FRACTIONAL RESIDUAL PLOT FOR MODEL VALIDATION

2016 ◽  
Vol 79 (1) ◽  
Author(s):  
Nur Arina Bazilah Kamisan ◽  
Muhammad Hisyam Lee ◽  
Suhartono Suhartono ◽  
Abdul Ghapor Hussin ◽  
Yong Zulina Zubairi
Keyword(s):  
Model Validation ◽  
Goodness Of Fit ◽  
Mean Absolute Error ◽  
Pairwise Comparison ◽  
Absolute Error ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Absolute Percentage Error ◽  
Residual Plot

A pairwise comparison is important to measure the goodness-of-fit of models. Error measurements are used for this purpose but it only limit to the value, thus a graph is used to help show the precision of the models. These two should show a tally result in order to defense the hypothesis correctly. In this study, a fractional residual plot is proposed to help showing the precision of forecasts. This plot improvises the scale of the graph by changing the scale into decimal ranging from -1 to 1. The closer the point to 0 will indicate that forecast is robust and value closer to -1 or 1 will indicate that the forecast is poor. Two error measurements which are mean absolute error (MAE) and mean absolute percentage error (MAPE) and residual plot are used to justify the results and make comparison with the proposed fractional residual plot. Three difference data are used for this purpose and the results have shown that the fractional residual plot could give as much information as the residual plot but in an easier and meaningful way. In conclusion, the error plot is important in visualize the accurateness of the forecast.  

scholarly journals PERAMALAN JUMLAH MAHASISWA MENGGUNAKAN MOVING AVERAGE

Telematika ◽  
2018 ◽  
Vol 15 (1) ◽  
pp. 67
Author(s):  
Hari Prapcoyo
Keyword(s):  
Mean Square Error ◽  
Mean Absolute Error ◽  
Average Length ◽  
Moving Average ◽  
Absolute Error ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Mean Square ◽  
Absolute Percentage Error ◽  
Weighted Moving Average

AbstractThe Process of using resources in higher education is influenced by the up and down of the number students. The purpose of this study is to predict the number of students who study in the department of informatics engineering UPN Veteran Yogyakarta for the next periods. This research, data is taken from forlap dikti for Informatics Engineering fom 2009 until 2016 at UPN Veteran Yogyakarta. The method that used to forecast the number of students is a Moving Average method consisting of: Single Moving Average (SMA), Weighted Moving Average (WMA) and Exponential Moving Average (EMA). This study will use the forecasting accuracy namely Mean Square Error (MSE), Mean Absolute Error (MAE) and Mean Absolute Percentage Error (MAPE) to select the best model to be used for forecasting. The best model that used for forecasting is Weighted Moving Average (WMA) with weighted 1/3 and average length (n) used for 2. The smallest value for MSE of 5807.96; the smallest MAE value of 55.89 and the smallest value for MAPE of 5.24%. Forecasting of the number of students for four semesters in the future after the even semester of 2016 are respectively: 902; 901,33; 901,56 and 901,48. Keywords : Forecasting, UPN Veteran Yogyakarta, Single moving average(SMA) AbstrakProses penggunaan sumber daya perguruan tinggi setiap tahun dipengaruhi oleh naik turunnya jumlah mahasiswa. Tujuan dari penelitian ini adalah untuk memprediksi jumlah mahasiswa yang kuliah di jurusan teknik informatika UPN Veteran Yogyakarta untuk periode yang akan datang. Data penelitian ini diambil dari forlap dikti untuk Teknik Informatika dari tahun 2009 sampai 2016 UPN Veteran Yogyakarta. Metode yang digunakan untuk melakukan peramalan jumlah mahasiswa adalah metode Moving Average yang tediri dari : Single Moving Average (SMA), Weighted Moving Average (WMA) dan Exponential Moving Average (EMA). Penelitian ini akan menggunkan akurasi peramalan Mean Square Error (MSE), Mean Absolute Error (MAE) dan Mean Absolute Percentage Error (MAPE) untuk memilih model terbaik yang akan digunakan untuk peramalan. Model terbaik yang digunakan untuk peramalan yaitu Weighted Moving Average (WMA) dengan pembobot 1/3 dan panjang rata-rata (n) yang dipakai sebesar 2. Nilai terkecil untuk MSE sebesar 5807,96; nilai terkecil MAE sebesar 55,89 dan nilai terkecil untuk MAPE sebesar 5,24 %. Peramalan untuk jumlah mahasiswa empat semester kedepan setelah semester genap 2016 masing-masing adalah : 902; 901,33; 901,56 dan 901,48. Kata Kunci : Peramalan, UPN Veteran Yogyakarta, Single Moving Average(SMA).

scholarly journals Novel Spatiotemporal Feature Extraction Parallel Deep Neural Network for Forecasting Confirmed Cases of Coronavirus Disease 2019

2020 ◽  
Author(s):  
Chiou-Jye Huang ◽  
Yamin Shen ◽  
Ping-Huan Kuo ◽  
Yung-Hsiang Chen
Keyword(s):  
Neural Network ◽  
Deep Neural Network ◽  
Absolute Error ◽  
Mean Absolute Percentage Error ◽  
The Other ◽  
Percentage Error ◽  
Model Assessment ◽  
Absolute Percentage Error ◽  
Spatiotemporal Feature ◽  
The Mean

AbstractThe coronavirus disease 2019 pandemic continues as of March 26 and spread to Europe on approximately February 24. A report from April 29 revealed 1.26 million confirmed cases and 125 928 deaths in Europe. This study proposed a novel deep neural network framework, COVID-19Net, which parallelly combines a convolutional neural network (CNN) and bidirectional gated recurrent units (GRUs). Three European countries with severe outbreaks were studied—Germany, Italy, and Spain—to extract spatiotemporal feature and predict the number of confirmed cases. The prediction results acquired from COVID-19Net were compared to those obtained using a CNN, GRU, and CNN-GRU. The mean absolute error, mean absolute percentage error, and root mean square error, which are commonly used model assessment indices, were used to compare the accuracy of the models. The results verified that COVID-19Net was notably more accurate than the other models. The mean absolute percentage error generated by COVID-19Net was 1.447 for Germany, 1.801 for Italy, and 2.828 for Spain, which were considerably lower than those of the other models. This indicated that the proposed framework can accurately predict the accumulated number of confirmed cases in the three countries and serve as a crucial reference for devising public health strategies.

scholarly journals Evaluation of Several Error Measures Applied to the Sales Forecast System of Chemicals Supply Enterprises

2020 ◽  
Vol 11 (4) ◽  
pp. 39
Author(s):  
Ma. del Rocío Castillo Estrada ◽  
Marco Edgar Gómez Camarillo ◽  
María Eva Sánchez Parraguirre ◽  
Marco Edgar Gómez Castillo ◽  
Efraín Meneses Juárez ◽  
...  
Keyword(s):  
Forecast Model ◽  
Absolute Error ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Error Evaluation ◽  
Sales Forecast ◽  
Absolute Percentage Error ◽  
Sales Prediction ◽  
Prediction Techniques ◽  
Evaluation Techniques

The objective of the industry in general, and of the chemical industry in particular, is to satisfy consumer demand for products and the best way to satisfy it is to forecast future sales and plan its operations.Considering that the choice of the best sales forecast model will largely depend on the accuracy of the selected indicator (Tofallis, 2015), in this work, seven techniques are compared, in order to select the most appropriate, for quantifying the error presented by the sales forecast models. These error evaluation techniques are: Mean Percentage Error (MPE), Mean Square Error (MSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE), Mean Absolute Scaled Error (MASE), Symmetric Mean Absolute Percentage Error (SMAPE) and Mean Absolute Arctangent Percentage Error (MAAPE). Forecasts for chemical product sales, to which error evaluation techniques are applied, are those obtained and reported by Castillo, et. al. (2016 & 2020).The error measuring techniques whose calculation yields adequate and convenient results, for the six prediction techniques handled in this article, as long as its interpretation is intuitive, are SMAPE and MAAPE. In this case, the most adequate technique to measure the error presented by the sales prediction system turned out to be SMAPE.

scholarly journals Accuracy and reliability of ultrasound estimation of fetal weight in women with a singleton term pregnancy

2019 ◽  
Vol 9 (1) ◽  
pp. 323
Author(s):  
Reena Sharma ◽  
Rohit Bhoil ◽  
Poojan Dogra ◽  
Sushruti Kaushal ◽  
Ajay Sharma
Keyword(s):  
Birth Weight ◽  
Mode Of Delivery ◽  
Absolute Error ◽  
Mean Absolute Percentage Error ◽  
Fetal Weight ◽  
Percentage Error ◽  
Strong Positive Correlation ◽  
Positive Correlation ◽  
Absolute Percentage Error ◽  
Estimated Fetal Weight

Background: Prenatal estimation of birth-weight is of utmost importance to predict the mode of delivery. This is also an important parameter of antenatal care. This study was conducted to evaluate the accuracy of estimated fetal weight by ultrasound, compared with actual birth weight.Methods: This was a prospective and comparative study comprising 110 pregnant women at term. Patients who had their sonography done within 7 days from date of delivery were included. Fetal weight was estimated by Hadlock 2 formula, the software of which was preinstalled in ultrasound-machine. The estimated fetal weight was compared to the post-delivery birth-weight. The Pearson's correlation coefficient was used and the accuracy of sonographic fetal weight estimation was evaluated using mean error, mean absolute error, mean percentage error, mean absolute percentage error and proportion of estimates within 10% of actual birth weight.Results: Mean estimated and actual birth weights were 3120.8±349.4 gm and 3088.2±404.5 g respectively. There was strong positive correlation between estimated fetal weight and actual birth weight (r = 0.58, p<0.001). The mean percentage error and mean absolute percentage error of ultrasound fetal weight estimations were 1.96±11.8% and 8.7±8.2% respectively. The percentage of estimates within ±10% of the actual birth weight was found to be 67.3%. In 23% of the cases, ultrasound overestimated the birth weight. In 13% of the cases, ultrasound underestimated the birth weight.Conclusions: There was strong positive correlation between actual and sonographically estimated fetal weight. So, ultrasonography can be considered as useful tool for estimating the fetal weight for improving the perinatal outcome.

scholarly journals Fuzzy Time Series for Forecasting Railway Passengers in Indonesia

2021 ◽  
Vol 2111 (1) ◽  
pp. 012013
Author(s):  
Muhammad Fatih Rizqon ◽  
Handaru Jati
Keyword(s):  
Time Series ◽  
Mean Absolute Error ◽  
Absolute Error ◽  
Fuzzy Time Series ◽  
Percentage Error ◽  
Time Series Models ◽  
Suitable Model ◽  
Arithmetic Operations ◽  
Advantages And Disadvantages ◽  
Absolute Percentage Error

Abstract Some fuzzy time series models have their own advantages and disadvantages. In addition, these models sometimes are complex and claimed to have better forecasting result than each other. The suitable model for forecasting depends on a wide variety of considerations. The models proposed by Chen (1996) applied simplified arithmetic operations and claimed more efficiency than before. The model proposed by Chen was introduced in 1996 and still exists in several previous studies. This research aims to forecast the number of railway passengers in Indonesia using the fuzzy time series. In addition, this research also evaluates the forecasting results based on mean absolute error (MAE) and mean absolute percentage error (MAPE). The results showed the forecasting results in this research has accuracy for 86.6%.

scholarly journals Heart Rate and Distance Measurement of Two Multisport Activity Trackers and a Cellphone App in Different Sports: A Cross-Sectional Validation and Comparison Field Study

Sensors ◽  
2021 ◽  
Vol 22 (1) ◽  
pp. 180
Author(s):  
Mario Budig ◽  
Michael Keiner ◽  
Riccardo Stoohs ◽  
Meike Hoffmeister ◽  
Volker Höltke
Keyword(s):  
Heart Rate ◽  
Field Study ◽  
Absolute Error ◽  
Distance Measurement ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Distance Measurements ◽  
Cross Sectional ◽  
Absolute Percentage Error ◽  
Activity Trackers

Options for monitoring sports have been continuously developed by using activity trackers to determine almost all vital and movement parameters. The aim of this study was to validate heart rate and distance measurements of two activity trackers (Polar Ignite; Garmin Forerunner 945) and a cellphone app (Polar Beat app using iPhone 7 as a hardware platform) in a cross-sectional field study. Thirty-six moderate endurance-trained adults (20 males/16 females) completed a test battery consisting of walking and running 3 km, a 1.6 km interval run (standard 400 m outdoor stadium), 3 km forest run (outdoor), 500/1000 m swim and 4.3/31.5 km cycling tests. Heart rate was recorded via a Polar H10 chest strap and distance was controlled via a map, 400 m stadium or 50 m pool. For all tests except swimming, strong correlation values of r > 0.90 were calculated with moderate exercise intensity and a mean absolute percentage error of 2.85%. During the interval run, several significant deviations (p < 0.049) were observed. The swim disciplines showed significant differences (p < 0.001), with the 500 m test having a mean absolute percentage error of 8.61%, and the 1000 m test of 55.32%. In most tests, significant deviations (p < 0.001) were calculated for distance measurement. However, a maximum mean absolute percentage error of 4.74% and small mean absolute error based on the total route lengths were calculated. This study showed that the accuracy of heart rate measurements could be rated as good, except for rapid changing heart rate during interval training and swimming. Distance measurement differences were rated as non-relevant in practice for use in sports.

scholarly journals Ανάπτυξη πολυκριτήριου συστήματος συστάσεων για προσωποποιημένο μάρκετινγκ

2018 ◽  
Author(s):  
Ιωάννης Ζήσος
Keyword(s):  
Root Mean Square Error ◽  
Recommender Systems ◽  
Mean Square Error ◽  
Root Mean Square ◽  
Mean Absolute Error ◽  
Cold Start ◽  
Absolute Error ◽  
Percentage Error ◽  
Mean Square ◽  
Absolute Percentage Error

Ένα από τα πιο καίρια ερωτήματα για τους χρήστες του διαδικτύου, είναι πώς θα καταφέρουν να διαχειριστούν την τεράστια ποσότητα διαθέσιμης πληροφορίας, ώστε να καταλήξουν σε επιλογή προϊόντων που ανταποκρίνονται όσο το δυνατό καλύτερα στις προτιμήσεις και ανάγκες τους. Αντίστοιχα, οι εταιρείες που παρέχουν προϊόντα ή υπηρεσίες μέσω του διαδικτύου, προσπαθούν συστηματικά να εντοπίσουν μεθόδους ώστε να αποκωδικοποιήσουν με ακρίβεια τα προφίλ προτίμησης των χρηστών, με στόχο να καταφέρουν να προσαρμόσουν κατάλληλα τα προϊόντα τους και να αυξήσουν τις πωλήσεις τους.Για τους παραπάνω λόγους, η επιστημονική και ερευνητική κοινότητα που δραστηριοποιείται στο τομέα της ανάλυσης δεδομένων και το μάρκετινγκ έχει επικεντρώσει την προσπάθεια της, στην δημιουργία μεθοδολογιών που θα απαντήσουν όσο το δυνατόν πιο αποτελεσματικά τα παραπάνω ερωτήματα. Οι περισσότερες από αυτές τις μεθοδολογίες καταλήγουν στην ανάπτυξη προσαρμοστικών συστημάτων που αντλούν δεδομένα από το διαδίκτυο και εξάγουν προτάσεις για τους χρήστες. Η πιο γνωστή κατηγορία τέτοιου είδους συστημάτων είναι τα συστήματα συστάσεων (Recommender Systems). Στην παρούσα ερευνητική εργασία παρουσιάζεται η μεθοδολογία και τα αποτελέσματα πιλοτικής λειτουργίας ενός νέου υβριδικού συστήματος συστάσεων που βασίζεται στη χρήση μεθόδων ανάλυσης συναισθήματος, πολυκριτήριας ανάλυσης καθώς και μεθόδων φιλτραρίσματος. Η μεθοδολογία καταλήγει σε τέσσερα διαφορετικά είδη σύστασης, με άκρως ενδιαφέροντα αποτελέσματα.Μέσω του μεθοδολογικού πλαισίου γίνεται εφικτός ο προσδιορισμός των προτιμησιακών προφίλ των χρηστών του συστήματος, τα οποία εν συνεχεία αντιστοιχίζονται σε «προφίλ πελατών» που επιλέγουν συγκεκριμένα προϊόντα/υπηρεσίες που τους «ταιριάζουν».Έτσι, καταλήγουμε σε προσωποποιημένες συστάσεις προϊόντων στον χρήστη του συστήματος, που είναι ανάλογες των προτιμήσεων του. Επιπλέον δίνεται στο χρήστη η δυνατότητα να φιλτράρει τις διαθέσιμες εναλλακτικές με σχετική επιλογή από ένα σύνολο κατ’ αποκοπή κριτηρίων. Η χρήση του κατωφλιού ελάχιστης ικανοποίησης, που προσδιορίζεται από τα αποτελέσματα της ανάλυσης συναισθήματος στα σχόλια των πελατών, εγγυάται την ποιότητα των συστάσεων.Τα δεδομένα του συστήματος είναι πραγματικές απόψεις και βαθμολογίες χρηστών για καταλύματα, καθώς και χαρακτηριστικά καταλυμάτων που αντλήθηκαν από γνωστή διαδικτυακή πλατφόρμα κρατήσεων. H ανάπτυξη του συστήματος βασίστηκε στην μεθοδολογία CRISP-DM(Shearer, 2000a). Η αξιολόγηση του συστήματος συστάσεων γίνεται με μέτρηση της ακρίβειας προβλέψεων αξιολογήσεων σε πείραμα με πραγματικούς χρήστες.Για τη μελέτη περίπτωσης χρησιμοποιήθηκαν δεδομένα για τα τουριστικά καταλύματα του Νομού Χανίων. Τα πιο σημαντικά χαρακτηριστικά της συγκεκριμένης ερευνητικής προσπάθειας είναι: α. H χρήση μεγάλου όγκου πραγματικών δεδομένων σε αντίθεση με τις περισσότερες από τις υπάρχουσες έρευνες που χρησιμοποιούν έτοιμα τεστ σετ δεδομένων. β. Η χρησιμοποίηση όλης της διαθέσιμης αντλημένης πληροφορίας προκειμένου να καταλήξουμε σε σύσταση. Πιο συγκεκριμένα στην παρούσα μεθοδολογία χρησιμοποιούνται δεδομένα βαθμολογιών προϊόντων για την ανάλυση ικανοποίησης πελατών, δεδομένα απόψεων για τη συναισθηματική ανάλυση, στατικά δεδομένα των προϊόντων σαν κατ’ αποκοπή κριτήρια σε αντίθεση με τις περισσότερες μελέτες όπου χρησιμοποιούνται είτε βαθμολογίες, είτε ανάλυση σχολίων για την τελική σύσταση.γ. Η χρήση των αποτελεσμάτων της ανάλυσης συναισθήματος ως κατώφλια ποιότητας σύστασης. δ. Η επιτυχής εφαρμογή παραλλαγής της πρόσφατα παρουσιασθείσας μεθόδου WAP, για τη δημιουργία προτιμησιακού προφίλ χρήστη.ε. Η απαίτηση για εισαγωγή ελάχιστων δεδομένων από το χρήστη.στ. Ο ελάχιστος χρόνος που απαιτείται για την παραγωγή της σύστασης κατά τη λειτουργία του συστήματος.η. Η αποφυγή άντλησης προσωπικών δεδομένων του χρήστη για χρήση τους στη διαδικασία της σύστασης. θ. H αποφυγή του προβλήματος της καθυστερημένης εκκίνησης (cold start). ι. Τα άκρως ικανοποιητικά αποτελέσματα με βάση τις μετρικές που χρησιμοποιήθηκαν για τη δοκιμή του συστήματος.κ. Η χρησιμότητα του συστήματος είναι χαρακτηριστική για όλες τις ομάδες στόχου, καθώς δίνεται η δυνατότητα παροχής χρήσιμης πληροφορίας τόσο στον πελάτη με σύσταση ανάλογη των αναγκών του, όσο και στον πάροχο υπηρεσίας/προϊόντος, προσδιορίζοντας του τις τάσεις όσον αφορά την ικανοποίηση των πελατών. Οι κύριες μετρικές που χρησιμοποιούνται για την μέτρηση της ποιότητας των συστάσεων που παράγονται είναι οι: Mean Square Error (MSE), Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Mean Absolute Percentage Error (MAPE).H διατριβή ολοκληρώνεται, με προτάσεις, για μελλοντική έρευνα και επέκταση του παρόντος συστήματος.

Towards optimal ATM cash replenishment using time series analysis

2021 ◽  
pp. 1-13
Author(s):  
Muhammad Rafi ◽  
Mohammad Taha Wahab ◽  
Muhammad Bilal Khan ◽  
Hani Raza
Keyword(s):  
Time Series ◽  
Moving Average ◽  
Arima Model ◽  
Mean Absolute Percentage Error ◽  
Percentage Error ◽  
Absolute Percentage Error ◽  
Automatic Teller Machine ◽  
Proposed Model ◽  
Auto Regressive ◽  
Specific Amount

Automatic Teller Machine (ATM) are still largely used to dispense cash to the customers. ATM cash replenishment is a process of refilling ATM machine with a specific amount of cash. Due to vacillating users demands and seasonal patterns, it is a very challenging problem for the financial institutions to keep the optimal amount of cash for each ATM. In this paper, we present a time series model based on Auto Regressive Integrated Moving Average (ARIMA) technique called Time Series ARIMA Model for ATM (TASM4ATM). This study used ATM back-end refilling historical data from 6 different financial organizations in Pakistan. There are 2040 distinct ATMs and 18 month of replenishment data from these ATMs are used to train the proposed model. The model is compared with the state-of- the-art models like Recurrent Neural Network (RNN) and Amazon’s DeepAR model. Two approaches are used for forecasting (i) Single ATM and (ii) clusters of ATMs (In which ATMs are clustered with similar cash-demands). The Mean Absolute Percentage Error (MAPE) and Symmetric Mean Absolute Percentage Error (SMAPE) are used to evaluate the models. The suggested model produces far better forecasting as compared to the models in comparison and produced an average of 7.86/7.99 values for MAPE/SMAPE errors on individual ATMs and average of 6.57/6.64 values for MAPE/SMAPE errors on clusters of ATMs.

scholarly journals Penerapan metode fuzzy sugeno untuk prediksi persediaan bahan baku

2019 ◽  
Vol 9 (2) ◽  
pp. 12-20
Author(s):  
Julio Warmansyah ◽  
Dida Hilpiah
Keyword(s):  
Fuzzy Logic ◽  
Raw Materials ◽  
Mean Absolute Percentage Error ◽  
Raw Material ◽  
Percentage Error ◽  
Human Power ◽  
Absolute Percentage Error ◽  
Input Variables ◽  
A Company

 PT. Cahaya Boxindo Prasetya is a company engaged in the manufacture of carton boxes or boxes. The company's activities also include cutting and printing services using machinery and human power. The problem faced in this company is the difficulty of predicting the amount of inventory of raw materials that will be  included in the production. The remaining raw materials for production will be used as the final stock to get the minimum, the goal is to reduce excess stock Overcoming this problem, fuzzy logic is used to predict raw material inventories by focusing on the final stock. In this study using Fuzzy Sugeno, with three input variables, namely: initial inventory, purchase, production, while the output is the final stock. Determination of prediction results using defuzzification using the average concept of MAPE (Mean Absolute Percentage Error). The results obtained, using the Fuzzy Sugeno method can predict the inventory of raw materials with a MAPE value of 38%. 

Sign in / Sign up

Export Citation Format

Share Document