Search results for: prediction model accuracy

Authors: Tawfik Thelaidjia, Salah Chenikher

Abstract:

Bearing fault diagnosis has attracted significant attention over the past few decades. It consists of two major parts: vibration signal feature extraction and condition classification for the extracted features. In this paper, feature extraction from faulty bearing vibration signals is performed by a combination of the signal’s Kurtosis and features obtained through the preprocessing of the vibration signal samples using Db2 discrete wavelet transform at the fifth level of decomposition. In this way, a 7-dimensional vector of the vibration signal feature is obtained. After feature extraction from vibration signal, the support vector machine (SVM) was applied to automate the fault diagnosis procedure. To improve the classification accuracy for bearing fault prediction, particle swarm optimization (PSO) is employed to simultaneously optimize the SVM kernel function parameter and the penalty parameter. The results have shown feasibility and effectiveness of the proposed approach

Keywords: condition monitoring, discrete wavelet transform, fault diagnosis, kurtosis, machine learning, particle swarm optimization, roller bearing, rotating machines, support vector machine, vibration measurement

Procedia PDF Downloads 442

Authors: Zhifei Hu, Feng Xia

Abstract:

In recent years, Graph neural network has been widely used in knowledge graph recommendation. The existing recommendation methods based on graph neural network extract information from knowledge graph through entity and relation, which may not be efficient in the way of information extraction. In order to better propose useful entity information for the current recommendation task in the knowledge graph, we propose an end-to-end Neural network Model based on multi-stream graph attentional Mechanism (MSGAT), which can effectively integrate the knowledge graph into the recommendation system by evaluating the importance of entities from both users and items. Specifically, we use the attention mechanism from the user's perspective to distil the domain nodes information of the predicted item in the knowledge graph, to enhance the user's information on items, and generate the feature representation of the predicted item. Due to user history, click items can reflect the user's interest distribution, we propose a multi-stream attention mechanism, based on the user's preference for entities and relationships, and the similarity between items to be predicted and entities, aggregate user history click item's neighborhood entity information in the knowledge graph and generate the user's feature representation. We evaluate our model on three real recommendation datasets: Movielens-1M (ML-1M), LFM-1B 2015 (LFM-1B), and Amazon-Book (AZ-book). Experimental results show that compared with the most advanced models, our proposed model can better capture the entity information in the knowledge graph, which proves the validity and accuracy of the model.

Keywords: graph attention network, knowledge graph, recommendation, information propagation

Procedia PDF Downloads 121

Authors: Aaditya U. Jhamb

Abstract:

Due to the current energy crisis that many countries are battling, energy-efficient buildings are the subject of extensive research in the modern technological era because of growing worries about energy consumption and its effects on the environment. The paper explores 8 factors that help determine energy efficiency for a building: (relative compactness, surface area, wall area, roof area, overall height, orientation, glazing area, and glazing area distribution), with Tsanas and Xifara providing a dataset. The data set employed 768 different residential building models to anticipate heating and cooling loads with a low mean squared error. By optimizing these characteristics, machine learning algorithms may assess and properly forecast a building's heating and cooling loads, lowering energy usage while increasing the quality of people's lives. As a result, the paper studied the magnitude of the correlation between these input factors and the two output variables using various statistical methods of analysis after determining which input variable was most closely associated with the output loads. The most conclusive model was the Decision Tree Regressor, which had a mean squared error of 0.258, whilst the least definitive model was the Isotonic Regressor, which had a mean squared error of 21.68. This paper also investigated the KNN Regressor and the Linear Regression, which had to mean squared errors of 3.349 and 18.141, respectively. In conclusion, the model, given the 8 input variables, was able to predict the heating and cooling loads of a residential building accurately and precisely.

Keywords: energy efficient buildings, heating load, cooling load, machine learning models

Procedia PDF Downloads 102

Authors: U. Ali Rahoma, Nabil Esawy, Fawzia Ibrahim Moursy, A. H. Hassan, Samy A. Khalil, Ashraf S. Khamees

Abstract:

The design of any solar energy conversion system requires the knowledge of solar radiation data obtained over a long period. Satellite data has been widely used to estimate solar energy where no ground observation of solar radiation is available, yet there are limitations on the temporal coverage of satellite data. Reanalysis is a “retrospective analysis” of the atmosphere parameters generated by assimilating observation data from various sources, including ground observation, satellites, ships, and aircraft observation with the output of NWP (Numerical Weather Prediction) models, to develop an exhaustive record of weather and climate parameters. The evaluation of the performance of reanalysis datasets (ERA-5) for North Africa against high-quality surface measured data was performed using statistical analysis. The estimation of global solar radiation (GSR) distribution over six different selected locations in North Africa during ten years from the period time 2011 to 2020. The root means square error (RMSE), mean bias error (MBE) and mean absolute error (MAE) of reanalysis data of solar radiation range from 0.079 to 0.222, 0.0145 to 0.198, and 0.055 to 0.178, respectively. The seasonal statistical analysis was performed to study seasonal variation of performance of datasets, which reveals the significant variation of errors in different seasons—the performance of the dataset changes by changing the temporal resolution of the data used for comparison. The monthly mean values of data show better performance, but the accuracy of data is compromised. The solar radiation data of ERA-5 is used for preliminary solar resource assessment and power estimation. The correlation coefficient (R2) varies from 0.93 to 99% for the different selected sites in North Africa in the present research. The goal of this research is to give a good representation for global solar radiation to help in solar energy application in all fields, and this can be done by using gridded data from European Centre for Medium-Range Weather Forecasts ECMWF and producing a new model to give a good result.

Keywords: solar energy, solar radiation, ERA-5, potential energy

Procedia PDF Downloads 216

Authors: Ching-Ting Hsu, Wei-Hua Ho, Yi-Chun Chang

Abstract:

Video object tracking is one of the popular research topics in computer graphics area. The trajectory can be applied in security, traffic control, even the sports training. The trajectory for sports training can be utilized to analyze the athlete’s performance without traditional sensors. There are many relevant works which utilize mean shift algorithm with background subtraction. This kind of the schemes should select a kernel function which may affect the accuracy and performance. In this paper, we consider the motion information in the pre-coded bitstream. The proposed algorithm extracts the trajectory by composing the motion vectors from the pre-coded bitstream. We gather the motion vectors from the overlap area of the object and calculate mean of the overlapped motion vectors. We implement and simulate our proposed algorithm in H.264 video codec. The performance is better than relevant works and keeps the accuracy of the object trajectory. The experimental results show that the proposed trajectory extraction can extract trajectory form the pre-coded bitstream in high accuracy and achieve higher performance other relevant works.

Keywords: H.264, video bitstream, video object tracking, sports training

Procedia PDF Downloads 429

Authors: Kishor Chandra Kandpal, Amit Kumar

Abstract:

The Indian Himalaya region harbours approximately 1748 plants of medicinal importance, and as per International Union for Conservation of Nature (IUCN), the 112 plant species among these are threatened and endangered. To ease the pressure on these plants, the government of India is encouraging its in-situ cultivation. The Saussurea costus, Valeriana jatamansi, and Picrorhiza kurroa have also been prioritized for large scale cultivation owing to their market demand, conservation value and medicinal properties. These species are found from 1000 m to 4000 m elevation ranges in the Indian Himalaya. Identification of these plants in the field requires taxonomic skills, which is one of the major bottleneck in the conservation and management of these plants. In recent years, Hyperspectral remote sensing techniques have been precisely used for the discrimination of plant species with the help of their unique spectral signatures. In this background, a spectral library of the above 03 medicinal plants was prepared by collecting the spectral data using a handheld spectroradiometer (325 to 1075 nm) from farmer’s fields of Himachal Pradesh and Uttarakhand states of Indian Himalaya. The Random forest (RF) model was implied on the spectral data for the classification of the medicinal plants. The 80:20 standard split ratio was followed for training and validation of the RF model, which resulted in training accuracy of 84.39 % (kappa coefficient = 0.72) and testing accuracy of 85.29 % (kappa coefficient = 0.77). This RF classifier has identified green (555 to 598 nm), red (605 nm), and near-infrared (725 to 840 nm) wavelength regions suitable for the discrimination of these species. The findings of this study have provided a technique for rapid and onsite identification of the above medicinal plants in the field. This will also be a key input for the classification of hyperspectral remote sensing images for mapping of these species in farmer’s field on a regional scale. This is a pioneer study in the Indian Himalaya region for medicinal plants in which the applicability of hyperspectral remote sensing has been explored.

Keywords: himalaya, hyperspectral remote sensing, machine learning; medicinal plants, random forests

Procedia PDF Downloads 208

Authors: Thanh N. Do

Abstract:

This paper addresses the modeling of two critical behaviors of concrete material in reinforced concrete components: (1) the increase in strength and ductility due to confining stresses from surrounding transverse steel reinforcements, and (2) the progressive deterioration in strength and stiffness due to high strain and/or cyclic loading. To improve the state-of-the-art, the author presents a new 3D constitutive model of concrete material based on plasticity and continuum damage mechanics theory to simulate both the confinement effect and the strength deterioration in reinforced concrete components. The model defines a yield function of the stress invariants and a compressive damage threshold based on the level of confining stresses to automatically capture the increase in strength and ductility when subjected to high compressive stresses. The model introduces two damage variables to describe the strength and stiffness deterioration under tensile and compressive stress states. The damage formulation characterizes well the degrading behavior of concrete material, including the nonsymmetric strength softening in tension and compression, as well as the progressive strength and stiffness degradation under primary and follower load cycles. The proposed damage model is implemented in a general purpose finite element analysis program allowing an extensive set of numerical simulations to assess its ability to capture the confinement effect and the degradation of the load-carrying capacity and stiffness of structural elements. It is validated against a collection of experimental data of the hysteretic behavior of reinforced concrete columns and shear walls under different load histories. These correlation studies demonstrate the ability of the model to describe vastly different hysteretic behaviors with a relatively consistent set of parameters. The model shows excellent consistency in response determination with very good accuracy. Its numerical robustness and computational efficiency are also very good and will be further assessed with large-scale simulations of structural systems.

Keywords: concrete, damage-plasticity, shear wall, confinement

Procedia PDF Downloads 173

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 425

Authors: Jaouadi Imen, Ben Djemaa Raoudha, Ben Abdallah Hanene

Abstract:

The access to relevant information that is adapted to users’ needs, preferences and environment is a challenge in many applications running. That causes an appearance of context-aware systems. To facilitate the development of this class of applications, it is necessary that these applications share a common context meta-model. In this article, we will present our context meta-model that is defined using the OMG Meta Object facility (MOF). This meta-model is based on the analysis and synthesis of context concepts proposed in literature.

Keywords: context, meta-model, MOF, awareness system

Procedia PDF Downloads 566

Authors: Ahmed Kayad Abdourazak, Abderafi Souad, Zejli Driss, Idriss Abdoulkader Ibrahim

Abstract:

In this paper Artificial Neural Network (ANN) is used to predict the solar irradiation in Djibouti for the first Time that is useful to the integration of Concentrating Solar Power (CSP) and sites selections for new or future solar plants as part of solar energy development. An ANN algorithm was developed to establish a forward/reverse correspondence between the latitude, longitude, altitude and monthly solar irradiation. For this purpose the German Aerospace Centre (DLR) data of eight Djibouti sites were used as training and testing in a standard three layers network with the back propagation algorithm of Lavenber-Marquardt. Results have shown a very good agreement for the solar irradiation prediction in Djibouti and proves that the proposed approach can be well used as an efficient tool for prediction of solar irradiation by providing so helpful information concerning sites selection, design and planning of solar plants.

Keywords: artificial neural network, solar irradiation, concentrated solar power, Lavenberg-Marquardt

Procedia PDF Downloads 357

Authors: S. Boria

Abstract:

In the last years, the crashworthiness of an automotive body structure can be improved, since the beginning of the design stage, thanks to the development of specific optimization tools. It is well known how the finite element codes can help the designer to investigate the crashing performance of structures under dynamic impact. Therefore, by coupling nonlinear mathematical programming procedure and statistical techniques with FE simulations, it is possible to optimize the design with reduced number of analytical evaluations. In engineering applications, many optimization methods which are based on statistical techniques and utilize estimated models, called meta-models, are quickly spreading. A meta-model is an approximation of a detailed simulation model based on a dataset of input, identified by the design of experiments (DOE); the number of simulations needed to build it depends on the number of variables. Among the various types of meta-modeling techniques, Kriging method seems to be excellent in accuracy, robustness and efficiency compared to other ones when applied to crashworthiness optimization. Therefore the application of such meta-model was used in this work, in order to improve the structural optimization of a bumper for a racing car in composite material subjected to frontal impact. The specific energy absorption represents the objective function to maximize and the geometrical parameters subjected to some design constraints are the design variables. LS-DYNA codes were interfaced with LS-OPT tool in order to find the optimized solution, through the use of a domain reduction strategy. With the use of the Kriging meta-model the crashworthiness characteristic of the composite bumper was improved.

Keywords: composite material, crashworthiness, finite element analysis, optimization

Procedia PDF Downloads 258

Authors: Buse T. Aydin, Enver Ozdemir

Abstract:

An automatic dependent surveillance-broadcast (ADS-B) system has serious security problems. In this study, a double layer authentication scheme between the aircraft and ground station, aircraft to aircraft, ground station to ATC tower is designed to prevent any unauthorized aircrafts from introducing themselves as friends. This method can be used as a solution to the problem of authentication. The method is a combination of classical cryptographic methods and new generation physical layers. The first layer has employed the embedded key of the aircraft. The embedded key is assumed to installed during the construction of the utility. The other layer is a physical attribute (flight path, distance, etc.) between the aircraft and the ATC tower. We create a mathematical model so that two layers’ information is employed and an aircraft is authenticated as a friend or unknown according to the accuracy of the results of the model. The results of the aircraft are compared with the results of the ATC tower and if the values found by the aircraft and ATC tower match within a certain error margin, we mark the aircraft as friend. As a result, the ADS-B messages coming from this authenticated friendly aircraft will be processed. In this method, even if the embedded key is captured by the unknown aircraft, without the information of the second layer, the unknown aircraft can easily be determined. Overall, in this work, we present a reliable system by adding physical layer in the authentication process.

Keywords: ADS-B, authentication, communication with physical layer security, cryptography, identification friend or foe

Procedia PDF Downloads 185

Authors: Anthony D. Rhodes, Manan Goel

Abstract:

We provide a high fidelity deep learning algorithm (HyperSeg) for interactive video segmentation tasks using a dense convolutional network with context-aware skip connections and compressed, 'hypercolumn' image features combined with a convolutional tessellation procedure. In order to maintain high output fidelity, our model crucially processes and renders all image features in high resolution, without utilizing downsampling or pooling procedures. We maintain this consistent, high grade fidelity efficiently in our model chiefly through two means: (1) we use a statistically-principled, tensor decomposition procedure to modulate the number of hypercolumn features and (2) we render these features in their native resolution using a convolutional tessellation technique. For improved pixel-level segmentation results, we introduce a boundary loss function; for improved temporal coherence in video data, we include temporal image information in our model. Through experiments, we demonstrate the improved accuracy of our model against baseline models for interactive segmentation tasks using high resolution video data. We also introduce a benchmark video segmentation dataset, the VFX Segmentation Dataset, which contains over 27,046 high resolution video frames, including green screen and various composited scenes with corresponding, hand-crafted, pixel-level segmentations. Our work presents a improves state of the art segmentation fidelity with high resolution data and can be used across a broad range of application domains, including VFX pipelines and medical imaging disciplines.

Keywords: computer vision, object segmentation, interactive segmentation, model compression

Procedia PDF Downloads 123

Authors: Zhongzhi Hu, Jie Shen, Jiqiang Wang

Abstract:

A high precision aeroengine model is needed when developing the engine control system. Compared with other main components, the axial compressor is the most challenging component to simulate. In this paper, a compressor map optimizing tool based on the introduction of a modifiable β function is developed for FWorks (FADEC Works). Three parameters (d density, f fitting coefficient, k₀ slope of the line β=0) are introduced to the β function to make it modifiable. The comparison of the traditional β function and the modifiable β function is carried out for a certain type of compressor. The interpolation errors show that both methods meet the modeling requirements, while the modifiable β function can predict compressor performance more accurately for some areas of the compressor map where the users are interested in.

Keywords: beta function, compressor map, interpolation error, map optimization tool

Procedia PDF Downloads 274

Authors: Abdulla D. Alblooshi

Abstract:

The stock market is a representation of human behavior and psychology, such as fear, greed, and discipline. Those are manifested in the form of price movements during the trading sessions. Therefore, predicting the stock movement and prices is a challenging effort. However, those trading sessions produce a large amount of data that can be utilized to train an AI agent for the purpose of predicting the stock movement. Predicting the stock market price action will be advantageous. In this paper, the stock movement data of three DFM listed stocks are studied using historical price movements and technical indicators value and used to train an agent using KNN and SVM methods to predict the future price movement. MATLAB Toolbox and a simple script is written to process and classify the information and output the prediction. It will also compare the different learning methods and parameters s using metrics like RMSE, MAE, and R².

Keywords: KNN, ANN, style, SVM, stocks, technical indicators, RSI, MACD, moving averages, RMSE, MAE

Procedia PDF Downloads 175

Authors: K. Sekulová, M. Šimon

Abstract:

This article focuses on upper-extremity musculoskeletal disorders risk assessment model at workplace. In this model are used risk factors that are responsible for musculoskeletal system damage. Based on statistic calculations the model is able to define what risk of MSD threatens workers who are under risk factors. The model is also able to say how MSD risk would decrease if these risk factors are eliminated.

Keywords: ergonomics, musculoskeletal disorders, occupational diseases, risk factors

Procedia PDF Downloads 554

Authors: Anthony Usoro

Abstract:

In this paper, two classes of bilinear time series model are obtained under certain conditions from the general bilinear autoregressive moving average model. Bilinear Autoregressive (BAR) and Bilinear Moving Average (BMA) Models have been identified. From the general bilinear model, BAR and BMA models have been proved to exist for q = Q = 0, => j = 0, and p = P = 0, => i = 0 respectively. These models are found useful in modelling most of the economic and financial data.

Keywords: autoregressive model, bilinear autoregressive model, bilinear moving average model, moving average model

Procedia PDF Downloads 414

Authors: A. Shakoor, M. Arshad

Abstract:

The utilization of groundwater resources in irrigation has significantly increased during the last two decades due to constrained canal water supplies. More than 70% of the farmers in the Punjab, Pakistan, depend directly or indirectly on groundwater to meet their crop water demands and hence, an unchecked paradigm shift has resulted in aquifer depletion and deterioration. Therefore, a comprehensive research was carried at central Punjab-Pakistan, regarding spatiotemporal variation in groundwater level and quality. Processing MODFLOW for window (PMWIN) and MT3D (solute transport model) models were used for existing and future prediction of groundwater level and quality till 2030. The comprehensive data set of aquifer lithology, canal network, groundwater level, groundwater salinity, evapotranspiration, groundwater abstraction, recharge etc. were used in PMWIN model development. The model was thus, successfully calibrated and validated with respect to groundwater level for the periods of 2003 to 2007 and 2008 to 2012, respectively. The coefficient of determination (R2) and model efficiency (MEF) for calibration and validation period were calculated as 0.89 and 0.98, respectively, which argued a high level of correlation between the calculated and measured data. For solute transport model (MT3D), the values of advection and dispersion parameters were used. The model used for future scenario up to 2030, by assuming that there would be no uncertain change in climate and groundwater abstraction rate would increase gradually. The model predicted results revealed that the groundwater would decline from 0.0131 to 1.68m/year during 2013 to 2030 and the maximum decline would be on the lower side of the study area, where infrastructure of canal system is very less. This lowering of groundwater level might cause an increase in the tubewell installation and pumping cost. Similarly, the predicted total dissolved solids (TDS) of the groundwater would increase from 6.88 to 69.88mg/L/year during 2013 to 2030 and the maximum increase would be on lower side. It was found that in 2030, the good quality would reduce by 21.4%, while marginal and hazardous quality water increased by 19.28 and 2%, respectively. It was found from the simulated results that the salinity of the study area had increased due to the intrusion of salts. The deterioration of groundwater quality would cause soil salinity and ultimately the reduction in crop productivity. It was concluded from the predicted results of groundwater model that the groundwater deteriorated with the depth of water table i.e. TDS increased with declining groundwater level. It is recommended that agronomic and engineering practices i.e. land leveling, rainwater harvesting, skimming well, ASR (Aquifer Storage and Recovery Wells) etc. should be integrated to meliorate management of groundwater for higher crop production in salt affected soils.

Keywords: groundwater quality, groundwater management, PMWIN, MT3D model

Procedia PDF Downloads 382

Authors: Anita Setianingrum, Oki S. Jaya, Zuherman Rustam

Abstract:

Forecasting stock price is a challenging task due to the complex time series of the data. The complexity arises from many variables that affect the stock market. Many time series models have been proposed before, but those previous models still have some problems: 1) put the subjectivity of choosing the technical indicators, and 2) rely upon some assumptions about the variables, so it is limited to be applied to all datasets. Therefore, this paper studied a novel Adaptive Neuro-Fuzzy Inference System (ANFIS) time series model based on Support Vector Regression (SVR) for forecasting the stock market. In order to evaluate the performance of proposed models, stock market transaction data of TAIEX and HIS from January to December 2015 is collected as experimental datasets. As a result, the method has outperformed its counterparts in terms of accuracy.

Keywords: ANFIS, fuzzy time series, stock forecasting, SVR

Procedia PDF Downloads 251

Authors: Wenlong Feng, Zhenchun Du, Jianguo Yang

Abstract:

To decrease the grating scale thermal expansion error, a novel method which based on multiple temperature detections is proposed. Several temperature sensors are installed on the grating scale and the temperatures of these sensors are recorded. The temperatures of every point on the grating scale are calculated by interpolating between adjacent sensors. According to the thermal expansion principle, the grating scale thermal expansion error model can be established by doing the integral for the variations of position and temperature. A novel compensation method is proposed in this paper. By applying the established error model, the grating scale thermal expansion error is decreased by 90% compared with no compensation. The residual positioning error of the grating scale is less than 15um/10m and the accuracy of the machine tool is significant improved.

Keywords: thermal expansion error of grating scale, error compensation, machine tools, integral method

Procedia PDF Downloads 375

Authors: Jossitt Williams Vargas Cruz, Aura Jazmín Pérez Ríos

Abstract:

The variations of solar dynamics have become a relevant topic of study due to the effects of climate changes generated on the earth. One of the most disconcerting aspects is the variability that the sun has on the climate is the role played by sunspots (extra-atmospheric variable) in the modulation of the Cosmic Rays CR (extra-atmospheric variable). CRs influence the earth's climate by affecting cloud formation (atmospheric variable), and solar cycle influence is associated with the presence of solar storms, and the magnetic activity is greater, resulting in less CR entering the earth's atmosphere. The different methods of climate prediction in Colombia do not take into account the extra-atmospheric variables. Therefore, correlations between atmospheric and extra-atmospheric variables were studied in order to implement a Python code based on neural networks to make the prediction of the extra-atmospheric variable with the highest correlation.

Keywords: correlations, cosmic rays, sun, sunspots and variations.

Procedia PDF Downloads 80

Authors: Chithra A. V., Somoshree Datta, Sandeep Nithyanandan

Abstract:

Sign Language Recognition (SLR) is the process of interpreting and translating sign language into spoken or written language using technological systems. It involves recognizing hand gestures, facial expressions, and body movements that makeup sign language communication. The primary goal of SLR is to facilitate communication between hearing- and speech-impaired communities and those who do not understand sign language. Due to the increased awareness and greater recognition of the rights and needs of the hearing- and speech-impaired community, sign language recognition has gained significant importance over the past 10 years. Technological advancements in the fields of Artificial Intelligence and Machine Learning have made it more practical and feasible to create accurate SLR systems. This paper presents a distinct approach to SLR by framing it as a video classification problem using Deep Learning (DL), whereby a combination of Convolutional Neural Networks (CNNs) and Recurrent Neural Networks (RNNs) has been used. This research targets the integration of sign language recognition into healthcare settings, aiming to improve communication between medical professionals and patients with hearing impairments. The spatial features from each video frame are extracted using a CNN, which captures essential elements such as hand shapes, movements, and facial expressions. These features are then fed into an RNN network that learns the temporal dependencies and patterns inherent in sign language sequences. The INCLUDE dataset has been enhanced with more videos from the healthcare domain and the model is evaluated on the same. Our model achieves 91% accuracy, representing state-of-the-art performance in this domain. The results highlight the effectiveness of treating SLR as a video classification task with the CNN-RNN architecture. This approach not only improves recognition accuracy but also offers a scalable solution for real-time SLR applications, significantly advancing the field of accessible communication technologies.

Keywords: sign language recognition, deep learning, convolution neural network, recurrent neural network

Procedia PDF Downloads 35

Authors: K. Khaerunnisa, D. Ryangga, S. A. Pawiro

Abstract:

Over the past few decades, film dosimetry has become a tool which is used in various radiotherapy modalities, either for clinical quality assurance (QA) or dose verification. The response of the film to irradiation is usually expressed in optical density (OD) or net optical density (netOD). While the film's response to radiation is not linear, then the use of film as a dosimeter must go through a calibration process. This study aimed to compare the function of the calibration curve of various measurement methods with various densitometer, using a flat bad scanner, point densitometer and spectrophotometer. For every response function, a radichromic film calibration curve is generated from each method by performing accuracy, precision and sensitivity analysis. netOD is obtained by measuring changes in the optical density (OD) of the film before irradiation and after irradiation when using a film scanner if it uses ImageJ to extract the pixel value of the film on the red channel of three channels (RGB), calculate the change in OD before and after irradiation when using a point densitometer, and calculate changes in absorbance before and after irradiation when using a spectrophotometer. the results showed that the three calibration methods gave readings with a netOD precision of doses below 3% for the uncertainty value of 1σ (one sigma). while the sensitivity of all three methods has the same trend in responding to film readings against radiation, it has a different magnitude of sensitivity. while the accuracy of the three methods provides readings below 3% for doses above 100 cGy and 200 cGy, but for doses below 100 cGy found above 3% when using point densitometers and spectrophotometers. when all three methods are used for clinical implementation, the results of the study show accuracy and precision below 2% for the use of scanners and spectrophotometers and above 3% for precision and accuracy when using point densitometers.

Keywords: Callibration Methods, Film Dosimetry EBT3, Flat Bad Scanner, Densitomete, Spectrophotometer

Procedia PDF Downloads 138

Authors: Frantisek Odvarka

Abstract:

Based on the data from the Moravian Karst, the influence of the calcite speleothem growth by selected meteorological factors was evaluated. External temperature was determined as one of the main factors influencing speleothem growth in Moravian Karst. This factor significantly influences the CO₂ concentration in soil/epikarst, and cave atmosphere in the Moravian Karst and significantly contributes to the changes in the CO₂ partial pressure differences between soil/epikarst and cave atmosphere in Moravian Karst, which determines the drip water supersaturation with respect to the calcite and quantity of precipitated calcite in the Moravian Karst cave environment. External air temperatures and cave air temperatures were measured using a COMET S3120 data logger, which can measure temperatures in the range from -30 to +80 °C with an accuracy of ± 0.4 °C. CO₂ concentrations in the cave and soils were measured with a FT A600 CO₂H Ahlborn probe (value range 0 ppmv to 10,000 ppmv, accuracy 1 ppmv), which was connected to the data logger ALMEMO 2290-4, V5 Ahlborn. The soil temperature was measured with a FHA646E1 Ahlborn probe (temperature range -20 to 70 °C, accuracy ± 0.4 °C) connected to an ALMEMO 2290-4 V5 Ahlborn data logger. The airflow velocities into and out of the cave were monitored by a FVA395 TH4 Thermo anemometer (speed range from 0.05 to 2 m s⁻¹, accuracy ± 0.04 m s⁻¹), which was connected to the ALMEMO 2590-4 V5 Ahlborn data logger for recording. The flow was measured in the lower and upper entrance of the Imperial Cave. The data were analyzed in MS Office Excel 2019 and PHREEQC.

Keywords: speleothem growth, carbon dioxide partial pressure, Moravian Karst, external temperature

Procedia PDF Downloads 147

Authors: Dewi Juliah Ratnaningsih, Imas Sukaesih Sitanggang

Abstract:

Classification is one of data mining techniques that aims to discover a model from training data that distinguishes records into the appropriate category or class. Data mining classification methods can be applied in education, for example, to determine the classification of non-active students in Indonesia Open University. This paper presents a comparison of three methods of classification: Naïve Bayes, Bagging, and C.45. The criteria used to evaluate the performance of three methods of classification are stratified cross-validation, confusion matrix, the value of the area under the ROC Curve (AUC), Recall, Precision, and F-measure. The data used for this paper are from the non-active Indonesia Open University students in registration period of 2004.1 to 2012.2. Target analysis requires that non-active students were divided into 3 groups: C1, C2, and C3. Data analyzed are as many as 4173 students. Results of the study show: (1) Bagging method gave a high degree of classification accuracy than Naïve Bayes and C.45, (2) the Bagging classification accuracy rate is 82.99 %, while the Naïve Bayes and C.45 are 80.04 % and 82.74 % respectively, (3) the result of Bagging classification tree method has a large number of nodes, so it is quite difficult in decision making, (4) classification of non-active Indonesia Open University student characteristics uses algorithms C.45, (5) based on the algorithm C.45, there are 5 interesting rules which can describe the characteristics of non-active Indonesia Open University students.

Keywords: comparative analysis, data mining, clasiffication, Bagging, Naïve Bayes, C.45, non-active students, Indonesia Open University

Procedia PDF Downloads 319

Authors: Roza Dzierzak, Waldemar Wojcik, Piotr Kacejko

Abstract:

Analysis of the texture of medical images consists of determining the parameters and characteristics of the examined tissue. The main goal is to assign the analyzed area to one of two basic groups: as a healthy tissue or a tissue with pathological changes. The CT images of the thoracic lumbar spine from 15 healthy patients and 15 with confirmed osteoporosis were used for the analysis. As a result, 120 samples with dimensions of 50x50 pixels were obtained. The set of features has been obtained based on the histogram, gradient, run-length matrix, co-occurrence matrix, autoregressive model, and Haar wavelet. As a result of the image analysis, 290 descriptors of textural features were obtained. The dimension of the space of features was reduced by the use of three selection methods: Fisher coefficient (FC), mutual information (MI), minimization of the classification error probability and average correlation coefficients between the chosen features minimization of classification error probability (POE) and average correlation coefficients (ACC). Each of them returned ten features occupying the initial place in the ranking devised according to its own coefficient. As a result of the Fisher coefficient and mutual information selections, the same features arranged in a different order were obtained. In both rankings, the 50% percentile (Perc.50%) was found in the first place. The next selected features come from the co-occurrence matrix. The sets of features selected in the selection process were evaluated using six classification tree methods. These were: decision stump (DS), Hoeffding tree (HT), logistic model trees (LMT), random forest (RF), random tree (RT) and reduced error pruning tree (REPT). In order to assess the accuracy of classifiers, the following parameters were used: overall classification accuracy (ACC), true positive rate (TPR, classification sensitivity), true negative rate (TNR, classification specificity), positive predictive value (PPV) and negative predictive value (NPV). Taking into account the classification results, it should be stated that the best results were obtained for the Hoeffding tree and logistic model trees classifiers, using the set of features selected by the POE + ACC method. In the case of the Hoeffding tree classifier, the highest values of three parameters were obtained: ACC = 90%, TPR = 93.3% and PPV = 93.3%. Additionally, the values of the other two parameters, i.e., TNR = 86.7% and NPV = 86.6% were close to the maximum values obtained for the LMT classifier. In the case of logistic model trees classifier, the same ACC value was obtained ACC=90% and the highest values for TNR=88.3% and NPV= 88.3%. The values of the other two parameters remained at a level close to the highest TPR = 91.7% and PPV = 91.6%. The results obtained in the experiment show that the use of classification trees is an effective method of classification of texture features. This allows identifying the conditions of the spongy tissue for healthy cases and those with the porosis.

Keywords: classification, feature selection, texture analysis, tree algorithms

Procedia PDF Downloads 184

Authors: Chung-Ming Lo, Kevin Li-Chun Hsieh

Abstract:

The central nervous system in the World Health Organization defines grade 2, 3, 4 gliomas according to the aggressiveness. For brain tumors, using image examination would have a lower risk than biopsy. Besides, it is a challenge to extract relevant tissues from biopsy operation. Observing the whole tumor structure and composition can provide a more objective assessment. This study further proposed a computer-aided diagnosis (CAD) system based on a convolutional neural network to quantitatively evaluate a tumor's malignancy from brain magnetic resonance imaging. A total of 30 grade 2, 43 grade 3, and 57 grade 4 gliomas were collected in the experiment. Transferred parameters from AlexNet were fine-tuned to classify the target brain tumors and achieved an accuracy of 98% and an area under the receiver operating characteristics curve (Az) of 0.99. Without pre-trained features, only 61% of accuracy was obtained. The proposed convolutional neural network can accurately and efficiently classify grade 2, 3, and 4 gliomas. The promising accuracy can provide diagnostic suggestions to radiologists in the clinic.

Keywords: convolutional neural network, computer-aided diagnosis, glioblastoma, magnetic resonance imaging

Procedia PDF Downloads 152

Authors: Dhahri Maher, Aouinet Hana

Abstract:

The presence of bubbles in the boundary layer introduces corrections into the log law, which must be taken into account. In this work, a logarithmic wall law was presented for bubbly two phase flows. The wall law presented in this work was based on the postulation of additional turbulent viscosity associated with bubble wakes in the boundary layer. The presented wall law contained empirical constant accounting both for shear induced turbulence interaction and for non-linearity of bubble. This constant was deduced from experimental data. The wall friction prediction achieved with the wall law was compared to the experimental data, in the case of a turbulent boundary layer developing on a vertical flat plate in the presence of millimetric bubbles. A very good agreement between experimental and numerical wall friction prediction was verified. The agreement was especially noticeable for the low void fraction when bubble induced turbulence plays a significant role.

Keywords: bubbly flows, log law, boundary layer, CFD

Procedia PDF Downloads 281

Authors: Abdelkader Hachemi & Boualem Remini

Abstract:

Seawater intrusion is a significant challenge faced by coastal aquifers in the Mediterranean basin. This study aims to determine the position of the sharp interface between seawater and freshwater in the aquifer of Wadi Nador, located in the Wilaya of Tipaza, Algeria. A numerical areal sharp interface model using the finite element method is developed to investigate the spatial and temporal behavior of seawater intrusion. The aquifer is assumed to be homogeneous and isotropic. The simulation results are compared with geophysical prospection data obtained through electrical methods in 2011 to validate the model. The simulation results demonstrate a good agreement with the geophysical prospection data, confirming the accuracy of the sharp interface model. The position of the sharp interface in the aquifer is found to be approximately 1617 meters from the sea. Two scenarios are proposed to predict the interface position for the year 2024: one without pumping and the other with pumping. The results indicate a noticeable retreat of the sharp interface position in the first scenario, while a slight decline is observed in the second scenario. The findings of this study provide valuable insights into the dynamics of seawater intrusion in the Wadi Nador aquifer. The predicted changes in the sharp interface position highlight the potential impact of pumping activities on the aquifer's vulnerability to seawater intrusion. This study emphasizes the importance of implementing measures to manage and mitigate seawater intrusion in coastal aquifers. The sharp interface model developed in this research can serve as a valuable tool for assessing and monitoring the vulnerability of aquifers to seawater intrusion.

Keywords: seawater, intrusion, sharp interface, Algeria

Procedia PDF Downloads 80

Authors: Sandra Mitrovic, Gaurav Singh

Abstract:

In many industries, including telecommunications, churn prediction has been a topic of active research. A lot of attention has been drawn on devising the most informative features, and this area of research has gained even more focus with spread of (social) network analytics. The call detail records (CDRs) have been used to construct customer networks and extract potentially useful features. However, to the best of our knowledge, no studies including network features have yet proposed a generic way of representing network information. Instead, ad-hoc and dataset dependent solutions have been suggested. In this work, we build upon a recently presented method (node2vec) to obtain representations for nodes in observed network. The proposed approach is generic and applicable to any network and domain. Unlike node2vec, which assumes a static network, we consider a dynamic and time-evolving network. To account for this, we propose an approach that constructs the feature representation of each node by generating its node2vec representations at different timestamps, concatenating them and finally compressing using an auto-encoder-like method in order to retain reasonably long and informative feature vectors. We test the proposed method on churn prediction task in telco domain. To predict churners at timestamp ts+1, we construct training and testing datasets consisting of feature vectors from time intervals [t1, ts-1] and [t2, ts] respectively, and use traditional supervised classification models like SVM and Logistic Regression. Observed results show the effectiveness of proposed approach as compared to ad-hoc feature selection based approaches and static node2vec.

Keywords: churn prediction, dynamic networks, node2vec, auto-encoders

Procedia PDF Downloads 317