Search results for: back-propagation algorithm

Authors: Andrew Hwang

Abstract:

The average American worker sits for thirteen hours a day, often with poor posture and infrequent breaks, which can lead to health issues and back problems. The Smart Cushion was created to alert individuals of their poor postures, and may potentially alleviate back problems and correct poor posture. The Smart Cushion is a portable, rectangular, foam cushion, with five strategically placed pressure sensors, that utilizes an Arduino Uno circuit board and specifically designed software, allowing it to collect data from the five pressure sensors and store the data on an SD card. The data is then compiled into graphs and compared to controlled postures. Before volunteers sat on the cushion, their levels of back pain were recorded on a scale from 1-10. Data was recorded for an hour during sitting, and then a new, corrected posture was suggested. After using the suggested posture for an hour, the volunteers described their level of discomfort on a scale from 1-10. Different patterns of sitting postures were generated that were able to serve as early warnings of potential back problems. By using the Smart Cushion, the areas where different volunteers were applying the most pressure while sitting could be identified, and the sitting postures could be corrected. Further studies regarding the relationships between posture and specific regions of the body are necessary to better understand the origins of back pain; however, the Smart Cushion is sufficient for correcting sitting posture and preventing the development of additional back pain.

Keywords: Arduino Sketch Algorithm, biomedical technology, pressure sensors, Smart Cushion

Procedia PDF Downloads 134

Authors: Nixon Kuruvila, H. V. Ravindra

Abstract:

Wire-cut Electro Discharge Machining (WEDM) is a special form of conventional EDM process in which electrode is a continuously moving conductive wire. The present study aims at determining parametric influence and optimum process parameters of Wire-EDM using Taguchi’s Technique and Genetic algorithm. The variation of the performance parameters with machining parameters was mathematically modeled by Regression analysis method. The objective functions are Dimensional Accuracy (DA) and Material Removal Rate (MRR). Experiments were designed as per Taguchi’s L16 Orthogonal Array (OA) where in Pulse-on duration, Pulse-off duration, Current, Bed-speed and Flushing rate have been considered as the important input parameters. The matrix experiments were conducted for the material Oil Hardened Non Shrinking Steel (OHNS) having the thickness of 40 mm. The results of the study reveals that among the machining parameters it is preferable to go in for lower pulse-off duration for achieving over all good performance. Regarding MRR, OHNS is to be eroded with medium pulse-off duration and higher flush rate. Finally, the validation exercise performed with the optimum levels of the process parameters. The results confirm the efficiency of the approach employed for optimization of process parameters in this study.

Keywords: dimensional accuracy (DA), regression analysis (RA), Taguchi method (TM), volumetric material removal rate (VMRR)

Procedia PDF Downloads 409

Authors: H.-H. Doh, J.-M. Yu, Y.-J. Kwon, J.-H. Shin, H.-W. Kim, S.-H. Nam, D.-H. Lee

Abstract:

This paper suggests a decision tree based approach for flexible job shop scheduling with multiple process plans, i. e. each job can be processed through alternative operations, each of which can be processed on alternative machines. The main decision variables are: (a) selecting operation/machine pair; and (b) sequencing the jobs assigned to each machine. As an extension of the priority scheduling approach that selects the best priority rule combination after many simulation runs, this study suggests a decision tree based approach in which a decision tree is used to select a priority rule combination adequate for a specific system state and hence the burdens required for developing simulation models and carrying out simulation runs can be eliminated. The decision tree based scheduling approach consists of construction and scheduling modules. In the construction module, a decision tree is constructed using a four-stage algorithm, and in the scheduling module, a priority rule combination is selected using the decision tree. To show the performance of the decision tree based approach suggested in this study, a case study was done on a flexible job shop with reconfigurable manufacturing cells and a conventional job shop, and the results are reported by comparing it with individual priority rule combinations for the objectives of minimizing total flow time and total tardiness.

Keywords: flexible job shop scheduling, decision tree, priority rules, case study

Procedia PDF Downloads 358

Authors: M. Dezvarei, S. Morovati

Abstract:

In recent years, increasing usage of electrical energy provides a widespread field for investigating new methods to produce clean electricity with high reliability and cost management. Fuel cells are new clean generations to make electricity and thermal energy together with high performance and no environmental pollution. According to the expansion of fuel cell usage in different industrial networks, the identification and optimization of its parameters is really significant. This paper presents optimization of a proton exchange membrane fuel cell (PEMFC) parameters based on modified particle swarm optimization with real valued mutation (RVM) and clonal algorithms. Mathematical equations of this type of fuel cell are presented as the main model structure in the optimization process. Optimized parameters based on clonal and RVM algorithms are compared with the desired values in the presence and absence of measurement noise. This paper shows that these methods can improve the performance of traditional optimization methods. Simulation results are employed to analyze and compare the performance of these methodologies in order to optimize the proton exchange membrane fuel cell parameters.

Keywords: clonal algorithm, proton exchange membrane fuel cell (PEMFC), particle swarm optimization (PSO), real-valued mutation (RVM)

Procedia PDF Downloads 351

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: Khalid Ali, Manar Jammal

Abstract:

In order to meet the stringent latency and reliability requirements of the upcoming 5G networks, Open Radio Access Networks (O-RAN) have been proposed. The virtualization of O-RAN has allowed it to be treated as a Network Function Virtualization (NFV) architecture, while its components are considered Virtualized Network Functions (VNFs). Hence, intelligent Machine Learning (ML) based solutions can be utilized to apply different resource management and allocation techniques on O-RAN. However, intelligently allocating resources for O-RAN VNFs can prove challenging due to the dynamicity of traffic in mobile networks. Network providers need to dynamically scale the allocated resources in response to the incoming traffic. Elastically allocating resources can provide a higher level of flexibility in the network in addition to reducing the OPerational EXpenditure (OPEX) and increasing the resources utilization. Most of the existing elastic solutions are reactive in nature, despite the fact that proactive approaches are more agile since they scale instances ahead of time by predicting the incoming traffic. In this work, we propose and evaluate traffic forecasting models based on the ML algorithm. The algorithms aim at predicting future O-RAN traffic by using previous traffic data. Detailed analysis of the traffic data was carried out to validate the quality and applicability of the traffic dataset. Hence, two ML models were proposed and evaluated based on their prediction capabilities.

Keywords: O-RAN, traffic forecasting, NFV, ARIMA, LSTM, elasticity

Procedia PDF Downloads 225

Authors: Ashish Shrivastava, C. Pandu Rangan

Abstract:

In this paper, we consider The Hospitals Residents problem with Social Stability (HRSS), where hospitals and residents can communicate only through the underlying social network. Those residents and hospitals which don not have any social connection between them can not communicate and hence they cannot be a social blocking pair with respect to a socially stable matching in an instance of hospitals residents problem with social stability. In large scale matching like NRMP or Scottish medical matching scheme etc. where set of agents, as well as length of preference lists, are very large, social stability is a useful notion in which members of a blocking pair could block a matching if and only if they know the existence of each other. Thus the notion of social stability in hospitals residents problem allows us to increase the cardinality of the matching without taking care of those blocking pairs which are not socially connected to each other. We know that finding a maximum cardinality socially stable matching, in an instance, of HRSS is NP-hard. This motivates us to solve this problem with bounded length preference lists on one side. In this paper, we have presented a polynomial time algorithm to compute maximum cardinality socially stable matching in a HRSS instance where residents can give at most two length and hospitals can give unbounded length preference list. Preference lists of residents and hospitals will be strict in nature.

Keywords: matching under preference, socially stable matching, the hospital residents problem, the stable marriage problem

Procedia PDF Downloads 277

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: Madhushi Bandara, Dharshana Kasthurirathna, Danaja Maldeniya, Mahendra Piraveenan

Abstract:

Community detection is an extremely useful technique in understanding the structure and function of a social network. Louvain algorithm, which is based on Newman-Girman modularity optimization technique, is extensively used as a computationally efficient method extract the communities in social networks. It has been suggested that the nodes that are in close geographical proximity have a higher tendency of forming communities. Variants of the Newman-Girman modularity measure such as dist-modularity try to normalize the effect of geographical proximity to extract geographically dispersed communities, at the expense of losing the information about the geographically proximate communities. In this work, we propose a method to extract geographically dispersed communities while preserving the information about the geographically proximate communities, by analyzing the ‘community network’, where the centroids of communities would be considered as network nodes. We suggest that the inter-community link strengths, which are normalized over the community sizes, may be used to identify and extract the ‘overlay communities’. The overlay communities would have relatively higher link strengths, despite being relatively apart in their spatial distribution. We apply this method to the Gowalla online social network, which contains the geographical signatures of its users, and identify the overlay communities within it.

Keywords: social networks, community detection, modularity optimization, geographically dispersed communities

Procedia PDF Downloads 235

Authors: H. Mansor, S.B. Mohd-Noor, N. I. Othman, N. Tazali, R. I. Boby

Abstract:

This paper presents an improved robust Proportional Derivative controller for a 3-Degree-of-Freedom (3-DOF) bench-top helicopter by using adaptive methodology. Bench-top helicopter is a laboratory scale helicopter used for experimental purposes which is widely used in teaching laboratory and research. Proportional Derivative controller has been developed for a 3-DOF bench-top helicopter by Quanser. Experiments showed that the transient response of designed PD controller has very large steady state error i.e., 50%, which is very serious. The objective of this research is to improve the performance of existing pitch angle control of PD controller on the bench-top helicopter by integration of PD controller with adaptive controller. Usually standard adaptive controller will produce zero steady state error; however response time to reach desired set point is large. Therefore, this paper proposed an adaptive with deadbeat algorithm to overcome the limitations. The output response that is fast, robust and updated online is expected. Performance comparisons have been performed between the proposed self-tuning deadbeat PD controller and standard PD controller. The efficiency of the self-tuning dead beat controller has been proven from the tests results in terms of faster settling time, zero steady state error and capability of the controller to be updated online.

Keywords: adaptive control, deadbeat control, bench-top helicopter, self-tuning control

Procedia PDF Downloads 325

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: Joshi Manisha, Shivaram, Anand Vinekar, Tanya Susan Mathews, Yeshaswini Nagaraj

Abstract:

Retinopathy of prematurity (ROP) is abnormal blood vessel development in the retina of the eye in a premature infant. The principal object of the invention is to provide a technique for detecting demarcation line and ridge detection for a given ROP image that facilitates early detection of ROP in stage 1 and stage 2. The demarcation line is an indicator of Stage 1 of the ROP and the ridge is the hallmark of typically Stage 2 ROP. Thirty Retcam images of Asian Indian infants obtained during routine ROP screening have been used for the analysis. A graphical user interface has been developed to detect demarcation line/ridge and to extract ground truth. This novel algorithm uses multilevel vessel enhancement to enhance tubular structures in the digital ROP images. It has been observed that the orientation of the demarcation line/ridge is normal to the direction of the blood vessels, which is used for the identification of the ridge/ demarcation line. Quantitative analysis has been presented based on gold standard images marked by expert ophthalmologist. Image based analysis has been based on the length and the position of the detected ridge. In image based evaluation, average sensitivity and positive predictive value was found to be 92.30% and 85.71% respectively. In pixel based evaluation, average sensitivity, specificity, positive predictive value and negative predictive value achieved were 60.38%, 99.66%, 52.77% and 99.75% respectively.

Keywords: ROP, ridge, multilevel vessel enhancement, biomedical

Procedia PDF Downloads 410

Authors: Najrullah Khan, Athar Ali Khan

Abstract:

The Topp-Leone distribution was introduced by Topp- Leone in 1955. In this paper, an attempt has been made to fit Topp-Leone Generalized exponential (TPGE) distribution. A real survival data set is used for illustrations. Implementation is done using R and JAGS and appropriate illustrations are made. R and JAGS codes have been provided to implement censoring mechanism using both optimization and simulation tools. The main aim of this paper is to describe and illustrate the Bayesian modelling approach to the analysis of survival data. Emphasis is placed on the modeling of data and the interpretation of the results. Crucial to this is an understanding of the nature of the incomplete or 'censored' data encountered. Analytic approximation and simulation tools are covered here, but most of the emphasis is on Markov chain based Monte Carlo method including independent Metropolis algorithm, which is currently the most popular technique. For analytic approximation, among various optimization algorithms and trust region method is found to be the best. In this paper, TPGE model is also used to analyze the lifetime data in Bayesian paradigm. Results are evaluated from the above mentioned real survival data set. The analytic approximation and simulation methods are implemented using some software packages. It is clear from our findings that simulation tools provide better results as compared to those obtained by asymptotic approximation.

Keywords: Bayesian Inference, JAGS, Laplace Approximation, LaplacesDemon, posterior, R Software, simulation

Procedia PDF Downloads 535

Authors: George Adomako Kumi

Abstract:

The response of structural members, when subjected to various forms of non-proportional loading, plays a major role in the overall stability and integrity of a structure. This research seeks to present the outcome of a finite element investigation conducted by the use of finite element programming software ABAQUS to validate the experimental results of elastic and inelastic behavior and strength of beam-columns subjected to axial loading, biaxial bending, and torsion under ambient temperature conditions. The application of the rigorous and highly complicated ABAQUS finite element software will seek to account for material, non-linear geometry, deformations, and, more specifically, the contact behavior between the beam-columns and support surfaces. Comparisons of the three-dimensional model with the results of actual tests conducted and results from a solution algorithm developed through the use of the finite difference method will be established in order to authenticate the veracity of the developed model. The results of this research will seek to provide structural engineers with much-needed knowledge about the behavior of steel beam columns and their response to various non-proportional loading conditions under ambient temperature conditions.

Keywords: beam-columns, axial loading, biaxial bending, torsion, ABAQUS, finite difference method

Procedia PDF Downloads 180

Authors: Ehsan Gholamalizadeh, Jae Dong Chung

Abstract:

Solar chimney power plant is a feasible solar thermal system which produces electricity from the Sun. The objective of this study is to investigate buoyancy-driven flow and heat transfer through a built pilot solar chimney system called 'Kerman Project'. The system has a chimney with the height and diameter of 60 m and 3 m, respectively, and the average radius of its solar collector is about 20 m, and also its average collector height is about 2 m. A three-dimensional simulation was conducted to analyze the system, using computational fluid dynamics (CFD). In this model, radiative transfer equation was solved using the discrete ordinates (DO) radiation model taking into account a non-gray radiation behavior. In order to modelling solar irradiation from the sun’s rays, the solar ray tracing algorithm was coupled to the computation via a source term in the energy equation. The model was validated with comparing to the experimental data of the Manzanares prototype and also the performance of the built pilot system. Then, based on the numerical simulations, velocity and temperature distributions through the system, the temperature profile of the ground surface and the system performance were presented. The analysis accurately shows the flow and heat transfer characteristics through the pilot system and predicts its performance.

Keywords: buoyancy-driven flow, computational fluid dynamics, heat transfer, renewable energy, solar chimney power plant

Procedia PDF Downloads 262

Authors: Shahrokh Barati, Reza Ramezani

Abstract:

Due to the countries growing attention to the renewable energy producing, the demand for energy from renewable energy has gone up among the renewable energy sources; wind energy is the fastest growth in recent years. In this regard, in order to increase the availability of wind turbines, using of Fault Detection and Isolation (FDI) system is necessary. Wind turbines include of various faults such as sensors fault, actuator faults, network connection fault, mechanical faults and faults in the generator subsystem. Although, sensors and actuators have a large number of faults in wind turbine but have discussed fewer in the literature. Therefore, in this work, we focus our attention to design a sensor and actuator fault detection and isolation algorithm and Fault-tolerant control systems (FTCS) for Wind Turbine. The aim of this research is to propose a comprehensive fault detection and isolation system for sensors and actuators of wind turbine based on data-driven approaches. To achieve this goal, the features of measurable signals in real wind turbine extract in any condition. The next step is the feature selection among the extract in any condition. The next step is the feature selection among the extracted features. Features are selected that led to maximum separation networks that implemented in parallel and results of classifiers fused together. In order to maximize the reliability of decision on fault, the property of fault repeatability is used.

Keywords: FDI, wind turbines, sensors and actuators faults, renewable energy

Procedia PDF Downloads 400

Authors: Boumaraf Malak

Abstract:

The development of intelligent transportation systems (ITS) and artificial intelligence (AI) are spurring us to pave the way for the widespread adoption of autonomous vehicles (AVs). This is open again opportunities for smart roads, smart traffic safety, and mobility comfort. A highly intelligent decision-making system is essential for autonomous driving around dense, dynamic objects. It must be able to handle complex road geometry and topology, as well as complex multiagent interactions, and closely follow higher-level commands such as routing information. Autonomous vehicles have become a very hot research topic in recent years due to their significant ability to reduce traffic accidents and personal injuries. Using new artificial intelligence-based technologies handles important functions in scene understanding, motion planning, decision making, vehicle control, social behavior, and communication for AV. This paper focuses only on deep reinforcement learning-based methods; it does not include traditional (flat) planar techniques, which have been the subject of extensive research in the past because reinforcement learning (RL) has become a powerful learning framework now capable of learning complex policies in high dimensional environments. The DRL algorithm used so far found solutions to the four main problems of autonomous driving; in our paper, we highlight the challenges and point to possible future research directions.

Keywords: deep reinforcement learning, autonomous driving, deep deterministic policy gradient, deep Q-learning

Procedia PDF Downloads 85

Authors: Xinyuan Y. Song, Kai Kang

Abstract:

Joint models for analyzing longitudinal and survival data are widely used to investigate the relationship between a failure time process and time-variant predictors. A common assumption in conventional joint models in the survival analysis literature is that all predictors are observable. However, this assumption may not always be supported because unobservable traits, namely, latent variables, which are indirectly observable and should be measured through multiple observed variables, are commonly encountered in the medical, behavioral, and financial research settings. In this study, a joint modeling approach to deal with this feature is proposed. The proposed model comprises three parts. The first part is a dynamic factor analysis model for characterizing latent variables through multiple observed indicators over time. The second part is a random coefficient trajectory model for describing the individual trajectories of latent variables. The third part is a proportional hazard model for examining the effects of time-invariant predictors and the longitudinal trajectories of time-variant latent risk factors on hazards of interest. A Bayesian approach coupled with a Markov chain Monte Carlo algorithm to perform statistical inference. An application of the proposed joint model to a study on the Alzheimer's disease neuroimaging Initiative is presented.

Keywords: Bayesian analysis, joint model, longitudinal data, time-to-event data

Procedia PDF Downloads 144

Authors: Rashid Javed, Hardy Lehmkuehler, Franz Josef-Behr

Abstract:

Web Processing Services (WPS) have up growing concern in geoinformation research. However, teaching about them is difficult because of the generally complex circumstances of their use. They limit the possibilities for hands- on- exercises on Web Processing Services. To support understanding however a Training Tools Collection was brought on the way at University of Applied Sciences Stuttgart (HFT). It is limited to the scope of Geostatistical Interpolation of sample point data where different algorithms can be used like IDW, Nearest Neighbor etc. The Tools Collection aims to support understanding of the scope, definition and deployment of Web Processing Services. For example it is necessary to characterize the input of Interpolation by the data set, the parameters for the algorithm and the interpolation results (here a grid of interpolated values is assumed). This paper reports on first experiences using a pilot installation. This was intended to find suitable software interfaces for later full implementations and conclude on potential user interface characteristics. Experiences were made with Deegree software, one of several Services Suites (Collections). Being strictly programmed in Java, Deegree offers several OGC compliant Service Implementations that also promise to be of benefit for the project. The mentioned parameters for a WPS were formalized following the paradigm that any meaningful component will be defined in terms of suitable standards. E.g. the data output can be defined as a GML file. But, the choice of meaningful information pieces and user interactions is not free but partially determined by the selected WPS Processing Suite.

Keywords: deegree, interpolation, IDW, web processing service (WPS)

Procedia PDF Downloads 355

Authors: F. Jiménez, R. Jódar, M. Martín, G. Sánchez, G. Sciavicco

Abstract:

Abstract—Attribute or feature selection is one of the basic strategies to improve the performances of data classification tasks, and, at the same time, to reduce the complexity of classifiers, and it is a particularly fundamental one when the number of attributes is relatively high. Its application to unsupervised classification is restricted to a limited number of experiments in the literature. Evolutionary computation has already proven itself to be a very effective choice to consistently reduce the number of attributes towards a better classification rate and a simpler semantic interpretation of the inferred classifiers. We present a feature selection wrapper model composed by a multi-objective evolutionary algorithm, the clustering method Expectation-Maximization (EM), and the classifier C4.5 for the unsupervised classification of data extracted from a psychological test named BASC-II (Behavior Assessment System for Children - II ed.) with two objectives: Maximizing the likelihood of the clustering model and maximizing the accuracy of the obtained classifier. We present a methodology to integrate feature selection for unsupervised classification, model evaluation, decision making (to choose the most satisfactory model according to a a posteriori process in a multi-objective context), and testing. We compare the performance of the classifier obtained by the multi-objective evolutionary algorithms ENORA and NSGA-II, and the best solution is then validated by the psychologists that collected the data.

Keywords: evolutionary computation, feature selection, classification, clustering

Procedia PDF Downloads 370

Authors: K. Bresilla, L. Manfrini, B. Morandi, A. Boini, G. Perulli, L. C. Grappadelli

Abstract:

Image/video processing for fruit in the tree using hard-coded feature extraction algorithms have shown high accuracy during recent years. While accurate, these approaches even with high-end hardware are computationally intensive and too slow for real-time systems. This paper details the use of deep convolution neural networks (CNNs), specifically an algorithm (YOLO - You Only Look Once) with 24+2 convolution layers. Using deep-learning techniques eliminated the need for hard-code specific features for specific fruit shapes, color and/or other attributes. This CNN is trained on more than 5000 images of apple and pear fruits on 960 cores GPU (Graphical Processing Unit). Testing set showed an accuracy of 90%. After this, trained data were transferred to an embedded device (Raspberry Pi gen.3) with camera for more portability. Based on correlation between number of visible fruits or detected fruits on one frame and the real number of fruits on one tree, a model was created to accommodate this error rate. Speed of processing and detection of the whole platform was higher than 40 frames per second. This speed is fast enough for any grasping/harvesting robotic arm or other real-time applications.

Keywords: artificial intelligence, computer vision, deep learning, fruit recognition, harvesting robot, precision agriculture

Procedia PDF Downloads 420

Authors: Belgherbi Aicha, Hadjidj Ismahen, Bessaid Abdelhafid

Abstract:

The phase of segmentation is an important step in the processing and interpretation of medical images. In this paper, we focus on the segmentation of liver and spleen from the abdomen computed tomography (CT) images. The importance of our study comes from the fact that the segmentation of ROI from CT images is usually a difficult task. This difficulty is the gray’s level of which is similar to the other organ also the ROI are connected to the ribs, heart, kidneys, etc. Our proposed method is based on the anatomical information and mathematical morphology tools used in the image processing field. At first, we try to remove the surrounding and connected organs and tissues by applying morphological filters. This first step makes the extraction of interest regions easier. The second step consists of improving the quality of the image gradient. In this step, we propose a method for improving the image gradient to reduce these deficiencies by applying the spatial filters followed by the morphological filters. Thereafter we proceed to the segmentation of the liver, spleen. To validate the segmentation technique proposed, we have tested it on several images. Our segmentation approach is evaluated by comparing our results with the manual segmentation performed by an expert. The experimental results are described in the last part of this work.The system has been evaluated by computing the sensitivity and specificity between the semi-automatically segmented (liver and spleen) contour and the manually contour traced by radiological experts.

Keywords: CT images, liver and spleen segmentation, anisotropic diffusion filter, morphological filters, watershed algorithm

Procedia PDF Downloads 495

Authors: Yash Bingi, Yiqiao Yin

Abstract:

Reduction of child mortality is an ongoing struggle and a commonly used factor in determining progress in the medical field. The under-5 mortality number is around 5 million around the world, with many of the deaths being preventable. In light of this issue, Cardiotocograms (CTGs) have emerged as a leading tool to determine fetal health. By using ultrasound pulses and reading the responses, CTGs help healthcare professionals assess the overall health of the fetus to determine the risk of child mortality. However, interpreting the results of the CTGs is time-consuming and inefficient, especially in underdeveloped areas where an expert obstetrician is hard to come by. Using a support vector machine (SVM) and oversampling, this paper proposed a model that classifies fetal health with an accuracy of 99.59%. To further explain the CTG measurements, an algorithm based on Randomized Input Sampling for Explanation ((RISE) of Black-box Models was created, called Feature Alteration for explanation of Black Box Models (FAB), and compared the findings to Shapley Additive Explanations (SHAP) and Local Interpretable Model Agnostic Explanations (LIME). This allows doctors and medical professionals to classify fetal health with high accuracy and determine which features were most influential in the process.

Keywords: machine learning, fetal health, gradient boosting, support vector machine, Shapley values, local interpretable model agnostic explanations

Procedia PDF Downloads 144

Authors: Victoria L. Malakhova

Abstract:

The research is devoted to multimodal content and its effectiveness in developing students’ linguistic and intercultural communicative competences as an indefeasible constituent of their future professional activity. Description of multimodal content both as a linguistic and didactic phenomenon makes the study relevant. The objective of the article is the analysis of creolized texts and the effect they have on fostering higher education students’ skills and their productivity. The main methods used are linguistic text analysis, qualitative and quantitative methods, deduction, generalization. The author studies texts with full and partial creolization, their features and role in composing multimodal textual space. The main verbal and non-verbal markers and paralinguistic means that enhance the linguo-pragmatic potential of creolized texts are covered. To reveal the efficiency of multimodal content application in English teaching, the author conducts an experiment among both undergraduate students and teachers. This allows specifying main functions of creolized texts in the process of language learning, detecting ways of enhancing students’ competences, and increasing their motivation. The described stages of using creolized texts can serve as an algorithm for work with multimodal content in teaching English as a foreign language. The findings contribute to improving the efficiency of the academic process.

Keywords: creolized text, English language learning, higher education, language and communication competences, multimodal content

Procedia PDF Downloads 112

Authors: Samer Muthana Sarsam, Abdul Samad Shibghatullah, Chit Su Mon, Abd Aziz Alias, Hosam Al-Samarraie

Abstract:

Generative Artificial Intelligence chatbots (GAI chatbots) have emerged as promising tools in various domains, including higher education. However, their specific role within the educational context and the level of legal support for their implementation remain unclear. Therefore, this study aims to investigate the role of Bard, a newly developed GAI chatbot, in higher education. To achieve this objective, English tweets were collected from Twitter's free streaming Application Programming Interface (API). The Latent Dirichlet Allocation (LDA) algorithm was applied to extract latent topics from the collected tweets. User sentiments, including disgust, surprise, sadness, anger, fear, joy, anticipation, and trust, as well as positive and negative sentiments, were extracted using the NRC Affect Intensity Lexicon and SentiStrength tools. This study explored the benefits, challenges, and future implications of integrating GAI chatbots in higher education. The findings shed light on the potential power of such tools, exemplified by Bard, in enhancing the learning process and providing support to students throughout their educational journey.

Keywords: generative artificial intelligence chatbots, bard, higher education, topic modelling, sentiment analysis

Procedia PDF Downloads 83

Authors: F. Hamidi, N. Amiri, H. Mishmast Nehi

Abstract:

The Bilevel Programming (BP) model has been presented for a decision making process that consists of two decision makers in a hierarchical structure. In fact, BP is a model for a static two person game (the leader player in the upper level and the follower player in the lower level) wherein each player tries to optimize his/her personal objective function under dependent constraints; this game is sequential and non-cooperative. The decision making variables are divided between the two players and one’s choice affects the other’s benefit and choices. In other words, BP consists of two nested optimization problems with two objective functions (upper and lower) where the constraint region of the upper level problem is implicitly determined by the lower level problem. In real cases, the coefficients of an optimization problem may not be precise, i.e. they may be interval. In this paper we develop an algorithm for solving interval bilevel linear fractional programming problems. That is to say, bilevel problems in which both objective functions are linear fractional, the coefficients are interval and the common constraint region is a polyhedron. From the original problem, the best and the worst bilevel linear fractional problems have been derived and then, using the extended Charnes and Cooper transformation, each fractional problem can be reduced to a linear problem. Then we can find the best and the worst optimal values of the leader objective function by two algorithms.

Keywords: best and worst optimal solutions, bilevel programming, fractional, interval coefficients

Procedia PDF Downloads 446

Authors: Niklas Panten, Eberhard Abele

Abstract:

This paper presents a novel approach for real-time and near-optimal control of industrial smart grids by deep reinforcement learning (DRL). To achieve highly energy-efficient factory systems, the energetic linkage of machines, technical building equipment and the building itself is desirable. However, the increased complexity of the interacting sub-systems, multiple time-variant target values and stochastic influences by the production environment, weather and energy markets make it difficult to efficiently control the energy production, storage and consumption in the hybrid industrial smart grids. The studied deep reinforcement learning approach allows to explore the solution space for proper control policies which minimize a cost function. The deep neural network of the DRL agent is based on a multilayer perceptron (MLP), Long Short-Term Memory (LSTM) and convolutional layers. The agent is trained within multiple Modelica-based factory simulation environments by the Advantage Actor Critic algorithm (A2C). The DRL controller is evaluated by means of the simulation and then compared to a conventional, rule-based approach. Finally, the results indicate that the DRL approach is able to improve the control performance and significantly reduce energy respectively operating costs of industrial smart grids.

Keywords: industrial smart grids, energy efficiency, deep reinforcement learning, optimal control

Procedia PDF Downloads 195

Authors: Kemal Polat

Abstract:

In this paper, an attribute weighting method called fuzzy C-means clustering based attribute weighting (FCMAW) for classification of Diabetes disease dataset has been used. The aims of this study are to reduce the variance within attributes of diabetes dataset and to improve the classification accuracy of classifier algorithm transforming from non-linear separable datasets to linearly separable datasets. Pima Indians Diabetes dataset has two classes including normal subjects (500 instances) and diabetes subjects (268 instances). Fuzzy C-means clustering is an improved version of K-means clustering method and is one of most used clustering methods in data mining and machine learning applications. In this study, as the first stage, fuzzy C-means clustering process has been used for finding the centers of attributes in Pima Indians diabetes dataset and then weighted the dataset according to the ratios of the means of attributes to centers of theirs. Secondly, after weighting process, the classifier algorithms including support vector machine (SVM) and k-NN (k- nearest neighbor) classifiers have been used for classifying weighted Pima Indians diabetes dataset. Experimental results show that the proposed attribute weighting method (FCMAW) has obtained very promising results in the classification of Pima Indians diabetes dataset.

Keywords: fuzzy C-means clustering, fuzzy C-means clustering based attribute weighting, Pima Indians diabetes, SVM

Procedia PDF Downloads 413

Authors: N. Guo, C. Xu, Z. C. Yang

Abstract:

In order to ensure the high reliability of an aircraft, the accurate structural dynamics analysis has become an indispensable part in the design of an aircraft structure. Therefore, the structural finite element model which can be used to accurately calculate the structural dynamics and their transfer relations is the prerequisite in structural dynamic design. A dynamic finite element model updating method is presented to correct the uncertain parameters of the finite element model of a structure using measured modal parameters. The coordinate modal assurance criterion is used to evaluate the correlation level at each coordinate over the experimental and the analytical mode shapes. Then, the weighted summation of the natural frequency residual and the coordinate modal assurance criterion residual is used as the objective function. Moreover, the hybrid pattern search (HPS) optimization technique, which synthesizes the advantages of pattern search (PS) optimization technique and genetic algorithm (GA), is introduced to solve the dynamic FE model updating problem. A numerical simulation and a model updating experiment for GARTEUR aircraft model are performed to validate the feasibility and effectiveness of the present dynamic model updating method, respectively. The updated results show that the proposed method can be successfully used to modify the incorrect parameters with good robustness.

Keywords: model updating, modal parameter, coordinate modal assurance criterion, hybrid genetic/pattern search

Procedia PDF Downloads 161

Authors: Qiang Zhang, Xiaojian Hu

Abstract:

In multi-vehicle tracking, based on feature selection, the tracking system efficiently tracks vehicles in a video with minimal error in combination with color attribution, which focuses on presenting a simple and fast, yet accurate and robust solution to the problem such as inaccurately and untimely responses of statistics-based adaptive traffic control system in the intersection scenario. In this study, a real-time tracking system is proposed for multi-vehicle tracking in the intersection scene. Considering the complexity and application feasibility of the algorithm, in the object detection step, the detection result provided by virtual loops were post-processed and then used as the input for the tracker. For the tracker, lightweight methods were designed to extract and select features and incorporate them into the adaptive color tracking (ACT) framework. And the approbatory online feature selection algorithms are integrated on the mature ACT system with good compatibility. The proposed feature selection methods and multi-vehicle tracking method are evaluated on KITTI datasets and show efficient vehicle tracking performance when compared to the other state-of-the-art approaches in the same category. And the system performs excellently on the video sequences recorded at the intersection. Furthermore, the presented vehicle tracking system is suitable for surveillance applications.

Keywords: real-time, multi-vehicle tracking, feature selection, color attribution

Procedia PDF Downloads 163