Receive a weekly summary and discussion of the top papers of the week by leading researchers in the field.

General General

Workplace activity classification from shoe-based movement sensors.

In BMC biomedical engineering

Background : High occupational physical activity is associated with lower health. Shoe-based movement sensors can provide an objective measurement of occupational physical activity in a lab setting but the performance of such methods in a free-living environment have not been investigated. The aim of the current study was to investigate the feasibility and accuracy of shoe sensor-based activity classification in an industrial work setting.

Results : An initial calibration part was performed with 35 subjects who performed different workplace activities in a structured lab setting while the movement was measured by a shoe-sensor. Three different machine-learning models (random forest (RF), support vector machine and k-nearest neighbour) were trained to classify activities using the collected lab data. In a second validation part, 29 industry workers were followed at work while an observer noted their activities and the movement was captured with a shoe-based movement sensor. The performance of the trained classification models were validated using the free-living workplace data. The RF classifier consistently outperformed the other models with a substantial difference in in the free-living validation. The accuracy of the initial RF classifier was 83% in the lab setting and 43% in the free-living validation. After combining activities that was difficult to discriminate the accuracy increased to 96 and 71% in the lab and free-living setting respectively. In the free-living part, 99% of the collected samples either consisted of stationary activities or walking.

Conclusions : Walking and stationary activities can be classified with high accuracy from a shoe-based movement sensor in a free-living occupational setting. The distribution of activities at the workplace should be considered when validating activity classification models in a free-living setting.

Fridolfsson Jonatan, Arvidsson Daniel, Doerks Frithjof, Kreidler Theresa J, Grau Stefan

2020

Accelerometry, Occupational health, Physical activity, Workload

General General

Predicting Network Controllability Robustness: A Convolutional Neural Network Approach.

In IEEE transactions on cybernetics

Network controllability measures how well a networked system can be controlled to a target state, and its robustness reflects how well the system can maintain the controllability against malicious attacks by means of node removals or edge removals. The measure of network controllability is quantified by the number of external control inputs needed to recover or to retain the controllability after the occurrence of an unexpected attack. The measure of the network controllability robustness, on the other hand, is quantified by a sequence of values that record the remaining controllability of the network after a sequence of attacks. Traditionally, the controllability robustness is determined by attack simulations, which is computationally time consuming. In this article, a method to predict the controllability robustness based on machine learning using a convolutional neural network (CNN) is proposed, motivated by the observations that: 1) there is no clear correlation between the topological features and the controllability robustness of a general network; 2) the adjacency matrix of a network can be regarded as a grayscale image; and 3) the CNN technique has proved successful in image processing without human intervention. Under the new framework, a fairly large number of training data generated by simulations are used to train a CNN for predicting the controllability robustness according to the input network-adjacency matrices, without performing conventional attack simulations. Extensive experimental studies were carried out, which demonstrate that the proposed framework for predicting controllability robustness of different network configurations is accurate and reliable with very low overheads.

Lou Yang, He Yaodong, Wang Lin, Chen Guanrong

2020-Sep-09

General General

A Novel Feature Selection Approach Based on Tree Models for Evaluating the Punching Shear Capacity of Steel Fiber-Reinforced Concrete Flat Slabs.

In Materials (Basel, Switzerland)

When designing flat slabs made of steel fiber-reinforced concrete (SFRC), it is very important to predict their punching shear capacity accurately. The use of machine learning seems to be a great way to improve the accuracy of empirical equations currently used in this field. Accordingly, this study utilized tree predictive models (i.e., random forest (RF), random tree (RT), and classification and regression trees (CART)) as well as a novel feature selection (FS) technique to introduce a new model capable of estimating the punching shear capacity of the SFRC flat slabs. Furthermore, to automatically create the structure of the predictive models, the current study employed a sequential algorithm of the FS model. In order to perform the training stage for the proposed models, a dataset consisting of 140 samples with six influential components (i.e., the depth of the slab, the effective depth of the slab, the length of the column, the compressive strength of the concrete, the reinforcement ratio, and the fiber volume) were collected from the relevant literature. Afterward, the sequential FS models were trained and verified using the above-mentioned database. To evaluate the accuracy of the proposed models for both testing and training datasets, various statistical indices, including the coefficient of determination (R2) and root mean square error (RMSE), were utilized. The results obtained from the experiments indicated that the FS-RT model outperformed FS-RF and FS-CART models in terms of prediction accuracy. The range of R2 and RMSE values were obtained as 0.9476-0.9831 and 14.4965-24.9310, respectively; in this regard, the FS-RT hybrid technique demonstrated the best performance. It was concluded that the three hybrid techniques proposed in this paper, i.e., FS-RT, FS-RF, and FS-CART, could be applied to predicting SFRC flat slabs.

Lu Shasha, Koopialipoor Mohammadreza, Asteris Panagiotis G, Bahri Maziyar, Armaghani Danial Jahed

2020-Sep-03

feature selection, fiber-reinforced concrete, hybrid predictive models, punching shear capacity, tree model

General General

Predicting the Time Period of Extension of Lockdown due to Increase in Rate of COVID-19 Cases in India using Machine Learning.

In Materials today. Proceedings

The research paper proposes a methodology to predict the extension of lockdown in order to eradicate COVID-19 from India. All the concepts related to Coronavirus, its history, prevention and cure is explained in the research paper. Concept used to predict the number of active cases, deaths and recovery is Linear Regression which is an application of machine learning. Extension of lockdown is predicted on the basis of predicted number of active cases, deaths and recovery all over India. To predict the number of active cases, deaths and recovery, date wise analysis of current data was done and necessary parameters like daily recovery, daily deaths, increase rate of covid-19 cases were included. Graphical representation of each analysis and prediction was done in order to make predicted results more understandable. The combined analysis was performed at the end which included the final result of total cases of coronavirus in India. Combined analysis included the no. of cases from start of COVID-19 to the predicted end of cases all over India. [copyright information to be updated in production process].

Wadhwa Parth, Aishwarya Tripathi, Amrendra Singh, Prabhishek Diwakar, Manoj Kumar

2020-Aug-28

COVID-19, COVID-19 pandemic, Coronavirus India, Coronavirus pandemic, coronavirus, lockdown prediction

General General

COVID-19 Pandemic Cyclic Lockdown Optimization Using Reinforcement Learning

ArXiv Preprint

This work examines the use of reinforcement learning (RL) to optimize cyclic lockdowns, which is one of the methods available for control of the COVID-19 pandemic. The problem is structured as an optimal control system for tracking a reference value, corresponding to the maximum usage level of a critical resource, such as ICU beds. However, instead of using conventional optimal control methods, RL is used to find optimal control policies. A framework was developed to calculate optimal cyclic lockdown timings using an RL-based on-off controller. The RL-based controller is implemented as an RL agent that interacts with an epidemic simulator, implemented as an extended SEIR epidemic model. The RL agent learns a policy function that produces an optimal sequence of open/lockdown decisions such that goals specified in the RL reward function are optimized. Two concurrent goals were used: the first one is a public health goal that minimizes overshoots of ICU bed usage above an ICU bed threshold, and the second one is a socio-economic goal that minimizes the time spent under lockdowns. It is assumed that cyclic lockdowns are considered as a temporary alternative to extended lockdowns when a region faces imminent danger of overpassing resource capacity limits and when imposing an extended lockdown would cause severe social and economic consequences due to lack of necessary economic resources to support its affected population during an extended lockdown.

Mauricio Arango, Lyudmil Pelov

2020-09-10

General General

COVID-19 Pandemic Cyclic Lockdown Optimization Using Reinforcement Learning

ArXiv Preprint

This work examines the use of reinforcement learning (RL) to optimize cyclic lockdowns, which is one of the methods available for control of the COVID-19 pandemic. The problem is structured as an optimal control system for tracking a reference value, corresponding to the maximum usage level of a critical resource, such as ICU beds. However, instead of using conventional optimal control methods, RL is used to find optimal control policies. A framework was developed to calculate optimal cyclic lockdown timings using an RL-based on-off controller. The RL-based controller is implemented as an RL agent that interacts with an epidemic simulator, implemented as an extended SEIR epidemic model. The RL agent learns a policy function that produces an optimal sequence of open/lockdown decisions such that goals specified in the RL reward function are optimized. Two concurrent goals were used: the first one is a public health goal that minimizes overshoots of ICU bed usage above an ICU bed threshold, and the second one is a socio-economic goal that minimizes the time spent under lockdowns. It is assumed that cyclic lockdowns are considered as a temporary alternative to extended lockdowns when a region faces imminent danger of overpassing resource capacity limits and when imposing an extended lockdown would cause severe social and economic consequences due to lack of necessary economic resources to support its affected population during an extended lockdown.

Mauricio Arango, Lyudmil Pelov

2020-09-10