An Exploratory-Descriptive Study on the Impact of COVID-19 on Teaching and Learning: The Experiences of Student Nurses in the Rural-Based Historically Disadvantaged University of South Africa.

Covid-19 has disrupted normal working conditions as people were not allowed to assemble in one place. There is a limit that is placed on the number of people congregating in public areas, and these measures also affect the education system worldwide. The purpose of the study was to explore nursing students' experiences in a historically disadvantaged rural-based university on the impact of Covid-19 on teaching and learning. The study employed an exploratory-descriptive qualitative design among nursing students who were purposively sampled to participate in the study. A qualitative self-administered open-ended online google form was used to collect data. Thematic analysis was employed for this study. All ethical measures were respected during this study. Interviews were conducted with 68 participants, including 12 undergraduate second-year students, 7 third-year students, and 49 fourth-year students. A total of 51 females and 17 males participated in this study. The study yielded several themes, including participants' expression of their experiences related to teaching and learning during the national lockdown, participants' views on the impact of COVID-19 on teaching and learning/research, and Participants suggested sustainable strategies to promote teaching and learning during the national lockdown. In conclusion, the role of preceptors in all clinical areas should be strengthened to improve clinical teaching and learning. The researchers recommend strengthening collaboration among university lecturers for sharing ideas and finding innovative solutions appropriate for handling any pandemic that threatens teaching and learning processes.

Exploring nursing students' need for social presence and its relevance to their learning preferences.

AIM: To explore nursing students' need for social presence in online learning, looking at its relevance to the adopted sensory modality learning styles. DESIGN: A qualitative descriptive design. METHODS: Two semi-structured online focus groups were held with five second-year and seven third-year undergraduate nursing students, purposively recruited from the Malta College of Arts, Science and Technology. Using a structured guide based on the Social Presence Model, participants were asked about their perceived need for social presence (a construct used to understand online interactions), and its relevance to their learning preferences using the VARK (Visual, Aural/Auditory, Read/write and Kinesthetic) learning styles. RESULTS: Despite varying learning preferences, all participants remarked on the need for social presence. Social presence was required for their perceived learning and for actively participating in online lectures. Several participants expressed the need for social presence for a collaborative constructivist learning experience, drawing on their diverse learning styles for a better learning experience.

BNAS: Efficient Neural Architecture Search Using Broad Scalable Architecture.

Efficient neural architecture search (ENAS) achieves novel efficiency for learning architecture with high-performance via parameter sharing and reinforcement learning (RL). In the phase of architecture search, ENAS employs deep scalable architecture as search space whose training process consumes most of the search cost. Moreover, time-consuming model training is proportional to the depth of deep scalable architecture. Through experiments using ENAS on CIFAR-10, we find that layer reduction of scalable architecture is an effective way to accelerate the search process of ENAS but suffers from a prohibitive performance drop in the phase of architecture estimation. In this article, we propose a broad neural architecture search (BNAS) where we elaborately design broad scalable architecture dubbed broad convolutional neural network (BCNN) to solve the above issue. On the one hand, the proposed broad scalable architecture has fast training speed due to its shallow topology. Moreover, we also adopt RL and parameter sharing used in ENAS as the optimization strategy of BNAS. Hence, the proposed approach can achieve higher search efficiency. On the other hand, the broad scalable architecture extracts multi-scale features and enhancement representations, and feeds them into global average pooling (GAP) layer to yield more reasonable and comprehensive representations. Therefore, the performance of broad scalable architecture can be promised. In particular, we also develop two variants for BNAS that modify the topology of BCNN. In order to verify the effectiveness of BNAS, several experiments are performed and experimental results show that 1) BNAS delivers 0.19 days which is 2.37× less expensive than ENAS who ranks the best in RL-based NAS approaches; 2) compared with small-size (0.5 million parameters) and medium-size (1.1 million parameters) models, the architecture learned by BNAS obtains state-of-the-art performance (3.58% and 3.24% test error) on CIFAR-10; and 3) the learned architecture achieves 25.3% top-1 error on ImageNet just using 3.9 million parameters.

Marcos teóricos para comprender y explicar los procesos de mentoría en investigación / Theoretical frameworks to understand and explain research mentoring processes

En este artículo especial, el tercero de una serie publicada en EVIDENCIA, el autor resume cuatro marcos teóricos adicionales que ayudan a comprender los procesos de la mentoría en investigación: la teoría ecológica de los sistemas, la teoría del intercambio social, la teoría de las redes sociales y la pedagogía de la formación doctoral. Para finalizar, integra los contenidos realizando una comparación de los todos los marcos teóricos comentados en esta serie, en términos de sus diferencias y sus puntos de intersección. (AU)

In this special issue, the third in a series published in EVIDENCIA, the author summarises four additional theoretical frameworks that help to understand the processes of mentoring in research: the ecological systems theory, the social exchange theory, the social network theory and the doctoral training pedagogy. Finally, a comparison of all the theoretical frameworks discussed in this series is integrated in terms of their differences and points of intersection. (AU)

Revelations of service-learning project: Multiple perspectives of college students' reflection.

This study explored the reflections of college students at different stages of their service provided to preschoolers and proposed recommendations on service-learning curricula according to the research findings. Thirty-six college juniors enrolled in an academic service-learning course were asked to complete a service-learning project, to undertake service activities in the form of eight storytelling sessions at preschools. This storytelling plan was 1.5-hour-long each, twice per month, for 16-weeks. Qualitative case study approach was employed in this study. Data consisted of documentation of the participants' reflections, focus group interviews, and research logs. The thematic analysis was employed to analyze data and data were analyzed using the constant comparative technique. The study revealed that the contents of participants' reflections took on a qualitative change as their service experience accumulated. Before their service experience, their reflections focused on personal expectations. This shifted professional learning and personal growth during the service experience. After their service experiences, their reflections were extended to include social concern. Also, the participants were inspired to actively acquire professional knowledge from their service experiences. Various reflection activities triggered different levels and functions of reflection by the participants. Writing activities caused the participants to focus on personal reflection, providing the opportunity for them to examine and adjust their ideas; group discussion activities allowed the participants to focus on group dialogue, with which they achieved learning and gained identity. Finally, students experienced emotional highs and lows during their experience of service, describing tension and fear initially, then joy or disquietude subsequently. Recommendations based on the research results were provided to facilitate planning of the service-learning curriculum by college educators.

Developing Global Health Diplomacy-related Skills Using a COVID-19-like Epidemic Simulation as a Learning Strategy.

Public health and global health practitioners need to develop global health diplomacy (GHD) skills to efficiently work within complex global health scenarios, such as the current coronavirus disease (COVID-19) pandemic. Problem-based learning was used as a framework to create a scenario-based activity designed to develop GHD-related skills. The application and effectiveness of this scenario-based activity to develop GHD-related skills were assessed. A mixed-methods approach involving a self-administered survey and one focus group discussion was used. The survey collected baseline participant characteristics as well as understanding and improvements in GHD-related skills using a 5-point Likert scale. The focus group was audio-recorded and thematically analyzed using both inductive and deductive codes. Data integration was achieved by connecting and weaving. Method and investigator triangulation techniques were used. Participants self-reported significantly better postscenario-based activity responses when asked about their understanding of diplomacy, negotiation, communication, and how to address public health emergencies (P < 0.01, Wilcoxon signed rank test). Most participants either agreed or strongly agreed that their GHD-related skills improved with participation in the scenario-based activity (diplomacy = 55.6%; negotiation = 66.5%; communication = 72.2%; addressing public health emergencies = 72.1%). Overall, qualitative data were consistent with results obtained using quantitative methods. The scenario-based activity was effective for improving the self-reported understanding of GHD-related skills. The scenario-based activity was also effective for developing the selected GHD-related skills (as self-reported). This scenario-based activity is likely to reduce cognitive load and avoid participant overload, thereby facilitating learning. Further research is required to elucidate its long-term impact on skills development.

Teaching anatomy under COVID-19 conditions at German universities: recommendations of the teaching commission of the anatomical society.

BACKGROUND: In this viewpoint representatives of the Teaching Commission of the Anatomical Society summarize their teaching experiences gained during the COVID-19 pandemic in the summer term of 2020 and derive first recommendations concerning face-to-face and remote teaching of anatomy for the future. METHODS: Representatives of the Teaching Commission of the Anatomical Society met virtually, exchanged experiences and summarized them in writing and answered a short questionnaire. RESULTS: The required transition to remote learning during summer term of 2020 was possible, but revealed technical shortcomings and major deficits concerning practical hands-on teaching. CONCLUSION: The Teaching Commission of the Anatomical Society recommends that universities should follow the idea of as much face-to-face teaching as possible and as much online teaching as necessary for future terms.

A Common Task Structure Links Together the Fate of Different Types of Memories.

Our memories frequently have features in common. For example, a learned sequence of words or actions can follow a common rule, which determines their serial order, despite being composed of very different events [1, 2]. This common abstract structure might link the fates of memories together. We tested this idea by creating different types of memory task: a sequence of words or actions that either did or did not have a common structure. Participants learned one of these memory tasks and then they learned another type of memory task 6 h later, either with or without the same structure. We then tested the newly formed memory's susceptibility to interference. We found that the newly formed memory was protected from interference when it shared a common structure with the earlier memory. Specifically, learning a sequence of words protected a subsequent sequence of actions learned hours later from interference, and conversely, learning a sequence of actions protected a subsequent sequence of words learned hours later from interference provided the sequences shared a common structure. Yet this protection of the newly formed memory came at a cost. The earlier memory had disrupted recall when it had the same rather than a different structure to the newly formed and protected memory. Thus, a common structure can determine what is retained (i.e., protected) and what is modified (i.e., disrupted). Our work reveals that a shared common structure links the fate of otherwise different types of memories together and identifies a novel mechanism for memory modification.

Psychometric properties of the Adelaide Diagnostic Learning Inventory-Brief (ADLIB).

OBJECTIVE: There has been increased attention in recent years to mental health, quality of life, stress and academic performance among university students, and the possible influence of learning styles. Brief reliable questionnaires are useful in large-scale multivariate research designs, such as the largely survey-based research on well-being and academic performance of university students. The objective of this study was to examine the psychometric properties of a briefer version of the 39-item Adelaide Diagnostic Learning Inventory. RESULTS: In two survey samples-medical and physiotherapy students-a 21-item version Adelaide Diagnostic Learning Inventory-Brief (ADLIB) was shown to have the same component structure as the parent instrument, and the component structure of the brief instrument was found to generalise across students of medicine and physiotherapy. Subscale reliability estimations were in the order of magnitude of the parent instrument. Subscale inter-correlations, inter-component congruence coefficients, and correlations between ADLIB subscale scores and several external measures provide support support for the construct and criterion validity of the instrument.

Musculoskeletal anatomy by self-examination: A learner-centered method for students and practitioners of musculoskeletal medicine.

BACKGROUND: The authors describe a series of learner-centered exercises, highlighting a technique in which the musculoskeletal anatomy is explored and learned through self-examination, with the examiner required to identify designated structures in both the static and dynamic state. METHODS: The technique of musculoskeletal anatomy through self-examination consists of applying knowledge of the surface anatomy of a region as it exists in the static state, to the analysis and understanding of changes that occur with movement and function of that body part. The sensory input of the examined part may contribute to the overall perception of the exercise. RESULTS: Three tables provide details that allow the reader to understand and perform the exercises describing the anatomic part explored, the physical maneuver required, the expected anatomic finding(s), and their clinical relevance. CONCLUSIONS: The authors believe that musculoskeletal self-examination provides an engaging learner-centered pedagogy that may complement that which is learned in peer or model examination. The lack of cost, the absence of intimacy barriers, and the opportunity to extend the method to further areas and functions are additional benefits of musculoskeletal self-examination as a learner-centered, self-study methodology.

Towards a new taxonomy of primate vocal production learning.

The extent to which vocal learning can be found in nonhuman primates is key to reconstructing the evolution of speech. Regarding the adjustment of vocal output in relation to auditory experience (vocal production learning in the narrow sense), effects on the ontogenetic trajectory of vocal development as well as adjustment to group-specific call features have been found. Yet, a comparison of the vocalizations of different primate genera revealed striking similarities in the structure of calls and repertoires in different species of the same genus, indicating that the structure of nonhuman primate vocalizations is highly conserved. Thus, modifications in relation to experience only appear to be possible within relatively tight species-specific constraints. By contrast, comprehension learning may be extremely rapid and open-ended. In conjunction, these findings corroborate the idea of an ancestral independence of vocal production and auditory comprehension learning. To overcome the futile debate about whether or not vocal production learning can be found in nonhuman primates, we suggest putting the focus on the different mechanisms that may mediate the adjustment of vocal output in response to experience; these mechanisms may include auditory facilitation and learning from success. This article is part of the theme issue 'What can animal communication teach us about human language?'

A taxonomy for vocal learning.

Humans and songbirds learn to sing or speak by listening to acoustic models, forming auditory templates, and then learning to produce vocalizations that match the templates. These taxa have evolved specialized telencephalic pathways to accomplish this complex form of vocal learning, which has been reported for very few other taxa. By contrast, the acoustic structure of most animal vocalizations is produced by species-specific vocal motor programmes in the brainstem that do not require auditory feedback. However, many mammals and birds can learn to fine-tune the acoustic features of inherited vocal motor patterns based upon listening to conspecifics or noise. These limited forms of vocal learning range from rapid alteration based on real-time auditory feedback to long-term changes of vocal repertoire and they may involve different mechanisms than complex vocal learning. Limited vocal learning can involve the brainstem, mid-brain and/or telencephalic networks. Understanding complex vocal learning, which underpins human speech, requires careful analysis of which species are capable of which forms of vocal learning. Selecting multiple animal models for comparing the neural pathways that generate these different forms of learning will provide a richer view of the evolution of complex vocal learning and the neural mechanisms that make it possible. This article is part of the theme issue 'What can animal communication teach us about human language?'

Categorias freireanas no ensino de graduação em enfermagem: revisão integrativa da literatura / Freireanas categories in nursing undergraduate education: integrative literature review / Categorías Freireanas en enfermería educación universitaria: revisión de la literatura integrativa

Objetivo: Identificar as principais publicações relacionadas às categorias Freireanas no ensino de graduação em enfermagem. Método: Revisão Integrativa de literatura a partir da busca nas bases Literatura LatinoAmericana e do Caribe em Ciências da Saúde, Sistema Online de Busca e Análise de Literatura Médica, Base de Dados de Enfermagem. Obteve-se 482 estudos, destes apenas 13 atendiam aos critérios de inclusão. Resultados: As categorias emergentes foram: diálogo e autonomia; tomada de consciência com vistas a formação de sujeitos críticos, reflexivos e participantes; metodologia da problematização para uma educação humanizante e um cuidar humanizado. Conclusão: Conclui-se que a incorporação das categorias Freireanas no ensino de enfermagem é fundamental para um ensino com travessias dialógicas. Tal incorporação tece uma educação humanizante, caminho para o cuidado humanizado do discente/futuro profissional

Objective: The study's purpose has been to identify the main publications relating to the use of Freirean categories in nursing undergraduate education. Methods: This integrative literature review was performed by searching publications in the following databases: Literatura LatinoAmericana e do Caribe em Ciências da Saúde (LILACS) [Latin American and Caribbean Literature in Health Sciences], Medical Literature Analysis and Retrieval System (MEDLINE), and Base de Dados de Enfermagem (BDENF) [Nursing Database]. A total of 482 studies were found, of which only 13 met the inclusion criteria. Results: The following categories were identified: "Dialogue and Autonomy"; "Raising awareness with a view to the training of people focused on the development of critical, reflective and participatory skills"; and "Problematization methodology as a form of humanizing education for a humanized care". Conclusion: It is concluded that the incorporation of Freirean categories into nursing education is fundamental for a dialogic education. Such incorporation leads to humanizing education, making it possible for students/future professionals to deliver humanized care

Objetivo: identificar las principales publicaciones relacionadas con las categorías Freireanas en la docencia de licenciatura en enfermería. Método: revisión Integrativa de la literatura a partir de la búsqueda en las bases de la literatura latinoamericana y caribeña en Ciencias de la salud, sistema online de búsqueda y análisis de la literatura médica, base de datos de enfermería. Se obtuvieron 482 estudios, de estos sólo 13 cumplieron los criterios de inclusión. Resultados: las categorías emergentes fueron: diálogo y autonomía; Sensibilización con vistas a la formación de sujetos críticos, reflexivos y participantes; Metodología de cuestionamiento para una educación humanizadora y un cuidado humanizado. Conclusión: se concluye que la incorporación de las categorías Freireanas en la enseñanza de enfermería es esencial para una enseñanza con cruces dialogales. Esta incorporación teje una educación humanizadora, el camino hacia el cuidado humanizado del estudiante/futuro profesional

Retrospective analysis of prevalent anatomy spotter's examination: an educational audit.

PURPOSE: The spotter's (objectively structured practical examination) is an assessment tool which is widely used to test the practical knowledge of anatomy extensively. In Indian context it is used as an inclusive model in the gross anatomy practical examination and the marks allotted to it varies. The traditional spotter examination often has been blamed for only incorporating the initial levels of revised Bloom's taxonomy. This study retrospectively analysed the pre-professional spotter's examination score and tested its efficacy in terms of reliability, internal consistency, validity, educational impact, and resource intensiveness. METHODS: The summative data of student's score on four different days of unrepeated spotter's examination and final theory examination score was collected and tabulated. These four group of students acted as independent cohorts. The difficulty index (DI), point biserial correlation (PBC), Cronbach α (CA) and descriptive statistics of each cohort were calculated. Revised bloom taxonomy rating was applied to spotter's. RESULTS: We found heterogenous distribution of spotter's in each cohort according to DI. The PBCs and CA of each cohort were acceptable. The majority of spotter's tested the cognitive and comprehension domain of revised bloom's taxonomy. There was nonsignificant difference between mean scores of cohorts but we found low positive significant correlation between theory and spotter's score. CONCLUSION: We concluded that the construct of spotter's was reliable, internally consistent, had fair validity, variable educational impact, and sustainable resource intensiveness. We propose urgent redesigning of spotter's to include higher level of taxonomy to comply with emerging curricular changes.

Confidence resets reveal hierarchical adaptive learning in humans.

Hierarchical processing is pervasive in the brain, but its computational significance for learning under uncertainty is disputed. On the one hand, hierarchical models provide an optimal framework and are becoming increasingly popular to study cognition. On the other hand, non-hierarchical (flat) models remain influential and can learn efficiently, even in uncertain and changing environments. Here, we show that previously proposed hallmarks of hierarchical learning, which relied on reports of learned quantities or choices in simple experiments, are insufficient to categorically distinguish hierarchical from flat models. Instead, we present a novel test which leverages a more complex task, whose hierarchical structure allows generalization between different statistics tracked in parallel. We use reports of confidence to quantitatively and qualitatively arbitrate between the two accounts of learning. Our results support the hierarchical learning framework, and demonstrate how confidence can be a useful metric in learning theory.

Introducción a la mentoría en investigación y principales marcos teóricos para comprender y explicar sus procesos / Introduction to mentoring in research and main theoretical frameworks to understand and explain their processes

En este artículo, los autores explican el origen y el uso actual del término mentoría y describen algunos marcos teóricosque ayudan a comprender los procesos y la repercusión de la mentoría en investigación: el del aprendizaje cognitivo, eldel aprendizaje no formal, el del aprendizaje sociocultural en el contexto de comunidades de práctica, el de la mentoríacomo una forma de acumulación de capital social, el de la mentoría como un medio para el desarrollo de la identidadcomo científico, y las miradas desde la teoría social y cognitiva de la carrera.(AU)

In this article, the authors explain the origin and the current use of the term mentoring and describe some theoreticalframeworks that help to understand the processes and impact of mentoring in research: cognitive learning, non-formallearning, sociocultural learning in the context of communities of practice, mentoring as a form of social capital accumulation,mentoring as a way to develope the identity as a scientist, and the views from the social and cognitive theory of the career.(AU)

Cognitive style assessment among medical students: A step towards achieving meta-cognitive integration in medical education.

Background: Knowledge of cognition and its regulation are important meta-cognitive activities, which are crucial for enhancement of learning. Their explicit teaching is meaningful and necessary yet seldom undertaken systematically in medical education programmes. Methods: We aimed to identify the cognitive styles using the Alert Scale of Cognitive Style among our undergraduate students. Students were also sensitized about different cognitive styles, their implications in strategic learning and the importance of meta-cognitive approach in education. Feedback from students was obtained to understand their awareness, perspectives and relevance of meta-cognitive concepts. Results: The intervention enhanced awareness of students about their own cognitive style and its implications to learning processes. The middle brain cognitive style was the most common (51.2%), followed by the right and the left brain cognitive styles (29.5% and 19.4%, respectively). A significant shift from the left towards the middle or the right cognitive style was observed in clinical years. No significant association was observed between a cognitive style and various variables such as age, gender and handedness. Conclusion: Incorporation of meta-cognitive learning practices in medical education offers a basis for enhancing classroom teaching, thereby making it learner-centric. The study helped students in identifying the way they process information and in identifying their preferred methods of assimilating knowledge. Identification of cognitive diversity is a primary pedagogic act for improving competence in learning. Meta-cognitive skills can be harnessed to bring about consonance of the left, right and middle brain cognitive styles to achieve better learning outcomes.

MMP-9 inhibitors impair learning in spontaneously hypertensive rats.

Vascular cognitive impairment dementia (VCID) is a major cause of cognitive loss in the elderly. Matrix metalloproteinases (MMPs) are a family of proteases involved in remodeling the extracellular matrix in development, injury and repair. Blood-brain barrier (BBB) disruption due to inflammation mediated by MMPs is a mechanism of white matter injury. Currently there are no treatments besides the control of vascular risk factors. We tested two MMP-9 inhibitors that improved outcome in acute stroke: DP-460 and SB-3CT. We hypothesized that these inhibitors would have a beneficial effect in chronic stroke by reducing edema in white matter and improving behavioral outcomes. Spontaneously hypertensive stroke-prone rats (SHRSPs) with unilateral carotid artery occlusion (UCAO) fed a Japanese Permissive Diet (JPD) were used as a model of VCID. JPD was begun in the 12th week of life. Rats were treated with DP-460 (500 mg/kg) for 4 weeks, or SB-3CT (10 mg/kg) for 8 weeks, beginning at the UCAO/JPD onset. Rats treated with a dextrose or DMSO solution served as vehicle controls. Naïve SHRSPs on a standard diet served as sham control. Magnetic resonance imaging (MRI) analyses of the corpus callosum, external capsule, hippocampus and Morris water maze behavioral tests were conducted. We found an increase in body weight (p = 0.004) and blood pressure (p = 0.007) at 15 weeks with the DP-460 drug. SB-3CT increased body weight at 14 weeks (p = 0.015) and had significant but variable effects on blood pressure. Neither drug affected imaging parameters. Behavioral studies showed an impaired ability to learn with DP-460 (p<0.001) and no effect on learning with SB-3CT. Unchanged MMP-9 levels were detected in DP-460-treated rats via gel zymography. Our findings suggest that MMPs are not major factors in white matter damage in the SHRSP model of VCID and that drugs that are relatively selective for MMP-9 can interfere with learning.

An automated approach to the quantitation of vocalizations and vocal learning in the songbird.

Studies of learning mechanisms critically depend on the ability to accurately assess learning outcomes. This assessment can be impeded by the often complex, multidimensional nature of behavior. We present a novel, automated approach to evaluating imitative learning. Conceptually, our approach estimates how much of the content present in a reference behavior is absent from the learned behavior. We validate our approach through examination of songbird vocalizations, complex learned behaviors the study of which has provided many insights into sensory-motor learning in general and vocal learning in particular. Historically, learning has been holistically assessed by human inspection or through comparison of specific song features selected by experimenters (e.g. fundamental frequency, spectral entropy). In contrast, our approach uses statistical models to broadly capture the structure of each song, and then estimates the divergence between the two models. We show that our measure of song learning (the Kullback-Leibler divergence between two distributions corresponding to specific song data, or, Song DKL) is well correlated with human evaluation of song learning. We then expand the analysis beyond learning and show that Song DKL also detects the typical song deterioration that occurs following deafening. Finally, we illustrate how this measure can be extended to quantify differences in other complex behaviors such as human speech and handwriting. This approach potentially provides a framework for assessing learning across a broad range of behaviors like song that can be described as a set of discrete and repeated motor actions.

Sparse feature learning for multi-class Parkinson's disease classification.

This paper solves the multi-class classification problem for Parkinson's disease (PD) analysis by a sparse discriminative feature selection framework. Specifically, we propose a framework to construct a least square regression model based on the Fisher's linear discriminant analysis (LDA) and locality preserving projection (LPP). This framework utilizes the global and local information to select the most relevant and discriminative features to boost classification performance. Differing in previous methods for binary classification, we perform a multi-class classification for PD diagnosis. Our proposed method is evaluated on the public available Parkinson's progression markers initiative (PPMI) datasets. Extensive experimental results indicate that our proposed method identifies highly suitable regions for further PD analysis and diagnosis and outperforms state-of-the-art methods.