A machine learning approach for traffic-noise annoyance assessment
یک روش یادگیری ماشین برای تخمین آزار سر و صدای ترافیک-2019
In this study, models for predicting traffic-noise annoyance based on noise perception, noise exposure levels, and demographics were developed. By applying machine-learning techniques, in particular artificial neural networks (ANN), support vector machines (SVM) and multiple linear regressions (MLR), the traffic-noise annoyance models were obtained, and the error rates compared. A traffic noise map and the estimation of noise exposure for the case study area were developed. Although, it is quite evident that subjective noise perception and predicted noise exposure levels strongly influence traffic-noise annoyance, traditional statistical models fail to produce accurate predictions. Therefore, a machine-learning approach was applied, which showed a better performance in terms of error rates and the coefficient of determination (R2). The best results for predicting traffic-noise annoyance were obtained with the ANN model, obtaining 42% and 35% error reduction in training subsets compared to the MRL and SVM models, respectively. For testing subsets, the error reductions were 24% and 19% for the corresponding models. The coefficient of determination R2 increased 3.8 and 2.3 times using ANN compared to MRL and SVM models in training subsets respectively, and 1.7 times (in both MRL and SVM models) for testing subsets. In this way, the applied methodology can be used as a reliable and more accurate tool for determining the impact of transportation noise in urban context, promoting the well-being of the population and the creation of suitable public policy.
Keywords: Noise annoyance | Traffic noise | Machine-learning | Artificial neural networks | Support vector machine
Accelerating flash calculation through deep learning methods
تسریع محاسبه فلش از طریق روش های یادگیری عمیق-2019
In the past two decades, researchers have made remarkable progress in accelerating flash calculation, which is very useful in a variety of engineering processes. In this paper, general phase splitting problem statements and flash calculation procedures using the Successive Substitution Method are reviewed, while the main shortages are pointed out. Two acceleration methods, Newton’s method and the Sparse Grids Method are presented afterwards as a comparison with the deep learning model proposed in this paper. A detailed introduction from artificial neural networks to deep learning methods is provided here with the authors’ own remarks. Factors in the deep learning model are investigated to show their effect on the final result. A selected model based on that has been used in a flash calculation predictor with comparison with other methods mentioned above. It is shown that results from the optimized deep learning model meet the experimental data well with the shortest CPU time. More comparison with experimental data has been conducted to show the robustness of our model.
Keywords: Vapor-liquid equilibrium | Flash calculation | Deep learning methods | Artificial neural networks
CWV-BANN-SVM ensemble learning classifier for an accurate diagnosis of breast cancer
طبقه بندی یادگیری گروه CWV-BANN-SVM برای تشخیص دقیق سرطان پستان-2019
This paper presents a new data mining technique for an accurate prediction of breast cancer (BC), which is one of the major mortality causes among women around the globe. The main objective of our study is to expand an automatic expert system (ES) to provide an accurate diagnosis of BC. Both, Support Vector Machines (SVMs) and Artificial Neural Networks (ANNs) were applied to analyze BC data. The wellknown Wisconsin Breast Cancer Dataset (WBCD), available in the UCI repository, was examined in our study. We first tested the SVM algorithm using various values of the C, e and c parameters. As a result of the first experiment, we were able to observe that the adjustment of these regularization parameters can greatly improve the performance of the traditional SVM algorithm applied for BC detection. The highest obtained accuracy at the first step was 99.71%. Then, we performed a new BC detection approach based on two ensemble learning techniques: the confidence-weighted voting method and the boosting ensemble technique. Our model, called CWV-BANNSVM, combines boosting ANNs (BANN) and two SVMs, using optimal parameters selected during the first experiment. The performance of the applied methods was evaluated using several popular metrics, such as specificity, sensitivity, precision, FPR, FNR, F1 score, AUC, Gini and accuracy. The proposed CWV-BANNSVM model was able to improve the performance of the traditional machine learning algorithms applied to BC detection, reaching the accuracy of 100%. To overcome the overfitting issue, we determined and used some appropriate parameter values of polynomial SVM. Our comparison with the existing studies dedicated to BC prediction suggests that the proposed CWV-BANN-SVM model provides one of the best prediction performances overall.
Keywords: Data mining | Machine learning | Ensemble technique | Breast cancer | Support vector machine | Artificial neural network
Intelligent decisions to stop or mitigate lost circulation based on machine learning
تصمیمات هوشمند برای متوقف کردن یا کاهش گردش خون از دست رفته بر اساس یادگیری ماشین-2019
Lost circulation is one of the frequent challenges encountered during the drilling of oil and gas wells. It is detrimental because it can not only increase non-productive time and operational cost but also lead to other safety hazards such as wellbore instability, pipe sticking, and blow out. However, selecting the most effective treatment may still be regarded as an ill-structured issue since it does not have a unique solution. Therefore, the objective of this study is to develop an expert system that can screen drilling operation parameters and drilling fluid characteristics required to diagnose the lost circulation problem correctly and suggest the most appropriate solution for the issue at hand. In the first step, field datasets were collected from 385 wells drilled in Southern Iraq from different fields. Then, fscaret package in R environment was applied to detect the importance and ranking of the input parameters that affect the lost circulation solution. The new models were developed to predict the lost circulation solution for vertical and deviated wells using artificial neural networks (ANNs) and support vector machine (SVM). The using of the machine learning methods could assist the drilling engineer to make an intelligent decision with proper corrective lost circulation treatment.
Keywords: Lost circulation | Intelligent decision | Artificial neural networks | Support vector machine
Design and field implementation of an impact detection system using committees of neural networks
طراحی و اجرای میدانی یک سیستم تشخیص ضربه با استفاده از کمیته های شبکه های عصبی-2019
Many critical societal functions depend on uninterrupted service of civil engineering infrastructure. Rail- roads represent important infrastructure components of the transportation sector and provide both pas- senger and freight services. Railroad bridges over roadways are susceptible to impacts from overheight vehicles and equipment, which may damage bridge girders or supports and must be investigated after each event. One method of monitoring for vehicle-bridge collisions utilizes accelerometers to monitor for abnormal bridge vibrations corresponding to abnormal activity. Passing trains under normal operat- ing conditions frequently produce significant bridge responses that have similar response characteristics to bridge strikes, but do not need to be investigated. This paper presents an expert system which com- prises committees of artificial neural networks trained to interrogate data collected from accelerometers mounted on the bridge, assess the nature of the acceleration signal, and classify the event as either a passing train or a potentially damaging impact. This system is trained using acceleration time histories from accelerometers installed on 8 low-clearance rail bridges; no finite element model simulations were used for network training or data stream creation. The presented system accurately detects and classifies impacts with average impact detection performance ranging from 91–100% with average false positive rates limited to 0.00–0.75%.
Keywords: Bridge impacts Impact detection | Signal classification | Feature selection | Artificial neural networks
Prediction and validation of alternative fillers used in micro surfacing mix-design using machine learning techniques
پیش بینی و اعتبارسنجی از پرکننده های جایگزین مورد استفاده در طراحی میکرو سطحی با استفاده از تکنیک های یادگیری ماشین-2019
In this study regression analysis using machine learning models was investigated to predict and validate the composition of alternative mineral filler in micro surfacing mix design. To generate the data, 168 experiments were conducted with mixing time (sec), cohesion (30 min) kg.cm, cohesion (60 min) kg. cm, set time (sec), wet track abrasion loss (g/m2) as an additives for the design of alternative fillers such as Copper Slag, Fly Ash and High Calcium Fly Ash. Training and testing of feature vector which were formed after conducting experiment was fed into machine learning regression models for prediction of composition of fillers. Support vector machine with polynomial, radial basis function and PUK kernel, Artificial neural network with RBF kernel and Isotonic regression models were considered in the present study. Machine learning regression models were evaluated using three parameters Correlation coefficient, Spearman rho’s and Mean absolute error. Excellent agreement between regression models and experimental results observed. The methodology used will be useful for prediction of micro surfacing mix design for alternative fillers used in the construction industry.
Keywords: Micro surfacing | Mineral fillers | Machine learning | Support vector machine | Artificial neural network
Agribusiness time series forecasting using Wavelet neural networks and metaheuristic optimization: An analysis of the soybean sack price and perishable products demand
پیش بینی سری های زمانی کسب و کارهای کشاورزی با استفاده از شبکه های عصبی موج کوچک و بهینه سازی اکتشافی ذهنی متا: یک تحلیل روی قیمت یک گونی سویبان و تقاضای محصولات فاسد شدنی-2018
Brazilian agribusiness is responsible for almost 25% of the country gross domestic product, and companies from this economic sector may have strategies to control their actions in a competitive market. In this way, models to properly predict variations in the price of products and services could be one of the keys to the success in agribusiness. Consistent models are being adopted by companies as part of a decision making process when important choices are based on short or long-term forecasting. This work aims to evaluate Wavelet Neural Networks (WNNs) performance combined with five optimization techniques in order to obtain the best time series forecasting by considering two case studies in the agribusiness sector. The first one adopts the soybean sack price and the second deals with the demand problem of a distinct groups of products from a food company, where nonlinear trends are the main characteristic on both time series. The optimization techniques adopted in this work are: Differential Evolution, Artificial Bee Colony, Glowworm Swarm Optimization, Gravitational Search Algorithm, and Imperialist Competitive Algorithm. Those were evaluated by considering short-term and long-term forecasting, and a prediction horizon of 30 days ahead was considered for the soybean sack price case, while 12 months ahead was selected for the products demand case. The performance of the optimization techniques in training the WNN were compared to the well-established Backpropagation algorithm and Extreme Learning Machine (ELM) assuming accuracy measures. In long-term forecasting, which is considered more difficult than the short-term case due to the error accumulation, the best combinations in terms of precision was reached by distinct methods according to each case, showing the importance of testing different training strategies. This work also showed that the prediction horizon significantly affected the performance of each optimization method in different ways, and the potential of assuming optimization in WNN learning process.
keywords: Agribusiness |Artificial neural networks |Time series forecasting |Metaheuristics |Natural computing |Optimization
Artificial neural network based prediction of malaria abundances using big data: A knowledge capturing approach
پیشگیری از فراوانی مالاریا بر اساس شبکه عصبی مصنوعی با استفاده از داده های بزرگ: رویکرد جذب دانش-2018
Background and objective: Malaria is one of the most prevalent diseases in urban areas. Malaria flourishes in subtropical countries and affect the public health. The impact is very high, where health monitoring facilities are very limited. To minimize the impact of malaria population in sub-tropical domains, a suitable disease prediction model is required. The objective of this study is to determine the malaria abundances using clinical and environmental variables with Big Data on the geographical location of Khammam district, Telanagana, India. Methods: Prediction model is based on the data collected from primary health centres of department of vector borne diseases (DVBD) of Khammam district and satellite data such as rain fall, relative humidity, temperature and vegetation taken for the time period of 1995–2014. In this study, we test the efficacy of the artificial neural network (ANN) for mosquito abundance prediction. Prediction model was developed for the period of 2015 using a feed forward neural network and compared with the observed values. Results and conclusions: The results vary from area to area based on clinical variables and rainfall in the prediction model corresponding to areas. The average error of the prediction model ranges from 18% to 117%. Clinical data such as number of patients treated with symptoms and without symptoms can improve the prediction level when combined with environmental variables. We perform preliminary findings of malaria abundances by collecting clinical big data across different seasons. Further, more exploration is required in prediction of malaria using big data to improve the accuracy in real practice. In this manuscript, we perform some preliminary findings of malaria abundances by collecting larger data across different seasons. Till today, many models have been developed to examine the malaria prediction with different approaches, but malaria prediction with environmental and clinical data is a new approach with big data analysis.
Keywords: Malaria prediction ، Primary health centers (PHCs) ، Big data ، Artificial neural networks (ANNs)
Traffic noise and pavement distresses: Modelling and assessment of input parameters influence through data mining techniques
سر و صدای ترافیکی و ناراحتی های پیاده رو : مدل سازی و ارزیابی پارامترهای ورودی تاثیر از طریق تکنیک های داده کاوی -2018
Traffic noise affects greatly health and well-being of people, consequently the knowledge and control of the factors affecting it is very important. In this study models to predict tyre-pavement noise acoustic and psy choacoustic indicators based on type of pavement, texture, pavement distresses and speed were developed and used to assess the importance of each factor. By applying data mining techniques, in particular artificial neural networks and support vector machines, models with good predictive capacity of both acoustic and psychoa coustic noise indicators were obtained, constituting a precious tool to reduce the tyre-pavement noise. Moreover, the proposed models allowed for the assessment of the influence of the input parameters controlling noise such as: type of pavement, texture, speed and pavement distresses for the first time. It was found that pavement distresses and, as expected, speed influence strongly tyre-pavement noise. In this way it is clearly shown that preventive maintenance of road pavements by authorities, which eliminates distresses, can have an important effect on tyre-road noise, promoting the well-being of the populations.
Keywords: Tyre-pavement noise ، Acoustic and psychoacoustic indicators ، Pavement distresses ، Data mining ، Support vector machines ، Artificial neural networks
چارچوب بیوفیزیکی نو برای پیش بینی انتشار CO 2 در هند
سال انتشار: 2018 - تعداد صفحات فایل pdf انگلیسی: 9 - تعداد صفحات فایل doc فارسی: 20
گازهای گلخانه ای (GHG) ناشی از احتراق سوخت های فسیلی منجر به تغییرات اقلیمی نامنظم و ایجاد مشکل شدید زیست محیطی در سراسر جهان می شود. انتشار گازهای گلخانهای از منابع متنوع تاثیرات مضر بر کیفیت هوا، آب، خاک و موجودات زنده دارد. کربن دی اکسید (CO 2 ) یکی از گازهای گلخانه ای است که نقش مهمی در آلایندگی هوا بازی می کند، از این رو تخمین و پیش بینی انتشار CO 2 برای برنامه ریزی انرژی و تصمیم گیری های استراتژیک زیست محیطی ضروری است. هدف این تحقیق، ارزیابی و پیش بینی انتشار CO 2 در هند از منابع مختلف مصرف انرژی است. مدل رگرسیون خطی چندگانه و الگوریتم PSO بر اساس مدل غیرخطی برای برآورد انتشار CO 2 استفاده شده است. نتایج به دست آمده نشان داده است که انتشار CO 2 در هند طی دهه گذشته هشدار دهنده بوده است. نتایج نشان می دهد که مدل PSO می تواند برآورد بسیار دقیق را نسبت به مدل MLR بدست آورد. از نتيجه برآورد PSO، پيشبيني آينده انتشار CO 2 در هند براي سالهاي 2017 تا 2030 با استفاده از شبكه عصبي مصنوعي انجام شد. نتایج پیش بینی همچنین تأکید می کنند که باید برای جلوگیری از انتشار CO 2 در سراسر کشور، باید اقدامات لازم را انجام داد ، زیرا افزایش ناگهانی آن در هند به تهدید شدید طبیعت و محیط منجر می شود.
کليدواژگان: آلودگي هوا | شبکه های عصبی مصنوعی | محاسبات بیو الهام | ارزیابی انتشار CO 2 | پیش بینی میزان انتشار CO 2 | بهینه سازی ذرات.
|مقاله ترجمه شده|