scholarly journals Combined Multilateration with Machine Learning for Enhanced Aircraft Localization

Proceedings ◽  
2020 ◽  
Vol 59 (1) ◽  
pp. 2
Author(s):  
Benoit Figuet ◽  
Raphael Monstein ◽  
Michael Felux
Keyword(s):  
Machine Learning ◽  
Sensitivity Analysis ◽  
Real World ◽  
Mean Squared Error ◽  
Accurate Estimate ◽  
Regression Technique ◽  
Gradient Boosting ◽  
Root Mean Squared Error ◽  
Squared Error ◽  
Using Data

In this paper, we present an aircraft localization solution developed in the context of the Aircraft Localization Competition and applied to the OpenSky Network real-world ADS-B data. The developed solution is based on a combination of machine learning and multilateration using data provided by time synchronized ground receivers. A gradient boosting regression technique is used to obtain an estimate of the geometric altitude of the aircraft, as well as a first guess of the 2D aircraft position. Then, a triplet-wise and an all-in-view multilateration technique are implemented to obtain an accurate estimate of the aircraft latitude and longitude. A sensitivity analysis of the accuracy as a function of the number of receivers is conducted and used to optimize the proposed solution. The obtained predictions have an accuracy below 25 m for the 2D root mean squared error and below 35 m for the geometric altitude.

scholarly journals Machine Learning Rekomendasi Produk dalam Penjualan Menggunakan Metode Item-Based Collaborative Filtering

2021 ◽  
pp. 202-208
Author(s):  
Daniel Theodorus ◽  
Sarjon Defit ◽  
Gunadi Widi Nurcahyo
Keyword(s):  
Machine Learning ◽  
Collaborative Filtering ◽  
User Experience ◽  
Mean Squared Error ◽  
Cosine Similarity ◽  
Weighted Sum ◽  
Root Mean Squared Error ◽  
Squared Error

Industri 4.0 mendorong banyak perusahaan bertransformasi ke sistem digital. Machine Learning merupakan salah satu solusi dalam analisa data. Analisa data menjadi poin penting dalam memberikan layanan yang terbaik (user experience) kepada pelanggan. Lokasi yang diangkat dalam penelitian ini adalah PT. Sentral Tukang Indonesia yang bergerak dalam bidang penjualan bahan bangunan dan alat pertukangan seperti: cat, tripleks, aluminium, keramik, dan hpl. Dengan banyaknya data yang tersedia, menyebabkan perusahaan mengalami kesulitan dalam memberikan rekomendasi produk kepada pelanggan. Sistem rekomendasi muncul sebagai solusi dalam memberikan rekomendasi produk,  berdasarkan interaksi antara pelanggan dengan pelanggan lainnya yang terdapat di dalam data histori penjualan. Tujuan dari penelitian ini adalah Membantu perusahaan dalam memberikan rekomendasi produk sehingga dapat meningkatkan penjualan, memudahkan pelanggan untuk menemukan produk yang dibutuhkan, dan meningkatkan layanan yang terbaik kepada pelanggan.Data yang digunakan adalah data histori penjualan dalam 1 periode (Q1 2021), data pelanggan, dan data produk pada PT. Sentral Tukang Indonesia. Data histori penjualan tersebut akan dibagi menjadi 80% untuk dataset training dan 20% untuk dataset testing. Metode Item-based Collaborative Filtering pada penelitian ini memakai algoritma Cosine Similarity untuk menghitung tingkat kemiripan antar produk. Prediksi score memakai rumus Weighted Sum dan dalam menghitung tingkat error memakai rumus Root Mean Squared Error. Hasil dari penelitian ini memperlihatkan rekomendasi top 10 produk per pelanggan. Produk yang tampil merupakan produk yang memiliki score tertinggi dari pelanggan tersebut. Penelitian ini dapat menjadi referensi dan acuan bagi perusahaan dalam memberikan rekomendasi produk yang dibutuhkan oleh pelanggan.

scholarly journals Predicting the band gap of binary compounds from machine-learning regression methods

2021 ◽  
Author(s):  
Mengbo Guo ◽  
Xuyang Xu ◽  
Han Xie
Keyword(s):  
Machine Learning ◽  
Band Gap ◽  
Density Functional ◽  
Mean Squared Error ◽  
Gradient Boosting ◽  
Functional Theory ◽  
Regression Methods ◽  
Squared Error ◽  
State Band ◽  
Binary Compounds

Density functional theory (DFT) is a ubiquitous first-principles method, but the approximate nature of the exchange-correlation functional poses an inherent limitation for the accuracy of various computed properties. In this context, surrogate models based on machine learning have the potential to provide a more efficient and physically meaningful understanding of electronic properties, such as the band gap. Here, we construct a gradient boosting regression (GBR) model for prediction of the band gap of binary compounds from simple physical descriptors, using a dataset of over 4000 DFT-computed band gaps. Out of 27 features, electronegativity, periodic group, and highest occupied energy level exhibit the highest importance score, consistent with the underlying physics of the electronic structure. We obtain a model accuracy of 0.81 and root mean squared error of 0.26 eV using the top five features, achieving accuracy comparable to previously reported values but employing less number of features. Our work presents a rapid and interpretable prediction model for solid-state band gap with high fidelity to DFT and can be extended beyond binary materials considered in this study.

scholarly journals Equations Relating Compacted and Uncompacted Live Crown Ratio for Common Tree Species in the South

2010 ◽  
Vol 34 (3) ◽  
pp. 118-123 ◽  
Author(s):  
KaDonna C. Randolph
Keyword(s):  
Mean Squared Error ◽  
Model Performance ◽  
Absolute Error ◽  
Logistic Function ◽  
Root Mean Squared Error ◽  
Fit Statistics ◽  
Squared Error ◽  
Hardwood Species ◽  
Using Data ◽  
Species Specific

Abstract Species-specific equations to predict uncompacted crown ratio (UNCR) from compacted live crown ratio (CCR), tree length, and stem diameter were developed for 24 species and 12 genera in the southern United States. Using data from the US Forest Service Forest Inventory and Analysis program, nonlinear regression was used to model UNCR with a logistic function. Model performance was evaluated with standard fit statistics (root mean squared error, mean absolute error, mean error, and model efficiency) and by comparing the results of using the observed and predicted UNCR values in secondary applications. Root mean squared error for the regression models ranged from 0.062 to 0.176 UNCR and averaged 0.114 UNCR across all models. Height to live crown base calculations and crown width estimations based on the observed and predicted UNCR values were in close agreement. Overall, the models performed well for the Pinus and Taxodium genera and several individual hardwood species; however, model performance was generally poor for the Acer, Quercus, and Carya genera.

scholarly journals PREDIKSI DATA TRANSAKSI PENJUALAN TIME SERIES MENGGUNAKAN REGRESI LSTM

2020 ◽  
Vol 9 (1) ◽  
pp. 1
Author(s):  
Marie Luthfi Ashari ◽  
Mujiono Sadikin
Keyword(s):  
Machine Learning ◽  
Time Series ◽  
Short Term Memory ◽  
Mean Squared Error ◽  
Percentage Error ◽  
Short Term ◽  
Term Memory ◽  
Root Mean Squared Error ◽  
Squared Error ◽  
Long Short Term Memory

Sebagai upaya untuk memenangkan persaingan di pasar, perusahaan farmasi harus menghasilkan produk obat – obatan yang berkualitas. Untuk menghasilkan produk yang berkualitas, diperlukan perencanaan produksi yang baik dan efisien. Salah satu dasar perencanaan produksi adalah prediksi penjualan. PT. Metiska Farma telah menerapkan metode prediksi dalam proses produksi, akan tetapi prediksi yang dihasilkan tidak akurat sehingga menyebabkan tidak optimal dalam memenuhi permintaan pasar. Untuk meminimalisir masalah kurang akuratnya proses prediksi tersebut, dalam penelitian yang disajikan pada makalah ini dilakukan uji coba prediksi menggunakan teknik Machine Learning dengan metode Regresi Long Short Term Memory (LSTM). Teknik yang diusulkan diuji coba menggunakan dataset penjualan produk “X” dari PT. Metiska Farma dengan parameter kinerja Root Mean Squared Error (RMSE) dan MAPE (Mean Absolute Percentage Error). Hasil penelitian ini berupa nilai rata – rata evaluasi error dari pemodelan data training dan data testing. Di mana hasil menunjukan bahwa Regresi LSTM memiliki nilai prediksi penjualan dengan evaluasi model melalui RMSE sebesar 286.465.424 untuk data training dan 187.013.430 untuk data testing. Untuk nilai MAPE sebesar 787% dan 309% untuk data training dan data testing secara berurut.

scholarly journals Algoritma Deep Learning-LSTM untuk Memprediksi Umur Transformator

2021 ◽  
Vol 8 (3) ◽  
pp. 539
Author(s):  
Ayu Ahadi Ningrum ◽  
Iwan Syarif ◽  
Agus Indra Gunawan ◽  
Edi Satriyanto ◽  
Rosmaliati Muchtar
Keyword(s):  
Quality Of Service ◽  
Deep Learning ◽  
Linear Regression ◽  
Multilayer Perceptron ◽  
Mean Squared Error ◽  
Series Data ◽  
Gradient Boosting ◽  
Root Mean Squared Error ◽  
Squared Error

<p>Kualitas dan ketersediaan pasokan listrik menjadi hal yang sangat penting. Kegagalan pada transformator menyebabkan pemadaman listrik yang dapat menurunkan kualitas layanan kepada pelanggan. Oleh karena itu, pengetahuan tentang umur transformator sangat penting untuk menghindari terjadinya kerusakan transformator secara mendadak yang dapat mengurangi kualitas layanan pada pelanggan. Penelitian ini bertujuan untuk mengembangkan aplikasi yang dapat memprediksi umur transformator secara akurat menggunakan metode <em>Deep Learning-LSTM. LSTM </em>adalah metode yang dapat digunakan untuk mempelajari suatu pola pada data deret waktu. Data yang digunakan dalam penelitian ini bersumber dari 25 unit transformator yang meliputi data dari sensor arus, tegangan, dan suhu. Analisis performa yang digunakan untuk mengukur kinerja LSTM adalah <em>Root Mean Squared Error</em> (RMSE) dan <em>Squared Correlation (SC</em>). Selain LSTM, penelitian ini juga menerapkan <em>algoritma Multilayer Perceptron, Linear Regression,</em> dan <em>Gradient Boosting Regressor</em> sebagai algoritma pembanding.  Hasil eksperimen menunjukkan bahwa LSTM mempunyai kinerja yang sangat bagus setelah dilakukan pencarian komposisi data, seleksi fitur menggunakan algoritma KBest dan melakukan percobaan beberapa variasi parameter. Hasil penelitian menunjukkan bahwa metode <em>Deep Learning-LSTM</em> mempunyai kinerja yang lebih baik daripada 3 algoritma lain yaitu nilai RMSE= 0,0004 dan nilai <em>Squared Correlation</em>= 0,9690.</p><p> </p><p><em><strong>Abstract</strong></em></p><p><em></em><em>The quality and availability of the electricity supply is very important. Failures in the transformer cause power outages which can reduce the quality of service to customers. Therefore, knowledge of transformer life is very important to avoid sudden transformer damage which can reduce the quality of service to customers. This study aims to develop applications that can predict transformer life accurately using the Deep Learning-LSTM method. LSTM is a method that can be used to study a pattern in time series data. The data used in this research comes from 25 transformer units which include data from current, voltage, and temperature sensors. The performance analysis used to measure LSTM performance is Root Mean Squared Error (RMSE) and Squared Correlation (SC). Apart from LSTM, this research also applies the Multilayer Perceptron algorithm, Linear Regression, and Gradient Boosting Regressor as a comparison algorithm. The experimental results show that LSTM has a very good performance after searching for the composition of the data, selecting features using the KBest algorithm and experimenting with several parameter variations. The results showed that the Deep Learning-LSTM method had better performance than the other 3 algorithms, namely the value of RMSE = 0.0004 and the value of Squared Correlation = 0.9690.</em></p>

Um sistema baseado em machine learning para apoio à decisão no gerenciamento de produção apícola

2021 ◽  
Vol 11 (1) ◽  
pp. 08-19
Author(s):  
Weskley Damasceno Silva ◽  
Silas Santiago Lopes Pereira ◽  
Daniel Santiago Pereira ◽  
Michell Olívio Xavier da Costa
Keyword(s):  
Machine Learning ◽  
Random Forest ◽  
Decision Tree ◽  
Support Vector Regression ◽  
Multilayer Perceptron ◽  
Mean Squared Error ◽  
Support Vector ◽  
Root Mean Squared Error ◽  
Squared Error

O setor apícola tem ganhado grandes proporções nos últimos tempos em termos de produção e comercialização de produtos, como o mel e seus derivados. O Brasil, apesar de ter acompanhado esse crescimento e possuir boas características para o desenvolvimento da apicultura, ainda sofre com a limitação no uso de ferramentas tecnológicas, o que afeta diretamente os níveis de produção. Este artigo propõe o desenvolvimento de uma ferramenta tecnológica que auxilie o apicultor no gerenciamento eficiente da produção apícola e na tomada de decisão a partir de modelos preditivos baseados em Machine Learning (ML) e integrados a um sistema web. Para tanto, foram utilizados diferentes algoritmos de ML para predição de produção de mel, tais como a Regressão Linear Múltipla, Decision Tree, Random Forest, Multilayer Perceptron (MLP) e Support Vector Regression (SVR). Os modelos gerados foram avaliados com base no coeficiente de determinação (R2 ou Score) e o cálculo de erro das predições utilizando a Root Mean Squared Error (RMSE). Os resultados desta pesquisa contam com um sistema web em desenvolvimento e resultados dos experimentos realizados, que mostram uma melhor performance da técnica MLP com Score de 0.98 e RMSE de 711196 libras.

scholarly journals Vorhersage der Fließgewässertemperaturen in österreichischen Einzugsgebieten mittels Machine Learning-Verfahren

2021 ◽  
Author(s):  
Moritz Feigl ◽  
Katharina Lebiedzinski ◽  
Mathew Herrnegger ◽  
Karsten Schulz
Keyword(s):  
Machine Learning ◽  
Neural Networks ◽  
Random Forest ◽  
Recurrent Neural Networks ◽  
Mean Squared Error ◽  
Feedforward Neural Networks ◽  
Gradient Boosting ◽  
Squared Error ◽  
Extreme Gradient Boosting ◽  
Lineare Regression

ZusammenfassungDie Fließgewässertemperatur ist ein essenzieller Umweltfaktor, der das Potenzial hat, sowohl ökologische als auch sozio-ökonomische Rahmenbedingungen im Umfeld eines Gewässers zu verändern. Um Fließgewässertemperaturen als Grundlage für effektive Anpassungsstrategien für zukünftige Veränderungen (z. B. durch den Klimawandel) berechnen zu können, sind adäquate Modellierungskonzepte notwendig. Die vorliegende Studie untersucht hierfür 6 Machine Learning-Modelle: Schrittweise Lineare Regression, Random Forest, eXtreme Gradient Boosting, Feedforward Neural Networks und zwei Arten von Recurrent Neural Networks. Die Modelle wurden an 10 österreichischen Einzugsgebieten mit unterschiedlichen physiographischen Eigenschaften und Eingangsdatenkombinationen getestet. Die Hyperparameter der angewandten Modelle wurden mittels Bayes’scher Hyperparameteroptimierung optimiert. Um die Ergebnisse mit anderen Studien vergleichbar zu machen, wurden die Vorhersagen der 6 Machine Learning-Modelle den Ergebnissen der linearen Regression und dem häufig verwendeten und bekannten Wassertemperaturmodell air2stream gegenübergestellt.Von den 6 getesteten Modellen zeigten die Feedforward Neural Networks und das eXtreme Gradient Boosting die besten Vorhersagen in jeweils 4 von 10 Einzugsgebieten. Mit einem durchschnittlichen RMSE (Wurzel der mittleren Fehlerquadratsumme; root mean squared error) von 0,55 °C konnten die getesteten Modelle die Fließgewässertemperaturen deutlich besser prognostizieren als die lineare Regression (1,55 °C) und air2stream (0,98 °C). Generell zeigten die Ergebnisse der 6 Modelle eine sehr vergleichbare Leistung mit lediglich einer mittleren Abweichung um den Medianwert von 0,08 °C zwischen den einzelnen Modellen. Im größten untersuchten Einzugsgebiet – Donau bei Kienstock – wiesen Recurrent Neural Networks die höchste Modellgüte auf, was darauf hinweist, dass sie sich am besten eignen, wenn im Einzugsgebiet Prozesse mit langfristigen Abhängigkeiten ausschlaggebend sind. Die Wahl der Hyperparameter beeinflusste die Vorhersagefähigkeit der Modelle stark, was die Bedeutung der Hyperparameteroptimierung besonders hervorhebt.Die Ergebnisse dieser Studie fassen die Bedeutung unterschiedlicher Eingangsdaten, Modelle und Trainingscharakteristiken für die Modellierung von mittleren täglichen Fließgewässertemperaturen zusammen. Gleichzeitig dient diese Studie als Basis für die Entwicklung zukünftiger Modelle für eine regionale Fließgewässertemperaturvorhersage. Die getesteten Modelle stehen im open source R‑Paket wateRtemp allen AnwenderInnen der Forschungsgemeinschaft und der Praxis zur Verfügung.

scholarly journals Imputing Parking Usage on Sparsely Monitored Areas Within Amsterdam Through the Application of Machine Learning

2021 ◽  
pp. 036119812110171
Author(s):  
Jeroen Schmidt ◽  
Elenna Dugundji ◽  
Bas Schotten
Keyword(s):  
Machine Learning ◽  
Mean Squared Error ◽  
Road Networks ◽  
Neighborhood Characteristics ◽  
Carbon Footprints ◽  
Root Mean Squared Error ◽  
Squared Error ◽  
Occupancy Patterns

Effective parking policy is essential for cities to reduce the demand their road networks experience and to combat their carbon footprints. Existing research in the application of machine learning to understand parking behavior assumes that cities have prohibitively expensive stationary parking sensors installed, while no research has yet attempted to use machine learning to impute for parking behavior using mobile probe data of sparsely monitored areas. To this end, this paper shows that it is indeed feasible to impute parking pressure (occupation as a percentage). Gradient boosted trees were found to perform the best with an R2 score of 0.20 and root mean squared error (RMSE) score of 0.087. This paper also found that three unique parking occupancy patterns exist in Amsterdam and that this information, in combination with neighborhood characteristics, has an impact on imputation under certain conditions.

Use of reflectance spectroscopy to estimate the organic carbon and CaCO3 contents of soils

2012 ◽  
Vol 61 (2) ◽  
pp. 277-290 ◽  
Author(s):  
Ádám Csorba ◽  
Vince Láng ◽  
László Fenyvesi ◽  
Erika Michéli
Keyword(s):  
Organic Carbon ◽  
Least Squares ◽  
Partial Least Squares ◽  
Partial Least Squares Regression ◽  
Mean Squared Error ◽  
Reflectance Spectroscopy ◽  
Least Squares Regression ◽  
Root Mean Squared Error ◽  
Squared Error

Napjainkban egyre nagyobb igény mutatkozik olyan technológiák és módszerek kidolgozására és alkalmazására, melyek lehetővé teszik a gyors, költséghatékony és környezetbarát talajadat-felvételezést és kiértékelést. Ezeknek az igényeknek felel meg a reflektancia spektroszkópia, mely az elektromágneses spektrum látható (VIS) és közeli infravörös (NIR) tartományában (350–2500 nm) végzett reflektancia-mérésekre épül. Figyelembe véve, hogy a talajokról felvett reflektancia spektrum információban nagyon gazdag, és a vizsgált tartományban számos talajalkotó rendelkezik karakterisztikus spektrális „ujjlenyomattal”, egyetlen görbéből lehetővé válik nagyszámú, kulcsfontosságú talajparaméter egyidejű meghatározása. Dolgozatunkban, a reflektancia spektroszkópia alapjaira helyezett, a talajok ösz-szetételének meghatározását célzó módszertani fejlesztés első lépéseit mutatjuk be. Munkánk során talajok szervesszén- és CaCO3-tartalmának megbecslését lehetővé tévő többváltozós matematikai-statisztikai módszerekre (részleges legkisebb négyzetek módszere, partial least squares regression – PLSR) épülő prediktív modellek létrehozását és tesztelését végeztük el. A létrehozott modellek tesztelése során megállapítottuk, hogy az eljárás mindkét talajparaméter esetében magas R2értéket [R2(szerves szén) = 0,815; R2(CaCO3) = 0,907] adott. A becslés pontosságát jelző közepes négyzetes eltérés (root mean squared error – RMSE) érték mindkét paraméter esetében közepesnek mondható [RMSE (szerves szén) = 0,467; RMSE (CaCO3) = 3,508], mely a reflektancia mérési előírások standardizálásával jelentősen javítható. Vizsgálataink alapján arra a következtetésre jutottunk, hogy a reflektancia spektroszkópia és a többváltozós kemometriai eljárások együttes alkalmazásával, gyors és költséghatékony adatfelvételezési és -értékelési módszerhez juthatunk.

scholarly journals Experimental Evaluation of Computer Vision and Machine Learning-Based UAV Detection and Ranging

Drones ◽  
2021 ◽  
Vol 5 (2) ◽  
pp. 37
Author(s):  
Bingsheng Wei ◽  
Martin Barczyk
Keyword(s):  
Machine Learning ◽  
Mean Squared Error ◽  
Tracking System ◽  
Ground Truth ◽  
White Background ◽  
Cascade Classifier ◽  
Detection Algorithms ◽  
Squared Error ◽  
Test Conditions ◽  
Video Feed

We consider the problem of vision-based detection and ranging of a target UAV using the video feed from a monocular camera onboard a pursuer UAV. Our previously published work in this area employed a cascade classifier algorithm to locate the target UAV, which was found to perform poorly in complex background scenes. We thus study the replacement of the cascade classifier algorithm with newer machine learning-based object detection algorithms. Five candidate algorithms are implemented and quantitatively tested in terms of their efficiency (measured as frames per second processing rate), accuracy (measured as the root mean squared error between ground truth and detected location), and consistency (measured as mean average precision) in a variety of flight patterns, backgrounds, and test conditions. Assigning relative weights of 20%, 40% and 40% to these three criteria, we find that when flying over a white background, the top three performers are YOLO v2 (76.73 out of 100), Faster RCNN v2 (63.65 out of 100), and Tiny YOLO (59.50 out of 100), while over a realistic background, the top three performers are Faster RCNN v2 (54.35 out of 100, SSD MobileNet v1 (51.68 out of 100) and SSD Inception v2 (50.72 out of 100), leading us to recommend Faster RCNN v2 as the recommended solution. We then provide a roadmap for further work in integrating the object detector into our vision-based UAV tracking system.

Sign in / Sign up

Export Citation Format

Share Document