Motion Prediction for Autonomous Vehicles from Lyft Dataset using Deep Learning

Mandal, Sampurna; Biswas, Swagatam; Balaş, Valentina E.; Shaw, Rabindra Nath; Ghosh, Ankush

doi:10.1109/iccca49541.2020.9250790

Cited by 84 publications

(18 citation statements)

References 13 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Mandal et al [13] had described four different types of algorithm for diabetic patient classification, namely, Naïve Bayes, Logistic Regression, ANNs, and Decision Tree. Some hyperparameters were tuned to enhance the accuracy of the model.…”

Section: Related Workmentioning

confidence: 99%

Machine Learning Technique to Prognosis Diabetes Disease: Random Forest Classifier Approach

Palimkar¹,

Shaw

Ghosh³

2021

Lecture Notes in Networks and Systems

Self Cite

126

View full text Add to dashboard Cite

Diabetes is one among many chronic diseases. It is the most common disease and lots of peoples are affected by this. There are many things that are liable for diabetes, mainly age, obesity, weakness, sudden weight loss, and many more. Diabetes patients have high risk of diseases like cardiopathy, renal disorder, stroke, nerve damage, eye damage, etc. Detection of the disease isn't very easy and prediction is additionally costlier. In today's situation, hospitals are extremely busy due to COVID-19 pandemic, and it might be revolutionary if one could know if they're at risk of being diabetic without visiting a doctor. But the rise in Artificial Intelligence techniques can be used for disease prognosis. The objective of this study is to develop a model with significant accuracy to diagnose diabetes in patients. Moreover, this paper also presents an effective diabetes prediction model for better classification of diabetes and to enhance the accuracy in diabetes prediction using several machine learning algorithms. Different machine learning algorithms are utilized for early stage diabetes prediction, namely, Logistic Regression, Random Forest Classifier, Support Vector Machine, Decision Trees, K-Nearest Neighbors, Gaussian Process Classifier, AdaBoost Classifier, and Gaussian Naïve Bayes. The performances of these models are measured on respective criteria like Accuracy, Precision, Recall, F-Measure, and Error. For this research work, latest available dataset dated 22nd July, 2020, is being utilized. Latest updated dataset will show comparatively better result.

show abstract

Section: Related Workmentioning

confidence: 99%

Machine Learning Technique to Prognosis Diabetes Disease: Random Forest Classifier Approach

Palimkar¹,

Shaw

Ghosh³

2021

Lecture Notes in Networks and Systems

Self Cite

126

View full text Add to dashboard Cite

show abstract

“…The motivation of this paper is to make a smart communication system for the smart city using the already existing resources by constructing an effective Wireless Sensor Network [8][9][10]. To make a smart city, any city can be chosen.…”

Section: Problem Formulation and Numerical Solutionsmentioning

confidence: 99%

Construction of Effective Wireless Sensor Network for Smart Communication Using Modified Ant Colony Optimization Technique

Banerjee¹,

De²,

Majumder

et al. 2021

Advanced Computing and Intelligent Technologies

Self Cite

View full text Add to dashboard Cite

Wireless Sensor Network (WSN) is generally used for constructing an efficient network with minimum infrastructure. With this note, the WSN can be considered to construct smart communication in the existing city to facilitate the inhabitants. Nowadays in India, so many cities are going to be transformed into smart cities. In those cities, the maximum electronic gadgets will be IoT enabled. These IoT enabled gadgets should be connected through a robust network. The WSN can be an alternative for constructing a robust network between the electronic devices and the local server (Sink Node). The WSN can also sense many external environmental factors to facilitate the user, such as traffic status, rainfall, heat or smoke, vibration, and pollution detection. One of the major important challenges for the construction of an effective Wireless Sensor Network is to use the existing infrastructure of a city. In this paper, the effective Wireless Sensor Network has been constructed using the existing infrastructure and this is the major reason to choose the existing roads to deploy the WSN nodes. One can easily use the existing lamp posts of those roads to deploy the WSN nodes. In this paper, the modified Ant Colony Optimization (ACO) technique has been used to construct efficient WSN. The ACO is the probabilistic technique which is used to solve computational problems of choosing a minimized

show abstract

“…Cho et al [24] proposed a deep learning-based algorithm (DLA) and variational autoencoder (VAE). The deep learning was made with 7 layers where there were 2 one-dimensional convolutional layers, 2 batch normalizations, 1 max-pooling, 1 dropout layer and one flatten layer.…”

Section: Survey Of Related Workmentioning

confidence: 99%

A Comparative Study of Myocardial Infarction Detection from ECG Data Using Machine Learning

Chakraborty

Chatterjee

Majumder

et al. 2021

Lecture Notes in Networks and Systems

Self Cite

View full text Add to dashboard Cite

Myocardial Infarction (MI) is a life-threatening heart disease, timely medical intervention of which can reduce the mortality rate. It can be detected from Electrocardiogram or ECG. Diagnostic methods of this disease by clinical approaches are typically invasive. They also do not fulfill the detection accuracy, and there is a chance of human error. In the medical field, machine learning techniques have great potential for disease diagnosis. We can achieve accurate detection from ECG by using deep learning methods. In this paper, we did a comprehensive comparative study of a few existing proposals with different approaches to detect and predict Myocardial infarction. And then we proposed a deep learning approach for future implementation in order to achieve superior performance.

show abstract

Motion Prediction for Autonomous Vehicles from Lyft Dataset using Deep Learning

Cited by 84 publications

References 13 publications

Machine Learning Technique to Prognosis Diabetes Disease: Random Forest Classifier Approach

Machine Learning Technique to Prognosis Diabetes Disease: Random Forest Classifier Approach

Construction of Effective Wireless Sensor Network for Smart Communication Using Modified Ant Colony Optimization Technique

A Comparative Study of Myocardial Infarction Detection from ECG Data Using Machine Learning

Contact Info

Product

Resources

About