Human Cognitive Mechanisms Research Articles

Memory-biomimetic deep Bayesian filtering

The widely used Bayesian filtering has a solid theoretical foundation and an efficient computational architecture, but it suffers from first-order Markovianity and the inability to learn from offline data. While recent research has utilized deep learning to overcome these limitations, issues remain with respect to theoretical rigor and scalability, resulting in the non-guaranteed optimality of filtering. In this work, we approach these problems from a biomimetic perspective. Firstly, a memory-based state evolution model is constructed inspired by the human cognitive mechanism, which enables recursive filtering while incorporating long-term state information. Secondly, a memory-biomimetic deep Bayesian filtering algorithm with good interpretability is designed, which improves the filtering process at multiple levels by naturally integrating recurrent neural networks and Bayesian filtering architecture. Thirdly, the Gaussian approximation implementation of the proposed filtering method is derived, which brings an efficient computational process with good analytical properties. Extensive experiments for airborne target tracking are performed to demonstrate the excellent estimation performance of the proposed method.

Fuser: An enhanced multimodal fusion framework with congruent reinforced perceptron for hateful memes detection

As a multimodal form of hate speech on social media, hateful memes are more aggressive and cryptic threats to the real life of humans. Automatic detection of hateful memes is crucial, but the images and texts in most memes are only weakly consistent or even irrelevant. Although existing works have achieved the initial goal of detecting hateful memes with pre-trained models, they are limited to monolithic inference methods while ignoring the semantic differences between multimodal representations. To strengthen the comprehension and reasoning of the hidden meaning behind the memes by combining real-world knowledge, we propose an enhanced multimodal fusion framework with congruent reinforced perceptron for hateful memes detection. Inspired by the human cognitive mechanism, we first divide the extracted multisource representations into main semantics and auxiliary contexts based on their strength and relevance, and then precode them into lightly correlated embeddings with unified spatial dimensions via a novel prefix uniform layer, respectively. To jointly learn the intrinsic correlation between primary and secondary semantics, a congruent reinforced perceptron with brain-like perceptual integration is designed to seamlessly fuse multimodal representations in a shared latent space while maintaining the feature integrity in the sub-fusion space, thereby implicitly reasoning about the subtle metaphors behind the memes. Extensive experiments on four benchmark datasets fully demonstrate the effectiveness and superiority of our architecture compared with previous state-of-the-art methods.

Perplexity Games: Maoism vs. Literature through the Lens of Cognitive Stylometry

The arrival of large language models (LLMs) has provoked an urgent search for stylistic markers that could differentiate machine text from human text, but while the human-like appearance of machine text has captivated public attention, the reverse phenomenon—human text becoming machine-like—has raised much less concern. This conceptual lag is surprising given the ample historical evidence of state-backed attempts to regulate human thought. The present article proposes a new comparative framework, Perplexity Games, to leverage the predictive power of LLMs and compare the statistical properties of Maospeak, a language style that emerged during the Mao Zedong’s era in China (1949-1976), with the style of canonical modern Chinese writers, such as Eileen Chang (1920-1995) and Mo Yan (1955-). The low perplexity of Maospeak, as computed across different GPT models, suggests that the impact of ideologies on language can be compared to likelihood-maximization text-generation techniques which reduce the scope of valid sequence continuations. These findings have cognitive implications: whereas engineered languages such as Maospeak hijack the predictive mechanisms of human cognition by narrowing the space of linguistic possibilities, literature resists such cognitive constraints by dispersing the probability mass over multiple, equally valid paths. Exposure to diverse language data counters the influences of ideologies on our linguistically mediated perceptions of the world and increases the perplexity of our imaginations.

CKTN: Commonsense knowledge transfer network for human activity understanding

In most human activity understanding research, various deep learning networks are well designed to fit the character distribution of different human activities in images. After being fed with enough training data, the networks can perceive related patterns passively. Such abilities originate from the stimulation of training data, but these networks lack the ability to perform subjective judgment. When lacking sufficient training data, networks have difficulty perceiving valuable information, which leads to poor performance. However, human beings can infer human activities in complex situations through subjective judgment with their knowledge. On this point, we propose the commonsense knowledge transfer network (CKTN), which is empowered with human cognitive mechanisms and is able to understand human activities by using prior commonsense knowledge. More specifically, we study the structural combination rules of human bodies and explore the co-occurrence relationship between different body parts and objects. Then, we construct the part action cooccurrence probability matrix and human skeleton knowledge matrix, which work as prior knowledge, guiding our network to absorb and reason what the human activities in images are. Compared with traditional deep learning methods, our network realizes the unification of both subjective cognition and passive perception abilities. Experiments show the effectiveness of this method.

Click-pixel Cognition Fusion Network with Balanced Cut for Interactive Image Segmentation.

Interactive image segmentation (IIS) has been widely used in various fields, such as medicine, industry, etc. However, some core issues, such as pixel imbalance, remain unresolved so far. Different from existing methods based on pre-processing or post-processing, we analyze the cause of pixel imbalance in depth from the two perspectives of pixel number and pixel difficulty. Based on this, a novel and unified Click-pixel Cognition Fusion network with Balanced Cut (CCF-BC) is proposed in this paper. On the one hand, the Click-pixel Cognition Fusion (CCF) module, inspired by the human cognition mechanism, is designed to increase the number of click-related pixels (namely, positive pixels) being correctly segmented, where the click and visual information are fully fused by using a progressive three-tier interaction strategy. On the other hand, a general loss, Balanced Normalized Focal Loss (BNFL), is proposed. Its core is to use a group of control coefficients related to sample gradients and forces the network to pay more attention to positive and hard-to-segment pixels during training. As a result, BNFL always tends to obtain a balanced cut of positive and negative samples in the decision space. Theoretical analysis shows that the commonly used Focal and BCE losses can be regarded as special cases of BNFL. Experiment results of five well-recognized datasets have shown the superiority of the proposed CCF-BC method compared to other state-of-the-art methods. Code will be publicly available at https://github.com/lab206/CCF-BC.

Parallel Multi-Path Network for Ocular Disease Detection Inspired by Visual Cognition Mechanism.

Various ocular diseases such as cataracts, glaucoma, and diabetic retinopathy have become several major factors causing non-congenital visual impairment, which seriously threatens people's vision health. The shortage of ophthalmic medical resources has brought huge obstacles to large-scale ocular disease screening. Therefore, it is necessary to use computer-aided diagnosis (CAD) technology to achieve large-scale screening and diagnosis of ocular diseases. In this work, inspired by the human visual cognition mechanism, we propose a parallel multi-path network for multiple ocular diseases detection, called PMP-OD, which integrates the detection of multiple common ocular diseases, including cataracts, glaucoma, diabetic retinopathy, and pathological myopia. The bottom-up features of the fundus image are extracted by a common convolutional module, the Low-level Feature Extraction module, which simulates the non-selective pathway. Simultaneously, the top-down vessel and other lesion features are extracted by the High-level Feature Extraction module that simulates the selective pathway. The retinal vessel and lesion features can be regarded as task-driven high-level semantic information in the physician's disease diagnosis process. Then, the features are fused by a feature fusion module based on the attention mechanism. Finally, the disease classifier gives prediction results according to the integrated multi-features. The experimental results indicate that our PMP-OD model outperforms other state-of-the-art (SOTA) models on an ocular disease dataset reconstructed from ODIR-5K, APTOS-2019, ORIGA-light, and Kaggle.

Pedestrian intention estimation and trajectory prediction based on data and knowledge‐driven method

AbstractWith the development of deep learning technology, the problem of data‐driven trajectory prediction and intention recognition has been widely studied. However, the pedestrian trajectory prediction and intention recognition methods based solely on data‐driven have weak data description ability and black‐box characteristics, which cannot reason about pedestrian crossing intention and predict pedestrian crossing trajectory as humans do. To address the above problems, the authors proposed a data and knowledge‐driven pedestrian intention estimation and trajectory prediction method by imitating human cognitive mechanisms. In the pedestrian intention inference process, the authors adopted the knowledge‐driven method. As a first step, the authors built a knowledge graph of pedestrian crossing scenes, and then paired it with a Bayesian network to estimate pedestrian crossing intentions. In the pedestrian trajectory prediction process, the authors used a data‐driven approach, combining pedestrian crossing trajectory features and knowledge‐based pedestrian intentions. Experiments show that all evaluation metrics of pedestrian trajectory prediction were improved after adding pedestrian intentions obtained by knowledge‐driven.

Analysis of Community Outdoor Public Spaces Based on Computer Vision Behavior Detection Algorithm

Community outdoor public spaces are indispensable to urban residents’ daily lives. Analyzing community outdoor public spaces from a behavioral perspective is crucial and an effective way to support human-centered development in urban areas. Traditional behavioral analysis often relies on manually collected behavioral data, which is time-consuming, labor-intensive, and lacks data breadth. With the use of sensors, the breadth of behavioral data has greatly increased, but its accuracy is still insufficient, especially in the fine-grained differentiation of populations and behaviors. Computer vision is more efficient in distinguishing populations and recognizing behaviors. However, most existing computer vision applications face some challenges. For example, behavior recognition is limited to pedestrian trajectory recognition, and there are few that recognize the diverse behaviors of crowds. In view of these gaps, this paper proposes a more efficient approach that employs computer vision tools to examine different populations and different behaviors, obtain important statistical measures of spatial behavior, taking the Bajiao Cultural Square in Beijing as a test bed. This population and behavior recognition model presents several improvement strategies: Firstly, by leveraging an attention mechanism, which emulates the human selective cognitive mechanism, it is capable of accentuating pertinent information while disregarding extraneous data, and the ResNet backbone network can be refined by integrating channel attention. This enables the amplification of critical feature channels or the suppression of irrelevant feature channels, thereby enhancing the efficacy of population and behavior recognition. Secondly, it uses public datasets and self-made data to construct the dataset required by this model to improve the robustness of the detection model in specific scenarios. This model can distinguish five types of people and six kinds of behaviors, with an identification accuracy of 83%, achieving fine-grained behavior detection for different populations. To a certain extent, it solves the problem that traditional data face of large-scale behavioral data being difficult to refine. The population and behavior recognition model was adapted and applied in conjunction with spatial typology analysis, and we can conclude that different crowds have different behavioral preferences. There is inconsistency in the use of space by different crowds, there is inconsistency between behavioral and spatial function, and behavior is concentrated over time. This provides more comprehensive and reliable decision support for fine-grained planning and design.

Darwin's doubt or Plantinga's conviction? Some failures in Plantinga's attempt to debunk naturalistic evolution

Abstract Darwin's Doubt (DD) – a thesis according to which the probability of the human cognitive mechanism's reliability given non-guided evolution is low – is central to Plantinga's Evolutionary Argument Against Naturalism and his suggestion that the adoption of guided evolution thesis is preferable from a theory choice point of view. In this article I'll argue that there are three fundamental failures in Plantinga's argument. First, I argue that Plantinga's argument for DD is question-begging. Second, I point out that this very same argument is not in accordance with the way the evolutionary scientists usually reason. And finally I argue that the replacement of non-guided by guided evolution violates some reasonable belief-revision procedures in the history of science.

Three-dimensional collaborative path planning for multiple UCAVs based on improved artificial ecosystem optimizer and reinforcement learning

This study proposes a multi-strategy evolutionary artificial ecosystem optimizer based on reinforcement learning (MEAEO-RL) to tackle the collaborative path-planning problem of multiple unmanned combat aerial vehicles (UCAVs) in complex environments with multiple constraints. The objective is to generate optimal candidate paths for each UCAV, ensuring they reach the destination simultaneously while considering time variables and obstacle avoidance. To overcome the limitations of the standard artificial ecosystem optimizer (AEO), such as local optimality and slow convergence, a learning framework inspired by brain-like perception is constructed. This framework enhances swarm agents with greater intelligence by fusing swarm intelligence and human cognitive mechanisms. Meanwhile, a multi-strategy database is implemented within the evolutionary learning framework to replace the single-update method of the AEO during the consumption phase. To reduce the computational complexity of the algorithm, agents in the consumption stage utilize experience accumulation from reinforcement learning to select an effective update strategy for obtaining the latest consumer location. Path-planning simulation experiments are conducted in a series of complex three-dimensional environments, demonstrating the algorithm’s robustness, improved convergence accuracy, and ability to plan collaborative paths for multiple UCAVs while satisfying various constraints.

A Cognitive-Driven Ordinal Preservation for Multimodal Imbalanced Brain Disease Diagnosis

The multi-modal imbalanced data learning problems are becoming increasingly common in the real world, especially in brain disease diagnosis. Although multi-modal data provides complementary information for decision making, it can also lead the model to be more sensitive to the adverse effects of imbalance. The existing imbalance learning methods are mostly based on single modality. In this paper, we design a cognitive driven ordinal preservation model optimized in both feature and sample levels for multi-modal imbalanced data. At the feature level, we project the original data into the label space by a second-order Laplacian manifold for better capturing the minor changes and preserving the discriminative information among samples. At the sample level, we derive the class-specific self-paced learning, simulating human cognitive mechanism, to drive data participating in learning from balance subset to the whole set, which can reduce the negative effects of imbalance on the learning model. Meanwhile, we impose the group sparse constraint on projection matrix to embed the latent relationship pattern among different modalities, and theoretically prove its convergence. The proposed method is applied to multi-modal brain disease diagnosis, including Alzheimer’s disease (AD) and epilepsy. The experimental results show that our method outperforms the existing imbalance and fusion algorithms.

Research on the standardization strategy of granular computing

As intelligent systems continue to evolve, problems are becoming increasingly complex. The constant abundance of data puts a higher demand on the value of data utilization. Granular computing is a new computational paradigm for complex problem-solving. It takes structured thinking, structured problem-solving methods, and structured information processing patterns as its research objects and belongs to the scope of higher-level human cognitive mechanism research. The development and application of granular computing must be more standardized and unified. The granular computing standardization strategy is the most direct means to promote the regularization of granular computing. In this paper, we first sort out the main applications of granular computing in standards. According to the characteristics of granular computing, a framework of its standard system is proposed to provide a reference for the subsequent research of granular computing standards. The next direction of the granular computing standards strategy is discussed, and solutions are given.

Mobile cognition: imaging the human brain in the 'real world'.

Cognitive neuroscience studies in humans have enabled decades of impactful discoveries but have primarily been limited to recording the brain activity of immobile participants in a laboratory setting. In recent years, advances in neuroimaging technologies have enabled recordings of human brain activity to be obtained during freely moving behaviours in the real world. Here, we propose that these mobile neuroimaging methods can provide unique insights into the neural mechanisms of human cognition and contribute to the development of novel treatments for neurological and psychiatric disorders. We further discuss the challenges associated with studying naturalistic human behaviours in complex real-world settings as well as strategies for overcoming them. We conclude that mobile neuroimaging methods have the potential to bring about a new era of cognitive neuroscience in which neural mechanisms can be studied with increased ecological validity and with the ability to address questions about natural behaviour and cognitive processes in humans engaged in dynamic real-world experiences.

Identification of depression state based on multi‐scale acoustic features in interrogation environment

AbstractDepression diagnosis based on speech signals has the advantages of non‐invasiveness, low cost, and few restrictions on portability. The research on the recognition of the depression state is carried out based on the acoustic information in the speech signal. Aiming at the interview dialogue speech in the consultation environment, a hierarchical attention temporal convolutional network (HATCN) acoustic depression recognition model is proposed. For sentence acoustic feature learning, a regional attention mechanism is introduced to extract multi‐scale sentence features; for segment acoustic feature extraction, the traditional attention mechanism is used to calculate, which is in line with human cognitive mechanism. In addition, a periodic focal loss function is introduced to address the imbalance of positive and negative samples in depression diagnosis. Experiments show that the proposed acoustic depression recognition model has a certain improvement in recognition performance compared with other methods. At the same time, the influence of noise on the recognition of acoustic depression in the real consultation environment is analysed through experiments, and the data enhancement is carried out utilising speech noise, which proves the effectiveness of the data expansion of speech noise.

A STUDY OF INTERSUBJECTIVITY IN TRANSLATION FROM A COGNITIVE PERSPECTIVE

With the emergence of a “cultural turn” in western translation researches since the 1970s, translators’ subjectivity has been highlighted, and some researchers have also been aware of the existence of intersubjectivity in translation activities; however, the views on the connotation and origin of intersubjectivity in translation are still controversial. This paper attempts to probe into the root causes for the existence of “intersubjectivity in translation” from a cognitive perspective, based on the fundamental “reality-cognition-language” principle in the Embodied Philosophy and cognitive linguistics. According to this principle, “cognition” mediates between “reality” and “language”. Language is formed on the basis of bodily experience and through the processing of human cognitive mechanism. Language is not a self-contained system, but closely related to the external world and human cognition. Furthermore, the author analyzes in depth Prof. Wang Yin’s viewpoint of “weakening phenomena” on “reality-cognition-language”, which sheds light on the study of intersubjectivity in translation. Qualitative research methods (including interviews and translation tests, etc.) have been adopted to collect relevant research data from carefully chosen respondents with different cultural backgrounds and bilingual competence, showing the manifestations of intersubjectivity in translation and the rationality of the kernel “reality-cognition language” principle in cognitive linguistics. In conclusion, fundamentally, it is the “commonness” and “differences” of individual subjects involved in translation activities (including the original author, the translator, the reader of the target text, and the translation initiator, etc.) together with the complicated interrelations among “reality”, “cognition” and “language” that cause intersubjectivity in translation. Intersubjectivity and subjectivity are interdependent, coexisting in the holistic field of translation.

Design considerations for a hierarchical semantic compositional framework for medical natural language understanding.

Medical natural language processing (NLP) systems are a key enabling technology for transforming Big Data from clinical report repositories to information used to support disease models and validate intervention methods. However, current medical NLP systems fall considerably short when faced with the task of logically interpreting clinical text. In this paper, we describe a framework inspired by mechanisms of human cognition in an attempt to jump the NLP performance curve. The design centers on a hierarchical semantic compositional model (HSCM), which provides an internal substrate for guiding the interpretation process. The paper describes insights from four key cognitive aspects: semantic memory, semantic composition, semantic activation, and hierarchical predictive coding. We discuss the design of a generative semantic model and an associated semantic parser used to transform a free-text sentence into a logical representation of its meaning. The paper discusses supportive and antagonistic arguments for the key features of the architecture as a long-term foundational framework.

Anthropocentric Nature of Figurative Simile and Its Correlation with Metaphor

The article presents an anthropocentric vision of the nature of figurative simile against the background of its correlation with metaphor, since simile, which underlies human cognitive mechanisms and is at the same time the basic structure, mechanism, and operation of virtually all components of the human thought process, still remains an incompletely studied phenomenon. The authors consider simile to be the quintessence of human cognitive activity, since, by creating a person’s imaginary world, it implements the ability to compare fragments of the world picture, which is inherent in the foundations of thinking, and which is a fundamental factor in categorisation and conceptualisation as the main processes of cognition. It has been found that the anthropocentric approach to the analysis of simile is justified in view of the anthropological understanding of this phenomenon as a universe of human thinking and cognition. It is fundamentally important in an anthropocentric view of the essence of simile to recognise that it lies not in the nature of the world, but in the nature of man – in human consciousness, i.e. simile is not just a way of thinking about the world, but also about what is beyond human perception – in metaphysics. It is revealed that human existence is closely connected with simile as a mental operation and an epistemological and semantic category, which is one of the powerful factors that create the inner world of a person – a picture of the world – in the mind. The interpretation of language as a complex “living” system, a creative “spirit of the folk” suggests the existence of the cognitive principle of “comparo ergo sum”. The latter is the source of the anthropocentric charge of simile, because, when cognising the world, a person compares everything to himself and likens everything to himself, which is the reason to consider this principle a separate manifestation of anthropocentrism. This also serves as a basis for defining simile as the main operation of axiological cognition, which is the basis for the formation of value concepts and value judgements.

CONSPIRACY THEORIES AS AN EXAMPLE OF DISINFORMATION IN THE NETWORK

Conspiracy theories have been with people since their inception. The tendency to conspiracy thinking is related to many human cognitive mechanisms that greatly affect our perception of reality. Drastic and sudden events, especially those taking place on the international arena, are an impulse to plot intrigues in order to explain them and understand their causes. Anxiety and fear caused by uncertainty and a low level of trust, both in politicians and experts, are responsible for attempts to question the socio-political order and generally accepted explanations. The aim of the article was to present the phenomenon of spreading disinformation in the form of conspiracy theories on the Internet. The research problem was the question of which societies believe the most in the truth of selected conspiracy theories. The research methods used were: literature analysis. Diagnostic survey, the techniques were: text analysis and a survey with a questionnaire.

“The Bignetti Model”: A Review

Most people believe in the freedom of their will, so they are convinced to decide their own voluntary actions, without being controlled by God, fate, or circumstances. Though, the cognitive success of a learning curve depends on a statistical correlation between the prior experience and the posterior effect. Since long ago, several scientific pieces of evidence denied the existence of free-will (FW). Our scientific work contributed to corroborating the idea that FW might be an illusion of the mind; then, the belief that our conscious mind might exhibit decisional ability without any form of external control, is nonsense. Since that, we may exclude that our conscious mind could host a “soul-inhabited self ” or a “ghost of the machine”; if anything, it could host a sort of witness with a specific critical sense towards incoming experiences. Then, the intriguing question was how the mind could anyway exhibit cognition and behavior. Our answer was that our mind emerges from the brain as a probabilistic-deterministic computational machine with a self-oriented, cognitive, autopoietic purpose; to this aim, a virtual Ego-FW binomial is genetically installed in the mind in place of a real, concrete, independent Ego-FW binomial. According to psychophysical “push-no-push” experiments, we observed that learning curves show classic Bayesian behavior, i.e. the positive experience of a trial will ameliorate the further one. Then, we concluded that the action decision mechanism is elaborated by a computational mechanism genetically installed in the brain of all people, while the experience gained in everyday life is the epigenetic force that modifies the memory archive, thus contributing to shaping personal identity (PI). The 1st-person perspective (1PP) and the 3rd-person perspective (3PP) play a crucial role in these processes. 1PP is the emotive, subjective side of the conscious mind; it deludes to decide and control the actions according to the freedom of its will but it may move around only as an avatar in a virtual game. On the contrary, 3PP is the objective and rational perspective of the conscious mind; it works as an external witness of the constrained activity of 1PP. Obviously, while reacting in response to a stimulus, the subject is on the 1PP side of the conscious mind; thus, she/he cannot accept the idea that FW might be an illusion; paradoxically, the false belief in FW is the necessary condition of the mind to get the best cognition and behavior. In conclusion, we have investigated these mechanisms of human cognition and behaviour in over 20-years of work; in the meanwhile, we have elaborated “The Bignetti Model”, a human cognitive model compatible with these results.

Millimeter-wave radar object classification using knowledge-assisted neural network.

To improve the cognition and understanding capabilities of artificial intelligence (AI) technology, it is a tendency to explore the human brain learning processing and integrate brain mechanisms or knowledge into neural networks for inspiration and assistance. This paper concentrates on the application of AI technology in advanced driving assistance system. In this field, millimeter-wave radar is essential for elaborate environment perception due to its robustness to adverse conditions. However, it is still challenging for radar object classification in the complex traffic environment. In this paper, a knowledge-assisted neural network (KANN) is proposed for radar object classification. Inspired by the human brain cognition mechanism and algorithms based on human expertise, two kinds of prior knowledge are injected into the neural network to guide its training and improve its classification accuracy. Specifically, image knowledge provides spatial information about samples. It is integrated into an attention mechanism in the early stage of the network to help reassign attention precisely. In the late stage, object knowledge is combined with the deep features extracted from the network. It contains discriminant semantic information about samples. An attention-based injection method is proposed to adaptively allocate weights to the knowledge and deep features, generating more comprehensive and discriminative features. Experimental results on measured data demonstrate that KANN is superior to current methods and the performance is improved with knowledge assistance.