Search results for: dimensional accuracy

Authors: Qian Liu, Steve Furber

Abstract:

To explore how the brain may recognise objects in its general,accurate and energy-efficient manner, this paper proposes the use of a neuromorphic hardware system formed from a Dynamic Video Sensor (DVS) silicon retina in concert with the SpiNNaker real-time Spiking Neural Network (SNN) simulator. As a first step in the exploration on this platform a recognition system for dynamic hand postures is developed, enabling the study of the methods used in the visual pathways of the brain. Inspired by the behaviours of the primary visual cortex, Convolutional Neural Networks (CNNs) are modelled using both linear perceptrons and spiking Leaky Integrate-and-Fire (LIF) neurons. In this study’s largest configuration using these approaches, a network of 74,210 neurons and 15,216,512 synapses is created and operated in real-time using 290 SpiNNaker processor cores in parallel and with 93.0% accuracy. A smaller network using only 1/10th of the resources is also created, again operating in real-time, and it is able to recognise the postures with an accuracy of around 86.4% - only 6.6% lower than the much larger system. The recognition rate of the smaller network developed on this neuromorphic system is sufficient for a successful hand posture recognition system, and demonstrates a much improved cost to performance trade-off in its approach.

Keywords: Spiking neural network (SNN), convolutional neural network (CNN), posture recognition, neuromorphic system.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2021

Authors: Belkacem Selma, Boumediene Selma, Samira Chouraqui, Hanifi Missoum, Tourkia Guerzou

Abstract:

Natural disasters have occurred and will continue to cause human and material damage. Therefore, the idea of "preventing" natural disasters will never be possible. However, their prediction is possible with the advancement of technology. Even if natural disasters are effectively inevitable, their consequences may be partly controlled. The rapid growth and progress of artificial intelligence (AI) had a major impact on the prediction of natural disasters and risk assessment which are necessary for effective disaster reduction. Earthquake prediction to prevent the loss of human lives and even property damage is an important factor; that, is why it is crucial to develop techniques for predicting this natural disaster. This study aims to analyze the ability of artificial neural networks (ANNs) to predict earthquakes that occur in a given area. The used data describe the problem of high energy (higher than 104 J) seismic bumps forecasting in a coal mine using two long walls as an example. For this purpose, seismic bumps data obtained from mines have been analyzed. The results obtained show that the ANN is able to predict earthquake parameters with  high accuracy; the classification accuracy through neural networks is more than 94%, and the models developed are efficient and robust and depend only weakly on the initial database.

Keywords: Earthquake prediction, artificial intelligence, AI, Artificial Neural Network, ANN, seismic bumps.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1116

Authors: Peng Shen Ong, Yoong Choon Chang, Chee Pun Ooi, Ettikan K. Karuppiah, Shahirina Mohd Tahir

Abstract:

Falling has been one of the major concerns and threats to the independence of the elderly in their daily lives. With the worldwide significant growth of the aging population, it is essential to have a promising solution of fall detection which is able to operate at high accuracy in real-time and supports large scale implementation using multiple cameras. Field Programmable Gate Array (FPGA) is a highly promising tool to be used as a hardware accelerator in many emerging embedded vision based system. Thus, it is the main objective of this paper to present an FPGA-based solution of visual based fall detection to meet stringent real-time requirements with high accuracy. The hardware architecture of visual based fall detection which utilizes the pixel locality to reduce memory accesses is proposed. By exploiting the parallel and pipeline architecture of FPGA, our hardware implementation of visual based fall detection using FGPA is able to achieve a performance of 60fps for a series of video analytical functions at VGA resolutions (640x480). The results of this work show that FPGA has great potentials and impacts in enabling large scale vision system in the future healthcare industry due to its flexibility and scalability.

Keywords: Fall detection, FPGA, hardware implementation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2442

Authors: Monika Neda, Elena Nikonova

Abstract:

We present a numerical study of the sensitivity of the so called time relaxation family of models of fluid motion with respect to the time relaxation parameter χ on the two dimensional cavity problem. The goal of the study is to compute and compare the sensitivity of the model using finite difference method (FFD) and sensitivity equation method (SEM).

Keywords: Sensitivity, time relaxation, deconvolution, Navier- Stokes equations.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1305

Authors: Nonlapun Meenil, Pisitpong Intarapong, Thitima Wongsheree, Pranchalee Samanpiboon

Abstract:

In Thailand, once pineapples are harvested, they must be classified into two classes based on their sweetness: sweet and unsweet. This paper has studied and developed the assessment of internal quality of pineapples using a low-cost compact spectroscopy sensor according to the spectroscopy approach and Neural Network (NN). During the experiments, Batavia pineapples were utilized, generating 100 samples. The extracted pineapple juice of each sample was used to determine the Soluble Solid Content (SSC) labeling into sweet and unsweet classes. In terms of experimental equipment, the sensor cover was specifically designed to install the sensor and light source to read the reflectance at a five mm depth from pineapple flesh. By using a spectroscopy sensor, data on visible and near-infrared reflectance (Vis-NIR) were collected. The NN was used to classify the pineapple classes. Before the classification step, the preprocessing methods, which are class balancing, data shuffling, and standardization, were applied. The 510 nm and 900 nm reflectance values of the middle parts of pineapples were used as features of the NN. With the sequential model and ReLU activation function, 100% accuracy of the training set and 76.67% accuracy of the test set were achieved. According to the abovementioned information, using a low-cost compact spectroscopy sensor has achieved favorable results in classifying the sweetness of the two classes of pineapples.

Keywords: Spectroscopy, soluble solid content, pineapple, neural network.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 59

Authors: An Hong Nguyen, Chatpan Chintanapakdee, Toshiro Hayashikawa

Abstract:

Presented herein is an assessment of current nonlinear static procedures (NSPs) for seismic evaluation of bucklingrestrained braced frames (BRBFs) which have become a favorable lateral-force resisting system for earthquake resistant buildings. The bias and accuracy of modal, improved modal pushover analysis (MPA, IMPA) and mass proportional pushover (MPP) procedures are comparatively investigated when they are applied to BRBF buildings subjected to two sets of strong ground motions. The assessment is based on a comparison of seismic displacement demands such as target roof displacements, peak floor/roof displacements and inter-story drifts. The NSP estimates are compared to 'exact' results from nonlinear response history analysis (NLRHA). The response statistics presented show that the MPP procedure tends to significantly overestimate seismic demands of lower stories of tall buildings considered in this study while MPA and IMPA procedures provide reasonably accurate results in estimating maximum inter-story drift over all stories of studied BRBF systems.

Keywords: Buckling-restrained braced frames, nonlinearresponse history analysis, nonlinear static procedure, seismicdemands.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1922

Authors: Faheem Ahmed, Fareed Ahmed, Yongheng Guo, Yong Yang

Abstract:

This paper deals with a high-order accurate Runge Kutta Discontinuous Galerkin (RKDG) method for the numerical solution of the wave equation, which is one of the simple case of a linear hyperbolic partial differential equation. Nodal DG method is used for a finite element space discretization in 'x' by discontinuous approximations. This method combines mainly two key ideas which are based on the finite volume and finite element methods. The physics of wave propagation being accounted for by means of Riemann problems and accuracy is obtained by means of high-order polynomial approximations within the elements. High order accurate Low Storage Explicit Runge Kutta (LSERK) method is used for temporal discretization in 't' that allows the method to be nonlinearly stable regardless of its accuracy. The resulting RKDG methods are stable and high-order accurate. The L1 ,L2 and L∞ error norm analysis shows that the scheme is highly accurate and effective. Hence, the method is well suited to achieve high order accurate solution for the scalar wave equation and other hyperbolic equations.

Keywords: Nodal Discontinuous Galerkin Method, RKDG, Scalar Wave Equation, LSERK

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2446

Authors: A. Moradi, S. Khodadadiyan

Abstract:

In this paper, one-dimensional analysis of flow in a single-stage gas gun is conducted. The compressible inviscid flow equations are numerically solved by the second-order Roe TVD method, by using moving boundaries. For investigation of real gas effect the Noble-Able equation is applied. The numerical results are compared with the experimental data to validate the numerical scheme. The results show that with using the Noble-Able equation, the muzzle velocity decreases.

Keywords: Gas gun, Roe, projectile, muzzle velocity

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2271

Authors: Kazuki Kamada, Haruka Yamashita

Abstract:

In Japan, taxi is one of the popular transportations and taxi industry is one of the big businesses. However, in recent years, there has been a difficult problem of reducing the number of taxi drivers. In the taxi business, mainly three passenger catching methods are applied. One style is "cruising" that drivers catches passengers while driving on a road. Second is "waiting" that waits passengers near by the places with many requirements for taxies such as entrances of hospitals, train stations. The third one is "dispatching" that is allocated based on the contact from the taxi company. Above all, the cruising taxi drivers need the experience and intuition for finding passengers, and it is difficult to decide "the destination for cruising". The strong recommendation system for the cruising taxies supports the new drivers to find passengers, and it can be the solution for the decreasing the number of drivers in the taxi industry. In this research, we propose a method of recommending a destination for cruising taxi drivers. On the other hand, as a machine learning technique, the embedding models that embed the high dimensional data to a low dimensional space is widely used for the data analysis, in order to represent the relationship of the meaning between the data clearly. Taxi drivers have their favorite courses based on their experiences, and the courses are different for each driver. We assume that the course of cruising taxies has meaning such as the course for finding business man passengers (go around the business area of the city of go to main stations) and course for finding traveler passengers (go around the sightseeing places or big hotels), and extract the meaning of their destinations. We analyze the cruising history data of taxis based on the embedding model and propose the recommendation system for passengers. Finally, we demonstrate the recommendation of destinations for cruising taxi drivers based on the real-world data analysis using proposing method.

Keywords: Taxi industry, decision making, recommendation system, embedding model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 394

Authors: Rahil Garnavi, Mohammad Aldeen, M. Emre Celebi, Alauddin Bhuiyan, Constantinos Dolianitis, George Varigos

Abstract:

Automatic segmentation of skin lesions is the first step towards development of a computer-aided diagnosis of melanoma. Although numerous segmentation methods have been developed, few studies have focused on determining the most discriminative and effective color space for melanoma application. This paper proposes a novel automatic segmentation algorithm using color space analysis and clustering-based histogram thresholding, which is able to determine the optimal color channel for segmentation of skin lesions. To demonstrate the validity of the algorithm, it is tested on a set of 30 high resolution dermoscopy images and a comprehensive evaluation of the results is provided, where borders manually drawn by four dermatologists, are compared to automated borders detected by the proposed algorithm. The evaluation is carried out by applying three previously used metrics of accuracy, sensitivity, and specificity and a new metric of similarity. Through ROC analysis and ranking the metrics, it is shown that the best results are obtained with the X and XoYoR color channels which results in an accuracy of approximately 97%. The proposed method is also compared with two state-ofthe- art skin lesion segmentation methods, which demonstrates the effectiveness and superiority of the proposed segmentation method.

Keywords: Border detection, Color space analysis, Dermoscopy, Histogram thresholding, Melanoma, Segmentation.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2045

Authors: Jagadish H. Pujar

Abstract:

Fuzzy Load forecasting plays a paramount role in the operation and management of power systems. Accurate estimation of future power demands for various lead times facilitates the task of generating power reliably and economically. The forecasting of future loads for a relatively large lead time (months to few years) is studied here (long term load forecasting). Among the various techniques used in forecasting load, artificial intelligence techniques provide greater accuracy to the forecasts as compared to conventional techniques. Fuzzy Logic, a very robust artificial intelligent technique, is described in this paper to forecast load on long term basis. The paper gives a general algorithm to forecast long term load. The algorithm is an Extension of Short term load forecasting method to Long term load forecasting and concentrates not only on the forecast values of load but also on the errors incorporated into the forecast. Hence, by correcting the errors in the forecast, forecasts with very high accuracy have been achieved. The algorithm, in the paper, is demonstrated with the help of data collected for residential sector (LT2 (a) type load: Domestic consumers). Load, is determined for three consecutive years (from April-06 to March-09) in order to demonstrate the efficiency of the algorithm and to forecast for the next two years (from April-09 to March-11).

Keywords: Fuzzy Logic Control (FLC), Data DependantFactors(DDF), Model Dependent Factors(MDF), StatisticalError(SE), Short Term Load Forecasting (STLF), MiscellaneousError(ME).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2439

Authors: Burçin Saltık, Levent Genç

Abstract:

In this study, it was aimed to determine a route for identification of rice cultivation areas within Thrace and Marmara regions of Turkey using remote sensing and GIS. Landsat 8 (OLI-TIRS) imageries acquired in production season of 2013 with 181/32 Path/Row number were used. Four different seasonal images were generated utilizing original bands and different transformation techniques. All images were classified individually using supervised classification techniques and Land Use Land Cover Maps (LULC) were generated with 8 classes. Areas (ha, %) of each classes were calculated. In addition, district-based rice distribution maps were developed and results of these maps were compared with Turkish Statistical Institute (TurkSTAT; TSI)’s actual rice cultivation area records. Accuracy assessments were conducted, and most accurate map was selected depending on accuracy assessment and coherency with TSI results. Additionally, rice areas on over 4° slope values were considered as mis-classified pixels and they eliminated using slope map and GIS tools. Finally, randomized rice zones were selected to obtain maximum-minimum value ranges of each date (May, June, July, August, September images separately) NDVI, LSWI, and LST images to test whether they may be used for rice area determination via raster calculator tool of ArcGIS. The most accurate classification for rice determination was obtained from seasonal LSWI LULC map, and considering TSI data and accuracy assessment results and mis-classified pixels were eliminated from this map. According to results, 83151.5 ha of rice areas exist within study area. However, this result is higher than TSI records with an area of 12702.3 ha. Use of maximum-minimum range of rice area NDVI, LSWI, and LST was tested in Meric district. It was seen that using the value ranges obtained from July imagery, gave the closest results to TSI records, and the difference was only 206.4 ha. This difference is normal due to relatively low resolution of images. Thus, employment of images with higher spectral, spatial, temporal and radiometric resolutions may provide more reliable results.

Keywords: Landsat 8 (OLI-TIRS), LULC, spectral indices, rice.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1271

Authors: Lily Ingsrisawang, Supawadee Ingsriswang, Saisuda Somchit, Prasert Aungsuratana, Warawut Khantiyanan

Abstract:

This paper presents the methodology from machine learning approaches for short-term rain forecasting system. Decision Tree, Artificial Neural Network (ANN), and Support Vector Machine (SVM) were applied to develop classification and prediction models for rainfall forecasts. The goals of this presentation are to demonstrate (1) how feature selection can be used to identify the relationships between rainfall occurrences and other weather conditions and (2) what models can be developed and deployed for predicting the accurate rainfall estimates to support the decisions to launch the cloud seeding operations in the northeastern part of Thailand. Datasets collected during 2004-2006 from the Chalermprakiat Royal Rain Making Research Center at Hua Hin, Prachuap Khiri khan, the Chalermprakiat Royal Rain Making Research Center at Pimai, Nakhon Ratchasima and Thai Meteorological Department (TMD). A total of 179 records with 57 features was merged and matched by unique date. There are three main parts in this work. Firstly, a decision tree induction algorithm (C4.5) was used to classify the rain status into either rain or no-rain. The overall accuracy of classification tree achieves 94.41% with the five-fold cross validation. The C4.5 algorithm was also used to classify the rain amount into three classes as no-rain (0-0.1 mm.), few-rain (0.1- 10 mm.), and moderate-rain (>10 mm.) and the overall accuracy of classification tree achieves 62.57%. Secondly, an ANN was applied to predict the rainfall amount and the root mean square error (RMSE) were used to measure the training and testing errors of the ANN. It is found that the ANN yields a lower RMSE at 0.171 for daily rainfall estimates, when compared to next-day and next-2-day estimation. Thirdly, the ANN and SVM techniques were also used to classify the rain amount into three classes as no-rain, few-rain, and moderate-rain as above. The results achieved in 68.15% and 69.10% of overall accuracy of same-day prediction for the ANN and SVM models, respectively. The obtained results illustrated the comparison of the predictive power of different methods for rainfall estimation.

Keywords: Machine learning, decision tree, artificial neural network, support vector machine, root mean square error.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3193

Authors: Mohd Fikri Azli bin Abdullah, Khairul Anwar bin Kamarul Hatta, Esther Jeganathan

Abstract:

WiFi has become an essential technology that is widely used nowadays. It is famous due to its convenience to be used with mobile devices. This is especially true for Internet users worldwide that use WiFi connections. There are many location based services that are available nowadays which uses Wireless Fidelity (WiFi) signal fingerprinting. A common example that is gaining popularity in this era would be Foursquare. In this work, the WiFi signal would be used to estimate the user or client’s location. Similar to GPS, fingerprinting method needs a floor plan to increase the accuracy of location estimation. Still, the factor of inconsistent WiFi signal makes the estimation defer at different time intervals. Given so, an adaptive method is needed to obtain the most accurate signal at all times. WiFi signals are heavily distorted by external factors such as physical objects, radio frequency interference, electrical interference, and environmental factors to name a few. Due to these factors, this work uses a method of reducing the signal noise and estimation using the Nearest Neighbour based on past activities of the signal to increase the signal accuracy up to more than 80%. The repository yet increases the accuracy by using Artificial Neural Network (ANN) pattern matching. The repository acts as the server cum support of the client side application decision. Numerous previous works has adapted the methods of collecting signal strengths in the repository over the years, but mostly were just static. In this work, proposed solutions on how the adaptive method is done to match the signal received to the data in the repository are highlighted. With the said approach, location estimation can be done more accurately. Adaptive update allows the latest location fingerprint to be stored in the repository. Furthermore, any redundant location fingerprints are removed and only the updated version of the fingerprint is stored in the repository. How the location estimation of the user can be predicted would be highlighted more in the proposed solution section. After some studies on previous works, it is found that the Artificial Neural Network is the most feasible method to deploy in updating the repository and making it adaptive. The Artificial Neural Network functions are to do the pattern matching of the WiFi signal to the existing data available in the repository.

Keywords: Adaptive Repository, Artificial Neural Network, Location Estimation, Nearest Neighbour Euclidean Distance, WiFi RSSI Fingerprinting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3435

Authors: İnci M. Erhan

Abstract:

A numerical method for solving the time-independent Schrödinger equation of a particle moving freely in a three-dimensional axisymmetric region is developed. The boundary of the region is defined by an arbitrary analytic function. The method uses a coordinate transformation and an expansion in eigenfunctions. The effectiveness is checked and confirmed by applying the method to a particular example, which is a prolate spheroid.

Keywords: Bessel functions, Eigenfunction expansion, Quantum billiard, Schrödinger equation, Spherical harmonics

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 5184

Authors: Arunesh Chandra, Pankaj Chandna, Surinder Deswal, Rajesh Kumar Mishra, Rajender Kumar

Abstract:

The arm length, hand length, hand breadth and middle finger length of 1540 right-handed industrial workers of Haryana state was used to assess the relationship between the upper limb dimensions and stature. Initially, the data were analyzed using basic univariate analysis and independent t-tests; then simple and multiple linear regression models were used to estimate stature using SPSS (version 17). There was a positive correlation between upper limb measurements (hand length, hand breadth, arm length and middle finger length) and stature (p < 0.01), which was highest for hand length. The accuracy of stature prediction ranged from ± 54.897 mm to ± 58.307 mm. The use of multiple regression equations gave better results than simple regression equations. This study provides new forensic standards for stature estimation from the upper limb measurements of male industrial workers of Haryana (India). The results of this research indicate that stature can be determined using hand dimensions with accuracy, when only upper limb is available due to any reasons likewise explosions, train/plane crashes, mutilated bodies, etc. The regression formula derived in this study will be useful for anatomists, archaeologists, anthropologists, design engineers and forensic scientists for fairly prediction of stature using regression equations.

Keywords: Anthropometric dimensions, Forensic identification, Industrial workers, Stature prediction.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2919

Authors: S. Chaisit, H.Y. Kung, N.T. Phuong

Abstract:

Radio frequency identification (RFID) applications have grown rapidly in many industries, especially in indoor location identification. The advantage of using received signal strength indicator (RSSI) values as an indoor location measurement method is a cost-effective approach without installing extra hardware. Because the accuracy of many positioning schemes using RSSI values is limited by interference factors and the environment, thus it is challenging to use RFID location techniques based on integrating positioning algorithm design. This study proposes the location estimation approach and analyzes a scheme relying on RSSI values to minimize location errors. In addition, this paper examines different factors that affect location accuracy by integrating the backpropagation neural network (BPN) with the LANDMARC algorithm in a training phase and an online phase. First, the training phase computes coordinates obtained from the LANDMARC algorithm, which uses RSSI values and the real coordinates of reference tags as training data for constructing an appropriate BPN architecture and training length. Second, in the online phase, the LANDMARC algorithm calculates the coordinates of tracking tags, which are then used as BPN inputs to obtain location estimates. The results show that the proposed scheme can estimate locations more accurately compared to LANDMARC without extra devices.

Keywords: BPNs, indoor location, location estimation, intelligent location identification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1988

Authors: Xinli Zhang

Abstract:

In this paper, we consider the nonlinear delay dynamic system xΔ(t) = p(t)f1(y(t)), yΔ(t) = −q(t)f2(x(t − τ )). We obtain some necessary and sufficient conditions for the existence of nonoscillatory solutions with special asymptotic properties of the system. We generalize the known results in the literature. One example is given to illustrate the results.

Keywords: Dynamic system, oscillation, time scales, two-dimensional.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1267

Authors: Sergey Sorokin, Irina Sorokina, Alexander Yazenin

Abstract:

We present a solution to the Maxmin u/E parameters estimation problem of possibility distributions in m-dimensional case. Our method is based on geometrical approach, where minimal area enclosing ellipsoid is constructed around the sample. Also we demonstrate that one can improve results of well-known algorithms in fuzzy model identification task using Maxmin u/E parameters estimation.

Keywords: Possibility distribution, parameters estimation, Maxmin u/E estimator, fuzzy model identification.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2403

Authors: Yohei Saika, Tatsuya Uezu

Abstract:

We constructed a method of phase unwrapping for a typical wave-front by utilizing the maximizer of the posterior marginal (MPM) estimate corresponding to equilibrium statistical mechanics of the three-state Ising model on a square lattice on the basis of an analogy between statistical mechanics and Bayesian inference. We investigated the static properties of an MPM estimate from a phase diagram using Monte Carlo simulation for a typical wave-front with synthetic aperture radar (SAR) interferometry. The simulations clarified that the surface-consistency conditions were useful for extending the phase where the MPM estimate was successful in phase unwrapping with a high degree of accuracy and that introducing prior information into the MPM estimate also made it possible to extend the phase under the constraint of the surface-consistency conditions with a high degree of accuracy. We also found that the MPM estimate could be used to reconstruct the original wave-fronts more smoothly, if we appropriately tuned hyper-parameters corresponding to temperature to utilize fluctuations around the MAP solution. Also, from the viewpoint of statistical mechanics of the Q-Ising model, we found that the MPM estimate was regarded as a method for searching the ground state by utilizing thermal fluctuations under the constraint of the surface-consistency condition.

Keywords: Bayesian inference, maximizer of the posterior marginal estimate, phase unwrapping, Monte Carlo simulation, statistical mechanics

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1685

Authors: Rodolfo Lorbieski, Silvia Modesto Nassar

Abstract:

Many supervised machine learning tasks require decision making across numerous different classes. Multi-class classification has several applications, such as face recognition, text recognition and medical diagnostics. The objective of this article is to analyze an adapted method of Stacking in multi-class problems, which combines ensembles within the ensemble itself. For this purpose, a training similar to Stacking was used, but with three levels, where the final decision-maker (level 2) performs its training by combining outputs from the tree-based pair of meta-classifiers (level 1) from Bayesian families. These are in turn trained by pairs of base classifiers (level 0) of the same family. This strategy seeks to promote diversity among the ensembles forming the meta-classifier level 2. Three performance measures were used: (1) accuracy, (2) area under the ROC curve, and (3) time for three factors: (a) datasets, (b) experiments and (c) levels. To compare the factors, ANOVA three-way test was executed for each performance measure, considering 5 datasets by 25 experiments by 3 levels. A triple interaction between factors was observed only in time. The accuracy and area under the ROC curve presented similar results, showing a double interaction between level and experiment, as well as for the dataset factor. It was concluded that level 2 had an average performance above the other levels and that the proposed method is especially efficient for multi-class problems when compared to binary problems.

Keywords: Stacking, multi-layers, ensemble, multi-class.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1062

Authors: L. C. Moreira, M. Kauffman

Abstract:

This paper outlines the results of an experimental research on deploying an emerging augmented reality (AR) system for real-time task assistance (or work instructions) of highly customised and high-risk manual operations. The focus is on human operators’ training effectiveness and performance and the aim is to test if such technologies can support enhancing the knowledge retention levels and accuracy of task execution to improve health and safety (H&S). An AR enhanced assembly method is proposed and experimentally tested using a real industrial process as case study for electric vehicles’ (EV) battery module assembly. The experimental results revealed that the proposed method improved the training practices and performance through increases in the knowledge retention levels from 40% to 84%, and accuracy of task execution from 20% to 71%, when compared to the traditional paper-based method. The results of this research validate and demonstrate how emerging technologies are advancing the choice for manual, hybrid or fully automated processes by promoting the XR-assisted processes, and the connected worker (a vision for Industry 4 and 5.0), and supporting manufacturing become more resilient in times of constant market changes.

Keywords: Augmented reality, extended reality, connected worker, XR-assisted operator, manual assembly 4.0, industry 5.0, smart training, battery assembly.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 341

Authors: Bradley Christensen, Kevin T. McCusker, Daniel J. Gauthier, Daniel Kumor, Venkat Chandar, P. G. Kwiat

Abstract:

We report on a high-speed quantum cryptography system that utilizes simultaneous entanglement in polarization and in “time-bins". With multiple degrees of freedom contributing to the secret key, we can achieve over ten bits of random entropy per detected coincidence. In addition, we collect from multiple spots o the downconversion cone to further amplify the data rate, allowing usto achieve over 10 Mbits of secure key per second.

Keywords: Downconversion, Hyper-entanglement, Quantum Cryptography

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1669

Authors: Mohammad Pooyan, Ali Taheri, Morteza Moazami-Goudarzi, Iman Saboori

Abstract:

In this paper we present a novel approach for wavelet compression of electrocardiogram (ECG) signals based on the set partitioning in hierarchical trees (SPIHT) coding algorithm. SPIHT algorithm has achieved prominent success in image compression. Here we use a modified version of SPIHT for one dimensional signals. We applied wavelet transform with SPIHT coding algorithm on different records of MIT-BIH database. The results show the high efficiency of this method in ECG compression.

Keywords: ECG compression, wavelet, SPIHT.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2376

Authors: Erna T. Herdiani, Maman A. Djauhari

Abstract:

In recent years, the use of vector variance as a measure of multivariate variability has received much attention in wide range of statistics. This paper deals with a more economic measure of multivariate variability, defined as vector variance minus all duplication elements. For high dimensional data, this will increase the computational efficiency almost 50 % compared to the original vector variance. Its sampling distribution will be investigated to make its applications possible.

Keywords: Asymptotic distribution, covariance matrix, likelihood ratio test, vector variance.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1540

Authors: Guanqiao Wang, Hongyang Yu

Abstract:

There is a lot of repetitive work in the traditional construction industry. These repetitive tasks can significantly improve production efficiency by replacing manual tasks with robots. Therefore, robots appear more and more frequently in the construction industry. Navigation and positioning is a very important task for construction robots, and the requirements for accuracy of positioning are very high. Traditional indoor robots mainly use radio frequency or vision methods for positioning. Compared with ordinary robots, the indoor plastering robot needs to be positioned closer to the wall for wall plastering, so the requirements for construction positioning accuracy are higher, and the traditional navigation positioning method has a large error, which will cause the robot to move. Without the exact position, the wall cannot be plastered or the error of plastering the wall is large. A positioning method is proposed, which is assisted by line lasers and uses image processing-based positioning to perform more accurate positioning on the traditional positioning work. In actual work, filter, edge detection, Hough transform and other operations are performed on the images captured by the camera. Each time the position of the laser line is found, it is compared with the standard value, and the position of the robot is moved or rotated to complete the positioning work. The experimental results show that the actual positioning error is reduced to less than 0.5 mm by this accurate positioning method.

Keywords: Indoor plastering robot, navigation, precise positioning, line laser, image processing.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 483

Authors: Chongya Song, Kang Yen, Alexander Pons, Jin Liu

Abstract:

In the field of machine learning, the ensemble has been employed as a common methodology to improve the performance upon multiple base classifiers. However, the true predictions are often canceled out by the false ones during consensus due to a phenomenon called “curse of correlation” which is represented as the strong interferences among the predictions produced by the base classifiers. In addition, the existing practices are still not able to effectively mitigate the problem of imbalanced classification. Based on the analysis on our experiment results, we conclude that the two problems are caused by some inherent deficiencies in the approach of consensus. Therefore, we create an enhanced ensemble algorithm which adopts a designed rank-based chain-mode consensus to overcome the two problems. In order to evaluate the proposed ensemble algorithm, we employ a well-known benchmark data set NSL-KDD (the improved version of dataset KDDCup99 produced by University of New Brunswick) to make comparisons between the proposed and 8 common ensemble algorithms. Particularly, each compared ensemble classifier uses the same 22 base classifiers, so that the differences in terms of the improvements toward the accuracy and reliability upon the base classifiers can be truly revealed. As a result, the proposed rank-based chain-mode consensus is proved to be a more effective ensemble solution than the traditional consensus approach, which outperforms the 8 ensemble algorithms by 20% on almost all compared metrices which include accuracy, precision, recall, F1-score and area under receiver operating characteristic curve.

Keywords: Consensus, curse of correlation, imbalanced classification, rank-based chain-mode ensemble.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 691

Authors: Jack R. McKenzie, Peter A. Appleby, Thomas House, Neil Walton

Abstract:

Cold-start is a notoriously difficult problem which can occur in recommendation systems, and arises when there is insufficient information to draw inferences for users or items. To address this challenge, a contextual bandit algorithm – the Fast Approximate Bayesian Contextual Cold Start Learning algorithm (FAB-COST) – is proposed, which is designed to provide improved accuracy compared to the traditionally used Laplace approximation in the logistic contextual bandit, while controlling both algorithmic complexity and computational cost. To this end, FAB-COST uses a combination of two moment projection variational methods: Expectation Propagation (EP), which performs well at the cold start, but becomes slow as the amount of data increases; and Assumed Density Filtering (ADF), which has slower growth of computational cost with data size but requires more data to obtain an acceptable level of accuracy. By switching from EP to ADF when the dataset becomes large, it is able to exploit their complementary strengths. The empirical justification for FAB-COST is presented, and systematically compared to other approaches on simulated data. In a benchmark against the Laplace approximation on real data consisting of over 670, 000 impressions from autotrader.co.uk, FAB-COST demonstrates at one point increase of over 16% in user clicks. On the basis of these results, it is argued that FAB-COST is likely to be an attractive approach to cold-start recommendation systems in a variety of contexts.

Keywords: Cold-start, expectation propagation, multi-armed bandits, Thompson sampling, variational inference.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 524

Authors: Xiaoqing Wang, Junfeng Wang, Xiaolan Zhu

Abstract:

Android operating system has been recognized by most application developers because of its good open-source and compatibility, which enriches the categories of applications greatly. However, it has become the target of malware attackers due to the lack of strict security supervision mechanisms, which leads to the rapid growth of malware, thus bringing serious safety hazards to users. Therefore, it is critical to detect Android malware effectively. Generally, the permissions declared in the AndroidManifest.xml can reflect the function and behavior of the application to a large extent. Since current Android system has not any restrictions to the number of permissions that an application can request, developers tend to apply more than actually needed permissions in order to ensure the successful running of the application, which results in the abuse of permissions. However, some traditional detection methods only consider the requested permissions and ignore whether it is actually used, which leads to incorrect identification of some malwares. Therefore, a machine learning detection method based on the actually used permissions combination and API calls was put forward in this paper. Meanwhile, several experiments are conducted to evaluate our methodology. The result shows that it can detect unknown malware effectively with higher true positive rate and accuracy while maintaining a low false positive rate. Consequently, the AdaboostM1 (J48) classification algorithm based on information gain feature selection algorithm has the best detection result, which can achieve an accuracy of 99.8%, a true positive rate of 99.6% and a lowest false positive rate of 0.

Keywords: Android, permissions combination, API calls, machine learning.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1888

Authors: A. Emre Ozturk, Ergun Ercelebi

Abstract:

Autonomous robotic systems need an equipment like a human eye for their movement. In this study a 3D laser scanner has been designed and implemented for those autonomous robotic systems. In general 3D laser scanners are using 2 dimension laser range finders that are moving on one-axis (1D) to generate the model. In this study, the model has been obtained by a one-dimensional laser range finder that is moving in two –axis (2D) and because of this the laser scanner has been produced cheaper.

Keywords: 3D Laser Scanner, embedded systems.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2402