Background Cerebellar ataxia is characterized by abnormalities in gait, speech, ocular movement, and coordination, making accurate detection challenging. Purpose This study develops a lightweight multimodal Deep Learning (DL)-based framework for cerebellar ataxia detection. Research Design The proposed approach integrates voice, gaze, and body pose features from independent public datasets and performs class-level multimodal feature fusion to capture complementary motor and behavioral cues. Fine-grained features such as Mel Frequency Cepstral Coefficients (MFCCs) and vocal perturbation measures, gaze fixation dynamics, and spatiotemporal body pose features are extracted using Python-compatible tools. Each modality is processed with a specific Multilayer Perceptron (MLP)-based encoder to produce small embeddings, which are fused through feature concatenation and processed by a fully connected MLP classifier. To ensure stable convergence and robust generalization capability on limited and noisy clinical data, a novel hybrid optimizer, Adaptive Sharp-Lookahead Lite, is used. Results Experimental results demonstrate that the proposed framework achieves an accuracy of 99.56% in distinguishing ataxia from normal cases under the adopted experimental setting. Conclusions The findings demonstrate the potential of the framework as a lightweight AI-based screening approach for resource-constrained settings.
Parkinson’s Disease (PD) is a common chronic neurological disorder leading to increased fall risk and movement difficulty. Individuals with PD experience rigidity and bradykinesia limiting movement speed and quality that may compromise motor strategies with normal function. The goal of this research is to compare the Timed Supine to Stand Test (TSS) speed, lower extremity range of motion (ROM) and strategy type (2-3 points of contact versus 4 points of contact) between a group of older adults with PD and those without PD (WPD). Data were collected using the Noraxon® Ultium Motion Analysis System via inertial measurement units (IMU), ground reaction force (GRF) with insole pressure sensors, and video. Each participant performed one repetition of the TSS. Chi Square analysis revealed individuals with PD preferred the 4-point contact method. MANOVA revealed no significant difference between lower extremity range of motion or GRF between groups but did demonstrate a significant difference in time to stand. Controlling for age via MANCOVA revealed no difference in range of motion, GRF, or time to perform the TSS. Speed with the TSS appeared to be a function of age rather than PD. Individuals with PD prefer to use 4 points of contact while transferring from the ground. Healthcare providers should tailor transfer recommendations for individuals with PD and older adults to include four points of contact.
This exploratory study investigated whether providing autonomy support through choice over externally focused attentional cues would influence countermovement jump (CMJ) performance, as predicted by the OPTIMAL theory. Sixty young adults performed four CMJs under either a choice condition, in which participants selected one of four external focus instructions before each jump, or a yoked condition without choice. Although participants in the choice group reported significantly greater perceived autonomy over instruction choice, autonomy support did not improve jump height. Differences in jump height were observed between external focus instructions, suggesting that the semantic and linguistic properties of instructional cues may influence performance. However, manipulation check data indicated that participants did not consistently reproduce the specific linguistic features of the cues, instead frequently omitting or substituting elements such as action words and spatial references. These findings suggest that performance differences are unlikely to reflect the isolated effects of specific linguistic components, but rather how cues are interpreted and integrated by performers. No interaction between autonomy support and external focus was observed. Overall, autonomy support enhanced perceived autonomy but did not improve immediate performance, and the effectiveness of instructional cues may depend on how performers represent task goals. These findings should be interpreted as exploratory and hypothesis-generating.
In a world filled with an overwhelming amount of visual information, the clean and distinctive visual style of minimalist photography stands out. However, empirical research on how minimalist style affects visual cognition and psychological responses remains limited. The present study investigated the effects of photographic style (minimalist versus complex) on viewers’ visual behavior, emotional responses, and brainwave state by conducting quantitative psychological experiments. Thirty participants viewed photographs in one of the two styles. Eye-tracking, consumer-grade electroencephalography (EEG), and subjective psychological assessment data were collected, enabling comprehensive evaluation of how the participants looked at, responded to, and emotionally engaged with the images. At the level of visual behavior, minimalism elicited significantly reduced number of fixations and saccades, but the duration of a single fixation is significantly longer, and the heatmap hotspots are highly concentrated, presenting a focused processing pattern of fewer but longer gazes. On a psychological level, minimalism evoked significantly less feeling of complexity and greater relaxation, although there was no significant difference in the aesthetics score between the two styles. In terms of brainwave state, viewing minimalist images resulted in significantly higher attention eSense levels, while the meditation eSense level did not show a significant difference. The results of this study therefore show that minimalist composition may influence the visual search pattern to be more focused, which is compatible with the tendency of simplified organization predicted by the principle of simplification. This study not only deepens the theoretical understanding of the psychological mechanisms of minimalist aesthetics, but also provides practical reference for visual communication and image creation of minimalist composition serving as an effective strategy for guiding the eyes toward the core subject.
Action possibilities may emerge or disappear over time due to interactions among multiple moving objects. Which action possibility and how it is actualized reflect the interplay among environmental constraints and individual capabilities and preferences. The present study aimed to identify individual and task-specific factors that predict target selection in an interception task and characterize the solutions executed by individuals to realize the chosen action possibility. We created a video game simulating team sports such as American Football, in which the participant controlled the thrower attempting to intercept one of the two moving targets. Near each target, there was a defender that could intercept the pass. In addition, a third defender moved from the endzone toward the thrower. We manipulated target speed and defender distance to alter both temporal and spatial constraints. Our results indicated that target selection was influenced mainly by the difference between the defenders’ relative gains. Throughout practice, participants also adapted all three execution variables that define the throwing outcome, with a relevant effect of target speed in scaling the values of each execution variable. This study demonstrated that during a virtual interception task with coexisting action possibilities, individuals select which target to intercept based on a high-order, relational variable and calibrate their movement according to the selected target speed.
