban areas. XPSTORM, a link-node based, integrated stormwater modelling software, has been used in this study for developing surface runoff hydrograph for a Golf course area located in Rockhampton in Central Queensland in Australia. Four commonly used methods, namely SWMM runoff, Kinematic wave, Laurenson, and Time-Area are employed to generate runoff hydrograph for design storm of this study area. In runoff mode of XPSTORM, the rainfall, infiltration, evaporation and depression storage for subcatchments were simulated and the runoff from the subcatchment to collection node was calculated. The simulation results are presented, discussed and compared. The total surface runoff generated by SWMM runoff, Kinematic wave and Time-Area methods are found to be reasonably close, which indicates any of these methods can be used for developing runoff hydrograph of the study area. Laurenson method produces a comparatively less amount of surface runoff, however, it creates highest peak of surface runoff among all which may be suitable for hilly region. Although the Laurenson hydrograph technique is widely acceptable surface runoff routing technique in Queensland (Australia), extensive investigation is recommended with detailed topographic and hydrologic data in order to assess its suitability for use in the case study area.

Keywords: ARI, design storm, IFD, rainfall temporal pattern, routing techniques, surface runoff, XPSTORM.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 4992

Authors: Vipul M. Patel, Hemantkumar B. Mehta

Abstract:

Technological innovations in electronic world demand novel, compact, simple in design, less costly and effective heat transfer devices. Closed Loop Pulsating Heat Pipe (CLPHP) is a passive phase change heat transfer device and has potential to transfer heat quickly and efficiently from source to sink. Thermal performance of a CLPHP is governed by various parameters such as number of U-turns, orientations, input heat, working fluids and filling ratio. The present paper is an attempt to predict the thermal performance of a CLPHP using Artificial Neural Network (ANN). Filling ratio and heat input are considered as input parameters while thermal resistance is set as target parameter. Types of neural networks considered in the present paper are radial basis, generalized regression, linear layer, cascade forward back propagation, feed forward back propagation; feed forward distributed time delay, layer recurrent and Elman back propagation. Linear, logistic sigmoid, tangent sigmoid and Radial Basis Gaussian Function are used as transfer functions. Prediction accuracy is measured based on the experimental data reported by the researchers in open literature as a function of Mean Absolute Relative Deviation (MARD). The prediction of a generalized regression ANN model with spread constant of 4.8 is found in agreement with the experimental data for MARD in the range of ±1.81%.

Keywords: ANN models, CLPHP, filling ratio, generalized regression, spread constant.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1138