CNN-Based Terrain Classification with Moisture Content Using RGB-IR Images

Unmanned mobile robots in rough terrains are a key technology for achieving smart agriculture and smart construction. The mobility performance of robots highly depends on the moisture content of soil, and past few studies have focused on terrain classification using moisture content. In this study, we demonstrate a convolutional neural network-based terrain classification method using RGB-infrared (IR) images. The method first classifies soil types and then categorizes the moisture content of the terrain. A three-step image preprocessing for RGB-IR images is also integrated into the method that is applicable to an actual environment. An experimental study of the terrain classification confirmed that the proposed method achieved an accuracy of more than 99% in classifying the soil type. Furthermore, the classification accuracy of the moisture content was approximately 69% for pumice and 100% for dark soil. The proposed method can be useful for different scenarios, such as small-scale agriculture with mobile robots, smart agriculture for monitoring the moisture content, and earthworks in small areas.

Factors Associated With Older Adults’ In-Hospital Mobility: A Comparison Between Israel and Denmark

Low levels of in-hospital mobility and excessive bed rest are widely described across the globe as a major risk factor for hospital associated disabilities. Different predictors of in-hospital and post-discharge mobility limitations have been proposed across studies, including age, admission diagnosis, physical performance, cognitive impairment, performance of activities of daily living, and length of stay. However, it is unknown whether similar risk factors across countries are associated with in-hospital mobility given different mobility measurement methods, variations in measurement of predictors and differences in populations studied. In the current study, we investigated the relationship between in-hospital mobility and a set of similar risk factors in functionally independent older adults (65+) hospitalized in acute care settings in Israel (N=206) and Denmark (N=113). In Israel, mobility was measured via ActiGraph and in Denmark by ActivPal for up to seven hospital days. Parallel analysis of covariance (ANCOVA) in each sample showed that community-mobility before hospitalization, mobility performance at admission and length of stay were associated with in-hospital mobility in both countries, whereas age and self-reported health status were associated with mobility only in Denmark. This comparison indicates that despite slightly different measurement approaches, similar risks are attributed to older adults’ low in-hospital mobility and emphasizes the contribution of commonly used pre-hospitalization mobility measures as strong and consistent risk factors. This knowledge can support a better understanding of the need of both standard risk assessments and country-based tailored approaches.

Physical and Cognitive Correlates of GPS-Derived Life-Space Characteristics in Older Adults

Life-space mobility, movement within one’s living environment, is important for functional independence in later life. It is unclear which life-space characteristics (i.e., space, duration, shape) are most affected by physical and cognitive limitations. GPS-derived measures mitigate recall bias and offer novel ways to characterize life-space. We examined associations between physical and cognitive performance and GPS-derived life-space characteristics. Participants were 164 community-dwelling adults (Age: M=77.3±6.5) from baseline data of a clinical trial to improve walking in older adults. Participants carried a portable GPS for 7 days, which passively collected real-time location. Standard deviational ellipses (SDEs) and minimum convex polygons (MCPs) were derived for each day. Area and compactness of these measures quantified activity space and shape, respectively. For each measure, 7-day medians and median absolute deviations (MAD) were computed to capture both central tendency and variability of weekly activity. Activity duration was quantified as percentage of time outside home. Adjusting for age and sex, percent time outside home was associated with lower mobility performance (i.e., 6-minute walk (6MWT), figure 8 walk, ρ’s=.17-.18, p’s<.05) and executive functioning (i.e., Trail Making Test, Part A: ρ=.16, p=.04, Part B: ρ=.19, p=.01). Median MCP and SDE areas, but not compactness, were associated with 6MWT performance (ρ’s=.18-.20, p’s<.05). MCP area MAD was associated with greater global cognition (3MSE, ρ=.15, p=.05). Life-space characteristics were differentially associated with performance measures, suggesting physical and cognitive limitations may constrain life-space mobility via different mechanisms. Variation in these associations by neighborhood walkability and active versus passive travel will also be examined.

Effectiveness of Exergaming-based Interventions for Mobility Performance in Older Adults with Parkinson’s Disease: Systematic Review and Meta-Analysis of Randomized Controlled Trials (Preprint)

BACKGROUND Background: Although physical exercises can help older adults with Parkinson’s disease to retain their mobility function, older adults are less motivated to attend repeated and intensive physical training. Exergaming-based interventions have the potential to provide a more engaged and enjoyable therapy. However, few meta-analysis studies discussed the effectiveness of exergaming-based interventions on the mobility performance of older adults with Parkinson’s disease. OBJECTIVE Objective: A systematic review and meta-analysis of randomized controlled trials (RCTs) were conducted to examine the effectiveness of exergaming-based interventions on mobility performance in older adults with Parkinson’s disease. METHODS Methods: Seven databases (Web of Science, Medline, Academic Search Premier, CINAHL Complete, PsycINFO, PsychARTICLE, and PubMed) were searched to identify the RCTs which examined the effectiveness of exergaming on the mobility performance of older adults with Parkinson’s disease up to September 2021. Using meta-analysis, we assessed mobility performance between intervention groups and control groups by comparing basic mobility function with the Timed Up and Go (TUG), walking capability with 6-Minute Walk Test (6MWT), postural balance function with the Berg Balance Scale (BBS), and gait ability with gait velocity, stride length, and the Functional Gait Assessment (FGA). RESULTS Results: After scanning 1110 articles, we identified and meta-analyzed 16 trials, including a total of 508 older adults with Parkinson’s disease. The results revealed statistical differences between intervention groups and control groups in the TUG (MD = -0.87; 95% CI = -1.60 to -0.15; P = .018), 6MWT (MD = 39.56; 95% CI = 1.21 to 77.91; P = 0.043), BBS (MD = 2.28; 95% CI = 1.42 to 3.14; P < .001), and FGA (MD = 1.40; 95% CI = -0.03 to 2.82; P = .054). The detectable clinically difference of the outcomes were discussed and the implications were provided. CONCLUSIONS Conclusions: Exergaming is superior to traditional training in improving PD older adults’ basic mobility skills, walking capability, and postural balance function, while it has an equal effect with traditional physical training in enhancing PD older adults’ gait ability.

Morphological Computation in Plant Seeds for a New Generation of Self-Burial and Flying Soft Robots

Plants have evolved different mechanisms to disperse from parent plants and improve germination to sustain their survival. The study of seed dispersal mechanisms, with the related structural and functional characteristics, is an active research topic for ecology, plant diversity, climate change, as well as for its relevance for material science and engineering. The natural mechanisms of seed dispersal show a rich source of robust, highly adaptive, mass and energy efficient mechanisms for optimized passive flying, landing, crawling and drilling. The secret of seeds mobility is embodied in the structural features and anatomical characteristics of their tissues, which are designed to be selectively responsive to changes in the environmental conditions, and which make seeds one of the most fascinating examples of morphological computation in Nature. Particularly clever for their spatial mobility performance, are those seeds that use their morphology and structural characteristics to be carried by the wind and dispersed over great distances (i.e. “winged” and “parachute” seeds), and seeds able to move and penetrate in soil with a self-burial mechanism driven by their hygromorphic properties and morphological features. By looking at their motion mechanisms, new design principles can be extracted and used as inspiration for smart artificial systems endowed with embodied intelligence. This mini-review systematically collects, for the first time together, the morphological, structural, biomechanical and aerodynamic information from selected plant seeds relevant to take inspiration for engineering design of soft robots, and discusses potential future developments in the field across material science, plant biology, robotics and embodied intelligence.

A review of the good practices of active mobility measures implemented by European cities due to the COVID-19 pandemic

The scope of this paper is to make a review of the good practices of active mobility measures implemented by big European cities to face the changing travel patterns and the social distancing requirement due to the COVID-19 pandemic. Active mobility good practices were gathered by 50 postgraduate students and they were categorized by the authors. 50 European cities were reported, of which four (4) were examined further as the most reported ones. These were the following: Paris, France; Milan, Italy; Brussels, Belgium; and Berlin, Germany. This does not mean that these cities are the best performing in active mobility, as there could be cities that already had adequate active mobility performance, and other factors interfere, such as the brand name of each city. The most reported good practice was the temporary pop-up bicycle lanes, also applied in Thessaloniki, Greece. Another good practice is the expansion of pedestrianization and the speed limit of 30 km/h. Athens, Thessaloniki, and other Greek cities have a lot to learn from the experience of the other European cities, and this paper is an attempt of knowledge transfer. It seems that the crisis of the COVID-19 pandemic has become an excellent opportunity for the promotion of active mobility in Europe that should not be left unexploited.