Fast Algorithm for Outlier Detection in Time Series: Finding a Solution with a Minimum Amount of Rejected Measurement Data | Chapter 1 | Physical Science: New Insights and Developments Vol. 3

 

This study addresses the challenge of detecting coarse measurements (outliers) in time series data, a common issue in fields such as space geodynamics, geodesy, and other measurement-driven sciences. The proposed outlier detection algorithm solves two key problems: first, it finds a solution containing the maximum possible amount of measurement data remaining after detecting and removing outliers. Second, it requires the minimum possible number of arithmetic operations, estimated by the value O(NlogN), which cannot be improved in order N, to find a solution. To construct the algorithm, it was shown that the required solution should be sought in the ordered sequence of input data in the form of a set of consecutive numbers. The search for the set of maximum length is performed step by step, with the range of possible values of the set length being halved at each step.  The transition to one of the two halves is performed by checking the fulfilment of certain criteria, not for all possible values of lengths from the range under consideration, but only for its mid value. Testing the algorithm on real data obtained from laser rangefinder measurements showed the advantages of it over others, both in terms of time consumption and the amount of data remaining after detection and removal of outliers. The algorithm is robust and always finds a solution, if one exists. Its time efficiency is evident when cleaning a large amount of measurement data of outliers. It can be used for automated cleaning from outliers of observation data in information and measuring systems, in systems with artificial intelligence, as well as when solving various scientific, applied managerial and other problems using modern computer systems in order to obtain promptly the most accurate final result.

 

 

Author(s) Details

Igor V.Bezmenov
Russian Metrological Institute of Technical Physics and Radio Engineering, Mendeleevo, Moscow Region, Russia.

 

Please see the link:- https://doi.org/10.9734/bpi/psniad/v3/6424

 

Data Driven Approach for Modeling and Forecasting of Maize Yield in India | Chapter 14 | Agricultural Sciences: Techniques and Innovations Vol. 4

 

The demand for food grain crops is increasing at a rapid rate worldwide. To meet the global food demand, efforts are needed for the enhancement of crop yield through improved varieties, policy support, subsidies, resource allocation, market development, and farmers’ motivation towards the cultivation of profitable crops. However, the yield of agricultural crops is influenced by several extraneous factors like climate change, pest attacks, resource scarcity, and land acquisition for construction and urbanisation. This study deals with modelling and forecasting of maize yield in India. The study encompasses temporal data from 1954 to 2023, allowing for a data-driven analysis of trends in maize yield over the years in India. The methodology involved the fitting of several conventional autoregressive integrated moving average (ARIMA) models. The accuracy of the fitted models was evaluated using model fit statistics criteria viz., akaike information criterion (AIC), root mean square error (RMSE) and mean absolute percentage error (MAPE). The best-fitted model was ARIMA (2,1,0) with drift, having an AIC value of 894.95, an RMSE value of 148.05, and an MAPE value of 7.71%. Furthermore, a comparative assessment of the conventional fitted models was made with the automated model, viz., ARIMA (1,1,2) with drift, which was o.btain.d on using function in R-studio. The diagnostic checking of residuals of the generated models was made using the Ljung-Box test. It was revealed that the Ljung-Box test statistic (Q) achieved a p-value greater than 0.05 for residuals of each fitted model, which indicated the acceptance of the null hypothesis (H0), i.e., the residuals of the various generated models were uncorrelated. The analytical results revealed that ARIMA (1,1,2) with a drift model slightly outperformed ARIMA (2,1,0) with a drift. The forecast values of maize yield for five successive years (viz., 2024-2028) were obtained with 80% and 95% prediction intervals utilising ARIMA (1,1,2) with drift model. The outcomes of the analysis reported a significantly rising trend of maize yield over the recent years, which indicated a favourable sign for policymakers and scientists regarding the formulation of strategies related to agricultural trade and nutritional security.

 

 

Author(s) Details

Manish Kumar
Department of Agricultural Statistics, Acharya Narendra Deva University of Agriculture & Technology, Ayodhya, India.

 

Shiv Kumar Rana
Department of Agricultural Statistics, Acharya Narendra Deva University of Agriculture & Technology, Ayodhya, India.

 

Please see the book here :- https://doi.org/10.9734/bpi/asti/v4/6379

Trend Detection in Time Series Using the Minimizing Sets Method: Applications in Space Geodynamics and Beyond | Chapter 8 | Physical Science: New Insights and Developments Vol. 1

A significant problem in achieving the required level of accuracy of modern computing complexes and systems is the detection of coarse measurements (outliers) in the time series of data at the preprocessing stage. The proper detection and removal of outliers from measurement data is a necessary step in any scientific application to obtain the most accurate final result. This chapter addresses the challenge of detecting trends in time series data contaminated with outliers, a common issue in fields such as space geodynamics, geodesy, and other measurement-driven sciences. The proposed solution builds on the author’s previously developed Minimising Sets (MS) method, which iteratively constructs a trend by maximising the usable portion of the data and minimising the influence of outliers. The method is extended beyond power polynomials to include trigonometric functions with fixed frequencies and harmonic functions with unknown parameters, increasing its applicability across diverse physical systems. Simulations demonstrate that the approach yields accurate trend approximations and robust outlier detection, without relying on arbitrary thresholds. The technique shows promise for high-precision scientific applications requiring reliable preprocessing of noisy measurement data.

 

Author(s) Details

Igor V. Bezmenov
Russian Metrological Institute of Technical Physics and Radio Engineering, Mendeleevo, Moscow Region, Russia.

 

Please see the book here:- https://doi.org/10.9734/bpi/psniad/v1/5621

Long-Term Equilibrium Relationship of the Johansen Model Applied to an Island Zone for Photovoltaic Energy Prediction | Chapter 2 | Science and Technology: Developments and Applications Vol. 10

Solar photovoltaic (PV) plant systems transform solar energy into electric power. A main goal of the Mauritian government is to significantly increase from 13% to 60% of the share of renewables in the energy mix. This paper presents findings based on the Johansen vector error correction model (VECM) cointegration approach, drawing from the author's original and prior research, with a focus on short-term predictions (15-minute intervals) for PV power output in Mauritius. The innovation of this study lies in applying the long-term equilibrium relationship identified in earlier research from Reunion Island to the PV plants in Mauritius. The prediction model has been trained using data from 2019 to 2022, focusing on a random month and day, for both hourly and 15-minute intervals. The data used in this study are measured from the PV system installed on the rooftop of the University of Mauritius (UoM) which is located on the west coast of the island. Experimental results indicate that the performance metric R² values exceed 93%, demonstrating a strong positive correlation between the Johansen model and onsite measurements. This proposed model serves as a robust predictive tool, with the potential for enhanced accuracy when integrated with machine learning techniques such as LSTM that can adapt to varying datasets. Future works will focus on the best artificial intelligence to fit the model as sudden variability in PV power output due to sudden fluctuation in irradiance can have a serious impact on grid stability.

 

Author (s) Details

 

Harry Ramenah
University of Lorraine, LCOMS Laboratory, 57070 Metz, France.

 

Abdel Khoodaruth
University of Mauritius, Faculty of Engineering, Réduit, Mauritius.

 

Vishwamitra Oree
University of Mauritius, Faculty of Engineering, Réduit, Mauritius.

 

Zahiir Coya
University of Mauritius, Faculty of Engineering, Réduit, Mauritius.

 

Anshu Murdan
University of Mauritius, Faculty of Engineering, Réduit, Mauritius.

 

Miloud Bessafi
University of Reunion Island, LE²P – Energy-Lab, 97744 Saint-Denis, France.

 

Damodar Doseeah
Central Electricity Board, Curepipe, Mauritius.

 

Please see the book here:- https://doi.org/10.9734/bpi/stda/v10/5077

Computational Framework for Trend Pattern Analysis of Wheat Production in Some Wheat Growing States of India | Chapter 11 | Research Advances and Challenges in Agricultural Sciences Vol. 7

The present study deals with the trend pattern analysis of wheat production in some wheat growing states of India on fitting well-known statistical models. The analysis was carried out on utilizing secondary time series data on wheat production. The trend values were obtained on fitting the statistical models, and the goodness of fit of the models was tested using chi-square test. Furthermore, statistical measures, viz. coefficient of determination (R2), root mean square error (RMSE), and relative mean absolute percentage error (RMAPE) were computed for revealing the model accuracy. The model with R2>0.5, and least values of RMSE and RMAPE, is regarded as the best model. Among the models considered under study, the cubic model was found to be the best in terms of precision for exploring the trends of wheat production in the concerned states. The findings of the study provide some useful insights on statistical modeling techniques for forecasting the scenario of wheat production in the concerned states.

Author(s) Details:

Manish Kumar,
Department of Agricultural Statistics, Acharya Narendra Deva University of Agriculture and Technology, Ayodhya, 224229, India.

Gyan Prakash,
Department of Agricultural Statistics, Acharya Narendra Deva University of Agriculture and Technology, Ayodhya, 224229, India.

Shiv Kumar Rana,
Department of Agricultural Statistics, Acharya Narendra Deva University of Agriculture and Technology, Ayodhya, 224229, India.

Please see the link here: https://stm.bookpi.org/RACAS-V7/article/view/14269

Image Matching Using Pseudo Time Series Representation | Chapter 6 | Current Overview on Science and Technology Research Vol. 5

 A wide range of vision tasks, including semantic segmentation and object recognition, can be significantly improved by boundary and edge information. The semantic edge detection problem is more difficult than classical edge detection, which is a difficult task in and of itself. Many computer vision tasks, including 3d reconstruction [1], 3d form recovery [2], medical image processing [3], and semantic segmentation [4,5], have demonstrated to benefit from the classical edge detection job. Two pre-processing methods for image/object retrieval are suggested in this research. The object is defined as a pseudo-time series in one dimension using a traditional pre-processing method. The first method that is offered modifies the SAX representation by using an Extended SAX (ESAX) approach to quickly and accurately identify key patterns, which is necessary to identify the related items that have the best chance of being true. The general resemblance between two families of symbolic words is then used to characterise the relationship between two images or objects. To determine the most likely matching between strings of symbolic words, a distance measure is employed. We empirically compare the Extended SAX strategy to the original SAX approach and show how it performs better at getting the most likely related objects at larger cardinality. The second method uses a specified collection (subset) of boundary points to identify each object or form. Each point is the centre of a small area that surrounds it and is represented by an image patch that reflects the patch's low-level properties. A family of image/object features corresponding to the image/patches object's is connected to it. The degree of general similarity between two families of image/shape patches is then used to define the similarity between two images or objects. To select the most likely matches, GA is used. The experimental findings have demonstrated that our approach is successful at retrieving related photos.

Author(s) Details:

Hala Ahmed Abdul-Moneim,
Department of Mathematics, Darb University College, Jazan University, Jazan, Saudi Arabia and Department of Mathematics, Faculty of Science, Minia University, Minia, Egypt.

Please see the link here: https://stm.bookpi.org/COSTR-V5/article/view/8336

Revised Study of Daily Time Series Data Analysis of Market Prices | Chapter 11 | Current Aspects in Business, Economics and Finance Vol. 2

 

This study aims to shed light on the occurrence of time series traits in the daily stock prices of securities traded on regulated exchanges. In contrast to earlier studies, this one focuses on real prices of traded assets as opposed to index numbers of daily stock market values. The idea of market efficiency and its application to the short-term forecasting of closing values of traded securities are further reasons why this work is significant. Additionally, the study contains evaluations of stock market responses to pandemic impacts (Scherf, Matschke, and Rieger, 2022) as well as approaches for forecast modification.

Author(s) Details:

Jeffrey Jarrett,
University of Rhode Island, US.

Please see the link here: https://stm.bookpi.org/CABEF-V2/article/view/7647

Assessment of Rainfall and Crop Yield Simulation in Nasarawa Town Nasarawa State Nigeria | Chapter 06 | Innovations in Science and Technology Vol. 5

 Simulation is being used in recent technologies to anticipate the amount and total crop production and yield in a certain plot of land. The growth of a crop per unit area is referred to as crop yield. This research calculates crop yields over a 20-year period and uses simulation to generate 18 years of crop yields at various places in Nasarawa Local Government Area, Nasarawa State, Nigeria. The goal is to demonstrate the relationship between rainfall variability and crop yield, as well as to simulate crop output using rainfall intensity as a basis. To determine agricultural yield, the study uses time series analysis with linear, quadratic, and growth curve models. The result suggests that rainfall was abundant in the prior year from 2020 to 2038, with an annual rainfall trend of more than 2200mm-2300mm. In the coming years, the agricultural production simulation predicts a faster growth curve and a bountiful harvest.

Author(S) Details

Ibrahim Sufiyan
Department of Surveying and Geoinformatics, Federal Polytechnic Nasarawa, Nigeria.

K. D. Muhammad
Department of Geography, Federal University Lafia, Nigeria.

Mohammed Alkali
Department of Environmental Management, Nasarawa State University Keffi, Nigeria.

View Book:- https://stm.bookpi.org/IST-V5/article/view/5701

A Case Study of Time Series Analysis to Forecast the Number of Patients with Tuberculosis in Khartoum State from 2007 to 2016 | Chapter 12 | New Innovations in Economics, Business and Management Vol. 5

 The number of tuberculosis (TB) cases in Khartoum state was predicted using time series analysis. It is based on data collected from tuberculosis patients between 2007 and 2016. The investigation was successful in determining the optimal data model of order (2) ARIMA (2, 1, 0). The study's most noteworthy finding is a quartile-based projection of the number of people with tuberculosis in the next four years. As a result, the predicted value was found to drop and represented the source time series data. The study's ineffectiveness derives from the utilisation of TB data and, as a result, the estimation of future patient numbers, which benefits both patients and specialists.

Author(S) Details

Abu Elgasim Abbas Abow Mohammed
College of Business and Economics, Qassim University, Kingdom of Saudi Arabia and College of Economic and Political Science Omdurman Islamic University, Sudan.

View Book:- https://stm.bookpi.org/NIEBM-V5/article/view/5624

Effect of Fuzzy Time Series Technique on Estimators of Spectral Analysis | Chapter 04 | Recent Advances in Mathematical Research and Computer Science Vol. 6

 The estimate of the spectral density function, as well as the properties of the resulting estimator, the periodogram, are discussed in this chapter. For actual and anticipated observations of the fuzzy time series, the statistical features of this periodogram are explored. MSEs, which are based on these statistical features, can be used to compare the periodogram results in both scenarios. For this, a programme was developed that converts observed time series into fuzzy time series with huge sizes.

Study Goal: To enhance the estimate of the spectral density function while maintaining its statistical features using the fuzzy time series technique.

Author(S) Details

Abd El-Moneim A. M. Teamah
Mathematics Department, Faculty of Science, Tanta University, Tanta, Egypt.

Hasnaa M. Faied
Mathematics Department, Faculty of Science, A1-Azhar University (Girls), Nasr-City, Cairo, Egypt.

Mohammed H. El-Menshawy
Mathematics Department, Faculty of Science, A1-Azhar University (Men), Nasr-City, Cairo, Egypt.

View Book:- https://stm.bookpi.org/RAMRCS-V6/article/view/5307

Using Time Series Analysis to Support the Water Resources Management in the Upper Basin of the Suquia River: An Observational Study | Chapter 12 | Challenging Issues on Environment and Earth Science Vol. 8

 A time series analysis is a useful tool for obtaining information about the examined data structures and their components, as well as a solid foundation for making accurate future forecasts. This data is useful in making decisions on how to best manage this resource. The hydrological cycles in the region where the province of Cordoba is located are quite variable. The city of Cordoba and its area of influence (Area of Greater Cordoba), which has a population of about 1.4000.000 people, have witnessed rapid population expansion in recent years, resulting in conflicts over the usage of this resource. There have been lengthy droughts and floods during the last few decades. The Suquia River, which runs through Cordoba, is the city's most important source of water. The ability to forecast rainfall over its basin is critical for managing reservoir levels, floods, and droughts. In this research, a time series analysis was used as a beneficial tool to obtain information on rainfall data structures and their components in order to offer a solid foundation for successful climate prediction in the future. This research focuses on the modelling and forecasting of rainfall time series in the upper Suquia River basin. San Antonio was the series that was investigated. Season: El Cajon and El Barrio Station Canal, El Condor. ARMA models were proposed as time series models for the study of each record. The findings demonstrate that time series analysis is a useful method for learning about pluviograph properties.

Author(s) Details

Reyna Teresa
Facultad de Ciencias Exactas, Físicasy Naturales, Ciudad Universitaria, U.N.C Av. Velez Sarsfield 1600, Argentina.


Guillén Nicolás
Facultad de Ciencias Exactas, Físicasy Naturales, Ciudad Universitaria, U.N.C Av. Velez Sarsfield 1600, Argentina.


Lábaque María
Facultad de Ciencias Exactas, Físicasy Naturales, Ciudad Universitaria, U.N.C Av. Velez Sarsfield 1600, Argentina.


Álvarez Javier
Facultad de Ciencias Exactas, Físicasy Naturales, Ciudad Universitaria, U.N.C Av. Velez Sarsfield 1600, Argentina.


Eder Matías
Facultad de Ciencias Exactas, Físicasy Naturales, Ciudad Universitaria, U.N.C Av. Velez Sarsfield 1600, Argentina.


Funes Federico
Facultad de Ciencias Exactas, Físicasy Naturales, Ciudad Universitaria, U.N.C Av. Velez Sarsfield 1600, Argentina.


View Book :- https://stm.bookpi.org/CIEES-V8/article/view/3245

Multiple Change Points by Filtered Derivative and False Discovery Rate | Chapter 15 | Theory and Practice of Mathematics and Computer Science Vol. 11

 Let X = (X1; X2; : : : ; Xn) be a time series, that is a sequence of random variable indexed by thetime t = 1; 2; : : : ; n. We assume the existence of a segmentation τ = (τ1; τ2; : : : ; τn) such that Xi is a family of independent identically distributed (i.i.d) random variable for i ∈ (τk; τk + 1]; and k = 0; : : : ; K where by convention τo and τK+1 = N. In the literature, it exist two main kinds of change points detection : The change points on-line and the change points off-line. In this paper, we only look at change point analysis (off-line) when the number of change points is unknown. The obtained result is based on the Filtered Derivative method, with a second step based on the False Discovery Rate. This new method is numerically compared to the Filtered Derivative with p-Value. We also present a real-world application of the Filtered Derivative with False Discovery Rate method (FDqV).

Author (s) Details

Mohamed Elmi
Research Laboratory in Mathematics and Economics (LME), University Djibouti, Republic of Djibouti

View Book  :   https://stm.bookpi.org/TPMCS-V11/article/view/1320

Application of Fourier Transform-based Cross-correlation in Determining Breaking Water Wave Phase Velocity from Station-to-Station Free Surface Elevation Time Series | Chapter 3| Theory and Practice of Mathematics and Computer Science Vol. 5

 Water waves were produced in a laboratory wave flume that propagated and broke as plunging waves on a 1:20 beach slope. In order to distinguish changes in wave dynamics as the waves propagated from deep water to the shore, free surface elevation time series were then measured along the flume. A pair of parallel-wire capacitive wave gauges were used to measure free surface elevations at various locations along the flume simultaneously. To provide a guide, one gauge was held fixed near the wave generator while the other was pushed near the break point in steps of 0.1 m. Data from these two wave gauges measured at the same time reflect a time series of station-to-station free surface elevation. To calculate the time lag between each pair of the time series, Fast Fourier Transform (FFT) based cross-correlation techniques were used. The time lag was used to determine the phase change between the reference wave measure and that along the flume at different points. In order to measure local mean wave phase velocity for a point lying in the centre, phase differences between two points spaced 0.1 m apart were then used. Results show that the calculated mean phase velocity decreases almost linearly from about 1.75 m/s to about 1.50 m/s at the break point when moving from deep water to shallow water. The wave phase velocity rises suddenly just after the break point to a maximum value of 1.87 m/s observed at a location 30 cm downstream of the break point. The phase velocity decreases thereafter, reaching a minimum of about 1.30 m/s.

Author(s) Details

R. Mukaro
North West University, Mafikeng Campus, School of Physical and Chemical Sciences, Department of Physics & Electronics, Private Bag X2046, Mmabatho 2735, South Africa.

K. Govender
Cape Peninsula University of Technology, Cape Town Campus, Faculty of Engineering, Department of Electrical, Electronic, and Computer Engineering, P.O. Box 652, Cape Town 8000, South Africa.

View Book :- https://bp.bookpi.org/index.php/bpi/catalog/book/341

Critical Research: Selection of Optimal Embedding Parameters Applied to Short and Noisy Time Series from Rössler System

 The State Space Reconstruction that integrates a non-linear time series is the first and important step in characterising and predicting the behaviour of a complex system in scientific research. This includes the selection of the necessary time delay T and embedded dimension dE values. Three methods are implemented and explored by the Rössler attractor equations set on nonlinear time series: the Cao method, the C-C method developed by Kim et al., and the C-C-1 method developed by Cai et al. A way is provided to fix a parameter that is needed to enforce the last process. Small size and/or noisy time series have been put into view. By using a metric based on the smoothness of the transformation, the reconstruction quality is measured. This paper offers an overview of embedding parameter methods for optimal selection applied by chaotic time series to the Rössler strange attractor reconstruction.

Author(s) Details

Olivier Delage
Department of Physics, The University of La Reunion, Saint Denis, France.

Alain Bourdier
Department of Physics and Astronomy, The University of New Mexico, Albuquerque, NM, USA.    

View Book :- https://bp.bookpi.org/index.php/bpi/catalog/book/301