Massive Crowd Research Articles

Improving microbial phylogeny with citizen science within a mass-market video game.

Citizen science video games are designed primarily for users already inclined to contribute to science, which severely limits their accessibility for an estimated community of 3 billion gamers worldwide. We created Borderlands Science (BLS), a citizen science activity that is seamlessly integrated within a popular commercial video game played by tens of millions of gamers. This integration is facilitated by a novel game-first design of citizen science games, in which the game design aspect has the highest priority, and a suitable task is then mapped to the game design. BLS crowdsources a multiple alignment task of 1 million 16S ribosomal RNA sequences obtained from human microbiome studies. Since its initial release on 7 April 2020, over 4 million players have solved more than 135 million science puzzles, a task unsolvable by a single individual. Leveraging these results, we show that our multiple sequence alignment simultaneously improves microbial phylogeny estimations and UniFrac effect sizes compared to state-of-the-art computational methods. This achievement demonstrates that hyper-gamified scientific tasks attract massive crowds of contributors and offers invaluable resources to the scientific community.

Smart Shopping Trolley Using Internet of Thing (IOT)

Abstract: Currently, billions of consumers shop at large in shopping mall stores for their everyday necessities. In today's life, purchasing has become a part of everyday life. On holidays and weekends, malls experience massive crowds .The integration of Internet of Things (IoT) technology into shopping trolleys presents a significant advancement in the retail industry, revolutionizing the shopping experience for consumers. The proposed SST utilizes a network of sensors and connectivity solutions to enable real-time monitoring, inventory management, and personalized services. Through IoT integration, the SST offers features such as automatic item detection, seamless checkout processes, and personalized recommendations based on individual shopping habits. Moreover, the system empowers retailers with tools for efficient inventory management, reducing stock outs, and analysing consumer behaviour for targeted marketing strategies. Intelligent Carts and automated recognition systems are being utilized by merchants to enhance the efficiency of their offerings and to boost market demand, enabling them to save time and money.

How Text-to-Image Generative AI Is Transforming Mediated Action.

This article examines the intricate relationship between humans and text-to-image generative models (generative artificial intelligence/genAI) in the realm of art. The article frames that relationship in the theory of mediated action-a well-established theory that conceptualizes how tools shape human thoughts and actions. The article describes genAI systems as learning, cocreating, and communicating, multimodally capable hybrid systems that distill and rely on the wisdom and creativity of massive crowds of people and can sometimes surpass them. Those systems elude the theoretical description of the role of tools and locus of control in mediated action. The article asks how well the theory can accommodate both the transformative potential of genAI tools in creative fields and art, and the ethics of the emergent social dynamics it generates. The article concludes by discussing the fundamental changes and broader implications that genAI brings to the realm of mediated action and, ultimately, to the very fabric of our daily lives.

Effects of Visitor Influx on the Indoor Climate of the Milan Cathedral

The indoor climate of non-climatized churches is usually subject to cyclical fluctuations of temperature and relative humidity induced by external climate conditions which might be dampened by the high thermal capacity of their envelope. However, several phenomena affect their indoor climate (e.g., internal gains due to people and artificial lighting, air infiltration, etc.), which lead to environmental variations that might jeopardize the artworks contained within. In particular, one of the most influential parameters that may affect non-climatized churches is the massive and intermittent presence of people who constantly visit their spaces. In such regard, long-term monitoring allows the collection of environmental data with different building operation conditions and visitor fluxes. This paper analyses the indoor climate of the Milan Cathedral (Duomo di Milano) in Italy for three continuous years (including the lockdown period that occurred in 2020 caused by the COVID-19 pandemic), with a focus on visitors’ effects on the indoor environment and the conservation of the main artworks contained within. The results of the analysis have shown that spaces with huge volume are most influenced by the opening of the doors rather than the hygrothermal contribution of the intermittent presence of massive crowds. Moreover, the absence of visitors for a prolonged period correlates with an improvement in the indoor conservation conditions for artworks, especially those made of hygroscopic materials, due to the reduction in short, rapid climate fluctuations.

Creating Connections through Storytelling: The African Diaspora Worldwide and Its Role in Us History

Creating Connections through Storytelling: The African Diaspora Worldwide and Its Role in Us History Jessica Smith (bio) On August 27, 1963—the day before various speakers from around the world stood addressing the massive crowd gathered at the Lincoln Memorial in Washington, DC, and urged civil and economic equity—the world said goodbye to an American-born intellectual and international icon who had made Accra, Ghana, his second home: Dr. William Edward Burghardt Du Bois. With his death at ninety-five years of age, Du Bois’s life spanned from slavery to the fight for justice, equality, and cultural identity among members of what would later be collectively known as the African Diaspora.1 When news of the loss reached the March on Washington for Jobs and Freedom the following day, a moment of silence was given for the activist, sociologist, and pan-Africanist who encouraged the strengthening of bonds between all ethnic groups of African descent, domestic and abroad. That same day, Executive Secretary of the NAACP Roy Wilkins reminded mourners at the march that the fight for social justice had been a long journey and it was Dr. W. E. B. Du Bois’s international voice “that was calling to you to gather here today in this cause.”2 Among those gathered that day for the cause were Dr. Martin Luther King Jr. and Josephine Baker, both of whom addressed the crowd gathered at the Lincoln Memorial. Of the two, Baker was the first to speak. In her speech, she talked of her “rocky path” and tumultuous times in her birth country of America, the differences between her treatment there and in France, the importance of education, and how her work and the work of many others helped to open doors for “not just the colored people, but the others as well, the other minorities too . . . both those here in the United States and those from India.”3 In harmony with the words of Baker, Dr. Martin Luther King Jr. stood and spoke his now well-known words of a dream where his children would live in a nation where judgement would not be based on “the color of their skin, but by the content of their character.”4 Though King was heavily involved in the movement for African American civil rights in the United States, he was a firm believer in W. E. B. Du Bois’s assertion of the interconnectedness of those of African descent regardless of where they reside, a sentiment that prompted his travel abroad to Ghana and his building of international links in the fight for peace and equality.5 Across the pond in an entirely different region from the American South, Josephine Baker—an American-born French entertainer and war hero—spent years in her adopted homeland as an opponent of racial segregation and discrimination, serving as an agent for the French Resistance during World War II and fighting Nazi occupation and its xenophobic regime in France.6 Despite their living and fighting for the civil liberties of the African Diaspora and [End Page 25] others in two different parts of the world, it was the unified cause of freedom—a cause bolstered by Du Bois’s earlier work—that brought Dr. Martin Luther King Jr. and Josephine Baker together at the March on Washington for Jobs and Freedom in Washington, DC. The March on Washington for Jobs and Freedom was a landmark event credited with helping to make positive changes countrywide in the United States of America, including the passing of the Civil Rights Act of 1964.7 W. E. B. Du Bois, Dr. Martin Luther King Jr., and Josephine Baker were just a few of the players in this pivotal chapter in the story of the African Diaspora and its resistance efforts for change. In the context of the March on Washington, it was the work and words of the aforementioned three figures that not only galvanized a worldwide civil rights movement, but helped to secure and sustain the rights and freedoms currently enjoyed globally by the diverse masses. In order to ensure that the cultural and historical fullness of the March on Washington is captured, it is essential to...

Forecasting the crowd: An effective and efficient neural network for citywide crowd information prediction at a fine spatio-temporal scale

Modelling and forecasting citywide crowd information (e.g., crowd volume of a region, the inflow of crowds into a region, outflow of crowds from a region) at a fine spatio-temporal scale is crucial for urban and transport planning, city management, public safety, and traffic management. However, this is a challenging task due to its complex spatial and temporal dependences. This paper proposes an effective and efficient model to reduce the training time cost while maintaining predictive accuracy in forecasting citywide crowd information at a fine spatio-temporal scale. Our model integrates Gated Recurrent Unit (GRU), convolutional neural network (CNN), and k-nearest neighbors (k-NN) to jointly capture the spatial and temporal dependences between two regions in a city. The evaluation with two different datasets in two different cities shows that compared to the state-of-the-art baselines, our model has better predictive accuracy (reducing the mean absolute errors MAEs by 20.99% on average) and a lower training time cost (reducing the time cost to only 26.16% on average of that of the baselines). Our model also has better abilities in making accurate predictions with low time cost under the influences of large-scale special events (when massive crowds of people are gathering in a short time) and for regions with high and irregular crowd changes. In summary, our model is an effective, efficient, and reliable method for forecasting citywide crowd information at a fine spatio-temporal scale, and has a high potential for many applications, such as city management, public safety, and transportation.

BMTC BUS DISTRIBUTION AND MANAGEMENT

The quality of any public transport system is crucially dependent on its reliability. BMTC bus distribution is not well planned in the Bengaluru Metro City resulting in massive crowds in Buses and Bus stands. Hence this is a real-life problem that needs an immediate solution. Using ‘YOLO’ (You Only Look Once) Machine Learning algorithm, we try to solve the existing crowd problem in BMTC buses. By making use of the camera present inside the bus upfront, we can count the onboarded passengers and store it in cloud (Real Time). These numbers can be seen by passengers who are waiting for the bus. If the upcoming buses are crowded, then passengers can choose another alternative means of transport like a cab or an auto rikshaw. The same count will be shown on an LED board in the BMTC base stations (depots) so that distribution is taken care manually. Like this we can achieve bus distribution and hence providing reliable and safe transportation for the public. As far as the BMTC management part is concerned, temperature and gas sensor are installed so that any smoke casualties can be prevented.

Assessment of Various Simulation Models Incorporating Queuing Concept

The investigation of security lines and the stochastic processes that personify them is known as queuing theory. Its goal is to use mathematics to understand real-world scenarios, for example, a massive crowd waiting in line at a bank, or tasks lining up on your smartphone's back end. In linear programming, how long the wait time or line extent is, is regularly hoped to be known which can be achieved using models. The wait does not always correspond to a perfect line; in theory, the first person to arrive will always be served first. Queuing theory is commonly recognized as a branch of operations research, and these models are widely used in development and software implementations. The end purpose of queuing up in queue research is to understand the behaviour and attitude of the underlying architecture so that appropriate strategic decisions can be made. Diverse Structured and Simulation Modelling Systems (SSMS) are described in the study, for example, any logic framework, Arena system, or Bizagi Simulation system.

Abnormal Behavior Learning Based on Edge Computing toward a Crowd Monitoring System

Abnormal behavior poses a great threat to social security and stability. The resulting violence or crime leads to terrible consequences. How to utilize reasonable means to predict the dangerous intentions of massive crowds and prevent the potential hazard to the public is significant for social security. A crowd monitoring and management system is an effective way to detect abnormal behavior. In this article, we release unmanned aerial vehicles as well as fixed ground devices to achieve multi-level and multi-modal behavioral sensing on a massive crowd, deploy a hybrid model in edge cloud to extract global features from behavioral data of a massive crowd, and then utilize these global features to construct decent classification algorithms for action recognition and behavioral semantic cognition. With the cooperation of behavioral data and cognitive algorithms, we can understand the instantaneous emotions of the crowd. On the basis of behavioral data and the emotional state of the crowd, the correlation between daily behavior and any dangerous intention of a massive crowd has been revealed by utilizing behavioral big data analysis, which is a key foundation for predicting people's dangerous intentions. Finally, we conduct a case study of abnormal behavior detection based on pix2pix and continuous video frames. The experimental results show that the performance of our method is better than other algorithms in both public datasets and the customized Hajj dataset. The proposed novel pattern for the effective learning of a massive crowd is validated to effectively eliminate some of the possible dangers caused by abnormal behavior.

Enabling CT-Scans for covid detection using transfer learning-based neural networks

Today, we are coping with the pandemic, and the novel virus is covertly evolving day by day. Therefore, a precautionary system to deal with the issue is required as early as possible. The last few years were very challenging for doctors, vaccine makers, hospitals, and medical authorities to deal with the massive crowd to provide results for all patients and newcomers in the past months. Thus, these issues should be handled with a robust system that can accord with many people and deliver the results in a fraction of time without visiting public places and help reduce crowd gathering. So, to deal with these issues, we developed an AI model using transfer learning that can aid doctors and other people to get to know whether they were suffering from covid or not. In this paper, we have used VGG-19 (CNN-based) model with open-sourced COVID-CT (CTSI) dataset. The dataset consists of 349 images of COVID-19 of 216 patients and 463 images of NON-COVID-19. We have achieved an accuracy of 95%, precision of 96%, recall of 94%, and F1-Score of 96% from the experiments. Communicated by Ramaswamy H. Sarma

QoE‐aware mobile computation offloading in mobile edge computing

AbstractDue to the rapid development of smart phone utilization, the use of fast response with delay sensitive applications leads to high traffic demands. These issues are not yet fulfill by current researchers. When there is a massive crowd of users gathering in hotspot areas such as, railway stations, corporate centers, and malls requires service accessing social networks, then there cause uncertain traffic with congestion and network delay. In this article, an Efficient Offloading Mechanism (EOM) is proposed to transfer the user's intensive computations to picocells, where each picocell (PE) is integrated with the functionalities of edge. Moreover, a novel distributed multihop mesh middle layer (DMMM) framework is proposed for seamless communication, where the self‐healing network provides high resilience, immediate response, and multiuser content sharing and saves battery power. Generally, a picocell is a distributed antenna system that is an alternative to the repeater utilized to extend wireless services to 100 users. An Adaptive Ant Optimization (AAO) algorithm is developed for backhaul routing conflicts. Simulation outcomes of EdgeCloudSim prove that the offloading tiny devices incorporated with considerable additional computational capacities to fulfill all the demands within 15 ms delay from each network.

An Intelligent Cluster Verification Model Using WSN to Avoid Close Proximity and Control Outbreak of Pandemic in a Massive Crowd

Assemblage at public places for religious or sports events has become an integral part of our lives. These gatherings pose a challenge at places where fast crowd verification with social distancing (SD) is required, especially during a pandemic. Presently, verification of crowds is carried out in the form of a queue that increases waiting time resulting in congestion, stampede, and the spread of diseases. This article proposes a cluster verification model (CVM) using a wireless sensor network (WSN), single cluster approach (SCA), and split cluster approach (SpCA) to solve the aforementioned problem for pandemic cases. We show that SD, cluster approaches, and verification by WSN can overcome the management issues by optimizing the cluster size and verification time. Hence, our proposed method minimizes the chances of spreading diseases and stampedes in large events such as a pilgrimage. We consider the assembly points in the annual pilgrimage to Makkah Al-Mukarmah and Umrah for verification using Contiki/Cooja tool. We compute results such as verified cluster members (CMs) to define cluster size, success rate to determine the best success rate, and verification time to determine the optimal verification time for various scenarios. We validate our model by comparing the results of each approach with the existing model. Our results show that the SpCA with SD is the best approach with a 96% success rate and optimization of verification time as compared to SCA with SD and the existing model.

Mechanisms and ways of transmission of SARS-CoV-2 coronavirus infection

The relevance of the problem. A new coronavirus infection caused by the SARS-CoV-2 virus has created an emergency situation of international importance. The incidence of it is characterized by a rapid spread across all countries, high morbidity rates, severe complications and mortality. Despite the fact that there are currently vaccines, it is not yet possible to stop the infection. Of particular importance as a preventive measure is the impact on the second link of the epidemic process. In this connection, obtaining objective data on the mechanisms and ways of spreading the SARS-CoV-2 virus will allow for more rational preventive measures and significantly reduce the risk of transmission of infection. The aim is to analyze current data on the mechanisms and ways of spreading the COVID-19 pathogen from available literature sources and to consider possible measures to influence the second link of the epidemiological chain in order to reduce the risks of infection. Materials and methods. The selection of peer-reviewed literature published from 2019 to 2021 was carried out. in the PubMed database and e-Library.ru, as well as links in articles. To obtain statistical data, the Internet resources of the World Health Organization (WHO), open data of Rospotrebnadzor, the Ministry of Health of the Russian Federation, Rosstat were used. Results. Analysis of scientific sources containing information on the mechanisms and ways of transmission of the new coronavirus infection COVID-19 indicates that the authors in their publications mention almost all the mechanisms and ways of transmission of this disease, but to varying degrees of their significance. The main mechanism of the spread of the SARS-CoV-2 virus is aspiration with airborne and airborne dust transmission routes. At the same time, the effect of contact, fecal-oral mechanisms is not excluded, the probability of the implementation of the vertical mechanism of transmission of the pathogen from the mother to the child, as well as the genital tract, is being studied. An important measure for the prevention of a new infection is the impact on the second link of the epidemic process, especially ensuring the highly efficient operation of ventilation and air conditioning systems in medical institutions and public places with a massive crowd of people, as well as compliance with personal preventive measures and disinfection measures.

Ensemble learning for large-scale crowd flow prediction

The Kumbh Mela festival is the largest mass gathering in the world that is celebrated every three years. In 2016, it attracted over 70 million people to Ujjain, India. The Mahakal temple is the “heart” of the festival that attracts a huge number of pilgrims and needs to accommodate with massive crowds. These types of events pose significant safety challenges as large-scale mass gatherings are often associated with risks such as crowd crushes. There have been a number of serious incidents documented in recent history such as the Hajj crush at Mina, Mecca, Saudi Arabia (2006 and 2015), the Lame Horse crush during a fire at Perm, Russia (2009), the Love Parade disaster at Duisburg, Germany (2010), and the Kumbh Mela stampede at Allahabad, Uttar Pradesh, India (2013) to name a few. Safety assurance at events of such tremendous size is closely connected with crowd control and understanding the general behaviour of the crowd. One of the basic challenges in understanding crowd dynamics is being able to predict crowd flows at a particular location based on past/present flows from another location. There are several existing methods and models used to predict and manage crowd flow. In this paper, we introduce a novel method for short-term crowd flow prediction and show that it decreases the prediction error by 13% as compared to existing methods. The model is based on ensemble learning where we demonstrate that a combination of complementary methods with different a-priory assumptions can create better estimations. Utilizing a unique data set derived from CCTV camera recordings of pilgrims that we collected during the Kumbh Mela 2016 festival, we tested different methods from artificial intelligence and computational modelling, such as simple shift of time-series (time-shift), agent-based modelling, machine learning methods, and show how combinations of these different methods as an ensemble provide synergy to obtain better predictions. Our results demonstrate that agent-based modelling, when combined with other models, provides better predictive power especially in complex scenarios. These results point to something fundamental about the information contained within and generated by these methods. We anticipate that our research could be a starting point for further research of informational synergetic aspects of models and predictors.

Deep learning-based bird eye view social distancing monitoring using surveillance video for curbing the COVID-19 spread.

The escalating transmission intensity of COVID-19 pandemic is straining the healthcare systems worldwide. Due to the unavailability of effective pharmaceutical treatment and vaccines, monitoring social distancing is the only viable tool to strive against asymptomatic transmission. Pertaining to the need of monitoring the social distancing at populated areas, a novel bird eye view computer vision-based framework implementing deep learning and utilizing surveillance video is proposed. This proposed method employs YOLO v3 object detection model and uses key point regressor to detect the key feature points. Additionally, as the massive crowd is detected, the bounding boxes on objects are received, and red boxes are also visible if social distancing is violated. When empirically tested over real-time data, proposed method is established to be efficacious than the existing approaches in terms of inference time and frame rate.

Pedestrian Flow Prediction in Open Public Places Using Graph Convolutional Network

Open public places, such as pedestrian streets, parks, and squares, are vulnerable when the pedestrians thronged into the sidewalks. The crowd count changes dynamically over time with various external factors, such as surroundings, weekends, and peak hours, so it is essential to predict the accurate and timely crowd count. To address this issue, this study introduces graph convolutional network (GCN), a network-based model, to predict the crowd flow in a walking street. Compared with other grid-based methods, the model is capable of directly processing road network graphs. Experiments show the GCN model and its extension STGCN consistently and significantly outperform other five baseline models, namely HA, ARIMA, SVM, CNN and LSTM, in terms of RMSE, MAE and R2. Considering the computation efficiency, the standard GCN model was selected to predict the crowd. The results showed that the model obtains superior performances with higher prediction precision on weekends and peak hours, of which R2 are above 0.9, indicating the GCN model can capture the pedestrian features in the road network effectively, especially during the periods with massive crowds. The results will provide practical references for city managers to alleviate road congestion and help pedestrians make smarter planning and save travel time.

Generative adversarial network based abnormal behavior detection in massive crowd videos: a Hajj case study

Generative adversarial network based abnormal behavior detection in massive crowd videos: a Hajj case study

Smart Shopping Trolley System using IoT

Currently, billions of consumers shop at large in shopping mall stores for their everyday necessities. In today’s life, purchasing has become a part of everyday life. On holidays and weekends, malls experience massive crowds. When there are exclusive sales and discounts, the urgency is intensified. Here we will use IOT based technology for people buy various things and place them in a trolley. When they have completed their order, they must pay at the billing desk. The Bills generated by a RFID reader which is a time-consuming procedure that leads to long queues at billing counters. The key objective is to build a framework that can be used in shopping malls to fix the issue described above. Both trolleys would be fitted with the system. It will require an RFID reader; RFID tags would be found in many of the mall’s goods. When a consumer places items in the trolley, the code is read, and the price of certain items is saved in the admin portal. When we add items to the cart, the device depicts the item’s name, number, expiration date, and rate, which is then applied to the overall bill. As a result, billing will take place within the trolley itself. The complete bill data will be passed to online portal Wi-Fi Module with trolley id, and we will be able to pay the balance either online or at bill counter by scanning the RFID tag placed in the trolley. In-season inventory reductions are often applied in transactions through admin, and item stock may be recorded. Intelligent Carts and automated recognition systems are being utilized by merchants to enhance the efficiency of their offerings and to boost market demand, enabling them to save time and money.

Artificial intelligence-enabled Internet of Things-based system for COVID-19 screening using aerial thermal imaging

Internet of Things (IoT) has recently brought an influential research and analysis platform in a broad diversity of academic and industrial disciplines, particularly in healthcare. The IoT revolution is reshaping current healthcare practices by consolidating technological, economic, and social views. Since December 2019, the spreading of COVID-19 across the world has impacted the world’s economy. IoT technology integrated with Artificial Intelligence (AI) can help to address COVID-19. UAVs equipped with IoT devices can collect raw data that demands computing and analysis to make intelligent decision without human intervention. To mitigate the effect of COVID-19, in this paper, we propose an IoT-UAV-based scheme to collect raw data using onboard thermal sensors. The thermal image captured from the thermal camera is used to determine the potential people in the image (of the massive crowd in a city), which may have COVID-19, based on the temperature recorded. An efficient hybrid approach for a face recognition system is proposed to detect the people in the image having high body temperature from infrared images captured in a real-time scenario. Also, a face mask detection scheme is introduced, which detects whether a person has a mask on the face or not. The schemes’ performance evaluation is done using various machine learning and deep learning classifiers. We use the edge computing infrastructure (onboard sensors and actuators) for data processing to reduce the response time for real-time analytics and prediction. The proposed scheme has an average accuracy of 99.5% using various performance evaluation metrics indicating its practical applicability in real-time scenarios.

A survey on intrusion detection system and prerequisite demands in IoT networks

Over the past few years the development in the mobile industry and development of internet, network for all, 4G, 5G etc. enabled the ordinary people as well as the elite people to depend upon mobile networks for regular business developments, entertainment, medical and educational needs. Almost all areas of development depend on the so called improvement of the mobile network. As the advantages and flexibility increases, the consumers entering by new registration increase widely and service requirement of existing consumers increase massively. It is mandatory to provide high level of security and dual privacy protection to the users sharing the large set of information through the cloud. The massive crowd sensing is important for any kind of network security system to ensure the detection of any miscellaneous activity entering the network grid. The study is focused on gathering various literature evidences on demand for intrusion detection system, analyzing the pitfalls in current models and creating an idea that would be helpful for us to proceed further with the research on intrusion detection system implementations and innovating a novel methodology that improvise from the present system. The future enhancement and interpretations on solutions would be discussed too.