Search

Exoskeletons and rehabilitation systems offer great potential for enhancing human strength and recovery through advanced human-machine interfaces (HMIs) that adapt to movement dynamics. However, the real-time application of physics-informed neural networks (PINNs) is limited by their reliance on fixed input lengths and surrogate models. This study introduces a novel physics-informed Gated Recurrent Network (PiGRN) designed to predict multi-joint torques using surface electromyography (sEMG) data. The PiGRN model employs a Gated Recurrent Unit (GRU) to convert time-series sEMG inputs into multi-joint kinematics and external loads, which are then integrated into an equation of motion to ensure consistency with physical laws. Experimental validation with sEMG data from five participants performing elbow flexion-extension tasks showed that the PiGRN model accurately predicted joint torques for 10 unfamiliar movements, with RMSE values between 4.02\% and 11.40\% and correlation coefficients ranging from 0.87 to 0.98. These findings highlight the PiGRN's potential for real-time exoskeleton and rehabilitation applications. Future research will explore more diverse datasets, improve musculoskeletal models, and investigate unsupervised learning methods.

We study the weighted Myerson value for Network games extending a similar concept for communication situations. Network games, unlike communication situations, treat direct and indirect links among players differently and distinguish their effects in both worth generation and allocation processes. The weighted Myerson value is an allocation rule for Network games that generalizes the Myerson value of Network games. Here, the players are assumed to have some weights measuring their capacity to form links with other players. Two characterization of the weighted Myerson value are provided. Finally, we propose a bidding mechanism to show that the weighted Myerson value is a subgame-perfect Nash equilibrium under a non-cooperative framework.

In this research, we present an innovative method known as a physics-informed neural network (PINN) model to predict multi-joint kinematics using electromyography (EMG) signals recorded from the muscles surrounding these joints across various loads. The primary aim is to simultaneously predict both the shoulder and elbow joint angles while executing elbow flexion-extension (FE) movements, especially under varying load conditions. The PINN model is constructed by combining a feed-forward Artificial Neural Network (ANN) with a joint torque computation model. During the training process, the model utilizes a custom loss function derived from an inverse dynamics joint torque musculoskeletal model, along with a mean square angle loss. The training dataset for the PINN model comprises EMG and time data collected from four different subjects. To assess the model's performance, we conducted a comparison between the predicted joint angles and experimental data using a testing data set. The results demonstrated strong correlations of 58% to 83% in joint angle prediction. The findings highlight the potential of incorporating physical principles into the model, not only increasing its versatility but also enhancing its accuracy. The findings could have significant implications for the precise estimation of multi-joint kinematics in dynamic scenarios, particularly concerning the advancement of human-machine interfaces (HMIs) for exoskeletons and prosthetic control systems.

In Network games under cooperative framework, the position value is a link based allocation rule. It is obtained from the Shapley value of an associated cooperative game where the links of the network are considered players. The Shapley value of each of the links is then divided equally among the players who form those links. The inherent assumption is that the value is indifferent to the weights of the players in the network. Depending on how much central a player is in the network, or the ability of making links with other players etc., for example, players can be considered to have weights. Thus, in such situations, dividing the Shapley value equally among the players can be an over-simplistic notion. We propose a generalised version of the position value: the weighted position value that allocates the Shapley shares proportional to the players' weights. These weights of the players are exogenously given. We provide two axiomatic characterizations of our value. Finally, a bidding mechanism is formulated to show that any sub-game perfect equilibrium (SPE) of this mechanism coincides with the weighted position value.

We study a class of probabilistic cooperative games which can be treated as an extension of the classical cooperative games with transferable utilities. The coalitions have an exogenous probability of being realized. This probability distribution is known beforehand and the distribution of the expected worth needs to be done before the realization of the state. We obtain a value for this class of games and present three characterizations of this value using natural extensions of the axioms used in the seminal axiomatization of the Shapley value. The value, which we call the Expected Shapley value, allocates the players their expected worth with respect to a probability distribution.

In cooperative games with transferable utilities, the Shapley value is an extreme case of marginalism while the Equal Division rule is an extreme case of egalitarianism. The Shapley value does not assign anything to the non-productive players and the Equal Division rule does not concern itself to the relative efficiency of the players in generating a resource. However, in real life situations neither of them is a good fit for the fair distribution of resources as the society is neither devoid of solidarity nor it can be indifferent to rewarding the relatively more productive players. Thus a trade-off between these two extreme cases has caught attention from many researchers. In this paper, we obtain a new value for cooperative games with transferable utilities that adopts egalitarianism in smaller coalitions on one hand and on the other hand takes care of the players' marginal productivity in sufficiently large coalitions. Our value is identical with the Shapley value on one extreme and the Equal Division rule on the other extreme. We provide four characterizations of the value using variants of standard axioms in the literature. We have also developed a strategic implementation mechanism of our value in sub-game perfect Nash equilibrium.

Mood recognition is an important problem in music informatics and has key applications in music discovery and recommendation. These applications have become even more relevant with the rise of music streaming. Our work investigates the research question of whether we can leverage audio metadata such as artist and year, which is readily available, to improve the performance of mood classification models. To this end, we propose a multi-task learning approach in which a shared model is simultaneously trained for mood and metadata prediction tasks with the goal to learn richer representations. Experimentally, we demonstrate that applying our technique on the existing state-of-the-art convolutional neural networks for mood classification improves their performances consistently. We conduct experiments on multiple datasets and report that our approach can lead to improvements in the average precision metric by up to 8.7 points.

A network game assigns a level of collectively generated wealth to every network that can form on a given set of players. A variable network game combines a network game with a network formation probability distribution, describing certain restrictions on network formation. Expected levels of collectively generated wealth and expected individual payoffs can be formulated in this setting. We investigate properties of the resulting expected wealth levels as well as the expected variants of well-established network game values as allocation rules that assign to every variable network game a payoff to the players in a variable network game. We establish two axiomatizations of the Expected Myerson Value, originally formulated and proven on the class of communication situations, based on the well-established component balance, equal bargaining power and balanced contributions properties. Furthermore, we extend an established axiomatization of the Position Value based on the balanced link contribution property to the Expected Position Value.