Human Perception Research Articles

Lightness Illusions Through AI Eyes: Assessing ConvNet and ViT Concordance with Human Perception

Lightness Illusions Through AI Eyes: Assessing ConvNet and ViT Concordance with Human Perception

The Role of Human Factors, Ergonomics, and 3D Modeling When Evaluating Incidents Involving Micromobility Devices: An E-Scooter Fall Case Study

Micromobility devices—encompassing a range of lightweight devices such as bicycles, pedal-assist bicycles, e-bikes, e-scooters, mopeds, and electronic skateboards—are promising as a complement to existing modes of travel. Human factors and ergonomics professionals can leverage available technology, education, and experience to assess aspects of human behavior, perception, expectations, performance, and kinematics when interacting with micromobility devices. This study discusses the application of Human Factors and 3D modeling when assessing micromobility devices during real-world incident investigations and showcases various tools that can be used for these types of assessments. This article outlines an incident case study involving an operator-owned e-scooter purchased from the manufacturer.

Combining human perception and street accessibility to provide information for better street construction: a case study of Chengdu City, China

ABSTRACT High-quality street spaces have a positive impact on residents’ lives. Revealing the differences in human perception and walkability across street spaces can highlight priority areas for street quality enhancement and provide valuable insights that help urban managers make informed decisions. This study first utilised machine learning models (SegNet) to extract visual elements from street view images and collected volunteers’ ratings of six perceptual dimensions of street scenes. Subsequently, it employed random forest algorithms and spatial autocorrelation models to predict and analyse overall street perception. Furthermore, principal component analysis was used to consolidate the six perceptual scores, coupled with an analysis of street walkability, to identify streets that most required quality enhancement. Finally, correlation and regression analyses were conducted between human perception ratings and street visual elements. The results indicated that buildings positively influence perceptions of wealth, safety, liveliness, and beauty and are the most significant positive perception elements. Conversely, walls were the most significant negative perception elements. Additionally, trees positively impacted perceptions of liveliness and beauty. Lastly, streets categorised as “high walkable-low perception” exhibited a radial dispersion from the city centre. In conclusion, the findings of this study provide valuable insights for enhancing street-space quality in Chengdu and other cities.

89 Streamlining the acquisition and analysis of digital images for the assessment of horn fly abundance

Abstract Horn flies are one of the most prevalent ectoparasites on pasture raised cattle. Studies have shown reasonable evidence of a genetic basis for horn fly attraction in beef cattle. Current methods for assessing fly abundance-related phenotypes (e.g., subjective assessment and image-based counts) suffer from limited accuracy and logistic difficulties. Previous attempts to assess horn fly abundance using image-based methods were hindered by several factors including weather conditions, distance and angle between the image taker and the animal, and lighting during image acquisition. The aim of this study was to address these limitations through the development of practical guidance to optimize image acquisition and to develop an adaptive image analysis algorithm to enhance the accuracy of image-based assessment of fly abundance. Images of beef cattle on pasture over multiple horn fly seasons (late spring to early fall) were collected. For each animal, the best image (where the entire side of the animal was in view) was selected and cropped from the withers to the hooks and from the chest floor to the udder. For every image (n = 314), all the flies were manually counted using the ImageJ software. Several image enhancement and analysis techniques including adaptive thresholding, pixel region connection, and pixel classification were used. The images were then clustered into three quality classes based on quality metrics computed using several algorithms from the image processing toolbox in MATLAB (BRISQUE, NIQE, and PIQE). BRISQUE and NIQE use distortions of natural scene statistics to compute quality scores. PIQE uses image features and models of human perception to compute quality scores. Pearson correlation, mean squared error (MSE), and the coefficient of determination (R2) were used to evaluate the concordance between the manual (ground truth) and the image predicted counts. Across the different scenarios, the Pearson correlation and R2 ranged between 0.21 to 0.67 and 0.04 and 0.45, respectively (Table 1). When the images were first clustered in quality classes, all the assessment metrics showed a substantial increase (Table 2). In fact, the Pearson correlation ranged between 0.47 to 0.80 using the NIQE. When the images were classified as low or medium quality by BRISQUE, the correlation was greater (0.74 to 0.79) compared with NIQE (0.47 to 0.70) and PIQE (0.69 to 0.74). Similar patterns were observed for the other assessment criteria (MSE and R2). These results seem to indicate that NIQE, BRISQUE, or a combination of the two algorithms could be used to assess image quality and determine the appropriate combination of image parameters to maximize the predictive ability. The NIQE method could be used as a filter to detect low quality images that are unsuitable for counting and then BRISQUE could be used on the remaining images.

Multi-receptor skin with highly sensitive tele-perception somatosensory.

The limitations and complexity of traditional noncontact sensors in terms of sensitivity and threshold settings pose great challenges to extend the traditional five human senses. Here, we propose tele-perception to enhance human perception and cognition beyond these conventional noncontact sensors. Our bionic multi-receptor skin employs structured doping of inorganic nanoparticles to enhance the local electric field, coupled with advanced deep learning algorithms, achieving a ΔV/Δd sensitivity of 14.2, surpassing benchmarks. This enables precise remote control of surveillance systems and robotic manipulators. Our long short-term memory-based adaptive pulse identification achieves 99.56% accuracy in material identification with accelerated processing speeds. In addition, we demonstrate the feasibility of using a two-dimensional (2D) sensor matrix to integrate real object scan data into a convolutional neural network to accurately discriminate the shape and material of 3D objects. This promises transformative advances in human-computer interaction and neuromorphic computing.

Language experience shapes predictive coding of rhythmic sound sequences.

Perceptual systems heavily rely on prior knowledge and predictions to make sense of the environment. Predictions can originate from multiple sources of information, including contextual short-term priors, based on isolated temporal situations, and context-independent long-term priors, arising from extended exposure to statistical regularities. While the effects of short-term predictions on auditory perception have been well-documented, how long-term predictions shape early auditory processing is poorly understood. To address this, we recorded magnetoencephalography data from native speakers of two languages with different word orders (Spanish: functor-initial vs Basque: functor-final) listening to simple sequences of binary sounds alternating in duration with occasional omissions. We hypothesized that, together with contextual transition probabilities, the auditory system uses the characteristic prosodic cues (duration) associated with the native language's word order as an internal model to generate long-term predictions about incoming non-linguistic sounds. Consistent with our hypothesis, we found that the amplitude of the mismatch negativity elicited by sound omissions varied orthogonally depending on the speaker's linguistic background and was most pronounced in the left auditory cortex. Importantly, listening to binary sounds alternating in pitch instead of duration did not yield group differences, confirming that the above results were driven by the hypothesized long-term 'duration' prior. These findings show that experience with a given language can shape a fundamental aspect of human perception - the neural processing of rhythmic sounds - and provides direct evidence for a long-term predictive coding system in the auditory cortex that uses auditory schemes learned over a lifetime to process incoming sound sequences.

Human-like virtual influencers: human perceptions and attitudes towards an emerging phenomenon

Human-like virtual influencers: human perceptions and attitudes towards an emerging phenomenon

SRARDA: A lightweight adaptive residual dense attention generative adversarial network for image super-resolution

Image super-resolution (SR) is the task of inferring a high resolution (HR) image from one/multiple single low resolution (LR) input(s). Traditional networks are evaluated by pixel-level metrics such as Peak-Signal-to-Noise Ratio (PSNR) etc., which do not always align with human perception of image quality. They often produce excessively smooth images that lack high-frequency texture and appear unnatural. Therefore, in this paper, we propose a lightweight adaptive residual dense attention generative adversarial network (SRARDA) for image SR. Firstly, our generator adopts the residual in residual (RIR) structure but redesigns the basic module. By using dynamic residual connection (ARC) to dynamically adjust the importance of residual and main paths, we design a novel adaptive residual dense attention block (ARDAB) that enhances the feature extraction capability of the generator. In addition, we build a high-frequency filtering unit (HFU) to extract more high-frequency features from the LR space. Finally, to fully utilize the discriminator, we use WGAN to compute the difference between the HR image and the reconstructed image. Experiments demonstrate that SRARDA effectively addresses the issue of excessive smoothing in reconstructed images, while also enhancing visual quality.

Research on shared control of robots based on hybrid brain-computer interface

BackgroundWith the arrival of the new generation of artificial intelligence wave, new human-robot interaction technologies continue to emerge. Brain–computer interface (BCI) offers a pathway for state monitoring and interaction control between human and robot. However, the unstable mental state reduce the accuracy of human brain intent decoding, and consequently affects the precision of BCI control. New methodsThis paper proposes a hybrid BCI-based shared control (HB-SC) method for brain-controlled robot navigation. Hybrid BCI fuses electroencephalogram (EEG) and electromyography (EMG) for mental state monitoring and interactive control to output human perception and decision. The shared control based on multi-sensory fusion integrates the special obstacle information perceived by humans with the regular environmental information perceived by the robot. In this process, valid BCI commands are screened by mental state assessment and output to a layered costmap for fusion. ResultsEight subjects participated in the navigation experiment with dynamically changing mental state levels to validate the effects of a hybrid brain-computer interface through two shared control modes. The results show that the proposed HB-SC reduces collisions by 37.50 %, improves the success rate of traversing obstacles by 25.00 %, and the navigation trajectory is more consistent with expectations. ConclusionsThe HB-SC method can dynamically and intelligently adjust command output according to different brain states, helping to reduce errors made by subjects in a unstable mental state, thereby greatly enhancing the system's safety.

Sense of embodiment with synchronized avatar during walking in mixed reality.

Gait guidance systems that synchronize the gait rhythm with an avatar in a mixed reality (MR) environment are attracting attention owing to their rehabilitation applications. More effective gait guidance can be achieved by changing body sensations for the sense of embodiment (SoE), which refers to the feeling of owning, controlling, and being inside a body in MR. This study investigated full-body synchronous motion between a human and a virtual avatar to enhance the SoE in walking with actual position changes in the real world. The full-body motion and gait rhythm were measured using body-worn inertial measurement units and a visual avatar was provided through a transparent head-mounted display. The results showed that the SoE of the participants was enhanced under higher synchronization conditions. In addition, questionnaire results showed that the SoE in the synchronous condition was significantly higher than that in the asynchronous condition, and the SoE in the self-avatar condition was significantly higher than that in the other-avatar condition. This indicates that a higher synchronization level with the appearance of an avatar leads to a stronger SoE in the human perception mechanism, which is important for potential application in medical or other fields.

Flexible Artificial Tactility with Excellent Robustness and Temperature Tolerance Based on Organohydrogel Sensor Array for Robot Motion Detection and Object Shape Recognition.

Hydrogel-based flexible artificial tactility is equipped to intelligent robots to mimic human mechanosensory perception. However, it remains a great challenge for hydrogel sensors to maintain flexibility and sensory performances during cyclic loadings at high or low temperatures due to water loss or freezing. Here, a flexible robot tactility is developed with high robustness based on organohydrogel sensor arrays with negligent hysteresis and temperature tolerance. Conductive polyaniline chains are interpenetrated through a poly(acrylamide-co-acrylic acid) network with glycerin/water mixture with interchain electrostatic interactions and hydrogen bonds, yielding a high dissipated energy of 1.58MJ m-3, and ultralow hysteresis during 1000 cyclic loadings. Moreover, the binary solvent provides the gels with outstanding tolerance from -100 to 60°C and the organohydrogel sensors remain flexible, fatigue resistant, conductive (0.27 S m-1), highly strain sensitive (GF of 3.88) and pressure sensitive (35.8 MPa-1). The organohydrogel sensor arrays are equipped on manipulator finger dorsa and pads to simultaneously monitor the finger motions and detect the pressure distribution exerted by grasped objects. A machine learning model is used to train the system to recognize the shape of grasped objects with 100% accuracy. The flexible robot tactility based on organohydrogels is promising for novel intelligent robots.

High Spatiotemporal Resolution Biomimetic Thermoreceptors Realizing by Jointless p‐n Integration Thermoelectric Composites

AbstractHuman body temperature is a critical physiological indicator, reflecting metabolism and temperature regulation. Biomimetic temperature sensors with high temporal and spatial resolution are highly desired to emulate human skin's temperature perception capabilities. Here, a selective filtration method is proposed to fabricate a jointless p‐n thermoelectric module, integrating p‐type and n‐type materials with minimal interfacial barriers. The structure enables rapid response, minimal signal variation, and a robust linear relationship between open circuit voltage and temperature difference, making it suitable as a biomimetic thermoreceptor for enhancing humanoid robots with intelligent sensing capabilities. A smart thermoelectric sensing system with a high temporal and spatial resolution is developed using with jointless p‐n module as the sensing element. In temporal thermal sensing, the sensing system can timely and effectively identify the heat source, with a fast response time of <0.1 s. In addition, in spatial thermal sensing, the system reliably detects thermal stimuli within discrete regions of each measuring area of <1 × 1 cm2. This study provides an effective strategy for temperature sensors in thermoelectric sensing and biomimetic thermoreceptor applications.

Model-Mediated Teleoperation: An Operator-Centric Perspective

Abstract Haptic teleoperation is a means of dexterously manipulating environments wherein a human operator can be situated several hundreds of kilometers away from the site of manipulation. Time delays between the local and remote sites pose problems for the user experience. Model-mediated teleoperation addresses these problems, but assumes a sufficiently representative model of the operator and of the environment. When applied to complex environments, this model becomes difficult to work with. A solution to this difficulty lies in the fact that human perceptual capabilities are limited. So too, possibly, is the amount of feedback needed in order to accomplish tasks effectively. In this work, we review information on human perception of the environmental properties involved in environmental perception (inertia, friction, roughness, compliance, and geometry). Moreover, we detail how these properties can be modeled. Finally, we propose some open questions that are relevant in understanding the link between the environment presented to the operator and their effectiveness at accomplishing tasks.

Extending speech emotion recognition systems to non-prototypical emotions using mixed-emotion model

In the conventional approach to speech emotion recognition (SER), the classifier is usually trained on acted emotional speech data to predict individual basic emotions. In this work, we extend the SER systems with the realistic assumption of the coexistence of multiple basic emotions in an utterance. We utilize the MSP-Podcast database for developing the SER system, which contains spontaneous speech utterances. From the primary and secondary emotion annotations of this database, we organize six prototypical and seven non-prototypical emotions. We then propose the mixed-emotion model and express the non-prototypical emotions as a linear combination of prototypical emotions. The combination weights of the mixed-emotion model are computed using a normalized dominance scale based algorithm inspired by the integration of basic emotion theory and dimensional emotion theory in human psychology. We first train a prototypical SER model using the ECAPA-TDNN architecture. The softmax predictions from this model serve as emotion profile inputs to the mixed-emotion model, which then predicts the non-prototypical emotions. Assuming the coexistence of multiple emotions, we only apply the utterances with uniform emotion profiles to the mixed-emotion model. The developed system continues with the conventional SER model if the emotion profile tends to delta function owing to the probable occurrence of a single prototypical emotion. We develop the proposed mixed-emotion model based SER framework using MFCC and wav2vec 2.0 extracted features. Further, we show that due to human perception variations, there exist prominent annotation variations in the non-prototypical emotion ground truths. To address that, we extend the supervised evaluation protocols in four different formulations that capture the subjective variability at different levels. The proposed system shows a best-case performance improvement of 7.10% and 8.39% over the conventional prototypical SER model for the MFCC and wav2vec 2.0 features, respectively.

Bridging auditory perception and natural language processing with semantically informed deep neural networks

Sound recognition is effortless for humans but poses a significant challenge for artificial hearing systems. Deep neural networks (DNNs), especially convolutional neural networks (CNNs), have recently surpassed traditional machine learning in sound classification. However, current DNNs map sounds to labels using binary categorical variables, neglecting the semantic relations between labels. Cognitive neuroscience research suggests that human listeners exploit such semantic information besides acoustic cues. Hence, our hypothesis is that incorporating semantic information improves DNN’s sound recognition performance, emulating human behaviour. In our approach, sound recognition is framed as a regression problem, with CNNs trained to map spectrograms to continuous semantic representations from NLP models (Word2Vec, BERT, and CLAP text encoder). Two DNN types were trained: semDNN with continuous embeddings and catDNN with categorical labels, both with a dataset extracted from a collection of 388,211 sounds enriched with semantic descriptions. Evaluations across four external datasets, confirmed the superiority of semantic labeling from semDNN compared to catDNN, preserving higher-level relations. Importantly, an analysis of human similarity ratings for natural sounds, showed that semDNN approximated human listener behaviour better than catDNN, other DNNs, and NLP models. Our work contributes to understanding the role of semantics in sound recognition, bridging the gap between artificial systems and human auditory perception.

Two-stage algorithm of spectral analysis for automatic speech recognition systems

Within the framework of a dynamically developing direction of research in the field of acoustic measurements, the task of spectral analysis of speech signals in automatic speech recognition systems is considered. The low efficiency of the systems in unfavorable speech production conditions (noise, insufficient intelligibility of speech sounds) compared to human perception of oral speech is noted. To improve the efficiency of automatic speech recognition systems, a two-stage algorithm for spectral analysis of speech signals is proposed. The first stage of speech signal processing consists of its parametric spectral analysis using an autoregressive model of the vocal tract of a conditional speaker. The second stage of processing is the transformation (modification) of the obtained spectral estimate according to the principle of frequency-selective amplification of the amplitude of the main formants of the intra-periodic power spectrum. The software implementation of the proposed algorithm based on the high-speed computational procedure of the fast Fourier transform is described. Using the author’s software, a full-scale experiment was carried out: an additive mixture of vowel sounds of the control speaker’s speech with white Gaussian noise was studied. Based on the results of the experiment, it was concluded that the amplitude of the main speech signal formants were amplified by 10–20 dB and, accordingly, a significant improvement in the speech sounds intelligibility. The scope of possible application of the developed algorithm covers automatic speech recognition systems based on speech signal processing in the frequency domain, including the use of artificial neural networks.

Исследование линейности цветовосприятия человека в графическом интерфейсе систем управления

The work is aimed at studying the process of human perception of visual information in conditions of interaction with a certain interface. The authors describe experimental research of the linearity of human colour perception in the graphical interface of control systems when observing colour pictograms in a conditional interface. To analyze the mechanism operation of the visual information perception, an information model of visual perception is used. Features of human perception of visual information can be of both an individual nature associated with a specific individual, and an external nature associated with the systemic interference of the operator’s direct interaction with the interface. The paper defines the factors of the study and describes the methodology for preparing stimulus material using the Processing programming language. As a tool for conducting the experiment, a software and hardware complex recording oculomotor activity Eye-tracker SMI RED 250 is used. The importance of creating effective user interfaces for control systems of complex objects and insufficient study of adapting interfaces to the features of human perception of visual information at the perceptual level of awareness determine the relevance of the study. The means of mathematical statistics process the obtained parametric data of the template for examining the stimulus material. The results got in the experiment allow concluding that the mechanism of human visual information perception, when the colour spot brightness decreases, remains sensitive to yellow colour the longest.

Single-Shot Multispectral Encoding: Advancing Optical Lithography for Encryption and Spectroscopy.

Most modern optical display and sensing devices utilize a limited number of spectral units within the visible range, based on human color perception. In contrast, the rapid advancement of machine-based pattern recognition and spectral analysis could facilitate the use of multispectral functional units, yet the challenge of creating complex, high-definition, and reproducible patterns with an increasing number of spectral units limits their widespread application. Here, we report a technique for optical lithography that employs a single-shot exposure to reproduce perovskite films with spatially controlled optical band gaps through light-induced compositional modulations. Luminescent patterns are designed to program correlations between spatial and spectral information, covering the entire visible spectral range. Using this platform, we demonstrate multispectral encoding patterns for encryption and multivariate optical converters for dispersive optics-free spectroscopy with high spectral resolution. The fabrication process is conducted at room temperature and can be extended to other material and device platforms.

Concept and Evolution of Cognitive Psychology

Cognitive psychology is a branch of psychology whereby scientists are motivated to study theunderlying mechanisms of the higher mental processes in human beings. Therefore, to other disciplines,cognitive scientists are interested in understanding human perception, decision-making, attention,problem-solving, thinking, and the development of speech among other mental processes. On the otherhand, the term cognition is derived from ‘cognosco’, which in Latin translates to making decisions,discovering, learning, investigating, studying, or recognizing. However, cognition has been defined bymost scientists as the processes involved in transforming, reducing, elaborating, storing, recovering,and using the sensory signal (input). Generally, cognitive psychology is focused on understanding themental processes of acquiring, processing, and storing information in human beings (Ruisel, 2010, p.268).This research paper discuss the concept of cognitive psychology and its concept as it greatlyaffects the learning power of the human being and play a vital role in educational institutions for thegrowth of students while effective learning processes

From Human Perception of Good Practices to Horse (Equus Caballus) Welfare: Example of Equine-Assisted Activities.

Equine-assisted intervention (EAI) studies deal with clients, whereas very few studies focused on the effects on animals. EAI equids are also submitted to management, which influences their welfare. Management and working conditions depend on human decisions and perception. We gathered information through a survey about facilities managers' strategies (n = 51) and obtained direct information on management and working practices and their consequences on equids' welfare through an observational study (n = eight facilities, 174 equids). Differences in managers' perceptions of good management practices were related to the facility's involvement in EAI, e.g., increased awareness of equids' needs (housing and feeding), especially when EAI was the main activity. A detailed observational study on eight additional facilities confirmed that. Facility management profiles were paralleled by equids' welfare profiles. Clear correlates were found between management decisions and welfare consequences. One major factor influencing welfare and human-equid interactions appeared to be working modalities, with more EAI facilities practicing groundwork and bitless work. Facilities where equids were the most involved in mixed activities had the most equids with compromised welfare. Given EAI clients' particularities, conventional working modalities are less adapted and at risk of increased discomfort for equids. Overall, survey and observational approaches converged but some discrepancies (choice of equid type) appeared between the reported and observed prevalence.