Motion Of People Research Articles

Improved RNN Model for Real-Time Human Activity Recognition

This study focuses on the automatic detection of human actions in video streams. The requirement to detect what human activities happen in videos is recognition of human action due to significant differences in people's visual and motion appearance and actions, camera perspective shifts, moving background, occlusions, noise, and a massive amount of video data. The human activity recognition challenge involves identifying physical activities carried out by individuals or groups based on traces of movements, including gestures, actions, interactions, and group activities. The detection of concepts usually requires additional annotations for the training dataset. In this paper, useful methods for categorizing human action recognition are discussed. The current models are an accurate deep learning method that is based on models that have been changed to be more useful. The large disparities that result from the backdrop and the size of the objects have prevented the identification of activities in videos from being fully and effectively addressed. The main objective is to achieve better accuracy for the Long Short-Term Memory (LSTM) method, which was used to improve the Recurrent Neural Networks (RNN) model. In this paper, LSTM is used to come up with models for different action recognition tasks. The model was made better by making the LSTM have four layers and putting 128 units, 64 units, 32 units, and 16 units in each layer, respectively. In addition, the performance evaluation of deep learning-based approaches has been compared to other related works. Therefore, an improved approach to RNN is proposed to recognize human actions. To classify the videos, a multilayer RNN with a specific type of LSTM is used to extract features from video sequences. The UCF-101 and UCF Sports human action recognition datasets are utilized in this study for both training and assessment. Test findings demonstrate that the suggested strategy achieved increased accuracy. Finally, the enhanced RNN model's total model accuracy in the UCF-101 dataset is 93.78% and 95.70% for the UCF Sport dataset.

Households as Historical Ethnography: People in Motion and Roads to School

Households as Historical Ethnography: People in Motion and Roads to School

Development of infants' preferential looking toward native language speakers across distinct social contexts.

Presenting pictures of faces side by side is a common paradigm to assess infants' attentional biases according to social categories, such as gender, race, and language. However, seeing static faces does not represent infants' typical experience of the social world, which involves people in motion and performing actions. Here, we assessed infants' looking preferences for native over foreign language speakers in two social contexts: the presentation of static faces and the presentation of people performing instrumental actions. In addition, we tested infants' preferential looking at 5 and 9 months of age to assess whether their pattern of preferential looking changes across development. The results of 5-month-old infants replicated and extended previous findings by showing that, at this age, infants typically look longer at people who previously spoke their native language. As found for other social categories such as race and gender, this familiarity-based looking preference was not evident at 9 months of age when infants were presented with static faces. However, when presented with more informative dynamic events, 9-month-old infants showed a temporally aligned preference for the native over the foreign language speaker. Specifically, infants' looking preference was time-locked to the completion of the action goal: when speakers grasped and lifted a toy. These results suggest potentially a familiarity-based preference toward native language speakers around 5 months of age, which may later develop into a more strategic selective response in service of information-seeking. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Exploration on flexible wearable sensor motion monitoring based on novel functional polymer conjugated materials.

With the continuous development of flexible electronics, multi-functional device integration, artificial intelligence technology, etc., flexible wearable sensors are playing an increasingly important role in people's daily motion monitoring. However, current flexible wearable sensors have problems such as low accuracy, poor real-time performance, and poor stability in motion monitoring, which seriously hinder the better application of flexible wearable sensors and are not conducive to the collection and monitoring of motion signals. To this end, this paper designed a flexible wearable sensor motion monitoring system and tested its performance through the preparation and performance research of new functional polymer conjugated materials. The research results show that the motion monitoring system designed based on the new functional polymer conjugated material flexible wearable sensor has good monitoring accuracy and real-time performance. When the output data is 500 pieces, the running monitoring accuracy reaches 95.4%, and the monitoring feedback time is 0.321s; the high jump movement monitoring accuracy rate reaches 97%, and the monitoring feedback time is 0.287s; the long jump movement monitoring accuracy rate reaches 96%, and the monitoring feedback time is 0.296s. This shows that the flexible wearable sensor motion monitoring system of this paper has better performance and can meet the current demand for accuracy and real-time motion monitoring. This study highlights the impact of new functional polymer conjugated materials on flexible wearable sensors, helping to further solve the deficiencies of flexible wearable sensors in sports monitoring and promote their better development.

Real-Time Embedded Eye Image Defocus Estimation for Iris Biometrics.

One of the main challenges faced by iris recognition systems is to be able to work with people in motion, where the sensor is at an increasing distance (more than 1 m) from the person. The ultimate goal is to make the system less and less intrusive and require less cooperation from the person. When this scenario is implemented using a single static sensor, it will be necessary for the sensor to have a wide field of view and for the system to process a large number of frames per second (fps). In such a scenario, many of the captured eye images will not have adequate quality (contrast or resolution). This paper describes the implementation in an MPSoC (multiprocessor system-on-chip) of an eye image detection system that integrates, in the programmable logic (PL) part, a functional block to evaluate the level of defocus blur of the captured images. In this way, the system will be able to discard images that do not have the required focus quality in the subsequent processing steps. The proposals were successfully designed using Vitis High Level Synthesis (VHLS) and integrated into an eye detection framework capable of processing over 57 fps working with a 16 Mpixel sensor. Using, for validation, an extended version of the CASIA-Iris-distance V4 database, the experimental evaluation shows that the proposed framework is able to successfully discard unfocused eye images. But what is more relevant is that, in a real implementation, this proposal allows discarding up to 97% of out-of-focus eye images, which will not have to be processed by the segmentation and normalised iris pattern extraction blocks.

Productive Frictions

Problem, research strategy, and findings Walking, biking, and transit are known to shape street commerce, whereas private motorized mobility is assumed to act against it. I advance a new theory of productive frictions according to which opportunities for street commerce depend not on the mode of transportation but on the mode of interaction between people in motion and the built environment. The construct of productive frictions is grounded in Vietnam’s motorbike-centric urbanism. There, what core factors relate private motorized mobility with vibrant retail that anchors street life? To answer this question, I recorded 68 interviews and 333 video clips of street life in Ho Chi Minh City in 2018. Grounded theory methods guided systematic data collection, coding, and mixed methods analyses that led to the conceptualization of productive frictions. Productive frictions are the opportunities for social interactions produced by the contact of people on the move with the built environment they traverse. In Ho Chi Minh City, the core factors that create contact and make motorbike riders particularly prone to productive frictions include: slow speed, direct sensory perceptions, ease of weaving in and out of traffic, and abundant stimuli from stalls, stores, and people lining the streets. Evidence suggests that motorbike riders experience productive frictions less intensely than pedestrians but over greater distances, whereas automobilists generally experience low levels of productive frictions. Takeaway for practice Productive frictions support small businesses, which shape accessibility, economic vibrancy, and street life. Cities like Ho Chi Minh City experiencing rising automobility should preserve motorized two-wheeled mobility for their productive frictions benefits, at least until mass transit is sufficiently developed to support dense and walkable urbanism.

Civil War Settlers: Scandinavians, Citizenship, and American Empire, 1848–1870

Civil War Settlers: Scandinavians, Citizenship, and American Empire, 1848–1870

The Development and Demonstration of an Enhanced Risk Model for the Evacuation Process of Large Passenger Vessels

Evacuating a large and complex environment, such as a large passenger vessel, either cruise or RoPax, is a safety-critical task that involves thousands of people in motion and a complex decision-making process. Despite the significant enhancement of maritime safety over the years, various hazards still pose threats to passengers and crew. To deal with this reality, the SafePASS project radically redefines the evacuation process by introducing novel technological solutions. In this context, this paper presents, in detail, an enhanced risk model for the ship evacuation process in order to facilitate the understanding of the actual risks of the process in fire and flooding accidents, and to assess various risk control measures and options toward risk mitigation. The risk model covers the entire event sequence in emergency cases on board, until the survival at sea phase, and it is constructed in two levels, following a combination of event tree analysis and Bayesian networks. Results show the risk corresponds to baseline scenarios for each accident case, which are also verified by relevant IMO and EMSA studies, and an example case of risk control option (RCO) is introduced to the model to demonstrate its ability to assess RCO’s efficiency in terms of risk reduction.

Attention‐aware spatio‐temporal learning for multi‐view gait‐based age estimation and gender classification

AbstractRecently, gait‐based age and gender recognition have attracted considerable attention in the fields of advertisement marketing and surveillance retrieval due to the unique advantage that gaits can be perceived at a long distance. Intuitively, age and gender can be recognised by observing people's static shape (e.g. different hairstyles between males and females) and dynamic motion (e.g. different walking velocities between the elderly and youth). However, most of the existing gait‐based age and gender recognition methods are based on Gait Energy Image (GEI), which loses the capability of explicitly modelling temporal dynamic information and is not robust to the multi‐view recognition that inevitably happens in a real application. Therefore, in this study, an Attention‐aware Spatio‐Temporal Learning (ASTL) framework is proposed, which employs a silhouette sequence as input to learn essential and invariable spatial‐temporal gait representations. More specifically, a Multi‐Scale Temporal Aggregation (MSTA) module provides an effective scheme for dynamic gait description by exploring and aggregating multi‐scale temporal interval information, which is a core supplement to spatial representation. Then, a Multiple Attention Aggregation (MAA) module is designed to help the network focus on the most discriminatory information along temporal, spatial and channel dimensions. Finally, a Multimodal Collaborative Learning (MCL) block gives full play to the advantages of different modal features through a multimodal cooperative learning strategy. The mean absolute error (MAE) for the age estimation and the correct classification rate (CCR) for the gender classification on OU‐MVLP achieve 6.68 years and 97%, respectively, demonstrating the superiority of the method. Ablation experiments and visualisation results also prove the effectiveness of the three individual modules in their framework.

Impact of feature reduction techniques on classification accuracy of machine learning techniques in leg rehabilitation

The scientific community has recently shown a lot of interest in biometric-based person recognition systems. It is a dynamic technology that tries to recognize biometrics automatically, swiftly, precisely, and consistently. Gait recognition is a sort of biometric classification that concentrates on identifying persons utilizing personal measurements and correlations, including trunk and limb size, in addition to spatial data connected to innate patterns in people's motions. The purpose of this study is to highlight how important it is to use feature reduction strategies to increase classification accuracy. Two of these approaches are employed in this work: Principal Component Analysis (PCA) and Singular Value Decomposition (SVD). To classify foot disease, six machine learning techniques are deployed as classifiers. These classifiers are Random Forest (RF), Naïve Bayes (NB), K-Nearest Neighbors (KNN), Logistic Regression (LR), Decision Tree (DT), and Stochastic Gradient Descent (SGD) for the purpose of determining which classifier performs best in classifying leg rehabilitation data. Experimental results using the EMG dataset in Lower Limb indicate that the classification accuracy reached 99% with a time not exceeding a few seconds.

“Deep in their hearts they still wanna come back” – Sonsorolese people in motion and the implications on culture and identity

“Deep in their hearts they still wanna come back” – Sonsorolese people in motion and the implications on culture and identity

Usefulness of Handrail for Standing-Sitting Support System Focusing on Older-Middle-Aged and Young People's Standing-Sitting Motion

Usefulness of Handrail for Standing-Sitting Support System Focusing on Older-Middle-Aged and Young People's Standing-Sitting Motion

People in Motion: Introduction to Transnational Movements and Transwar Connections in the Anthropological and Genetic Study of Human Populations

People in Motion: Introduction to Transnational Movements and Transwar Connections in the Anthropological and Genetic Study of Human Populations

Fostering Global Citizenship Education by the New American Diaspora. An approach from a critical perspective

ABSTRACT This article focuses on the diasporas’ role in fostering Global Citizenship Education (GCE) and provides a basis for understanding how diaspora organizations educate themselves to defend their rights in everyday life. I argue that diaspora organizations are potential agents that foster GCE to defend rights in a hostile environment against people in motion. From the GCE-driven critical perspective, this article offers an interdisciplinary dialogue between Diaspora Studies (International Relations), Sociology of Education, and Sociology of Collective Action to identify the practice of GCE at the New American Diaspora in Mexico City. The article is oriented to discussing the non-state actors’ agency in promoting GCE outside the walls of schools and classrooms. With a qualitative approach (case study), through an American/Mexican organization, I offer empirical evidence through the lens of GCE: The Others Dreams in Action (ODA) and its cultural space, namely the Poch@ House.

Incorporating Affective Computing Into an Interactive System With MakeyMakey

People's motions or behaviors often ensue from these positive or negative emotions. Set off either subconsciously or intentionally, these fragmentary responses also represent people's emotional vacillations at different times, albeit rarely noted or discovered. This system incorporates affective computing into an interactive installation: While a user is performing an operation, the system instantaneously and randomly generates corresponding musical instrument sound effects and special effects. The system is intended to enable users to interact with emotions through the interactive installation to yield a personalized digital artwork as well learning about how emotions affect the causative factors of consciousness and personal behaviors. At the end of the process, this project design renders three questionnaires for users to fill in as a means to enhance the integrity and richness of the system with a survey and to further increase the stability and precision of the system through progressive modifications aligned with user suggestions.

Trade, uneven development and people in motion: Used territories and the initial spread of COVID-19 in Mesoamerica and the Caribbean

Mesoamerica and the Caribbean form a region comprised by middle- and low-income countries affected by the COVID-19 pandemic differently. Here, we ask whether the spread of COVID-19, measured using early epidemic growth rates (r), reproduction numbers (Rt), accumulated cases, and deaths, is influenced by how the ‘used territories’ across the regions have been differently shaped by uneven development, human movement and trade differences. Using an econometric approach, we found that trade openness increased cases and deaths, while the number of international cities connected at main airports increased r, cases and deaths. Similarly, increases in concentration of imports, a sign of uneven development, coincided with increases in early epidemic growth and deaths. These results suggest that countries whose used territory was defined by a less uneven development were less likely to show exacerbated COVID-19 patterns of transmission. Health outcomes were worst in more trade-dependent countries, even after controlling for the impact of transmission prevention and mitigation policies, highlighting how structural effects of economic integration in used territories were associated with the initial COVID-19 spread in Mesoamerica and the Caribbean.

Metaphorical perceptions of sports management students in Turkey with regard to “leadership” notion

This study aims to analyze the metaphorical perceptions of sports management students in Turkey with regard to “leadership” notion. In the study, qualitative research method was used. The study group of the research was composed of 90 people studying at a Sports Management Department in a Faculty of Sports Sciences in 2020-2021 academic year in Turkey. In order to determine the metaphorical perceptions of prospective sports managers with regard to leadership Notion, the study required the participants to complete the sentence “Leadership is like... because...”. The descriptive analysis method was used for the analysis of the data. The analysis showed that metaphorical descriptions made by the participants with regard to leadership were composed of the themes of ‘providing guidance’, ‘influencing people’, ‘uniting people’ and ‘setting people in motion’. It was found that the most common metaphorical perception of participants with regard to leadership notion was ‘providing guidance’, followed by ‘influencing people’. It was also seen that the least common metaphorical perceptions of participants with regard to leadership were related to the themes of ‘setting people in motion’ and ‘uniting people’.

Scribal service people in motion: Culture, power and the politics of mobility in India’s long eighteenth century, c. 1680–1820

A decade after IESHR’s Special Issue of 2010, ‘Munshis, Pandits and Record-Keepers: Scribal communities and historical change in India’, we return again to the challenges and dilemmas that scribes, bureaucrats, intellectuals and literati of different kinds faced during the early modern centuries. Building on recent advances in our understanding of these key communities, this Special Issue turns the focus to the eighteenth century. We explore the strategies of individuals as they navigated new conditions of service, unexpected opportunities for personal advancement and the complexities of affiliation amid personal networks that extended across boundaries of region, language and religion. We investigate the important role of scribal people in the literary cultures of the eighteenth century, and the new meanings that their participation gave to literary syncretism and hybridity. We return again to questions of intellectual history and the reflections of scribal service people as they sought to find meaning in the collapse of old political formations and the rise of new ones. This Introduction surveys the recent scholarly literature in these connected fields, situates the essays here in the context of this new work, and identifies some of the key questions which remain to be answered in this critical era of transition between the India of ‘early modernity’ and the coming of the colonial world.

A Device-Free Intelligent Alarm System Based on the Channel State Information

Security has always been a hot issue of concern. Most of today's home security systems are based on cameras or sensors. These systems have challenges, such as involving in users’ privacy and high initial cost, so they are not highly popular. In order to resolve these challenges, a single commodity Wi-Fi device is utilized to design a device-free intelligent alarm system. The proposed system relies on the cooperation of active and passive alarm modules so that the user is not required to wear any sensor. In the active alarm module, a novel algorithm is proposed to identify the user's tiny help-seeking action (e.g.special breath) using channel state information (CSI). Moreover, the passive alarm module employs the CSI-based prospect detection to identify the physical attack behavior. The proposed system uses the invisible Wi-Fi signal to identify the people's motion. Then, it uses the results of the activity recognition to identify the dangerous event, which has the characteristic of the concealment. A large number of experiments are carried out in the present study to investigate the accuracy and robustness of the proposed system. It is found that the average accuracy of the system identification is over 95%.

Dissociating gait from static appearance: A virtual reality study of the role of dynamic identity signatures in person recognition

Studies on person recognition have primarily examined recognition of static faces, presented on a computer screen at a close distance. Nevertheless, in naturalistic situations we typically see the whole dynamic person, often approaching from a distance. In such cases, facial information may be less clear, and the motion pattern of an individual, their dynamic identity signature (DIS), may be used for person recognition. Studies that examined the role of motion in person recognition, presented videos of people in motion. However, such stimuli do not allow for the dissociation of gait from face and body form, as different identities differ both in their gait and static appearance. To examine the contribution of gait in person recognition, independently from static appearance, we used a virtual environment, and presented across participants, the same face and body form with different gaits. The virtual environment also enabled us to assess the distance at which a person is recognized as a continuous variable. Using this setting, we assessed the accuracy and distance at which identities are recognized based on their gait, as a function of gait distinctiveness. We find that the accuracy and distance at which people were recognized increased with gait distinctiveness. Importantly, these effects were found when recognizing identities in motion but not from static displays, indicating that DIS rather than attention, enabled more accurate person recognition. Overall these findings highlight that gait contributes to person recognition beyond the face and body and stress an important role for gait in real-life person recognition.