A Comparison of Machine Learning Methods for the Prediction of Traffic Speed in Urban Places

Rising interest in the field of Intelligent Transportation Systems combined with the increased availability of collected data allows the study of different methods for prevention of traffic congestion in cities. A common need in all of these methods is the use of traffic predictions for supporting planning and operation of the traffic lights and traffic management schemes. This paper focuses on comparing the forecasting effectiveness of three machine learning models, namely Random Forests, Support Vector Regression, and Multilayer Perceptron—in addition to Multiple Linear Regression—using probe data collected from the road network of Thessaloniki, Greece. The comparison was conducted with multiple tests clustered in three types of scenarios. The first scenario tests the algorithms on specific randomly selected dates on different randomly selected roads. The second scenario tests the algorithms on randomly selected roads over eight consecutive 15 min intervals; the third scenario tests the algorithms on random roads for the duration of a whole day. The experimental results show that while the Support Vector Regression model performs best at stable conditions with minor variations, the Multilayer Perceptron model adapts better to circumstances with greater variations, in addition to having the most near-zero errors.

Download Full-text

Real-Time Adaptive Traffic Signals Using Rate-Monotonic Scheduling

ITM Web of Conferences ◽

10.1051/itmconf/20192903002 ◽

2019 ◽

Vol 29 ◽

pp. 03002 ◽

Cited By ~ 1

Author(s):

Mãdãlin-Dorin Pop

Keyword(s):

Real Time ◽

Intelligent Transportation Systems ◽

Traffic Congestion ◽

Traffic Signals ◽

Fixed Time ◽

Transportation Systems ◽

Real Time Scheduling ◽

Traffic Lights ◽

Rate Monotonic ◽

Rate Monotonic Scheduling

The studies and real situations shown that the traffic congestion is one of nowadays highest problems. This problem wassolved in the past using roundabouts and traffic signals. Taking in account the number of cars that is increasing continuously, we can see that past approaches using traffic lights with fixed-time controller for traffic signals timing is obsolete. The present and the future is the using of Intelligent Transportation Systems. Traffic lights systems should be aware about realtime traffic parameters and should adapt accordingly to them. The purpose of this paper is to present a new approach to control traffic signals using rate-monotonic scheduling. Obtained results will be compared with the results obtained by using others real-time scheduling algorithms.

Download Full-text

Utilização de técnicas de Machine Learning e de Deep Learning para a predição de casos de internações causadas por dengue em municípios da Paraíba

10.5753/ercemapi.2021.17914 ◽

2021 ◽

Author(s):

Ewerthon Dyego de Araújo Batista ◽

Wellington Candeia de Araújo ◽

Romeryto Vieira Lira ◽

Laryssa Izabel de Araújo Batista

Keyword(s):

Neural Network ◽

Machine Learning ◽

Deep Learning ◽

Random Forest ◽

Convolutional Neural Network ◽

Support Vector Regression ◽

Multilayer Perceptron ◽

Support Vector

Dengue é um problema de saúde pública no Brasil, os casos da doença voltaram a crescer na Paraíba. O boletim epidemiológico da Paraíba, divulgado em agosto de 2021, informa um aumento de 53% de casos em relação ao ano anterior. Técnicas de Machine Learning (ML) e de Deep Learning estão sendo utilizadas como ferramentas para a predição da doença e suporte ao seu combate. Por meio das técnicas Random Forest (RF), Support Vector Regression (SVR), Multilayer Perceptron (MLP), Long ShortTerm Memory (LSTM) e Convolutional Neural Network (CNN), este artigo apresenta um sistema capaz de realizar previsões de internações causadas por dengue para as cidades Bayeux, Cabedelo, João Pessoa e Santa Rita. O sistema conseguiu realizar previsões para Bayeux com taxa de erro 0,5290, já em Cabedelo o erro foi 0,92742, João Pessoa 9,55288 e Santa Rita 0,74551.

Download Full-text

A Zoning Earthquake Casualty Prediction Model Based on Machine Learning

Remote Sensing ◽

10.3390/rs14010030 ◽

2021 ◽

Vol 14 (1) ◽

pp. 30

Author(s):

Boyi Li ◽

Adu Gong ◽

Tingting Zeng ◽

Wenxuan Bao ◽

Can Xu ◽

...

Keyword(s):

Machine Learning ◽

Prediction Model ◽

Support Vector Regression ◽

Prediction Method ◽

Historical Earthquakes ◽

Support Vector ◽

Learning Methods ◽

Support Vector Regression Model ◽

Machine Learning Methods ◽

Earthquake Casualty

The evaluation of mortality in earthquake-stricken areas is vital for the emergency response during rescue operations. Hence, an effective and universal approach for accurately predicting the number of casualties due to an earthquake is needed. To obtain a precise casualty prediction method that can be applied to regions with different geographical environments, a spatial division method based on regional differences and a zoning casualty prediction method based on support vector regression (SVR) are proposed in this study. This study comprises three parts: (1) evaluating the importance of influential features on seismic fatality based on random forest to select indicators for the prediction model; (2) dividing the study area into different grades of risk zones with a strata fault line dataset and WorldPop population dataset; and (3) developing a zoning support vector regression model (Z-SVR) with optimal parameters that is suitable for different risk areas. We selected 30 historical earthquakes that occurred in China’s mainland from 1950 to 2017 to examine the prediction performance of Z-SVR and compared its performance with those of other widely used machine learning methods. The results show that Z-SVR outperformed the other machine learning methods and can further enhance the accuracy of casualty prediction.

Download Full-text

The Data-Driven Multi-Step Approach for Dynamic Estimation of Buildings’ Interior Temperature

Energies ◽

10.3390/en13246654 ◽

2020 ◽

Vol 13 (24) ◽

pp. 6654

Author(s):

Stefano Villa ◽

Claudio Sassanelli

Keyword(s):

Machine Learning ◽

Regression Model ◽

Support Vector Regression ◽

Regression Models ◽

Absolute Error ◽

Data Driven ◽

Support Vector ◽

Support Vector Regression Model ◽

Prediction Horizon ◽

Dynamic Estimation

Buildings are among the main protagonists of the world’s growing energy consumption, employing up to 45%. Wide efforts have been directed to improve energy saving and reduce environmental impacts to attempt to address the objectives fixed by policymakers in the past years. Meanwhile, new approaches using Machine Learning regression models surged in the modeling and simulation research context. This research develops and proposes an innovative data-driven black box predictive model for estimating in a dynamic way the interior temperature of a building. Therefore, the rationale behind the approach has been chosen based on two steps. First, an investigation of the extant literature on the methods to be considered for tests has been conducted, shrinking the field of investigation to non-recursive multi-step approaches. Second, the results obtained on a pilot case using various Machine Learning regression models in the multi-step approach have been assessed, leading to the choice of the Support Vector Regression model. The prediction mean absolute error on the pilot case is 0.1 ± 0.2 °C when the offset from the prediction instant is 15 min and grows slowly for further future instants, up to 0.3 ± 0.8 °C for a prediction horizon of 8 h. In the end, the advantages and limitations of the new data-driven multi-step approach based on the Support Vector Regression model are provided. Relying only on data related to external weather, interior temperature and calendar, the proposed approach is promising to be applicable to any type of building without needing as input specific geometrical/physical characteristics.

Download Full-text

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

REVISTA BRASILEIRA DE AGROTECNOLOGIA ◽

10.18378/rebagro.v11i1.8679 ◽

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.

Download Full-text

Study on optimal conditions of flocculation in deinking wastewater treatment

Journal of Engineering and Applied Science ◽

10.1186/s44147-021-00044-6 ◽

2021 ◽

Vol 68 (1) ◽

Author(s):

Ming Li ◽

Kaitang Hu ◽

Jin Wang

Keyword(s):

Machine Learning ◽

Genetic Algorithm ◽

Wastewater Treatment ◽

Support Vector Regression ◽

Fitness Function ◽

Real Life ◽

Support Vector ◽

Optimal Conditions ◽

Support Vector Regression Model ◽

Hydraulic Conditions

AbstractFlocculation is an important method to treat paper manufacturing wastewater. Coagulants and flocculants added to wastewater facilitate the aggregation and sedimentation of various particles in the wastewater and lead to the formation of floc networks which can be easily removed using physical methods. The goal of this paper is to determine the optimal hydraulic conditions using machine learning in order to enable efficient flocculation and improve performance during the treatment of deinking wastewater. Experiments using polymerized aluminum chloride as flocculant to treat deinking wastewater were carried out. Based on the orthogonal array test, 16 different combinations of hydraulic conditions were chosen to investigate the performance of flocculation, which was indicated by the turbidity of the solution after treatment. To develop a model representing the relationship between the hydraulic conditions and the performance of wastewater treatment, the machine learning methods, support vector regression and Gaussian process regression, were compared, whereby the support vector regression method was chosen. According to the fitness function derived from the support vector regression model, a genetic algorithm was applied to evaluate the optimal hydraulic conditions. Based on the optimal conditions determined by the genetic algorithm and real-life experience, a set of hydraulic conditions were implemented experimentally. After treatment under higher stirring speed at 120 rpm for 1 min and lower stirring speed at 20 rpm for 5 min at a temperature of 20 °C, the turbidity of deinking wastewater was measured as 1 NTU. The turbidity reduction was as high as 99.6%, which indicated good performance of the deinking wastewater treatment.

Download Full-text

A Comprehensive Study on Intelligent Transportation Systems

SMART MOVES JOURNAL IJOSCIENCE ◽

10.24113/ijoscience.v4i10.167 ◽

2018 ◽

Vol 4 (10) ◽

pp. 10

Author(s):

Ankur Mishra ◽

Aayushi Priya

Keyword(s):

Intelligent Transportation Systems ◽

Traffic Congestion ◽

Transportation Systems ◽

Environmental Conservation ◽

Integrated System ◽

Transport Systems ◽

Transport Sector ◽

Intelligent Transport System ◽

Intelligent Transport ◽

Transportation Sector

Transportation or transport sector is a legal source to take or carry things from one place to another. With the passage of time, transportation faces many issues like high accidents rate, traffic congestion, traffic & carbon emissions air pollution, etc. In some cases, transportation sector faced alleviating the brutality of crash related injuries in accident. Due to such complexity, researchers integrate virtual technologies with transportation which known as Intelligent Transport System. Intelligent Transport Systems (ITS) provide transport solutions by utilizing state-of-the-art information and telecommunications technologies. It is an integrated system of people, roads and vehicles, designed to significantly contribute to improve road safety, efficiency and comfort, as well as environmental conservation through realization of smoother traffic by relieving traffic congestion. This paper aims to elucidate various aspects of ITS - it's need, the various user applications, technologies utilized and concludes by emphasizing the case study of IBM ITS.

Download Full-text

IMPLEMENTASI SUPPORT VECTOR MACHINE PADA PREDIKSI HARGA SAHAM GABUNGAN (IHSG)

Jurnal Ilmiah Teknologi dan Rekayasa ◽

10.35760/tr.2020.25i1.2571 ◽

2020 ◽

Vol 25 (1) ◽

pp. 24-38

Author(s):

Eka Patriya

Keyword(s):

Machine Learning ◽

Support Vector Machine ◽

Support Vector Regression ◽

Support Vector

Saham adalah instrumen pasar keuangan yang banyak dipilih oleh investor sebagai alternatif sumber keuangan, akan tetapi saham yang diperjual belikan di pasar keuangan sering mengalami fluktuasi harga (naik dan turun) yang tinggi. Para investor berpeluang tidak hanya mendapat keuntungan, tetapi juga dapat mengalami kerugian di masa mendatang. Salah satu indikator yang perlu diperhatikan oleh investor dalam berinvestasi saham adalah pergerakan Indeks Harga Saham Gabungan (IHSG). Tindakan dalam menganalisa IHSG merupakan hal yang penting dilakukan oleh investor dengan tujuan untuk menemukan suatu trend atau pola yang mungkin berulang dari pergerakan harga saham masa lalu, sehingga dapat digunakan untuk memprediksi pergerakan harga saham di masa mendatang. Salah satu metode yang dapat digunakan untuk memprediksi pergerakan harga saham secara akurat adalah machine learning. Pada penelitian ini dibuat sebuah model prediksi harga penutupan IHSG menggunakan algoritma Support Vector Regression (SVR) yang menghasilkan kemampuan prediksi dan generalisasi yang baik dengan nilai RMSE training dan testing sebesar 14.334 dan 20.281, serta MAPE training dan testing sebesar 0.211% dan 0.251%. Hasil penelitian ini diharapkan dapat membantu para investor dalam mengambil keputusan untuk menyusun strategi investasi saham.

Download Full-text

Stress evaluation in seven-wire strands based on singular value feature of ultrasonic guided waves

Structural Health Monitoring ◽

10.1177/14759217211005399 ◽

2021 ◽

pp. 147592172110053

Author(s):

Qian Ji ◽

Li Jian-Bin ◽

Liu Fan-Rui ◽

Zhou Jian-Ting ◽

Wang Xu

Keyword(s):

Dispersion Curve ◽

Support Vector Regression ◽

Stress Level ◽

Guided Waves ◽

Guided Wave ◽

Singular Value ◽

Support Vector ◽

Support Vector Regression Model ◽

Various Boundary Conditions ◽

Wave Methods

The seven-wire strands are the crucial components of prestressed structures, though their performance inevitably degrades with the passage of time. The ultrasonic guided wave methods have been intensely studied, owing to its tremendous potential for full-scale applications, among the existing nondestructive testing methods, for evaluating the stress status of strands. We have employed the theoretical and finite element methods to solve the dispersion curve of single wire and steel strands under various boundary conditions. Thereafter, the singular value decomposition was adopted to work with the simulated and experimental signals for extracting a feature vector that carries valuable stress status information. The effectiveness of the vector was verified by analyzing the relationship between the vector and the stress level. The vector was also used as an input to establish a support vector regression model. The accuracy of the model has been discussed for different sample sizes. The results show that the fundamental mode dispersion curve offset on the high-frequency part and cut-off frequency increases as the boundary constraints enhance. Simulated and experimental results have demonstrated the effectiveness and potential of the proposed support vector regression method for evaluating the stress level in the strands. This method performs well even at low stress levels and the reliability can be enhanced by adding more samples.

Download Full-text