Detecting paroxysmal coughing from pertussis cases using voice recognition technology.
Ontology highlight
ABSTRACT: Background
Pertussis is highly contagious; thus, prompt identification of cases is essential to control outbreaks. Clinicians experienced with the disease can easily identify classic cases, where patients have bursts of rapid coughing followed by gasps, and a characteristic whooping sound. However, many clinicians have never seen a case, and thus may miss initial cases during an outbreak. The purpose of this project was to use voice-recognition software to distinguish pertussis coughs from croup and other coughs.Methods
We collected a series of recordings representing pertussis, croup and miscellaneous coughing by children. We manually categorized coughs as either pertussis or non-pertussis, and extracted features for each category. We used Mel-frequency cepstral coefficients (MFCC), a sampling rate of 16 KHz, a frame Duration of 25 msec, and a frame rate of 10 msec. The coughs were filtered. Each cough was divided into 3 sections of proportion 3-4-3. The average of the 13 MFCCs for each section was computed and made into a 39-element feature vector used for the classification. We used the following machine learning algorithms: Neural Networks, K-Nearest Neighbor (KNN), and a 200 tree Random Forest (RF). Data were reserved for cross-validation of the KNN and RF. The Neural Network was trained 100 times, and the averaged results are presented.Results
After categorization, we had 16 examples of non-pertussis coughs and 31 examples of pertussis coughs. Over 90% of all pertussis coughs were properly classified as pertussis. The error rates were: Type I errors of 7%, 12%, and 25% and Type II errors of 8%, 0%, and 0%, using the Neural Network, Random Forest, and KNN, respectively.Conclusion
Our results suggest that we can build a robust classifier to assist clinicians and the public to help identify pertussis cases in children presenting with typical symptoms.
SUBMITTER: Parker D
PROVIDER: S-EPMC3876998 | biostudies-literature |
REPOSITORIES: biostudies-literature
Similar Datasets
Project description:Long-term social recognition is vital for species with complex social networks, where familiar individuals can encounter one another after long periods of separation. For non-human primates who live in dense forest environments, visual access to one another is often limited, and recognition of social partners over distances largely depends on vocal communication. Vocal recognition after years of separation has never been reported in any great ape species, despite their complex societies and advanced social intelligence. Here we show that bonobos, Pan paniscus, demonstrate reliable vocal recognition of social partners, even if they have been separated for five years. We experimentally tested bonobos' responses to the calls of previous group members that had been transferred between captive groups. Despite long separations, subjects responded more intensely to familiar voices than to calls from unknown individuals - the first experimental evidence that bonobos can identify individuals utilising vocalisations even years after their last encounter. Our study also suggests that bonobos may cease to discriminate between familiar and unfamiliar individuals after a period of eight years, indicating that voice representations or interest could be limited in time in this species.
| S-EPMC4766561 | biostudies-literature
Project description:BackgroundAlternative methods could be used to enhance the monitoring and forecasting of re-emerging conditions such as pertussis. Here, whether data on the volume of Internet searching on pertussis could complement traditional modeling based solely on reported case numbers was assessed.MethodsSARIMA models were fitted to describe reported weekly pertussis case numbers over a four-year period in Germany. Pertussis-related Google Trends data (GTD) was added as an external regressor. Predictions were made by the models, both with and without GTD, and compared with values within the validation dataset over a one-year and for a two-weeks period.ResultsPredictions of the traditional model using solely reported case numbers resulted in an RMSE (residual mean squared error) of 192.65 and 207.8, a mean absolute percentage error (MAPE) of 58.59 and 72.1, and a mean absolute error (MAE) 169.53 and 190.53 for the one-year and for the two-weeks period, respectively. The GTD expanded model achieved better forecasting accuracy (RMSE: 144.22 and 201.78), a MAPE 43.86, and 68.54 and a MAE of 124.46 and 178.96. Corrected Akaike Information Criteria also favored the GTD expanded model (1750.98 vs. 1746.73). The difference between the predictive performances was significant when using a two-sided Diebold-Mariano test (DM value: 6.86, p < 0.001) for the one-year period.ConclusionInternet-based surveillance data enhanced the predictive ability of a traditionally based model and should be considered as a method to enhance future disease modeling.
| S-EPMC8605298 | biostudies-literature
Project description:Despite the advances in the diagnosis and treatment of heart failure (HF), the current hospital-oriented framework for HF management does not appear to be sufficient to maintain the stability of HF patients in the long term. The importance of self-care management is increasingly being emphasized as a promising long-term treatment strategy for patients with chronic HF.The objective of this study was to evaluate whether a new information communication technology (ICT)-based telehealth program with voice recognition technology could improve clinical or laboratory outcomes in HF patients.In this prospective single-arm pilot study, we recruited 31 consecutive patients with chronic HF who were referred to our institute. An ICT-based telehealth program with voice recognition technology was developed and used by patients with HF for 12 weeks. Patients were educated on the use of this program via mobile phone, landline, or the Internet for the purpose of improving communication and data collection. Using these systems, we collected comprehensive data elements related to the risk of HF self-care management such as weight, diet, exercise, medication adherence, overall symptom change, and home blood pressure. The study endpoints were the changes observed in urine sodium concentration (uNa), Minnesota Living with Heart Failure (MLHFQ) scores, 6-min walk test, and N-terminal prohormone of brain natriuretic peptide (NT-proBNP) as surrogate markers for appropriate HF management.Among the 31 enrolled patients, 27 (87%) patients completed the study, and 10 (10/27, 37%) showed good adherence to ICT-based telehealth program with voice recognition technology, which was defined as the use of the program for 100 times or more during the study period. Nearly three-fourths of the patients had been hospitalized at least once because of HF before the enrollment (20/27, 74%); 14 patients had 1, 2 patients had 2, and 4 patients had 3 or more previous HF hospitalizations. In the total study population, there was no significant interval change in laboratory and functional outcome variables after 12 weeks of ICT-based telehealth program. In patients with good adherence to ICT-based telehealth program, there was a significant improvement in the mean uNa (103.1 to 78.1; P=.01) but not in those without (85.4 to 96.9; P=.49). Similarly, a marginal improvement in MLHFQ scores was only observed in patients with good adherence (27.5 to 21.4; P=.08) but not in their counterparts (19.0 to 19.7; P=.73). The mean 6-min walk distance and NT-proBNP were not significantly increased in patients regardless of their adherence.Short-term application of ICT-based telehealth program with voice recognition technology showed the potential to improve uNa values and MLHFQ scores in HF patients, suggesting that better control of sodium intake and greater quality of life can be achieved by this program.
| S-EPMC5643844 | biostudies-other
Project description:Right or bilateral anterior temporal damage can impair face recognition, but whether this is an associative variant of prosopagnosia or part of a multimodal disorder of person recognition is an unsettled question, with implications for cognitive and neuroanatomic models of person recognition. We assessed voice perception and short-term recognition of recently heard voices in 10 subjects with impaired face recognition acquired after cerebral lesions. All 4 subjects with apperceptive prosopagnosia due to lesions limited to fusiform cortex had intact voice discrimination and recognition. One subject with bilateral fusiform and anterior temporal lesions had a combined apperceptive prosopagnosia and apperceptive phonagnosia, the first such described case. Deficits indicating a multimodal syndrome of person recognition were found only in 2 subjects with bilateral anterior temporal lesions. All 3 subjects with right anterior temporal lesions had normal voice perception and recognition, 2 of whom performed normally on perceptual discrimination of faces. This confirms that such lesions can cause a modality-specific associative prosopagnosia.
| S-EPMC4785942 | biostudies-literature
Project description:Natural objects provide partially redundant information to the brain through different sensory modalities. For example, voices and faces both give information about the speech content, age, and gender of a person. Thanks to this redundancy, multimodal recognition is fast, robust, and automatic. In unimodal perception, however, only part of the information about an object is available. Here, we addressed whether, even under conditions of unimodal sensory input, crossmodal neural circuits that have been shaped by previous associative learning become activated and underpin a performance benefit. We measured brain activity with functional magnetic resonance imaging before, while, and after participants learned to associate either sensory redundant stimuli, i.e. voices and faces, or arbitrary multimodal combinations, i.e. voices and written names, ring tones, and cell phones or brand names of these cell phones. After learning, participants were better at recognizing unimodal auditory voices that had been paired with faces than those paired with written names, and association of voices with faces resulted in an increased functional coupling between voice and face areas. No such effects were observed for ring tones that had been paired with cell phones or names. These findings demonstrate that brief exposure to ecologically valid and sensory redundant stimulus pairs, such as voices and faces, induces specific multisensory associations. Consistent with predictive coding theories, associative representations become thereafter available for unimodal perception and facilitate object recognition. These data suggest that for natural objects effective predictive signals can be generated across sensory systems and proceed by optimization of functional connectivity between specialized cortical sensory modules.
| S-EPMC1570760 | biostudies-literature
Project description:Common leaf spot (caused by Pseudopeziza medicaginis), rust (caused by Uromyces striatus), Leptosphaerulina leaf spot (caused by Leptosphaerulina briosiana) and Cercospora leaf spot (caused by Cercospora medicaginis) are the four common types of alfalfa leaf diseases. Timely and accurate diagnoses of these diseases are critical for disease management, alfalfa quality control and the healthy development of the alfalfa industry. In this study, the identification and diagnosis of the four types of alfalfa leaf diseases were investigated using pattern recognition algorithms based on image-processing technology. A sub-image with one or multiple typical lesions was obtained by artificial cutting from each acquired digital disease image. Then the sub-images were segmented using twelve lesion segmentation methods integrated with clustering algorithms (including K_means clustering, fuzzy C-means clustering and K_median clustering) and supervised classification algorithms (including logistic regression analysis, Naive Bayes algorithm, classification and regression tree, and linear discriminant analysis). After a comprehensive comparison, the segmentation method integrating the K_median clustering algorithm and linear discriminant analysis was chosen to obtain lesion images. After the lesion segmentation using this method, a total of 129 texture, color and shape features were extracted from the lesion images. Based on the features selected using three methods (ReliefF, 1R and correlation-based feature selection), disease recognition models were built using three supervised learning methods, including the random forest, support vector machine (SVM) and K-nearest neighbor methods. A comparison of the recognition results of the models was conducted. The results showed that when the ReliefF method was used for feature selection, the SVM model built with the most important 45 features (selected from a total of 129 features) was the optimal model. For this SVM model, the recognition accuracies of the training set and the testing set were 97.64% and 94.74%, respectively. Semi-supervised models for disease recognition were built based on the 45 effective features that were used for building the optimal SVM model. For the optimal semi-supervised models built with three ratios of labeled to unlabeled samples in the training set, the recognition accuracies of the training set and the testing set were both approximately 80%. The results indicated that image recognition of the four alfalfa leaf diseases can be implemented with high accuracy. This study provides a feasible solution for lesion image segmentation and image recognition of alfalfa leaf disease.
| S-EPMC5158033 | biostudies-literature
Project description:The ability to recognize people by their voice is an important social behavior. Individuals differ in how they pronounce words, and listeners may take advantage of language-specific knowledge of speech phonology to facilitate recognizing voices. Impaired phonological processing is characteristic of dyslexia and thought to be a basis for difficulty in learning to read. We tested voice-recognition abilities of dyslexic and control listeners for voices speaking listeners' native language or an unfamiliar language. Individuals with dyslexia exhibited impaired voice-recognition abilities compared with controls only for voices speaking their native language. These results demonstrate the importance of linguistic representations for voice recognition. Humans appear to identify voices by making comparisons between talkers' pronunciations of words and listeners' stored abstract representations of the sounds in those words.
| S-EPMC4242590 | biostudies-literature
Project description:The ability to recognise the identity of others is a key requirement for successful communication. Brain regions that respond selectively to voices exist in humans from early infancy on. Currently, it is unclear whether dysfunction of these voice-sensitive regions can explain voice identity recognition impairments. Here, we used two independent functional magnetic resonance imaging studies to investigate voice processing in a population that has been reported to have no voice-sensitive regions: autism spectrum disorder (ASD). Our results refute the earlier report that individuals with ASD have no responses in voice-sensitive regions: Passive listening to vocal, compared to non-vocal, sounds elicited typical responses in voice-sensitive regions in the high-functioning ASD group and controls. In contrast, the ASD group had a dysfunction in voice-sensitive regions during voice identity but not speech recognition in the right posterior superior temporal sulcus/gyrus (STS/STG)-a region implicated in processing complex spectrotemporal voice features and unfamiliar voices. The right anterior STS/STG correlated with voice identity recognition performance in controls but not in the ASD group. The findings suggest that right STS/STG dysfunction is critical for explaining voice recognition impairments in high-functioning ASD and show that ASD is not characterised by a general lack of voice-sensitive responses.
| S-EPMC5091681 | biostudies-literature
Project description:The way we process language is influenced by our experience. We are more likely to attend to features that proved to be useful in the past. Importantly, the size of individuals' social network can influence their experience, and consequently, how they process language. In the case of voice recognition, having a larger social network might provide more variable input and thus enhance the ability to recognise new voices. On the other hand, learning to recognise voices is more demanding and less beneficial for people with a larger social network as they have more speakers to learn yet spend less time with each. This paper tests whether social network size influences voice recognition, and if so, in which direction. Native Dutch speakers listed their social network and performed a voice recognition task. Results showed that people with larger social networks were poorer at learning to recognise voices. Experiment 2 replicated the results with a British sample and English stimuli. Experiment 3 showed that the effect does not generalise to voice recognition in an unfamiliar language suggesting that social network size influences attention to the linguistic rather than non-linguistic markers that differentiate speakers. The studies thus show that our social network size influences our inclination to learn speaker-specific patterns in our environment, and consequently, the development of skills that rely on such learned patterns, such as voice recognition.
| S-EPMC8793288 | biostudies-literature
Project description:PRML, a novel candlestick pattern recognition model using machine learning methods, is proposed to improve stock trading decisions. Four popular machine learning methods and 11 different features types are applied to all possible combinations of daily patterns to start the pattern recognition schedule. Different time windows from one to ten days are used to detect the prediction effect at different periods. An investment strategy is constructed according to the identified candlestick patterns and suitable time window. We deploy PRML for the forecast of all Chinese market stocks from Jan 1, 2000 until Oct 30, 2020. Among them, the data from Jan 1, 2000 to Dec 31, 2014 is used as the training data set, and the data set from Jan 1, 2015 to Oct 30, 2020 is used to verify the forecasting effect. Empirical results show that the two-day candlestick patterns after filtering have the best prediction effect when forecasting one day ahead; these patterns obtain an average annual return, an annual Sharpe ratio, and an information ratio as high as 36.73%, 0.81, and 2.37, respectively. After screening, three-day candlestick patterns also present a beneficial effect when forecasting one day ahead in that these patterns show stable characteristics. Two other popular machine learning methods, multilayer perceptron network and long short-term memory neural networks, are applied to the pattern recognition framework to evaluate the dependency of the prediction model. A transaction cost of 0.2% is considered on the two-day patterns predicting one day ahead, thus confirming the profitability. Empirical results show that applying different machine learning methods to two-day and three-day patterns for one-day-ahead forecasts can be profitable.
| S-EPMC8345893 | biostudies-literature