Dataset Information

Heterogeneous Sensing Data Analysis for Commercial Waste Collection.

ABSTRACT: Waste collection has become a major issue all over the world, especially when it is offered as a service for businesses; unlike public waste collection where the parameters are relatively homogeneous. This industry can greatly benefit from new sensing technologies and advances in artificial intelligence that have been achieved over the last few years. However, in most situations waste management systems are based on obsolete technologies, with a low level of interoperability and thus offering static processes. The most advanced solutions are generally limited to statistical, non-predictive approaches and have a limited view of reality, making them weakly effective in dealing with day-to-day business issues (overflowing containers, poor quality of service, etc.). This paper presents a case study currently being developed in Luxembourg with a company offering a business waste collection service, which has a significant amount of constraints to consider. Our main objective is to investigate the use of multiple waste data sources to derive useful indicators for improving collection processes. We start with company-owned historical data and then investigate GPS information from tracking devices positioned on collection trucks. Furthermore, we analyze data collected from ultrasonic sensors deployed on almost 50 different containers to measure fill levels. We describe the deployment steps and show that this approach, combined with anomaly detection and prediction techniques, has the potential to change the way this business operates. We also discuss the interest of the different datasets presented and multi-objective optimization issues. To the best of our knowledge, this article is the first major work dedicated to the world of professional waste collection.

SUBMITTER: Melakessou F

PROVIDER: S-EPMC7071114 | biostudies-literature | 2020 Feb

REPOSITORIES: biostudies-literature

ACCESS DATA

Publications

Heterogeneous Sensing Data Analysis for Commercial Waste Collection.

Melakessou Foued F Kugener Paul P Alnaffakh Neamah N Faye Sébastien S Khadraoui Djamel D

Sensors (Basel, Switzerland) 20200212 4

Waste collection has become a major issue all over the world, especially when it is offered as a service for businesses; unlike public waste collection where the parameters are relatively homogeneous. This industry can greatly benefit from new sensing technologies and advances in artificial intelligence that have been achieved over the last few years. However, in most situations waste management systems are based on obsolete technologies, with a low level of interoperability and thus offering st ...[more]

PMID: 32059411

Similar Datasets

Project description:mHealth researchers can now collect a wealth of data using “life tracking apps” (LTAs), which are smartphone applications that use mobile sensing to capture and summarise a multitude of data channels (e.g., location, movement, keyword use, sleep, exercise, and so on). The combined wealth of information can create digital signatures of individuals, which hold immense promise for mental health research and interventions by allowing new insights into moment-to-moment changes in behaviour and mental states. However, little is known about what a common research demographic (university students) thinks about these apps and what might factor into their decisions to participate in research using a LTA. This qualitative study ran five focus group sessions (21 students in total) to explore students’ experiences, beliefs, and opinions about LTAs to generate insights into what would make them more or less likely to participate in research involving LTAs. Transcripts were coded and examined for categories using qualitative content analysis. Important categories that emerged were privacy (although this varied based on the individual and data being collected), data security, inconvenience, intrusiveness, financial compensation, and the perceived nature of the research team responsible. On the basis of these categories, we derived seven key insights to increase student participation in research using LTAs: strengthen and communicate privacy and data security, design the app to be as convenient as possible to users, maximise passive data collection, think cautiously before tracking data perceived as “creepy” such as messages, offer suitable financial compensation, be transparent about goals and justification for data being collection to build trust, and attract participants by highlighting how the app can help them achieve their goals. With these insights, mHealth researchers can maximise their participant pool and improve this nascent and promising field.

Project description:The Central African Republic is one of the world's most vulnerable countries, suffering from chronic poverty, violent conflicts and weak disaster resilience. In collaboration with Doctors without Borders/Médecins Sans Frontières (MSF), this study presents a novel approach to collect information about socio-economic vulnerabilities related to malnutrition, access to resources and coping capacities. The first technical test was carried out in the North of the country (sub-prefecture Kabo) in May 2015. All activities were aimed at the investigation of technical feasibility, not at operational data collection, which requires a random sampling strategy. At the core of the study is an open-source Android application named SATIDA COLLECT that facilitates rapid and simple data collection. All assessments were carried out by local MSF staff after they had been trained for one day. Once a mobile network is available, all assessments can easily be uploaded to a database for further processing and trend analysis via MSF in-house software. On one hand, regularly updated food security assessments can complement traditional large-scale surveys, whose completion can take up to eight months. Ideally, this leads to a gain in time for disaster logistics. On the other hand, recording the location of every assessment via the smart phones' GPS receiver helps to analyze and display the coupling between drought risk and impacts over many years. Although the current situation in the Central African Republic is mostly related to violent conflict it is necessary to consider information about drought risk, because climatic shocks can further disrupt the already vulnerable system. SATIDA COLLECT can easily be adapted to local conditions or other applications, such as the evaluation of vaccination campaigns. Most importantly, it facilitates the standardized collection of information without pen and paper, as well as straightforward sharing of collected data with the MSF headquarters or other aid organizations.

Dataset Information

Heterogeneous Sensing Data Analysis for Commercial Waste Collection.

Publications

Heterogeneous Sensing Data Analysis for Commercial Waste Collection.

Similar Datasets

OmicsDI is part of the ELIXIR infrastructure

Tweets