scholarly journals Data-Driven Urban Traffic Accident Analysis and Prediction Using Logit and Machine Learning-Based Pattern Recognition Models

2021 ◽  
Vol 2021 ◽  
pp. 1-11
Author(s):  
Vahid Najafi Moghaddam Gilani ◽  
Seyed Mohsen Hosseinian ◽  
Meisam Ghasedi ◽  
Mohammad Nikookar
Keyword(s):  
Machine Learning ◽  
Pattern Recognition ◽  
Logistic Regression ◽  
Logit Model ◽  
Dominant Role ◽  
Poor Quality ◽  
Urban Traffic ◽  
Multiple Logistic Regression ◽  
Artificial Neural Network Ann

Modeling the severity of accidents based on the most effective variables accounts for developing a high-precision model presenting the possibility of occurrence of each category of future accidents, and it could be utilized to prioritize the corrective measures for authorities. The purpose of this study is to identify the variables affecting the severity of the injury, fatal, and property damage only (PDO) accidents in Rasht city by collecting information on urban accidents from March 2019 to March 2020. In this regard, the multiple logistic regression and the pattern recognition type of artificial neural network (ANN) as a machine learning solution are used to recognize the most influential variables on the severity of accidents and the superior approach for accident prediction. Results show that the multiple logistic regression in the forward stepwise method has R2 of 0.854 and an accuracy prediction power of 89.17%. It turns out that the accidents occurred between 18 and 24 and KIA Pride vehicle has the highest effect on increasing the severity of accidents, respectively. The most important result of the logit model accentuates the role of environmental variables, including poor lighting conditions alongside unfavorable weather and the dominant role of unsafe and poor quality of vehicles on increasing the severity of accidents. In addition, the machine learning model performs significantly better and has higher prediction accuracy (98.9%) than the logit model. In addition, the ANN model’s greater power to predict and estimate future accidents is confirmed through performance and sensitivity analysis.

scholarly journals Prediction and Analysis of the Severity and Number of Suburban Accidents Using Logit Model, Factor Analysis and Machine Learning: A case study in a developing country

2021 ◽  
Vol 3 (1) ◽  
Author(s):  
Meisam Ghasedi ◽  
Maryam Sarfjoo ◽  
Iraj Bargegol
Keyword(s):  
Machine Learning ◽  
Factor Analysis ◽  
Logit Model ◽  
Predictive Power ◽  
Dominant Role ◽  
Learning Approaches ◽  
Lighting Condition ◽  
Rainy Weather ◽  
Pedestrian Accidents ◽  
Effective Principal

AbstractThe purpose of this study is to investigate and determine the factors affecting vehicle and pedestrian accidents taking place in the busiest suburban highway of Guilan Province located in the north of Iran and provide the most accurate prediction model. Therefore, the effective principal variables and the probability of occurrence of each category of crashes are analyzed and computed utilizing the factor analysis, logit, and Machine Learning approaches simultaneously. This method not only could contribute to achieving the most comprehensive and efficient model to specify the major contributing factor, but also it can provide officials with suggestions to take effective measures with higher precision to lessen accident impacts and improve road safety. Both the factor analysis and logit model show the significant roles of exceeding lawful speed, rainy weather and driver age (30–50) variables in the severity of vehicle accidents. On the other hand, the rainy weather and lighting condition variables as the most contributing factors in pedestrian accidents severity, underline the dominant role of environmental factors in the severity of all vehicle-pedestrian accidents. Moreover, considering both utilized methods, the machine-learning model has higher predictive power in all cases, especially in pedestrian accidents, with 41.6% increase in the predictive power of fatal accidents and 12.4% in whole accidents. Thus, the Artificial Neural Network model is chosen as the superior approach in predicting the number and severity of crashes. Besides, the good performance and validation of the machine learning is proved through performance and sensitivity analysis.

scholarly journals The role of ambient parameters on transmission rates of the COVID-19 outbreak: A machine learning model

Work ◽  
2021 ◽  
pp. 1-9
Author(s):  
Amir Jamshidnezhad ◽  
Seyed Ahmad Hosseini ◽  
Leila Ibrahimi Ghavamabadi ◽  
Seyed Mahdi Hossaeini Marashi ◽  
Hediye Mousavi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Climatic Factors ◽  
Ambient Air ◽  
Coefficient Of Determination ◽  
Ann Model ◽  
Machine Learning Model ◽  
Testing Stage ◽  
Artificial Neural Network Ann ◽  
Air Conditioning Systems

BACKGROUND: In recent years the relationship between ambient air temperature and the prevalence of viral infection has been under investigation. OBJECTIVE: The study was aimed at providing the statistical and machine learning-based analysis to investigate the influence of climatic factors on frequency of COVID-19 confirmed cases in Iran. METHOD: The data of confirmed cases of COVID-19 and some climatic factors related to 31 provinces of Iran between 04/03/2020 and 05/05/2020 was gathered from official resources. In order to investigate the important climatic factors on the frequency of confirmed cases of COVID-19 in all studied cities, a model based on an artificial neural network (ANN) was developed. RESULTS: The proposed ANN model showed accuracy rates of 87.25%and 86.4%in the training and testing stage, respectively, for classification of COVID-19 confirmed cases. The results showed that in the city of Ahvaz, despite the increase in temperature, the coefficient of determination R2 has been increasing. CONCLUSION: This study clearly showed that, with increasing outdoor temperature, the use of air conditioning systems to set a comfort zone temperature is unavoidable. Thus, the number of positive cases of COVID-19 increases. Also, this study shows the role of closed-air cycle condition in the indoor environment of tropical cities.

scholarly journals PREDIKSI STATUS PENGIRIMAN BARANG MENGGUNAKAN METODE MACHINE LEARNING

2020 ◽  
Vol 6 (2) ◽  
pp. 100-109
Author(s):  
Hardian Kokoh Pambudi ◽  
Putu Giri Artha Kusuma ◽  
Femi Yulianti ◽  
Kevin Ahessa Julian
Keyword(s):  
Machine Learning ◽  
Logistic Regression ◽  
Customer Service ◽  
Business Processes ◽  
Model Development ◽  
Service Level ◽  
Logistics Industry ◽  
Customer Service Level ◽  
Freight Forwarder ◽  
Artificial Neural Network Ann

One of the key performance indicators for the logistics industry, especially freight forwarder company (cargo), is the delivery time. This is still a challenge in this industry in terms of ensuring the customer service level and reducing transportation costs. On the other hand, the development of information technology now allows an organization or company to collect large amounts of data automatically. A decent method that can be used to analyze the data for prediction purposes is machine learning, which is a method of extracting data into a certain pattern of information. This research aims to apply three machine learning methods to estimate the status of shipping goods. The method used in this study follows the machine learning process published by the Cross Industry Standard Process for Data Mining (CRISP-DM), namely; business processes understanding, data understanding, data preparation, model development, evaluation, and implementation. Based on the results of the study, the random forest method produces better accuracy than the logistic regression and artificial neural network (ANN) methods, which is 76.6%, while the results of ANN and logistic regression methods are 73.81% and 72.84% respectively.  

scholarly journals Smoking Cessation Intention and Its Association with Advice to Quit from Significant Others and Medical Professionals

2021 ◽  
Vol 18 (6) ◽  
pp. 2899
Author(s):  
Jun Hyun Hwang ◽  
Soon-Woo Park
Keyword(s):  
Smoking Cessation ◽  
Logistic Regression ◽  
Regression Analysis ◽  
Multiple Logistic Regression Analysis ◽  
Significant Others ◽  
Intention To Quit ◽  
Medical Professionals ◽  
Multiple Logistic Regression ◽  
Quit Smoking

Few studies have simultaneously considered the effects of significant others and medical professionals’ advice to quit smoking on smoking cessation intention. The present study involved 3841 current adult Korean smokers, divided into four groups with an intention to quit within 1 month, within 6 months, someday, and without intention to quit. Multinomial multiple logistic regression analysis was conducted according to smoking cessation intention level, adjusted for potential confounders, including past smoking cessation attempts. Smokers who had been advised to quit smoking by both significant others and medical professionals, significant others only, and medical professionals only were 2.63 (95% confidence interval (CI): 1.62–4.29), 1.84 (95% CI: 1.17–2.89), and 1.44 (95% CI: 0.70–2.94) times more likely to intend to quit within 1 month, respectively, than those who were not advised to quit. The odds ratios of an intention to quit within 6 months were 2.91 (95% CI: 1.87–4.54), 2.49 (95% CI: 1.69–3.68), and 0.94 (95% CI: 0.44–2.05), respectively. To promote smokers’ intention to quit, the role of significant others should be considered. Medical professionals’ advice to quit smoking remains important, increasing the effects of significant others’ advice.

scholarly journals Testing for Frequency and Structural Effects in an English Stress Shift

2010 ◽  
Vol 36 (1) ◽  
pp. 411 ◽  
Author(s):  
Morgan Sonderegger
Keyword(s):  
Logistic Regression ◽  
Language Change ◽  
Frequency Effect ◽  
Multiple Logistic Regression ◽  
Structural Effects ◽  
Conditioning Factors ◽  
Phonological Structure ◽  
Initial Syllable ◽  
As Effects

In lieu of an abstract, here is a brief excerpt:This paper considers the English diatonic stress shift (DSS). We examine the role of frequency and phonological structure as conditioning factors for which of a set of noun/verb pairs have undergone the DSS between 1700 and the present. Previous work by Phillips (1984) has shown a role of frequency: on average, words which have undergone the DSS have lower frequency than those which have not. Using a new dataset, we show via multiple logistic regression that there is a significant effect of frequency in the direction shown by Phillips, as well as effects of phonological structure; for example, a closed initial syllable makes change more likely. There is also a strong interaction between the effects of frequency and structure; in particular, structure modulates the strength and direction of the frequency effect. Our use of multiple regression follows its widespread use in sociolinguistics (e.g., Labov 1994) for quantifying the relative effects of different conditioning factors in cases of language change.

scholarly journals Sosialisasi Ilmu Statistik dalam Penelitian Bagi Mahasiswa Di Kota Palembang

2022 ◽  
Vol 5 (1) ◽  
pp. 7-12
Author(s):  
Muhammad Bahrul Ulum ◽  
Ayu Geby Gisela Syaputri
Keyword(s):  
Quantitative Research ◽  
Positive Impact ◽  
Dominant Role ◽  
Poor Quality ◽  
State Universities ◽  
Writing Research ◽  
Questions And Answers ◽  
The City

Abstract: Statistics and research are two things that cannot be separated. Although there are types of research that do not require the dominant role of statistics (qualitative research), but to be able to produce conclusions that can be generalized to a wider population, statistics is needed. Such research is quantitative research with a positivistic paradigm, ie a phenomenon is real if it can be seen, measured, and classified. The application of statistical science which is generally needed by students in writing research such as theses and theses, will have a positive impact, especially in improving the quality of the research. To achieve this goal, it is necessary to conduct socialization to students. The socialization was carried out to several students from both state universities and private universities in the city of Palembang. The socialization was done by introducing and giving tutorials on how to use statistical applications such as SPSS and Eviews, because several lecturers at several universities in Palembang complained about the poor quality of research and some said that their students did not really understand how to use SPSS and Eviews. The first result of this service is that students' understanding of SPSS and Eviews can be seen from discussions and questions and answers, second, namely the ability of students to apply the use of SPSS and Eviews in research.Keywords: research; socialization; statisticsAbstrak: Statistik dan penelitian merupakan dua hal yang tidak bisa dipisahkan. Meskipun ada jenis penelitian yang tidak membutuhkan peranan statistika yang dominan (penelitian kualitatif), namun untuk dapat menghasilkan kesimpulan yang dapat digeneralisasikan ke populasi yang lebih luas diperlukan ilmu statistika. Penelitian yang demikian adalah penelitian kuantitatif dengan paradigma yang positivistik, yakni suatu gejala itu adalah nyata jika bisa dilihat, diukur, dan diklasifikasikan. Penerapan ilmu statistik yang umumnya dibutuhkan mahasiswa dalam penulisan penelitian seperti skripsi dan tesis, akan berdampak positif terutama dalam meningkatan kualitas penelitian tersebut. Untuk mencapai tujuan tersebut maka perlu diadakan sosialisasi kepada mahasiswa. Sosialisasi dilakukan pada beberapa mahasiswa baik dari perguruan tinggi negeri maupun perguruan tinggi swasta di Kota Palembang. Sosialisasi dilakukan dengan cara mengenalkan dan memberikan tutorial bagaimana penggunaan aplikasi statistic seperti, SPSS dan Eviews, karena beberapa dosen di beberapa universitas di Palembang mengeluhkan buruknya kualitas penelitian dan ada juga yang mengatakan bahwa mahasiswa mereka tidak begitu mengerti cara penggunaan SPSS dan Eviews. Hasil dari pengabdian ini yang pertama adalah pemahaman mahasiswa mengenai SPSS dan Eviews dapat dilihat dari diskusi dan tanya jawab, kedua yaitu kemampuan mahasiswa dalam menerapkan penggunaan SPSS dan Eviews dalam penelitian.Kata Kunci: penelitian; sosialisasi; statistik

scholarly journals Perbandingan Model Logistic Regression dan Artificial Neural Network pada Prediksi Pembatalan Hotel

2021 ◽  
Vol 6 (1) ◽  
pp. 29
Author(s):  
Moch Shandy Tsalasa Putra ◽  
Yufis Azhar
Keyword(s):  
Neural Network ◽  
Machine Learning ◽  
Artificial Neural Network ◽  
Logistic Regression ◽  
Management Systems ◽  
Complex Data ◽  
Hotel Performance ◽  
Artificial Neural ◽  
Artificial Neural Network Ann ◽  
Modern Era

Prediction for canceled booking hotels is an important part of hotel revenue management systems in the modern era. Because the predicted result can be used for the optimization of hotel performance. The application of machine learning will be very helpful for predicting canceled booking hotels because machine learning can process complex data. In this research, the proposed methods are Artificial Neural Network (ANN) and Logistic Regression. Later it will be done five times experiments with hyperparameter tuning to see which method is the most optimal to do prediction canceled booking hotel. From five times experiments, experiments number five (logistic regression with GridSearchCV) is the most optimal for predicting canceled booking hotels, with 79.77% accuracy, 85.86% precision, and 55.07% recall.

scholarly journals The Role of Ambient parameters on Transmission Rates of the COVID-19 Outbreak: A machine learning model

2021 ◽  
Author(s):  
Amir Jamshidnezhad ◽  
Seyed Ahmad Hosseini ◽  
Seyed Mahdi Hossaeini Marashic ◽  
Leila Ibrahimi Ghavamabadi ◽  
Hediye Mousavi ◽  
...  
Keyword(s):  
Machine Learning ◽  
Climatic Factors ◽  
Ambient Air ◽  
Coefficient Of Determination ◽  
Ann Model ◽  
Machine Learning Model ◽  
Testing Stage ◽  
Artificial Neural Network Ann ◽  
Air Conditioning Systems

Abstract The relation between ambient air temperature and prevalence of viral infection has been under investigation in recent years. The study was aimed at providing the statistical and machine learning-based analysis to investigate the influence of climatic factors on frequency of COVID-19 confirmed cases in Iran. The data of confirmed cases of COVID-19 and some climatic factors related to 31 provinces of Iran during 04/03/2020 to 05/05/2020 was gathered from the official resources. In order to investigate the important climatic factors on the frequency of confirmed cases of COVID-19 in all studied cities, a model based on an artificial neural network (ANN) was developed. The proposed ANN model showed accuracy rates of 87.25% and 86.4% in the training and testing stage, respectively, for classification of COVID-19 confirmed cases. The results showed that in the city of Ahvaz, despite the increase in temperature, the coefficient of determination R2 has been increasing. This study clearly showed that, with increasing outdoor temperature, the use of air conditioning systems to set a comfort zone temperature is unavoidable; thus, the number of positive cases of COVID-19 increases. Also, this study shows the role of closed-air cycle condition in the indoor environment of tropical cities.

scholarly journals Serum Procalcitonin as a Diagnostic Marker for Systemic Inflammatory Response Syndrome in Intensive Care Unit Patients

2020 ◽  
Author(s):  
Rama Mishra Ramapriya ◽  
Pallavi Prakash
Keyword(s):  
Intensive Care Unit ◽  
Logistic Regression ◽  
Intensive Care ◽  
Systemic Inflammatory Response Syndrome ◽  
Inflammatory Response ◽  
Predictive Value ◽  
Systemic Inflammatory Response ◽  
Multiple Logistic Regression ◽  
Early Assessment

Introduction: Early assessment of Systemic Inflammatory Response Syndrome (SIRS) through various biomarkers like Procalcitonin (PCT), C-reactive Protein (CRP), Interleukin-1 (IL-1) etc., is crucial to manage the outcome of patients. Levels of PCT concerning its likelihood to distinguish patients with SIRS and non-SIRS and the possibility to predict mortality in patients with sepsis has been variable. Aim: To investigate the role of PCT in early diagnosis of sepsis in patients admitted to Intensive Care Unit (ICU). Materials and Methods: In this prospective observational study, 136 patients hospitalised in ICU at Vydehi Institute of Medical Sciences and Research Centre, Bangalore, Karnataka, India, between July 2019 to June 2020 were evaluated and PCT was analysed using Finecare™ PCT rapid test. Receiver Operating Characteristic (ROC) curve analysis and multiple logistic regression was carried out to detect the association of predictive PCT value with its outcomes. Results: PCT showed the best predictive value in the diagnosis of SIRS at 1.68 ng/mL (Area Under Curve (AUC)-0.87; p<0.05) having Positive Predictive Value (PPV) and Negative Predictive Value (NPV) of 90.43% and 73.81%, respectively. Multiple logistic regression model adjusted for age, weight, and duration of stay to predict the outcome of SIRS, positive blood culture and fatality case rate derived a significant association of PCT with Odds Ratio (OR) being 1.23 (1.11-2.31), 1.06 (1.01-1.98) and 1.76 (1.08-2.14), respectively. Conclusion: Early identification and treatment for sepsis significantly affects mortality. It appears that consecutive measurements of biomarkers could be valuable, but further prospective studies are important to characterise the role of PCT as a prognostic marker in sepsis and severe sepsis.

scholarly journals The Effects of Illness Perception on Diet Adherence in Patients With Hypertension

2021 ◽  
Vol 6 (2) ◽  
pp. 65-72
Author(s):  
Leila Rouhi Balasi ◽  
◽  
Arsalan Salari ◽  
Abdolhosein Emami Sigaroudi ◽  
Asieh Ashouri ◽  
...  
Keyword(s):  
Logistic Regression ◽  
Multiple Logistic Regression Analysis ◽  
Illness Perception ◽  
Analysis Data ◽  
Study Data ◽  
Dietary Adherence ◽  
Multiple Logistic Regression ◽  
Cross Sectional ◽  
Diet Adherence

Background: The role of nutrition is undeniable in controlling hypertension; diet is among the most effective non-pharmaceutical methods. The current study aimed to determine the role of illness perception on diet adherence in patients with hypertension. Materials & Methods: This cross-sectional study examined 268 patients with hypertension. The study sample was selected by convenience sampling method. The study tool consisted of the patients’ individual, social, and clinical factors, illness perception about hypertension, and adherence to the diet. The necessary data were analyzed using multiple logistic regression models. Results: The Mean±SD score of illness perception was measured as 37.09±4.91 out of 56. Adherence to the recommended diet was relatively desirable in the majority of the examined patients (62%). Multiple logistic regression analysis data revealed no significant relationship between the scores of illness perception and dietary adherence (Adjusted OR=1.038, 95%CI: 0.974-1.105, P =0.250). The main predictor of dietary adherence was having hypertension dietary knowledge (OR=2.198, 95%CI: 1.198-4.035, P=0.011). Conclusion: Our study data revealed that increasing awareness among patients with hypertension complications can improve self-care behaviors, including adherence to standard diets. Therefore, emphasis on increasing awareness among these patients and their continued follow-up seems necessar

Sign in / Sign up

Export Citation Format

Share Document