Search results for: computational accuracy

Authors: Husam Kaid, Abdulrahman Al-Ahmari, Zhiwu Li

Abstract:

This paper develops a robust deadlock control technique for shared and unreliable resources in automated manufacturing systems (AMSs) based on structural analysis and colored Petri nets, which consists of three steps. The first step involves using strict minimal siphon control to create a live (deadlock-free) system that does not consider resource failure. The second step uses an approach based on colored Petri net, in which all monitors designed in the first step are merged into a single monitor. The third step addresses the deadlock control problems caused by resource failures. For all resource failures in the Petri net model a common recovery subnet based on colored petri net is proposed. The common recovery subnet is added to the obtained system at the second step to make the system reliable. The proposed approach is evaluated using an AMS from the literature. The results show that the proposed approach can be applied to an unreliable complex Petri net model, has a simpler structure and less computational complexity, and can obtain one common recovery subnet to model all resource failures.

Keywords: automated manufacturing system, colored Petri net, deadlocks, siphon

Procedia PDF Downloads 129

Authors: Aqsa Ali, Aleem Mushtaq, Attaullah Memon, Monna

Abstract:

In this paper, we present a low cost design for a smart glove that can perform sign language recognition to assist the speech impaired people. Specifically, we have designed and developed an Assistive Hand Gesture Interpreter that recognizes hand movements relevant to the American Sign Language (ASL) and translates them into text for display on a Thin-Film-Transistor Liquid Crystal Display (TFT LCD) screen as well as synthetic speech. Linear Bayes Classifiers and Multilayer Neural Networks have been used to classify 11 feature vectors obtained from the sensors on the glove into one of the 27 ASL alphabets and a predefined gesture for space. Three types of features are used; bending using six bend sensors, orientation in three dimensions using accelerometers and contacts at vital points using contact sensors. To gauge the performance of the presented design, the training database was prepared using five volunteers. The accuracy of the current version on the prepared dataset was found to be up to 99.3% for target user. The solution combines electronics, e-textile technology, sensor technology, embedded system and machine learning techniques to build a low cost wearable glove that is scrupulous, elegant and portable.

Keywords: American sign language, assistive hand gesture interpreter, human-machine interface, machine learning, sensing glove

Procedia PDF Downloads 302

Authors: Aicha Bouhlala, Sabah Chettibi

Abstract:

Doping CeO₂ with transition metals is an effective way of tuning its properties. In the present work, we have performed self-consistent ab-initio calculation using the full-potential linearized augmented plane-wave method (FP-LAPW), based on the density functional theory (DFT) as implemented in the Wien2k simulation code to study the structural, electronic, and magnetic properties of the compound Ce₁₋ₓCuₓO₂ (x=12.5%) fluorite type oxide and to explore the effects of dopant Cu in ceria. The exchange correlation potential has been treated using the Perdew-Burke-Eenzerhof revised of solid (PBEsol). In structural properties, the equilibrium lattice constant is observed for the compound, which exists within the value of 5.382 A°. In electronic properties, the spin-polarized electronic bandstructure elucidates the semiconductor nature of the material in both spin channels, with the compound was observed to have a narrow bandgap on the spin-down configuration (0.162 EV) and bandgap on the spin-up (2.067 EV). Hence, the doped atom Cu plays a vital role in increasing the magnetic moments of the supercell, and the value of the total magnetic moment is found to be 2.99438 μB. Therefore, the compound Cu-doped CeO₂ shows a strong ferromagnetic behavior. The predicted results propose the compound could be a good candidate for spintronics applications.

Keywords: Cu-doped CeO₂, DFT, Wien2k, properties

Procedia PDF Downloads 255

Authors: Mahmut Yildirim

Abstract:

This paper proposed the bidirectional long short-term memory (Bi-LSTM) network-aided deep learning (DL)-based signal detection for Orthogonal frequency division multiplexing with all index modulation (OFDM-AIM), namely Bi-DeepAIM. OFDM-AIM is developed to increase the spectral efficiency of OFDM with index modulation (OFDM-IM), a promising multi-carrier technique for communication systems beyond 5G. In this paper, due to its strong classification ability, Bi-LSTM is considered an alternative to the maximum likelihood (ML) algorithm, which is used for signal detection in the classical OFDM-AIM scheme. The performance of the Bi-DeepAIM is compared with LSTM network-aided DL-based OFDM-AIM (DeepAIM) and classic OFDM-AIM that uses (ML)-based signal detection via BER performance and computational time criteria. Simulation results show that Bi-DeepAIM obtains better bit error rate (BER) performance than DeepAIM and lower computation time in signal detection than ML-AIM.

Keywords: bidirectional long short-term memory, deep learning, maximum likelihood, OFDM with all index modulation, signal detection

Procedia PDF Downloads 72

Authors: Anjali Chouksey, Riya Nimje, Jahanvi Saraf

Abstract:

Online transactions have increased dramatically in this new ‘social-distancing’ era. With online transactions, Fraud in online payments has also increased significantly. Frauds are a significant problem in various industries like insurance companies, baking, etc. These frauds include leaking sensitive information related to the credit card, which can be easily misused. Due to the government also pushing online transactions, E-commerce is on a boom. But due to increasing frauds in online payments, these E-commerce industries are suffering a great loss of trust from their customers. These companies are finding credit card fraud to be a big problem. People have started using online payment options and thus are becoming easy targets of credit card fraud. In this research paper, we will be discussing machine learning algorithms. We have used a decision tree, XGBOOST, k-nearest neighbour, logistic-regression, random forest, and SVM on a dataset in which there are transactions done online mode using credit cards. We will test all these algorithms for detecting fraud cases using the confusion matrix, F1 score, and calculating the accuracy score for each model to identify which algorithm can be used in detecting frauds.

Keywords: machine learning, fraud detection, artificial intelligence, decision tree, k nearest neighbour, random forest, XGBOOST, logistic regression, support vector machine

Procedia PDF Downloads 148

Authors: Khitem Amiri, Mohamed Farah

Abstract:

Image classification is a challenging task and is gaining lots of interest since it helps us to understand the content of images. Recently Deep Learning (DL) based methods gave very interesting results on several benchmarks. For Hyperspectral images (HSI), the application of DL techniques is still challenging due to the scarcity of labeled data and to the curse of dimensionality. Among other approaches, Deep Belief Network (DBN) based approaches gave a fair classification accuracy. In this paper, we address the problem of the curse of dimensionality by reducing the number of bands and replacing the HSI channels by the channels representing radiometric indices. Therefore, instead of using all the HSI bands, we compute the radiometric indices such as NDVI (Normalized Difference Vegetation Index), NDWI (Normalized Difference Water Index), etc, and we use the combination of these indices as input for the Deep Belief Network (DBN) based classification model. Thus, we keep almost all the pertinent spectral information while reducing considerably the size of the image. In order to test our image representation, we applied our method on several HSI datasets including the Indian pines dataset, Jasper Ridge data and it gave comparable results to the state of the art methods while reducing considerably the time of training and testing.

Keywords: hyperspectral images, deep belief network, radiometric indices, image classification

Procedia PDF Downloads 280

Authors: Swathi M. Vanniarajan

Abstract:

Reading research suggests that online contextual vocabulary comprehension while reading is an interactive and integrative process. One’s success in it depends on a variety of factors including the amount and the nature of available linguistic and nonlinguistic cues, his/her analytical and integrative skills, schema memory (content familiarity), and processing speed characterized along the continuum of controlled to automatic processing. The experiment reported here, conducted with 30 native speakers as one group and 30 nonnative speakers as another group (all graduate students), hypothesized that while working on (24) tasks which required them to comprehend an unfamiliar word in real time without backtracking, due to the differences in the nature of their respective reading processes, the nonnative subjects would be less able to construct the meanings of the unknown words by integrating the multiple but sufficient contextual cues provided in the text but the native subjects would be able to. The results indicated that there were significant inter-group as well as intra-group differences in terms of the quality of definitions given. However, when given additional time, while the nonnative speakers could significantly improve the quality of their definitions, the native speakers in general would not, suggesting that all things being equal, time is a significant factor for success in nonnative vocabulary and reading comprehension processes and that accuracy precedes automaticity in the development of nonnative reading processes also.

Keywords: reading, second language processing, vocabulary comprehension

Procedia PDF Downloads 166

Authors: Gabriele Iannotta

Abstract:

This paper investigates credit cycles by means of an experiment based on a Kiyotaki & Moore (1997) model with heterogeneous expectations. The aim is to examine how a credit squeeze caused by high lender-level risk perceptions affects the real prices of a collateralised asset, with a special focus on the macroeconomic implications of rising price volatility in terms of total welfare and the number of bankruptcies that occur. To do that, a learning-to-forecast experiment (LtFE) has been run where participants are asked to predict the future price of land and then rewarded based on the accuracy of their forecasts. The setting includes one lender and five borrowers in each of the twelve sessions split between six control groups (G1) and six treatment groups (G2). The only difference is that while in G1 the lender always satisfies borrowers’ loan demand (bankruptcies permitting), in G2 he/she closes the entire credit market in case three or more bankruptcies occur in the previous round. Experimental results show that negative risk-driven supply shocks amplify the volatility of collateral prices. This uncertainty worsens the agents’ ability to predict the future value of land and, as a consequence, the number of defaults increases and the total welfare deteriorates.

Keywords: Behavioural Macroeconomics, Credit Cycle, Experimental Economics, Heterogeneous Expectations, Learning-to-Forecast Experiment

Procedia PDF Downloads 125

Authors: Likewin Thomas, M. V. Manoj Kumar, B. Annappa

Abstract:

Traditional execution process follows the path of execution drawn by the process analyst without observing the behaviour of resource and other real-time constraints. Identifying process model, predicting the behaviour of resource and recommending the optimal path of execution for a real time process is challenging. The proposed AlfyMiner: αyM iner gives a new dimension in process execution with the novel techniques Process Model Analyser: PMAMiner and Resource behaviour Analyser: RBAMiner for recommending the probable path of execution. PMAMiner discovers next probable activity for currently executing activity in an online process using variant matching technique to identify the set of next probable activity, among which the next probable activity is discovered using decision tree model. RBAMiner identifies the resource suitable for performing the discovered next probable activity and observe the behaviour based on; load and performance using polynomial regression model, and waiting time using queueing theory. Based on the observed behaviour αyM iner recommend the probable path of execution with; next probable activity and the best suitable resource for performing it. Experiments were conducted on process logs of CoSeLoG Project1 and 72% of accuracy is obtained in identifying and recommending next probable activity and the efficiency of resource performance was optimised by 59% by decreasing their load.

Keywords: cross-organization process mining, process behaviour, path of execution, polynomial regression model

Procedia PDF Downloads 334

Authors: Adel Gurel, Ozge Ceylin Yildirim

Abstract:

Nowadays, design and architecture are being affected and underwent change with the rapid advancements in technology, economics, politics, society and culture. Architecture has been transforming with the latest developments after the inclusion of computers into design. Integration of design into the computational environment has revolutionized the architecture and new perspectives in architecture have been gained. The history of architecture shows the various technological developments and changes in which the architecture has transformed with time. Therefore, the analysis of integration between technology and the history of the architectural process makes it possible to build a consensus on the idea of how architecture is to proceed. In this study, each period that occurs with the integration of technology into architecture is addressed within historical process. At the same time, changes in architecture via technology are identified as important milestones and predictions with regards to the future of architecture have been determined. Developments and changes in technology and the use of technology in architecture within years are analyzed in charts and graphs comparatively. The historical process of architecture and its transformation via technology are supported with detailed literature review and they are consolidated with the examination of focal points of 20th-century architecture under the titles; parametric design, genetic architecture, simulation, and biomimicry. It is concluded that with the historical research between past and present; the developments in architecture cannot keep up with the advancements in technology and recent developments in technology overshadow the architecture, even the technology decides the direction of architecture. As a result, a scenario is presented with regards to the reach of technology in the future of architecture and the role of the architect.

Keywords: computer technologies, future architecture, scientific developments, transformation

Procedia PDF Downloads 191

Authors: Ana Serafimovic, Karthik Devarajan

Abstract:

Non-negative matrix factorization approximates a high dimensional non-negative matrix V as the product of two non-negative matrices, W and H, and allows only additive linear combinations of data, enabling it to learn parts with representations in reality. It has been successfully applied in the analysis and interpretation of high dimensional data arising in neuroscience, computational biology, and natural language processing, to name a few. The objective of this paper is to assess a hybrid algorithm for non-negative matrix factorization with multiplicative updates. The method aims to minimize the symmetric version of Kullback-Leibler divergence known as intrinsic information and assumes that the noise is signal-dependent and that it originates from an arbitrary distribution from the exponential family. It is a generalization of currently available algorithms for Gaussian, Poisson, gamma and inverse Gaussian noise. We demonstrate the potential usefulness of the new generalized algorithm by comparing its performance to the baseline methods which also aim to minimize symmetric divergence measures.

Keywords: non-negative matrix factorization, dimension reduction, clustering, intrinsic information, symmetric information divergence, signal-dependent noise, exponential family, generalized Kullback-Leibler divergence, dual divergence

Procedia PDF Downloads 246

Authors: Rujia Chen, Ajit Narayanan

Abstract:

Convolutional neural networks (CNN), as typically applied in deep learning, use layer-wise backpropagation (BP) to construct filters and kernels for feature extraction. Such filters are 2D or 3D groups of weights for constructing feature maps at subsequent layers of the CNN and are shared across the entire input. BP as a gradient descent algorithm has well-known problems of getting stuck at local optima. The use of genetic algorithms (GAs) for evolving weights between layers of standard artificial neural networks (ANNs) is a well-established area of neuroevolution. In particular, the use of crossover techniques when optimizing weights can help to overcome problems of local optima. However, the application of GAs for evolving the weights of filters and kernels in CNNs is not yet an established area of neuroevolution. In this paper, a GA-based filter development algorithm is proposed. The results of the proof-of-concept experiments described in this paper show the proposed GA algorithm can find filter weights through evolutionary techniques rather than BP learning. For some simple classification tasks like geometric shape recognition, the proposed algorithm can achieve 100% accuracy. The results for MNIST classification, while not as good as possible through standard filter learning through BP, show that filter and kernel evolution warrants further investigation as a new subarea of neuroevolution for deep architectures.

Keywords: neuroevolution, convolutional neural network, genetic algorithm, filters, kernels

Procedia PDF Downloads 186

Authors: S. J. Shahidzadeh Tabatabaei, A. M. Fattahi

Abstract:

Modal analysis of an FGM plate containing the ceramic phase of Al2O3 and metal phase of stainless steel 304 was performed using ABAQUS, with the assumptions that the material has an elastic mechanical behavior and its Young modulus and density are varying in thickness direction. For this purpose, a subroutine was written in FORTRAN and linked with ABAQUS. First, a simulation was performed in accordance to other researcher’s model, and then after comparing the obtained results, the accuracy of the present study was verified. The obtained results for natural frequency and mode shapes indicate good performance of user-written subroutine as well as FEM model used in present study. After verification of obtained results, the effect of clamping condition and the material type (i.e. the parameter n) was investigated. In this respect, finite element analysis was carried out in fully clamped condition for different values of n. The results indicate that the natural frequency decreases with increase of n, since with increase of n, the amount of ceramic phase in FGM plate decreases, while the amount of metal phase increases, leading to decrease of the plate stiffness and hence, natural frequency, as the Young modulus of Al2O3 is equal to 380 GPa and the Young modulus of stainless steel 304 is equal to 207 GPa.

Keywords: FGM plates, modal analysis, natural frequency, finite element method

Procedia PDF Downloads 342

Authors: E. R. Swart, S. J. Gismondi, N. R. Swart, C. E. Bell

Abstract:

We present an heuristic algorithm that decides graph non-Hamiltonicity. All graphs are directed, each undirected edge regarded as a pair of counter directed arcs. Each of the n! Hamilton cycles in a complete graph on n+1 vertices is mapped to an n-permutation matrix P where p(u,i)=1 if and only if the ith arc in a cycle enters vertex u, starting and ending at vertex n+1. We first create exclusion set E by noting all arcs (u, v) not in G, sufficient to code precisely all cycles excluded from G i.e. cycles not in G use at least one arc not in G. Members are pairs of components of P, {p(u,i),p(v,i+1)}, i=1, n-1. A doubly stochastic-like relaxed LP formulation of the Hamilton cycle decision problem is constructed. Each {p(u,i),p(v,i+1)} in E is coded as variable q(u,i,v,i+1)=0 i.e. shrinks the feasible region. We then implement the Weak Closure Algorithm (WCA) that tests necessary conditions of a matching, together with Boolean closure to decide 0/1 variable assignments. Each {p(u,i),p(v,j)} not in E is tested for membership in E, and if possible, added to E (q(u,i,v,j)=0) to iteratively maximize |E|. If the WCA constructs E to be maximal, the set of all {p(u,i),p(v,j)}, then G is decided non-Hamiltonian. Only non-Hamiltonian G share this maximal property. Ten non-Hamiltonian graphs (10 through 104 vertices) and 2000 randomized 31 vertex non-Hamiltonian graphs are tested and correctly decided non-Hamiltonian. For Hamiltonian G, the complement of E covers a matching, perhaps useful in searching for cycles. We also present an example where the WCA fails.

Keywords: Hamilton cycle decision problem, computational complexity theory, graph theory, theoretical computer science

Procedia PDF Downloads 373

Authors: Arthur D. Wiedemann, Christopher Fuller, Kyle A. Pascioni

Abstract:

With the introduction of electric motors, small unmanned aerial vehicle designers have to consider trade-offs between acoustic noise and thrust generated. Currently, there are few low-computational tools available for predicting acoustic noise emitted by a propeller into the far-field. Artificial neural networks offer a highly non-linear and adaptive model for predicting isolated and interactive tonal noise. But neural networks require large data sets, exceeding practical considerations in modeling experimental results. A methodology known as physics guided machine learning has been applied in this study to reduce the required data set to train the network. After building and evaluating several neural networks, the best model is investigated to determine how the network successfully predicts the acoustic waveform. Lastly, a post-network transfer function is developed to remove discontinuity from the predicted waveform. Overall, methodologies from physics guided machine learning show a notable improvement in prediction performance, but additional loss functions are necessary for constructing predictive networks on small datasets.

Keywords: aeroacoustics, machine learning, propeller, rotor, neural network, physics guided machine learning

Procedia PDF Downloads 228

Authors: Yanni Chang, Dezhi Dai, Albert Y. Tong

Abstract:

Piecewise linear interface calculation (PLIC) schemes are widely used in the volume-of-fluid (VOF) method to capture interfaces in numerical simulations of multiphase flows. Dynamic overset meshes can be especially useful in applications involving component motions and complex geometric shapes. In the present study, the VOF value of an acceptor cell is evaluated in a geometric way that transfers the fraction field between the meshes precisely with reconstructed interfaces from the corresponding donor elements. The acceptor cell value is evaluated by using a weighted average of its donors for most of the overset interpolation schemes for continuous flow variables. The weighting factors are obtained by different algebraic methods. Unlike the continuous flow variables, the VOF equation is a step function near the interfaces, which ranges from zero to unity rapidly. A geometric interpolation scheme of the VOF field in overset meshes for the PLIC-VOF method has been proposed in the paper. It has been tested successfully in quadrilateral/hexahedral overset meshes by employing several VOF advection tests with imposed solenoidal velocity fields. The proposed algorithm has been shown to yield higher accuracy in mass conservation and interface reconstruction compared with three other algebraic ones.

Keywords: interpolation scheme, multiphase flows, overset meshes, PLIC-VOF method

Procedia PDF Downloads 176

Authors: Esmaeil Bahmyari

Abstract:

The natural frequency analysis of the functionally graded (FG) rotating cylindrical shells subjected to thermal loads is studied based on the three-dimensional elasticity theory. The temperature-dependent assumption of the material properties is graded in the thickness direction, which varies based on the simple power law distribution. The governing equations and the appropriate boundary conditions, which include the effects of initial thermal stresses, are derived employing Hamilton’s principle. The initial thermo-mechanical stresses are obtained by the thermo-elastic equilibrium equation’s solution. As an efficient and accurate numerical tool, the differential quadrature method (DQM) is adopted to solve the thermo-elastic equilibrium equations, free vibration equations and natural frequencies are obtained. The high accuracy of the method is demonstrated by comparison studies with those existing solutions in the literature. Ultimately, the parametric studies are performed to demonstrate the effects of boundary conditions, temperature rise, material graded index, the thickness-to-length and the aspect ratios for the rotating cylindrical shells on the natural frequency.

Keywords: free vibration, DQM, elasticity theory, FG shell, rotating cylindrical shell

Procedia PDF Downloads 84

Authors: Abdulbaset Saad, Adel Younis, Zuomin Dong

Abstract:

For design optimization with high-dimensional expensive problems, an effective and efficient optimization methodology is desired. This work proposes a series of modification to the Differential Evolution (DE) algorithm for solving computation Intensive Black-Box Problems. The proposed methodology is called Radial Basis Meta-Model Algorithm Assisted Differential Evolutionary (RBF-DE), which is a global optimization algorithm based on the meta-modeling techniques. A meta-modeling assisted DE is proposed to solve computationally expensive optimization problems. The Radial Basis Function (RBF) model is used as a surrogate model to approximate the expensive objective function, while DE employs a mechanism to dynamically select the best performing combination of parameters such as differential rate, cross over probability, and population size. The proposed algorithm is tested on benchmark functions and real life practical applications and problems. The test results demonstrate that the proposed algorithm is promising and performs well compared to other optimization algorithms. The proposed algorithm is capable of converging to acceptable and good solutions in terms of accuracy, number of evaluations, and time needed to converge.

Keywords: differential evolution, engineering design, expensive computations, meta-modeling, radial basis function, optimization

Procedia PDF Downloads 396

Authors: Jamshaid Ul Rahman, Faiza Makhdoom, Dianchen Lu

Abstract:

Activation functions play a decisive role in determining the capacity of Deep Neural Networks (DNNs) as they enable neural networks to capture inherent nonlinearities present in data fed to them. The prior research on activation functions primarily focused on the utility of monotonic or non-oscillatory functions, until Growing Cosine Unit (GCU) broke the taboo for a number of applications. In this paper, a Convolutional Neural Network (CNN) model named as ASU-CNN is proposed which utilizes recently designed activation function ASU across its layers. The effect of this non-monotonic and oscillatory function is inspected through feature map visualizations from different convolutional layers. The optimization of proposed network is offered by Adam with a fine-tuned adjustment of learning rate. The network achieved promising results on both training and testing data for the classification of CIFAR-10. The experimental results affirm the computational feasibility and efficacy of the proposed model for performing tasks related to the field of computer vision.

Keywords: amplifying sine unit, activation function, convolutional neural networks, oscillatory activation, image classification, CIFAR-10

Procedia PDF Downloads 111

Authors: Yuan-Hsiang Chang, Pin-Chi Lin, Li-Der Jeng

Abstract:

Advance in techniques of image and video processing has enabled the development of intelligent video surveillance systems. This study was aimed to automatically detect moving human objects and to analyze events of dual human interaction in a surveillance scene. Our system was developed in four major steps: image preprocessing, human object detection, human object tracking, and motion trajectory analysis. The adaptive background subtraction and image processing techniques were used to detect and track moving human objects. To solve the occlusion problem during the interaction, the Kalman filter was used to retain a complete trajectory for each human object. Finally, the motion trajectory analysis was developed to distinguish between the interaction and non-interaction events based on derivatives of trajectories related to the speed of the moving objects. Using a database of 60 video sequences, our system could achieve the classification accuracy of 80% in interaction events and 95% in non-interaction events, respectively. In summary, we have explored the idea to investigate a system for the automatic classification of events for interaction and non-interaction events using surveillance cameras. Ultimately, this system could be incorporated in an intelligent surveillance system for the detection and/or classification of abnormal or criminal events (e.g., theft, snatch, fighting, etc.).

Keywords: motion detection, motion tracking, trajectory analysis, video surveillance

Procedia PDF Downloads 548

Authors: Aishwarya Ravindra Fursule, Shruti Kshirsagar

Abstract:

In the intersection of artificial intelligence and human-centered computing, this paper delves into speech emotion recognition (SER). It presents a comparative analysis of machine learning models such as K-Nearest Neighbors (KNN),logistic regression, support vector machines (SVM), decision trees, ensemble classifiers, and random forests, applied to SER. The research employs four datasets: Crema D, SAVEE, TESS, and RAVDESS. It focuses on extracting salient audio signal features like Zero Crossing Rate (ZCR), Chroma_stft, Mel Frequency Cepstral Coefficients (MFCC), root mean square (RMS) value, and MelSpectogram. These features are used to train and evaluate the models’ ability to recognize eight types of emotions from speech: happy, sad, neutral, angry, calm, disgust, fear, and surprise. Among the models, the Random Forest algorithm demonstrated superior performance, achieving approximately 79% accuracy. This suggests its suitability for SER within the parameters of this study. The research contributes to SER by showcasing the effectiveness of various machine learning algorithms and feature extraction techniques. The findings hold promise for the development of more precise emotion recognition systems in the future. This abstract provides a succinct overview of the paper’s content, methods, and results.

Keywords: comparison, ML classifiers, KNN, decision tree, SVM, random forest, logistic regression, ensemble classifiers

Procedia PDF Downloads 45

Authors: Abigail Gragg

Abstract:

The goal of this research study was to adjudicate if implementing Howard Gardner’s multiple levels of intelligence would enhance student achievement levels in an Algebra 1 College Preparatory class. This was conducted within every class by incorporating one level of the eight levels of intelligence into small group work in stations. Every class was conducted utilizing small-group instruction. Achievement levels were measured through various forms of collected data that expressed student understandings in class through formative assessments versus student understandings on summative assessments. The data samples included: assessments (i.e. summative and formative assessments), observable data, video recordings, a daily log book, student surveys, and checklists kept during the observation periods. Formative assessments were analyzed during each class period to measure in-class understanding. Summative assessments were dissected per question per accuracy to review the effects of each intelligence implemented. The data was collated into a coding workbook for further analysis to conclude the resulting themes of the research. These themes include 1) there was no correlation to multiple levels of intelligence enhancing student achievement, 2) bodily-kinesthetic intelligence showed to be the intelligence that had the most improvement on test questions and 3) out of all of the bits of intelligence, interpersonal intelligence enhanced student understanding in class.

Keywords: stations, small group instruction, multiple levels of intelligence, Mathematics, Algebra 1, student achievement, secondary school, instructional Pedagogies

Procedia PDF Downloads 111

Authors: Abdoulaye Diop, Nahid Emad, Thierry Winter, Mohamed Hilia

Abstract:

Data assets protection is a crucial issue in the cybersecurity field. Companies use logical access control tools to vault their information assets and protect them against external threats, but they lack solutions to counter insider threats. Nowadays, insider threats are the most significant concern of security analysts. They are mainly individuals with legitimate access to companies information systems, which use their rights with malicious intents. In several fields, behavior anomaly detection is the method used by cyber specialists to counter the threats of user malicious activities effectively. In this paper, we present the step toward the construction of a user and entity behavior analysis framework by proposing a behavior anomaly detection model. This model combines machine learning classification techniques and graph-based methods, relying on linear algebra and parallel computing techniques. We show the utility of an ensemble learning approach in this context. We present some detection methods tests results on an representative access control dataset. The use of some explored classifiers gives results up to 99% of accuracy.

Keywords: cybersecurity, data protection, access control, insider threat, user behavior analysis, ensemble learning, high performance computing

Procedia PDF Downloads 128

Authors: Joseph C. Chen, Venkata Karthik Jakka

Abstract:

The main objective of this research is to optimize tensile strength and dimensional accuracy in injection molding processes using Taguchi Parameter Design. An L16 orthogonal array (OA) is used in Taguchi experimental design with five control factors at four levels each and with non-controllable factor vibration. A total of 32 experiments were designed to obtain the optimal parameter setting for the process. The optimal parameters identified for the shrinkage are shot volume, 1.7 cubic inch (A4); mold term temperature, 130 ºF (B1); hold pressure, 3200 Psi (C4); injection speed, 0.61 inch3/sec (D2); and hold time of 14 seconds (E2). The optimal parameters identified for the tensile strength are shot volume, 1.7 cubic inch (A4); mold temperature, 160 ºF (B4); hold pressure, 3100 Psi (C3); injection speed, 0.69 inch3/sec (D4); and hold time of 14 seconds (E2). The Taguchi-based optimization framework was systematically and successfully implemented to obtain an adjusted optimal setting in this research. The mean shrinkage of the confirmation runs is 0.0031%, and the tensile strength value was found to be 3148.1 psi. Both outcomes are far better results from the baseline, and defects have been further reduced in injection molding processes.

Keywords: injection molding processes, taguchi parameter design, tensile strength, high-density polyethylene(HDPE)

Procedia PDF Downloads 196

Authors: Waleed Basuliman

Abstract:

Anthropometric dimensions are considered one of the important factors when designing human-machine systems. In this study, the estimation of anthropometric dimensions has been improved by using Artificial Neural Network (ANN) model that is able to predict the anthropometric measurements of Saudi males in Riyadh City. A total of 1427 Saudi males aged 6 to 60 years participated in measuring 20 anthropometric dimensions. These anthropometric measurements are considered important for designing the work and life applications in Saudi Arabia. The data were collected during eight months from different locations in Riyadh City. Five of these dimensions were used as predictors variables (inputs) of the model, and the remaining 15 dimensions were set to be the measured variables (Model’s outcomes). The hidden layers varied during the structuring stage, and the best performance was achieved with the network structure 6-25-15. The results showed that the developed Neural Network model was able to estimate the body dimensions of Saudi male population in Riyadh City. The network's mean absolute percentage error (MAPE) and the root mean squared error (RMSE) were found to be 0.0348 and 3.225, respectively. These results were found less, and then better, than the errors found in the literature. Finally, the accuracy of the developed neural network was evaluated by comparing the predicted outcomes with regression model. The ANN model showed higher coefficient of determination (R2) between the predicted and actual dimensions than the regression model.

Keywords: artificial neural network, anthropometric measurements, back-propagation

Procedia PDF Downloads 487

Authors: Shih-Wen Hsiao, Rong-Qi Chen, Chien-Yu Lin

Abstract:

The topic of surface flattening plays a vital role in the field of computer aided design and manufacture. Surface flattening enables the production of 2D patterns and it can be used in design and manufacturing for developing a 3D surface to a 2D platform, especially in fashion design. This study describes surface flattening based on minimum energy methods according to the property of different fabrics. Firstly, through the geometric feature of a 3D surface, the less transformed area can be flattened on a 2D platform by geodesic. Then, strain energy that has accumulated in mesh can be stably released by an approximate implicit method and revised error function. In some cases, cutting mesh to further release the energy is a common way to fix the situation and enhance the accuracy of the surface flattening, and this makes the obtained 2D pattern naturally generate significant cracks. When this methodology is applied to a 3D mannequin constructed with feature lines, it enhances the level of computer-aided fashion design. Besides, when different fabrics are applied to fashion design, it is necessary to revise the shape of a 2D pattern according to the properties of the fabric. With this model, the outline of 2D patterns can be revised by distributing the strain energy with different results according to different fabric properties. Finally, this research uses some common design cases to illustrate and verify the feasibility of this methodology.

Keywords: surface flattening, strain energy, minimum energy, approximate implicit method, fashion design

Procedia PDF Downloads 334

Authors: Leah Lee

Abstract:

This paper examines the correlation between deep learning models and emotions with noises to see whether or not noises mask emotions. The deep learning models used are plain convolutional neural networks (CNN), auto-encoder, long short-term memory (LSTM), and Visual Geometry Group-16 (VGG-16). Emotion datasets used are Ryerson Audio-Visual Database of Emotional Speech and Song (RAVDESS), Crowd-sourced Emotional Multimodal Actors Dataset (CREMA-D), Toronto Emotional Speech Set (TESS), and Surrey Audio-Visual Expressed Emotion (SAVEE). To make it four times bigger, audio set files, stretch, and pitch augmentations are utilized. From the augmented datasets, five different features are extracted for inputs of the models. There are eight different emotions to be classified. Noise variations are white noise, dog barking, and cough sounds. The variation in the signal-to-noise ratio (SNR) is 0, 20, and 40. In summation, per a deep learning model, nine different sets with noise and SNR variations and just augmented audio files without any noises will be used in the experiment. To compare the results of the deep learning models, the accuracy and receiver operating characteristic (ROC) are checked.

Keywords: auto-encoder, convolutional neural networks, long short-term memory, speech emotion recognition, visual geometry group-16

Procedia PDF Downloads 75

Authors: Mallika Supa-Aksorn, Buaream Maneewan, Jiraporn Rojtinnakorn

Abstract:

For animals, trypsin and chymotrypsin are the 2 proteases that play the important role in protein digestion and involving in growth rate. In many animals, these two enzymes are indicated as growth parameter by feed. Although enzyme assay at optimal condition is significant for its accuracy activity determination. There is less report of trypsin and chymotrypsin. Therefore, in this study, optimization of pH and temperature for trypsin (T) and chymotrypsin (C) in economic species; i.e. Nile tilapia (Oreochromis niloticus), sand goby (Oxyeleotoris marmoratus), giant freshwater prawn (Macrobachium rosenberchii) and native chicken (Gallus gallus) were investigated. Each enzyme of each species was assaying for its specific activity with variation of pH in range of 2-12 and temperature in range of 30-80 °C. It revealed that, for Nile tilapia, T had optimal condition at pH 9 and temperature 50-80 °C, whereas C had optimal condition at pH 8 and temperature 60 °C. For sand goby, T had optimal condition at pH 7 and temperature of 50 °C, while C had optimal condition at pH 11 and temperature of 70-75 °C. For juvenile freshwater prawn, T had optimal condition at pH 10-11 and temperature of 60-65 °C, C had optimal condition at pH 8 and temperature of 70°C. For starter native chicken, T has optimal condition at pH 7 and temperature of 70 °C, whereas C had o optimal condition at pH 8 and temperature of 60°C. This information of optimal conditions will be high valuable in further for, actual enzyme measurement of T and C activities that benefit for growth and feed analysis.

Keywords: trypsin, chymotrypsin, Oreochromis niloticus, Oxyeleotoris marmoratus, Macrobachium rosenberchii, Gallus gallus

Procedia PDF Downloads 259

Authors: Hossain A., Chowdhury S. I.

Abstract:

Introduction: The use of a gamma camera is a standard procedure in nuclear medicine facilities or hospitals to diagnose chronic kidney disease (CKD), but the gamma camera does not precisely stage the disease. The authors sought to determine whether they could use an artificial neural network to determine whether CKD was in normal or abnormal stages based on GFR values (ANN). Method: The 250 kidney patients (Training 188, Testing 62) who underwent an ultrasonography test to diagnose a renal test in our nuclear medical center were scanned using a gamma camera. Before the scanning procedure, the patients received an injection of ⁹⁹ᵐTc-DTPA. The gamma camera computes the pre- and post-syringe radioactive counts after the injection has been pushed into the patient's vein. The artificial neural network uses the softmax function with cross-entropy loss to determine whether CKD is normal or abnormal based on the GFR value in the output layer. Results: The proposed ANN model had a 99.20 % accuracy according to K-fold cross-validation. The sensitivity and specificity were 99.10 and 99.20 %, respectively. AUC was 0.994. Conclusion: The proposed model can distinguish between normal and abnormal stages of CKD by using an artificial neural network. The gamma camera could be upgraded to diagnose normal or abnormal stages of CKD with an appropriate GFR value following the clinical application of the proposed model.

Keywords: artificial neural network, glomerular filtration rate, stages of the kidney, gamma camera

Procedia PDF Downloads 103

Authors: U. Yerlikaya, R. T. Balkan

Abstract:

In this research, a method is developed to obtain high-dimensional configuration space for path planning problems. In typical cases, the path planning problems are solved directly in the 3-dimensional (D) workspace. However, this method is inefficient in handling the robots with various geometrical and mechanical restrictions. To overcome these difficulties, path planning may be formalized and solved in a new space which is called configuration space. The number of dimensions of the configuration space comes from the degree of freedoms of the system of interest. The method can be applied in two ways. In the first way, the point clouds of all the bodies of the system and interaction of them are used. The second way is performed via using the clearance function of simulation software where the minimum distances between surfaces of bodies are simultaneously measured. A double-turret system is held in the scope of this study. The 4-D configuration space of a double-turret system is obtained in these two ways. As a result, the difference between these two methods is around 1%, depending on the density of the point cloud. The disparity between the two forms steadily decreases as the point cloud density increases. At the end of the study, in order to verify 4-D configuration space obtained, 4-D path planning problem was realized as 2-D + 2-D and a sample path planning is carried out with using A* algorithm. Then, the accuracy of the configuration space is proved using the obtained paths on the simulation model of the double-turret system.

Keywords: A* algorithm, autonomous turrets, high-dimensional C-space, manifold C-space, point clouds

Procedia PDF Downloads 139