scholarly journals Fair and Effective Policing for Neighborhood Safety: Understanding and Overcoming Selection Biases

2021 ◽  
Vol 4 ◽  
Author(s):  
Weijeiying Ren ◽  
Kunpeng Liu ◽  
Tianxiang Zhao ◽  
Yanjie Fu
Keyword(s):  
New York ◽  
Causal Inference ◽  
Risk Estimation ◽  
Data Distribution ◽  
Neighborhood Safety ◽  
Treatment Interventions ◽  
Adversarial Learning ◽  
Learning Techniques ◽  
Efficiency And Effectiveness ◽  
Search Program

An accurate crime prediction and risk estimation can help improve the efficiency and effectiveness of policing activities. However, reports have revealed that biases like racial prejudice could exist in policing enforcement, and trained predictors may inherit them. In this work, we study the possible reasons and countermeasures to this problem, using records from the New York frisk and search program (NYCSF) as the dataset. Concretely, we provide analysis on the possible origin of this phenomenon from the perspective of risk discrepancy, and study it with the scope of selection bias. Motivated by theories in causal inference, we propose a re-weighting approach based on propensity score to balance the data distribution, with respect to the identified treatment: search action. Naively applying existing re-weighting approaches in causal inference is not suitable as the weight is passively estimated from observational data. Inspired by adversarial learning techniques, we formulate the predictor training and re-weighting as a min-max game, so that the re-weighting scale can be automatically learned. Specifically, the proposed approach aims to train a model that: 1) able to balance the data distribution in the searched and un-searched groups; 2) remain discriminative between treatment interventions. Extensive evaluations on real-world dataset are conducted, and results validate the effectiveness of the proposed framework.

scholarly journals Game-Based Methods to Encourage EFL Learners to Transition to Autonomous Learning

2014 ◽  
pp. 309-314
Author(s):  
Janine Berger
Keyword(s):  
High School ◽  
New York ◽  
New York City ◽  
Action Research ◽  
York City ◽  
Independent Learning ◽  
Action Research Project ◽  
Efl Learners ◽  
Learning Techniques ◽  
Efl Students

This paper describes a work in progress in which we aim to encourage EFL students to take their learning beyond the classroom in order to experience English in different ways. Inspired by what is being done at the Quest to Learn middle and high school in New York City and ChicagoQuest (Institute of Play, 2014b) our idea involves conducting an action research project in order to find out if game-like learning techniques, modified and adapted to the needs of university-aged EFL learners in Ecuador will help to increase motivation and independent learning for our students.

scholarly journals Prediction of Bike Sharing Demand

2017 ◽  
Vol 10 (1) ◽  
pp. 219-226 ◽  
Author(s):  
Purnima Sachdeva ◽  
K N Sarvanan
Keyword(s):  
New York ◽  
Linear Combination ◽  
Random Forests ◽  
Traffic Congestion ◽  
Urban Areas ◽  
Machine Learning Techniques ◽  
Health Consciousness ◽  
Learning Techniques ◽  
The World ◽  
Bike Sharing

Bike sharing systems have been gaining prominence all over the world with more than 500 successful systems being deployed in major cities like New York, Washington, London. With an increasing awareness of the harms of fossil based mean of transportation, problems of traffic congestion in cities and increasing health consciousness in urban areas, citizens are adopting bike sharing systems with zest. Even developing countries like India are adopting the trend with a bike sharing system in the pipeline for Karnataka. This paper tackles the problem of predicting the number of bikes which will be rented at any given hour in a given city, henceforth referred to as the problem of ‘Bike Sharing Demand’. In this vein, this paper investigates the efficacy of standard machine learning techniques namely SVM, Regression, Random Forests, Boosting by implementing and analyzing their performance with respect to each other.This paper also presents two novel methods, Linear Combination and Discriminating Linear Combination, for the ‘Bike Sharing Demand’ problem which supersede the aforementioned techniques as good estimates in the real world.

Community scale non-potable reuse in London using an MBR

2008 ◽  
Vol 3 (2) ◽  
Author(s):  
R. Birks ◽  
S. Hills ◽  
E. Grant ◽  
B. Verrecht
Keyword(s):  
New York ◽  
Research Programme ◽  
Wastewater Reclamation ◽  
Zero Energy ◽  
Energy Usage ◽  
Potable Reuse ◽  
Efficiency And Effectiveness ◽  
Usage Patterns ◽  
The Uk

Due to increasing pressure on water resources in southeast England, Thames Water are currently installing the first membrane bioreactor (MBR) plant for reuse (toilet flushing and irrigation) in the UK, at Beddington Zero Energy Development (BedZED), a prestigious sustainable development in south London. Thames Water will operate and evaluate the system via an in depth research programme for a 3 year period. A case study, the Solaire in New York (US), informed the BedZED Wastewater Reclamation Plant (BWRP) design and is presented. The BWRP process stream comprises 3mm screens, MBR, granular activated carbon and chlorination. Research will include process optimisation, water quality and water saving studies, post treatment efficiency and effectiveness, energy usage, studies of biofilm regrowth potential and householder perception studies. A comprehensive metering system consisting of hardwired pulse, electromagnetic and radio meters will monitor reclaimed and potable water throughout the site. The metering data will be used to calculate water balances and water savings at various scales. Research using the radio meters (AMR) will cover areas such as customer side leakage and usage patterns. This research will allow a holistic and complete understanding of water use and recycling in a sustainable community.

scholarly journals Gigafactory Logistics in Space and Time: Tesla’s Fourth Gigafactory and Its Rivals

2020 ◽  
Vol 12 (5) ◽  
pp. 2044 ◽  
Author(s):  
Philip Cooke
Keyword(s):  
New York ◽  
Time Management ◽  
New York State ◽  
Big Data Analytics ◽  
Greenhouse Gas Mitigation ◽  
Manufacturing Plant ◽  
Railway Line ◽  
Efficiency And Effectiveness ◽  
Production And Distribution ◽  
Management Issues

This paper concerns the spatial structure of Tesla’s four ‘gigafactories’ (‘giga’ is gigawatt hour, GWh) which are located in Tesla’s first Gigafacility (1) at Sparks, near Reno, Nevada; the Solar City Gigafactory (2) at Buffalo, New York state; the 2019 Tesla plant at Shanghai, China Gigafactory (3); and the new Tesla gigafactory Europe Gigafactory (4), which is a manufacturing plant to be constructed in Grünheide, near Berlin, Germany. The newest campus is 20 miles southeast of central Berlin on the main railway line to Wrocław, Poland. Three main features of the ‘gigafactory’ phenomenon, apart from their scale, are in the industry organisation of production, which thus far reverses much current conventional wisdom regarding production geography. Thus, Tesla’s automotive facility in Fremont California reconcentrates manufacturing on site as in-house own brand componentry, especially heavy parts, or by requiring hitherto distant global suppliers to locate in proximity to the main manufacturing plant. Second, as an electric vehicle (EV) producer, the contributions of Tesla’s production infrastructure and logistics infrastructure are important in meeting greenhouse gas mitigation and the reduction of global warming. Finally, the deployment of Big Data analytics, artificial intelligence (AI) and ‘predictive management’ are important. This lies in gigafactory logistics contributing to production and distribution efficiency and effectiveness as a primer for all future industry and services in seeking to minimise time-management issues. This too potentially contributes significantly to the reduction of wasteful energy usage.

scholarly journals A scoping review of causal methods enabling predictions under hypothetical interventions

2021 ◽  
Vol 5 (1) ◽  
Author(s):  
Lijing Lin ◽  
Matthew Sperrin ◽  
David A. Jenkins ◽  
Glen P. Martin ◽  
Niels Peek
Keyword(s):  
Machine Learning ◽  
Causal Inference ◽  
Observational Data ◽  
Prediction Models ◽  
Risk Estimation ◽  
Clinical Decision ◽  
Causal Effects ◽  
Statistical Machine Learning ◽  
Methodological Approaches ◽  
Meta Analyses

Abstract Background The methods with which prediction models are usually developed mean that neither the parameters nor the predictions should be interpreted causally. For many applications, this is perfectly acceptable. However, when prediction models are used to support decision making, there is often a need for predicting outcomes under hypothetical interventions. Aims We aimed to identify published methods for developing and validating prediction models that enable risk estimation of outcomes under hypothetical interventions, utilizing causal inference. We aimed to identify the main methodological approaches, their underlying assumptions, targeted estimands, and potential pitfalls and challenges with using the method. Finally, we aimed to highlight unresolved methodological challenges. Methods We systematically reviewed literature published by December 2019, considering papers in the health domain that used causal considerations to enable prediction models to be used for predictions under hypothetical interventions. We included both methodologies proposed in statistical/machine learning literature and methodologies used in applied studies. Results We identified 4919 papers through database searches and a further 115 papers through manual searches. Of these, 87 papers were retained for full-text screening, of which 13 were selected for inclusion. We found papers from both the statistical and the machine learning literature. Most of the identified methods for causal inference from observational data were based on marginal structural models and g-estimation. Conclusions There exist two broad methodological approaches for allowing prediction under hypothetical intervention into clinical prediction models: (1) enriching prediction models derived from observational studies with estimated causal effects from clinical trials and meta-analyses and (2) estimating prediction models and causal effects directly from observational data. These methods require extending to dynamic treatment regimes, and consideration of multiple interventions to operationalise a clinical decision support system. Techniques for validating ‘causal prediction models’ are still in their infancy.

scholarly journals MACHINE LEARNING FOR APPROXIMATING UNKNOWN FACE

2020 ◽  
Vol XLIII-B2-2020 ◽  
pp. 857-862 ◽  
Author(s):  
V. A. Knyaz ◽  
V. V. Kniaz ◽  
M. M. Novikov ◽  
R. M. Galeev
Keyword(s):  
Deep Learning ◽  
3D Model ◽  
3D Models ◽  
Learning Approach ◽  
Neural Network Training ◽  
Adversarial Learning ◽  
Network Training ◽  
Learning Techniques ◽  
Facial Approximation ◽  
Automated Technique

Abstract. The problem of facial appearance reconstruction (or facial approximation) basing on a skull is very important as for anthropology and archaeology as for forensics. Recent progress in optical 3D measurements allowed to substitute manual facial reconstruction techniques with computer-aided ones based on digital skull 3D models. Growing amount of data and developing methods for data processing provide a background for creating fully automated technique of face approximation.The performed study addressed to a problem of facial approximation based on skull digital 3D model with deep learning techniques. The skull 3D models used for appearance reconstruction are generated by the original photogrammetric system in automated mode. These 3D models are then used as input for the algorithm for face appearance reconstruction. The paper presents a deep learning approach for facial approximation basing on a skull. It exploits the generative adversarial learning for transition data from one modality (skull) to another modality (face) using digital skull 3D models and face 3D models. A special dataset containing skull 3D models and face 3D models has been collected and adapted for convolutional neural network training and testing. Evaluation results on testing part of the dataset demonstrates high potential of the developed approach in facial approximation.

Sign in / Sign up

Export Citation Format

Share Document