Machine Learning in Mobile Crowd Sourcing: A Behavior-Based Recruitment Model

With the advent of mobile crowd sourcing (MCS) systems and its applications, the selection of the right crowd is gaining utmost importance. The increasing variability in the context of MCS tasks makes the selection of not only the capable but also the willing workers crucial for a high task completion rate. Most of the existing MCS selection frameworks rely primarily on reputation-based feedback mechanisms to assess the level of commitment of potential workers. Such frameworks select workers having high reputation scores but without any contextual awareness of the workers, at the time of selection, or the task. This may lead to an unfair selection of workers who will not perform the task. Hence, reputation on its own only gives an approximation of workers’ behaviors since it assumes that workers always behave consistently regardless of the situational context. However, following the concept of cross-situational consistency, where people tend to show similar behavior in similar situations and behave differently in disparate ones, this work proposes a novel recruitment system in MCS based on behavioral profiling. The proposed approach uses machine learning to predict the probability of the workers performing a given task, based on their learned behavioral models. Subsequently, a group-based selection mechanism, based on the genetic algorithm, uses these behavioral models in complementation with a reputation-based model to recruit a group of workers that maximizes the quality of recruitment of the tasks. Simulations based on a real-life dataset show that considering human behavior in varying situations improves the quality of recruitment achieved by the tasks and their completion confidence when compared with a benchmark that relies solely on reputation.

GIS Mapping of Short-Term Noisy Event of Diwali Night in Lucknow City

Noise is a universal problem that is particularly prominent in developing nations like India. Short-term noise-sensitive events like New Year’s Eve, derby matches, DJ night, Diwali night (celebration with firecracker) in India, etc. create lots of noise in a short period. There is a need to come up with a system that can predict the noise level for an area for a short period indicating its detailed variations. GIS (Geographic Information System)-based google maps for terrain data and crowd-sourced or indirect collection of noise data can overcome this challenge to a great extent. Authors have tried to map the highly noisy Diwali night for Lucknow, a northern city of India. The mapping was done by collecting the data from 100 points using the noise capture app (30% were close to the source and 70% were away from the source (receiver). Noise data were predicted for 750 data points using the modeling interpolation technique. A noise map is generated for this Diwali night using the crowd-sourcing technique for Diwali night. The results were also varied with 50 test points and are found to be within ±4.4 dB. Further, a noise map is also developed for the same site using indirect data of noise produced from the air pollution open-sourced data. The produced noise map is also verified with 50 test points and found to be ±6.2 dB. The results are also corroborated with the health assessment survey report of the residents of nearby areas.

Evidences of horizontal urban heat advection in London using 6 years of data from a citizen weather station network

Recent advances in citizen weather station (CWS) networks, with data accessible via crowd-sourcing, provide relevant climatic information to urban scientists and decision makers. In particular, CWS can provide long-term measurements of urban heat and valuable information on spatio-temporal heterogeneity related to horizontal heat advection. In this study, we make the first compilation of a quasi-climatologic dataset covering 6 years (2015–2020) of hourly near-surface air temperature measurements obtained via 1560 suitable CWS in a domain covering south-east England and Greater London. We investigated the spatio- temporal distribution of urban heat and the influences of local environments on climate, captured by CWS through the scope of Local Climate Zones (LCZ) – a land-use land-cover classification specifically designed for urban climate studies. We further calculate, for the first time, the amount of advected heat captured by CWS located in Greater London and the wider south east England region. We find that London is on average warmer by ∼1.0 ◦C to ∼2.0 ◦C than the rest of south-east England. Characteristics of the southern coastal climate are also captured in the analysis. We find that on average, urban heat advection (UHA) contributes to 0.22 ◦C of the total urban heat in Greater London. Certain areas, mostly in the centre of London are deprived of urban heat through advection since heat is transferred more to downwind suburban areas. UHA can positively contribute to urban heat by up to ∼2.0 ◦C on average and negatively by down to ∼-1.0 ◦C. Our results also show an important degree of inter- and intra-LCZ variability in UHA, calling for more research in the future. Nevertheless, we already find that UHA can impact green areas and reduce their cooling benefit. Such outcomes show the added value of CWS for future urban design.

Mapping the surrounding environment by pupils. Case study: Primary school “Ismail Qemali” in Chair - Skopje

Cartography in primary schools in the Republic of North Macedonia is present as part of geography subject, for four years from sixth to ninth level, per two hours weekly. Program is limited only on usage of paper maps aimed for learning geospatial phenomena, without information for map making process.Step forward toward increasing the awareness for including mapping in practical part of curricula in geography and other related subjects, are the activities undertaken by the Geo-SEE Institute from Skopje, by giving practical lectures to pupils in Primary School “Ismail Qemali” in Chair municipality, for usage the digital cartography tools via GIS software.Training was designed to be used FOSS for GIS and open geospatial data by teachers and pupils. Field identification and collection of geospatial data based on ortho images and other base materials, as well usage of smart phones have been used as supplementary methodology for establishing geospatial database aimed for map compilation. Voluntary geographic information and crowd sourcing methodologies as opportunities for usage in teaching and learning process in primary schools not only for geography but for all subjects that intersects with geospatial information, were explained to attendees. Within very short period of one and half month, before pandemic on march 2020, pupils achieved to work with basic tools of QGIS software, as well to compile two maps, one geographical map of North Macedonia, and a map of neighbourhood “Topansko Pole (Fushë Topanë)” as city map of the settlement in which the primary school is located.

Comparing Output from Two Methods of Participatory Design for Developing Implementation Strategies: Traditional Contextual Inquiry vs. Rapid Crowd Sourcing

BackgroundParticipatory design methods are a key component of designing tailored implementation strategies. These methods vary in the resources required to execute and analyze their outputs. No work to date has examined the extent to which the output obtained from different approaches to participatory design varies.MethodsWe concurrently used two separate participatory design methods: 1) field observations and qualitative interviews and 2) rapid crowd sourcing (an innovation tournament). Our goal was to generate information to tailor implementation strategies to increase the use of evidence-based data collection practices among one-to-one aides working with children with autism. Each method was executed and analyzed by study team members blinded to the output of the other method. We estimated the personnel time and monetary costs associated with each method to further facilitate comparison.ResultsObservations and interviews generated nearly double the number of implementation strategies (n = 26) than did the innovation tournament (n = 14). When strategies were classified into clusters from the Expert Recommendations for Implementing Change (ERIC) taxonomy, there was considerable overlap in the content of identified strategies. Strategies derived from observations and interviews were more specific than those from the innovation tournament. Nine strategies (23%) reflected content unique to observations and interviews and 4 (10%) strategies were unique to the innovation tournament. Only observations and interviews identified implementation strategies related to adapting and tailoring to context; only the innovation tournament identified implementation strategies that used incentives. Observations and interviews required more than three times the personnel hours than the innovation tournament, but the innovation tournament was more costly overall due to the technological platform used.ConclusionsThere was substantial overlap in content derived from observations and interviews and the innovation tournament. However, each yielded unique information. To select the best participatory design approach to inform implementation strategy design for a particular context, researchers should carefully consider what each method may elicit and weigh the resources available to invest in the process.Trial RegistrationN/A

Appraisal of Socio-Economic and Political Implications of COVID-19 Pandemic on Residents of Enugu State, Nigeria

COVID-19 pandemic determines public health, presenting the biggest threat since the Second World War. All continents, except for Antarctica, are active in battling the pandemic. As other socio-economic and political problems are arising from this crisis, the pandemic cannot only be attributed to health issues. Every nation affected by this pandemic may witness a destructive or ravaging social, economic, political and psychological backlash that may leave long lasting scars. The World Bank has projected a decline in remittances of $110 billion and 800 million people will not be able to meet basic needs this year, with the International Labour Organization (ILO) forecasting that over 195 million people will lose their jobs. In managing this pandemic, there is a need for strategic planning by a government organization through the development of long-lasting policies that will help minimize the impact on individuals and nations. Previous experiences of epidemics such as Ebola, HIV, SARs, TB and Malaria will therefore be valuable in the development of policies that can help to mitigate the socio-economic and political impact. The solution may lie in contacting the most vulnerable through crowd sourcing to provide them with food, in particular life necessities. Expanded social security may also be an important step in that direction for the disadvantaged and the disabled.

CACHE (Critical Assessment of Computational Hit-finding Experiments): A public-private partnership benchmarking initiative to enable the development of computational methods for hit-finding

Computational approaches in drug discovery and development hold great promise, with artificial intelligence methods undergoing widespread contemporary use, but the experimental validation of these new approaches is frequently inadequate. We are initiating Critical Assessment of Computational Hit-finding Experiments (CACHE) as a public benchmarking project that aims to accelerate the development of small molecule hit-finding algorithms by competitive assessment. Compounds will be identified by participants using a wide range of computational methods for dozens of protein targets selected for different types of prediction scenarios, as well as for their potential biological or pharmaceutical relevance. Community-generated predictions will be tested centrally and rigorously in an experimental hub(s), and all data, including the chemical structures of experimentally tested compounds, will be made publicly available without restrictions. The ability of a range of computational approaches to find novel compounds will be evaluated, compared, and published. The overarching goal of CACHE is to accelerate the development of computational chemistry methods by providing rapid and unbiased feedback to those developing methods, with an ancillary and valuable benefit of identifying new compound-protein binding pairs for biologically interesting targets. The initiative builds on the power of crowd sourcing and expands the open science paradigm for drug discovery.

Behavioral Correlates of the Muzak Experience

The current work seeks to characterize a unique genre of music, elevator music (Muzak), using behavioral crowd-sourcing data from Amazon Mechanical Turk. Participants rated excerpts of elevator music along with more rewarding genres of music for pleasure, valence, familiarity, and recognition. Our results demonstrate that elevator music is rated as neutrally pleasurable, with high valence, and highly familiar. Data collection is ongoing, and future experiments use computational models of music to tease apart the neutral effects of elevator music listening. Our results have practical significance in that they may provide a potential control musical stimulus to be used with self-selected rewarding music.