sEMG-Based Robust Recognition of Grasping Postures with a Machine Learning Approach for Low-Cost Hand Control

The design and control of artificial hands remains a challenge in engineering. Popular prostheses are bio-mechanically simple with restricted manipulation capabilities, as advanced devices are pricy or abandoned due to their difficult communication with the hand. For social robots, the interpretation of human intention is key for their integration in daily life. This can be achieved with machine learning (ML) algorithms, which are barely used for grasping posture recognition. This work proposes an ML approach to recognize nine hand postures, representing 90% of the activities of daily living in real time using an sEMG human-robot interface (HRI). Data from 20 subjects wearing a Myo armband (8 sEMG signals) were gathered from the NinaPro DS5 and from experimental tests with the YCB Object Set, and they were used jointly in the development of a simple multi-layer perceptron in MATLAB, with a global percentage success of 73% using only two features. GPU-based implementations were run to select the best architecture, with generalization capabilities, robustness-versus-electrode shift, low memory expense, and real-time performance. This architecture enables the implementation of grasping posture recognition in low-cost devices, aimed at the development of affordable functional prostheses and HRI for social robots.

Design of Virtual Hands for Natural Interaction in the Metaverse

The emergence of the Metaverse is raising important questions in the field of human-machine interaction that must be addressed for a successful implementation of the new paradigm. Therefore, the exploration and integration of both technology and human interaction within this new framework are needed. This paper describes an innovative and technically viable proposal for virtual shopping in the fashion field. Virtual hands directly scanned from the real world have been integrated, after a retopology process, in a virtual environment created for the Metaverse, and have been integrated with digital nails. Human interaction with the Metaverse has been carried out through the acquisition of the real posture of the user's hands using an infrared-based sensor and mapping it in its virtualized version, achieving natural identification. The technique has been successfully tested in an immersive shopping experience with the Meta Quest 2 headset as a pilot project, where a transactions mechanism based on the blockchain technology (non-fungible tokens, NFTs) has allowed for the development of a feasible solution for massive audiences. The consumers' reactions were extremely positive, with a total of 250 in-person participants and 120 remote accesses to the Metaverse. Very interesting technical guidelines are raised in this project, the resolution of which may be useful for future implementations.

Unraveling the depuration mechanisms of metals in the burrowing crab (Neohelice granulata Dana, 1852): Biochemical biomarkers, metal-rich granules and bioaccumulation patterns

We studied the depuration mechanisms of metals (Cd, Cu, Pb, Zn, Mn, Ni, Cr, Fe) in Neohelice granulata, from sites with different human impacts (PC, a more impacted site and VM, a less impacted one). Our objectives included assessing metal concentrations (essential and non-essential) before and after depuration treatment, evaluating biochemical biomarkers (non-enzymatic and enzymatic) pre and post-treatment, and determining the role of metal-rich granules (MRG) in depuration. We observed variability in metals and biomarkers post-depuration, with no significant differences observed in PC, while Cd and Mn increased and Ni, Cu, and Fe decreased in VM. Integrated biomarkers' response indicated the prevailing antioxidant capacity in depurated organisms. Lipid peroxidation changes were insignificant, except in depurated-VM where values increased. MRG showed a significant decrease only for Mn and Fe, suggesting they were not the primary depuration structure. We concluded that depuration might depend on the species, gender and contamination history.

Assessment of metal contamination in an urbanized estuary (Atlantic Ocean) using crabs as biomonitors: A multiple biomarker approach

Estuarine environments, which are complex and sensitive coastal system, and are the final receptacle of several human wastes. Consequently, biomonitoring contaminants, such as metals, within these environments and developing scientific-based tools to conserve them have become particularly importat in recent years. Therefore, in the present study, we determined the levels of certain metals (Cd, Cu, Pb, Zn, Mn, Ni, Cr and Fe) both in sediments and in a key ecological benthic species, the burrowing crab Neohelice granulata, in sites of the Bahía Blanca estuary (SW Atlantic Ocean) with different anthropogenic impacts. We combined these records with geochemical indices and enzymatic and non-enzymatic biochemical biomarkers as early warning signals of contamination and damage to establish an integrated metal contamination profile. Our results indicated that some metals like Cu moderately contaminate the estuary and that the primary input of metals in this area is due to malfunctioning sewage discharges. Crabs exhibited the following pattern of metal accumulation: Fe ≥ Cu > Zn > Mn > Ni > Cd. Pb and Cr were under the method detection limit, and Cu was probably bioaccumulated from sediments. Metal concentrations showed significant differences according to the sites and seasons (p > 0.05) and not strictly to the crab gender. Besides, a similar pattern was observed for biomarkers, and the integrated biomarker response allowed establishing different oxidative stress patterns, according not only to human impacts but also to the seasonal physiological needs of this species and environmental endpoints (salinity, temperature, and pH). This work demonstrates that environmental factors also affect the metal influx in crabs and the activity of biomarkers beyond the source and fate of these elements. This information is vital for future integrated monitoring programs.

Real-Time Path Planning Based on Harmonic Functions under a Proper Generalized Decomposition-Based Framework

This paper presents a real-time global path planning method for mobile robots using harmonic functions, such as the Poisson equation, based on the Proper Generalized Decomposition (PGD) of these functions. The main property of the proposed technique is that the computational cost is negligible in real-time, even if the robot is disturbed or the goal is changed. The main idea of the method is the off-line generation, for a given environment, of the whole set of paths from any start and goal configurations of a mobile robot, namely the computational vademecum, derived from a harmonic potential field in order to use it on-line for decision-making purposes. Up until now, the resolution of the Laplace or Poisson equations has been based on traditional numerical techniques unfeasible for real-time calculation. This drawback has prevented the extensive use of harmonic functions in autonomous navigation, despite their powerful properties. The numerical technique that reverses this situation is the Proper Generalized Decomposition. To demonstrate and validate the properties of the PGD-vademecum in a potential-guided path planning framework, both real and simulated implementations have been developed. Simulated scenarios, such as an L-Shaped corridor and a benchmark bug trap, are used, and a real navigation of a LEGO^®MINDSTORMS robot running in static environments with variable start and goal configurations is shown. This device has been selected due to its computational and memory-restricted capabilities, and it is a good example of how its properties could help the development of social robots.

A Novel Real-Time MATLAB/Simulink/LEGO EV3 Platform for Academic Use in Robotics and Computer Science

Over the last years, mobile robot platforms are having a key role in education worldwide. Among others, LEGO Robots and MATLAB/Simulink are being used mainly in universities to improve the teaching experience. Most LEGO systems used in the literature are based on NXT, as the EV3 version is relatively recent. In contrast to the previous versions, the EV3 allows the development of real-time applications for teaching a wide variety of subjects as well as conducting research experiments. The goal of the research presented in this paper was to develop and validate a novel real-time educational platform based on the MATLAB/Simulink package and the LEGO EV3 brick for academic use in the fields of robotics and computer science. The proposed framework is tested here in different university teaching situations and several case studies are presented in the form of interactive projects developed by students. Without loss of generality, the platform is used for testing different robot path planning algorithms. Classical algorithms like rapidly-exploring random trees or artificial potential fields, developed by robotics researchers, are tested by bachelor students, since the code is freely available on the Internet. Furthermore, recent path planning algorithms developed by the authors are also tested in the platform with the aim of detecting the limits of its applicability. The restrictions and advantages of the proposed platform are discussed in order to enlighten future educational applications.

Grip force and force sharing in two different manipulation tasks with bottles

Grip force and force sharing during two activities of daily living were analysed experimentally in 10 right-handed subjects. Four different bottles, filled to two different levels, were manipulated for two tasks: transporting and pouring. Each test subject's hand was instrumented with eight thin wearable force sensors. The grip force and force sharing were significantly different for each bottle model. Increasing the filling level resulted in an increase in grip force, but the ratio of grip force to load force was higher for lighter loads. The task influenced the force sharing but not the mean grip force. The contributions of the thumb and ring finger were higher in the pouring task, whereas the contributions of the palm and the index finger were higher in the transport task. Mean force sharing among fingers was 30% for index, 29% for middle, 22% for ring and 19% for little finger. Practitioner Summary: We analysed grip force and force sharing in two manipulation tasks with bottles: transporting and pouring. The objective was to understand the effects of the bottle features, filling level and task on the contribution of different areas of the hand to the grip force. Force sharing was different for each task and the bottles features affected to both grip force and force sharing.

Hand Posture Prediction Using Neural Networks within a Biomechanical Model

This paper proposes the use of artificial neural networks (ANNs) in the framework of a biomechanical hand model for grasping. ANNs enhance the model capabilities as they substitute estimated data for the experimental inputs required by the grasping algorithm used. These inputs are the tentative grasping posture and the most open posture during grasping. As a consequence, more realistic grasping postures are predicted by the grasping algorithm, along with the contact information required by the dynamic biomechanical model (contact points and normals). Several neural network architectures are tested and compared in terms of prediction errors, leading to encouraging results. The performance of the overall proposal is also shown through simulation, where a grasping experiment is replicated and compared to the real grasping data collected by a data glove device.

Functional range of motion of the hand joints in activities of the International Classification of Functioning, Disability and Health

STUDY DESIGN

Cross-sectional research design.

INTRODUCTION

Active range of motion (AROM) is used as indicator of hand function. However, functional range of motion (FROM) data are limited, and fail to represent activities of daily living (ADL).

PURPOSE OF THE STUDY

To estimate dominant hand FROM in flexion, abduction and palmar arching in people under 50 years of age performing ADL.

METHODS

AROMs and hand postures in 24 representative ADL of the International Classification of Functioning, Disability and Health (ICF) were recorded in 12 men and 12 women. FROM data were reported by activity and ICF area, and compared with AROMs. The relationship between ROM measures to gender and hand size was analyzed by correlation.

RESULTS

FROM was 5° to 28° less than available AROM depending on the joint and movement performed.

DISCUSSION

Joints do not necessarily move through full AROM while performing ADL which has benefits in retaining function despite loss of motion. This may also suggest that ADL alone are insufficient to retain or restore full AROM.

CONCLUSIONS

Therapists should consider FROM requirements and normal AROM when defining hand therapy goals, interventions and evaluating the success of treatment.

LEVEL OF EVIDENCE

N/A.

Canine infection and the possible role of dogs in the transmission of American tegumentary leishmaniosis in Salta, Argentina

Some Leishmania species affect humans in two principal forms: visceral and cutaneous leishmaniosis (CL). Several studies have identified dogs as the main reservoirs of the visceral leishmaniosis (VL) caused by Leishmania infantum. The purpose of this work was to carry out a survey of the canine population associated with human cases of American tegumentary leishmaniosis (ATL), in order to establish the clinical, parasitological, serological and immunological characteristics of the canine disease, in an endemic region for both ATL and Chagas' disease in the province of Salta, in northwestern Argentina. Two hundred and eight dogs from the endemic area were examined and 41 (19.7%) of them presented lesions compatible with leishmaniosis. In order to investigate the presence of antibodies against Leishmania spp. and Trypanosoma cruzi, sera were screened by ELISA using two complex antigens from these parasites and, because of cross-reactions between them, a specific antigen for diagnosis of T. cruzi infection. Sixty-two (29.8%) of 208 dogs were positive for the complex antigen F45 from Leishmania and 50 (24%) were positive for the complex antigen F105 from T. cruzi. Nine dogs (4.3%) were positive for the specific Ag163B6-cruzipain suggesting that these dogs were truly infected with T. cruzi. Furthermore, three of these nine dogs presented Leishmania sp. in their skin lesions and therefore were considered as infected by both, T. cruzi and Leishmania parasites. The prevalence of Leishmania infection detected by lesions and/or positive serology was 27.4% (57/208). On the basis of previous observations regarding the clustered appearance of human ATL, the dog population was divided into two groups: zone A, dogs living within a 100 m radius from houses with human cases, and zone B, dogs living beyond this limit. The prevalence of ATL in dogs was significantly higher in zone A (34.6%) than in zone B (7.3%), suggesting a strong correlation between canine and human cases. The average time required for a parasitological diagnosis by microscopy was six times longer for dog samples than human ones, and the average number of parasites per 100 microscopic fields was 14-fold lower in canine samples. The high prevalence of Leishmania infection and the close association with human cases, demonstrated that dogs are a very susceptible host for Leishmania infection, but the scarcity of parasites in their lesions suggests that they may not be the main reservoir of the parasite in this endemic area.

[The transmission de Chagas disease in Salta and the detection of congenital cases]

Data on the prevalence of Trypanosoma cruzi infection is presented for the province of Salta, Argentina. Special emphasis is given to the detection of congenital transmission and to the economic benefits of preventing Chagas' disease. Seroepidemiological data obtained from 20 year old army draftees revealed a reduction, from 22.7 to 11.11% between 1964 and 1985. In university students, a rate of 0.96% was found in 1998. Surveys carried out during 1996 showed that more than 15% of the pregnant women analyzed carried T. cruzi infection, particularly in the north of the province. This situation brings about a high risk of appearance of congenital cases and represents an opportunity to test the most adequate strategies for detection. By applying systematically microhematocrit, hemoculture and PCR methods, to umbilical chord blood, an increase in the early detection of congenitally infected babies is being achieved. In 1992-94, very high seroprevalence rates of infection were found among indians of the Chaco region of Salta. The overall rate was 37%, but there were 5 localities where more than 54% of the population was infected. These numbers indicate that, in vast areas of the provincial territory, fight against vector bugs must not merely consist of surveilance activities, but rather of renewed spraying attacks. The fight must include control of pregnant women and blood banks. An economic analysis of the economic return, calculated only for spraying activities and for the Department of Anta (Salta), indicated a net present value of over 7 million dollars and an internal rate of return exceeding 60%.

Field trial of vaccination against American trypanosomiasis (Chagas' disease) in dogs

In Santiago del Estero, an area endemic for Chagas' disease in northwestern Argentina, household dogs were vaccinated with live-attenuated Trypanosoma cruzi, and the prospective incidence of natural infection by this parasite was assessed during a two-year followup period. Vaccinated dogs received 10(7) attenuated, TCC strain T. cruzi epimastigotes and were given booster vaccinations two and 14 months later. The number of animals that could be evaluated in vaccinated versus control groups was 73 and 75 after one year and 49 and 40 after two years, respectively. Parasitologic evaluation by xenodiagnosis indicated that vaccination had reduced natural T. cruzi infection from 26.7% to 12.3% after one year (P = 0.015). The preventive effect of vaccination after the second year was less significant in spite of the booster vaccinations. Inclusion of indirect hemagglutination data for the diagnosis of infection slightly increased the number of infected dogs without affecting the evidence for protection in the first year. Serologic, parasitologic, and isoenzyme studies indicated that protection was mediated by an attenuated, self-cured infection. In 15 dogs in which the vaccination failed to completely prevent natural infection, immunization nevertheless impaired their ability to infect the natural insect vectors of the disease in humans.

[Medically diagnosed alcoholic morbidity in wine-producing and mining cantons of Languedoc]

The aim of this study is to evaluate the severity of medically diagnosed alcoholic disease in two regions of France, the Hérault region (wine producing) and the Gard region (mining), by means of a questionnaire filled in by 84 p. cent of general practitioners with a very low loss rate (7%). This is not a study of incidence, but an analysis of the morbidity observed and diagnosed in a large population sample. The survey detected 2,4 p. cent and 2,7 p. cent of the male population and 0,2 and 0,3 p. cent of the female population. The morbidity varies with age and sex and alcohol abuse was found to occur earlier in the mining region than in the wine producing region. Although there is no correlation between age and the frequency of consultations, the proportion of patients consulting for an alcohol related disease decreases with increasing age. The more advanced the alcohol related disease, the more difficult it is for the doctor to distinguish between symptoms which are due to aging and those due to alcohol. The doctor does not relate hypertension to alcoholism.