To see the other types of publications on this topic, follow the link: K-Nearest Neighbor - Time Series Prediction.
Journal articles on the topic 'K-Nearest Neighbor - Time Series Prediction'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'K-Nearest Neighbor - Time Series Prediction.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Deng, Mingjun, and Shiru Qu. "Road Short-Term Travel Time Prediction Method Based on Flow Spatial Distribution and the Relations." Mathematical Problems in Engineering 2016 (2016): 1–14. http://dx.doi.org/10.1155/2016/7626875.
Full textAbstract:
There are many short-term road travel time forecasting studies based on time series, but indeed, road travel time not only relies on the historical travel time series, but also depends on the road and its adjacent sections history flow. However, few studies have considered that. This paper is based on the correlation of flow spatial distribution and the road travel time series, applying nearest neighbor and nonparametric regression method to build a forecasting model. In aspect of spatial nearest neighbor search, three different space distances are defined. In addition, two forecasting functions are introduced: one combines the forecasting value by mean weight and the other uses the reciprocal of nearest neighbors distance as combined weight. Three different distances are applied in nearest neighbor search, which apply to the two forecasting functions. For travel time series, the nearest neighbor and nonparametric regression are applied too. Then minimizing forecast error variance is utilized as an objective to establish the combination model. The empirical results show that the combination model can improve the forecast performance obviously. Besides, the experimental results of the evaluation for the computational complexity show that the proposed method can satisfy the real-time requirement.
2
She, Dunxian, and Xiaohua Yang. "A New Adaptive Local Linear Prediction Method and Its Application in Hydrological Time Series." Mathematical Problems in Engineering 2010 (2010): 1–15. http://dx.doi.org/10.1155/2010/205438.
Full textAbstract:
The embedding dimension and the number of nearest neighbors are very important parameters in the prediction of a chaotic time series. In order to reduce the uncertainties in the determination of the forgoing two parameters, a new adaptive local linear prediction method is proposed in this study. In the new method, the embedding dimension and the number of nearest neighbors are combined as a parameter set and change adaptively in the process of prediction. The generalized degree of freedom is used to help select the optimal parameters. Real hydrological time series are taken to examine the performance of the new method. The prediction results indicate that the new method can choose the optimal parameters of embedding dimension and the nearest neighbor number adaptively in the prediction process. And the nonlinear hydrological time series perhaps could be modeled better by the new method.
3
Priambodo, Bagus, and Yuwan Jumaryadi. "Time Series Traffic Speed Prediction Using k-Nearest Neighbour Based on Similar Traffic Data." MATEC Web of Conferences 218 (2018): 03021. http://dx.doi.org/10.1051/matecconf/201821803021.
Full textAbstract:
During the past few years, time series models and neural network models are widely used to predict traffic flow and traffic congestion based on historical data. Historical data traffic from sensors is often applied to time series prediction or various neural network predictions. Recent research shows that traffic flow pattern will be different on weekdays and weekends. We conducted a time series prediction of traffic flow on Monday, using data on weekdays and whole days data. Prediction of short time traffic flows on Monday based on weekdays data using k-NN methods shows a better result, compared to prediction based on all day’s data. We compared the results of the experiment using k-NN and Neural Network methods. From this study, we observed that generally, using similar traffic data for time series prediction show a better result than using the whole data.
4
Tang, Li, Ping He Pan, and Yong Yi Yao. "EPAK: A Computational Intelligence Model for 2-level Prediction of Stock Indices." International Journal of Computers Communications & Control 13, no. 2 (April 13, 2018): 268–79. http://dx.doi.org/10.15837/ijccc.2018.2.3187.
Full textAbstract:
This paper proposes a new computational intelligence model for predicting univariate time series, called EPAK, and a complex prediction model for stock market index synthesizing all the sector index predictions using EPAK as a kernel. The EPAK model uses a complex nonlinear feature extraction procedure integrating a forward rolling Empirical Mode Decomposition (EMD) for financial time series signal analysis and Principal Component Analysis (PCA) for dimension reduction to generate information-rich features as input to a new two-layer K-Nearest Neighbor (KNN) with Affinity Propagation (AP) clustering for prediction via regression. The EPAK model is then used as a kernel for predicting each of all the sector indices of the stock market. The sector indices predictions are then synthesized via weighted average to generate the prediction of the stock market index, yielding a complex prediction model for the stock market index. The EPAK model and the complex prediction model for stock index are tested on real historical financial time series in Chinese stock index including CSI 300 and ten sector indices, with results confirming the effectiveness of the proposed models.
5
Koutroumbas, K., and A. Belehaki. "One-step ahead prediction of <i>fo</i>F2 using time series forecasting techniques." Annales Geophysicae 23, no. 9 (November 22, 2005): 3035–42. http://dx.doi.org/10.5194/angeo-23-3035-2005.
Full textAbstract:
Abstract. In this paper the problem of one-step ahead prediction of the critical frequency (foF2) of the middle-latitude ionosphere, using time series forecasting methods, is considered. The whole study is based on a sample of about 58000 observations of foF2 with 15-min time resolution, derived from the Athens digisonde ionograms taken from the Digisonde Portable Sounder (DPS4) located at Palaia Penteli (38° N, 23.5° E), for the period from October 2002 to May 2004. First, the embedding dimension of the dynamical system that generates the above sample is estimated using the false nearest neighbor method. This information is then utilized for the training of the predictors employed in this study, which are the linear predictor, the neural network predictor, the persistence predictor and the k-nearest neighbor predictor. The results obtained by the above predictors suggest that, as far as the mean square error is considered as performance criterion, the first two predictors are significantly better than the latter two predictors. In addition, the results obtained by the linear and the neural network predictors are not significantly different from each other. This may be taken as an indication that a linear model suffices for one step ahead prediction of foF2.
6
Miśkiewicz-Nawrocka, Monika. "The Application of Random Noise Reduction By Nearest Neighbor Method To Forecasting of Economic Time Series." Folia Oeconomica Stetinensia 13, no. 2 (July 8, 2014): 96–108. http://dx.doi.org/10.2478/foli-2013-0020.
Full textAbstract:
Abstract Since the deterministic chaos appeared in the literature, we have observed a huge increase in interest in nonlinear dynamic systems theory among researchers, which has led to the creation of new methods of time series prediction, e.g. the largest Lyapunov exponent method and the nearest neighbor method. Real time series are usually disturbed by random noise, which can complicate the problem of forecasting of time series. Since the presence of noise in the data can significantly affect the quality of forecasts, the aim of the paper will be to evaluate the accuracy of predicting the time series filtered using the nearest neighbor method. The test will be conducted on the basis of selected financial time series.
7
Cortez, Klender, Martha del Pilar Rodríguez-García, and Samuel Mongrut. "Exchange Market Liquidity Prediction with the K-Nearest Neighbor Approach: Crypto vs. Fiat Currencies." Mathematics 9, no. 1 (December 29, 2020): 56. http://dx.doi.org/10.3390/math9010056.
Full textAbstract:
In this paper, we compare the predictions on the market liquidity in crypto and fiat currencies between two traditional time series methods, the autoregressive moving average (ARMA) and the generalized autoregressive conditional heteroskedasticity (GARCH), and the machine learning algorithm called the k-nearest neighbor (KNN) approach. We measure market liquidity as the log rates of bid-ask spreads in a sample of three cryptocurrencies (Bitcoin, Ethereum, and Ripple) and 16 major fiat currencies from 9 February 2018 to 8 February 2019. We find that the KNN approach is better suited for capturing the market liquidity in a cryptocurrency in the short-term than the ARMA and GARCH models maybe due to the complexity of the microstructure of the market. Considering traditional time series models, we find that ARMA models perform well when estimating the liquidity of fiat currencies in developed markets, whereas GARCH models do the same for fiat currencies in emerging markets. Nevertheless, our results show that the KNN approach can better predict the log rates of the bid-ask spreads of crypto and fiat currencies than ARMA and GARCH models.
8
Su, Liyun, and Chenlong Li. "Local Functional Coefficient Autoregressive Model for Multistep Prediction of Chaotic Time Series." Discrete Dynamics in Nature and Society 2015 (2015): 1–13. http://dx.doi.org/10.1155/2015/329487.
Full textAbstract:
A new methodology, which combines nonparametric method based on local functional coefficient autoregressive (LFAR) form with chaos theory and regional method, is proposed for multistep prediction of chaotic time series. The objective of this research study is to improve the performance of long-term forecasting of chaotic time series. To obtain the prediction values of chaotic time series, three steps are involved. Firstly, the original time series is reconstructed inm-dimensional phase space with a time delayτby using chaos theory. Secondly, select the nearest neighbor points by using local method in them-dimensional phase space. Thirdly, we use the nearest neighbor points to get a LFAR model. The proposed model’s parameters are selected by modified generalized cross validation (GCV) criterion. Both simulated data (Lorenz and Mackey-Glass systems) and real data (Sunspot time series) are used to illustrate the performance of the proposed methodology. By detailed investigation and comparing our results with published researches, we find that the LFAR model can effectively fit nonlinear characteristics of chaotic time series by using simple structure and has excellent performance for multistep forecasting.
9
BOLLT, ERIK M. "MODEL SELECTION, CONFIDENCE AND SCALING IN PREDICTING CHAOTIC TIME-SERIES." International Journal of Bifurcation and Chaos 10, no. 06 (June 2000): 1407–22. http://dx.doi.org/10.1142/s0218127400000906.
Full textAbstract:
Assuming a good embedding and additive noise, the traditional approach to time-series embedding prediction has been to predict pointwise by (usually linear) regression of the k-nearest neighbors; no good mathematics has been previously developed to appropriately select the model (where to truncate Taylor's series) to balance the conflict between noise fluctuations of a small k, and large k data needs of fitting many parameters of a high ordered model. We present a systematic approach to: (1) select the statistically significant neighborhood for a fixed (usually linear) model, (2) give an unbiased estimate of predicted mean response together with a statement of quality of the prediction in terms of confidence bands.
10
WAYLAND, R., D. PICKETT, D. BROMLEY, and A. PASSAMANTE. "MEASURING THE PREDICTABILITY OF NOISY RECURRENT TIME SERIES." International Journal of Bifurcation and Chaos 03, no. 03 (June 1993): 797–802. http://dx.doi.org/10.1142/s0218127493000738.
Full textAbstract:
The effect of the chosen forecasting method on the measured predictability of a noisy recurrent time series is investigated. Situations where the length of the time series is limited, and where the level of corrupting noise is significant are emphasized. Two simple prediction methods based on explicit nearest-neighbor averages are compared to a more complicated, and computationally expensive, local linearization technique based on the method of total least squares. The comparison is made first for noise-free, and then for noisy time series. It is shown that when working with short time series in high levels of additive noise, the simple prediction schemes perform just as well as the more sophisticated total least squares method.
11
WEIGEND, ANDREAS S., and ASHOK N. SRIVASTAVA. "PREDICTING CONDITIONAL PROBABILITY DISTRIBUTIONS: A CONNECTIONIST APPROACH." International Journal of Neural Systems 06, no. 02 (June 1995): 109–18. http://dx.doi.org/10.1142/s0129065795000093.
Full textAbstract:
Most traditional prediction techniques deliver a single point, usually the mean of a probability distribution. For multimodal processes, instead of predicting the mean, it is important to predict the full distribution. This article presents a new connectionist method to predict the conditional probability distribution in response to an input. The main idea is to transform the problem from a regression problem to a classification problem. The conditional probability distribution network can perform both direct predictions and iterated predictions, the latter task being specific for time series problems. We compare this new method to fuzzy logic and discuss important differences, and also demonstrate the architecture on two time series. The first is the benchmark laser series used in the Santa Fe competition, a deterministic chaotic system. The second is a time series from a Markov process which exhibits structure on two time scales. The network produces multimodal predictions for this series. We compare the predictions of the network with a nearest-neighbor predictor and find that the conditional probability network is more than twice as likely a model.
12
Kombo, Omar Haji, Santhi Kumaran, Yahya H. Sheikh, Alastair Bovim, and Kayalvizhi Jayavel. "Long-Term Groundwater Level Prediction Model Based on Hybrid KNN-RF Technique." Hydrology 7, no. 3 (August 18, 2020): 59. http://dx.doi.org/10.3390/hydrology7030059.
Full textAbstract:
Reliable seasonal prediction of groundwater levels is not always possible when the quality and the amount of available on-site groundwater data are limited. In the present work, a hybrid K-Nearest Neighbor-Random Forest (KNN-RF) is used for the prediction of variations in groundwater levels (L) of an aquifer with the groundwater relatively close to the surface (<10 m) is proposed. First, the time-series smoothing methods are applied to improve the quality of groundwater data. Then, the ensemble K-Nearest Neighbor-Random Forest (KNN-RF) model is treated using hydro-climatic data for the prediction of variations in the levels of the groundwater tables up to three months ahead. Climatic and groundwater data collected from eastern Rwanda were used for validation of the model on a rolling window basis. Potential predictors were: the observed daily mean temperature (T), precipitation (P), and daily maximum solar radiation (S). Previous day’s precipitation P (t − 1), solar radiation S (t), temperature T (t), and groundwater level L (t) showed the highest variation in the fluctuations of the groundwater tables. The KNN-RF model presents its results in an intelligible manner. Experimental results have confirmed the high performance of the proposed model in terms of root mean square error (RMSE), mean absolute error (MAE), Nash–Sutcliffe (NSE), and coefficient of determination (R2).
13
Tang, Li, Heping Pan, and Yiyong Yao. "PANK-A financial time series prediction model integrating principal component analysis, affinity propagation clustering and nested k-nearest neighbor regression." Journal of Interdisciplinary Mathematics 21, no. 3 (March 27, 2018): 717–28. http://dx.doi.org/10.1080/09720502.2018.1456825.
Full text
14
Anh, Duong Tuan, and Ta Ngoc Huy Nam. "Chaotic time series prediction with deep belief networks: an empirical evaluation." Science & Technology Development Journal - Engineering and Technology 3, SI1 (December 4, 2020): SI102—SI112. http://dx.doi.org/10.32508/stdjet.v3isi1.571.
Full textAbstract:
Chaotic time series are widespread in several real world areas such as finance, environment, meteorology, traffic flow, weather. A chaotic time series is considered as generated from the deterministic dynamics of a nonlinear system. The chaotic system is sensitive to initial conditions; points that are arbitrarily close initially become exponentially further apart with progressing time. Therefore, it is challenging to make accurate prediction in chaotic time series. The prediction using conventional statistical techniques, k-nearest-nearest neighbors algorithm, Multi-Layer-Perceptron (MPL) neural networks, Recurrent Neural Networks, Radial-Basis-Function (RBF) Networks and Support Vector Machines, do not give reliable prediction results for chaotic time series. In this paper, we investigate the use of a deep learning method, Deep Belief Network (DBN), combined with chaos theory to forecast chaotic time series. DBN should be used to forecast chaotic time series. First, the chaotic time series are analyzed by calculating the largest Lyapunov exponent, reconstructing the time series by phase-space reconstruction and determining the best embedding dimension and the best delay time. When the forecasting model is constructed, the deep belief network is used to feature learning and the neural network is used for prediction. We also compare the DBN –based method to RBF network-based method, which is the state-of-the-art method for forecasting chaotic time series. The predictive performance of the two models is examined using mean absolute error (MAE), mean squared error (MSE) and mean absolute percentage error (MAPE). Experimental results on several synthetic and real world chaotic datasets revealed that the DBN model is applicable to the prediction of chaotic time series since it achieves better performance than RBF network.
15
Akbari, Mahmood, and Abbas Afshar. "Similarity-based error prediction approach for real-time inflow forecasting." Hydrology Research 45, no. 4-5 (November 5, 2013): 589–602. http://dx.doi.org/10.2166/nh.2013.098.
Full textAbstract:
Regardless of extensive researches on hydrologic forecasting models, the issue of updating the outputs from forecasting models has remained a main challenge. Most of the existing output updating methods are mainly based on the presence of persistence in the errors. This paper presents an alternative approach to updating the outputs from forecasting models in order to produce more accurate forecast results. The approach uses the concept of the similarity in errors for error prediction. The K nearest neighbor (KNN) algorithm is employed as a similarity-based error prediction model and improvements are made by new data, and two other forms of the KNN are developed in this study. The KNN models are applied for the error prediction of flow forecasting models in two catchments and the updated flows are compared to those of persistence-based methods such as autoregressive (AR) and artificial neural network (ANN) models. The results show that the similarity-based error prediction models can be recognized as an efficient alternative for real-time inflow forecasting, especially where the persistence in the error series of flow forecasting model is relatively low.
16
Jackson, Rhydon, Debra Knisley, Cecilia McIntosh, and Phillip Pfeiffer. "Predicting Flavonoid UGT Regioselectivity." Advances in Bioinformatics 2011 (June 30, 2011): 1–15. http://dx.doi.org/10.1155/2011/506583.
Full textAbstract:
Machine learning was applied to a challenging and biologically significant protein classification problem: the prediction of avonoid UGT acceptor regioselectivity from primary sequence. Novel indices characterizing graphical models of residues were proposed and found to be widely distributed among existing amino acid indices and to cluster residues appropriately. UGT subsequences biochemically linked to regioselectivity were modeled as sets of index sequences. Several learning techniques incorporating these UGT models were compared with classifications based on standard sequence alignment scores. These techniques included an application of time series distance functions to protein classification. Time series distances defined on the index sequences were used in nearest neighbor and support vector machine classifiers. Additionally, Bayesian neural network classifiers were applied to the index sequences. The experiments identified improvements over the nearest neighbor and support vector machine classifications relying on standard alignment similarity scores, as well as strong correlations between specific subsequences and regioselectivities.
17
Majidpour, Mostafa, Hamidreza Nazaripouya, Peter Chu, Hemanshu Pota, and Rajit Gadh. "Fast Univariate Time Series Prediction of Solar Power for Real-Time Control of Energy Storage System." Forecasting 1, no. 1 (September 17, 2018): 107–20. http://dx.doi.org/10.3390/forecast1010008.
Full textAbstract:
In this paper, super-short-term prediction of solar power generation for applications in dynamic control of energy system has been investigated. In order to follow and satisfy the dynamics of the controller, the deployed prediction method should have a fast response time. To this end, this paper proposes fast prediction methods to provide the control system with one step ahead of solar power generation. The proposed methods are based on univariate time series prediction. That is, instead of using external data such as the weather forecast as the input of prediction algorithms, they solely rely on past values of solar power data, hence lowering the volume and acquisition time of input data. In addition, the selected algorithms are able to generate the forecast output in less than a second. The proposed methods in this paper are grounded on four well-known prediction algorithms including Autoregressive Integrated Moving Average (ARIMA), K-Nearest Neighbors (kNN), Support Vector Regression (SVR), and Random Forest (RF). The speed and accuracy of the proposed algorithms have been compared based on two different error measures, Mean Absolute Error (MAE) and Symmetric Mean Absolute Percentage Error (SMAPE). Real world data collected from the PV installation at the University of California, Riverside (UCR) are used for prediction purposes. The results show that kNN and RF have better predicting performance with respect to SMAPE and MAE criteria.
18
Hopfinger, Melissa C., Charles C. Kirkpatrick, and Brent M. Znosko. "Predictions and analyses of RNA nearest neighbor parameters for modified nucleotides." Nucleic Acids Research 48, no. 16 (August 18, 2020): 8901–13. http://dx.doi.org/10.1093/nar/gkaa654.
Full textAbstract:
Abstract The most popular RNA secondary structure prediction programs utilize free energy (ΔG°37) minimization and rely upon thermodynamic parameters from the nearest neighbor (NN) model. Experimental parameters are derived from a series of optical melting experiments; however, acquiring enough melt data to derive accurate NN parameters with modified base pairs is expensive and time consuming. Given the multitude of known natural modifications and the continuing use and development of unnatural nucleotides, experimentally characterizing all modified NNs is impractical. This dilemma necessitates a computational model that can predict NN thermodynamics where experimental data is scarce or absent. Here, we present a combined molecular dynamics/quantum mechanics protocol that accurately predicts experimental NN ΔG°37 parameters for modified nucleotides with neighboring Watson–Crick base pairs. NN predictions for Watson-Crick and modified base pairs yielded an overall RMSD of 0.32 kcal/mol when compared with experimentally derived parameters. NN predictions involving modified bases without experimental parameters (N6-methyladenosine, 2-aminopurineriboside, and 5-methylcytidine) demonstrated promising agreement with available experimental melt data. This procedure not only yields accurate NN ΔG°37 predictions but also quantifies stacking and hydrogen bonding differences between modified NNs and their canonical counterparts, allowing investigators to identify energetic differences and providing insight into sources of (de)stabilization from nucleotide modifications.
19
Nguyen, Thi Hao, Anda Ionescu, Olivier Ramalho, and Evelyne Géhin. "Predicting the Window Opening State in an Office to Improve Indoor Air Quality." Engineering Proceedings 5, no. 1 (June 28, 2021): 24. http://dx.doi.org/10.3390/engproc2021005024.
Full textAbstract:
Window operation is among one of the most influential factors on indoor air quality (IAQ). In this paper, we focus on the modeling of the windows’ opening state in a real open-plan office with five windows. The IAQ of this open-plan office was monitored over a whole year along with the opening state of the windows. A k-Nearest Neighbor (k-NN) classification model was implemented, based on a long time series of both indoor and outdoor monitored environmental factors such as temperature and relative humidity, and CO2 indoor concentration. In addition, the month, the day of the week and the time of the day were included. The obtained model for the window state prediction performs well with an accuracy of 92% for the training set and 86% for the testing set.
20
Ryu, Seungyo, Dongseung Kim, and Joongheon Kim. "Weather-Aware Long-Range Traffic Forecast Using Multi-Module Deep Neural Network." Applied Sciences 10, no. 6 (March 12, 2020): 1938. http://dx.doi.org/10.3390/app10061938.
Full textAbstract:
This study proposes a novel multi-module deep neural network framework which aims at improving intelligent long-term traffic forecasting. Following our previous system, the internal architecture of the new system adds deep learning modules that enable data separation during computation. Thus, prediction becomes more accurate in many sections of the road network and gives dependable results even under possible changes in weather conditions during driving. The performance of the framework is then evaluated for different cases, which include all plausible cases of driving, i.e., regular days, holidays, and days involving severe weather conditions. Compared with other traffic predicting systems that employ the convolutional neural networks, k-nearest neighbor algorithm, and the time series model, it is concluded that the system proposed herein achieves better performance and helps drivers schedule their trips well in advance.
21
BRANDT, MICHAEL E., AHMET ADEMOĞLU, and WALTER S. PRITCHARD. "NONLINEAR PREDICTION AND COMPLEXITY OF ALPHA EEG ACTIVITY." International Journal of Bifurcation and Chaos 10, no. 01 (January 2000): 123–33. http://dx.doi.org/10.1142/s0218127400000074.
Full textAbstract:
Two prediction techniques were used to investigate the dynamical complexity of the alpha EEG; a nonlinear method using the K-nearest-neighbor local linear (KNNLL) approximation, and one based on global linear autoregressive (AR) modeling. Generally, KNNLL has more ability to predict nonlinearity in a chaotic time series under moderately noisy conditions as demonstrated by using increasingly noisy realizations of the Hénon (a low-dimensional chaotic) and Mackey–Glass (a high-dimensional chaotic) maps. However, at higher noise levels KNNLL performs no better than AR prediction. For linear stochastic time series, such as a sine wave with added Gaussian noise, prediction using KNNLL is no better than AR even at very low signal-to-noise ratios. Both prediction techniques were applied to resting EEGs (O2 scalp recording site, 10–20 EEG system) from ten normal adult subjects under eyes-closed and eyes-open conditions. In all recordings tested, KNNLL did not yield a lower root mean squared error (RMSE) than AR prediction. This result more closely resembles that obtained for noisy sine waves as opposed to chaotic time series with added noise. This lends further support to the notion that these EEG signals are linear-stochastic in nature. However, the possibility that some EEG signals, particularly those with high prediction errors produced by a noisy nonlinear system cannot be ruled out in this study.
22
Qu, Licheng, Minghao Zhang, Zhaolu Li, and Wei Li. "Temporal Backtracking and Multistep Delay of Traffic Speed Series Prediction." Journal of Advanced Transportation 2020 (December 11, 2020): 1–13. http://dx.doi.org/10.1155/2020/8899478.
Full textAbstract:
As a typical time series, the length of the data sequence is critical to the accuracy of traffic state prediction. In order to fully explore the causality between traffic data, this study established a temporal backtracking and multistep delay model based on recurrent neural networks (RNNs) to learn and extract the long- and short-term dependencies of the traffic state data. With a real traffic data set, the coordinate descent algorithm was employed to search and determine the optimal backtracking length of traffic sequence, and multistep delay predictions were performed to demonstrate the relationship between delay steps and prediction accuracies. Besides, the performances were compared between three variants of RNNs (LSTM, GRU, and BiLSTM) and 6 frequently used models, which are decision tree (DT), support vector machine (SVM), k-nearest neighbour (KNN), random forest (RF), gradient boosting decision tree (GBDT), and stacked autoencoder (SAE). The prediction results of 10 consecutive delay steps suggest that the accuracies of RNNs are far superior to those of other models because of the more powerful and accurate pattern representing ability in time series. It is also proved that RNNs can learn and mine longer time dependencies.
23
Song, Donghwan, Adrian Matias Chung Baek, Jageon Koo, Moise Busogi, and Namhun Kim. "Forecasting Warping Deformation Using Multivariate Thermal Time Series and K-Nearest Neighbors in Fused Deposition Modeling." Applied Sciences 10, no. 24 (December 15, 2020): 8951. http://dx.doi.org/10.3390/app10248951.
Full textAbstract:
Over the past decades, additive manufacturing has rapidly advanced due to its advantages in enabling diverse material usage and complex design production. Nevertheless, the technology has limitations in terms of quality, as printed products are sometimes different from their desired designs or are inconsistent due to defects. Warping deformation, a defect involving layer shrinkage induced by the thermal residual stress generated during manufacturing processes, is a major factor in lowering the quality and raising the cost of printed products. This study utilized a variety of thermal time series data and the K-nearest neighbors (KNN) algorithm with dynamic time warping (DTW) to detect and predict the warping deformation in the printed parts using fused deposition modeling (FDM) printers. Multivariate thermal time series data extracted from thermocouples were trained using DTW-based KNN to classify warping deformation. The results showed that the proposed approach can predict warping deformation with an accuracy of over 80% by only using thermal time series data corresponding to 20% of the whole printing process. Additionally, the classification accuracy exhibited the promising potential of the proposed approach in warping prediction and in actual manufacturing processes, so the additional time and cost resulting from defective processes can be reduced.
24
Almanjahie, Ibrahim M., Zoulikha Kaid, Ali Laksaci, and Mustapha Rachdi. "Predicting temperature curve based on fast kNN local linear estimation of the conditional distribution function." PeerJ 9 (July 9, 2021): e11719. http://dx.doi.org/10.7717/peerj.11719.
Full textAbstract:
Predicting the yearly curve of the temperature, based on meteorological data, is essential for understanding the impact of climate change on humans and the environment. The standard statistical models based on the big data discretization in the finite grid suffer from certain drawbacks such as dimensionality when the size of the data is large. We consider, in this paper, the predictive region problem in functional time series analysis. We study the prediction by the shortest conditional modal interval constructed by the local linear estimation of the cumulative function of $Y$ given functional input variable $X$. More precisely, we combine the $k$-Nearest Neighbors procedure to the local linear algorithm to construct two estimators of the conditional distribution function. The main purpose of this paper is to compare, by a simulation study, the efficiency of the two estimators concerning the level of dependence. The feasibility of these estimators in the functional times series prediction is examined at the end of this paper. More precisely, we compare the shortest conditional modal interval predictive regions of both estimators using real meteorological data.
25
AUSSEM, ALEX, FIONN MURTAGH, and MARC SARAZIN. "DYNAMICAL RECURRENT NEURAL NETWORKS — TOWARDS ENVIRONMENTAL TIME SERIES PREDICTION." International Journal of Neural Systems 06, no. 02 (June 1995): 145–70. http://dx.doi.org/10.1142/s0129065795000123.
Full textAbstract:
Dynamical Recurrent Neural Networks (DRNN) (Aussem 1995a) are a class of fully recurrent networks obtained by modeling synapses as autoregressive filters. By virtue of their internal dynamic, these networks approximate the underlying law governing the time series by a system of nonlinear difference equations of internal variables. They therefore provide history-sensitive forecasts without having to be explicitly fed with external memory. The model is trained by a local and recursive error propagation algorithm called temporal-recurrent-backpropagation. The efficiency of the procedure benefits from the exponential decay of the gradient terms backpropagated through the adjoint network. We assess the predictive ability of the DRNN model with meteorological and astronomical time series recorded around the candidate observation sites for the future VLT telescope. The hope is that reliable environmental forecasts provided with the model will allow the modern telescopes to be preset, a few hours in advance, in the most suited instrumental mode. In this perspective, the model is first appraised on precipitation measurements with traditional nonlinear AR and ARMA techniques using feedforward networks. Then we tackle a complex problem, namely the prediction of astronomical seeing, known to be a very erratic time series. A fuzzy coding approach is used to reduce the complexity of the underlying laws governing the seeing. Then, a fuzzy correspondence analysis is carried out to explore the internal relationships in the data. Based on a carefully selected set of meteorological variables at the same time-point, a nonlinear multiple regression, termed nowcasting (Murtagh et al. 1993, 1995), is carried out on the fuzzily coded seeing records. The DRNN is shown to outperform the fuzzy k-nearest neighbors method.
26
Hasan, Md Kamrul, Md Asif Ahamed, Mohiuddin Ahmad, and M. A. Rashid. "Prediction of Epileptic Seizure by Analysing Time Series EEG Signal Using k-NN Classifier." Applied Bionics and Biomechanics 2017 (2017): 1–12. http://dx.doi.org/10.1155/2017/6848014.
Full textAbstract:
Electroencephalographic signal is a representative signal that contains information about brain activity, which is used for the detection of epilepsy since epileptic seizures are caused by a disturbance in the electrophysiological activity of the brain. The prediction of epileptic seizure usually requires a detailed and experienced analysis of EEG. In this paper, we have introduced a statistical analysis of EEG signal that is capable of recognizing epileptic seizure with a high degree of accuracy and helps to provide automatic detection of epileptic seizure for different ages of epilepsy. To accomplish the target research, we extract various epileptic features namely approximate entropy (ApEn), standard deviation (SD), standard error (SE), modified mean absolute value (MMAV), roll-off (R), and zero crossing (ZC) from the epileptic signal. The k-nearest neighbours (k-NN) algorithm is used for the classification of epilepsy then regression analysis is used for the prediction of the epilepsy level at different ages of the patients. Using the statistical parameters and regression analysis, a prototype mathematical model is proposed which helps to find the epileptic randomness with respect to the age of different subjects. The accuracy of this prototype equation depends on proper analysis of the dynamic information from the epileptic EEG.
27
Iswanto, Yuliana Melita Pranoto, and Reddy Alexandro Harianto. "APPLYING THE CLASSIFICATION ALGORITHM FOR THE SYSTEM RECOMMENDATIONS BUY SELL IN FOREX TRADING." JURNAL FASILKOM 10, no. 2 (August 13, 2020): 152–58. http://dx.doi.org/10.37859/jf.v10i2.2076.
Full textAbstract:
Abstract- Having a sophisticated application, even though often experience problems in deciding BUY - SELL in trading forex trading. This is due to the often time series predictions, in the high variable experiencing high values as well as low variables, for that it is needed a recommendation system to overcome this problem.
The application of classification algorithms to the recommendation system in support of BUY-SELL decisions is one appropriate alternative to overcome this. K-Nearest Neighbor (K-NN) algorithm was chosen because the K-NN method is an algorithm that can be used in building a recommendation system that can classify data based on the closest distance. This system is designed to assist traders in making BUY-SELL decisions, based on predictive data.
The results of the recommendation system from the ten trials predicted by Arima are recommended. When compared to the price in the field the target profit is 7% per week from ten experiments if the average profit has exceeded the target
28
Liong, S. Y., K. K. Phoon, M. F. K. Pasha, and C. D. Doan. "Efficient implementation of inverse approach for forecasting hydrological time series using micro GA." Journal of Hydroinformatics 7, no. 3 (July 1, 2005): 151–63. http://dx.doi.org/10.2166/hydro.2005.0013.
Full textAbstract:
This paper implements the inverse approach for forecasting hydrological time series in an efficient way using a micro-GA (mGA) search engine. The inverse approach is based on chaos theory and it involves: (1) calibrating the delay time ((), embedding dimension (m) and number of nearest neighbors (k) simultaneously using a single definite criterion, namely optimum prediction accuracy, (2) verifying that the optimal parameters have wider applicability outside the scope of calibration, and (3) demonstrating that chaotic behaviour is present when optimal parameters are used in conjunction with existing system characterization tools. The first stage is conducted efficiently by coupling the Nonlinear Prediction (NLP) method with mGA using a lookup facility to eliminate costly duplicate NLP evaluations. The mGA-NLP algorithm is applied to a theoretical chaotic time series (Mackey–Glass) and a real hydrological time series (Mississippi river flow at Vicksburg) to examine its efficiency. Results show that: (1) mGA is capable of producing comparable or superior triplets using only up to 5% of the computational effort of all possible points in the search space, (2) the lookup facility is very cost-effective because only about 50% of the triplets generated by mGA are distinct, (3) mGA seems to produce more robust solutions in the sense that the record length required to achieve a stable optimum triplet is much shorter, and (4) the prediction accuracy is not sensitive to the parameter k. It is sufficient to use k = 10 in future studies. In this way, the 3D search space could be reduced to a much smaller 2D search space of m and τ.
29
Liu, Moyang, Yingchun Huang, Zhijia Li, Bingxing Tong, Zhentao Liu, Mingkun Sun, Feiqing Jiang, and Hanchen Zhang. "The Applicability of LSTM-KNN Model for Real-Time Flood Forecasting in Different Climate Zones in China." Water 12, no. 2 (February 6, 2020): 440. http://dx.doi.org/10.3390/w12020440.
Full textAbstract:
Flow forecasting is an essential topic for flood prevention and mitigation. This study utilizes a data-driven approach, the Long Short-Term Memory neural network (LSTM), to simulate rainfall–runoff relationships for catchments with different climate conditions. The LSTM method presented was tested in three catchments with distinct climate zones in China. The recurrent neural network (RNN) was adopted for comparison to verify the superiority of the LSTM model in terms of time series prediction problems. The results of LSTM were also compared with a widely used process-based model, the Xinanjiang model (XAJ), as a benchmark to test the applicability of this novel method. The results suggest that LSTM could provide comparable quality predictions as the XAJ model and can be considered an efficient hydrology modeling approach. A real-time forecasting approach coupled with the k-nearest neighbor (KNN) algorithm as an updating method was proposed in this study to generalize the plausibility of the LSTM method for flood forecasting in a decision support system. We compared the simulation results of the LSTM and the LSTM-KNN model, which demonstrated the effectiveness of the LSTM-KNN model in the study areas and underscored the potential of the proposed model for real-time flood forecasting.
30
Sikora, Marek, and Beata Sikora. "Improving prediction models applied in systems monitoring natural hazards and machinery." International Journal of Applied Mathematics and Computer Science 22, no. 2 (June 1, 2012): 477–91. http://dx.doi.org/10.2478/v10006-012-0036-3.
Full textAbstract:
Improving prediction models applied in systems monitoring natural hazards and machineryA method of combining three analytic techniques including regression rule induction, thek-nearest neighbors method and time series forecasting by means of the ARIMA methodology is presented. A decrease in the forecasting error while solving problems that concern natural hazards and machinery monitoring in coal mines was the main objective of the combined application of these techniques. The M5 algorithm was applied as a basic method of developing prediction models. In spite of an intensive development of regression rule induction algorithms and fuzzy-neural systems, the M5 algorithm is still characterized by the generalization ability and unbeatable time of data model creation competitive with other systems. In the paper, two solutions designed to decrease the mean square error of the obtained rules are presented. One consists in introducing into a set of conditional variables the so-called meta-variable (an analogy to constructive induction) whose values are determined by an autoregressive or the ARIMA model. The other shows that limitation of a data set on which the M5 algorithm operates by thek-nearest neighbor method can also lead to error decreasing. Moreover, three application examples of the presented solutions for data collected by systems of natural hazards and machinery monitoring in coal mines are described. In Appendix, results of several benchmark data sets analyses are given as a supplement of the presented results.
31
Feng, Bin, Jianmin Xu, Yonggang Zhang, and Yongjie Lin. "Multi-Step Traffic Speed Prediction Based on Ensemble Learning on an Urban Road Network." Applied Sciences 11, no. 10 (May 13, 2021): 4423. http://dx.doi.org/10.3390/app11104423.
Full textAbstract:
Short-term traffic speed prediction plays an important role in the field of Intelligent Transportation Systems (ITS). Usually, traffic speed forecasting can be divided into single-step-ahead and multi-step-ahead. Compared with the single-step method, multi-step prediction can provide more future traffic condition to road traffic participants for guidance decision-making. This paper proposes a multi-step traffic speed forecasting by using ensemble learning model with traffic speed detrending algorithm. Firstly, the correlation analysis is conducted to determine the representative features by considering the spatial and temporal characteristics of traffic speed. Then, the traffic speed time series is split into a trend set and a residual set via a detrending algorithm. Thirdly, a multi-step residual prediction with direct strategy is formulated by the ensemble learning model of stacking integrating support vector machine (SVM), CATBOOST, and K-nearest neighbor (KNN). Finally, the forecasting traffic speed can be reached by adding predicted residual part to the trend one. In tests that used field data from Zhongshan, China, the experimental results indicate that the proposed model outperforms the benchmark ones like SVM, CATBOOST, KNN, and BAGGING.
32
Cen, Yi, Mingliu Liu, Deshi Li, Kaitao Meng, and Huihui Xu. "Double-Scale Adaptive Transmission in Time-Varying Channel for Underwater Acoustic Sensor Networks." Sensors 21, no. 6 (March 23, 2021): 2252. http://dx.doi.org/10.3390/s21062252.
Full textAbstract:
The communication channel in underwater acoustic sensor networks (UASNs) is time-varying due to the dynamic environmental factors, such as ocean current, wind speed, and temperature profile. Generally, these phenomena occur with a certain regularity, resulting in a similar variation pattern inherited in the communication channels. Based on these observations, the energy efficiency of data transmission can be improved by controlling the modulation method, coding rate, and transmission power according to the channel dynamics. Given the limited computational capacity and energy in underwater nodes, we propose a double-scale adaptive transmission mechanism for the UASNs, where the transmission configuration will be determined by the predicted channel states adaptively. In particular, the historical channel state series will first be decomposed into large-scale and small-scale series and then be predicted by a novel k-nearest neighbor search algorithm with sliding window. Next, an energy-efficient transmission algorithm is designed to solve the problem of long-term modulation and coding optimization. In particular, a quantitative model is constructed to describe the relationship between data transmission and the buffer threshold used in this mechanism, which can then analyze the influence of buffer threshold under different channel states or data arrival rates theoretically. Finally, numerical simulations are conducted to verify the proposed schemes, and results show that they can achieve good performance in terms of channel prediction and energy consumption with moderate buffer length.
33
Qu, K. Z., H. Li, J. D. Whetstone, A. D. Sferruzza, and R. A. Bender. "Molecular identification of carcinoma of unknown primary (CUP) with gene expression profiling." Journal of Clinical Oncology 25, no. 18_suppl (June 20, 2007): 21024. http://dx.doi.org/10.1200/jco.2007.25.18_suppl.21024.
Full textAbstract:
21024 Background: We previously reported a method for determining the site of tumor origin for CUP by comparing a 92- gene expression profile to that in a database created from 600 primary and metastatic tumor bank specimens of known origin. K-nearest neighbor analysis was used to determine the likelihood of an unknown patient specimen originating from a particular site with the likelihood assigned as a confidence level and reported as high, medium, low, or unclassified. Herein, we report the analysis of the gene expression profiling results from our initial series of clinical CUP specimens. Methods: We reviewed the results of 76 consecutive de-identified patient samples submitted to our laboratory for routine CUP testing. RNA was extracted from the formalin-fixed, paraffin-embedded (FFPE) tissue blocks and cDNA products used in a semi-quantitative real-time PCR to detect 87 tumor-associated genes and 5 reference genes. Gene expression data were then compared with our database and k-nearest neighbor analysis used to identify the 5 closest neighbors. If all 5 or 4/5 were the same, the result was classified as “high likelihood”, 3/5 = “moderate likelihood”, 2/5 = “low likelihood” and none matching was “unclassifiable”. Results: For the 76 clinical CUP samples tested, gene profiling analysis yielded high-likelihood predictions for 34 (45%), moderate for 12 (16%), low for 12 (16%), and unclassified for 14 (18%); amplification was inadequate for 4 (5%) samples. Overall, gene profiling analysis yielded classifiable predictions in 58 (76%) of clinical CUP samples. An occult carcinoid, metastatic melanoma and adenocarcinoma of the endocervix were identified and then found clinically using this assay. Conclusions: Our previous findings indicate that gene expression profiling can correctly identify the site of tumor origin in a high percentage of tumor bank samples. Data from the present study suggests that this approach can identify a primary site of tumor origin in 76% of actual clinical specimens from pathologist-submitted CUP cases. No significant financial relationships to disclose.
34
Dawkins, Bryan A., Trang T. Le, and Brett A. McKinney. "Theoretical properties of distance distributions and novel metrics for nearest-neighbor feature selection." PLOS ONE 16, no. 2 (February 8, 2021): e0246761. http://dx.doi.org/10.1371/journal.pone.0246761.
Full textAbstract:
The performance of nearest-neighbor feature selection and prediction methods depends on the metric for computing neighborhoods and the distribution properties of the underlying data. Recent work to improve nearest-neighbor feature selection algorithms has focused on new neighborhood estimation methods and distance metrics. However, little attention has been given to the distributional properties of pairwise distances as a function of the metric or data type. Thus, we derive general analytical expressions for the mean and variance of pairwise distances for Lq metrics for normal and uniform random data with p attributes and m instances. The distribution moment formulas and detailed derivations provide a resource for understanding the distance properties for metrics and data types commonly used with nearest-neighbor methods, and the derivations provide the starting point for the following novel results. We use extreme value theory to derive the mean and variance for metrics that are normalized by the range of each attribute (difference of max and min). We derive analytical formulas for a new metric for genetic variants, which are categorical variables that occur in genome-wide association studies (GWAS). The genetic distance distributions account for minor allele frequency and the transition/transversion ratio. We introduce a new metric for resting-state functional MRI data (rs-fMRI) and derive its distance distribution properties. This metric is applicable to correlation-based predictors derived from time-series data. The analytical means and variances are in strong agreement with simulation results. We also use simulations to explore the sensitivity of the expected means and variances in the presence of correlation and interactions in the data. These analytical results and new metrics can be used to inform the optimization of nearest neighbor methods for a broad range of studies, including gene expression, GWAS, and fMRI data.
35
Hall, Timothy J., Carl N. Mutchler, Greg J. Bloy, Rachel N. Thessin, Stephanie K. Gaffney, and Jonathan J. Lareau. "Performance of Observation-Based Prediction Algorithms for Very Short-Range, Probabilistic Clear-Sky Condition Forecasting." Journal of Applied Meteorology and Climatology 50, no. 1 (January 1, 2011): 3–19. http://dx.doi.org/10.1175/2010jamc2529.1.
Full textAbstract:
Abstract Very short-range sky condition forecasts are produced to support a variety of military, civil, and commercial activities. In this investigation, six advanced, observation (obs)-based prediction algorithms were developed and tested that generated probabilistic sky condition forecasts for 1-, 2-, 3-, 4-, and 5-h forecast intervals, for local and regional target types, in six geographic regions within the continental United States. Three of the methods were based on predictive learning algorithms including neural network, random forest, and regression tree. The other three methods were statistical techniques including a k–nearest neighbor algorithm, a classifier based on the Bayes decision rule, and a multialgorithm ensemble. The performances of these six algorithms were compared with forecasts from three benchmark methods: basic persistence, the climatological-expectancy-of-persistence, and satellite cloud climatology. The obs database for each forecast target was composed of a multiyear, half-hourly time series of atmospheric parameters that included cloud features extracted from weather satellite imagery and meteorological variables extracted or derived from data assimilation–based model analyses generated by NCEP’s Eta Data Assimilation System. The performances of the advanced prediction algorithms exceeded those of the benchmarks at all five forecast intervals for both target types in all regions, on the basis of a group of metrics that included receiver operating characteristic score, sharpness, accuracy, expected best cost, and reliability.
36
Syafaah, Lailis, Setio Basuki, Fauzi Dwi Setiawan Sumadi, Amrul Faruq, and Mauridhi Hery Purnomo. "Diabetes prediction based on discrete and continuous mean amplitude of glycemic excursions using machine learning." Bulletin of Electrical Engineering and Informatics 9, no. 6 (August 1, 2020): 2619–29. http://dx.doi.org/10.11591/eei.v9i6.2387.
Full textAbstract:
Chronic hyperglycemia and acute glucose fluctuations are the two main factors that trigger complications in diabetes mellitus (DM). Continuous and sustainable observation of these factors is significant to be done to reduce the potential of cardiovascular problems in the future by minimizing the occurrence of glycemic variability (GV). At present, observations on GV are based on the mean amplitude of glycemic excursion (MAGE), which is measured based on continuous blood glucose data from patients using particular devices. This study aims to calculate the value of MAGE based on discrete blood glucose observations from 43 volunteer patients to predict the diabetes status of patients. Experiments were carried out by calculating MAGE values from original discrete data and continuous data obtained using Spline Interpolation. This study utilizes the machine learning algorithm, especially k-Nearest Neighbor with dynamic time wrapping (DTW) to measure the distance between time series data. From the classification test, discrete data and continuous data from the interpolation results show precisely the same accuracy value that is equal to 92.85%. Furthermore, there are variations in the MAGE value for each patient where the diabetes class has the most significant difference, followed by the pre-diabetes class, and the typical class.
37
Alizadeh, Zahra, Jafar Yazdi, Joong Kim, and Abobakr Al-Shamiri. "Assessment of Machine Learning Techniques for Monthly Flow Prediction." Water 10, no. 11 (November 17, 2018): 1676. http://dx.doi.org/10.3390/w10111676.
Full textAbstract:
Monthly flow predictions provide an essential basis for efficient decision-making regarding water resource allocation. In this paper, the performance of different popular data-driven models for monthly flow prediction is assessed to detect the appropriate model. The considered methods include feedforward neural networks (FFNNs), time delay neural networks (TDNNs), radial basis neural networks (RBFNNs), recurrent neural network (RNN), a grasshopper optimization algorithm (GOA)-based support vector machine (SVM) and K-nearest neighbors (KNN) model. For this purpose, the performance of each model is evaluated in terms of several residual metrics using a monthly flow time series for two real case studies with different flow regimes. The results show that the KNN outperforms the different neural network configurations for the first case study, whereas RBFNN model has better performance for the second case study in terms of the correlation coefficient. According to the accuracy of the results, in the first case study with more input features, the KNN model is recommended for short-term predictions and for the second case with a smaller number of input features, but more training observations, the RBFNN model is suitable.
38
Nguyen, Trung, Simon Jones, Mariela Soto-Berelov, Andrew Haywood, and Samuel Hislop. "A Comparison of Imputation Approaches for Estimating Forest Biomass Using Landsat Time-Series and Inventory Data." Remote Sensing 10, no. 11 (November 17, 2018): 1825. http://dx.doi.org/10.3390/rs10111825.
Full textAbstract:
The prediction of forest biomass at the landscape scale can be achieved by integrating data from field plots with satellite imagery, in particular data from the Landsat archive, using k-nearest neighbour (kNN) imputation models. While studies have demonstrated different kNN imputation approaches for estimating forest biomass from remote sensing data and forest inventory plots, there is no general agreement on which approach is most appropriate for biomass estimation across large areas. In this study, we compared several imputation approaches for estimating forest biomass using Landsat time-series and inventory plot data. We evaluated 18 kNN models to impute three aboveground biomass (AGB) variables (total AGB, AGB of live trees and AGB of dead trees). These models were developed using different distance techniques (Random Forest or RF, Gradient Nearest Neighbour or GNN, and Most Similar Neighbour or MSN) and different combinations of response variables (model scenarios). Direct biomass imputation models were trained according to the biomass variables while indirect biomass imputation models were trained according to combinations of forest structure variables (e.g., basal area, stem density and stem volume of live and dead-standing trees). We also assessed the ability of our imputation method to spatially predict biomass variables across large areas in relation to a forest disturbance history over a 30-year period (1987–2016). Our results show that RF consistently outperformed MSN and GNN distance techniques across different model scenarios and biomass variables. The lowest error rates were achieved by RF-based models with generalized root mean squared difference (gRMSD, RMSE divided by the standard deviation of the observed values) ranging from 0.74 to 1.24. Whereas gRMSD associated with MSN-based and GNN-based models ranged from 0.92 to 1.36 and from 1.04 to 1.42, respectively. The indirect imputation method generally achieved better biomass predictions than the direct imputation method. In particular, the kNN model trained with the combination of basal area and stem density variables was the most robust for estimating forest biomass. This model reported a gRMSD of 0.89, 0.95 and 1.08 for total AGB, AGB of live trees and AGB of dead trees, respectively. In addition, spatial predictions of biomass showed relatively consistent trends with disturbance severity and time since disturbance across the time-series. As the kNN imputation method is increasingly being used by land managers and researchers to map forest biomass, this work helps those using these methods ensure their modelling and mapping practices are optimized.
39
Williams, Billy M., Priya K. Durvasula, and Donald E. Brown. "Urban Freeway Traffic Flow Prediction: Application of Seasonal Autoregressive Integrated Moving Average and Exponential Smoothing Models." Transportation Research Record: Journal of the Transportation Research Board 1644, no. 1 (January 1998): 132–41. http://dx.doi.org/10.3141/1644-14.
Full textAbstract:
The application of seasonal time series models to the single-interval traffic flow forecasting problem for urban freeways is addressed. Seasonal time series approaches have not been used in previous forecasting research. However, time series of traffic flow data are characterized by definite periodic cycles. Seasonal autoregressive integrated moving average (ARIMA) and Winters exponential smoothing models were developed and tested on data sets belonging to two sites: Telegraph Road and the Woodrow Wilson Bridge on the inner and outer loops of the Capital Beltway in northern Virginia. Data were 15-min flow rates and were the same as used in prior forecasting research by B. Smith. Direct comparisons with the Smith report findings were made and it was found that ARIMA (2, 0, 1)(0, 1, 1)96 and ARIMA (1, 0, 1)(0, 1, 1)96 were the best-fit models for the Telegraph Road and Wilson Bridge sites, respectively. Best-fit Winters exponential smoothing models were also developed for each site. The single-step forecasting results indicate that seasonal ARIMA models outperform the nearest-neighbor, neural network, and historical average models as reported by Smith.
40
Naghavi, Nader, Aaron Miller, and Eric Wade. "Towards Real-Time Prediction of Freezing of Gait in Patients With Parkinson’s Disease: Addressing the Class Imbalance Problem." Sensors 19, no. 18 (September 10, 2019): 3898. http://dx.doi.org/10.3390/s19183898.
Full textAbstract:
Freezing of gait (FoG) is a common motor symptom in patients with Parkinson’s disease (PD). FoG impairs gait initiation and walking and increases fall risk. Intelligent external cueing systems implementing FoG detection algorithms have been developed to help patients recover gait after freezing. However, predicting FoG before its occurrence enables preemptive cueing and may prevent FoG. Such prediction remains challenging given the relative infrequency of freezing compared to non-freezing events. In this study, we investigated the ability of individual and ensemble classifiers to predict FoG. We also studied the effect of the ADAptive SYNthetic (ADASYN) sampling algorithm and classification cost on classifier performance. Eighteen PD patients performed a series of daily walking tasks wearing accelerometers on their ankles, with nine experiencing FoG. The ensemble classifier formed by Support Vector Machines, K-Nearest Neighbors, and Multi-Layer Perceptron using bagging techniques demonstrated highest performance (F1 = 90.7) when synthetic FoG samples were added to the training set and class cost was set as twice that of normal gait. The model identified 97.4% of the events, with 66.7% being predicted. This study demonstrates our algorithm’s potential for accurate prediction of gait events and the provision of preventive cueing in spite of limited event frequency.
41
Chen, Yong, Peng Li, Huan Wang, Wenping Ren, and Min Cao. "Icing Load and Risk Forecasting for Power Transmission Line Based on Multi-scale Time Series Phase-Space Reconstruction and Regression." International Journal of Safety and Security Engineering 11, no. 1 (February 28, 2021): 79–90. http://dx.doi.org/10.18280/ijsse.110109.
Full textAbstract:
Accurately forecasting the icing load on overhead power transmission lines is an important issue to ensure the security and reliability of the power grid. A multi-scale time series phase-space reconstruction and regression model for icing load prediction is proposed in this paper to treat the non-stationary, nonlinear, and intermittent volatility of power line icing load data. Those is motivated by the traditional icing load prediction models having many disadvantages in the forecasting accuracy, as well as the casualness of the parameters selected. Firstly, the icing load data are decomposed into a multi-scale time series of intrinsic model function (IMF) components with stability by using the ensemble empirical mode decomposition (EEMD), which can reduce the interactions between different types of feature information. Secondly, phase-space reconstruction (PSR) theory is applied using the mutual information and the false nearest neighbor to determine the optimal delay time and embedding dimension of each IMF component. Thirdly, considering the characteristics of each IMF component, different kernel functions and optimization parameters are selected to establish the prediction model based support vector regression (SVR). Finally, according to the load prediction results, fuzzy reasoning method was used to determine the risk status of transmission line towers in this paper. Upon experimentally evaluating the validity of the model using related transmission lines of the Yunnan Power Grid, it is shown that this method could predict the real-time icing load on overhead power lines, obtaining better regression performance. This model could be used on power transmission and distribution systems for deicing and maintenance decisions.
42
YUYAMA, Aimi, Junya YAMASAKI, Daisuke MIZUNO, Tomohiro NAGATANI, Takeru MORIYAMA, Koki NISHIMURA, Shunji MAEDA, Masaya TAKAHASHI, Kazuhide TANAKA, and Yugo HOSHIHIRA. "Study of Learning Data Selection Method with K-nearest Neighbor and VAR Model in Wind Speed Prediction using Wind Speed Time-series Data of Multiple Sites by Support Vector Regression." Journal of the Japan Society for Precision Engineering 83, no. 10 (2017): 941–48. http://dx.doi.org/10.2493/jjspe.83.941.
Full text
43
Pan, Jie, Li-Ping Li, Chang-Qing Yu, Zhu-Hong You, Zhong-Hao Ren, and Jing-Yu Tang. "FWHT-RF: A Novel Computational Approach to Predict Plant Protein-Protein Interactions via an Ensemble Learning Method." Scientific Programming 2021 (July 22, 2021): 1–11. http://dx.doi.org/10.1155/2021/1607946.
Full textAbstract:
Protein-protein interactions (PPIs) in plants are crucial for understanding biological processes. Although high-throughput techniques produced valuable information to identify PPIs in plants, they are usually expensive, inefficient, and extremely time-consuming. Hence, there is an urgent need to develop novel computational methods to predict PPIs in plants. In this article, we proposed a novel approach to predict PPIs in plants only using the information of protein sequences. Specifically, plants’ protein sequences are first converted as position-specific scoring matrix (PSSM); then, the fast Walsh–Hadamard transform (FWHT) algorithm is used to extract feature vectors from PSSM to obtain evolutionary information of plant proteins. Lastly, the rotation forest (RF) classifier is trained for prediction and produced a series of evaluation results. In this work, we named this approach FWHT-RF because FWHT and RF are used for feature extraction and classification, respectively. When applying FWHT-RF on three plants’ PPI datasets Maize, Rice, and Arabidopsis thaliana (Arabidopsis), the average accuracies of FWHT-RF using 5-fold cross validation were achieved as high as 95.20%, 94.42%, and 83.85%, respectively. To further evaluate the predictive power of FWHT-RF, we compared it with the state-of-art support vector machine (SVM) and K-nearest neighbor (KNN) classifier in different aspects. The experimental results demonstrated that FWHT-RF can be a useful supplementary method to predict potential PPIs in plants.
44
Tomppo, Erkki, Oleg Antropov, and Jaan Praks. "Cropland Classification Using Sentinel-1 Time Series: Methodological Performance and Prediction Uncertainty Assessment." Remote Sensing 11, no. 21 (October 24, 2019): 2480. http://dx.doi.org/10.3390/rs11212480.
Full textAbstract:
Methods based on Sentinel-1 data were developed to monitor crops and fields to facilitate the distribution of subsidies. The objectives were to (1) develop a methodology to predict individual crop species or or management regimes; (2) investigate the earliest time point in the growing season when the species predictions are satisfactory; and (3) to present a method to assess the uncertainty of the predictions at an individual field level. Seventeen Sentinel-1 synthetic aperture radar (SAR) scenes (VV and VH polarizations) acquired in interferometric wide swath mode from 14 May through to 30 August 2017 in the same geometry, and selected based on the weather conditions, were used in the study. The improved k nearest neighbour estimation, ik-NN, with a genetic algorithm feature optimization was tailored for classification with optional Sentinel-1 data sets, species groupings, and thresholds for the minimum parcel area. The number of species groups varied from 7 to as large as 41. Multinomial logistic regression was tested as an optional method. The Overall Accuracies (OA) varied depending on the number of species included in the classification, and whether all or not field parcels were included. OA with nine species groups was 72% when all parcels were included, 81% when the parcels area threshold (for incorporating parcels into classification) was 0.5 ha, and around 90% when the threshold was 4 ha. The OA gradually increased when adding extra Sentinel-1 scenes up until the early August, and the initial scenes were acquired in early June or mid-May. After that, only minor improvements in the crop recognition accuracy were noted. The ik-NN method gave greater overall accuracies than the logistic regression analysis with all data combinations tested. The width of the 95% confidence intervals with ik-NN for the estimate of the probability of the species with the largest probability on an individual parcel varied depending on the species, the area threshold of the parcel and the number of the Sentinel-1 scenes used. The results ranged between 0.06–0.08 units (6–8% points) for the most common species when the Sentinel-1 scenes were between 1 June and 12 August. The results were well-received by the authorities and encourage further research to continue the study towards an operational method in which the space-borne SAR data are a part of the information chain.
45
Szeląg, Bartosz, Lidia Bartkiewicz, Jan Studziński, and Krzysztof Barbusiński. "Evaluation of the impact of explanatory variables on the accuracy of prediction of daily inflow to the sewage treatment plant by selected models nonlinear." Archives of Environmental Protection 43, no. 3 (September 1, 2017): 74–81. http://dx.doi.org/10.1515/aep-2017-0030.
Full textAbstract:
AbstractThe aim of the study was to evaluate the possibility of applying different methods of data mining to model the inflow of sewage into the municipal sewage treatment plant. Prediction models were elaborated using methods of support vector machines (SVM), random forests (RF), k-nearest neighbour (k-NN) and of Kernel regression (K). Data consisted of the time series of daily rainfalls, water level measurements in the clarified sewage recipient and the wastewater inflow into the Rzeszow city plant. Results indicate that the best models with one input delayed by 1 day were obtained using the k-NN method while the worst with the K method. For the models with two input variables and one explanatory one the smallest errors were obtained if model inputs were sewage inflow and rainfall data delayed by 1 day and the best fit is provided using RF method while the worst with the K method. In the case of models with three inputs and two explanatory variables, the best results were reported for the SVM and the worst for the K method. In the most of the modelling runs the smallest prediction errors are obtained using the SVM method and the biggest ones with the K method. In the case of the simplest model with one input delayed by 1 day the best results are provided using k-NN method and by the models with two inputs in two modelling runs the RF method appeared as the best.
46
Roche-Lima, Abiel, Patricia Ordoñez, Nelson Schwarz, Adnel Figueroa-Jiménez, and Leonardo A. Garcia-Lebron. "2498." Journal of Clinical and Translational Science 1, S1 (September 2017): 19. http://dx.doi.org/10.1017/cts.2017.81.
Full textAbstract:
OBJECTIVES/SPECIFIC AIMS: To learn the edit distance costs of a symbolic univariate time series representation through a stochastic finite-state transducer to predict patient outcomes in intensive care units. METHODS/STUDY POPULATION: High frequency data of patients in intensive care units were used as a data set. The nearest neighbor method with edit distance costs (learned by the FST) were used to classify the patient status within an hour after 10 hours of data. Several experiments were developed to estimate the parameters that better fit the model regarding the prediction metrics. RESULTS/ANTICIPATED RESULTS: Different metrics were obtained for the several parameters. These metrics were metrics (ie, accuracy, precision, and F-measure). DISCUSSION/SIGNIFICANCE OF IMPACT: Our best results are compared with published works, where most of the metrics (ie, accuracy, precision, and F-measure) were improved.
47
Priambodo, Bagus, Azlina Ahmad, and Rabiah Abdul Kadir. "Prediction of Average Speed Based on Relationships Between Neighbouring Roads Using K-NN and Neural Network." International Journal of Online and Biomedical Engineering (iJOE) 16, no. 01 (January 21, 2020): 18. http://dx.doi.org/10.3991/ijoe.v16i01.11671.
Full textAbstract:
For decades, various algorithms to predict traffic flow have been developed to address traffic congestion. Traffic congestion or traffic jam occurs as a ripple effect from a road congestion in the neighbouring area. Previous research shows that there is a spatial correlation between traffic flow in neighbouring roads. Similar traffic pattern is observed between roads in a neighbouring area with respect to day and time. Currently, time series models and neural network models are widely applied to predict traffic flow and traffic congestion based on historical data. However, studies on relationships between road segments in a neighbouring area are still limited. It is important to investigate these relationships because they can assist drivers in avoiding roads which are impacted by road congestion. Also, the result can be used to improve the accuracy of prediction of traffic flow. Hence, this study investigates relationships of roads in a neighbouring area based on similarity of traffic condition. Traffic condition is influenced by number of vehicles and average speed of vehicles. In our study, clustering method is used to divide the speed of traffic into four (4) categories: very congested, congested, clear and very clear. We used k-means clustering method to cluster condition of traffic flow on road segments. Then, we applied the k-Nearest Neighbour (k-NN) method to classify the traffic condition in neighbouring roads. From the classification of traffic condition in neighbouring roads, we then determine the relationship between road segments. We presented the road with highest relationship on the map and used it as input factor to predict traffic speed of the road using neural network. Results show that combination of k-means and k-NN method produced better results than using both, correlation method and using the k-means method only.
48
Lo Duca, Angelica, and Andrea Marchetti. "Exploiting multiclass classification algorithms for the prediction of ship routes: a study in the area of Malta." Journal of Systems and Information Technology 12, no. 3 (July 23, 2020): 289–307. http://dx.doi.org/10.1108/jsit-10-2019-0212.
Full textAbstract:
Purpose Ship route prediction (SRP) is a quite complicated task, which enables the determination of the next position of a ship after a given period of time, given its current position. This paper aims to describe a study, which compares five families of multiclass classification algorithms to perform SRP. Design/methodology/approach Tested algorithm families include: Naive Bayes (NB), nearest neighbors, decision trees, linear algorithms and extension from binary. A common structure for all the algorithm families was implemented and adapted to the specific case, according to the test to be done. The tests were done on one month of real data extracted from automatic identification system messages, collected around the island of Malta. Findings Experiments show that K-nearest neighbors and decision trees algorithms outperform all the other algorithms. Experiments also demonstrate that linear algorithms and NB have a very poor performance. Research limitations/implications This study is limited to the area surrounding Malta. Thus, findings cannot be generalized to every context. However, the methodology presented is general and can help other researchers in this area to choose appropriate methods for their problems. Practical implications The results of this study can be exploited by applications for maritime surveillance to build decision support systems to monitor and predict ship routes in a given area. For example, to protect the marine environment, the use of SRP techniques could be used to protect areas at risk such as marine protected areas, from illegal fishing. Originality/value The paper proposes a solid methodology to perform tests on SRP, based on a series of important machine learning algorithms for the prediction.
49
Wang, Jing Jing, Jian Yu Huang, and Shi Yin Qin. "Detection and Tracking of Cooperative Target for Space Exploration Task Based on Visual Measurement." Applied Mechanics and Materials 385-386 (August 2013): 1461–65. http://dx.doi.org/10.4028/www.scientific.net/amm.385-386.1461.
Full textAbstract:
The detection and tracking of cooperative targets are crucial significance in the rendezvous and docking of space targets. In this paper, a high performance detection and tracking method is proposed based on the combination of adaptive threshold sub-pixel detective positioning with the nearest neighbor clustering analysis of feature points in visual images. In order to enhance the accuracy of detective positioning the bilinear interpolation is employed to achieve sub-pixel coordinates positioning. And then the improved particle filter is used to carry out the prediction and tracking of cooperative targets so as to overcome stochasctic disturbances from stray light and noises. A series of experiment results indicate that the proposed method is characterized with its well performances of detection accuracy and real-time tracking and its outstanding simpleness and practicability so as to play important role in the implementation of cooperative target detection and tracking by visual measurement in the RVD of space exploration.
50
Cao, Hongduo, Tiantian Lin, Ying Li, and Hanyu Zhang. "Stock Price Pattern Prediction Based on Complex Network and Machine Learning." Complexity 2019 (May 28, 2019): 1–12. http://dx.doi.org/10.1155/2019/4132485.
Full textAbstract:
Complex networks in stock market and stock price volatility pattern prediction are the important issues in stock price research. Previous studies have used historical information regarding a single stock to predict the future trend of the stock’s price, seldom considering comovement among stocks in the same market. In this study, in order to extract the information about relation stocks for prediction, we try to combine the complex network method with machine learning to predict stock price patterns. Firstly, we propose a new pattern network construction method for multivariate stock time series. The price volatility combination patterns of the Standard & Poor’s 500 Index (S&P 500), the NASDAQ Composite Index (NASDAQ), and the Dow Jones Industrial Average (DJIA) are transformed into directed weighted networks. It is found that network topology characteristics, such as average degree centrality, average strength, average shortest path length, and closeness centrality, can identify periods of sharp fluctuations in the stock market. Next, the topology characteristic variables for each combination symbolic pattern are used as the input variables for K-nearest neighbors (KNN) and support vector machine (SVM) algorithms to predict the next-day volatility patterns of a single stock. The results show that the optimal models corresponding to the two algorithms can be found through cross-validation and search methods, respectively. The prediction accuracy rates for the three indexes in relation to the testing data set are greater than 70%. In general, the prediction ability of SVM algorithms is better than that of KNN algorithms.