General Recognition Research Articles

Understanding Return to Work After a Cancer-Related Sickness Absence. Perceptions of Barriers and Facilitators Among all Relevant Stakeholders.

The aim of this study was to examine the themes acting as barriers or facilitators, from diagnosis and sickness absence (SA) to RTW and work retention, after a cancer-related SA from the perspectives of all stakeholders in the Spanish setting. Descriptive qualitative approach with a socio-constructivist perspective. Theoretical sampling was carried out until saturation. Six discussion groups (4-8 people/group) were conducted: three groups of people with a cancer-related SA in Catalonia (Spain), one with oncology care professionals, and two with company representatives. An additional individual interview was conducted with a primary care physician. The sessions were held virtually and were recorded, transcribed verbatim, and analyzed using thematic analysis and mixed coding. Barriers to RTW and work retention detected by stakeholders included insufficient information and guidance on the impact of cancer on work and SA management, lack of general knowledge and recognition of side effects, lack of consideration of job tasks by medical tribunals, and working in precarious employment. Facilitators included workplace support, psycho-oncologists, patient associations, and working for a public company. Both work interruption due to an SA and RTW, are key moments for determining cancer survivors' work retention. We found a general perception of lack of involvement of the social security system, companies, and health professionals in Spain in the impact of cancer on work. Integrating the work sphere in cancer care from the beginning of cancer treatment, and by all stakeholders, could facilitate successful future RTW.

DeFFace: Deep Face Recognition Unlocked by Illumination Attributes

General face recognition is currently one of the key technologies in the field of computer vision, and it has achieved tremendous success with the support of deep-learning technology. General face recognition models currently exhibit extremely high accuracy on some high-quality face datasets. However, their performance decreases in challenging environments, such as low-light scenes. To enhance the performance of face recognition models in low-light scenarios, we propose a face recognition approach based on feature decoupling and fusion (DeFFace). Our main idea is to extract facial-related features from images that are not influenced by illumination. First, we introduce a feature decoupling network (D-Net) to decouple the image into facial-related features and illumination-related features. By incorporating the illumination triplet loss optimized with unpaired identity IDs, we regulate illumination-related features to minimize the impact of lighting conditions on the face recognition system. However, the decoupled features are relatively coarse. Therefore, we introduce a feature fusion network (F-Net) to further extract the residual facial-related features from the illumination-related features and fuse them with the initial facial-related features. Finally, we introduce a lighting-facial correlation loss to reduce the correlation between the two decoupled features in the specific space. We demonstrate the effectiveness of our method on four real-world low-light datasets and three simulated low-light datasets. We retrain multiple general face recognition methods using our proposed low-light training sets to further validate the advanced performance of our method. Compared to general face recognition methods, our approach achieves an average improvement of more than 2.11 percentage points on low-light face datasets. In comparison with image enhancement-based solutions, our method shows an average improvement of around 16 percentage points on low-light datasets, and it also delivers an average improvement of approximately 5.67 percentage points when compared to illumination normalization-based methods.

Physiologists as medical scientists: An early warning from the German academic system.

"Medical scientists" are postgraduate investigators who are engaged in biomedical research, and either hold a biomedical PhD or are qualified in medicine but do not participate in patient care. Medical scientists constitute ~40% of staff at medical faculties and >90% at nonuniversity medical research institutions in Germany. However, medical scientists in Germany face limited long-term career prospects and a lack of dedicated training and support programmes. They also face time limits on their career progression arising from national academic employment legislation, and imminent reforms by the German government are likely to make this worse. Nevertheless, recent developments in the educational landscape including the introduction of increasingly focused MSc, pre-PhD, and doctoral programmes to train medically aware basic scientists, as well as improved general recognition of the roles and relevance of medical scientists in health research, are encouraging. Physiologists have taken essential steps to improve the recognition of medical scientists in Germany by introducing a "specialist physiologist" qualification; this initiative could be applied to support medical scientists in other fields and countries. In this review, we describe the particular challenges facing medical scientists in Germany and make recommendations that may apply to other academic systems.

A comprehensive review of approaches for spatial domain recognition of spatial transcriptomes.

In current bioinformatics research, spatial transcriptomics (ST) as a rapidly evolving technology is gradually receiving widespread attention from researchers. Spatial domains are regions where gene expression and histology are consistent in space, and detecting spatial domains can better understand the organization and functional distribution of tissues. Spatial domain recognition is a fundamental step in the process of ST data interpretation, which is also a major challenge in ST analysis. Therefore, developing more accurate, efficient, and general spatial domain recognition methods has become an important and urgent research direction. This article aims to review the current status and progress of spatial domain recognition research, explore the advantages and limitations of existing methods, and provide suggestions and directions for future tool development.

Einstein–Perrin dilemma on the Brownian motion (Avogadro’s number) resolved?

The general recognition of the existence of atoms and molecules occurred only at the beginning of the twentieth century. Many researchers contributed to this, but the ultimate proof of the molecular nature of matter that convinced even the last sceptics was the confirmation of Albert Einstein’s statistical-fluctuation theory of Brownian motion, a part of his comprehension of interdisciplinary atomism, by Jean Perrin’s experiments on colloidal gamboge particles. Einstein noticed a difference between the values of Avogadro’s constant derived from Perrin’s experiments and Planck’s calculation from black-body radiation. Einstein assumed the incorrectly evaluated size of the gamboge spherules to be a culprit of the difference and asked Perrin to check the assumption with additional experiments and using the viscosity formula introduced in his own dissertation. The result was a discrepancy that neither Einstein nor Perrin settled any further. In this communication, based on the survey of developments in colloid and polymer science and their comparison with relevant experiments, an explanation of the dilemma is given that now, after more than a century, proves Einstein correct. The comparison was de facto possible during his lifetime.

Gender, Racial, and Ethnic Diversity in Plastic Surgery: Evaluating Effective Initiatives and Identifying Areas for Improvement.

Women and racial and ethnic minorities have historically been underrepresented in medicine, making up a minority of all physicians and a smaller subset of plastic surgeons. Furthermore, these groups represent an even smaller fraction of plastic surgeons in research and leadership roles. Parallel to the general recognition of the importance of increasing diversity in the medical field, there has been a surge in the literature detailing current issues and highlighting potential areas for intervention within plastic surgery. Various initiatives have been piloted to address the underrepresentation of certain demographic groups in the field. These have largely targeted the medical student level, with a focus on increasing mentorship, targeted recruitment, exposure to the field, and scholarly opportunities. With the growing body of research conducted in this realm, this review seeks to synthesize our understanding of the modern landscape of gender, racial, and ethnic diversity within plastic surgery, with an emphasis on identifying successful initiatives that have positively impacted representation and inclusivity.

A Multi-Fruit Recognition Method for a Fruit-Harvesting Robot Using MSA-Net and Hough Transform Elliptical Detection Compensation

In the context of agricultural modernization and intelligentization, automated fruit recognition is of significance for improving harvest efficiency and reducing labor costs. The variety of fruits commonly planted in orchards and the fluctuations in market prices require farmers to adjust the types of crops they plant flexibly. However, the differences in size, shape, and color among different types of fruits make fruit recognition quite challenging. If each type of fruit requires a separate visual model, it becomes time-consuming and labor intensive to train and deploy these models, as well as increasing system complexity and maintenance costs. Therefore, developing a general visual model capable of recognizing multiple types of fruits has great application potential. Existing multi-fruit recognition methods mainly include traditional image processing techniques and deep learning models. Traditional methods perform poorly in dealing with complex backgrounds and diverse fruit morphologies, while current deep learning models may struggle to effectively capture and recognize targets of different scales. To address these challenges, this paper proposes a general fruit recognition model based on the Multi-Scale Attention Network (MSA-Net) and a Hough Transform localization compensation mechanism. By generating multi-scale feature maps through a multi-scale attention mechanism, the model enhances feature learning for fruits of different sizes. In addition, the Hough Transform ellipse detection compensation mechanism uses the shape features of fruits and combines them with MSA-Net recognition results to correct the initial positioning of spherical fruits and improve positioning accuracy. Experimental results show that the MSA-Net model achieves a precision of 97.56, a recall of 92.21, and an mAP@0.5 of 94.81 on a comprehensive dataset containing blueberries, lychees, strawberries, and tomatoes, demonstrating the ability to accurately recognize multiple types of fruits. Moreover, the introduction of the Hough Transform mechanism reduces the average localization error by 8.8 pixels and 3.5 pixels for fruit images at different distances, effectively improving the accuracy of fruit localization.

Integration of the brain jogging program in physical education on the cognitive abilities of elementary school students

Background. Developing children's cognitive since childhood is very important for parents so that children can develop optimally. There are many benefits if children have good cognitive abilities or skills, such as reasoning and solving problems they face better. Cognitive abilities are very important for children because they are a provision in living everyday life and working as adults. Purpose. Therefore, this study aimed to look into how brain jogging affected elementary school school students' cognitive capacities. Material and methods. An experimental methodology with a pretest-posttest-one-group design was employed in this investigation. The research instrument used was the Intelligenz Structure Test (IST) which was used as a memory test; the Digit Symbol Substitution Test (DSST) was used to test attention; and the Grid Concentration Test (GCT) was used to test concentration. The sample in this study were elementary school students with an average age of 10-11 years who joined six elementary schools in Sumedang Regency, Indonesia, totaling 75 people, consisting of 40 boys and 35 girls. Non-probability sampling with the purposive sampling method, or purposive sampling only, was used. That is, the location of the sample is close to the research location. Results. Based on the calculation of the hypothesis test using the Paired Sample t-test, the difference in the average pre-test and post-test data from the child's cognitive ability through the IST test obtained a P-value of 0.000. Then the DSST test obtained a P-value of 0.000, and the GCT test obtained a P-value of 0.000. Thus, there is a difference between the average pre-test and post-test scores indicated by a P-value less than 0.05. Conclusions. The results of this study prove that the brain jogging program significantly affects the cognitive abilities of elementary school children. The significant effect is because the brain jogging program focuses on several coordination activities that lead to mental processes related to abilities in the form of general recognition, which is mental and is marked by the representation of an object in a person's mental picture, whether in the form of symbols, responses, ideas or ideas, and values ​​or considerations.

A General Metal Ion Recognition Strategy to Mediate Dual-Atomic-Site Catalysts.

Heterogeneous dual-atomic-site catalysts (DACs) hold great potential for diverse applications. However, to date, the synthesis of DACs primarily relies on different atoms freely colliding on the support during synthesis, principally leading to low yields. Herein, we report a general metal ion recognition (MIR) strategy for constructing a series of DACs, including but not limited to Fe1Sn1, Fe1Co1, Fe1Ni1, Fe1Cu1, Fe1Mn1, Co1Ni1, Co1Cu1, Co2, and Cu2. This strategy is achieved by coupling target inorganometallic cations and anions as ion pairs, which are sequentially adsorbed onto a nitrogen-doped carbon substrate as the precursor. Taking the oxygen reduction reaction as an example, we demonstrated that the Fe1Sn1-DAC synthesized through this strategy delivers a record peak power density of 1.218 W cm-2 under 2.0 bar H2-O2 conditions and enhanced stability compared to the single-atom-site FeN4. Further study revealed that the superior performance arises from the synergistic effect of Fe1Sn1 dual vicinal sites, which effectively optimizes the adsorption of *OH and alleviates the troublesome Fenton-like reaction.

Cross-cultural comparison of the neural correlates of true and false memory retrieval

ABSTRACT Prior work has shown Americans have higher levels of memory specificity than East Asians. Neuroimaging studies have not investigated mechanisms that account for cultural differences at retrieval. In this study, we use fMRI to assess whether mnemonic discrimination, distinguishing novel from previously encountered stimuli, accounts for cultural differences in memory. Fifty-five American and 55 Taiwanese young adults completed an object recognition paradigm testing discrimination of old targets, similar lures and novel foils. Mnemonic discrimination was tested by comparing discrimination of similar lures from studied targets, and results showed the relationship between activity in right fusiform gyrus and behavioural discrimination between target and lure objects differed across cultural groups. Parametric modulation analyses of activity during lure correct rejections also indicated that groups differed in left superior parietal cortex response to variations in lure similarity. Additional analyses of old vs. new activity indicated that Americans and Taiwanese differ in the neural activity supporting general object recognition in the hippocampus, left inferior frontal gyrus and middle frontal gyrus. Results are juxtaposed against comparisons of the regions activated in common across the two cultures. Overall, Americans and Taiwanese differ in the extent to which they recruit visual processing and attention modulating brain regions.

Helicopter cockpit speech recognition method based on transfer learning and context biasing

Currently, Chinese speech recognition technology is generally designed for common domains, primarily focusing on accurate recognition of standard Mandarin Chinese in low-noise environments. However, helicopter cockpit speech presents unique challenges, characterized by high-noise environments, specific industry jargon, low contextual relevance, and a lack of publicly available datasets. To address these issues, this paper proposes a helicopter cockpit speech recognition method based on transfer learning and context biasing. By fine-tuning a general speech recognition model, we aim to better adapt it to the characteristics of speech in helicopter cockpits. This study explores noise reduction processing, context biasing, and speed perturbation in helicopter cockpit speech data. Combining pre-trained models with language models, we conduct transfer training to develop a specialized model for helicopter cockpit speech recognition. Finally, the effectiveness of this method is validated using a real dataset. Experimental results show that, on the helicopter speech dataset, this method reduces the word error rate from 72.69% to 12.58%. Furthermore, this approach provides an effective solution for small-sample speech recognition, enhancing model performance on limited datasets.

Cross-modal knowledge distillation for continuous sign language recognition

Continuous Sign Language Recognition (CSLR) is a task which converts a sign language video into a gloss sequence. The existing deep learning based sign language recognition methods usually rely on large-scale training data and rich supervised information. However, current sign language datasets are limited, and they are only annotated at sentence-level rather than frame-level. Inadequate supervision of sign language data poses a serious challenge for sign language recognition, which may result in insufficient training of sign language recognition models. To address above problems, we propose a cross-modal knowledge distillation method for continuous sign language recognition, which contains two teacher models and one student model. One of the teacher models is the Sign2Text dialogue teacher model, which takes a sign language video and a dialogue sentence as input and outputs the sign language recognition result. The other teacher model is the Text2Gloss translation teacher model, which targets to translate a text sentence into a gloss sequence. Both teacher models can provide information-rich soft labels to assist the training of the student model, which is a general sign language recognition model. We conduct extensive experiments on multiple commonly used sign language datasets, i.e., PHOENIX 2014T, CSL-Daily and QSL, the results show that the proposed cross-modal knowledge distillation method can effectively improve the sign language recognition accuracy by transferring multi-modal information from teacher models to the student model. Code is available at https://github.com/glq-1992/cross-modal-knowledge-distillation_new.

A ligand discovery toolbox for the WWE domain family of human E3 ligases

The WWE domain is a relatively under-researched domain found in twelve human proteins and characterized by a conserved tryptophan-tryptophan-glutamate (WWE) sequence motif. Six of these WWE domain-containing proteins also contain domains with E3 ubiquitin ligase activity. The general recognition of poly-ADP-ribosylated substrates by WWE domains suggests a potential avenue for development of Proteolysis-Targeting Chimeras (PROTACs). Here, we present novel crystal structures of the HUWE1, TRIP12, and DTX1 WWE domains in complex with PAR building blocks and their analogs, thus enabling a comprehensive analysis of the PAR binding site structural diversity. Furthermore, we introduce a versatile toolbox of biophysical and biochemical assays for the discovery and characterization of novel WWE domain binders, including fluorescence polarization-based PAR binding and displacement assays, 15N-NMR-based binding affinity assays and 19F-NMR-based competition assays. Through these assays, we have characterized the binding of monomeric iso-ADP-ribose (iso-ADPr) and its nucleotide analogs with the aforementioned WWE proteins. Finally, we have utilized the assay toolbox to screen a small molecule fragment library leading to the successful discovery of novel ligands targeting the HUWE1 WWE domain.

Sequence-specific targeting of intrinsically disordered protein regions.

A general approach to design proteins that bind tightly and specifically to intrinsically disordered regions (IDRs) of proteins and flexible peptides would have wide application in biological research, therapeutics, and diagnosis. However, the lack of defined structures and the high variability in sequence and conformational preferences has complicated such efforts. We sought to develop a method combining biophysical principles with deep learning to readily generate binders for any disordered sequence. Instead of assuming a fixed regular structure for the target, general recognition is achieved by threading the query sequence through diverse extended binding modes in hundreds of templates with varying pocket depths and spacings, followed by RFdiffusion refinement to optimize the binder-target fit. We tested the method by designing binders to 39 highly diverse unstructured targets. Experimental testing of ∼36 designs per target yielded binders with affinities better than 100 nM in 34 cases, and in the pM range in four cases. The co-crystal structure of a designed binder in complex with dynorphin A is closely consistent with the design model. All by all binding experiments for 20 designs binding diverse targets show they are highly specific for the intended targets, with no crosstalk even for the closely related dynorphin A and dynorphin B. Our approach thus could provide a general solution to the intrinsically disordered protein and peptide recognition problem.

Improving word reading skills of low‐skilled readers: An intervention combining a syllable‐based approach with digital game‐based features

AbstractBackgroundChildren with low reading skills are less frequently engaged in reading activities and therefore the likelihood of improving their reading skills decreases. Digital game‐based interventions have emerged as a promising tool for promoting reading development in children, particularly those with reading difficulties. As syllable‐based reading interventions are likely to increase word reading skills in low‐skilled readers, we developed a new reading intervention application that emphasizes syllable segmentation and integrates proven elements of digital game‐based learning. The intervention aimed to promote phonological recoding and consolidating orthographic representation of syllables.ObjectivesThe present study investigated the effects of the newly developed syllable‐based reading intervention application on general word recognition skills, phonological recoding processes, orthographic decoding processes and text‐level reading comprehension skills in German second graders.MethodsIn a quasi‐experimental design, children with low word recognition skills were randomly assigned to a treatment group (n = 66) or a wait‐list group (n = 66). General word recognition skills, phonological recoding processes, orthographic decoding processes and text‐level reading comprehension were measured with standardized German reading tests before and after the treatment group received the digital reading intervention for 20 sessions.ResultsResults indicated that the children in the treatment group showed significant improvement in general word recognition and in phonological recoding processes compared to equally low‐skilled untreated children in the wait‐list group. Orthographic decoding processes improved only in children with less severe impairments, whereas no significant improvements were found in text‐level reading comprehension.Take AwaysThe digital reading intervention is a promising approach for supporting word reading in low‐skilled reading second graders and can serve as an effective intervention tool for this target group.

From X-ray crystallographic structure to intrinsic thermodynamics of protein-ligand binding using carbonic anhydrase isozymes as a model system.

Carbonic anhydrase (CA) was among the first proteins whose X-ray crystal structure was solved to atomic resolution. CA proteins have essentially the same fold and similar active centers that differ in only several amino acids. Primary sulfonamides are well defined, strong and specific binders of CA. However, minor variations in chemical structure can significantly alter their binding properties. Over 1000 sulfonamides have been designed, synthesized and evaluated to understand the correlations between the structure and thermodynamics of their binding to the human CA isozyme family. Compound binding was determined by several binding assays: fluorescence-based thermal shift assay, stopped-flow enzyme activity inhibition assay, isothermal titration calorimetry and competition assay for enzyme expressed on cancer cell surfaces. All assays have advantages and limitations but are necessary for deeper characterization of these protein-ligand interactions. Here, the concept and importance of intrinsic binding thermodynamics is emphasized and the role of structure-thermodynamics correlations for the novel inhibitors of CA IX is discussed - an isozyme that is overexpressed in solid hypoxic tumors, and thus these inhibitors may serve as anticancer drugs. The abundant structural and thermodynamic data are assembled into the Protein-Ligand Binding Database to understand general protein-ligand recognition principles that could be used in drug discovery.

Collaborative intelligent decision systems for safe and reliable AI-assisted medical image diagnostics

The cost of diagnostic errors has been high in the developed world economics according to a number of recent studies and continues to rise. Up till now, a common process of performing image diagnostics for a growing number of conditions has been examination by a single human specialist (i.e., single-channel recognition and classification decision system). Such a system has natural limitations of unmitigated error that can be detected only much later in the treatment cycle, as well as resource intensity and poor ability to scale to the rising demand. At the same time Machine Intelligence (ML, AI) systems, specifically those including deep neural network and large visual domain models have made significant progress in the field of general image recognition, in many instances achieving the level of an average human and in a growing number of cases, a human specialist in the effectiveness of image recognition tasks. The objectives of the AI in Medicine (AIM) program were set to leverage the opportunities and advantages of the rapidly evolving Artificial Intelligence technology to achieve real and measurable gains in public healthcare, in quality, access, public confidence and cost efficiency. The proposal for a collaborative AI-human image diagnostics system falls directly into the scope of this program.

Task-Specific Rapid Auditory Perceptual Learning in Adult Cochlear Implant Recipients: What Could It Mean for Speech Recognition.

Speech recognition in cochlear implant (CI) recipients is quite variable, particularly in challenging listening conditions. Demographic, audiological, and cognitive factors explain some, but not all, of this variance. The literature suggests that rapid auditory perceptual learning explains unique variance in speech recognition in listeners with normal hearing and those with hearing loss. The present study focuses on the early adaptation phase of task-specific rapid auditory perceptual learning. It investigates whether adult CI recipients exhibit this learning and, if so, whether it accounts for portions of the variance in their recognition of fast speech and speech in noise. Thirty-six adult CI recipients (ages = 35 to 77, M = 55) completed a battery of general speech recognition tests (sentences in speech-shaped noise, four-talker babble noise, and natural-fast speech), cognitive measures (vocabulary, working memory, attention, and verbal processing speed), and a rapid auditory perceptual learning task with time-compressed speech. Accuracy in the general speech recognition tasks was modeled with a series of generalized mixed models that accounted for demographic, audiological, and cognitive factors before accounting for the contribution of task-specific rapid auditory perceptual learning of time-compressed speech. Most CI recipients exhibited early task-specific rapid auditory perceptual learning of time-compressed speech within the course of the first 20 sentences. This early task-specific rapid auditory perceptual learning had unique contribution to the recognition of natural-fast speech in quiet and speech in noise, although the contribution to natural-fast speech may reflect the rapid learning that occurred in this task. When accounting for demographic and cognitive characteristics, an increase of 1 SD in the early task-specific rapid auditory perceptual learning rate was associated with ~52% increase in the odds of correctly recognizing natural-fast speech in quiet, and ~19% to 28% in the odds of correctly recognizing the different types of speech in noise. Age, vocabulary, attention, and verbal processing speed also had unique contributions to general speech recognition. However, their contribution varied between the different general speech recognition tests. Consistent with previous findings in other populations, in CI recipients, early task-specific rapid auditory perceptual, learning also accounts for some of the individual differences in the recognition of speech in noise and natural-fast speech in quiet. Thus, across populations, the early rapid adaptation phase of task-specific rapid auditory perceptual learning might serve as a skill that supports speech recognition in various adverse conditions. In CI users, the ability to rapidly adapt to ongoing acoustical challenges may be one of the factors associated with good CI outcomes. Overall, CI recipients with higher cognitive resources and faster rapid learning rates had better speech recognition.

Gait-Based Human Activity Recognition Using Efficient Sensor Fusion and Deep Learning Approach

Human activity recognition is an important area of computer vision research. Its applications include surveillance systems, patient monitoring systems, and a variety of systems that involve interactions between persons and electronic devices such as human-computer interfaces. Most of these applications require an automated recognition of high-level activities, composed of multiple simple (or atomic) actions of persons. A novel feature selection approach is then proposed in order to select a subset of discriminant features, construct an online activity recognizer with better generalization ability, and reduce the smartphone power consumption. Experimental results on a publicly available data set show that the fusion of both accelerometer and gyroscope data contributes to obtain better recognition performance than that of using single source data, and that the proposed feature selector outperforms three other comparative approaches in terms of four performance measures. Such activity profiling systems are dependent on classification algorithms which can effectively interpret body-worn sensor data and identify different activities. the key research challenges that human activity recognition shares with general pattern recognition and identify those challenges that are specific to human activity recognition. The aim of paper is to explore real life applications like contactless employee recognition system using gait analysis which uses sensor data as base to identify employees based on their gait movement. This requires understanding the dimensions of sensor data and its application exploring other potential real-life applications and optimizing the methodology are also one of the core objectives.

Energy democracy, public participation, and support for local energy system change in Canada

In the face of climate change and associated energy system change, there is a growing literature and more general recognition of the ‘four Ds’ (decarbonization, decentralization, digitalization, and democratization). Yet there has been very little quantitative work that analyzes public perceptions of these changes. Utilizing data from a Canada-wide, nationally representative survey (n = 941), this study conducted provincial and regional assessments to spatially explore the public's views of moves toward innovative local energy system change through the development of what we call Local Smart Grids (LSGs). Through descriptive statistics and t-tests, we sought to answer three main questions: i) To what extent does the public support energy democracy via new local energy systems? ii) What does the public desire in terms of participation? and iii) What motivates the public to participate? We find overall support for energy democracy across Canada, yet varied support among provinces and regions. Canadians seem to want to participate in moves toward energy democracy, although we found a strong preference for more passive participatory actions. Additionally, support and a desire to participate is predominantly motivated by environmental factors, including combating climate change, with community and social motivations playing a secondary role, followed by financial motivations. These findings, some of the first of their kind in the realm of energy democracy in Canada, provide useful insights relevant to scholars, policymakers, and practitioners working on LSG implementation as well as others with an interest in socio-technical innovation and energy system change.