Search results for: squared prediction risk

Authors: Mohammad Ghavami, Reza S. Dilmaghani

Abstract:

This paper presents an adaptive framework for modelling financial markets using equity risk premiums, risk free rates and volatilities. The recorded economic factors are initially used to train four adaptive filters for a certain limited period of time in the past. Once the systems are trained, the adjusted coefficients are used for modelling and prediction of an important financial market index. Two different approaches based on least mean squares (LMS) and recursive least squares (RLS) algorithms are investigated. Performance analysis of each method in terms of the mean squared error (MSE) is presented and the results are discussed. Computer simulations carried out using recorded data show MSEs of 4% and 3.4% for the next month prediction using LMS and RLS adaptive algorithms, respectively. In terms of twelve months prediction, RLS method shows a better tendency estimation compared to the LMS algorithm.

Keywords: adaptive methods, LSE, MSE, prediction of financial Markets

Procedia PDF Downloads 308

Authors: Alan Wan

Abstract:

In recent years, the body of literature on frequentist model averaging in statistics has grown significantly. Most of this work focuses on models with different mean structures but leaves out the variance consideration. In this paper, we consider a regression model with multiplicative heteroscedasticity and develop a model averaging method that combines maximum likelihood estimators of unknown parameters in both the mean and variance functions of the model. Our weight choice criterion is based on a minimisation of a plug-in estimator of the model average estimator's squared prediction risk. We prove that the new estimator possesses an asymptotic optimality property. Our investigation of finite-sample performance by simulations demonstrates that the new estimator frequently exhibits very favourable properties compared to some existing heteroscedasticity-robust model average estimators. The model averaging method hedges against the selection of very bad models and serves as a remedy to variance function misspecification, which often discourages practitioners from modeling heteroscedasticity altogether. The proposed model average estimator is applied to the analysis of two real data sets.

Keywords: heteroscedasticity-robust, model averaging, multiplicative heteroscedasticity, plug-in, squared prediction risk

Procedia PDF Downloads 344

Authors: Jeena R. S., Sukesh Kumar A.

Abstract:

Stroke is one of the major reasons of adult disability and morbidity in many of the developing countries like India. Early diagnosis of stroke is essential for timely prevention and cure. Various conventional statistical methods and computational intelligent models have been developed for predicting the risk and outcome of stroke. This research work focuses on a multilevel approach for predicting the occurrence of stroke based on various risk factors and invasive techniques like retinal imaging. This risk prediction model can aid in clinical decision making and help patients to have an improved and reliable risk prediction.

Keywords: prediction, retinal imaging, risk factors, stroke

Procedia PDF Downloads 277

Authors: James Purnama, Riri Fitri Sari

Abstract:

We investigate the machine learning algorithm selection problem in the term of a depth image based eye gaze estimation, with respect to its essential difficulty in reducing the number of required training samples and duration time of training. Statistics based prediction accuracy are increasingly used to assess and evaluate prediction or estimation in gaze estimation. This article evaluates Root Mean Squared Error (RMSE) and R-Squared statistical analysis to assess machine learning methods on depth camera data for gaze estimation. There are 4 machines learning methods have been evaluated: Random Forest Regression, Regression Tree, Support Vector Machine (SVM), and Linear Regression. The experiment results show that the Random Forest Regression has the lowest RMSE and the highest R-Squared, which means that it is the best among other methods.

Keywords: gaze estimation, gaze tracking, eye tracking, kinect, regression model, orange python

Procedia PDF Downloads 514

Authors: Shervin Alaei, Reza Moradi

Abstract:

Trading in financial markets is subject to risks due to their high volatilities. Here, using an LSTM neural network, and by doing some risk-based feature engineering tasks, we developed a method that can accurately predict trends of the Tehran stock exchange market index from a few days ago. Our test results have shown that the proposed method with an average prediction accuracy of more than 94% is superior to the other common machine learning algorithms. To the best of our knowledge, this is the first work incorporating deep learning and risk factors to accurately predict market trends.

Keywords: deep learning, LSTM, trend prediction, risk management, artificial neural networks

Procedia PDF Downloads 128

Authors: Nor Zila Abd Hamid, Mohd Salmi M. Noorani

Abstract:

This study is focused on the development of prediction models of the Ozone concentration time series. Prediction model is built based on chaotic approach. Firstly, the chaotic nature of the time series is detected by means of phase space plot and the Cao method. Then, the prediction model is built and the local linear approximation method is used for the forecasting purposes. Traditional prediction of autoregressive linear model is also built. Moreover, an improvement in local linear approximation method is also performed. Prediction models are applied to the hourly ozone time series observed at the benchmark station in Malaysia. Comparison of all models through the calculation of mean absolute error, root mean squared error and correlation coefficient shows that the one with improved prediction method is the best. Thus, chaotic approach is a good approach to be used to develop a prediction model for the Ozone concentration time series.

Keywords: chaotic approach, phase space, Cao method, local linear approximation method

Procedia PDF Downloads 306

Authors: Xiaodong Li, Peng Gao, Chao-Jung Huang, Shiying Hao, Xuefeng B. Ling, Yongxia Han, Yaqi Zhang, Le Zheng, Chengyin Ye, Modi Liu, Minjie Xia, Changlin Fu, Bo Jin, Karl G. Sylvester, Eric Widen

Abstract:

Predicting the risk of Pancreatic Adenocarcinoma (PA) in advance can benefit the quality of care and potentially reduce population mortality and morbidity. The aim of this study was to develop and prospectively validate a risk prediction model to identify patients at risk of new incident PA as early as 3 months before the onset of PA in a statewide, general population in Maine. The PA prediction model was developed using Deep Neural Networks, a deep learning algorithm, with a 2-year electronic-health-record (EHR) cohort. Prospective results showed that our model identified 54.35% of all inpatient episodes of PA, and 91.20% of all PA that required subsequent chemoradiotherapy, with a lead-time of up to 3 months and a true alert of 67.62%. The risk assessment tool has attained an improved discriminative ability. It can be immediately deployed to the health system to provide automatic early warnings to adults at risk of PA. It has potential to identify personalized risk factors to facilitate customized PA interventions.

Keywords: cancer prediction, deep learning, electronic health records, pancreatic adenocarcinoma

Procedia PDF Downloads 129

Authors: Carl van Walraven, Meltem Tuna

Abstract:

Background: Network meta-analysis (NMA) quantifies the relative efficacy of 3 or more interventions from studies containing a subgroup of interventions. This study applied the analytical approach of NMA to quantify the relative accuracy of prediction models with distinct inclusion criteria that are evaluated on a common population (‘concurrent external validation’). Methods: We simulated binary events in 5000 patients using a known risk function. We biased the risk function and modified its precision by pre-specified amounts to create 15 prediction models with varying accuracy and distinct patient applicability. Prediction model accuracy was measured using the Scaled Brier Score (SBS). Overall prediction model accuracy was measured using fixed-effects methods that accounted for model applicability patterns. Prediction model accuracy was summarized as the Network Relative Model Accuracy (NeRMA) Score which ranges from -∞ through 0 (accuracy of random guessing) to 1 (accuracy of most accurate model in concurrent external validation). Results: The unbiased prediction model had the highest SBS. The NeRMA score correctly ranked all simulated prediction models by the extent of bias from the known risk function. A SAS macro and R-function was created to implement the NeRMA Score. Conclusions: The NeRMA Score makes it possible to quantify the accuracy of binomial prediction models having distinct inclusion criteria in a concurrent external validation.

Keywords: prediction model accuracy, scaled brier score, fixed effects methods, concurrent external validation

Procedia PDF Downloads 206

Authors: John Kabuba

Abstract:

The study investigated the implementation of the Neural Network (NN) techniques for prediction of the loading of Cu ions onto clinoptilolite. The experimental design using analysis of variance (ANOVA) was chosen for testing the adequacy of the Neural Network and for optimizing of the effective input parameters (pH, temperature and initial concentration). Feed forward, multi-layer perceptron (MLP) NN successfully tracked the non-linear behavior of the adsorption process versus the input parameters with mean squared error (MSE), correlation coefficient (R) and minimum squared error (MSRE) of 0.102, 0.998 and 0.004 respectively. The results showed that NN modeling techniques could effectively predict and simulate the highly complex system and non-linear process such as ion-exchange.

Keywords: clinoptilolite, loading, modeling, neural network

Procedia PDF Downloads 398

Authors: Soheila Sadeghi

Abstract:

Accurate cost prediction is essential for effective project management and decision-making in the construction industry. This study aims to develop a cost prediction model for construction projects using Machine Learning techniques and Particle Swarm Optimization (PSO). The research utilizes a comprehensive dataset containing project cost estimates, actual costs, resource details, and project performance metrics from a road reconstruction project. The methodology involves data preprocessing, feature selection, and the development of an Artificial Neural Network (ANN) model optimized using PSO. The study investigates the impact of various input features, including cost estimates, resource allocation, and project progress, on the accuracy of cost predictions. The performance of the optimized ANN model is evaluated using metrics such as Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), and R-squared. The results demonstrate the effectiveness of the proposed approach in predicting project costs, outperforming traditional benchmark models. The feature selection process identifies the most influential variables contributing to cost variations, providing valuable insights for project managers. However, this study has several limitations. Firstly, the model's performance may be influenced by the quality and quantity of the dataset used. A larger and more diverse dataset covering different types of construction projects would enhance the model's generalizability. Secondly, the study focuses on a specific optimization technique (PSO) and a single Machine Learning algorithm (ANN). Exploring other optimization methods and comparing the performance of various ML algorithms could provide a more comprehensive understanding of the cost prediction problem. Future research should focus on several key areas. Firstly, expanding the dataset to include a wider range of construction projects, such as residential buildings, commercial complexes, and infrastructure projects, would improve the model's applicability. Secondly, investigating the integration of additional data sources, such as economic indicators, weather data, and supplier information, could enhance the predictive power of the model. Thirdly, exploring the potential of ensemble learning techniques, which combine multiple ML algorithms, may further improve cost prediction accuracy. Additionally, developing user-friendly interfaces and tools to facilitate the adoption of the proposed cost prediction model in real-world construction projects would be a valuable contribution to the industry. The findings of this study have significant implications for construction project management, enabling proactive cost estimation, resource allocation, budget planning, and risk assessment, ultimately leading to improved project performance and cost control. This research contributes to the advancement of cost prediction techniques in the construction industry and highlights the potential of Machine Learning and PSO in addressing this critical challenge. However, further research is needed to address the limitations and explore the identified future research directions to fully realize the potential of ML-based cost prediction models in the construction domain.

Keywords: cost prediction, construction projects, machine learning, artificial neural networks, particle swarm optimization, project management, feature selection, road reconstruction

Procedia PDF Downloads 19

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 74

Authors: The Danh Phan

Abstract:

House price forecasting is a main topic in the real estate market research. Effective house price prediction models could not only allow home buyers and real estate agents to make better data-driven decisions but may also be beneficial for the property policymaking process. This study investigates the housing market by using machine learning techniques to analyze real historical house sale transactions in Australia. It seeks useful models which could be deployed as an application for house buyers and sellers. Data analytics show a high discrepancy between the house price in the most expensive suburbs and the most affordable suburbs in the city of Melbourne. In addition, experiments demonstrate that the combination of Stepwise and Support Vector Machine (SVM), based on the Mean Squared Error (MSE) measurement, consistently outperforms other models in terms of prediction accuracy.

Keywords: house price prediction, regression trees, neural network, support vector machine, stepwise

Procedia PDF Downloads 196

Authors: Peifang Hsieh

Abstract:

The prevention of child abuse has aroused serious concerns in Taiwan because of the disparity between the increasing amount of reported child abuse cases that doubled over the past decade and the scarcity of social workers. New Taipei city, with the most population in Taiwan and over 70% of its 4 million citizens are migrant families in which the needs of children can be easily neglected due to insufficient support from relatives and communities, sees urgency for a social support system, by preemptively identifying and outreaching high-risk families of child abuse, so as to offer timely assistance and preventive measure to safeguard the welfare of the children. Big data analysis is the inspiration. As it was clear that high-risk families of child abuse have certain characteristics in common, New Taipei city decides to consolidate detailed background information data from departments of social affairs, education, labor, and health (for example considering status of parents’ employment, health, and if they are imprisoned, fugitives or under substance abuse), to cross-reference for accurate and prompt identification of the high-risk families in need. 'The Service Center for High-Risk Families' (SCHF) was established to integrate data cross-departmentally. By utilizing the machine learning 'random forest method' to build a risk prediction model which can early detect families that may very likely to have child abuse occurrence, the SCHF marks high-risk families red, yellow, or green to indicate the urgency for intervention, so as to those families concerned can be provided timely services. The accuracy and recall rates of the above model were 80% and 65%. This prediction model can not only improve the child abuse prevention process by helping social workers differentiate the risk level of newly reported cases, which may further reduce their major workload significantly but also can be referenced for future policy-making.

Keywords: child abuse, high-risk families, big data analysis, risk prediction model

Procedia PDF Downloads 115

Authors: Yinglisong, Jingge Chen, Jingxuan Chen, Yan Wang, Hui Huang, Jing Zhnag, Qianqian Zhang, Zhenzhen Zhang, Ji Zhang

Abstract:

Purpose: The study aims to establish a nomogram prediction model for postpartum hemorrhage (PPH) in vaginal delivery. Patients and Methods: Clinical data were retrospectively collected from vaginal delivery patients admitted to a hospital in Zhengzhou, China, from June 1, 2022 - October 31, 2022. Univariate and multivariate logistic regression were used to filter out independent risk factors. A nomogram model was established for PPH in vaginal delivery based on the risk factors coefficient. Bootstrapping was used for internal validation. To assess discrimination and calibration, receiver operator characteristics (ROC) and calibration curves were generated in the derivation and validation groups. Results: A total of 1340 cases of vaginal delivery were enrolled, with 81 (6.04%) having PPH. Logistic regression indicated that history of uterine surgery, induction of labor, duration of first labor, neonatal weight, WBC value (during the first stage of labor), and cervical lacerations were all independent risk factors of hemorrhage (P <0.05). The area-under-curve (AUC) of ROC curves of the derivation group and the validation group were 0.817 and 0.821, respectively, indicating good discrimination. Two calibration curves showed that nomogram prediction and practical results were highly consistent (P = 0.105, P = 0.113). Conclusion: The developed individualized risk prediction nomogram model can assist midwives in recognizing and diagnosing high-risk groups of PPH and initiating early warning to reduce PPH incidence.

Keywords: vaginal delivery, postpartum hemorrhage, risk factor, nomogram

Procedia PDF Downloads 46

Authors: Seyed Esmail Seyedi Bariran, Khairul Salleh Mohamed Sahari

Abstract:

In multi-echelon supply chain networks, optimal supplier selection significantly depends on the accuracy of suppliers’ performance prediction. Different methods of multi criteria decision making such as ANN, GA, Fuzzy, AHP, etc have been previously used to predict the supplier performance but the “black-box” characteristic of these methods is yet a major concern to be resolved. Therefore, the primary objective in this paper is to implement an artificial intelligence-based gene expression programming (GEP) model to compare the prediction accuracy with that of ANN. A full factorial design with %95 confidence interval is initially applied to determine the appropriate set of criteria for supplier performance evaluation. A test-train approach is then utilized for the ANN and GEP exclusively. The training results are used to find the optimal network architecture and the testing data will determine the prediction accuracy of each method based on measures of root mean square error (RMSE) and correlation coefficient (R2). The results of a case study conducted in Supplying Automotive Parts Co. (SAPCO) with more than 100 local and foreign supply chain members revealed that, in comparison with ANN, gene expression programming has a significant preference in predicting supplier performance by referring to the respective RMSE and R-squared values. Moreover, using GEP, a mathematical function was also derived to solve the issue of ANN black-box structure in modeling the performance prediction.

Keywords: Supplier Performance Prediction, ANN, GEP, Automotive, SAPCO

Procedia PDF Downloads 399

Authors: Ehsan Mehryaar, Seyed Armin Motahari Tabari

Abstract:

Without a doubt, soil shear strength is the most important property of the soil. The majority of fatal and catastrophic geological accidents are related to shear strength failure of the soil. Therefore, its prediction is a matter of high importance. However, acquiring the shear strength is usually a cumbersome task that might need complicated laboratory testing. Therefore, prediction of it based on common and easy to get soil properties can simplify the projects substantially. In this paper, A hybrid model based on the classification and regression tree algorithm and logistic regression is proposed where each leaf of the tree is an independent regression model. A database of 189 points for clay soil, including Moisture content, liquid limit, plastic limit, clay content, and shear strength, is collected. The performance of the developed model compared to the existing models and equations using root mean squared error and coefficient of correlation.

Keywords: model tree, CART, logistic regression, soil shear strength

Procedia PDF Downloads 173

Authors: Jongsung Kim, Daegun Han, Myungjin Lee, Soojun Kim, Hung Soo Kim

Abstract:

Recently, the frequency and magnitude of natural disasters are gradually increasing due to climate change. Especially in Korea, large-scale damage caused by heavy rainfall frequently occurs due to rapid urbanization. Therefore, this study proposed a Heavy rain Damage Risk Index (HDRI) using PSR (Pressure – State - Response) structure for heavy rain risk assessment. We constructed pressure index, state index, and response index for the risk assessment of each local government in Gyeonggi-do province, and the evaluation indices were determined by principal component analysis. The indices were standardized using the Z-score method then HDRIs were obtained for 31 local governments in the province. The HDRI is categorized into three classes, say, the safest class is 1st class. As the results, the local governments of the 1st class were 15, 2nd class 7, and 3rd class 9. From the study, we were able to identify the risk class due to the heavy rainfall for each local government. It will be useful to develop the heavy rainfall prediction function by risk class, and this was performed in this issue. Also, this risk class could be used for the decision making for efficient disaster management. Acknowledgements: This research was supported by Basic Science Research Program through the National Research Foundation of Korea (NRF) funded by the Ministry of Science, ICT & Future Planning (2017R1A2B3005695).

Keywords: natural disaster, heavy rain risk assessment, HDRI, PSR

Procedia PDF Downloads 175

Authors: Kamalpreet Kaur, Renu Dhir

Abstract:

Climate prediction is an essential component of climate research, which helps evaluate possible effects on economies, communities, and ecosystems. Climate prediction involves short-term weather prediction, seasonal prediction, and long-term climate change prediction. Climate prediction can use the information gathered from satellites, ground-based stations, and ocean buoys, among other sources. The paper's four architectures, such as ResNet50, VGG19, Inception-v3, and Xception, have been combined using an ensemble approach for overall performance and robustness. An ensemble of different models makes a prediction, and the majority vote determines the final prediction. The various architectures such as ResNet50, VGG19, Inception-v3, and Xception efficiently classify the dataset RSI-CB256, which contains satellite images into cloudy and non-cloudy. The generated ensembled S-E model (Sar-ensembled model) provides an accuracy of 99.25%.

Keywords: climate, satellite images, prediction, classification

Procedia PDF Downloads 44

Authors: Jing Jiang, Wenhuan XU, Lei Zhang, Shiyi Zhang, Tongli Wang

Abstract:

Climate data quality significantly affects the reliability of ecological modeling. In the Asia Pacific (AP) region, low-quality climate data hinders ecological modeling. ClimateAP, a software developed in 2017, generates high-quality climate data for the AP region, benefiting researchers in forestry and agriculture. However, its adoption remains limited. This study aims to confirm the validity of biologically relevant variable data generated by ClimateAP during the normal climate period through comparison with the currently available gridded data. Climate data from 2,366 weather stations were used to evaluate the prediction accuracy of ClimateAP in comparison with the commonly used gridded data from WorldClim1.4. Univariate regressions were applied to 48 monthly biologically relevant variables, and the relationship between the observational data and the predictions made by ClimateAP and WorldClim was evaluated using Adjusted R-Squared and Root Mean Squared Error (RMSE). Locations were categorized into mountainous and flat landforms, considering elevation, slope, ruggedness, and Topographic Position Index. Univariate regressions were then applied to all biologically relevant variables for each landform category. Random Forest (RF) models were implemented for the climatic niche modeling of Cunninghamia lanceolata. A comparative analysis of the prediction accuracies of RF models constructed with distinct climate data sources was conducted to evaluate their relative effectiveness. Biologically relevant variables were obtained from three unpublished Chinese meteorological datasets. ClimateAPv3.0 and WorldClim predictions were obtained from weather station coordinates and WorldClim1.4 rasters, respectively, for the normal climate period of 1961-1990. Occurrence data for Cunninghamia lanceolata came from integrated biodiversity databases with 3,745 unique points. ClimateAP explains a minimum of 94.74%, 97.77%, 96.89%, and 94.40% of monthly maximum, minimum, average temperature, and precipitation variances, respectively. It outperforms WorldClim in 37 biologically relevant variables with lower RMSE values. ClimateAP achieves higher R-squared values for the 12 monthly minimum temperature variables and consistently higher Adjusted R-squared values across all landforms for precipitation. ClimateAP's temperature data yields lower Adjusted R-squared values than gridded data in high-elevation, rugged, and mountainous areas but achieves higher values in mid-slope drainages, plains, open slopes, and upper slopes. Using ClimateAP improves the prediction accuracy of tree occurrence from 77.90% to 82.77%. The biologically relevant climate data produced by ClimateAP is validated based on evaluations using observations from weather stations. The use of ClimateAP leads to an improvement in data quality, especially in non-mountainous regions. The results also suggest that using biologically relevant variables generated by ClimateAP can slightly enhance climatic niche modeling for tree species, offering a better understanding of tree species adaptation and resilience compared to using gridded data.

Keywords: climate data validation, data quality, Asia pacific climate, climatic niche modeling, random forest models, tree species

Procedia PDF Downloads 49

Authors: Cheng-yu Hsieh, Bo Zhang, Ahmed Hambaba

Abstract:

Stock market prediction has long been an area of interest for both expert analysts and investors, driven by its complexity and the noisy, volatile conditions it operates under. This research examines the efficacy of combining the Patch Time Series Transformer (PatchTST) with wavelet transforms, specifically focusing on Haar and Daubechies wavelets, in forecasting the adjusted closing price of the S&P 500 index for the following day. By comparing the performance of the augmented PatchTST models with traditional predictive models such as Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Transformers, this study highlights significant enhancements in prediction accuracy. The integration of the Daubechies wavelet with PatchTST notably excels, surpassing other configurations and conventional models in terms of Mean Absolute Error (MAE) and Mean Squared Error (MSE). The success of the PatchTST model paired with Daubechies wavelet is attributed to its superior capability in extracting detailed signal information and eliminating irrelevant noise, thus proving to be an effective approach for financial time series forecasting.

Keywords: deep learning, financial forecasting, stock market prediction, patch time series transformer, wavelet transform

Procedia PDF Downloads 18

Authors: Divvela Vishnu Sai Kumar, Deepak Arora, Sheenu Rizvi

Abstract:

Forecasting a cyclone through satellite images consists of the estimation of the intensity of the cyclone and predicting it before a cyclone comes. This research work can help people to take safety measures before the cyclone comes. The prediction of the intensity of a cyclone is very important to save lives and minimize the damage caused by cyclones. These cyclones are very costliest natural disasters that cause a lot of damage globally due to a lot of hazards. Authors have proposed five different CNN (Convolutional Neural Network) models that estimate the intensity of cyclones through INSAT-3D IR images. There are a lot of techniques that are used to estimate the intensity; the best model proposed by authors estimates intensity with a root mean squared error (RMSE) of 10.02 kts.

Keywords: estimating cyclone intensity, deep learning, convolution neural network, prediction models

Procedia PDF Downloads 94

Authors: Marzieh Karimihaghighi, Carlos Castillo

Abstract:

This work studies how Machine Learning (ML) may be used to increase the effectiveness of a criminal recidivism risk assessment tool, RisCanvi. The two key dimensions of this analysis are predictive accuracy and algorithmic fairness. ML-based prediction models obtained in this study are more accurate at predicting criminal recidivism than the manually-created formula used in RisCanvi, achieving an AUC of 0.76 and 0.73 in predicting violent and general recidivism respectively. However, the improvements are small, and it is noticed that algorithmic discrimination can easily be introduced between groups such as national vs foreigner, or young vs old. It is described how effectiveness and algorithmic fairness objectives can be balanced, applying a method in which a single error disparity in terms of generalized false positive rate is minimized, while calibration is maintained across groups. Obtained results show that this bias mitigation procedure can substantially reduce generalized false positive rate disparities across multiple groups. Based on these results, it is proposed that ML-based criminal recidivism risk prediction should not be introduced without applying algorithmic bias mitigation procedures.

Keywords: algorithmic fairness, criminal risk assessment, equalized odds, recidivism

Procedia PDF Downloads 130

Authors: J. K. Alhassan, B. Attah, S. Misra

Abstract:

Human beings have the ability to make logical decisions. Although human decision - making is often optimal, it is insufficient when huge amount of data is to be classified. medical dataset is a vital ingredient used in predicting patients health condition. In other to have the best prediction, there calls for most suitable machine learning algorithms. This work compared the performance of Artificial Neural Network (ANN) and Decision Tree Algorithms (DTA) as regards to some performance metrics using diabetes data. The evaluations was done using weka software and found out that DTA performed better than ANN. Multilayer Perceptron (MLP) and Radial Basis Function (RBF) were the two algorithms used for ANN, while RegTree and LADTree algorithms were the DTA models used. The Root Mean Squared Error (RMSE) of MLP is 0.3913,that of RBF is 0.3625, that of RepTree is 0.3174 and that of LADTree is 0.3206 respectively.

Keywords: artificial neural network, classification, decision tree algorithms, diabetes mellitus

Procedia PDF Downloads 384

Authors: B. Sir, M. Podhoranyi, S. Kuchar, T. Kocyan

Abstract:

Rainfall-runoff models play important role in hydrological predictions. However, the model is only one part of the process for creation of flood prediction. The aim of this paper is to show the process of successful prediction for flood event (May 15–May 18 2014). The prediction was performed by rainfall runoff model HEC–HMS, one of the models computed within Floreon+ system. The paper briefly evaluates the results of automatic hydrologic prediction on the river Olše catchment and its gages Český Těšín and Věřňovice.

Keywords: flood, HEC-HMS, prediction, rainfall, runoff

Procedia PDF Downloads 370

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 164

Authors: Yilin Liao, Hewen Li, Paula McConvey

Abstract:

Speed skaters often face a risk of concussion when they fall on the ice floor and impact crash mats during practices and competitive races. Several variables, including those related to the skater, the crash mat, and the impact position (body side/head/feet impact), are believed to influence the severity of the skater's concussion. While computer simulation modeling can be employed to analyze these accidents, the simulation process is time-consuming and does not provide rapid information for coaches and teams to assess the skater's injury risk in competitive events. This research paper promotes the exploration of the feasibility of using AI techniques for evaluating skater’s potential concussion severity, and to develop a fast concussion prediction tool using artificial neural networks to reduce the risk of treatment delays for injured skaters. The primary data is collected through virtual tests and physical experiments designed to simulate skater-mat impact. It is then analyzed to identify patterns and correlations; finally, it is used to train and fine-tune the artificial neural networks for accurate prediction. The development of the prediction tool by employing machine learning strategies contributes to the application of AI methods in sports science and has theoretical involvements for using AI techniques in predicting and preventing sports-related injuries.

Keywords: artificial neural networks, concussion, machine learning, impact, speed skater

Procedia PDF Downloads 71

Authors: Retno A. Vinarti, Lucy M. Hederman

Abstract:

This research describes a knowledge model for a system which give personalized alert to users about infectious disease risks in the context of weather, location and time. The knowledge model is based on established epidemiological concepts augmented by information gleaned from infection-related data repositories. The existing disease risk prediction research has more focuses on utilizing raw historical data and yield seasonal patterns of infectious disease risk emergence. This research incorporates both data and epidemiological concepts gathered from Atlas of Human Infectious Disease (AHID) and Centre of Disease Control (CDC) as basic reasoning of infectious disease risk prediction. Using CommonKADS methodology, the disease risk prediction task is an assignment synthetic task, starting from knowledge identification through specification, refinement to implementation. First, knowledge is gathered from AHID primarily from the epidemiology and risk group chapters for each infectious disease. The result of this stage is five major elements (Person, Infectious Disease, Weather, Location and Time) and their properties. At the knowledge specification stage, the initial tree model of each element and detailed relationships are produced. This research also includes a validation step as part of knowledge refinement: on the basis that the best model is formed using the most common features, Frequency-based Selection (FBS) is applied. The portion of the Infectious Disease risk model relating to Person comes out strongest, with Location next, and Weather weaker. For Person attribute, Age is the strongest, Activity and Habits are moderate, and Blood type is weakest. At the Location attribute, General category (e.g. continents, region, country, and island) results much stronger than Specific category (i.e. terrain feature). For Weather attribute, Less Precise category (i.e. season) comes out stronger than Precise category (i.e. exact temperature or humidity interval). However, given that some infectious diseases are significantly more serious than others, a frequency based metric may not be appropriate. Future work will incorporate epidemiological measurements of disease seriousness (e.g. odds ratio, hazard ratio and fatality rate) into the validation metrics. This research is limited to modelling existing knowledge about epidemiology and chain of infection concepts. Further step, verification in knowledge refinement stage, might cause some minor changes on the shape of tree.

Keywords: epidemiology, knowledge modelling, infectious disease, prediction, risk

Procedia PDF Downloads 214

Authors: Peter David Reiss

Abstract:

The concept of the psychosis prodrome has allowed for the identification of adolescent and young adult patients who have a significantly elevated risk of developing schizophrenia spectrum disorders. A number of different interventions have been tested in order to prevent or delay progression of symptoms. To date, there has been no consistent meta-analytical evidence to support efficacy of antipsychotic treatment for patients in the prodromal state, and their use remains therefore inconclusive. Although antipsychotics may manage symptoms transiently, they have not been found to prevent or delay onset of psychotic disorders. Furthermore, pharmacological intervention in high-risk individuals remains controversial, because of the antipsychotic side effect profile in a population in which only about 20 to 35 percent will eventually convert to psychosis over a two-year period, with even after two years conversion rates not exceeding 30 to 40 percent. This general estimate is additionally problematic, in that it ignores the fact that there is significant variation in individual risk among clinical high-risk cases. The current lack of reliable tests for at-risk patients makes it difficult to justify individual treatment decisions. Preventive treatment should ideally be dictated by an individual’s risk while minimizing potentially harmful medication exposure. This requires more accurate predictive assessments by using valid and accessible prognostic markers. The following will compare prediction and risk modification potential of behavioral biomarkers such as disturbances of basic sense of self and emotion awareness, neurocognitive biomarkers such as attention, working and declarative memory, and neurophysiological biomarkers such as glutamatergic abnormalities and NMDA receptor dysfunction. Identification of robust biomarkers could therefore not only provide more reliable means of psychosis prediction, but also help test and develop new clinical interventions targeted at the prodromal state.

Keywords: at-risk mental state, biomarkers, glutamatergic system, NMDA receptor, psychosis prodrome, schizophrenia

Procedia PDF Downloads 173

Authors: Supria Sarkar, Vasit Sagan, Sourav Bhadra, Meghnath Pokharel, Felix B.Fritschi

Abstract:

Soybean and their derivatives are very important agricultural commodities around the world because of their wide applicability in human food, animal feed, biofuel, and industries. However, the significance of soybean production depends on the quality of the soybean seeds rather than the yield alone. Seed composition is widely dependent on plant physiological properties, aerobic and anaerobic environmental conditions, nutrient content, and plant phenological characteristics, which can be captured by high temporal resolution remote sensing datasets. Planet scope (PS) satellite images have high potential in sequential information of crop growth due to their frequent revisit throughout the world. In this study, we estimate soybean seed composition while the plants are in the field by utilizing PlanetScope (PS) satellite images and different machine learning algorithms. Several experimental fields were established with varying genotypes and different seed compositions were measured from the samples as ground truth data. The PS images were processed to extract 462 hand-crafted vegetative and textural features. Four machine learning algorithms, i.e., partial least squares (PLSR), random forest (RFR), gradient boosting machine (GBM), support vector machine (SVM), and two recurrent neural network architectures, i.e., long short-term memory (LSTM) and gated recurrent unit (GRU) were used in this study to predict oil, protein, sucrose, ash, starch, and fiber of soybean seed samples. The GRU and LSTM architectures had two separate branches, one for vegetative features and the other for textures features, which were later concatenated together to predict seed composition. The results show that sucrose, ash, protein, and oil yielded comparable prediction results. Machine learning algorithms that best predicted the six seed composition traits differed. GRU worked well for oil (R-Squared: of 0.53) and protein (R-Squared: 0.36), whereas SVR and PLSR showed the best result for sucrose (R-Squared: 0.74) and ash (R-Squared: 0.60), respectively. Although, the RFR and GBM provided comparable performance, the models tended to extremely overfit. Among the features, vegetative features were found as the most important variables compared to texture features. It is suggested to utilize many vegetation indices for machine learning training and select the best ones by using feature selection methods. Overall, the study reveals the feasibility and efficiency of PS images and machine learning for plot-level seed composition estimation. However, special care should be given while designing the plot size in the experiments to avoid mixed pixel issues.

Keywords: agriculture, computer vision, data science, geospatial technology

Procedia PDF Downloads 111

Authors: Mohammed El-Arbi Khalfallah, Mohamed Lakhdar Hadji

Abstract:

Managing and controlling risk is a topic research in the world of finance. Before a risky situation, the stakeholders need to do comparison according to the positions and actions, and financial institutions must take measures of a particular market risk and credit. In this work, we study a model of risk measure in finance: Value at Risk (VaR), which is a new tool for measuring an entity's exposure risk. We explain the concept of value at risk, your average, tail, and describe the three methods for computing: Parametric method, Historical method, and numerical method of Monte Carlo. Finally, we briefly describe advantages and disadvantages of the three methods for computing value at risk.

Keywords: average value at risk, conditional value at risk, tail value at risk, value at risk

Procedia PDF Downloads 416