Cognitive Computation and Systems最新文献

String instruments, wind instruments and percussion instruments are three traditional categories of musical instruments, among which wind instruments play an important role. Usually, pitches of wind instruments are determined by the vibrating air column, and the musical pitches will be affected by multiple factors of the air flow. In this article, the mechanism of sound production by a pipe is analysed in terms of the coupling of the edge tone and the air column's vibration in the tube. Experiments and computational fluid dynamics numerical calculations are combined to study the influence of the jet velocity on the oscillation frequency of the edge tone and the musical sound produced by the tube, which help to gain deeper insight into the relation between physics and music.

This paper is part of a special issue on Music Technology. We study the type recognition of traditional Chinese musical instrument audio in the common way. Using MEL spectrum characteristics as input, we train an 8-layer convolutional neural network, and finally achieve 99.3% accuracy. After that, this paper mainly studies the performance skill recognition of Chinese traditional musical instruments. Firstly, for a single instrument, the features were extracted by using the pre-trained ResNet model, and then the SVM algorithm was used to classify all the instruments with an accuracy of 99%. Then, in order to improve the generalization of the model, the paper proposes the performance skill recognition of the same kind of instruments. In this way, the regularity of the same playing technique of different instruments can be utilized. Finally, the recognition accuracy of the four kinds of instruments is as follows: 95.7% for blowing instruments, 82.2% for plucked-string instruments, 88.3% for strings instruments, and 97.5% for percussion instruments. We open source the audio database of traditional Chinese musical instruments and the Python source code of the whole experiment for further research.

Patients with cerebral haemorrhages need to drain haematomas. Fresh blood may appear during the haematoma drainage process, so this needs to be observed and detected in real time. To solve this problem, this paper studies images produced during the haematoma drainage process. A blood image feature selection recognition and classification framework is designed. First, aiming at the characteristics of the small colour differences in blood images, the general RGB colour space feature is not obvious. This study proposes an optimal colour channel selection method. By extracting the colour information from the images, it is recombined into a 3 × 3 matrix. The normalised 4-neighbourhood contrast and variance are calculated for quantitative comparison. The optimised colour channel is selected to overcome the problem of weak features caused by a single colour space. After that, the effective region in the image is intercepted, and the best colour channel of the image in the region is transformed. The first, second and third moments of the three best colour channels are extracted to form a nine-dimensional eigenvector. K-means clustering is used to obtain the image eigenvector, outliers are removed, and the results are then transferred to the hidden Markov model (HMM) and support vector machine (SVM) for classification. After selecting the best color channel, the classification accuracy of HMM-SVM is greatly improved. Compared with other classification algorithms, the proposed method offers great advantages. Experiments show that the recognition accuracy of this method reaches 98.9%.

Music can be regarded as an art of expressing inner feelings. However, most of the existing networks for music generation ignore the analysis of its emotional expression. In this paper, we propose to synthesise music according to the specified emotion, and also integrate the internal structural characteristics of music into the generation process. Specifically, we embed the emotional labels along with music structure features as the conditional input and then investigate the GRU network for generating emotional music. In addition to the generator, we also design a novel perceptually optimised emotion classification model which aims for promoting the generated music close to the emotion expression of real music. In order to validate the effectiveness of the proposed framework, both the subjective and objective experiments are conducted to verify that our method can produce emotional music correlated to the specified emotion and music structures.

Energy consumption in buildings is a major contributor to global warming and therefore has become a field of intensive research. This type of energy consumption can be described in two dimensions: an appliance-based dimension and a behaviour-based dimension. To address the behaviour-based dimension a recent study proposed a cognitive human-building interaction model that builds on the instance-based learning paradigm. However, since the values of the standard cognitive parameters commonly used for modelling lab-based behaviours are not suitable for the ‘real-world’ domain of human-building interaction, this paper aims to identify cognitive parameter values adapted to and suitable for the specific character of this application domain. To achieve this goal, a virtual test environment—consisting of an occupied room and a corresponding model task—was designed to test the performance of the model and its dependence on a set of fundamental cognitive parameters. A test criterion was developed that did not depend on empirical data but used the predictive consistency of the model as reference. A range of values was pre-selected for each parameter based on theoretical and empirical considerations, which was then tested against the evaluation criterion. The performance of the model was improved significantly throughout the parametrisation process and yielded plausible results.

The paper presents a novel algorithm to classify children's epileptic syndromes based on the fused features of electroencephalogram (EEG) and electrocardiogram (ECG). The purpose is to assess whether multimodal physiological signals could improve the classification performance of epileptic syndromes over a single physiological signal. The study is carried out on the epileptic syndromes database recorded by the Children's Hospital, Zhejiang University School of Medicine (CHZU), that includes the synchronised EEGs and ECGs of 16 children suffered from the infantile spasms (known as the WEST syndrome, named) and the childhood absence epilepsy (CAE), respectively. Experiments are conducted and compared using the EEGs and ECGs in the ictal and interictal periods. The data imbalanced issue between the ictal and interictal periods is also considered by applying a synthetic minority sample generating approach. The experimental results show that using the fused feature of EEG + ECG can achieve an average of 98.15% overall classification accuracy, which is better than using the single physiological signal.

The snubber circuit plays an important role in motor drives. This paper deals with the detection of the inverter switch snubber circuit resistance fault (ISSCRF) in brushless direct current (BLDC) motors used for robotic applications. This has been carried out in two parts: Fast-Fourier-Transform-based analysis and wavelet-decomposition-based analysis on the stator current of the BLDC motor. The first analysis investigates the effects of different percentages of ISSCRF on direct current (DC) component, fundamental frequency component and total harmonic distortion percentage. Next analyses consider all of kurtosis, skewness and root-mean-square values of wavelet coefficients of stator current harmonic spectra. Comparative learning is made to obtain a few selective parameters best fit for the detection of ISSCRF. A fault detection algorithm to detect ISSCRF has been proposed and validated by three case studies. The algorithm is again modified with best-fit parameters. Comparative discussion and novel contributions of the work have also been presented.

This paper details a solution of fusing combination features, Iterative Closest Point (ICP) and Monte Carlo algorithm, in order to solve the problem that mobile robot positioning is easy to fail in a dynamic environment. Firstly, an ICP algorithm based on the maximum common combination feature is proposed to provide a more stable observation point information and therefore avoids the problem of local extremes and obtains more accurate matching results. A novel proposal distribution is then designed and auxiliary particles are used, so that the particle sets are distributed in high-observational areas closer to the true posterior probability of the state. Finally, the experimental results on the public datasets show that the proposed algorithm is more accurate in these environments.

Flexible tactile sensing based on capacitive sensing has become a research hotspot in recent years because of its low energy consumption, high performance and wide application prospects. However, the axis error caused by the coupling deformation of the dielectric will seriously affect the accuracy of the sensor. In this paper, a capacitive flexible three-axis tactile sensor array is modelled and simulated, and a neural network-based calibrator for the three-axis sensor array is proposed, which can be used to calibrate the simulated measurement data. The simulation results show that even though the correlation coefficient of linear regression for each axis is very close to 1, the effect of dielectric nonlinear coupling distortion cannot be eliminated. The calibration method based on the neural network can effectively suppress the nonlinear coupling distortion of the dielectric, and reduce the measurement coupling rate of the sensor model from 26% to 1%. At the same time, in order to ensure the measurement accuracy and robustness of different units in the sensor array, the input layer of the calibrator is expanded, and the data set containing capacitance information and two-dimensional location information is used for training. The experimental results show that the proposed calibration method combining two-dimensional position information training accurately calibrates the capacitive flexible three-dimensional tactile sensor array.

In a cross-cultural context, exploring musical elements' cultural specificity and universality that affect various types of music is conducive to personalised emotion recognition. In this study, high-level musical elements are introduced to explore their influence on emotional perception. By comparing music emotion recognition (MER) models of varied cultural music, musical elements with cultural universality and cultural specificity are further determined. Participants rated valence, tension arousal, and energy arousal on labelled nine-point analogical–categorical scales for four types of classical music: Chinese ensemble, Chinese solo, Western ensemble, and Western solo. Fifteen musical elements in five categories—timbre, rhythm, articulation, dynamics, and register were annotated through manual evaluation or the automatic algorithm. The relationship between music emotion and musical elements was analysed through partial least squares regression. Results showed that tempo, rhythm complexity, and articulation are culturally universal; musical elements related to timbre, register, and dynamics features are culturally specific. By increasing tempo, rhythm complexity, staccato, perception of valence, tension arousal, and energy arousal can be effectively improved. Based on the Partial least squares regression (PLSR) model's results for the datasets, the combination of manual and automatic annotation for musical elements can improve the MER system's performance.