Using an Interpretable Machine Learning Framework to Understand the Relationship of Mobility and Reliability Indices on Truck Drivers' Route Choices

2021 ◽  
pp. 1-10
Author(s):  
Xiaoqiang Kong ◽  
Yunlong Zhang ◽  
William L. Eisele ◽  
Xiao Xiao
Keyword(s):  
Machine Learning ◽  
Truck Drivers ◽  
Reliability Indices ◽  
Learning Framework ◽  
Interpretable Machine Learning ◽  
Route Choices ◽  
Relationship Of ◽  
The Relationship

scholarly journals DSSMFM: Combining user and item feature interactions for recommendation systems

2020 ◽  
Vol 309 ◽  
pp. 03010
Author(s):  
Weishan Zeng
Keyword(s):  
Machine Learning ◽  
Recommendation Systems ◽  
Machine Learning Algorithms ◽  
Model Data ◽  
New Model ◽  
Feature Interactions ◽  
Short Video ◽  
Item Attributes ◽  
Relationship Of ◽  
The Relationship

Effort has been done to optimize machine learning algorithms by applying relevant knowledges in data fields in recommendation systems. Ways are explored to discover the relationship of features independently, making the model more effective and robust. A new model, DSSMFM is proposed in this paper which combines user and item features interactions to improve the performance of recommendation systems. In this model, data are divided into user features and item features represented by one-hot vectors. The pre-training for the model is proceeded through FM, and implicit vectors are obtained for both user and item features. The implicit vectors are used as the input of DSSM, and the training of the DSSM part of the model will maximize the cosine distances of the user attributes vectors and the item attributes vectors. According to the experimental results on dataset of ICME 2019 Short Video Understanding and Recommendation Challenge, the model shows improvements on some results of the baselines.

scholarly journals Persepsi antara Risiko Keselamatan Berkendaraan dengan Perilaku Pemakaian Safety Belt pada Driver Truk

2018 ◽  
Vol 4 (2) ◽  
pp. 53
Author(s):  
Muhamad Bob Anthony
Keyword(s):  
Traffic Accidents ◽  
Truck Drivers ◽  
Driving Safety ◽  
Mining Company ◽  
Perception Of Safety ◽  
Safety Belt ◽  
Independent Variable ◽  
Safety Belts ◽  
Relationship Of ◽  
The Relationship

Deaths and injuries from traffic accidents have become health problems for people throughout the world including Indonesia. The saddest data from the victims who died due to traffic accidents found that 10,428 people were killed in 2017 because the drivers did not use seat belts. This research aims to see the relationship between the perception of safety risk i.e. the ability, knowledge and environmental factors with the behavior of the use of safety belts in truck drivers in mining companies. This research is a comparative causal research i.e. research that states the relationship of one variable causes other variables. What is affected is the dependent variable, namely the use of safety belt behavior and the influencing variable is the independent variable, namely the perception of the risk of driving safety. Participants are 25 mining company truck drivers. The data obtained is then processed and analyzed using the SPSS version 16. Based on the results of data processing and analysis, it is found that the ability, knowledge and work environment factors have an influence on the safety belt usage behavior.

scholarly journals Interpretable Machine Learning Framework Reveals Robust Gut Microbiome Features Associated With Type 2 Diabetes

2020 ◽  
Author(s):  
Wanglong Gou ◽  
Chu-wen Ling ◽  
Yan He ◽  
Zengliang Jiang ◽  
Yuanqing Fu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Type 2 Diabetes ◽  
Gut Microbiome ◽  
Diabetes Risk ◽  
Dietary Factors ◽  
Blood Metabolites ◽  
Learning Framework ◽  
Interpretable Machine Learning ◽  
Prospective Association

<b>OBJECTIVE </b>To identify the core gut microbial features associated with type 2 diabetes risk, and potential demographic, adiposity and dietary factors associated with these features.<b></b> <p><b>RESEARCH DESIGN AND METHODS </b><a>We used an interpretable machine learning framework to identify the type 2 diabetes-related </a>gut microbiome features in the cross-sectional analyses of three Chinese cohorts: <a></a><a>one discovery cohort </a>(n=1832, 270 cases) and two validation cohorts (cohort 1: n=203, 48 cases; cohort 2: n=7009, 608 cases). We constructed a microbiome risk score (MRS) with the identified features. We examined the prospective association of the MRS with glucose increment in 249 non-T2D participants, and assessed the correlation between the MRS and host blood metabolites (n=1016). We transferred human faecal samples with different MRS levels to <a>germ-free mice </a>to confirm the <a>MRS-</a>type 2 diabetes relationship. We then examined the prospective association of demographic, adiposity and dietary factors with the MRS (n=1832).<b></b></p> <p><b>RESULTS<a> </a></b><a></a><a>The MRS (including 14 </a>microbial features) consistently associated with type 2 diabetes, with risk ratio for per one unit change in MRS 1.28 (95%CI 1.23-1.33), 1.23 (1.13-1.34) and 1.12 (1.06-1.18) across 3 cohorts. The MRS was positively associated with future glucose increment (P<0.05), and was correlated with a variety of gut microbiota-derived blood metabolites. Animal study further <a>confirms the MRS-</a>type 2 diabetes relationship. Body fat distribution was found to be a key factor modulating the gut microbiome-type 2 diabetes relationship. <b></b></p> <b>CONCLUSIONS </b>Our results reveal a core set of gut microbiome features associated with type 2 diabetes risk and future glucose increment.

scholarly journals Artificial Intelligence and the Limitations of Information

Information ◽  
2018 ◽  
Vol 9 (12) ◽  
pp. 332 ◽  
Author(s):  
Paul Walton
Keyword(s):  
Artificial Intelligence ◽  
Machine Learning ◽  
Information Processing ◽  
General Intelligence ◽  
Selection Pressures ◽  
Artificial General Intelligence ◽  
Relationship Of ◽  
The Relationship ◽  
The Way

Artificial intelligence (AI) and machine learning promise to make major changes to the relationship of people and organizations with technology and information. However, as with any form of information processing, they are subject to the limitations of information linked to the way in which information evolves in information ecosystems. These limitations are caused by the combinatorial challenges associated with information processing, and by the tradeoffs driven by selection pressures. Analysis of the limitations explains some current difficulties with AI and machine learning and identifies the principles required to resolve the limitations when implementing AI and machine learning in organizations. Applying the same type of analysis to artificial general intelligence (AGI) highlights some key theoretical difficulties and gives some indications about the challenges of resolving them.

From Tf-Idf to Learning-to-Rank

2016 ◽  
pp. 1245-1292 ◽  
Author(s):  
Muhammad Ibrahim ◽  
Manzur Murshed
Keyword(s):  
Machine Learning ◽  
Information Retrieval ◽  
Learning To Rank ◽  
Language Model ◽  
Supervised Machine Learning ◽  
Learning Framework ◽  
Learning Tasks ◽  
Technical Details ◽  
The Relationship ◽  
Broad Understanding

Ranking a set of documents based on their relevances with respect to a given query is a central problem of information retrieval (IR). Traditionally people have been using unsupervised scoring methods like tf-idf, BM25, Language Model etc., but recently supervised machine learning framework is being used successfully to learn a ranking function, which is called learning-to-rank (LtR) problem. There are a few surveys on LtR in the literature; but these reviews provide very little assistance to someone who, before delving into technical details of different algorithms, wants to have a broad understanding of LtR systems and its evolution from and relation to the traditional IR methods. This chapter tries to address this gap in the literature. Mainly the following aspects are discussed: the fundamental concepts of IR, the motivation behind LtR, the evolution of LtR from and its relation to the traditional methods, the relationship between LtR and other supervised machine learning tasks, the general issues pertaining to an LtR algorithm, and the theory of LtR.

scholarly journals Machine Learning for the Relationship of High-Energy Electron Flux between GEO and MEO with Application to Missing Values Imputation for Beidou MEO Data

2021 ◽  
Vol 30 (1) ◽  
pp. 62-72
Author(s):  
Ruifei Cui ◽  
Yu Jiang ◽  
Chao Tian ◽  
Riwei Zhang ◽  
Sihui Hu ◽  
...  
Keyword(s):  
Machine Learning ◽  
Missing Values ◽  
Electron Flux ◽  
Original Data ◽  
High Energy ◽  
Energy Electron ◽  
Earth Orbit ◽  
High Energy Electron ◽  
Relationship Of ◽  
The Relationship

Abstract We consider the problem of building the relationship of high-energy electron flux between Geostationary Earth Orbit (GEO) and Medium Earth Orbit (MEO). A time-series decomposition technique is first applied to the original data, resulting in trend and detrended part for both GEO and MEO data. Then we predict MEO trend with GEO data using three machine learning models: Linear Regression (LR), Random Forest (RF), and Multi-Layer Perceptron (MLP). Experiment shows that RF gains best performance in all scenarios. Feature extraction analysis demonstrates that the inclusion of lagged features and (possible) ahead features is substantially helpful to the prediction. At last, an application of imputing missing values for MEO data is presented, in which RF model with selected features is used to handle the trend part while a moving block method is for the detrended part.

scholarly journals Post-prediction inference

2020 ◽  
Author(s):  
Siruo Wang ◽  
Tyler H McCormick ◽  
Jeffrey T Leek
Keyword(s):  
Machine Learning ◽  
Statistical Inference ◽  
Variance Estimation ◽  
R Package ◽  
Outcome Data ◽  
Learning Framework ◽  
Autopsy Data ◽  
Validation Set ◽  
Low Dimensional ◽  
The Relationship

Many modern problems in medicine and public health leverage machine learning methods to predict outcomes based on observable covariates. In an increasingly wide array of settings, these predicted outcomes are used in subsequent statistical analysis, often without accounting for the distinction between observed and predicted outcomes. We call inference with predicted outcomes post-prediction inference. In this paper, we develop methods for correcting statistical inference using outcomes predicted with an arbitrary machine learning method. Rather than trying to derive the correction from the first principles for each machine learning tool, we make the observation that there is typically a low-dimensional and easily modeled representation of the relationship between the observed and predicted outcomes. We build an approach for the post-prediction inference that naturally fits into the standard machine learning framework, where the data is divided into training, testing, and validation sets. We train the prediction model in the training set,. We estimate the relationship between the observed and predicted outcomes on the testing set and use that model to correct inference on the validation set and subsequent statistical models. We show our postpi approach can correct bias and improve variance estimation (and thus subsequent statistical inference) with predicted outcome data. To show the broad range of applicability of our approach, we show postpi can improve inference in two totally distinct fields: modeling predicted phenotypes in re-purposed gene expression data and modeling predicted causes of death in verbal autopsy data. We have made our method available through an open-source R package: https://github.com/leekgroup/postpi

scholarly journals An interpretable machine-learning framework for dark matter halo formation

2019 ◽  
Vol 490 (1) ◽  
pp. 331-342 ◽  
Author(s):  
Luisa Lucie-Smith ◽  
Hiranya V Peiris ◽  
Andrew Pontzen
Keyword(s):  
Machine Learning ◽  
Dark Matter ◽  
Initial Density ◽  
Dark Matter Halo ◽  
Halo Formation ◽  
Learning Framework ◽  
Interpretable Machine Learning ◽  
Leibler Divergence ◽  
The Difference ◽  
The Impact

ABSTRACT We present a generalization of our recently proposed machine-learning framework, aiming to provide new physical insights into dark matter halo formation. We investigate the impact of the initial density and tidal shear fields on the formation of haloes over the mass range 11.4 ≤ log (M/M⊙) ≤ 13.4. The algorithm is trained on an N-body simulation to infer the final mass of the halo to which each dark matter particle will later belong. We then quantify the difference in the predictive accuracy between machine-learning models using a metric based on the Kullback–Leibler divergence. We first train the algorithm with information about the density contrast in the particles’ local environment. The addition of tidal shear information does not yield an improved halo collapse model over one based on density information alone; the difference in their predictive performance is consistent with the statistical uncertainty of the density-only based model. This result is confirmed as we verify the ability of the initial conditions-to-halo mass mapping learnt from one simulation to generalize to independent simulations. Our work illustrates the broader potential of developing interpretable machine-learning frameworks to gain physical understanding of non-linear large-scale structure formation.

Sign in / Sign up

Export Citation Format

Share Document