Human Action Research Articles

Human in the collaborative loop: a strategy for integrating human activity recognition and non-invasive brain-machine interfaces to control collaborative robots.

Human activity recognition (HAR) and brain-machine interface (BMI) are two emerging technologies that can enhance human-robot collaboration (HRC) in domains such as industry or healthcare. HAR uses sensors or cameras to capture and analyze the movements and actions of humans, while BMI uses human brain signals to decode action intentions. Both technologies face challenges impacting accuracy, reliability, and usability. In this article, we review the state-of-the-art techniques and methods for HAR and BMI and highlight their strengths and limitations. We then propose a hybrid framework that fuses HAR and BMI data, which can integrate the complementary information from the brain and body motion signals and improve the performance of human state decoding. We also discuss our hybrid method's potential benefits and implications for HRC.

Foreknowledge and causal determinism

AbstractI evaluate Patrick Todd's critique of the idea accepted by many, including (in contemporary philosophy) Nelson Pike and John Martin Fischer, that there can be non‐causal constraints on human actions (including basic actions). I suggest that Todd's critical reflections, although illuminating, are not persuasive. I defend non‐causal constraints in part by putting forward an interpretation of the intuitive idea of the fixity of the past following Carl Ginet: our freedom is the power to add to the given past.

Superación del objetivismo mediante experiencias creativas en la filosofía de López Quintás

The overcoming of objectivism is one of the programmatic desires of a large part of 20th century philosophy, since the various objectivist currents have made self-understanding of the human being extremely difficult, since they have frustrated a balanced interpretation of the relationships between ethics, aesthetics, metaphysics and religion, fragmenting the multiform variety of human life. It is in this context that the work of Alfonso López Quintás, the main Spanish representative of dialogical personalism, is situated. He has developed an original perspective on human experience and creativity that has allowed for the attainment of a new and fruitful hermeneutics of human action. The regulating ideal that guides López Quintás' thought consists of a return to the articulation of fundamental human experiences, those that enrich and give meaning to human existence. In order to achieve a full understanding of the structural affinity of the diverse experiences of the person, López Quintás has made a contribution to personalist thought by overcoming the incipient intellectualism of other thinkers and offering an integral philosophy based on a series of methodological elements: the levels of reality, the category of encounter, the theory of creative play and the concept of reversible experience.

A benchmark dataset and semantics-guided detection network for spatial–temporal human actions in urban driving scenes

In real urban driving scenes, human actions are very complex and have the characteristic of multiple concurrent actions. It has a great significance to detect human actions in urban traffic scenes for auxiliary or autonomous driving systems. In this view, we introduce the TITAN-Human Action dataset for the task of multi-person spatial–temporal action detection in urban driving scenes. TITAN-Human Action provides the fine-grained action labels and location coordinates for 17,574 persons in the processed frames from the TITAN dataset. Furthermore, we propose a semantics-guided detection network (SGDNet) based on a semantic inference module (SIM) for spatial–temporal human action detection in urban driving scenes. SIM encodes the category labels into sentence vectors at the semantic level with prompting and embedding, utilizes graphs to represent the directed co-occurrence relations between categories, and adopts the graph convolutional network for semantic inference. SGDNet exploits the inference results of SIM to guide the visual branch in better performing human action detection, thereby achieving the integration of visual and linguistic information. We conducted experiments to evaluate SGDNet and several baseline methods on the TITAN-Human Action dataset, and reveal the generalizability of SIM in spatial–temporal human action detection. The source code and annotation files will be available at https://github.com/yyhbswyn/SGDNet.

Self-fulfillment and Work in the Light of "The Acting Person" of Karol Wojtyla

This study focused on the philosophy of Karol Wojtyla in his book entitled “The Acting Person” about one of the activities of a human person, i.e. work itself. Although he did not dedicate any topic to human work, his very explanation of the action of the person as both subjective and personal is what human work is. Work, as lived experience, is one of the many actions a human person is capable of doing. On one side, despite the toilsome or burdensome character of human work, there exists a uniqueness in the person apart from beings. On the other, despite the uniqueness and value of work, there still exists a dehumanization from work, that of being replaced by faster and seemingly more reliable machinery or technology. However, work, as one of the many voluntary human actions, actually reveals the person and goes beyond his cosmological situatedness as simply a man. It is in the transcendence in action that changes these negative connotations of work putting the person as the subject and never the object of work. Work is a true manifestation of, first and foremost, our consciousness. The human person is not only conscious of his actions but even conscious of his conscious acting. Since the person is conscious of what he is doing, he is the efficient cause, that is, the active agent that brings about a series of effects. This conscious and efficacious acting brings about what Wojtyla would call self-determination, self-possession and self-governance. Lastly, work as one of the conscious and efficacious actions of a human person brings about self-fulfilment or in other words “felicity,” knowing that it is the same person who creates and contributes, in and through his work how and what it is to be human.

Computational Modeling of Sodium-Ion-Channel-Based Glucose Sensing Biophysics to Study Cardiac Pacemaker Action Potential

Elevated blood glucose levels, known as hyperglycemia, play a significant role in sudden cardiac arrest, often resulting in sudden cardiac death, particularly among those with diabetes. Understanding the internal mechanisms has been a challenge for healthcare professionals, leading many research groups to investigate the relationship between blood glucose levels and cardiac electrical activity. Our hypothesis suggests that glucose-sensing biophysics mechanisms in cardiac tissue could clarify this connection. To explore this, we adapted a single-compartment computational model of the human pacemaker action potential. We incorporated glucose-sensing mechanisms with voltage-gated sodium ion channels using ordinary differential equations. Parameters for the model were based on existing experimental studies to mimic the impact of glucose levels on pacemaker action potential firing. Simulations using voltage clamp and current clamp techniques showed that elevated glucose levels decreased sodium ion channel currents, leading to a reduction in the pacemaker action potential frequency. In summary, our mathematical model provides a cellular-level understanding of how high glucose levels can lead to bradycardia and sudden cardiac death.

Exploring health inequities through the actor‐network theory lens

AbstractSocial theory plays an important role in the nursing discipline and nursing inquiry as it helps conceptually embed nursing in the larger picture of the social world. For example, a broad category of critical theory provides a unique lens for uncovering social conditions of inequity and oppression. Among the sociological theories, actor‐network theory (ANT) is an approach to research and analysis that has recently gained interest among nurse philosophers and researchers. Studies guided by ANT seek to understand phenomena of interest as constituted within the relationships between human and nonhuman actors to understand how care practices are co‐created/enacted and how they can be made more humane. In this paper, we describe the benefits of ANT for examining healthcare access for incarcerated individuals with life‐limiting illnesses accessing palliative care and for people using illicit drugs. We argue that attention to the materiality of care practices can contribute to efforts of advancing health equity for these groups.

Simple esteem and the method of commonplaces in Pufendorf

ABSTRACT In his discussion of simple esteem—one of the moral entities meant to regulate human actions—Pufendorf invokes a juridical commonplace: the rule that, before evidence to the contrary, we should presume others to be good. This argumentative strategy is an illuminating example for understanding his method of commonplaces. The present paper has three goals: (1) to analyze how Pufendorf adopted from legal humanism the view that presumptions should be based on considerations of what comes about most easily in nature; (2) to show that Pufendorf’s inclusion of ethical aspects in the juridical presumption of goodness is an application of this view of forming presumptions; (3) to argue that Pufendorf did not regard juridical and philosophical commonplaces as expressions of a particular stage of intellectual history but rather as the result of reflection about human needs and abilities.

Strategic naturalizing in the Anthropocene: Managing cells, bodies and ecosystems

Discussions on the Anthropocene have called for increased attention to how the effects of human actions on the planet are accounted for. While much of this debate remains at a theoretical level, more studies on situated Anthropocene realities have been called for. Contributing to the latter, this article explores how experimental and clinical interventions are being accounted for in life science laboratories. Drawing on three research cases, genetically modified mosquitoes, laboratory-grown stem cell lines and assisted reproduction in the IVF clinic, the article traces how ‘strategic naturalizing’ is conducted to make sense of and justify human interventions on cells, bodies and ecosystems. Strategic naturalizing in laboratory work is situated, fluid, and also implicates the presence of the social scientist. Although naturalizing biotechnologies is not a new phenomenon, according to our observations scientists increasingly draw on notions of a planet profoundly transformed by human intervention as they conceptualize their own accountability. Consequently, we propose that strategic naturalizing is emerging as an elemental logic in the patchy local enactments of the Anthropocene and its concerns. In the context of experimental and clinical laboratory work, it is a key element in enacting good science and orienting the work towards making biotechnology acceptable in wider society. In studying this, the social scientist also is implicated in situated local enactments of the Anthropocene.

MAFormer: A cross-channel spatio-temporal feature aggregation method for human action recognition

Human action recognition has been widely used in fields such as human–computer interaction and virtual reality. Despite significant progress, existing approaches still struggle with effectively integrating hierarchical information and processing data beyond a certain frame count. To address these challenges, we introduce the Multi-AxisFormer (MAFormer) model, which is organized in terms of spatial, temporal, and channel dimensions of the action sequence, thereby enhancing the model’s understanding of correlations and intricate structures among and within features. Drawing on the Transformer architecture, we propose the Cross-channel Spatio-temporal Aggregation (CSA) structure for more refined feature extraction and the Multi-Axis Attention (MAA) module for more comprehensive feature aggregation. Moreover, the integration of Rotary Position Embedding (RoPE) boosts the model’s extrapolation and generalization abilities. MAFormer surpasses the known state-of-the-art on multiple skeleton-based action recognition benchmarks with the accuracy of 93.2% on NTU RGB+D 60 cross-subject split, 89.9% on NTU RGB+D 120 cross-subject split, and 97.2% on N-UCLA, offering a novel paradigm for hierarchical modeling in human action recognition.

What Can We Do About the Climate Crisis?

Understanding how our planet’s climate is changing because of human actions is super important if we want to keep living here. A changing climate means hotter weather, droughts, wildfires, heavy rains, storms, and floods. To fix things, we need to figure out which human activities are making the climate act this way and how we can change those activities. Everyone has a part to play—politicians, companies, engineers, and citizens. Small things like changing how we travel or use energy can help a lot. When the younger people who will inherit the planet come together and demand action on climate change, they can have a big impact. It helps when young people combine these demands with personal action, to show others that they, and lots of other people, care about this issue: by eating less red meat, using transportation wisely, pushing for changes in how businesses operate, and voting for leaders who care about the environment.

Guess what? Only correct choices forge immediate stimulus–response bindings in guessing scenarios

A central mechanism of human action control is the prompt binding between actions and the stimuli provoking them. Perceiving the same stimuli again retrieves any bound responses, facilitating their execution. An open question is whether such binding and retrieval only emerges when stimulus–response rules are known upon taking action or also when agents are forced to guess and receive feedback about whether they were successful or not afterward. In two experiments, we tested the hypothesis that knowing rules before responding would boost binding between stimuli and responses during action-taking relative to guessing situations. Second, we assessed whether the content of the feedback matters for binding in that agents might use feedback to build correct stimulus–response bindings even for wrong guesses. We used a sequential prime-probe design to induce stimulus–response binding for prime responses that were either rule-based or guesses, and to measure retrieval of these bindings in response times and errors in the probe. Results indicate that binding and retrieval emerge for successful but not for wrong guesses. Binding effects for correct guesses were consistently small in effect size, suggesting that pre-established stimulus–response bindings from instructed rules might indeed boost binding when taking action.

A survey of video-based human action recognition in team sports

Over the past few decades, numerous studies have focused on identifying and recognizing human actions using machine learning and computer vision techniques. Video-based human action recognition (HAR) aims to detect actions from video sequences automatically. This can cover simple gestures to complex actions involving multiple people interacting with objects. Actions in team sports exhibit a different nature compared to other sports, since they tend to occur at a faster pace and involve more human-human interactions. As a result, research has typically not focused on the challenges of HAR in team sports. This paper comprehensively summarises HAR-related research and applications with specific focus on team sports such as football (soccer), basketball and Australian rules football. Key datasets used for HAR-related team sports research are explored. Finally, common challenges and future work are discussed, and possible research directions identified.

The crisis of truth, and Its impact on human actions

Not only does Moral Theology tell us what we should do, but it also provides the reasons why we should do some things and avoid others. Over the centuries Christians paid attention to God’s creatures because they realised that He speaks to us through them and reveals His will as well (Rom 1). This issue also became the object of metaphysical inquiry. The concept of the truth of all things explained how man gets knowledge about God’s will through his creatures, which he subsequently should take into account in his moral conduct. The Enlightment proclaimed human freedom from religious beliefs and restrictions. Its philosophy, known as modern philosophy, tried to „conquer” metaphysics and the notion of the truth of all things. This paper presents these efforts and their consequences.

Adam Smith, human betterment, and his erroneous indentification with self-interested human action

In this essay I discuss the proposition that Adam Smith has been widely misinterpreted as asserting in his second book, The Wealth of Nations, that emergent modern economies are driven by the strictly selfish motives of their human inhabitants. The propositions articulated in his first book, The Theory of Moral Sentiments, which offered a theory of society, extended seamlessly into his second book, and continued to be part of his theory of economy. In both works, he distinguished the universal state of being self-interested from actions taken in one's self-interest, and modeled people as creating and following rules of propriety that enabled them to better get along with their neighbors. This distinction explains why, in his second book, he refers to people following their “own interest” in their “own way” explicitly avoiding any suggestion that people pursued only their strictly selfish interests in the process of wealth creation. That cautionary effort failed, although Smith continues to be a spectacularly successful theorist of society and economy, especially of interest to scholars in behavioral and experimental economics.

The fundamentally uncertain economic agent: Brian J. Loasby’s growth of knowledge approach to the psychology of human action

The fundamentally uncertain economic agent: Brian J. Loasby’s growth of knowledge approach to the psychology of human action

Perception of human actions on the four fundamental dimensions of formidableness, friendliness, intentionality and abduction

Perception of human actions on the four fundamental dimensions of formidableness, friendliness, intentionality and abduction

Ethical aspects and applications of artificial intelligence in maxillofacial imaging

Artificial intelligence (AI) seeks to develop algorithms and software capable of emulating intelligent human actions. AI applications in dentistry hold considerable promise for enhancing the precision and effectiveness of diverse dental imaging techniques. While this domain is still relatively young, it demands thorough exploration. Human supervision remains essential to mitigate potential adverse consequences. This article endeavors to shed light on the prevailing ethical considerations stemming from the integration of artificial intelligence into dental practice. It seeks to stimulate discourse surrounding potential ethical pitfalls and encourages critical examination of these issues.

A novel hybrid deep learning approach with GWO–WOA optimization technique for human activity recognition

The effectiveness of Human Activity Recognition (HAR) models can be largely attributed to the components derived from domain expertise. The classification system swiftly and effectively categorizes human physical activity by utilizing a comprehensive collection of variables. To construct HAR models and categorize different activities, deep learning algorithms have recently seen increased application in academic research for autonomously extracting features from raw sensory data. The primary goal of this study is to develop a strong and accurate activity classification model by first extracting features from an input dataset and then using deep learning models. In this research, we look at how well the model does in the field of HAR. Analyzing time-series data from smartphones and wearable sensors, algorithms based on deep learning (DL) have been used to forecast various human actions. Applying DL-based methods to time-series data presents a variety of challenges, notwithstanding their usage for activity identification. If the suggested approach is put into practice, the concerns mentioned before may be alleviated. To construct HAR classification techniques using data collected from wearable sensors, this study presents two Hybrid Learning Algorithms (HLA). This research employs Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) methods to teach the model sequential and spatial patterns. The process of selecting characteristics has been enhanced through the use of optimization techniques. Together, the Whale Optimization Algorithm and the Grey Wolf Optimizer form a Hybrid Optimization approach, which is introduced in this study. By combining and capitalizing the benefits of both approaches, the hybrid technique enhances the optimization process as a whole. This research may also assist individuals who have undergone amputations or experienced strokes in selecting an appropriate model and developing a personalized gait reference trajectory.

Divine teleology in Spinoza's thought: an underexplored side of Spinoza’s philosophical journey

ABSTRACT This paper shows that Spinoza went through a drastic change in his view on divine teleology, and that this change is worth paying attention to. In the Short Treatise (KV), Spinoza endorsed a version of divine teleology. As is widely recognized, however, he explicitly rejects divine teleology in the Ethics. I argue that this marks a significant change in his view. To illustrate the significance, I argue that Spinoza consistently maintains the following two premises in both the KV and the Ethics: (1) human beings act on account of some end; (2) human actions are actions of God. While the endorsement of divine teleology is consistent with these two, the rejection of divine teleology results in a trilemma. The trilemma, to be sure, can be resolved by introducing referential opacity to divine action contexts. I argue, however, that it is worth asking why Spinoza revised his view in this way.