Search

Diachasmimorpha longicaudata (Ashmead) (Hymenoptera: Braconidae) is a generalist larval‐prepupal parasitoid of true fruit flies (Diptera: Tephritidae). During host‐seeking, females use visual information to locate the habitat of the host (fruit of various species). Previous studies have shown that females associate the colour of the host habitat with the availability of hosts through associative learning. In this study, we aimed to understand how this process is reinforced as the number of positive experiences increases and also how stable this association is, when the positive experiences cease. Additionally, under the hypothesis that associative learning has adaptive value, we evaluated the benefits of learning in two contexts: one in which host larvae are still associated with the learned colour and one where larvae are associated with a different colour. Repeated exposure to the unconditional stimulus for 1, 3, 5, and 7 consecutive training bouts influenced the preference response, as the percentage of females that preferred the stimulus increases with the number of training sessions. This preference seems to be reversible, as we found that the memory duration declines as time since the last training bout increased. The results obtained regarding the benefits of learning showed that females that learned a particular colour associated with the host, spent more time in that colour, made more oviposition attempts, and produced more offspring compared to females that learned a colour that is no longer associated with the host. This suggests that learning should not be fixed, and females would benefit from adjusting their behaviour to host availability. Such colour would allow females to find their host more efficiently, by associating cues that lead to host finding but also modifying their response when the cues are no longer associated with a reward, which seems a reasonable strategy for parasitoids of polyphagous hosts infesting ephemeral and changing habitats, such as fruit of different species. [ABSTRACT FROM AUTHOR]

Accelerometers worn by animals produce distinct behavioral signatures, which can be classified accurately using machine learning methods such as random forest decision trees. The objective of this study was to identify accelerometer signal separation among parsimonious behaviors. We achieved this objective by (1) describing functional differences in accelerometer signals among discrete behaviors, (2) identifying the optimal window size for signal pre-processing, and (3) demonstrating the number of observations required to achieve the desired level of model accuracy,. Crossbred steers (Bos taurus indicus; n = 10) were fitted with GPS collars containing a video camera and tri-axial accelerometers (read-rate = 40 Hz). Distinct behaviors from accelerometer signals, particularly for grazing, were apparent because of the head-down posture. Increasing the smoothing window size to 10 s improved classification accuracy (p < 0.05), but reducing the number of observations below 50% resulted in a decrease in accuracy for all behaviors (p < 0.05). In-pasture observation increased accuracy and precision (0.05 and 0.08 percent, respectively) compared with animal-borne collar video observations. [ABSTRACT FROM AUTHOR]

Visual statistical Learning (SL) allows infants to extract the statistical relationships embedded in a sequence of elements. SL plays a crucial role in language and communication competencies and has been found to be impacted in Autism Spectrum Disorder (ASD). This study aims to investigate visual SL in infants at higher likelihood of developing ASD (HL-ASD) and its predictive value on autistic-related traits at 24–36 months. At 6 months of age, SL was tested using a visual habituation task in HL-ASD and neurotypical (NT) infants. All infants were habituated to a visual sequence of shapes containing statistically predictable patterns. In the test phase, infants viewed the statistically structured, familiar sequence in alternation with a novel sequence that did not contain any statistical information. HL-ASD infants were then evaluated at 24–36 months to investigate the associations between visual SL and ASD-related traits. Our results showed that NT infants were able to learn the statistical structure embedded in the visual sequences, while HL-ASD infants showed different learning patterns. A regression analysis revealed that SL ability in 6-month-old HL-ASD infants was related to social communication and interaction abilities at 24–36 months of age. These findings indicate that early differences in learning visual statistical patterns might contribute to later social communication skills. [ABSTRACT FROM AUTHOR]

Background: Recent evidences have shown sex-differential cognitive deficits in bipolar disorder (BD) and differences in cognitions across BD subtypes. However, the sex-specific effect on cognitive impairment in BD subtype II (BD-II) remains obscure. The aim of the current study was to examine whether cognitive deficits differ by gender in youth with BD-II depression. Method: This cross-sectional study recruited 125 unmedicated youths with BD-II depression and 140 age-, sex-, and education-matched healthy controls (HCs). The Chinese version of the Measurement and Treatment Research to Improve Cognition in Schizophrenia (MATRICS) Consensus Cognitive Battery (MCCB) was used to assess cognitive functions. Mood state was assessed using the 24-item Hamilton Depression Rating Scale (24-HDRS) and the Young Mania Rating Scale (YMRS). Multivariate analysis of covariance (MANCOVA) was conducted. Result: ​Compared with HCs, patients with BD-II depression had lower scores on MCCB composite and its seven cognitive domains (all p < 0.001). After controlling for age and education, MANCOVA revealed significant gender-by-group interaction on attention/vigilance (F = 6.224, df = 1, p = 0.013), verbal learning (F = 9.847, df = 1, p = 0.002), visual learning (F = 4.242, df = 1, p = 0.040), and composite (F = 8.819, df = 1, p = 0.003). Post hoc analyses suggested that males performed worse in the above-mentioned MCCB tests than females in BD-II depression. Conclusion: Our study demonstrated generalized cognitive deficits in unmedicated youths with BD-II depression. Male patients performed more serious cognitive impairment on attention/vigilance, verbal learning, and visual learning compared to female patients. [ABSTRACT FROM AUTHOR]

Cognitive impairment is a core symptom of schizophrenia. The gut microbiota (GM) and oxidative stress may play important roles in the pathophysiological mechanisms of cognitive impairment. This study aimed to explore the relationship between GM and oxidative stress in the cognitive function of schizophrenia. GM obtained by 16S RNA sequencing and serum superoxide dismutase (SOD) levels from schizophrenia patients (N = 68) and healthy controls (HCs, N = 72) were analyzed. All psychiatric symptoms were assessed using the Positive and Negative Syndrome Scale (PANSS). Cognitive function was assessed using the MATRICS Consensus Cognitive Battery (MCCB). Correlation analysis was used to explore the relationship between GM, SOD, and cognitive function. Machine learning models were used to identify potential biomarkers. Compared to HCs, the relative abundances of Collinsella , undefined Ruminococcus , Lactobacillus , Eubacterium , Mogibacterium , Desulfovibrio , Bulleidia , Succinivibrio , Corynebacterium, and Atopobium were higher in patients with schizophrenia, but Faecalibacterium , Anaerostipes , Turicibacter, and Ruminococcus were lower. In patients with schizophrenia, the positive factor, general factor, and total score of MCCB positively correlated with Lactobacillus , Collinsella, and Lactobacillus , respectively; SOD negatively correlated with Eubacterium , Collinsella , Lactobacillus , Corynebacterium , Bulleidia, Mogibacterium, and Succinivibrio, but positively correlated with Faecalibacterium, Ruminococcus , and MCCB verbal learning index scores; Faecalibacterium and Turicibacter were positively correlated with MCCB visual learning index scores and speed of processing index scores, respectively. Our findings revealed a correlation between SOD and GM and confirmed that cognitive dysfunction in patients with schizophrenia involves abnormal SOD levels and GM changes. [ABSTRACT FROM AUTHOR]

Attention fluctuates between optimal and suboptimal states. However, whether these fluctuations affect how we learn visual regularities remains untested. Using web-based real-time triggering, we investigated the impact of sustained attentional state on statistical learning using online and offline measures of learning. In three experiments (N = 450), participants performed a continuous performance task (CPT) with shape stimuli. Unbeknownst to participants, we measured response times (RTs) preceding each trial in real time and inserted distinct shape triplets in the trial stream when RTs indicated that a participant was attentive or inattentive. We measured online statistical learning using changes in RTs to regular triplets relative to random triplets encountered in the same attentional states. We measured offline statistical learning with a target detection task in which participants responded to target shapes selected from the regular triplets and with tasks in which participants explicitly re-created the regular triplets or selected regular shapes from foils. Online learning evidence was greater in high vs. low attentional states when combining data from all three experiments, although this was not evident in any experiment alone. On the other hand, we saw no evidence of impacts of attention fluctuations on measures of statistical learning collected offline, after initial exposure in the CPT. These results suggest that attention fluctuations may impact statistical learning while regularities are being extracted online, but that these effects do not persist to subsequent tests of learning about regularities. [ABSTRACT FROM AUTHOR]

In this study, we examine the design process for a visual learning analytics (VLA) approach in addition to its effect on developing students' epistemic understanding of discourse and relationships to promote knowledge‐building inquiry. Over a 3‐month period, an experimental class of secondary school students took a visual arts course using a knowledge‐building design augmented by VLA, while a comparison class took the same course within a regular knowledge‐building environment. The VLA approach implemented in the experimental class emphasized collective reflections using assessment tools to visualize the students' online and classroom discussions. The analysis of the students' questionnaire responses and Knowledge Forum discourse showed that the VLA approach helped the students develop a deeper epistemic understanding of discourse for productive inquiry and greater domain knowledge. In addition, the students' epistemic understanding was associated with their performance in productive Knowledge Forum inquiry. Qualitative analysis of the classroom and group discussions, interview responses and learning artefacts showed that the VLA design helped them understand the nature of discourse deeply by encouraging them to notice community orientations, increase their awareness of productive discourse moves and advance idea development. The implications of the VLA design in improving epistemic understanding of discourse are discussed. We contribute to the literature by examining the epistemic dimensions of discourse and implementing VLA as an epistemic tool for knowledge building. Practitioner notesWhat is already known about this topic Supporting students to develop a meta‐level understanding, ie, their epistemic understanding of the nature of discourse, is important for promoting productive inquiry but continues to be challenging in education, and limited research has focused on the epistemic aspects of discourse.Little research has examined the role of a computer‐supported knowledge‐building environment augmented by a visual learning analytics approach on students' epistemic understanding of discourse, productive inquiry and domain knowledge.What this paper adds A knowledge‐building design augmented by a visual learning analytics approach linking online and face‐to‐face discourse supported students' epistemic understanding of discourse, productive inquiry and domain knowledge.VLA‐supported collective reflection in knowledge‐building facilitated students' noticing of community orientations, awareness of productive discourse moves and their idea development. These metacognitive processes helped students develop deeper epistemic understanding of discourse, productive inquiry and greater domain knowledge.Implications for practice and/or policy Epistemic understanding of the nature of discourse acts as a medium for promoting productive knowledge‐building inquiry and learning outcomes, and it is critical to help students develop meta‐level understanding by combining discourse content and epistemic components.It is important to create a VLA‐supported community that provides VLA‐related data‐supported collective reflection opportunities to help students engage in productive inquiry and knowledge building.Teachers can scaffold students to link online and face‐to‐face discourse and help them inquire into and reflect on discourse processes. [ABSTRACT FROM AUTHOR]

Many cognitive problems can be decomposed into series of subproblems that are solved sequentially by the brain. When subproblems are solved, relevant intermediate results need to be stored by neurons and propagated to the next subproblem, until the overarching goal has been completed. We will here consider visual tasks, which can be decomposed into sequences of elemental visual operations. Experimental evidence suggests that intermediate results of the elemental operations are stored in working memory as an enhancement of neural activity in the visual cortex. The focus of enhanced activity is then available for subsequent operations to act upon. The main question at stake is how the elemental operations and their sequencing can emerge in neural networks that are trained with only rewards, in a reinforcement learning setting. We here propose a new recurrent neural network architecture that can learn composite visual tasks that require the application of successive elemental operations. Specifically, we selected three tasks for which electrophysiological recordings of monkeys' visual cortex are available. To train the networks, we used RELEARNN, a biologically plausible four-factor Hebbian learning rule, which is local both in time and space. We report that networks learn elemental operations, such as contour grouping and visual search, and execute sequences of operations, solely based on the characteristics of the visual stimuli and the reward structure of a task. After training was completed, the activity of the units of the neural network elicited by behaviorally relevant image items was stronger than that elicited by irrelevant ones, just as has been observed in the visual cortex of monkeys solving the same tasks. Relevant information that needed to be exchanged between subroutines was maintained as a focus of enhanced activity and passed on to the subsequent subroutines. Our results demonstrate how a biologically plausible learning rule can train a recurrent neural network on multistep visual tasks. Author summary: Many visual problems, like finding your way on a map, are solved by decomposing them into a series of subproblems. For a successful decomposition, the neuronal processes that solve one subproblem must make their results available to the subsequent ones. Experiments in monkeys demonstrated that the outcomes of subproblems are represented as foci of enhanced activity in the visual cortex, which are related to attention shifts and can be used as inputs for the processes solving the next subproblems. To understand how subproblems and their sequencing are learned, we trained a recurrent artificial neural network on the same tasks that monkeys performed, using a biologically plausible reinforcement learning rule. The networks learned the tasks and, importantly, the activation of the networks' units resembled the spatiotemporal patterns of activity observed in the visual cortex of monkeys. Our results shed light on how recurrent neural networks trained with a biologically plausible learning rule can learn to propagate enhanced activity between subroutines to solve complex visual tasks. [ABSTRACT FROM AUTHOR]

Pupil size is a significant biosignal for human behavior monitoring and can reveal much underlying information. This study explored the effects of task load, task familiarity, and gaze position on pupil response during learning a visual tracking task. We hypothesized that pupil size would increase with task load, up to a certain level before decreasing, decrease with task familiarity, and increase more when focusing on areas preceding the target than other areas. Fifteen participants were recruited for an arrow tracking learning task with incremental task load. Pupil size data were collected using a Tobii Pro Nano eye tracker. A 2 × 3 × 5 three-way factorial repeated measures ANOVA was conducted using R (version 4.2.1) to evaluate the main and interactive effects of key variables on adjusted pupil size. The association between individuals' cognitive load, assessed by NASA-TLX, and pupil size was further analyzed using a linear mixed-effect model. We found that task repetition resulted in a reduction in pupil size; however, this effect was found to diminish as the task load increased. The main effect of task load approached statistical significance, but different trends were observed in trial 1 and trial 2. No significant difference in pupil size was detected among the three gaze positions. The relationship between pupil size and cognitive load overall followed an inverted U curve. Our study showed how pupil size changes as a function of task load, task familiarity, and gaze scanning. This finding provides sensory evidence that could improve educational outcomes. [ABSTRACT FROM AUTHOR]

Learning visual models of object classes conventionally require hundreds or a large number of training samples. Conventional gradient-based approaches for target recognition require lot of data to be trained on and require exhaustive training with high computational expense. Hence, when a new condition or untrained data is encountered, such systems inadequately misconfigure newly learned feature sets in the trained model. This misconfigures the structure of re-learned features and is then carried out in subsequent recognition stages. Thus, a development in this scenario with low training time will allow us to fend of this disadvantage. This study presents a new automatic target recognition framework that gives the enhanced performance of target-recognition system when several imaging sensors are connected with one another. This is in contrast with traditional automatic target recognition frameworks, which utilizes one-on-one computational model over synthetic-aperture radar image-processing systems. The work comprises of a learning-based classifications strategy when dealing with sharing of learned parameters over the network to discern critical changes in target-recognition performance by utilizing a novel one-shot learning-based reconfigurable learning network for image processing platform. This upgrades the networked connected CCTV and multiview synthetic-aperture radar image object identification and recognition process. [ABSTRACT FROM AUTHOR]

The proliferation of Web 2.0 tools in visual arts education has ushered in multifaceted learning environments that cater to diverse sensory experiences. Among these tools, Canva for Education application stands out, offering an array of visual assets, content, and templates for diverse design endeavors. This tool not only augments learning experiences but also enhances creativity by piquing students' engagement through its myriad features. Nonetheless, the efficacy of such a tool is augmented when intertwined with active learning methodologies in pedagogical settings. Specifically, when Canva for Education is embedded within a collaborative learning framework, it fosters a distinct learning milieu, promoting peer-to-peer interactions. In this paper, activities that can be implemented in collaborative groups with Canva for Education application in middle school visual arts class were introduced. These activities were prepared within the framework of the objectives related to the use of technology in visual arts curriculum in Türkiye. Within the scope of this study, products developed with different design types are presented to guide teachers. It is thought that these activities will provide insights for practitioners and students on the use of Canva for Education. [ABSTRACT FROM AUTHOR]

This study proposes an automatic findings generation method that performs in-context few-shot learning of a visual language model. The automatic generation of findings can reduce the burden of creating inspection records for infrastructure facilities. However, the findings must include the opinions and judgments of engineers, in addition to what is recognized from the image; therefore, the direct generation of findings is still challenging. With this background, we introduce in-context few-short learning that focuses on image similarity and text diversity in the visual language model, which enables text output with a highly accurate understanding of both vision and language. Based on a novel in-context few-shot learning strategy, the proposed method comprehensively considers the characteristics of the distress image and diverse findings and can achieve high accuracy in generating findings. In the experiments, the proposed method outperformed the comparative methods in generating findings for distress images captured during bridge inspections. [ABSTRACT FROM AUTHOR]

The non-transparency of artificial intelligence (AI) systems, particularly in deep learning (DL), poses significant challenges to their comprehensibility and trustworthiness. This study aims to enhance the explainability of DL models through visual analytics (VA) and human-in-the-loop (HITL) principles, making these systems more transparent and understandable to end users. In this work, we propose a novel approach that utilizes a transition matrix to interpret results from DL models through more comprehensible machine learning (ML) models. The methodology involves constructing a transition matrix between the feature spaces of DL and ML models as formal and mental models, respectively, improving the explainability for classification tasks. We validated our approach with computational experiments on the MNIST, FNC-1, and Iris datasets using a qualitative and quantitative comparison criterion, that is, how different the results obtained by our approach are from the ground truth of the training and testing samples. The proposed approach significantly enhanced model clarity and understanding in the MNIST dataset, with SSIM and PSNR values of 0.697 and 17.94, respectively, showcasing high-fidelity reconstructions. Moreover, achieving an F1m score of 77.76% and a weighted accuracy of 89.38%, our approach proved its effectiveness in stance detection with the FNC-1 dataset, complemented by its ability to explain key textual nuances. For the Iris dataset, the separating hyperplane constructed based on the proposed approach allowed for enhancing classification accuracy. Overall, using VA, HITL principles, and a transition matrix, our approach significantly improves the explainability of DL models without compromising their performance, marking a step forward in developing more transparent and trustworthy AI systems. [ABSTRACT FROM AUTHOR]

Schizophrenia is characterized by cognitive impairment affecting everyday functioning. Earlier research has hypothesized that antidepressants may associate with better cognitive functioning, but results are mixed. This study explored the association between antidepressant use and cognitive performance in terms of reaction time and visual learning in a clinical sample. In addition, we examined benzodiazepine use and anticholinergic burden. Study participants were drawn from the SUPER-Finland cohort, collected among patients with psychotic illnesses in 2016–2018 throughout Finland (n = 10,410). The analysis included adults with a schizophrenia diagnosis (F20) and results from a cognitive assessment (n = 3365). Information about medications and psychosocial factors were gathered through questionnaire and interview. Cognitive performance was assessed with the Cambridge Neuropsychological Test Automated Battery (CANTAB) with two subtests measuring reaction time and visual learning. Almost 36 % of participants used at least one antidepressant. The use of antidepressants in general was not associated with performance in the reaction time and visual learning tasks. However, the use of SNRI antidepressants was associated with a faster reaction time. Benzodiazepine use and a higher anticholinergic burden were associated with poorer performance in both tests. The results strengthen earlier findings that there is no association between antidepressant use in general and cognitive performance in schizophrenia. However, the association of SNRI medications with a faster reaction time warrants further research. Moreover, the results suggest that more attention should be paid to the anticholinergic burden of the medications used by patients with schizophrenia, as well as avoiding continuous benzodiazepine use. [ABSTRACT FROM AUTHOR]

Visual perceptual learning is traditionally thought to arise in visual cortex. However, typical perceptual learning tasks also involve systematic mapping of visual information onto motor actions. Because the motor system contains both effector-specific and effector-unspecific representations, the question arises whether visual perceptual learning is effector-specific itself, or not. Here, we study this question in an orientation discrimination task. Subjects learn to indicate their choices either with joystick movements or with manual reaches. After training, we challenge them to perform the same task with eye movements. We dissect the decision-making process using the drift diffusion model. We find that learning effects on the rate of evidence accumulation depend on effectors, albeit not fully. This suggests that during perceptual learning, visual information is mapped onto effector-specific integrators. Overlap of the populations of neurons encoding motor plans for these effectors may explain partial generalization. Taken together, visual perceptual learning is not limited to visual cortex, but also affects sensorimotor mapping at the interface of visual processing and decision making. [ABSTRACT FROM AUTHOR]

The challenge of supporting literacy among deaf children is as much linguistic as educational, since a major stumbling block can be the lack of a firm first language foundation. It is critical to meet this challenge, given the range of serious negative correlates to illiteracy. Students on the campuses of Gallaudet University and Swarthmore College collaborate to address this issue in an inter-institutional course in which we make bimodal-bilingual videobooks designed for enjoyable shared reading activities between deaf children and their caretakers. These videobooks bring a good signing model into the home and help develop a range of essential preliteracy skills. [ABSTRACT FROM AUTHOR]

Solitarily foraging ant species differ in their reliance on their two primary navigational systems— path integration and visual learning. Despite many species of Australian bull ants spending most of their foraging time on their foraging tree, little is known about the use of these systems while climbing. "Rewinding" displacements are commonly used to understand navigational system usage, and work by introducing a mismatch between these navigational systems, by displacing foragers after they have run-down their path integration vector. We used rewinding to test the role of path integration on the arboreal and terrestrial navigation of M. midas. We rewound foragers along either the vertical portion, the ground surface portion, or across both portions of their homing trip. Since rewinding involves repeatedly capturing and releasing foragers, we included a nondisplacement, capture-and-release control, in which the path integration vector is unchanged. We found that rewound foragers do not seem to accumulate path integration vector, although a limited effect of vertical rewinding was found, suggesting a potential higher sensitivity while descending the foraging tree. However, the decrease in navigational efficiency due to capture was larger than the vertical rewinding effect, which along with the negative impact of the vertical surface, and an interaction between capture and rewinding, may suggest aversion rather than path integration caused the vertical rewinding response. Together these results add to the evidence that M. midas makes minimal use of path integration while foraging, and the growing evidence that they are capable of quickly learning from aversive stimulus. [ABSTRACT FROM AUTHOR]

Hyperspectral image (HSI) classification is an active research problem in computer vision and multimedia field. Contrary to traditional image data, HSIs contain rich spectral, spatial and semantic information. Thus, how to extract the discriminative features for HSIs by integrating spectral , spatial and semantic cues together is the core issue to address HSI classification task. Existing works mainly focus on exploring spectral and spatial information which usually fail to fully explore the rich semantic information in HSIs. To address this issue, in this paper, we first propose a novel semantic Transformer scheme, named SemanticFormer, which aims to learn discriminative visual representations for semantics by exploiting the interaction among different semantic tokens. Using the proposed SemanticFormer, we then propose a novel heterogeneous network that contains both spectral–spatial convolution network branch and SemanticFormer branch to extract spectral–spatial and semantic features simultaneously for HSIs. Experiments on two widely used datasets demonstrate the effectiveness of our SemanticFormer and HSI classification network method. Our codes will be available in https://github.com/SissiW/SemanticFormer. • We propose a novel SemanticFormer module for semantic representation. • We integrate SemanticFormer into HSI classification framework. • SemanticFormer is a general scheme in CV. • Extensive experimental results prove the effectiveness of SemanticFormer. [ABSTRACT FROM AUTHOR]

Animates receive preferential attentional processing over inanimates because, from an evolutionary perspective, animates are important to human survival. We investigated whether animacy affects visual statistical learning—the detection and extraction of regularities in visual information from our rich, dynamic, and complex environment. Participants completed a selective-attention task, in which regularities were embedded in two visual streams, an attended and an unattended visual stream. The attended visual stream always consisted of line-drawings of non-objects, while the unattended visual stream consisted of line-drawings of either animates or inanimates. Participants then completed a triplet-discrimination task, which assessed their ability to extract regularities from the attended and unattended visual streams. We also assessed participants' awareness of regularities in the visual statistical learning task, and asked if any learning strategies were used. We were specifically interested in whether the animacy status of line-drawings in the unattended visual stream would affect visual statistical learning. There were four key findings. First, selective attention modulates visual statistical learning, with greater visual statistical learning for attended than for unattended information. Second, animacy does not affect visual statistical learning, with no differences found in visual statistical learning performance between the animate and inanimate condition. Third, awareness of regularities was associated with visual statistical learning of attended information. Fourth, participants used strategies (e.g., naming or labelling stimuli) during the visual statistical learning task. Further research is required to understand whether visual statistical learning is one of the adaptive functions that evolved from ancestral environments. [ABSTRACT FROM AUTHOR]

Reliable obstacle avoidance, which is essential for safe autonomous robot interaction with the real world, raises various challenges such as difficulties with obstacle perception and latent factor cognition impacting multi-modal obstacle avoidance. In this paper, we propose a Depth visUal Ego-motion Learning (DUEL) model, consisting of a cognitive generation network, a policy decision network and a potential partition network, to learn autonomous obstacle avoidance from expert policies. The DUEL model takes advantage of binocular vision to perceive scene depth. This serves as the input to the cognitive generation network which generates obstacle avoidance policies by maximizing its causal entropy. The policy decision network then optimizes the generation of the policies referring to expert policies. The generated obstacle avoidance policies are simultaneously transferred to the potential partition network to capture the latent factors contained within expert policies and perform multi-modal obstacle avoidance. These three core networks iteratively optimize the multi-modal policies relying on causal entropy and mutual information theorems, which are proven theoretically. Experimental comparisons with state-of-the-art models on 7 metrics demonstrate the effectiveness of the DUEL model. It achieves the best performance with an average ADE (Average Displacement Error) of 0.29 and average FDE (Final Displacement Error) of 0.55 across five different scenarios. Results show that the DUEL model can maintain an average obstacle avoidance success rate of 97% for both simulated and real world scenarios with multiple obstacles, demonstrating its success at capturing latent factors from expert policies. Our source codes are available at https://github.com/ACoTAI/DUEL. [ABSTRACT FROM AUTHOR]

Objective In line with global trends, growing number of educational institutions in Saudi Arabia are developing their curricula based on the feedback and suggestions from their students to help improve the quality of teaching. This study aims to assess the differences in learning style preferences among female nursing students of Saudi Arabia. Methods This cross-sectional study included 124 female nursing students who were asked to answer the culturally adapted Arabic version of visual, aural/auditory, read/write, and kinesthetic (VARK) survey. Data were analyzed with SPSS, version 23. The Wilks' lambda or multivariate analysis (MANOVA) was used to determine the relationship between the participants' learning preferences, sociodemographic characteristics, and year of study. Results Nursing students who had visual learning preferences had a significantly different learning style as compared to those who preferred aural and kinesthetic learning (p < 0.001). On the contrary, there was not enough evidence to conclude that the same was true for students who preferred to read/write. Conclusions Further research is required to explore the relationship between learning style preferences and learning outcomes with the inclusion of a larger sample size and representatives of two genders, males and females. The findings of the current research provide the foundation for adaptive learning by identifying the individual preferences in learning among the nursing students. [ABSTRACT FROM AUTHOR]

Many animal species rely on the Earth's magnetic field during navigation, but where in the brain magnetic information is processed is still unknown. To unravel this, we manipulated the natural magnetic field at the nest entrance of Cataglyphis desert ants and investigated how this affects relevant brain regions during early compass calibration. We found that manipulating the Earth's magnetic field has profound effects on neuronal plasticity in two sensory integration centers. Magnetic field manipulations interfere with a typical look-back behavior during learning walks of naive ants. Most importantly, structural analyses in the ants' neuronal compass (central complex) and memory centers (mushroom bodies) demonstrate that magnetic information affects neuronal plasticity during early visual learning. This suggests that magnetic information does not only serve as a compass cue for navigation but also as a global reference system crucial for spatial memory formation. We propose a neural circuit for integration of magnetic information into visual guidance networks in the ant brain. Taken together, our results provide an insight into the neural substrate for magnetic navigation in insects. [ABSTRACT FROM AUTHOR]

This paper addresses few-shot semantic segmentation and proposes a novel transductive end-to-end method that overcomes three key problems affecting performance. First, we present a novel ensemble of visual features learned from pretrained classification and semantic segmentation networks with the same architecture. Our approach leverages the varying discriminative power of these networks, resulting in rich and diverse visual features that are more informative than a pretrained classification backbone that is not optimized for dense pixel-wise classification tasks used in most state-of-the-art methods. Secondly, the pretrained semantic segmentation network serves as a base class extractor, which effectively mitigates false positives that occur during inference time and are caused by base objects other than the object of interest. Thirdly, a two-step segmentation approach using transductive meta-learning is presented to address the episodes with poor similarity between the support and query images. The proposed transductive meta-learning method addresses the prediction by first learning the relationship between labeled and unlabeled data points with matching support foreground to query features (intra-class similarity) and then applying this knowledge to predict on the unlabeled query image (intra-object similarity), which simultaneously learns propagation and false positive suppression. To evaluate our method, we performed experiments on benchmark datasets, and the results demonstrate significant improvement with minimal trainable parameters of 2.98M. Specifically, using Resnet-101, we achieve state-of-the-art performance for both 1-shot and 5-shot Pascal- 5 i , as well as for 1-shot and 5-shot COCO- 20 i . [ABSTRACT FROM AUTHOR]

Many species learn temporal regularities in their visual environment, demonstrating visual statistical learning. In this study, we explored the sensitivity of macaque inferior temporal (IT) cortical neurons to transition probabilities of sequentially presented visual images, presented at different locations in the visual field. We exposed monkeys to sequences of two images, where the first image was presented either foveally or peripherally, and the second image was consistently presented foveally. Following several weeks of exposure, we recorded IT responses to assess differences between the exposed (Fixed) and new, Deviant sequences, where the identity of the first image in a sequence differed from the exposure phase. While enhanced responses to Deviant sequences were observed when both images of a pair were foveally presented during exposure, no such deviant responses were present when the first image was presented peripherally. This finding challenges the notion that mere exposure to image sequences always leads to deviant responses in macaque IT. The results highlight the complexity of the mechanisms underlying statistical learning in primates, particularly in the context of peripheral image presentations, emphasizing the need for further investigation into the origins of these responses in the IT cortex. [ABSTRACT FROM AUTHOR]

A reciprocal relationship between perceptual learning and functional brain changes towards perceptual learning effectiveness has been demonstrated previously; however, the underlying neural correlates remain unclear. Further, visual perceptual learning (VPL) is implicated in visual field defect (VFD) recovery following chronic stroke. We investigated resting-state functional connectivity (RSFC) in the visual cortices associated with mean total deviation (MTD) scores for VPL-induced VFD recovery in chronic stroke. Patients with VFD due to chronic ischemic stroke in the visual cortex received 24 VPL training sessions over 2 months, which is a dual discrimination task of orientation and letters. At baseline and two months later, the RSFC in the ipsilesional, interhemispheric, and contralesional visual cortices and MTD scores in the affected hemi-field were assessed. Interhemispheric visual RSFC at baseline showed the strongest correlation with MTD scores post-2-month VPL training. Notably, only the subgroup with high baseline interhemispheric visual RSFC showed significant VFD improvement following the VPL training. The interactions between the interhemispheric visual RSFC at baseline and VPL led to improvement in MTD scores and largely influenced the degree of VFD recovery. The interhemispheric visual RSFC at baseline could be a promising brain biomarker for the effectiveness of VPL-induced VFD recovery. [ABSTRACT FROM AUTHOR]

In the technological age, higher education is at a crossroads that requires a redefinition of pedagogical paradigms. The analysis focuses on the integration of Instagram and YouTube as pedagogical tools for visual culture. The convergence of visual culture and social media poses challenges in the face of media saturation. The systematic review underpins the transformative potential of these platforms in higher education. Continuous teacher training and innovative pedagogical strategies are essential to optimise their impact. Envisioning the classroom as a space where visual culture and active methods converge opens up a promising pedagogical horizon for higher education. [ABSTRACT FROM AUTHOR]

Modern education demands innovative approaches to engage students effectively and enhance learning outcomes. This article explores the implementation of an innovative pedagogical approach, namely Project-Based Learning (PjBL), in the context of the Visual Programming course. The study aims to investigate the impact of this approach on students’ participation and learning achievements. Using a Classroom Action Research (CAR) design, the research was conducted in two cycles. The participants were 30 students enrolled in the Educational Technology Informatics program at Universitas Negeri Padang. The study used a descriptive comparative method to assess the outcomes, comparing pre-cycle to Cycle II results. The findings reveal remarkable improvements in student’s cognitive growth (53.33%), affective development (46.66%), and psychomotor skills (56.66%) following the application of the PjBL approach. Furthermore, there was a noticeable increase of 43.44% in the active participation of students during the learning process after incorporating the PjBL approach. In conclusion, this study underscores the effectiveness of PjBL in fostering active participation and elevating learning achievements in the Visual Programming course. The article contributes to the discourse on innovative pedagogical strategies. It highlights the potential of PjBL to revolutionize traditional educational methods, equipping students with skills engagingly and effectively. [ABSTRACT FROM AUTHOR]

This paper describes a doctoral seminar in visual and arts-based inquiry (V/ABR) to champion the generativity of such approaches for advancing doctoral research. We first describe the social and institutional context of the course and its design to situate the projects and the need for creating institutional spaces to amplify creative inquiry approaches in doctoral education. Then, five researchers reflect on their research approaches, including comics, collaging, critical visual analysis, a virtual walkography, and photo-elicitation. The projects focused on contemporary issues including researcher identity, racial justice, mothering crises, and Christian summer camps, collectively underscoring the productivity of V/ABR inquiry for amplifying researchers' imaginaries and processes of becoming. We underscore the necessity of exploring qualitative diversity in doctoral education to unsettle fixed inquiry approaches that Bailey (2018) calls "methodological taxidermy." Collectively, we demonstrate the vitality of advancing doctoral research using creative methods in relational, socially responsive, and critical, visionary ways (Finley, 2003). [ABSTRACT FROM AUTHOR]

Classifying specimens is a critical component of ecological research, biodiversity monitoring and conservation. However, manual classification can be prohibitively time‐consuming and expensive, limiting how much data a project can afford to process.Computer vision, a form of machine learning, can help overcome these problems by rapidly, automatically and accurately classifying images of specimens. Given the diversity of animal species and contexts in which images are captured, there is no universal classifier for all species and use cases. As such, ecologists often need to train their own models. While numerous software programs exist to support this process, ecologists need a fundamental understanding of how computer vision works to select appropriate model workflows based on their specific use case, data types, computing resources and desired performance capabilities. Ecologists may also face characteristic quirks of ecological datasets, such as long‐tail distributions, 'unknown' species, similarity between species and polymorphism within species, which impact the efficacy of computer vision.Despite growing interest in computer vision for ecology, there are few resources available to help ecologists face the challenges they are likely to encounter. Here, we present a gentle introduction for species classification using computer vision. In this manuscript and associated GitHub repository, we demonstrate how to prepare training data, basic model training procedures, and methods for model evaluation and selection. Throughout, we explore specific considerations ecologists should make when training classification models, such as data domains, feature extractors and class imbalances.With these basics, ecologists can adjust their workflows to achieve research goals and/or account for uncertainty in downstream analysis. Our goal is to provide guidance for ecologists for getting started in or improving their use of machine learning for visual classification tasks. [ABSTRACT FROM AUTHOR]

Remote sensing change detection (RSCD), which aims to identify surface changes from bitemporal images, is significant for many applications, such as environmental protection and disaster monitoring. In the last decade, driven by the wave of artificial intelligence, many change detection methods based on deep learning emerged and have achieved essential breakthroughs. However, these methods pay more attention to visual representation learning while ignoring the potential of multimodal data. Recently, the foundation vision-language model, i.e. CLIP, has provided a new paradigm for multimodal AI, demonstrating impressive performance on downstream tasks. Following this trend, in this study, we introduce ChangeCLIP, a novel framework that leverages robust semantic information from image-text pairs, specifically tailored for Remote Sensing Change Detection (RSCD). Specifically, we reconstruct the original CLIP to extract bitemporal features and propose a novel differential features compensation module to capture the detailed semantic changes between them. Besides, we proposed a vision-language-driven decoder by combining the results of image-text encoding with the visual features of the decoding stage, thereby enhancing the image semantics. The proposed ChangeCLIP achieved state-of-the-art IoU on 5 well-known change detection datasets, LEVIR-CD (85.20%), LEVIR-CD+ (75.63%), WHUCD (90.15%), CDD (95.87%) and SYSU-CD (71.41%). The code and the pretrained models of ChangeCLIP will be publicly available on https://github.com/dyzy41/ChangeCLIP. [ABSTRACT FROM AUTHOR]

Cognitive impairment (CI) is regarded as a remarkable burden in COVID-19 survivors. Its prevalence and profile, and relationships with the disease clinical and laboratory indices, remain unclear. The present study investigated, in a large sample of patients recovered from COVID-19, the frequency of CI with both a face-to-face screening tool and comprehensive test battery (MCCB). The study also evaluated the profile of CI and its relationships with COVID-19 clinical and laboratory indices and with psychopathological features. Out of 1344 subjects assessed for eligibility, 736 completed the screening phase 11 months after the COVID-19 infection; 402 participated in the baseline phase and completed an in depth cognitive, clinical and laboratory assessment about one month later. More than one third of the screened subjects presented a CI (COG+); it was associated to age, education, male gender, COVID-19 severity, and presence of anosmia, dyspnea at rest and exertional dyspnea during the acute phase. COG+ subjects showed a higher severity of depression, anxiety and post-traumatic distress, and worse global functioning, than subjects without CI. The MCCB showed that 45% of the subjects had a CI involving attention, working memory, verbal learning, visual learning, and reasoning and problem solving. Finally, neurocognitive functioning was inversely correlated with LDH blood levels, a potential biomarker of disease severity. According to our findings, cognitive functioning should be routinely and periodically assessed in COVID-19 patients, especially in older subjects, who experienced more severe COVID-19 symptoms. In case of persisting dysfunctions cognitive training programs should be considered as treatment strategies. [ABSTRACT FROM AUTHOR]

Large-scale contrastive vision-language pretraining has shown significant progress in visual representation learning. Unlike traditional visual systems trained by a fixed set of discrete labels, a new paradigm was introduced in Radford et al. (International conference on machine learning, PMLR, 2021) to directly learn to align images with raw texts in an open-vocabulary setting. On downstream tasks, a carefully chosen text prompt is employed to make zero-shot predictions. To avoid non-trivial prompt engineering, context optimization (Zhou et al. in Int J Comput Vis 130(9):2337–2348, 2022) has been proposed to learn continuous vectors as task-specific prompts with few-shot training examples. In this paper, we show that there is an alternative path to achieve better vision-language models other than prompt tuning. While prompt tuning is for the textual inputs, we propose CLIP-Adapter to conduct fine-tuning with feature adapters on either visual or language branch. Specifically, CLIP-Adapter adopts an additional bottleneck layer to learn new features and performs residual-style feature blending with the original pretrained features. As a consequence, CLIP-Adapter is able to outperform context optimization while maintaining a simple design. Experiments and extensive ablation studies on various visual classification tasks demonstrate the effectiveness of our approach. [ABSTRACT FROM AUTHOR]

The mushroom bodies, an integrative region of the insect brain involved in learning and memory, have undergone volumetric increase in several independent lineages including bees and ants, cockroaches and some beetles. However, the selective pressures driving these expansion events are not fully understood. One promising system for investigating this question is the Neotropical butterfly genus Heliconius , which exhibits markedly enlarged mushroom bodies compared with other members of the Heliconiini tribe. Notably, this neural elaboration co-occurs with the evolution of trap line foraging behaviour and an improved capacity for learning complex visual cues and long-term memory. Here, we further investigated the behavioural consequences of this brain expansion by testing reversal learning ability, a commonly used measure of cognition and behavioural flexibility in both vertebrates and invertebrates, across three Heliconius and three closely related Heliconiini species. We trained butterflies to associate a food reward with either purple or yellow flowers, before training them with the reversed associations, and then reversing the cues again. All six species successfully learned the reversed cues, and, contrary to our expectations, we found no evidence that Heliconius performed better than the other Heliconiini species. These results are surprising, given previous evidence linking the mushroom bodies to reversal learning in other insects and the enhanced performance of Heliconius in other cognitive tests. This serves as a reminder that the functional consequences of brain expansion can be multifaceted and do not necessarily result in an overall increase in general cognitive ability, but rather result in enhanced performance in specific, ecologically relevant tasks. • Heliconiini butterflies learnt twice-reversed colour–food associations. • Heliconius did not outperform other Heliconiini in this reversal learning task. • Heliconius showed higher accuracy in the initial associative learning task. [ABSTRACT FROM AUTHOR]

Based on a sample of the most commonly used textbooks and online teaching resources, we find that photos play a central but deeply problematic role in Holocaust education in the UK. The impact of photos on a generation of 'primarily visual learners' is significant. But an over-reliance on a set of problematic stock photos, inadequate or erroneous captioning, and a lack of prompts for a critical analysis of photos create problems. Their combined effect can adversely affect understandings of this difficult history, and limit the development of visual literacy skills required for tackling contemporary misinformation and visual indoctrination. [ABSTRACT FROM AUTHOR]

Multimodal few-shot learning aims to exploit complementary information inherent in multiple modalities for vision tasks in low data scenarios. Most of the current research focuses on a suitable embedding space for the various modalities. While solutions based on embedding provide state-of-the-art results, they reduce the interpretability of the model. Separate visualization approaches enable the models to become more transparent. In this paper, a multimodal few-shot learning framework that is inherently interpretable is presented. This is achieved by using the textual modality in the form of attributes without embedding them. This enables the model to directly explain which attributes caused it to classify an image into a particular class. The model consists of a variational autoencoder to learn the visual latent representation, which is combined with a semantic latent representation that is learnt from a normal autoencoder, which calculates a semantic loss between the latent representation and a binary attribute vector. A decoder reconstructs the original image from concatenated latent vectors. The proposed model outperforms other multimodal methods when all test classes are used, e.g., 50 classes in a 50-way 1-shot setting, and is comparable for lesser number of ways. Since raw text attributes are used, the datasets for evaluation are CUB, SUN and AWA2. The effectiveness of interpretability provided by the model is evaluated by analyzing how well it has learnt to identify the attributes. [ABSTRACT FROM AUTHOR]

The purpose of this study is to identify whether students' academic performance is influenced by their learning style. The research addressed students in the field of educational sciences. To collect research data, a questionnaire was applied to a number of 143 students aged between 19 and 56 years. The research data were statistically analyzed using the Kruskal Wallis Test. The statistical results indicate significant differences between students with auditory, visual and practical learning styles depending on the academic performance and the year of study. Our results can be used in the teaching-learning process by the teacher. [ABSTRACT FROM AUTHOR]

Hallucinations can be experienced across multiple sensory modalities, but psychiatric studies investigating the cognitive mechanisms of hallucinations have been somewhat restricted to the auditory domain. This study explored the cognitive profiles of individuals experiencing multisensory hallucinations (MH) in schizophrenia-spectrum disorders (SSD) and compared these to those experiencing unimodal auditory hallucinations (AH) or no hallucinations (NH). Participants included SSD patients (n = 119) stratified by current hallucination status (NH, AH, MH) and nonclinical controls (NCs; n = 113). Group performance was compared across several cognitive domains: speed of processing, attention, working memory, verbal learning, visual learning, reasoning and problem-solving, social cognition, and inhibition. The clinical groups performed worse than NCs but differences between the clinical groups were not evident across most cognitive domains. Exploratory analyses revealed that the MH group was more impaired on the visual learning task compared to the NH (but not AH) group. Preliminary results suggest that impaired visual learning may be related to MH. This could be attributed to the presence of visual hallucinations (VH), or greater psychopathology, in this group. However, replication is needed, as well as the investigation of other potential cognitive mechanisms of MH. [ABSTRACT FROM AUTHOR]

We conducted laboratory experiments using Japanese carpenter ants (Camponotus japonicus) to investigate whether movement during visual learning can influence the learning performance of ant foragers. We performed three different experiments. In the first experiment, the ants could move freely in a straight maze during the visual learning. The ants in the experiments two and three were fixed to a certain position during the visual learning training. A distinct difference between these two experiments was that the ants in one experiment could perceive an approaching visual stimulus during the training, although they were fixed. After training phases, a Y-maze test was performed. One arm of the Y-maze had a visual stimulus presented to the ants during the training. We found that the ants in the first experiment showed rapid learning and correctly selected the landmark arm. However, the ants in the experiments two and three did not exhibit any preference for the chosen arm. Interestingly, we found differences in the time spent around a certain location in the Y-maze between the experiments two and three. These results suggest that movement during visual learning may influence the rapid learning of ant foragers. [ABSTRACT FROM AUTHOR]

BACKGROUND: Amblyopia is a neurological deficit in binocular vision that affects 3% of the population and is the result of disruptions in early visual development. OBJECTIVE: In this study, we used a visual perceptual learning system for the short-term treatment of children with ametropic amblyopia and evaluated the clinical efficacy of this system in terms of visual plasticity. METHODS: We conducted a retrospective analysis of the clinical data of 114 children (228 eyes) with refractive amblyopia, who were aged 6.51 ± 1.51 years. Prior to the treatment, we evaluated all children with amblyopia using the visual information processing test. We determined the type of amblyopic defect according to the type of amblyopia, corrected visual acuity, and advanced visual function test results. Based on the type of defect, each child with amblyopia was given short-term visual perception training for 10 days. Finally, we compared the results of visual acuity and visual information processing tests before and after the treatment. RESULTS: The best-corrected visual acuity of patients was better after 10 days of visual training than that before training (P < 0.05). The perceptual eye position after training improved with statistically significant differences in horizontal and vertical perceptual eye position (both P < 0.05) compared to that before training. The number of amblyopic children without suppression in both eyes was 81 cases (71.1%) after training which was higher than that (65 cases, or 57.0%) before training, with a statistically significant difference (P < 0.05). Binocular fine stereopsis and dynamic stereopsis improved after training with a statistically significant difference (both P < 0.05). CONCLUSION: In this study, it was found that patients with amblyopia showed visual plasticity. Moreover, continuous visual perceptual learning improved the best-corrected visual acuity and recovered stereopsis in children with refractive amblyopia. [ABSTRACT FROM AUTHOR]

This research investigates the potential of in vivo learning to enhance visual representation learning for image-based person re-identification (re-ID). Compared to traditional self-supervised learning (which require external data), the introduced in vivo learning utilizes supervisory labels generated from pedestrian images to improve re-ID accuracy without relying on external data sources. Three carefully designed in vivo learning tasks, leveraging statistical regularities within images, are proposed without the need for laborious manual annotations. These tasks enable feature extractors to learn more comprehensive and discriminative person representations by jointly modeling various aspects of human biological structure information, contributing to enhanced re-ID performance. Notably, the method seamlessly integrates with existing re-ID frameworks, requiring minimal modifications and no additional data beyond the existing training set. Extensive experiments on diverse datasets, including Market1501, CUHK03-NP, Celeb-reID, Celeb-reid-light, PRCC, and LTCC, demonstrate substantial enhancements in rank-1 precision compared to state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Recently, Zhang et al. (Nature communications, 9(1), 3730, 2018) proposed an interesting model of attention guidance that uses visual features learnt by convolutional neural networks (CNNs) for object classification. I adapted this model for search experiments, with accuracy as the measure of performance. Simulation of our previously published feature and conjunction search experiments revealed that the CNN-based search model proposed by Zhang et al. considerably underestimates human attention guidance by simple visual features. Using target-distractor differences instead of target features for attention guidance or computing attention map at lower layers of the network could improve the performance. Still, the model fails to reproduce qualitative regularities of human visual search. The most likely explanation is that standard CNNs that are trained on image classification have not learnt medium- or high-level features required for human-like attention guidance. [ABSTRACT FROM AUTHOR]

In Visual Indoor Navigation (VIN), Deep Reinforcement Learning (DRL) is commonly used by agents to achieve end-to-end mapping from vision to action when navigating toward a target based on observation. However, current DRL-based work suffers from two challenges: partial observability resulting from using solely a single first-person view and poor generalization in the case of unknown scenes and unknown objects. In light of these issues, this paper introduces the integration of multi-view as an expansion of observability and meta-learning as a primary generalization technique into the DRL framework and presents the meta-reinforcement learning method that leverages Multi-View Semantic Spatial Context (MVSSC). Specifically, aiming to explore the informative multi-view context for better efficiency in searching for and navigating to the target, we model the objects' relationship from two aspects, multi-view semantic context (MVSEC) and multi-view spatial context (MVSPC). MVSEC enables agents to encode prior semantic relationships adaptively via a multi-view modulated graph. Meanwhile, MVSPC enhances the spatial representation of target-related objects' correlation through similarity grids of multi-view. After adaptively fusing the multi-view and context information under the meta-reinforcement learning framework, our method can encourage efficient target search and robust navigation with stronger generalization performance to unknown scenes and unknown objects. Extensive experimental results on the AI2-THOR simulator demonstrate that our method outperforms the current state-of-the-art approaches. • Utilize the multi-view representation to enlarge the agent's perception. • Construct a semantic graph and spatial grids to learn multi-view context information. • Incorporate meta-learning into the multi-view framework for better generalization. • Results show the superior generalization to new objects and new scenes. [ABSTRACT FROM AUTHOR]

The constant development and the wider usage of computed tomography (CT) has gained the attention of researchers during medical practice related to radiation dose. The intention to eradicate the dosage causes increased artefacts and noise influences the confidentiality of the radiologist. Specifically, various noises like speckle, pepper, impulse, salt and Gaussian noise are determined as the complex source of image noise. Therefore, the enhancements in image reconstruction from the CT image need to be enhanced with the diagnostic performance are a challenging issue related to ill-posed nature. Various CT prediction approaches have given superior outcomes. Moreover, there are fewer works in image denoising using learning approaches as these approaches pretend to reduce mean square error (MSE) among the denoised CT images. The outcomes of the models are compromising and show the visibility of aggressive denoising. This research focuses on modelling an efficient approach for CT image denoising with an adaptive adversarial network model that uses weighted similarity measure ( aa - WSM ). The anticipated model has the key concept of enhancing the performance and reducing the error rate. The proposed model concentrates on migrating the noise distribution and learning the visual perception knowledge to perform the denoising task. The PSNR of the proposed model is 16.6 and SSIM is 0.64 which is comparatively better than existing methods. The suppressed noise is 5.2, artefacts reduction is 3.6 and the overall quality is 3.8 which is nominal than others. The model handles the essential information and manages the error rate with promising outcomes. [ABSTRACT FROM AUTHOR]

Visual analysis and authentication of artworks are challenging tasks central to art history and criticism. This preliminary study presents a computational tool for scholars examining and authenticating a restricted class of paintings, with a specific focus on the paintings of Raffaello Sanzio da Urbino, more popularly known as Raphael. We applied transfer learning to the ResNet50 deep neural network for feature extraction and used a support vector machine (SVM) binary classifier in support of authentication. Edge detection and analysis algorithms, considered to be crucial for capturing the essence of Raphael's artistic style, including the brushwork signatures, were also integrated and are used as an authentication tool. The machine learning approach we have developed demonstrates an accuracy of 98% in image-based classification tasks during validation using a test set of well known and authentic paintings by Raphael. Of course, a full authentication protocol relies on provenance, history, material studies, iconography, studies of a work's condition, and more. Our work, then, contributes to just a portion of a full authentication protocol. Our findings suggest that machine learning methods, properly employed by experts aware of context, may enhance and expand traditional visual analysis for problems in art authentication. [ABSTRACT FROM AUTHOR]