Place Categories Research Articles

UPAYA PENINGKATAN BISNIS DENGAN DIGITAL BRANDING PEMBUATAN LOKASI UMKM MELALUI APLIKASI GOOGLE MAPS DI DESA SIRNAJAYA

This activity is carried out to help install Google Maps pins. Some features that can help MSMEs are directions, sharing locations, and reviews that can be accompanied by images. With these features, the public can access searches and provide ratings, so that MSMEs can optimize branding and add addresses, telephone numbers, place categories, and store operating hours, which will increase consumer interest. This community service activity is carried out using a community empowerment system method in the form of socialization and mentoring. The results of the implementation of community service are the successful registration of business locations in Sirnajaya Village MSMEs, providing complete and actual MSME information, and appearing in searches when consumers search for relevant products. In addition, reviews and ratings from experienced customers can provide strong social evidence that can increase the trust and interest of potential customers so as to increase sales.

Predictability of human mobility during the COVID-19 pandemic in the United States.

Human mobility is fundamental to a range of applications including epidemic control, urban planning, and traffic engineering. While laws governing individual movement trajectories and population flows across locations have been extensively studied, the predictability of population-level mobility during the COVID-19 pandemic driven by specific activities such as work, shopping, and recreation remains elusive. Here we analyze mobility data for six place categories at the US county level from 2020 February 15 to 2021 November 23 and measure how the predictability of these mobility metrics changed during the COVID-19 pandemic. We quantify the time-varying predictability in each place category using an information-theoretic metric, permutation entropy. We find disparate predictability patterns across place categories over the course of the pandemic, suggesting differential behavioral changes in human activities perturbed by disease outbreaks. Notably, predictability change in foot traffic to residential locations is mostly in the opposite direction to other mobility categories. Specifically, visits to residences had the highest predictability during stay-at-home orders in March 2020, while visits to other location types had low predictability during this period. This pattern flipped after the lifting of restrictions during summer 2020. We identify four key factors, including weather conditions, population size, COVID-19 case growth, and government policies, and estimate their nonlinear effects on mobility predictability. Our findings provide insights on how people change their behaviors during public health emergencies and may inform improved interventions in future epidemics.

Representational Dissimilarity of Faces and Places during a Working Memory Task is Associated with Subsequent Recognition Memory during Development.

Nearly 50 years of research has focused on faces as a special visual category, especially during development. Yet it remains unclear how spatial patterns of neural similarity of faces and places relate to how information processing supports subsequent recognition of items from these categories. The current study uses representational similarity analysis and functional imaging data from 9- and 10-year-old youth during an emotional n-back task from the Adolescent Brain and Cognitive Development Study 3.0 data release to relate spatial patterns of neural similarity during working memory to subsequent out-of-scanner performance on a recognition memory task. Specifically, we examine how similarities in representations within face categories (neutral, happy, and fearful faces) and representations between visual categories (faces and places) relate to subsequent recognition memory of these visual categories. Although working memory performance was higher for faces than places, subsequent recognition memory was greater for places than faces. Representational similarity analysis revealed category-specific patterns in face-and place-sensitive brain regions (fusiform gyrus, parahippocampal gyrus) compared with a nonsensitive visual region (pericalcarine cortex). Similarity within face categories and dissimilarity between face and place categories in the parahippocampus was related to better recognition of places from the n-back task. Conversely, in the fusiform, similarity within face categories and their relative dissimilarity from places was associated with better recognition of new faces, but not old faces. These findings highlight how the representational distinctiveness of visual categories influence what information is subsequently prioritized in recognition memory during development.

Public support for smoke-free private indoor and public outdoor areas in the Netherlands: A trend analysis from 2018-2022.

In addition to smoke-free policies in indoor public and workplaces, governments increasingly implement smoke-free policies at beaches, in parks, playgrounds and private cars ('novel smoke-free policies'). An important element in the implementation of such policies is public support. In the context of the ambition of the Netherlands to reach a smoke-free generation by 2040, we investigated temporal changes in public support for novel smoke-free policies. We analyzed annual cross-sectional questionnaires in a representative sample of the Dutch population from 2018 to 2022. Multivariable logistic regression was applied to model public support for each smoke-free policy area as a function of time (calendar year), smoking status, gender, and socioeconomic status. Interaction terms were added for time with smoking status and with socioeconomic status. A total of 5582 participant responses were included. Between 2018 and 2022, support increased most for smoke-free policies regarding train platforms (+16%), theme parks (+12%), beaches (+10%), and terraces (+10%). In 2022, average support was higher than 65% for all categories of smoke-free places and highest for private cars with children (91%). Regression analyses indicated significant increases in support over time within each category of smoke-free places (adjusted odds ratio, AOR between 1.09 and 1.17 per year), except smoke-free private cars with children (AOR=0.97; 95% CI: 0.89-1.05). Regardless of smoking status, support was high for places where children often go. Support for novel smoke-free places in the Netherlands is high and increasing, in particular for places frequented by children. This indicates the potential to implement such measures in the Netherlands.

Indoor Air Quality in the Most Crowded Public Places of Tehran: An Inhalation Health Risk Assessment

Satisfying indoor air quality in public environments has become essential in cities. In the present study, indoor PM2.5, CO2, NO2, SO2, nicotine, and BTEX have been assessed in 12 categories of public places. The highest average concentrations of PM2.5, NO2, and SO2 were observed in waterpipe cafés (233, 29.6, and 5.1 µg/m3), whereas the lowest concentrations were found in health clubs and hospitals, respectively. Moreover, indoor BTEX concentration varied from 69.5 µg/m3 (passenger terminals) to 1739.2 µg/m3 (elderly care centers). Given nicotine, the highest concentrations were found in waterpipe cafés, ranging from approximately 11.0 to 50 µg/m3. The mean hazard quotient (HQ) and Hazard Index (HI) for benzene, toluene, ethylbenzene, and xylene were calculated in all types of public environments, and results showed that the amount of HQ and HI in none of the places was more than 1. Furthermore, the lifetime cancer risk (LTCR) exceeded the guideline threshold in hospitals, restaurants, elderly care centers, passenger terminals, movie theaters, and beauty salons. The findings of our study indicate that the indoor air quality in most public settings within Tehran city is not acceptable and necessitates appropriate management. These findings underscore the importance of monitoring indoor air quality and implementing effective strategies to mitigate exposure to air pollutants.

Active exploration based on information gain by particle filter for efficient spatial concept formation

Autonomous robots need to learn the categories of various places by exploring their environments and interacting with users. However, preparing training datasets with linguistic instructions from users is time-consuming and labor-intensive. Moreover, effective exploration is essential for appropriate concept formation and rapid environmental coverage. To address this issue, we propose an active inference method, referred to as spatial concept formation with information gain-based active exploration (SpCoAE) that combines sequential Bayesian inference using particle filters and information gain-based destination determination in a probabilistic generative model. This study interprets the robot's action as a selection of destinations to ask the user, ‘What kind of place is this?’ in the context of active inference. This study provides insights into the technical aspects of the proposed method, including active perception and exploration by the robot, and how the method can enable mobile robots to learn spatial concepts through active exploration. Our experiment demonstrated the effectiveness of the SpCoAE in efficiently determining a destination for learning appropriate spatial concepts in home environments.

Nowhere to go? A study of marginalization, social connection, and mental health outcomes among young adults experiencing the COVID-19 pandemic

The COVID-19 pandemic onset necessitated large-scale closures of third places, potentially exacerbating social barriers experienced by young adults in the United States. To better understand the role of urban form in facilitating socialization, we examine the effects of pandemic-based third place closures on mental health outcomes as mediated by changes in social connection. Because identifying as a racial, gender, or sexual minority can compound baseline disadvantages rooted in systemic inequities, we investigate outcome differences for non-white, woman/nonbinary, and LGBTQ+ young adults to disentangle identity-based nuances of the pandemic experience. In February 2021, we administered a web-based survey with retrospective name and place generators to 313 18-to-34-year-olds in California, Illinois, and Texas. A structural equation model is estimated showing the direct and indirect effects of physical and virtual mobility constraints on mental health. Both the closure of third places and dissatisfaction with alternative social spaces are associated with the deterioration of social connections and mental health. The strongest direct predictor of mental health decline is dissatisfaction with virtual socialization (more significant for women and nonbinary respondents). Surprisingly, two distinct categories of third places (i.e., 'civic' and 'commercial') reveal different relationships with social connections and mental health outcomes. Asian, other non-white, and non-heterosexual young adults experienced greater 'civic' visit reduction, while those with intersecting identities of low income and woman/nonbinary or Black experienced greater 'commercial' visit reduction. Physical and virtual mobility reductions contributed to the inequitable mental health outcomes experienced by young adults during the pandemic. This highlights the potential for a careful redesign of physical and virtual social spaces to support feelings of belonging/safety and spontaneous 'weak tie' interactions, encourages further investigation of social infrastructure's role in facilitating the maintenance of social connections and mental health, and reveals the value of examining differences in mobility-related experiences across social identities.

The content of complex psychedelic experiences resulting from inhalation of N,N-dimethyltryptamine

AbstractAimThis study examines narratives describing complex psychedelic experiences after smoking N,N-dimethyltryptamine.MethodsThe narrative accounts examined here were gathered from a variety of online sites and analyzed in order to discover themes, categories and patterns in the phenomenon of the resulting psychedelic experiences.ResultsSubjects reported seeing complex and unusual visual and synesthetic phenomena, leaving this world and entering into extraordinary places, encounters with a variety of strange entities, interactions with unusual objects and a wide variety of powerful feelings. The general categories of Places, Objects, Entities and Feelings were found in the phenomena experienced by people who smoked N,N-Dimethyltryptamine. These provided a framework within which more detailed subcategories were found and the range of most frequent to least frequent experiences were identified.DiscussionWhile DMT experiences are commonly described by people smoking N,N-dimethyltryptamine as indescribable, unique to everyone and taking place in a single domain called Hyperspace or the Hyperdimension, this research found distinct subcategories of frequently visited Places as well as frequently encountered Entities, Objects and Feelings. From these a more comprehensive understanding can be developed of the unusual and profound experiences resulting from inhalation of N,N,-Dimethyltryptamine.

Combining recurrent and Graph Neural Networks to predict the next place’s category

Graph Neural Networks (GNNs) have a growing potential for helping solve problems in different contexts by working as a secondary technique that assists traditional methods. In the context of human mobility, it is expected that Recurrent Neural Networks (RNNs) are used to make predictions about individuals’ routine/mobility. In this work, we present POI-RGNN (Points of Interest-Recurrent and Graph-based Neural Network), a neural network for predicting the category of the next PoI that an individual will visit. Our proposal leverages Recurrent Neural Networks and Graph Neural Networks and combines them in a novel architecture. POI-RGNN explores new types of inputs sent to recurrent and graph layers. We evaluate the solution on a well-known and labeled dataset and a raw GPS-based dataset. For the latter, we propose a novel neural network model named Prediction of General Categories (PGC) for predicting a wide variety of PoI categories (e.g., Home, Work, Shopping, Nightlife, among others). We apply transfer learning with a GNN model that fuses different perspectives of the users’ mobility. As a result, we show that POI-RGNN leads to significant improvements compared to the state-of-the-art by combining RNNs and GNNs. Moreover, PGC can assign categories of places in an offline approach that requires minimum data.

Indoor Place Category Recognition for a Cleaning Robot by Fusing a Probabilistic Approach and Deep Learning.

Indoor place category recognition for a cleaning robot is a problem in which a cleaning robot predicts the category of the indoor place using images captured by it. This is similar to scene recognition in computer vision as well as semantic mapping in robotics. Compared with scene recognition, the indoor place category recognition considered in this article differs as follows: 1) the indoor places include typical home objects; 2) a sequence of images instead of an isolated image is provided because the images are captured successively by a cleaning robot; and 3) the camera of the cleaning robot has a different view compared with those of cameras typically used by human beings. Compared with semantic mapping, indoor place category recognition can be considered as a component in semantic SLAM. In this article, a new method based on the combination of a probabilistic approach and deep learning is proposed to address indoor place category recognition for a cleaning robot. Concerning the probabilistic approach, a new place-object fusion method is proposed based on Bayesian inference. For deep learning, the proposed place-object fusion method is trained using a convolutional neural network in an end-to-end framework. Furthermore, a new recurrent neural network, called the Bayesian filtering network (BFN), is proposed to conduct time-domain fusion. Finally, the proposed method is applied to a benchmark dataset and a new dataset developed in this article, and its validity is demonstrated experimentally.

Understanding Risk Communication Effectiveness From Public Interest, Mobility, and COVID-19 Cases: A Case Study of COVID-19 in Nigeria

Since the emergence of COVID-19 in 2020, various actions have been taken by governments and agencies globally to curtail its spread and devastating effects. Risk communication is an essential component of such actions. Examination of public interest, risk perception and new cases of COVID-19 is vital to understanding the effectiveness of risk communication strategies implemented. With data paucity plaguing policymaking in Nigeria, there is a need to examine new data sources to support the enhancement of risk communication. The study explored Google Trends (GT) and Google Mobility Reports (GMR) in monitoring public restlessness and risk perception, respectively, toward COVID-19 in Nigeria. This is geared toward understanding the effectiveness of the national risk communication strategy. COVID-19 case statistics, stringency index, mobility, and search indices for selected terms were collated (February 28 to June 30, 2020). Temporal dynamics were examined while correlation analysis was carried out to examine the association. Public attention peaked just around the commencement of the nationwide lockdown and declined considerably afterwards despite increasing new cases. Mobility toward most place categories showed a sharp decline at the beginning of the pandemic, except for residential areas. This trend also reversed soon after the lockdown. COVID-19 case statistics were found to be negatively correlated with the public interest. Public interest had a weak but both negative and positive association with the stringency index, while mobility exhibited a weak negative association with the case statistics (except residential area mobility). The results indicated that the risk communication efforts were inadequate in providing a prolonged health behavior change. The initial risk communication and lockdown created a positive outcome, however, the impact soon faded out. The evidence suggests that risk perception may have been poorly targeted by risk communication interventions. It is recommended that continuous monitoring of public interest and risk perception is implemented during an emergency and risk communication adjusted accordingly.

An unsupervised approach for semantic place annotation of trajectories based on the prior probability

Semantic place annotation can provide individual semantics, greatly helping the field of trajectory data mining. Most existing methods rely on annotated or external data and require retraining models following a region change, thus preventing their large-scale applications. Herein, we propose an unsupervised method denoted as UPAPP for the semantic place annotation of individual trajectories using spatiotemporal information. The Bayesian Criterion is specifically employed to decompose the spatiotemporal probability of visiting the candidate place into spatial probability, duration probability, and visiting time probability. Spatial information in two geospatial data sources is comprehensively integrated to calculate the spatial probability. In terms of the temporal probabilities, the Term Frequency–Inverse Document Frequency weighting algorithm is used to count the potential visits to different place types in the trajectories and to generate the prior probabilities of the visiting time and duration. Finally, the spatiotemporal probability of the candidate place is then combined with the importance of the place category to annotate the visited places. Experimental results in a trajectory dataset collected by 709 volunteers in Beijing showed that our method achieved an overall and average accuracy of 0.712 and 0.720, respectively, indicating that the visited places can be annotated accurately without any annotated data.

Topological Semantic Mapping by Consolidation of Deep Visual Features

Many works in the recent literature introduce semantic mapping methods that use CNNs (Convolutional Neural Networks) to recognize semantic properties in images. The types of properties (eg.: room size, place category, and objects) and their classes (eg.: kitchen and bathroom, for place category) are usually predefined and restricted to a specific task. Thus, all the visual data acquired and processed during the construction of the maps are lost and only the recognized semantic properties remain on the maps. In contrast, this work introduces a topological semantic mapping method that uses deep visual features extracted by a CNN (GoogLeNet), from 2D images captured in multiple views of the environment as the robot operates, to create, through averages, consolidated representations of the visual features acquired in the regions covered by each topological node. These representations allow flexible recognition of semantic properties of the regions and use in other visual tasks. Experiments with a real-world indoor dataset showed that the method is able to consolidate the visual features of regions and use them to recognize objects and place categories as semantic properties, and to indicate the topological location of images, with very promising results.

The Gap-Closing Estimand: A Causal Approach to Study Interventions That Close Disparities Across Social Categories

Disparities across race, gender, and class are important targets of descriptive research. But rather than only describe disparities, research would ideally inform interventions to close those gaps. The gap-closing estimand quantifies how much a gap (e.g., incomes by race) would close if we intervened to equalize a treatment (e.g., access to college). Drawing on causal decomposition analyses, this type of research question yields several benefits. First, gap-closing estimands place categories like race in a causal framework without making them play the role of the treatment (which is philosophically fraught for non-manipulable variables). Second, gap-closing estimands empower researchers to study disparities using new statistical and machine learning estimators designed for causal effects. Third, gap-closing estimands can directly inform policy: if we sampled from the population and actually changed treatment assignments, how much could we close gaps in outcomes? I provide open-source software (the R package gapclosing) to support these methods.

Combining Recurrent and Graph Neural Networks to Predict the Next Place's Category

Combining Recurrent and Graph Neural Networks to Predict the Next Place's Category

Measuring the mobility impact on the COVID-19 pandemic.

This assessment aims at measuring the impact of different location mobility on the COVID-19 pandemic. Data over time and over the 27 Brazilian federations in 5 regions provided by Google's COVID-19 community mobility reports and classified by place categories (retail and recreation, grocery and pharmacy, parks, transit stations, workplaces, and residences) are autoregressed on the COVID-19 incidence in Brazil using generalized linear regressions to measure the aggregate dynamic impact of mobility on each socioeconomic category. The work provides a novel multicriteria approach for selecting the most appropriate estimation model in the context of this application. Estimations for the time gap between contagion and data disclosure for public authorities' decision-making, estimations regarding the propagation rate, and the marginal mobility contribution for each place category are also provided. We report the pandemic evolution on the dimensions of cases and a geostatistical analysis evaluating the most critical cities in Brazil based on optimized hotspots with a brief discussion on the effects of population density and the carnival.

Incidents1M: A Large-Scale Dataset of Images With Natural Disasters, Damage, and Incidents.

Natural disasters, such as floods, tornadoes, or wildfires, are increasingly pervasive as the Earth undergoes global warming. It is difficult to predict when and where an incident will occur, so timely emergency response is critical to saving the lives of those endangered by destructive events. Fortunately, technology can play a role in these situations. Social media posts can be used as a low-latency data source to understand the progression and aftermath of a disaster, yet parsing this data is tedious without automated methods. Prior work has mostly focused on text-based filtering, yet image and video-based filtering remains largely unexplored. In this work, we present the Incidents1M Dataset, a large-scale multi-label dataset which contains 977,088 images, with 43 incident and 49 place categories. We provide details of the dataset construction, statistics and potential biases; introduce and train a model for incident detection; and perform image-filtering experiments on millions of images on Flickr and Twitter. We also present some applications on incident analysis to encourage and enable future work in computer vision for humanitarian aid. Code, data, and models are available at http://incidentsdataset.csail.mit.edu.

Carbon Emissions from the Transportation Sector during the Covid-19 Pandemic in the Special Region of Yogyakarta, Indonesia

Government policies to curb the Covid-19 pandemic have drastically changed the pattern of energy demand worldwide. Closed borders and international travel bans have changed consumption patterns and reduced transport use, thus significantly lowering carbon emissions in several countries, particularly urban areas in the Southeast Asia region. Based on these conditions, the study aimed to analyze carbon dioxide emissions generated by the transportation sector in the Special Region of Yogyakarta during the pandemic. The required data, serving as research objects, included fuel consumption, fuel sales, transportation sector activities, road sections, and road density derived from the Transportation Department’s traffic cameras and BPS-Statistics Indonesia. Google Form was also used to collect information for fuel consumption pattern analysis. The Covid-19 - Google Global Mobility Report was used to map trends of change in the respondents’ activity and mobility. The results showed that, from 2019 to 2020, the fuel consumption decreased by 74 kL/year and the CO2 emissions by 169,865 tons/year. Government policies, including the large-scale social activity restrictions implemented for the first time in the region, have influenced community mobility trends across different categories of places.

Comparing community mobility reduction between first and second COVID-19 waves

BackgroundIn this paper, we conduct a mobility reduction rate comparison between the first and second COVID-19 waves in several localities from America and Europe using Google community mobility reports (CMR) data. Through multi-dimensional visualization, we are able to compare the reduction in mobility from the different lockdown periods for each locality selected, simultaneously considering multiple place categories provided in CMR. In addition, our analysis comprises a 56-day lockdown period for each locality and COVID-19 wave, which we analyze both as 56-day periods and as 14-day consecutive windows. MethodsWe use locality-wise calibrated CMR data, which we process through seasonal-trend decomposition by LOESS (STL) to isolate trend from seasonal and noise effects. We scale trend data to draw Pareto-compliant conclusions using radar charts. For each temporal granularity considered, data for a given place category is aggregated using the area under the curve (AUC) approach. ResultsIn general, reduction rates observed during the first wave were much higher than during the second. Alarmingly, December holiday season mobility in some of the localities reached pre-pandemic levels for some of the place categories reported. Manaus was the only locality where second wave mobility was nearly as reduced as during the first wave, likely due to the P1 variant outbreak and oxygen supply crisis.

Exploiting Semantic Annotations for Clustering Geographic Areas and Users in Location-based Social Networks

Location-Based Social Networks (LBSN) present so far the most vivid realization of the convergence of the physical and virtual social planes. In this work we propose a novel approach on modeling human activity and geographical areas by means of place categories. We apply a spectral clustering algorithm on areas and users of two metropolitan cities on a dataset sourced from the most vibrant LBSN, Foursquare. Our methodology allows the identification of user communities that visit similar categories of places and the comparison of urban neighborhoods within and across cities. We demonstrate how semantic information attached to places could be plausibly used as a modeling interface for applications such as recommender systems and digital tourist guides.