Kanta Tachibana

Muscle cross-sectional areas and performance power of limbs and trunk in the rowing motion

Although it is clear that rowers have a large muscle mass, their distribution of muscle mass and which of the main motions in rowing mediates muscle hypertrophy in each body part are unclear. We examine the relationships between partial motion power in rowing and muscle cross-sectional area of the thigh, lower back, and upper arms. Sixty young rowers (39 males and 21 females) participated in the study. Joint positions and forces were measured by video cameras and rowing ergometer software, respectively. One-dimensional motion analysis was performed to calculate the power of leg drive, trunk swing, and arm pull motions. Muscle cross-sectional areas were measured using magnetic resonance imaging. Multiple regression analyses were carried out to determine the association of different muscle cross-sectional areas with partial motion power. The anterior thigh best explained the power demonstrated by leg drive (r 2 = 0.508), the posterior thigh and lower back combined best explained the power demonstrated by the trunk swing (r 2 = 0.493), and the elbow extensors best explained the power demonstrated by the arm pull (r 2 = 0.195). Other correlations, such as arm muscles with leg drive power (r 2 = 0.424) and anterior thigh with trunk swing power (r 2 = 0.335), were also significant. All muscle cross-sectional areas were associated with rowing performance either through the production of power or by transmitting work. The results imply that rowing motion requires a well-balanced distribution of muscle mass throughout the body.

Optimal learning rates for clifford neurons

Neural computation in Clifford algebras, which include familiar complex numbers and quaternions as special cases, has recently become an active research field. As always, neurons are the atoms of computation. The paper provides a general notion for the Hessian matrix of Clifford neurons of an arbitrary algebra. This new result on the dynamics of Clifford neurons then allows the computation of optimal learning rates. A thorough discussion of error surfaces together with simulation results for different neurons is also provided. The presented contents should give rise to very efficient second-order training methods for Clifford Multilayer perceptrons in the future.

Classification and Clustering of Spatial Patterns with Geometric Algebra

In fields of classification and clustering of patterns most conventional methods of feature extraction do not pay much attention to the geometric properties of data, even in cases where the data have spatial features. This paper proposes to use geometric algebra to systematically extract geometric features from data given in a vector space. We show the results of classification of handwritten digits and those of clustering of consumers’ impression with the proposed method.

Feature extractions with geometric algebra for classification of objects

Most conventional methods of feature extraction do not pay much attention to the geometric properties of data, even in cases where the data have spatial features. In this study we introduce geometric algebra to undertake various kinds of feature extraction from spatial data. Geometric algebra is a generalization of complex numbers and of quaternions, and it is able to describe spatial objects and relations between them. This paper proposes to use geometric algebra to systematically extract geometric features from data given in a vector space. We show the results of classification of hand-written digits, which were classified by feature extraction with the proposed method.

A clustering method for geometric data based on approximation using conformal geometric algebra

Clustering is one of the most useful methods for understanding similarity among data. However, most conventional clustering methods do not pay sufficient attention to the geometric properties of data. Geometric algebra (GA) is a generalization of complex numbers and quaternions able to describe spatial objects and the relations between them. This paper uses conformal GA (CGA), which is a part of GA, to transform a vector in a real vector space into a vector in a CGA space and presents a proposed new clustering method using conformal vectors. In particular, this paper shows that the proposed method was able to extract the geometric clusters which could not be detected by conventional methods.

An application of fuzzy modeling to rowing motion analysis

Fuzzy modeling has distinct features, which are applicable to nonlinear systems and has an ability to extract knowledge. Fuzzy neural networks (FNNs) enable automatic acquisition of knowledge. The authors have proposed an uneven division of input space for an FNN which reduces the number of fuzzy rules without sacrificing the precision of the model. In many sports, nonlinear factors affect the performance. In rowing competitions, the performance criterion is the boat speed. In the paper, fuzzy modeling is applied to reveal the relationships between the supplied power and the boat speed. The forces and the angles of on-water rowing are measured. The subjects are candidate Japanese national team members. The total propulsive work, consistency and uniformity of the propulsive power were calculated from the force and the angle data. The relationships between these factors and the performance were identified with fuzzy modeling. Compared to linear regression, a more precise and more comprehensive model was obtained.

A hierarchical fuzzy modeling method using genetic algorithm for identification of concise submodels

Fuzzy modeling is a promising technique to describe input-output relationships of nonlinear system. This paper presents a new hierarchical fuzzy modeling method using genetic algorithm (GA). Uneven allocation of membership functions in the antecedent of each submodel in the hierarchical fuzzy model can be achieved with the proposed method. This paper introduces a simple coding method and a quick rule identification method for efficient search for a submodel using a fuzzy neural network (FNN). The obtained hierarchical fuzzy model are more concise than those identified with the conventional methods.

Consideration of State Representation for Semi-autonomous Reinforcement Learning of Sailing Within a Navigable Area

To sail quickly to a goal within a navigable area, complex control of the rudder and sail is required. Sailors must determine the current action with consideration of the time series of states; i.e., both current and future states. Reinforcement learning is an appropriate method for learning a complex problem, such as sailing. In this paper, we apply the navigable area such that a robotic sailor must avoid touching a boundary. To realise a higher layer of sailing architecture, the action space is simplified and discretised to the degree of the sailboat direction change. Moreover, we utilize semi-autonomous reinforcement learning, also known as imitation learning, in which a human selects an action and a robot updates its Q-values to evaluate pairs of states and actions until the robot’s action selection is equivalent to the human’s. For semi-autonomous learning, as well as for normal reinforcement learning, a representation of the state space is important. The state representation should be defined so that the state space is discretised to specify a desirable action, thereby removing any redundancy if possible. In this paper, we verify and investigate the possibility of state representation.

A Note on a Statistical Hypothesis Testing for Removing Noise by the Random Matrix Theory, and Its Application to Co-Volatility Matrices

It is well known that the bias called market microstructure noise will arise, when estimating realized co-volatility matrix which is calculated as a sum of cross products of intraday high-frequency returns. An existing conventional technique for removing such a market microstructure noise is to perform eigenvalue decomposition of the sum of cross products matrix and to identify the elements corresponding to the decomposed values which are smaller than the maximum eigenvalue of the random matrix as noises. Although the maximum eigenvalue of a random matrix follows asymptotically Tracy-Widom distribution, the existing technique does not take this asymptotic nature into consideration, but only the convergence value is used for it. Therefore, it cannot evaluate quantitatively such a risk that regards accidentally essential volatility as a noise. In this paper, we propose a statistical hypothesis test for removing noise in co-volatility matrix based on the nature in which the maximum eigenvalue of a random matrix follows Tracy-Widom distribution asymptotically.

Robust feature extractions from geometric data using geometric algebra

Most conventional methods of feature extraction for pattern recognition do not pay sufficient attention to inherent geometric properties of data, even in the case where the data have spatial features. This paper introduces geometric algebra to extract invariant geometric features from spatial data given in a vector space. Geometric algebra is a multidimensional generalization of complex numbers and of quaternions, and it ables to accurately describe oriented spatial objects and relations between them. This paper proposes to combine several geometric features using Gaussian mixture models. It applies the proposed method to the classification of hand-written digits.