Evaluation of Music Features for PUK Kernel Based Genre Classification

Chapaneri, Santosh; Lopes, Renia; Jayaswal, Deepak

doi:10.1016/j.procs.2015.03.119

Cited by 9 publications

(6 citation statements)

References 12 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Therefore, these features could be used to analyze how products are innovated in the music industry context and, for this reason, we focus on them in our analysis. Musical features can be split into computational features, referring to the mathematical analysis of the signal, and perceptual features, related to how humans perceive music [32]. Furthermore, computational features are grouped into dynamics and spectral features, while perceptual features are divided into rhythm and tonal features [32].…”

Section: Theoretical Backgroundmentioning

confidence: 99%

Information Retrieval Technologies and Big Data Analytics to Analyze Product Innovation in the Music Industry

et al. 2023

View full text Add to dashboard Cite

In Cultural and Creative Industries, innovation contributes to generating a competitive advantage thanks to the fundamental role assumed by the human creativity and the quest for novelty. In particular, the music industry stands out as one of the most successful ones, in terms of both revenue and employment. The music industry is also quickly and constantly growing, supported by the new digital technologies and the rise of streaming platforms and digital services, which have increased the availability of continuous, reliable, and timely data. Consequently, this may allow the implementation of novel techniques to study product innovation occurring in the music industry. Nonetheless, quantitative approaches to study innovation in this industry are scant. The present study aims at filling this gap by developing a quantitative approach to analyze product innovation dynamics in the music industry exploiting data collected through Music Information Retrieval technologies. We selected a successful band as a case study and analyzed each song released from 1984 to 2016 to obtain a quantitative representation of their musical production. We then developed and applied quantitative similarity metrics to see how each album was similar or different from the previous ones and from the most relevant music genres, to better understand innovation dynamics in music production.

show abstract

Section: Theoretical Backgroundmentioning

confidence: 99%

Information Retrieval Technologies and Big Data Analytics to Analyze Product Innovation in the Music Industry

et al. 2023

View full text Add to dashboard Cite

show abstract

“…A kernel function is commonly used in GPR to represent the behavior of the dataset. The Pearson Universal Kernel (PUK) function expressed in Equation ( 24) is chosen due to its ability to adapt to various other functions [55]. The conditional densities and posterior for prediction are given by Equations ( 25) and ( 26), respectively.…”

Section: Gaussian Process-based Load Shed Value Estimationmentioning

confidence: 99%

An Online Security Prediction and Control Framework for Modern Power Grids

2021

View full text Add to dashboard Cite

The proliferation of renewable energy sources distributed generation (RES-DG) into the grid results in time-varying inertia constant. To ensure the security of the grid under varying inertia, techniques for fast security assessment are required. In addition, considering the high penetration of RES-DG units into the modern grids, security prediction using varying grid features is crucial. The computation burden concerns of conventional time-domain security assessment techniques make it unsuitable for real-time security prediction. This paper, therefore, proposes a fast security monitoring model that includes security prediction and load shedding for security control. The attributes considered in this paper include the load level, inertia constant, fault location, and power dispatched from the renewable energy sources generator. An incremental Naïve Bayes algorithm is applied on the training dataset developed from the responses of the grid to transient stability simulations. An additive Gaussian process regression (GPR) model is proposed to estimate the load shedding required for the predicted insecure states. Finally, an algorithm based on the nodes’ security margin is proposed to determine the optimal node (s) for the load shedding. The average security prediction and load shedding estimation model training times are 1.2 s and 3 s, respectively. The result shows that the proposed model can predict the security of the grid, estimate the amount of load shed required, and determine the specific node for load shedding operation.

show abstract

“…In this paper, correlationbased feature selection (CFS) algorithm is used. CFS is considered as the most stable feature selection algorithm which selects feature subsets that are highly correlated with the class, but uncorrelated with each other [16,17]. CFS uses Pearson correlation coefficient which is calculated as follows [18]:…”

Section: Feature Selectionmentioning

confidence: 99%

“…CFS has been used for large databases to reduce the problems of class imbalance, high dimensionality, and information redundancy [17,20,21]. For the proposed database in this paper, it reduces the feature-set from 45 to 22.…”

Section: Feature Selectionmentioning

confidence: 99%

“…SVM with PUK has the strongest mapping power and better generalization as compared to other kernel functions like polynomial, linear, and RBF [24]. They outperformed in terms of recognition accuracy as compared to other kernels and classifiers like -NN, MLP, and SVM with polynomial and RBF kernels [17,25]. ELM is used in various multiclass classification applications and gives similar or better generalizations at faster learning speed as compared to SVM which has high computational complexity [23].…”

Section: Classifiersmentioning

confidence: 99%

See 1 more Smart Citation

Lower Order Krawtchouk Moment-Based Feature-Set for Hand Gesture Recognition

Kaur

Joshi

2016

Advances in Human-Computer Interaction

View full text Add to dashboard Cite

The capability of lower order Krawtchouk moment-based shape features has been analyzed. The behaviour of 1D and 2D Krawtchouk polynomials at lower orders is observed by varying Region of Interest (ROI). The paper measures the effectiveness of shape recognition capability of 2D Krawtchouk features at lower orders on the basis of Jochen-Triesch’s database and hand gesture database of 10 Indian Sign Language (ISL) alphabets. Comparison of original and reduced feature-set is also done. Experimental results demonstrate that the reduced feature dimensionality gives competent accuracy as compared to the original feature-set for all the proposed classifiers. Thus, the Krawtchouk moment-based features prove to be effective in terms of shape recognition capability at lower orders.

show abstract

Evaluation of Music Features for PUK Kernel Based Genre Classification

Cited by 9 publications

References 12 publications

Information Retrieval Technologies and Big Data Analytics to Analyze Product Innovation in the Music Industry

Information Retrieval Technologies and Big Data Analytics to Analyze Product Innovation in the Music Industry

An Online Security Prediction and Control Framework for Modern Power Grids

Lower Order Krawtchouk Moment-Based Feature-Set for Hand Gesture Recognition

Contact Info

Product

Resources

About