Search results for: time prediction algorithms
20618 Estimation of Relative Subsidence of Collapsible Soils Using Electromagnetic Measurements
Authors: Henok Hailemariam, Frank Wuttke
Abstract:
Collapsible soils are weak soils that appear to be stable in their natural state, normally dry condition, but rapidly deform under saturation (wetting), thus generating large and unexpected settlements which often yield disastrous consequences for structures unwittingly built on such deposits. In this study, a prediction model for the relative subsidence of stressed collapsible soils based on dielectric permittivity measurement is presented. Unlike most existing methods for soil subsidence prediction, this model does not require moisture content as an input parameter, thus providing the opportunity to obtain accurate estimation of the relative subsidence of collapsible soils using dielectric measurement only. The prediction model is developed based on an existing relative subsidence prediction model (which is dependent on soil moisture condition) and an advanced theoretical frequency and temperature-dependent electromagnetic mixing equation (which effectively removes the moisture content dependence of the original relative subsidence prediction model). For large scale sub-surface soil exploration purposes, the spatial sub-surface soil dielectric data over wide areas and high depths of weak (collapsible) soil deposits can be obtained using non-destructive high frequency electromagnetic (HF-EM) measurement techniques such as ground penetrating radar (GPR). For laboratory or small scale in-situ measurements, techniques such as an open-ended coaxial line with widely applicable time domain reflectometry (TDR) or vector network analysers (VNAs) are usually employed to obtain the soil dielectric data. By using soil dielectric data obtained from small or large scale non-destructive HF-EM investigations, the new model can effectively predict the relative subsidence of weak soils without the need to extract samples for moisture content measurement. Some of the resulting benefits are the preservation of the undisturbed nature of the soil as well as a reduction in the investigation costs and analysis time in the identification of weak (problematic) soils. The accuracy of prediction of the presented model is assessed by conducting relative subsidence tests on a collapsible soil at various initial soil conditions and a good match between the model prediction and experimental results is obtained.Keywords: collapsible soil, dielectric permittivity, moisture content, relative subsidence
Procedia PDF Downloads 36120617 Digital Structural Monitoring Tools @ADaPT for Cracks Initiation and Growth due to Mechanical Damage Mechanism
Authors: Faizul Azly Abd Dzubir, Muhammad F. Othman
Abstract:
Conventional structural health monitoring approach for mechanical equipment uses inspection data from Non-Destructive Testing (NDT) during plant shut down window and fitness for service evaluation to estimate the integrity of the equipment that is prone to crack damage. Yet, this forecast is fraught with uncertainty because it is often based on assumptions of future operational parameters, and the prediction is not continuous or online. Advanced Diagnostic and Prognostic Technology (ADaPT) uses Acoustic Emission (AE) technology and a stochastic prognostic model to provide real-time monitoring and prediction of mechanical defects or cracks. The forecast can help the plant authority handle their cracked equipment before it ruptures, causing an unscheduled shutdown of the facility. The ADaPT employs process historical data trending, finite element analysis, fitness for service, and probabilistic statistical analysis to develop a prediction model for crack initiation and growth due to mechanical damage. The prediction model is combined with live equipment operating data for real-time prediction of the remaining life span owing to fracture. ADaPT was devised at a hot combined feed exchanger (HCFE) that had suffered creep crack damage. The ADaPT tool predicts the initiation of a crack at the top weldment area by April 2019. During the shutdown window in April 2019, a crack was discovered and repaired. Furthermore, ADaPT successfully advised the plant owner to run at full capacity and improve output by up to 7% by April 2019. ADaPT was also used on a coke drum that had extensive fatigue cracking. The initial cracks are declared safe with ADaPT, with remaining crack lifetimes extended another five (5) months, just in time for another planned facility downtime to execute repair. The prediction model, when combined with plant information data, allows plant operators to continuously monitor crack propagation caused by mechanical damage for improved maintenance planning and to avoid costly shutdowns to repair immediately.Keywords: mechanical damage, cracks, continuous monitoring tool, remaining life, acoustic emission, prognostic model
Procedia PDF Downloads 7420616 Using Historical Data for Stock Prediction
Authors: Sofia Stoica
Abstract:
In this paper, we use historical data to predict the stock price of a tech company. To this end, we use a dataset consisting of the stock prices in the past five years of ten major tech companies – Adobe, Amazon, Apple, Facebook, Google, Microsoft, Netflix, Oracle, Salesforce, and Tesla. We experimented with a variety of models– a linear regressor model, K nearest Neighbors (KNN), a sequential neural network – and algorithms - Multiplicative Weight Update, and AdaBoost. We found that the sequential neural network performed the best, with a testing error of 0.18%. Interestingly, the linear model performed the second best with a testing error of 0.73%. These results show that using historical data is enough to obtain high accuracies, and a simple algorithm like linear regression has a performance similar to more sophisticated models while taking less time and resources to implement.Keywords: finance, machine learning, opening price, stock market
Procedia PDF Downloads 18820615 Hybrid Fuzzy Weighted K-Nearest Neighbor to Predict Hospital Readmission for Diabetic Patients
Authors: Soha A. Bahanshal, Byung G. Kim
Abstract:
Identification of patients at high risk for hospital readmission is of crucial importance for quality health care and cost reduction. Predicting hospital readmissions among diabetic patients has been of great interest to many researchers and health decision makers. We build a prediction model to predict hospital readmission for diabetic patients within 30 days of discharge. The core of the prediction model is a modified k Nearest Neighbor called Hybrid Fuzzy Weighted k Nearest Neighbor algorithm. The prediction is performed on a patient dataset which consists of more than 70,000 patients with 50 attributes. We applied data preprocessing using different techniques in order to handle data imbalance and to fuzzify the data to suit the prediction algorithm. The model so far achieved classification accuracy of 80% compared to other models that only use k Nearest Neighbor.Keywords: machine learning, prediction, classification, hybrid fuzzy weighted k-nearest neighbor, diabetic hospital readmission
Procedia PDF Downloads 18520614 Integration of Big Data to Predict Transportation for Smart Cities
Authors: Sun-Young Jang, Sung-Ah Kim, Dongyoun Shin
Abstract:
The Intelligent transportation system is essential to build smarter cities. Machine learning based transportation prediction could be highly promising approach by delivering invisible aspect visible. In this context, this research aims to make a prototype model that predicts transportation network by using big data and machine learning technology. In detail, among urban transportation systems this research chooses bus system. The research problem that existing headway model cannot response dynamic transportation conditions. Thus, bus delay problem is often occurred. To overcome this problem, a prediction model is presented to fine patterns of bus delay by using a machine learning implementing the following data sets; traffics, weathers, and bus statues. This research presents a flexible headway model to predict bus delay and analyze the result. The prototyping model is composed by real-time data of buses. The data are gathered through public data portals and real time Application Program Interface (API) by the government. These data are fundamental resources to organize interval pattern models of bus operations as traffic environment factors (road speeds, station conditions, weathers, and bus information of operating in real-time). The prototyping model is designed by the machine learning tool (RapidMiner Studio) and conducted tests for bus delays prediction. This research presents experiments to increase prediction accuracy for bus headway by analyzing the urban big data. The big data analysis is important to predict the future and to find correlations by processing huge amount of data. Therefore, based on the analysis method, this research represents an effective use of the machine learning and urban big data to understand urban dynamics.Keywords: big data, machine learning, smart city, social cost, transportation network
Procedia PDF Downloads 26020613 Comparing Community Detection Algorithms in Bipartite Networks
Authors: Ehsan Khademi, Mahdi Jalili
Abstract:
Despite the special features of bipartite networks, they are common in many systems. Real-world bipartite networks may show community structure, similar to what one can find in one-mode networks. However, the interpretation of the community structure in bipartite networks is different as compared to one-mode networks. In this manuscript, we compare a number of available methods that are frequently used to discover community structure of bipartite networks. These networks are categorized into two broad classes. One class is the methods that, first, transfer the network into a one-mode network, and then apply community detection algorithms. The other class is the algorithms that have been developed specifically for bipartite networks. These algorithms are applied on a model network with prescribed community structure.Keywords: community detection, bipartite networks, co-clustering, modularity, network projection, complex networks
Procedia PDF Downloads 62420612 Cooperative Coevolution for Neuro-Evolution of Feed Forward Networks for Time Series Prediction Using Hidden Neuron Connections
Authors: Ravneil Nand
Abstract:
Cooperative coevolution uses problem decomposition methods to solve a larger problem. The problem decomposition deals with breaking down the larger problem into a number of smaller sub-problems depending on their method. Different problem decomposition methods have their own strengths and limitations depending on the neural network used and application problem. In this paper we are introducing a new problem decomposition method known as Hidden-Neuron Level Decomposition (HNL). The HNL method is competing with established problem decomposition method in time series prediction. The results show that the proposed approach has improved the results in some benchmark data sets when compared to the standalone method and has competitive results when compared to methods from literature.Keywords: cooperative coevaluation, feed forward network, problem decomposition, neuron, synapse
Procedia PDF Downloads 33320611 An Application to Predict the Best Study Path for Information Technology Students in Learning Institutes
Authors: L. S. Chathurika
Abstract:
Early prediction of student performance is an important factor to be gained academic excellence. Whatever the study stream in secondary education, students lay the foundation for higher studies during the first year of their degree or diploma program in Sri Lanka. The information technology (IT) field has certain improvements in the education domain by selecting specialization areas to show the talents and skills of students. These specializations can be software engineering, network administration, database administration, multimedia design, etc. After completing the first-year, students attempt to select the best path by considering numerous factors. The purpose of this experiment is to predict the best study path using machine learning algorithms. Five classification algorithms: decision tree, support vector machine, artificial neural network, Naïve Bayes, and logistic regression are selected and tested. The support vector machine obtained the highest accuracy, 82.4%. Then affecting features are recognized to select the best study path.Keywords: algorithm, classification, evaluation, features, testing, training
Procedia PDF Downloads 11820610 Prediction of PM₂.₅ Concentration in Ulaanbaatar with Deep Learning Models
Authors: Suriya
Abstract:
Rapid socio-economic development and urbanization have led to an increasingly serious air pollution problem in Ulaanbaatar (UB), the capital of Mongolia. PM₂.₅ pollution has become the most pressing aspect of UB air pollution. Therefore, monitoring and predicting PM₂.₅ concentration in UB is of great significance for the health of the local people and environmental management. As of yet, very few studies have used models to predict PM₂.₅ concentrations in UB. Using data from 0:00 on June 1, 2018, to 23:00 on April 30, 2020, we proposed two deep learning models based on Bayesian-optimized LSTM (Bayes-LSTM) and CNN-LSTM. We utilized hourly observed data, including Himawari8 (H8) aerosol optical depth (AOD), meteorology, and PM₂.₅ concentration, as input for the prediction of PM₂.₅ concentrations. The correlation strengths between meteorology, AOD, and PM₂.₅ were analyzed using the gray correlation analysis method; the comparison of the performance improvement of the model by using the AOD input value was tested, and the performance of these models was evaluated using mean absolute error (MAE) and root mean square error (RMSE). The prediction accuracies of Bayes-LSTM and CNN-LSTM deep learning models were both improved when AOD was included as an input parameter. Improvement of the prediction accuracy of the CNN-LSTM model was particularly enhanced in the non-heating season; in the heating season, the prediction accuracy of the Bayes-LSTM model slightly improved, while the prediction accuracy of the CNN-LSTM model slightly decreased. We propose two novel deep learning models for PM₂.₅ concentration prediction in UB, Bayes-LSTM, and CNN-LSTM deep learning models. Pioneering the use of AOD data from H8 and demonstrating the inclusion of AOD input data improves the performance of our two proposed deep learning models.Keywords: deep learning, AOD, PM2.5, prediction, Ulaanbaatar
Procedia PDF Downloads 4620609 Prediction of Coronary Artery Stenosis Severity Based on Machine Learning Algorithms
Authors: Yu-Jia Jian, Emily Chia-Yu Su, Hui-Ling Hsu, Jian-Jhih Chen
Abstract:
Coronary artery is the major supplier of myocardial blood flow. When fat and cholesterol are deposit in the coronary arterial wall, narrowing and stenosis of the artery occurs, which may lead to myocardial ischemia and eventually infarction. According to the World Health Organization (WHO), estimated 740 million people have died of coronary heart disease in 2015. According to Statistics from Ministry of Health and Welfare in Taiwan, heart disease (except for hypertensive diseases) ranked the second among the top 10 causes of death from 2013 to 2016, and it still shows a growing trend. According to American Heart Association (AHA), the risk factors for coronary heart disease including: age (> 65 years), sex (men to women with 2:1 ratio), obesity, diabetes, hypertension, hyperlipidemia, smoking, family history, lack of exercise and more. We have collected a dataset of 421 patients from a hospital located in northern Taiwan who received coronary computed tomography (CT) angiography. There were 300 males (71.26%) and 121 females (28.74%), with age ranging from 24 to 92 years, and a mean age of 56.3 years. Prior to coronary CT angiography, basic data of the patients, including age, gender, obesity index (BMI), diastolic blood pressure, systolic blood pressure, diabetes, hypertension, hyperlipidemia, smoking, family history of coronary heart disease and exercise habits, were collected and used as input variables. The output variable of the prediction module is the degree of coronary artery stenosis. The output variable of the prediction module is the narrow constriction of the coronary artery. In this study, the dataset was randomly divided into 80% as training set and 20% as test set. Four machine learning algorithms, including logistic regression, stepwise regression, neural network and decision tree, were incorporated to generate prediction results. We used area under curve (AUC) / accuracy (Acc.) to compare the four models, the best model is neural network, followed by stepwise logistic regression, decision tree, and logistic regression, with 0.68 / 79 %, 0.68 / 74%, 0.65 / 78%, and 0.65 / 74%, respectively. Sensitivity of neural network was 27.3%, specificity was 90.8%, stepwise Logistic regression sensitivity was 18.2%, specificity was 92.3%, decision tree sensitivity was 13.6%, specificity was 100%, logistic regression sensitivity was 27.3%, specificity 89.2%. From the result of this study, we hope to improve the accuracy by improving the module parameters or other methods in the future and we hope to solve the problem of low sensitivity by adjusting the imbalanced proportion of positive and negative data.Keywords: decision support, computed tomography, coronary artery, machine learning
Procedia PDF Downloads 22820608 Application of Data Mining Techniques for Tourism Knowledge Discovery
Authors: Teklu Urgessa, Wookjae Maeng, Joong Seek Lee
Abstract:
Application of five implementations of three data mining classification techniques was experimented for extracting important insights from tourism data. The aim was to find out the best performing algorithm among the compared ones for tourism knowledge discovery. Knowledge discovery process from data was used as a process model. 10-fold cross validation method is used for testing purpose. Various data preprocessing activities were performed to get the final dataset for model building. Classification models of the selected algorithms were built with different scenarios on the preprocessed dataset. The outperformed algorithm tourism dataset was Random Forest (76%) before applying information gain based attribute selection and J48 (C4.5) (75%) after selection of top relevant attributes to the class (target) attribute. In terms of time for model building, attribute selection improves the efficiency of all algorithms. Artificial Neural Network (multilayer perceptron) showed the highest improvement (90%). The rules extracted from the decision tree model are presented, which showed intricate, non-trivial knowledge/insight that would otherwise not be discovered by simple statistical analysis with mediocre accuracy of the machine using classification algorithms.Keywords: classification algorithms, data mining, knowledge discovery, tourism
Procedia PDF Downloads 29420607 Design of a Small and Medium Enterprise Growth Prediction Model Based on Web Mining
Authors: Yiea Funk Te, Daniel Mueller, Irena Pletikosa Cvijikj
Abstract:
Small and medium enterprises (SMEs) play an important role in the economy of many countries. When the overall world economy is considered, SMEs represent 95% of all businesses in the world, accounting for 66% of the total employment. Existing studies show that the current business environment is characterized as highly turbulent and strongly influenced by modern information and communication technologies, thus forcing SMEs to experience more severe challenges in maintaining their existence and expanding their business. To support SMEs at improving their competitiveness, researchers recently turned their focus on applying data mining techniques to build risk and growth prediction models. However, data used to assess risk and growth indicators is primarily obtained via questionnaires, which is very laborious and time-consuming, or is provided by financial institutes, thus highly sensitive to privacy issues. Recently, web mining (WM) has emerged as a new approach towards obtaining valuable insights in the business world. WM enables automatic and large scale collection and analysis of potentially valuable data from various online platforms, including companies’ websites. While WM methods have been frequently studied to anticipate growth of sales volume for e-commerce platforms, their application for assessment of SME risk and growth indicators is still scarce. Considering that a vast proportion of SMEs own a website, WM bears a great potential in revealing valuable information hidden in SME websites, which can further be used to understand SME risk and growth indicators, as well as to enhance current SME risk and growth prediction models. This study aims at developing an automated system to collect business-relevant data from the Web and predict future growth trends of SMEs by means of WM and data mining techniques. The envisioned system should serve as an 'early recognition system' for future growth opportunities. In an initial step, we examine how structured and semi-structured Web data in governmental or SME websites can be used to explain the success of SMEs. WM methods are applied to extract Web data in a form of additional input features for the growth prediction model. The data on SMEs provided by a large Swiss insurance company is used as ground truth data (i.e. growth-labeled data) to train the growth prediction model. Different machine learning classification algorithms such as the Support Vector Machine, Random Forest and Artificial Neural Network are applied and compared, with the goal to optimize the prediction performance. The results are compared to those from previous studies, in order to assess the contribution of growth indicators retrieved from the Web for increasing the predictive power of the model.Keywords: data mining, SME growth, success factors, web mining
Procedia PDF Downloads 26620606 Development of an EEG-Based Real-Time Emotion Recognition System on Edge AI
Authors: James Rigor Camacho, Wansu Lim
Abstract:
Over the last few years, the development of new wearable and processing technologies has accelerated in order to harness physiological data such as electroencephalograms (EEGs) for EEG-based applications. EEG has been demonstrated to be a source of emotion recognition signals with the highest classification accuracy among physiological signals. However, when emotion recognition systems are used for real-time classification, the training unit is frequently left to run offline or in the cloud rather than working locally on the edge. That strategy has hampered research, and the full potential of using an edge AI device has yet to be realized. Edge AI devices are computers with high performance that can process complex algorithms. It is capable of collecting, processing, and storing data on its own. It can also analyze and apply complicated algorithms like localization, detection, and recognition on a real-time application, making it a powerful embedded device. The NVIDIA Jetson series, specifically the Jetson Nano device, was used in the implementation. The cEEGrid, which is integrated to the open-source brain computer-interface platform (OpenBCI), is used to collect EEG signals. An EEG-based real-time emotion recognition system on Edge AI is proposed in this paper. To perform graphical spectrogram categorization of EEG signals and to predict emotional states based on input data properties, machine learning-based classifiers were used. Until the emotional state was identified, the EEG signals were analyzed using the K-Nearest Neighbor (KNN) technique, which is a supervised learning system. In EEG signal processing, after each EEG signal has been received in real-time and translated from time to frequency domain, the Fast Fourier Transform (FFT) technique is utilized to observe the frequency bands in each EEG signal. To appropriately show the variance of each EEG frequency band, power density, standard deviation, and mean are calculated and employed. The next stage is to identify the features that have been chosen to predict emotion in EEG data using the K-Nearest Neighbors (KNN) technique. Arousal and valence datasets are used to train the parameters defined by the KNN technique.Because classification and recognition of specific classes, as well as emotion prediction, are conducted both online and locally on the edge, the KNN technique increased the performance of the emotion recognition system on the NVIDIA Jetson Nano. Finally, this implementation aims to bridge the research gap on cost-effective and efficient real-time emotion recognition using a resource constrained hardware device, like the NVIDIA Jetson Nano. On the cutting edge of AI, EEG-based emotion identification can be employed in applications that can rapidly expand the research and implementation industry's use.Keywords: edge AI device, EEG, emotion recognition system, supervised learning algorithm, sensors
Procedia PDF Downloads 10420605 Data Mining Algorithms Analysis: Case Study of Price Predictions of Lands
Authors: Julio Albuja, David Zaldumbide
Abstract:
Data analysis is an important step before taking a decision about money. The aim of this work is to analyze the factors that influence the final price of the houses through data mining algorithms. To our best knowledge, previous work was researched just to compare results. Furthermore, before using the data of the data set, the Z-Transformation were used to standardize the data in the same range. Hence, the data was classified into two groups to visualize them in a readability format. A decision tree was built, and graphical data is displayed where clearly is easy to see the results and the factors' influence in these graphics. The definitions of these methods are described, as well as the descriptions of the results. Finally, conclusions and recommendations are presented related to the released results that our research showed making it easier to apply these algorithms using a customized data set.Keywords: algorithms, data, decision tree, transformation
Procedia PDF Downloads 37220604 Wind Speed Prediction Using Passive Aggregation Artificial Intelligence Model
Authors: Tarek Aboueldahab, Amin Mohamed Nassar
Abstract:
Wind energy is a fluctuating energy source unlike conventional power plants, thus, it is necessary to accurately predict short term wind speed to integrate wind energy in the electricity supply structure. To do so, we present a hybrid artificial intelligence model of short term wind speed prediction based on passive aggregation of the particle swarm optimization and neural networks. As a result, improvement of the prediction accuracy is obviously obtained compared to the standard artificial intelligence method.Keywords: artificial intelligence, neural networks, particle swarm optimization, passive aggregation, wind speed prediction
Procedia PDF Downloads 44920603 Springback Prediction for Sheet Metal Cold Stamping Using Convolutional Neural Networks
Abstract:
Cold stamping has been widely applied in the automotive industry for the mass production of a great range of automotive panels. Predicting the springback to ensure the dimensional accuracy of the cold-stamped components is a critical step. The main approaches for the prediction and compensation of springback in cold stamping include running Finite Element (FE) simulations and conducting experiments, which require forming process expertise and can be time-consuming and expensive for the design of cold stamping tools. Machine learning technologies have been proven and successfully applied in learning complex system behaviours using presentative samples. These technologies exhibit the promising potential to be used as supporting design tools for metal forming technologies. This study, for the first time, presents a novel application of a Convolutional Neural Network (CNN) based surrogate model to predict the springback fields for variable U-shape cold bending geometries. A dataset is created based on the U-shape cold bending geometries and the corresponding FE simulations results. The dataset is then applied to train the CNN surrogate model. The result shows that the surrogate model can achieve near indistinguishable full-field predictions in real-time when compared with the FE simulation results. The application of CNN in efficient springback prediction can be adopted in industrial settings to aid both conceptual and final component designs for designers without having manufacturing knowledge.Keywords: springback, cold stamping, convolutional neural networks, machine learning
Procedia PDF Downloads 14820602 Gradient Boosted Trees on Spark Platform for Supervised Learning in Health Care Big Data
Authors: Gayathri Nagarajan, L. D. Dhinesh Babu
Abstract:
Health care is one of the prominent industries that generate voluminous data thereby finding the need of machine learning techniques with big data solutions for efficient processing and prediction. Missing data, incomplete data, real time streaming data, sensitive data, privacy, heterogeneity are few of the common challenges to be addressed for efficient processing and mining of health care data. In comparison with other applications, accuracy and fast processing are of higher importance for health care applications as they are related to the human life directly. Though there are many machine learning techniques and big data solutions used for efficient processing and prediction in health care data, different techniques and different frameworks are proved to be effective for different applications largely depending on the characteristics of the datasets. In this paper, we present a framework that uses ensemble machine learning technique gradient boosted trees for data classification in health care big data. The framework is built on Spark platform which is fast in comparison with other traditional frameworks. Unlike other works that focus on a single technique, our work presents a comparison of six different machine learning techniques along with gradient boosted trees on datasets of different characteristics. Five benchmark health care datasets are considered for experimentation, and the results of different machine learning techniques are discussed in comparison with gradient boosted trees. The metric chosen for comparison is misclassification error rate and the run time of the algorithms. The goal of this paper is to i) Compare the performance of gradient boosted trees with other machine learning techniques in Spark platform specifically for health care big data and ii) Discuss the results from the experiments conducted on datasets of different characteristics thereby drawing inference and conclusion. The experimental results show that the accuracy is largely dependent on the characteristics of the datasets for other machine learning techniques whereas gradient boosting trees yields reasonably stable results in terms of accuracy without largely depending on the dataset characteristics.Keywords: big data analytics, ensemble machine learning, gradient boosted trees, Spark platform
Procedia PDF Downloads 23820601 SNR Classification Using Multiple CNNs
Authors: Thinh Ngo, Paul Rad, Brian Kelley
Abstract:
Noise estimation is essential in today wireless systems for power control, adaptive modulation, interference suppression and quality of service. Deep learning (DL) has already been applied in the physical layer for modulation and signal classifications. Unacceptably low accuracy of less than 50% is found to undermine traditional application of DL classification for SNR prediction. In this paper, we use divide-and-conquer algorithm and classifier fusion method to simplify SNR classification and therefore enhances DL learning and prediction. Specifically, multiple CNNs are used for classification rather than a single CNN. Each CNN performs a binary classification of a single SNR with two labels: less than, greater than or equal. Together, multiple CNNs are combined to effectively classify over a range of SNR values from −20 ≤ SNR ≤ 32 dB.We use pre-trained CNNs to predict SNR over a wide range of joint channel parameters including multiple Doppler shifts (0, 60, 120 Hz), power-delay profiles, and signal-modulation types (QPSK,16QAM,64-QAM). The approach achieves individual SNR prediction accuracy of 92%, composite accuracy of 70% and prediction convergence one order of magnitude faster than that of traditional estimation.Keywords: classification, CNN, deep learning, prediction, SNR
Procedia PDF Downloads 13320600 COVID-19 Analysis with Deep Learning Model Using Chest X-Rays Images
Authors: Uma Maheshwari V., Rajanikanth Aluvalu, Kumar Gautam
Abstract:
The COVID-19 disease is a highly contagious viral infection with major worldwide health implications. The global economy suffers as a result of COVID. The spread of this pandemic disease can be slowed if positive patients are found early. COVID-19 disease prediction is beneficial for identifying patients' health problems that are at risk for COVID. Deep learning and machine learning algorithms for COVID prediction using X-rays have the potential to be extremely useful in solving the scarcity of doctors and clinicians in remote places. In this paper, a convolutional neural network (CNN) with deep layers is presented for recognizing COVID-19 patients using real-world datasets. We gathered around 6000 X-ray scan images from various sources and split them into two categories: normal and COVID-impacted. Our model examines chest X-ray images to recognize such patients. Because X-rays are commonly available and affordable, our findings show that X-ray analysis is effective in COVID diagnosis. The predictions performed well, with an average accuracy of 99% on training photographs and 88% on X-ray test images.Keywords: deep CNN, COVID–19 analysis, feature extraction, feature map, accuracy
Procedia PDF Downloads 7920599 Evaluation of Spatial Distribution Prediction for Site-Scale Soil Contaminants Based on Partition Interpolation
Authors: Pengwei Qiao, Sucai Yang, Wenxia Wei
Abstract:
Soil pollution has become an important issue in China. Accurate spatial distribution prediction of pollutants with interpolation methods is the basis for soil remediation in the site. However, a relatively strong variability of pollutants would decrease the prediction accuracy. Theoretically, partition interpolation can result in accurate prediction results. In order to verify the applicability of partition interpolation for a site, benzo (b) fluoranthene (BbF) in four soil layers was adopted as the research object in this paper. IDW (inverse distance weighting)-, RBF (radial basis function)-and OK (ordinary kriging)-based partition interpolation accuracies were evaluated, and their influential factors were analyzed; then, the uncertainty and applicability of partition interpolation were determined. Three conclusions were drawn. (1) The prediction error of partitioned interpolation decreased by 70% compared to unpartitioned interpolation. (2) Partition interpolation reduced the impact of high CV (coefficient of variation) and high concentration value on the prediction accuracy. (3) The prediction accuracy of IDW-based partition interpolation was higher than that of RBF- and OK-based partition interpolation, and it was suitable for the identification of highly polluted areas at a contaminated site. These results provide a useful method to obtain relatively accurate spatial distribution information of pollutants and to identify highly polluted areas, which is important for soil pollution remediation in the site.Keywords: accuracy, applicability, partition interpolation, site, soil pollution, uncertainty
Procedia PDF Downloads 14420598 Prediction of Damage to Cutting Tools in an Earth Pressure Balance Tunnel Boring Machine EPB TBM: A Case Study L3 Guadalajara Metro Line (Mexico)
Authors: Silvia Arrate, Waldo Salud, Eloy París
Abstract:
The wear of cutting tools is one of the most decisive elements when planning tunneling works, programming the maintenance stops and saving the optimum stock of spare parts during the evolution of the excavation. Being able to predict the behavior of cutting tools can give a very competitive advantage in terms of costs and excavation performance, optimized to the needs of the TBM itself. The incredible evolution of data science in recent years gives the option to implement it at the time of analyzing the key and most critical parameters related to machinery with the purpose of knowing how the cutting head is performing in front of the excavated ground. Taking this as a case study, Metro Line 3 of Guadalajara in Mexico will develop the feasibility of using Specific Energy versus data science applied over parameters of Torque, Penetration, and Contact Force, among others, to predict the behavior and status of cutting tools. The results obtained through both techniques are analyzed and verified in the function of the wear and the field situations observed in the excavation in order to determine its effectiveness regarding its predictive capacity. In conclusion, the possibilities and improvements offered by the application of digital tools and the programming of calculation algorithms for the analysis of wear of cutting head elements compared to purely empirical methods allow early detection of possible damage to cutting tools, which is reflected in optimization of excavation performance and a significant improvement in costs and deadlines.Keywords: cutting tools, data science, prediction, TBM, wear
Procedia PDF Downloads 4720597 Uplink Throughput Prediction in Cellular Mobile Networks
Authors: Engin Eyceyurt, Josko Zec
Abstract:
The current and future cellular mobile communication networks generate enormous amounts of data. Networks have become extremely complex with extensive space of parameters, features and counters. These networks are unmanageable with legacy methods and an enhanced design and optimization approach is necessary that is increasingly reliant on machine learning. This paper proposes that machine learning as a viable approach for uplink throughput prediction. LTE radio metric, such as Reference Signal Received Power (RSRP), Reference Signal Received Quality (RSRQ), and Signal to Noise Ratio (SNR) are used to train models to estimate expected uplink throughput. The prediction accuracy with high determination coefficient of 91.2% is obtained from measurements collected with a simple smartphone application.Keywords: drive test, LTE, machine learning, uplink throughput prediction
Procedia PDF Downloads 15520596 Evaluation of Features Extraction Algorithms for a Real-Time Isolated Word Recognition System
Authors: Tomyslav Sledevič, Artūras Serackis, Gintautas Tamulevičius, Dalius Navakauskas
Abstract:
This paper presents a comparative evaluation of features extraction algorithm for a real-time isolated word recognition system based on FPGA. The Mel-frequency cepstral, linear frequency cepstral, linear predictive and their cepstral coefficients were implemented in hardware/software design. The proposed system was investigated in the speaker-dependent mode for 100 different Lithuanian words. The robustness of features extraction algorithms was tested recognizing the speech records at different signals to noise rates. The experiments on clean records show highest accuracy for Mel-frequency cepstral and linear frequency cepstral coefficients. For records with 15 dB signal to noise rate the linear predictive cepstral coefficients give best result. The hard and soft part of the system is clocked on 50 MHz and 100 MHz accordingly. For the classification purpose, the pipelined dynamic time warping core was implemented. The proposed word recognition system satisfies the real-time requirements and is suitable for applications in embedded systems.Keywords: isolated word recognition, features extraction, MFCC, LFCC, LPCC, LPC, FPGA, DTW
Procedia PDF Downloads 49420595 External Validation of Risk Prediction Score for Candidemia in Critically Ill Patients: A Retrospective Observational Study
Authors: Nurul Mazni Abdullah, Saw Kian Cheah, Raha Abdul Rahman, Qurratu 'Aini Musthafa
Abstract:
Purpose: Candidemia was associated with high mortality in the critically ill patients. Early candidemia prediction is imperative for preemptive antifungal treatment. This study aimed to externally validate the candidemia risk prediction scores by Jameran et al. (2021) by identifying risk factors of acute kidney injury, renal replacement therapy, parenteral nutrition, and multifocal candida colonization. Methods: This single-center, retrospective observational study included all critically ill patients admitted to the intensive care unit (ICU) in a tertiary referral center from January 2018 to December 2023. The study evaluated the candidemia risk prediction score performance by analysing the occurrence of candidemia within the study period. Patients’ demographic characteristics, comorbidities, SOFA scores, and ICU outcomes were analyzed. Patients who were diagnosed with candidemia prior to ICU admission were excluded. Results: A total of 500 patients were analyzed with 2 dropouts due to incomplete data. Validation analysis showed that the candidemia risk prediction score has a sensitivity of 75.00% (95% CI: 59.66-86.81), specificity of 65.35% (95% CI: 60.78-69.72), positive predictive value of 17.28, and negative predictive value of 96.44. The incidence of candidemia was 8.86%, with no significant differences in demographics or comorbidities except for higher SOFA scoring in the candidemia group. The candidemia group showed significantly longer ICU, hospital LOS, and higher ICU in-hospital mortality. Conclusion: This study concluded the candidemia risk prediction score by Jameran et al. (2021) had good sensitivity and a high negative prediction value. Thus, the risk prediction score was validated for candidemia prediction in critically ill patients.Keywords: Candidemia, intensive care, acute kidney injury, clinical prediction rule, incidence
Procedia PDF Downloads 520594 Red-Tide Detection and Prediction Using MODIS Data in the Arabian Gulf of Qatar
Authors: Yasir E. Mohieldeen
Abstract:
Qatar is one of the most water scarce countries in the World. In 2014, the average per capita rainfall was less than 29 m3/y/ca, while the global average is 6,000 m3/y/ca. However, the per capita water consumption in Qatar is among the highest in the World: more than 500 liters per person per day, whereas the global average is 160 liters per person per day. Since the early 2000s, Qatar has been relying heavily on desalinated water from the Arabian Gulf as the main source of fresh water. In 2009, about 99.9% of the total potable water produced was desalinated. Reliance on desalinated water makes Qatar very vulnerable to water related natural disasters, such as the red-tide phenomenon. Qatar’s strategic water reserve lasts for only 7 days. In case of red-tide outbreak, the country would not be able to desalinate water for days, let alone the months that this disaster would bring about (as it clogs the desalination equipment). The 2008-09 red-tide outbreak, for instance, lasted for more than eight months and forced the closure of desalination plants in the region for weeks. This study aims at identifying favorite conditions for red-tide outbreaks, using satellite data along with in-situ measurements. This identification would allow the prediction of these outbreaks and their hotspots. Prediction and monitoring of outbreaks are crucial to water security in the country, as different measures could be put in place in advance to prevent an outbreak and mitigate its impact if it happened. Red-tide outbreaks are detected using different algorithms for chlorophyll concentration in the Gulf waters. Vegetation indices, such as Normalized Difference Vegetation Index (NDVI) and Enhanced Vegetation Index (EVI) were used along with Surface Algae Bloom Index (SABI) to detect known outbreaks. MODIS (or Moderate Resolution Imaging Spectroradiometer) bands are used to calculate these indices. A red-tide outbreaks atlas in the Arabian Gulf is being produced. Prediction of red-tide outbreaks ahead of their occurrences would give critical information on possible water-shortage in the country. Detecting known outbreaks in the past few decades and related parameters (e.g. water salinity, water surface temperature, nutrition, sandstorms, … etc) enables the identification of favorite conditions of red-tide outbreak that are key to the prediction of these outbreaks.Keywords: Arabian Gulf, MODIS, red-tide detection, strategic water reserve, water desalination
Procedia PDF Downloads 10620593 Localization of Geospatial Events and Hoax Prediction in the UFO Database
Authors: Harish Krishnamurthy, Anna Lafontant, Ren Yi
Abstract:
Unidentified Flying Objects (UFOs) have been an interesting topic for most enthusiasts and hence people all over the United States report such findings online at the National UFO Report Center (NUFORC). Some of these reports are a hoax and among those that seem legitimate, our task is not to establish that these events confirm that they indeed are events related to flying objects from aliens in outer space. Rather, we intend to identify if the report was a hoax as was identified by the UFO database team with their existing curation criterion. However, the database provides a wealth of information that can be exploited to provide various analyses and insights such as social reporting, identifying real-time spatial events and much more. We perform analysis to localize these time-series geospatial events and correlate with known real-time events. This paper does not confirm any legitimacy of alien activity, but rather attempts to gather information from likely legitimate reports of UFOs by studying the online reports. These events happen in geospatial clusters and also are time-based. We look at cluster density and data visualization to search the space of various cluster realizations to decide best probable clusters that provide us information about the proximity of such activity. A random forest classifier is also presented that is used to identify true events and hoax events, using the best possible features available such as region, week, time-period and duration. Lastly, we show the performance of the scheme on various days and correlate with real-time events where one of the UFO reports strongly correlates to a missile test conducted in the United States.Keywords: time-series clustering, feature extraction, hoax prediction, geospatial events
Procedia PDF Downloads 37620592 Profit-Based Artificial Neural Network (ANN) Trained by Migrating Birds Optimization: A Case Study in Credit Card Fraud Detection
Authors: Ashkan Zakaryazad, Ekrem Duman
Abstract:
A typical classification technique ranks the instances in a data set according to the likelihood of belonging to one (positive) class. A credit card (CC) fraud detection model ranks the transactions in terms of probability of being fraud. In fact, this approach is often criticized, because firms do not care about fraud probability but about the profitability or costliness of detecting a fraudulent transaction. The key contribution in this study is to focus on the profit maximization in the model building step. The artificial neural network proposed in this study works based on profit maximization instead of minimizing the error of prediction. Moreover, some studies have shown that the back propagation algorithm, similar to other gradient–based algorithms, usually gets trapped in local optima and swarm-based algorithms are more successful in this respect. In this study, we train our profit maximization ANN using the Migrating Birds optimization (MBO) which is introduced to literature recently.Keywords: neural network, profit-based neural network, sum of squared errors (SSE), MBO, gradient descent
Procedia PDF Downloads 47320591 Study on the Model Predicting Post-Construction Settlement of Soft Ground
Authors: Pingshan Chen, Zhiliang Dong
Abstract:
In order to estimate the post-construction settlement more objectively, the power-polynomial model is proposed, which can reflect the trend of settlement development based on the observed settlement data. It was demonstrated by an actual case history of an embankment, and during the prediction. Compared with the other three prediction models, the power-polynomial model can estimate the post-construction settlement more accurately with more simple calculation.Keywords: prediction, model, post-construction settlement, soft ground
Procedia PDF Downloads 42520590 A Speeded up Robust Scale-Invariant Feature Transform Currency Recognition Algorithm
Authors: Daliyah S. Aljutaili, Redna A. Almutlaq, Suha A. Alharbi, Dina M. Ibrahim
Abstract:
All currencies around the world look very different from each other. For instance, the size, color, and pattern of the paper are different. With the development of modern banking services, automatic methods for paper currency recognition become important in many applications like vending machines. One of the currency recognition architecture’s phases is Feature detection and description. There are many algorithms that are used for this phase, but they still have some disadvantages. This paper proposes a feature detection algorithm, which merges the advantages given in the current SIFT and SURF algorithms, which we call, Speeded up Robust Scale-Invariant Feature Transform (SR-SIFT) algorithm. Our proposed SR-SIFT algorithm overcomes the problems of both the SIFT and SURF algorithms. The proposed algorithm aims to speed up the SIFT feature detection algorithm and keep it robust. Simulation results demonstrate that the proposed SR-SIFT algorithm decreases the average response time, especially in small and minimum number of best key points, increases the distribution of the number of best key points on the surface of the currency. Furthermore, the proposed algorithm increases the accuracy of the true best point distribution inside the currency edge than the other two algorithms.Keywords: currency recognition, feature detection and description, SIFT algorithm, SURF algorithm, speeded up and robust features
Procedia PDF Downloads 23420589 An Auxiliary Technique for Coronary Heart Disease Prediction by Analyzing Electrocardiogram Based on ResNet and Bi-Long Short-Term Memory
Authors: Yang Zhang, Jian He
Abstract:
Heart disease is one of the leading causes of death in the world, and coronary heart disease (CHD) is one of the major heart diseases. Electrocardiogram (ECG) is widely used in the detection of heart diseases, but the traditional manual method for CHD prediction by analyzing ECG requires lots of professional knowledge for doctors. This paper introduces sliding window and continuous wavelet transform (CWT) to transform ECG signals into images, and then ResNet and Bi-LSTM are introduced to build the ECG feature extraction network (namely ECGNet). At last, an auxiliary system for coronary heart disease prediction was developed based on modified ResNet18 and Bi-LSTM, and the public ECG dataset of CHD from MIMIC-3 was used to train and test the system. The experimental results show that the accuracy of the method is 83%, and the F1-score is 83%. Compared with the available methods for CHD prediction based on ECG, such as kNN, decision tree, VGGNet, etc., this method not only improves the prediction accuracy but also could avoid the degradation phenomenon of the deep learning network.Keywords: Bi-LSTM, CHD, ECG, ResNet, sliding window
Procedia PDF Downloads 88