Probability Distributions.- Linear Models for Regression.- Linear Models for Classification.- Neural Networks.- Kernel Methods.- Sparse Kernel Machines.- Graphical Models.- Mixture Models and EM.- Approximate Inference.- Sampling Methods.- Continuous Latent Variables.- Sequential Data.- Combining Models.

Pattern Recognition and Machine Learning

To evaluate binary classifications and their confusion matrices, scientific researchers can employ several statistical rates, accordingly to the goal of the experiment they are investigating. Despite being a crucial issue in machine learning, no widespread consensus has been reached on a unified elective chosen measure yet. Accuracy and F1 score computed on confusion matrices have been (and still are) among the most popular adopted metrics in binary classification tasks. However, these statistical measures can dangerously show overoptimistic inflated results, especially on imbalanced datasets. The Matthews correlation coefficient (MCC), instead, is a more reliable statistical rate which produces a high score only if the prediction obtained good results in all of the four confusion matrix categories (true positives, false negatives, true negatives, and false positives), proportionally both to the size of positive elements and the size of negative elements in the dataset. In this article, we show how MCC produces a more informative and truthful score in evaluating binary classifications than accuracy and F1 score, by first explaining the mathematical properties, and then the asset of MCC in six synthetic use cases and in a real genomics scenario. We believe that the Matthews correlation coefficient should be preferred to accuracy and F1 score in evaluating binary classification tasks by all scientific communities.

/pdf/the-advantages-of-the-matthews-correlation-coefficient-mcc-hn3s2s0jsg.pdf

The advantages of the Matthews correlation coefficient (MCC) over F1 score and accuracy in binary classification evaluation

Artificial neural networks (ANNs) constitute a class of flexible nonlinear models designed to mimic biological neural systems. In this entry, we introduce ANN using familiar econometric terminology and provide an overview of ANN modeling approach and its implementation methods. † Correspondence: Chung-Ming Kuan, Institute of Economics, Academia Sinica, 128 Academia Road, Sec. 2, Taipei 115, Taiwan; ckuan@econ.sinica.edu.tw. †† I would like to express my sincere gratitude to the editor, Professor Steven Durlauf, for his patience and constructive comments on early drafts of this entry. I also thank Shih-Hsun Hsu and Yu-Lieh Huang for very helpful suggestions. The remaining errors are all mine.

Artificial neural networks

https://hal.archives-ouvertes.fr/hal-02395411/document

Agri-food 4.0: A survey of the supply chains and technologies for the future agriculture

The performance of the Mel-Frequency Cepstrum Coefficients (MFCC) may be affected by (1) the number of filters, (2) the shape of filters, (3) the way in which filters are spaced, and (4) the way in which the power spectrum is warped. In this paper, several comparison experiments are done to find a best implementation. The traditional MFCC calculation excludes the 0th coefficient for the reason that it is regarded as somewhat unreliable. According to the analysis and experiments, the authors find that it can be regarded as the generalized frequency band energy (FBE) and is hence useful, which results in the FBE-MFCC. The authors also propose a better analysis, namely the auto-regressive analysis, on the frame energy,which outperforms its 1st and/or 2nd order differential derivatives. Experiments with the “863”Speech Database show that, compared with the traditional MFCC with its corresponding autoregressive analysis coefficients, the FBE-MFCC and the frame energy with their corresponding auto-regressive analysis coefficients form the best combination, reducing the Chinese syllable error rate (CSER) by about 10%, while the FBE-MFCC with the corresponding auto-regressive analysis coefficients reduces CSER by 2.5%. Comparison experiments are also done with a quite casual Chinese speech database, named Chinese Annotated Spontaneous Speech (CASS)corpus. The FBE-MFCC can reduce the error rate by about 2.9% on an average.

Comparison of Different Implementations of MFCC

The impact of class imbalance in classification performance metrics based on the binary confusion matrix

Randomized methods for design of uncertain systems

In this paper, we study the sample complexity of probabilistic methods for control of uncertain systems. In particular, we show the role of the binomial distribution for some problems involving analysis and design of robust controllers with finite families. We also address the particular case in which the design problem can be formulated as an uncertain convex optimization problem. The results of the paper provide simple explicit sample bounds to guarantee that the obtained solutions meet some pre-specified probabilistic specifications.

On the sample complexity of randomized approaches to the analysis and design under uncertainty

Since their origins, human societies have integrated into the natural environment, where social metabolism that identified the interactions between society and nature was established. This social metabolism enables the flows of energy and materials between social and natural environments to be analyzed and quantified. However, in the last century, many societies have undergone a transformation from an agricultural to an industrial system. Thus, labour, as a generator of economic capital through the supply chain, has provoked a loss of natural and social capital, especially in emerging economies, thereby generating the metabolic rift. This situation can be mitigated and reversed through a circular economy, the use of digital and technological enablers of Industry 4.0 and the incorporation of an organizational enabler such as the holonic paradigm. The integration of these enablers has given rise to the development of the cyber-physical holon, which incorporates inherently sustainable concepts and allows the analysis of distributed complex systems. This paper proposes a holonic framework for multiscale and multilevel Adaptive and Integrated Sustainable Supply Chain Management (AISSCM). This framework supports a smart connected social metabolism integrated within the natural environment and oriented towards mitigation and reversal of the metabolic rift, through the processes of adaptation and integration to enable the co-evolution of the supply chain within the environment. The framework developed is applied to a family of products through their sustainable supply chain based on circularity. This proposal is developed to enable the necessary transition towards sustainable societies.

Amalia Luque

Papers

The impact of class imbalance in classification performance metrics based on the binary confusion matrix

Randomized methods for design of uncertain systems

On the sample complexity of randomized approaches to the analysis and design under uncertainty

A holonic framework for managing the sustainable supply chain in emerging economies with smart connected metabolism

State of the Industry 4.0 in the Andalusian food sector