Model Of Perception Research Articles

Neural network–based transfer learning to improve stiffness modeling of industrial robots with small experimental data sets

AbstractStiffness modeling is an essential subject for the composition of robot control. Accurate stiffness modeling is helpful for improving the control accuracy of industrial robots, particularly under dynamic load circumstances. The classic virtual joint modeling (VJM) method is challenging in predicting the deformation of the end-effector throughout the full workspace due to the nonlinear deformation of the robot joint and its serial articulated structure. This paper proposes a full-space stiffness modeling method for robots based on the integration of a multi-layer perceptual (MLP) model and VJM. To provide enough training data for the MLP model, VJM is used to build a stiffness model with a small set of experimental data to generate 106,400 training data. A model-based transfer learning approach is proposed to improve the model’s accuracy and generalization regarding the difference between generated training data and actual experimental data. The VJM stiffness model is compared with the MLP stiffness model and the existing CNN-based transfer learning model based on the same experimental data. Considering the deformation prediction in the three directions in Cartesian space, the mean absolute error, standard deviation, and maximum error of the MLP model are decreased by at least 24.90%, 14.20%, and 8.50%, respectively, than the VJM. These prediction results demonstrate that the proposed modeling technique can significantly increase the accuracy of robot stiffness modeling, which is essential for position compensation in precise motion control of robots under dynamic load.

Behavioral Inhibition and Social Competence Through the Eyes of Parent and Teacher Informants

The centrality of social competence to children’s well-being has sparked interest in documenting its correlates and precursors. Behavioral Inhibition (BI) is studied extensively as an early appearing, biologically based, temperamental disposition that places children at increased risk for maladaptive social functioning. Children with BI are characterized by the tendency to react to unfamiliarity or uncertainty with fear and to respond with avoidance or withdrawal, eventuating in missed opportunities to gain social competence (SC). Early interventions that aim to interrupt this negative cycle often rely on parents or teachers to observe BI, but they often disagree in their ratings, raising understudied but basic questions about how to translate the research findings into effective interventions. In this study, parents and teachers rated kindergarteners’ (N = 174) disposition toward fear and shyness, underpinnings of BI and SC. As expected, we found modest overlap in the classification of children into relatively High, Average, and Low BI groups based on parent and teacher ratings. Whereas about 40 percent were classified similarly, about 33 percent were discrepant in their classification by more than one category. Yet, the High BI group was at a social disadvantage (lower SC) compared to the Low BI group, even when the comparison groups only included children whose classification was discrepant. In line with the Realistic Accuracy Model of person perception, we describe a context/informant-specific conceptualization of the BI–SC connection with implications for intervention.

The first catchment water balance: New insights into Pierre Perrault, his perceptual model and his peculiar catchment

ABSTRACT Pierre Perrault and his 1674 book De l’Origine des Fontaines are widely acknowledged in hydrology as the first formal articulation of the catchment water balance based on field data. Many summaries of his work have now been written, but few of these summaries have examined Perrault’s perceptual model in detail and none that we are aware of have gone back to his study catchment to collect new data in which to frame these historic findings in a modern context. Here we report new insights (with re-calculations of some of his analyses) into Perrault’s work, his perceptual model of streamflow generation and his rather peculiar 119 km2 headwater catchment of the Seine River basin. We show the uncertainty of his flow and catchment area estimates, some errors in perception about hydrological flowpaths and new age estimates for the spring-fed site where he worked. Despite these modern criticisms and updates, Perrault’s place in hydrological history is secure: he was the first to bring quantitative analysis to fundamental questions of the terrestrial water cycle.

Genetic and Neuronal Basis for Facial Emotion Perception in Humans and Macaques

Abstract The ability to rapidly recognize basic facial emotions (e.g., fear) is crucial for social interactions and adaptive functioning. To date, the origin of facial emotion recognition ability remains equivocal. Using a classical twin design in humans, we found a clear dissection of low and high spatial frequencies (LSF and HSF) in facial emotion perception: whereas genetic factors contributed to individual variation in LSF processing, HSF processing is largely shaped by environmental effects. Furthermore, the ability to recognize facial emotion of LSF content genetically correlated with the function of the amygdala. Crucially, single-unit recording of the amygdala in macaques further revealed the dissociation between LSF and HSF processing in facial emotion perception, indicating the existence of an evolutionarily conserved mechanism. This cross-species study enhances insights into the neurobiological dual-route model (subcortical vs. cortical) of emotion perception and illuminates the origin and the functional development of the emotional brain in primates.

"You Can either Blame Technology or Blame a Person..." --- A Conceptual Model of Users' AI-Risk Perception as a Tool for HCI

AI-powered systems pose unknown challenges for designers, policymakers, and users, making it more difficult to assess potential harms and outcomes. Although understanding risks is a requirement for building trust in technology, users are often excluded from risk assessments and explanations in policy and design. To address this issue, we conducted three workshops with 18 participants and discussed the EU AI Act, which is the European proposal for a legal framework for AI regulation. Based on results of these workshops, we propose a user-centered conceptual model with five risk dimensions (Design and Development, Operational, Distributive, Individual, and Societal) that includes 17 key risks. We further identify six criteria for categorizing use cases. Our conceptual model (1) contributes to responsible design discourses by connecting the risk assessment theories with user-centered approaches, and (2) supports designers and policymakers in more strongly considering a user perspective that complements their own expert views.

MODEL OF MAXIMAL WEIGHTS INVERSE CHAINS FOR THE ANALYSIS OF THE INFLUENCE FACTORS OF THE SOFTWARE COMPLEXES SUPPORT

Context. The problem of identification, formation and restoration of the boundaries of influencing factors, lost as a result of the implementation of multi-layer perceptron models into the models of subjective perception of the object of software complexes support, as well as the applied practical problem of primary monitoring of the frequency manifestation of a given influencing factor in the post-real-time mode, is considered. The object of research is the influencing factors of support of software complexes. Objective – the goal of the work is to develop a model of inverse chains of maximum weights for the analysis of influencing factors of the software complexes support. Method. A model of maximal weights inverse chains for the analysis of the influence factors of the software complexes support was developed for the analysis of the influencing factors of the software complexes support. The developed model provides possibility to identify and form feedback chains of maximum weights for the identification and further analysis of influencing factors that are reflected into the results of the object perception (the supported software complex or its support processes), by the relevant subjects of interaction which directly or indirectly interact with it. Results. Results of the resolved applied practical problem of primary monitoring of the frequency manifestation of a given influencing factor in the post-real-time mode have been provided as an example of the applied practical use of the developed model. The output results of the developed models functioning – are the reverse chains of maximum weights. In the future, the results obtained by the developed model are used to solve the applied-scientific problem of identification, formation and restoration of the boundaries of influencing factors, lost as a result of the implementation of the appropriate models of multilayer perceptron inside the models of subjective perception of the software complexes support. So the developed model of maximal weights inverse chains for the analysis of the influence factors of the software complexes support resolves this applied-scientific problem, initially caused by the implementation of the corresponding multilayer perceptron models inside the model of the subjective perception of the object of software complexessupport. The developed model provides the possibility of carrying out a qualitative analysis of the transformation of the input characteristics of the object of support into the output resulting characteristics of its subjective perception. Conclusions. Developed model allows to resolve the described problems. At the same time, the developed model improves the classical understanding of multilayer perceptron artificial neural networks, as it introduces an additional value to the neurons of hidden layers, which (starting from now) are able to perform a completely new role of influencing factors markers, while in the classical understanding of multilayer perceptron artificial neural networks they did not perform any functions other than arithmetic to ensure the possibility of correct learning and functioning of a multilayer perceptron artificial neural networks.

Office soundscape assessment: A model of acoustic environment perception in open-plan officesa).

The soundscape approach has been utilised in recent research for residential environments, but applications to indoor working environments remain limited. This study investigated the suitability of affective quality evaluations of open-plan office acoustics. Perceptual assessments were completed by occupants of eight open-plan office floorplates, using affective dimensions outlined in PD ISO/TS 12913-3:2019 and indoor soundscape studies. Participant demographic, contextual, work-related quality, and psychological well-being data were collected. Workstation noise levels were measured following BS ISO 22955:2021. Principal component analysis identified Pleasantness, Eventfulness, and Emptiness as the main perceptual dimensions, cumulatively explaining 56% of the total variance. Results indicate the suitability of the PD ISO/TS 12913-3:2019 two-dimensional model for open-plan offices. The perceived presence of human sounds negatively correlated with ISO Pleasantness yet positively correlated with ISO Eventfulness. Participant gender and aural diversity mediated ISO Pleasantness. Psychological well-being and work-related quality correlated positively with soundscape pleasantness. No correlations were found between level-based acoustical indicators-equivalent continuous sound level (LAeq), level exceeded 10% (LA10) and 90% (LA90) of the time, level variability (LA10-LA90) and Liveliness-and perceptual scores. A conceptual representation of open-plan office soundscape perception is presented, offering a framework for evaluating and designing workspaces to enhance well-being.

Developing a safety and health practices in building model of physical environment, facility management, and worker perception: Structural equation modeling approach

Developing a safety and health practices in building model of physical environment, facility management, and worker perception: Structural equation modeling approach

Perceived risk of death among patients with advanced cancer: a qualitative directed content analysis

BackgroundRisk perception with respect to death is a prerequisite for patients with advanced cancer when the time comes to make medical decisions. However, the nature of death risk perception remains unclear.MethodIn-depth interviews were conducted with 28 patients with advanced cancer who were recruited from two hospitals and one home-based hospice in Fujian, China. Interviews were transcribed and directed content analysis applied. The Tripartite Model of Risk Perception was used as a theoretical framework.ResultsPatients with advanced cancer perceived their risk of death in different ways. Professional communication about death risk and data-driven risk perception were common in clinical settings. Affective influences, inherent cognition, and comparisons to others or oneself also contributed to the subjects’ self-perceived death risk.ConclusionThis theory-informed qualitative study clarifies the nature of the perceived risk of death among patients with advanced cancer. The study findings offer healthcare providers a more nuanced understanding of the perceived risk of death among patients with advanced cancer.

Perception and reconstruction of temperature field in forgings based on physical model and CNN model

Accurately perceiving and reconstructing the temperature field of hot-deformed large forgings is essential for intelligent forging and enhancing forging quality. In this study, the surface temperature of large forgings is measured using an infrared thermal imager. The relationship between the grayscale of infrared images and the surface temperature of large forgings is analyzed. A physical model, incorporating a convolutional neural network (CNN) model, is established to ascertain the surface temperature of large forgings. The CNN model utilizes standard convolution and multilayer perceptron modules for the backbone network and implements an adaptive learning rate. The correlation between three channel information and the surface temperature besides the grayscale is considered in the CNN model. Lastly, this study proposes a method for reconstructing the temperature field of large forgings based on the developed perception model, enabling accurate surface temperature measurement even when the large forgings are covered by oxide skin.

Multi-modal scene graph inspired policy for visual navigation

Visual navigation needs the agent locate the given target with visual perception. To enable robots to effectively execute tasks, combining large language models (LLMs) with multi-modal inputs in navigation is necessary. While LLMs offer rich semantic knowledge, they lack specific real-world information and real-time interaction capabilities. This paper introduces a Multi-modal Scene Graph (MMSG) navigation framework that aligns LLMs with visual perception models to predict next steps. Firstly, a multi-modal scene dataset is constructed, containing triplets of object-relations-target words. We provide target words and lists of existing objects in the scene to generate a large number of instructions and corresponding action plans for GPT-\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$-$$\\end{document}3.5. The generated data is then utilized for pre-train LLM for path planning. During inference, we discover objects in the scene by extending the DETR visual object detector to multi-view RGB image collected from different reachable positions. Experimental results show that path planning generated from MMSG outperforms state-of-the-art methods, indicating its feasibility in complex environments. We evaluate our methods on the ProTHOR dataset and show superior navigation performance.

A review on depth perception techniques in organoid images

Organoids are an in vitro model that can simulate the complex structure and function of tissues in vivo. Functions such as classification, screening and trajectory recognition have been realized through organoid image analysis, but there are still problems such as low accuracy in recognition classification and cell tracking. Deep learning algorithm and organoid image fusion analysis are the most advanced organoid image analysis methods. In this paper, the organoid image depth perception technology is investigated and sorted out, the organoid culture mechanism and its application concept in depth perception are introduced, and the key progress of four depth perception algorithms such as organoid image and classification recognition, pattern detection, image segmentation and dynamic tracking are reviewed respectively, and the performance advantages of different depth models are compared and analyzed. In addition, this paper also summarizes the depth perception technology of various organ images from the aspects of depth perception feature learning, model generalization and multiple evaluation parameters, and prospects the development trend of organoids based on deep learning methods in the future, so as to promote the application of depth perception technology in organoid images. It provides an important reference for the academic research and practical application in this field.

T-Smade: A Two-Stage Smart Detector for Evasive Spectre Attacks Under Various Workloads

Evasive Spectre attacks have used additional nop or memory delay instructions to make effective hardware performance counter based detectors with lower attack detection successful rate. Interestingly, the detection performance gets worse under different workloads. For example, the attack detection successful rate is only 59.8% for realistic applications, while it is much lower 27.52% for memory stress test. Therefore, this paper proposes a two-stage smart detector T-Smade designed for evasive Spectre attacks (e.g., evasive Spectre nop and evasive Spectre memory) under various workloads. T-Smade uses the first-stage detector to identify the type of workloads and then selects the appropriate second-stage detector, which uses four hardware performance counter events to characterize the high cache miss rate and low branch miss rate of Spectre attacks. More importantly, the second stage detector adds one dimension of reusing cache miss rate and branch miss rate to exploit the characteristics of various workloads to detect evasive Spectre attacks effectively. Furthermore, to achieve the good generalization for more unseen evasive Spectre attacks, the proposed classification detector T-Smade is trained by the raw data of Spectre attacks and non-attacks in different workloads using simple Multi-Layer Perception models. The comprehensive results demonstrate that T-Smade makes the average attack detection successful rate of evasive Spectre nop under different workload return from 27.52% to 95.42%, and that of evasive Spectre memory from 59.8% up to 100%.

Active Models in Speech Perception: A Critical Review in Phonetics

This critical review examines four prominent active models of speech perception: quantal theory, motor theory, hyper-hypo-articulation theory, and exemplar theory. Each of these models offers distinctive insights into how listeners perceive, interpret, and categorize speech sounds. Quantal theory explores the non-linear relationship between articulation and acoustic output, emphasizing stable and unstable regions in speech production. Motor theory posits that speech perception is grounded in articulatory gestures, suggesting a direct link between production and perception. The hyper-hypo-articulation theory focuses on the speaker’s adaptive articulation, which ranges from hyper- to hypo-articulation depending on the listener's needs and the communicative context. Exemplar theory, rooted in cognitive psychology, highlights the role of memory and experience, with individual speech sounds compared to stored exemplars in memory to aid perception. Despite their contributions, none of these models offers a comprehensive solution to all speech perception challenges. Each theory is suited to specific contexts, speech features, or tasks, making it crucial for researchers to understand their limitations. Furthermore, the review underscores the importance of selecting the appropriate model for particular research or practical applications, given the variability in their functionality. Finally, it calls for future research to delve deeper into passive models of speech perception and suggests that comparative studies between active and passive models could yield valuable insights.

A following model considering multiple vehicles from the driver's front and rear perspectives

In the current traffic environment dominated by manual driving, existing models of drivers' rear-view perceptions are inadequate. Existing car-following models that incorporate rear-view information are primarily focused on the Internet of Vehicles (IoV) and automated driving environments. However, they fail to realistically reflect the visual processing mechanisms of human drivers, limiting their effectiveness in realistic traffic scenarios. Therefore, we propose a new following model, the multi-vehicle influence from front and rear perspectives (MVFR), that considers the influence of multiple vehicles. The MVFR model combines information from both front and rear vehicles, integrating views from the front, side front and rear. It provides an in-depth analysis of the effects of relative state differences between a vehicle and its surrounding vehicles on speed, including the effects of perspectives in both the lateral and longitudinal directions. Linear stability analysis and numerical simulation demonstrate that considering the perspectives of rear-following vehicles and lateral offset angles can improve traffic flow stability to a certain extent. Furthermore, properly considering the lateral offset distance and the number of vehicles ahead also positively affects traffic flow stability. This study reveals that observing following vehicles and considering information from multiple front vehicles enhances system stability, especially when there is no or minimal lateral offset. In contrast, focusing on fewer front vehicles is more effective for traffic flow stability when there is a large lateral offset. Experimental results using the CKQ4up dataset show that the MVFR model achieves higher accuracy than the conventional FVD model, the front-view-only improved FVD model (MFVD-RV), and the MFRHVAD-RV and MFRHVAD-AV models. Compared with models relying solely on front-view or non-visual perception, the MVFR model demonstrates a better fit, validating the advantages of this full-view perception model in manual driving environments. This innovation addresses the shortcomings of existing research, thereby enhancing the reliability of models under manual driving conditions on highways.

Lifestyle Changes, Individual Mobility, and Interactions in Suburban Settlement Areas of Makassar City, Indonesia: Perceptual Model Approach

Lifestyle Changes, Individual Mobility, and Interactions in Suburban Settlement Areas of Makassar City, Indonesia: Perceptual Model Approach

The Nitty Gritty of Stress and Mental Health: The Role of Grit in Moderating the Relationship Between Stress, Anxiety, and Depression

ABSTRACT College students in the United States contend with unprecedented mental health difficulties. College-specific challenges and stressors associated with emerging adulthood exacerbate these mental health struggles. In the ABC-X model of stress, cognitive appraisal or perception mediates the relationship between stressful events and degraded mental health. In this model, a resource, such as grit, may strengthen student resilience. Using data collected from 844 US college students, the path analysis results identified the mediation effect of the perception of stress on the association between college life challenges and mental health difficulties (depression and anxiety). These mediation effects were not significantly affected by the level of grit. However, the relationships between the perception of stress and both anxiety and depression were weaker at higher levels of grit. The implications of these findings, relative to grit interventions and attrition, are considered.

Research on Game Players' Willingness to Purchase Based on the Perspective of Ambivalent Attitudes

Consumer ambivalence not only reflects the emotional and cognitive responses formed after perceiving external marketing stimuli but also influences subsequent purchase intentions. Based on the TAM (Technology Acceptance Model) and S-O-R (Stimulus-Organism-Response) models, this study introduces ambivalent attitudes as a mediating variable to construct and test a theoretical model of external marketing stimuli, consumer perception, ambivalent attitudes, and purchase intentions. Using 716 valid responses from gaming communities, the measurement and structural models were evaluated using AMOS 26.0 and SPSS 26.0 software. The empirical results show that the clarity and total volume of external marketing information can significantly influence purchase intentions by affecting consumer perceptions. Ambivalent attitudes directly influence purchase intentions and serve as a mediating factor in the pathways where perceptions affect purchase intentions.

Speckle-free holography with a diffraction-aware global perceptual model

Computer-generated holography (CGH) based on neural networks has been actively investigated in recent years, and convolutional neural networks (CNNs) are frequently adopted. A convolutional kernel captures local dependencies between neighboring pixels. However, in CGH, each pixel on the hologram influences all the image pixels on the observation plane, thus requiring a network capable of learning long-distance dependencies. To tackle this problem, we propose a CGH model called Holomer. Its single-layer perceptual field is 43 times larger than that of a widely used 3×3 convolutional kernel, thanks to the embedding-based feature dimensionality reduction and multi-head sliding-window self-attention mechanisms. In addition, we propose a metric to measure the networks’ learning ability of the inverse diffraction process. In the simulation, our method demonstrated noteworthy performance on the DIV2K dataset at a resolution of 1920×1024, achieving a PSNR and an SSIM of 35.59 dB and 0.93, respectively. The optical experiments reveal that our results have excellent image details and no observable background speckle noise. This work paves the path of high-quality hologram generation.

DEVELOPMENT OF MARKETING IN AZERBAIJAN

The main goal of the article is to study activities aimed at marketing development in Azerbaijan. It is noted that benefiting from the synthesis of the national characteristics of the economy (including the experience of the Soviet era) and the world experience is one of the urgent requirements of the modern era. Method and methodologies. In the analysis process, comparative analysis of statistical indicators, analysis of legal-normative documents necessary for the development of marketing, classification of existing problems in the system of formation of market relations in Azerbaijan, forecasting and projecting methods were used. Novelty on the article. The article focuses on some rational and non-rational activities that are neglected in the scientific literature and necessitates the development of marketing. Conclusion and suggestions. The article emphasizes that marketing promotion is a step that serves to make companies popular among the population. These steps are one of the necessary steps to be carried out and updated both thoroughly and systematically. It is noted that 90% of managers of companies operating in Azerbaijan think that there is no need for marketing research. Thus, the decision to implement marketing measures is not based on the analysis of research data, and this, in turn, does not justify the effectiveness of marketing projects. Businessmen rely too much on their intuition and make unreasonable expenses based only on their own experience and unsystematized information that reaches them over a period of time. As a result: 1. Unsuccessful image campaigns are organized that do not produce any desired intangible effect; 2. Sales of newly launched products are falling; 3. Preference is given to advertising campaigns mainly aimed at financial impact; 4. Absurd models of brand perception emerge as a result of lack of study of brand perception after marketing activities; 5. Low level of service and, as a result, customer satisfaction. At best, marketers refer to a company's to-do list.