The study on mechanical model considering optimal self-adaption in the bottleneck area.

It aims to solve the problem that the evacuation state of pedestrians depicted by the traditional social force model in a crowded multiexit scenario has a relatively large difference with the actual state, especially the 'optimal path' considered by the self-driving force is the problem of shortest path, and the multiexit evacuation mode depicted by the 'herd behavior' is the local optimum problem. Through in-depth analysis of actual evacuation data of pedestrians and causes of problem, a new crowd evacuation optimization model is established in order to effectively improve the simulation accuracy of crowd evacuation in a multi-exit environment. The model obtains the direction of motion of pedestrians using a field model, fully considers the factors such as exit distance, distribution of pedestrians and regional crowding degree, makes a global optimization for the self-driving force in the social force model using a centralized and distributed network model, and makes a local optimization for it using an elephant herding algorithm, so as to establish a new evacuation optimization method for optimal self-adaption in the bottleneck area. The performance status is compared between the improved social force model and the new model by experiments, and the key factors that affect the new model are analyzed in an in-depth manner. The results show that the new model can optimize the optimal path choice at the early stage of evacuation and improve the evacuation efficiency of pedestrians at the late stage, so as to ensure relatively even distribution of pedestrians at each exit, and also make the simulated evacuation process be more real; and the improvement in overall evacuation efficiency is greater when the number of pedestrians to be evacuated is larger. Therefore, the new model provides a method to solve the phenomenon of disorder in overall pedestrian evacuation due to excessive crowd density during the process of multi-exit evacuation.

Implicit induction of expressive suppression in regulation of happy crowd emotions.

Implicit emotion regulation provides an effective means of controlling emotions triggered by a single face without conscious awareness and effort. Crowd emotion has been proposed to be perceived as more intense than it actually is, but it is still unclear how to regulate it implicitly. In this study, participants viewed sets of faces of varying emotionality (e.g. happy to angry) and estimated the mean emotion of each set after being primed with an expressive suppression goal, a cognitive reappraisal goal, or a neutral goal. Faster discrimination for happy than angry crowds was observed. After induction of the expressive suppression goal instead of the cognitive reappraisal goal, augmented N170 and early posterior negativity (EPN) amplitudes, as well as attenuated late positive potential (LPP) amplitudes, were observed in response to happy crowds compared to the neutral goal. Differential processing of angry crowds was not observed after the induction of both regulatory goals compared to the neutral goal. Our findings thus reveal the happy-superiority effect and that implicit induction of expressive suppression improves happy crowd emotion recognition, promotes selective coding, and successfully downregulates the neural response to happy crowds.

An Adaptive Temporal Convolutional Network Autoencoder for Malicious Data Detection in Mobile Crowd Sensing.

Mobile crowdsensing (MCS) systems rely on the collective contribution of sensor data from numerous mobile devices carried by participants. However, the open and participatory nature of MCS renders these systems vulnerable to adversarial attacks or data poisoning attempts where threat actors can inject malicious data into the system. There is a need for a detection system that mitigates malicious sensor data to maintain the integrity and reliability of the collected information. This paper addresses this issue by proposing an adaptive and robust model for detecting malicious data in MCS scenarios involving sensor data from mobile devices. The proposed model incorporates an adaptive learning mechanism that enables the TCN-based model to continually evolve and adapt to new patterns, enhancing its capability to detect novel malicious data as threats evolve. We also present a comprehensive evaluation of the proposed model's performance using the SherLock datasets, demonstrating its effectiveness in accurately detecting malicious sensor data and mitigating potential threats to the integrity of MCS systems. Comparative analysis with existing models highlights the performance of the proposed TCN-based model in terms of detection accuracy, with an accuracy score of 98%. Through these contributions, the paper aims to advance the state of the art in ensuring the trustworthiness and security of MCS systems, paving the way for the development of more reliable and robust crowdsensing applications.

Coupling an agent-based model and an ensemble Kalman filter for real-time crowd modelling.

Agent-based modelling has emerged as a powerful tool for modelling systems that are driven by discrete, heterogeneous individuals and has proven particularly popular in the realm of pedestrian simulation. However, real-time agent-based simulations face the challenge that they will diverge from the real system over time. This paper addresses this challenge by integrating the ensemble Kalman filter (EnKF) with an agent-based crowd model to enhance its accuracy in real time. Using the example of Grand Central Station in New York, we demonstrate how our approach can update the state of an agent-based model in real time, aligning it with the evolution of the actual system. The findings reveal that the EnKF can substantially improve the accuracy of agent-based pedestrian simulations by assimilating data as they evolve. This approach not only offers efficiency advantages over existing methods but also presents a more realistic representation of a complex environment than most previous attempts. The potential applications of this method span the management of public spaces under 'normality' to exceptional circumstances such as disaster response, marking a significant advancement for real-time agent-based modelling applications.

Research on collaborative edge network service migration strategy based on crowd clustering.

The innovative application of Crowd Intelligent Devices (CIDS) in edge networks has garnered attention due to the rapid development of artificial intelligence and computer technology. This application offers users more reliable and low-latency computing services through computation offloading technology. However, the dynamic nature of network terminals and the limited coverage of edge servers pose challenges, such as data loss and service interruption. Furthermore, the high-speed mobility of intelligent terminals in the dynamic edge network environment further complicates the design of computation offloading and service migration strategies. To address these challenges, this paper explores the computation offloading model of cluster intelligence collaboration in a heterogeneous network environment. This model involves multiple intelligences collaborating to provide computation offloading services for terminals. To accommodate various roles, a switching strategy of split-cluster group collaboration is introduced, assigning the cluster head, the alternate cluster head, and the ordinary user are assigned to a group with different functions. Additionally, the paper formulates the optimal offloading strategy for group smart terminals as a Markov decision process, taking into account factors such as user mobility, service delay, service accuracy, and migration cost. To implement this strategy, the paper utilizes the deep reinforcement learning-based CCSMS algorithm. Simulation results demonstrate that the proposed edge network service migration strategy, rooted in groupwise cluster collaboration, effectively mitigates interruption delay and enhances service migration efficiency.

Adaptive Network Model for Assisting People with Disabilities through Crowd Monitoring and Control.

Here, we present an effective application of adaptive cooperative networks, namely assisting disables in navigating in a crowd in a pandemic or emergency situation. To achieve this, we model crowd movement and introduce a cooperative learning approach to enable cooperation and self-organization of the crowd members with impaired health or on wheelchairs to ensure their safe movement in the crowd. Here, it is assumed that the movement path and the varying locations of the other crowd members can be estimated by each agent. Therefore, the network nodes (agents) should continuously reorganize themselves by varying their speeds and distances from each other, from the surrounding walls, and from obstacles within a predefined limit. It is also demonstrated how the available wireless trackers such as AirTags can be used for this purpose. The model effectiveness is examined with respect to the real-time changes in environmental parameters and its efficacy is verified.

A Dilated Convolutional Neural Network for Cross-Layers of Contextual Information for Congested Crowd Counting.

Crowd counting is an important task that serves as a preprocessing step in many applications. Despite obvious improvement reported by various convolutional-neural-network-based approaches, they only focus on the role of deep feature maps while neglecting the importance of shallow features for crowd counting. In order to surmount this issue, a dilated convolutional-neural-network-based cross-level contextual information extraction network is proposed in this work, which is abbreviated as CL-DCNN. Specifically, a dilated contextual module (DCM) is constructed by importing cross-level connection between different feature maps. It can effectively integrate contextual information while conserving the local details of crowd scenes. Extensive experiments show that the proposed approach outperforms state-of-the-art approaches using five public datasets, i.e., ShanghaiTech part A, ShanghaiTech part B, Mall, UCF_CC_50 and UCF-QNRF, achieving MAE 52.6, 8.1, 1.55, 181.8, and 96.4, respectively.

A Crowd Movement Analysis Method Based on Radar Particle Flow.

Crowd movement analysis (CMA) is a key technology in the field of public safety. This technology provides reference for identifying potential hazards in public places by analyzing crowd aggregation and dispersion behavior. Traditional video processing techniques are susceptible to factors such as environmental lighting and depth of field when analyzing crowd movements, so cannot accurately locate the source of events. Radar, on the other hand, offers all-weather distance and angle measurements, effectively compensating for the shortcomings of video surveillance. This paper proposes a crowd motion analysis method based on radar particle flow (RPF). Firstly, radar particle flow is extracted from adjacent frames of millimeter-wave radar point sets by utilizing the optical flow method. Then, a new concept of micro-source is defined to describe whether any two RPF vectors originated from or reach the same location. Finally, in each local area, the internal micro-sources are counted to form a local diffusion potential, which characterizes the movement state of the crowd. The proposed algorithm is validated in real scenarios. By analyzing and processing radar data on aggregation, dispersion, and normal movements, the algorithm is able to effectively identify these movements with an accuracy rate of no less than 88%.

Conservation gaps and priorities of range-restricted birds in the Northern Andes.

The ongoing destruction of habitats in the tropics accelerates the current rate of species extinction. Range-restricted species are exceptionally vulnerable, yet we have insufficient knowledge about their protection. Species' current distributions, range sizes, and protection gaps are crucial to determining conservation priorities. Here, we identified priority range-restricted bird species and their conservation hotspots in the Northern Andes. We employed maps of the Area of Habitat (AOH), that better reflect their current distributions than existing maps. AOH provides unprecedented resolution and maps a species in the detail essential for practical conservation actions. We estimated protection within each species' AOH and for the cumulative distribution of all 335 forest-dependent range-restricted birds across the Northern Andes. For the latter, we also calculated protection across the elevational gradient. We estimated how much additional protection community lands (Indigenous and Afro-Latin American lands) would contribute if they were conservation-focused. AOHs ranged from 8 to 141,000 km2. We identified four conservation priorities based on cumulative species richness: the number of AOHs stacked per unit area. These priorities are high-resolution mapped representations of Endemic Bird Areas for the Tropical Andes that we consider critically important. Protected areas cover only 31% of the cumulative AOH, but community lands could add 19% more protection. Sixty-two per cent of the 335 species have ranges smaller than their published estimates, yet IUCN designates only 23% of these as Threatened. We identified 50 species as top conservation priorities. Most of these concentrate in areas of low protection near community lands and at middle elevations where, on average, only 34% of the land is protected. We highlight the importance of collaborative efforts among stakeholders: governments should support private and community-based conservation practices to protect the region with the most range-restricted birds worldwide.

A clinical consensus-compliant deep learning approach to quantitatively evaluate human in vitro fertilization early embryonic development with optical microscope images.

The selection of embryos is a key for the success of in vitro fertilization (IVF). However, automatic quality assessment on human IVF embryos with optical microscope images is still challenging. In this study, we developed a clinical consensus-compliant deep learning approach, named Esava (Embryo Segmentation and Viability Assessment), to quantitatively evaluate the development of IVF embryos using optical microscope images. In total 551 optical microscope images of human IVF embryos of day-2 to day-3 were collected, preprocessed, and annotated. Using the Faster R-CNN model as baseline, our Esava model was constructed, refined, trained, and validated for precise and robust blastomere detection. A novel algorithm Crowd-NMS was proposed and employed in Esava to enhance the object detection and to precisely quantify the embryonic cells and their size uniformity. Additionally, an innovative GrabCut-based unsupervised module was integrated for the segmentation of blastomeres and embryos. Independently tested on 94 embryo images for blastomere detection, Esava obtained the high rates of 0.9940, 0.9121, and 0.9531 for precision, recall, and mAP respectively, and gained significant advances compared with previous computational methods. Intraclass correlation coefficients indicated the consistency between Esava and three experienced embryologists. Another test on 51 extra images demonstrated that Esava surpassed other tools significantly, achieving the highest average precision 0.9025. Moreover, it also accurately identified the borders of blastomeres with mIoU over 0.88 on the independent testing dataset. Esava is compliant with the Istanbul clinical consensus and compatible to senior embryologists. Taken together, Esava improves the accuracy and efficiency of embryonic development assessment with optical microscope images.

An enhanced multi-attribute crowd evacuation model incorporating the effects of environmental impact factors.

We propose an enhanced floor field model (FFM) to analyze the behavioral characteristics of crowds with varying attributes proportions during evacuation. This model governs pedestrian movement through the Dynamic Floor Field (DFF) and the Static Floor Field (SFF). The DFF takes into account individual factors such as the gender, familiarity with the environment, and social relationships of evacuees, which influence safe evacuation. Concurrently, the SFF encapsulates the impact of environmental factors like obstacles, exits, and guidance effects. Subsequently, this refined FFM was applied and validated using a sports center evacuation scenario. The results demonstrated that the enhanced FFM accurately replicated evacuees' asymmetric behavior and queuing, and aligned well with other models when the number of evacuees fluctuated over time. In the absence of guidance, both environmental familiarity and gender emerged as primary factors influencing partial evacuation. Additionally, the gender of pedestrians significantly affected the overall evacuation. Notably, compared to pre-existing environmental information available to evacuees, the implementation of guidance to augment pedestrians' environmental familiarity resulted in a more efficient evacuation. The FFM model and these findings could be instrumental in simulating personnel evacuation and formulating emergency management strategies in crowded areas.

Fourier feature decorrelation based sample attention for dense crowd localization.

Crowd localization, which prevails to extract the independent individual features, plays an significant role in critical analysis for crowd scene. Dense trivial features of individual targets are frequently susceptible to interference from complex background features, which makes it difficult to obtain satisfactory predictions for individual targets. Aiming at this issue, a Fourier feature decorrelation based sample attention is proposed for dense crowd localization. The correlation between features are decoupled in the Fourier transform domain, which induces the model to focus more on the true correlation between individual target features and labels. From the perspective of Fourier feature correlation between samples, independence test statistic optimization with cross-covariance operator is developed for feature decorrelation within the sample attention framework. The sample attention with global weight learning is iteratively optimized through matching the prediction loss, which can induce model partial out the spurious correlation between target-irrelevant features and labels. Experimental results show that the method proposed in this paper outperforms the current advanced crowd location methods on public dense crowd datasets.

Research on the evacuation of people from a road tunnel fire based on a mathematical model.

A mathematical model for the evacuation of people from a road tunnel is created, taking into account various factors such as the speed at which people move, the density of the flow of people, and the outcome of the fire. This model allows for the precise calculation of the evacuation time and the optimization of the evacuation route in a fire scenario. The constructed mathematical model was used to determine how long it would take for people to evacuate this road tunnel, and the findings of the Pathfinder simulation were compared. The findings demonstrate a relationship between the model's evacuation time and the human flow density, movement velocity, and fire product characteristics. The evacuation time is closer to the outcome of the actual fire scene when the impact of the fire environment on the speed of evacuation is quantified. The mathematical model of human evacuation's calculation of the evacuation time is essentially accurate when compared to the Pathfinder simulation's calculation, with an error of only 0.77 %. The model provides recommendations for optimizing the evacuation of people from a road tunnel in the case of a fire by not only predicting where the crowding would occur but also by calculating the duration of the crowding.

Beyond 'stampedes': Towards a new psychology of crowd crush disasters.

The Bethnal Green tube shelter disaster, in which 173 people died, is a significant event in both history and psychology. While notions of 'panic' and 'stampede' have been discredited in contemporary psychology and disaster research as explanations for crowd crushes, Bethnal Green has been put forward as the exception that proves the rule. Alternative explanations for crushing disasters focus on mismanagement and physical factors, and lack a psychology. We analysed 85 witness statements from the Bethnal Green tragedy to develop a new psychological account of crowd disasters. Contrary to the established view of the Bethnal Green disaster as caused by widespread public overreaction to the sound of rockets, our analysis suggests that public perceptions were contextually calibrated to a situation of genuine threat; that only a small minority misperceived the sound; and that therefore, this cannot account for the surge behaviour in the majority. We develop a new model, in which crowd flight behaviour in response to threat is normatively structured rather than uncontrolled, and in which crowd density combines with both limited information on obstruction and normatively expected ingress behaviour to create a crushing disaster.

Human Crowds as Social Networks: Collective Dynamics of Consensus and Polarization.

A ubiquitous type of collective behavior and decision-making is the coordinated motion of bird flocks, fish schools, and human crowds. Collective decisions to move in the same direction, turn right or left, or split into subgroups arise in a self-organized fashion from local interactions between individuals without central plans or designated leaders. Strikingly similar phenomena of consensus (collective motion), clustering (subgroup formation), and bipolarization (splitting into extreme groups) are also observed in opinion formation. As we developed models of crowd dynamics and analyzed crowd networks, we found ourselves going down the same path as models of opinion dynamics in social networks. In this article, we draw out the parallels between human crowds and social networks. We show that models of crowd dynamics and opinion dynamics have a similar mathematical form and generate analogous phenomena in multiagent simulations. We suggest that they can be unified by a common collective dynamics, which may be extended to other psychological collectives. Models of collective dynamics thus offer a means to account for collective behavior and collective decisions without appealing to a priori mental structures.

The effect of gaze information associated with the search items on contextual cueing effect.

Previous research on the mechanisms of contextual cueing effect has been inconsistent, with some researchers showing that the contextual benefit was derived from the attentional guidance whereas others argued that the former theory was not the source of contextual cueing effect. We brought the "stare-in-the-crowd" effect that used pictures of gaze with different orientations as stimuli into a traditional contextual cueing effect paradigm to investigate whether attentional guidance plays a part in this effect. We embedded the letters used in a traditional contextual cueing effect paradigm into the gaze pictures with direct and averted orientation. In Experiment 1, we found that there was a weak interaction between the contextual cueing effect and the "stare-in-the-crowd" effect. In Experiments 2 and 3, we found that the contextual cueing effect was influenced differently when the direct gaze was combined with the target or distractors. These results suggested that attentional guidance played an important role in the generation of a contextual cueing effect and the direct gaze had a special impact on visual search. To summarize the three findings, the direct gaze on target location facilitates the contextual cueing effect, and such an effect is even greater when we compared condition with the direct gaze on target location with condition with the direct gaze on distractor location (Experiments 2 and 3). Such an effect of gaze on a contextual cueing effect is manifested even when the effect of gaze ("stare-in-the-crowd" effect) was absent in the New configurations (search trials without learning).

Modular hierarchical reinforcement learning for multi-destination navigation in hybrid crowds.

Real-world robot applications usually require navigating agents to face multiple destinations. Besides, the real-world crowded environments usually contain dynamic and static crowds that implicitly interact with each other during navigation. To address this challenging task, a novel modular hierarchical reinforcement learning (MHRL) method is developed in this paper. MHRL is composed of three modules, i.e., destination evaluation, policy switch, and motion network, which are designed exactly according to the three phases of solving the original navigation problem. First, the destination evaluation module rates all destinations and selects the one with the lowest cost. Subsequently, the policy switch module decides which motion network to be used according to the selected destination and the obstacle state. Finally, the selected motion network outputs the robot action. Owing to the complementary strengths of a variety of motion networks and the cooperation of modules in each layer, MHRL is able to deal with hybrid crowds effectively. Extensive simulation experiments demonstrate that MHRL achieves better performance than state-of-the-art methods.

The Impact of Spatial Frequency on the Perception of Crowd Emotion: An fMRI Study.

Recognizing the emotions of faces in a crowd is crucial for understanding overall behavior and intention as well as for smooth and friendly social interactions. However, it is unclear whether the spatial frequency of faces affects the discrimination of crowd emotion. Although high- and low-spatial-frequency information for individual faces is processed by distinct neural channels, there is a lack of evidence on how this applies to crowd faces. Here, we used functional magnetic resonance imaging (fMRI) to investigate neural representations of crowd faces at different spatial frequencies. Thirty-three participants were asked to compare whether a test face was happy or more fearful than a crowd face that varied in high, low, and broad spatial frequencies. Our findings revealed that fearful faces with low spatial frequencies were easier to recognize in terms of accuracy (78.9%) and response time (927 ms). Brain regions, such as the fusiform gyrus, located in the ventral visual stream, were preferentially activated in high spatial frequency crowds, which, however, were the most difficult to recognize behaviorally (68.9%). Finally, the right inferior frontal gyrus was found to be better activated in the broad spatial frequency crowds. Our study suggests that people are more sensitive to fearful crowd faces with low spatial frequency and that high spatial frequency does not promote crowd face recognition.

Attention-Assisted Feature Comparison and Feature Enhancement for Class-Agnostic Counting.

In this study, we address the class-agnostic counting (CAC) challenge, aiming to count instances in a query image, using just a few exemplars. Recent research has shifted towards few-shot counting (FSC), which involves counting previously unseen object classes. We present ACECount, an FSC framework that combines attention mechanisms and convolutional neural networks (CNNs). ACECount identifies query image-exemplar similarities, using cross-attention mechanisms, enhances feature representations with a feature attention module, and employs a multi-scale regression head, to handle scale variations in CAC. ACECount's experiments on theFSC-147 dataset exhibited the expected performance. ACECount achieved a reduction of 0.3 in the mean absolute error (MAE) on the validation set and a reduction of 0.26 on the test set of FSC-147, compared to previous methods. Notably, ACECount also demonstrated convincing performance in class-specific counting (CSC) tasks. Evaluation on crowd and vehicle counting datasets revealed that ACECount surpasses FSC algorithms like GMN, FamNet, SAFECount, LOCA, and SPDCN, in terms of performance. These results highlight the robust dataset generalization capabilities of our proposed algorithm.

Incentivizing free riders improves collective intelligence in social dilemmas.

Collective intelligence challenges are often entangled with collective action problems. For example, voting, rating, and social innovation are collective intelligence tasks that require costly individual contributions. As a result, members of a group often free ride on the information contributed by intrinsically motivated people. Are intrinsically motivated agents the best participants in collective decisions? We embedded a collective intelligence task in a large-scale, virtual world public good game and found that participants who joined the information system but were reluctant to contribute to the public good (free riders) provided more accurate evaluations, whereas participants who rated frequently underperformed. Testing the underlying mechanism revealed that a negative rating bias in free riders is associated with higher accuracy. Importantly, incentivizing evaluations amplifies the relative influence of participants who tend to free ride without altering the (higher) quality of their evaluations, thereby improving collective intelligence. These results suggest that many of the currently available information systems, which strongly select for intrinsically motivated participants, underperform and that collective intelligence can benefit from incentivizing free riding members to engage. More generally, enhancing the diversity of contributor motivations can improve collective intelligence in settings that are entangled with collective action problems.