Machine learning is a widely growing field which helps in better learning from data and its analysis without any human intervention. It is being popularly used in the field of healthcare for analyzing and detecting se...
详细信息
ISBN:
(纸本)9789811303418;9789811303401
Machine learning is a widely growing field which helps in better learning from data and its analysis without any human intervention. It is being popularly used in the field of healthcare for analyzing and detecting serious and complex conditions. Diabetes is one such condition that heavily affects the entire system. In this paper, application of intelligent machine learning algorithms like logistic regression, naive Bayes, support vector machine, decision tree, k-nearest neighbors, neural network, and random decision forest are used along with feature extraction. The accuracy of each algorithm, with and without feature extraction, leads to a comparative study of these predictive models. Therefore, a list of algorithms that works better with feature extraction and another that works better without it is obtained. These results can be used further for better prediction and diagnosis of diabetes.
Intelligent transport support systems have had a major impact on people's urban mobility. In large urban centers, transportation services still need ways to optimize vehicle supply in certain areas, according to t...
详细信息
ISBN:
(纸本)9781728175393
Intelligent transport support systems have had a major impact on people's urban mobility. In large urban centers, transportation services still need ways to optimize vehicle supply in certain areas, according to the demand in each of them. Optimized distribution of on-demand taxi services can be part of an intelligent urban mobility plan, causing direct impacts on urban traffic, improving transport accessibility, improving safety at taxi standpoints by reduced waiting times, reduce transportation fare etc. Many vehicle-mounted sensors currently generate real-time information that is not used for processing and generating information with value. This paper proposes a Taxi Demand Forecasting methodology using stream machine learning algorithms that tackle concept drift detection on taxi data stream. A real data source made available on the New York open platform feeds a stream learning model, constructed using the Massive Online Analysis (MOA) tool - a framework for data stream mining. The stream model shows promising results in forecasting taxi demand, reaching 78% accuracy. Despite using data from a specific city, the methodology and results of this work can contribute to a more proactive demand management in other cities.
For the uncertain characteristics of output power of distributed Photovoltaic (PV), the energy storage device is used to make up the error, between the predicted output and the actual output, to achieve the volatility...
详细信息
ISBN:
(纸本)9783037857410
For the uncertain characteristics of output power of distributed Photovoltaic (PV), the energy storage device is used to make up the error, between the predicted output and the actual output, to achieve the volatility control of PV power system. This paper presents that the application of support vector machine (SVM) in the power output forecasting of PV volatility control. Based on the complex and non-linear of the factor affecting the PV output, it points the non-linear relationship between the influencing factors and predicted values, and it establishes the SVM regression model of the PV system. Meanwhile, combined with the historical data of the PV operation, it gives the predictive values. Both theoretical analyses and calculation examples show that this method is simple, with high precision, and it is more suitable to the PV output volatility control.
In big cities, taxi service is imbalanced. In some areas, passengers wait too long for a taxi, while in others, many taxis roam without passengers. Knowledge of where a taxi will become available can help us solve the...
详细信息
ISBN:
(纸本)9781467390057
In big cities, taxi service is imbalanced. In some areas, passengers wait too long for a taxi, while in others, many taxis roam without passengers. Knowledge of where a taxi will become available can help us solve the taxi demand imbalance problem. In this paper, we employ a holistic approach to predict taxi demand at high spatial resolution. We showcase our techniques using two real-world data sets, yellow cabs and Uber trips in New York City, and perform an evaluation over 9,940 building blocks in Manhattan. Our approach consists of two key steps. First, we use entropy and the temporal correlation of human mobility to measure the demand uncertainty at the building block level. Second, to identify which predictive algorithm can approach the theoretical maximum predictability, we implement and compare three predictors: the Markov predictor (a probability-based predictive algorithm), the Lempel-Ziv-Welch predictor (a sequence-based predictive algorithm), and the Neural Network predictor (a predictive algorithm that uses machine learning). The results show that predictability varies by building block and, on average, the theoretical maximum predictability can be as high as 83%. The performance of the predictors also vary: the Neural Network predictor provides better accuracy for blocks with low predictability, and the Markov predictor provides better accuracy for blocks with high predictability. In blocks with high maximum predictability, the Markov predictor is able to predict the taxi demand with an 89% accuracy, 11% better than the Neural Network predictor, while requiring only 0.03% computation time. These findings indicate that the maximum predictability can be a good metric for selecting prediction algorithms.
In this paper, nonlinear time series forecasting system combining algorithm proposed prediction model. For the model of the existing combination forecasting method selection and mixed results so that it can be improve...
详细信息
ISBN:
(纸本)9783038350453
In this paper, nonlinear time series forecasting system combining algorithm proposed prediction model. For the model of the existing combination forecasting method selection and mixed results so that it can be improved terms for a variety of different sequences with adaptive prediction. The results show that for different test data set, the method can effectively use all kinds of prediction Models pool without specific filter to adjust the mixing weight ratio of each of the prediction results so that the adaptive prediction, ensure higher prediction accuracy achieved.
The control of the airtightness is a key factor to reduce the buildings energy demand. The present document describes the development of a predictive algorithm to estimate the airtightness of new or renovated building...
详细信息
ISBN:
(纸本)9781728134017
The control of the airtightness is a key factor to reduce the buildings energy demand. The present document describes the development of a predictive algorithm to estimate the airtightness of new or renovated buildings. The study is based on the results of almost 300 blower-door tests made in different dwellings and buildings with diverse envelope configurations and geometries. Two different analysis were made, the first one interrelates seven different parameters from an algorithm specifically designed for that purpose. Then, a second analysis from an energy efficiency point of view were made, evaluating the numerical results obtained, valuating the physical correlations of these results, defining the risk threshold for each case, categorizing the different alternatives and defining the conclusions of the study. Among other advantages, the predictive algorithm allows to evaluate, before assuming any investment, the risk that the company should fulfil to reach the different standards demanded by the clients. Besides, based on the test results, this algorithm let determine, in an early stage, what design or constructive changes need to be done to reach the specific airtightness demanded. This research demonstrates the relevance that the quality of workmanship must obtain an airtight building or dwelling. Besides, it is highlighted the influence that the choice of the materials and constructive solutions have on the level of air infiltration.
Recently, computer-aided assessment (CAA) systems have been used for mathematics education, with some CAA systems capable of assessing learners' answers using mathematical expressions. However, the standard input ...
详细信息
ISBN:
(数字)9783319569321
ISBN:
(纸本)9783319569321;9783319569307
Recently, computer-aided assessment (CAA) systems have been used for mathematics education, with some CAA systems capable of assessing learners' answers using mathematical expressions. However, the standard input method for mathematics education systems is cumbersome for novice learners. In 2011, we proposed a new mathematical input method that allowed users to input mathematical expressions through an interactive conversion of mathematical expressions from colloquial-style linear strings in WYSIWYG. In this study, we propose a predictive algorithm to improve the input efficiency of this conversion process by using machine learning to determine the score parameters with a structured perceptron similar to natural language processing. In our experimental evaluation, with a training dataset comprising 700 formulae, the prediction accuracy was 96.2% for the top ten ranking by stable score parameter learning;this accuracy is sufficient for a mathematical input interface system.
In this study, the coefficient of frictions under variable normal load and reciprocating frequencies of alumina ceramics have been investigated with various level (upto 4 wt%) of nano-crystalline MgO addition. A linea...
详细信息
In this study, the coefficient of frictions under variable normal load and reciprocating frequencies of alumina ceramics have been investigated with various level (upto 4 wt%) of nano-crystalline MgO addition. A linear reciprocating tribotester was used to carry out the experimental investigations in dry condition using a silicon nitride (Si3N4) ball as a counter surface on the sintered samples. The friction tests were performed for a sliding time of 30 min with reciprocating frequency of 15, 30, 45, 60 Hz keeping the normal load fixed at 0.5 kgf and at normal loads of 0.3, 0.5, 0.7, 1.0 kgf keeping the sliding frequency fixed at 30 Hz. The friction coefficient increases with increasing sliding frequency, normal load but decreases with nano-magnesia addition. The friction coefficient data is used to develop an algorithm following the best fit topology to predict the addition level of magnesia in alumina for given friction coefficient and sliding frequency or normal load. Among various curve fitting techniques like polynomial fit of degree two, exponential fit of degree one and two, smoothing spline and Weibull fit, with minimum root mean square error, cubicspline fit method is adopted to form smooth curves in MATLAB. The validated result lies within a maximum error of 3.37% for cubicspline fit. Copyright (C) 2022 Elsevier Ltd. All rights reserved. Selection and peer-review under responsibility of the scientific committee of the Symposium on Failure and Preventive Maintenance of Machineries 2022.
The friction coefficient of sintered alumina with nano-crystalline titania (up to 4 wt.%) is investigated in relation with sliding frequency and normal load by computational method. The proposed work studies the ...
详细信息
A new predictive power control scheme was considered for a wireless cellular system employing orthogonal frequency division multiplexing (OFDM). To mitigate the effect of cochannel interference CCI while satisfying re...
详细信息
ISBN:
(纸本)9781424472352
A new predictive power control scheme was considered for a wireless cellular system employing orthogonal frequency division multiplexing (OFDM). To mitigate the effect of cochannel interference CCI while satisfying required quality of service, the power level on each subchannel of OFDM systems should be allocated to and controlled at an optimum level. A conventional approach to OFDM power allocation system design is to maintain the same link quality for all subchannels. This simple scheme requires high power consumption and deteriorates control stability and convergence properties. To overcome the drawbacks of the traditional approach, a new power control scheme is proposed. Numerical results are presented to illustrate the advantages of the proposed algorithm over the conventional one.
暂无评论