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

Background 
Automatic detection or classification of adventitious sounds is useful to assist physicians in diagnosing or monitoring diseases such as asthma, Chronic Obstructive Pulmonary Disease (COPD), and pneumonia While computerised respiratory sound analysis, specifically for the detection or classification of adventitious sounds, has recently been the focus of an increasing number of studies, a standardised approach and comparison has not been well established


Objective 
To provide a review of existing algorithms for the detection or classification of adventitious respiratory sounds This systematic review provides a complete summary of methods used in the literature to give a baseline for future works


Data sources 
A systematic review of English articles published between 1938 and 2016, searched using the Scopus (1938-2016) and IEEExplore (1984-2016) databases Additional articles were further obtained by references listed in the articles found Search terms included adventitious sound detection, adventitious sound classification, abnormal respiratory sound detection, abnormal respiratory sound classification, wheeze detection, wheeze classification, crackle detection, crackle classification, rhonchi detection, rhonchi classification, stridor detection, stridor classification, pleural rub detection, pleural rub classification, squawk detection, and squawk classification


Study selection 
Only articles were included that focused on adventitious sound detection or classification, based on respiratory sounds, with performance reported and sufficient information provided to be approximately repeated


Data extraction 
Investigators extracted data about the adventitious sound type analysed, approach and level of analysis, instrumentation or data source, location of sensor, amount of data obtained, data management, features, methods, and performance achieved


Data synthesis 
A total of 77 reports from the literature were included in this review 55 (7143%) of the studies focused on wheeze, 40 (5195%) on crackle, 9 (1169%) on stridor, 9 (1169%) on rhonchi, and 18 (2338%) on other sounds such as pleural rub, squawk, as well as the pathology Instrumentation used to collect data included microphones, stethoscopes, and accelerometers Several references obtained data from online repositories or book audio CD companions Detection or classification methods used varied from empirically determined thresholds to more complex machine learning techniques Performance reported in the surveyed works were converted to accuracy measures for data synthesis


Limitations 
Direct comparison of the performance of surveyed works cannot be performed as the input data used by each was different A standard validation method has not been established, resulting in different works using different methods and performance measure definitions


Conclusion 
A review of the literature was performed to summarise different analysis approaches, features, and methods used for the analysis The performance of recent studies showed a high agreement with conventional non-automatic identification This suggests that automated adventitious sound detection or classification is a promising solution to overcome the limitations of conventional auscultation and to assist in the monitoring of relevant diseases

/pdf/automatic-adventitious-respiratory-sound-analysis-a-3ikbv4aywn.pdf

Automatic adventitious respiratory sound analysis: A systematic review.

Optimum Gabor filter design and local binary patterns for texture segmentation

Machine learning in lung sound analysis: a systematic review

Probabilistic topic modeling of text collections has been recently developed mainly within the framework of graphical models and Bayesian inference. In this paper we introduce an alternative semi-probabilistic approach, which we call additive regularization of topic models (ARTM). Instead of building a purely probabilistic generative model of text we regularize an ill-posed problem of stochastic matrix factorization by maximizing a weighted sum of the log-likelihood and additional criteria. This approach enables us to combine probabilistic assumptions with linguistic and problem-specific requirements in a single multi-objective topic model. In the theoretical part of the work we derive the regularized EM-algorithm and provide a pool of regularizers, which can be applied together in any combination. We show that many models previously developed within Bayesian framework can be inferred easier within ARTM and in some cases generalized. In the experimental part we show that a combination of sparsing, smoothing, and decorrelation improves several quality measures at once with almost no loss of the likelihood.

/pdf/additive-regularization-of-topic-models-3rpwet24sa.pdf

Additive regularization of topic models

In this paper, we compare latent Dirichlet allocation (LDA) with probabilistic latent semantic indexing (pLSI) as a dimensionality reduction method and investigate their effectiveness in document clustering by using real-world document sets. For clustering of documents, we use a method based on multinomial mixture, which is known as an efficient framework for text mining. Clustering results are evaluated by F-measure, i.e., harmonic mean of precision and recall. We use Japanese and Korean Web articles for evaluation and regard the category assigned to each Web article as the ground truth for the evaluation of clustering results. Our experiment shows that the dimensionality reduction via LDA and pLSI results in document clusters of almost the same quality as those obtained by using original feature vectors. Therefore, we can reduce the vector dimension without degrading cluster quality. Further, both LDA and pLSI are more effective than random projection, the baseline method in our experiment. However, our experiment provides no meaningful difference between LDA and pLSI. This result suggests that LDA does not replace pLSI at least for dimensionality reduction in document clustering.

Comparing LDA with pLSI as a dimensionality reduction method in document clustering

The typical nonparametric method of pattern recognition "k-nearest neighbor rule (kNN)" is carried out by counting the labels of k-nearest training samples to a test sample. This method collects the k-nearest neighbors without taking into account a class, and it outputs the class of the test sample by using only the labels of neighborhoods. This work presents a classifier that outputs the class of a test sample by measuring the distance between the test sample and the average patterns, which are calculated using the k-nearest neighbors belonging to individual classes. A kernel method can be applied to this classifier for improving recognition rates. The performance of the proposed method is verified by experiments with benchmark data sets.

Pattern recognition using average patterns of categorical k-nearest neighbors

In this paper, we propose a method for image clustering using multinomial mixture models. The mixture of multinomial distributions, often called multinomial mixture, is a probabilistic model mainly used for text mining. The effectiveness of multinomial distribution for text mining originates from the fact that words can be regarded as independently generated in the first approximation. In this paper, we apply multinomial distribution to image clustering. We regard each color as a "word" and color histograms as "term frequency" distributions. Recent work provides an evidence that color histograms are quite non-Gaussian. Therefore, we assume that there are no intrinsic dependencies between the frequencies of similar colors and adopt multinomial model. We can append other information, e.g. spatial information, because our model assumes no intrinsic dependencies among image features. Our experiment has compared multinomial mixture, Dirichlet mixture and k-means. Dirichlet mixture, a Bayesian version of multinomial mixture, is applied to image clustering for the first time as far as we know. The results of our evaluation experiment demonstrate that multinomial mixture gives higher accuracies than k-means. Further, Dirichlet mixture provides a result comparable to the best result of multinomial mixture.

Clustering Images with Multinomial Mixture Models

In this paper, we propose a method for composing templates of lung sound classification. First, we obtain a sequence of power spectra by FFT for each given lung sound and compute a small number of component spectra by ICA for each of the overlapping sets of tens of consecutive power spectra. Second, we put component spectra obtained from various lung sounds into a single set and conduct clustering a large number of times. When component spectra belong to the same cluster in all clustering results, these spectra show robust similarity. Therefore, we can use such spectra to compose a template of lung sound classification.

/pdf/unmixed-spectrum-clustering-for-template-composition-in-lung-om75d0jq9h.pdf

Unmixed spectrum clustering for template composition in lung sound classification

Toward assistance of respiratory system diagnosis, sparse representation of auscultation signals is utilized to extract pulmonary sound components. This signal extraction is a challenging task because the pulmonary sounds such as vesicular sounds and crackles are overlapping each other in the time and frequency domains, and they are so faint that the quality of recorded signals is quite low in many cases. It is experimentally shown that the pulmonary sound components are successfully extracted from low-quality auscultation signals via the sparse representation. This extraction method is confirmed to be highly robust against random noise and digital quantization.

Senya Kiyasu

Papers

Comparing LDA with pLSI as a dimensionality reduction method in document clustering

Pattern recognition using average patterns of categorical k-nearest neighbors

Clustering Images with Multinomial Mixture Models

Unmixed spectrum clustering for template composition in lung sound classification

Sparse representation-based extraction of pulmonary sound components from low-quality auscultation signals