Exploration of Driver Posture Monitoring Using Pressure Sensors with Lower Resolution

Pressure sensors are good candidates for measuring driver postural information, which is indicative for identifying driver’s intention and seating posture. However, monitoring systems based on pressure sensors must overcome the price barriers in order to be practically feasible. This study, therefore, was dedicated to explore the possibility of using pressure sensors with lower resolution for driver posture monitoring. We proposed pressure features including center of pressure, contact area proportion, and pressure ratios to recognize five typical trunk postures, two typical left foot postures, and three typical right foot postures. The features from lower-resolution mapping were compared with those from high-resolution Xsensor pressure mats on the backrest and seat pan. We applied five different supervised machine-learning techniques to recognize the postures of each body part and used leave-one-out cross-validation to evaluate their performance. A uniform sampling method was used to reduce number of pressure sensors, and five new layouts were tested by using the best classifier. Results showed that the random forest classifier outperformed the other classifiers with an average classification accuracy of 86% using the original pressure mats and 85% when only 8% of the pressure sensors were available. This study demonstrates the feasibility of using fewer pressure sensors for driver posture monitoring and suggests research directions for better sensor designs.

Download Full-text

Algebraic Shortcuts for Leave-One-Out Cross-Validation in Supervised Network Inference

10.1101/242321 ◽

2018 ◽

Author(s):

Michiel Stock ◽

Tapio Pahikkala ◽

Antti Airola ◽

Willem Waegeman ◽

Bernard De Baets

Keyword(s):

Machine Learning ◽

Biological Networks ◽

Regulatory Networks ◽

Network Inference ◽

Cross Validation ◽

Supervised Machine Learning ◽

Machine Learning Techniques ◽

Ligand Interaction ◽

Learning Techniques ◽

Leave One Out

AbstractMotivationSupervised machine learning techniques have traditionally been very successful at reconstructing biological networks, such as protein-ligand interaction, protein-protein interaction and gene regulatory networks. Recently, much emphasis has been placed on the correct evaluation of such supervised models. It is vital to distinguish between using the model to either predict new interactions in a given network or to predict interactions for a new vertex not present in the original network. Specific cross-validation schemes need to be used to assess the performance in such different prediction settings.ResultsWe present a series of leave-one-out cross-validation shortcuts to rapidly estimate the performance of state-of-the-art kernel-based network inference techniques.AvailabilityThe machine learning techniques with the algebraic shortcuts are implemented in the RLScore software package.

Download Full-text

Application of Machine Learning Techniques to Predict Binding Affinity for Drug Targets: A Study of Cyclin-Dependent Kinase 2

Current Medicinal Chemistry ◽

10.2174/2213275912666191102162959 ◽

2020 ◽

Vol 28 (2) ◽

pp. 253-265 ◽

Cited By ~ 3

Author(s):

Gabriela Bitencourt-Ferreira ◽

Amauri Duarte da Silva ◽

Walter Filgueira de Azevedo

Keyword(s):

Machine Learning ◽

Binding Affinity ◽

Predictive Performance ◽

Supervised Machine Learning ◽

Machine Learning Techniques ◽

Scoring Functions ◽

Cyclin Dependent Kinase ◽

Learning Models ◽

Learning Techniques ◽

Machine Learning Models

Background: The elucidation of the structure of cyclin-dependent kinase 2 (CDK2) made it possible to develop targeted scoring functions for virtual screening aimed to identify new inhibitors for this enzyme. CDK2 is a protein target for the development of drugs intended to modulate cellcycle progression and control. Such drugs have potential anticancer activities. Objective: Our goal here is to review recent applications of machine learning methods to predict ligand- binding affinity for protein targets. To assess the predictive performance of classical scoring functions and targeted scoring functions, we focused our analysis on CDK2 structures. Methods: We have experimental structural data for hundreds of binary complexes of CDK2 with different ligands, many of them with inhibition constant information. We investigate here computational methods to calculate the binding affinity of CDK2 through classical scoring functions and machine- learning models. Results: Analysis of the predictive performance of classical scoring functions available in docking programs such as Molegro Virtual Docker, AutoDock4, and Autodock Vina indicated that these methods failed to predict binding affinity with significant correlation with experimental data. Targeted scoring functions developed through supervised machine learning techniques showed a significant correlation with experimental data. Conclusion: Here, we described the application of supervised machine learning techniques to generate a scoring function to predict binding affinity. Machine learning models showed superior predictive performance when compared with classical scoring functions. Analysis of the computational models obtained through machine learning could capture essential structural features responsible for binding affinity against CDK2.

Download Full-text

Local mortality estimates during the COVID-19 pandemic in Italy

Journal of Population Economics ◽

10.1007/s00148-021-00857-y ◽

2021 ◽

Author(s):

Augusto Cerqua ◽

Roberta Di Stefano ◽

Marco Letta ◽

Sara Miccoli

Keyword(s):

Machine Learning ◽

Excess Mortality ◽

Control Method ◽

Local Level ◽

Supervised Machine Learning ◽

Machine Learning Techniques ◽

Mortality Data ◽

Official Method ◽

Learning Techniques ◽

Mortality Estimates

AbstractEstimates of the real death toll of the COVID-19 pandemic have proven to be problematic in many countries, Italy being no exception. Mortality estimates at the local level are even more uncertain as they require stringent conditions, such as granularity and accuracy of the data at hand, which are rarely met. The “official” approach adopted by public institutions to estimate the “excess mortality” during the pandemic draws on a comparison between observed all-cause mortality data for 2020 and averages of mortality figures in the past years for the same period. In this paper, we apply the recently developed machine learning control method to build a more realistic counterfactual scenario of mortality in the absence of COVID-19. We demonstrate that supervised machine learning techniques outperform the official method by substantially improving the prediction accuracy of the local mortality in “ordinary” years, especially in small- and medium-sized municipalities. We then apply the best-performing algorithms to derive estimates of local excess mortality for the period between February and September 2020. Such estimates allow us to provide insights about the demographic evolution of the first wave of the pandemic throughout the country. To help improve diagnostic and monitoring efforts, our dataset is freely available to the research community.

Download Full-text